| 190 5 4 119 85 79 185 172 169 134 131 311 127 185 13 13 244 247 245 124 123 38 40 39 17 24 40 40 3 157 3 154 28 563 4 131 131 98 84 84 131 9 131 43 35 153 10 15 129 21 1 29 12 12 12 11 9 3 9 3 8 4 11 11 10 8 2 4 9 9 5 2 12 10 12 2 43 39 14 11 8 17 12 23 35 46 47 22 10 10 14 47 33 33 15 15 15 8 129 131 19 30 131 1 4 32 110 160 23 63 12 12 3 311 58 69 28 133 134 1 1 48 4 7 11 34 30 28 34 127 132 23 131 37 29 105 11 132 134 132 11 131 1 34 30 34 1 3 27 38 7 30 30 6 11 9 5 9 23 4 25 5 17 3 9 1 3 5 4 1 13 1 33 33 1 4 8 4 8 618 618 2 345 345 19 19 15 1 17 6 13 10 13 19 16 14 4 1 25 118 376 376 61 52 376 376 11 1 376 14 595 598 344 345 248 102 123 1 345 346 123 560 235 327 562 563 559 26 9 562 346 345 129 561 4 519 2 22 62 87 2 112 166 33 133 166 166 14 28 28 40 2 15 15 15 35 29 34 1 2 3 3 3 3 3 124 45 123 53 35 5 30 22 100 92 1 124 123 34 93 25 50 4 1 5 5 5 5 4 1 1 5 5 5 5 5 5 5 5 389 273 130 2 1 129 2 125 125 31 117 7 5 5 71 1 71 316 251 5 67 1 1 71 71 2 65 2171 2171 1737 79 23 2 26 26 4 30 2122 318 2 2 71 64 11 41 41 2 39 2091 5 2073 2063 122 164 283 443 2061 65 1988 56 8 6 2 7 13 182 168 11 20 163 153 239 15 44 485 195 290 176 20 315 20 216 219 219 216 219 114 3 2 216 219 199 26 1 1 26 25 26 26 25 1 7 2 20 20 20 2 8 8 3 3 3 5 5 5 3 2 2 2 2 2 2 2 2 3 3 3 3 156 22 21 21 21 21 21 156 156 156 21 134 134 17 17 1 2 3 30 8 13 23 14 4 30 10 28 10 7 24 52 5 49 16 2 4 2 9 2 52 52 1 44 8 16 16 30 30 30 17 17 16 16 16 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * xfrm_policy.c * * Changes: * Mitsuru KANDA @USAGI * Kazunori MIYAZAWA @USAGI * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * IPv6 support * Kazunori MIYAZAWA @USAGI * YOSHIFUJI Hideaki * Split up af-specific portion * Derek Atkins <derek@ihtfp.com> Add the post_input processor * */ #include <linux/err.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/workqueue.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/module.h> #include <linux/cache.h> #include <linux/cpu.h> #include <linux/audit.h> #include <linux/rhashtable.h> #include <linux/if_tunnel.h> #include <linux/icmp.h> #include <net/dst.h> #include <net/flow.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/gre.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #ifdef CONFIG_XFRM_STATISTICS #include <net/snmp.h> #endif #ifdef CONFIG_XFRM_ESPINTCP #include <net/espintcp.h> #endif #include <net/inet_dscp.h> #include "xfrm_hash.h" #define XFRM_QUEUE_TMO_MIN ((unsigned)(HZ/10)) #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ)) #define XFRM_MAX_QUEUE_LEN 100 struct xfrm_flo { struct dst_entry *dst_orig; u8 flags; }; /* prefixes smaller than this are stored in lists, not trees. */ #define INEXACT_PREFIXLEN_IPV4 16 #define INEXACT_PREFIXLEN_IPV6 48 struct xfrm_pol_inexact_node { struct rb_node node; union { xfrm_address_t addr; struct rcu_head rcu; }; u8 prefixlen; struct rb_root root; /* the policies matching this node, can be empty list */ struct hlist_head hhead; }; /* xfrm inexact policy search tree: * xfrm_pol_inexact_bin = hash(dir,type,family,if_id); * | * +---- root_d: sorted by daddr:prefix * | | * | xfrm_pol_inexact_node * | | * | +- root: sorted by saddr/prefix * | | | * | | xfrm_pol_inexact_node * | | | * | | + root: unused * | | | * | | + hhead: saddr:daddr policies * | | * | +- coarse policies and all any:daddr policies * | * +---- root_s: sorted by saddr:prefix * | | * | xfrm_pol_inexact_node * | | * | + root: unused * | | * | + hhead: saddr:any policies * | * +---- coarse policies and all any:any policies * * Lookups return four candidate lists: * 1. any:any list from top-level xfrm_pol_inexact_bin * 2. any:daddr list from daddr tree * 3. saddr:daddr list from 2nd level daddr tree * 4. saddr:any list from saddr tree * * This result set then needs to be searched for the policy with * the lowest priority. If two candidates have the same priority, the * struct xfrm_policy pos member with the lower number is used. * * This replicates previous single-list-search algorithm which would * return first matching policy in the (ordered-by-priority) list. */ struct xfrm_pol_inexact_key { possible_net_t net; u32 if_id; u16 family; u8 dir, type; }; struct xfrm_pol_inexact_bin { struct xfrm_pol_inexact_key k; struct rhash_head head; /* list containing '*:*' policies */ struct hlist_head hhead; seqcount_spinlock_t count; /* tree sorted by daddr/prefix */ struct rb_root root_d; /* tree sorted by saddr/prefix */ struct rb_root root_s; /* slow path below */ struct list_head inexact_bins; struct rcu_head rcu; }; enum xfrm_pol_inexact_candidate_type { XFRM_POL_CAND_BOTH, XFRM_POL_CAND_SADDR, XFRM_POL_CAND_DADDR, XFRM_POL_CAND_ANY, XFRM_POL_CAND_MAX, }; struct xfrm_pol_inexact_candidates { struct hlist_head *res[XFRM_POL_CAND_MAX]; }; struct xfrm_flow_keys { struct flow_dissector_key_basic basic; struct flow_dissector_key_control control; union { struct flow_dissector_key_ipv4_addrs ipv4; struct flow_dissector_key_ipv6_addrs ipv6; } addrs; struct flow_dissector_key_ip ip; struct flow_dissector_key_icmp icmp; struct flow_dissector_key_ports ports; struct flow_dissector_key_keyid gre; }; static struct flow_dissector xfrm_session_dissector __ro_after_init; static DEFINE_SPINLOCK(xfrm_if_cb_lock); static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly; static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1] __read_mostly; static struct kmem_cache *xfrm_dst_cache __ro_after_init; static struct rhashtable xfrm_policy_inexact_table; static const struct rhashtable_params xfrm_pol_inexact_params; static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr); static int stale_bundle(struct dst_entry *dst); static int xfrm_bundle_ok(struct xfrm_dst *xdst); static void xfrm_policy_queue_process(struct timer_list *t); static void __xfrm_policy_link(struct xfrm_policy *pol, int dir); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir); static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir, u32 if_id); static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir, u32 if_id); static struct xfrm_policy * xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy, bool excl); static bool xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand, struct xfrm_pol_inexact_bin *b, const xfrm_address_t *saddr, const xfrm_address_t *daddr); static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy) { return refcount_inc_not_zero(&policy->refcnt); } static inline bool __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi4 *fl4 = &fl->u.ip4; return addr4_match(fl4->daddr, sel->daddr.a4, sel->prefixlen_d) && addr4_match(fl4->saddr, sel->saddr.a4, sel->prefixlen_s) && !((xfrm_flowi_dport(fl, &fl4->uli) ^ sel->dport) & sel->dport_mask) && !((xfrm_flowi_sport(fl, &fl4->uli) ^ sel->sport) & sel->sport_mask) && (fl4->flowi4_proto == sel->proto || !sel->proto) && (fl4->flowi4_oif == sel->ifindex || !sel->ifindex); } static inline bool __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi6 *fl6 = &fl->u.ip6; return addr_match(&fl6->daddr, &sel->daddr, sel->prefixlen_d) && addr_match(&fl6->saddr, &sel->saddr, sel->prefixlen_s) && !((xfrm_flowi_dport(fl, &fl6->uli) ^ sel->dport) & sel->dport_mask) && !((xfrm_flowi_sport(fl, &fl6->uli) ^ sel->sport) & sel->sport_mask) && (fl6->flowi6_proto == sel->proto || !sel->proto) && (fl6->flowi6_oif == sel->ifindex || !sel->ifindex); } bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl, unsigned short family) { if (family != sel->family && sel->family != AF_UNSPEC) return false; switch (family) { case AF_INET: return __xfrm4_selector_match(sel, fl); case AF_INET6: return __xfrm6_selector_match(sel, fl); } return false; } static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family) { const struct xfrm_policy_afinfo *afinfo; if (unlikely(family >= ARRAY_SIZE(xfrm_policy_afinfo))) return NULL; rcu_read_lock(); afinfo = rcu_dereference(xfrm_policy_afinfo[family]); if (unlikely(!afinfo)) rcu_read_unlock(); return afinfo; } /* Called with rcu_read_lock(). */ static const struct xfrm_if_cb *xfrm_if_get_cb(void) { return rcu_dereference(xfrm_if_cb); } struct dst_entry *__xfrm_dst_lookup(int family, const struct xfrm_dst_lookup_params *params) { const struct xfrm_policy_afinfo *afinfo; struct dst_entry *dst; afinfo = xfrm_policy_get_afinfo(family); if (unlikely(afinfo == NULL)) return ERR_PTR(-EAFNOSUPPORT); dst = afinfo->dst_lookup(params); rcu_read_unlock(); return dst; } EXPORT_SYMBOL(__xfrm_dst_lookup); static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, dscp_t dscp, int oif, xfrm_address_t *prev_saddr, xfrm_address_t *prev_daddr, int family, u32 mark) { struct xfrm_dst_lookup_params params; struct net *net = xs_net(x); xfrm_address_t *saddr = &x->props.saddr; xfrm_address_t *daddr = &x->id.daddr; struct dst_entry *dst; if (x->type->flags & XFRM_TYPE_LOCAL_COADDR) { saddr = x->coaddr; daddr = prev_daddr; } if (x->type->flags & XFRM_TYPE_REMOTE_COADDR) { saddr = prev_saddr; daddr = x->coaddr; } params.net = net; params.saddr = saddr; params.daddr = daddr; params.dscp = dscp; params.oif = oif; params.mark = mark; params.ipproto = x->id.proto; if (x->encap) { switch (x->encap->encap_type) { case UDP_ENCAP_ESPINUDP: params.ipproto = IPPROTO_UDP; params.uli.ports.sport = x->encap->encap_sport; params.uli.ports.dport = x->encap->encap_dport; break; case TCP_ENCAP_ESPINTCP: params.ipproto = IPPROTO_TCP; params.uli.ports.sport = x->encap->encap_sport; params.uli.ports.dport = x->encap->encap_dport; break; } } dst = __xfrm_dst_lookup(family, ¶ms); if (!IS_ERR(dst)) { if (prev_saddr != saddr) memcpy(prev_saddr, saddr, sizeof(*prev_saddr)); if (prev_daddr != daddr) memcpy(prev_daddr, daddr, sizeof(*prev_daddr)); } return dst; } static inline unsigned long make_jiffies(long secs) { if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ) return MAX_SCHEDULE_TIMEOUT-1; else return secs*HZ; } static void xfrm_policy_timer(struct timer_list *t) { struct xfrm_policy *xp = timer_container_of(xp, t, timer); time64_t now = ktime_get_real_seconds(); time64_t next = TIME64_MAX; int warn = 0; int dir; read_lock(&xp->lock); if (unlikely(xp->walk.dead)) goto out; dir = xfrm_policy_id2dir(xp->index); if (xp->lft.hard_add_expires_seconds) { time64_t tmo = xp->lft.hard_add_expires_seconds + xp->curlft.add_time - now; if (tmo <= 0) goto expired; if (tmo < next) next = tmo; } if (xp->lft.hard_use_expires_seconds) { time64_t tmo = xp->lft.hard_use_expires_seconds + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) goto expired; if (tmo < next) next = tmo; } if (xp->lft.soft_add_expires_seconds) { time64_t tmo = xp->lft.soft_add_expires_seconds + xp->curlft.add_time - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; } if (tmo < next) next = tmo; } if (xp->lft.soft_use_expires_seconds) { time64_t tmo = xp->lft.soft_use_expires_seconds + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; } if (tmo < next) next = tmo; } if (warn) km_policy_expired(xp, dir, 0, 0); if (next != TIME64_MAX && !mod_timer(&xp->timer, jiffies + make_jiffies(next))) xfrm_pol_hold(xp); out: read_unlock(&xp->lock); xfrm_pol_put(xp); return; expired: read_unlock(&xp->lock); if (!xfrm_policy_delete(xp, dir)) km_policy_expired(xp, dir, 1, 0); xfrm_pol_put(xp); } /* Allocate xfrm_policy. Not used here, it is supposed to be used by pfkeyv2 * SPD calls. */ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) { struct xfrm_policy *policy; policy = kzalloc_obj(struct xfrm_policy, gfp); if (policy) { write_pnet(&policy->xp_net, net); INIT_LIST_HEAD(&policy->walk.all); INIT_HLIST_HEAD(&policy->state_cache_list); INIT_HLIST_NODE(&policy->bydst); INIT_HLIST_NODE(&policy->byidx); rwlock_init(&policy->lock); refcount_set(&policy->refcnt, 1); skb_queue_head_init(&policy->polq.hold_queue); timer_setup(&policy->timer, xfrm_policy_timer, 0); timer_setup(&policy->polq.hold_timer, xfrm_policy_queue_process, 0); } return policy; } EXPORT_SYMBOL(xfrm_policy_alloc); static void xfrm_policy_destroy_rcu(struct rcu_head *head) { struct xfrm_policy *policy = container_of(head, struct xfrm_policy, rcu); security_xfrm_policy_free(policy->security); kfree(policy); } /* Destroy xfrm_policy: descendant resources must be released to this moment. */ void xfrm_policy_destroy(struct xfrm_policy *policy) { BUG_ON(!policy->walk.dead); if (timer_delete(&policy->timer) || timer_delete(&policy->polq.hold_timer)) BUG(); xfrm_dev_policy_free(policy); call_rcu(&policy->rcu, xfrm_policy_destroy_rcu); } EXPORT_SYMBOL(xfrm_policy_destroy); /* Rule must be locked. Release descendant resources, announce * entry dead. The rule must be unlinked from lists to the moment. */ static void xfrm_policy_kill(struct xfrm_policy *policy) { struct net *net = xp_net(policy); struct xfrm_state *x; xfrm_dev_policy_delete(policy); write_lock_bh(&policy->lock); policy->walk.dead = 1; write_unlock_bh(&policy->lock); atomic_inc(&policy->genid); if (timer_delete(&policy->polq.hold_timer)) xfrm_pol_put(policy); skb_queue_purge(&policy->polq.hold_queue); if (timer_delete(&policy->timer)) xfrm_pol_put(policy); /* XXX: Flush state cache */ spin_lock_bh(&net->xfrm.xfrm_state_lock); hlist_for_each_entry_rcu(x, &policy->state_cache_list, state_cache) { hlist_del_init_rcu(&x->state_cache); } spin_unlock_bh(&net->xfrm.xfrm_state_lock); xfrm_pol_put(policy); } static unsigned int xfrm_policy_hashmax __read_mostly = 1 * 1024 * 1024; static inline unsigned int idx_hash(struct net *net, u32 index) { return __idx_hash(index, net->xfrm.policy_idx_hmask); } /* calculate policy hash thresholds */ static void __get_hash_thresh(struct net *net, unsigned short family, int dir, u8 *dbits, u8 *sbits) { switch (family) { case AF_INET: *dbits = net->xfrm.policy_bydst[dir].dbits4; *sbits = net->xfrm.policy_bydst[dir].sbits4; break; case AF_INET6: *dbits = net->xfrm.policy_bydst[dir].dbits6; *sbits = net->xfrm.policy_bydst[dir].sbits6; break; default: *dbits = 0; *sbits = 0; } } static struct hlist_head *policy_hash_bysel(struct net *net, const struct xfrm_selector *sel, unsigned short family, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash; u8 dbits; u8 sbits; __get_hash_thresh(net, family, dir, &dbits, &sbits); hash = __sel_hash(sel, family, hmask, dbits, sbits); if (hash == hmask + 1) return NULL; return rcu_dereference_check(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash; } static struct hlist_head *policy_hash_direct(struct net *net, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash; u8 dbits; u8 sbits; __get_hash_thresh(net, family, dir, &dbits, &sbits); hash = __addr_hash(daddr, saddr, family, hmask, dbits, sbits); return rcu_dereference_check(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash; } static void xfrm_dst_hash_transfer(struct net *net, struct hlist_head *list, struct hlist_head *ndsttable, unsigned int nhashmask, int dir) { struct hlist_node *tmp, *entry0 = NULL; struct xfrm_policy *pol; unsigned int h0 = 0; u8 dbits; u8 sbits; redo: hlist_for_each_entry_safe(pol, tmp, list, bydst) { unsigned int h; __get_hash_thresh(net, pol->family, dir, &dbits, &sbits); h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr, pol->family, nhashmask, dbits, sbits); if (!entry0 || pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { hlist_del_rcu(&pol->bydst); hlist_add_head_rcu(&pol->bydst, ndsttable + h); h0 = h; } else { if (h != h0) continue; hlist_del_rcu(&pol->bydst); hlist_add_behind_rcu(&pol->bydst, entry0); } entry0 = &pol->bydst; } if (!hlist_empty(list)) { entry0 = NULL; goto redo; } } static void xfrm_idx_hash_transfer(struct hlist_head *list, struct hlist_head *nidxtable, unsigned int nhashmask) { struct hlist_node *tmp; struct xfrm_policy *pol; hlist_for_each_entry_safe(pol, tmp, list, byidx) { unsigned int h; h = __idx_hash(pol->index, nhashmask); hlist_add_head(&pol->byidx, nidxtable+h); } } static unsigned long xfrm_new_hash_mask(unsigned int old_hmask) { return ((old_hmask + 1) << 1) - 1; } static void xfrm_bydst_resize(struct net *net, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int nhashmask = xfrm_new_hash_mask(hmask); unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); struct hlist_head *ndst = xfrm_hash_alloc(nsize); struct hlist_head *odst; int i; if (!ndst) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)); for (i = hmask; i >= 0; i--) xfrm_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir); rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst); net->xfrm.policy_bydst[dir].hmask = nhashmask; write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); synchronize_rcu(); xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head)); } static void xfrm_byidx_resize(struct net *net) { unsigned int hmask = net->xfrm.policy_idx_hmask; unsigned int nhashmask = xfrm_new_hash_mask(hmask); unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); struct hlist_head *oidx = net->xfrm.policy_byidx; struct hlist_head *nidx = xfrm_hash_alloc(nsize); int i; if (!nidx) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); for (i = hmask; i >= 0; i--) xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask); net->xfrm.policy_byidx = nidx; net->xfrm.policy_idx_hmask = nhashmask; spin_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head)); } static inline int xfrm_bydst_should_resize(struct net *net, int dir, int *total) { unsigned int cnt = READ_ONCE(net->xfrm.policy_count[dir]); unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; if (total) *total += cnt; if ((hmask + 1) < xfrm_policy_hashmax && cnt > hmask) return 1; return 0; } static inline int xfrm_byidx_should_resize(struct net *net, int total) { unsigned int hmask = net->xfrm.policy_idx_hmask; if ((hmask + 1) < xfrm_policy_hashmax && total > hmask) return 1; return 0; } void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) { si->incnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_IN]); si->outcnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT]); si->fwdcnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_FWD]); si->inscnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]); si->outscnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]); si->fwdscnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]); si->spdhcnt = net->xfrm.policy_idx_hmask; si->spdhmcnt = xfrm_policy_hashmax; } EXPORT_SYMBOL(xfrm_spd_getinfo); static DEFINE_MUTEX(hash_resize_mutex); static void xfrm_hash_resize(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.policy_hash_work); int dir, total; mutex_lock(&hash_resize_mutex); total = 0; for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { if (xfrm_bydst_should_resize(net, dir, &total)) xfrm_bydst_resize(net, dir); } if (xfrm_byidx_should_resize(net, total)) xfrm_byidx_resize(net); mutex_unlock(&hash_resize_mutex); } /* Make sure *pol can be inserted into fastbin. * Useful to check that later insert requests will be successful * (provided xfrm_policy_lock is held throughout). */ static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir) { struct xfrm_pol_inexact_bin *bin, *prev; struct xfrm_pol_inexact_key k = { .family = pol->family, .type = pol->type, .dir = dir, .if_id = pol->if_id, }; struct net *net = xp_net(pol); lockdep_assert_held(&net->xfrm.xfrm_policy_lock); write_pnet(&k.net, net); bin = rhashtable_lookup_fast(&xfrm_policy_inexact_table, &k, xfrm_pol_inexact_params); if (bin) return bin; bin = kzalloc_obj(*bin, GFP_ATOMIC); if (!bin) return NULL; bin->k = k; INIT_HLIST_HEAD(&bin->hhead); bin->root_d = RB_ROOT; bin->root_s = RB_ROOT; seqcount_spinlock_init(&bin->count, &net->xfrm.xfrm_policy_lock); prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table, &bin->k, &bin->head, xfrm_pol_inexact_params); if (!prev) { list_add(&bin->inexact_bins, &net->xfrm.inexact_bins); return bin; } kfree(bin); return IS_ERR(prev) ? NULL : prev; } static bool xfrm_pol_inexact_addr_use_any_list(const xfrm_address_t *addr, int family, u8 prefixlen) { if (xfrm_addr_any(addr, family)) return true; if (family == AF_INET6 && prefixlen < INEXACT_PREFIXLEN_IPV6) return true; if (family == AF_INET && prefixlen < INEXACT_PREFIXLEN_IPV4) return true; return false; } static bool xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy *policy) { const xfrm_address_t *addr; bool saddr_any, daddr_any; u8 prefixlen; addr = &policy->selector.saddr; prefixlen = policy->selector.prefixlen_s; saddr_any = xfrm_pol_inexact_addr_use_any_list(addr, policy->family, prefixlen); addr = &policy->selector.daddr; prefixlen = policy->selector.prefixlen_d; daddr_any = xfrm_pol_inexact_addr_use_any_list(addr, policy->family, prefixlen); return saddr_any && daddr_any; } static void xfrm_pol_inexact_node_init(struct xfrm_pol_inexact_node *node, const xfrm_address_t *addr, u8 prefixlen) { node->addr = *addr; node->prefixlen = prefixlen; } static struct xfrm_pol_inexact_node * xfrm_pol_inexact_node_alloc(const xfrm_address_t *addr, u8 prefixlen) { struct xfrm_pol_inexact_node *node; node = kzalloc_obj(*node, GFP_ATOMIC); if (node) xfrm_pol_inexact_node_init(node, addr, prefixlen); return node; } static int xfrm_policy_addr_delta(const xfrm_address_t *a, const xfrm_address_t *b, u8 prefixlen, u16 family) { u32 ma, mb, mask; unsigned int pdw, pbi; int delta = 0; switch (family) { case AF_INET: if (prefixlen == 0) return 0; mask = ~0U << (32 - prefixlen); ma = ntohl(a->a4) & mask; mb = ntohl(b->a4) & mask; if (ma < mb) delta = -1; else if (ma > mb) delta = 1; break; case AF_INET6: pdw = prefixlen >> 5; pbi = prefixlen & 0x1f; if (pdw) { delta = memcmp(a->a6, b->a6, pdw << 2); if (delta) return delta; } if (pbi) { mask = ~0U << (32 - pbi); ma = ntohl(a->a6[pdw]) & mask; mb = ntohl(b->a6[pdw]) & mask; if (ma < mb) delta = -1; else if (ma > mb) delta = 1; } break; default: break; } return delta; } static void xfrm_policy_inexact_list_reinsert(struct net *net, struct xfrm_pol_inexact_node *n, u16 family) { unsigned int matched_s, matched_d; struct xfrm_policy *policy, *p; matched_s = 0; matched_d = 0; list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { struct hlist_node *newpos = NULL; bool matches_s, matches_d; if (policy->walk.dead || !policy->bydst_reinsert) continue; WARN_ON_ONCE(policy->family != family); policy->bydst_reinsert = false; hlist_for_each_entry(p, &n->hhead, bydst) { if (policy->priority > p->priority) newpos = &p->bydst; else if (policy->priority == p->priority && policy->pos > p->pos) newpos = &p->bydst; else break; } if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET) hlist_add_behind_rcu(&policy->bydst, newpos); else hlist_add_head_rcu(&policy->bydst, &n->hhead); /* paranoia checks follow. * Check that the reinserted policy matches at least * saddr or daddr for current node prefix. * * Matching both is fine, matching saddr in one policy * (but not daddr) and then matching only daddr in another * is a bug. */ matches_s = xfrm_policy_addr_delta(&policy->selector.saddr, &n->addr, n->prefixlen, family) == 0; matches_d = xfrm_policy_addr_delta(&policy->selector.daddr, &n->addr, n->prefixlen, family) == 0; if (matches_s && matches_d) continue; WARN_ON_ONCE(!matches_s && !matches_d); if (matches_s) matched_s++; if (matches_d) matched_d++; WARN_ON_ONCE(matched_s && matched_d); } } static void xfrm_policy_inexact_node_reinsert(struct net *net, struct xfrm_pol_inexact_node *n, struct rb_root *new, u16 family) { struct xfrm_pol_inexact_node *node; struct rb_node **p, *parent; /* we should not have another subtree here */ WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root)); restart: parent = NULL; p = &new->rb_node; while (*p) { u8 prefixlen; int delta; parent = *p; node = rb_entry(*p, struct xfrm_pol_inexact_node, node); prefixlen = min(node->prefixlen, n->prefixlen); delta = xfrm_policy_addr_delta(&n->addr, &node->addr, prefixlen, family); if (delta < 0) { p = &parent->rb_left; } else if (delta > 0) { p = &parent->rb_right; } else { bool same_prefixlen = node->prefixlen == n->prefixlen; struct xfrm_policy *tmp; hlist_for_each_entry(tmp, &n->hhead, bydst) { tmp->bydst_reinsert = true; hlist_del_rcu(&tmp->bydst); } node->prefixlen = prefixlen; xfrm_policy_inexact_list_reinsert(net, node, family); if (same_prefixlen) { kfree_rcu(n, rcu); return; } rb_erase(*p, new); kfree_rcu(n, rcu); n = node; goto restart; } } rb_link_node_rcu(&n->node, parent, p); rb_insert_color(&n->node, new); } /* merge nodes v and n */ static void xfrm_policy_inexact_node_merge(struct net *net, struct xfrm_pol_inexact_node *v, struct xfrm_pol_inexact_node *n, u16 family) { struct xfrm_pol_inexact_node *node; struct xfrm_policy *tmp; struct rb_node *rnode; /* To-be-merged node v has a subtree. * * Dismantle it and insert its nodes to n->root. */ while ((rnode = rb_first(&v->root)) != NULL) { node = rb_entry(rnode, struct xfrm_pol_inexact_node, node); rb_erase(&node->node, &v->root); xfrm_policy_inexact_node_reinsert(net, node, &n->root, family); } hlist_for_each_entry(tmp, &v->hhead, bydst) { tmp->bydst_reinsert = true; hlist_del_rcu(&tmp->bydst); } xfrm_policy_inexact_list_reinsert(net, n, family); } static struct xfrm_pol_inexact_node * xfrm_policy_inexact_insert_node(struct net *net, struct rb_root *root, xfrm_address_t *addr, u16 family, u8 prefixlen, u8 dir) { struct xfrm_pol_inexact_node *cached = NULL; struct rb_node **p, *parent = NULL; struct xfrm_pol_inexact_node *node; p = &root->rb_node; while (*p) { int delta; parent = *p; node = rb_entry(*p, struct xfrm_pol_inexact_node, node); delta = xfrm_policy_addr_delta(addr, &node->addr, node->prefixlen, family); if (delta == 0 && prefixlen >= node->prefixlen) { WARN_ON_ONCE(cached); /* ipsec policies got lost */ return node; } if (delta < 0) p = &parent->rb_left; else p = &parent->rb_right; if (prefixlen < node->prefixlen) { delta = xfrm_policy_addr_delta(addr, &node->addr, prefixlen, family); if (delta) continue; /* This node is a subnet of the new prefix. It needs * to be removed and re-inserted with the smaller * prefix and all nodes that are now also covered * by the reduced prefixlen. */ rb_erase(&node->node, root); if (!cached) { xfrm_pol_inexact_node_init(node, addr, prefixlen); cached = node; } else { /* This node also falls within the new * prefixlen. Merge the to-be-reinserted * node and this one. */ xfrm_policy_inexact_node_merge(net, node, cached, family); kfree_rcu(node, rcu); } /* restart */ p = &root->rb_node; parent = NULL; } } node = cached; if (!node) { node = xfrm_pol_inexact_node_alloc(addr, prefixlen); if (!node) return NULL; } rb_link_node_rcu(&node->node, parent, p); rb_insert_color(&node->node, root); return node; } static void xfrm_policy_inexact_gc_tree(struct rb_root *r, bool rm) { struct xfrm_pol_inexact_node *node; struct rb_node *rn = rb_first(r); while (rn) { node = rb_entry(rn, struct xfrm_pol_inexact_node, node); xfrm_policy_inexact_gc_tree(&node->root, rm); rn = rb_next(rn); if (!hlist_empty(&node->hhead) || !RB_EMPTY_ROOT(&node->root)) { WARN_ON_ONCE(rm); continue; } rb_erase(&node->node, r); kfree_rcu(node, rcu); } } static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool net_exit) { write_seqcount_begin(&b->count); xfrm_policy_inexact_gc_tree(&b->root_d, net_exit); xfrm_policy_inexact_gc_tree(&b->root_s, net_exit); write_seqcount_end(&b->count); if (!RB_EMPTY_ROOT(&b->root_d) || !RB_EMPTY_ROOT(&b->root_s) || !hlist_empty(&b->hhead)) { WARN_ON_ONCE(net_exit); return; } if (rhashtable_remove_fast(&xfrm_policy_inexact_table, &b->head, xfrm_pol_inexact_params) == 0) { list_del(&b->inexact_bins); kfree_rcu(b, rcu); } } static void __xfrm_policy_inexact_flush(struct net *net) { struct xfrm_pol_inexact_bin *bin, *t; lockdep_assert_held(&net->xfrm.xfrm_policy_lock); list_for_each_entry_safe(bin, t, &net->xfrm.inexact_bins, inexact_bins) __xfrm_policy_inexact_prune_bin(bin, false); } static struct hlist_head * xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin, struct xfrm_policy *policy, u8 dir) { struct xfrm_pol_inexact_node *n; struct net *net; net = xp_net(policy); lockdep_assert_held(&net->xfrm.xfrm_policy_lock); if (xfrm_policy_inexact_insert_use_any_list(policy)) return &bin->hhead; if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr, policy->family, policy->selector.prefixlen_d)) { write_seqcount_begin(&bin->count); n = xfrm_policy_inexact_insert_node(net, &bin->root_s, &policy->selector.saddr, policy->family, policy->selector.prefixlen_s, dir); write_seqcount_end(&bin->count); if (!n) return NULL; return &n->hhead; } /* daddr is fixed */ write_seqcount_begin(&bin->count); n = xfrm_policy_inexact_insert_node(net, &bin->root_d, &policy->selector.daddr, policy->family, policy->selector.prefixlen_d, dir); write_seqcount_end(&bin->count); if (!n) return NULL; /* saddr is wildcard */ if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr, policy->family, policy->selector.prefixlen_s)) return &n->hhead; write_seqcount_begin(&bin->count); n = xfrm_policy_inexact_insert_node(net, &n->root, &policy->selector.saddr, policy->family, policy->selector.prefixlen_s, dir); write_seqcount_end(&bin->count); if (!n) return NULL; return &n->hhead; } static struct xfrm_policy * xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl) { struct xfrm_pol_inexact_bin *bin; struct xfrm_policy *delpol; struct hlist_head *chain; struct net *net; bin = xfrm_policy_inexact_alloc_bin(policy, dir); if (!bin) return ERR_PTR(-ENOMEM); net = xp_net(policy); lockdep_assert_held(&net->xfrm.xfrm_policy_lock); chain = xfrm_policy_inexact_alloc_chain(bin, policy, dir); if (!chain) { __xfrm_policy_inexact_prune_bin(bin, false); return ERR_PTR(-ENOMEM); } delpol = xfrm_policy_insert_list(chain, policy, excl); if (delpol && excl) { __xfrm_policy_inexact_prune_bin(bin, false); return ERR_PTR(-EEXIST); } if (delpol) __xfrm_policy_inexact_prune_bin(bin, false); return delpol; } static bool xfrm_policy_is_dead_or_sk(const struct xfrm_policy *policy) { int dir; if (policy->walk.dead) return true; dir = xfrm_policy_id2dir(policy->index); return dir >= XFRM_POLICY_MAX; } static void xfrm_hash_rebuild(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.policy_hthresh.work); struct xfrm_policy *pol; struct xfrm_policy *policy; struct hlist_head *chain; struct hlist_node *newpos; int dir; unsigned seq; u8 lbits4, rbits4, lbits6, rbits6; mutex_lock(&hash_resize_mutex); /* read selector prefixlen thresholds */ do { seq = read_seqbegin(&net->xfrm.policy_hthresh.lock); lbits4 = net->xfrm.policy_hthresh.lbits4; rbits4 = net->xfrm.policy_hthresh.rbits4; lbits6 = net->xfrm.policy_hthresh.lbits6; rbits6 = net->xfrm.policy_hthresh.rbits6; } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); /* make sure that we can insert the indirect policies again before * we start with destructive action. */ list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) { struct xfrm_pol_inexact_bin *bin; u8 dbits, sbits; if (xfrm_policy_is_dead_or_sk(policy)) continue; dir = xfrm_policy_id2dir(policy->index); if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { if (policy->family == AF_INET) { dbits = rbits4; sbits = lbits4; } else { dbits = rbits6; sbits = lbits6; } } else { if (policy->family == AF_INET) { dbits = lbits4; sbits = rbits4; } else { dbits = lbits6; sbits = rbits6; } } if (policy->selector.prefixlen_d >= dbits && policy->selector.prefixlen_s >= sbits) continue; bin = xfrm_policy_inexact_alloc_bin(policy, dir); if (!bin) goto out_unlock; if (!xfrm_policy_inexact_alloc_chain(bin, policy, dir)) goto out_unlock; } for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { /* dir out => dst = remote, src = local */ net->xfrm.policy_bydst[dir].dbits4 = rbits4; net->xfrm.policy_bydst[dir].sbits4 = lbits4; net->xfrm.policy_bydst[dir].dbits6 = rbits6; net->xfrm.policy_bydst[dir].sbits6 = lbits6; } else { /* dir in/fwd => dst = local, src = remote */ net->xfrm.policy_bydst[dir].dbits4 = lbits4; net->xfrm.policy_bydst[dir].sbits4 = rbits4; net->xfrm.policy_bydst[dir].dbits6 = lbits6; net->xfrm.policy_bydst[dir].sbits6 = rbits6; } } /* re-insert all policies by order of creation */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { if (xfrm_policy_is_dead_or_sk(policy)) continue; hlist_del_rcu(&policy->bydst); newpos = NULL; dir = xfrm_policy_id2dir(policy->index); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); if (!chain) { void *p = xfrm_policy_inexact_insert(policy, dir, 0); WARN_ONCE(IS_ERR(p), "reinsert: %ld\n", PTR_ERR(p)); continue; } hlist_for_each_entry(pol, chain, bydst) { if (policy->priority >= pol->priority) newpos = &pol->bydst; else break; } if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET) hlist_add_behind_rcu(&policy->bydst, newpos); else hlist_add_head_rcu(&policy->bydst, chain); } out_unlock: __xfrm_policy_inexact_flush(net); write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); mutex_unlock(&hash_resize_mutex); } void xfrm_policy_hash_rebuild(struct net *net) { schedule_work(&net->xfrm.policy_hthresh.work); } EXPORT_SYMBOL(xfrm_policy_hash_rebuild); /* Generate new index... KAME seems to generate them ordered by cost * of an absolute inpredictability of ordering of rules. This will not pass. */ static u32 xfrm_gen_index(struct net *net, int dir, u32 index) { for (;;) { struct hlist_head *list; struct xfrm_policy *p; u32 idx; int found; if (!index) { idx = (net->xfrm.idx_generator | dir); net->xfrm.idx_generator += 8; } else { idx = index; index = 0; } if (idx == 0) idx = 8; list = net->xfrm.policy_byidx + idx_hash(net, idx); found = 0; hlist_for_each_entry(p, list, byidx) { if (p->index == idx) { found = 1; break; } } if (!found) return idx; } } static inline int selector_cmp(struct xfrm_selector *s1, struct xfrm_selector *s2) { u32 *p1 = (u32 *) s1; u32 *p2 = (u32 *) s2; int len = sizeof(struct xfrm_selector) / sizeof(u32); int i; for (i = 0; i < len; i++) { if (p1[i] != p2[i]) return 1; } return 0; } static void xfrm_policy_requeue(struct xfrm_policy *old, struct xfrm_policy *new) { struct xfrm_policy_queue *pq = &old->polq; struct sk_buff_head list; if (skb_queue_empty(&pq->hold_queue)) return; __skb_queue_head_init(&list); spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice_init(&pq->hold_queue, &list); if (timer_delete(&pq->hold_timer)) xfrm_pol_put(old); spin_unlock_bh(&pq->hold_queue.lock); pq = &new->polq; spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice(&list, &pq->hold_queue); pq->timeout = XFRM_QUEUE_TMO_MIN; if (!mod_timer(&pq->hold_timer, jiffies)) xfrm_pol_hold(new); spin_unlock_bh(&pq->hold_queue.lock); } static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark, struct xfrm_policy *pol) { return mark->v == pol->mark.v && mark->m == pol->mark.m; } static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed) { const struct xfrm_pol_inexact_key *k = data; u32 a = k->type << 24 | k->dir << 16 | k->family; return jhash_3words(a, k->if_id, net_hash_mix(read_pnet(&k->net)), seed); } static u32 xfrm_pol_bin_obj(const void *data, u32 len, u32 seed) { const struct xfrm_pol_inexact_bin *b = data; return xfrm_pol_bin_key(&b->k, 0, seed); } static int xfrm_pol_bin_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct xfrm_pol_inexact_key *key = arg->key; const struct xfrm_pol_inexact_bin *b = ptr; int ret; if (!net_eq(read_pnet(&b->k.net), read_pnet(&key->net))) return -1; ret = b->k.dir ^ key->dir; if (ret) return ret; ret = b->k.type ^ key->type; if (ret) return ret; ret = b->k.family ^ key->family; if (ret) return ret; return b->k.if_id ^ key->if_id; } static const struct rhashtable_params xfrm_pol_inexact_params = { .head_offset = offsetof(struct xfrm_pol_inexact_bin, head), .hashfn = xfrm_pol_bin_key, .obj_hashfn = xfrm_pol_bin_obj, .obj_cmpfn = xfrm_pol_bin_cmp, .automatic_shrinking = true, }; static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy, bool excl) { struct xfrm_policy *pol, *newpos = NULL, *delpol = NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) return ERR_PTR(-EEXIST); delpol = pol; if (policy->priority > pol->priority) continue; } else if (policy->priority >= pol->priority) { newpos = pol; continue; } if (delpol) break; } if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET) hlist_add_behind_rcu(&policy->bydst, &newpos->bydst); else /* Packet offload policies enter to the head * to speed-up lookups. */ hlist_add_head_rcu(&policy->bydst, chain); return delpol; } int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) { struct net *net = xp_net(policy); struct xfrm_policy *delpol; struct hlist_head *chain; /* Sanitize mark before store */ policy->mark.v &= policy->mark.m; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); if (chain) delpol = xfrm_policy_insert_list(chain, policy, excl); else delpol = xfrm_policy_inexact_insert(policy, dir, excl); if (IS_ERR(delpol)) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return PTR_ERR(delpol); } __xfrm_policy_link(policy, dir); /* After previous checking, family can either be AF_INET or AF_INET6 */ if (policy->family == AF_INET) rt_genid_bump_ipv4(net); else rt_genid_bump_ipv6(net); if (delpol) { xfrm_policy_requeue(delpol, policy); __xfrm_policy_unlink(delpol, dir); } policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index); hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index)); policy->curlft.add_time = ktime_get_real_seconds(); policy->curlft.use_time = 0; if (!mod_timer(&policy->timer, jiffies + HZ)) xfrm_pol_hold(policy); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (delpol) xfrm_policy_kill(delpol); else if (xfrm_bydst_should_resize(net, dir, NULL)) schedule_work(&net->xfrm.policy_hash_work); return 0; } EXPORT_SYMBOL(xfrm_policy_insert); static struct xfrm_policy * __xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx) { struct xfrm_policy *pol; if (!chain) return NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && pol->if_id == if_id && xfrm_policy_mark_match(mark, pol) && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) return pol; } return NULL; } struct xfrm_policy * xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err) { struct xfrm_pol_inexact_bin *bin = NULL; struct xfrm_policy *pol, *ret = NULL; struct hlist_head *chain; *err = 0; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, sel, sel->family, dir); if (!chain) { struct xfrm_pol_inexact_candidates cand; int i; bin = xfrm_policy_inexact_lookup(net, type, sel->family, dir, if_id); if (!bin) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return NULL; } if (!xfrm_policy_find_inexact_candidates(&cand, bin, &sel->saddr, &sel->daddr)) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return NULL; } pol = NULL; for (i = 0; i < ARRAY_SIZE(cand.res); i++) { struct xfrm_policy *tmp; tmp = __xfrm_policy_bysel_ctx(cand.res[i], mark, if_id, type, dir, sel, ctx); if (!tmp) continue; if (!pol || tmp->pos < pol->pos) pol = tmp; } } else { pol = __xfrm_policy_bysel_ctx(chain, mark, if_id, type, dir, sel, ctx); } if (pol) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete(pol->security); if (*err) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); } ret = pol; } if (bin && delete) __xfrm_policy_inexact_prune_bin(bin, false); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); return ret; } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); struct xfrm_policy * xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, u32 id, int delete, int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; *err = -ENOENT; if (xfrm_policy_id2dir(id) != dir) return NULL; *err = 0; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = net->xfrm.policy_byidx + idx_hash(net, id); ret = NULL; hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete( pol->security); if (*err) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); } ret = pol; break; } } spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); return ret; } EXPORT_SYMBOL(xfrm_policy_byid); #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { struct xfrm_policy *pol; int err = 0; list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { if (pol->walk.dead || xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX || pol->type != type) continue; err = security_xfrm_policy_delete(pol->security); if (err) { xfrm_audit_policy_delete(pol, 0, task_valid); return err; } } return err; } static inline int xfrm_dev_policy_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) { struct xfrm_policy *pol; int err = 0; list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { if (pol->walk.dead || xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX || pol->xdo.dev != dev) continue; err = security_xfrm_policy_delete(pol->security); if (err) { xfrm_audit_policy_delete(pol, 0, task_valid); return err; } } return err; } #else static inline int xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { return 0; } static inline int xfrm_dev_policy_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) { return 0; } #endif int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) { int dir, err = 0, cnt = 0; struct xfrm_policy *pol; spin_lock_bh(&net->xfrm.xfrm_policy_lock); err = xfrm_policy_flush_secctx_check(net, type, task_valid); if (err) goto out; again: list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { if (pol->walk.dead) continue; dir = xfrm_policy_id2dir(pol->index); if (dir >= XFRM_POLICY_MAX || pol->type != type) continue; __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); spin_lock_bh(&net->xfrm.xfrm_policy_lock); goto again; } if (cnt) __xfrm_policy_inexact_flush(net); else err = -ESRCH; out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; } EXPORT_SYMBOL(xfrm_policy_flush); int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, bool task_valid) { int dir, err = 0, cnt = 0; struct xfrm_policy *pol; spin_lock_bh(&net->xfrm.xfrm_policy_lock); err = xfrm_dev_policy_flush_secctx_check(net, dev, task_valid); if (err) goto out; again: list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { if (pol->walk.dead) continue; dir = xfrm_policy_id2dir(pol->index); if (dir >= XFRM_POLICY_MAX || pol->xdo.dev != dev) continue; __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); spin_lock_bh(&net->xfrm.xfrm_policy_lock); goto again; } if (cnt) __xfrm_policy_inexact_flush(net); else err = -ESRCH; out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; } EXPORT_SYMBOL(xfrm_dev_policy_flush); int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, int (*func)(struct xfrm_policy *, int, int, void*), void *data) { struct xfrm_policy *pol; struct xfrm_policy_walk_entry *x; int error = 0; if (walk->type >= XFRM_POLICY_TYPE_MAX && walk->type != XFRM_POLICY_TYPE_ANY) return -EINVAL; if (list_empty(&walk->walk.all) && walk->seq != 0) return 0; spin_lock_bh(&net->xfrm.xfrm_policy_lock); if (list_empty(&walk->walk.all)) x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all); else x = list_first_entry(&walk->walk.all, struct xfrm_policy_walk_entry, all); list_for_each_entry_from(x, &net->xfrm.policy_all, all) { if (x->dead) continue; pol = container_of(x, struct xfrm_policy, walk); if (walk->type != XFRM_POLICY_TYPE_ANY && walk->type != pol->type) continue; error = func(pol, xfrm_policy_id2dir(pol->index), walk->seq, data); if (error) { list_move_tail(&walk->walk.all, &x->all); goto out; } walk->seq++; } if (walk->seq == 0) { error = -ENOENT; goto out; } list_del_init(&walk->walk.all); out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return error; } EXPORT_SYMBOL(xfrm_policy_walk); void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type) { INIT_LIST_HEAD(&walk->walk.all); walk->walk.dead = 1; walk->type = type; walk->seq = 0; } EXPORT_SYMBOL(xfrm_policy_walk_init); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net) { if (list_empty(&walk->walk.all)) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */ list_del(&walk->walk.all); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_policy_walk_done); /* * Find policy to apply to this flow. * * Returns 0 if policy found, else an -errno. */ static int xfrm_policy_match(const struct xfrm_policy *pol, const struct flowi *fl, u8 type, u16 family, u32 if_id) { const struct xfrm_selector *sel = &pol->selector; int ret = -ESRCH; bool match; if (pol->family != family || pol->if_id != if_id || (fl->flowi_mark & pol->mark.m) != pol->mark.v || pol->type != type) return ret; match = xfrm_selector_match(sel, fl, family); if (match) ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid); return ret; } static struct xfrm_pol_inexact_node * xfrm_policy_lookup_inexact_addr(const struct rb_root *r, seqcount_spinlock_t *count, const xfrm_address_t *addr, u16 family) { const struct rb_node *parent; int seq; again: seq = read_seqcount_begin(count); parent = rcu_dereference_raw(r->rb_node); while (parent) { struct xfrm_pol_inexact_node *node; int delta; node = rb_entry(parent, struct xfrm_pol_inexact_node, node); delta = xfrm_policy_addr_delta(addr, &node->addr, node->prefixlen, family); if (delta < 0) { parent = rcu_dereference_raw(parent->rb_left); continue; } else if (delta > 0) { parent = rcu_dereference_raw(parent->rb_right); continue; } return node; } if (read_seqcount_retry(count, seq)) goto again; return NULL; } static bool xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand, struct xfrm_pol_inexact_bin *b, const xfrm_address_t *saddr, const xfrm_address_t *daddr) { struct xfrm_pol_inexact_node *n; u16 family; if (!b) return false; family = b->k.family; memset(cand, 0, sizeof(*cand)); cand->res[XFRM_POL_CAND_ANY] = &b->hhead; n = xfrm_policy_lookup_inexact_addr(&b->root_d, &b->count, daddr, family); if (n) { cand->res[XFRM_POL_CAND_DADDR] = &n->hhead; n = xfrm_policy_lookup_inexact_addr(&n->root, &b->count, saddr, family); if (n) cand->res[XFRM_POL_CAND_BOTH] = &n->hhead; } n = xfrm_policy_lookup_inexact_addr(&b->root_s, &b->count, saddr, family); if (n) cand->res[XFRM_POL_CAND_SADDR] = &n->hhead; return true; } static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir, u32 if_id) { struct xfrm_pol_inexact_key k = { .family = family, .type = type, .dir = dir, .if_id = if_id, }; write_pnet(&k.net, net); return rhashtable_lookup(&xfrm_policy_inexact_table, &k, xfrm_pol_inexact_params); } static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir, u32 if_id) { struct xfrm_pol_inexact_bin *bin; lockdep_assert_held(&net->xfrm.xfrm_policy_lock); rcu_read_lock(); bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id); rcu_read_unlock(); return bin; } static struct xfrm_policy * __xfrm_policy_eval_candidates(struct hlist_head *chain, struct xfrm_policy *prefer, const struct flowi *fl, u8 type, u16 family, u32 if_id) { u32 priority = prefer ? prefer->priority : ~0u; struct xfrm_policy *pol; if (!chain) return NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { int err; if (pol->priority > priority) break; err = xfrm_policy_match(pol, fl, type, family, if_id); if (err) { if (err != -ESRCH) return ERR_PTR(err); continue; } if (prefer) { /* matches. Is it older than *prefer? */ if (pol->priority == priority && prefer->pos < pol->pos) return prefer; } return pol; } return NULL; } static struct xfrm_policy * xfrm_policy_eval_candidates(struct xfrm_pol_inexact_candidates *cand, struct xfrm_policy *prefer, const struct flowi *fl, u8 type, u16 family, u32 if_id) { struct xfrm_policy *tmp; int i; for (i = 0; i < ARRAY_SIZE(cand->res); i++) { tmp = __xfrm_policy_eval_candidates(cand->res[i], prefer, fl, type, family, if_id); if (!tmp) continue; if (IS_ERR(tmp)) return tmp; prefer = tmp; } return prefer; } static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, const struct flowi *fl, u16 family, u8 dir, u32 if_id) { struct xfrm_pol_inexact_candidates cand; const xfrm_address_t *daddr, *saddr; struct xfrm_pol_inexact_bin *bin; struct xfrm_policy *pol, *ret; struct hlist_head *chain; unsigned int sequence; int err; daddr = xfrm_flowi_daddr(fl, family); saddr = xfrm_flowi_saddr(fl, family); if (unlikely(!daddr || !saddr)) return NULL; rcu_read_lock(); retry: do { sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); chain = policy_hash_direct(net, daddr, saddr, family, dir); } while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)); ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, if_id); if (err) { if (err == -ESRCH) continue; else { ret = ERR_PTR(err); goto fail; } } else { ret = pol; break; } } if (ret && ret->xdo.type == XFRM_DEV_OFFLOAD_PACKET) goto skip_inexact; bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id); if (!bin || !xfrm_policy_find_inexact_candidates(&cand, bin, saddr, daddr)) goto skip_inexact; pol = xfrm_policy_eval_candidates(&cand, ret, fl, type, family, if_id); if (pol) { ret = pol; if (IS_ERR(pol)) goto fail; } skip_inexact: if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)) goto retry; if (ret && !xfrm_pol_hold_rcu(ret)) goto retry; fail: rcu_read_unlock(); return ret; } static struct xfrm_policy *xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, u32 if_id) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_policy *pol; pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir, if_id); if (pol != NULL) return pol; #endif return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir, if_id); } static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, const struct flowi *fl, u16 family, u32 if_id) { struct xfrm_policy *pol; rcu_read_lock(); again: pol = rcu_dereference(sk->sk_policy[dir]); if (pol != NULL) { bool match; int err = 0; if (pol->family != family) { pol = NULL; goto out; } match = xfrm_selector_match(&pol->selector, fl, family); if (match) { if ((READ_ONCE(sk->sk_mark) & pol->mark.m) != pol->mark.v || pol->if_id != if_id) { pol = NULL; goto out; } err = security_xfrm_policy_lookup(pol->security, fl->flowi_secid); if (!err) { if (!xfrm_pol_hold_rcu(pol)) goto again; } else if (err == -ESRCH) { pol = NULL; } else { pol = ERR_PTR(err); } } else pol = NULL; } out: rcu_read_unlock(); return pol; } static u32 xfrm_gen_pos_slow(struct net *net) { struct xfrm_policy *policy; u32 i = 0; /* oldest entry is last in list */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { if (!xfrm_policy_is_dead_or_sk(policy)) policy->pos = ++i; } return i; } static u32 xfrm_gen_pos(struct net *net) { const struct xfrm_policy *policy; u32 i = 0; /* most recently added policy is at the head of the list */ list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) { if (xfrm_policy_is_dead_or_sk(policy)) continue; if (policy->pos == UINT_MAX) return xfrm_gen_pos_slow(net); i = policy->pos + 1; break; } return i; } static void __xfrm_policy_link(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); switch (dir) { case XFRM_POLICY_IN: case XFRM_POLICY_FWD: case XFRM_POLICY_OUT: pol->pos = xfrm_gen_pos(net); break; } list_add(&pol->walk.all, &net->xfrm.policy_all); WRITE_ONCE(net->xfrm.policy_count[dir], net->xfrm.policy_count[dir] + 1); xfrm_pol_hold(pol); } static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); if (list_empty(&pol->walk.all)) return NULL; /* Socket policies are not hashed. */ if (!hlist_unhashed(&pol->bydst)) { hlist_del_rcu(&pol->bydst); hlist_del(&pol->byidx); } list_del_init(&pol->walk.all); WRITE_ONCE(net->xfrm.policy_count[dir], net->xfrm.policy_count[dir] - 1); return pol; } static void xfrm_sk_policy_link(struct xfrm_policy *pol, int dir) { __xfrm_policy_link(pol, XFRM_POLICY_MAX + dir); } static void xfrm_sk_policy_unlink(struct xfrm_policy *pol, int dir) { __xfrm_policy_unlink(pol, XFRM_POLICY_MAX + dir); } int xfrm_policy_delete(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); spin_lock_bh(&net->xfrm.xfrm_policy_lock); pol = __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (pol) { xfrm_policy_kill(pol); return 0; } return -ENOENT; } EXPORT_SYMBOL(xfrm_policy_delete); int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) { struct net *net = sock_net(sk); struct xfrm_policy *old_pol; #ifdef CONFIG_XFRM_SUB_POLICY if (pol && pol->type != XFRM_POLICY_TYPE_MAIN) return -EINVAL; #endif spin_lock_bh(&net->xfrm.xfrm_policy_lock); old_pol = rcu_dereference_protected(sk->sk_policy[dir], lockdep_is_held(&net->xfrm.xfrm_policy_lock)); if (pol) { pol->curlft.add_time = ktime_get_real_seconds(); pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0); xfrm_sk_policy_link(pol, dir); } rcu_assign_pointer(sk->sk_policy[dir], pol); if (old_pol) { if (pol) xfrm_policy_requeue(old_pol, pol); /* Unlinking succeeds always. This is the only function * allowed to delete or replace socket policy. */ xfrm_sk_policy_unlink(old_pol, dir); } spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (old_pol) { xfrm_policy_kill(old_pol); } return 0; } static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) { struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC); struct net *net = xp_net(old); if (newp) { newp->selector = old->selector; if (security_xfrm_policy_clone(old->security, &newp->security)) { kfree(newp); return NULL; /* ENOMEM */ } newp->lft = old->lft; newp->curlft = old->curlft; newp->mark = old->mark; newp->if_id = old->if_id; newp->action = old->action; newp->flags = old->flags; newp->xfrm_nr = old->xfrm_nr; newp->index = old->index; newp->type = old->type; newp->family = old->family; memcpy(newp->xfrm_vec, old->xfrm_vec, newp->xfrm_nr*sizeof(struct xfrm_tmpl)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); xfrm_sk_policy_link(newp, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_pol_put(newp); } return newp; } int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { const struct xfrm_policy *p; struct xfrm_policy *np; int i, ret = 0; rcu_read_lock(); for (i = 0; i < 2; i++) { p = rcu_dereference(osk->sk_policy[i]); if (p) { np = clone_policy(p, i); if (unlikely(!np)) { ret = -ENOMEM; break; } rcu_assign_pointer(sk->sk_policy[i], np); } } rcu_read_unlock(); return ret; } static int xfrm_get_saddr(unsigned short family, xfrm_address_t *saddr, const struct xfrm_dst_lookup_params *params) { int err; const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); if (unlikely(afinfo == NULL)) return -EINVAL; err = afinfo->get_saddr(saddr, params); rcu_read_unlock(); return err; } /* Resolve list of templates for the flow, given policy. */ static int xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, struct xfrm_state **xfrm, unsigned short family) { struct net *net = xp_net(policy); int nx; int i, error; xfrm_address_t *daddr = xfrm_flowi_daddr(fl, family); xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family); xfrm_address_t tmp; for (nx = 0, i = 0; i < policy->xfrm_nr; i++) { struct xfrm_state *x; xfrm_address_t *remote = daddr; xfrm_address_t *local = saddr; struct xfrm_tmpl *tmpl = &policy->xfrm_vec[i]; if (tmpl->mode == XFRM_MODE_TUNNEL || tmpl->mode == XFRM_MODE_IPTFS || tmpl->mode == XFRM_MODE_BEET) { remote = &tmpl->id.daddr; local = &tmpl->saddr; if (xfrm_addr_any(local, tmpl->encap_family)) { struct xfrm_dst_lookup_params params; memset(¶ms, 0, sizeof(params)); params.net = net; params.oif = fl->flowi_oif; params.daddr = remote; error = xfrm_get_saddr(tmpl->encap_family, &tmp, ¶ms); if (error) goto fail; local = &tmp; } } x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family, policy->if_id); if (x && x->dir && x->dir != XFRM_SA_DIR_OUT) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEDIRERROR); xfrm_state_put(x); error = -EINVAL; goto fail; } if (x && x->km.state == XFRM_STATE_VALID) { xfrm[nx++] = x; daddr = remote; saddr = local; continue; } if (x) { error = (x->km.state == XFRM_STATE_ERROR ? -EINVAL : -EAGAIN); xfrm_state_put(x); } else if (error == -ESRCH) { error = -EAGAIN; } if (!tmpl->optional) goto fail; } return nx; fail: for (nx--; nx >= 0; nx--) xfrm_state_put(xfrm[nx]); return error; } static int xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, struct xfrm_state **xfrm, unsigned short family) { struct xfrm_state *tp[XFRM_MAX_DEPTH]; struct xfrm_state **tpp = (npols > 1) ? tp : xfrm; int cnx = 0; int error; int ret; int i; for (i = 0; i < npols; i++) { if (cnx + pols[i]->xfrm_nr >= XFRM_MAX_DEPTH) { error = -ENOBUFS; goto fail; } ret = xfrm_tmpl_resolve_one(pols[i], fl, &tpp[cnx], family); if (ret < 0) { error = ret; goto fail; } else cnx += ret; } /* found states are sorted for outbound processing */ if (npols > 1) xfrm_state_sort(xfrm, tpp, cnx, family); return cnx; fail: for (cnx--; cnx >= 0; cnx--) xfrm_state_put(tpp[cnx]); return error; } static dscp_t xfrm_get_dscp(const struct flowi *fl, int family) { if (family == AF_INET) return fl->u.ip4.flowi4_dscp; return 0; } static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); struct dst_ops *dst_ops; struct xfrm_dst *xdst; if (!afinfo) return ERR_PTR(-EINVAL); switch (family) { case AF_INET: dst_ops = &net->xfrm.xfrm4_dst_ops; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: dst_ops = &net->xfrm.xfrm6_dst_ops; break; #endif default: BUG(); } xdst = dst_alloc(dst_ops, NULL, DST_OBSOLETE_NONE, 0); if (likely(xdst)) { memset_after(xdst, 0, u.dst); } else xdst = ERR_PTR(-ENOBUFS); rcu_read_unlock(); return xdst; } static void xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len) { if (dst->ops->family == AF_INET6) { path->path_cookie = rt6_get_cookie(dst_rt6_info(dst)); path->u.rt6.rt6i_nfheader_len = nfheader_len; } } static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(xdst->u.dst.ops->family); int err; if (!afinfo) return -EINVAL; err = afinfo->fill_dst(xdst, dev, fl); rcu_read_unlock(); return err; } /* Allocate chain of dst_entry's, attach known xfrm's, calculate * all the metrics... Shortly, bundle a bundle. */ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, struct xfrm_dst **bundle, int nx, const struct flowi *fl, struct dst_entry *dst) { const struct xfrm_state_afinfo *afinfo; const struct xfrm_mode *inner_mode; struct net *net = xp_net(policy); unsigned long now = jiffies; struct net_device *dev; struct xfrm_dst *xdst_prev = NULL; struct xfrm_dst *xdst0 = NULL; int i = 0; int err; int header_len = 0; int nfheader_len = 0; int trailer_len = 0; int family = policy->selector.family; xfrm_address_t saddr, daddr; dscp_t dscp; xfrm_flowi_addr_get(fl, &saddr, &daddr, family); dscp = xfrm_get_dscp(fl, family); dst_hold(dst); for (; i < nx; i++) { struct xfrm_dst *xdst = xfrm_alloc_dst(net, family); struct dst_entry *dst1 = &xdst->u.dst; err = PTR_ERR(xdst); if (IS_ERR(xdst)) { dst_release(dst); goto put_states; } bundle[i] = xdst; if (!xdst_prev) xdst0 = xdst; else /* Ref count is taken during xfrm_alloc_dst() * No need to do dst_clone() on dst1 */ xfrm_dst_set_child(xdst_prev, &xdst->u.dst); if (xfrm[i]->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(xfrm[i], xfrm_af2proto(family)); if (!inner_mode) { err = -EAFNOSUPPORT; dst_release(dst); goto put_states; } } else inner_mode = &xfrm[i]->inner_mode; xdst->route = dst; dst_copy_metrics(dst1, dst); if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { __u32 mark = 0; int oif; if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); if (xfrm[i]->xso.type != XFRM_DEV_OFFLOAD_PACKET) family = xfrm[i]->props.family; oif = fl->flowi_oif ? : fl->flowi_l3mdev; dst = xfrm_dst_lookup(xfrm[i], dscp, oif, &saddr, &daddr, family, mark); err = PTR_ERR(dst); if (IS_ERR(dst)) goto put_states; } else dst_hold(dst); dst1->xfrm = xfrm[i]; xdst->xfrm_genid = xfrm[i]->genid; dst1->obsolete = DST_OBSOLETE_FORCE_CHK; dst1->lastuse = now; dst1->input = dst_discard; if (xfrm[i]->mode_cbs && xfrm[i]->mode_cbs->output) { dst1->output = xfrm[i]->mode_cbs->output; } else { rcu_read_lock(); afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family); if (likely(afinfo)) dst1->output = afinfo->output; else dst1->output = dst_discard_out; rcu_read_unlock(); } xdst_prev = xdst; header_len += xfrm[i]->props.header_len; if (xfrm[i]->type->flags & XFRM_TYPE_NON_FRAGMENT) nfheader_len += xfrm[i]->props.header_len; trailer_len += xfrm[i]->props.trailer_len; } xfrm_dst_set_child(xdst_prev, dst); xdst0->path = dst; err = -ENODEV; dev = dst->dev; if (!dev) goto free_dst; xfrm_init_path(xdst0, dst, nfheader_len); xfrm_init_pmtu(bundle, nx); for (xdst_prev = xdst0; xdst_prev != (struct xfrm_dst *)dst; xdst_prev = (struct xfrm_dst *) xfrm_dst_child(&xdst_prev->u.dst)) { err = xfrm_fill_dst(xdst_prev, dev, fl); if (err) goto free_dst; xdst_prev->u.dst.header_len = header_len; xdst_prev->u.dst.trailer_len = trailer_len; header_len -= xdst_prev->u.dst.xfrm->props.header_len; trailer_len -= xdst_prev->u.dst.xfrm->props.trailer_len; } return &xdst0->u.dst; put_states: for (; i < nx; i++) xfrm_state_put(xfrm[i]); free_dst: if (xdst0) dst_release_immediate(&xdst0->u.dst); return ERR_PTR(err); } static int xfrm_expand_policies(const struct flowi *fl, u16 family, struct xfrm_policy **pols, int *num_pols, int *num_xfrms) { int i; if (*num_pols == 0 || !pols[0]) { *num_pols = 0; *num_xfrms = 0; return 0; } if (IS_ERR(pols[0])) { *num_pols = 0; return PTR_ERR(pols[0]); } *num_xfrms = pols[0]->xfrm_nr; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->action == XFRM_POLICY_ALLOW && pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]), XFRM_POLICY_TYPE_MAIN, fl, family, XFRM_POLICY_OUT, pols[0]->if_id); if (pols[1]) { if (IS_ERR(pols[1])) { xfrm_pols_put(pols, *num_pols); *num_pols = 0; return PTR_ERR(pols[1]); } (*num_pols)++; (*num_xfrms) += pols[1]->xfrm_nr; } } #endif for (i = 0; i < *num_pols; i++) { if (pols[i]->action != XFRM_POLICY_ALLOW) { *num_xfrms = -1; break; } } return 0; } static struct xfrm_dst * xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, const struct flowi *fl, u16 family, struct dst_entry *dst_orig) { struct net *net = xp_net(pols[0]); struct xfrm_state *xfrm[XFRM_MAX_DEPTH]; struct xfrm_dst *bundle[XFRM_MAX_DEPTH]; struct xfrm_dst *xdst; struct dst_entry *dst; int err; /* Try to instantiate a bundle */ err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family); if (err <= 0) { if (err == 0) return NULL; if (err != -EAGAIN) XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); return ERR_PTR(err); } dst = xfrm_bundle_create(pols[0], xfrm, bundle, err, fl, dst_orig); if (IS_ERR(dst)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR); return ERR_CAST(dst); } xdst = (struct xfrm_dst *)dst; xdst->num_xfrms = err; xdst->num_pols = num_pols; memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); xdst->policy_genid = atomic_read(&pols[0]->genid); return xdst; } static void xfrm_policy_queue_process(struct timer_list *t) { struct sk_buff *skb; struct sock *sk; struct dst_entry *dst; struct xfrm_policy *pol = timer_container_of(pol, t, polq.hold_timer); struct net *net = xp_net(pol); struct xfrm_policy_queue *pq = &pol->polq; struct flowi fl; struct sk_buff_head list; __u32 skb_mark; spin_lock(&pq->hold_queue.lock); skb = skb_peek(&pq->hold_queue); if (!skb) { spin_unlock(&pq->hold_queue.lock); goto out; } dst = skb_dst(skb); sk = skb->sk; /* Fixup the mark to support VTI. */ skb_mark = skb->mark; skb->mark = pol->mark.v; xfrm_decode_session(net, skb, &fl, dst->ops->family); skb->mark = skb_mark; spin_unlock(&pq->hold_queue.lock); dst_hold(xfrm_dst_path(dst)); dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) goto purge_queue; if (dst->flags & DST_XFRM_QUEUE) { dst_release(dst); if (pq->timeout >= XFRM_QUEUE_TMO_MAX) goto purge_queue; pq->timeout = pq->timeout << 1; if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout)) xfrm_pol_hold(pol); goto out; } dst_release(dst); __skb_queue_head_init(&list); spin_lock(&pq->hold_queue.lock); pq->timeout = 0; skb_queue_splice_init(&pq->hold_queue, &list); spin_unlock(&pq->hold_queue.lock); while (!skb_queue_empty(&list)) { skb = __skb_dequeue(&list); /* Fixup the mark to support VTI. */ skb_mark = skb->mark; skb->mark = pol->mark.v; xfrm_decode_session(net, skb, &fl, skb_dst(skb)->ops->family); skb->mark = skb_mark; dst_hold(xfrm_dst_path(skb_dst(skb))); dst = xfrm_lookup(net, xfrm_dst_path(skb_dst(skb)), &fl, skb->sk, 0); if (IS_ERR(dst)) { kfree_skb(skb); continue; } nf_reset_ct(skb); skb_dst_drop(skb); skb_dst_set(skb, dst); dst_output(net, skb_to_full_sk(skb), skb); } out: xfrm_pol_put(pol); return; purge_queue: pq->timeout = 0; skb_queue_purge(&pq->hold_queue); xfrm_pol_put(pol); } static int xdst_queue_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned long sched_next; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *) dst; struct xfrm_policy *pol = xdst->pols[0]; struct xfrm_policy_queue *pq = &pol->polq; if (unlikely(skb_fclone_busy(sk, skb))) { kfree_skb(skb); return 0; } if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) { kfree_skb(skb); return -EAGAIN; } skb_dst_force(skb); spin_lock_bh(&pq->hold_queue.lock); if (!pq->timeout) pq->timeout = XFRM_QUEUE_TMO_MIN; sched_next = jiffies + pq->timeout; if (timer_delete(&pq->hold_timer)) { if (time_before(pq->hold_timer.expires, sched_next)) sched_next = pq->hold_timer.expires; xfrm_pol_put(pol); } __skb_queue_tail(&pq->hold_queue, skb); if (!mod_timer(&pq->hold_timer, sched_next)) xfrm_pol_hold(pol); spin_unlock_bh(&pq->hold_queue.lock); return 0; } static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, struct xfrm_flo *xflo, const struct flowi *fl, int num_xfrms, u16 family) { int err; struct net_device *dev; struct dst_entry *dst; struct dst_entry *dst1; struct xfrm_dst *xdst; xdst = xfrm_alloc_dst(net, family); if (IS_ERR(xdst)) return xdst; if (!(xflo->flags & XFRM_LOOKUP_QUEUE) || net->xfrm.sysctl_larval_drop || num_xfrms <= 0) return xdst; dst = xflo->dst_orig; dst1 = &xdst->u.dst; dst_hold(dst); xdst->route = dst; dst_copy_metrics(dst1, dst); dst1->obsolete = DST_OBSOLETE_FORCE_CHK; dst1->flags |= DST_XFRM_QUEUE; dst1->lastuse = jiffies; dst1->input = dst_discard; dst1->output = xdst_queue_output; dst_hold(dst); xfrm_dst_set_child(xdst, dst); xdst->path = dst; xfrm_init_path((struct xfrm_dst *)dst1, dst, 0); err = -ENODEV; dev = dst->dev; if (!dev) goto free_dst; err = xfrm_fill_dst(xdst, dev, fl); if (err) goto free_dst; out: return xdst; free_dst: dst_release(dst1); xdst = ERR_PTR(err); goto out; } static struct xfrm_dst *xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct xfrm_flo *xflo, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols = 0, num_xfrms = 0, err; struct xfrm_dst *xdst; /* Resolve policies to use if we couldn't get them from * previous cache entry */ num_pols = 1; pols[0] = xfrm_policy_lookup(net, fl, family, dir, if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) goto inc_error; if (num_pols == 0) return NULL; if (num_xfrms <= 0) goto make_dummy_bundle; xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, xflo->dst_orig); if (IS_ERR(xdst)) { err = PTR_ERR(xdst); if (err == -EREMOTE) { xfrm_pols_put(pols, num_pols); return NULL; } if (err != -EAGAIN) goto error; goto make_dummy_bundle; } else if (xdst == NULL) { num_xfrms = 0; goto make_dummy_bundle; } return xdst; make_dummy_bundle: /* We found policies, but there's no bundles to instantiate: * either because the policy blocks, has no transformations or * we could not build template (no xfrm_states).*/ xdst = xfrm_create_dummy_bundle(net, xflo, fl, num_xfrms, family); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); return ERR_CAST(xdst); } xdst->num_pols = num_pols; xdst->num_xfrms = num_xfrms; memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); return xdst; inc_error: XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); error: xfrm_pols_put(pols, num_pols); return ERR_PTR(err); } static struct dst_entry *make_blackhole(struct net *net, u16 family, struct dst_entry *dst_orig) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); struct dst_entry *ret; if (!afinfo) { dst_release(dst_orig); return ERR_PTR(-EINVAL); } else { ret = afinfo->blackhole_route(net, dst_orig); } rcu_read_unlock(); return ret; } /* Finds/creates a bundle for given flow and if_id * * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. * * xfrm_lookup uses an if_id of 0 by default, and is provided for * compatibility */ struct dst_entry *xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; struct xfrm_dst *xdst; struct dst_entry *dst, *route; u16 family = dst_orig->ops->family; u8 dir = XFRM_POLICY_OUT; int i, err, num_pols, num_xfrms = 0, drop_pols = 0; dst = NULL; xdst = NULL; route = NULL; sk = sk_const_to_full_sk(sk); if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { num_pols = 1; pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family, if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) goto dropdst; if (num_pols) { if (num_xfrms <= 0) { drop_pols = num_pols; goto no_transform; } xdst = xfrm_resolve_and_create_bundle( pols, num_pols, fl, family, dst_orig); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); err = PTR_ERR(xdst); if (err == -EREMOTE) goto nopol; goto dropdst; } else if (xdst == NULL) { num_xfrms = 0; drop_pols = num_pols; goto no_transform; } route = xdst->route; } } if (xdst == NULL) { struct xfrm_flo xflo; xflo.dst_orig = dst_orig; xflo.flags = flags; /* To accelerate a bit... */ if (!if_id && ((dst_orig->flags & DST_NOXFRM) || !READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT]))) goto nopol; xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id); if (xdst == NULL) goto nopol; if (IS_ERR(xdst)) { err = PTR_ERR(xdst); goto dropdst; } num_pols = xdst->num_pols; num_xfrms = xdst->num_xfrms; memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols); route = xdst->route; } dst = &xdst->u.dst; if (route == NULL && num_xfrms > 0) { /* The only case when xfrm_bundle_lookup() returns a * bundle with null route, is when the template could * not be resolved. It means policies are there, but * bundle could not be created, since we don't yet * have the xfrm_state's. We need to wait for KM to * negotiate new SA's or bail out with error.*/ if (net->xfrm.sysctl_larval_drop) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); err = -EREMOTE; goto error; } err = -EAGAIN; XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); goto error; } no_transform: if (num_pols == 0) goto nopol; if ((flags & XFRM_LOOKUP_ICMP) && !(pols[0]->flags & XFRM_POLICY_ICMP)) { err = -ENOENT; goto error; } for (i = 0; i < num_pols; i++) WRITE_ONCE(pols[i]->curlft.use_time, ktime_get_real_seconds()); if (num_xfrms < 0) { /* Prohibit the flow */ XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK); err = -EPERM; goto error; } else if (num_xfrms > 0) { /* Flow transformed */ dst_release(dst_orig); } else { /* Flow passes untransformed */ dst_release(dst); dst = dst_orig; } ok: xfrm_pols_put(pols, drop_pols); if (dst->xfrm && (dst->xfrm->props.mode == XFRM_MODE_TUNNEL || dst->xfrm->props.mode == XFRM_MODE_IPTFS)) dst->flags |= DST_XFRM_TUNNEL; return dst; nopol: if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) && READ_ONCE(net->xfrm.policy_default[dir]) == XFRM_USERPOLICY_BLOCK) { err = -EPERM; goto error; } if (!(flags & XFRM_LOOKUP_ICMP)) { dst = dst_orig; goto ok; } err = -ENOENT; error: dst_release(dst); dropdst: if (!(flags & XFRM_LOOKUP_KEEP_DST_REF)) dst_release(dst_orig); xfrm_pols_put(pols, drop_pols); return ERR_PTR(err); } EXPORT_SYMBOL(xfrm_lookup_with_ifid); /* Main function: finds/creates a bundle for given flow. * * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. */ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { return xfrm_lookup_with_ifid(net, dst_orig, fl, sk, flags, 0); } EXPORT_SYMBOL(xfrm_lookup); /* Callers of xfrm_lookup_route() must ensure a call to dst_output(). * Otherwise we may send out blackholed packets. */ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, flags | XFRM_LOOKUP_QUEUE | XFRM_LOOKUP_KEEP_DST_REF); if (PTR_ERR(dst) == -EREMOTE) return make_blackhole(net, dst_orig->ops->family, dst_orig); if (IS_ERR(dst)) dst_release(dst_orig); return dst; } EXPORT_SYMBOL(xfrm_lookup_route); static inline int xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) { struct sec_path *sp = skb_sec_path(skb); struct xfrm_state *x; if (!sp || idx < 0 || idx >= sp->len) return 0; x = sp->xvec[idx]; if (!x->type->reject) return 0; return x->type->reject(x, skb, fl); } /* When skb is transformed back to its "native" form, we have to * check policy restrictions. At the moment we make this in maximally * stupid way. Shame on me. :-) Of course, connected sockets must * have policy cached at them. */ static inline int xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family, u32 if_id) { if (xfrm_state_kern(x)) return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family); return x->id.proto == tmpl->id.proto && (x->id.spi == tmpl->id.spi || !tmpl->id.spi) && (x->props.reqid == tmpl->reqid || !tmpl->reqid) && x->props.mode == tmpl->mode && (tmpl->allalgs || (tmpl->aalgos & (1<<x->props.aalgo)) || !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) && !(x->props.mode != XFRM_MODE_TRANSPORT && xfrm_state_addr_cmp(tmpl, x, family)) && (if_id == 0 || if_id == x->if_id); } /* * 0 or more than 0 is returned when validation is succeeded (either bypass * because of optional transport mode, or next index of the matched secpath * state with the template. * -1 is returned when no matching template is found. * Otherwise "-2 - errored_index" is returned. */ static inline int xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start, unsigned short family, u32 if_id) { int idx = start; if (tmpl->optional) { if (tmpl->mode == XFRM_MODE_TRANSPORT) return start; } else start = -1; for (; idx < sp->len; idx++) { if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { if (idx < sp->verified_cnt) { /* Secpath entry previously verified, consider optional and * continue searching */ continue; } if (start == -1) start = -2-idx; break; } } return start; } static void decode_session4(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reverse) { struct flowi4 *fl4 = &fl->u.ip4; memset(fl4, 0, sizeof(struct flowi4)); if (reverse) { fl4->saddr = flkeys->addrs.ipv4.dst; fl4->daddr = flkeys->addrs.ipv4.src; fl4->fl4_sport = flkeys->ports.dst; fl4->fl4_dport = flkeys->ports.src; } else { fl4->saddr = flkeys->addrs.ipv4.src; fl4->daddr = flkeys->addrs.ipv4.dst; fl4->fl4_sport = flkeys->ports.src; fl4->fl4_dport = flkeys->ports.dst; } switch (flkeys->basic.ip_proto) { case IPPROTO_GRE: fl4->fl4_gre_key = flkeys->gre.keyid; break; case IPPROTO_ICMP: fl4->fl4_icmp_type = flkeys->icmp.type; fl4->fl4_icmp_code = flkeys->icmp.code; break; } fl4->flowi4_proto = flkeys->basic.ip_proto; fl4->flowi4_dscp = inet_dsfield_to_dscp(flkeys->ip.tos); } #if IS_ENABLED(CONFIG_IPV6) static void decode_session6(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reverse) { struct flowi6 *fl6 = &fl->u.ip6; memset(fl6, 0, sizeof(struct flowi6)); if (reverse) { fl6->saddr = flkeys->addrs.ipv6.dst; fl6->daddr = flkeys->addrs.ipv6.src; fl6->fl6_sport = flkeys->ports.dst; fl6->fl6_dport = flkeys->ports.src; } else { fl6->saddr = flkeys->addrs.ipv6.src; fl6->daddr = flkeys->addrs.ipv6.dst; fl6->fl6_sport = flkeys->ports.src; fl6->fl6_dport = flkeys->ports.dst; } switch (flkeys->basic.ip_proto) { case IPPROTO_GRE: fl6->fl6_gre_key = flkeys->gre.keyid; break; case IPPROTO_ICMPV6: fl6->fl6_icmp_type = flkeys->icmp.type; fl6->fl6_icmp_code = flkeys->icmp.code; break; } fl6->flowi6_proto = flkeys->basic.ip_proto; } #endif int __xfrm_decode_session(struct net *net, struct sk_buff *skb, struct flowi *fl, unsigned int family, int reverse) { struct xfrm_flow_keys flkeys; memset(&flkeys, 0, sizeof(flkeys)); __skb_flow_dissect(net, skb, &xfrm_session_dissector, &flkeys, NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_ENCAP); switch (family) { case AF_INET: decode_session4(&flkeys, fl, reverse); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: decode_session6(&flkeys, fl, reverse); break; #endif default: return -EAFNOSUPPORT; } fl->flowi_mark = skb->mark; if (reverse) { fl->flowi_oif = skb->skb_iif; } else { int oif = 0; if (skb_dst(skb) && skb_dst(skb)->dev) oif = skb_dst(skb)->dev->ifindex; fl->flowi_oif = oif; } return security_xfrm_decode_session(skb, &fl->flowi_secid); } EXPORT_SYMBOL(__xfrm_decode_session); static inline int secpath_has_nontransport(const struct sec_path *sp, int k, int *idxp) { for (; k < sp->len; k++) { if (sp->xvec[k]->props.mode != XFRM_MODE_TRANSPORT) { *idxp = k; return 1; } } return 0; } static bool icmp_err_packet(const struct flowi *fl, unsigned short family) { const struct flowi4 *fl4 = &fl->u.ip4; if (family == AF_INET && fl4->flowi4_proto == IPPROTO_ICMP && (fl4->fl4_icmp_type == ICMP_DEST_UNREACH || fl4->fl4_icmp_type == ICMP_TIME_EXCEEDED)) return true; #if IS_ENABLED(CONFIG_IPV6) if (family == AF_INET6) { const struct flowi6 *fl6 = &fl->u.ip6; if (fl6->flowi6_proto == IPPROTO_ICMPV6 && (fl6->fl6_icmp_type == ICMPV6_DEST_UNREACH || fl6->fl6_icmp_type == ICMPV6_PKT_TOOBIG || fl6->fl6_icmp_type == ICMPV6_TIME_EXCEED)) return true; } #endif return false; } static bool xfrm_icmp_flow_decode(struct sk_buff *skb, unsigned short family, const struct flowi *fl, struct flowi *fl1) { bool ret = true; struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); int hl = family == AF_INET ? (sizeof(struct iphdr) + sizeof(struct icmphdr)) : (sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr)); if (!newskb) return true; if (!pskb_pull(newskb, hl)) goto out; skb_reset_network_header(newskb); if (xfrm_decode_session_reverse(dev_net(skb->dev), newskb, fl1, family) < 0) goto out; fl1->flowi_oif = fl->flowi_oif; fl1->flowi_mark = fl->flowi_mark; fl1->flowi_dscp = fl->flowi_dscp; nf_nat_decode_session(newskb, fl1, family); ret = false; out: consume_skb(newskb); return ret; } static bool xfrm_selector_inner_icmp_match(struct sk_buff *skb, unsigned short family, const struct xfrm_selector *sel, const struct flowi *fl) { bool ret = false; if (icmp_err_packet(fl, family)) { struct flowi fl1; if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) return ret; ret = xfrm_selector_match(sel, &fl1, family); } return ret; } static inline struct xfrm_policy *xfrm_in_fwd_icmp(struct sk_buff *skb, const struct flowi *fl, unsigned short family, u32 if_id) { struct xfrm_policy *pol = NULL; if (icmp_err_packet(fl, family)) { struct flowi fl1; struct net *net = dev_net(skb->dev); if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) return pol; pol = xfrm_policy_lookup(net, &fl1, family, XFRM_POLICY_FWD, if_id); if (IS_ERR(pol)) pol = NULL; } return pol; } static inline struct dst_entry *xfrm_out_fwd_icmp(struct sk_buff *skb, struct flowi *fl, unsigned short family, struct dst_entry *dst) { if (icmp_err_packet(fl, family)) { struct net *net = dev_net(skb->dev); struct dst_entry *dst2; struct flowi fl1; if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) return dst; dst_hold(dst); dst2 = xfrm_lookup(net, dst, &fl1, NULL, (XFRM_LOOKUP_QUEUE | XFRM_LOOKUP_ICMP)); if (IS_ERR(dst2)) return dst; if (dst2->xfrm) { dst_release(dst); dst = dst2; } else { dst_release(dst2); } } return dst; } int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); struct xfrm_policy *pol; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int npols = 0; int xfrm_nr; int pi; int reverse; struct flowi fl; int xerr_idx = -1; const struct xfrm_if_cb *ifcb; struct sec_path *sp; u32 if_id = 0; rcu_read_lock(); ifcb = xfrm_if_get_cb(); if (ifcb) { struct xfrm_if_decode_session_result r; if (ifcb->decode_session(skb, family, &r)) { if_id = r.if_id; net = r.net; } } rcu_read_unlock(); reverse = dir & ~XFRM_POLICY_MASK; dir &= XFRM_POLICY_MASK; if (__xfrm_decode_session(net, skb, &fl, family, reverse) < 0) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); return 0; } nf_nat_decode_session(skb, &fl, family); /* First, check used SA against their selectors. */ sp = skb_sec_path(skb); if (sp) { int i; for (i = sp->len - 1; i >= 0; i--) { struct xfrm_state *x = sp->xvec[i]; int ret = 0; if (!xfrm_selector_match(&x->sel, &fl, family)) { ret = 1; if (x->props.flags & XFRM_STATE_ICMP && xfrm_selector_inner_icmp_match(skb, family, &x->sel, &fl)) ret = 0; if (ret) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); return 0; } } } } pol = NULL; sk = sk_to_full_sk(sk); if (sk && sk->sk_policy[dir]) { pol = xfrm_sk_policy_lookup(sk, dir, &fl, family, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } } if (!pol) pol = xfrm_policy_lookup(net, &fl, family, dir, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } if (!pol && dir == XFRM_POLICY_FWD) pol = xfrm_in_fwd_icmp(skb, &fl, family, if_id); if (!pol) { const bool is_crypto_offload = sp && (xfrm_input_state(skb)->xso.type == XFRM_DEV_OFFLOAD_CRYPTO); if (READ_ONCE(net->xfrm.policy_default[dir]) == XFRM_USERPOLICY_BLOCK) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); return 0; } if (sp && secpath_has_nontransport(sp, 0, &xerr_idx) && !is_crypto_offload) { xfrm_secpath_reject(xerr_idx, skb, &fl); XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); return 0; } return 1; } /* This lockless write can happen from different cpus. */ WRITE_ONCE(pol->curlft.use_time, ktime_get_real_seconds()); pols[0] = pol; npols++; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, &fl, family, XFRM_POLICY_IN, if_id); if (pols[1]) { if (IS_ERR(pols[1])) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); xfrm_pol_put(pols[0]); return 0; } /* This write can happen from different cpus. */ WRITE_ONCE(pols[1]->curlft.use_time, ktime_get_real_seconds()); npols++; } } #endif if (pol->action == XFRM_POLICY_ALLOW) { static struct sec_path dummy; struct xfrm_tmpl *tp[XFRM_MAX_DEPTH]; struct xfrm_tmpl *stp[XFRM_MAX_DEPTH]; struct xfrm_tmpl **tpp = tp; int i, k = 0; int ti = 0; sp = skb_sec_path(skb); if (!sp) sp = &dummy; for (pi = 0; pi < npols; pi++) { if (pols[pi] != pol && pols[pi]->action != XFRM_POLICY_ALLOW) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); goto reject; } if (ti + pols[pi]->xfrm_nr >= XFRM_MAX_DEPTH) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto reject_error; } for (i = 0; i < pols[pi]->xfrm_nr; i++) tpp[ti++] = &pols[pi]->xfrm_vec[i]; } xfrm_nr = ti; if (npols > 1) { xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); tpp = stp; } if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET && sp == &dummy) /* This policy template was already checked by HW * and secpath was removed in __xfrm_policy_check2. */ goto out; /* For each tunnel xfrm, find the first matching tmpl. * For each tmpl before that, find corresponding xfrm. * Order is _important_. Later we will implement * some barriers, but at the moment barriers * are implied between each two transformations. * Upon success, marks secpath entries as having been * verified to allow them to be skipped in future policy * checks (e.g. nested tunnels). */ for (i = xfrm_nr - 1; i >= 0; i--) { k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); if (k < 0) { if (k < -1) /* "-2 - errored_index" returned */ xerr_idx = -(2+k); XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH); goto reject; } } if (secpath_has_nontransport(sp, k, &xerr_idx)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH); goto reject; } out: xfrm_pols_put(pols, npols); sp->verified_cnt = k; return 1; } XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); reject: xfrm_secpath_reject(xerr_idx, skb, &fl); reject_error: xfrm_pols_put(pols, npols); return 0; } EXPORT_SYMBOL(__xfrm_policy_check); int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); struct flowi fl; struct dst_entry *dst; int res = 1; if (xfrm_decode_session(net, skb, &fl, family) < 0) { XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR); return 0; } skb_dst_force(skb); dst = skb_dst(skb); if (!dst) { XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR); return 0; } /* ignore return value from skb_dstref_steal, xfrm_lookup takes * care of dropping the refcnt if needed. */ skb_dstref_steal(skb); dst = xfrm_lookup(net, dst, &fl, NULL, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) { res = 0; dst = NULL; } if (dst && !dst->xfrm) dst = xfrm_out_fwd_icmp(skb, &fl, family, dst); skb_dst_set(skb, dst); return res; } EXPORT_SYMBOL(__xfrm_route_forward); /* Optimize later using cookies and generation ids. */ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) { /* Code (such as xfrm_bundle_create()) sets dst->obsolete * to DST_OBSOLETE_FORCE_CHK to force all XFRM destinations to * get validated by dst_ops->check on every use. We do this * because when a normal route referenced by an XFRM dst is * obsoleted we do not go looking around for all parent * referencing XFRM dsts so that we can invalidate them. It * is just too much work. Instead we make the checks here on * every use. For example: * * XFRM dst A --> IPv4 dst X * * X is the "xdst->route" of A (X is also the "dst->path" of A * in this example). If X is marked obsolete, "A" will not * notice. That's what we are validating here via the * stale_bundle() check. * * When a dst is removed from the fib tree, DST_OBSOLETE_DEAD will * be marked on it. * This will force stale_bundle() to fail on any xdst bundle with * this dst linked in it. */ if (READ_ONCE(dst->obsolete) < 0 && !stale_bundle(dst)) return dst; return NULL; } static int stale_bundle(struct dst_entry *dst) { return !xfrm_bundle_ok((struct xfrm_dst *)dst); } void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) { dst->dev = blackhole_netdev; dev_hold(dst->dev); dev_put(dev); } } EXPORT_SYMBOL(xfrm_dst_ifdown); static void xfrm_link_failure(struct sk_buff *skb) { /* Impossible. Such dst must be popped before reaches point of failure. */ } static void xfrm_negative_advice(struct sock *sk, struct dst_entry *dst) { if (READ_ONCE(dst->obsolete)) sk_dst_reset(sk); } static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr) { while (nr--) { struct xfrm_dst *xdst = bundle[nr]; u32 pmtu, route_mtu_cached; struct dst_entry *dst; dst = &xdst->u.dst; pmtu = dst_mtu(xfrm_dst_child(dst)); xdst->child_mtu_cached = pmtu; pmtu = xfrm_state_mtu(dst->xfrm, pmtu); route_mtu_cached = dst_mtu(xdst->route); xdst->route_mtu_cached = route_mtu_cached; if (pmtu > route_mtu_cached) pmtu = route_mtu_cached; dst_metric_set(dst, RTAX_MTU, pmtu); } } /* Check that the bundle accepts the flow and its components are * still valid. */ static int xfrm_bundle_ok(struct xfrm_dst *first) { struct xfrm_dst *bundle[XFRM_MAX_DEPTH]; struct dst_entry *dst = &first->u.dst; struct xfrm_dst *xdst; int start_from, nr; u32 mtu; if (!dst_check(xfrm_dst_path(dst), ((struct xfrm_dst *)dst)->path_cookie) || (dst->dev && !netif_running(dst->dev))) return 0; if (dst->flags & DST_XFRM_QUEUE) return 1; start_from = nr = 0; do { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; if (dst->xfrm->km.state != XFRM_STATE_VALID) return 0; if (xdst->xfrm_genid != dst->xfrm->genid) return 0; if (xdst->num_pols > 0 && xdst->policy_genid != atomic_read(&xdst->pols[0]->genid)) return 0; bundle[nr++] = xdst; mtu = dst_mtu(xfrm_dst_child(dst)); if (xdst->child_mtu_cached != mtu) { start_from = nr; xdst->child_mtu_cached = mtu; } if (!dst_check(xdst->route, xdst->route_cookie)) return 0; mtu = dst_mtu(xdst->route); if (xdst->route_mtu_cached != mtu) { start_from = nr; xdst->route_mtu_cached = mtu; } dst = xfrm_dst_child(dst); } while (dst->xfrm); if (likely(!start_from)) return 1; xdst = bundle[start_from - 1]; mtu = xdst->child_mtu_cached; while (start_from--) { dst = &xdst->u.dst; mtu = xfrm_state_mtu(dst->xfrm, mtu); if (mtu > xdst->route_mtu_cached) mtu = xdst->route_mtu_cached; dst_metric_set(dst, RTAX_MTU, mtu); if (!start_from) break; xdst = bundle[start_from - 1]; xdst->child_mtu_cached = mtu; } return 1; } static unsigned int xfrm_default_advmss(const struct dst_entry *dst) { return dst_metric_advmss(xfrm_dst_path(dst)); } static unsigned int xfrm_mtu(const struct dst_entry *dst) { unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); return mtu ? : dst_mtu(xfrm_dst_path(dst)); } static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst, const void *daddr) { while (dst->xfrm) { const struct xfrm_state *xfrm = dst->xfrm; dst = xfrm_dst_child(dst); if (xfrm->props.mode == XFRM_MODE_TRANSPORT) continue; if (xfrm->type->flags & XFRM_TYPE_REMOTE_COADDR) daddr = xfrm->coaddr; else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR)) daddr = &xfrm->id.daddr; } return daddr; } static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct dst_entry *path = xfrm_dst_path(dst); if (!skb) daddr = xfrm_get_dst_nexthop(dst, daddr); return path->ops->neigh_lookup(path, skb, daddr); } static void xfrm_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct dst_entry *path = xfrm_dst_path(dst); daddr = xfrm_get_dst_nexthop(dst, daddr); path->ops->confirm_neigh(path, daddr); } int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int family) { int err = 0; if (WARN_ON(family >= ARRAY_SIZE(xfrm_policy_afinfo))) return -EAFNOSUPPORT; spin_lock(&xfrm_policy_afinfo_lock); if (unlikely(xfrm_policy_afinfo[family] != NULL)) err = -EEXIST; else { struct dst_ops *dst_ops = afinfo->dst_ops; if (likely(dst_ops->kmem_cachep == NULL)) dst_ops->kmem_cachep = xfrm_dst_cache; if (likely(dst_ops->check == NULL)) dst_ops->check = xfrm_dst_check; if (likely(dst_ops->default_advmss == NULL)) dst_ops->default_advmss = xfrm_default_advmss; if (likely(dst_ops->mtu == NULL)) dst_ops->mtu = xfrm_mtu; if (likely(dst_ops->negative_advice == NULL)) dst_ops->negative_advice = xfrm_negative_advice; if (likely(dst_ops->link_failure == NULL)) dst_ops->link_failure = xfrm_link_failure; if (likely(dst_ops->neigh_lookup == NULL)) dst_ops->neigh_lookup = xfrm_neigh_lookup; if (likely(!dst_ops->confirm_neigh)) dst_ops->confirm_neigh = xfrm_confirm_neigh; rcu_assign_pointer(xfrm_policy_afinfo[family], afinfo); } spin_unlock(&xfrm_policy_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_policy_register_afinfo); void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo) { struct dst_ops *dst_ops = afinfo->dst_ops; int i; for (i = 0; i < ARRAY_SIZE(xfrm_policy_afinfo); i++) { if (rcu_access_pointer(xfrm_policy_afinfo[i]) != afinfo) continue; RCU_INIT_POINTER(xfrm_policy_afinfo[i], NULL); break; } synchronize_rcu(); dst_ops->kmem_cachep = NULL; dst_ops->check = NULL; dst_ops->negative_advice = NULL; dst_ops->link_failure = NULL; } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb) { spin_lock(&xfrm_if_cb_lock); rcu_assign_pointer(xfrm_if_cb, ifcb); spin_unlock(&xfrm_if_cb_lock); } EXPORT_SYMBOL(xfrm_if_register_cb); void xfrm_if_unregister_cb(void) { RCU_INIT_POINTER(xfrm_if_cb, NULL); synchronize_rcu(); } EXPORT_SYMBOL(xfrm_if_unregister_cb); #ifdef CONFIG_XFRM_STATISTICS static int __net_init xfrm_statistics_init(struct net *net) { int rv; net->mib.xfrm_statistics = alloc_percpu(struct linux_xfrm_mib); if (!net->mib.xfrm_statistics) return -ENOMEM; rv = xfrm_proc_init(net); if (rv < 0) free_percpu(net->mib.xfrm_statistics); return rv; } static void xfrm_statistics_fini(struct net *net) { xfrm_proc_fini(net); free_percpu(net->mib.xfrm_statistics); } #else static int __net_init xfrm_statistics_init(struct net *net) { return 0; } static void xfrm_statistics_fini(struct net *net) { } #endif static int __net_init xfrm_policy_init(struct net *net) { unsigned int hmask, sz; int dir, err; if (net_eq(net, &init_net)) { xfrm_dst_cache = KMEM_CACHE(xfrm_dst, SLAB_HWCACHE_ALIGN | SLAB_PANIC); err = rhashtable_init(&xfrm_policy_inexact_table, &xfrm_pol_inexact_params); BUG_ON(err); } hmask = 8 - 1; sz = (hmask+1) * sizeof(struct hlist_head); net->xfrm.policy_byidx = xfrm_hash_alloc(sz); if (!net->xfrm.policy_byidx) goto out_byidx; net->xfrm.policy_idx_hmask = hmask; for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy_hash *htab; net->xfrm.policy_count[dir] = 0; net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0; htab = &net->xfrm.policy_bydst[dir]; rcu_assign_pointer(htab->table, xfrm_hash_alloc(sz)); if (!htab->table) goto out_bydst; htab->hmask = hmask; htab->dbits4 = 32; htab->sbits4 = 32; htab->dbits6 = 128; htab->sbits6 = 128; } net->xfrm.policy_hthresh.lbits4 = 32; net->xfrm.policy_hthresh.rbits4 = 32; net->xfrm.policy_hthresh.lbits6 = 128; net->xfrm.policy_hthresh.rbits6 = 128; seqlock_init(&net->xfrm.policy_hthresh.lock); INIT_LIST_HEAD(&net->xfrm.policy_all); INIT_LIST_HEAD(&net->xfrm.inexact_bins); INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize); INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild); return 0; out_bydst: for (dir--; dir >= 0; dir--) { struct xfrm_policy_hash *htab; htab = &net->xfrm.policy_bydst[dir]; xfrm_hash_free(rcu_dereference_protected(htab->table, true), sz); } xfrm_hash_free(net->xfrm.policy_byidx, sz); out_byidx: return -ENOMEM; } static void __net_exit xfrm_net_pre_exit(struct net *net) { disable_work_sync(&net->xfrm.policy_hthresh.work); flush_work(&net->xfrm.policy_hash_work); #ifdef CONFIG_XFRM_SUB_POLICY xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false); #endif xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false); } static void xfrm_policy_fini(struct net *net) { struct xfrm_pol_inexact_bin *b, *t; unsigned int sz; int dir; WARN_ON(!list_empty(&net->xfrm.policy_all)); for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy_hash *htab; htab = &net->xfrm.policy_bydst[dir]; sz = (htab->hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(rcu_dereference_protected(htab->table, true))); xfrm_hash_free(rcu_dereference_protected(htab->table, true), sz); } sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(net->xfrm.policy_byidx)); xfrm_hash_free(net->xfrm.policy_byidx, sz); spin_lock_bh(&net->xfrm.xfrm_policy_lock); list_for_each_entry_safe(b, t, &net->xfrm.inexact_bins, inexact_bins) __xfrm_policy_inexact_prune_bin(b, true); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); } static int __net_init xfrm_net_init(struct net *net) { int rv; /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); spin_lock_init(&net->xfrm.xfrm_policy_lock); seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); net->xfrm.policy_default[XFRM_POLICY_IN] = XFRM_USERPOLICY_ACCEPT; net->xfrm.policy_default[XFRM_POLICY_FWD] = XFRM_USERPOLICY_ACCEPT; net->xfrm.policy_default[XFRM_POLICY_OUT] = XFRM_USERPOLICY_ACCEPT; rv = xfrm_statistics_init(net); if (rv < 0) goto out_statistics; rv = xfrm_state_init(net); if (rv < 0) goto out_state; rv = xfrm_policy_init(net); if (rv < 0) goto out_policy; rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; rv = xfrm_nat_keepalive_net_init(net); if (rv < 0) goto out_nat_keepalive; return 0; out_nat_keepalive: xfrm_sysctl_fini(net); out_sysctl: xfrm_policy_fini(net); out_policy: xfrm_state_fini(net); out_state: xfrm_statistics_fini(net); out_statistics: return rv; } static void __net_exit xfrm_net_exit(struct net *net) { xfrm_nat_keepalive_net_fini(net); xfrm_sysctl_fini(net); xfrm_policy_fini(net); xfrm_state_fini(net); xfrm_statistics_fini(net); } static struct pernet_operations __net_initdata xfrm_net_ops = { .init = xfrm_net_init, .pre_exit = xfrm_net_pre_exit, .exit = xfrm_net_exit, }; static const struct flow_dissector_key xfrm_flow_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct xfrm_flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct xfrm_flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct xfrm_flow_keys, addrs.ipv4), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct xfrm_flow_keys, addrs.ipv6), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct xfrm_flow_keys, ports), }, { .key_id = FLOW_DISSECTOR_KEY_GRE_KEYID, .offset = offsetof(struct xfrm_flow_keys, gre), }, { .key_id = FLOW_DISSECTOR_KEY_IP, .offset = offsetof(struct xfrm_flow_keys, ip), }, { .key_id = FLOW_DISSECTOR_KEY_ICMP, .offset = offsetof(struct xfrm_flow_keys, icmp), }, }; void __init xfrm_init(void) { skb_flow_dissector_init(&xfrm_session_dissector, xfrm_flow_dissector_keys, ARRAY_SIZE(xfrm_flow_dissector_keys)); register_pernet_subsys(&xfrm_net_ops); xfrm_dev_init(); xfrm_input_init(); #ifdef CONFIG_XFRM_ESPINTCP espintcp_init(); #endif register_xfrm_state_bpf(); xfrm_nat_keepalive_init(AF_INET); } #ifdef CONFIG_AUDITSYSCALL static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp, struct audit_buffer *audit_buf) { struct xfrm_sec_ctx *ctx = xp->security; struct xfrm_selector *sel = &xp->selector; if (ctx) audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); switch (sel->family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4); if (sel->prefixlen_s != 32) audit_log_format(audit_buf, " src_prefixlen=%d", sel->prefixlen_s); audit_log_format(audit_buf, " dst=%pI4", &sel->daddr.a4); if (sel->prefixlen_d != 32) audit_log_format(audit_buf, " dst_prefixlen=%d", sel->prefixlen_d); break; case AF_INET6: audit_log_format(audit_buf, " src=%pI6", sel->saddr.a6); if (sel->prefixlen_s != 128) audit_log_format(audit_buf, " src_prefixlen=%d", sel->prefixlen_s); audit_log_format(audit_buf, " dst=%pI6", sel->daddr.a6); if (sel->prefixlen_d != 128) audit_log_format(audit_buf, " dst_prefixlen=%d", sel->prefixlen_d); break; } } void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SPD-add"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); audit_log_format(audit_buf, " res=%u", result); xfrm_audit_common_policyinfo(xp, audit_buf); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_policy_add); void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SPD-delete"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); audit_log_format(audit_buf, " res=%u", result); xfrm_audit_common_policyinfo(xp, audit_buf); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_policy_delete); #endif #ifdef CONFIG_XFRM_MIGRATE static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel, u8 dir, u8 type, struct net *net, u32 if_id) { struct xfrm_policy *pol; struct flowi fl; memset(&fl, 0, sizeof(fl)); fl.flowi_proto = sel->proto; switch (sel->family) { case AF_INET: fl.u.ip4.saddr = sel->saddr.a4; fl.u.ip4.daddr = sel->daddr.a4; if (sel->proto == IPSEC_ULPROTO_ANY) break; fl.u.flowi4_oif = sel->ifindex; fl.u.ip4.fl4_sport = sel->sport; fl.u.ip4.fl4_dport = sel->dport; break; case AF_INET6: fl.u.ip6.saddr = sel->saddr.in6; fl.u.ip6.daddr = sel->daddr.in6; if (sel->proto == IPSEC_ULPROTO_ANY) break; fl.u.flowi6_oif = sel->ifindex; fl.u.ip6.fl4_sport = sel->sport; fl.u.ip6.fl4_dport = sel->dport; break; default: return ERR_PTR(-EAFNOSUPPORT); } rcu_read_lock(); pol = xfrm_policy_lookup_bytype(net, type, &fl, sel->family, dir, if_id); if (IS_ERR_OR_NULL(pol)) goto out_unlock; out_unlock: rcu_read_unlock(); return pol; } static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tmpl *t) { int match = 0; if (t->mode == m->mode && t->id.proto == m->proto && (m->old_reqid == 0 || t->reqid == m->old_reqid)) { switch (t->mode) { case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: case XFRM_MODE_IPTFS: if (xfrm_addr_equal(&t->id.daddr, &m->old_daddr, m->old_family) && xfrm_addr_equal(&t->saddr, &m->old_saddr, m->old_family)) { match = 1; } break; case XFRM_MODE_TRANSPORT: /* in case of transport mode, template does not store any IP addresses, hence we just compare mode and protocol */ match = 1; break; default: break; } } return match; } /* update endpoint address(es) of template(s) */ static int xfrm_policy_migrate(struct xfrm_policy *pol, struct xfrm_migrate *m, int num_migrate, struct netlink_ext_ack *extack) { struct xfrm_migrate *mp; int i, j, n = 0; write_lock_bh(&pol->lock); if (unlikely(pol->walk.dead)) { /* target policy has been deleted */ NL_SET_ERR_MSG(extack, "Target policy not found"); write_unlock_bh(&pol->lock); return -ENOENT; } for (i = 0; i < pol->xfrm_nr; i++) { for (j = 0, mp = m; j < num_migrate; j++, mp++) { if (!migrate_tmpl_match(mp, &pol->xfrm_vec[i])) continue; n++; if (pol->xfrm_vec[i].mode != XFRM_MODE_TUNNEL && pol->xfrm_vec[i].mode != XFRM_MODE_BEET && pol->xfrm_vec[i].mode != XFRM_MODE_IPTFS) continue; /* update endpoints */ memcpy(&pol->xfrm_vec[i].id.daddr, &mp->new_daddr, sizeof(pol->xfrm_vec[i].id.daddr)); memcpy(&pol->xfrm_vec[i].saddr, &mp->new_saddr, sizeof(pol->xfrm_vec[i].saddr)); pol->xfrm_vec[i].encap_family = mp->new_family; /* flush bundles */ atomic_inc(&pol->genid); } } write_unlock_bh(&pol->lock); if (!n) return -ENODATA; return 0; } static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate, struct netlink_ext_ack *extack) { int i, j; if (num_migrate < 1 || num_migrate > XFRM_MAX_DEPTH) { NL_SET_ERR_MSG(extack, "Invalid number of SAs to migrate, must be 0 < num <= XFRM_MAX_DEPTH (6)"); return -EINVAL; } for (i = 0; i < num_migrate; i++) { if (xfrm_addr_any(&m[i].new_daddr, m[i].new_family) || xfrm_addr_any(&m[i].new_saddr, m[i].new_family)) { NL_SET_ERR_MSG(extack, "Addresses in the MIGRATE attribute's list cannot be null"); return -EINVAL; } /* check if there is any duplicated entry */ for (j = i + 1; j < num_migrate; j++) { if (!memcmp(&m[i].old_daddr, &m[j].old_daddr, sizeof(m[i].old_daddr)) && !memcmp(&m[i].old_saddr, &m[j].old_saddr, sizeof(m[i].old_saddr)) && m[i].proto == m[j].proto && m[i].mode == m[j].mode && m[i].old_reqid == m[j].old_reqid && m[i].old_family == m[j].old_family) { NL_SET_ERR_MSG(extack, "Entries in the MIGRATE attribute's list must be unique"); return -EINVAL; } } } return 0; } /* * Fill migrate fields that are invariant in XFRM_MSG_MIGRATE: inherited * from the existing SA unchanged. XFRM_MSG_MIGRATE_STATE can update these. */ static void xfrm_migrate_copy_old(const struct xfrm_state *x, struct xfrm_migrate *mp) { mp->msg_type = XFRM_MSG_MIGRATE; mp->smark = x->props.smark; mp->new_reqid = x->props.reqid; mp->nat_keepalive_interval = x->nat_keepalive_interval; mp->mapping_maxage = x->mapping_maxage; mp->new_mark = &x->mark; } int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, struct xfrm_kmaddress *k, struct net *net, struct xfrm_encap_tmpl *encap, u32 if_id, struct netlink_ext_ack *extack, struct xfrm_user_offload *xuo) { int i, err, nx_cur = 0, nx_new = 0; struct xfrm_policy *pol = NULL; struct xfrm_state *x, *xc; struct xfrm_state *x_cur[XFRM_MAX_DEPTH]; struct xfrm_state *x_new[XFRM_MAX_DEPTH]; struct xfrm_migrate *mp; /* Stage 0 - sanity checks */ err = xfrm_migrate_check(m, num_migrate, extack); if (err < 0) goto out; if (dir >= XFRM_POLICY_MAX) { NL_SET_ERR_MSG(extack, "Invalid policy direction"); err = -EINVAL; goto out; } /* Stage 1 - find policy */ pol = xfrm_migrate_policy_find(sel, dir, type, net, if_id); if (IS_ERR_OR_NULL(pol)) { NL_SET_ERR_MSG(extack, "Target policy not found"); err = IS_ERR(pol) ? PTR_ERR(pol) : -ENOENT; goto out; } /* Stage 2 - find and update state(s) */ for (i = 0, mp = m; i < num_migrate; i++, mp++) { if ((x = xfrm_migrate_state_find(mp, net, if_id))) { x_cur[nx_cur] = x; nx_cur++; mp->encap = encap; mp->xuo = xuo; xfrm_migrate_copy_old(x, mp); xc = xfrm_state_migrate(x, mp, net, extack); if (xc) { x_new[nx_new] = xc; nx_new++; } else { err = -ENODATA; goto restore_state; } } } /* Stage 3 - update policy */ err = xfrm_policy_migrate(pol, m, num_migrate, extack); if (err < 0) goto restore_state; /* Stage 4 - delete old state(s) */ if (nx_cur) { xfrm_states_put(x_cur, nx_cur); xfrm_states_delete(x_cur, nx_cur); } /* Stage 5 - announce */ km_migrate(sel, dir, type, m, num_migrate, k, net, encap); xfrm_pol_put(pol); return 0; out: return err; restore_state: if (pol) xfrm_pol_put(pol); if (nx_cur) xfrm_states_put(x_cur, nx_cur); if (nx_new) xfrm_states_delete(x_new, nx_new); return err; } EXPORT_SYMBOL(xfrm_migrate); #endif |
| 83 1068 1069 1070 110 120 1058 4 860 19 19 19 19 19 19 19 19 19 1051 865 173 21 1042 7 1052 1056 1053 1054 1 101 2 5 107 86 992 1056 1057 110 125 22 14 90 91 3 101 23 123 969 973 623 161 457 18 6 14 463 624 618 622 618 622 622 621 479 73 73 73 73 90 73 18 37 37 37 36 37 37 33 25 37 42 43 43 7 39 43 43 43 72 73 30 44 44 25 39 3 37 32 35 4 32 31 11 3 37 43 11 246 57 193 14 463 460 462 462 7 156 60 18 271 56 2 1 1 34 7 21 6 12 8 395 8 443 1 10 451 442 50 422 50 45 438 442 54 395 1 135 335 439 437 1 438 211 10 437 380 66 329 135 86 1 6 6 1 5 70 70 68 68 70 66 12 300 163 5 28 28 26 2 432 430 1 312 146 146 401 32 1 273 14 51 248 280 422 1 422 422 44 25 277 399 117 310 140 4 127 292 423 423 310 139 421 423 421 313 15 130 15 226 422 366 126 221 222 62 40 40 229 18 22 200 21 37 4 29 4 33 33 33 16 21 21 10 11 20 1 18 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 | // SPDX-License-Identifier: GPL-2.0-only /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * The Internet Protocol (IP) output module. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Donald Becker, <becker@super.org> * Alan Cox, <Alan.Cox@linux.org> * Richard Underwood * Stefan Becker, <stefanb@yello.ping.de> * Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Hirokazu Takahashi, <taka@valinux.co.jp> * * See ip_input.c for original log * * Fixes: * Alan Cox : Missing nonblock feature in ip_build_xmit. * Mike Kilburn : htons() missing in ip_build_xmit. * Bradford Johnson: Fix faulty handling of some frames when * no route is found. * Alexander Demenshin: Missing sk/skb free in ip_queue_xmit * (in case if packet not accepted by * output firewall rules) * Mike McLagan : Routing by source * Alexey Kuznetsov: use new route cache * Andi Kleen: Fix broken PMTU recovery and remove * some redundant tests. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Andi Kleen : Replace ip_reply with ip_send_reply. * Andi Kleen : Split fast and slow ip_build_xmit path * for decreased register pressure on x86 * and more readability. * Marc Boucher : When call_out_firewall returns FW_QUEUE, * silently drop skb instead of failing with -EPERM. * Detlev Wengorz : Copy protocol for fragments. * Hirokazu Takahashi: HW checksumming for outgoing UDP * datagrams. * Hirokazu Takahashi: sendfile() on UDP works now. */ #include <linux/uaccess.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/highmem.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/init.h> #include <net/flow.h> #include <net/snmp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/xfrm.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/arp.h> #include <net/icmp.h> #include <net/checksum.h> #include <net/gso.h> #include <net/inetpeer.h> #include <net/lwtunnel.h> #include <net/inet_dscp.h> #include <linux/bpf-cgroup.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> #include <linux/netlink.h> #include <linux/tcp.h> #include <net/psp.h> static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, int (*output)(struct net *, struct sock *, struct sk_buff *)); /* Generate a checksum for an outgoing IP datagram. */ void ip_send_check(struct iphdr *iph) { iph->check = 0; iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } EXPORT_SYMBOL(ip_send_check); int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); IP_INC_STATS(net, IPSTATS_MIB_OUTREQUESTS); iph_set_totlen(iph, skb->len); ip_send_check(iph); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip_out(sk, skb); if (unlikely(!skb)) return 0; skb->protocol = htons(ETH_P_IP); return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst_dev(skb), dst_output); } int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = __ip_local_out(net, sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } EXPORT_SYMBOL_GPL(ip_local_out); static inline int ip_select_ttl(const struct inet_sock *inet, const struct dst_entry *dst) { int ttl = READ_ONCE(inet->uc_ttl); if (ttl < 0) ttl = ip4_dst_hoplimit(dst); return ttl; } /* * Add an ip header to a skbuff and send it out. * */ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt, u8 tos) { const struct inet_sock *inet = inet_sk(sk); struct rtable *rt = skb_rtable(skb); struct net *net = sock_net(sk); struct iphdr *iph; /* Build the IP header. */ skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = tos; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; /* Do not bother generating IPID for small packets (eg SYNACK) */ if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) { iph->frag_off = htons(IP_DF); iph->id = 0; } else { iph->frag_off = 0; /* TCP packets here are SYNACK with fat IPv4/TCP options. * Avoid using the hashed IP ident generator. */ if (sk->sk_protocol == IPPROTO_TCP) iph->id = (__force __be16)get_random_u16(); else __ip_select_ident(net, iph, 1); } if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; ip_options_build(skb, &opt->opt, daddr, rt); } skb->priority = READ_ONCE(sk->sk_priority); if (!skb->mark) skb->mark = READ_ONCE(sk->sk_mark); /* Send it out. */ return ip_local_out(net, skb->sk, skb); } static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = dst_rtable(dst); struct net_device *dev = dst_dev(dst); unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len); } else if (rt->rt_type == RTN_BROADCAST) IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len); /* OUTOCTETS should be counted after fragment */ IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); if (res != LWTUNNEL_XMIT_CONTINUE) return res; } rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int res; sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ res = neigh_output(neigh, skb, is_v6gw); rcu_read_unlock(); return res; } rcu_read_unlock(); net_dbg_ratelimited("%s: No header cache and no neighbour!\n", __func__); kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL); return PTR_ERR(neigh); } static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { struct sk_buff *segs, *nskb; netdev_features_t features; int ret = 0; /* common case: seglen is <= mtu */ if (skb_gso_validate_network_len(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length exceeds the egress MTU. * * This can happen in several cases: * - Forwarding of a TCP GRO skb, when DF flag is not set. * - Forwarding of an skb that arrived on a virtualization interface * (virtio-net/vhost/tap) with TSO/GSO size set by other network * stack. * - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an * interface with a smaller MTU. * - Arriving GRO skb (or GSO skb in a virtualized environment) that is * bridged to a NETIF_F_TSO tunnel stacked over an interface with an * insufficient MTU. */ features = netif_skb_features(skb); BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); return -ENOMEM; } consume_skb(skb); skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); err = ip_fragment(net, sk, segs, mtu, ip_finish_output2); if (err && ret == 0) ret = err; } return ret; } static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(net, sk, skb); } #endif mtu = ip_skb_dst_mtu(sk, skb); if (skb_is_gso(skb)) return ip_finish_output_gso(net, sk, skb, mtu); if (skb->len > mtu || IPCB(skb)->frag_max_size) return ip_fragment(net, sk, skb, mtu, ip_finish_output2); return ip_finish_output2(net, sk, skb); } static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { int ret; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_SUCCESS: return __ip_finish_output(net, sk, skb); case NET_XMIT_CN: return __ip_finish_output(net, sk, skb) ? : ret; default: kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); return ret; } } static int ip_mc_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *new_rt; bool do_cn = false; int ret, err; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_CN: do_cn = true; fallthrough; case NET_XMIT_SUCCESS: break; default: kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); return ret; } /* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting * this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten, * see ipv4_pktinfo_prepare(). */ new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb)); if (new_rt) { new_rt->rt_iif = 0; skb_dst_drop(skb); skb_dst_set(skb, &new_rt->dst); } err = dev_loopback_xmit(net, sk, skb); return (do_cn && err) ? ret : err; } int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; /* * If the indicated interface is up and running, send the packet. */ skb->dev = dev; skb->protocol = htons(ETH_P_IP); /* * Multicasts are looped back for other local users */ if (rt->rt_flags&RTCF_MULTICAST) { if (sk_mc_loop(sk) #ifdef CONFIG_IP_MROUTE /* Small optimization: do not loopback not local frames, which returned after forwarding; they will be dropped by ip_mr_input in any case. Note, that local frames are looped back to be delivered to local recipients. This check is duplicated in ip_mr_input at the moment. */ && ((rt->rt_flags & RTCF_LOCAL) || !(IPCB(skb)->flags & IPSKB_FORWARDED)) #endif ) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, ip_mc_finish_output); } /* Multicasts with ttl 0 must not go beyond the host */ if (ip_hdr(skb)->ttl == 0) { kfree_skb(skb); return 0; } } if (rt->rt_flags&RTCF_BROADCAST) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, ip_mc_finish_output); } return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev, *indev = skb->dev; int ret_val; rcu_read_lock(); dev = skb_dst_dev_rcu(skb); skb->dev = dev; skb->protocol = htons(ETH_P_IP); ret_val = NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, indev, dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); rcu_read_unlock(); return ret_val; } EXPORT_SYMBOL(ip_output); /* * copy saddr and daddr, possibly using 64bit load/stores * Equivalent to : * iph->saddr = fl4->saddr; * iph->daddr = fl4->daddr; */ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) { BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) != offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr)); iph->saddr = fl4->saddr; iph->daddr = fl4->daddr; } /* Note: skb->sk can be different from sk, in case of tunnels */ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, __u8 tos) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options_rcu *inet_opt; struct flowi4 *fl4; struct rtable *rt; struct iphdr *iph; int res; /* Skip all of this if the packet is already routed, * f.e. by something like SCTP. */ rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); fl4 = &fl->u.ip4; rt = skb_rtable(skb); if (rt) goto packet_routed; /* Make sure we can route this packet. */ rt = dst_rtable(__sk_dst_check(sk, 0)); if (!rt) { inet_sk_init_flowi4(inet, fl4); /* sctp_v4_xmit() uses its own DSCP value */ fl4->flowi4_dscp = inet_dsfield_to_dscp(tos); /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; sk_setup_caps(sk, &rt->dst); } skb_dst_set_noref(skb, &rt->dst); packet_routed: if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway) goto no_route; /* OK, we know where to send it, allocate and build IP header. */ skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff)); if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); /* Transport layer set skb->h.foo itself. */ if (inet_opt && inet_opt->opt.optlen) { iph->ihl += inet_opt->opt.optlen >> 2; ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt); } ip_select_ident_segs(net, skb, sk, skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); res = ip_local_out(net, sk, skb); rcu_read_unlock(); return res; no_route: rcu_read_unlock(); IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); kfree_skb_reason(skb, SKB_DROP_REASON_IP_OUTNOROUTES); return -EHOSTUNREACH; } EXPORT_SYMBOL(__ip_queue_xmit); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) { return __ip_queue_xmit(sk, skb, fl, READ_ONCE(inet_sk(sk)->tos)); } EXPORT_SYMBOL(ip_queue_xmit); static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) { to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; to->skb_iif = from->skb_iif; skb_dst_drop(to); skb_dst_copy(to, from); to->dev = from->dev; to->mark = from->mark; skb_copy_hash(to, from); #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif nf_copy(to, from); skb_ext_copy(to, from); #if IS_ENABLED(CONFIG_IP_VS) to->ipvs_property = from->ipvs_property; #endif skb_copy_secmark(to, from); } static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph = ip_hdr(skb); if ((iph->frag_off & htons(IP_DF)) == 0) return ip_do_fragment(net, sk, skb, output); if (unlikely(!skb->ignore_df || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); kfree_skb(skb); return -EMSGSIZE; } return ip_do_fragment(net, sk, skb, output); } void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, unsigned int hlen, struct ip_fraglist_iter *iter) { unsigned int first_len = skb_pagelen(skb); iter->frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); iter->offset = 0; iter->iph = iph; iter->hlen = hlen; skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; iph->tot_len = htons(first_len); iph->frag_off = htons(IP_MF); ip_send_check(iph); } EXPORT_SYMBOL(ip_fraglist_init); void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) { unsigned int hlen = iter->hlen; struct iphdr *iph = iter->iph; struct sk_buff *frag; frag = iter->frag; frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), iph, hlen); iter->iph = ip_hdr(frag); iph = iter->iph; iph->tot_len = htons(frag->len); ip_copy_metadata(frag, skb); iter->offset += skb->len - hlen; iph->frag_off = htons(iter->offset >> 3); if (frag->next) iph->frag_off |= htons(IP_MF); /* Ready, complete checksum */ ip_send_check(iph); } EXPORT_SYMBOL(ip_fraglist_prepare); void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs, unsigned int mtu, bool DF, struct ip_frag_state *state) { struct iphdr *iph = ip_hdr(skb); state->DF = DF; state->hlen = hlen; state->ll_rs = ll_rs; state->mtu = mtu; state->left = skb->len - hlen; /* Space per frame */ state->ptr = hlen; /* Where to start from */ state->offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3; state->not_last_frag = iph->frag_off & htons(IP_MF); } EXPORT_SYMBOL(ip_frag_init); static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, bool first_frag) { /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; /* ANK: dirty, but effective trick. Upgrade options only if * the segment to be fragmented was THE FIRST (otherwise, * options are already fixed) and make it ONCE * on the initial skb, so that all the following fragments * will inherit fixed options. */ if (first_frag) ip_options_fragment(from); } struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state) { unsigned int len = state->left; struct sk_buff *skb2; struct iphdr *iph; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > state->mtu) len = state->mtu; /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < state->left) { len &= ~7; } /* Allocate buffer */ skb2 = alloc_skb(len + state->hlen + state->ll_rs, GFP_ATOMIC); if (!skb2) return ERR_PTR(-ENOMEM); /* * Set up data on packet */ ip_copy_metadata(skb2, skb); skb_reserve(skb2, state->ll_rs); skb_put(skb2, len + state->hlen); skb_reset_network_header(skb2); skb2->transport_header = skb2->network_header + state->hlen; /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(skb2, skb->sk); /* * Copy the packet header into the new buffer. */ skb_copy_from_linear_data(skb, skb_network_header(skb2), state->hlen); /* * Copy a block of the IP datagram. */ if (skb_copy_bits(skb, state->ptr, skb_transport_header(skb2), len)) BUG(); state->left -= len; /* * Fill in the new header fields. */ iph = ip_hdr(skb2); iph->frag_off = htons((state->offset >> 3)); if (state->DF) iph->frag_off |= htons(IP_DF); /* * Added AC : If we are fragmenting a fragment that's not the * last fragment then keep MF on each bit */ if (state->left > 0 || state->not_last_frag) iph->frag_off |= htons(IP_MF); state->ptr += len; state->offset += len; iph->tot_len = htons(len + state->hlen); ip_send_check(iph); return skb2; } EXPORT_SYMBOL(ip_frag_next); /* * This IP datagram is too large to be sent in one piece. Break it up into * smaller pieces (each of size equal to IP header plus * a block of the data of the original IP data part) that will yet fit in a * single device frame, and queue such a frame for sending. */ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph; struct sk_buff *skb2; u8 tstamp_type = skb->tstamp_type; struct rtable *rt = skb_rtable(skb); unsigned int mtu, hlen, ll_rs; struct ip_fraglist_iter iter; ktime_t tstamp = skb->tstamp; struct ip_frag_state state; int err = 0; /* for offloaded checksums cleanup checksum before fragmentation */ if (skb->ip_summed == CHECKSUM_PARTIAL && (err = skb_checksum_help(skb))) goto fail; /* * Point into the IP datagram header. */ iph = ip_hdr(skb); mtu = ip_skb_dst_mtu(sk, skb); if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu) mtu = IPCB(skb)->frag_max_size; /* * Setup starting values. */ hlen = iph->ihl * 4; mtu = mtu - hlen; /* Size of data space */ IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE; ll_rs = LL_RESERVED_SPACE(rt->dst.dev); /* When frag_list is given, use it. First, check its validity: * some transformers could create wrong frag_list or break existing * one, it is not prohibited. In this case fall back to copying. * * LATER: this step can be merged to real generation of fragments, * we can switch to copy when see the first bad fragment. */ if (skb_has_frag_list(skb)) { struct sk_buff *frag, *frag2; unsigned int first_len = skb_pagelen(skb); if (first_len - hlen > mtu || ((first_len - hlen) & 7) || ip_is_fragment(iph) || skb_cloned(skb) || skb_headroom(skb) < ll_rs) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen + ll_rs) goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } skb->truesize -= frag->truesize; } /* Everything is OK. Generate! */ ip_fraglist_init(skb, iph, hlen, &iter); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) { bool first_frag = (iter.offset == 0); IPCB(iter.frag)->flags = IPCB(skb)->flags; ip_fraglist_prepare(skb, &iter); if (first_frag && IPCB(skb)->opt.optlen) { /* ipcb->opt is not populated for frags * coming from __ip_make_skb(), * ip_options_fragment() needs optlen */ IPCB(iter.frag)->opt.optlen = IPCB(skb)->opt.optlen; ip_options_fragment(iter.frag); ip_send_check(iter.iph); } } skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, skb); if (!err) IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); if (err || !iter.frag) break; skb = ip_fraglist_next(&iter); } if (err == 0) { IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return 0; } kfree_skb_list(iter.frag); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; slow_path_clean: skb_walk_frags(skb, frag2) { if (frag2 == frag) break; frag2->sk = NULL; frag2->destructor = NULL; skb->truesize += frag2->truesize; } } slow_path: /* * Fragment the datagram. */ ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU, &state); /* * Keep copying data until we run out. */ while (state.left > 0) { bool first_frag = (state.offset == 0); skb2 = ip_frag_next(skb, &state); if (IS_ERR(skb2)) { err = PTR_ERR(skb2); goto fail; } ip_frag_ipcb(skb, skb2, first_frag); /* * Put this fragment into the sending queue. */ skb_set_delivery_time(skb2, tstamp, tstamp_type); err = output(net, sk, skb2); if (err) goto fail; IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); } consume_skb(skb); IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return err; fail: kfree_skb(skb); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; } EXPORT_SYMBOL(ip_do_fragment); int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct msghdr *msg = from; if (skb->ip_summed == CHECKSUM_PARTIAL) { if (!copy_from_iter_full(to, len, &msg->msg_iter)) return -EFAULT; } else { __wsum csum = 0; if (!csum_and_copy_from_iter_full(to, len, &csum, &msg->msg_iter)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, odd); } return 0; } EXPORT_SYMBOL(ip_generic_getfrag); static int __ip_append_data(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; struct ip_options *opt = cork->opt; int hh_len; int exthdrlen; int mtu; int copy; int err; int offset = 0; bool zc = false; unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = dst_rtable(cork->dst); bool paged, hold_tskey = false, extra_uref = false; unsigned int wmem_alloc_delta = 0; u32 tskey = 0; skb = skb_peek_tail(queue); exthdrlen = !skb ? rt->dst.header_len : 0; mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu - (opt ? opt->optlen : 0)); return -EMSGSIZE; } /* * transhdrlen > 0 means that this is the first fragment and we wish * it won't be fragmented in the future. */ if (transhdrlen && length + fragheaderlen <= mtu && rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) && (!(flags & MSG_MORE) || cork->gso_size) && (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM))) csummode = CHECKSUM_PARTIAL; if ((flags & MSG_ZEROCOPY) && length) { struct msghdr *msg = from; if (getfrag == ip_generic_getfrag && msg->msg_ubuf) { if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb)) return -EINVAL; /* Leave uarg NULL if can't zerocopy, callers should * be able to handle it. */ if ((rt->dst.dev->features & NETIF_F_SG) && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; uarg = msg->msg_ubuf; } } else if (sock_flag(sk, SOCK_ZEROCOPY)) { uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb), false); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ if (rt->dst.dev->features & NETIF_F_SG && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; } else { uarg_to_msgzc(uarg)->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); } } } else if ((flags & MSG_SPLICE_PAGES) && length) { if (inet_test_bit(HDRINCL, sk)) return -EPERM; if (rt->dst.dev->features & NETIF_F_SG && getfrag == ip_generic_getfrag) /* We need an empty buffer to attach stuff to */ paged = true; else flags &= ~MSG_SPLICE_PAGES; } cork->length += length; if (cork->tx_flags & SKBTX_ANY_TSTAMP && READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) { if (cork->flags & IPCORK_TS_OPT_ID) { tskey = cork->ts_opt_id; } else { tskey = atomic_inc_return(&sk->sk_tskey) - 1; hold_tskey = true; } } /* So, what's going on in the loop below? * * We use calculated fragment length to generate chained skb, * each of segments is IP fragment ready for sending to network after * adding appropriate IP header. */ if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = mtu - skb->len; if (copy < length) copy = maxfraglen - skb->len; if (copy <= 0) { char *data; unsigned int datalen; unsigned int fraglen; unsigned int fraggap; unsigned int alloclen, alloc_extra; unsigned int pagedlen; struct sk_buff *skb_prev; alloc_new_skb: skb_prev = skb; if (skb_prev) fraggap = skb_prev->len - maxfraglen; else fraggap = 0; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > mtu - fragheaderlen) datalen = maxfraglen - fragheaderlen; fraglen = datalen + fragheaderlen; pagedlen = 0; alloc_extra = hh_len + 15; alloc_extra += exthdrlen; /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, * because we have no idea what fragment will be * the last. */ if (datalen == length + fraggap) alloc_extra += rt->dst.trailer_len; if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else if (!paged && (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = fragheaderlen + transhdrlen + fraggap; pagedlen = datalen - transhdrlen - fraggap; } alloclen += alloc_extra; if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; } if (!skb) goto error; /* * Fill in the control structures */ skb->ip_summed = csummode; skb->csum = 0; skb_reserve(skb, hh_len); /* * Find where to start putting bytes. */ data = skb_put(skb, fraglen + exthdrlen - pagedlen); skb_set_network_header(skb, exthdrlen); skb->transport_header = (skb->network_header + fragheaderlen); data += fragheaderlen + exthdrlen; if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, data + transhdrlen, fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } copy = datalen - transhdrlen - fraggap - pagedlen; if (copy > 0 && INDIRECT_CALL_1(getfrag, ip_generic_getfrag, from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } else if (flags & MSG_SPLICE_PAGES) { copy = 0; } offset += copy; length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; csummode = CHECKSUM_NONE; /* only the initial fragment is time stamped */ skb_shinfo(skb)->tx_flags = cork->tx_flags; cork->tx_flags = 0; skb_shinfo(skb)->tskey = tskey; tskey = 0; skb_zcopy_set(skb, uarg, &extra_uref); if ((flags & MSG_CONFIRM) && !skb_prev) skb_set_dst_pending_confirm(skb, 1); /* * Put the packet on the pending queue. */ if (!skb->destructor) { skb->destructor = sock_wfree; skb->sk = sk; wmem_alloc_delta += skb->truesize; } __skb_queue_tail(queue, skb); continue; } if (copy > length) copy = length; if (!(rt->dst.dev->features&NETIF_F_SG) && skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, from, skb_put(skb, copy), offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } } else if (flags & MSG_SPLICE_PAGES) { struct msghdr *msg = from; err = -EIO; if (WARN_ON_ONCE(copy > msg->msg_iter.count)) goto error; err = skb_splice_from_iter(skb, &msg->msg_iter, copy); if (err < 0) goto error; copy = err; if (!(flags & MSG_NO_SHARED_FRAGS)) skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; wmem_alloc_delta += copy; } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; skb_zcopy_downgrade_managed(skb); if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; if (i == MAX_SKB_FRAGS) goto error; __skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, 0); skb_shinfo(skb)->nr_frags = ++i; get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; pfrag->offset += copy; skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb_len_add(skb, copy); wmem_alloc_delta += copy; } else { err = skb_zerocopy_iter_dgram(skb, from, copy); if (err < 0) goto error; } offset += copy; length -= copy; } if (wmem_alloc_delta) refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return 0; error_efault: err = -EFAULT; error: net_zcopy_put_abort(uarg, extra_uref); cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); if (hold_tskey) atomic_dec(&sk->sk_tskey); return err; } static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, struct ipcm_cookie *ipc, struct rtable **rtp) { struct ip_options_rcu *opt; struct rtable *rt; rt = *rtp; if (unlikely(!rt)) return -EFAULT; cork->fragsize = ip_sk_use_pmtu(sk) ? dst4_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); if (!inetdev_valid_mtu(cork->fragsize)) return -ENETUNREACH; /* * setup for corking. */ opt = ipc->opt; if (opt) { if (!cork->opt) { cork->opt = kmalloc(sizeof(struct ip_options) + 40, sk->sk_allocation); if (unlikely(!cork->opt)) return -ENOBUFS; } memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen); cork->flags |= IPCORK_OPT; cork->addr = ipc->addr; } cork->gso_size = ipc->gso_size; cork->dst = &rt->dst; /* We stole this route, caller should not release it. */ *rtp = NULL; cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; cork->mark = ipc->sockc.mark; cork->priority = ipc->sockc.priority; cork->transmit_time = ipc->sockc.transmit_time; cork->tx_flags = 0; sock_tx_timestamp(sk, &ipc->sockc, &cork->tx_flags); if (ipc->sockc.tsflags & SOCKCM_FLAG_TS_OPT_ID) { cork->flags |= IPCORK_TS_OPT_ID; cork->ts_opt_id = ipc->sockc.ts_opt_id; } return 0; } /* * ip_append_data() can make one large IP datagram from many pieces of * data. Each piece will be held on the socket until * ip_push_pending_frames() is called. Each piece can be a page or * non-page data. * * Not only UDP, other transport protocols - e.g. raw sockets - can use * this interface potentially. * * LATER: length must be adjusted by pad at tail, when it is required. */ int ip_append_data(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); int err; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) { err = ip_setup_cork(sk, &inet->cork.base, ipc, rtp); if (err) return err; } else { transhdrlen = 0; } return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base, sk_page_frag(sk), getfrag, from, length, transhdrlen, flags); } static void ip_cork_release(struct inet_cork *cork) { cork->flags &= ~IPCORK_OPT; kfree(cork->opt); cork->opt = NULL; dst_release(cork->dst); cork->dst = NULL; } /* * Combined all pending IP fragments on the socket as one IP datagram * and push them out. */ struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork) { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options *opt = NULL; struct rtable *rt = dst_rtable(cork->dst); struct iphdr *iph; u8 pmtudisc, ttl; __be16 df = 0; skb = __skb_dequeue(queue); if (!skb) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); /* move skb->data to ip header from ext header */ if (skb->data < skb_network_header(skb)) __skb_pull(skb, skb_network_offset(skb)); while ((tmp_skb = __skb_dequeue(queue)) != NULL) { __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } /* Unless user demanded real pmtu discovery (IP_PMTUDISC_DO), we allow * to fragment the frame generated here. No matter, what transforms * how transforms change size of the packet, it will come out. */ skb->ignore_df = ip_sk_ignore_df(sk); /* DF bit is set when we want to see DF on outgoing frames. * If ignore_df is set too, we still allow to fragment this frame * locally. */ pmtudisc = READ_ONCE(inet->pmtudisc); if (pmtudisc == IP_PMTUDISC_DO || pmtudisc == IP_PMTUDISC_PROBE || (skb->len <= dst4_mtu(&rt->dst) && ip_dont_fragment(sk, &rt->dst))) df = htons(IP_DF); if (cork->flags & IPCORK_OPT) opt = cork->opt; if (cork->ttl != 0) ttl = cork->ttl; else if (rt->rt_type == RTN_MULTICAST) ttl = READ_ONCE(inet->mc_ttl); else ttl = ip_select_ttl(inet, &rt->dst); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = (cork->tos != -1) ? cork->tos : READ_ONCE(inet->tos); iph->frag_off = df; iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); ip_select_ident(net, skb, sk); if (opt) { iph->ihl += opt->optlen >> 2; ip_options_build(skb, opt, cork->addr, rt); } skb->priority = cork->priority; skb->mark = cork->mark; if (sk_is_tcp(sk)) skb_set_delivery_time(skb, cork->transmit_time, SKB_CLOCK_MONOTONIC); else skb_set_delivery_type_by_clockid(skb, cork->transmit_time, sk->sk_clockid); /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount */ cork->dst = NULL; skb_dst_set(skb, &rt->dst); if (iph->protocol == IPPROTO_ICMP) { u8 icmp_type; /* For such sockets, transhdrlen is zero when do ip_append_data(), * so icmphdr does not in skb linear region and can not get icmp_type * by icmp_hdr(skb)->type. */ if (sk->sk_type == SOCK_RAW && !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH)) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; icmp_out_count(net, icmp_type); } ip_cork_release(cork); out: return skb; } int ip_send_skb(struct net *net, struct sk_buff *skb) { int err; err = ip_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); if (err) IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); } return err; } int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4) { struct sk_buff *skb; skb = ip_finish_skb(sk, fl4); if (!skb) return 0; /* Netfilter gets whole the not fragmented skb. */ return ip_send_skb(sock_net(sk), skb); } /* * Throw away all pending data on the socket. */ static void __ip_flush_pending_frames(struct sock *sk, struct sk_buff_head *queue, struct inet_cork *cork) { struct sk_buff *skb; while ((skb = __skb_dequeue_tail(queue)) != NULL) kfree_skb(skb); ip_cork_release(cork); } void ip_flush_pending_frames(struct sock *sk) { __ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base); } struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, struct inet_cork *cork, unsigned int flags) { struct sk_buff_head queue; int err; if (flags & MSG_PROBE) return NULL; __skb_queue_head_init(&queue); cork->flags = 0; cork->addr = 0; cork->opt = NULL; err = ip_setup_cork(sk, cork, ipc, rtp); if (err) return ERR_PTR(err); err = __ip_append_data(sk, fl4, &queue, cork, ¤t->task_frag, getfrag, from, length, transhdrlen, flags); if (err) { __ip_flush_pending_frames(sk, &queue, cork); return ERR_PTR(err); } return __ip_make_skb(sk, fl4, &queue, cork); } /* * Fetch data from kernel space and fill in checksum if needed. */ static int ip_reply_glue_bits(void *dptr, char *to, int offset, int len, int odd, struct sk_buff *skb) { __wsum csum; csum = csum_partial_copy_nocheck(dptr+offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); return 0; } /* * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. */ void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len, u64 transmit_time, u32 txhash) { DEFINE_RAW_FLEX(struct ip_options_rcu, replyopts, opt.__data, IP_OPTIONS_DATA_FIXED_SIZE); struct ipcm_cookie ipc; struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); struct net *net = sock_net(sk); struct sk_buff *nskb; int err; int oif; if (__ip_options_echo(net, &replyopts->opt, skb, sopt)) return; ipcm_init(&ipc); ipc.addr = daddr; ipc.sockc.transmit_time = transmit_time; if (replyopts->opt.optlen) { ipc.opt = replyopts; if (replyopts->opt.srr) daddr = replyopts->opt.faddr; } oif = arg->bound_dev_if; if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) oif = skb->skb_iif; flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark, arg->tos & INET_DSCP_MASK, RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, ip_reply_arg_flowi_flags(arg), daddr, saddr, tcp_hdr(skb)->source, tcp_hdr(skb)->dest, arg->uid); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) return; inet_sk(sk)->tos = arg->tos; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { ip_flush_pending_frames(sk); goto out; } nskb = skb_peek(&sk->sk_write_queue); if (nskb) { if (arg->csumoffset >= 0) *((__sum16 *)skb_transport_header(nskb) + arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; if (orig_sk) { skb_set_owner_edemux(nskb, (struct sock *)orig_sk); psp_reply_set_decrypted(orig_sk, nskb); } if (transmit_time) nskb->tstamp_type = SKB_CLOCK_MONOTONIC; if (txhash) skb_set_hash(nskb, txhash, PKT_HASH_TYPE_L4); ip_push_pending_frames(sk, &fl4); } out: ip_rt_put(rt); } void __init ip_init(void) { ip_rt_init(); inet_initpeers(); #if defined(CONFIG_IP_MULTICAST) igmp_mc_init(); #endif } |
| 10777 603 46 1 9497 4907 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_COUNTER_H #define _LINUX_PERCPU_COUNTER_H /* * A simple "approximate counter" for use in ext2 and ext3 superblocks. * * WARNING: these things are HUGE. 4 kbytes per counter on 32-way P4. */ #include <linux/spinlock.h> #include <linux/smp.h> #include <linux/list.h> #include <linux/threads.h> #include <linux/percpu.h> #include <linux/types.h> /* percpu_counter batch for local add or sub */ #define PERCPU_COUNTER_LOCAL_BATCH INT_MAX #ifdef CONFIG_SMP struct percpu_counter { raw_spinlock_t lock; s64 count; #ifdef CONFIG_HOTPLUG_CPU struct list_head list; /* All percpu_counters are on a list */ #endif s32 __percpu *counters; }; extern int percpu_counter_batch; int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount, gfp_t gfp, u32 nr_counters, struct lock_class_key *key); #define percpu_counter_init_many(fbc, value, gfp, nr_counters) \ ({ \ static struct lock_class_key __key; \ \ __percpu_counter_init_many(fbc, value, gfp, nr_counters,\ &__key); \ }) #define percpu_counter_init(fbc, value, gfp) \ percpu_counter_init_many(fbc, value, gfp, 1) void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters); static inline void percpu_counter_destroy(struct percpu_counter *fbc) { percpu_counter_destroy_many(fbc, 1); } void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); bool __percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount, s32 batch); void percpu_counter_sync(struct percpu_counter *fbc); static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { return __percpu_counter_compare(fbc, rhs, percpu_counter_batch); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } static inline bool percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount) { return __percpu_counter_limited_add(fbc, limit, amount, percpu_counter_batch); } /* * With percpu_counter_add_local() and percpu_counter_sub_local(), counts * are accumulated in local per cpu counter and not in fbc->count until * local count overflows PERCPU_COUNTER_LOCAL_BATCH. This makes counter * write efficient. * But percpu_counter_sum(), instead of percpu_counter_read(), needs to be * used to add up the counts from each CPU to account for all the local * counts. So percpu_counter_add_local() and percpu_counter_sub_local() * should be used when a counter is updated frequently and read rarely. */ static inline void percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_batch(fbc, amount, PERCPU_COUNTER_LOCAL_BATCH); } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { s64 ret = __percpu_counter_sum(fbc); return ret < 0 ? 0 : ret; } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return __percpu_counter_sum(fbc); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * It is possible for the percpu_counter_read() to return a small negative * number for some counter which should never be negative. * */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { /* Prevent reloads of fbc->count */ s64 ret = READ_ONCE(fbc->count); if (ret >= 0) return ret; return 0; } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return (fbc->counters != NULL); } #else /* !CONFIG_SMP */ struct percpu_counter { s64 count; }; static inline int percpu_counter_init_many(struct percpu_counter *fbc, s64 amount, gfp_t gfp, u32 nr_counters) { u32 i; for (i = 0; i < nr_counters; i++) fbc[i].count = amount; return 0; } static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp) { return percpu_counter_init_many(fbc, amount, gfp, 1); } static inline void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters) { } static inline void percpu_counter_destroy(struct percpu_counter *fbc) { } static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { fbc->count = amount; } static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { if (fbc->count > rhs) return 1; else if (fbc->count < rhs) return -1; else return 0; } static inline int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { return percpu_counter_compare(fbc, rhs); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { unsigned long flags; local_irq_save(flags); fbc->count += amount; local_irq_restore(flags); } static inline bool percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount) { unsigned long flags; bool good = false; s64 count; if (amount == 0) return true; local_irq_save(flags); count = fbc->count + amount; if ((amount > 0 && count <= limit) || (amount < 0 && count >= limit)) { fbc->count = count; good = true; } local_irq_restore(flags); return good; } /* non-SMP percpu_counter_add_local is the same with percpu_counter_add */ static inline void percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) { percpu_counter_add(fbc, amount); } static inline void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { percpu_counter_add(fbc, amount); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * percpu_counter is intended to track positive numbers. In the UP case the * number should never be negative. */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { return fbc->count; } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { return percpu_counter_read_positive(fbc); } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return percpu_counter_read(fbc); } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return true; } static inline void percpu_counter_sync(struct percpu_counter *fbc) { } #endif /* CONFIG_SMP */ static inline void percpu_counter_inc(struct percpu_counter *fbc) { percpu_counter_add(fbc, 1); } static inline void percpu_counter_dec(struct percpu_counter *fbc) { percpu_counter_add(fbc, -1); } static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) { percpu_counter_add(fbc, -amount); } static inline void percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_local(fbc, -amount); } #endif /* _LINUX_PERCPU_COUNTER_H */ |
| 9 16 5 16 4 18 16 6 15 15 2 26 27 27 27 6 1 7 16 33 14 1 15 7 14 3 5 21 19 3 19 19 19 18 18 18 12 7 2 5 17 2 1 1 17 1 1 6 3 2 1 4 4 3 1 24 24 24 2 1 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/nospec.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "filetable.h" #include "io_uring.h" #include "tctx.h" #include "sqpoll.h" #include "uring_cmd.h" #include "poll.h" #include "timeout.h" #include "waitid.h" #include "futex.h" #include "cancel.h" #include "wait.h" struct io_cancel { struct file *file; u64 addr; u32 flags; s32 fd; u8 opcode; }; #define CANCEL_FLAGS (IORING_ASYNC_CANCEL_ALL | IORING_ASYNC_CANCEL_FD | \ IORING_ASYNC_CANCEL_ANY | IORING_ASYNC_CANCEL_FD_FIXED | \ IORING_ASYNC_CANCEL_USERDATA | IORING_ASYNC_CANCEL_OP) /* * Returns true if the request matches the criteria outlined by 'cd'. */ bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd) { bool match_user_data = cd->flags & IORING_ASYNC_CANCEL_USERDATA; if (req->ctx != cd->ctx) return false; if (!(cd->flags & (IORING_ASYNC_CANCEL_FD | IORING_ASYNC_CANCEL_OP))) match_user_data = true; if (cd->flags & IORING_ASYNC_CANCEL_ANY) goto check_seq; if (cd->flags & IORING_ASYNC_CANCEL_FD) { if (req->file != cd->file) return false; } if (cd->flags & IORING_ASYNC_CANCEL_OP) { if (req->opcode != cd->opcode) return false; } if (match_user_data && req->cqe.user_data != cd->data) return false; if (cd->flags & IORING_ASYNC_CANCEL_ALL) { check_seq: if (io_cancel_match_sequence(req, cd->seq)) return false; } return true; } static bool io_cancel_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_cancel_data *cd = data; return io_cancel_req_match(req, cd); } static int io_async_cancel_one(struct io_uring_task *tctx, struct io_cancel_data *cd) { enum io_wq_cancel cancel_ret; int ret = 0; bool all; if (!tctx || !tctx->io_wq) return -ENOENT; all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, cd, all); switch (cancel_ret) { case IO_WQ_CANCEL_OK: ret = 0; break; case IO_WQ_CANCEL_RUNNING: ret = -EALREADY; break; case IO_WQ_CANCEL_NOTFOUND: ret = -ENOENT; break; } return ret; } int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, unsigned issue_flags) { struct io_ring_ctx *ctx = cd->ctx; int ret; WARN_ON_ONCE(!io_wq_current_is_worker() && tctx != current->io_uring); ret = io_async_cancel_one(tctx, cd); /* * Fall-through even for -EALREADY, as we may have poll armed * that need unarming. */ if (!ret) return 0; ret = io_poll_cancel(ctx, cd, issue_flags); if (ret != -ENOENT) return ret; ret = io_waitid_cancel(ctx, cd, issue_flags); if (ret != -ENOENT) return ret; ret = io_futex_cancel(ctx, cd, issue_flags); if (ret != -ENOENT) return ret; spin_lock(&ctx->completion_lock); if (!(cd->flags & IORING_ASYNC_CANCEL_FD)) ret = io_timeout_cancel(ctx, cd); spin_unlock(&ctx->completion_lock); return ret; } int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_cancel *cancel = io_kiocb_to_cmd(req, struct io_cancel); if (unlikely(req->flags & REQ_F_BUFFER_SELECT)) return -EINVAL; if (sqe->off || sqe->splice_fd_in) return -EINVAL; cancel->addr = READ_ONCE(sqe->addr); cancel->flags = READ_ONCE(sqe->cancel_flags); if (cancel->flags & ~CANCEL_FLAGS) return -EINVAL; if (cancel->flags & IORING_ASYNC_CANCEL_FD) { if (cancel->flags & IORING_ASYNC_CANCEL_ANY) return -EINVAL; cancel->fd = READ_ONCE(sqe->fd); } if (cancel->flags & IORING_ASYNC_CANCEL_OP) { u32 op; if (cancel->flags & IORING_ASYNC_CANCEL_ANY) return -EINVAL; op = READ_ONCE(sqe->len); if (op >= IORING_OP_LAST) return -EINVAL; cancel->opcode = op; } return 0; } static int __io_async_cancel(struct io_cancel_data *cd, struct io_uring_task *tctx, unsigned int issue_flags) { bool all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); struct io_ring_ctx *ctx = cd->ctx; struct io_tctx_node *node; int ret, nr = 0; do { ret = io_try_cancel(tctx, cd, issue_flags); if (ret == -ENOENT) break; if (!all) return ret; nr++; } while (1); /* slow path, try all io-wq's */ __set_current_state(TASK_RUNNING); io_ring_submit_lock(ctx, issue_flags); mutex_lock(&ctx->tctx_lock); ret = -ENOENT; list_for_each_entry(node, &ctx->tctx_list, ctx_node) { ret = io_async_cancel_one(node->task->io_uring, cd); if (ret != -ENOENT) { if (!all) break; nr++; } } mutex_unlock(&ctx->tctx_lock); io_ring_submit_unlock(ctx, issue_flags); return all ? nr : ret; } int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) { struct io_cancel *cancel = io_kiocb_to_cmd(req, struct io_cancel); struct io_cancel_data cd = { .ctx = req->ctx, .data = cancel->addr, .flags = cancel->flags, .opcode = cancel->opcode, .seq = atomic_inc_return(&req->ctx->cancel_seq), }; struct io_uring_task *tctx = req->tctx; int ret; if (cd.flags & IORING_ASYNC_CANCEL_FD) { if (req->flags & REQ_F_FIXED_FILE || cd.flags & IORING_ASYNC_CANCEL_FD_FIXED) { req->flags |= REQ_F_FIXED_FILE; req->file = io_file_get_fixed(req, cancel->fd, issue_flags); } else { req->file = io_file_get_normal(req, cancel->fd); } if (!req->file) { ret = -EBADF; goto done; } cd.file = req->file; } ret = __io_async_cancel(&cd, tctx, issue_flags); done: if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); return IOU_COMPLETE; } static int __io_sync_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, int fd) { struct io_ring_ctx *ctx = cd->ctx; /* fixed must be grabbed every time since we drop the uring_lock */ if ((cd->flags & IORING_ASYNC_CANCEL_FD) && (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) { struct io_rsrc_node *node; node = io_rsrc_node_lookup(&ctx->file_table.data, fd); if (unlikely(!node)) return -EBADF; cd->file = io_slot_file(node); if (!cd->file) return -EBADF; } return __io_async_cancel(cd, tctx, 0); } int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg) __must_hold(&ctx->uring_lock) { struct io_cancel_data cd = { .ctx = ctx, .seq = atomic_inc_return(&ctx->cancel_seq), }; ktime_t timeout = KTIME_MAX; struct io_uring_sync_cancel_reg sc; struct file *file = NULL; DEFINE_WAIT(wait); int ret, i; if (copy_from_user(&sc, arg, sizeof(sc))) return -EFAULT; if (sc.flags & ~CANCEL_FLAGS) return -EINVAL; for (i = 0; i < ARRAY_SIZE(sc.pad); i++) if (sc.pad[i]) return -EINVAL; for (i = 0; i < ARRAY_SIZE(sc.pad2); i++) if (sc.pad2[i]) return -EINVAL; cd.data = sc.addr; cd.flags = sc.flags; cd.opcode = sc.opcode; /* we can grab a normal file descriptor upfront */ if ((cd.flags & IORING_ASYNC_CANCEL_FD) && !(cd.flags & IORING_ASYNC_CANCEL_FD_FIXED)) { file = fget(sc.fd); if (!file) return -EBADF; cd.file = file; } ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); /* found something, done! */ if (ret != -EALREADY) goto out; if (sc.timeout.tv_sec != -1UL || sc.timeout.tv_nsec != -1UL) { struct timespec64 ts = { .tv_sec = sc.timeout.tv_sec, .tv_nsec = sc.timeout.tv_nsec }; timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); } /* * Keep looking until we get -ENOENT. we'll get woken everytime * every time a request completes and will retry the cancelation. */ do { cd.seq = atomic_inc_return(&ctx->cancel_seq); prepare_to_wait(&ctx->cq_wait, &wait, TASK_INTERRUPTIBLE); ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); mutex_unlock(&ctx->uring_lock); if (ret != -EALREADY) break; ret = io_run_task_work_sig(ctx); if (ret < 0) break; ret = schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS); if (!ret) { ret = -ETIME; break; } mutex_lock(&ctx->uring_lock); } while (1); finish_wait(&ctx->cq_wait, &wait); mutex_lock(&ctx->uring_lock); if (ret == -ENOENT || ret > 0) ret = 0; out: if (file) fput(file); return ret; } bool io_cancel_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx, struct hlist_head *list, bool cancel_all, bool (*cancel)(struct io_kiocb *)) { struct hlist_node *tmp; struct io_kiocb *req; bool found = false; lockdep_assert_held(&ctx->uring_lock); hlist_for_each_entry_safe(req, tmp, list, hash_node) { if (!io_match_task_safe(req, tctx, cancel_all)) continue; hlist_del_init(&req->hash_node); if (cancel(req)) found = true; } return found; } int io_cancel_remove(struct io_ring_ctx *ctx, struct io_cancel_data *cd, unsigned int issue_flags, struct hlist_head *list, bool (*cancel)(struct io_kiocb *)) { struct hlist_node *tmp; struct io_kiocb *req; int nr = 0; io_ring_submit_lock(ctx, issue_flags); hlist_for_each_entry_safe(req, tmp, list, hash_node) { if (!io_cancel_req_match(req, cd)) continue; if (cancel(req)) nr++; if (!(cd->flags & IORING_ASYNC_CANCEL_ALL)) break; } io_ring_submit_unlock(ctx, issue_flags); return nr ?: -ENOENT; } static bool io_match_linked(struct io_kiocb *head) { struct io_kiocb *req; io_for_each_link(req, head) { if (req->flags & REQ_F_INFLIGHT) return true; } return false; } /* * As io_match_task() but protected against racing with linked timeouts. * User must not hold timeout_lock. */ bool io_match_task_safe(struct io_kiocb *head, struct io_uring_task *tctx, bool cancel_all) { bool matched; if (tctx && head->tctx != tctx) return false; if (cancel_all) return true; if (head->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = head->ctx; /* protect against races with linked timeouts */ raw_spin_lock_irq(&ctx->timeout_lock); matched = io_match_linked(head); raw_spin_unlock_irq(&ctx->timeout_lock); } else { matched = io_match_linked(head); } return matched; } void __io_uring_cancel(bool cancel_all) { io_uring_unreg_ringfd(); io_uring_cancel_generic(cancel_all, NULL); } struct io_task_cancel { struct io_uring_task *tctx; bool all; }; static bool io_cancel_task_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_task_cancel *cancel = data; return io_match_task_safe(req, cancel->tctx, cancel->all); } static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx, struct io_uring_task *tctx, bool cancel_all) { struct io_defer_entry *de; LIST_HEAD(list); list_for_each_entry_reverse(de, &ctx->defer_list, list) { if (io_match_task_safe(de->req, tctx, cancel_all)) { list_cut_position(&list, &ctx->defer_list, &de->list); break; } } if (list_empty(&list)) return false; while (!list_empty(&list)) { de = list_first_entry(&list, struct io_defer_entry, list); list_del_init(&de->list); ctx->nr_drained -= io_linked_nr(de->req); io_req_task_queue_fail(de->req, -ECANCELED); kfree(de); } return true; } __cold bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); return req->ctx == data; } static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) { struct io_tctx_node *node; enum io_wq_cancel cret; bool ret = false; mutex_lock(&ctx->uring_lock); mutex_lock(&ctx->tctx_lock); list_for_each_entry(node, &ctx->tctx_list, ctx_node) { struct io_uring_task *tctx = node->task->io_uring; /* * io_wq will stay alive while we hold uring_lock, because it's * killed after ctx nodes, which requires to take the lock. */ if (!tctx || !tctx->io_wq) continue; cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true); ret |= (cret != IO_WQ_CANCEL_NOTFOUND); } mutex_unlock(&ctx->tctx_lock); mutex_unlock(&ctx->uring_lock); return ret; } __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct io_uring_task *tctx, bool cancel_all, bool is_sqpoll_thread) { struct io_task_cancel cancel = { .tctx = tctx, .all = cancel_all, }; enum io_wq_cancel cret; bool ret = false; /* set it so io_req_local_work_add() would wake us up */ if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) { atomic_set(&ctx->cq_wait_nr, 1); smp_mb(); } /* failed during ring init, it couldn't have issued any requests */ if (!ctx->rings) return false; if (!tctx) { ret |= io_uring_try_cancel_iowq(ctx); } else if (tctx->io_wq) { /* * Cancels requests of all rings, not only @ctx, but * it's fine as the task is in exit/exec. */ cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb, &cancel, true); ret |= (cret != IO_WQ_CANCEL_NOTFOUND); } /* SQPOLL thread does its own polling */ if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) || is_sqpoll_thread) { while (!list_empty(&ctx->iopoll_list)) { io_iopoll_try_reap_events(ctx); ret = true; cond_resched(); } } if ((ctx->flags & IORING_SETUP_DEFER_TASKRUN) && io_allowed_defer_tw_run(ctx)) ret |= io_run_local_work(ctx, INT_MAX, INT_MAX) > 0; mutex_lock(&ctx->uring_lock); ret |= io_cancel_defer_files(ctx, tctx, cancel_all); ret |= io_poll_remove_all(ctx, tctx, cancel_all); ret |= io_waitid_remove_all(ctx, tctx, cancel_all); ret |= io_futex_remove_all(ctx, tctx, cancel_all); ret |= io_uring_try_cancel_uring_cmd(ctx, tctx, cancel_all); ret |= io_kill_timeouts(ctx, tctx, cancel_all); mutex_unlock(&ctx->uring_lock); if (tctx) ret |= io_run_task_work() > 0; return ret; } static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) { if (tracked) return atomic_read(&tctx->inflight_tracked); return percpu_counter_sum(&tctx->inflight); } /* * Find any io_uring ctx that this task has registered or done IO on, and cancel * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation. */ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) { struct io_uring_task *tctx = current->io_uring; struct io_ring_ctx *ctx; struct io_tctx_node *node; unsigned long index; s64 inflight; DEFINE_WAIT(wait); WARN_ON_ONCE(sqd && sqpoll_task_locked(sqd) != current); if (!current->io_uring) return; if (tctx->io_wq) io_wq_exit_start(tctx->io_wq); atomic_inc(&tctx->in_cancel); do { bool loop = false; io_uring_drop_tctx_refs(current); if (!tctx_inflight(tctx, !cancel_all)) break; /* read completions before cancelations */ inflight = tctx_inflight(tctx, false); if (!inflight) break; if (!sqd) { xa_for_each(&tctx->xa, index, node) { /* sqpoll task will cancel all its requests */ if (node->ctx->sq_data) continue; loop |= io_uring_try_cancel_requests(node->ctx, current->io_uring, cancel_all, false); } } else { list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) loop |= io_uring_try_cancel_requests(ctx, current->io_uring, cancel_all, true); } if (loop) { cond_resched(); continue; } prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE); io_run_task_work(); io_uring_drop_tctx_refs(current); xa_for_each(&tctx->xa, index, node) { if (io_local_work_pending(node->ctx)) { WARN_ON_ONCE(node->ctx->submitter_task && node->ctx->submitter_task != current); goto end_wait; } } /* * If we've seen completions, retry without waiting. This * avoids a race where a completion comes in before we did * prepare_to_wait(). */ if (inflight == tctx_inflight(tctx, !cancel_all)) schedule(); end_wait: finish_wait(&tctx->wait, &wait); } while (1); io_uring_clean_tctx(tctx); if (cancel_all) { /* * We shouldn't run task_works after cancel, so just leave * ->in_cancel set for normal exit. */ atomic_dec(&tctx->in_cancel); /* for exec all current's requests should be gone, kill tctx */ io_uring_free_tctx(current); } } |
| 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 */ #ifndef _DEVICE_DEVRES_H_ #define _DEVICE_DEVRES_H_ #include <linux/err.h> #include <linux/gfp_types.h> #include <linux/numa.h> #include <linux/overflow.h> #include <linux/stdarg.h> #include <linux/types.h> #include <asm/bug.h> #include <asm/percpu.h> struct device; struct device_node; struct resource; /* device resource management */ typedef void (*dr_release_t)(struct device *dev, void *res); typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); void * __malloc __devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid, const char *name); #define devres_alloc(release, size, gfp) \ __devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release) #define devres_alloc_node(release, size, gfp, nid) \ __devres_alloc_node(release, size, gfp, nid, #release) void devres_free(void *res); void devres_add(struct device *dev, void *res); void *devres_find(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); void *devres_get(struct device *dev, void *new_res, dr_match_t match, void *match_data); void *devres_remove(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_release(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); /* devres group */ void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp); void devres_close_group(struct device *dev, void *id); void devres_remove_group(struct device *dev, void *id); int devres_release_group(struct device *dev, void *id); /* managed devm_k.alloc/kfree for device drivers */ void * __alloc_size(2) devm_kmalloc(struct device *dev, size_t size, gfp_t gfp); void * __must_check __realloc_size(3) devm_krealloc(struct device *dev, void *ptr, size_t size, gfp_t gfp); static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) { return devm_kmalloc(dev, size, gfp | __GFP_ZERO); } static inline void *devm_kmalloc_array(struct device *dev, size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return devm_kmalloc(dev, bytes, flags); } static inline void *devm_kcalloc(struct device *dev, size_t n, size_t size, gfp_t flags) { return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO); } static inline __realloc_size(3, 4) void * __must_check devm_krealloc_array(struct device *dev, void *p, size_t new_n, size_t new_size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; return devm_krealloc(dev, p, bytes, flags); } void devm_kfree(struct device *dev, const void *p); void * __realloc_size(3) devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp); const void * devm_kmemdup_const(struct device *dev, const void *src, size_t len, gfp_t gfp); static inline void *devm_kmemdup_array(struct device *dev, const void *src, size_t n, size_t size, gfp_t flags) { return devm_kmemdup(dev, src, size_mul(size, n), flags); } char * __malloc devm_kstrdup(struct device *dev, const char *s, gfp_t gfp); const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp); char * __printf(3, 0) __malloc devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, va_list ap); char * __printf(3, 4) __malloc devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...); /** * devm_alloc_percpu - Resource-managed alloc_percpu * @dev: Device to allocate per-cpu memory for * @type: Type to allocate per-cpu memory for * * Managed alloc_percpu. Per-cpu memory allocated with this function is * automatically freed on driver detach. * * RETURNS: * Pointer to allocated memory on success, NULL on failure. */ #define devm_alloc_percpu(dev, type) \ ((typeof(type) __percpu *)__devm_alloc_percpu((dev), sizeof(type), __alignof__(type))) void __percpu *__devm_alloc_percpu(struct device *dev, size_t size, size_t align); unsigned long devm_get_free_pages(struct device *dev, gfp_t gfp_mask, unsigned int order); void devm_free_pages(struct device *dev, unsigned long addr); #ifdef CONFIG_HAS_IOMEM void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res); void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res); void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size); #else static inline void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res) { return IOMEM_ERR_PTR(-EINVAL); } static inline void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res) { return IOMEM_ERR_PTR(-EINVAL); } static inline void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size) { return IOMEM_ERR_PTR(-EINVAL); } #endif /* allows to add/remove a custom action to devres stack */ int devm_remove_action_nowarn(struct device *dev, void (*action)(void *), void *data); /** * devm_remove_action() - removes previously added custom action * @dev: Device that owns the action * @action: Function implementing the action * @data: Pointer to data passed to @action implementation * * Removes instance of @action previously added by devm_add_action(). * Both action and data should match one of the existing entries. */ static inline void devm_remove_action(struct device *dev, void (*action)(void *), void *data) { WARN_ON(devm_remove_action_nowarn(dev, action, data)); } void devm_release_action(struct device *dev, void (*action)(void *), void *data); int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name); #define devm_add_action(dev, action, data) \ __devm_add_action(dev, action, data, #action) static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *), void *data, const char *name) { int ret; ret = __devm_add_action(dev, action, data, name); if (ret) action(data); return ret; } #define devm_add_action_or_reset(dev, action, data) \ __devm_add_action_or_reset(dev, action, data, #action) bool devm_is_action_added(struct device *dev, void (*action)(void *), void *data); #endif /* _DEVICE_DEVRES_H_ */ |
| 4028 | 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 | #ifndef _LINUX_SCHED_ISOLATION_H #define _LINUX_SCHED_ISOLATION_H #include <linux/cpumask.h> #include <linux/init.h> #include <linux/tick.h> enum hk_type { /* Inverse of boot-time isolcpus= argument */ HK_TYPE_DOMAIN_BOOT, /* * Same as HK_TYPE_DOMAIN_BOOT but also includes the * inverse of cpuset isolated partitions. As such it * is always a subset of HK_TYPE_DOMAIN_BOOT. */ HK_TYPE_DOMAIN, /* Inverse of boot-time isolcpus=managed_irq argument */ HK_TYPE_MANAGED_IRQ, /* Inverse of boot-time nohz_full= or isolcpus=nohz arguments */ HK_TYPE_KERNEL_NOISE, HK_TYPE_MAX, /* * HK_TYPE_KTHREAD is now an alias of HK_TYPE_DOMAIN */ HK_TYPE_KTHREAD = HK_TYPE_DOMAIN, /* * The following housekeeping types are only set by the nohz_full * boot commandline option. So they can share the same value. */ HK_TYPE_TICK = HK_TYPE_KERNEL_NOISE, HK_TYPE_TIMER = HK_TYPE_KERNEL_NOISE, HK_TYPE_RCU = HK_TYPE_KERNEL_NOISE, HK_TYPE_MISC = HK_TYPE_KERNEL_NOISE, HK_TYPE_WQ = HK_TYPE_KERNEL_NOISE, }; #ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overridden); extern int housekeeping_any_cpu(enum hk_type type); extern const struct cpumask *housekeeping_cpumask(enum hk_type type); extern bool housekeeping_enabled(enum hk_type type); extern void housekeeping_affine(struct task_struct *t, enum hk_type type); extern bool housekeeping_test_cpu(int cpu, enum hk_type type); extern int housekeeping_update(struct cpumask *isol_mask); extern void __init housekeeping_init(void); #else static inline int housekeeping_any_cpu(enum hk_type type) { return smp_processor_id(); } static inline const struct cpumask *housekeeping_cpumask(enum hk_type type) { return cpu_possible_mask; } static inline bool housekeeping_enabled(enum hk_type type) { return false; } static inline void housekeeping_affine(struct task_struct *t, enum hk_type type) { } static inline bool housekeeping_test_cpu(int cpu, enum hk_type type) { return true; } static inline int housekeeping_update(struct cpumask *isol_mask) { return 0; } static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ static inline bool housekeeping_cpu(int cpu, enum hk_type type) { #ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely(&housekeeping_overridden)) return housekeeping_test_cpu(cpu, type); #endif return true; } static inline bool cpu_is_isolated(int cpu) { return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN); } #endif /* _LINUX_SCHED_ISOLATION_H */ |
| 1 1 1 1 156 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 | // SPDX-License-Identifier: GPL-2.0-or-later /* * xfrm_proc.c * * Copyright (C)2006-2007 USAGI/WIDE Project * * Authors: Masahide NAKAMURA <nakam@linux-ipv6.org> */ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/export.h> #include <net/snmp.h> #include <net/xfrm.h> static const struct snmp_mib xfrm_mib_list[] = { SNMP_MIB_ITEM("XfrmInError", LINUX_MIB_XFRMINERROR), SNMP_MIB_ITEM("XfrmInBufferError", LINUX_MIB_XFRMINBUFFERERROR), SNMP_MIB_ITEM("XfrmInHdrError", LINUX_MIB_XFRMINHDRERROR), SNMP_MIB_ITEM("XfrmInNoStates", LINUX_MIB_XFRMINNOSTATES), SNMP_MIB_ITEM("XfrmInStateProtoError", LINUX_MIB_XFRMINSTATEPROTOERROR), SNMP_MIB_ITEM("XfrmInStateModeError", LINUX_MIB_XFRMINSTATEMODEERROR), SNMP_MIB_ITEM("XfrmInStateSeqError", LINUX_MIB_XFRMINSTATESEQERROR), SNMP_MIB_ITEM("XfrmInStateExpired", LINUX_MIB_XFRMINSTATEEXPIRED), SNMP_MIB_ITEM("XfrmInStateMismatch", LINUX_MIB_XFRMINSTATEMISMATCH), SNMP_MIB_ITEM("XfrmInStateInvalid", LINUX_MIB_XFRMINSTATEINVALID), SNMP_MIB_ITEM("XfrmInTmplMismatch", LINUX_MIB_XFRMINTMPLMISMATCH), SNMP_MIB_ITEM("XfrmInNoPols", LINUX_MIB_XFRMINNOPOLS), SNMP_MIB_ITEM("XfrmInPolBlock", LINUX_MIB_XFRMINPOLBLOCK), SNMP_MIB_ITEM("XfrmInPolError", LINUX_MIB_XFRMINPOLERROR), SNMP_MIB_ITEM("XfrmOutError", LINUX_MIB_XFRMOUTERROR), SNMP_MIB_ITEM("XfrmOutBundleGenError", LINUX_MIB_XFRMOUTBUNDLEGENERROR), SNMP_MIB_ITEM("XfrmOutBundleCheckError", LINUX_MIB_XFRMOUTBUNDLECHECKERROR), SNMP_MIB_ITEM("XfrmOutNoStates", LINUX_MIB_XFRMOUTNOSTATES), SNMP_MIB_ITEM("XfrmOutStateProtoError", LINUX_MIB_XFRMOUTSTATEPROTOERROR), SNMP_MIB_ITEM("XfrmOutStateModeError", LINUX_MIB_XFRMOUTSTATEMODEERROR), SNMP_MIB_ITEM("XfrmOutStateSeqError", LINUX_MIB_XFRMOUTSTATESEQERROR), SNMP_MIB_ITEM("XfrmOutStateExpired", LINUX_MIB_XFRMOUTSTATEEXPIRED), SNMP_MIB_ITEM("XfrmOutPolBlock", LINUX_MIB_XFRMOUTPOLBLOCK), SNMP_MIB_ITEM("XfrmOutPolDead", LINUX_MIB_XFRMOUTPOLDEAD), SNMP_MIB_ITEM("XfrmOutPolError", LINUX_MIB_XFRMOUTPOLERROR), SNMP_MIB_ITEM("XfrmFwdHdrError", LINUX_MIB_XFRMFWDHDRERROR), SNMP_MIB_ITEM("XfrmOutStateInvalid", LINUX_MIB_XFRMOUTSTATEINVALID), SNMP_MIB_ITEM("XfrmAcquireError", LINUX_MIB_XFRMACQUIREERROR), SNMP_MIB_ITEM("XfrmOutStateDirError", LINUX_MIB_XFRMOUTSTATEDIRERROR), SNMP_MIB_ITEM("XfrmInStateDirError", LINUX_MIB_XFRMINSTATEDIRERROR), SNMP_MIB_ITEM("XfrmInIptfsError", LINUX_MIB_XFRMINIPTFSERROR), SNMP_MIB_ITEM("XfrmOutNoQueueSpace", LINUX_MIB_XFRMOUTNOQSPACE), }; static int xfrm_statistics_seq_show(struct seq_file *seq, void *v) { unsigned long buff[ARRAY_SIZE(xfrm_mib_list)]; const int cnt = ARRAY_SIZE(xfrm_mib_list); struct net *net = seq->private; int i; memset(buff, 0, sizeof(buff)); xfrm_state_update_stats(net); snmp_get_cpu_field_batch_cnt(buff, xfrm_mib_list, cnt, net->mib.xfrm_statistics); for (i = 0; i < cnt; i++) seq_printf(seq, "%-24s\t%lu\n", xfrm_mib_list[i].name, buff[i]); return 0; } int __net_init xfrm_proc_init(struct net *net) { if (!proc_create_net_single("xfrm_stat", 0444, net->proc_net, xfrm_statistics_seq_show, NULL)) return -ENOMEM; return 0; } void xfrm_proc_fini(struct net *net) { remove_proc_entry("xfrm_stat", net->proc_net); } |
| 1 1 2 2 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 | // SPDX-License-Identifier: GPL-2.0 /* * platform.c - platform 'pseudo' bus for legacy devices * * Copyright (c) 2002-3 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * * Please see Documentation/driver-api/driver-model/platform.rst for more * information. */ #include <linux/string.h> #include <linux/platform_device.h> #include <linux/of_device.h> #include <linux/of_irq.h> #include <linux/module.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/ioport.h> #include <linux/dma-mapping.h> #include <linux/memblock.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/pm_runtime.h> #include <linux/pm_domain.h> #include <linux/idr.h> #include <linux/acpi.h> #include <linux/clk/clk-conf.h> #include <linux/limits.h> #include <linux/property.h> #include <linux/kmemleak.h> #include <linux/types.h> #include <linux/iommu.h> #include <linux/dma-map-ops.h> #include "base.h" #include "power/power.h" /* For automatically allocated device IDs */ static DEFINE_IDA(platform_devid_ida); struct device platform_bus = { .init_name = "platform", }; EXPORT_SYMBOL_GPL(platform_bus); /** * platform_get_resource - get a resource for a device * @dev: platform device * @type: resource type * @num: resource index * * Return: a pointer to the resource or NULL on failure. */ struct resource *platform_get_resource(struct platform_device *dev, unsigned int type, unsigned int num) { u32 i; for (i = 0; i < dev->num_resources; i++) { struct resource *r = &dev->resource[i]; if (type == resource_type(r) && num-- == 0) return r; } return NULL; } EXPORT_SYMBOL_GPL(platform_get_resource); struct resource *platform_get_mem_or_io(struct platform_device *dev, unsigned int num) { u32 i; for (i = 0; i < dev->num_resources; i++) { struct resource *r = &dev->resource[i]; if ((resource_type(r) & (IORESOURCE_MEM | IORESOURCE_IO)) && num-- == 0) return r; } return NULL; } EXPORT_SYMBOL_GPL(platform_get_mem_or_io); #ifdef CONFIG_HAS_IOMEM /** * devm_platform_get_and_ioremap_resource - call devm_ioremap_resource() for a * platform device and get resource * * @pdev: platform device to use both for memory resource lookup as well as * resource management * @index: resource index * @res: optional output parameter to store a pointer to the obtained resource. * * Return: a pointer to the remapped memory or an ERR_PTR() encoded error code * on failure. */ void __iomem * devm_platform_get_and_ioremap_resource(struct platform_device *pdev, unsigned int index, struct resource **res) { struct resource *r; r = platform_get_resource(pdev, IORESOURCE_MEM, index); if (res) *res = r; return devm_ioremap_resource(&pdev->dev, r); } EXPORT_SYMBOL_GPL(devm_platform_get_and_ioremap_resource); /** * devm_platform_ioremap_resource - call devm_ioremap_resource() for a platform * device * * @pdev: platform device to use both for memory resource lookup as well as * resource management * @index: resource index * * Return: a pointer to the remapped memory or an ERR_PTR() encoded error code * on failure. */ void __iomem *devm_platform_ioremap_resource(struct platform_device *pdev, unsigned int index) { return devm_platform_get_and_ioremap_resource(pdev, index, NULL); } EXPORT_SYMBOL_GPL(devm_platform_ioremap_resource); /** * devm_platform_ioremap_resource_byname - call devm_ioremap_resource for * a platform device, retrieve the * resource by name * * @pdev: platform device to use both for memory resource lookup as well as * resource management * @name: name of the resource * * Return: a pointer to the remapped memory or an ERR_PTR() encoded error code * on failure. */ void __iomem * devm_platform_ioremap_resource_byname(struct platform_device *pdev, const char *name) { struct resource *res; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, name); return devm_ioremap_resource(&pdev->dev, res); } EXPORT_SYMBOL_GPL(devm_platform_ioremap_resource_byname); #endif /* CONFIG_HAS_IOMEM */ static const struct cpumask *get_irq_affinity(struct platform_device *dev, unsigned int num) { const struct cpumask *mask = NULL; #ifndef CONFIG_SPARC struct fwnode_handle *fwnode = dev_fwnode(&dev->dev); if (is_of_node(fwnode)) mask = of_irq_get_affinity(to_of_node(fwnode), num); else if (is_acpi_device_node(fwnode)) mask = acpi_irq_get_affinity(ACPI_HANDLE_FWNODE(fwnode), num); #endif return mask ?: cpu_possible_mask; } /** * platform_get_irq_affinity - get an optional IRQ and its affinity for a device * @dev: platform device * @num: interrupt number index * @affinity: optional cpumask pointer to get the affinity of a per-cpu interrupt * * Gets an interrupt for a platform device. Device drivers should check the * return value for errors so as to not pass a negative integer value to * the request_irq() APIs. Optional affinity information is provided in the * affinity pointer if available, and NULL otherwise. * * Return: non-zero interrupt number on success, negative error number on failure. */ int platform_get_irq_affinity(struct platform_device *dev, unsigned int num, const struct cpumask **affinity) { int ret; #ifdef CONFIG_SPARC /* sparc does not have irqs represented as IORESOURCE_IRQ resources */ if (!dev || num >= dev->archdata.num_irqs) goto out_not_found; ret = dev->archdata.irqs[num]; goto out; #else struct fwnode_handle *fwnode = dev_fwnode(&dev->dev); struct resource *r; if (is_of_node(fwnode)) { ret = of_irq_get(to_of_node(fwnode), num); if (ret > 0 || ret == -EPROBE_DEFER) goto out; } r = platform_get_resource(dev, IORESOURCE_IRQ, num); if (is_acpi_device_node(fwnode)) { if (r && r->flags & IORESOURCE_DISABLED) { ret = acpi_irq_get(ACPI_HANDLE_FWNODE(fwnode), num, r); if (ret) goto out; } } /* * The resources may pass trigger flags to the irqs that need * to be set up. It so happens that the trigger flags for * IORESOURCE_BITS correspond 1-to-1 to the IRQF_TRIGGER* * settings. */ if (r && r->flags & IORESOURCE_BITS) { struct irq_data *irqd; irqd = irq_get_irq_data(r->start); if (!irqd) goto out_not_found; irqd_set_trigger_type(irqd, r->flags & IORESOURCE_BITS); } if (r) { ret = r->start; goto out; } /* * For the index 0 interrupt, allow falling back to GpioInt * resources. While a device could have both Interrupt and GpioInt * resources, making this fallback ambiguous, in many common cases * the device will only expose one IRQ, and this fallback * allows a common code path across either kind of resource. */ if (num == 0 && is_acpi_device_node(fwnode)) { ret = acpi_dev_gpio_irq_get(to_acpi_device_node(fwnode), num); /* Our callers expect -ENXIO for missing IRQs. */ if (ret >= 0 || ret == -EPROBE_DEFER) goto out; } #endif out_not_found: ret = -ENXIO; out: if (WARN(!ret, "0 is an invalid IRQ number\n")) return -EINVAL; if (ret > 0 && affinity) *affinity = get_irq_affinity(dev, num); return ret; } EXPORT_SYMBOL_GPL(platform_get_irq_affinity); /** * platform_get_irq_optional - get an optional interrupt for a device * @dev: platform device * @num: interrupt number index * * Gets an interrupt for a platform device. Device drivers should check the * return value for errors so as to not pass a negative integer value to * the request_irq() APIs. This is the same as platform_get_irq(), except * that it does not print an error message if an interrupt can not be * obtained. * * For example:: * * int irq = platform_get_irq_optional(pdev, 0); * if (irq < 0) * return irq; * * Return: non-zero interrupt number on success, negative error number on failure. */ int platform_get_irq_optional(struct platform_device *dev, unsigned int num) { return platform_get_irq_affinity(dev, num, NULL); } EXPORT_SYMBOL_GPL(platform_get_irq_optional); /** * platform_get_irq - get an IRQ for a device * @dev: platform device * @num: IRQ number index * * Gets an IRQ for a platform device and prints an error message if finding the * IRQ fails. Device drivers should check the return value for errors so as to * not pass a negative integer value to the request_irq() APIs. * * For example:: * * int irq = platform_get_irq(pdev, 0); * if (irq < 0) * return irq; * * Return: non-zero IRQ number on success, negative error number on failure. */ int platform_get_irq(struct platform_device *dev, unsigned int num) { int ret; ret = platform_get_irq_optional(dev, num); if (ret < 0) return dev_err_probe(&dev->dev, ret, "IRQ index %u not found\n", num); return ret; } EXPORT_SYMBOL_GPL(platform_get_irq); /** * platform_irq_count - Count the number of IRQs a platform device uses * @dev: platform device * * Return: Number of IRQs a platform device uses or EPROBE_DEFER */ int platform_irq_count(struct platform_device *dev) { int ret, nr = 0; while ((ret = platform_get_irq_optional(dev, nr)) >= 0) nr++; if (ret == -EPROBE_DEFER) return ret; return nr; } EXPORT_SYMBOL_GPL(platform_irq_count); struct irq_affinity_devres { unsigned int count; unsigned int irq[] __counted_by(count); }; static void platform_disable_acpi_irq(struct platform_device *pdev, int index) { struct resource *r; r = platform_get_resource(pdev, IORESOURCE_IRQ, index); if (r) irqresource_disabled(r, 0); } static void devm_platform_get_irqs_affinity_release(struct device *dev, void *res) { struct irq_affinity_devres *ptr = res; int i; for (i = 0; i < ptr->count; i++) { irq_dispose_mapping(ptr->irq[i]); if (is_acpi_device_node(dev_fwnode(dev))) platform_disable_acpi_irq(to_platform_device(dev), i); } } /** * devm_platform_get_irqs_affinity - devm method to get a set of IRQs for a * device using an interrupt affinity descriptor * @dev: platform device pointer * @affd: affinity descriptor * @minvec: minimum count of interrupt vectors * @maxvec: maximum count of interrupt vectors * @irqs: pointer holder for IRQ numbers * * Gets a set of IRQs for a platform device, and updates IRQ afffinty according * to the passed affinity descriptor * * Return: Number of vectors on success, negative error number on failure. */ int devm_platform_get_irqs_affinity(struct platform_device *dev, struct irq_affinity *affd, unsigned int minvec, unsigned int maxvec, int **irqs) { struct irq_affinity_devres *ptr; struct irq_affinity_desc *desc; size_t size; int i, ret, nvec; if (!affd) return -EPERM; if (maxvec < minvec) return -ERANGE; nvec = platform_irq_count(dev); if (nvec < 0) return nvec; if (nvec < minvec) return -ENOSPC; nvec = irq_calc_affinity_vectors(minvec, nvec, affd); if (nvec < minvec) return -ENOSPC; if (nvec > maxvec) nvec = maxvec; size = sizeof(*ptr) + sizeof(unsigned int) * nvec; ptr = devres_alloc(devm_platform_get_irqs_affinity_release, size, GFP_KERNEL); if (!ptr) return -ENOMEM; ptr->count = nvec; for (i = 0; i < nvec; i++) { int irq = platform_get_irq(dev, i); if (irq < 0) { ret = irq; goto err_free_devres; } ptr->irq[i] = irq; } desc = irq_create_affinity_masks(nvec, affd); if (!desc) { ret = -ENOMEM; goto err_free_devres; } for (i = 0; i < nvec; i++) { ret = irq_update_affinity_desc(ptr->irq[i], &desc[i]); if (ret) { dev_err(&dev->dev, "failed to update irq%d affinity descriptor (%d)\n", ptr->irq[i], ret); goto err_free_desc; } } devres_add(&dev->dev, ptr); kfree(desc); *irqs = ptr->irq; return nvec; err_free_desc: kfree(desc); err_free_devres: devres_free(ptr); return ret; } EXPORT_SYMBOL_GPL(devm_platform_get_irqs_affinity); /** * platform_get_resource_byname - get a resource for a device by name * @dev: platform device * @type: resource type * @name: resource name */ struct resource *platform_get_resource_byname(struct platform_device *dev, unsigned int type, const char *name) { u32 i; for (i = 0; i < dev->num_resources; i++) { struct resource *r = &dev->resource[i]; if (unlikely(!r->name)) continue; if (type == resource_type(r) && !strcmp(r->name, name)) return r; } return NULL; } EXPORT_SYMBOL_GPL(platform_get_resource_byname); static int __platform_get_irq_byname(struct platform_device *dev, const char *name) { struct resource *r; int ret; ret = fwnode_irq_get_byname(dev_fwnode(&dev->dev), name); if (ret > 0 || ret == -EPROBE_DEFER) return ret; r = platform_get_resource_byname(dev, IORESOURCE_IRQ, name); if (r) { if (WARN(!r->start, "0 is an invalid IRQ number\n")) return -EINVAL; return r->start; } return -ENXIO; } /** * platform_get_irq_byname - get an IRQ for a device by name * @dev: platform device * @name: IRQ name * * Get an IRQ like platform_get_irq(), but then by name rather then by index. * * Return: non-zero IRQ number on success, negative error number on failure. */ int platform_get_irq_byname(struct platform_device *dev, const char *name) { int ret; ret = __platform_get_irq_byname(dev, name); if (ret < 0) return dev_err_probe(&dev->dev, ret, "IRQ %s not found\n", name); return ret; } EXPORT_SYMBOL_GPL(platform_get_irq_byname); /** * platform_get_irq_byname_optional - get an optional IRQ for a device by name * @dev: platform device * @name: IRQ name * * Get an optional IRQ by name like platform_get_irq_byname(). Except that it * does not print an error message if an IRQ can not be obtained. * * Return: non-zero IRQ number on success, negative error number on failure. */ int platform_get_irq_byname_optional(struct platform_device *dev, const char *name) { return __platform_get_irq_byname(dev, name); } EXPORT_SYMBOL_GPL(platform_get_irq_byname_optional); /** * platform_add_devices - add a numbers of platform devices * @devs: array of platform devices to add * @num: number of platform devices in array * * Return: 0 on success, negative error number on failure. */ int platform_add_devices(struct platform_device **devs, int num) { int i, ret = 0; for (i = 0; i < num; i++) { ret = platform_device_register(devs[i]); if (ret) { while (--i >= 0) platform_device_unregister(devs[i]); break; } } return ret; } EXPORT_SYMBOL_GPL(platform_add_devices); struct platform_object { struct platform_device pdev; char name[]; }; /* * Set up default DMA mask for platform devices if the they weren't * previously set by the architecture / DT. */ static void setup_pdev_dma_masks(struct platform_device *pdev) { pdev->dev.dma_parms = &pdev->dma_parms; if (!pdev->dev.coherent_dma_mask) pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); if (!pdev->dev.dma_mask) { pdev->platform_dma_mask = DMA_BIT_MASK(32); pdev->dev.dma_mask = &pdev->platform_dma_mask; } }; /** * platform_device_put - destroy a platform device * @pdev: platform device to free * * Free all memory associated with a platform device. This function must * _only_ be externally called in error cases. All other usage is a bug. */ void platform_device_put(struct platform_device *pdev) { if (!IS_ERR_OR_NULL(pdev)) put_device(&pdev->dev); } EXPORT_SYMBOL_GPL(platform_device_put); static void platform_device_release(struct device *dev) { struct platform_object *pa = container_of(dev, struct platform_object, pdev.dev); of_node_put(pa->pdev.dev.of_node); kfree(pa->pdev.dev.platform_data); kfree(pa->pdev.mfd_cell); kfree(pa->pdev.resource); kfree(pa); } static void platform_device_release_full(struct device *dev) { device_remove_software_node(dev); platform_device_release(dev); } /** * platform_device_alloc - create a platform device * @name: base name of the device we're adding * @id: instance id * * Create a platform device object which can have other objects attached * to it, and which will have attached objects freed when it is released. */ struct platform_device *platform_device_alloc(const char *name, int id) { struct platform_object *pa; pa = kzalloc(sizeof(*pa) + strlen(name) + 1, GFP_KERNEL); if (pa) { strcpy(pa->name, name); pa->pdev.name = pa->name; pa->pdev.id = id; device_initialize(&pa->pdev.dev); pa->pdev.dev.release = platform_device_release; setup_pdev_dma_masks(&pa->pdev); } return pa ? &pa->pdev : NULL; } EXPORT_SYMBOL_GPL(platform_device_alloc); /** * platform_device_add_resources - add resources to a platform device * @pdev: platform device allocated by platform_device_alloc to add resources to * @res: set of resources that needs to be allocated for the device * @num: number of resources * * Add a copy of the resources to the platform device. The memory * associated with the resources will be freed when the platform device is * released. */ int platform_device_add_resources(struct platform_device *pdev, const struct resource *res, unsigned int num) { struct resource *r = NULL; if (res) { r = kmemdup_array(res, num, sizeof(*r), GFP_KERNEL); if (!r) return -ENOMEM; } kfree(pdev->resource); pdev->resource = r; pdev->num_resources = num; return 0; } EXPORT_SYMBOL_GPL(platform_device_add_resources); /** * platform_device_add_data - add platform-specific data to a platform device * @pdev: platform device allocated by platform_device_alloc to add resources to * @data: platform specific data for this platform device * @size: size of platform specific data * * Add a copy of platform specific data to the platform device's * platform_data pointer. The memory associated with the platform data * will be freed when the platform device is released. */ int platform_device_add_data(struct platform_device *pdev, const void *data, size_t size) { void *d = NULL; if (data) { d = kmemdup(data, size, GFP_KERNEL); if (!d) return -ENOMEM; } kfree(pdev->dev.platform_data); pdev->dev.platform_data = d; return 0; } EXPORT_SYMBOL_GPL(platform_device_add_data); /** * platform_device_add - add a platform device to device hierarchy * @pdev: platform device we're adding * * This is part 2 of platform_device_register(), though may be called * separately _iff_ pdev was allocated by platform_device_alloc(). */ int platform_device_add(struct platform_device *pdev) { struct device *dev = &pdev->dev; u32 i; int ret; if (!dev->parent) dev->parent = &platform_bus; dev->bus = &platform_bus_type; switch (pdev->id) { default: dev_set_name(dev, "%s.%d", pdev->name, pdev->id); break; case PLATFORM_DEVID_NONE: dev_set_name(dev, "%s", pdev->name); break; case PLATFORM_DEVID_AUTO: /* * Automatically allocated device ID. We mark it as such so * that we remember it must be freed, and we append a suffix * to avoid namespace collision with explicit IDs. */ ret = ida_alloc(&platform_devid_ida, GFP_KERNEL); if (ret < 0) return ret; pdev->id = ret; pdev->id_auto = true; dev_set_name(dev, "%s.%d.auto", pdev->name, pdev->id); break; } for (i = 0; i < pdev->num_resources; i++) { struct resource *p, *r = &pdev->resource[i]; if (r->name == NULL) r->name = dev_name(dev); p = r->parent; if (!p) { if (resource_type(r) == IORESOURCE_MEM) p = &iomem_resource; else if (resource_type(r) == IORESOURCE_IO) p = &ioport_resource; } if (p) { ret = insert_resource(p, r); if (ret) { dev_err(dev, "failed to claim resource %d: %pR\n", i, r); goto failed; } } } pr_debug("Registering platform device '%s'. Parent at %s\n", dev_name(dev), dev_name(dev->parent)); ret = device_add(dev); if (ret) goto failed; return 0; failed: if (pdev->id_auto) { ida_free(&platform_devid_ida, pdev->id); pdev->id = PLATFORM_DEVID_AUTO; } while (i--) { struct resource *r = &pdev->resource[i]; if (r->parent) release_resource(r); } return ret; } EXPORT_SYMBOL_GPL(platform_device_add); /** * platform_device_del - remove a platform-level device * @pdev: platform device we're removing * * Note that this function will also release all memory- and port-based * resources owned by the device (@dev->resource). This function must * _only_ be externally called in error cases. All other usage is a bug. */ void platform_device_del(struct platform_device *pdev) { u32 i; if (!IS_ERR_OR_NULL(pdev)) { device_del(&pdev->dev); if (pdev->id_auto) { ida_free(&platform_devid_ida, pdev->id); pdev->id = PLATFORM_DEVID_AUTO; } for (i = 0; i < pdev->num_resources; i++) { struct resource *r = &pdev->resource[i]; if (r->parent) release_resource(r); } } } EXPORT_SYMBOL_GPL(platform_device_del); /** * platform_device_register - add a platform-level device * @pdev: platform device we're adding * * NOTE: _Never_ directly free @pdev after calling this function, even if it * returned an error! Always use platform_device_put() to give up the * reference initialised in this function instead. */ int platform_device_register(struct platform_device *pdev) { device_initialize(&pdev->dev); setup_pdev_dma_masks(pdev); return platform_device_add(pdev); } EXPORT_SYMBOL_GPL(platform_device_register); /** * platform_device_unregister - unregister a platform-level device * @pdev: platform device we're unregistering * * Unregistration is done in 2 steps. First we release all resources * and remove it from the subsystem, then we drop reference count by * calling platform_device_put(). */ void platform_device_unregister(struct platform_device *pdev) { platform_device_del(pdev); platform_device_put(pdev); } EXPORT_SYMBOL_GPL(platform_device_unregister); /** * platform_device_register_full - add a platform-level device with * resources and platform-specific data * * @pdevinfo: data used to create device * * Returns &struct platform_device pointer on success, or ERR_PTR() on error. */ struct platform_device *platform_device_register_full(const struct platform_device_info *pdevinfo) { int ret; struct platform_device *pdev; /* * Only one software node per device is allowed. Make sure we don't * accept or create two. */ if ((pdevinfo->swnode && pdevinfo->properties) || (pdevinfo->swnode && is_software_node(pdevinfo->fwnode)) || (pdevinfo->properties && is_software_node(pdevinfo->fwnode))) return ERR_PTR(-EINVAL); pdev = platform_device_alloc(pdevinfo->name, pdevinfo->id); if (!pdev) return ERR_PTR(-ENOMEM); pdev->dev.parent = pdevinfo->parent; pdev->dev.fwnode = pdevinfo->fwnode; pdev->dev.of_node = of_node_get(to_of_node(pdev->dev.fwnode)); dev_assign_of_node_reused(&pdev->dev, pdevinfo->of_node_reused); if (pdevinfo->dma_mask) { pdev->platform_dma_mask = pdevinfo->dma_mask; pdev->dev.dma_mask = &pdev->platform_dma_mask; pdev->dev.coherent_dma_mask = pdevinfo->dma_mask; } ret = platform_device_add_resources(pdev, pdevinfo->res, pdevinfo->num_res); if (ret) goto err; ret = platform_device_add_data(pdev, pdevinfo->data, pdevinfo->size_data); if (ret) goto err; if (pdevinfo->swnode) { ret = device_add_software_node(&pdev->dev, pdevinfo->swnode); if (ret) goto err; pdev->dev.release = platform_device_release_full; } else if (pdevinfo->properties) { ret = device_create_managed_software_node(&pdev->dev, pdevinfo->properties, NULL); if (ret) goto err; } ret = platform_device_add(pdev); if (ret) { err: ACPI_COMPANION_SET(&pdev->dev, NULL); platform_device_put(pdev); return ERR_PTR(ret); } return pdev; } EXPORT_SYMBOL_GPL(platform_device_register_full); /** * __platform_driver_register - register a driver for platform-level devices * @drv: platform driver structure * @owner: owning module/driver * @mod_name: module name string */ int __platform_driver_register(struct platform_driver *drv, struct module *owner, const char *mod_name) { drv->driver.owner = owner; drv->driver.bus = &platform_bus_type; drv->driver.mod_name = mod_name; return driver_register(&drv->driver); } EXPORT_SYMBOL_GPL(__platform_driver_register); /** * platform_driver_unregister - unregister a driver for platform-level devices * @drv: platform driver structure */ void platform_driver_unregister(struct platform_driver *drv) { driver_unregister(&drv->driver); } EXPORT_SYMBOL_GPL(platform_driver_unregister); static int platform_probe_fail(struct platform_device *pdev) { return -ENXIO; } static int is_bound_to_driver(struct device *dev, void *driver) { if (dev->driver == driver) return 1; return 0; } /** * __platform_driver_probe - register driver for non-hotpluggable device * @drv: platform driver structure * @probe: the driver probe routine, probably from an __init section * @module: module which will be the owner of the driver * @mod_name: module name string * * Use this instead of platform_driver_register() when you know the device * is not hotpluggable and has already been registered, and you want to * remove its run-once probe() infrastructure from memory after the driver * has bound to the device. * * One typical use for this would be with drivers for controllers integrated * into system-on-chip processors, where the controller devices have been * configured as part of board setup. * * Note that this is incompatible with deferred probing. * * Returns zero if the driver registered and bound to a device, else returns * a negative error code and with the driver not registered. */ int __init_or_module __platform_driver_probe(struct platform_driver *drv, int (*probe)(struct platform_device *), struct module *module, const char *mod_name) { int retval; if (drv->driver.probe_type == PROBE_PREFER_ASYNCHRONOUS) { pr_err("%s: drivers registered with %s can not be probed asynchronously\n", drv->driver.name, __func__); return -EINVAL; } /* * We have to run our probes synchronously because we check if * we find any devices to bind to and exit with error if there * are any. */ drv->driver.probe_type = PROBE_FORCE_SYNCHRONOUS; /* * Prevent driver from requesting probe deferral to avoid further * futile probe attempts. */ drv->prevent_deferred_probe = true; /* make sure driver won't have bind/unbind attributes */ drv->driver.suppress_bind_attrs = true; /* temporary section violation during probe() */ drv->probe = probe; retval = __platform_driver_register(drv, module, mod_name); if (retval) return retval; /* Force all new probes of this driver to fail */ drv->probe = platform_probe_fail; /* Walk all platform devices and see if any actually bound to this driver. * If not, return an error as the device should have done so by now. */ if (!bus_for_each_dev(&platform_bus_type, NULL, &drv->driver, is_bound_to_driver)) { retval = -ENODEV; platform_driver_unregister(drv); } return retval; } EXPORT_SYMBOL_GPL(__platform_driver_probe); /** * __platform_create_bundle - register driver and create corresponding device * @driver: platform driver structure * @probe: the driver probe routine, probably from an __init section * @res: set of resources that needs to be allocated for the device * @n_res: number of resources * @data: platform specific data for this platform device * @size: size of platform specific data * @module: module which will be the owner of the driver * @mod_name: module name string * * Use this in legacy-style modules that probe hardware directly and * register a single platform device and corresponding platform driver. * * Returns &struct platform_device pointer on success, or ERR_PTR() on error. */ struct platform_device * __init_or_module __platform_create_bundle(struct platform_driver *driver, int (*probe)(struct platform_device *), struct resource *res, unsigned int n_res, const void *data, size_t size, struct module *module, const char *mod_name) { struct platform_device *pdev; int error; pdev = platform_device_alloc(driver->driver.name, PLATFORM_DEVID_NONE); if (!pdev) { error = -ENOMEM; goto err_out; } error = platform_device_add_resources(pdev, res, n_res); if (error) goto err_pdev_put; error = platform_device_add_data(pdev, data, size); if (error) goto err_pdev_put; error = platform_device_add(pdev); if (error) goto err_pdev_put; error = __platform_driver_probe(driver, probe, module, mod_name); if (error) goto err_pdev_del; return pdev; err_pdev_del: platform_device_del(pdev); err_pdev_put: platform_device_put(pdev); err_out: return ERR_PTR(error); } EXPORT_SYMBOL_GPL(__platform_create_bundle); /** * __platform_register_drivers - register an array of platform drivers * @drivers: an array of drivers to register * @count: the number of drivers to register * @owner: module owning the drivers * @mod_name: module name string * * Registers platform drivers specified by an array. On failure to register a * driver, all previously registered drivers will be unregistered. Callers of * this API should use platform_unregister_drivers() to unregister drivers in * the reverse order. * * Returns: 0 on success or a negative error code on failure. */ int __platform_register_drivers(struct platform_driver * const *drivers, unsigned int count, struct module *owner, const char *mod_name) { unsigned int i; int err; for (i = 0; i < count; i++) { pr_debug("registering platform driver %ps\n", drivers[i]); err = __platform_driver_register(drivers[i], owner, mod_name); if (err < 0) { pr_err("failed to register platform driver %ps: %d\n", drivers[i], err); goto error; } } return 0; error: while (i--) { pr_debug("unregistering platform driver %ps\n", drivers[i]); platform_driver_unregister(drivers[i]); } return err; } EXPORT_SYMBOL_GPL(__platform_register_drivers); /** * platform_unregister_drivers - unregister an array of platform drivers * @drivers: an array of drivers to unregister * @count: the number of drivers to unregister * * Unregisters platform drivers specified by an array. This is typically used * to complement an earlier call to platform_register_drivers(). Drivers are * unregistered in the reverse order in which they were registered. */ void platform_unregister_drivers(struct platform_driver * const *drivers, unsigned int count) { while (count--) { pr_debug("unregistering platform driver %ps\n", drivers[count]); platform_driver_unregister(drivers[count]); } } EXPORT_SYMBOL_GPL(platform_unregister_drivers); static const struct platform_device_id * platform_match_id(const struct platform_device_id *id, struct platform_device *pdev) { while (id->name[0]) { if (strcmp(pdev->name, id->name) == 0) { pdev->id_entry = id; return id; } id++; } return NULL; } #ifdef CONFIG_PM_SLEEP static int platform_legacy_suspend(struct device *dev, pm_message_t mesg) { struct platform_driver *pdrv = to_platform_driver(dev->driver); struct platform_device *pdev = to_platform_device(dev); int ret = 0; if (dev->driver && pdrv->suspend) ret = pdrv->suspend(pdev, mesg); return ret; } static int platform_legacy_resume(struct device *dev) { struct platform_driver *pdrv = to_platform_driver(dev->driver); struct platform_device *pdev = to_platform_device(dev); int ret = 0; if (dev->driver && pdrv->resume) ret = pdrv->resume(pdev); return ret; } #endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_SUSPEND int platform_pm_suspend(struct device *dev) { const struct device_driver *drv = dev->driver; int ret = 0; if (!drv) return 0; if (drv->pm) { if (drv->pm->suspend) ret = drv->pm->suspend(dev); } else { ret = platform_legacy_suspend(dev, PMSG_SUSPEND); } return ret; } int platform_pm_resume(struct device *dev) { const struct device_driver *drv = dev->driver; int ret = 0; if (!drv) return 0; if (drv->pm) { if (drv->pm->resume) ret = drv->pm->resume(dev); } else { ret = platform_legacy_resume(dev); } return ret; } #endif /* CONFIG_SUSPEND */ #ifdef CONFIG_HIBERNATE_CALLBACKS int platform_pm_freeze(struct device *dev) { const struct device_driver *drv = dev->driver; int ret = 0; if (!drv) return 0; if (drv->pm) { if (drv->pm->freeze) ret = drv->pm->freeze(dev); } else { ret = platform_legacy_suspend(dev, PMSG_FREEZE); } return ret; } int platform_pm_thaw(struct device *dev) { const struct device_driver *drv = dev->driver; int ret = 0; if (!drv) return 0; if (drv->pm) { if (drv->pm->thaw) ret = drv->pm->thaw(dev); } else { ret = platform_legacy_resume(dev); } return ret; } int platform_pm_poweroff(struct device *dev) { const struct device_driver *drv = dev->driver; int ret = 0; if (!drv) return 0; if (drv->pm) { if (drv->pm->poweroff) ret = drv->pm->poweroff(dev); } else { ret = platform_legacy_suspend(dev, PMSG_HIBERNATE); } return ret; } int platform_pm_restore(struct device *dev) { const struct device_driver *drv = dev->driver; int ret = 0; if (!drv) return 0; if (drv->pm) { if (drv->pm->restore) ret = drv->pm->restore(dev); } else { ret = platform_legacy_resume(dev); } return ret; } #endif /* CONFIG_HIBERNATE_CALLBACKS */ /* modalias support enables more hands-off userspace setup: * (a) environment variable lets new-style hotplug events work once system is * fully running: "modprobe $MODALIAS" * (b) sysfs attribute lets new-style coldplug recover from hotplug events * mishandled before system is fully running: "modprobe $(cat modalias)" */ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, char *buf) { struct platform_device *pdev = to_platform_device(dev); int len; len = of_device_modalias(dev, buf, PAGE_SIZE); if (len != -ENODEV) return len; len = acpi_device_modalias(dev, buf, PAGE_SIZE - 1); if (len != -ENODEV) return len; return sysfs_emit(buf, "platform:%s\n", pdev->name); } static DEVICE_ATTR_RO(modalias); static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", dev_to_node(dev)); } static DEVICE_ATTR_RO(numa_node); static struct attribute *platform_dev_attrs[] = { &dev_attr_modalias.attr, &dev_attr_numa_node.attr, NULL, }; static umode_t platform_dev_attrs_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = container_of(kobj, typeof(*dev), kobj); if (a == &dev_attr_numa_node.attr && dev_to_node(dev) == NUMA_NO_NODE) return 0; return a->mode; } static const struct attribute_group platform_dev_group = { .attrs = platform_dev_attrs, .is_visible = platform_dev_attrs_visible, }; __ATTRIBUTE_GROUPS(platform_dev); /** * platform_match - bind platform device to platform driver. * @dev: device. * @drv: driver. * * Platform device IDs are assumed to be encoded like this: * "<name><instance>", where <name> is a short description of the type of * device, like "pci" or "floppy", and <instance> is the enumerated * instance of the device, like '0' or '42'. Driver IDs are simply * "<name>". So, extract the <name> from the platform_device structure, * and compare it against the name of the driver. Return whether they match * or not. */ static int platform_match(struct device *dev, const struct device_driver *drv) { struct platform_device *pdev = to_platform_device(dev); struct platform_driver *pdrv = to_platform_driver(drv); int ret; /* When driver_override is set, only bind to the matching driver */ ret = device_match_driver_override(dev, drv); if (ret >= 0) return ret; /* Attempt an OF style match first */ if (of_driver_match_device(dev, drv)) return 1; /* Then try ACPI style match */ if (acpi_driver_match_device(dev, drv)) return 1; /* Then try to match against the id table */ if (pdrv->id_table) return platform_match_id(pdrv->id_table, pdev) != NULL; /* fall-back to driver name match */ return (strcmp(pdev->name, drv->name) == 0); } static int platform_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct platform_device *pdev = to_platform_device(dev); int rc; /* Some devices have extra OF data and an OF-style MODALIAS */ rc = of_device_uevent_modalias(dev, env); if (rc != -ENODEV) return rc; rc = acpi_device_uevent_modalias(dev, env); if (rc != -ENODEV) return rc; add_uevent_var(env, "MODALIAS=%s%s", PLATFORM_MODULE_PREFIX, pdev->name); return 0; } static int platform_probe(struct device *_dev) { struct platform_driver *drv = to_platform_driver(_dev->driver); struct platform_device *dev = to_platform_device(_dev); int ret; /* * A driver registered using platform_driver_probe() cannot be bound * again later because the probe function usually lives in __init code * and so is gone. For these drivers .probe is set to * platform_probe_fail in __platform_driver_probe(). Don't even prepare * clocks and PM domains for these to match the traditional behaviour. */ if (unlikely(drv->probe == platform_probe_fail)) return -ENXIO; ret = of_clk_set_defaults(_dev->of_node, false); if (ret < 0) return ret; ret = dev_pm_domain_attach(_dev, PD_FLAG_ATTACH_POWER_ON | PD_FLAG_DETACH_POWER_OFF); if (ret) goto out; if (drv->probe) ret = drv->probe(dev); out: if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) { dev_warn(_dev, "probe deferral not supported\n"); ret = -ENXIO; } return ret; } static void platform_remove(struct device *_dev) { struct platform_driver *drv = to_platform_driver(_dev->driver); struct platform_device *dev = to_platform_device(_dev); if (drv->remove) drv->remove(dev); } static void platform_shutdown(struct device *_dev) { struct platform_device *dev = to_platform_device(_dev); struct platform_driver *drv; if (!_dev->driver) return; drv = to_platform_driver(_dev->driver); if (drv->shutdown) drv->shutdown(dev); } static int platform_dma_configure(struct device *dev) { struct device_driver *drv = READ_ONCE(dev->driver); struct fwnode_handle *fwnode = dev_fwnode(dev); enum dev_dma_attr attr; int ret = 0; if (is_of_node(fwnode)) { ret = of_dma_configure(dev, to_of_node(fwnode), true); } else if (is_acpi_device_node(fwnode)) { attr = acpi_get_dma_attr(to_acpi_device_node(fwnode)); ret = acpi_dma_configure(dev, attr); } /* @dev->driver may not be valid when we're called from the IOMMU layer */ if (ret || !drv || to_platform_driver(drv)->driver_managed_dma) return ret; ret = iommu_device_use_default_domain(dev); if (ret) arch_teardown_dma_ops(dev); return ret; } static void platform_dma_cleanup(struct device *dev) { struct platform_driver *drv = to_platform_driver(dev->driver); if (!drv->driver_managed_dma) iommu_device_unuse_default_domain(dev); } static const struct dev_pm_ops platform_dev_pm_ops = { SET_RUNTIME_PM_OPS(pm_generic_runtime_suspend, pm_generic_runtime_resume, NULL) USE_PLATFORM_PM_SLEEP_OPS }; const struct bus_type platform_bus_type = { .name = "platform", .dev_groups = platform_dev_groups, .driver_override = true, .match = platform_match, .uevent = platform_uevent, .probe = platform_probe, .remove = platform_remove, .shutdown = platform_shutdown, .dma_configure = platform_dma_configure, .dma_cleanup = platform_dma_cleanup, .pm = &platform_dev_pm_ops, }; EXPORT_SYMBOL_GPL(platform_bus_type); static inline int __platform_match(struct device *dev, const void *drv) { return platform_match(dev, (struct device_driver *)drv); } /** * platform_find_device_by_driver - Find a platform device with a given * driver. * @start: The device to start the search from. * @drv: The device driver to look for. */ struct device *platform_find_device_by_driver(struct device *start, const struct device_driver *drv) { return bus_find_device(&platform_bus_type, start, drv, __platform_match); } EXPORT_SYMBOL_GPL(platform_find_device_by_driver); void __weak __init early_platform_cleanup(void) { } int __init platform_bus_init(void) { int error; early_platform_cleanup(); error = device_register(&platform_bus); if (error) { put_device(&platform_bus); return error; } error = bus_register(&platform_bus_type); if (error) device_unregister(&platform_bus); return error; } |
| 12 12 12 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/netfilter/ipset/pfxlen.h> /* Prefixlen maps for fast conversions, by Jan Engelhardt. */ #ifdef E #undef E #endif #define PREFIXES_MAP \ E(0x00000000, 0x00000000, 0x00000000, 0x00000000), \ E(0x80000000, 0x00000000, 0x00000000, 0x00000000), \ E(0xC0000000, 0x00000000, 0x00000000, 0x00000000), \ E(0xE0000000, 0x00000000, 0x00000000, 0x00000000), \ E(0xF0000000, 0x00000000, 0x00000000, 0x00000000), \ E(0xF8000000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFC000000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFE000000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFF000000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFF800000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFC00000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFE00000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFF00000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFF80000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFC0000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFE0000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFF0000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFF8000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFC000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFE000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFF000, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFF800, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFFC00, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFFE00, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFFF00, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFFF80, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFFFC0, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFFFE0, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFFFF0, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFFFF8, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFFFFC, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFFFFE, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0x00000000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0x80000000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xC0000000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xE0000000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xF0000000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xF8000000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFC000000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFE000000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFF000000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFF800000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFC00000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFE00000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFF00000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFF80000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFC0000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFE0000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFF0000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFF8000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFC000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFE000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFF000, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFF800, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFC00, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFE00, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFF00, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFF80, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFC0, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFE0, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFF0, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFF8, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFC, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFE, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0x00000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0x80000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x80000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE), \ E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF), #define E(a, b, c, d) \ {.ip6 = { \ htonl(a), htonl(b), \ htonl(c), htonl(d), \ } } /* This table works for both IPv4 and IPv6; * just use prefixlen_netmask_map[prefixlength].ip. */ const union nf_inet_addr ip_set_netmask_map[] = { PREFIXES_MAP }; EXPORT_SYMBOL_GPL(ip_set_netmask_map); #undef E #define E(a, b, c, d) \ {.ip6 = { (__force __be32)a, (__force __be32)b, \ (__force __be32)c, (__force __be32)d, \ } } /* This table works for both IPv4 and IPv6; * just use prefixlen_hostmask_map[prefixlength].ip. */ const union nf_inet_addr ip_set_hostmask_map[] = { PREFIXES_MAP }; EXPORT_SYMBOL_GPL(ip_set_hostmask_map); /* Find the largest network which matches the range from left, in host order. */ u32 ip_set_range_to_cidr(u32 from, u32 to, u8 *cidr) { u32 last; u8 i; for (i = 1; i < 32; i++) { if ((from & ip_set_hostmask(i)) != from) continue; last = from | ~ip_set_hostmask(i); if (!after(last, to)) { *cidr = i; return last; } } *cidr = 32; return from; } EXPORT_SYMBOL_GPL(ip_set_range_to_cidr); |
| 22 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) 2011 Instituto Nokia de Tecnologia * Copyright (C) 2014 Marvell International Ltd. * * Authors: * Lauro Ramos Venancio <lauro.venancio@openbossa.org> * Aloisio Almeida Jr <aloisio.almeida@openbossa.org> */ #ifndef __NET_NFC_H #define __NET_NFC_H #include <linux/nfc.h> #include <linux/device.h> #include <linux/skbuff.h> #define nfc_dbg(dev, fmt, ...) dev_dbg((dev), "NFC: " fmt, ##__VA_ARGS__) #define nfc_info(dev, fmt, ...) dev_info((dev), "NFC: " fmt, ##__VA_ARGS__) #define nfc_err(dev, fmt, ...) dev_err((dev), "NFC: " fmt, ##__VA_ARGS__) struct nfc_phy_ops { int (*write)(void *dev_id, struct sk_buff *skb); int (*enable)(void *dev_id); void (*disable)(void *dev_id); }; struct nfc_dev; /** * data_exchange_cb_t - Definition of nfc_data_exchange callback * * @context: nfc_data_exchange cb_context parameter * @skb: response data * @err: If an error has occurred during data exchange, it is the * error number. Zero means no error. * * When a rx or tx package is lost or corrupted or the target gets out * of the operating field, err is -EIO. */ typedef void (*data_exchange_cb_t)(void *context, struct sk_buff *skb, int err); typedef void (*se_io_cb_t)(void *context, u8 *apdu, size_t apdu_len, int err); struct nfc_target; struct nfc_ops { int (*dev_up)(struct nfc_dev *dev); int (*dev_down)(struct nfc_dev *dev); int (*start_poll)(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols); void (*stop_poll)(struct nfc_dev *dev); int (*dep_link_up)(struct nfc_dev *dev, struct nfc_target *target, u8 comm_mode, u8 *gb, size_t gb_len); int (*dep_link_down)(struct nfc_dev *dev); int (*activate_target)(struct nfc_dev *dev, struct nfc_target *target, u32 protocol); void (*deactivate_target)(struct nfc_dev *dev, struct nfc_target *target, u8 mode); int (*im_transceive)(struct nfc_dev *dev, struct nfc_target *target, struct sk_buff *skb, data_exchange_cb_t cb, void *cb_context); int (*tm_send)(struct nfc_dev *dev, struct sk_buff *skb); int (*check_presence)(struct nfc_dev *dev, struct nfc_target *target); int (*fw_download)(struct nfc_dev *dev, const char *firmware_name); /* Secure Element API */ int (*discover_se)(struct nfc_dev *dev); int (*enable_se)(struct nfc_dev *dev, u32 se_idx); int (*disable_se)(struct nfc_dev *dev, u32 se_idx); int (*se_io) (struct nfc_dev *dev, u32 se_idx, u8 *apdu, size_t apdu_length, se_io_cb_t cb, void *cb_context); }; #define NFC_TARGET_IDX_ANY -1 #define NFC_MAX_GT_LEN 48 #define NFC_ATR_RES_GT_OFFSET 15 #define NFC_ATR_REQ_GT_OFFSET 14 /** * struct nfc_target - NFC target description * * @sens_res: 2 bytes describing the target SENS_RES response, if the target * is a type A one. The %sens_res most significant byte must be byte 2 * as described by the NFC Forum digital specification (i.e. the platform * configuration one) while %sens_res least significant byte is byte 1. * @ats_len: length of Answer To Select in bytes * @ats: Answer To Select returned by an ISO 14443 Type A target upon activation */ struct nfc_target { u32 idx; u32 supported_protocols; u16 sens_res; u8 sel_res; u8 nfcid1_len; u8 nfcid1[NFC_NFCID1_MAXSIZE]; u8 nfcid2_len; u8 nfcid2[NFC_NFCID2_MAXSIZE]; u8 sensb_res_len; u8 sensb_res[NFC_SENSB_RES_MAXSIZE]; u8 sensf_res_len; u8 sensf_res[NFC_SENSF_RES_MAXSIZE]; u8 hci_reader_gate; u8 logical_idx; u8 is_iso15693; u8 iso15693_dsfid; u8 iso15693_uid[NFC_ISO15693_UID_MAXSIZE]; u8 ats_len; u8 ats[NFC_ATS_MAXSIZE]; }; /** * nfc_se - A structure for NFC accessible secure elements. * * @idx: The secure element index. User space will enable or * disable a secure element by its index. * @type: The secure element type. It can be SE_UICC or * SE_EMBEDDED. * @state: The secure element state, either enabled or disabled. * */ struct nfc_se { struct list_head list; u32 idx; u16 type; u16 state; }; /** * nfc_evt_transaction - A struct for NFC secure element event transaction. * * @aid: The application identifier triggering the event * * @aid_len: The application identifier length [5:16] * * @params: The application parameters transmitted during the transaction * * @params_len: The applications parameters length [0:255] * */ #define NFC_MIN_AID_LENGTH 5 #define NFC_MAX_AID_LENGTH 16 #define NFC_MAX_PARAMS_LENGTH 255 #define NFC_EVT_TRANSACTION_AID_TAG 0x81 #define NFC_EVT_TRANSACTION_PARAMS_TAG 0x82 struct nfc_evt_transaction { u32 aid_len; u8 aid[NFC_MAX_AID_LENGTH]; u8 params_len; u8 params[]; } __packed; struct nfc_genl_data { u32 poll_req_portid; struct mutex genl_data_mutex; }; struct nfc_vendor_cmd { __u32 vendor_id; __u32 subcmd; int (*doit)(struct nfc_dev *dev, void *data, size_t data_len); }; struct nfc_dev { int idx; u32 target_next_idx; struct nfc_target *targets; int n_targets; int targets_generation; struct device dev; bool dev_up; bool fw_download_in_progress; u8 rf_mode; bool polling; struct nfc_target *active_target; bool dep_link_up; struct nfc_genl_data genl_data; u32 supported_protocols; struct list_head secure_elements; int tx_headroom; int tx_tailroom; struct timer_list check_pres_timer; struct work_struct check_pres_work; bool shutting_down; struct rfkill *rfkill; const struct nfc_vendor_cmd *vendor_cmds; int n_vendor_cmds; const struct nfc_ops *ops; struct genl_info *cur_cmd_info; }; #define to_nfc_dev(_dev) container_of(_dev, struct nfc_dev, dev) extern const struct class nfc_class; struct nfc_dev *nfc_allocate_device(const struct nfc_ops *ops, u32 supported_protocols, int tx_headroom, int tx_tailroom); /** * nfc_free_device - free nfc device * * @dev: The nfc device to free */ static inline void nfc_free_device(struct nfc_dev *dev) { put_device(&dev->dev); } int nfc_register_device(struct nfc_dev *dev); void nfc_unregister_rfkill(struct nfc_dev *dev); void nfc_remove_device(struct nfc_dev *dev); void nfc_unregister_device(struct nfc_dev *dev); /** * nfc_set_parent_dev - set the parent device * * @nfc_dev: The nfc device whose parent is being set * @dev: The parent device */ static inline void nfc_set_parent_dev(struct nfc_dev *nfc_dev, struct device *dev) { nfc_dev->dev.parent = dev; } /** * nfc_set_drvdata - set driver specific data * * @dev: The nfc device * @data: Pointer to driver specific data */ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) { dev_set_drvdata(&dev->dev, data); } /** * nfc_get_drvdata - get driver specific data * * @dev: The nfc device */ static inline void *nfc_get_drvdata(const struct nfc_dev *dev) { return dev_get_drvdata(&dev->dev); } /** * nfc_device_name - get the nfc device name * * @dev: The nfc device whose name to return */ static inline const char *nfc_device_name(const struct nfc_dev *dev) { return dev_name(&dev->dev); } struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk, unsigned int flags, unsigned int size, unsigned int *err); struct sk_buff *nfc_alloc_recv_skb(unsigned int size, gfp_t gfp); int nfc_set_remote_general_bytes(struct nfc_dev *dev, const u8 *gt, u8 gt_len); u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, size_t *gb_len); int nfc_fw_download_done(struct nfc_dev *dev, const char *firmware_name, u32 result); int nfc_targets_found(struct nfc_dev *dev, struct nfc_target *targets, int ntargets); int nfc_target_lost(struct nfc_dev *dev, u32 target_idx); int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, const u8 *gb, size_t gb_len); int nfc_tm_deactivated(struct nfc_dev *dev); int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb); void nfc_driver_failure(struct nfc_dev *dev, int err); int nfc_se_transaction(struct nfc_dev *dev, u8 se_idx, struct nfc_evt_transaction *evt_transaction); int nfc_se_connectivity(struct nfc_dev *dev, u8 se_idx); int nfc_add_se(struct nfc_dev *dev, u32 se_idx, u16 type); int nfc_remove_se(struct nfc_dev *dev, u32 se_idx); struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx); void nfc_send_to_raw_sock(struct nfc_dev *dev, struct sk_buff *skb, u8 payload_type, u8 direction); static inline int nfc_set_vendor_cmds(struct nfc_dev *dev, const struct nfc_vendor_cmd *cmds, int n_cmds) { if (dev->vendor_cmds || dev->n_vendor_cmds) return -EINVAL; dev->vendor_cmds = cmds; dev->n_vendor_cmds = n_cmds; return 0; } struct sk_buff *__nfc_alloc_vendor_cmd_reply_skb(struct nfc_dev *dev, enum nfc_attrs attr, u32 oui, u32 subcmd, int approxlen); int nfc_vendor_cmd_reply(struct sk_buff *skb); /** * nfc_vendor_cmd_alloc_reply_skb - allocate vendor command reply * @dev: nfc device * @oui: vendor oui * @approxlen: an upper bound of the length of the data that will * be put into the skb * * This function allocates and pre-fills an skb for a reply to * a vendor command. Since it is intended for a reply, calling * it outside of a vendor command's doit() operation is invalid. * * The returned skb is pre-filled with some identifying data in * a way that any data that is put into the skb (with skb_put(), * nla_put() or similar) will end up being within the * %NFC_ATTR_VENDOR_DATA attribute, so all that needs to be done * with the skb is adding data for the corresponding userspace tool * which can then read that data out of the vendor data attribute. * You must not modify the skb in any other way. * * When done, call nfc_vendor_cmd_reply() with the skb and return * its error code as the result of the doit() operation. * * Return: An allocated and pre-filled skb. %NULL if any errors happen. */ static inline struct sk_buff * nfc_vendor_cmd_alloc_reply_skb(struct nfc_dev *dev, u32 oui, u32 subcmd, int approxlen) { return __nfc_alloc_vendor_cmd_reply_skb(dev, NFC_ATTR_VENDOR_DATA, oui, subcmd, approxlen); } #endif /* __NET_NFC_H */ |
| 32 31 16 31 31 32 32 32 32 32 32 32 31 16 16 16 31 16 | 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 | // SPDX-License-Identifier: GPL-2.0 OR MIT /* * Copyright (C) 2020 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * Copyright (c) 2016-2020 INRIA, CMU and Microsoft Corporation */ #include <linux/types.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <asm/cpufeature.h> #include <asm/processor.h> static __always_inline u64 eq_mask(u64 a, u64 b) { u64 x = a ^ b; u64 minus_x = ~x + (u64)1U; u64 x_or_minus_x = x | minus_x; u64 xnx = x_or_minus_x >> (u32)63U; return xnx - (u64)1U; } static __always_inline u64 gte_mask(u64 a, u64 b) { u64 x = a; u64 y = b; u64 x_xor_y = x ^ y; u64 x_sub_y = x - y; u64 x_sub_y_xor_y = x_sub_y ^ y; u64 q = x_xor_y | x_sub_y_xor_y; u64 x_xor_q = x ^ q; u64 x_xor_q_ = x_xor_q >> (u32)63U; return x_xor_q_ - (u64)1U; } /* Computes the addition of four-element f1 with value in f2 * and returns the carry (if any) */ static inline u64 add_scalar(u64 *out, const u64 *f1, u64 f2) { u64 carry_r; asm volatile( /* Clear registers to propagate the carry bit */ " xor %%r8d, %%r8d;" " xor %%r9d, %%r9d;" " xor %%r10d, %%r10d;" " xor %%r11d, %%r11d;" " xor %k1, %k1;" /* Begin addition chain */ " addq 0(%3), %0;" " movq %0, 0(%2);" " adcxq 8(%3), %%r8;" " movq %%r8, 8(%2);" " adcxq 16(%3), %%r9;" " movq %%r9, 16(%2);" " adcxq 24(%3), %%r10;" " movq %%r10, 24(%2);" /* Return the carry bit in a register */ " adcx %%r11, %1;" : "+&r"(f2), "=&r"(carry_r) : "r"(out), "r"(f1) : "%r8", "%r9", "%r10", "%r11", "memory", "cc"); return carry_r; } /* Computes the field addition of two field elements */ static inline void fadd(u64 *out, const u64 *f1, const u64 *f2) { asm volatile( /* Compute the raw addition of f1 + f2 */ " movq 0(%0), %%r8;" " addq 0(%2), %%r8;" " movq 8(%0), %%r9;" " adcxq 8(%2), %%r9;" " movq 16(%0), %%r10;" " adcxq 16(%2), %%r10;" " movq 24(%0), %%r11;" " adcxq 24(%2), %%r11;" /* Wrap the result back into the field */ /* Step 1: Compute carry*38 */ " mov $0, %%rax;" " mov $38, %0;" " cmovc %0, %%rax;" /* Step 2: Add carry*38 to the original sum */ " xor %%ecx, %%ecx;" " add %%rax, %%r8;" " adcx %%rcx, %%r9;" " movq %%r9, 8(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 16(%1);" " adcx %%rcx, %%r11;" " movq %%r11, 24(%1);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %0, %%rax;" " add %%rax, %%r8;" " movq %%r8, 0(%1);" : "+&r"(f2) : "r"(out), "r"(f1) : "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11", "memory", "cc"); } /* Computes the field subtraction of two field elements */ static inline void fsub(u64 *out, const u64 *f1, const u64 *f2) { asm volatile( /* Compute the raw subtraction of f1-f2 */ " movq 0(%1), %%r8;" " subq 0(%2), %%r8;" " movq 8(%1), %%r9;" " sbbq 8(%2), %%r9;" " movq 16(%1), %%r10;" " sbbq 16(%2), %%r10;" " movq 24(%1), %%r11;" " sbbq 24(%2), %%r11;" /* Wrap the result back into the field */ /* Step 1: Compute carry*38 */ " mov $0, %%rax;" " mov $38, %%rcx;" " cmovc %%rcx, %%rax;" /* Step 2: Subtract carry*38 from the original difference */ " sub %%rax, %%r8;" " sbb $0, %%r9;" " sbb $0, %%r10;" " sbb $0, %%r11;" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rcx, %%rax;" " sub %%rax, %%r8;" /* Store the result */ " movq %%r8, 0(%0);" " movq %%r9, 8(%0);" " movq %%r10, 16(%0);" " movq %%r11, 24(%0);" : : "r"(out), "r"(f1), "r"(f2) : "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11", "memory", "cc"); } /* Computes a field multiplication: out <- f1 * f2 * Uses the 8-element buffer tmp for intermediate results */ static inline void fmul(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) { asm volatile( /* Compute the raw multiplication: tmp <- src1 * src2 */ /* Compute src1[0] * src2 */ " movq 0(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " movq %%r8, 0(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" /* Compute src1[1] * src2 */ " movq 8(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 8(%2), %%r8;" " movq %%r8, 8(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 16(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[2] * src2 */ " movq 16(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 16(%2), %%r8;" " movq %%r8, 16(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 24(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[3] * src2 */ " movq 24(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 24(%2), %%r8;" " movq %%r8, 24(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 32(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 40(%2);" " mov $0, %%r8;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%2);" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 56(%2);" /* Line up pointers */ " mov %2, %0;" " mov %3, %2;" /* Wrap the result back into the field */ /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 32(%0), %%r8, %%r13;" " xor %k1, %k1;" " adoxq 0(%0), %%r8;" " mulxq 40(%0), %%r9, %%rbx;" " adcx %%r13, %%r9;" " adoxq 8(%0), %%r9;" " mulxq 48(%0), %%r10, %%r13;" " adcx %%rbx, %%r10;" " adoxq 16(%0), %%r10;" " mulxq 56(%0), %%r11, %%rax;" " adcx %%r13, %%r11;" " adoxq 24(%0), %%r11;" " adcx %1, %%rax;" " adox %1, %%rax;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %1, %%r9;" " movq %%r9, 8(%2);" " adcx %1, %%r10;" " movq %%r10, 16(%2);" " adcx %1, %%r11;" " movq %%r11, 24(%2);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 0(%2);" : "+&r"(f1), "+&r"(f2), "+&r"(tmp) : "r"(out) : "%rax", "%rbx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r13", "%r14", "memory", "cc"); } /* Computes two field multiplications: * out[0] <- f1[0] * f2[0] * out[1] <- f1[1] * f2[1] * Uses the 16-element buffer tmp for intermediate results: */ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) { asm volatile( /* Compute the raw multiplication tmp[0] <- f1[0] * f2[0] */ /* Compute src1[0] * src2 */ " movq 0(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " movq %%r8, 0(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" /* Compute src1[1] * src2 */ " movq 8(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 8(%2), %%r8;" " movq %%r8, 8(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 16(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[2] * src2 */ " movq 16(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 16(%2), %%r8;" " movq %%r8, 16(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 24(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[3] * src2 */ " movq 24(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 24(%2), %%r8;" " movq %%r8, 24(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 32(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 40(%2);" " mov $0, %%r8;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%2);" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 56(%2);" /* Compute the raw multiplication tmp[1] <- f1[1] * f2[1] */ /* Compute src1[0] * src2 */ " movq 32(%0), %%rdx;" " mulxq 32(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " movq %%r8, 64(%2);" " mulxq 40(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 72(%2);" " mulxq 48(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " mulxq 56(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" /* Compute src1[1] * src2 */ " movq 40(%0), %%rdx;" " mulxq 32(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 72(%2), %%r8;" " movq %%r8, 72(%2);" " mulxq 40(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 80(%2);" " mulxq 48(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 56(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[2] * src2 */ " movq 48(%0), %%rdx;" " mulxq 32(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 80(%2), %%r8;" " movq %%r8, 80(%2);" " mulxq 40(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 88(%2);" " mulxq 48(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 56(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[3] * src2 */ " movq 56(%0), %%rdx;" " mulxq 32(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 88(%2), %%r8;" " movq %%r8, 88(%2);" " mulxq 40(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 96(%2);" " mulxq 48(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 104(%2);" " mov $0, %%r8;" " mulxq 56(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 112(%2);" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 120(%2);" /* Line up pointers */ " mov %2, %0;" " mov %3, %2;" /* Wrap the results back into the field */ /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 32(%0), %%r8, %%r13;" " xor %k1, %k1;" " adoxq 0(%0), %%r8;" " mulxq 40(%0), %%r9, %%rbx;" " adcx %%r13, %%r9;" " adoxq 8(%0), %%r9;" " mulxq 48(%0), %%r10, %%r13;" " adcx %%rbx, %%r10;" " adoxq 16(%0), %%r10;" " mulxq 56(%0), %%r11, %%rax;" " adcx %%r13, %%r11;" " adoxq 24(%0), %%r11;" " adcx %1, %%rax;" " adox %1, %%rax;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %1, %%r9;" " movq %%r9, 8(%2);" " adcx %1, %%r10;" " movq %%r10, 16(%2);" " adcx %1, %%r11;" " movq %%r11, 24(%2);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 0(%2);" /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 96(%0), %%r8, %%r13;" " xor %k1, %k1;" " adoxq 64(%0), %%r8;" " mulxq 104(%0), %%r9, %%rbx;" " adcx %%r13, %%r9;" " adoxq 72(%0), %%r9;" " mulxq 112(%0), %%r10, %%r13;" " adcx %%rbx, %%r10;" " adoxq 80(%0), %%r10;" " mulxq 120(%0), %%r11, %%rax;" " adcx %%r13, %%r11;" " adoxq 88(%0), %%r11;" " adcx %1, %%rax;" " adox %1, %%rax;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %1, %%r9;" " movq %%r9, 40(%2);" " adcx %1, %%r10;" " movq %%r10, 48(%2);" " adcx %1, %%r11;" " movq %%r11, 56(%2);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 32(%2);" : "+&r"(f1), "+&r"(f2), "+&r"(tmp) : "r"(out) : "%rax", "%rbx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r13", "%r14", "memory", "cc"); } /* Computes the field multiplication of four-element f1 with value in f2 * Requires f2 to be smaller than 2^17 */ static inline void fmul_scalar(u64 *out, const u64 *f1, u64 f2) { register u64 f2_r asm("rdx") = f2; asm volatile( /* Compute the raw multiplication of f1*f2 */ " mulxq 0(%2), %%r8, %%rcx;" /* f1[0]*f2 */ " mulxq 8(%2), %%r9, %%rbx;" /* f1[1]*f2 */ " add %%rcx, %%r9;" " mov $0, %%rcx;" " mulxq 16(%2), %%r10, %%r13;" /* f1[2]*f2 */ " adcx %%rbx, %%r10;" " mulxq 24(%2), %%r11, %%rax;" /* f1[3]*f2 */ " adcx %%r13, %%r11;" " adcx %%rcx, %%rax;" /* Wrap the result back into the field */ /* Step 1: Compute carry*38 */ " mov $38, %%rdx;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %%rcx, %%r9;" " movq %%r9, 8(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 16(%1);" " adcx %%rcx, %%r11;" " movq %%r11, 24(%1);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 0(%1);" : "+&r"(f2_r) : "r"(out), "r"(f1) : "%rax", "%rbx", "%rcx", "%r8", "%r9", "%r10", "%r11", "%r13", "memory", "cc"); } /* Computes p1 <- bit ? p2 : p1 in constant time */ static inline void cswap2(u64 bit, const u64 *p1, const u64 *p2) { asm volatile( /* Transfer bit into CF flag */ " add $18446744073709551615, %0;" /* cswap p1[0], p2[0] */ " movq 0(%1), %%r8;" " movq 0(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 0(%1);" " movq %%r9, 0(%2);" /* cswap p1[1], p2[1] */ " movq 8(%1), %%r8;" " movq 8(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 8(%1);" " movq %%r9, 8(%2);" /* cswap p1[2], p2[2] */ " movq 16(%1), %%r8;" " movq 16(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 16(%1);" " movq %%r9, 16(%2);" /* cswap p1[3], p2[3] */ " movq 24(%1), %%r8;" " movq 24(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 24(%1);" " movq %%r9, 24(%2);" /* cswap p1[4], p2[4] */ " movq 32(%1), %%r8;" " movq 32(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 32(%1);" " movq %%r9, 32(%2);" /* cswap p1[5], p2[5] */ " movq 40(%1), %%r8;" " movq 40(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 40(%1);" " movq %%r9, 40(%2);" /* cswap p1[6], p2[6] */ " movq 48(%1), %%r8;" " movq 48(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 48(%1);" " movq %%r9, 48(%2);" /* cswap p1[7], p2[7] */ " movq 56(%1), %%r8;" " movq 56(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 56(%1);" " movq %%r9, 56(%2);" : "+&r"(bit) : "r"(p1), "r"(p2) : "%r8", "%r9", "%r10", "memory", "cc"); } /* Computes the square of a field element: out <- f * f * Uses the 8-element buffer tmp for intermediate results */ static inline void fsqr(u64 *out, const u64 *f, u64 *tmp) { asm volatile( /* Compute the raw multiplication: tmp <- f * f */ /* Step 1: Compute all partial products */ " movq 0(%0), %%rdx;" /* f[0] */ " mulxq 8(%0), %%r8, %%r14;" " xor %%r15d, %%r15d;" /* f[1]*f[0] */ " mulxq 16(%0), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ " mulxq 24(%0), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ " movq 24(%0), %%rdx;" /* f[3] */ " mulxq 8(%0), %%r11, %%rbx;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ " mulxq 16(%0), %%rax, %%r13;" " adcx %%rax, %%rbx;" /* f[2]*f[3] */ " movq 8(%0), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ " mulxq 16(%0), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ /* Step 2: Compute two parallel carry chains */ " xor %%r15d, %%r15d;" " adox %%rax, %%r10;" " adcx %%r8, %%r8;" " adox %%rcx, %%r11;" " adcx %%r9, %%r9;" " adox %%r15, %%rbx;" " adcx %%r10, %%r10;" " adox %%r15, %%r13;" " adcx %%r11, %%r11;" " adox %%r15, %%r14;" " adcx %%rbx, %%rbx;" " adcx %%r13, %%r13;" " adcx %%r14, %%r14;" /* Step 3: Compute intermediate squares */ " movq 0(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */ " movq %%rax, 0(%1);" " add %%rcx, %%r8;" " movq %%r8, 8(%1);" " movq 8(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */ " adcx %%rax, %%r9;" " movq %%r9, 16(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 24(%1);" " movq 16(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ " adcx %%rax, %%r11;" " movq %%r11, 32(%1);" " adcx %%rcx, %%rbx;" " movq %%rbx, 40(%1);" " movq 24(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ " adcx %%rax, %%r13;" " movq %%r13, 48(%1);" " adcx %%rcx, %%r14;" " movq %%r14, 56(%1);" /* Line up pointers */ " mov %1, %0;" " mov %2, %1;" /* Wrap the result back into the field */ /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 32(%0), %%r8, %%r13;" " xor %%ecx, %%ecx;" " adoxq 0(%0), %%r8;" " mulxq 40(%0), %%r9, %%rbx;" " adcx %%r13, %%r9;" " adoxq 8(%0), %%r9;" " mulxq 48(%0), %%r10, %%r13;" " adcx %%rbx, %%r10;" " adoxq 16(%0), %%r10;" " mulxq 56(%0), %%r11, %%rax;" " adcx %%r13, %%r11;" " adoxq 24(%0), %%r11;" " adcx %%rcx, %%rax;" " adox %%rcx, %%rax;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %%rcx, %%r9;" " movq %%r9, 8(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 16(%1);" " adcx %%rcx, %%r11;" " movq %%r11, 24(%1);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 0(%1);" : "+&r"(f), "+&r"(tmp) : "r"(out) : "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r13", "%r14", "%r15", "memory", "cc"); } /* Computes two field squarings: * out[0] <- f[0] * f[0] * out[1] <- f[1] * f[1] * Uses the 16-element buffer tmp for intermediate results */ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp) { asm volatile( /* Step 1: Compute all partial products */ " movq 0(%0), %%rdx;" /* f[0] */ " mulxq 8(%0), %%r8, %%r14;" " xor %%r15d, %%r15d;" /* f[1]*f[0] */ " mulxq 16(%0), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ " mulxq 24(%0), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ " movq 24(%0), %%rdx;" /* f[3] */ " mulxq 8(%0), %%r11, %%rbx;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ " mulxq 16(%0), %%rax, %%r13;" " adcx %%rax, %%rbx;" /* f[2]*f[3] */ " movq 8(%0), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ " mulxq 16(%0), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ /* Step 2: Compute two parallel carry chains */ " xor %%r15d, %%r15d;" " adox %%rax, %%r10;" " adcx %%r8, %%r8;" " adox %%rcx, %%r11;" " adcx %%r9, %%r9;" " adox %%r15, %%rbx;" " adcx %%r10, %%r10;" " adox %%r15, %%r13;" " adcx %%r11, %%r11;" " adox %%r15, %%r14;" " adcx %%rbx, %%rbx;" " adcx %%r13, %%r13;" " adcx %%r14, %%r14;" /* Step 3: Compute intermediate squares */ " movq 0(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */ " movq %%rax, 0(%1);" " add %%rcx, %%r8;" " movq %%r8, 8(%1);" " movq 8(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */ " adcx %%rax, %%r9;" " movq %%r9, 16(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 24(%1);" " movq 16(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ " adcx %%rax, %%r11;" " movq %%r11, 32(%1);" " adcx %%rcx, %%rbx;" " movq %%rbx, 40(%1);" " movq 24(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ " adcx %%rax, %%r13;" " movq %%r13, 48(%1);" " adcx %%rcx, %%r14;" " movq %%r14, 56(%1);" /* Step 1: Compute all partial products */ " movq 32(%0), %%rdx;" /* f[0] */ " mulxq 40(%0), %%r8, %%r14;" " xor %%r15d, %%r15d;" /* f[1]*f[0] */ " mulxq 48(%0), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ " mulxq 56(%0), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ " movq 56(%0), %%rdx;" /* f[3] */ " mulxq 40(%0), %%r11, %%rbx;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ " mulxq 48(%0), %%rax, %%r13;" " adcx %%rax, %%rbx;" /* f[2]*f[3] */ " movq 40(%0), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ " mulxq 48(%0), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ /* Step 2: Compute two parallel carry chains */ " xor %%r15d, %%r15d;" " adox %%rax, %%r10;" " adcx %%r8, %%r8;" " adox %%rcx, %%r11;" " adcx %%r9, %%r9;" " adox %%r15, %%rbx;" " adcx %%r10, %%r10;" " adox %%r15, %%r13;" " adcx %%r11, %%r11;" " adox %%r15, %%r14;" " adcx %%rbx, %%rbx;" " adcx %%r13, %%r13;" " adcx %%r14, %%r14;" /* Step 3: Compute intermediate squares */ " movq 32(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */ " movq %%rax, 64(%1);" " add %%rcx, %%r8;" " movq %%r8, 72(%1);" " movq 40(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */ " adcx %%rax, %%r9;" " movq %%r9, 80(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 88(%1);" " movq 48(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ " adcx %%rax, %%r11;" " movq %%r11, 96(%1);" " adcx %%rcx, %%rbx;" " movq %%rbx, 104(%1);" " movq 56(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ " adcx %%rax, %%r13;" " movq %%r13, 112(%1);" " adcx %%rcx, %%r14;" " movq %%r14, 120(%1);" /* Line up pointers */ " mov %1, %0;" " mov %2, %1;" /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 32(%0), %%r8, %%r13;" " xor %%ecx, %%ecx;" " adoxq 0(%0), %%r8;" " mulxq 40(%0), %%r9, %%rbx;" " adcx %%r13, %%r9;" " adoxq 8(%0), %%r9;" " mulxq 48(%0), %%r10, %%r13;" " adcx %%rbx, %%r10;" " adoxq 16(%0), %%r10;" " mulxq 56(%0), %%r11, %%rax;" " adcx %%r13, %%r11;" " adoxq 24(%0), %%r11;" " adcx %%rcx, %%rax;" " adox %%rcx, %%rax;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %%rcx, %%r9;" " movq %%r9, 8(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 16(%1);" " adcx %%rcx, %%r11;" " movq %%r11, 24(%1);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 0(%1);" /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 96(%0), %%r8, %%r13;" " xor %%ecx, %%ecx;" " adoxq 64(%0), %%r8;" " mulxq 104(%0), %%r9, %%rbx;" " adcx %%r13, %%r9;" " adoxq 72(%0), %%r9;" " mulxq 112(%0), %%r10, %%r13;" " adcx %%rbx, %%r10;" " adoxq 80(%0), %%r10;" " mulxq 120(%0), %%r11, %%rax;" " adcx %%r13, %%r11;" " adoxq 88(%0), %%r11;" " adcx %%rcx, %%rax;" " adox %%rcx, %%rax;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %%rcx, %%r9;" " movq %%r9, 40(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 48(%1);" " adcx %%rcx, %%r11;" " movq %%r11, 56(%1);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 32(%1);" : "+&r"(f), "+&r"(tmp) : "r"(out) : "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r13", "%r14", "%r15", "memory", "cc"); } static void point_add_and_double(u64 *q, u64 *p01_tmp1, u64 *tmp2) { u64 *nq = p01_tmp1; u64 *nq_p1 = p01_tmp1 + (u32)8U; u64 *tmp1 = p01_tmp1 + (u32)16U; u64 *x1 = q; u64 *x2 = nq; u64 *z2 = nq + (u32)4U; u64 *z3 = nq_p1 + (u32)4U; u64 *a = tmp1; u64 *b = tmp1 + (u32)4U; u64 *ab = tmp1; u64 *dc = tmp1 + (u32)8U; u64 *x3; u64 *z31; u64 *d0; u64 *c0; u64 *a1; u64 *b1; u64 *d; u64 *c; u64 *ab1; u64 *dc1; fadd(a, x2, z2); fsub(b, x2, z2); x3 = nq_p1; z31 = nq_p1 + (u32)4U; d0 = dc; c0 = dc + (u32)4U; fadd(c0, x3, z31); fsub(d0, x3, z31); fmul2(dc, dc, ab, tmp2); fadd(x3, d0, c0); fsub(z31, d0, c0); a1 = tmp1; b1 = tmp1 + (u32)4U; d = tmp1 + (u32)8U; c = tmp1 + (u32)12U; ab1 = tmp1; dc1 = tmp1 + (u32)8U; fsqr2(dc1, ab1, tmp2); fsqr2(nq_p1, nq_p1, tmp2); a1[0U] = c[0U]; a1[1U] = c[1U]; a1[2U] = c[2U]; a1[3U] = c[3U]; fsub(c, d, c); fmul_scalar(b1, c, (u64)121665U); fadd(b1, b1, d); fmul2(nq, dc1, ab1, tmp2); fmul(z3, z3, x1, tmp2); } static void point_double(u64 *nq, u64 *tmp1, u64 *tmp2) { u64 *x2 = nq; u64 *z2 = nq + (u32)4U; u64 *a = tmp1; u64 *b = tmp1 + (u32)4U; u64 *d = tmp1 + (u32)8U; u64 *c = tmp1 + (u32)12U; u64 *ab = tmp1; u64 *dc = tmp1 + (u32)8U; fadd(a, x2, z2); fsub(b, x2, z2); fsqr2(dc, ab, tmp2); a[0U] = c[0U]; a[1U] = c[1U]; a[2U] = c[2U]; a[3U] = c[3U]; fsub(c, d, c); fmul_scalar(b, c, (u64)121665U); fadd(b, b, d); fmul2(nq, dc, ab, tmp2); } static void montgomery_ladder(u64 *out, const u8 *key, u64 *init1) { u64 tmp2[16U] = { 0U }; u64 p01_tmp1_swap[33U] = { 0U }; u64 *p0 = p01_tmp1_swap; u64 *p01 = p01_tmp1_swap; u64 *p03 = p01; u64 *p11 = p01 + (u32)8U; u64 *x0; u64 *z0; u64 *p01_tmp1; u64 *p01_tmp11; u64 *nq10; u64 *nq_p11; u64 *swap1; u64 sw0; u64 *nq1; u64 *tmp1; memcpy(p11, init1, (u32)8U * sizeof(init1[0U])); x0 = p03; z0 = p03 + (u32)4U; x0[0U] = (u64)1U; x0[1U] = (u64)0U; x0[2U] = (u64)0U; x0[3U] = (u64)0U; z0[0U] = (u64)0U; z0[1U] = (u64)0U; z0[2U] = (u64)0U; z0[3U] = (u64)0U; p01_tmp1 = p01_tmp1_swap; p01_tmp11 = p01_tmp1_swap; nq10 = p01_tmp1_swap; nq_p11 = p01_tmp1_swap + (u32)8U; swap1 = p01_tmp1_swap + (u32)32U; cswap2((u64)1U, nq10, nq_p11); point_add_and_double(init1, p01_tmp11, tmp2); swap1[0U] = (u64)1U; { u32 i; for (i = (u32)0U; i < (u32)251U; i = i + (u32)1U) { u64 *p01_tmp12 = p01_tmp1_swap; u64 *swap2 = p01_tmp1_swap + (u32)32U; u64 *nq2 = p01_tmp12; u64 *nq_p12 = p01_tmp12 + (u32)8U; u64 bit = (u64)(key[((u32)253U - i) / (u32)8U] >> ((u32)253U - i) % (u32)8U & (u8)1U); u64 sw = swap2[0U] ^ bit; cswap2(sw, nq2, nq_p12); point_add_and_double(init1, p01_tmp12, tmp2); swap2[0U] = bit; } } sw0 = swap1[0U]; cswap2(sw0, nq10, nq_p11); nq1 = p01_tmp1; tmp1 = p01_tmp1 + (u32)16U; point_double(nq1, tmp1, tmp2); point_double(nq1, tmp1, tmp2); point_double(nq1, tmp1, tmp2); memcpy(out, p0, (u32)8U * sizeof(p0[0U])); memzero_explicit(tmp2, sizeof(tmp2)); memzero_explicit(p01_tmp1_swap, sizeof(p01_tmp1_swap)); } static void fsquare_times(u64 *o, const u64 *inp, u64 *tmp, u32 n1) { u32 i; fsqr(o, inp, tmp); for (i = (u32)0U; i < n1 - (u32)1U; i = i + (u32)1U) fsqr(o, o, tmp); } static void finv(u64 *o, const u64 *i, u64 *tmp) { u64 t1[16U] = { 0U }; u64 *a0 = t1; u64 *b = t1 + (u32)4U; u64 *c = t1 + (u32)8U; u64 *t00 = t1 + (u32)12U; u64 *tmp1 = tmp; u64 *a; u64 *t0; fsquare_times(a0, i, tmp1, (u32)1U); fsquare_times(t00, a0, tmp1, (u32)2U); fmul(b, t00, i, tmp); fmul(a0, b, a0, tmp); fsquare_times(t00, a0, tmp1, (u32)1U); fmul(b, t00, b, tmp); fsquare_times(t00, b, tmp1, (u32)5U); fmul(b, t00, b, tmp); fsquare_times(t00, b, tmp1, (u32)10U); fmul(c, t00, b, tmp); fsquare_times(t00, c, tmp1, (u32)20U); fmul(t00, t00, c, tmp); fsquare_times(t00, t00, tmp1, (u32)10U); fmul(b, t00, b, tmp); fsquare_times(t00, b, tmp1, (u32)50U); fmul(c, t00, b, tmp); fsquare_times(t00, c, tmp1, (u32)100U); fmul(t00, t00, c, tmp); fsquare_times(t00, t00, tmp1, (u32)50U); fmul(t00, t00, b, tmp); fsquare_times(t00, t00, tmp1, (u32)5U); a = t1; t0 = t1 + (u32)12U; fmul(o, t0, a, tmp); } static void store_felem(u64 *b, u64 *f) { u64 f30 = f[3U]; u64 top_bit0 = f30 >> (u32)63U; u64 f31; u64 top_bit; u64 f0; u64 f1; u64 f2; u64 f3; u64 m0; u64 m1; u64 m2; u64 m3; u64 mask; u64 f0_; u64 f1_; u64 f2_; u64 f3_; u64 o0; u64 o1; u64 o2; u64 o3; f[3U] = f30 & (u64)0x7fffffffffffffffU; add_scalar(f, f, (u64)19U * top_bit0); f31 = f[3U]; top_bit = f31 >> (u32)63U; f[3U] = f31 & (u64)0x7fffffffffffffffU; add_scalar(f, f, (u64)19U * top_bit); f0 = f[0U]; f1 = f[1U]; f2 = f[2U]; f3 = f[3U]; m0 = gte_mask(f0, (u64)0xffffffffffffffedU); m1 = eq_mask(f1, (u64)0xffffffffffffffffU); m2 = eq_mask(f2, (u64)0xffffffffffffffffU); m3 = eq_mask(f3, (u64)0x7fffffffffffffffU); mask = ((m0 & m1) & m2) & m3; f0_ = f0 - (mask & (u64)0xffffffffffffffedU); f1_ = f1 - (mask & (u64)0xffffffffffffffffU); f2_ = f2 - (mask & (u64)0xffffffffffffffffU); f3_ = f3 - (mask & (u64)0x7fffffffffffffffU); o0 = f0_; o1 = f1_; o2 = f2_; o3 = f3_; b[0U] = o0; b[1U] = o1; b[2U] = o2; b[3U] = o3; } static void encode_point(u8 *o, const u64 *i) { const u64 *x = i; const u64 *z = i + (u32)4U; u64 tmp[4U] = { 0U }; u64 tmp_w[16U] = { 0U }; finv(tmp, z, tmp_w); fmul(tmp, tmp, x, tmp_w); store_felem((u64 *)o, tmp); } static void curve25519_ever64(u8 *out, const u8 *priv, const u8 *pub) { u64 init1[8U] = { 0U }; u64 tmp[4U] = { 0U }; u64 tmp3; u64 *x; u64 *z; { u32 i; for (i = (u32)0U; i < (u32)4U; i = i + (u32)1U) { u64 *os = tmp; const u8 *bj = pub + i * (u32)8U; u64 u = *(u64 *)bj; u64 r = u; u64 x0 = r; os[i] = x0; } } tmp3 = tmp[3U]; tmp[3U] = tmp3 & (u64)0x7fffffffffffffffU; x = init1; z = init1 + (u32)4U; z[0U] = (u64)1U; z[1U] = (u64)0U; z[2U] = (u64)0U; z[3U] = (u64)0U; x[0U] = tmp[0U]; x[1U] = tmp[1U]; x[2U] = tmp[2U]; x[3U] = tmp[3U]; montgomery_ladder(init1, priv, init1); encode_point(out, init1); } /* The below constants were generated using this sage script: * * #!/usr/bin/env sage * import sys * from sage.all import * * def limbs(n): * n = int(n) * l = ((n >> 0) % 2^64, (n >> 64) % 2^64, (n >> 128) % 2^64, (n >> 192) % 2^64) * return "0x%016xULL, 0x%016xULL, 0x%016xULL, 0x%016xULL" % l * ec = EllipticCurve(GF(2^255 - 19), [0, 486662, 0, 1, 0]) * p_minus_s = (ec.lift_x(9) - ec.lift_x(1))[0] * print("static const u64 p_minus_s[] = { %s };\n" % limbs(p_minus_s)) * print("static const u64 table_ladder[] = {") * p = ec.lift_x(9) * for i in range(252): * l = (p[0] + p[2]) / (p[0] - p[2]) * print(("\t%s" + ("," if i != 251 else "")) % limbs(l)) * p = p * 2 * print("};") * */ static const u64 p_minus_s[] = { 0x816b1e0137d48290ULL, 0x440f6a51eb4d1207ULL, 0x52385f46dca2b71dULL, 0x215132111d8354cbULL }; static const u64 table_ladder[] = { 0xfffffffffffffff3ULL, 0xffffffffffffffffULL, 0xffffffffffffffffULL, 0x5fffffffffffffffULL, 0x6b8220f416aafe96ULL, 0x82ebeb2b4f566a34ULL, 0xd5a9a5b075a5950fULL, 0x5142b2cf4b2488f4ULL, 0x6aaebc750069680cULL, 0x89cf7820a0f99c41ULL, 0x2a58d9183b56d0f4ULL, 0x4b5aca80e36011a4ULL, 0x329132348c29745dULL, 0xf4a2e616e1642fd7ULL, 0x1e45bb03ff67bc34ULL, 0x306912d0f42a9b4aULL, 0xff886507e6af7154ULL, 0x04f50e13dfeec82fULL, 0xaa512fe82abab5ceULL, 0x174e251a68d5f222ULL, 0xcf96700d82028898ULL, 0x1743e3370a2c02c5ULL, 0x379eec98b4e86eaaULL, 0x0c59888a51e0482eULL, 0xfbcbf1d699b5d189ULL, 0xacaef0d58e9fdc84ULL, 0xc1c20d06231f7614ULL, 0x2938218da274f972ULL, 0xf6af49beff1d7f18ULL, 0xcc541c22387ac9c2ULL, 0x96fcc9ef4015c56bULL, 0x69c1627c690913a9ULL, 0x7a86fd2f4733db0eULL, 0xfdb8c4f29e087de9ULL, 0x095e4b1a8ea2a229ULL, 0x1ad7a7c829b37a79ULL, 0x342d89cad17ea0c0ULL, 0x67bedda6cced2051ULL, 0x19ca31bf2bb42f74ULL, 0x3df7b4c84980acbbULL, 0xa8c6444dc80ad883ULL, 0xb91e440366e3ab85ULL, 0xc215cda00164f6d8ULL, 0x3d867c6ef247e668ULL, 0xc7dd582bcc3e658cULL, 0xfd2c4748ee0e5528ULL, 0xa0fd9b95cc9f4f71ULL, 0x7529d871b0675ddfULL, 0xb8f568b42d3cbd78ULL, 0x1233011b91f3da82ULL, 0x2dce6ccd4a7c3b62ULL, 0x75e7fc8e9e498603ULL, 0x2f4f13f1fcd0b6ecULL, 0xf1a8ca1f29ff7a45ULL, 0xc249c1a72981e29bULL, 0x6ebe0dbb8c83b56aULL, 0x7114fa8d170bb222ULL, 0x65a2dcd5bf93935fULL, 0xbdc41f68b59c979aULL, 0x2f0eef79a2ce9289ULL, 0x42ecbf0c083c37ceULL, 0x2930bc09ec496322ULL, 0xf294b0c19cfeac0dULL, 0x3780aa4bedfabb80ULL, 0x56c17d3e7cead929ULL, 0xe7cb4beb2e5722c5ULL, 0x0ce931732dbfe15aULL, 0x41b883c7621052f8ULL, 0xdbf75ca0c3d25350ULL, 0x2936be086eb1e351ULL, 0xc936e03cb4a9b212ULL, 0x1d45bf82322225aaULL, 0xe81ab1036a024cc5ULL, 0xe212201c304c9a72ULL, 0xc5d73fba6832b1fcULL, 0x20ffdb5a4d839581ULL, 0xa283d367be5d0fadULL, 0x6c2b25ca8b164475ULL, 0x9d4935467caaf22eULL, 0x5166408eee85ff49ULL, 0x3c67baa2fab4e361ULL, 0xb3e433c67ef35cefULL, 0x5259729241159b1cULL, 0x6a621892d5b0ab33ULL, 0x20b74a387555cdcbULL, 0x532aa10e1208923fULL, 0xeaa17b7762281dd1ULL, 0x61ab3443f05c44bfULL, 0x257a6c422324def8ULL, 0x131c6c1017e3cf7fULL, 0x23758739f630a257ULL, 0x295a407a01a78580ULL, 0xf8c443246d5da8d9ULL, 0x19d775450c52fa5dULL, 0x2afcfc92731bf83dULL, 0x7d10c8e81b2b4700ULL, 0xc8e0271f70baa20bULL, 0x993748867ca63957ULL, 0x5412efb3cb7ed4bbULL, 0x3196d36173e62975ULL, 0xde5bcad141c7dffcULL, 0x47cc8cd2b395c848ULL, 0xa34cd942e11af3cbULL, 0x0256dbf2d04ecec2ULL, 0x875ab7e94b0e667fULL, 0xcad4dd83c0850d10ULL, 0x47f12e8f4e72c79fULL, 0x5f1a87bb8c85b19bULL, 0x7ae9d0b6437f51b8ULL, 0x12c7ce5518879065ULL, 0x2ade09fe5cf77aeeULL, 0x23a05a2f7d2c5627ULL, 0x5908e128f17c169aULL, 0xf77498dd8ad0852dULL, 0x74b4c4ceab102f64ULL, 0x183abadd10139845ULL, 0xb165ba8daa92aaacULL, 0xd5c5ef9599386705ULL, 0xbe2f8f0cf8fc40d1ULL, 0x2701e635ee204514ULL, 0x629fa80020156514ULL, 0xf223868764a8c1ceULL, 0x5b894fff0b3f060eULL, 0x60d9944cf708a3faULL, 0xaeea001a1c7a201fULL, 0xebf16a633ee2ce63ULL, 0x6f7709594c7a07e1ULL, 0x79b958150d0208cbULL, 0x24b55e5301d410e7ULL, 0xe3a34edff3fdc84dULL, 0xd88768e4904032d8ULL, 0x131384427b3aaeecULL, 0x8405e51286234f14ULL, 0x14dc4739adb4c529ULL, 0xb8a2b5b250634ffdULL, 0x2fe2a94ad8a7ff93ULL, 0xec5c57efe843faddULL, 0x2843ce40f0bb9918ULL, 0xa4b561d6cf3d6305ULL, 0x743629bde8fb777eULL, 0x343edd46bbaf738fULL, 0xed981828b101a651ULL, 0xa401760b882c797aULL, 0x1fc223e28dc88730ULL, 0x48604e91fc0fba0eULL, 0xb637f78f052c6fa4ULL, 0x91ccac3d09e9239cULL, 0x23f7eed4437a687cULL, 0x5173b1118d9bd800ULL, 0x29d641b63189d4a7ULL, 0xfdbf177988bbc586ULL, 0x2959894fcad81df5ULL, 0xaebc8ef3b4bbc899ULL, 0x4148995ab26992b9ULL, 0x24e20b0134f92cfbULL, 0x40d158894a05dee8ULL, 0x46b00b1185af76f6ULL, 0x26bac77873187a79ULL, 0x3dc0bf95ab8fff5fULL, 0x2a608bd8945524d7ULL, 0x26449588bd446302ULL, 0x7c4bc21c0388439cULL, 0x8e98a4f383bd11b2ULL, 0x26218d7bc9d876b9ULL, 0xe3081542997c178aULL, 0x3c2d29a86fb6606fULL, 0x5c217736fa279374ULL, 0x7dde05734afeb1faULL, 0x3bf10e3906d42babULL, 0xe4f7803e1980649cULL, 0xe6053bf89595bf7aULL, 0x394faf38da245530ULL, 0x7a8efb58896928f4ULL, 0xfbc778e9cc6a113cULL, 0x72670ce330af596fULL, 0x48f222a81d3d6cf7ULL, 0xf01fce410d72caa7ULL, 0x5a20ecc7213b5595ULL, 0x7bc21165c1fa1483ULL, 0x07f89ae31da8a741ULL, 0x05d2c2b4c6830ff9ULL, 0xd43e330fc6316293ULL, 0xa5a5590a96d3a904ULL, 0x705edb91a65333b6ULL, 0x048ee15e0bb9a5f7ULL, 0x3240cfca9e0aaf5dULL, 0x8f4b71ceedc4a40bULL, 0x621c0da3de544a6dULL, 0x92872836a08c4091ULL, 0xce8375b010c91445ULL, 0x8a72eb524f276394ULL, 0x2667fcfa7ec83635ULL, 0x7f4c173345e8752aULL, 0x061b47feee7079a5ULL, 0x25dd9afa9f86ff34ULL, 0x3780cef5425dc89cULL, 0x1a46035a513bb4e9ULL, 0x3e1ef379ac575adaULL, 0xc78c5f1c5fa24b50ULL, 0x321a967634fd9f22ULL, 0x946707b8826e27faULL, 0x3dca84d64c506fd0ULL, 0xc189218075e91436ULL, 0x6d9284169b3b8484ULL, 0x3a67e840383f2ddfULL, 0x33eec9a30c4f9b75ULL, 0x3ec7c86fa783ef47ULL, 0x26ec449fbac9fbc4ULL, 0x5c0f38cba09b9e7dULL, 0x81168cc762a3478cULL, 0x3e23b0d306fc121cULL, 0x5a238aa0a5efdcddULL, 0x1ba26121c4ea43ffULL, 0x36f8c77f7c8832b5ULL, 0x88fbea0b0adcf99aULL, 0x5ca9938ec25bebf9ULL, 0xd5436a5e51fccda0ULL, 0x1dbc4797c2cd893bULL, 0x19346a65d3224a08ULL, 0x0f5034e49b9af466ULL, 0xf23c3967a1e0b96eULL, 0xe58b08fa867a4d88ULL, 0xfb2fabc6a7341679ULL, 0x2a75381eb6026946ULL, 0xc80a3be4c19420acULL, 0x66b1f6c681f2b6dcULL, 0x7cf7036761e93388ULL, 0x25abbbd8a660a4c4ULL, 0x91ea12ba14fd5198ULL, 0x684950fc4a3cffa9ULL, 0xf826842130f5ad28ULL, 0x3ea988f75301a441ULL, 0xc978109a695f8c6fULL, 0x1746eb4a0530c3f3ULL, 0x444d6d77b4459995ULL, 0x75952b8c054e5cc7ULL, 0xa3703f7915f4d6aaULL, 0x66c346202f2647d8ULL, 0xd01469df811d644bULL, 0x77fea47d81a5d71fULL, 0xc5e9529ef57ca381ULL, 0x6eeeb4b9ce2f881aULL, 0xb6e91a28e8009bd6ULL, 0x4b80be3e9afc3fecULL, 0x7e3773c526aed2c5ULL, 0x1b4afcb453c9a49dULL, 0xa920bdd7baffb24dULL, 0x7c54699f122d400eULL, 0xef46c8e14fa94bc8ULL, 0xe0b074ce2952ed5eULL, 0xbea450e1dbd885d5ULL, 0x61b68649320f712cULL, 0x8a485f7309ccbdd1ULL, 0xbd06320d7d4d1a2dULL, 0x25232973322dbef4ULL, 0x445dc4758c17f770ULL, 0xdb0434177cc8933cULL, 0xed6fe82175ea059fULL, 0x1efebefdc053db34ULL, 0x4adbe867c65daf99ULL, 0x3acd71a2a90609dfULL, 0xe5e991856dd04050ULL, 0x1ec69b688157c23cULL, 0x697427f6885cfe4dULL, 0xd7be7b9b65e1a851ULL, 0xa03d28d522c536ddULL, 0x28399d658fd2b645ULL, 0x49e5b7e17c2641e1ULL, 0x6f8c3a98700457a4ULL, 0x5078f0a25ebb6778ULL, 0xd13c3ccbc382960fULL, 0x2e003258a7df84b1ULL, 0x8ad1f39be6296a1cULL, 0xc1eeaa652a5fbfb2ULL, 0x33ee0673fd26f3cbULL, 0x59256173a69d2cccULL, 0x41ea07aa4e18fc41ULL, 0xd9fc19527c87a51eULL, 0xbdaacb805831ca6fULL, 0x445b652dc916694fULL, 0xce92a3a7f2172315ULL, 0x1edc282de11b9964ULL, 0xa1823aafe04c314aULL, 0x790a2d94437cf586ULL, 0x71c447fb93f6e009ULL, 0x8922a56722845276ULL, 0xbf70903b204f5169ULL, 0x2f7a89891ba319feULL, 0x02a08eb577e2140cULL, 0xed9a4ed4427bdcf4ULL, 0x5253ec44e4323cd1ULL, 0x3e88363c14e9355bULL, 0xaa66c14277110b8cULL, 0x1ae0391610a23390ULL, 0x2030bd12c93fc2a2ULL, 0x3ee141579555c7abULL, 0x9214de3a6d6e7d41ULL, 0x3ccdd88607f17efeULL, 0x674f1288f8e11217ULL, 0x5682250f329f93d0ULL, 0x6cf00b136d2e396eULL, 0x6e4cf86f1014debfULL, 0x5930b1b5bfcc4e83ULL, 0x047069b48aba16b6ULL, 0x0d4ce4ab69b20793ULL, 0xb24db91a97d0fb9eULL, 0xcdfa50f54e00d01dULL, 0x221b1085368bddb5ULL, 0xe7e59468b1e3d8d2ULL, 0x53c56563bd122f93ULL, 0xeee8a903e0663f09ULL, 0x61efa662cbbe3d42ULL, 0x2cf8ddddde6eab2aULL, 0x9bf80ad51435f231ULL, 0x5deadacec9f04973ULL, 0x29275b5d41d29b27ULL, 0xcfde0f0895ebf14fULL, 0xb9aab96b054905a7ULL, 0xcae80dd9a1c420fdULL, 0x0a63bf2f1673bbc7ULL, 0x092f6e11958fbc8cULL, 0x672a81e804822fadULL, 0xcac8351560d52517ULL, 0x6f3f7722c8f192f8ULL, 0xf8ba90ccc2e894b7ULL, 0x2c7557a438ff9f0dULL, 0x894d1d855ae52359ULL, 0x68e122157b743d69ULL, 0xd87e5570cfb919f3ULL, 0x3f2cdecd95798db9ULL, 0x2121154710c0a2ceULL, 0x3c66a115246dc5b2ULL, 0xcbedc562294ecb72ULL, 0xba7143c36a280b16ULL, 0x9610c2efd4078b67ULL, 0x6144735d946a4b1eULL, 0x536f111ed75b3350ULL, 0x0211db8c2041d81bULL, 0xf93cb1000e10413cULL, 0x149dfd3c039e8876ULL, 0xd479dde46b63155bULL, 0xb66e15e93c837976ULL, 0xdafde43b1f13e038ULL, 0x5fafda1a2e4b0b35ULL, 0x3600bbdf17197581ULL, 0x3972050bbe3cd2c2ULL, 0x5938906dbdd5be86ULL, 0x34fce5e43f9b860fULL, 0x75a8a4cd42d14d02ULL, 0x828dabc53441df65ULL, 0x33dcabedd2e131d3ULL, 0x3ebad76fb814d25fULL, 0xd4906f566f70e10fULL, 0x5d12f7aa51690f5aULL, 0x45adb16e76cefcf2ULL, 0x01f768aead232999ULL, 0x2b6cc77b6248febdULL, 0x3cd30628ec3aaffdULL, 0xce1c0b80d4ef486aULL, 0x4c3bff2ea6f66c23ULL, 0x3f2ec4094aeaeb5fULL, 0x61b19b286e372ca7ULL, 0x5eefa966de2a701dULL, 0x23b20565de55e3efULL, 0xe301ca5279d58557ULL, 0x07b2d4ce27c2874fULL, 0xa532cd8a9dcf1d67ULL, 0x2a52fee23f2bff56ULL, 0x8624efb37cd8663dULL, 0xbbc7ac20ffbd7594ULL, 0x57b85e9c82d37445ULL, 0x7b3052cb86a6ec66ULL, 0x3482f0ad2525e91eULL, 0x2cb68043d28edca0ULL, 0xaf4f6d052e1b003aULL, 0x185f8c2529781b0aULL, 0xaa41de5bd80ce0d6ULL, 0x9407b2416853e9d6ULL, 0x563ec36e357f4c3aULL, 0x4cc4b8dd0e297bceULL, 0xa2fc1a52ffb8730eULL, 0x1811f16e67058e37ULL, 0x10f9a366cddf4ee1ULL, 0x72f4a0c4a0b9f099ULL, 0x8c16c06f663f4ea7ULL, 0x693b3af74e970fbaULL, 0x2102e7f1d69ec345ULL, 0x0ba53cbc968a8089ULL, 0xca3d9dc7fea15537ULL, 0x4c6824bb51536493ULL, 0xb9886314844006b1ULL, 0x40d2a72ab454cc60ULL, 0x5936a1b712570975ULL, 0x91b9d648debda657ULL, 0x3344094bb64330eaULL, 0x006ba10d12ee51d0ULL, 0x19228468f5de5d58ULL, 0x0eb12f4c38cc05b0ULL, 0xa1039f9dd5601990ULL, 0x4502d4ce4fff0e0bULL, 0xeb2054106837c189ULL, 0xd0f6544c6dd3b93cULL, 0x40727064c416d74fULL, 0x6e15c6114b502ef0ULL, 0x4df2a398cfb1a76bULL, 0x11256c7419f2f6b1ULL, 0x4a497962066e6043ULL, 0x705b3aab41355b44ULL, 0x365ef536d797b1d8ULL, 0x00076bd622ddf0dbULL, 0x3bbf33b0e0575a88ULL, 0x3777aa05c8e4ca4dULL, 0x392745c85578db5fULL, 0x6fda4149dbae5ae2ULL, 0xb1f0b00b8adc9867ULL, 0x09963437d36f1da3ULL, 0x7e824e90a5dc3853ULL, 0xccb5f6641f135cbdULL, 0x6736d86c87ce8fccULL, 0x625f3ce26604249fULL, 0xaf8ac8059502f63fULL, 0x0c05e70a2e351469ULL, 0x35292e9c764b6305ULL, 0x1a394360c7e23ac3ULL, 0xd5c6d53251183264ULL, 0x62065abd43c2b74fULL, 0xb5fbf5d03b973f9bULL, 0x13a3da3661206e5eULL, 0xc6bd5837725d94e5ULL, 0x18e30912205016c5ULL, 0x2088ce1570033c68ULL, 0x7fba1f495c837987ULL, 0x5a8c7423f2f9079dULL, 0x1735157b34023fc5ULL, 0xe4f9b49ad2fab351ULL, 0x6691ff72c878e33cULL, 0x122c2adedc5eff3eULL, 0xf8dd4bf1d8956cf4ULL, 0xeb86205d9e9e5bdaULL, 0x049b92b9d975c743ULL, 0xa5379730b0f6c05aULL, 0x72a0ffacc6f3a553ULL, 0xb0032c34b20dcd6dULL, 0x470e9dbc88d5164aULL, 0xb19cf10ca237c047ULL, 0xb65466711f6c81a2ULL, 0xb3321bd16dd80b43ULL, 0x48c14f600c5fbe8eULL, 0x66451c264aa6c803ULL, 0xb66e3904a4fa7da6ULL, 0xd45f19b0b3128395ULL, 0x31602627c3c9bc10ULL, 0x3120dc4832e4e10dULL, 0xeb20c46756c717f7ULL, 0x00f52e3f67280294ULL, 0x566d4fc14730c509ULL, 0x7e3a5d40fd837206ULL, 0xc1e926dc7159547aULL, 0x216730fba68d6095ULL, 0x22e8c3843f69cea7ULL, 0x33d074e8930e4b2bULL, 0xb6e4350e84d15816ULL, 0x5534c26ad6ba2365ULL, 0x7773c12f89f1f3f3ULL, 0x8cba404da57962aaULL, 0x5b9897a81999ce56ULL, 0x508e862f121692fcULL, 0x3a81907fa093c291ULL, 0x0dded0ff4725a510ULL, 0x10d8cc10673fc503ULL, 0x5b9d151c9f1f4e89ULL, 0x32a5c1d5cb09a44cULL, 0x1e0aa442b90541fbULL, 0x5f85eb7cc1b485dbULL, 0xbee595ce8a9df2e5ULL, 0x25e496c722422236ULL, 0x5edf3c46cd0fe5b9ULL, 0x34e75a7ed2a43388ULL, 0xe488de11d761e352ULL, 0x0e878a01a085545cULL, 0xba493c77e021bb04ULL, 0x2b4d1843c7df899aULL, 0x9ea37a487ae80d67ULL, 0x67a9958011e41794ULL, 0x4b58051a6697b065ULL, 0x47e33f7d8d6ba6d4ULL, 0xbb4da8d483ca46c1ULL, 0x68becaa181c2db0dULL, 0x8d8980e90b989aa5ULL, 0xf95eb14a2c93c99bULL, 0x51c6c7c4796e73a2ULL, 0x6e228363b5efb569ULL, 0xc6bbc0b02dd624c8ULL, 0x777eb47dec8170eeULL, 0x3cde15a004cfafa9ULL, 0x1dc6bc087160bf9bULL, 0x2e07e043eec34002ULL, 0x18e9fc677a68dc7fULL, 0xd8da03188bd15b9aULL, 0x48fbc3bb00568253ULL, 0x57547d4cfb654ce1ULL, 0xd3565b82a058e2adULL, 0xf63eaf0bbf154478ULL, 0x47531ef114dfbb18ULL, 0xe1ec630a4278c587ULL, 0x5507d546ca8e83f3ULL, 0x85e135c63adc0c2bULL, 0x0aa7efa85682844eULL, 0x72691ba8b3e1f615ULL, 0x32b4e9701fbe3ffaULL, 0x97b6d92e39bb7868ULL, 0x2cfe53dea02e39e8ULL, 0x687392cd85cd52b0ULL, 0x27ff66c910e29831ULL, 0x97134556a9832d06ULL, 0x269bb0360a84f8a0ULL, 0x706e55457643f85cULL, 0x3734a48c9b597d1bULL, 0x7aee91e8c6efa472ULL, 0x5cd6abc198a9d9e0ULL, 0x0e04de06cb3ce41aULL, 0xd8c6eb893402e138ULL, 0x904659bb686e3772ULL, 0x7215c371746ba8c8ULL, 0xfd12a97eeae4a2d9ULL, 0x9514b7516394f2c5ULL, 0x266fd5809208f294ULL, 0x5c847085619a26b9ULL, 0x52985410fed694eaULL, 0x3c905b934a2ed254ULL, 0x10bb47692d3be467ULL, 0x063b3d2d69e5e9e1ULL, 0x472726eedda57debULL, 0xefb6c4ae10f41891ULL, 0x2b1641917b307614ULL, 0x117c554fc4f45b7cULL, 0xc07cf3118f9d8812ULL, 0x01dbd82050017939ULL, 0xd7e803f4171b2827ULL, 0x1015e87487d225eaULL, 0xc58de3fed23acc4dULL, 0x50db91c294a7be2dULL, 0x0b94d43d1c9cf457ULL, 0x6b1640fa6e37524aULL, 0x692f346c5fda0d09ULL, 0x200b1c59fa4d3151ULL, 0xb8c46f760777a296ULL, 0x4b38395f3ffdfbcfULL, 0x18d25e00be54d671ULL, 0x60d50582bec8aba6ULL, 0x87ad8f263b78b982ULL, 0x50fdf64e9cda0432ULL, 0x90f567aac578dcf0ULL, 0xef1e9b0ef2a3133bULL, 0x0eebba9242d9de71ULL, 0x15473c9bf03101c7ULL, 0x7c77e8ae56b78095ULL, 0xb678e7666e6f078eULL, 0x2da0b9615348ba1fULL, 0x7cf931c1ff733f0bULL, 0x26b357f50a0a366cULL, 0xe9708cf42b87d732ULL, 0xc13aeea5f91cb2c0ULL, 0x35d90c991143bb4cULL, 0x47c1c404a9a0d9dcULL, 0x659e58451972d251ULL, 0x3875a8c473b38c31ULL, 0x1fbd9ed379561f24ULL, 0x11fabc6fd41ec28dULL, 0x7ef8dfe3cd2a2dcaULL, 0x72e73b5d8c404595ULL, 0x6135fa4954b72f27ULL, 0xccfc32a2de24b69cULL, 0x3f55698c1f095d88ULL, 0xbe3350ed5ac3f929ULL, 0x5e9bf806ca477eebULL, 0xe9ce8fb63c309f68ULL, 0x5376f63565e1f9f4ULL, 0xd1afcfb35a6393f1ULL, 0x6632a1ede5623506ULL, 0x0b7d6c390c2ded4cULL, 0x56cb3281df04cb1fULL, 0x66305a1249ecc3c7ULL, 0x5d588b60a38ca72aULL, 0xa6ecbf78e8e5f42dULL, 0x86eeb44b3c8a3eecULL, 0xec219c48fbd21604ULL, 0x1aaf1af517c36731ULL, 0xc306a2836769bde7ULL, 0x208280622b1e2adbULL, 0x8027f51ffbff94a6ULL, 0x76cfa1ce1124f26bULL, 0x18eb00562422abb6ULL, 0xf377c4d58f8c29c3ULL, 0x4dbbc207f531561aULL, 0x0253b7f082128a27ULL, 0x3d1f091cb62c17e0ULL, 0x4860e1abd64628a9ULL, 0x52d17436309d4253ULL, 0x356f97e13efae576ULL, 0xd351e11aa150535bULL, 0x3e6b45bb1dd878ccULL, 0x0c776128bed92c98ULL, 0x1d34ae93032885b8ULL, 0x4ba0488ca85ba4c3ULL, 0x985348c33c9ce6ceULL, 0x66124c6f97bda770ULL, 0x0f81a0290654124aULL, 0x9ed09ca6569b86fdULL, 0x811009fd18af9a2dULL, 0xff08d03f93d8c20aULL, 0x52a148199faef26bULL, 0x3e03f9dc2d8d1b73ULL, 0x4205801873961a70ULL, 0xc0d987f041a35970ULL, 0x07aa1f15a1c0d549ULL, 0xdfd46ce08cd27224ULL, 0x6d0a024f934e4239ULL, 0x808a7a6399897b59ULL, 0x0a4556e9e13d95a2ULL, 0xd21a991fe9c13045ULL, 0x9b0e8548fe7751b8ULL, 0x5da643cb4bf30035ULL, 0x77db28d63940f721ULL, 0xfc5eeb614adc9011ULL, 0x5229419ae8c411ebULL, 0x9ec3e7787d1dcf74ULL, 0x340d053e216e4cb5ULL, 0xcac7af39b48df2b4ULL, 0xc0faec2871a10a94ULL, 0x140a69245ca575edULL, 0x0cf1c37134273a4cULL, 0xc8ee306ac224b8a5ULL, 0x57eaee7ccb4930b0ULL, 0xa1e806bdaacbe74fULL, 0x7d9a62742eeb657dULL, 0x9eb6b6ef546c4830ULL, 0x885cca1fddb36e2eULL, 0xe6b9f383ef0d7105ULL, 0x58654fef9d2e0412ULL, 0xa905c4ffbe0e8e26ULL, 0x942de5df9b31816eULL, 0x497d723f802e88e1ULL, 0x30684dea602f408dULL, 0x21e5a278a3e6cb34ULL, 0xaefb6e6f5b151dc4ULL, 0xb30b8e049d77ca15ULL, 0x28c3c9cf53b98981ULL, 0x287fb721556cdd2aULL, 0x0d317ca897022274ULL, 0x7468c7423a543258ULL, 0x4a7f11464eb5642fULL, 0xa237a4774d193aa6ULL, 0xd865986ea92129a1ULL, 0x24c515ecf87c1a88ULL, 0x604003575f39f5ebULL, 0x47b9f189570a9b27ULL, 0x2b98cede465e4b78ULL, 0x026df551dbb85c20ULL, 0x74fcd91047e21901ULL, 0x13e2a90a23c1bfa3ULL, 0x0cb0074e478519f6ULL, 0x5ff1cbbe3af6cf44ULL, 0x67fe5438be812dbeULL, 0xd13cf64fa40f05b0ULL, 0x054dfb2f32283787ULL, 0x4173915b7f0d2aeaULL, 0x482f144f1f610d4eULL, 0xf6210201b47f8234ULL, 0x5d0ae1929e70b990ULL, 0xdcd7f455b049567cULL, 0x7e93d0f1f0916f01ULL, 0xdd79cbf18a7db4faULL, 0xbe8391bf6f74c62fULL, 0x027145d14b8291bdULL, 0x585a73ea2cbf1705ULL, 0x485ca03e928a0db2ULL, 0x10fc01a5742857e7ULL, 0x2f482edbd6d551a7ULL, 0x0f0433b5048fdb8aULL, 0x60da2e8dd7dc6247ULL, 0x88b4c9d38cd4819aULL, 0x13033ac001f66697ULL, 0x273b24fe3b367d75ULL, 0xc6e8f66a31b3b9d4ULL, 0x281514a494df49d5ULL, 0xd1726fdfc8b23da7ULL, 0x4b3ae7d103dee548ULL, 0xc6256e19ce4b9d7eULL, 0xff5c5cf186e3c61cULL, 0xacc63ca34b8ec145ULL, 0x74621888fee66574ULL, 0x956f409645290a1eULL, 0xef0bf8e3263a962eULL, 0xed6a50eb5ec2647bULL, 0x0694283a9dca7502ULL, 0x769b963643a2dcd1ULL, 0x42b7c8ea09fc5353ULL, 0x4f002aee13397eabULL, 0x63005e2c19b7d63aULL, 0xca6736da63023beaULL, 0x966c7f6db12a99b7ULL, 0xace09390c537c5e1ULL, 0x0b696063a1aa89eeULL, 0xebb03e97288c56e5ULL, 0x432a9f9f938c8be8ULL, 0xa6a5a93d5b717f71ULL, 0x1a5fb4c3e18f9d97ULL, 0x1c94e7ad1c60cdceULL, 0xee202a43fc02c4a0ULL, 0x8dafe4d867c46a20ULL, 0x0a10263c8ac27b58ULL, 0xd0dea9dfe4432a4aULL, 0x856af87bbe9277c5ULL, 0xce8472acc212c71aULL, 0x6f151b6d9bbb1e91ULL, 0x26776c527ceed56aULL, 0x7d211cb7fbf8faecULL, 0x37ae66a6fd4609ccULL, 0x1f81b702d2770c42ULL, 0x2fb0b057eac58392ULL, 0xe1dd89fe29744e9dULL, 0xc964f8eb17beb4f8ULL, 0x29571073c9a2d41eULL, 0xa948a18981c0e254ULL, 0x2df6369b65b22830ULL, 0xa33eb2d75fcfd3c6ULL, 0x078cd6ec4199a01fULL, 0x4a584a41ad900d2fULL, 0x32142b78e2c74c52ULL, 0x68c4e8338431c978ULL, 0x7f69ea9008689fc2ULL, 0x52f2c81e46a38265ULL, 0xfd78072d04a832fdULL, 0x8cd7d5fa25359e94ULL, 0x4de71b7454cc29d2ULL, 0x42eb60ad1eda6ac9ULL, 0x0aad37dfdbc09c3aULL, 0x81004b71e33cc191ULL, 0x44e6be345122803cULL, 0x03fe8388ba1920dbULL, 0xf5d57c32150db008ULL, 0x49c8c4281af60c29ULL, 0x21edb518de701aeeULL, 0x7fb63e418f06dc99ULL, 0xa4460d99c166d7b8ULL, 0x24dd5248ce520a83ULL, 0x5ec3ad712b928358ULL, 0x15022a5fbd17930fULL, 0xa4f64a77d82570e3ULL, 0x12bc8d6915783712ULL, 0x498194c0fc620abbULL, 0x38a2d9d255686c82ULL, 0x785c6bd9193e21f0ULL, 0xe4d5c81ab24a5484ULL, 0x56307860b2e20989ULL, 0x429d55f78b4d74c4ULL, 0x22f1834643350131ULL, 0x1e60c24598c71fffULL, 0x59f2f014979983efULL, 0x46a47d56eb494a44ULL, 0x3e22a854d636a18eULL, 0xb346e15274491c3bULL, 0x2ceafd4e5390cde7ULL, 0xba8a8538be0d6675ULL, 0x4b9074bb50818e23ULL, 0xcbdab89085d304c3ULL, 0x61a24fe0e56192c4ULL, 0xcb7615e6db525bcbULL, 0xdd7d8c35a567e4caULL, 0xe6b4153acafcdd69ULL, 0x2d668e097f3c9766ULL, 0xa57e7e265ce55ef0ULL, 0x5d9f4e527cd4b967ULL, 0xfbc83606492fd1e5ULL, 0x090d52beb7c3f7aeULL, 0x09b9515a1e7b4d7cULL, 0x1f266a2599da44c0ULL, 0xa1c49548e2c55504ULL, 0x7ef04287126f15ccULL, 0xfed1659dbd30ef15ULL, 0x8b4ab9eec4e0277bULL, 0x884d6236a5df3291ULL, 0x1fd96ea6bf5cf788ULL, 0x42a161981f190d9aULL, 0x61d849507e6052c1ULL, 0x9fe113bf285a2cd5ULL, 0x7c22d676dbad85d8ULL, 0x82e770ed2bfbd27dULL, 0x4c05b2ece996f5a5ULL, 0xcd40a9c2b0900150ULL, 0x5895319213d9bf64ULL, 0xe7cc5d703fea2e08ULL, 0xb50c491258e2188cULL, 0xcce30baa48205bf0ULL, 0x537c659ccfa32d62ULL, 0x37b6623a98cfc088ULL, 0xfe9bed1fa4d6aca4ULL, 0x04d29b8e56a8d1b0ULL, 0x725f71c40b519575ULL, 0x28c7f89cd0339ce6ULL, 0x8367b14469ddc18bULL, 0x883ada83a6a1652cULL, 0x585f1974034d6c17ULL, 0x89cfb266f1b19188ULL, 0xe63b4863e7c35217ULL, 0xd88c9da6b4c0526aULL, 0x3e035c9df0954635ULL, 0xdd9d5412fb45de9dULL, 0xdd684532e4cff40dULL, 0x4b5c999b151d671cULL, 0x2d8c2cc811e7f690ULL, 0x7f54be1d90055d40ULL, 0xa464c5df464aaf40ULL, 0x33979624f0e917beULL, 0x2c018dc527356b30ULL, 0xa5415024e330b3d4ULL, 0x73ff3d96691652d3ULL, 0x94ec42c4ef9b59f1ULL, 0x0747201618d08e5aULL, 0x4d6ca48aca411c53ULL, 0x66415f2fcfa66119ULL, 0x9c4dd40051e227ffULL, 0x59810bc09a02f7ebULL, 0x2a7eb171b3dc101dULL, 0x441c5ab99ffef68eULL, 0x32025c9b93b359eaULL, 0x5e8ce0a71e9d112fULL, 0xbfcccb92429503fdULL, 0xd271ba752f095d55ULL, 0x345ead5e972d091eULL, 0x18c8df11a83103baULL, 0x90cd949a9aed0f4cULL, 0xc5d1f4cb6660e37eULL, 0xb8cac52d56c52e0bULL, 0x6e42e400c5808e0dULL, 0xa3b46966eeaefd23ULL, 0x0c4f1f0be39ecdcaULL, 0x189dc8c9d683a51dULL, 0x51f27f054c09351bULL, 0x4c487ccd2a320682ULL, 0x587ea95bb3df1c96ULL, 0xc8ccf79e555cb8e8ULL, 0x547dc829a206d73dULL, 0xb822a6cd80c39b06ULL, 0xe96d54732000d4c6ULL, 0x28535b6f91463b4dULL, 0x228f4660e2486e1dULL, 0x98799538de8d3abfULL, 0x8cd8330045ebca6eULL, 0x79952a008221e738ULL, 0x4322e1a7535cd2bbULL, 0xb114c11819d1801cULL, 0x2016e4d84f3f5ec7ULL, 0xdd0e2df409260f4cULL, 0x5ec362c0ae5f7266ULL, 0xc0462b18b8b2b4eeULL, 0x7cc8d950274d1afbULL, 0xf25f7105436b02d2ULL, 0x43bbf8dcbff9ccd3ULL, 0xb6ad1767a039e9dfULL, 0xb0714da8f69d3583ULL, 0x5e55fa18b42931f5ULL, 0x4ed5558f33c60961ULL, 0x1fe37901c647a5ddULL, 0x593ddf1f8081d357ULL, 0x0249a4fd813fd7a6ULL, 0x69acca274e9caf61ULL, 0x047ba3ea330721c9ULL, 0x83423fc20e7e1ea0ULL, 0x1df4c0af01314a60ULL, 0x09a62dab89289527ULL, 0xa5b325a49cc6cb00ULL, 0xe94b5dc654b56cb6ULL, 0x3be28779adc994a0ULL, 0x4296e8f8ba3a4aadULL, 0x328689761e451eabULL, 0x2e4d598bff59594aULL, 0x49b96853d7a7084aULL, 0x4980a319601420a8ULL, 0x9565b9e12f552c42ULL, 0x8a5318db7100fe96ULL, 0x05c90b4d43add0d7ULL, 0x538b4cd66a5d4edaULL, 0xf4e94fc3e89f039fULL, 0x592c9af26f618045ULL, 0x08a36eb5fd4b9550ULL, 0x25fffaf6c2ed1419ULL, 0x34434459cc79d354ULL, 0xeeecbfb4b1d5476bULL, 0xddeb34a061615d99ULL, 0x5129cecceb64b773ULL, 0xee43215894993520ULL, 0x772f9c7cf14c0b3bULL, 0xd2e2fce306bedad5ULL, 0x715f42b546f06a97ULL, 0x434ecdceda5b5f1aULL, 0x0da17115a49741a9ULL, 0x680bd77c73edad2eULL, 0x487c02354edd9041ULL, 0xb8efeff3a70ed9c4ULL, 0x56a32aa3e857e302ULL, 0xdf3a68bd48a2a5a0ULL, 0x07f650b73176c444ULL, 0xe38b9b1626e0ccb1ULL, 0x79e053c18b09fb36ULL, 0x56d90319c9f94964ULL, 0x1ca941e7ac9ff5c4ULL, 0x49c4df29162fa0bbULL, 0x8488cf3282b33305ULL, 0x95dfda14cabb437dULL, 0x3391f78264d5ad86ULL, 0x729ae06ae2b5095dULL, 0xd58a58d73259a946ULL, 0xe9834262d13921edULL, 0x27fedafaa54bb592ULL, 0xa99dc5b829ad48bbULL, 0x5f025742499ee260ULL, 0x802c8ecd5d7513fdULL, 0x78ceb3ef3f6dd938ULL, 0xc342f44f8a135d94ULL, 0x7b9edb44828cdda3ULL, 0x9436d11a0537cfe7ULL, 0x5064b164ec1ab4c8ULL, 0x7020eccfd37eb2fcULL, 0x1f31ea3ed90d25fcULL, 0x1b930d7bdfa1bb34ULL, 0x5344467a48113044ULL, 0x70073170f25e6dfbULL, 0xe385dc1a50114cc8ULL, 0x2348698ac8fc4f00ULL, 0x2a77a55284dd40d8ULL, 0xfe06afe0c98c6ce4ULL, 0xc235df96dddfd6e4ULL, 0x1428d01e33bf1ed3ULL, 0x785768ec9300bdafULL, 0x9702e57a91deb63bULL, 0x61bdb8bfe5ce8b80ULL, 0x645b426f3d1d58acULL, 0x4804a82227a557bcULL, 0x8e57048ab44d2601ULL, 0x68d6501a4b3a6935ULL, 0xc39c9ec3f9e1c293ULL, 0x4172f257d4de63e2ULL, 0xd368b450330c6401ULL, 0x040d3017418f2391ULL, 0x2c34bb6090b7d90dULL, 0x16f649228fdfd51fULL, 0xbea6818e2b928ef5ULL, 0xe28ccf91cdc11e72ULL, 0x594aaa68e77a36cdULL, 0x313034806c7ffd0fULL, 0x8a9d27ac2249bd65ULL, 0x19a3b464018e9512ULL, 0xc26ccff352b37ec7ULL, 0x056f68341d797b21ULL, 0x5e79d6757efd2327ULL, 0xfabdbcb6553afe15ULL, 0xd3e7222c6eaf5a60ULL, 0x7046c76d4dae743bULL, 0x660be872b18d4a55ULL, 0x19992518574e1496ULL, 0xc103053a302bdcbbULL, 0x3ed8e9800b218e8eULL, 0x7b0b9239fa75e03eULL, 0xefe9fb684633c083ULL, 0x98a35fbe391a7793ULL, 0x6065510fe2d0fe34ULL, 0x55cb668548abad0cULL, 0xb4584548da87e527ULL, 0x2c43ecea0107c1ddULL, 0x526028809372de35ULL, 0x3415c56af9213b1fULL, 0x5bee1a4d017e98dbULL, 0x13f6b105b5cf709bULL, 0x5ff20e3482b29ab6ULL, 0x0aa29c75cc2e6c90ULL, 0xfc7d73ca3a70e206ULL, 0x899fc38fc4b5c515ULL, 0x250386b124ffc207ULL, 0x54ea28d5ae3d2b56ULL, 0x9913149dd6de60ceULL, 0x16694fc58f06d6c1ULL, 0x46b23975eb018fc7ULL, 0x470a6a0fb4b7b4e2ULL, 0x5d92475a8f7253deULL, 0xabeee5b52fbd3adbULL, 0x7fa20801a0806968ULL, 0x76f3faf19f7714d2ULL, 0xb3e840c12f4660c3ULL, 0x0fb4cd8df212744eULL, 0x4b065a251d3a2dd2ULL, 0x5cebde383d77cd4aULL, 0x6adf39df882c9cb1ULL, 0xa2dd242eb09af759ULL, 0x3147c0e50e5f6422ULL, 0x164ca5101d1350dbULL, 0xf8d13479c33fc962ULL, 0xe640ce4d13e5da08ULL, 0x4bdee0c45061f8baULL, 0xd7c46dc1a4edb1c9ULL, 0x5514d7b6437fd98aULL, 0x58942f6bb2a1c00bULL, 0x2dffb2ab1d70710eULL, 0xccdfcf2fc18b6d68ULL, 0xa8ebcba8b7806167ULL, 0x980697f95e2937e3ULL, 0x02fbba1cd0126e8cULL }; static void curve25519_ever64_base(u8 *out, const u8 *priv) { u64 swap = 1; int i, j, k; u64 tmp[16 + 32 + 4]; u64 *x1 = &tmp[0]; u64 *z1 = &tmp[4]; u64 *x2 = &tmp[8]; u64 *z2 = &tmp[12]; u64 *xz1 = &tmp[0]; u64 *xz2 = &tmp[8]; u64 *a = &tmp[0 + 16]; u64 *b = &tmp[4 + 16]; u64 *c = &tmp[8 + 16]; u64 *ab = &tmp[0 + 16]; u64 *abcd = &tmp[0 + 16]; u64 *ef = &tmp[16 + 16]; u64 *efgh = &tmp[16 + 16]; u64 *key = &tmp[0 + 16 + 32]; memcpy(key, priv, 32); ((u8 *)key)[0] &= 248; ((u8 *)key)[31] = (((u8 *)key)[31] & 127) | 64; x1[0] = 1, x1[1] = x1[2] = x1[3] = 0; z1[0] = 1, z1[1] = z1[2] = z1[3] = 0; z2[0] = 1, z2[1] = z2[2] = z2[3] = 0; memcpy(x2, p_minus_s, sizeof(p_minus_s)); j = 3; for (i = 0; i < 4; ++i) { while (j < (const int[]){ 64, 64, 64, 63 }[i]) { u64 bit = (key[i] >> j) & 1; k = (64 * i + j - 3); swap = swap ^ bit; cswap2(swap, xz1, xz2); swap = bit; fsub(b, x1, z1); fadd(a, x1, z1); fmul(c, &table_ladder[4 * k], b, ef); fsub(b, a, c); fadd(a, a, c); fsqr2(ab, ab, efgh); fmul2(xz1, xz2, ab, efgh); ++j; } j = 0; } point_double(xz1, abcd, efgh); point_double(xz1, abcd, efgh); point_double(xz1, abcd, efgh); encode_point(out, xz1); memzero_explicit(tmp, sizeof(tmp)); } static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_bmi2_adx); static void curve25519_arch(u8 mypublic[CURVE25519_KEY_SIZE], const u8 secret[CURVE25519_KEY_SIZE], const u8 basepoint[CURVE25519_KEY_SIZE]) { if (static_branch_likely(&curve25519_use_bmi2_adx)) curve25519_ever64(mypublic, secret, basepoint); else curve25519_generic(mypublic, secret, basepoint); } static void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE], const u8 secret[CURVE25519_KEY_SIZE]) { if (static_branch_likely(&curve25519_use_bmi2_adx)) curve25519_ever64_base(pub, secret); else curve25519_generic(pub, secret, curve25519_base_point); } #define curve25519_mod_init_arch curve25519_mod_init_arch static void curve25519_mod_init_arch(void) { if (boot_cpu_has(X86_FEATURE_BMI2) && boot_cpu_has(X86_FEATURE_ADX)) static_branch_enable(&curve25519_use_bmi2_adx); } |
| 9 8 1 5 5 36 1 35 35 27 2 6 36 35 2 1 1 4 28 17 2 2 2 36 1 1 1 9 27 48 48 | 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 | // SPDX-License-Identifier: GPL-2.0 /* XDP user-space packet buffer * Copyright(c) 2018 Intel Corporation. */ #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/bpf.h> #include <linux/mm.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/idr.h> #include <linux/vmalloc.h> #include "xdp_umem.h" #include "xsk_queue.h" static DEFINE_IDA(umem_ida); static void xdp_umem_unpin_pages(struct xdp_umem *umem) { unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true); kvfree(umem->pgs); umem->pgs = NULL; } static void xdp_umem_unaccount_pages(struct xdp_umem *umem) { if (umem->user) { atomic_long_sub(umem->npgs, &umem->user->locked_vm); free_uid(umem->user); } } static void xdp_umem_addr_unmap(struct xdp_umem *umem) { vunmap(umem->addrs); umem->addrs = NULL; } static int xdp_umem_addr_map(struct xdp_umem *umem, struct page **pages, u32 nr_pages) { umem->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); if (!umem->addrs) return -ENOMEM; return 0; } static void xdp_umem_release(struct xdp_umem *umem) { umem->zc = false; ida_free(&umem_ida, umem->id); xdp_umem_addr_unmap(umem); xdp_umem_unpin_pages(umem); xdp_umem_unaccount_pages(umem); kfree(umem); } static void xdp_umem_release_deferred(struct work_struct *work) { struct xdp_umem *umem = container_of(work, struct xdp_umem, work); xdp_umem_release(umem); } void xdp_get_umem(struct xdp_umem *umem) { refcount_inc(&umem->users); } void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup) { if (!umem) return; if (refcount_dec_and_test(&umem->users)) { if (defer_cleanup) { INIT_WORK(&umem->work, xdp_umem_release_deferred); schedule_work(&umem->work); } else { xdp_umem_release(umem); } } } static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) { unsigned int gup_flags = FOLL_WRITE; long npgs; int err; umem->pgs = kvzalloc_objs(*umem->pgs, umem->npgs, GFP_KERNEL | __GFP_NOWARN); if (!umem->pgs) return -ENOMEM; mmap_read_lock(current->mm); npgs = pin_user_pages(address, umem->npgs, gup_flags | FOLL_LONGTERM, &umem->pgs[0]); mmap_read_unlock(current->mm); if (npgs != umem->npgs) { if (npgs >= 0) { umem->npgs = npgs; err = -ENOMEM; goto out_pin; } err = npgs; goto out_pgs; } return 0; out_pin: xdp_umem_unpin_pages(umem); out_pgs: kvfree(umem->pgs); umem->pgs = NULL; return err; } static int xdp_umem_account_pages(struct xdp_umem *umem) { unsigned long lock_limit, new_npgs, old_npgs; if (capable(CAP_IPC_LOCK)) return 0; lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; umem->user = get_uid(current_user()); do { old_npgs = atomic_long_read(&umem->user->locked_vm); new_npgs = old_npgs + umem->npgs; if (new_npgs > lock_limit) { free_uid(umem->user); umem->user = NULL; return -ENOBUFS; } } while (atomic_long_cmpxchg(&umem->user->locked_vm, old_npgs, new_npgs) != old_npgs); return 0; } #define XDP_UMEM_FLAGS_VALID ( \ XDP_UMEM_UNALIGNED_CHUNK_FLAG | \ XDP_UMEM_TX_SW_CSUM | \ XDP_UMEM_TX_METADATA_LEN | \ 0) static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) { bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; u32 chunk_size = mr->chunk_size, headroom = mr->headroom; u64 addr = mr->addr, size = mr->len; u32 chunks_rem, npgs_rem; u64 chunks, npgs; int err; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { /* Strictly speaking we could support this, if: * - huge pages, or* * - using an IOMMU, or * - making sure the memory area is consecutive * but for now, we simply say "computer says no". */ return -EINVAL; } if (mr->flags & ~XDP_UMEM_FLAGS_VALID) return -EINVAL; if (!unaligned_chunks && !is_power_of_2(chunk_size)) return -EINVAL; if (!PAGE_ALIGNED(addr)) { /* Memory area has to be page size aligned. For * simplicity, this might change. */ return -EINVAL; } if ((addr + size) < addr) return -EINVAL; npgs = div_u64_rem(size, PAGE_SIZE, &npgs_rem); if (npgs_rem) npgs++; if (npgs > U32_MAX) return -EINVAL; chunks = div_u64_rem(size, chunk_size, &chunks_rem); if (!chunks || chunks > U32_MAX) return -EINVAL; if (!unaligned_chunks && chunks_rem) return -EINVAL; if (headroom > chunk_size - XDP_PACKET_HEADROOM - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) - 128) return -EINVAL; if (mr->flags & XDP_UMEM_TX_METADATA_LEN) { if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) return -EINVAL; if (mr->tx_metadata_len < 16) return -EINVAL; umem->tx_metadata_len = mr->tx_metadata_len; } umem->size = size; umem->headroom = headroom; umem->chunk_size = chunk_size; umem->chunks = chunks; umem->npgs = npgs; umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; INIT_LIST_HEAD(&umem->xsk_dma_list); refcount_set(&umem->users, 1); err = xdp_umem_account_pages(umem); if (err) return err; err = xdp_umem_pin_pages(umem, (unsigned long)addr); if (err) goto out_account; err = xdp_umem_addr_map(umem, umem->pgs, umem->npgs); if (err) goto out_unpin; return 0; out_unpin: xdp_umem_unpin_pages(umem); out_account: xdp_umem_unaccount_pages(umem); return err; } struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr) { struct xdp_umem *umem; int err; umem = kzalloc_obj(*umem); if (!umem) return ERR_PTR(-ENOMEM); err = ida_alloc(&umem_ida, GFP_KERNEL); if (err < 0) { kfree(umem); return ERR_PTR(err); } umem->id = err; err = xdp_umem_reg(umem, mr); if (err) { ida_free(&umem_ida, umem->id); kfree(umem); return ERR_PTR(err); } return umem; } |
| 10 14 4 10 38 47 44 1 3 2 20 6 42 60 20 2 38 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to io context handling */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/sched/task.h> #include "blk.h" #include "blk-mq-sched.h" /* * For io context allocations */ static struct kmem_cache *iocontext_cachep; #ifdef CONFIG_BLK_ICQ /** * get_io_context - increment reference count to io_context * @ioc: io_context to get * * Increment reference count to @ioc. */ static void get_io_context(struct io_context *ioc) { BUG_ON(atomic_long_read(&ioc->refcount) <= 0); atomic_long_inc(&ioc->refcount); } /* * Exit an icq. Called with ioc locked for blk-mq, and with both ioc * and queue locked for legacy. */ static void ioc_exit_icq(struct io_cq *icq) { struct elevator_type *et = icq->q->elevator->type; if (icq->flags & ICQ_EXITED) return; if (et->ops.exit_icq) et->ops.exit_icq(icq); icq->flags |= ICQ_EXITED; } static void ioc_exit_icqs(struct io_context *ioc) { struct io_cq *icq; spin_lock_irq(&ioc->lock); hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) ioc_exit_icq(icq); spin_unlock_irq(&ioc->lock); } /* * Release an icq. Called with ioc locked for blk-mq, and with both ioc * and queue locked for legacy. */ static void ioc_destroy_icq(struct io_cq *icq) { struct io_context *ioc = icq->ioc; struct request_queue *q = icq->q; struct elevator_type *et = q->elevator->type; lockdep_assert_held(&ioc->lock); lockdep_assert_held(&q->queue_lock); if (icq->flags & ICQ_DESTROYED) return; radix_tree_delete(&ioc->icq_tree, icq->q->id); hlist_del_init(&icq->ioc_node); list_del_init(&icq->q_node); /* * Both setting lookup hint to and clearing it from @icq are done * under queue_lock. If it's not pointing to @icq now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(ioc->icq_hint) == icq) rcu_assign_pointer(ioc->icq_hint, NULL); ioc_exit_icq(icq); /* * @icq->q might have gone away by the time RCU callback runs * making it impossible to determine icq_cache. Record it in @icq. */ icq->__rcu_icq_cache = et->icq_cache; icq->flags |= ICQ_DESTROYED; kfree_rcu(icq, __rcu_head); } /* * Slow path for ioc release in put_io_context(). Performs double-lock * dancing to unlink all icq's and then frees ioc. */ static void ioc_release_fn(struct work_struct *work) { struct io_context *ioc = container_of(work, struct io_context, release_work); spin_lock_irq(&ioc->lock); while (!hlist_empty(&ioc->icq_list)) { struct io_cq *icq = hlist_entry(ioc->icq_list.first, struct io_cq, ioc_node); struct request_queue *q = icq->q; if (spin_trylock(&q->queue_lock)) { ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); } else { /* Make sure q and icq cannot be freed. */ rcu_read_lock(); /* Re-acquire the locks in the correct order. */ spin_unlock(&ioc->lock); spin_lock(&q->queue_lock); spin_lock(&ioc->lock); ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); rcu_read_unlock(); } } spin_unlock_irq(&ioc->lock); kmem_cache_free(iocontext_cachep, ioc); } /* * Releasing icqs requires reverse order double locking and we may already be * holding a queue_lock. Do it asynchronously from a workqueue. */ static bool ioc_delay_free(struct io_context *ioc) { unsigned long flags; spin_lock_irqsave(&ioc->lock, flags); if (!hlist_empty(&ioc->icq_list)) { queue_work(system_power_efficient_wq, &ioc->release_work); spin_unlock_irqrestore(&ioc->lock, flags); return true; } spin_unlock_irqrestore(&ioc->lock, flags); return false; } /** * ioc_clear_queue - break any ioc association with the specified queue * @q: request_queue being cleared * * Walk @q->icq_list and exit all io_cq's. */ void ioc_clear_queue(struct request_queue *q) { spin_lock_irq(&q->queue_lock); while (!list_empty(&q->icq_list)) { struct io_cq *icq = list_first_entry(&q->icq_list, struct io_cq, q_node); /* * Other context won't hold ioc lock to wait for queue_lock, see * details in ioc_release_fn(). */ spin_lock(&icq->ioc->lock); ioc_destroy_icq(icq); spin_unlock(&icq->ioc->lock); } spin_unlock_irq(&q->queue_lock); } #else /* CONFIG_BLK_ICQ */ static inline void ioc_exit_icqs(struct io_context *ioc) { } static inline bool ioc_delay_free(struct io_context *ioc) { return false; } #endif /* CONFIG_BLK_ICQ */ /** * put_io_context - put a reference of io_context * @ioc: io_context to put * * Decrement reference count of @ioc and release it if the count reaches * zero. */ void put_io_context(struct io_context *ioc) { BUG_ON(atomic_long_read(&ioc->refcount) <= 0); if (atomic_long_dec_and_test(&ioc->refcount) && !ioc_delay_free(ioc)) kmem_cache_free(iocontext_cachep, ioc); } EXPORT_SYMBOL_GPL(put_io_context); /* Called by the exiting task */ void exit_io_context(struct task_struct *task) { struct io_context *ioc; task_lock(task); ioc = task->io_context; task->io_context = NULL; task_unlock(task); if (atomic_dec_and_test(&ioc->active_ref)) { ioc_exit_icqs(ioc); put_io_context(ioc); } } static struct io_context *alloc_io_context(gfp_t gfp_flags, int node) { struct io_context *ioc; ioc = kmem_cache_alloc_node(iocontext_cachep, gfp_flags | __GFP_ZERO, node); if (unlikely(!ioc)) return NULL; atomic_long_set(&ioc->refcount, 1); atomic_set(&ioc->active_ref, 1); #ifdef CONFIG_BLK_ICQ spin_lock_init(&ioc->lock); INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC); INIT_HLIST_HEAD(&ioc->icq_list); INIT_WORK(&ioc->release_work, ioc_release_fn); #endif ioc->ioprio = IOPRIO_DEFAULT; return ioc; } int set_task_ioprio(struct task_struct *task, int ioprio) { int err; const struct cred *cred = current_cred(), *tcred; rcu_read_lock(); tcred = __task_cred(task); if (!uid_eq(tcred->uid, cred->euid) && !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) { rcu_read_unlock(); return -EPERM; } rcu_read_unlock(); err = security_task_setioprio(task, ioprio); if (err) return err; task_lock(task); if (unlikely(!task->io_context)) { struct io_context *ioc; task_unlock(task); ioc = alloc_io_context(GFP_ATOMIC, NUMA_NO_NODE); if (!ioc) return -ENOMEM; task_lock(task); if (task->flags & PF_EXITING) { kmem_cache_free(iocontext_cachep, ioc); goto out; } if (task->io_context) kmem_cache_free(iocontext_cachep, ioc); else task->io_context = ioc; } task->io_context->ioprio = ioprio; out: task_unlock(task); return 0; } EXPORT_SYMBOL_GPL(set_task_ioprio); int __copy_io(u64 clone_flags, struct task_struct *tsk) { struct io_context *ioc = current->io_context; /* * Share io context with parent, if CLONE_IO is set */ if (clone_flags & CLONE_IO) { atomic_inc(&ioc->active_ref); tsk->io_context = ioc; } else if (ioprio_valid(ioc->ioprio)) { tsk->io_context = alloc_io_context(GFP_KERNEL, NUMA_NO_NODE); if (!tsk->io_context) return -ENOMEM; tsk->io_context->ioprio = ioc->ioprio; } return 0; } #ifdef CONFIG_BLK_ICQ /** * ioc_lookup_icq - lookup io_cq from ioc in io issue path * @q: the associated request_queue * * Look up io_cq associated with @ioc - @q pair from @ioc. Must be called * from io issue path, either return NULL if current issue io to @q for the * first time, or return a valid icq. */ struct io_cq *ioc_lookup_icq(struct request_queue *q) { struct io_context *ioc = current->io_context; struct io_cq *icq; /* * icq's are indexed from @ioc using radix tree and hint pointer, * both of which are protected with RCU, io issue path ensures that * both request_queue and current task are valid, the found icq * is guaranteed to be valid until the io is done. */ rcu_read_lock(); icq = rcu_dereference(ioc->icq_hint); if (icq && icq->q == q) goto out; icq = radix_tree_lookup(&ioc->icq_tree, q->id); if (icq && icq->q == q) rcu_assign_pointer(ioc->icq_hint, icq); /* allowed to race */ else icq = NULL; out: rcu_read_unlock(); return icq; } EXPORT_SYMBOL(ioc_lookup_icq); /** * ioc_create_icq - create and link io_cq * @q: request_queue of interest * * Make sure io_cq linking @ioc and @q exists. If icq doesn't exist, they * will be created using @gfp_mask. * * The caller is responsible for ensuring @ioc won't go away and @q is * alive and will stay alive until this function returns. */ static struct io_cq *ioc_create_icq(struct request_queue *q) { struct io_context *ioc = current->io_context; struct elevator_type *et = q->elevator->type; struct io_cq *icq; /* allocate stuff */ icq = kmem_cache_alloc_node(et->icq_cache, GFP_ATOMIC | __GFP_ZERO, q->node); if (!icq) return NULL; if (radix_tree_maybe_preload(GFP_ATOMIC) < 0) { kmem_cache_free(et->icq_cache, icq); return NULL; } icq->ioc = ioc; icq->q = q; INIT_LIST_HEAD(&icq->q_node); INIT_HLIST_NODE(&icq->ioc_node); /* lock both q and ioc and try to link @icq */ spin_lock_irq(&q->queue_lock); spin_lock(&ioc->lock); if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) { hlist_add_head(&icq->ioc_node, &ioc->icq_list); list_add(&icq->q_node, &q->icq_list); if (et->ops.init_icq) et->ops.init_icq(icq); } else { kmem_cache_free(et->icq_cache, icq); icq = ioc_lookup_icq(q); if (!icq) printk(KERN_ERR "cfq: icq link failed!\n"); } spin_unlock(&ioc->lock); spin_unlock_irq(&q->queue_lock); radix_tree_preload_end(); return icq; } struct io_cq *ioc_find_get_icq(struct request_queue *q) { struct io_context *ioc = current->io_context; struct io_cq *icq = NULL; if (unlikely(!ioc)) { ioc = alloc_io_context(GFP_ATOMIC, q->node); if (!ioc) return NULL; task_lock(current); if (current->io_context) { kmem_cache_free(iocontext_cachep, ioc); ioc = current->io_context; } else { current->io_context = ioc; } get_io_context(ioc); task_unlock(current); } else { get_io_context(ioc); icq = ioc_lookup_icq(q); } if (!icq) { icq = ioc_create_icq(q); if (!icq) { put_io_context(ioc); return NULL; } } return icq; } EXPORT_SYMBOL_GPL(ioc_find_get_icq); #endif /* CONFIG_BLK_ICQ */ static int __init blk_ioc_init(void) { iocontext_cachep = kmem_cache_create("blkdev_ioc", sizeof(struct io_context), 0, SLAB_PANIC, NULL); return 0; } subsys_initcall(blk_ioc_init); |
| 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CONTEXT_TRACKING_H #define _LINUX_CONTEXT_TRACKING_H #include <linux/sched.h> #include <linux/vtime.h> #include <linux/context_tracking_state.h> #include <linux/instrumentation.h> #include <asm/ptrace.h> #ifdef CONFIG_CONTEXT_TRACKING_USER extern void ct_cpu_track_user(int cpu); /* Called with interrupts disabled. */ extern void __ct_user_enter(enum ctx_state state); extern void __ct_user_exit(enum ctx_state state); extern void ct_user_enter(enum ctx_state state); extern void ct_user_exit(enum ctx_state state); extern void user_enter_callable(void); extern void user_exit_callable(void); static inline void user_enter(void) { if (context_tracking_enabled()) ct_user_enter(CT_STATE_USER); } static inline void user_exit(void) { if (context_tracking_enabled()) ct_user_exit(CT_STATE_USER); } /* Called with interrupts disabled. */ static __always_inline void user_enter_irqoff(void) { if (context_tracking_enabled()) __ct_user_enter(CT_STATE_USER); } static __always_inline void user_exit_irqoff(void) { if (context_tracking_enabled()) __ct_user_exit(CT_STATE_USER); } static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; if (IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) || !context_tracking_enabled()) return 0; prev_ctx = __ct_state(); if (prev_ctx != CT_STATE_KERNEL) ct_user_exit(prev_ctx); return prev_ctx; } static inline void exception_exit(enum ctx_state prev_ctx) { if (!IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) && context_tracking_enabled()) { if (prev_ctx != CT_STATE_KERNEL) ct_user_enter(prev_ctx); } } static __always_inline bool context_tracking_guest_enter(void) { if (context_tracking_enabled()) __ct_user_enter(CT_STATE_GUEST); return context_tracking_enabled_this_cpu(); } static __always_inline bool context_tracking_guest_exit(void) { if (context_tracking_enabled()) __ct_user_exit(CT_STATE_GUEST); return context_tracking_enabled_this_cpu(); } #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) #else static inline void user_enter(void) { } static inline void user_exit(void) { } static inline void user_enter_irqoff(void) { } static inline void user_exit_irqoff(void) { } static inline int exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline int ct_state(void) { return -1; } static inline int __ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } static __always_inline bool context_tracking_guest_exit(void) { return false; } #define CT_WARN_ON(cond) do { } while (0) #endif /* !CONFIG_CONTEXT_TRACKING_USER */ #ifdef CONFIG_CONTEXT_TRACKING_USER_FORCE extern void context_tracking_init(void); #else static inline void context_tracking_init(void) { } #endif /* CONFIG_CONTEXT_TRACKING_USER_FORCE */ #ifdef CONFIG_CONTEXT_TRACKING_IDLE extern void ct_idle_enter(void); extern void ct_idle_exit(void); /* * Is RCU watching the current CPU (IOW, it is not in an extended quiescent state)? * * Note that this returns the actual boolean data (watching / not watching), * whereas ct_rcu_watching() returns the RCU_WATCHING subvariable of * context_tracking.state. * * No ordering, as we are sampling CPU-local information. */ static __always_inline bool rcu_is_watching_curr_cpu(void) { return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING; } /* * Increment the current CPU's context_tracking structure's ->state field * with ordering. Return the new value. */ static __always_inline unsigned long ct_state_inc(int incby) { return raw_atomic_add_return(incby, this_cpu_ptr(&context_tracking.state)); } static __always_inline bool warn_rcu_enter(void) { bool ret = false; /* * Horrible hack to shut up recursive RCU isn't watching fail since * lots of the actual reporting also relies on RCU. */ preempt_disable_notrace(); if (!rcu_is_watching_curr_cpu()) { ret = true; ct_state_inc(CT_RCU_WATCHING); } return ret; } static __always_inline void warn_rcu_exit(bool rcu) { if (rcu) ct_state_inc(CT_RCU_WATCHING); preempt_enable_notrace(); } #else static inline void ct_idle_enter(void) { } static inline void ct_idle_exit(void) { } static __always_inline bool warn_rcu_enter(void) { return false; } static __always_inline void warn_rcu_exit(bool rcu) { } #endif /* !CONFIG_CONTEXT_TRACKING_IDLE */ #endif |
| 11 13 4 10 10 1 1 15 15 9 7 9 9 9 51 48 9 8 51 9 9 9 9 9 19 8 17 9 16 16 13 4 10 43 2 2 2 2 2 2 2 2 4 3 2 2 78 51 78 78 78 78 51 51 43 11 51 51 51 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * IEEE 802.1D Generic Attribute Registration Protocol (GARP) * * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> */ #include <linux/kernel.h> #include <linux/timer.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/llc.h> #include <linux/slab.h> #include <linux/module.h> #include <net/llc.h> #include <net/llc_pdu.h> #include <net/garp.h> #include <linux/unaligned.h> static unsigned int garp_join_time __read_mostly = 200; module_param(garp_join_time, uint, 0644); MODULE_PARM_DESC(garp_join_time, "Join time in ms (default 200ms)"); MODULE_DESCRIPTION("IEEE 802.1D Generic Attribute Registration Protocol (GARP)"); MODULE_LICENSE("GPL"); static const struct garp_state_trans { u8 state; u8 action; } garp_applicant_state_table[GARP_APPLICANT_MAX + 1][GARP_EVENT_MAX + 1] = { [GARP_APPLICANT_VA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_AA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, }, [GARP_APPLICANT_AA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_QA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, }, [GARP_APPLICANT_QA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, }, [GARP_APPLICANT_LA] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_VO, .action = GARP_ACTION_S_LEAVE_EMPTY }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_LA }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_LA }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_LA }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_VA }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, [GARP_APPLICANT_VP] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_AA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AP }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_VO }, }, [GARP_APPLICANT_AP] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_QA, .action = GARP_ACTION_S_JOIN_IN }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QP }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_AO }, }, [GARP_APPLICANT_QP] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QP }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_QO }, }, [GARP_APPLICANT_VO] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AO }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_VP }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, [GARP_APPLICANT_AO] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QO }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_AP }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, [GARP_APPLICANT_QO] = { [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QO }, [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_QP }, [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, }, }; static int garp_attr_cmp(const struct garp_attr *attr, const void *data, u8 len, u8 type) { if (attr->type != type) return attr->type - type; if (attr->dlen != len) return attr->dlen - len; return memcmp(attr->data, data, len); } static struct garp_attr *garp_attr_lookup(const struct garp_applicant *app, const void *data, u8 len, u8 type) { struct rb_node *parent = app->gid.rb_node; struct garp_attr *attr; int d; while (parent) { attr = rb_entry(parent, struct garp_attr, node); d = garp_attr_cmp(attr, data, len, type); if (d > 0) parent = parent->rb_left; else if (d < 0) parent = parent->rb_right; else return attr; } return NULL; } static struct garp_attr *garp_attr_create(struct garp_applicant *app, const void *data, u8 len, u8 type) { struct rb_node *parent = NULL, **p = &app->gid.rb_node; struct garp_attr *attr; int d; while (*p) { parent = *p; attr = rb_entry(parent, struct garp_attr, node); d = garp_attr_cmp(attr, data, len, type); if (d > 0) p = &parent->rb_left; else if (d < 0) p = &parent->rb_right; else { /* The attribute already exists; re-use it. */ return attr; } } attr = kmalloc(sizeof(*attr) + len, GFP_ATOMIC); if (!attr) return attr; attr->state = GARP_APPLICANT_VO; attr->type = type; attr->dlen = len; memcpy(attr->data, data, len); rb_link_node(&attr->node, parent, p); rb_insert_color(&attr->node, &app->gid); return attr; } static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr) { rb_erase(&attr->node, &app->gid); kfree(attr); } static void garp_attr_destroy_all(struct garp_applicant *app) { struct rb_node *node, *next; struct garp_attr *attr; for (node = rb_first(&app->gid); next = node ? rb_next(node) : NULL, node != NULL; node = next) { attr = rb_entry(node, struct garp_attr, node); garp_attr_destroy(app, attr); } } static int garp_pdu_init(struct garp_applicant *app) { struct sk_buff *skb; struct garp_pdu_hdr *gp; #define LLC_RESERVE sizeof(struct llc_pdu_un) skb = alloc_skb(app->dev->mtu + LL_RESERVED_SPACE(app->dev), GFP_ATOMIC); if (!skb) return -ENOMEM; skb->dev = app->dev; skb->protocol = htons(ETH_P_802_2); skb_reserve(skb, LL_RESERVED_SPACE(app->dev) + LLC_RESERVE); gp = __skb_put(skb, sizeof(*gp)); put_unaligned(htons(GARP_PROTOCOL_ID), &gp->protocol); app->pdu = skb; return 0; } static int garp_pdu_append_end_mark(struct garp_applicant *app) { if (skb_tailroom(app->pdu) < sizeof(u8)) return -1; __skb_put_u8(app->pdu, GARP_END_MARK); return 0; } static void garp_pdu_queue(struct garp_applicant *app) { if (!app->pdu) return; garp_pdu_append_end_mark(app); garp_pdu_append_end_mark(app); llc_pdu_header_init(app->pdu, LLC_PDU_TYPE_U, LLC_SAP_BSPAN, LLC_SAP_BSPAN, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(app->pdu); llc_mac_hdr_init(app->pdu, app->dev->dev_addr, app->app->proto.group_address); skb_queue_tail(&app->queue, app->pdu); app->pdu = NULL; } static void garp_queue_xmit(struct garp_applicant *app) { struct sk_buff *skb; while ((skb = skb_dequeue(&app->queue))) dev_queue_xmit(skb); } static int garp_pdu_append_msg(struct garp_applicant *app, u8 attrtype) { struct garp_msg_hdr *gm; if (skb_tailroom(app->pdu) < sizeof(*gm)) return -1; gm = __skb_put(app->pdu, sizeof(*gm)); gm->attrtype = attrtype; garp_cb(app->pdu)->cur_type = attrtype; return 0; } static int garp_pdu_append_attr(struct garp_applicant *app, const struct garp_attr *attr, enum garp_attr_event event) { struct garp_attr_hdr *ga; unsigned int len; int err; again: if (!app->pdu) { err = garp_pdu_init(app); if (err < 0) return err; } if (garp_cb(app->pdu)->cur_type != attr->type) { if (garp_cb(app->pdu)->cur_type && garp_pdu_append_end_mark(app) < 0) goto queue; if (garp_pdu_append_msg(app, attr->type) < 0) goto queue; } len = sizeof(*ga) + attr->dlen; if (skb_tailroom(app->pdu) < len) goto queue; ga = __skb_put(app->pdu, len); ga->len = len; ga->event = event; memcpy(ga->data, attr->data, attr->dlen); return 0; queue: garp_pdu_queue(app); goto again; } static void garp_attr_event(struct garp_applicant *app, struct garp_attr *attr, enum garp_event event) { enum garp_applicant_state state; state = garp_applicant_state_table[attr->state][event].state; if (state == GARP_APPLICANT_INVALID) return; switch (garp_applicant_state_table[attr->state][event].action) { case GARP_ACTION_NONE: break; case GARP_ACTION_S_JOIN_IN: /* When appending the attribute fails, don't update state in * order to retry on next TRANSMIT_PDU event. */ if (garp_pdu_append_attr(app, attr, GARP_JOIN_IN) < 0) return; break; case GARP_ACTION_S_LEAVE_EMPTY: garp_pdu_append_attr(app, attr, GARP_LEAVE_EMPTY); /* As a pure applicant, sending a leave message implies that * the attribute was unregistered and can be destroyed. */ garp_attr_destroy(app, attr); return; default: WARN_ON(1); } attr->state = state; } int garp_request_join(const struct net_device *dev, const struct garp_application *appl, const void *data, u8 len, u8 type) { struct garp_port *port = rtnl_dereference(dev->garp_port); struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]); struct garp_attr *attr; spin_lock_bh(&app->lock); attr = garp_attr_create(app, data, len, type); if (!attr) { spin_unlock_bh(&app->lock); return -ENOMEM; } garp_attr_event(app, attr, GARP_EVENT_REQ_JOIN); spin_unlock_bh(&app->lock); return 0; } EXPORT_SYMBOL_GPL(garp_request_join); void garp_request_leave(const struct net_device *dev, const struct garp_application *appl, const void *data, u8 len, u8 type) { struct garp_port *port = rtnl_dereference(dev->garp_port); struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]); struct garp_attr *attr; spin_lock_bh(&app->lock); attr = garp_attr_lookup(app, data, len, type); if (!attr) { spin_unlock_bh(&app->lock); return; } garp_attr_event(app, attr, GARP_EVENT_REQ_LEAVE); spin_unlock_bh(&app->lock); } EXPORT_SYMBOL_GPL(garp_request_leave); static void garp_gid_event(struct garp_applicant *app, enum garp_event event) { struct rb_node *node, *next; struct garp_attr *attr; for (node = rb_first(&app->gid); next = node ? rb_next(node) : NULL, node != NULL; node = next) { attr = rb_entry(node, struct garp_attr, node); garp_attr_event(app, attr, event); } } static void garp_join_timer_arm(struct garp_applicant *app) { unsigned long delay; delay = get_random_u32_below(msecs_to_jiffies(garp_join_time)); mod_timer(&app->join_timer, jiffies + delay); } static void garp_join_timer(struct timer_list *t) { struct garp_applicant *app = timer_container_of(app, t, join_timer); spin_lock(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); garp_pdu_queue(app); spin_unlock(&app->lock); garp_queue_xmit(app); garp_join_timer_arm(app); } static int garp_pdu_parse_end_mark(struct sk_buff *skb) { if (!pskb_may_pull(skb, sizeof(u8))) return -1; if (*skb->data == GARP_END_MARK) { skb_pull(skb, sizeof(u8)); return -1; } return 0; } static int garp_pdu_parse_attr(struct garp_applicant *app, struct sk_buff *skb, u8 attrtype) { const struct garp_attr_hdr *ga; struct garp_attr *attr; enum garp_event event; unsigned int dlen; if (!pskb_may_pull(skb, sizeof(*ga))) return -1; ga = (struct garp_attr_hdr *)skb->data; if (ga->len < sizeof(*ga)) return -1; if (!pskb_may_pull(skb, ga->len)) return -1; ga = (struct garp_attr_hdr *)skb->data; skb_pull(skb, ga->len); dlen = ga->len - sizeof(*ga); if (attrtype > app->app->maxattr) return 0; switch (ga->event) { case GARP_LEAVE_ALL: if (dlen != 0) return -1; garp_gid_event(app, GARP_EVENT_R_LEAVE_EMPTY); return 0; case GARP_JOIN_EMPTY: event = GARP_EVENT_R_JOIN_EMPTY; break; case GARP_JOIN_IN: event = GARP_EVENT_R_JOIN_IN; break; case GARP_LEAVE_EMPTY: event = GARP_EVENT_R_LEAVE_EMPTY; break; case GARP_EMPTY: event = GARP_EVENT_R_EMPTY; break; default: return 0; } if (dlen == 0) return -1; attr = garp_attr_lookup(app, ga->data, dlen, attrtype); if (attr == NULL) return 0; garp_attr_event(app, attr, event); return 0; } static int garp_pdu_parse_msg(struct garp_applicant *app, struct sk_buff *skb) { const struct garp_msg_hdr *gm; u8 attrtype; if (!pskb_may_pull(skb, sizeof(*gm))) return -1; gm = (struct garp_msg_hdr *)skb->data; if (gm->attrtype == 0) return -1; skb_pull(skb, sizeof(*gm)); attrtype = gm->attrtype; while (skb->len > 0) { if (garp_pdu_parse_attr(app, skb, attrtype) < 0) return -1; if (garp_pdu_parse_end_mark(skb) < 0) break; } return 0; } static void garp_pdu_rcv(const struct stp_proto *proto, struct sk_buff *skb, struct net_device *dev) { struct garp_application *appl = proto->data; struct garp_port *port; struct garp_applicant *app; const struct garp_pdu_hdr *gp; port = rcu_dereference(dev->garp_port); if (!port) goto err; app = rcu_dereference(port->applicants[appl->type]); if (!app) goto err; if (!pskb_may_pull(skb, sizeof(*gp))) goto err; gp = (struct garp_pdu_hdr *)skb->data; if (get_unaligned(&gp->protocol) != htons(GARP_PROTOCOL_ID)) goto err; skb_pull(skb, sizeof(*gp)); spin_lock(&app->lock); while (skb->len > 0) { if (garp_pdu_parse_msg(app, skb) < 0) break; if (garp_pdu_parse_end_mark(skb) < 0) break; } spin_unlock(&app->lock); err: kfree_skb(skb); } static int garp_init_port(struct net_device *dev) { struct garp_port *port; port = kzalloc_obj(*port); if (!port) return -ENOMEM; rcu_assign_pointer(dev->garp_port, port); return 0; } static void garp_release_port(struct net_device *dev) { struct garp_port *port = rtnl_dereference(dev->garp_port); unsigned int i; for (i = 0; i <= GARP_APPLICATION_MAX; i++) { if (rtnl_dereference(port->applicants[i])) return; } RCU_INIT_POINTER(dev->garp_port, NULL); kfree_rcu(port, rcu); } int garp_init_applicant(struct net_device *dev, struct garp_application *appl) { struct garp_applicant *app; int err; ASSERT_RTNL(); if (!rtnl_dereference(dev->garp_port)) { err = garp_init_port(dev); if (err < 0) goto err1; } err = -ENOMEM; app = kzalloc_obj(*app); if (!app) goto err2; err = dev_mc_add(dev, appl->proto.group_address); if (err < 0) goto err3; app->dev = dev; app->app = appl; app->gid = RB_ROOT; spin_lock_init(&app->lock); skb_queue_head_init(&app->queue); rcu_assign_pointer(dev->garp_port->applicants[appl->type], app); timer_setup(&app->join_timer, garp_join_timer, 0); garp_join_timer_arm(app); return 0; err3: kfree(app); err2: garp_release_port(dev); err1: return err; } EXPORT_SYMBOL_GPL(garp_init_applicant); void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl) { struct garp_port *port = rtnl_dereference(dev->garp_port); struct garp_applicant *app = rtnl_dereference(port->applicants[appl->type]); ASSERT_RTNL(); RCU_INIT_POINTER(port->applicants[appl->type], NULL); /* Delete timer and generate a final TRANSMIT_PDU event to flush out * all pending messages before the applicant is gone. */ timer_shutdown_sync(&app->join_timer); spin_lock_bh(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); garp_attr_destroy_all(app); garp_pdu_queue(app); spin_unlock_bh(&app->lock); garp_queue_xmit(app); dev_mc_del(dev, appl->proto.group_address); kfree_rcu(app, rcu); garp_release_port(dev); } EXPORT_SYMBOL_GPL(garp_uninit_applicant); int garp_register_application(struct garp_application *appl) { appl->proto.rcv = garp_pdu_rcv; appl->proto.data = appl; return stp_proto_register(&appl->proto); } EXPORT_SYMBOL_GPL(garp_register_application); void garp_unregister_application(struct garp_application *appl) { stp_proto_unregister(&appl->proto); } EXPORT_SYMBOL_GPL(garp_unregister_application); |
| 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001 Sistina Software (UK) Limited * * This file is released under the GPL. */ #include "dm-core.h" #include <linux/module.h> #include <linux/init.h> #include <linux/kmod.h> #include <linux/bio.h> #include <linux/dax.h> #define DM_MSG_PREFIX "target" static LIST_HEAD(_targets); static DECLARE_RWSEM(_lock); static inline struct target_type *__find_target_type(const char *name) { struct target_type *tt; list_for_each_entry(tt, &_targets, list) if (!strcmp(name, tt->name)) return tt; return NULL; } static struct target_type *get_target_type(const char *name) { struct target_type *tt; down_read(&_lock); tt = __find_target_type(name); if (tt && !try_module_get(tt->module)) tt = NULL; up_read(&_lock); return tt; } static void load_module(const char *name) { request_module("dm-%s", name); } struct target_type *dm_get_target_type(const char *name) { struct target_type *tt = get_target_type(name); if (!tt) { load_module(name); tt = get_target_type(name); } return tt; } void dm_put_target_type(struct target_type *tt) { down_read(&_lock); module_put(tt->module); up_read(&_lock); } int dm_target_iterate(void (*iter_func)(struct target_type *tt, void *param), void *param) { struct target_type *tt; down_read(&_lock); list_for_each_entry(tt, &_targets, list) iter_func(tt, param); up_read(&_lock); return 0; } int dm_register_target(struct target_type *tt) { int rv = 0; down_write(&_lock); if (__find_target_type(tt->name)) { DMERR("%s: '%s' target already registered", __func__, tt->name); rv = -EBUSY; } else { list_add(&tt->list, &_targets); } up_write(&_lock); return rv; } EXPORT_SYMBOL(dm_register_target); void dm_unregister_target(struct target_type *tt) { down_write(&_lock); if (!__find_target_type(tt->name)) { DMCRIT("Unregistering unrecognised target: %s", tt->name); BUG(); } list_del(&tt->list); up_write(&_lock); } EXPORT_SYMBOL(dm_unregister_target); /* * io-err: always fails an io, useful for bringing * up LVs that have holes in them. */ struct io_err_c { struct dm_dev *dev; sector_t start; }; static int io_err_get_args(struct dm_target *tt, unsigned int argc, char **args) { unsigned long long start; struct io_err_c *ioec; char dummy; int ret; ioec = kmalloc_obj(*ioec); if (!ioec) { tt->error = "Cannot allocate io_err context"; return -ENOMEM; } ret = -EINVAL; if (sscanf(args[1], "%llu%c", &start, &dummy) != 1 || start != (sector_t)start) { tt->error = "Invalid device sector"; goto bad; } ioec->start = start; ret = dm_get_device(tt, args[0], dm_table_get_mode(tt->table), &ioec->dev); if (ret) { tt->error = "Device lookup failed"; goto bad; } tt->private = ioec; return 0; bad: kfree(ioec); return ret; } static int io_err_ctr(struct dm_target *tt, unsigned int argc, char **args) { /* * If we have arguments, assume it is the path to the backing * block device and its mapping start sector (same as dm-linear). * In this case, get the device so that we can get its limits. */ if (argc == 2) { int ret = io_err_get_args(tt, argc, args); if (ret) return ret; } /* * Return error for discards instead of -EOPNOTSUPP */ tt->num_discard_bios = 1; tt->discards_supported = true; return 0; } static void io_err_dtr(struct dm_target *tt) { struct io_err_c *ioec = tt->private; if (ioec) { dm_put_device(tt, ioec->dev); kfree(ioec); } } static int io_err_map(struct dm_target *tt, struct bio *bio) { return DM_MAPIO_KILL; } static int io_err_clone_and_map_rq(struct dm_target *ti, struct request *rq, union map_info *map_context, struct request **clone) { return DM_MAPIO_KILL; } static void io_err_release_clone_rq(struct request *clone, union map_info *map_context) { } #ifdef CONFIG_BLK_DEV_ZONED static sector_t io_err_map_sector(struct dm_target *ti, sector_t bi_sector) { struct io_err_c *ioec = ti->private; return ioec->start + dm_target_offset(ti, bi_sector); } static int io_err_report_zones(struct dm_target *ti, struct dm_report_zones_args *args, unsigned int nr_zones) { struct io_err_c *ioec = ti->private; /* * This should never be called when we do not have a backing device * as that mean the target is not a zoned one. */ if (WARN_ON_ONCE(!ioec)) return -EIO; return dm_report_zones(ioec->dev->bdev, ioec->start, io_err_map_sector(ti, args->next_sector), args, nr_zones); } #else #define io_err_report_zones NULL #endif static int io_err_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { struct io_err_c *ioec = ti->private; if (!ioec) return 0; return fn(ti, ioec->dev, ioec->start, ti->len, data); } static void io_err_io_hints(struct dm_target *ti, struct queue_limits *limits) { limits->max_hw_discard_sectors = UINT_MAX; limits->discard_granularity = 512; } static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, long nr_pages, enum dax_access_mode mode, void **kaddr, unsigned long *pfn) { return -EIO; } static struct target_type error_target = { .name = "error", .version = {1, 7, 0}, .features = DM_TARGET_WILDCARD | DM_TARGET_ZONED_HM | DM_TARGET_PASSES_INTEGRITY, .ctr = io_err_ctr, .dtr = io_err_dtr, .map = io_err_map, .clone_and_map_rq = io_err_clone_and_map_rq, .release_clone_rq = io_err_release_clone_rq, .iterate_devices = io_err_iterate_devices, .io_hints = io_err_io_hints, .direct_access = io_err_dax_direct_access, .report_zones = io_err_report_zones, }; int __init dm_target_init(void) { return dm_register_target(&error_target); } void dm_target_exit(void) { dm_unregister_target(&error_target); } |
| 6 7 3 1 19 19 1 18 16 17 11 11 11 6 19 19 5 5 5 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "queueing.h" #include "device.h" #include "peer.h" #include "timers.h" #include "messages.h" #include "cookie.h" #include "socket.h" #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/udp.h> #include <net/ip_tunnels.h> /* Must be called with bh disabled. */ static void update_rx_stats(struct wg_peer *peer, size_t len) { dev_sw_netstats_rx_add(peer->device->dev, len); peer->rx_bytes += len; } #define SKB_TYPE_LE32(skb) (((struct message_header *)(skb)->data)->type) static size_t validate_header_len(struct sk_buff *skb) { if (unlikely(skb->len < sizeof(struct message_header))) return 0; if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_DATA) && skb->len >= MESSAGE_MINIMUM_LENGTH) return sizeof(struct message_data); if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION) && skb->len == sizeof(struct message_handshake_initiation)) return sizeof(struct message_handshake_initiation); if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE) && skb->len == sizeof(struct message_handshake_response)) return sizeof(struct message_handshake_response); if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE) && skb->len == sizeof(struct message_handshake_cookie)) return sizeof(struct message_handshake_cookie); return 0; } static int prepare_skb_header(struct sk_buff *skb, struct wg_device *wg) { size_t data_offset, data_len, header_len; struct udphdr *udp; if (unlikely(!wg_check_packet_protocol(skb) || skb_transport_header(skb) < skb->head || (skb_transport_header(skb) + sizeof(struct udphdr)) > skb_tail_pointer(skb))) return -EINVAL; /* Bogus IP header */ udp = udp_hdr(skb); data_offset = (u8 *)udp - skb->data; if (unlikely(data_offset > U16_MAX || data_offset + sizeof(struct udphdr) > skb->len)) /* Packet has offset at impossible location or isn't big enough * to have UDP fields. */ return -EINVAL; data_len = ntohs(udp->len); if (unlikely(data_len < sizeof(struct udphdr) || data_len > skb->len - data_offset)) /* UDP packet is reporting too small of a size or lying about * its size. */ return -EINVAL; data_len -= sizeof(struct udphdr); data_offset = (u8 *)udp + sizeof(struct udphdr) - skb->data; if (unlikely(!pskb_may_pull(skb, data_offset + sizeof(struct message_header)) || pskb_trim(skb, data_len + data_offset) < 0)) return -EINVAL; skb_pull(skb, data_offset); if (unlikely(skb->len != data_len)) /* Final len does not agree with calculated len */ return -EINVAL; header_len = validate_header_len(skb); if (unlikely(!header_len)) return -EINVAL; __skb_push(skb, data_offset); if (unlikely(!pskb_may_pull(skb, data_offset + header_len))) return -EINVAL; __skb_pull(skb, data_offset); return 0; } static void wg_receive_handshake_packet(struct wg_device *wg, struct sk_buff *skb) { enum cookie_mac_state mac_state; struct wg_peer *peer = NULL; /* This is global, so that our load calculation applies to the whole * system. We don't care about races with it at all. */ static u64 last_under_load; bool packet_needs_cookie; bool under_load; if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE)) { net_dbg_skb_ratelimited("%s: Receiving cookie response from %pISpfsc\n", wg->dev->name, skb); wg_cookie_message_consume( (struct message_handshake_cookie *)skb->data, wg); return; } under_load = atomic_read(&wg->handshake_queue_len) >= MAX_QUEUED_INCOMING_HANDSHAKES / 8; if (under_load) { last_under_load = ktime_get_coarse_boottime_ns(); } else if (last_under_load) { under_load = !wg_birthdate_has_expired(last_under_load, 1); if (!under_load) last_under_load = 0; } mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb, under_load); if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) || (!under_load && mac_state == VALID_MAC_BUT_NO_COOKIE)) { packet_needs_cookie = false; } else if (under_load && mac_state == VALID_MAC_BUT_NO_COOKIE) { packet_needs_cookie = true; } else { net_dbg_skb_ratelimited("%s: Invalid MAC of handshake, dropping packet from %pISpfsc\n", wg->dev->name, skb); return; } switch (SKB_TYPE_LE32(skb)) { case cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION): { struct message_handshake_initiation *message = (struct message_handshake_initiation *)skb->data; if (packet_needs_cookie) { wg_packet_send_handshake_cookie(wg, skb, message->sender_index); return; } peer = wg_noise_handshake_consume_initiation(message, wg); if (unlikely(!peer)) { net_dbg_skb_ratelimited("%s: Invalid handshake initiation from %pISpfsc\n", wg->dev->name, skb); return; } wg_socket_set_peer_endpoint_from_skb(peer, skb); net_dbg_ratelimited("%s: Receiving handshake initiation from peer %llu (%pISpfsc)\n", wg->dev->name, peer->internal_id, &peer->endpoint.addr); wg_packet_send_handshake_response(peer); break; } case cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE): { struct message_handshake_response *message = (struct message_handshake_response *)skb->data; if (packet_needs_cookie) { wg_packet_send_handshake_cookie(wg, skb, message->sender_index); return; } peer = wg_noise_handshake_consume_response(message, wg); if (unlikely(!peer)) { net_dbg_skb_ratelimited("%s: Invalid handshake response from %pISpfsc\n", wg->dev->name, skb); return; } wg_socket_set_peer_endpoint_from_skb(peer, skb); net_dbg_ratelimited("%s: Receiving handshake response from peer %llu (%pISpfsc)\n", wg->dev->name, peer->internal_id, &peer->endpoint.addr); if (wg_noise_handshake_begin_session(&peer->handshake, &peer->keypairs)) { wg_timers_session_derived(peer); wg_timers_handshake_complete(peer); /* Calling this function will either send any existing * packets in the queue and not send a keepalive, which * is the best case, Or, if there's nothing in the * queue, it will send a keepalive, in order to give * immediate confirmation of the session. */ wg_packet_send_keepalive(peer); } break; } } if (unlikely(!peer)) { WARN(1, "Somehow a wrong type of packet wound up in the handshake queue!\n"); return; } local_bh_disable(); update_rx_stats(peer, skb->len); local_bh_enable(); wg_timers_any_authenticated_packet_received(peer); wg_timers_any_authenticated_packet_traversal(peer); wg_peer_put(peer); } void wg_packet_handshake_receive_worker(struct work_struct *work) { struct crypt_queue *queue = container_of(work, struct multicore_worker, work)->ptr; struct wg_device *wg = container_of(queue, struct wg_device, handshake_queue); struct sk_buff *skb; while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) { wg_receive_handshake_packet(wg, skb); dev_kfree_skb(skb); atomic_dec(&wg->handshake_queue_len); cond_resched(); } } static void keep_key_fresh(struct wg_peer *peer) { struct noise_keypair *keypair; bool send; if (peer->sent_lastminute_handshake) return; rcu_read_lock_bh(); keypair = rcu_dereference_bh(peer->keypairs.current_keypair); send = keypair && READ_ONCE(keypair->sending.is_valid) && keypair->i_am_the_initiator && wg_birthdate_has_expired(keypair->sending.birthdate, REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT); rcu_read_unlock_bh(); if (unlikely(send)) { peer->sent_lastminute_handshake = true; wg_packet_send_queued_handshake_initiation(peer, false); } } static bool decrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) { struct scatterlist sg[MAX_SKB_FRAGS + 8]; struct sk_buff *trailer; unsigned int offset; int num_frags; if (unlikely(!keypair)) return false; if (unlikely(!READ_ONCE(keypair->receiving.is_valid) || wg_birthdate_has_expired(keypair->receiving.birthdate, REJECT_AFTER_TIME) || READ_ONCE(keypair->receiving_counter.counter) >= REJECT_AFTER_MESSAGES)) { WRITE_ONCE(keypair->receiving.is_valid, false); return false; } PACKET_CB(skb)->nonce = le64_to_cpu(((struct message_data *)skb->data)->counter); /* We ensure that the network header is part of the packet before we * call skb_cow_data, so that there's no chance that data is removed * from the skb, so that later we can extract the original endpoint. */ offset = -skb_network_offset(skb); skb_push(skb, offset); num_frags = skb_cow_data(skb, 0, &trailer); offset += sizeof(struct message_data); skb_pull(skb, offset); if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg))) return false; sg_init_table(sg, num_frags); if (skb_to_sgvec(skb, sg, 0, skb->len) <= 0) return false; if (!chacha20poly1305_decrypt_sg_inplace(sg, skb->len, NULL, 0, PACKET_CB(skb)->nonce, keypair->receiving.key)) return false; /* Another ugly situation of pushing and pulling the header so as to * keep endpoint information intact. */ skb_push(skb, offset); if (pskb_trim(skb, skb->len - noise_encrypted_len(0))) return false; skb_pull(skb, offset); return true; } /* This is RFC6479, a replay detection bitmap algorithm that avoids bitshifts */ static bool counter_validate(struct noise_replay_counter *counter, u64 their_counter) { unsigned long index, index_current, top, i; bool ret = false; spin_lock_bh(&counter->lock); if (unlikely(counter->counter >= REJECT_AFTER_MESSAGES + 1 || their_counter >= REJECT_AFTER_MESSAGES)) goto out; ++their_counter; if (unlikely((COUNTER_WINDOW_SIZE + their_counter) < counter->counter)) goto out; index = their_counter >> ilog2(BITS_PER_LONG); if (likely(their_counter > counter->counter)) { index_current = counter->counter >> ilog2(BITS_PER_LONG); top = min_t(unsigned long, index - index_current, COUNTER_BITS_TOTAL / BITS_PER_LONG); for (i = 1; i <= top; ++i) counter->backtrack[(i + index_current) & ((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0; WRITE_ONCE(counter->counter, their_counter); } index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1; ret = !test_and_set_bit(their_counter & (BITS_PER_LONG - 1), &counter->backtrack[index]); out: spin_unlock_bh(&counter->lock); return ret; } #include "selftest/counter.c" static void wg_packet_consume_data_done(struct wg_peer *peer, struct sk_buff *skb, struct endpoint *endpoint) { struct net_device *dev = peer->device->dev; unsigned int len, len_before_trim; struct wg_peer *routed_peer; wg_socket_set_peer_endpoint(peer, endpoint); if (unlikely(wg_noise_received_with_keypair(&peer->keypairs, PACKET_CB(skb)->keypair))) { wg_timers_handshake_complete(peer); wg_packet_send_staged_packets(peer); } keep_key_fresh(peer); wg_timers_any_authenticated_packet_received(peer); wg_timers_any_authenticated_packet_traversal(peer); /* A packet with length 0 is a keepalive packet */ if (unlikely(!skb->len)) { update_rx_stats(peer, message_data_len(0)); net_dbg_ratelimited("%s: Receiving keepalive packet from peer %llu (%pISpfsc)\n", dev->name, peer->internal_id, &peer->endpoint.addr); goto packet_processed; } wg_timers_data_received(peer); if (unlikely(skb_network_header(skb) < skb->head)) goto dishonest_packet_size; if (unlikely(!(pskb_network_may_pull(skb, sizeof(struct iphdr)) && (ip_hdr(skb)->version == 4 || (ip_hdr(skb)->version == 6 && pskb_network_may_pull(skb, sizeof(struct ipv6hdr))))))) goto dishonest_packet_type; skb->dev = dev; /* We've already verified the Poly1305 auth tag, which means this packet * was not modified in transit. We can therefore tell the networking * stack that all checksums of every layer of encapsulation have already * been checked "by the hardware" and therefore is unnecessary to check * again in software. */ skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = ~0; /* All levels */ skb->protocol = ip_tunnel_parse_protocol(skb); if (skb->protocol == htons(ETH_P_IP)) { len = ntohs(ip_hdr(skb)->tot_len); if (unlikely(len < sizeof(struct iphdr))) goto dishonest_packet_size; INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ip_hdr(skb)->tos); } else if (skb->protocol == htons(ETH_P_IPV6)) { len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ipv6_get_dsfield(ipv6_hdr(skb))); } else { goto dishonest_packet_type; } if (unlikely(len > skb->len)) goto dishonest_packet_size; len_before_trim = skb->len; if (unlikely(pskb_trim(skb, len))) goto packet_processed; routed_peer = wg_allowedips_lookup_src(&peer->device->peer_allowedips, skb); wg_peer_put(routed_peer); /* We don't need the extra reference. */ if (unlikely(routed_peer != peer)) goto dishonest_packet_peer; napi_gro_receive(&peer->napi, skb); update_rx_stats(peer, message_data_len(len_before_trim)); return; dishonest_packet_peer: net_dbg_skb_ratelimited("%s: Packet has unallowed src IP (%pISc) from peer %llu (%pISpfsc)\n", dev->name, skb, peer->internal_id, &peer->endpoint.addr); DEV_STATS_INC(dev, rx_errors); DEV_STATS_INC(dev, rx_frame_errors); goto packet_processed; dishonest_packet_type: net_dbg_ratelimited("%s: Packet is neither ipv4 nor ipv6 from peer %llu (%pISpfsc)\n", dev->name, peer->internal_id, &peer->endpoint.addr); DEV_STATS_INC(dev, rx_errors); DEV_STATS_INC(dev, rx_frame_errors); goto packet_processed; dishonest_packet_size: net_dbg_ratelimited("%s: Packet has incorrect size from peer %llu (%pISpfsc)\n", dev->name, peer->internal_id, &peer->endpoint.addr); DEV_STATS_INC(dev, rx_errors); DEV_STATS_INC(dev, rx_length_errors); goto packet_processed; packet_processed: dev_kfree_skb(skb); } int wg_packet_rx_poll(struct napi_struct *napi, int budget) { struct wg_peer *peer = container_of(napi, struct wg_peer, napi); struct noise_keypair *keypair; struct endpoint endpoint; enum packet_state state; struct sk_buff *skb; int work_done = 0; bool free; if (unlikely(budget <= 0)) return 0; while ((skb = wg_prev_queue_peek(&peer->rx_queue)) != NULL && (state = atomic_read_acquire(&PACKET_CB(skb)->state)) != PACKET_STATE_UNCRYPTED) { wg_prev_queue_drop_peeked(&peer->rx_queue); keypair = PACKET_CB(skb)->keypair; free = true; if (unlikely(state != PACKET_STATE_CRYPTED)) goto next; if (unlikely(!counter_validate(&keypair->receiving_counter, PACKET_CB(skb)->nonce))) { net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n", peer->device->dev->name, PACKET_CB(skb)->nonce, READ_ONCE(keypair->receiving_counter.counter)); goto next; } if (unlikely(wg_socket_endpoint_from_skb(&endpoint, skb))) goto next; wg_reset_packet(skb, false); wg_packet_consume_data_done(peer, skb, &endpoint); free = false; next: wg_noise_keypair_put(keypair, false); wg_peer_put(peer); if (unlikely(free)) dev_kfree_skb(skb); if (++work_done >= budget) break; } if (work_done < budget) napi_complete_done(napi, work_done); return work_done; } void wg_packet_decrypt_worker(struct work_struct *work) { struct crypt_queue *queue = container_of(work, struct multicore_worker, work)->ptr; struct sk_buff *skb; while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) { enum packet_state state = likely(decrypt_packet(skb, PACKET_CB(skb)->keypair)) ? PACKET_STATE_CRYPTED : PACKET_STATE_DEAD; wg_queue_enqueue_per_peer_rx(skb, state); if (need_resched()) cond_resched(); } } static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb) { __le32 idx = ((struct message_data *)skb->data)->key_idx; struct wg_peer *peer = NULL; int ret; rcu_read_lock_bh(); PACKET_CB(skb)->keypair = (struct noise_keypair *)wg_index_hashtable_lookup( wg->index_hashtable, INDEX_HASHTABLE_KEYPAIR, idx, &peer); if (unlikely(!wg_noise_keypair_get(PACKET_CB(skb)->keypair))) goto err_keypair; if (unlikely(READ_ONCE(peer->is_dead))) goto err; ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, &peer->rx_queue, skb, wg->packet_crypt_wq); if (unlikely(ret == -EPIPE)) wg_queue_enqueue_per_peer_rx(skb, PACKET_STATE_DEAD); if (likely(!ret || ret == -EPIPE)) { rcu_read_unlock_bh(); return; } err: wg_noise_keypair_put(PACKET_CB(skb)->keypair, false); err_keypair: rcu_read_unlock_bh(); wg_peer_put(peer); dev_kfree_skb(skb); } void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb) { if (unlikely(prepare_skb_header(skb, wg) < 0)) goto err; switch (SKB_TYPE_LE32(skb)) { case cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION): case cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE): case cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE): { int cpu, ret = -EBUSY; if (unlikely(!rng_is_initialized())) goto drop; if (atomic_read(&wg->handshake_queue_len) > MAX_QUEUED_INCOMING_HANDSHAKES / 2) { if (spin_trylock_bh(&wg->handshake_queue.ring.producer_lock)) { ret = __ptr_ring_produce(&wg->handshake_queue.ring, skb); spin_unlock_bh(&wg->handshake_queue.ring.producer_lock); } } else ret = ptr_ring_produce_bh(&wg->handshake_queue.ring, skb); if (ret) { drop: net_dbg_skb_ratelimited("%s: Dropping handshake packet from %pISpfsc\n", wg->dev->name, skb); goto err; } atomic_inc(&wg->handshake_queue_len); cpu = wg_cpumask_next_online(&wg->handshake_queue.last_cpu); /* Queues up a call to packet_process_queued_handshake_packets(skb): */ queue_work_on(cpu, wg->handshake_receive_wq, &per_cpu_ptr(wg->handshake_queue.worker, cpu)->work); break; } case cpu_to_le32(MESSAGE_DATA): PACKET_CB(skb)->ds = ip_tunnel_get_dsfield(ip_hdr(skb), skb); wg_packet_consume_data(wg, skb); break; default: WARN(1, "Non-exhaustive parsing of packet header lead to unknown packet type!\n"); goto err; } return; err: dev_kfree_skb(skb); } |
| 5 5 1 1 1 1 6 5 5 6 6 5 5 5 5 2 2 1 7 7 2 2 2 2 2 5 1 6 6 6 5 154 154 154 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPVS: Locality-Based Least-Connection with Replication scheduler * * Authors: Wensong Zhang <wensong@gnuchina.org> * * Changes: * Julian Anastasov : Added the missing (dest->weight>0) * condition in the ip_vs_dest_set_max. */ /* * The lblc/r algorithm is as follows (pseudo code): * * if serverSet[dest_ip] is null then * n, serverSet[dest_ip] <- {weighted least-conn node}; * else * n <- {least-conn (alive) node in serverSet[dest_ip]}; * if (n is null) OR * (n.conns>n.weight AND * there is a node m with m.conns<m.weight/2) then * n <- {weighted least-conn node}; * add n to serverSet[dest_ip]; * if |serverSet[dest_ip]| > 1 AND * now - serverSet[dest_ip].lastMod > T then * m <- {most conn node in serverSet[dest_ip]}; * remove m from serverSet[dest_ip]; * if serverSet[dest_ip] changed then * serverSet[dest_ip].lastMod <- now; * * return n; * */ #define pr_fmt(fmt) "IPVS: " fmt #include <linux/ip.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/jiffies.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/hash.h> /* for sysctl */ #include <linux/fs.h> #include <linux/sysctl.h> #include <net/net_namespace.h> #include <net/ip_vs.h> /* * It is for garbage collection of stale IPVS lblcr entries, * when the table is full. */ #define CHECK_EXPIRE_INTERVAL (60*HZ) #define ENTRY_TIMEOUT (6*60*HZ) #define DEFAULT_EXPIRATION (24*60*60*HZ) /* * It is for full expiration check. * When there is no partial expiration check (garbage collection) * in a half hour, do a full expiration check to collect stale * entries that haven't been touched for a day. */ #define COUNT_FOR_FULL_EXPIRATION 30 /* * for IPVS lblcr entry hash table */ #ifndef CONFIG_IP_VS_LBLCR_TAB_BITS #define CONFIG_IP_VS_LBLCR_TAB_BITS 10 #endif #define IP_VS_LBLCR_TAB_BITS CONFIG_IP_VS_LBLCR_TAB_BITS #define IP_VS_LBLCR_TAB_SIZE (1 << IP_VS_LBLCR_TAB_BITS) #define IP_VS_LBLCR_TAB_MASK (IP_VS_LBLCR_TAB_SIZE - 1) /* * IPVS destination set structure and operations */ struct ip_vs_dest_set_elem { struct list_head list; /* list link */ struct ip_vs_dest *dest; /* destination server */ struct rcu_head rcu_head; }; struct ip_vs_dest_set { atomic_t size; /* set size */ unsigned long lastmod; /* last modified time */ struct list_head list; /* destination list */ }; static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set, struct ip_vs_dest *dest, bool check) { struct ip_vs_dest_set_elem *e; if (check) { list_for_each_entry(e, &set->list, list) { if (e->dest == dest) return; } } e = kmalloc_obj(*e, GFP_ATOMIC); if (e == NULL) return; ip_vs_dest_hold(dest); e->dest = dest; list_add_rcu(&e->list, &set->list); atomic_inc(&set->size); set->lastmod = jiffies; } static void ip_vs_lblcr_elem_rcu_free(struct rcu_head *head) { struct ip_vs_dest_set_elem *e; e = container_of(head, struct ip_vs_dest_set_elem, rcu_head); ip_vs_dest_put_and_free(e->dest); kfree(e); } static void ip_vs_dest_set_erase(struct ip_vs_dest_set *set, struct ip_vs_dest *dest) { struct ip_vs_dest_set_elem *e; list_for_each_entry(e, &set->list, list) { if (e->dest == dest) { /* HIT */ atomic_dec(&set->size); set->lastmod = jiffies; list_del_rcu(&e->list); call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free); break; } } } static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set) { struct ip_vs_dest_set_elem *e, *ep; list_for_each_entry_safe(e, ep, &set->list, list) { list_del_rcu(&e->list); call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free); } } /* get weighted least-connection node in the destination set */ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) { struct ip_vs_dest_set_elem *e; struct ip_vs_dest *dest, *least; int loh, doh; /* select the first destination server, whose weight > 0 */ list_for_each_entry_rcu(e, &set->list, list) { least = e->dest; if (least->flags & IP_VS_DEST_F_OVERLOAD) continue; if ((atomic_read(&least->weight) > 0) && (least->cflags & IP_VS_DEST_CF_AVAILABLE)) { loh = ip_vs_dest_conn_overhead(least); goto nextstage; } } return NULL; /* find the destination with the weighted least load */ nextstage: list_for_each_entry_continue_rcu(e, &set->list, list) { dest = e->dest; if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_dest_conn_overhead(dest); if (((__s64)loh * atomic_read(&dest->weight) > (__s64)doh * atomic_read(&least->weight)) && (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) { least = dest; loh = doh; } } IP_VS_DBG_BUF(6, "%s(): server %s:%d " "activeconns %d refcnt %d weight %d overhead %d\n", __func__, IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; } /* get weighted most-connection node in the destination set */ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) { struct ip_vs_dest_set_elem *e; struct ip_vs_dest *dest, *most; int moh, doh; if (set == NULL) return NULL; /* select the first destination server, whose weight > 0 */ list_for_each_entry(e, &set->list, list) { most = e->dest; if (atomic_read(&most->weight) > 0) { moh = ip_vs_dest_conn_overhead(most); goto nextstage; } } return NULL; /* find the destination with the weighted most load */ nextstage: list_for_each_entry_continue(e, &set->list, list) { dest = e->dest; doh = ip_vs_dest_conn_overhead(dest); /* moh/mw < doh/dw ==> moh*dw < doh*mw, where mw,dw>0 */ if (((__s64)moh * atomic_read(&dest->weight) < (__s64)doh * atomic_read(&most->weight)) && (atomic_read(&dest->weight) > 0)) { most = dest; moh = doh; } } IP_VS_DBG_BUF(6, "%s(): server %s:%d " "activeconns %d refcnt %d weight %d overhead %d\n", __func__, IP_VS_DBG_ADDR(most->af, &most->addr), ntohs(most->port), atomic_read(&most->activeconns), refcount_read(&most->refcnt), atomic_read(&most->weight), moh); return most; } /* * IPVS lblcr entry represents an association between destination * IP address and its destination server set */ struct ip_vs_lblcr_entry { struct hlist_node list; int af; /* address family */ union nf_inet_addr addr; /* destination IP address */ struct ip_vs_dest_set set; /* destination server set */ unsigned long lastuse; /* last used time */ struct rcu_head rcu_head; }; /* * IPVS lblcr hash table */ struct ip_vs_lblcr_table { struct rcu_head rcu_head; struct hlist_head bucket[IP_VS_LBLCR_TAB_SIZE]; /* hash bucket */ atomic_t entries; /* number of entries */ int max_size; /* maximum size of entries */ struct timer_list periodic_timer; /* collect stale entries */ struct ip_vs_service *svc; /* pointer back to service */ int rover; /* rover for expire check */ int counter; /* counter for no expire */ bool dead; }; #ifdef CONFIG_SYSCTL /* * IPVS LBLCR sysctl table */ static struct ctl_table vs_vars_table[] = { { .procname = "lblcr_expiration", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, }; #endif static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en) { hlist_del_rcu(&en->list); ip_vs_dest_set_eraseall(&en->set); kfree_rcu(en, rcu_head); } /* * Returns hash value for IPVS LBLCR entry */ static inline unsigned int ip_vs_lblcr_hashkey(int af, const union nf_inet_addr *addr) { __be32 addr_fold = addr->ip; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif return hash_32(ntohl(addr_fold), IP_VS_LBLCR_TAB_BITS); } /* * Hash an entry in the ip_vs_lblcr_table. * returns bool success. */ static void ip_vs_lblcr_hash(struct ip_vs_lblcr_table *tbl, struct ip_vs_lblcr_entry *en) { unsigned int hash = ip_vs_lblcr_hashkey(en->af, &en->addr); hlist_add_head_rcu(&en->list, &tbl->bucket[hash]); atomic_inc(&tbl->entries); } /* Get ip_vs_lblcr_entry associated with supplied parameters. */ static inline struct ip_vs_lblcr_entry * ip_vs_lblcr_get(int af, struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *addr) { unsigned int hash = ip_vs_lblcr_hashkey(af, addr); struct ip_vs_lblcr_entry *en; hlist_for_each_entry_rcu(en, &tbl->bucket[hash], list) if (ip_vs_addr_equal(af, &en->addr, addr)) return en; return NULL; } /* * Create or update an ip_vs_lblcr_entry, which is a mapping of a destination * IP address to a server. Called under spin lock. */ static inline struct ip_vs_lblcr_entry * ip_vs_lblcr_new(struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *daddr, u16 af, struct ip_vs_dest *dest) { struct ip_vs_lblcr_entry *en; en = ip_vs_lblcr_get(af, tbl, daddr); if (!en) { en = kmalloc_obj(*en, GFP_ATOMIC); if (!en) return NULL; en->af = af; ip_vs_addr_copy(af, &en->addr, daddr); en->lastuse = jiffies; /* initialize its dest set */ atomic_set(&(en->set.size), 0); INIT_LIST_HEAD(&en->set.list); ip_vs_dest_set_insert(&en->set, dest, false); ip_vs_lblcr_hash(tbl, en); return en; } ip_vs_dest_set_insert(&en->set, dest, true); return en; } /* * Flush all the entries of the specified table. */ static void ip_vs_lblcr_flush(struct ip_vs_service *svc) { struct ip_vs_lblcr_table *tbl = svc->sched_data; int i; struct ip_vs_lblcr_entry *en; struct hlist_node *next; spin_lock_bh(&svc->sched_lock); tbl->dead = true; for (i = 0; i < IP_VS_LBLCR_TAB_SIZE; i++) { hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) { ip_vs_lblcr_free(en); } } spin_unlock_bh(&svc->sched_lock); } static int sysctl_lblcr_expiration(struct ip_vs_service *svc) { #ifdef CONFIG_SYSCTL return svc->ipvs->sysctl_lblcr_expiration; #else return DEFAULT_EXPIRATION; #endif } static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc) { struct ip_vs_lblcr_table *tbl = svc->sched_data; unsigned long now = jiffies; int i, j; struct ip_vs_lblcr_entry *en; struct hlist_node *next; for (i = 0, j = tbl->rover; i < IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; spin_lock(&svc->sched_lock); hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) { if (time_after(en->lastuse + sysctl_lblcr_expiration(svc), now)) continue; ip_vs_lblcr_free(en); atomic_dec(&tbl->entries); } spin_unlock(&svc->sched_lock); } tbl->rover = j; } /* * Periodical timer handler for IPVS lblcr table * It is used to collect stale entries when the number of entries * exceeds the maximum size of the table. * * Fixme: we probably need more complicated algorithm to collect * entries that have not been used for a long time even * if the number of entries doesn't exceed the maximum size * of the table. * The full expiration check is for this purpose now. */ static void ip_vs_lblcr_check_expire(struct timer_list *t) { struct ip_vs_lblcr_table *tbl = timer_container_of(tbl, t, periodic_timer); struct ip_vs_service *svc = tbl->svc; unsigned long now = jiffies; int goal; int i, j; struct ip_vs_lblcr_entry *en; struct hlist_node *next; if ((tbl->counter % COUNT_FOR_FULL_EXPIRATION) == 0) { /* do full expiration check */ ip_vs_lblcr_full_check(svc); tbl->counter = 1; goto out; } if (atomic_read(&tbl->entries) <= tbl->max_size) { tbl->counter++; goto out; } goal = (atomic_read(&tbl->entries) - tbl->max_size)*4/3; if (goal > tbl->max_size/2) goal = tbl->max_size/2; for (i = 0, j = tbl->rover; i < IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; spin_lock(&svc->sched_lock); hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) { if (time_before(now, en->lastuse+ENTRY_TIMEOUT)) continue; ip_vs_lblcr_free(en); atomic_dec(&tbl->entries); goal--; } spin_unlock(&svc->sched_lock); if (goal <= 0) break; } tbl->rover = j; out: mod_timer(&tbl->periodic_timer, jiffies+CHECK_EXPIRE_INTERVAL); } static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) { int i; struct ip_vs_lblcr_table *tbl; /* * Allocate the ip_vs_lblcr_table for this service */ tbl = kmalloc_obj(*tbl); if (tbl == NULL) return -ENOMEM; svc->sched_data = tbl; IP_VS_DBG(6, "LBLCR hash table (memory=%zdbytes) allocated for " "current service\n", sizeof(*tbl)); /* * Initialize the hash buckets */ for (i = 0; i < IP_VS_LBLCR_TAB_SIZE; i++) { INIT_HLIST_HEAD(&tbl->bucket[i]); } tbl->max_size = IP_VS_LBLCR_TAB_SIZE*16; tbl->rover = 0; tbl->counter = 1; tbl->dead = false; tbl->svc = svc; atomic_set(&tbl->entries, 0); /* * Hook periodic timer for garbage collection */ timer_setup(&tbl->periodic_timer, ip_vs_lblcr_check_expire, 0); mod_timer(&tbl->periodic_timer, jiffies + CHECK_EXPIRE_INTERVAL); return 0; } static void ip_vs_lblcr_done_svc(struct ip_vs_service *svc) { struct ip_vs_lblcr_table *tbl = svc->sched_data; /* remove periodic timer */ timer_shutdown_sync(&tbl->periodic_timer); /* got to clean up table entries here */ ip_vs_lblcr_flush(svc); /* release the table itself */ kfree_rcu(tbl, rcu_head); IP_VS_DBG(6, "LBLCR hash table (memory=%zdbytes) released\n", sizeof(*tbl)); } static inline struct ip_vs_dest * __ip_vs_lblcr_schedule(struct ip_vs_service *svc) { struct ip_vs_dest *dest, *least; int loh, doh; /* * We use the following formula to estimate the load: * (dest overhead) / dest->weight * * Remember -- no floats in kernel mode!!! * The comparison of h1*w2 > h2*w1 is equivalent to that of * h1/w1 > h2/w2 * if every weight is larger than zero. * * The server with weight=0 is quiesced and will not receive any * new connection. */ list_for_each_entry_rcu(dest, &svc->destinations, n_list) { if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; if (atomic_read(&dest->weight) > 0) { least = dest; loh = ip_vs_dest_conn_overhead(least); goto nextstage; } } return NULL; /* * Find the destination with the least load. */ nextstage: list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) { if (dest->flags & IP_VS_DEST_F_OVERLOAD) continue; doh = ip_vs_dest_conn_overhead(dest); if ((__s64)loh * atomic_read(&dest->weight) > (__s64)doh * atomic_read(&least->weight)) { least = dest; loh = doh; } } IP_VS_DBG_BUF(6, "LBLCR: server %s:%d " "activeconns %d refcnt %d weight %d overhead %d\n", IP_VS_DBG_ADDR(least->af, &least->addr), ntohs(least->port), atomic_read(&least->activeconns), refcount_read(&least->refcnt), atomic_read(&least->weight), loh); return least; } /* * If this destination server is overloaded and there is a less loaded * server, then return true. */ static inline int is_overloaded(struct ip_vs_dest *dest, struct ip_vs_service *svc) { if (atomic_read(&dest->activeconns) > atomic_read(&dest->weight)) { struct ip_vs_dest *d; list_for_each_entry_rcu(d, &svc->destinations, n_list) { if (atomic_read(&d->activeconns)*2 < atomic_read(&d->weight)) { return 1; } } } return 0; } /* * Locality-Based (weighted) Least-Connection scheduling */ static struct ip_vs_dest * ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_lblcr_table *tbl = svc->sched_data; struct ip_vs_dest *dest; struct ip_vs_lblcr_entry *en; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); /* First look in our cache */ en = ip_vs_lblcr_get(svc->af, tbl, &iph->daddr); if (en) { en->lastuse = jiffies; /* Get the least loaded destination */ dest = ip_vs_dest_set_min(&en->set); /* More than one destination + enough time passed by, cleanup */ if (atomic_read(&en->set.size) > 1 && time_after(jiffies, en->set.lastmod + sysctl_lblcr_expiration(svc))) { spin_lock_bh(&svc->sched_lock); if (atomic_read(&en->set.size) > 1) { struct ip_vs_dest *m; m = ip_vs_dest_set_max(&en->set); if (m) ip_vs_dest_set_erase(&en->set, m); } spin_unlock_bh(&svc->sched_lock); } /* If the destination is not overloaded, use it */ if (dest && !is_overloaded(dest, svc)) goto out; /* The cache entry is invalid, time to schedule */ dest = __ip_vs_lblcr_schedule(svc); if (!dest) { ip_vs_scheduler_err(svc, "no destination available"); return NULL; } /* Update our cache entry */ spin_lock_bh(&svc->sched_lock); if (!tbl->dead) ip_vs_dest_set_insert(&en->set, dest, true); spin_unlock_bh(&svc->sched_lock); goto out; } /* No cache entry, time to schedule */ dest = __ip_vs_lblcr_schedule(svc); if (!dest) { IP_VS_DBG(1, "no destination available\n"); return NULL; } /* If we fail to create a cache entry, we'll just use the valid dest */ spin_lock_bh(&svc->sched_lock); if (!tbl->dead) ip_vs_lblcr_new(tbl, &iph->daddr, svc->af, dest); spin_unlock_bh(&svc->sched_lock); out: IP_VS_DBG_BUF(6, "LBLCR: destination IP address %s --> server %s:%d\n", IP_VS_DBG_ADDR(svc->af, &iph->daddr), IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port)); return dest; } /* * IPVS LBLCR Scheduler structure */ static struct ip_vs_scheduler ip_vs_lblcr_scheduler = { .name = "lblcr", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_lblcr_scheduler.n_list), .init_service = ip_vs_lblcr_init_svc, .done_service = ip_vs_lblcr_done_svc, .schedule = ip_vs_lblcr_schedule, }; /* * per netns init. */ #ifdef CONFIG_SYSCTL static int __net_init __ip_vs_lblcr_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); size_t vars_table_size = ARRAY_SIZE(vs_vars_table); if (!ipvs) return -ENOENT; if (!net_eq(net, &init_net)) { ipvs->lblcr_ctl_table = kmemdup(vs_vars_table, sizeof(vs_vars_table), GFP_KERNEL); if (ipvs->lblcr_ctl_table == NULL) return -ENOMEM; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) vars_table_size = 0; } else ipvs->lblcr_ctl_table = vs_vars_table; ipvs->sysctl_lblcr_expiration = DEFAULT_EXPIRATION; ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration; ipvs->lblcr_ctl_header = register_net_sysctl_sz(net, "net/ipv4/vs", ipvs->lblcr_ctl_table, vars_table_size); if (!ipvs->lblcr_ctl_header) { if (!net_eq(net, &init_net)) kfree(ipvs->lblcr_ctl_table); return -ENOMEM; } return 0; } static void __net_exit __ip_vs_lblcr_exit(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); unregister_net_sysctl_table(ipvs->lblcr_ctl_header); if (!net_eq(net, &init_net)) kfree(ipvs->lblcr_ctl_table); } #else static int __net_init __ip_vs_lblcr_init(struct net *net) { return 0; } static void __net_exit __ip_vs_lblcr_exit(struct net *net) { } #endif static struct pernet_operations ip_vs_lblcr_ops = { .init = __ip_vs_lblcr_init, .exit = __ip_vs_lblcr_exit, }; static int __init ip_vs_lblcr_init(void) { int ret; ret = register_pernet_subsys(&ip_vs_lblcr_ops); if (ret) return ret; ret = register_ip_vs_scheduler(&ip_vs_lblcr_scheduler); if (ret) unregister_pernet_subsys(&ip_vs_lblcr_ops); return ret; } static void __exit ip_vs_lblcr_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler); unregister_pernet_subsys(&ip_vs_lblcr_ops); rcu_barrier(); } module_init(ip_vs_lblcr_init); module_exit(ip_vs_lblcr_cleanup); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ipvs locality-based least-connection with replication scheduler"); |
| 89 36 66 171 158 18 3 3 206 176 25 1 20 214 207 209 206 6 6 174 176 10 7 7 3 3 5 4 2 36 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_fifo.c The simplest FIFO queue. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> /* 1 band FIFO pseudo-"scheduler" */ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= READ_ONCE(sch->limit))) return qdisc_enqueue_tail(skb, sch); return qdisc_drop(skb, sch, to_free); } static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { if (likely(sch->q.qlen < READ_ONCE(sch->limit))) return qdisc_enqueue_tail(skb, sch); return qdisc_drop(skb, sch, to_free); } static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { unsigned int prev_backlog; if (unlikely(READ_ONCE(sch->limit) == 0)) return qdisc_drop(skb, sch, to_free); if (likely(sch->q.qlen < READ_ONCE(sch->limit))) return qdisc_enqueue_tail(skb, sch); prev_backlog = sch->qstats.backlog; /* queue full, remove one skb to fulfill the limit */ __qdisc_queue_drop_head(sch, &sch->q, to_free); qdisc_qstats_drop(sch); qdisc_enqueue_tail(skb, sch); qdisc_tree_reduce_backlog(sch, 0, prev_backlog - sch->qstats.backlog); return NET_XMIT_CN; } static void fifo_offload_init(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct tc_fifo_qopt_offload qopt; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return; qopt.command = TC_FIFO_REPLACE; qopt.handle = sch->handle; qopt.parent = sch->parent; dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_FIFO, &qopt); } static void fifo_offload_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct tc_fifo_qopt_offload qopt; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return; qopt.command = TC_FIFO_DESTROY; qopt.handle = sch->handle; qopt.parent = sch->parent; dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_FIFO, &qopt); } static int fifo_offload_dump(struct Qdisc *sch) { struct tc_fifo_qopt_offload qopt; qopt.command = TC_FIFO_STATS; qopt.handle = sch->handle; qopt.parent = sch->parent; qopt.stats.bstats = &sch->bstats; qopt.stats.qstats = &sch->qstats; return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_FIFO, &qopt); } static int __fifo_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { bool bypass; bool is_bfifo = sch->ops == &bfifo_qdisc_ops; if (opt == NULL) { u32 limit = qdisc_dev(sch)->tx_queue_len; if (is_bfifo) limit *= psched_mtu(qdisc_dev(sch)); WRITE_ONCE(sch->limit, limit); } else { struct tc_fifo_qopt *ctl = nla_data(opt); if (nla_len(opt) < sizeof(*ctl)) return -EINVAL; WRITE_ONCE(sch->limit, ctl->limit); } if (is_bfifo) bypass = sch->limit >= psched_mtu(qdisc_dev(sch)); else bypass = sch->limit >= 1; if (bypass) sch->flags |= TCQ_F_CAN_BYPASS; else sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } static int fifo_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { int err; err = __fifo_init(sch, opt, extack); if (err) return err; fifo_offload_init(sch); return 0; } static int fifo_hd_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { return __fifo_init(sch, opt, extack); } static void fifo_destroy(struct Qdisc *sch) { fifo_offload_destroy(sch); } static int __fifo_dump(struct Qdisc *sch, struct sk_buff *skb) { struct tc_fifo_qopt opt = { .limit = READ_ONCE(sch->limit) }; if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; return skb->len; nla_put_failure: return -1; } static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb) { int err; err = fifo_offload_dump(sch); if (err) return err; return __fifo_dump(sch, skb); } static int fifo_hd_dump(struct Qdisc *sch, struct sk_buff *skb) { return __fifo_dump(sch, skb); } struct Qdisc_ops pfifo_qdisc_ops __read_mostly = { .id = "pfifo", .priv_size = 0, .enqueue = pfifo_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, .init = fifo_init, .destroy = fifo_destroy, .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, .owner = THIS_MODULE, }; EXPORT_SYMBOL(pfifo_qdisc_ops); struct Qdisc_ops bfifo_qdisc_ops __read_mostly = { .id = "bfifo", .priv_size = 0, .enqueue = bfifo_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, .init = fifo_init, .destroy = fifo_destroy, .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, .owner = THIS_MODULE, }; EXPORT_SYMBOL(bfifo_qdisc_ops); struct Qdisc_ops pfifo_head_drop_qdisc_ops __read_mostly = { .id = "pfifo_head_drop", .priv_size = 0, .enqueue = pfifo_tail_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, .init = fifo_hd_init, .reset = qdisc_reset_queue, .change = fifo_hd_init, .dump = fifo_hd_dump, .owner = THIS_MODULE, }; /* Pass size change message down to embedded FIFO */ int fifo_set_limit(struct Qdisc *q, unsigned int limit) { struct nlattr *nla; int ret = -ENOMEM; /* Hack to avoid sending change message to non-FIFO */ if (strncmp(q->ops->id + 1, "fifo", 4) != 0) return 0; if (!q->ops->change) return 0; nla = kmalloc(nla_attr_size(sizeof(struct tc_fifo_qopt)), GFP_KERNEL); if (nla) { nla->nla_type = RTM_NEWQDISC; nla->nla_len = nla_attr_size(sizeof(struct tc_fifo_qopt)); ((struct tc_fifo_qopt *)nla_data(nla))->limit = limit; ret = q->ops->change(q, nla, NULL); kfree(nla); } return ret; } EXPORT_SYMBOL(fifo_set_limit); struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, unsigned int limit, struct netlink_ext_ack *extack) { struct Qdisc *q; int err = -ENOMEM; q = qdisc_create_dflt(sch->dev_queue, ops, TC_H_MAKE(sch->handle, 1), extack); if (q) { err = fifo_set_limit(q, limit); if (err < 0) { qdisc_put(q); q = NULL; } } return q ? : ERR_PTR(err); } EXPORT_SYMBOL(fifo_create_dflt); MODULE_DESCRIPTION("Single queue packet and byte based First In First Out(P/BFIFO) scheduler"); |
| 8 2091 578 2 2 7 6 1 7 7 4 2 6 2 2 1 1 1 3 2 1 1 1 623 596 65 9 9 298 298 298 2433 2156 1 627 2358 2360 569 7 1 2 4 3 1 1479 533 66 1479 297 2452 2446 1479 597 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 | // SPDX-License-Identifier: GPL-2.0 /* * Management Component Transport Protocol (MCTP) - device implementation. * * Copyright (c) 2021 Code Construct * Copyright (c) 2021 Google */ #include <linux/if_arp.h> #include <linux/if_link.h> #include <linux/mctp.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <linux/rtnetlink.h> #include <net/addrconf.h> #include <net/netlink.h> #include <net/mctp.h> #include <net/mctpdevice.h> #include <net/sock.h> struct mctp_dump_cb { unsigned long ifindex; size_t a_idx; }; /* unlocked: caller must hold rcu_read_lock. * Returned mctp_dev has its refcount incremented, or NULL if unset. */ struct mctp_dev *__mctp_dev_get(const struct net_device *dev) { struct mctp_dev *mdev = rcu_dereference(dev->mctp_ptr); /* RCU guarantees that any mdev is still live. * Zero refcount implies a pending free, return NULL. */ if (mdev) if (!refcount_inc_not_zero(&mdev->refs)) return NULL; return mdev; } /* Returned mctp_dev does not have refcount incremented. The returned pointer * remains live while rtnl_lock is held, as that prevents mctp_unregister() */ struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->mctp_ptr); } static int mctp_addrinfo_size(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(1) // IFA_LOCAL + nla_total_size(1) // IFA_ADDRESS ; } /* flag should be NLM_F_MULTI for dump calls */ static int mctp_fill_addrinfo(struct sk_buff *skb, struct mctp_dev *mdev, mctp_eid_t eid, int msg_type, u32 portid, u32 seq, int flag) { struct ifaddrmsg *hdr; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, portid, seq, msg_type, sizeof(*hdr), flag); if (!nlh) return -EMSGSIZE; hdr = nlmsg_data(nlh); memset(hdr, 0, sizeof(*hdr)); hdr->ifa_family = AF_MCTP; hdr->ifa_prefixlen = 0; hdr->ifa_flags = 0; hdr->ifa_scope = 0; hdr->ifa_index = mdev->dev->ifindex; if (nla_put_u8(skb, IFA_LOCAL, eid)) goto cancel; if (nla_put_u8(skb, IFA_ADDRESS, eid)) goto cancel; nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int mctp_dump_dev_addrinfo(struct mctp_dev *mdev, struct sk_buff *skb, struct netlink_callback *cb) { struct mctp_dump_cb *mcb = (void *)cb->ctx; u32 portid, seq; int rc = 0; portid = NETLINK_CB(cb->skb).portid; seq = cb->nlh->nlmsg_seq; for (; mcb->a_idx < mdev->num_addrs; mcb->a_idx++) { rc = mctp_fill_addrinfo(skb, mdev, mdev->addrs[mcb->a_idx], RTM_NEWADDR, portid, seq, NLM_F_MULTI); if (rc < 0) break; } return rc; } static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct mctp_dump_cb *mcb = (void *)cb->ctx; struct net *net = sock_net(skb->sk); struct net_device *dev; struct ifaddrmsg *hdr; struct mctp_dev *mdev; int ifindex = 0, rc; /* Filter by ifindex if a header is provided */ hdr = nlmsg_payload(cb->nlh, sizeof(*hdr)); if (hdr) { ifindex = hdr->ifa_index; } else { if (cb->strict_check) { NL_SET_ERR_MSG(cb->extack, "mctp: Invalid header for addr dump request"); return -EINVAL; } } rcu_read_lock(); for_each_netdev_dump(net, dev, mcb->ifindex) { if (ifindex && ifindex != dev->ifindex) continue; mdev = __mctp_dev_get(dev); if (!mdev) continue; rc = mctp_dump_dev_addrinfo(mdev, skb, cb); mctp_dev_put(mdev); if (rc < 0) break; mcb->a_idx = 0; } rcu_read_unlock(); return skb->len; } static void mctp_addr_notify(struct mctp_dev *mdev, mctp_eid_t eid, int msg_type, struct sk_buff *req_skb, struct nlmsghdr *req_nlh) { u32 portid = NETLINK_CB(req_skb).portid; struct net *net = dev_net(mdev->dev); struct sk_buff *skb; int rc = -ENOBUFS; skb = nlmsg_new(mctp_addrinfo_size(), GFP_KERNEL); if (!skb) goto out; rc = mctp_fill_addrinfo(skb, mdev, eid, msg_type, portid, req_nlh->nlmsg_seq, 0); if (rc < 0) { WARN_ON_ONCE(rc == -EMSGSIZE); goto out; } rtnl_notify(skb, net, portid, RTNLGRP_MCTP_IFADDR, req_nlh, GFP_KERNEL); return; out: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_MCTP_IFADDR, rc); } static const struct nla_policy ifa_mctp_policy[IFA_MAX + 1] = { [IFA_ADDRESS] = { .type = NLA_U8 }, [IFA_LOCAL] = { .type = NLA_U8 }, }; static int mctp_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[IFA_MAX + 1]; struct net_device *dev; struct mctp_addr *addr; struct mctp_dev *mdev; struct ifaddrmsg *ifm; unsigned long flags; u8 *tmp_addrs; int rc; rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_mctp_policy, extack); if (rc < 0) return rc; ifm = nlmsg_data(nlh); if (tb[IFA_LOCAL]) addr = nla_data(tb[IFA_LOCAL]); else if (tb[IFA_ADDRESS]) addr = nla_data(tb[IFA_ADDRESS]); else return -EINVAL; /* find device */ dev = __dev_get_by_index(net, ifm->ifa_index); if (!dev) return -ENODEV; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return -ENODEV; if (!mctp_address_unicast(addr->s_addr)) return -EINVAL; /* Prevent duplicates. Under RTNL so don't need to lock for reading */ if (memchr(mdev->addrs, addr->s_addr, mdev->num_addrs)) return -EEXIST; tmp_addrs = kmalloc(mdev->num_addrs + 1, GFP_KERNEL); if (!tmp_addrs) return -ENOMEM; memcpy(tmp_addrs, mdev->addrs, mdev->num_addrs); tmp_addrs[mdev->num_addrs] = addr->s_addr; /* Lock to write */ spin_lock_irqsave(&mdev->addrs_lock, flags); mdev->num_addrs++; swap(mdev->addrs, tmp_addrs); spin_unlock_irqrestore(&mdev->addrs_lock, flags); kfree(tmp_addrs); mctp_addr_notify(mdev, addr->s_addr, RTM_NEWADDR, skb, nlh); mctp_route_add_local(mdev, addr->s_addr); return 0; } static int mctp_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[IFA_MAX + 1]; struct net_device *dev; struct mctp_addr *addr; struct mctp_dev *mdev; struct ifaddrmsg *ifm; unsigned long flags; u8 *pos; int rc; rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_mctp_policy, extack); if (rc < 0) return rc; ifm = nlmsg_data(nlh); if (tb[IFA_LOCAL]) addr = nla_data(tb[IFA_LOCAL]); else if (tb[IFA_ADDRESS]) addr = nla_data(tb[IFA_ADDRESS]); else return -EINVAL; /* find device */ dev = __dev_get_by_index(net, ifm->ifa_index); if (!dev) return -ENODEV; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return -ENODEV; pos = memchr(mdev->addrs, addr->s_addr, mdev->num_addrs); if (!pos) return -ENOENT; rc = mctp_route_remove_local(mdev, addr->s_addr); // we can ignore -ENOENT in the case a route was already removed if (rc < 0 && rc != -ENOENT) return rc; spin_lock_irqsave(&mdev->addrs_lock, flags); memmove(pos, pos + 1, mdev->num_addrs - 1 - (pos - mdev->addrs)); mdev->num_addrs--; spin_unlock_irqrestore(&mdev->addrs_lock, flags); mctp_addr_notify(mdev, addr->s_addr, RTM_DELADDR, skb, nlh); return 0; } void mctp_dev_hold(struct mctp_dev *mdev) { refcount_inc(&mdev->refs); } void mctp_dev_put(struct mctp_dev *mdev) { if (mdev && refcount_dec_and_test(&mdev->refs)) { kfree(mdev->addrs); dev_put(mdev->dev); kfree_rcu(mdev, rcu); } } void mctp_dev_release_key(struct mctp_dev *dev, struct mctp_sk_key *key) __must_hold(&key->lock) { if (!dev) return; if (dev->ops && dev->ops->release_flow) dev->ops->release_flow(dev, key); key->dev = NULL; mctp_dev_put(dev); } void mctp_dev_set_key(struct mctp_dev *dev, struct mctp_sk_key *key) __must_hold(&key->lock) { mctp_dev_hold(dev); key->dev = dev; } static struct mctp_dev *mctp_add_dev(struct net_device *dev) { struct mctp_dev *mdev; ASSERT_RTNL(); mdev = kzalloc_obj(*mdev); if (!mdev) return ERR_PTR(-ENOMEM); spin_lock_init(&mdev->addrs_lock); mdev->net = mctp_default_net(dev_net(dev)); /* associate to net_device */ refcount_set(&mdev->refs, 1); rcu_assign_pointer(dev->mctp_ptr, mdev); dev_hold(dev); mdev->dev = dev; return mdev; } static int mctp_fill_link_af(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask) { struct mctp_dev *mdev; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return -ENODATA; if (nla_put_u32(skb, IFLA_MCTP_NET, mdev->net)) return -EMSGSIZE; if (nla_put_u8(skb, IFLA_MCTP_PHYS_BINDING, mdev->binding)) return -EMSGSIZE; return 0; } static size_t mctp_get_link_af_size(const struct net_device *dev, u32 ext_filter_mask) { struct mctp_dev *mdev; unsigned int ret; /* caller holds RCU */ mdev = __mctp_dev_get(dev); if (!mdev) return 0; ret = nla_total_size(4); /* IFLA_MCTP_NET */ ret += nla_total_size(1); /* IFLA_MCTP_PHYS_BINDING */ mctp_dev_put(mdev); return ret; } static const struct nla_policy ifla_af_mctp_policy[IFLA_MCTP_MAX + 1] = { [IFLA_MCTP_NET] = { .type = NLA_U32 }, }; static int mctp_set_link_af(struct net_device *dev, const struct nlattr *attr, struct netlink_ext_ack *extack) { struct nlattr *tb[IFLA_MCTP_MAX + 1]; struct mctp_dev *mdev; int rc; rc = nla_parse_nested(tb, IFLA_MCTP_MAX, attr, ifla_af_mctp_policy, NULL); if (rc) return rc; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return 0; if (tb[IFLA_MCTP_NET]) WRITE_ONCE(mdev->net, nla_get_u32(tb[IFLA_MCTP_NET])); return 0; } /* Matches netdev types that should have MCTP handling */ static bool mctp_known(struct net_device *dev) { /* only register specific types (inc. NONE for TUN devices) */ return dev->type == ARPHRD_MCTP || dev->type == ARPHRD_LOOPBACK || dev->type == ARPHRD_NONE; } static void mctp_unregister(struct net_device *dev) { struct mctp_dev *mdev; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return; RCU_INIT_POINTER(mdev->dev->mctp_ptr, NULL); mctp_route_remove_dev(mdev); mctp_neigh_remove_dev(mdev); mctp_dev_put(mdev); } static int mctp_register(struct net_device *dev) { struct mctp_dev *mdev; /* Already registered? */ if (rtnl_dereference(dev->mctp_ptr)) return 0; /* only register specific types */ if (!mctp_known(dev)) return 0; mdev = mctp_add_dev(dev); if (IS_ERR(mdev)) return PTR_ERR(mdev); return 0; } static int mctp_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); int rc; switch (event) { case NETDEV_REGISTER: rc = mctp_register(dev); if (rc) return notifier_from_errno(rc); break; case NETDEV_UNREGISTER: mctp_unregister(dev); break; } return NOTIFY_OK; } static int mctp_register_netdevice(struct net_device *dev, const struct mctp_netdev_ops *ops, enum mctp_phys_binding binding) { struct mctp_dev *mdev; mdev = mctp_add_dev(dev); if (IS_ERR(mdev)) return PTR_ERR(mdev); mdev->ops = ops; mdev->binding = binding; return register_netdevice(dev); } int mctp_register_netdev(struct net_device *dev, const struct mctp_netdev_ops *ops, enum mctp_phys_binding binding) { int rc; rtnl_lock(); rc = mctp_register_netdevice(dev, ops, binding); rtnl_unlock(); return rc; } EXPORT_SYMBOL_GPL(mctp_register_netdev); void mctp_unregister_netdev(struct net_device *dev) { unregister_netdev(dev); } EXPORT_SYMBOL_GPL(mctp_unregister_netdev); static struct rtnl_af_ops mctp_af_ops = { .family = AF_MCTP, .fill_link_af = mctp_fill_link_af, .get_link_af_size = mctp_get_link_af_size, .set_link_af = mctp_set_link_af, }; static struct notifier_block mctp_dev_nb = { .notifier_call = mctp_dev_notify, .priority = ADDRCONF_NOTIFY_PRIORITY, }; static const struct rtnl_msg_handler mctp_device_rtnl_msg_handlers[] = { {.owner = THIS_MODULE, .protocol = PF_MCTP, .msgtype = RTM_NEWADDR, .doit = mctp_rtm_newaddr}, {.owner = THIS_MODULE, .protocol = PF_MCTP, .msgtype = RTM_DELADDR, .doit = mctp_rtm_deladdr}, {.owner = THIS_MODULE, .protocol = PF_MCTP, .msgtype = RTM_GETADDR, .dumpit = mctp_dump_addrinfo}, }; int __init mctp_device_init(void) { int err; err = register_netdevice_notifier(&mctp_dev_nb); if (err) return err; err = rtnl_af_register(&mctp_af_ops); if (err) goto err_notifier; err = rtnl_register_many(mctp_device_rtnl_msg_handlers); if (err) goto err_af; return 0; err_af: rtnl_af_unregister(&mctp_af_ops); err_notifier: unregister_netdevice_notifier(&mctp_dev_nb); return err; } void __exit mctp_device_exit(void) { rtnl_unregister_many(mctp_device_rtnl_msg_handlers); rtnl_af_unregister(&mctp_af_ops); unregister_netdevice_notifier(&mctp_dev_nb); } |
| 1 4 202 12 18 1 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UNALIGNED_H #define __LINUX_UNALIGNED_H /* * This is the most generic implementation of unaligned accesses * and should work almost anywhere. */ #include <linux/unaligned/packed_struct.h> #include <asm/byteorder.h> #include <vdso/unaligned.h> #define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) #define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr)) static inline u16 get_unaligned_le16(const void *p) { return le16_to_cpu(__get_unaligned_t(__le16, p)); } static inline u32 get_unaligned_le32(const void *p) { return le32_to_cpu(__get_unaligned_t(__le32, p)); } static inline u64 get_unaligned_le64(const void *p) { return le64_to_cpu(__get_unaligned_t(__le64, p)); } static inline void put_unaligned_le16(u16 val, void *p) { __put_unaligned_t(__le16, cpu_to_le16(val), p); } static inline void put_unaligned_le32(u32 val, void *p) { __put_unaligned_t(__le32, cpu_to_le32(val), p); } static inline void put_unaligned_le64(u64 val, void *p) { __put_unaligned_t(__le64, cpu_to_le64(val), p); } static inline u16 get_unaligned_be16(const void *p) { return be16_to_cpu(__get_unaligned_t(__be16, p)); } static inline u32 get_unaligned_be32(const void *p) { return be32_to_cpu(__get_unaligned_t(__be32, p)); } static inline u64 get_unaligned_be64(const void *p) { return be64_to_cpu(__get_unaligned_t(__be64, p)); } static inline void put_unaligned_be16(u16 val, void *p) { __put_unaligned_t(__be16, cpu_to_be16(val), p); } static inline void put_unaligned_be32(u32 val, void *p) { __put_unaligned_t(__be32, cpu_to_be32(val), p); } static inline void put_unaligned_be64(u64 val, void *p) { __put_unaligned_t(__be64, cpu_to_be64(val), p); } static inline u32 __get_unaligned_be24(const u8 *p) { return p[0] << 16 | p[1] << 8 | p[2]; } static inline u32 get_unaligned_be24(const void *p) { return __get_unaligned_be24(p); } static inline u32 __get_unaligned_le24(const u8 *p) { return p[0] | p[1] << 8 | p[2] << 16; } static inline u32 get_unaligned_le24(const void *p) { return __get_unaligned_le24(p); } static inline void __put_unaligned_be24(const u32 val, u8 *p) { *p++ = (val >> 16) & 0xff; *p++ = (val >> 8) & 0xff; *p++ = val & 0xff; } static inline void put_unaligned_be24(const u32 val, void *p) { __put_unaligned_be24(val, p); } static inline void __put_unaligned_le24(const u32 val, u8 *p) { *p++ = val & 0xff; *p++ = (val >> 8) & 0xff; *p++ = (val >> 16) & 0xff; } static inline void put_unaligned_le24(const u32 val, void *p) { __put_unaligned_le24(val, p); } static inline void __put_unaligned_be48(const u64 val, u8 *p) { *p++ = (val >> 40) & 0xff; *p++ = (val >> 32) & 0xff; *p++ = (val >> 24) & 0xff; *p++ = (val >> 16) & 0xff; *p++ = (val >> 8) & 0xff; *p++ = val & 0xff; } static inline void put_unaligned_be48(const u64 val, void *p) { __put_unaligned_be48(val, p); } static inline u64 __get_unaligned_be48(const u8 *p) { return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 | p[3] << 16 | p[4] << 8 | p[5]; } static inline u64 get_unaligned_be48(const void *p) { return __get_unaligned_be48(p); } #endif /* __LINUX_UNALIGNED_H */ |
| 67 66 64 59 63 67 67 58 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Linux VM pressure * * Copyright 2012 Linaro Ltd. * Anton Vorontsov <anton.vorontsov@linaro.org> * * Based on ideas from Andrew Morton, David Rientjes, KOSAKI Motohiro, * Leonid Moiseichuk, Mel Gorman, Minchan Kim and Pekka Enberg. */ #include <linux/cgroup.h> #include <linux/fs.h> #include <linux/log2.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/eventfd.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/printk.h> #include <linux/vmpressure.h> /* * The window size (vmpressure_win) is the number of scanned pages before * we try to analyze scanned/reclaimed ratio. So the window is used as a * rate-limit tunable for the "low" level notification, and also for * averaging the ratio for medium/critical levels. Using small window * sizes can cause lot of false positives, but too big window size will * delay the notifications. * * As the vmscan reclaimer logic works with chunks which are multiple of * SWAP_CLUSTER_MAX, it makes sense to use it for the window size as well. * * TODO: Make the window size depend on machine size, as we do for vmstat * thresholds. Currently we set it to 512 pages (2MB for 4KB pages). */ static const unsigned long vmpressure_win = SWAP_CLUSTER_MAX * 16; /* * These thresholds are used when we account memory pressure through * scanned/reclaimed ratio. The current values were chosen empirically. In * essence, they are percents: the higher the value, the more number * unsuccessful reclaims there were. */ static const unsigned int vmpressure_level_med = 60; static const unsigned int vmpressure_level_critical = 95; /* * When there are too little pages left to scan, vmpressure() may miss the * critical pressure as number of pages will be less than "window size". * However, in that case the vmscan priority will raise fast as the * reclaimer will try to scan LRUs more deeply. * * The vmscan logic considers these special priorities: * * prio == DEF_PRIORITY (12): reclaimer starts with that value * prio <= DEF_PRIORITY - 2 : kswapd becomes somewhat overwhelmed * prio == 0 : close to OOM, kernel scans every page in an lru * * Any value in this range is acceptable for this tunable (i.e. from 12 to * 0). Current value for the vmpressure_level_critical_prio is chosen * empirically, but the number, in essence, means that we consider * critical level when scanning depth is ~10% of the lru size (vmscan * scans 'lru_size >> prio' pages, so it is actually 12.5%, or one * eights). */ static const unsigned int vmpressure_level_critical_prio = ilog2(100 / 10); static struct vmpressure *work_to_vmpressure(struct work_struct *work) { return container_of(work, struct vmpressure, work); } static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr) { struct mem_cgroup *memcg = vmpressure_to_memcg(vmpr); memcg = parent_mem_cgroup(memcg); if (!memcg) return NULL; return memcg_to_vmpressure(memcg); } enum vmpressure_levels { VMPRESSURE_LOW = 0, VMPRESSURE_MEDIUM, VMPRESSURE_CRITICAL, VMPRESSURE_NUM_LEVELS, }; enum vmpressure_modes { VMPRESSURE_NO_PASSTHROUGH = 0, VMPRESSURE_HIERARCHY, VMPRESSURE_LOCAL, VMPRESSURE_NUM_MODES, }; static const char * const vmpressure_str_levels[] = { [VMPRESSURE_LOW] = "low", [VMPRESSURE_MEDIUM] = "medium", [VMPRESSURE_CRITICAL] = "critical", }; static const char * const vmpressure_str_modes[] = { [VMPRESSURE_NO_PASSTHROUGH] = "default", [VMPRESSURE_HIERARCHY] = "hierarchy", [VMPRESSURE_LOCAL] = "local", }; static enum vmpressure_levels vmpressure_level(unsigned long pressure) { if (pressure >= vmpressure_level_critical) return VMPRESSURE_CRITICAL; else if (pressure >= vmpressure_level_med) return VMPRESSURE_MEDIUM; return VMPRESSURE_LOW; } static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, unsigned long reclaimed) { unsigned long scale = scanned + reclaimed; unsigned long pressure = 0; /* * reclaimed can be greater than scanned for things such as reclaimed * slab pages. shrink_node() just adds reclaimed pages without a * related increment to scanned pages. */ if (reclaimed >= scanned) goto out; /* * We calculate the ratio (in percents) of how many pages were * scanned vs. reclaimed in a given time frame (window). Note that * time is in VM reclaimer's "ticks", i.e. number of pages * scanned. This makes it possible to set desired reaction time * and serves as a ratelimit. */ pressure = scale - (reclaimed * scale / scanned); pressure = pressure * 100 / scale; out: pr_debug("%s: %3lu (s: %lu r: %lu)\n", __func__, pressure, scanned, reclaimed); return vmpressure_level(pressure); } struct vmpressure_event { struct eventfd_ctx *efd; enum vmpressure_levels level; enum vmpressure_modes mode; struct list_head node; }; static bool vmpressure_event(struct vmpressure *vmpr, const enum vmpressure_levels level, bool ancestor, bool signalled) { struct vmpressure_event *ev; bool ret = false; mutex_lock(&vmpr->events_lock); list_for_each_entry(ev, &vmpr->events, node) { if (ancestor && ev->mode == VMPRESSURE_LOCAL) continue; if (signalled && ev->mode == VMPRESSURE_NO_PASSTHROUGH) continue; if (level < ev->level) continue; eventfd_signal(ev->efd); ret = true; } mutex_unlock(&vmpr->events_lock); return ret; } static void vmpressure_work_fn(struct work_struct *work) { struct vmpressure *vmpr = work_to_vmpressure(work); unsigned long scanned; unsigned long reclaimed; enum vmpressure_levels level; bool ancestor = false; bool signalled = false; spin_lock(&vmpr->sr_lock); /* * Several contexts might be calling vmpressure(), so it is * possible that the work was rescheduled again before the old * work context cleared the counters. In that case we will run * just after the old work returns, but then scanned might be zero * here. No need for any locks here since we don't care if * vmpr->reclaimed is in sync. */ scanned = vmpr->tree_scanned; if (!scanned) { spin_unlock(&vmpr->sr_lock); return; } reclaimed = vmpr->tree_reclaimed; vmpr->tree_scanned = 0; vmpr->tree_reclaimed = 0; spin_unlock(&vmpr->sr_lock); level = vmpressure_calc_level(scanned, reclaimed); do { if (vmpressure_event(vmpr, level, ancestor, signalled)) signalled = true; ancestor = true; } while ((vmpr = vmpressure_parent(vmpr))); } /** * vmpressure() - Account memory pressure through scanned/reclaimed ratio * @gfp: reclaimer's gfp mask * @order: allocation order being reclaimed for * @memcg: cgroup memory controller handle * @tree: legacy subtree mode * @scanned: number of pages scanned * @reclaimed: number of pages reclaimed * * This function should be called from the vmscan reclaim path to account * "instantaneous" memory pressure (scanned/reclaimed ratio). The raw * pressure index is then further refined and averaged over time. * * If @tree is set, vmpressure is in traditional userspace reporting * mode: @memcg is considered the pressure root and userspace is * notified of the entire subtree's reclaim efficiency. * * If @tree is not set, reclaim efficiency is recorded for @memcg, and * only in-kernel users are notified. * * This function does not return any value. */ void vmpressure(gfp_t gfp, int order, struct mem_cgroup *memcg, bool tree, unsigned long scanned, unsigned long reclaimed) { struct vmpressure *vmpr; if (mem_cgroup_disabled()) return; /* * The in-kernel users only care about the reclaim efficiency * for this @memcg rather than the whole subtree, and there * isn't and won't be any in-kernel user in a legacy cgroup. */ if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !tree) return; vmpr = memcg_to_vmpressure(memcg); /* * Here we only want to account pressure that userland is able to * help us with. For example, suppose that DMA zone is under * pressure; if we notify userland about that kind of pressure, * then it will be mostly a waste as it will trigger unnecessary * freeing of memory by userland (since userland is more likely to * have HIGHMEM/MOVABLE pages instead of the DMA fallback). That * is why we include only movable, highmem and FS/IO pages. * Indirect reclaim (kswapd) sets sc->gfp_mask to GFP_KERNEL, so * we account it too. */ if (!(gfp & (__GFP_HIGHMEM | __GFP_MOVABLE | __GFP_IO | __GFP_FS))) return; /* * If we got here with no pages scanned, then that is an indicator * that reclaimer was unable to find any shrinkable LRUs at the * current scanning depth. But it does not mean that we should * report the critical pressure, yet. If the scanning priority * (scanning depth) goes too high (deep), we will be notified * through vmpressure_prio(). But so far, keep calm. */ if (!scanned) return; if (tree) { spin_lock(&vmpr->sr_lock); scanned = vmpr->tree_scanned += scanned; vmpr->tree_reclaimed += reclaimed; spin_unlock(&vmpr->sr_lock); if (scanned < vmpressure_win) return; schedule_work(&vmpr->work); } else { enum vmpressure_levels level; /* For now, no users for root-level efficiency */ if (!memcg || mem_cgroup_is_root(memcg)) return; spin_lock(&vmpr->sr_lock); scanned = vmpr->scanned += scanned; reclaimed = vmpr->reclaimed += reclaimed; if (scanned < vmpressure_win) { spin_unlock(&vmpr->sr_lock); return; } vmpr->scanned = vmpr->reclaimed = 0; spin_unlock(&vmpr->sr_lock); level = vmpressure_calc_level(scanned, reclaimed); /* * Once we go above COSTLY_ORDER, reclaim relies heavily on * compaction to make progress. Reclaim efficiency was never a * great proxy for pressure to begin with, but it's outright * misleading with these high orders. Don't throttle sockets * because somebody is attempting something crazy like an order-7 * and predictably struggling. */ if (level > VMPRESSURE_LOW && order <= PAGE_ALLOC_COSTLY_ORDER) { /* * Let the socket buffer allocator know that * we are having trouble reclaiming LRU pages. * * For hysteresis keep the pressure state * asserted for a second in which subsequent * pressure events can occur. */ mem_cgroup_set_socket_pressure(memcg); } } } /** * vmpressure_prio() - Account memory pressure through reclaimer priority level * @gfp: reclaimer's gfp mask * @memcg: cgroup memory controller handle * @prio: reclaimer's priority * * This function should be called from the reclaim path every time when * the vmscan's reclaiming priority (scanning depth) changes. * * This function does not return any value. */ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) { /* * We only use prio for accounting critical level. For more info * see comment for vmpressure_level_critical_prio variable above. */ if (prio > vmpressure_level_critical_prio) return; /* * OK, the prio is below the threshold, updating vmpressure * information before shrinker dives into long shrinking of long * range vmscan. Passing scanned = vmpressure_win, reclaimed = 0 * to the vmpressure() basically means that we signal 'critical' * level. */ vmpressure(gfp, 0, memcg, true, vmpressure_win, 0); } #define MAX_VMPRESSURE_ARGS_LEN (strlen("critical") + strlen("hierarchy") + 2) /** * vmpressure_register_event() - Bind vmpressure notifications to an eventfd * @memcg: memcg that is interested in vmpressure notifications * @eventfd: eventfd context to link notifications with * @args: event arguments (pressure level threshold, optional mode) * * This function associates eventfd context with the vmpressure * infrastructure, so that the notifications will be delivered to the * @eventfd. The @args parameter is a comma-delimited string that denotes a * pressure level threshold (one of vmpressure_str_levels, i.e. "low", "medium", * or "critical") and an optional mode (one of vmpressure_str_modes, i.e. * "hierarchy" or "local"). * * To be used as memcg event method. * * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could * not be parsed. */ int vmpressure_register_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd, const char *args) { struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH; enum vmpressure_levels level; char *spec, *spec_orig; char *token; int ret = 0; spec_orig = spec = kstrndup(args, MAX_VMPRESSURE_ARGS_LEN, GFP_KERNEL); if (!spec) return -ENOMEM; /* Find required level */ token = strsep(&spec, ","); ret = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token); if (ret < 0) goto out; level = ret; /* Find optional mode */ token = strsep(&spec, ","); if (token) { ret = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token); if (ret < 0) goto out; mode = ret; } ev = kzalloc_obj(*ev); if (!ev) { ret = -ENOMEM; goto out; } ev->efd = eventfd; ev->level = level; ev->mode = mode; mutex_lock(&vmpr->events_lock); list_add(&ev->node, &vmpr->events); mutex_unlock(&vmpr->events_lock); ret = 0; out: kfree(spec_orig); return ret; } /** * vmpressure_unregister_event() - Unbind eventfd from vmpressure * @memcg: memcg handle * @eventfd: eventfd context that was used to link vmpressure with the @cg * * This function does internal manipulations to detach the @eventfd from * the vmpressure notifications, and then frees internal resources * associated with the @eventfd (but the @eventfd itself is not freed). * * To be used as memcg event method. */ void vmpressure_unregister_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd) { struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; mutex_lock(&vmpr->events_lock); list_for_each_entry(ev, &vmpr->events, node) { if (ev->efd != eventfd) continue; list_del(&ev->node); kfree(ev); break; } mutex_unlock(&vmpr->events_lock); } /** * vmpressure_init() - Initialize vmpressure control structure * @vmpr: Structure to be initialized * * This function should be called on every allocated vmpressure structure * before any usage. */ void vmpressure_init(struct vmpressure *vmpr) { spin_lock_init(&vmpr->sr_lock); mutex_init(&vmpr->events_lock); INIT_LIST_HEAD(&vmpr->events); INIT_WORK(&vmpr->work, vmpressure_work_fn); } /** * vmpressure_cleanup() - shuts down vmpressure control structure * @vmpr: Structure to be cleaned up * * This function should be called before the structure in which it is * embedded is cleaned up. */ void vmpressure_cleanup(struct vmpressure *vmpr) { /* * Make sure there is no pending work before eventfd infrastructure * goes away. */ flush_work(&vmpr->work); } |
| 43 43 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 | // SPDX-License-Identifier: GPL-2.0+ /* * Helpers for controlling modem lines via GPIO * * Copyright (C) 2014 Paratronic S.A. */ #include <linux/err.h> #include <linux/device.h> #include <linux/irq.h> #include <linux/gpio/consumer.h> #include <linux/termios.h> #include <linux/serial_core.h> #include <linux/module.h> #include <linux/property.h> #include "serial_mctrl_gpio.h" struct mctrl_gpios { struct uart_port *port; struct gpio_desc *gpio[UART_GPIO_MAX]; int irq[UART_GPIO_MAX]; unsigned int mctrl_prev; bool mctrl_on; }; static const struct { const char *name; unsigned int mctrl; enum gpiod_flags flags; } mctrl_gpios_desc[UART_GPIO_MAX] = { { "cts", TIOCM_CTS, GPIOD_IN, }, { "dsr", TIOCM_DSR, GPIOD_IN, }, { "dcd", TIOCM_CD, GPIOD_IN, }, { "rng", TIOCM_RNG, GPIOD_IN, }, { "rts", TIOCM_RTS, GPIOD_OUT_LOW, }, { "dtr", TIOCM_DTR, GPIOD_OUT_LOW, }, }; static bool mctrl_gpio_flags_is_dir_out(unsigned int idx) { return mctrl_gpios_desc[idx].flags & GPIOD_FLAGS_BIT_DIR_OUT; } /** * mctrl_gpio_set - set gpios according to mctrl state * @gpios: gpios to set * @mctrl: state to set * * Set the gpios according to the mctrl state. */ void mctrl_gpio_set(struct mctrl_gpios *gpios, unsigned int mctrl) { enum mctrl_gpio_idx i; struct gpio_desc *desc_array[UART_GPIO_MAX]; DECLARE_BITMAP(values, UART_GPIO_MAX); unsigned int count = 0; if (gpios == NULL) return; for (i = 0; i < UART_GPIO_MAX; i++) if (gpios->gpio[i] && mctrl_gpio_flags_is_dir_out(i)) { desc_array[count] = gpios->gpio[i]; __assign_bit(count, values, mctrl & mctrl_gpios_desc[i].mctrl); count++; } gpiod_set_array_value(count, desc_array, NULL, values); } EXPORT_SYMBOL_GPL(mctrl_gpio_set); /** * mctrl_gpio_to_gpiod - obtain gpio_desc of modem line index * @gpios: gpios to look into * @gidx: index of the modem line * Returns: the gpio_desc structure associated to the modem line index */ struct gpio_desc *mctrl_gpio_to_gpiod(struct mctrl_gpios *gpios, enum mctrl_gpio_idx gidx) { if (gpios == NULL) return NULL; return gpios->gpio[gidx]; } EXPORT_SYMBOL_GPL(mctrl_gpio_to_gpiod); /** * mctrl_gpio_get - update mctrl with the gpios values. * @gpios: gpios to get the info from * @mctrl: mctrl to set * Returns: modified mctrl (the same value as in @mctrl) * * Update mctrl with the gpios values. */ unsigned int mctrl_gpio_get(struct mctrl_gpios *gpios, unsigned int *mctrl) { enum mctrl_gpio_idx i; if (gpios == NULL) return *mctrl; for (i = 0; i < UART_GPIO_MAX; i++) { if (gpios->gpio[i] && !mctrl_gpio_flags_is_dir_out(i)) { if (gpiod_get_value(gpios->gpio[i])) *mctrl |= mctrl_gpios_desc[i].mctrl; else *mctrl &= ~mctrl_gpios_desc[i].mctrl; } } return *mctrl; } EXPORT_SYMBOL_GPL(mctrl_gpio_get); unsigned int mctrl_gpio_get_outputs(struct mctrl_gpios *gpios, unsigned int *mctrl) { enum mctrl_gpio_idx i; if (gpios == NULL) return *mctrl; for (i = 0; i < UART_GPIO_MAX; i++) { if (gpios->gpio[i] && mctrl_gpio_flags_is_dir_out(i)) { if (gpiod_get_value(gpios->gpio[i])) *mctrl |= mctrl_gpios_desc[i].mctrl; else *mctrl &= ~mctrl_gpios_desc[i].mctrl; } } return *mctrl; } EXPORT_SYMBOL_GPL(mctrl_gpio_get_outputs); struct mctrl_gpios *mctrl_gpio_init_noauto(struct device *dev, unsigned int idx) { struct mctrl_gpios *gpios; enum mctrl_gpio_idx i; gpios = devm_kzalloc(dev, sizeof(*gpios), GFP_KERNEL); if (!gpios) return ERR_PTR(-ENOMEM); for (i = 0; i < UART_GPIO_MAX; i++) { char *gpio_str; bool present; /* Check if GPIO property exists and continue if not */ gpio_str = kasprintf(GFP_KERNEL, "%s-gpios", mctrl_gpios_desc[i].name); if (!gpio_str) continue; present = device_property_present(dev, gpio_str); kfree(gpio_str); if (!present) continue; gpios->gpio[i] = devm_gpiod_get_index_optional(dev, mctrl_gpios_desc[i].name, idx, mctrl_gpios_desc[i].flags); if (IS_ERR(gpios->gpio[i])) return ERR_CAST(gpios->gpio[i]); } return gpios; } EXPORT_SYMBOL_GPL(mctrl_gpio_init_noauto); #define MCTRL_ANY_DELTA (TIOCM_RI | TIOCM_DSR | TIOCM_CD | TIOCM_CTS) static irqreturn_t mctrl_gpio_irq_handle(int irq, void *context) { struct mctrl_gpios *gpios = context; struct uart_port *port = gpios->port; u32 mctrl = gpios->mctrl_prev; u32 mctrl_diff; unsigned long flags; mctrl_gpio_get(gpios, &mctrl); uart_port_lock_irqsave(port, &flags); mctrl_diff = mctrl ^ gpios->mctrl_prev; gpios->mctrl_prev = mctrl; if (mctrl_diff & MCTRL_ANY_DELTA && port->state != NULL) { if ((mctrl_diff & mctrl) & TIOCM_RI) port->icount.rng++; if ((mctrl_diff & mctrl) & TIOCM_DSR) port->icount.dsr++; if (mctrl_diff & TIOCM_CD) uart_handle_dcd_change(port, mctrl & TIOCM_CD); if (mctrl_diff & TIOCM_CTS) uart_handle_cts_change(port, mctrl & TIOCM_CTS); wake_up_interruptible(&port->state->port.delta_msr_wait); } uart_port_unlock_irqrestore(port, flags); return IRQ_HANDLED; } /** * mctrl_gpio_init - initialize uart gpios * @port: port to initialize gpios for * @idx: index of the gpio in the @port's device * * This will get the {cts,rts,...}-gpios from device tree if they are present * and request them, set direction etc, and return an allocated structure. * `devm_*` functions are used, so there's no need to explicitly free. * As this sets up the irq handling, make sure to not handle changes to the * gpio input lines in your driver, too. */ struct mctrl_gpios *mctrl_gpio_init(struct uart_port *port, unsigned int idx) { struct mctrl_gpios *gpios; enum mctrl_gpio_idx i; gpios = mctrl_gpio_init_noauto(port->dev, idx); if (IS_ERR(gpios)) return gpios; gpios->port = port; for (i = 0; i < UART_GPIO_MAX; ++i) { int ret; if (!gpios->gpio[i] || mctrl_gpio_flags_is_dir_out(i)) continue; ret = gpiod_to_irq(gpios->gpio[i]); if (ret < 0) { dev_err(port->dev, "failed to find corresponding irq for %s (idx=%d, err=%d)\n", mctrl_gpios_desc[i].name, idx, ret); return ERR_PTR(ret); } gpios->irq[i] = ret; /* irqs should only be enabled in .enable_ms */ irq_set_status_flags(gpios->irq[i], IRQ_NOAUTOEN); ret = devm_request_irq(port->dev, gpios->irq[i], mctrl_gpio_irq_handle, IRQ_TYPE_EDGE_BOTH, dev_name(port->dev), gpios); if (ret) { /* alternatively implement polling */ dev_err(port->dev, "failed to request irq for %s (idx=%d, err=%d)\n", mctrl_gpios_desc[i].name, idx, ret); return ERR_PTR(ret); } } return gpios; } EXPORT_SYMBOL_GPL(mctrl_gpio_init); /** * mctrl_gpio_enable_ms - enable irqs and handling of changes to the ms lines * @gpios: gpios to enable */ void mctrl_gpio_enable_ms(struct mctrl_gpios *gpios) { enum mctrl_gpio_idx i; if (gpios == NULL) return; /* .enable_ms may be called multiple times */ if (gpios->mctrl_on) return; gpios->mctrl_on = true; /* get initial status of modem lines GPIOs */ mctrl_gpio_get(gpios, &gpios->mctrl_prev); for (i = 0; i < UART_GPIO_MAX; ++i) { if (!gpios->irq[i]) continue; enable_irq(gpios->irq[i]); } } EXPORT_SYMBOL_GPL(mctrl_gpio_enable_ms); static void mctrl_gpio_disable_ms(struct mctrl_gpios *gpios, bool sync) { enum mctrl_gpio_idx i; if (gpios == NULL) return; if (!gpios->mctrl_on) return; gpios->mctrl_on = false; for (i = 0; i < UART_GPIO_MAX; ++i) { if (!gpios->irq[i]) continue; if (sync) disable_irq(gpios->irq[i]); else disable_irq_nosync(gpios->irq[i]); } } /** * mctrl_gpio_disable_ms_sync - disable irqs and handling of changes to the ms * lines, and wait for any pending IRQ to be processed * @gpios: gpios to disable */ void mctrl_gpio_disable_ms_sync(struct mctrl_gpios *gpios) { mctrl_gpio_disable_ms(gpios, true); } EXPORT_SYMBOL_GPL(mctrl_gpio_disable_ms_sync); /** * mctrl_gpio_disable_ms_no_sync - disable irqs and handling of changes to the * ms lines, and return immediately * @gpios: gpios to disable */ void mctrl_gpio_disable_ms_no_sync(struct mctrl_gpios *gpios) { mctrl_gpio_disable_ms(gpios, false); } EXPORT_SYMBOL_GPL(mctrl_gpio_disable_ms_no_sync); void mctrl_gpio_enable_irq_wake(struct mctrl_gpios *gpios) { enum mctrl_gpio_idx i; if (!gpios) return; if (!gpios->mctrl_on) return; for (i = 0; i < UART_GPIO_MAX; ++i) { if (!gpios->irq[i]) continue; enable_irq_wake(gpios->irq[i]); } } EXPORT_SYMBOL_GPL(mctrl_gpio_enable_irq_wake); void mctrl_gpio_disable_irq_wake(struct mctrl_gpios *gpios) { enum mctrl_gpio_idx i; if (!gpios) return; if (!gpios->mctrl_on) return; for (i = 0; i < UART_GPIO_MAX; ++i) { if (!gpios->irq[i]) continue; disable_irq_wake(gpios->irq[i]); } } EXPORT_SYMBOL_GPL(mctrl_gpio_disable_irq_wake); MODULE_DESCRIPTION("Helpers for controlling modem lines via GPIO"); MODULE_LICENSE("GPL"); |
| 45 44 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Do sleep inside a spin-lock * Copyright (c) 1999 by Takashi Iwai <tiwai@suse.de> */ #include <linux/export.h> #include <sound/core.h> #include "seq_lock.h" /* wait until all locks are released */ void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line) { int warn_count = 5 * HZ; if (atomic_read(lockp) < 0) { pr_warn("ALSA: seq_lock: lock trouble [counter = %d] in %s:%d\n", atomic_read(lockp), file, line); return; } while (atomic_read(lockp) > 0) { if (warn_count-- == 0) pr_warn("ALSA: seq_lock: waiting [%d left] in %s:%d\n", atomic_read(lockp), file, line); schedule_timeout_uninterruptible(1); } } EXPORT_SYMBOL(snd_use_lock_sync_helper); |
| 1829 1831 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 | // SPDX-License-Identifier: GPL-2.0 /* * Device physical location support * * Author: Won Chung <wonchung@google.com> */ #include <linux/acpi.h> #include <linux/sysfs.h> #include <linux/string_choices.h> #include "physical_location.h" bool dev_add_physical_location(struct device *dev) { struct acpi_pld_info *pld; if (!has_acpi_companion(dev)) return false; if (!acpi_get_physical_device_location(ACPI_HANDLE(dev), &pld)) return false; dev->physical_location = kzalloc_obj(*dev->physical_location); if (!dev->physical_location) { ACPI_FREE(pld); return false; } dev->physical_location->panel = pld->panel; dev->physical_location->vertical_position = pld->vertical_position; dev->physical_location->horizontal_position = pld->horizontal_position; dev->physical_location->dock = pld->dock; dev->physical_location->lid = pld->lid; ACPI_FREE(pld); return true; } static ssize_t panel_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *panel; switch (dev->physical_location->panel) { case DEVICE_PANEL_TOP: panel = "top"; break; case DEVICE_PANEL_BOTTOM: panel = "bottom"; break; case DEVICE_PANEL_LEFT: panel = "left"; break; case DEVICE_PANEL_RIGHT: panel = "right"; break; case DEVICE_PANEL_FRONT: panel = "front"; break; case DEVICE_PANEL_BACK: panel = "back"; break; default: panel = "unknown"; } return sysfs_emit(buf, "%s\n", panel); } static DEVICE_ATTR_RO(panel); static ssize_t vertical_position_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *vertical_position; switch (dev->physical_location->vertical_position) { case DEVICE_VERT_POS_UPPER: vertical_position = "upper"; break; case DEVICE_VERT_POS_CENTER: vertical_position = "center"; break; case DEVICE_VERT_POS_LOWER: vertical_position = "lower"; break; default: vertical_position = "unknown"; } return sysfs_emit(buf, "%s\n", vertical_position); } static DEVICE_ATTR_RO(vertical_position); static ssize_t horizontal_position_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *horizontal_position; switch (dev->physical_location->horizontal_position) { case DEVICE_HORI_POS_LEFT: horizontal_position = "left"; break; case DEVICE_HORI_POS_CENTER: horizontal_position = "center"; break; case DEVICE_HORI_POS_RIGHT: horizontal_position = "right"; break; default: horizontal_position = "unknown"; } return sysfs_emit(buf, "%s\n", horizontal_position); } static DEVICE_ATTR_RO(horizontal_position); static ssize_t dock_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", str_yes_no(dev->physical_location->dock)); } static DEVICE_ATTR_RO(dock); static ssize_t lid_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", str_yes_no(dev->physical_location->lid)); } static DEVICE_ATTR_RO(lid); static struct attribute *dev_attr_physical_location[] = { &dev_attr_panel.attr, &dev_attr_vertical_position.attr, &dev_attr_horizontal_position.attr, &dev_attr_dock.attr, &dev_attr_lid.attr, NULL, }; const struct attribute_group dev_attr_physical_location_group = { .name = "physical_location", .attrs = dev_attr_physical_location, }; |
| 50 | 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 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_IOPRIO_H #define _UAPI_LINUX_IOPRIO_H #include <linux/stddef.h> #include <linux/types.h> /* * Gives us 8 prio classes with 13-bits of data for each class */ #define IOPRIO_CLASS_SHIFT 13 #define IOPRIO_NR_CLASSES 8 #define IOPRIO_CLASS_MASK (IOPRIO_NR_CLASSES - 1) #define IOPRIO_PRIO_MASK ((1UL << IOPRIO_CLASS_SHIFT) - 1) #define IOPRIO_PRIO_CLASS(ioprio) \ (((ioprio) >> IOPRIO_CLASS_SHIFT) & IOPRIO_CLASS_MASK) #define IOPRIO_PRIO_DATA(ioprio) ((ioprio) & IOPRIO_PRIO_MASK) /* * These are the io priority classes as implemented by the BFQ and mq-deadline * schedulers. RT is the realtime class, it always gets premium service. For * ATA disks supporting NCQ IO priority, RT class IOs will be processed using * high priority NCQ commands. BE is the best-effort scheduling class, the * default for any process. IDLE is the idle scheduling class, it is only * served when no one else is using the disk. */ enum { IOPRIO_CLASS_NONE = 0, IOPRIO_CLASS_RT = 1, IOPRIO_CLASS_BE = 2, IOPRIO_CLASS_IDLE = 3, /* Special class to indicate an invalid ioprio value */ IOPRIO_CLASS_INVALID = 7, }; /* * The RT and BE priority classes both support up to 8 priority levels that * can be specified using the lower 3-bits of the priority data. */ #define IOPRIO_LEVEL_NR_BITS 3 #define IOPRIO_NR_LEVELS (1 << IOPRIO_LEVEL_NR_BITS) #define IOPRIO_LEVEL_MASK (IOPRIO_NR_LEVELS - 1) #define IOPRIO_PRIO_LEVEL(ioprio) ((ioprio) & IOPRIO_LEVEL_MASK) #define IOPRIO_BE_NR IOPRIO_NR_LEVELS /* * Possible values for the "which" argument of the ioprio_get() and * ioprio_set() system calls (see "man ioprio_set"). */ enum { IOPRIO_WHO_PROCESS = 1, IOPRIO_WHO_PGRP, IOPRIO_WHO_USER, }; /* * Fallback BE class priority level. */ #define IOPRIO_NORM 4 #define IOPRIO_BE_NORM IOPRIO_NORM /* * The 10 bits between the priority class and the priority level are used to * optionally define I/O hints for any combination of I/O priority class and * level. Depending on the kernel configuration, I/O scheduler being used and * the target I/O device being used, hints can influence how I/Os are processed * without affecting the I/O scheduling ordering defined by the I/O priority * class and level. */ #define IOPRIO_HINT_SHIFT IOPRIO_LEVEL_NR_BITS #define IOPRIO_HINT_NR_BITS 10 #define IOPRIO_NR_HINTS (1 << IOPRIO_HINT_NR_BITS) #define IOPRIO_HINT_MASK (IOPRIO_NR_HINTS - 1) #define IOPRIO_PRIO_HINT(ioprio) \ (((ioprio) >> IOPRIO_HINT_SHIFT) & IOPRIO_HINT_MASK) /* * I/O hints. */ enum { /* No hint */ IOPRIO_HINT_NONE = 0, /* * Device command duration limits: indicate to the device a desired * duration limit for the commands that will be used to process an I/O. * These will currently only be effective for SCSI and ATA devices that * support the command duration limits feature. If this feature is * enabled, then the commands issued to the device to process an I/O with * one of these hints set will have the duration limit index (dld field) * set to the value of the hint. */ IOPRIO_HINT_DEV_DURATION_LIMIT_1 = 1, IOPRIO_HINT_DEV_DURATION_LIMIT_2 = 2, IOPRIO_HINT_DEV_DURATION_LIMIT_3 = 3, IOPRIO_HINT_DEV_DURATION_LIMIT_4 = 4, IOPRIO_HINT_DEV_DURATION_LIMIT_5 = 5, IOPRIO_HINT_DEV_DURATION_LIMIT_6 = 6, IOPRIO_HINT_DEV_DURATION_LIMIT_7 = 7, }; #define IOPRIO_BAD_VALUE(val, max) ((val) < 0 || (val) >= (max)) /* * Return an I/O priority value based on a class, a level and a hint. */ static __always_inline __u16 ioprio_value(int prioclass, int priolevel, int priohint) { if (IOPRIO_BAD_VALUE(prioclass, IOPRIO_NR_CLASSES) || IOPRIO_BAD_VALUE(priolevel, IOPRIO_NR_LEVELS) || IOPRIO_BAD_VALUE(priohint, IOPRIO_NR_HINTS)) return IOPRIO_CLASS_INVALID << IOPRIO_CLASS_SHIFT; return (prioclass << IOPRIO_CLASS_SHIFT) | (priohint << IOPRIO_HINT_SHIFT) | priolevel; } #define IOPRIO_PRIO_VALUE(prioclass, priolevel) \ ioprio_value(prioclass, priolevel, IOPRIO_HINT_NONE) #define IOPRIO_PRIO_VALUE_HINT(prioclass, priolevel, priohint) \ ioprio_value(prioclass, priolevel, priohint) #endif /* _UAPI_LINUX_IOPRIO_H */ |
| 39 3 39 38 3 27 30 31 38194 6 38191 38328 35 730 24 726 729 1 1 44 27 42 2 30 36 36 22 32 36 36 20 33 39 39 39 39 1224 1223 1220 1228 1 1226 37668 37668 37686 37828 175 37663 6309 6319 6316 6317 6333 16 124 125 125 125 112 323 326 318 329 7 326 492 494 3342 3 3 3 3 9 5 5 5 30 2 28 27 10 1 1 1 1 16 4 9 12 13 20 20 20 1 20 1 1 1 3 3 19 19 19 3 20 20 20 3 58 7986 7982 6 7973 9157 9163 56 8534 6326 6 6 6 6 39 39 38 8 230 231 231 208 32 229 229 1 7 4 30 3 12 1 1 14 19 16 23 50 10 3 27 10 30 17 20 48 50 9 27 35 10 28 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 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 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel timekeeping code and accessor functions. Based on code from * timer.c, moved in commit 8524070b7982. */ #include <linux/audit.h> #include <linux/clocksource.h> #include <linux/compiler.h> #include <linux/jiffies.h> #include <linux/kobject.h> #include <linux/module.h> #include <linux/nmi.h> #include <linux/pvclock_gtod.h> #include <linux/random.h> #include <linux/sched/clock.h> #include <linux/sched/loadavg.h> #include <linux/static_key.h> #include <linux/stop_machine.h> #include <linux/syscore_ops.h> #include <linux/tick.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/timekeeper_internal.h> #include <vdso/auxclock.h> #include "tick-internal.h" #include "timekeeping_internal.h" #include "ntp_internal.h" #define TK_CLEAR_NTP (1 << 0) #define TK_CLOCK_WAS_SET (1 << 1) #define TK_UPDATE_ALL (TK_CLEAR_NTP | TK_CLOCK_WAS_SET) enum timekeeping_adv_mode { /* Update timekeeper when a tick has passed */ TK_ADV_TICK, /* Update timekeeper on a direct frequency change */ TK_ADV_FREQ }; /* * The most important data for readout fits into a single 64 byte * cache line. */ struct tk_data { seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; struct timekeeper shadow_timekeeper; raw_spinlock_t lock; } ____cacheline_aligned; static struct tk_data timekeeper_data[TIMEKEEPERS_MAX]; /* The core timekeeper */ #define tk_core (timekeeper_data[TIMEKEEPER_CORE]) #ifdef CONFIG_POSIX_AUX_CLOCKS static inline bool tk_get_aux_ts64(unsigned int tkid, struct timespec64 *ts) { return ktime_get_aux_ts64(CLOCK_AUX + tkid - TIMEKEEPER_AUX_FIRST, ts); } static inline bool tk_is_aux(const struct timekeeper *tk) { return tk->id >= TIMEKEEPER_AUX_FIRST && tk->id <= TIMEKEEPER_AUX_LAST; } static inline struct tk_data *aux_get_tk_data(clockid_t id); #else static inline bool tk_get_aux_ts64(unsigned int tkid, struct timespec64 *ts) { return false; } static inline bool tk_is_aux(const struct timekeeper *tk) { return false; } static inline struct tk_data *aux_get_tk_data(clockid_t id) { return NULL; } #endif static inline void tk_update_aux_offs(struct timekeeper *tk, ktime_t offs) { tk->offs_aux = offs; tk->monotonic_to_aux = ktime_to_timespec64(offs); } /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; /** * struct tk_fast - NMI safe timekeeper * @seq: Sequence counter for protecting updates. The lowest bit * is the index for the tk_read_base array * @base: tk_read_base array. Access is indexed by the lowest bit of * @seq. * * See @update_fast_timekeeper() below. */ struct tk_fast { seqcount_latch_t seq; struct tk_read_base base[2]; }; /* Suspend-time cycles value for halted fast timekeeper. */ static u64 cycles_at_suspend; static u64 dummy_clock_read(struct clocksource *cs) { if (timekeeping_suspended) return cycles_at_suspend; return local_clock(); } static struct clocksource dummy_clock = { .read = dummy_clock_read, }; /* * Boot time initialization which allows local_clock() to be utilized * during early boot when clocksources are not available. local_clock() * returns nanoseconds already so no conversion is required, hence mult=1 * and shift=0. When the first proper clocksource is installed then * the fast time keepers are updated with the correct values. */ #define FAST_TK_INIT \ { \ .clock = &dummy_clock, \ .mask = CLOCKSOURCE_MASK(64), \ .mult = 1, \ .shift = 0, \ } static struct tk_fast tk_fast_mono ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static struct tk_fast tk_fast_raw ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; #ifdef CONFIG_POSIX_AUX_CLOCKS static __init void tk_aux_setup(void); static void tk_aux_update_clocksource(void); static void tk_aux_advance(void); #else static inline void tk_aux_setup(void) { } static inline void tk_aux_update_clocksource(void) { } static inline void tk_aux_advance(void) { } #endif unsigned long timekeeper_lock_irqsave(void) { unsigned long flags; raw_spin_lock_irqsave(&tk_core.lock, flags); return flags; } void timekeeper_unlock_irqrestore(unsigned long flags) { raw_spin_unlock_irqrestore(&tk_core.lock, flags); } /* * Multigrain timestamps require tracking the latest fine-grained timestamp * that has been issued, and never returning a coarse-grained timestamp that is * earlier than that value. * * mg_floor represents the latest fine-grained time that has been handed out as * a file timestamp on the system. This is tracked as a monotonic ktime_t, and * converted to a realtime clock value on an as-needed basis. * * Maintaining mg_floor ensures the multigrain interfaces never issue a * timestamp earlier than one that has been previously issued. * * The exception to this rule is when there is a backward realtime clock jump. If * such an event occurs, a timestamp can appear to be earlier than a previous one. */ static __cacheline_aligned_in_smp atomic64_t mg_floor; static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) { tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift; tk->raw_sec++; } } static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static inline struct timespec64 tk_xtime_coarse(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = tk->coarse_nsec; return ts; } /* * Update the nanoseconds part for the coarse time keepers. They can't rely * on xtime_nsec because xtime_nsec could be adjusted by a small negative * amount when the multiplication factor of the clock is adjusted, which * could cause the coarse clocks to go slightly backwards. See * timekeeping_apply_adjustment(). Thus we keep a separate copy for the coarse * clockids which only is updated when the clock has been set or we have * accumulated time. */ static inline void tk_update_coarse_nsecs(struct timekeeper *tk) { tk->coarse_nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_update_coarse_nsecs(tk); } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); tk_update_coarse_nsecs(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp)); tk->wall_to_monotonic = wtm; set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); /* Paired with READ_ONCE() in ktime_mono_to_any() */ WRITE_ONCE(tk->offs_real, timespec64_to_ktime(tmp)); WRITE_ONCE(tk->offs_tai, ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0))); } static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { /* Paired with READ_ONCE() in ktime_mono_to_any() */ WRITE_ONCE(tk->offs_boot, ktime_add(tk->offs_boot, delta)); /* * Timespec representation for VDSO update to avoid 64bit division * on every update. */ tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot); } #ifdef CONFIG_ARCH_WANTS_CLOCKSOURCE_READ_INLINE #include <asm/clock_inlined.h> static DEFINE_STATIC_KEY_FALSE(clocksource_read_inlined); /* * tk_clock_read - atomic clocksource read() helper * * This helper is necessary to use in the read paths because, while the * seqcount ensures we don't return a bad value while structures are updated, * it doesn't protect from potential crashes. There is the possibility that * the tkr's clocksource may change between the read reference, and the * clock reference passed to the read function. This can cause crashes if * the wrong clocksource is passed to the wrong read function. * This isn't necessary to use when holding the tk_core.lock or doing * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ static __always_inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); if (static_branch_likely(&clocksource_read_inlined)) return arch_inlined_clocksource_read(clock); return clock->read(clock); } static inline void clocksource_disable_inline_read(void) { static_branch_disable(&clocksource_read_inlined); } static inline void clocksource_enable_inline_read(void) { static_branch_enable(&clocksource_read_inlined); } #else static __always_inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); return clock->read(clock); } static inline void clocksource_disable_inline_read(void) { } static inline void clocksource_enable_inline_read(void) { } #endif /** * tk_setup_internals - Set up internals to use clocksource clock. * * @tk: The target timekeeper to setup. * @clock: Pointer to clocksource. * * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment * pair and interval request. * * Unless you're the timekeeping code, you should not be using this! */ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) { u64 interval; u64 tmp, ntpinterval; struct clocksource *old_clock; ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.mask = clock->mask; tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; ntpinterval = tmp; tmp += clock->mult/2; do_div(tmp, clock->mult); if (tmp == 0) tmp = 1; interval = (u64) tmp; tk->cycle_interval = interval; /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) { tk->tkr_mono.xtime_nsec >>= -shift_change; tk->tkr_raw.xtime_nsec >>= -shift_change; } else { tk->tkr_mono.xtime_nsec <<= shift_change; tk->tkr_raw.xtime_nsec <<= shift_change; } } tk->tkr_mono.shift = clock->shift; tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ tk->tkr_mono.mult = clock->mult; tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; tk->skip_second_overflow = 0; tk->cs_id = clock->id; /* Coupled clockevent data */ if (IS_ENABLED(CONFIG_GENERIC_CLOCKEVENTS_COUPLED) && clock->flags & CLOCK_SOURCE_HAS_COUPLED_CLOCK_EVENT) { /* * Aim for an one hour maximum delta and use KHz to handle * clocksources with a frequency above 4GHz correctly as * the frequency argument of clocks_calc_mult_shift() is u32. */ clocks_calc_mult_shift(&tk->cs_ns_to_cyc_mult, &tk->cs_ns_to_cyc_shift, NSEC_PER_MSEC, clock->freq_khz, 3600 * 1000); /* * Initialize the conversion limit as the previous clocksource * might have the same shift/mult pair so the quick check in * tk_update_ns_to_cyc() fails to update it after a clocksource * change leaving it effectivly zero. */ tk->cs_ns_to_cyc_maxns = div_u64(clock->mask, tk->cs_ns_to_cyc_mult); } } /* Timekeeper helper functions. */ static noinline u64 delta_to_ns_safe(const struct tk_read_base *tkr, u64 delta) { return mul_u64_u32_add_u64_shr(delta, tkr->mult, tkr->xtime_nsec, tkr->shift); } static __always_inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { /* Calculate the delta since the last update_wall_time() */ u64 mask = tkr->mask, delta = (cycles - tkr->cycle_last) & mask; /* * This detects both negative motion and the case where the delta * overflows the multiplication with tkr->mult. */ if (unlikely(delta > tkr->clock->max_cycles)) { /* * Handle clocksource inconsistency between CPUs to prevent * time from going backwards by checking for the MSB of the * mask being set in the delta. */ if (delta & ~(mask >> 1)) return tkr->xtime_nsec >> tkr->shift; return delta_to_ns_safe(tkr, delta); } return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift; } static __always_inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr)); } /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update * @tkf: Pointer to NMI safe timekeeper * * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. * * Employ the latch technique; see @write_seqcount_latch. * * So if a NMI hits the update of base[0] then it will use base[1] * which is still consistent. In the worst case this can result is a * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ static void update_fast_timekeeper(const struct tk_read_base *tkr, struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ write_seqcount_latch_begin(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); write_seqcount_latch_end(&tkf->seq); } static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { seq = read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); now += timekeeping_get_ns(tkr); } while (read_seqcount_latch_retry(&tkf->seq, seq)); return now; } /** * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic * * This timestamp is not guaranteed to be monotonic across an update. * The timestamp is calculated by: * * now = base_mono + clock_delta * slope * * So if the update lowers the slope, readers who are forced to the * not yet updated second array are still using the old steeper slope. * * tmono * ^ * | o n * | o n * | u * | o * |o * |12345678---> reader order * * o = old slope * u = update * n = new slope * * So reader 6 will observe time going backwards versus reader 5. * * While other CPUs are likely to be able to observe that, the only way * for a CPU local observation is when an NMI hits in the middle of * the update. Timestamps taken from that NMI context might be ahead * of the following timestamps. Callers need to be aware of that and * deal with it. */ u64 notrace ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); /** * ktime_get_raw_fast_ns - Fast NMI safe access to clock monotonic raw * * Contrary to ktime_get_mono_fast_ns() this is always correct because the * conversion factor is not affected by NTP/PTP correction. */ u64 notrace ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); /** * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. * * To keep it NMI safe since we're accessing from tracing, we're not using a * separate timekeeper with updates to monotonic clock and boot offset * protected with seqcounts. This has the following minor side effects: * * (1) Its possible that a timestamp be taken after the boot offset is updated * but before the timekeeper is updated. If this happens, the new boot offset * is added to the old timekeeping making the clock appear to update slightly * earlier: * CPU 0 CPU 1 * timekeeping_inject_sleeptime64() * __timekeeping_inject_sleeptime(tk, delta); * timestamp(); * timekeeping_update_staged(tkd, TK_CLEAR_NTP...); * * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be * partially updated. Since the tk->offs_boot update is a rare event, this * should be a rare occurrence which postprocessing should be able to handle. * * The caveats vs. timestamp ordering as documented for ktime_get_mono_fast_ns() * apply as well. */ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_boot))); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); /** * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock. * * The same limitations as described for ktime_get_boot_fast_ns() apply. The * mono time and the TAI offset are not read atomically which may yield wrong * readouts. However, an update of the TAI offset is an rare event e.g., caused * by settime or adjtimex with an offset. The user of this function has to deal * with the possibility of wrong timestamps in post processing. */ u64 notrace ktime_get_tai_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai))); } EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns); /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. * * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering. */ u64 ktime_get_real_fast_ns(void) { struct tk_fast *tkf = &tk_fast_mono; struct tk_read_base *tkr; u64 baser, delta; unsigned int seq; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); baser = ktime_to_ns(tkr->base_real); delta = timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); return baser + delta; } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. * * It generally is unsafe to access the clocksource after timekeeping has been * suspended, so take a snapshot of the readout base of @tk and use it as the * fast timekeeper's readout base while suspended. It will return the same * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); tkr_dummy.clock = &dummy_clock; tkr_dummy.base_real = tkr->base + tk->offs_real; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** * pvclock_gtod_register_notifier - register a pvclock timedata update listener * @nb: Pointer to the notifier block to register */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { struct timekeeper *tk = &tk_core.timekeeper; int ret; guard(raw_spinlock_irqsave)(&tk_core.lock); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); update_pvclock_gtod(tk, true); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); /** * pvclock_gtod_unregister_notifier - unregister a pvclock * timedata update listener * @nb: Pointer to the notifier block to unregister */ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) { guard(raw_spinlock_irqsave)(&tk_core.lock); return raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* * tk_update_leap_state - helper to update the next_leap_ktime */ static inline void tk_update_leap_state(struct timekeeper *tk) { tk->next_leap_ktime = ntp_get_next_leap(tk->id); if (tk->next_leap_ktime != KTIME_MAX) /* Convert to monotonic time */ tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real); } /* * Leap state update for both shadow and the real timekeeper * Separate to spare a full memcpy() of the timekeeper. */ static void tk_update_leap_state_all(struct tk_data *tkd) { write_seqcount_begin(&tkd->seq); tk_update_leap_state(&tkd->shadow_timekeeper); tkd->timekeeper.next_leap_ktime = tkd->shadow_timekeeper.next_leap_ktime; write_seqcount_end(&tkd->seq); } /* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) { u64 seconds; u32 nsec; /* * The xtime based monotonic readout is: * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); * The ktime based monotonic readout is: * nsec = base_mono + now(); * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; /* Update the monotonic raw base */ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } static inline void tk_update_ns_to_cyc(struct timekeeper *tks, struct timekeeper *tkc) { struct tk_read_base *tkrs = &tks->tkr_mono; struct tk_read_base *tkrc = &tkc->tkr_mono; unsigned int shift; if (!IS_ENABLED(CONFIG_GENERIC_CLOCKEVENTS_COUPLED) || !(tkrs->clock->flags & CLOCK_SOURCE_HAS_COUPLED_CLOCK_EVENT)) return; if (tkrs->mult == tkrc->mult && tkrs->shift == tkrc->shift) return; /* * The conversion math is simple: * * CS::MULT (1 << NS_TO_CYC_SHIFT) * --------------- = ---------------------- * (1 << CS:SHIFT) NS_TO_CYC_MULT * * Ergo: * * NS_TO_CYC_MULT = (1 << (CS::SHIFT + NS_TO_CYC_SHIFT)) / CS::MULT * * NS_TO_CYC_SHIFT has been set up in tk_setup_internals() */ shift = tkrs->shift + tks->cs_ns_to_cyc_shift; tks->cs_ns_to_cyc_mult = (u32)div_u64(1ULL << shift, tkrs->mult); tks->cs_ns_to_cyc_maxns = div_u64(tkrs->clock->mask, tks->cs_ns_to_cyc_mult); } /* * Restore the shadow timekeeper from the real timekeeper. */ static void timekeeping_restore_shadow(struct tk_data *tkd) { lockdep_assert_held(&tkd->lock); memcpy(&tkd->shadow_timekeeper, &tkd->timekeeper, sizeof(tkd->timekeeper)); } static void timekeeping_update_from_shadow(struct tk_data *tkd, unsigned int action) { struct timekeeper *tk = &tkd->shadow_timekeeper; lockdep_assert_held(&tkd->lock); /* * Block out readers before running the updates below because that * updates VDSO and other time related infrastructure. Not blocking * the readers might let a reader see time going backwards when * reading from the VDSO after the VDSO update and then reading in * the kernel from the timekeeper before that got updated. */ write_seqcount_begin(&tkd->seq); if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(tk->id); } tk_update_leap_state(tk); tk_update_ktime_data(tk); tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real; if (tk->id == TIMEKEEPER_CORE) { tk_update_ns_to_cyc(tk, &tkd->timekeeper); update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); } else if (tk_is_aux(tk)) { vdso_time_update_aux(tk); } if (action & TK_CLOCK_WAS_SET) tk->clock_was_set_seq++; /* * Update the real timekeeper. * * We could avoid this memcpy() by switching pointers, but that has * the downside that the reader side does not longer benefit from * the cacheline optimized data layout of the timekeeper and requires * another indirection. */ memcpy(&tkd->timekeeper, tk, sizeof(*tk)); write_seqcount_end(&tkd->seq); } /** * timekeeping_forward_now - update clock to the current time * @tk: Pointer to the timekeeper to update * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ static void timekeeping_forward_now(struct timekeeper *tk) { u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; while (delta > 0) { u64 max = tk->tkr_mono.clock->max_cycles; u64 incr = delta < max ? delta : max; tk->tkr_mono.xtime_nsec += incr * tk->tkr_mono.mult; tk->tkr_raw.xtime_nsec += incr * tk->tkr_raw.mult; tk_normalize_xtime(tk); delta -= incr; } tk_update_coarse_nsecs(tk); } /* * ktime_expiry_to_cycles - Convert a expiry time to clocksource cycles * @id: Clocksource ID which is required for validity * @expires_ns: Absolute CLOCK_MONOTONIC expiry time (nsecs) to be converted * @cycles: Pointer to storage for corresponding absolute cycles value * * Convert a CLOCK_MONOTONIC based absolute expiry time to a cycles value * based on the correlated clocksource of the clockevent device by using * the base nanoseconds and cycles values of the last timekeeper update and * converting the delta between @expires_ns and base nanoseconds to cycles. * * This only works for clockevent devices which are using a less than or * equal comparator against the clocksource. * * Utilizing this avoids two clocksource reads for such devices, the * ktime_get() in clockevents_program_event() to calculate the delta expiry * value and the readout in the device::set_next_event() callback to * convert the delta back to a absolute comparator value. * * Returns: True if @id matches the current clocksource ID, false otherwise */ bool ktime_expiry_to_cycles(enum clocksource_ids id, ktime_t expires_ns, u64 *cycles) { struct timekeeper *tk = &tk_core.timekeeper; struct tk_read_base *tkrm = &tk->tkr_mono; ktime_t base_ns, delta_ns, max_ns; u64 base_cycles, delta_cycles; unsigned int seq; u32 mult, shift; /* * Racy check to avoid the seqcount overhead when ID does not match. If * the relevant clocksource is installed concurrently, then this will * just delay the switch over to this mechanism until the next event is * programmed. If the ID is not matching the clock events code will use * the regular relative set_next_event() callback as before. */ if (data_race(tk->cs_id) != id) return false; do { seq = read_seqcount_begin(&tk_core.seq); if (tk->cs_id != id) return false; base_cycles = tkrm->cycle_last; base_ns = tkrm->base + (tkrm->xtime_nsec >> tkrm->shift); mult = tk->cs_ns_to_cyc_mult; shift = tk->cs_ns_to_cyc_shift; max_ns = tk->cs_ns_to_cyc_maxns; } while (read_seqcount_retry(&tk_core.seq, seq)); /* Prevent negative deltas and multiplication overflows */ delta_ns = min(expires_ns - base_ns, max_ns); delta_ns = max(delta_ns, 0); /* Convert to cycles */ delta_cycles = ((u64)delta_ns * mult) >> shift; *cycles = base_cycles + delta_cycles; return true; } /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec64 (WARN if suspended). */ void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_real_ts64); ktime_t ktime_get(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); u32 ktime_get_resolution_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u32 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return nsecs; } EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static const ktime_t *const offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; ktime_t ktime_get_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; const ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; const ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = tk->coarse_nsec; } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); /** * ktime_mono_to_any() - convert monotonic time to any other time * @tmono: time to convert. * @offs: which offset to use */ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { const ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t tconv; if (IS_ENABLED(CONFIG_64BIT)) { /* * Paired with WRITE_ONCE()s in tk_set_wall_to_mono() and * tk_update_sleep_time(). */ return ktime_add(tmono, READ_ONCE(*offset)); } do { seq = read_seqcount_begin(&tk_core.seq); tconv = ktime_add(tmono, *offset); } while (read_seqcount_retry(&tk_core.seq, seq)); return tconv; } EXPORT_SYMBOL_GPL(ktime_mono_to_any); /** * ktime_get_raw - Returns the raw monotonic time in ktime_t format */ ktime_t ktime_get_raw(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_raw.base; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_raw); /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable * * The function calculates the monotonic clock from the realtime * clock and the wall_to_monotonic offset and stores the result * in normalized timespec64 format in the variable pointed to by @ts. */ void ktime_get_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono; unsigned int seq; u64 nsec; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_sec += tomono.tv_sec; ts->tv_nsec = 0; timespec64_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts64); /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * * Returns the seconds portion of CLOCK_MONOTONIC with a single non * serialized read. tk->ktime_sec is of type 'unsigned long' so this * works on both 32 and 64 bit systems. On 32 bit systems the readout * covers ~136 years of uptime which should be enough to prevent * premature wrap arounds. */ time64_t ktime_get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; WARN_ON(timekeeping_suspended); return tk->ktime_sec; } EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * * Returns the wall clock seconds since 1970. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence * counter to provide "atomic" access to the 64bit tk->xtime_sec * value. */ time64_t ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; time64_t seconds; unsigned int seq; if (IS_ENABLED(CONFIG_64BIT)) return tk->xtime_sec; do { seq = read_seqcount_begin(&tk_core.seq); seconds = tk->xtime_sec; } while (read_seqcount_retry(&tk_core.seq, seq)); return seconds; } EXPORT_SYMBOL_GPL(ktime_get_real_seconds); /** * __ktime_get_real_seconds - Unprotected access to CLOCK_REALTIME seconds * * The same as ktime_get_real_seconds() but without the sequence counter * protection. This function is used in restricted contexts like the x86 MCE * handler and in KGDB. It's unprotected on 32-bit vs. concurrent half * completed modification and only to be used for such critical contexts. * * Returns: Racy snapshot of the CLOCK_REALTIME seconds value */ noinstr time64_t __ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } static inline u64 tk_clock_read_snapshot(const struct tk_read_base *tkr, struct clocksource_hw_snapshot *chs) { struct clocksource *clock = READ_ONCE(tkr->clock); if (unlikely(clock->read_snapshot)) return clock->read_snapshot(clock, chs); return clock->read(clock); } /** * ktime_get_snapshot_id - Simultaneously snapshot a given clock ID with * CLOCK_MONOTONIC_RAW and the underlying * clocksource counter value. * @clock_id: The clock ID to snapshot * @systime_snapshot: Pointer to struct receiving the system time snapshot */ void ktime_get_snapshot_id(clockid_t clock_id, struct system_time_snapshot *systime_snapshot) { ktime_t base_raw, base_sys, offs_sys, *offs, offs_zero = 0; u64 nsec_raw, nsec_sys, now; struct timekeeper *tk; struct tk_data *tkd; unsigned int seq; /* Invalidate the snapshot for all failure cases */ systime_snapshot->valid = false; if (WARN_ON_ONCE(timekeeping_suspended)) return; switch (clock_id) { case CLOCK_REALTIME: tkd = &tk_core; offs = &tk_core.timekeeper.offs_real; break; /* Map RAW to MONOTONIC so the loop below is trivial */ case CLOCK_MONOTONIC_RAW: case CLOCK_MONOTONIC: tkd = &tk_core; offs = &offs_zero; break; case CLOCK_BOOTTIME: tkd = &tk_core; offs = &tk_core.timekeeper.offs_boot; break; case CLOCK_AUX ... CLOCK_AUX_LAST: tkd = aux_get_tk_data(clock_id); if (!tkd) return; offs = &tkd->timekeeper.offs_aux; break; default: WARN_ON_ONCE(1); return; } tk = &tkd->timekeeper; do { struct clocksource_hw_snapshot chs = { }; seq = read_seqcount_begin(&tkd->seq); /* Aux clocks can be invalid */ if (!tk->clock_valid) return; now = tk_clock_read_snapshot(&tk->tkr_mono, &chs); systime_snapshot->cs_id = tk->tkr_mono.clock->id; systime_snapshot->hw_cycles = chs.hw_cycles; systime_snapshot->hw_csid = chs.hw_csid; systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_sys = tk->tkr_mono.base; offs_sys = *offs; base_raw = tk->tkr_raw.base; nsec_sys = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); } while (read_seqcount_retry(&tkd->seq, seq)); systime_snapshot->cycles = now; systime_snapshot->systime = ktime_add_ns(base_sys, offs_sys + nsec_sys); systime_snapshot->monoraw = ktime_add_ns(base_raw, nsec_raw); /* * Special case for PTP. Just transfer the raw time into sys, * so the call sites can consistently use snap::systime. */ if (clock_id == CLOCK_MONOTONIC_RAW) systime_snapshot->systime = systime_snapshot->monoraw; /* Tell the consumer that this snapshot is valid */ systime_snapshot->valid = true; } EXPORT_SYMBOL_GPL(ktime_get_snapshot_id); /* Scale base by mult/div checking for overflow */ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) { u64 tmp, rem; tmp = div64_u64_rem(*base, div, &rem); if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } /** * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval * @history: Snapshot representing start of history * @partial_history_cycles: Cycle offset into history (fractional part) * @total_history_cycles: Total history length in cycles * @discontinuity: True indicates clock was set on history period * @ts: Cross timestamp that should be adjusted using * partial/total ratio * * Helper function used by get_device_system_crosststamp() to correct the * crosstimestamp corresponding to the start of the current interval to the * system counter value (timestamp point) provided by the driver. The * total_history_* quantities are the total history starting at the provided * reference point and ending at the start of the current interval. The cycle * count between the driver timestamp point and the start of the current * interval is partial_history_cycles. */ static int adjust_historical_crosststamp(struct system_time_snapshot *history, u64 partial_history_cycles, u64 total_history_cycles, bool discontinuity, struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 corr_raw, corr_sys; bool interp_forward; int ret; if (total_history_cycles == 0 || partial_history_cycles == 0) return 0; /* Interpolate shortest distance from beginning or end of history */ interp_forward = partial_history_cycles > total_history_cycles / 2; partial_history_cycles = interp_forward ? total_history_cycles - partial_history_cycles : partial_history_cycles; /* * Scale the monotonic raw time delta by: * partial_history_cycles / total_history_cycles */ corr_raw = (u64)ktime_to_ns(ktime_sub(ts->sys_monoraw, history->monoraw)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_raw); if (ret) return ret; /* * If there is a discontinuity in the history, scale monotonic raw * correction by: * mult(sys)/mult(raw) yielding the system time correction * * Otherwise, calculate the system time correction similar to monotonic * raw calculation */ if (discontinuity) { corr_sys = mul_u64_u32_div(corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); } else { corr_sys = (u64)ktime_to_ns(ktime_sub(ts->sys_systime, history->systime)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_sys); if (ret) return ret; } /* Fixup monotonic raw and system time time values */ if (interp_forward) { ts->sys_monoraw = ktime_add_ns(history->monoraw, corr_raw); ts->sys_systime = ktime_add_ns(history->systime, corr_sys); } else { ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); ts->sys_systime = ktime_sub_ns(ts->sys_systime, corr_sys); } return 0; } /* * timestamp_in_interval - true if ts is chronologically in [start, end] * * True if ts occurs chronologically at or after start, and before or at end. */ static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { if (ts >= start && ts <= end) return true; if (start > end && (ts >= start || ts <= end)) return true; return false; } static bool convert_clock(u64 *val, u32 numerator, u32 denominator) { u64 rem, res; if (!numerator || !denominator) return false; res = div64_u64_rem(*val, denominator, &rem) * numerator; *val = res + div_u64(rem * numerator, denominator); return true; } static bool convert_base_to_cs(struct system_counterval_t *scv) { struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock; struct clocksource_base *base; u32 num, den; /* The timestamp was taken from the time keeper clock source */ if (cs->id == scv->cs_id) return true; /* * Check whether cs_id matches the base clock. Prevent the compiler from * re-evaluating @base as the clocksource might change concurrently. */ base = READ_ONCE(cs->base); if (!base || base->id != scv->cs_id) return false; num = scv->use_nsecs ? cs->freq_khz : base->numerator; den = scv->use_nsecs ? USEC_PER_SEC : base->denominator; if (!convert_clock(&scv->cycles, num, den)) return false; scv->cycles += base->offset; /* Set the clocksource ID as scv::cycles is now clocksource based */ scv->cs_id = cs->id; return true; } static bool convert_cs_to_base(u64 *cycles, enum clocksource_ids base_id) { struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock; struct clocksource_base *base; /* * Check whether base_id matches the base clock. Prevent the compiler from * re-evaluating @base as the clocksource might change concurrently. */ base = READ_ONCE(cs->base); if (!base || base->id != base_id) return false; *cycles -= base->offset; if (!convert_clock(cycles, base->denominator, base->numerator)) return false; return true; } static bool convert_ns_to_cs(u64 *delta) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; if (BITS_TO_BYTES(fls64(*delta) + tkr->shift) >= sizeof(*delta)) return false; *delta = div_u64((*delta << tkr->shift) - tkr->xtime_nsec, tkr->mult); return true; } /** * ktime_real_to_base_clock() - Convert CLOCK_REALTIME timestamp to a base clock timestamp * @treal: CLOCK_REALTIME timestamp to convert * @base_id: base clocksource id * @cycles: pointer to store the converted base clock timestamp * * Converts a supplied, future realtime clock value to the corresponding base clock value. * * Return: true if the conversion is successful, false otherwise. */ bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 delta; do { seq = read_seqcount_begin(&tk_core.seq); if ((u64)treal < tk->tkr_mono.base_real) return false; delta = (u64)treal - tk->tkr_mono.base_real; if (!convert_ns_to_cs(&delta)) return false; *cycles = tk->tkr_mono.cycle_last + delta; if (!convert_cs_to_base(cycles, base_id)) return false; } while (read_seqcount_retry(&tk_core.seq, seq)); return true; } EXPORT_SYMBOL_GPL(ktime_real_to_base_clock); /** * get_device_system_crosststamp - Synchronously capture system/device timestamp * @get_time_fn: Callback to get simultaneous device time and system counter * from the device driver * @ctx: Context passed to get_time_fn() * @history_begin: Historical reference point used to interpolate system time when * the counter value provided by the driver is before the current interval * @xtstamp: Receives simultaneously captured system and device time * * Reads a timestamp from a device and correlates it to system time */ int get_device_system_crosststamp(int (*get_time_fn) (ktime_t *device_time, struct system_counterval_t *sys_counterval, void *ctx), void *ctx, struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { u64 syscnt_cycles, cycles, now, interval_start; unsigned int seq, clock_was_set_seq = 0; ktime_t base_sys, base_raw, *offs; u64 nsec_sys, nsec_raw; u8 cs_was_changed_seq; bool do_interp; struct timekeeper *tk; struct tk_data *tkd; int ret; switch (xtstamp->clock_id) { case CLOCK_REALTIME: tkd = &tk_core; offs = &tk_core.timekeeper.offs_real; break; case CLOCK_AUX ... CLOCK_AUX_LAST: tkd = aux_get_tk_data(xtstamp->clock_id); if (!tkd) return -ENODEV; offs = &tkd->timekeeper.offs_aux; break; default: WARN_ON_ONCE(1); return -ENODEV; } tk = &tkd->timekeeper; do { seq = read_seqcount_begin(&tkd->seq); /* * Try to synchronously capture device time and a system * counter value calling back into the device driver */ ret = get_time_fn(&xtstamp->device, &xtstamp->sys_counter, ctx); if (ret) return ret; /* * Verify that the clocksource ID associated with the captured * system counter value is the same as for the currently * installed timekeeper clocksource and convert to it. */ if (xtstamp->sys_counter.cs_id == CSID_GENERIC || !convert_base_to_cs(&xtstamp->sys_counter)) return -ENODEV; cycles = syscnt_cycles = xtstamp->sys_counter.cycles; /* * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; do_interp = true; } else { do_interp = false; } base_sys = ktime_add(tk->tkr_mono.base, *offs); base_raw = tk->tkr_raw.base; nsec_sys = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tkd->seq, seq)); xtstamp->sys_systime = ktime_add_ns(base_sys, nsec_sys); xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); /* * Interpolate if necessary, adjusting back from the start of the * current interval */ if (do_interp) { u64 partial_history_cycles, total_history_cycles; bool discontinuity; /* * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || !timestamp_in_interval(history_begin->cycles, cycles, syscnt_cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - syscnt_cycles; total_history_cycles = cycles - history_begin->cycles; discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq; ret = adjust_historical_crosststamp(history_begin, partial_history_cycles, total_history_cycles, discontinuity, xtstamp); } return ret; } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * timekeeping_clocksource_has_base - Check whether the current clocksource * is based on given a base clock * @id: base clocksource ID * * Note: The return value is a snapshot which can become invalid right * after the function returns. * * Return: true if the timekeeper clocksource has a base clock with @id, * false otherwise */ bool timekeeping_clocksource_has_base(enum clocksource_ids id) { /* * This is a snapshot, so no point in using the sequence * count. Just prevent the compiler from re-evaluating @base as the * clocksource might change concurrently. */ struct clocksource_base *base = READ_ONCE(tk_core.timekeeper.tkr_mono.clock->base); return base ? base->id == id : false; } EXPORT_SYMBOL_GPL(timekeeping_clocksource_has_base); /** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time * * Sets the time of day to the new time and update NTP and notify hrtimers */ int do_settimeofday64(const struct timespec64 *ts) { struct timespec64 ts_delta, xt; if (!timespec64_valid_settod(ts)) return -EINVAL; scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; timekeeping_forward_now(tks); xt = tk_xtime(tks); ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tks->wall_to_monotonic, &ts_delta) > 0) { timekeeping_restore_shadow(&tk_core); return -EINVAL; } tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, ts_delta)); tk_set_xtime(tks, ts); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); audit_tk_injoffset(ts_delta); add_device_randomness(ts, sizeof(*ts)); return 0; } EXPORT_SYMBOL(do_settimeofday64); static inline bool timekeeper_is_core_tk(struct timekeeper *tk) { return !IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS) || tk->id == TIMEKEEPER_CORE; } /** * __timekeeping_inject_offset - Adds or subtracts from the current time. * @tkd: Pointer to the timekeeper to modify * @ts: Pointer to the timespec variable containing the offset * * Adds or subtracts an offset value from the current time. */ static int __timekeeping_inject_offset(struct tk_data *tkd, const struct timespec64 *ts) { struct timekeeper *tks = &tkd->shadow_timekeeper; struct timespec64 tmp; if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; timekeeping_forward_now(tks); if (timekeeper_is_core_tk(tks)) { /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tks), *ts); if (timespec64_compare(&tks->wall_to_monotonic, ts) > 0 || !timespec64_valid_settod(&tmp)) { timekeeping_restore_shadow(tkd); return -EINVAL; } tk_xtime_add(tks, ts); tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, *ts)); } else { struct tk_read_base *tkr_mono = &tks->tkr_mono; ktime_t now, offs; /* Get the current time */ now = ktime_add_ns(tkr_mono->base, timekeeping_get_ns(tkr_mono)); /* Add the relative offset change */ offs = ktime_add(tks->offs_aux, timespec64_to_ktime(*ts)); /* Prevent that the resulting time becomes negative */ if (ktime_add(now, offs) < 0) { timekeeping_restore_shadow(tkd); return -EINVAL; } tk_update_aux_offs(tks, offs); } timekeeping_update_from_shadow(tkd, TK_UPDATE_ALL); return 0; } static int timekeeping_inject_offset(const struct timespec64 *ts) { int ret; scoped_guard (raw_spinlock_irqsave, &tk_core.lock) ret = __timekeeping_inject_offset(&tk_core, ts); /* Signal hrtimers about time change */ if (!ret) clock_was_set(CLOCK_SET_WALL); return ret; } /* * Indicates if there is an offset between the system clock and the hardware * clock/persistent clock/rtc. */ int persistent_clock_is_local; /* * Adjust the time obtained from the CMOS to be UTC time instead of * local time. * * This is ugly, but preferable to the alternatives. Otherwise we * would either need to write a program to do it in /etc/rc (and risk * confusion if the program gets run more than once; it would also be * hard to make the program warp the clock precisely n hours) or * compile in the timezone information into the kernel. Bad, bad.... * * - TYT, 1992-01-01 * * The best thing to do is to keep the CMOS clock in universal time (UTC) * as real UNIX machines always do it. This avoids all headaches about * daylight saving times and warping kernel clocks. */ void timekeeping_warp_clock(void) { if (sys_tz.tz_minuteswest != 0) { struct timespec64 adjust; persistent_clock_is_local = 1; adjust.tv_sec = sys_tz.tz_minuteswest * 60; adjust.tv_nsec = 0; timekeeping_inject_offset(&adjust); } } /* * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) { tk->tai_offset = tai_offset; tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } /* * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource */ static int change_clocksource(void *data) { struct clocksource *new = data, *old = NULL; /* * If the clocksource is in a module, get a module reference. * Succeeds for built-in code (owner == NULL) as well. Abort if the * reference can't be acquired. */ if (!try_module_get(new->owner)) return 0; /* Abort if the device can't be enabled */ if (new->enable && new->enable(new) != 0) { module_put(new->owner); return 0; } scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; timekeeping_forward_now(tks); old = tks->tkr_mono.clock; tk_setup_internals(tks, new); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } tk_aux_update_clocksource(); if (old) { if (old->disable) old->disable(old); module_put(old->owner); } return 0; } /** * timekeeping_notify - Install a new clock source * @clock: pointer to the clock source * * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; if (tk->tkr_mono.clock == clock) return 0; /* Disable inlined reads accross the clocksource switch */ clocksource_disable_inline_read(); stop_machine(change_clocksource, clock, NULL); /* * If the clocksource has been selected and supports inlined reads * enable the branch. */ if (tk->tkr_mono.clock == clock && clock->flags & CLOCK_SOURCE_CAN_INLINE_READ) clocksource_enable_inline_read(); tick_clock_notify(); return tk->tkr_mono.clock == clock ? 0 : -1; } /** * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec * @ts: pointer to the timespec64 to be set * * Returns the raw monotonic time (completely un-modified by ntp) */ void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->raw_sec; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_raw_ts64); /** * ktime_get_clock_ts64 - Returns time of a clock in a timespec * @id: POSIX clock ID of the clock to read * @ts: Pointer to the timespec64 to be set * * The timestamp is invalidated (@ts->sec is set to -1) if the * clock @id is not available. */ void ktime_get_clock_ts64(clockid_t id, struct timespec64 *ts) { /* Invalidate time stamp */ ts->tv_sec = -1; ts->tv_nsec = 0; switch (id) { case CLOCK_REALTIME: ktime_get_real_ts64(ts); return; case CLOCK_MONOTONIC: ktime_get_ts64(ts); return; case CLOCK_MONOTONIC_RAW: ktime_get_raw_ts64(ts); return; case CLOCK_AUX ... CLOCK_AUX_LAST: if (IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS)) ktime_get_aux_ts64(id, ts); return; default: WARN_ON_ONCE(1); } } EXPORT_SYMBOL_GPL(ktime_get_clock_ts64); /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; int ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred */ u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * read_persistent_clock64 - Return time from the persistent clock. * @ts: Pointer to the storage for the readout value * * Weak dummy function for arches that do not yet support it. * Reads the time from the battery backed persistent clock. * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ void __weak read_persistent_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; } /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. * @wall_time: current time as returned by persistent clock * @boot_offset: offset that is defined as wall_time - boot_time * * Weak dummy function for arches that do not yet support it. * * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't * support dedicated boot time clock will provide the best estimate of the * boot time. */ void __weak __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, struct timespec64 *boot_offset) { read_persistent_clock64(wall_time); *boot_offset = ns_to_timespec64(local_clock()); } static __init void tkd_basic_setup(struct tk_data *tkd, enum timekeeper_ids tk_id, bool valid) { raw_spin_lock_init(&tkd->lock); seqcount_raw_spinlock_init(&tkd->seq, &tkd->lock); tkd->timekeeper.id = tkd->shadow_timekeeper.id = tk_id; tkd->timekeeper.clock_valid = tkd->shadow_timekeeper.clock_valid = valid; } /* * Flag reflecting whether timekeeping_resume() has injected sleeptime. * * The flag starts of false and is only set when a suspend reaches * timekeeping_suspend(), timekeeping_resume() sets it to false when the * timekeeper clocksource is not stopping across suspend and has been * used to update sleep time. If the timekeeper clocksource has stopped * then the flag stays true and is used by the RTC resume code to decide * whether sleeptime must be injected and if so the flag gets false then. * * If a suspend fails before reaching timekeeping_resume() then the flag * stays false and prevents erroneous sleeptime injection. */ static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ void __init timekeeping_init(void) { struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tks = &tk_core.shadow_timekeeper; struct clocksource *clock; tkd_basic_setup(&tk_core, TIMEKEEPER_CORE, true); tk_aux_setup(); read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { pr_warn("Persistent clock returned invalid value"); wall_time = (struct timespec64){0}; } if (timespec64_compare(&wall_time, &boot_offset) < 0) boot_offset = (struct timespec64){0}; /* * We want set wall_to_mono, so the following is true: * wall time + wall_to_mono = boot time */ wall_to_mono = timespec64_sub(boot_offset, wall_time); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); guard(raw_spinlock_irqsave)(&tk_core.lock); ntp_init(); tk_setup_internals(tks, clock); tk_set_xtime(tks, &wall_time); tks->raw_sec = 0; tk_set_wall_to_mono(tks, wall_to_mono); timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); } /* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @tk: Pointer to the timekeeper to be updated * @delta: Pointer to the delta value in timespec64 format * * Takes a timespec offset measuring a suspend interval and properly * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) /* * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource * 2) persistent clock (ie: RTC accessible when irqs are off) * 3) RTC * * 1) and 2) are used by timekeeping, 3) by RTC subsystem. * If system has neither 1) nor 2), 3) will be used finally. * * * If timekeeping has injected sleeptime via either 1) or 2), * 3) becomes needless, so in this case we don't need to call * rtc_resume(), and this is what timekeeping_rtc_skipresume() * means. */ bool timekeeping_rtc_skipresume(void) { return !suspend_timing_needed; } /* * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). * * But if system has 2), 2) will definitely be used, so in this * case we don't need to call rtc_suspend(), and this is what * timekeeping_rtc_skipsuspend() means. */ bool timekeeping_rtc_skipsuspend(void) { return persistent_clock_exists; } /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { scoped_guard(raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; suspend_timing_needed = false; timekeeping_forward_now(tks); __timekeeping_inject_sleeptime(tks, delta); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL | CLOCK_SET_BOOT); } #endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. */ void timekeeping_resume(void) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct clocksource *clock = tks->tkr_mono.clock; struct timespec64 ts_new, ts_delta; bool inject_sleeptime = false; u64 cycle_now, nsec; unsigned long flags; read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&tk_core.lock, flags); /* * After system resumes, we need to calculate the suspended time and * compensate it for the OS time. There are 3 sources that could be * used: Nonstop clocksource during suspend, persistent clock and rtc * device. * * One specific platform may have 1 or 2 or all of them, and the * preference will be: * suspend-nonstop clocksource -> persistent clock -> rtc * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tks->tkr_mono); nsec = clocksource_stop_suspend_timing(clock, cycle_now); if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); inject_sleeptime = true; } if (inject_sleeptime) { suspend_timing_needed = false; __timekeeping_inject_sleeptime(tks, &ts_delta); } /* Re-base the last cycle value */ tks->tkr_mono.cycle_last = cycle_now; tks->tkr_raw.cycle_last = cycle_now; tks->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); raw_spin_unlock_irqrestore(&tk_core.lock, flags); touch_softlockup_watchdog(); /* Resume the clockevent device(s) and hrtimers */ tick_resume(); /* Notify timerfd as resume is equivalent to clock_was_set() */ timerfd_resume(); } static void timekeeping_syscore_resume(void *data) { timekeeping_resume(); } int timekeeping_suspend(void) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; struct clocksource *curr_clock; unsigned long flags; u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at * timekeeping_init by its return value, so if we see a valid * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; suspend_timing_needed = true; raw_spin_lock_irqsave(&tk_core.lock, flags); timekeeping_forward_now(tks); timekeeping_suspended = 1; /* * Since we've called forward_now, cycle_last stores the value * just read from the current clocksource. Save this to potentially * use in suspend timing. */ curr_clock = tks->tkr_mono.clock; cycle_now = tks->tkr_mono.cycle_last; clocksource_start_suspend_timing(curr_clock, cycle_now); if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, * which each can add ~1 second drift error, * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ delta = timespec64_sub(tk_xtime(tks), timekeeping_suspend_time); delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction * has occurred and set old_delta to the current delta. */ old_delta = delta; } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = timespec64_add(timekeeping_suspend_time, delta_delta); } } timekeeping_update_from_shadow(&tk_core, 0); halt_fast_timekeeper(tks); raw_spin_unlock_irqrestore(&tk_core.lock, flags); tick_suspend(); clocksource_suspend(); clockevents_suspend(); return 0; } static int timekeeping_syscore_suspend(void *data) { return timekeeping_suspend(); } /* sysfs resume/suspend bits for timekeeping */ static const struct syscore_ops timekeeping_syscore_ops = { .resume = timekeeping_syscore_resume, .suspend = timekeeping_syscore_suspend, }; static struct syscore timekeeping_syscore = { .ops = &timekeeping_syscore_ops, }; static int __init timekeeping_init_ops(void) { register_syscore(&timekeeping_syscore); return 0; } device_initcall(timekeeping_init_ops); /* * Apply a multiplier adjustment to the timekeeper */ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, s64 offset, s32 mult_adj) { s64 interval = tk->cycle_interval; if (mult_adj == 0) { return; } else if (mult_adj == -1) { interval = -interval; offset = -offset; } else if (mult_adj != 1) { interval *= mult_adj; offset *= mult_adj; } /* * So the following can be confusing. * * To keep things simple, lets assume mult_adj == 1 for now. * * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier * by one, this causes the xtime_interval to be incremented by * one cycle_interval. This is because: * xtime_interval = cycle_interval * mult * So if mult is being incremented by one: * xtime_interval = cycle_interval * (mult + 1) * Its the same as: * xtime_interval = (cycle_interval * mult) + cycle_interval * Which can be shortened to: * xtime_interval += cycle_interval * * So offset stores the non-accumulated cycles. Thus the current * time (in shifted nanoseconds) is: * now = (offset * adj) + xtime_nsec * Now, even though we're adjusting the clock frequency, we have * to keep time consistent. In other words, we can't jump back * in time, and we also want to avoid jumping forward in time. * * So given the same offset value, we need the time to be the same * both before and after the freq adjustment. * now = (offset * adj_1) + xtime_nsec_1 * now = (offset * adj_2) + xtime_nsec_2 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_2) + xtime_nsec_2 * And we know: * adj_2 = adj_1 + 1 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * (adj_1+1)) + xtime_nsec_2 * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_1) + offset + xtime_nsec_2 * Canceling the sides: * xtime_nsec_1 = offset + xtime_nsec_2 * Which gives us: * xtime_nsec_2 = xtime_nsec_1 - offset * Which simplifies to: * xtime_nsec -= offset */ if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; tk->tkr_mono.xtime_nsec -= offset; } /* * Adjust the timekeeper's multiplier to the correct frequency * and also to reduce the accumulated error value. */ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { u64 ntp_tl = ntp_tick_length(tk->id); u32 mult; /* * Determine the multiplier from the current NTP tick length. * Avoid expensive division when the tick length doesn't change. */ if (likely(tk->ntp_tick == ntp_tl)) { mult = tk->tkr_mono.mult - tk->ntp_err_mult; } else { tk->ntp_tick = ntp_tl; mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) - tk->xtime_remainder, tk->cycle_interval); } /* * If the clock is behind the NTP time, increase the multiplier by 1 * to catch up with it. If it's ahead and there was a remainder in the * tick division, the clock will slow down. Otherwise it will stay * ahead until the tick length changes to a non-divisible value. */ tk->ntp_err_mult = tk->ntp_error > 0 ? 1 : 0; mult += tk->ntp_err_mult; timekeeping_apply_adjustment(tk, offset, mult - tk->tkr_mono.mult); if (unlikely(tk->tkr_mono.clock->maxadj && (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource * in the code above, its possible the required corrective factor to * xtime_nsec could cause it to underflow. * * Now, since we have already accumulated the second and the NTP * subsystem has been notified via second_overflow(), we need to skip * the next update. */ if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { tk->tkr_mono.xtime_nsec += (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec--; tk->skip_second_overflow = 1; } } /* * accumulate_nsecs_to_secs - Accumulates nsecs into secs * * Helper function that accumulates the nsecs greater than a second * from the xtime_nsec field to the xtime_secs field. * It also calls into the NTP code to handle leapsecond processing. */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* * Skip NTP update if this second was accumulated before, * i.e. xtime_nsec underflowed in timekeeping_adjust() */ if (unlikely(tk->skip_second_overflow)) { tk->skip_second_overflow = 0; continue; } /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->id, tk->xtime_sec); if (unlikely(leap)) { struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_set = TK_CLOCK_WAS_SET; } } return clock_set; } /* * logarithmic_accumulation - shifted accumulation of cycles * * This functions accumulates a shifted interval of cycles into * a shifted interval nanoseconds. Allows for O(log) accumulation * loop. * * Returns the unconsumed cycles. */ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) return offset; /* Accumulate one shifted interval */ offset -= interval; tk->tkr_mono.cycle_last += interval; tk->tkr_raw.cycle_last += interval; tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { tk->tkr_raw.xtime_nsec -= snsec_per_sec; tk->raw_sec++; } /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length */ static bool __timekeeping_advance(struct tk_data *tkd, enum timekeeping_adv_mode mode) { struct timekeeper *tk = &tkd->shadow_timekeeper; struct timekeeper *real_tk = &tkd->timekeeper; unsigned int clock_set = 0; int shift = 0, maxshift; u64 offset, orig_offset; /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) return false; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); orig_offset = offset; /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) return false; /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, * we calculate the largest doubling multiple of cycle_intervals * that is smaller than the offset. We then accumulate that * chunk in one go, and then try to consume the next smaller * doubled multiple. */ shift = ilog2(offset) - ilog2(tk->cycle_interval); shift = max(0, shift); /* Bound shift to one less than what overflows tick_length */ maxshift = (64 - (ilog2(ntp_tick_length(tk->id)) + 1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { offset = logarithmic_accumulation(tk, offset, shift, &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); /* * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ clock_set |= accumulate_nsecs_to_secs(tk); /* * To avoid inconsistencies caused adjtimex TK_ADV_FREQ calls * making small negative adjustments to the base xtime_nsec * value, only update the coarse clocks if we accumulated time */ if (orig_offset != offset) tk_update_coarse_nsecs(tk); timekeeping_update_from_shadow(tkd, clock_set); return !!clock_set; } static bool timekeeping_advance(enum timekeeping_adv_mode mode) { guard(raw_spinlock_irqsave)(&tk_core.lock); return __timekeeping_advance(&tk_core, mode); } /** * update_wall_time - Uses the current clocksource to increment the wall time * * It also updates the enabled auxiliary clock timekeepers */ void update_wall_time(void) { if (timekeeping_advance(TK_ADV_TICK)) clock_was_set_delayed(); tk_aux_advance(); } /** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime_coarse(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); /** * ktime_get_coarse_real_ts64_mg - return latter of coarse grained time or floor * @ts: timespec64 to be filled * * Fetch the global mg_floor value, convert it to realtime and compare it * to the current coarse-grained time. Fill @ts with whichever is * latest. Note that this is a filesystem-specific interface and should be * avoided outside of that context. */ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 floor = atomic64_read(&mg_floor); ktime_t f_real, offset, coarse; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime_coarse(tk); offset = tk_core.timekeeper.offs_real; } while (read_seqcount_retry(&tk_core.seq, seq)); coarse = timespec64_to_ktime(*ts); f_real = ktime_add(floor, offset); if (ktime_after(f_real, coarse)) *ts = ktime_to_timespec64(f_real); } /** * ktime_get_real_ts64_mg - attempt to update floor value and return result * @ts: pointer to the timespec to be set * * Get a monotonic fine-grained time value and attempt to swap it into * mg_floor. If that succeeds then accept the new floor value. If it fails * then another task raced in during the interim time and updated the * floor. Since any update to the floor must be later than the previous * floor, either outcome is acceptable. * * Typically this will be called after calling ktime_get_coarse_real_ts64_mg(), * and determining that the resulting coarse-grained timestamp did not effect * a change in ctime. Any more recent floor value would effect a change to * ctime, so there is no need to retry the atomic64_try_cmpxchg() on failure. * * @ts will be filled with the latest floor value, regardless of the outcome of * the cmpxchg. Note that this is a filesystem specific interface and should be * avoided outside of that context. */ void ktime_get_real_ts64_mg(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t old = atomic64_read(&mg_floor); ktime_t offset, mono; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; mono = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); offset = tk_core.timekeeper.offs_real; } while (read_seqcount_retry(&tk_core.seq, seq)); mono = ktime_add_ns(mono, nsecs); /* * Attempt to update the floor with the new time value. As any * update must be later then the existing floor, and would effect * a change to ctime from the perspective of the current task, * accept the resulting floor value regardless of the outcome of * the swap. */ if (atomic64_try_cmpxchg(&mg_floor, &old, mono)) { ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); timekeeping_inc_mg_floor_swaps(); } else { /* * Another task changed mg_floor since "old" was fetched. * "old" has been updated with the latest value of "mg_floor". * That value is newer than the previous floor value, which * is enough to effect a change to ctime. Accept it. */ *ts = ktime_to_timespec64(ktime_add(old, offset)); } } void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime_coarse(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); /* * Must hold jiffies_lock */ void do_timer(unsigned long ticks) { jiffies_64 += ticks; calc_global_load(); } /** * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the * sequence number in @cwsseq and timekeeper.clock_was_set_seq are * different. * * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); base = ktime_add_ns(base, nsecs); if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } /* Handle leapsecond insertion adjustments */ if (unlikely(base >= tk->next_leap_ktime)) *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0)); } while (read_seqcount_retry(&tk_core.seq, seq)); return base; } /* * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ static int timekeeping_validate_timex(const struct __kernel_timex *txc, bool aux_clock) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; if (!(txc->modes & ADJ_OFFSET_READONLY) && !capable(CAP_SYS_TIME)) return -EPERM; } else { /* In order to modify anything, you gotta be super-user! */ if (txc->modes && !capable(CAP_SYS_TIME)) return -EPERM; /* * if the quartz is off by more than 10% then * something is VERY wrong! */ if (txc->modes & ADJ_TICK && (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; } if (txc->modes & ADJ_SETOFFSET) { /* In order to inject time, you gotta be super-user! */ if (!capable(CAP_SYS_TIME)) return -EPERM; /* * Validate if a timespec/timeval used to inject a time * offset is valid. Offsets can be positive or negative, so * we don't check tv_sec. The value of the timeval/timespec * is the sum of its fields,but *NOTE*: * The field tv_usec/tv_nsec must always be non-negative and * we can't have more nanoseconds/microseconds than a second. */ if (txc->time.tv_usec < 0) return -EINVAL; if (txc->modes & ADJ_NANO) { if (txc->time.tv_usec >= NSEC_PER_SEC) return -EINVAL; } else { if (txc->time.tv_usec >= USEC_PER_SEC) return -EINVAL; } } /* * Check for potential multiplication overflows that can * only happen on 64-bit systems: */ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { if (LLONG_MIN / PPM_SCALE > txc->freq) return -EINVAL; if (LLONG_MAX / PPM_SCALE < txc->freq) return -EINVAL; } if (aux_clock) { /* Auxiliary clocks are similar to TAI and do not have leap seconds */ if (txc->modes & ADJ_STATUS && txc->status & (STA_INS | STA_DEL)) return -EINVAL; /* No TAI offset setting */ if (txc->modes & ADJ_TAI) return -EINVAL; /* No PPS support either */ if (txc->modes & ADJ_STATUS && txc->status & (STA_PPSFREQ | STA_PPSTIME)) return -EINVAL; } return 0; } /** * random_get_entropy_fallback - Returns the raw clock source value, * used by random.c for platforms with no valid random_get_entropy(). */ unsigned long random_get_entropy_fallback(void) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; struct clocksource *clock = READ_ONCE(tkr->clock); if (unlikely(timekeeping_suspended || !clock)) return 0; return clock->read(clock); } EXPORT_SYMBOL_GPL(random_get_entropy_fallback); struct adjtimex_result { struct audit_ntp_data ad; struct timespec64 delta; bool clock_set; }; static int __do_adjtimex(struct tk_data *tkd, struct __kernel_timex *txc, struct adjtimex_result *result) { struct timekeeper *tks = &tkd->shadow_timekeeper; bool aux_clock = !timekeeper_is_core_tk(tks); struct timespec64 ts; s32 orig_tai, tai; int ret; /* Validate the data before disabling interrupts */ ret = timekeeping_validate_timex(txc, aux_clock); if (ret) return ret; add_device_randomness(txc, sizeof(*txc)); if (!aux_clock) ktime_get_real_ts64(&ts); else tk_get_aux_ts64(tkd->timekeeper.id, &ts); add_device_randomness(&ts, sizeof(ts)); guard(raw_spinlock_irqsave)(&tkd->lock); if (!tks->clock_valid) return -ENODEV; if (txc->modes & ADJ_SETOFFSET) { result->delta.tv_sec = txc->time.tv_sec; result->delta.tv_nsec = txc->time.tv_usec; if (!(txc->modes & ADJ_NANO)) result->delta.tv_nsec *= 1000; ret = __timekeeping_inject_offset(tkd, &result->delta); if (ret) return ret; result->clock_set = true; } orig_tai = tai = tks->tai_offset; ret = ntp_adjtimex(tks->id, txc, &ts, &tai, &result->ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tks, tai); timekeeping_update_from_shadow(tkd, TK_CLOCK_WAS_SET); result->clock_set = true; } else { tk_update_leap_state_all(tkd); } /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) result->clock_set |= __timekeeping_advance(tkd, TK_ADV_FREQ); return ret; } /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function * @txc: Pointer to kernel_timex structure containing NTP parameters */ int do_adjtimex(struct __kernel_timex *txc) { struct adjtimex_result result = { }; int ret; ret = __do_adjtimex(&tk_core, txc, &result); if (ret < 0) return ret; if (txc->modes & ADJ_SETOFFSET) audit_tk_injoffset(result.delta); audit_ntp_log(&result.ad); if (result.clock_set) clock_was_set(CLOCK_SET_WALL); ntp_notify_cmos_timer(result.delta.tv_sec != 0); return ret; } /* * Invoked from NTP with the time keeper lock held, so lockless access is * fine. */ long ktime_get_ntp_seconds(unsigned int id) { return timekeeper_data[id].timekeeper.xtime_sec; } #ifdef CONFIG_NTP_PPS /** * hardpps() - Accessor function to NTP __hardpps function * @phase_ts: Pointer to timespec64 structure representing phase timestamp * @raw_ts: Pointer to timespec64 structure representing raw timestamp */ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { guard(raw_spinlock_irqsave)(&tk_core.lock); __hardpps(phase_ts, raw_ts); } EXPORT_SYMBOL(hardpps); #endif /* CONFIG_NTP_PPS */ #ifdef CONFIG_POSIX_AUX_CLOCKS #include "posix-timers.h" /* * Bitmap for the activated auxiliary timekeepers to allow lockless quick * checks in the hot paths without touching extra cache lines. If set, then * the state of the corresponding timekeeper has to be re-checked under * timekeeper::lock. */ static unsigned long aux_timekeepers; static inline unsigned int clockid_to_tkid(unsigned int id) { return TIMEKEEPER_AUX_FIRST + id - CLOCK_AUX; } static inline struct tk_data *aux_get_tk_data(clockid_t id) { if (!clockid_aux_valid(id)) return NULL; return &timekeeper_data[clockid_to_tkid(id)]; } /* Invoked from timekeeping after a clocksource change */ static void tk_aux_update_clocksource(void) { unsigned long active = READ_ONCE(aux_timekeepers); unsigned int id; for_each_set_bit(id, &active, BITS_PER_LONG) { struct tk_data *tkd = &timekeeper_data[id + TIMEKEEPER_AUX_FIRST]; struct timekeeper *tks = &tkd->shadow_timekeeper; guard(raw_spinlock_irqsave)(&tkd->lock); if (!tks->clock_valid) continue; timekeeping_forward_now(tks); tk_setup_internals(tks, tk_core.timekeeper.tkr_raw.clock); timekeeping_update_from_shadow(tkd, TK_UPDATE_ALL); } } static void tk_aux_advance(void) { unsigned long active = READ_ONCE(aux_timekeepers); unsigned int id; /* Lockless quick check to avoid extra cache lines */ for_each_set_bit(id, &active, BITS_PER_LONG) { struct tk_data *aux_tkd = &timekeeper_data[id + TIMEKEEPER_AUX_FIRST]; guard(raw_spinlock)(&aux_tkd->lock); if (aux_tkd->shadow_timekeeper.clock_valid) __timekeeping_advance(aux_tkd, TK_ADV_TICK); } } /** * ktime_get_aux - Get time for a AUX clock * @id: ID of the clock to read (CLOCK_AUX...) * @kt: Pointer to ktime_t to store the time stamp * * Returns: True if the timestamp is valid, false otherwise */ bool ktime_get_aux(clockid_t id, ktime_t *kt) { struct tk_data *aux_tkd = aux_get_tk_data(id); struct timekeeper *aux_tk; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); if (!aux_tkd) return false; aux_tk = &aux_tkd->timekeeper; do { seq = read_seqcount_begin(&aux_tkd->seq); if (!aux_tk->clock_valid) return false; base = ktime_add(aux_tk->tkr_mono.base, aux_tk->offs_aux); nsecs = timekeeping_get_ns(&aux_tk->tkr_mono); } while (read_seqcount_retry(&aux_tkd->seq, seq)); *kt = ktime_add_ns(base, nsecs); return true; } EXPORT_SYMBOL_GPL(ktime_get_aux); /** * ktime_get_aux_ts64 - Get time for a AUX clock * @id: ID of the clock to read (CLOCK_AUX...) * @ts: Pointer to timespec64 to store the time stamp * * Returns: True if the timestamp is valid, false otherwise */ bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *ts) { ktime_t now; if (!ktime_get_aux(id, &now)) return false; *ts = ktime_to_timespec64(now); return true; } EXPORT_SYMBOL_GPL(ktime_get_aux_ts64); static int aux_get_res(clockid_t id, struct timespec64 *tp) { if (!clockid_aux_valid(id)) return -ENODEV; tp->tv_sec = aux_clock_resolution_ns() / NSEC_PER_SEC; tp->tv_nsec = aux_clock_resolution_ns() % NSEC_PER_SEC; return 0; } static int aux_get_timespec(clockid_t id, struct timespec64 *tp) { return ktime_get_aux_ts64(id, tp) ? 0 : -ENODEV; } static int aux_clock_set(const clockid_t id, const struct timespec64 *tnew) { struct tk_data *aux_tkd = aux_get_tk_data(id); struct timekeeper *aux_tks; ktime_t tnow, nsecs; if (!timespec64_valid_settod(tnew)) return -EINVAL; if (!aux_tkd) return -ENODEV; aux_tks = &aux_tkd->shadow_timekeeper; guard(raw_spinlock_irq)(&aux_tkd->lock); if (!aux_tks->clock_valid) return -ENODEV; /* Forward the timekeeper base time */ timekeeping_forward_now(aux_tks); /* * Get the updated base time. tkr_mono.base has not been * updated yet, so do that first. That makes the update * in timekeeping_update_from_shadow() redundant, but * that's harmless. After that @tnow can be calculated * by using tkr_mono::cycle_last, which has been set * by timekeeping_forward_now(). */ tk_update_ktime_data(aux_tks); nsecs = timekeeping_cycles_to_ns(&aux_tks->tkr_mono, aux_tks->tkr_mono.cycle_last); tnow = ktime_add(aux_tks->tkr_mono.base, nsecs); /* * Calculate the new AUX offset as delta to @tnow ("monotonic"). * That avoids all the tk::xtime back and forth conversions as * xtime ("realtime") is not applicable for auxiliary clocks and * kept in sync with "monotonic". */ tk_update_aux_offs(aux_tks, ktime_sub(timespec64_to_ktime(*tnew), tnow)); timekeeping_update_from_shadow(aux_tkd, TK_UPDATE_ALL); return 0; } static int aux_clock_adj(const clockid_t id, struct __kernel_timex *txc) { struct tk_data *aux_tkd = aux_get_tk_data(id); struct adjtimex_result result = { }; if (!aux_tkd) return -ENODEV; /* * @result is ignored for now as there are neither hrtimers nor a * RTC related to auxiliary clocks for now. */ return __do_adjtimex(aux_tkd, txc, &result); } const struct k_clock clock_aux = { .clock_getres = aux_get_res, .clock_get_timespec = aux_get_timespec, .clock_set = aux_clock_set, .clock_adj = aux_clock_adj, }; static void aux_clock_enable(clockid_t id) { struct tk_read_base *tkr_raw = &tk_core.timekeeper.tkr_raw; struct tk_data *aux_tkd = aux_get_tk_data(id); struct timekeeper *aux_tks = &aux_tkd->shadow_timekeeper; /* Prevent the core timekeeper from changing. */ guard(raw_spinlock_irq)(&tk_core.lock); /* * Setup the auxiliary clock assuming that the raw core timekeeper * clock frequency conversion is close enough. Userspace has to * adjust for the deviation via clock_adjtime(2). */ guard(raw_spinlock_nested)(&aux_tkd->lock); /* Remove leftovers of a previous registration */ memset(aux_tks, 0, sizeof(*aux_tks)); /* Restore the timekeeper id */ aux_tks->id = aux_tkd->timekeeper.id; /* Setup the timekeeper based on the current system clocksource */ tk_setup_internals(aux_tks, tkr_raw->clock); /* Mark it valid and set it live */ aux_tks->clock_valid = true; timekeeping_update_from_shadow(aux_tkd, TK_UPDATE_ALL); } static void aux_clock_disable(clockid_t id) { struct tk_data *aux_tkd = aux_get_tk_data(id); guard(raw_spinlock_irq)(&aux_tkd->lock); aux_tkd->shadow_timekeeper.clock_valid = false; timekeeping_update_from_shadow(aux_tkd, TK_UPDATE_ALL); } static DEFINE_MUTEX(aux_clock_mutex); static ssize_t aux_clock_enable_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { /* Lazy atoi() as name is "0..7" */ int id = kobj->name[0] & 0x7; bool enable; if (!capable(CAP_SYS_TIME)) return -EPERM; if (kstrtobool(buf, &enable) < 0) return -EINVAL; guard(mutex)(&aux_clock_mutex); if (enable == test_bit(id, &aux_timekeepers)) return count; if (enable) { aux_clock_enable(CLOCK_AUX + id); set_bit(id, &aux_timekeepers); } else { aux_clock_disable(CLOCK_AUX + id); clear_bit(id, &aux_timekeepers); } return count; } static ssize_t aux_clock_enable_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { unsigned long active = READ_ONCE(aux_timekeepers); /* Lazy atoi() as name is "0..7" */ int id = kobj->name[0] & 0x7; return sysfs_emit(buf, "%d\n", test_bit(id, &active)); } static struct kobj_attribute aux_clock_enable_attr = __ATTR_RW(aux_clock_enable); static struct attribute *aux_clock_enable_attrs[] = { &aux_clock_enable_attr.attr, NULL }; static const struct attribute_group aux_clock_enable_attr_group = { .attrs = aux_clock_enable_attrs, }; static int __init tk_aux_sysfs_init(void) { struct kobject *auxo, *tko = kobject_create_and_add("time", kernel_kobj); int ret = -ENOMEM; if (!tko) return ret; auxo = kobject_create_and_add("aux_clocks", tko); if (!auxo) goto err_clean; for (int i = 0; i < MAX_AUX_CLOCKS; i++) { char id[2] = { [0] = '0' + i, }; struct kobject *clk = kobject_create_and_add(id, auxo); if (!clk) { ret = -ENOMEM; goto err_clean; } ret = sysfs_create_group(clk, &aux_clock_enable_attr_group); if (ret) goto err_clean; } return 0; err_clean: kobject_put(auxo); kobject_put(tko); return ret; } late_initcall(tk_aux_sysfs_init); static __init void tk_aux_setup(void) { for (int i = TIMEKEEPER_AUX_FIRST; i <= TIMEKEEPER_AUX_LAST; i++) tkd_basic_setup(&timekeeper_data[i], i, false); } #endif /* CONFIG_POSIX_AUX_CLOCKS */ |
| 1 2 3 4 5 6 7 8 9 10 | // SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> #ifndef __CHECKER__ #include <net/cfg802154.h> #include "driver-ops.h" #define CREATE_TRACE_POINTS #include "trace.h" #endif |
| 1 1 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 | // SPDX-License-Identifier: GPL-2.0 /* Bluetooth HCI driver model support. */ #include <linux/module.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> static const struct class bt_class = { .name = "bluetooth", }; static void bt_link_release(struct device *dev) { struct hci_conn *conn = to_hci_conn(dev); kfree(conn); } static const struct device_type bt_link = { .name = "link", .release = bt_link_release, }; void hci_conn_init_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; bt_dev_dbg(hdev, "conn %p", conn); conn->dev.type = &bt_link; conn->dev.class = &bt_class; conn->dev.parent = &hdev->dev; device_initialize(&conn->dev); } void hci_conn_add_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; bt_dev_dbg(hdev, "conn %p", conn); if (device_is_registered(&conn->dev)) return; dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle); if (device_add(&conn->dev) < 0) bt_dev_err(hdev, "failed to register connection device"); } void hci_conn_del_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; bt_dev_dbg(hdev, "conn %p", conn); if (!device_is_registered(&conn->dev)) { /* If device_add() has *not* succeeded, use *only* put_device() * to drop the reference count. */ put_device(&conn->dev); return; } /* If there are devices using the connection as parent reset it to NULL * before unregistering the device. */ while (1) { struct device *dev; dev = device_find_any_child(&conn->dev); if (!dev) break; device_move(dev, NULL, DPM_ORDER_DEV_LAST); put_device(dev); } device_unregister(&conn->dev); } static void bt_host_release(struct device *dev) { struct hci_dev *hdev = to_hci_dev(dev); if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) { hci_release_dev(hdev); } else { cleanup_srcu_struct(&hdev->srcu); kfree(hdev); } module_put(THIS_MODULE); } static ssize_t reset_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct hci_dev *hdev = to_hci_dev(dev); if (hdev->reset) hdev->reset(hdev); return count; } static DEVICE_ATTR_WO(reset); static struct attribute *bt_host_attrs[] = { &dev_attr_reset.attr, NULL, }; ATTRIBUTE_GROUPS(bt_host); static const struct device_type bt_host = { .name = "host", .release = bt_host_release, .groups = bt_host_groups, }; void hci_init_sysfs(struct hci_dev *hdev) { struct device *dev = &hdev->dev; dev->type = &bt_host; dev->class = &bt_class; __module_get(THIS_MODULE); device_initialize(dev); } int __init bt_sysfs_init(void) { return class_register(&bt_class); } void bt_sysfs_cleanup(void) { class_unregister(&bt_class); } |
| 4471 4493 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * A generic implementation of binary search for the Linux kernel * * Copyright (C) 2008-2009 Ksplice, Inc. * Author: Tim Abbott <tabbott@ksplice.com> */ #include <linux/export.h> #include <linux/bsearch.h> #include <linux/kprobes.h> /* * bsearch - binary search an array of elements * @key: pointer to item being searched for * @base: pointer to first element to search * @num: number of elements * @size: size of each element * @cmp: pointer to comparison function * * This function does a binary search on the given array. The * contents of the array should already be in ascending sorted order * under the provided comparison function. * * Note that the key need not have the same type as the elements in * the array, e.g. key could be a string and the comparison function * could compare the string with the struct's name field. However, if * the key and elements in the array are of the same type, you can use * the same comparison function for both sort() and bsearch(). */ void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { return __inline_bsearch(key, base, num, size, cmp); } EXPORT_SYMBOL(bsearch); NOKPROBE_SYMBOL(bsearch); |
| 9 1 9 9 9 6 6 2 6 6 3 4 3 2 1 1 43 4 40 29 12 3 6 20 2 4 6 13 6 5 1 5 1 4 4 2 2 1 154 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C)2003,2004 USAGI/WIDE Project * * Author: * Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> */ #include <linux/types.h> #include <linux/timer.h> #include <linux/module.h> #include <linux/netfilter.h> #include <linux/in6.h> #include <linux/icmpv6.h> #include <linux/ipv6.h> #include <net/ipv6.h> #include <net/ip6_checksum.h> #include <linux/seq_file.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_log.h> #include "nf_internals.h" static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) { const struct icmp6hdr *hp; struct icmp6hdr _hdr; hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); if (hp == NULL) return false; tuple->dst.u.icmp.type = hp->icmp6_type; tuple->src.u.icmp.id = hp->icmp6_identifier; tuple->dst.u.icmp.code = hp->icmp6_code; return true; } /* Add 1; spaces filled with 0. */ static const u_int8_t invmap[] = { [ICMPV6_ECHO_REQUEST - 128] = ICMPV6_ECHO_REPLY + 1, [ICMPV6_ECHO_REPLY - 128] = ICMPV6_ECHO_REQUEST + 1, [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_REPLY + 1, [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_QUERY + 1 }; static const u_int8_t noct_valid_new[] = { [ICMPV6_MGM_QUERY - 130] = 1, [ICMPV6_MGM_REPORT - 130] = 1, [ICMPV6_MGM_REDUCTION - 130] = 1, [NDISC_ROUTER_SOLICITATION - 130] = 1, [NDISC_ROUTER_ADVERTISEMENT - 130] = 1, [NDISC_NEIGHBOUR_SOLICITATION - 130] = 1, [NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1, [ICMPV6_MLD2_REPORT - 130] = 1, [ICMPV6_MRDISC_ADV - 130] = 1, [ICMPV6_MRDISC_SOL - 130] = 1 }; bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig) { int type = orig->dst.u.icmp.type - 128; if (type < 0 || type >= sizeof(invmap) || !invmap[type]) return false; tuple->src.u.icmp.id = orig->src.u.icmp.id; tuple->dst.u.icmp.type = invmap[type] - 1; tuple->dst.u.icmp.code = orig->dst.u.icmp.code; return true; } static unsigned int *icmpv6_get_timeouts(struct net *net) { return &nf_icmpv6_pernet(net)->timeout; } /* Returns verdict for packet, or -1 for invalid. */ int nf_conntrack_icmpv6_packet(struct nf_conn *ct, struct sk_buff *skb, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { unsigned int *timeout = nf_ct_timeout_lookup(ct); static const u8 valid_new[] = { [ICMPV6_ECHO_REQUEST - 128] = 1, [ICMPV6_NI_QUERY - 128] = 1 }; if (state->pf != NFPROTO_IPV6) return -NF_ACCEPT; if (!nf_ct_is_confirmed(ct)) { int type = ct->tuplehash[0].tuple.dst.u.icmp.type - 128; if (type < 0 || type >= sizeof(valid_new) || !valid_new[type]) { /* Can't create a new ICMPv6 `conn' with this. */ pr_debug("icmpv6: can't create new conn with type %u\n", type + 128); nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple); return -NF_ACCEPT; } } if (!timeout) timeout = icmpv6_get_timeouts(nf_ct_net(ct)); /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic and also to handle correctly ICMP echo reply duplicates. */ nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } static void icmpv6_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { nf_l4proto_log_invalid(skb, state, IPPROTO_ICMPV6, "%s", msg); } static noinline_for_stack int nf_conntrack_icmpv6_redirect(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { u8 hl = ipv6_hdr(skb)->hop_limit; union nf_inet_addr outer_daddr; union { struct nd_opt_hdr nd_opt; struct rd_msg rd_msg; } tmp; const struct nd_opt_hdr *nd_opt; const struct rd_msg *rd_msg; rd_msg = skb_header_pointer(skb, dataoff, sizeof(*rd_msg), &tmp.rd_msg); if (!rd_msg) { icmpv6_error_log(skb, state, "short redirect"); return -NF_ACCEPT; } if (rd_msg->icmph.icmp6_code != 0) return NF_ACCEPT; if (hl != 255 || !(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { icmpv6_error_log(skb, state, "invalid saddr or hoplimit for redirect"); return -NF_ACCEPT; } dataoff += sizeof(*rd_msg); /* warning: rd_msg no longer usable after this call */ nd_opt = skb_header_pointer(skb, dataoff, sizeof(*nd_opt), &tmp.nd_opt); if (!nd_opt || nd_opt->nd_opt_len == 0) { icmpv6_error_log(skb, state, "redirect without options"); return -NF_ACCEPT; } /* We could call ndisc_parse_options(), but it would need * skb_linearize() and a bit more work. */ if (nd_opt->nd_opt_type != ND_OPT_REDIRECT_HDR) return NF_ACCEPT; memcpy(&outer_daddr.ip6, &ipv6_hdr(skb)->daddr, sizeof(outer_daddr.ip6)); dataoff += 8; return nf_conntrack_inet_error(tmpl, skb, dataoff, state, IPPROTO_ICMPV6, &outer_daddr); } int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { union nf_inet_addr outer_daddr; const struct icmp6hdr *icmp6h; struct icmp6hdr _ih; int type; icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); if (icmp6h == NULL) { icmpv6_error_log(skb, state, "short packet"); return -NF_ACCEPT; } if (state->hook == NF_INET_PRE_ROUTING && state->net->ct.sysctl_checksum && nf_ip6_checksum(skb, state->hook, dataoff, IPPROTO_ICMPV6)) { icmpv6_error_log(skb, state, "ICMPv6 checksum failed"); return -NF_ACCEPT; } type = icmp6h->icmp6_type - 130; if (type >= 0 && type < sizeof(noct_valid_new) && noct_valid_new[type]) { nf_ct_set(skb, NULL, IP_CT_UNTRACKED); return NF_ACCEPT; } if (icmp6h->icmp6_type == NDISC_REDIRECT) return nf_conntrack_icmpv6_redirect(tmpl, skb, dataoff, state); /* is not error message ? */ if (icmp6h->icmp6_type >= 128) return NF_ACCEPT; memcpy(&outer_daddr.ip6, &ipv6_hdr(skb)->daddr, sizeof(outer_daddr.ip6)); dataoff += sizeof(*icmp6h); return nf_conntrack_inet_error(tmpl, skb, dataoff, state, IPPROTO_ICMPV6, &outer_daddr); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> static int icmpv6_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *t) { if (nla_put_be16(skb, CTA_PROTO_ICMPV6_ID, t->src.u.icmp.id) || nla_put_u8(skb, CTA_PROTO_ICMPV6_TYPE, t->dst.u.icmp.type) || nla_put_u8(skb, CTA_PROTO_ICMPV6_CODE, t->dst.u.icmp.code)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = { [CTA_PROTO_ICMPV6_TYPE] = { .type = NLA_U8 }, [CTA_PROTO_ICMPV6_CODE] = { .type = NLA_U8 }, [CTA_PROTO_ICMPV6_ID] = { .type = NLA_U16 }, }; static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *tuple, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_TYPE)) { if (!tb[CTA_PROTO_ICMPV6_TYPE]) return -EINVAL; tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); if (tuple->dst.u.icmp.type < 128 || tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || !invmap[tuple->dst.u.icmp.type - 128]) return -EINVAL; } if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_CODE)) { if (!tb[CTA_PROTO_ICMPV6_CODE]) return -EINVAL; tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); } if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_ID)) { if (!tb[CTA_PROTO_ICMPV6_ID]) return -EINVAL; tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); } return 0; } static unsigned int icmpv6_nlattr_tuple_size(void) { static unsigned int size __read_mostly; if (!size) size = nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1); return size; } #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; struct nf_icmp_net *in = nf_icmpv6_pernet(net); if (!timeout) timeout = icmpv6_get_timeouts(net); if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) { *timeout = ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ; } else { /* Set default ICMPv6 timeout. */ *timeout = in->timeout; } return 0; } static int icmpv6_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeout = data; if (nla_put_be32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { [CTA_TIMEOUT_ICMPV6_TIMEOUT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_icmpv6_init_net(struct net *net) { struct nf_icmp_net *in = nf_icmpv6_pernet(net); in->timeout = nf_ct_icmpv6_timeout; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = { .l4proto = IPPROTO_ICMPV6, .allow_clash = true, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmpv6_tuple_to_nlattr, .nlattr_tuple_size = icmpv6_nlattr_tuple_size, .nlattr_to_tuple = icmpv6_nlattr_to_tuple, .nla_policy = icmpv6_nla_policy, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmpv6_timeout_nlattr_to_obj, .obj_to_nlattr = icmpv6_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_ICMP_MAX, .obj_size = sizeof(unsigned int), .nla_policy = icmpv6_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; |
| 16 16 3 11 2 6 1 2 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/slab.h> #include <linux/stat.h> #include <linux/sched/xacct.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> #include <linux/dax.h> #include <linux/overflow.h> #include "internal.h" #include <linux/uaccess.h> #include <asm/unistd.h> /* * Performs necessary checks before doing a clone. * * Can adjust amount of bytes to clone via @req_count argument. * Returns appropriate error code that caller should return or * zero in case the clone should be allowed. */ static int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *req_count, unsigned int remap_flags) { struct inode *inode_in = file_in->f_mapping->host; struct inode *inode_out = file_out->f_mapping->host; uint64_t count = *req_count; uint64_t bcount; loff_t size_in, size_out; loff_t bs = inode_out->i_sb->s_blocksize; int ret; /* The start of both ranges must be aligned to an fs block. */ if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs)) return -EINVAL; /* Ensure offsets don't wrap. */ if (pos_in + count < pos_in || pos_out + count < pos_out) return -EINVAL; size_in = i_size_read(inode_in); size_out = i_size_read(inode_out); /* Dedupe requires both ranges to be within EOF. */ if ((remap_flags & REMAP_FILE_DEDUP) && (pos_in >= size_in || pos_in + count > size_in || pos_out >= size_out || pos_out + count > size_out)) return -EINVAL; /* Ensure the infile range is within the infile. */ if (pos_in >= size_in) return -EINVAL; count = min(count, size_in - (uint64_t)pos_in); ret = generic_write_check_limits(file_out, pos_out, &count); if (ret) return ret; /* * If the user wanted us to link to the infile's EOF, round up to the * next block boundary for this check. * * Otherwise, make sure the count is also block-aligned, having * already confirmed the starting offsets' block alignment. */ if (pos_in + count == size_in && (!(remap_flags & REMAP_FILE_DEDUP) || pos_out + count == size_out)) { bcount = ALIGN(size_in, bs) - pos_in; } else { if (!IS_ALIGNED(count, bs)) count = ALIGN_DOWN(count, bs); bcount = count; } /* Don't allow overlapped cloning within the same file. */ if (inode_in == inode_out && pos_out + bcount > pos_in && pos_out < pos_in + bcount) return -EINVAL; /* * We shortened the request but the caller can't deal with that, so * bounce the request back to userspace. */ if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) return -EINVAL; *req_count = count; return 0; } int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write) { int mask = write ? MAY_WRITE : MAY_READ; loff_t tmp; int ret; if (unlikely(pos < 0 || len < 0)) return -EINVAL; if (unlikely(check_add_overflow(pos, len, &tmp))) return -EINVAL; ret = security_file_permission(file, mask); if (ret) return ret; return fsnotify_file_area_perm(file, mask, &pos, len); } EXPORT_SYMBOL_GPL(remap_verify_area); /* * Ensure that we don't remap a partial EOF block in the middle of something * else. Assume that the offsets have already been checked for block * alignment. * * For clone we only link a partial EOF block above or at the destination file's * EOF. For deduplication we accept a partial EOF block only if it ends at the * destination file's EOF (can not link it into the middle of a file). * * Shorten the request if possible. */ static int generic_remap_check_len(struct inode *inode_in, struct inode *inode_out, loff_t pos_out, loff_t *len, unsigned int remap_flags) { u64 blkmask = i_blocksize(inode_in) - 1; loff_t new_len = *len; if ((*len & blkmask) == 0) return 0; if (pos_out + *len < i_size_read(inode_out)) new_len &= ~blkmask; if (new_len == *len) return 0; if (remap_flags & REMAP_FILE_CAN_SHORTEN) { *len = new_len; return 0; } return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL; } /* Read a page's worth of file data into the page cache. */ static struct folio *vfs_dedupe_get_folio(struct file *file, loff_t pos) { return read_mapping_folio(file->f_mapping, pos >> PAGE_SHIFT, file); } /* * Lock two folios, ensuring that we lock in offset order if the folios * are from the same file. */ static void vfs_lock_two_folios(struct folio *folio1, struct folio *folio2) { /* Always lock in order of increasing index. */ if (folio1->index > folio2->index) swap(folio1, folio2); folio_lock(folio1); if (folio1 != folio2) folio_lock(folio2); } /* Unlock two folios, being careful not to unlock the same folio twice. */ static void vfs_unlock_two_folios(struct folio *folio1, struct folio *folio2) { folio_unlock(folio1); if (folio1 != folio2) folio_unlock(folio2); } /* * Compare extents of two files to see if they are the same. * Caller must have locked both inodes to prevent write races. */ static int vfs_dedupe_file_range_compare(struct file *src, loff_t srcoff, struct file *dest, loff_t dstoff, loff_t len, bool *is_same) { bool same = true; int error = -EINVAL; while (len) { struct folio *src_folio, *dst_folio; void *src_addr, *dst_addr; loff_t cmp_len = min(PAGE_SIZE - offset_in_page(srcoff), PAGE_SIZE - offset_in_page(dstoff)); cmp_len = min(cmp_len, len); if (cmp_len <= 0) goto out_error; src_folio = vfs_dedupe_get_folio(src, srcoff); if (IS_ERR(src_folio)) { error = PTR_ERR(src_folio); goto out_error; } dst_folio = vfs_dedupe_get_folio(dest, dstoff); if (IS_ERR(dst_folio)) { error = PTR_ERR(dst_folio); folio_put(src_folio); goto out_error; } vfs_lock_two_folios(src_folio, dst_folio); /* * Now that we've locked both folios, make sure they're still * mapped to the file data we're interested in. If not, * someone is invalidating pages on us and we lose. */ if (!folio_test_uptodate(src_folio) || !folio_test_uptodate(dst_folio) || src_folio->mapping != src->f_mapping || dst_folio->mapping != dest->f_mapping) { same = false; goto unlock; } src_addr = kmap_local_folio(src_folio, offset_in_folio(src_folio, srcoff)); dst_addr = kmap_local_folio(dst_folio, offset_in_folio(dst_folio, dstoff)); flush_dcache_folio(src_folio); flush_dcache_folio(dst_folio); if (memcmp(src_addr, dst_addr, cmp_len)) same = false; kunmap_local(dst_addr); kunmap_local(src_addr); unlock: vfs_unlock_two_folios(src_folio, dst_folio); folio_put(dst_folio); folio_put(src_folio); if (!same) break; srcoff += cmp_len; dstoff += cmp_len; len -= cmp_len; } *is_same = same; return 0; out_error: return error; } /* * Check that the two inodes are eligible for cloning, the ranges make * sense, and then flush all dirty data. Caller must ensure that the * inodes have been locked against any other modifications. * * If there's an error, then the usual negative error code is returned. * Otherwise returns 0 with *len set to the request length. */ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *dax_read_ops) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); bool same_inode = (inode_in == inode_out); int ret; /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Don't reflink dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; /* Zero length dedupe exits immediately; reflink goes to EOF. */ if (*len == 0) { loff_t isize = i_size_read(inode_in); if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize) return 0; if (pos_in > isize) return -EINVAL; *len = isize - pos_in; if (*len == 0) return 0; } /* Check that we don't violate system file offset limits. */ ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len, remap_flags); if (ret || *len == 0) return ret; /* Wait for the completion of any pending IOs on both files */ inode_dio_wait(inode_in); if (!same_inode) inode_dio_wait(inode_out); ret = filemap_write_and_wait_range(inode_in->i_mapping, pos_in, pos_in + *len - 1); if (ret) return ret; ret = filemap_write_and_wait_range(inode_out->i_mapping, pos_out, pos_out + *len - 1); if (ret) return ret; /* * Check that the extents are the same. */ if (remap_flags & REMAP_FILE_DEDUP) { bool is_same = false; if (!IS_DAX(inode_in)) ret = vfs_dedupe_file_range_compare(file_in, pos_in, file_out, pos_out, *len, &is_same); else if (dax_read_ops) ret = dax_dedupe_file_range_compare(inode_in, pos_in, inode_out, pos_out, *len, &is_same, dax_read_ops); else return -EINVAL; if (ret) return ret; if (!is_same) return -EBADE; } ret = generic_remap_check_len(inode_in, inode_out, pos_out, len, remap_flags); if (ret || *len == 0) return ret; /* If can't alter the file contents, we're done. */ if (!(remap_flags & REMAP_FILE_DEDUP)) ret = file_modified(file_out); return ret; } int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags) { return __generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, len, remap_flags, NULL); } EXPORT_SYMBOL(generic_remap_file_range_prep); loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags) { loff_t ret; WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP); if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) return -EXDEV; ret = generic_file_rw_checks(file_in, file_out); if (ret < 0) return ret; if (!file_in->f_op->remap_file_range) return -EOPNOTSUPP; ret = remap_verify_area(file_in, pos_in, len, false); if (ret) return ret; ret = remap_verify_area(file_out, pos_out, len, true); if (ret) return ret; file_start_write(file_out); ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, len, remap_flags); file_end_write(file_out); if (ret < 0) return ret; fsnotify_access(file_in); fsnotify_modify(file_out); return ret; } EXPORT_SYMBOL(vfs_clone_file_range); /* Check whether we are allowed to dedupe the destination file */ static bool may_dedupe_file(struct file *file) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct inode *inode = file_inode(file); if (capable(CAP_SYS_ADMIN)) return true; if (file->f_mode & FMODE_WRITE) return true; if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), current_fsuid())) return true; if (!inode_permission(idmap, inode, MAY_WRITE)) return true; return false; } loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags) { loff_t ret; WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_CAN_SHORTEN)); /* * This is redundant if called from vfs_dedupe_file_range(), but other * callers need it and it's not performance sesitive... */ ret = remap_verify_area(src_file, src_pos, len, false); if (ret) return ret; ret = remap_verify_area(dst_file, dst_pos, len, true); if (ret) return ret; /* * This needs to be called after remap_verify_area() because of * sb_start_write() and before may_dedupe_file() because the mount's * MAY_WRITE need to be checked with mnt_get_write_access_file() held. */ ret = mnt_want_write_file(dst_file); if (ret) return ret; ret = -EPERM; if (!may_dedupe_file(dst_file)) goto out_drop_write; ret = -EXDEV; if (file_inode(src_file)->i_sb != file_inode(dst_file)->i_sb) goto out_drop_write; ret = -EISDIR; if (S_ISDIR(file_inode(dst_file)->i_mode)) goto out_drop_write; ret = -EINVAL; if (!dst_file->f_op->remap_file_range) goto out_drop_write; if (len == 0) { ret = 0; goto out_drop_write; } ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file, dst_pos, len, remap_flags | REMAP_FILE_DEDUP); out_drop_write: mnt_drop_write_file(dst_file); return ret; } EXPORT_SYMBOL(vfs_dedupe_file_range_one); int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) { struct file_dedupe_range_info *info; struct inode *src = file_inode(file); u64 off; u64 len; int i; int ret; u16 count = same->dest_count; loff_t deduped; if (!(file->f_mode & FMODE_READ)) return -EINVAL; if (same->reserved1 || same->reserved2) return -EINVAL; off = same->src_offset; len = same->src_length; if (S_ISDIR(src->i_mode)) return -EISDIR; if (!S_ISREG(src->i_mode)) return -EINVAL; if (!file->f_op->remap_file_range) return -EOPNOTSUPP; ret = remap_verify_area(file, off, len, false); if (ret < 0) return ret; ret = 0; if (off + len > i_size_read(src)) return -EINVAL; /* Arbitrary 1G limit on a single dedupe request, can be raised. */ len = min_t(u64, len, 1 << 30); /* pre-format output fields to sane values */ for (i = 0; i < count; i++) { same->info[i].bytes_deduped = 0ULL; same->info[i].status = FILE_DEDUPE_RANGE_SAME; } for (i = 0, info = same->info; i < count; i++, info++) { CLASS(fd, dst_fd)(info->dest_fd); if (fd_empty(dst_fd)) { info->status = -EBADF; goto next_loop; } if (info->reserved) { info->status = -EINVAL; goto next_loop; } deduped = vfs_dedupe_file_range_one(file, off, fd_file(dst_fd), info->dest_offset, len, REMAP_FILE_CAN_SHORTEN); if (deduped == -EBADE) info->status = FILE_DEDUPE_RANGE_DIFFERS; else if (deduped < 0) info->status = deduped; else info->bytes_deduped = len; next_loop: if (fatal_signal_pending(current)) break; } return ret; } EXPORT_SYMBOL(vfs_dedupe_file_range); |
| 451 449 447 169 451 223 221 455 453 5 424 411 415 144 418 78 77 420 417 22 5 5 5 5 5 5 5 5 9 9 6 3 6 13 13 9 4 9 22 13 9 12 12 12 12 12 125 3 1 115 7 2 445 444 445 7 6 75 189 319 4 430 2 446 448 430 9 432 612 2 4 3 466 583 547 16 277 281 2 9 5 73 24 35 3 590 27 27 630 1 2 2 2 2 597 580 624 681 3 677 25 19 16 24 17 2 409 4 412 1 410 5 2 392 165 196 240 412 413 392 11 403 26 5 22 3 17 682 1 682 655 615 39 3 3 124 112 110 23 38 19 23 36 92 78 14 101 51 39 19 94 9 85 51 51 2 49 48 1 39 2 37 19 3 16 8 3 16 16 18 18 9 9 9 9 4 4 4 4 4 13 12 13 12 13 12 12 13 6 13 12 3 5 5 5 5 5 5 5 8 8 8 8 8 8 8 7 153 154 8 146 154 8 146 154 8 146 8 9 9 9 513 295 514 512 483 275 486 154 9 9 9 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * x_tables core - Backend for {ip,ip6,arp}_tables * * Copyright (C) 2006-2006 Harald Welte <laforge@netfilter.org> * Copyright (C) 2006-2012 Patrick McHardy <kaber@trash.net> * * Based on existing ip_tables code which is * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/string.h> #include <linux/vmalloc.h> #include <linux/mutex.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/audit.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_arp.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_arp/arp_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module"); #define XT_PCPU_BLOCK_SIZE 4096 #define XT_MAX_TABLE_SIZE (512 * 1024 * 1024) struct xt_template { struct list_head list; /* called when table is needed in the given netns */ int (*table_init)(struct net *net); struct module *me; /* A unique name... */ char name[XT_TABLE_MAXNAMELEN]; }; static struct list_head xt_templates[NFPROTO_NUMPROTO]; struct xt_pernet { struct list_head tables[NFPROTO_NUMPROTO]; /* stash area used during netns exit */ struct list_head dead_tables[NFPROTO_NUMPROTO]; }; struct compat_delta { unsigned int offset; /* offset in kernel */ int delta; /* delta in 32bit user land */ }; struct xt_af { struct mutex mutex; struct list_head match; struct list_head target; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct mutex compat_mutex; struct compat_delta *compat_tab; unsigned int number; /* number of slots in compat_tab[] */ unsigned int cur; /* number of used slots in compat_tab[] */ #endif }; static unsigned int xt_pernet_id __read_mostly; static struct xt_af *xt __read_mostly; static const char *const xt_prefix[NFPROTO_NUMPROTO] = { [NFPROTO_UNSPEC] = "x", [NFPROTO_IPV4] = "ip", [NFPROTO_ARP] = "arp", [NFPROTO_BRIDGE] = "eb", [NFPROTO_IPV6] = "ip6", }; /* Registration hooks for targets. */ int xt_register_target(struct xt_target *target) { u_int8_t af = target->family; mutex_lock(&xt[af].mutex); list_add(&target->list, &xt[af].target); mutex_unlock(&xt[af].mutex); return 0; } EXPORT_SYMBOL(xt_register_target); void xt_unregister_target(struct xt_target *target) { u_int8_t af = target->family; mutex_lock(&xt[af].mutex); list_del(&target->list); mutex_unlock(&xt[af].mutex); } EXPORT_SYMBOL(xt_unregister_target); int xt_register_targets(struct xt_target *target, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = xt_register_target(&target[i]); if (err) goto err; } return err; err: if (i > 0) xt_unregister_targets(target, i); return err; } EXPORT_SYMBOL(xt_register_targets); void xt_unregister_targets(struct xt_target *target, unsigned int n) { while (n-- > 0) xt_unregister_target(&target[n]); } EXPORT_SYMBOL(xt_unregister_targets); int xt_register_match(struct xt_match *match) { u_int8_t af = match->family; mutex_lock(&xt[af].mutex); list_add(&match->list, &xt[af].match); mutex_unlock(&xt[af].mutex); return 0; } EXPORT_SYMBOL(xt_register_match); void xt_unregister_match(struct xt_match *match) { u_int8_t af = match->family; mutex_lock(&xt[af].mutex); list_del(&match->list); mutex_unlock(&xt[af].mutex); } EXPORT_SYMBOL(xt_unregister_match); int xt_register_matches(struct xt_match *match, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = xt_register_match(&match[i]); if (err) goto err; } return err; err: if (i > 0) xt_unregister_matches(match, i); return err; } EXPORT_SYMBOL(xt_register_matches); void xt_unregister_matches(struct xt_match *match, unsigned int n) { while (n-- > 0) xt_unregister_match(&match[n]); } EXPORT_SYMBOL(xt_unregister_matches); /* * These are weird, but module loading must not be done with mutex * held (since they will register), and we have to have a single * function to use. */ /* Find match, grabs ref. Returns ERR_PTR() on error. */ struct xt_match *xt_find_match(u8 af, const char *name, u8 revision) { struct xt_match *m; int err = -ENOENT; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); mutex_lock(&xt[af].mutex); list_for_each_entry(m, &xt[af].match, list) { if (strcmp(m->name, name) == 0) { if (m->revision == revision) { if (try_module_get(m->me)) { mutex_unlock(&xt[af].mutex); return m; } } else err = -EPROTOTYPE; /* Found something. */ } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC) /* Try searching again in the family-independent list */ return xt_find_match(NFPROTO_UNSPEC, name, revision); return ERR_PTR(err); } EXPORT_SYMBOL(xt_find_match); struct xt_match * xt_request_find_match(uint8_t nfproto, const char *name, uint8_t revision) { struct xt_match *match; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); match = xt_find_match(nfproto, name, revision); if (IS_ERR(match)) { request_module("%st_%s", xt_prefix[nfproto], name); match = xt_find_match(nfproto, name, revision); } return match; } EXPORT_SYMBOL_GPL(xt_request_find_match); /* Find target, grabs ref. Returns ERR_PTR() on error. */ static struct xt_target *xt_find_target(u8 af, const char *name, u8 revision) { struct xt_target *t; int err = -ENOENT; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt[af].target, list) { if (strcmp(t->name, name) == 0) { if (t->revision == revision) { if (try_module_get(t->me)) { mutex_unlock(&xt[af].mutex); return t; } } else err = -EPROTOTYPE; /* Found something. */ } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC) /* Try searching again in the family-independent list */ return xt_find_target(NFPROTO_UNSPEC, name, revision); return ERR_PTR(err); } struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision) { struct xt_target *target; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); target = xt_find_target(af, name, revision); if (IS_ERR(target)) { request_module("%st_%s", xt_prefix[af], name); target = xt_find_target(af, name, revision); } return target; } EXPORT_SYMBOL_GPL(xt_request_find_target); static int xt_obj_to_user(u16 __user *psize, u16 size, void __user *pname, const char *name, u8 __user *prev, u8 rev) { if (put_user(size, psize)) return -EFAULT; if (copy_to_user(pname, name, strlen(name) + 1)) return -EFAULT; if (put_user(rev, prev)) return -EFAULT; return 0; } #define XT_OBJ_TO_USER(U, K, TYPE, C_SIZE) \ xt_obj_to_user(&U->u.TYPE##_size, C_SIZE ? : K->u.TYPE##_size, \ U->u.user.name, K->u.kernel.TYPE->name, \ &U->u.user.revision, K->u.kernel.TYPE->revision) int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size) { usersize = usersize ? : size; if (copy_to_user(dst, src, usersize)) return -EFAULT; if (usersize != aligned_size && clear_user(dst + usersize, aligned_size - usersize)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(xt_data_to_user); #define XT_DATA_TO_USER(U, K, TYPE) \ xt_data_to_user(U->data, K->data, \ K->u.kernel.TYPE->usersize, \ K->u.kernel.TYPE->TYPE##size, \ XT_ALIGN(K->u.kernel.TYPE->TYPE##size)) int xt_match_to_user(const struct xt_entry_match *m, struct xt_entry_match __user *u) { return XT_OBJ_TO_USER(u, m, match, 0) || XT_DATA_TO_USER(u, m, match); } EXPORT_SYMBOL_GPL(xt_match_to_user); int xt_target_to_user(const struct xt_entry_target *t, struct xt_entry_target __user *u) { return XT_OBJ_TO_USER(u, t, target, 0) || XT_DATA_TO_USER(u, t, target); } EXPORT_SYMBOL_GPL(xt_target_to_user); static int match_revfn(u8 af, const char *name, u8 revision, int *bestp) { const struct xt_match *m; int have_rev = 0; mutex_lock(&xt[af].mutex); list_for_each_entry(m, &xt[af].match, list) { if (strcmp(m->name, name) == 0) { if (m->revision > *bestp) *bestp = m->revision; if (m->revision == revision) have_rev = 1; } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return match_revfn(NFPROTO_UNSPEC, name, revision, bestp); return have_rev; } static int target_revfn(u8 af, const char *name, u8 revision, int *bestp) { const struct xt_target *t; int have_rev = 0; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt[af].target, list) { if (strcmp(t->name, name) == 0) { if (t->revision > *bestp) *bestp = t->revision; if (t->revision == revision) have_rev = 1; } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return target_revfn(NFPROTO_UNSPEC, name, revision, bestp); return have_rev; } /* Returns true or false (if no such extension at all) */ int xt_find_revision(u8 af, const char *name, u8 revision, int target, int *err) { int have_rev, best = -1; if (target == 1) have_rev = target_revfn(af, name, revision, &best); else have_rev = match_revfn(af, name, revision, &best); /* Nothing at all? Return 0 to try loading module. */ if (best == -1) { *err = -ENOENT; return 0; } *err = best; if (!have_rev) *err = -EPROTONOSUPPORT; return 1; } EXPORT_SYMBOL_GPL(xt_find_revision); static char * textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto) { static const char *const inetbr_names[] = { "PREROUTING", "INPUT", "FORWARD", "OUTPUT", "POSTROUTING", "BROUTING", }; static const char *const arp_names[] = { "INPUT", "FORWARD", "OUTPUT", }; const char *const *names; unsigned int i, max; char *p = buf; bool np = false; int res; names = (nfproto == NFPROTO_ARP) ? arp_names : inetbr_names; max = (nfproto == NFPROTO_ARP) ? ARRAY_SIZE(arp_names) : ARRAY_SIZE(inetbr_names); *p = '\0'; for (i = 0; i < max; ++i) { if (!(mask & (1 << i))) continue; res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]); if (res > 0) { size -= res; p += res; } np = true; } return buf; } /** * xt_check_proc_name - check that name is suitable for /proc file creation * * @name: file name candidate * @size: length of buffer * * some x_tables modules wish to create a file in /proc. * This function makes sure that the name is suitable for this * purpose, it checks that name is NUL terminated and isn't a 'special' * name, like "..". * * returns negative number on error or 0 if name is useable. */ int xt_check_proc_name(const char *name, unsigned int size) { if (name[0] == '\0') return -EINVAL; if (strnlen(name, size) == size) return -ENAMETOOLONG; if (strcmp(name, ".") == 0 || strcmp(name, "..") == 0 || strchr(name, '/')) return -EINVAL; return 0; } EXPORT_SYMBOL(xt_check_proc_name); static int xt_check_match_common(struct xt_mtchk_param *par, unsigned int size, u16 proto, bool inv_proto) { if (XT_ALIGN(par->match->matchsize) != size && par->match->matchsize != -1) { /* * ebt_among is exempt from centralized matchsize checking * because it uses a dynamic-size data set. */ pr_err_ratelimited("%s_tables: %s.%u match: invalid size %u (kernel) != (user) %u\n", xt_prefix[par->family], par->match->name, par->match->revision, XT_ALIGN(par->match->matchsize), size); return -EINVAL; } if (par->match->table != NULL && strcmp(par->match->table, par->table) != 0) { pr_info_ratelimited("%s_tables: %s match: only valid in %s table, not %s\n", xt_prefix[par->family], par->match->name, par->match->table, par->table); return -EINVAL; } /* NFPROTO_UNSPEC implies NF_INET_* hooks which do not overlap with * NF_ARP_IN,OUT,FORWARD, allow explicit extensions with NFPROTO_ARP * support. */ if (par->family == NFPROTO_ARP && par->match->family != NFPROTO_ARP) { pr_info_ratelimited("%s_tables: %s match: not valid for this family\n", xt_prefix[par->family], par->match->name); return -EINVAL; } if (par->match->hooks && (par->hook_mask & ~par->match->hooks) != 0) { char used[64], allow[64]; pr_info_ratelimited("%s_tables: %s match: used from hooks %s, but only valid from %s\n", xt_prefix[par->family], par->match->name, textify_hooks(used, sizeof(used), par->hook_mask, par->family), textify_hooks(allow, sizeof(allow), par->match->hooks, par->family)); return -EINVAL; } if (par->match->proto && (par->match->proto != proto || inv_proto)) { pr_info_ratelimited("%s_tables: %s match: only valid for protocol %u\n", xt_prefix[par->family], par->match->name, par->match->proto); return -EINVAL; } return 0; } static int xt_checkentry_match(struct xt_mtchk_param *par) { int ret; if (par->match->checkentry != NULL) { ret = par->match->checkentry(par); if (ret < 0) return ret; else if (ret > 0) /* Flag up potential errors. */ return -EIO; } return 0; } int xt_check_hooks_match(struct xt_mtchk_param *par) { if (par->match->check_hooks != NULL) return par->match->check_hooks(par); return 0; } EXPORT_SYMBOL_GPL(xt_check_hooks_match); int xt_check_match(struct xt_mtchk_param *par, unsigned int size, u16 proto, bool inv_proto) { int ret; ret = xt_check_match_common(par, size, proto, inv_proto); if (ret < 0) return ret; ret = xt_check_hooks_match(par); if (ret < 0) return ret; return xt_checkentry_match(par); } EXPORT_SYMBOL_GPL(xt_check_match); /** xt_check_entry_match - check that matches end before start of target * * @match: beginning of xt_entry_match * @target: beginning of this rules target (alleged end of matches) * @alignment: alignment requirement of match structures * * Validates that all matches add up to the beginning of the target, * and that each match covers at least the base structure size. * * Return: 0 on success, negative errno on failure. */ static int xt_check_entry_match(const char *match, const char *target, const size_t alignment) { const struct xt_entry_match *pos; int length = target - match; if (length == 0) /* no matches */ return 0; pos = (struct xt_entry_match *)match; do { if ((unsigned long)pos % alignment) return -EINVAL; if (length < (int)sizeof(struct xt_entry_match)) return -EINVAL; if (pos->u.match_size < sizeof(struct xt_entry_match)) return -EINVAL; if (pos->u.match_size > length) return -EINVAL; length -= pos->u.match_size; pos = ((void *)((char *)(pos) + (pos)->u.match_size)); } while (length > 0); return 0; } /** xt_check_table_hooks - check hook entry points are sane * * @info xt_table_info to check * @valid_hooks - hook entry points that we can enter from * * Validates that the hook entry and underflows points are set up. * * Return: 0 on success, negative errno on failure. */ int xt_check_table_hooks(const struct xt_table_info *info, unsigned int valid_hooks) { const char *err = "unsorted underflow"; unsigned int i, max_uflow, max_entry; bool check_hooks = false; BUILD_BUG_ON(ARRAY_SIZE(info->hook_entry) != ARRAY_SIZE(info->underflow)); max_entry = 0; max_uflow = 0; for (i = 0; i < ARRAY_SIZE(info->hook_entry); i++) { if (!(valid_hooks & (1 << i))) continue; if (info->hook_entry[i] == 0xFFFFFFFF) return -EINVAL; if (info->underflow[i] == 0xFFFFFFFF) return -EINVAL; if (check_hooks) { if (max_uflow > info->underflow[i]) goto error; if (max_uflow == info->underflow[i]) { err = "duplicate underflow"; goto error; } if (max_entry > info->hook_entry[i]) { err = "unsorted entry"; goto error; } if (max_entry == info->hook_entry[i]) { err = "duplicate entry"; goto error; } } max_entry = info->hook_entry[i]; max_uflow = info->underflow[i]; check_hooks = true; } return 0; error: pr_err_ratelimited("%s at hook %d\n", err, i); return -EINVAL; } EXPORT_SYMBOL(xt_check_table_hooks); static bool verdict_ok(int verdict) { if (verdict > 0) return true; if (verdict < 0) { int v = -verdict - 1; if (verdict == XT_RETURN) return true; switch (v) { case NF_ACCEPT: return true; case NF_DROP: return true; case NF_QUEUE: return true; default: break; } return false; } return false; } static bool error_tg_ok(unsigned int usersize, unsigned int kernsize, const char *msg, unsigned int msglen) { return usersize == kernsize && strnlen(msg, msglen) < msglen; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta) { struct xt_af *xp = &xt[af]; WARN_ON(!mutex_is_locked(&xt[af].compat_mutex)); if (WARN_ON(!xp->compat_tab)) return -ENOMEM; if (xp->cur >= xp->number) return -EINVAL; if (xp->cur) delta += xp->compat_tab[xp->cur - 1].delta; xp->compat_tab[xp->cur].offset = offset; xp->compat_tab[xp->cur].delta = delta; xp->cur++; return 0; } EXPORT_SYMBOL_GPL(xt_compat_add_offset); void xt_compat_flush_offsets(u_int8_t af) { WARN_ON(!mutex_is_locked(&xt[af].compat_mutex)); if (xt[af].compat_tab) { vfree(xt[af].compat_tab); xt[af].compat_tab = NULL; xt[af].number = 0; xt[af].cur = 0; } } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); int xt_compat_calc_jump(u_int8_t af, unsigned int offset) { struct compat_delta *tmp = xt[af].compat_tab; int mid, left = 0, right = xt[af].cur - 1; while (left <= right) { mid = (left + right) >> 1; if (offset > tmp[mid].offset) left = mid + 1; else if (offset < tmp[mid].offset) right = mid - 1; else return mid ? tmp[mid - 1].delta : 0; } return left ? tmp[left - 1].delta : 0; } EXPORT_SYMBOL_GPL(xt_compat_calc_jump); int xt_compat_init_offsets(u8 af, unsigned int number) { size_t mem; WARN_ON(!mutex_is_locked(&xt[af].compat_mutex)); if (!number || number > (INT_MAX / sizeof(struct compat_delta))) return -EINVAL; if (WARN_ON(xt[af].compat_tab)) return -EINVAL; mem = sizeof(struct compat_delta) * number; if (mem > XT_MAX_TABLE_SIZE) return -ENOMEM; xt[af].compat_tab = vmalloc(mem); if (!xt[af].compat_tab) return -ENOMEM; xt[af].number = number; xt[af].cur = 0; return 0; } EXPORT_SYMBOL(xt_compat_init_offsets); int xt_compat_match_offset(const struct xt_match *match) { u_int16_t csize = match->compatsize ? : match->matchsize; return XT_ALIGN(match->matchsize) - COMPAT_XT_ALIGN(csize); } EXPORT_SYMBOL_GPL(xt_compat_match_offset); void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, unsigned int *size) { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m; int off = xt_compat_match_offset(match); u_int16_t msize = cm->u.user.match_size; char name[sizeof(m->u.user.name)]; m = *dstptr; memcpy(m, cm, sizeof(*cm)); if (match->compat_from_user) match->compat_from_user(m->data, cm->data); else memcpy(m->data, cm->data, msize - sizeof(*cm)); msize += off; m->u.user.match_size = msize; strscpy(name, match->name, sizeof(name)); module_put(match->me); strscpy_pad(m->u.user.name, name, sizeof(m->u.user.name)); *size += off; *dstptr += msize; } EXPORT_SYMBOL_GPL(xt_compat_match_from_user); #define COMPAT_XT_DATA_TO_USER(U, K, TYPE, C_SIZE) \ xt_data_to_user(U->data, K->data, \ K->u.kernel.TYPE->usersize, \ C_SIZE, \ COMPAT_XT_ALIGN(C_SIZE)) int xt_compat_match_to_user(const struct xt_entry_match *m, void __user **dstptr, unsigned int *size) { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match __user *cm = *dstptr; int off = xt_compat_match_offset(match); u_int16_t msize = m->u.user.match_size - off; if (XT_OBJ_TO_USER(cm, m, match, msize)) return -EFAULT; if (match->compat_to_user) { if (match->compat_to_user((void __user *)cm->data, m->data)) return -EFAULT; } else { if (COMPAT_XT_DATA_TO_USER(cm, m, match, msize - sizeof(*cm))) return -EFAULT; } *size -= off; *dstptr += msize; return 0; } EXPORT_SYMBOL_GPL(xt_compat_match_to_user); /* non-compat version may have padding after verdict */ struct compat_xt_standard_target { /* Must be last as it ends in a flexible-array member. */ TRAILING_OVERLAP(struct compat_xt_entry_target, t, data, compat_uint_t verdict; ); }; struct compat_xt_error_target { /* Must be last as it ends in a flexible-array member. */ TRAILING_OVERLAP(struct compat_xt_entry_target, t, data, char errorname[XT_FUNCTION_MAXNAMELEN]; ); }; int xt_compat_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset) { long size_of_base_struct = elems - (const char *)base; const struct compat_xt_entry_target *t; const char *e = base; if (target_offset < size_of_base_struct) return -EINVAL; if (target_offset + sizeof(*t) > next_offset) return -EINVAL; t = (void *)(e + target_offset); if (t->u.target_size < sizeof(*t)) return -EINVAL; if (target_offset + t->u.target_size > next_offset) return -EINVAL; if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0) { const struct compat_xt_standard_target *st = (const void *)t; if (COMPAT_XT_ALIGN(target_offset + sizeof(*st)) != next_offset) return -EINVAL; if (!verdict_ok(st->verdict)) return -EINVAL; } else if (strcmp(t->u.user.name, XT_ERROR_TARGET) == 0) { const struct compat_xt_error_target *et = (const void *)t; if (!error_tg_ok(t->u.target_size, sizeof(*et), et->errorname, sizeof(et->errorname))) return -EINVAL; } /* compat_xt_entry match has less strict alignment requirements, * otherwise they are identical. In case of padding differences * we need to add compat version of xt_check_entry_match. */ BUILD_BUG_ON(sizeof(struct compat_xt_entry_match) != sizeof(struct xt_entry_match)); return xt_check_entry_match(elems, base + target_offset, __alignof__(struct compat_xt_entry_match)); } EXPORT_SYMBOL(xt_compat_check_entry_offsets); #endif /* CONFIG_NETFILTER_XTABLES_COMPAT */ /** * xt_check_entry_offsets - validate arp/ip/ip6t_entry * * @base: pointer to arp/ip/ip6t_entry * @elems: pointer to first xt_entry_match, i.e. ip(6)t_entry->elems * @target_offset: the arp/ip/ip6_t->target_offset * @next_offset: the arp/ip/ip6_t->next_offset * * validates that target_offset and next_offset are sane and that all * match sizes (if any) align with the target offset. * * This function does not validate the targets or matches themselves, it * only tests that all the offsets and sizes are correct, that all * match structures are aligned, and that the last structure ends where * the target structure begins. * * Also see xt_compat_check_entry_offsets for CONFIG_NETFILTER_XTABLES_COMPAT version. * * The arp/ip/ip6t_entry structure @base must have passed following tests: * - it must point to a valid memory location * - base to base + next_offset must be accessible, i.e. not exceed allocated * length. * * A well-formed entry looks like this: * * ip(6)t_entry match [mtdata] match [mtdata] target [tgdata] ip(6)t_entry * e->elems[]-----' | | * matchsize | | * matchsize | | * | | * target_offset---------------------------------' | * next_offset---------------------------------------------------' * * elems[]: flexible array member at end of ip(6)/arpt_entry struct. * This is where matches (if any) and the target reside. * target_offset: beginning of target. * next_offset: start of the next rule; also: size of this rule. * Since targets have a minimum size, target_offset + minlen <= next_offset. * * Every match stores its size, sum of sizes must not exceed target_offset. * * Return: 0 on success, negative errno on failure. */ int xt_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset) { long size_of_base_struct = elems - (const char *)base; const struct xt_entry_target *t; const char *e = base; /* target start is within the ip/ip6/arpt_entry struct */ if (target_offset < size_of_base_struct) return -EINVAL; if (target_offset + sizeof(*t) > next_offset) return -EINVAL; t = (void *)(e + target_offset); if (t->u.target_size < sizeof(*t)) return -EINVAL; if (target_offset + t->u.target_size > next_offset) return -EINVAL; if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0) { const struct xt_standard_target *st = (const void *)t; if (XT_ALIGN(target_offset + sizeof(*st)) != next_offset) return -EINVAL; if (!verdict_ok(st->verdict)) return -EINVAL; } else if (strcmp(t->u.user.name, XT_ERROR_TARGET) == 0) { const struct xt_error_target *et = (const void *)t; if (!error_tg_ok(t->u.target_size, sizeof(*et), et->errorname, sizeof(et->errorname))) return -EINVAL; } return xt_check_entry_match(elems, base + target_offset, __alignof__(struct xt_entry_match)); } EXPORT_SYMBOL(xt_check_entry_offsets); /** * xt_alloc_entry_offsets - allocate array to store rule head offsets * * @size: number of entries * * Return: NULL or zeroed kmalloc'd or vmalloc'd array */ unsigned int *xt_alloc_entry_offsets(unsigned int size) { if (size > XT_MAX_TABLE_SIZE / sizeof(unsigned int)) return NULL; return kvcalloc(size, sizeof(unsigned int), GFP_KERNEL); } EXPORT_SYMBOL(xt_alloc_entry_offsets); /** * xt_find_jump_offset - check if target is a valid jump offset * * @offsets: array containing all valid rule start offsets of a rule blob * @target: the jump target to search for * @size: entries in @offset */ bool xt_find_jump_offset(const unsigned int *offsets, unsigned int target, unsigned int size) { int m, low = 0, hi = size; while (hi > low) { m = (low + hi) / 2u; if (offsets[m] > target) hi = m; else if (offsets[m] < target) low = m + 1; else return true; } return false; } EXPORT_SYMBOL(xt_find_jump_offset); static int xt_check_target_common(struct xt_tgchk_param *par, unsigned int size, u16 proto, bool inv_proto) { if (XT_ALIGN(par->target->targetsize) != size) { pr_err_ratelimited("%s_tables: %s.%u target: invalid size %u (kernel) != (user) %u\n", xt_prefix[par->family], par->target->name, par->target->revision, XT_ALIGN(par->target->targetsize), size); return -EINVAL; } if (par->target->table != NULL && strcmp(par->target->table, par->table) != 0) { pr_info_ratelimited("%s_tables: %s target: only valid in %s table, not %s\n", xt_prefix[par->family], par->target->name, par->target->table, par->table); return -EINVAL; } /* NFPROTO_UNSPEC implies NF_INET_* hooks which do not overlap with * NF_ARP_IN,OUT,FORWARD, allow explicit extensions with NFPROTO_ARP * support. */ if (par->family == NFPROTO_ARP && par->target->family != NFPROTO_ARP) { pr_info_ratelimited("%s_tables: %s target: not valid for this family\n", xt_prefix[par->family], par->target->name); return -EINVAL; } if (par->target->hooks && (par->hook_mask & ~par->target->hooks) != 0) { char used[64], allow[64]; pr_info_ratelimited("%s_tables: %s target: used from hooks %s, but only usable from %s\n", xt_prefix[par->family], par->target->name, textify_hooks(used, sizeof(used), par->hook_mask, par->family), textify_hooks(allow, sizeof(allow), par->target->hooks, par->family)); return -EINVAL; } if (par->target->proto && (par->target->proto != proto || inv_proto)) { pr_info_ratelimited("%s_tables: %s target: only valid for protocol %u\n", xt_prefix[par->family], par->target->name, par->target->proto); return -EINVAL; } return 0; } int xt_check_hooks_target(struct xt_tgchk_param *par) { if (par->target->check_hooks != NULL) return par->target->check_hooks(par); return 0; } EXPORT_SYMBOL_GPL(xt_check_hooks_target); static int xt_checkentry_target(struct xt_tgchk_param *par) { int ret; if (par->target->checkentry != NULL) { ret = par->target->checkentry(par); if (ret < 0) return ret; else if (ret > 0) /* Flag up potential errors. */ return -EIO; } return 0; } int xt_check_target(struct xt_tgchk_param *par, unsigned int size, u16 proto, bool inv_proto) { int ret; ret = xt_check_target_common(par, size, proto, inv_proto); if (ret < 0) return ret; ret = xt_check_hooks_target(par); if (ret < 0) return ret; return xt_checkentry_target(par); } EXPORT_SYMBOL_GPL(xt_check_target); /** * xt_copy_counters - copy counters and metadata from a sockptr_t * * @arg: src sockptr * @len: alleged size of userspace memory * @info: where to store the xt_counters_info metadata * * Copies counter meta data from @user and stores it in @info. * * vmallocs memory to hold the counters, then copies the counter data * from @user to the new memory and returns a pointer to it. * * If called from a compat syscall, @info gets converted automatically to the * 64bit representation. * * The metadata associated with the counters is stored in @info. * * Return: returns pointer that caller has to test via IS_ERR(). * If IS_ERR is false, caller has to vfree the pointer. */ void *xt_copy_counters(sockptr_t arg, unsigned int len, struct xt_counters_info *info) { size_t offset; void *mem; u64 size; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) { /* structures only differ in size due to alignment */ struct compat_xt_counters_info compat_tmp; if (len <= sizeof(compat_tmp)) return ERR_PTR(-EINVAL); len -= sizeof(compat_tmp); if (copy_from_sockptr(&compat_tmp, arg, sizeof(compat_tmp)) != 0) return ERR_PTR(-EFAULT); memcpy(info->name, compat_tmp.name, sizeof(info->name) - 1); info->num_counters = compat_tmp.num_counters; offset = sizeof(compat_tmp); } else #endif { if (len <= sizeof(*info)) return ERR_PTR(-EINVAL); len -= sizeof(*info); if (copy_from_sockptr(info, arg, sizeof(*info)) != 0) return ERR_PTR(-EFAULT); offset = sizeof(*info); } info->name[sizeof(info->name) - 1] = '\0'; size = sizeof(struct xt_counters); size *= info->num_counters; if (size != (u64)len) return ERR_PTR(-EINVAL); mem = vmalloc(len); if (!mem) return ERR_PTR(-ENOMEM); if (copy_from_sockptr_offset(mem, arg, offset, len) == 0) return mem; vfree(mem); return ERR_PTR(-EFAULT); } EXPORT_SYMBOL_GPL(xt_copy_counters); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT int xt_compat_target_offset(const struct xt_target *target) { u_int16_t csize = target->compatsize ? : target->targetsize; return XT_ALIGN(target->targetsize) - COMPAT_XT_ALIGN(csize); } EXPORT_SYMBOL_GPL(xt_compat_target_offset); void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, unsigned int *size) { const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t; int off = xt_compat_target_offset(target); u_int16_t tsize = ct->u.user.target_size; char name[sizeof(t->u.user.name)]; t = *dstptr; memcpy(t, ct, sizeof(*ct)); if (target->compat_from_user) target->compat_from_user(t->data, ct->data); else unsafe_memcpy(t->data, ct->data, tsize - sizeof(*ct), /* UAPI 0-sized destination */); tsize += off; t->u.user.target_size = tsize; strscpy(name, target->name, sizeof(name)); module_put(target->me); strscpy_pad(t->u.user.name, name, sizeof(t->u.user.name)); *size += off; *dstptr += tsize; } EXPORT_SYMBOL_GPL(xt_compat_target_from_user); int xt_compat_target_to_user(const struct xt_entry_target *t, void __user **dstptr, unsigned int *size) { const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target __user *ct = *dstptr; int off = xt_compat_target_offset(target); u_int16_t tsize = t->u.user.target_size - off; if (XT_OBJ_TO_USER(ct, t, target, tsize)) return -EFAULT; if (target->compat_to_user) { if (target->compat_to_user((void __user *)ct->data, t->data)) return -EFAULT; } else { if (COMPAT_XT_DATA_TO_USER(ct, t, target, tsize - sizeof(*ct))) return -EFAULT; } *size -= off; *dstptr += tsize; return 0; } EXPORT_SYMBOL_GPL(xt_compat_target_to_user); #endif struct xt_table_info *xt_alloc_table_info(unsigned int size) { struct xt_table_info *info = NULL; size_t sz = sizeof(*info) + size; if (sz < sizeof(*info) || sz >= XT_MAX_TABLE_SIZE) return NULL; info = kvmalloc(sz, GFP_KERNEL_ACCOUNT); if (!info) return NULL; memset(info, 0, sizeof(*info)); info->size = size; return info; } EXPORT_SYMBOL(xt_alloc_table_info); void xt_free_table_info(struct xt_table_info *info) { int cpu; if (info->jumpstack != NULL) { for_each_possible_cpu(cpu) kvfree(info->jumpstack[cpu]); kvfree(info->jumpstack); } kvfree(info); } EXPORT_SYMBOL(xt_free_table_info); struct xt_table *xt_find_table(struct net *net, u8 af, const char *name) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct xt_table *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_net->tables[af], list) { if (strcmp(t->name, name) == 0) { mutex_unlock(&xt[af].mutex); return t; } } mutex_unlock(&xt[af].mutex); return NULL; } EXPORT_SYMBOL(xt_find_table); /* Find table by name, grabs mutex & ref. Returns ERR_PTR on error. */ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct module *owner = NULL; struct xt_template *tmpl; struct xt_table *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0 && try_module_get(t->me)) return t; /* Table doesn't exist in this netns, check larval list */ list_for_each_entry(tmpl, &xt_templates[af], list) { int err; if (strcmp(tmpl->name, name)) continue; if (!try_module_get(tmpl->me)) goto out; owner = tmpl->me; mutex_unlock(&xt[af].mutex); err = tmpl->table_init(net); if (err < 0) { module_put(owner); return ERR_PTR(err); } mutex_lock(&xt[af].mutex); break; } /* and once again: */ list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0 && owner == t->me) return t; module_put(owner); out: mutex_unlock(&xt[af].mutex); return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(xt_find_table_lock); struct xt_table *xt_request_find_table_lock(struct net *net, u_int8_t af, const char *name) { struct xt_table *t = xt_find_table_lock(net, af, name); #ifdef CONFIG_MODULES if (IS_ERR(t)) { int err = request_module("%stable_%s", xt_prefix[af], name); if (err < 0) return ERR_PTR(err); t = xt_find_table_lock(net, af, name); } #endif return t; } EXPORT_SYMBOL_GPL(xt_request_find_table_lock); void xt_table_unlock(struct xt_table *table) { mutex_unlock(&xt[table->af].mutex); } EXPORT_SYMBOL_GPL(xt_table_unlock); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT void xt_compat_lock(u_int8_t af) { mutex_lock(&xt[af].compat_mutex); } EXPORT_SYMBOL_GPL(xt_compat_lock); void xt_compat_unlock(u_int8_t af) { mutex_unlock(&xt[af].compat_mutex); } EXPORT_SYMBOL_GPL(xt_compat_unlock); #endif struct static_key xt_tee_enabled __read_mostly; EXPORT_SYMBOL_GPL(xt_tee_enabled); #ifdef CONFIG_NETFILTER_XTABLES_LEGACY DEFINE_PER_CPU(seqcount_t, xt_recseq); EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq); static int xt_jumpstack_alloc(struct xt_table_info *i) { unsigned int size; int cpu; size = sizeof(void **) * nr_cpu_ids; if (size > PAGE_SIZE) i->jumpstack = kvzalloc(size, GFP_KERNEL); else i->jumpstack = kzalloc(size, GFP_KERNEL); if (i->jumpstack == NULL) return -ENOMEM; /* ruleset without jumps -- no stack needed */ if (i->stacksize == 0) return 0; /* Jumpstack needs to be able to record two full callchains, one * from the first rule set traversal, plus one table reentrancy * via -j TEE without clobbering the callchain that brought us to * TEE target. * * This is done by allocating two jumpstacks per cpu, on reentry * the upper half of the stack is used. * * see the jumpstack setup in ipt_do_table() for more details. */ size = sizeof(void *) * i->stacksize * 2u; for_each_possible_cpu(cpu) { i->jumpstack[cpu] = kvmalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); if (i->jumpstack[cpu] == NULL) /* * Freeing will be done later on by the callers. The * chain is: xt_replace_table -> __do_replace -> * do_replace -> xt_free_table_info. */ return -ENOMEM; } return 0; } struct xt_counters *xt_counters_alloc(unsigned int counters) { struct xt_counters *mem; if (counters == 0 || counters > INT_MAX / sizeof(*mem)) return NULL; counters *= sizeof(*mem); if (counters > XT_MAX_TABLE_SIZE) return NULL; return vzalloc(counters); } EXPORT_SYMBOL(xt_counters_alloc); static struct xt_table_info * do_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error) { struct xt_table_info *private; unsigned int cpu; int ret; ret = xt_jumpstack_alloc(newinfo); if (ret < 0) { *error = ret; return NULL; } /* Do the substitution. */ local_bh_disable(); private = table->private; /* Check inside lock: is the old number correct? */ if (num_counters != private->number) { pr_debug("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); local_bh_enable(); *error = -EAGAIN; return NULL; } newinfo->initial_entries = private->initial_entries; /* * Ensure contents of newinfo are visible before assigning to * private. */ smp_wmb(); table->private = newinfo; /* make sure all cpus see new ->private value */ smp_mb(); /* * Even though table entries have now been swapped, other CPU's * may still be using the old entries... */ local_bh_enable(); /* ... so wait for even xt_recseq on all cpus */ for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); u32 seq = raw_read_seqcount(s); if (seq & 1) { do { cond_resched(); cpu_relax(); } while (seq == raw_read_seqcount(s)); } } return private; } struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error) { struct xt_table_info *private; private = do_replace_table(table, num_counters, newinfo, error); if (private) audit_log_nfcfg(table->name, table->af, private->number, AUDIT_XT_OP_REPLACE, GFP_KERNEL); return private; } EXPORT_SYMBOL_GPL(xt_replace_table); struct xt_table *xt_register_table(struct net *net, const struct xt_table *input_table, const struct nf_hook_ops *template_ops, struct xt_table_info *bootstrap, struct xt_table_info *newinfo) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct xt_table *t, *table = NULL; struct nf_hook_ops *ops = NULL; struct xt_table_info *private; unsigned int num_ops; int ret = -EINVAL; num_ops = hweight32(input_table->valid_hooks); if (num_ops == 0) goto out; ret = -ENOMEM; if (template_ops) { ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) goto out; } /* Don't add one object to multiple lists. */ table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL); if (!table) goto out; mutex_lock(&xt[table->af].mutex); /* Don't autoload: we'd eat our tail... */ list_for_each_entry(t, &xt_net->tables[table->af], list) { if (strcmp(t->name, table->name) == 0) { ret = -EEXIST; goto unlock; } } /* Simplifies replace_table code. */ table->private = bootstrap; if (!do_replace_table(table, 0, newinfo, &ret)) goto unlock; private = table->private; pr_debug("table->private->number = %u\n", private->number); /* save number of initial entries */ private->initial_entries = private->number; if (ops) { int i; for (i = 0; i < num_ops; i++) ops[i].priv = table; ret = nf_register_net_hooks(net, ops, num_ops); if (ret != 0) { mutex_unlock(&xt[table->af].mutex); /* nf_register_net_hooks() might have published a * base chain before internal error unwind. */ synchronize_rcu(); goto out; } table->ops = ops; } audit_log_nfcfg(table->name, table->af, private->number, AUDIT_XT_OP_REGISTER, GFP_KERNEL); list_add(&table->list, &xt_net->tables[table->af]); mutex_unlock(&xt[table->af].mutex); return table; unlock: mutex_unlock(&xt[table->af].mutex); out: kfree(table); kfree(ops); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(xt_register_table); /** * xt_unregister_table_pre_exit - pre-shutdown unregister of a table * @net: network namespace * @af: address family (e.g., NFPROTO_IPV4, NFPROTO_IPV6) * @name: name of the table to unregister * * Unregisters the specified netfilter table from the given network namespace * and also unregisters the hooks from netfilter core: no new packets will be * processed. * * This must be called prior to xt_unregister_table_exit() from the pernet * .pre_exit callback. After this call, the table is no longer visible to * the get/setsockopt path. In case of rmmod, module exit path must have * called xt_unregister_template() prior to unregistering pernet ops to * prevent re-instantiation of the table. * * See also: xt_unregister_table_exit() */ void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct xt_table *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_net->tables[af], list) { if (strcmp(t->name, name) == 0) { list_move(&t->list, &xt_net->dead_tables[af]); mutex_unlock(&xt[af].mutex); if (t->ops) /* nat table registers with nat core, t->ops is NULL. */ nf_unregister_net_hooks(net, t->ops, hweight32(t->valid_hooks)); return; } } mutex_unlock(&xt[af].mutex); } EXPORT_SYMBOL(xt_unregister_table_pre_exit); /** * xt_unregister_table_exit - remove a table during namespace teardown * @net: the network namespace from which to unregister the table * @af: address family (e.g., NFPROTO_IPV4, NFPROTO_IPV6) * @name: name of the table to unregister * * Completes the unregister process for a table. This must be called from * the pernet ops .exit callback. This is the second stage after * xt_unregister_table_pre_exit(). * * pair with xt_unregister_table_pre_exit() during namespace shutdown. * * Return: the unregistered table or NULL if the table was never * instantiated. The caller needs to kfree() the table after it * has removed the family specific matches/targets. */ struct xt_table *xt_unregister_table_exit(struct net *net, u8 af, const char *name) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct xt_table *table; mutex_lock(&xt[af].mutex); list_for_each_entry(table, &xt_net->dead_tables[af], list) { struct nf_hook_ops *ops = NULL; if (strcmp(table->name, name) != 0) continue; list_del(&table->list); audit_log_nfcfg(table->name, table->af, table->private->number, AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); swap(table->ops, ops); mutex_unlock(&xt[af].mutex); kfree(ops); return table; } mutex_unlock(&xt[af].mutex); return NULL; } EXPORT_SYMBOL_GPL(xt_unregister_table_exit); #endif #ifdef CONFIG_PROC_FS static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos) { u8 af = (unsigned long)pde_data(file_inode(seq->file)); struct net *net = seq_file_net(seq); struct xt_pernet *xt_net; xt_net = net_generic(net, xt_pernet_id); mutex_lock(&xt[af].mutex); return seq_list_start(&xt_net->tables[af], *pos); } static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos) { u8 af = (unsigned long)pde_data(file_inode(seq->file)); struct net *net = seq_file_net(seq); struct xt_pernet *xt_net; xt_net = net_generic(net, xt_pernet_id); return seq_list_next(v, &xt_net->tables[af], pos); } static void xt_table_seq_stop(struct seq_file *seq, void *v) { u_int8_t af = (unsigned long)pde_data(file_inode(seq->file)); mutex_unlock(&xt[af].mutex); } static int xt_table_seq_show(struct seq_file *seq, void *v) { struct xt_table *table = list_entry(v, struct xt_table, list); if (*table->name) seq_printf(seq, "%s\n", table->name); return 0; } static const struct seq_operations xt_table_seq_ops = { .start = xt_table_seq_start, .next = xt_table_seq_next, .stop = xt_table_seq_stop, .show = xt_table_seq_show, }; /* * Traverse state for ip{,6}_{tables,matches} for helping crossing * the multi-AF mutexes. */ struct nf_mttg_trav { struct list_head *head, *curr; uint8_t class; }; enum { MTTG_TRAV_INIT, MTTG_TRAV_NFP_UNSPEC, MTTG_TRAV_NFP_SPEC, MTTG_TRAV_DONE, }; static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, bool is_target) { static const uint8_t next_class[] = { [MTTG_TRAV_NFP_UNSPEC] = MTTG_TRAV_NFP_SPEC, [MTTG_TRAV_NFP_SPEC] = MTTG_TRAV_DONE, }; uint8_t nfproto = (unsigned long)pde_data(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; if (ppos != NULL) ++(*ppos); switch (trav->class) { case MTTG_TRAV_INIT: trav->class = MTTG_TRAV_NFP_UNSPEC; mutex_lock(&xt[NFPROTO_UNSPEC].mutex); trav->head = trav->curr = is_target ? &xt[NFPROTO_UNSPEC].target : &xt[NFPROTO_UNSPEC].match; break; case MTTG_TRAV_NFP_UNSPEC: trav->curr = trav->curr->next; if (trav->curr != trav->head) break; mutex_unlock(&xt[NFPROTO_UNSPEC].mutex); mutex_lock(&xt[nfproto].mutex); trav->head = trav->curr = is_target ? &xt[nfproto].target : &xt[nfproto].match; trav->class = next_class[trav->class]; break; case MTTG_TRAV_NFP_SPEC: trav->curr = trav->curr->next; if (trav->curr != trav->head) break; fallthrough; default: return NULL; } return trav; } static void *xt_mttg_seq_start(struct seq_file *seq, loff_t *pos, bool is_target) { struct nf_mttg_trav *trav = seq->private; unsigned int j; trav->class = MTTG_TRAV_INIT; for (j = 0; j < *pos; ++j) if (xt_mttg_seq_next(seq, NULL, NULL, is_target) == NULL) return NULL; return trav; } static void xt_mttg_seq_stop(struct seq_file *seq, void *v) { uint8_t nfproto = (unsigned long)pde_data(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; switch (trav->class) { case MTTG_TRAV_NFP_UNSPEC: mutex_unlock(&xt[NFPROTO_UNSPEC].mutex); break; case MTTG_TRAV_NFP_SPEC: mutex_unlock(&xt[nfproto].mutex); break; } } static void *xt_match_seq_start(struct seq_file *seq, loff_t *pos) { return xt_mttg_seq_start(seq, pos, false); } static void *xt_match_seq_next(struct seq_file *seq, void *v, loff_t *ppos) { return xt_mttg_seq_next(seq, v, ppos, false); } static int xt_match_seq_show(struct seq_file *seq, void *v) { const struct nf_mttg_trav *trav = seq->private; const struct xt_match *match; switch (trav->class) { case MTTG_TRAV_NFP_UNSPEC: case MTTG_TRAV_NFP_SPEC: if (trav->curr == trav->head) return 0; match = list_entry(trav->curr, struct xt_match, list); if (*match->name) seq_printf(seq, "%s\n", match->name); } return 0; } static const struct seq_operations xt_match_seq_ops = { .start = xt_match_seq_start, .next = xt_match_seq_next, .stop = xt_mttg_seq_stop, .show = xt_match_seq_show, }; static void *xt_target_seq_start(struct seq_file *seq, loff_t *pos) { return xt_mttg_seq_start(seq, pos, true); } static void *xt_target_seq_next(struct seq_file *seq, void *v, loff_t *ppos) { return xt_mttg_seq_next(seq, v, ppos, true); } static int xt_target_seq_show(struct seq_file *seq, void *v) { const struct nf_mttg_trav *trav = seq->private; const struct xt_target *target; switch (trav->class) { case MTTG_TRAV_NFP_UNSPEC: case MTTG_TRAV_NFP_SPEC: if (trav->curr == trav->head) return 0; target = list_entry(trav->curr, struct xt_target, list); if (*target->name) seq_printf(seq, "%s\n", target->name); } return 0; } static const struct seq_operations xt_target_seq_ops = { .start = xt_target_seq_start, .next = xt_target_seq_next, .stop = xt_mttg_seq_stop, .show = xt_target_seq_show, }; #define FORMAT_TABLES "_tables_names" #define FORMAT_MATCHES "_tables_matches" #define FORMAT_TARGETS "_tables_targets" #endif /* CONFIG_PROC_FS */ /** * xt_hook_ops_alloc - set up hooks for a new table * @table: table with metadata needed to set up hooks * @fn: Hook function * * This function will create the nf_hook_ops that the x_table needs * to hand to xt_hook_link_net(). */ struct nf_hook_ops * xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn) { unsigned int hook_mask = table->valid_hooks; uint8_t i, num_hooks = hweight32(hook_mask); uint8_t hooknum; struct nf_hook_ops *ops; if (!num_hooks) return ERR_PTR(-EINVAL); ops = kzalloc_objs(*ops, num_hooks); if (ops == NULL) return ERR_PTR(-ENOMEM); for (i = 0, hooknum = 0; i < num_hooks && hook_mask != 0; hook_mask >>= 1, ++hooknum) { if (!(hook_mask & 1)) continue; ops[i].hook = fn; ops[i].pf = table->af; ops[i].hooknum = hooknum; ops[i].priority = table->priority; ++i; } return ops; } EXPORT_SYMBOL_GPL(xt_hook_ops_alloc); int xt_register_template(const struct xt_table *table, int (*table_init)(struct net *net)) { int ret = -EBUSY, af = table->af; struct xt_template *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_templates[af], list) { if (WARN_ON_ONCE(strcmp(table->name, t->name) == 0)) goto out_unlock; } ret = -ENOMEM; t = kzalloc_obj(*t); if (!t) goto out_unlock; BUILD_BUG_ON(sizeof(t->name) != sizeof(table->name)); strscpy(t->name, table->name, sizeof(t->name)); t->table_init = table_init; t->me = table->me; list_add(&t->list, &xt_templates[af]); ret = 0; out_unlock: mutex_unlock(&xt[af].mutex); return ret; } EXPORT_SYMBOL_GPL(xt_register_template); void xt_unregister_template(const struct xt_table *table) { struct xt_template *t; int af = table->af; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_templates[af], list) { if (strcmp(table->name, t->name)) continue; list_del(&t->list); mutex_unlock(&xt[af].mutex); kfree(t); return; } mutex_unlock(&xt[af].mutex); WARN_ON_ONCE(1); } EXPORT_SYMBOL_GPL(xt_unregister_template); int xt_proto_init(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS char buf[XT_FUNCTION_MAXNAMELEN]; struct proc_dir_entry *proc; kuid_t root_uid; kgid_t root_gid; #endif if (af >= ARRAY_SIZE(xt_prefix)) return -EINVAL; #ifdef CONFIG_PROC_FS root_uid = make_kuid(net->user_ns, 0); root_gid = make_kgid(net->user_ns, 0); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); proc = proc_create_net_data(buf, 0440, net->proc_net, &xt_table_seq_ops, sizeof(struct seq_net_private), (void *)(unsigned long)af); if (!proc) goto out; if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); proc = proc_create_seq_private(buf, 0440, net->proc_net, &xt_match_seq_ops, sizeof(struct nf_mttg_trav), (void *)(unsigned long)af); if (!proc) goto out_remove_tables; if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); proc = proc_create_seq_private(buf, 0440, net->proc_net, &xt_target_seq_ops, sizeof(struct nf_mttg_trav), (void *)(unsigned long)af); if (!proc) goto out_remove_matches; if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); #endif return 0; #ifdef CONFIG_PROC_FS out_remove_matches: strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); out_remove_tables: strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); out: return -1; #endif } EXPORT_SYMBOL_GPL(xt_proto_init); void xt_proto_fini(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS char buf[XT_FUNCTION_MAXNAMELEN]; strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); remove_proc_entry(buf, net->proc_net); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); #endif /*CONFIG_PROC_FS*/ } EXPORT_SYMBOL_GPL(xt_proto_fini); #ifdef CONFIG_NETFILTER_XTABLES_LEGACY /** * xt_percpu_counter_alloc - allocate x_tables rule counter * * @state: pointer to xt_percpu allocation state * @counter: pointer to counter struct inside the ip(6)/arpt_entry struct * * On SMP, the packet counter [ ip(6)t_entry->counters.pcnt ] will then * contain the address of the real (percpu) counter. * * Rule evaluation needs to use xt_get_this_cpu_counter() helper * to fetch the real percpu counter. * * To speed up allocation and improve data locality, a 4kb block is * allocated. Freeing any counter may free an entire block, so all * counters allocated using the same state must be freed at the same * time. * * xt_percpu_counter_alloc_state contains the base address of the * allocated page and the current sub-offset. * * returns false on error. */ bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state, struct xt_counters *counter) { BUILD_BUG_ON(XT_PCPU_BLOCK_SIZE < (sizeof(*counter) * 2)); if (nr_cpu_ids <= 1) return true; if (!state->mem) { state->mem = __alloc_percpu(XT_PCPU_BLOCK_SIZE, XT_PCPU_BLOCK_SIZE); if (!state->mem) return false; } counter->pcnt = (__force unsigned long)(state->mem + state->off); state->off += sizeof(*counter); if (state->off > (XT_PCPU_BLOCK_SIZE - sizeof(*counter))) { state->mem = NULL; state->off = 0; } return true; } EXPORT_SYMBOL_GPL(xt_percpu_counter_alloc); void xt_percpu_counter_free(struct xt_counters *counters) { unsigned long pcnt = counters->pcnt; if (nr_cpu_ids > 1 && (pcnt & (XT_PCPU_BLOCK_SIZE - 1)) == 0) free_percpu((void __percpu *)pcnt); } EXPORT_SYMBOL_GPL(xt_percpu_counter_free); #endif static int __net_init xt_net_init(struct net *net) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; for (i = 0; i < NFPROTO_NUMPROTO; i++) { INIT_LIST_HEAD(&xt_net->tables[i]); INIT_LIST_HEAD(&xt_net->dead_tables[i]); } return 0; } static void __net_exit xt_net_exit(struct net *net) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; for (i = 0; i < NFPROTO_NUMPROTO; i++) { WARN_ON_ONCE(!list_empty(&xt_net->tables[i])); WARN_ON_ONCE(!list_empty(&xt_net->dead_tables[i])); } } static struct pernet_operations xt_net_ops = { .init = xt_net_init, .exit = xt_net_exit, .id = &xt_pernet_id, .size = sizeof(struct xt_pernet), }; static int __init xt_init(void) { unsigned int i; int rv; if (IS_ENABLED(CONFIG_NETFILTER_XTABLES_LEGACY)) { for_each_possible_cpu(i) { seqcount_init(&per_cpu(xt_recseq, i)); } } xt = kzalloc_objs(struct xt_af, NFPROTO_NUMPROTO); if (!xt) return -ENOMEM; for (i = 0; i < NFPROTO_NUMPROTO; i++) { mutex_init(&xt[i].mutex); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT mutex_init(&xt[i].compat_mutex); xt[i].compat_tab = NULL; #endif INIT_LIST_HEAD(&xt[i].target); INIT_LIST_HEAD(&xt[i].match); INIT_LIST_HEAD(&xt_templates[i]); } rv = register_pernet_subsys(&xt_net_ops); if (rv < 0) kfree(xt); return rv; } static void __exit xt_fini(void) { unregister_pernet_subsys(&xt_net_ops); kfree(xt); } module_init(xt_init); module_exit(xt_fini); |
| 8 8 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This is a module which is used for logging packets. */ /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/spinlock.h> #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/ip.h> #include <net/ipv6.h> #include <net/icmp.h> #include <net/udp.h> #include <net/tcp.h> #include <net/route.h> #include <linux/netfilter.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_LOG.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/netfilter/nf_log.h> static unsigned int log_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_log_info *loginfo = par->targinfo; struct net *net = xt_net(par); struct nf_loginfo li; li.type = NF_LOG_TYPE_LOG; li.u.log.level = loginfo->level; li.u.log.logflags = loginfo->logflags; nf_log_packet(net, xt_family(par), xt_hooknum(par), skb, xt_in(par), xt_out(par), &li, "%s", loginfo->prefix); return XT_CONTINUE; } static int log_tg_check(const struct xt_tgchk_param *par) { const struct xt_log_info *loginfo = par->targinfo; int ret; if (par->family != NFPROTO_IPV4 && par->family != NFPROTO_IPV6) return -EINVAL; if (loginfo->level >= 8) { pr_debug("level %u >= 8\n", loginfo->level); return -EINVAL; } if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { pr_debug("prefix is not null-terminated\n"); return -EINVAL; } ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); if (ret != 0 && !par->nft_compat) { request_module("%s", "nf_log_syslog"); ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); } return ret; } static void log_tg_destroy(const struct xt_tgdtor_param *par) { nf_logger_put(par->family, NF_LOG_TYPE_LOG); } static struct xt_target log_tg_regs[] __read_mostly = { { .name = "LOG", .family = NFPROTO_IPV4, .target = log_tg, .targetsize = sizeof(struct xt_log_info), .checkentry = log_tg_check, .destroy = log_tg_destroy, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "LOG", .family = NFPROTO_IPV6, .target = log_tg, .targetsize = sizeof(struct xt_log_info), .checkentry = log_tg_check, .destroy = log_tg_destroy, .me = THIS_MODULE, }, #endif }; static int __init log_tg_init(void) { return xt_register_targets(log_tg_regs, ARRAY_SIZE(log_tg_regs)); } static void __exit log_tg_exit(void) { xt_unregister_targets(log_tg_regs, ARRAY_SIZE(log_tg_regs)); } module_init(log_tg_init); module_exit(log_tg_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_AUTHOR("Jan Rekorajski <baggins@pld.org.pl>"); MODULE_DESCRIPTION("Xtables: IPv4/IPv6 packet logging"); MODULE_ALIAS("ipt_LOG"); MODULE_ALIAS("ip6t_LOG"); MODULE_SOFTDEP("pre: nf_log_syslog"); |
| 11 7 8 3 2449 2448 49 49 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 33 33 1 75 2 66 7 19 2 2 2 2 2 2 2 2 19 2 2 2 2 2 2 2 2 18 4 1 2 3 2 3 3 2 15 4 4 4 4 4 4 5 3 38 5 4 5 4 6 3 40 4 3 3 4 3 4 30 13 4 8 9 8 9 31 9 6 8 7 7 8 15 26 14 8 2 4 20 12 4 2 2 22 6 37 6 28 6 42 1 1 31 8 2 2 4 2 1 1 3 3 3 8 8 8 1 37 1 33 1 2 1 1 154 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 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* gw.c - CAN frame Gateway/Router/Bridge with netlink interface * * Copyright (c) 2019 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include <linux/module.h> #include <linux/init.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/can/gw.h> #include <net/can.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #define CAN_GW_NAME "can-gw" MODULE_DESCRIPTION("PF_CAN netlink gateway"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); MODULE_ALIAS(CAN_GW_NAME); #define CGW_MIN_HOPS 1 #define CGW_MAX_HOPS 6 #define CGW_DEFAULT_HOPS 1 static unsigned char max_hops __read_mostly = CGW_DEFAULT_HOPS; module_param(max_hops, byte, 0444); MODULE_PARM_DESC(max_hops, "maximum " CAN_GW_NAME " routing hops for CAN frames " "(valid values: " __stringify(CGW_MIN_HOPS) "-" __stringify(CGW_MAX_HOPS) " hops, " "default: " __stringify(CGW_DEFAULT_HOPS) ")"); static struct notifier_block notifier; static struct kmem_cache *cgw_cache __read_mostly; /* structure that contains the (on-the-fly) CAN frame modifications */ struct cf_mod { struct { struct canfd_frame and; struct canfd_frame or; struct canfd_frame xor; struct canfd_frame set; } modframe; struct { u8 and; u8 or; u8 xor; u8 set; } modtype; void (*modfunc[MAX_MODFUNCTIONS])(struct canfd_frame *cf, struct cf_mod *mod); /* CAN frame checksum calculation after CAN frame modifications */ struct { struct cgw_csum_xor xor; struct cgw_csum_crc8 crc8; } csum; struct { void (*xor)(struct canfd_frame *cf, struct cgw_csum_xor *xor); void (*crc8)(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8); } csumfunc; u32 uid; }; /* So far we just support CAN -> CAN routing and frame modifications. * * The internal can_can_gw structure contains data and attributes for * a CAN -> CAN gateway job. */ struct can_can_gw { struct can_filter filter; int src_idx; int dst_idx; }; /* list entry for CAN gateways jobs */ struct cgw_job { struct hlist_node list; struct rcu_head rcu; u32 handled_frames; u32 dropped_frames; u32 deleted_frames; struct cf_mod __rcu *cf_mod; union { /* CAN frame data source */ struct net_device *dev; } src; union { /* CAN frame data destination */ struct net_device *dev; } dst; union { struct can_can_gw ccgw; /* tbc */ }; u8 gwtype; u8 limit_hops; u16 flags; }; /* modification functions that are invoked in the hot path in can_can_gw_rcv */ #define MODFUNC(func, op) static void func(struct canfd_frame *cf, \ struct cf_mod *mod) { op ; } MODFUNC(mod_and_id, cf->can_id &= mod->modframe.and.can_id) MODFUNC(mod_and_len, cf->len &= mod->modframe.and.len) MODFUNC(mod_and_flags, cf->flags &= mod->modframe.and.flags) MODFUNC(mod_and_data, *(u64 *)cf->data &= *(u64 *)mod->modframe.and.data) MODFUNC(mod_or_id, cf->can_id |= mod->modframe.or.can_id) MODFUNC(mod_or_len, cf->len |= mod->modframe.or.len) MODFUNC(mod_or_flags, cf->flags |= mod->modframe.or.flags) MODFUNC(mod_or_data, *(u64 *)cf->data |= *(u64 *)mod->modframe.or.data) MODFUNC(mod_xor_id, cf->can_id ^= mod->modframe.xor.can_id) MODFUNC(mod_xor_len, cf->len ^= mod->modframe.xor.len) MODFUNC(mod_xor_flags, cf->flags ^= mod->modframe.xor.flags) MODFUNC(mod_xor_data, *(u64 *)cf->data ^= *(u64 *)mod->modframe.xor.data) MODFUNC(mod_set_id, cf->can_id = mod->modframe.set.can_id) MODFUNC(mod_set_len, cf->len = mod->modframe.set.len) MODFUNC(mod_set_flags, cf->flags = mod->modframe.set.flags) MODFUNC(mod_set_data, *(u64 *)cf->data = *(u64 *)mod->modframe.set.data) static void mod_and_fddata(struct canfd_frame *cf, struct cf_mod *mod) { int i; for (i = 0; i < CANFD_MAX_DLEN; i += 8) *(u64 *)(cf->data + i) &= *(u64 *)(mod->modframe.and.data + i); } static void mod_or_fddata(struct canfd_frame *cf, struct cf_mod *mod) { int i; for (i = 0; i < CANFD_MAX_DLEN; i += 8) *(u64 *)(cf->data + i) |= *(u64 *)(mod->modframe.or.data + i); } static void mod_xor_fddata(struct canfd_frame *cf, struct cf_mod *mod) { int i; for (i = 0; i < CANFD_MAX_DLEN; i += 8) *(u64 *)(cf->data + i) ^= *(u64 *)(mod->modframe.xor.data + i); } static void mod_set_fddata(struct canfd_frame *cf, struct cf_mod *mod) { memcpy(cf->data, mod->modframe.set.data, CANFD_MAX_DLEN); } /* retrieve valid CC DLC value and store it into 'len' */ static void mod_retrieve_ccdlc(struct canfd_frame *cf) { struct can_frame *ccf = (struct can_frame *)cf; /* len8_dlc is only valid if len == CAN_MAX_DLEN */ if (ccf->len != CAN_MAX_DLEN) return; /* do we have a valid len8_dlc value from 9 .. 15 ? */ if (ccf->len8_dlc > CAN_MAX_DLEN && ccf->len8_dlc <= CAN_MAX_RAW_DLC) ccf->len = ccf->len8_dlc; } /* convert valid CC DLC value in 'len' into struct can_frame elements */ static void mod_store_ccdlc(struct canfd_frame *cf) { struct can_frame *ccf = (struct can_frame *)cf; /* clear potential leftovers */ ccf->len8_dlc = 0; /* plain data length 0 .. 8 - that was easy */ if (ccf->len <= CAN_MAX_DLEN) return; /* potentially broken values are caught in can_can_gw_rcv() */ if (ccf->len > CAN_MAX_RAW_DLC) return; /* we have a valid dlc value from 9 .. 15 in ccf->len */ ccf->len8_dlc = ccf->len; ccf->len = CAN_MAX_DLEN; } static void mod_and_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_retrieve_ccdlc(cf); mod_and_len(cf, mod); mod_store_ccdlc(cf); } static void mod_or_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_retrieve_ccdlc(cf); mod_or_len(cf, mod); mod_store_ccdlc(cf); } static void mod_xor_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_retrieve_ccdlc(cf); mod_xor_len(cf, mod); mod_store_ccdlc(cf); } static void mod_set_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_set_len(cf, mod); mod_store_ccdlc(cf); } static void canframecpy(struct canfd_frame *dst, struct can_frame *src) { /* Copy the struct members separately to ensure that no uninitialized * data are copied in the 3 bytes hole of the struct. This is needed * to make easy compares of the data in the struct cf_mod. */ dst->can_id = src->can_id; dst->len = src->len; *(u64 *)dst->data = *(u64 *)src->data; } static void canfdframecpy(struct canfd_frame *dst, struct canfd_frame *src) { /* Copy the struct members separately to ensure that no uninitialized * data are copied in the 2 bytes hole of the struct. This is needed * to make easy compares of the data in the struct cf_mod. */ dst->can_id = src->can_id; dst->flags = src->flags; dst->len = src->len; memcpy(dst->data, src->data, CANFD_MAX_DLEN); } static int cgw_chk_csum_parms(s8 fr, s8 to, s8 re, struct rtcanmsg *r) { s8 dlen = CAN_MAX_DLEN; if (r->flags & CGW_FLAGS_CAN_FD) dlen = CANFD_MAX_DLEN; /* absolute dlc values 0 .. 7 => 0 .. 7, e.g. data [0] * relative to received dlc -1 .. -8 : * e.g. for received dlc = 8 * -1 => index = 7 (data[7]) * -3 => index = 5 (data[5]) * -8 => index = 0 (data[0]) */ if (fr >= -dlen && fr < dlen && to >= -dlen && to < dlen && re >= -dlen && re < dlen) return 0; else return -EINVAL; } static inline int calc_idx(int idx, int rx_len) { if (idx < 0) return rx_len + idx; else return idx; } static void cgw_csum_xor_rel(struct canfd_frame *cf, struct cgw_csum_xor *xor) { int from = calc_idx(xor->from_idx, cf->len); int to = calc_idx(xor->to_idx, cf->len); int res = calc_idx(xor->result_idx, cf->len); u8 val = xor->init_xor_val; int i; if (from < 0 || to < 0 || res < 0) return; if (from <= to) { for (i = from; i <= to; i++) val ^= cf->data[i]; } else { for (i = from; i >= to; i--) val ^= cf->data[i]; } cf->data[res] = val; } static void cgw_csum_xor_pos(struct canfd_frame *cf, struct cgw_csum_xor *xor) { u8 val = xor->init_xor_val; int i; for (i = xor->from_idx; i <= xor->to_idx; i++) val ^= cf->data[i]; cf->data[xor->result_idx] = val; } static void cgw_csum_xor_neg(struct canfd_frame *cf, struct cgw_csum_xor *xor) { u8 val = xor->init_xor_val; int i; for (i = xor->from_idx; i >= xor->to_idx; i--) val ^= cf->data[i]; cf->data[xor->result_idx] = val; } static void cgw_csum_crc8_rel(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8) { int from = calc_idx(crc8->from_idx, cf->len); int to = calc_idx(crc8->to_idx, cf->len); int res = calc_idx(crc8->result_idx, cf->len); u8 crc = crc8->init_crc_val; int i; if (from < 0 || to < 0 || res < 0) return; if (from <= to) { for (i = from; i <= to; i++) crc = crc8->crctab[crc ^ cf->data[i]]; } else { for (i = from; i >= to; i--) crc = crc8->crctab[crc ^ cf->data[i]]; } switch (crc8->profile) { case CGW_CRC8PRF_1U8: crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } cf->data[res] = crc ^ crc8->final_xor_val; } static void cgw_csum_crc8_pos(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8) { u8 crc = crc8->init_crc_val; int i; for (i = crc8->from_idx; i <= crc8->to_idx; i++) crc = crc8->crctab[crc ^ cf->data[i]]; switch (crc8->profile) { case CGW_CRC8PRF_1U8: crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } static void cgw_csum_crc8_neg(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8) { u8 crc = crc8->init_crc_val; int i; for (i = crc8->from_idx; i >= crc8->to_idx; i--) crc = crc8->crctab[crc ^ cf->data[i]]; switch (crc8->profile) { case CGW_CRC8PRF_1U8: crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } /* the receive & process & send function */ static void can_can_gw_rcv(struct sk_buff *skb, void *data) { struct cgw_job *gwj = (struct cgw_job *)data; struct canfd_frame *cf; struct sk_buff *nskb; struct can_skb_ext *csx, *ncsx; struct cf_mod *mod; int modidx = 0; /* process strictly Classic CAN or CAN FD frames */ if (gwj->flags & CGW_FLAGS_CAN_FD) { if (!can_is_canfd_skb(skb)) return; } else { if (!can_is_can_skb(skb)) return; } csx = can_skb_ext_find(skb); if (!csx) return; /* Do not handle CAN frames routed more than 'max_hops' times. * In general we should never catch this delimiter which is intended * to cover a misconfiguration protection (e.g. circular CAN routes). */ if (csx->can_gw_hops >= max_hops) { /* indicate deleted frames due to misconfiguration */ gwj->deleted_frames++; return; } if (!(gwj->dst.dev->flags & IFF_UP)) { gwj->dropped_frames++; return; } /* is sending the skb back to the incoming interface not allowed? */ if (!(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK) && csx->can_iif == gwj->dst.dev->ifindex) return; /* clone the given skb, which has not been done in can_rcv() * * When there is at least one modification function activated, * we need to copy the skb as we want to modify skb->data. */ mod = rcu_dereference(gwj->cf_mod); if (mod->modfunc[0]) nskb = skb_copy(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) { gwj->dropped_frames++; return; } /* the cloned/copied nskb points to the skb extension of the original * skb with an increased refcount. skb_ext_add() creates a copy to * separate the skb extension data to modify the can_gw_hops. */ ncsx = skb_ext_add(nskb, SKB_EXT_CAN); if (!ncsx) { kfree_skb(nskb); gwj->dropped_frames++; return; } /* put the incremented hop counter in the cloned skb */ ncsx->can_gw_hops = csx->can_gw_hops + 1; /* first processing of this CAN frame -> adjust to private hop limit */ if (gwj->limit_hops && ncsx->can_gw_hops == 1) ncsx->can_gw_hops = max_hops - gwj->limit_hops + 1; nskb->dev = gwj->dst.dev; /* pointer to modifiable CAN frame */ cf = (struct canfd_frame *)nskb->data; /* perform preprocessed modification functions if there are any */ while (modidx < MAX_MODFUNCTIONS && mod->modfunc[modidx]) (*mod->modfunc[modidx++])(cf, mod); /* Has the CAN frame been modified? */ if (modidx) { /* get available space for the processed CAN frame type */ int max_len = nskb->len - offsetof(struct canfd_frame, data); /* dlc may have changed, make sure it fits to the CAN frame */ if (cf->len > max_len) { /* delete frame due to misconfiguration */ gwj->deleted_frames++; kfree_skb(nskb); return; } /* check for checksum updates */ if (mod->csumfunc.crc8) (*mod->csumfunc.crc8)(cf, &mod->csum.crc8); if (mod->csumfunc.xor) (*mod->csumfunc.xor)(cf, &mod->csum.xor); } /* clear the skb timestamp if not configured the other way */ if (!(gwj->flags & CGW_FLAGS_CAN_SRC_TSTAMP)) nskb->tstamp = 0; /* send to netdevice */ if (can_send(nskb, gwj->flags & CGW_FLAGS_CAN_ECHO)) gwj->dropped_frames++; else gwj->handled_frames++; } static inline int cgw_register_filter(struct net *net, struct cgw_job *gwj) { return can_rx_register(net, gwj->src.dev, gwj->ccgw.filter.can_id, gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj, "gw", NULL); } static inline void cgw_unregister_filter(struct net *net, struct cgw_job *gwj) { can_rx_unregister(net, gwj->src.dev, gwj->ccgw.filter.can_id, gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj); } static void cgw_job_free_rcu(struct rcu_head *rcu_head) { struct cgw_job *gwj = container_of(rcu_head, struct cgw_job, rcu); /* cgw_job::cf_mod is always accessed from the same cgw_job object within * the same RCU read section. Once cgw_job is scheduled for removal, * cf_mod can also be removed without mandating an additional grace period. */ kfree(rcu_access_pointer(gwj->cf_mod)); kmem_cache_free(cgw_cache, gwj); } /* Return cgw_job::cf_mod with RTNL protected section */ static struct cf_mod *cgw_job_cf_mod(struct cgw_job *gwj) { return rcu_dereference_protected(gwj->cf_mod, rtnl_is_locked()); } static int cgw_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg == NETDEV_UNREGISTER) { struct cgw_job *gwj = NULL; struct hlist_node *nx; ASSERT_RTNL(); hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); call_rcu(&gwj->rcu, cgw_job_free_rcu); } } } return NOTIFY_DONE; } static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, u32 pid, u32 seq, int flags) { struct rtcanmsg *rtcan; struct nlmsghdr *nlh; struct cf_mod *mod; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtcan), flags); if (!nlh) return -EMSGSIZE; rtcan = nlmsg_data(nlh); rtcan->can_family = AF_CAN; rtcan->gwtype = gwj->gwtype; rtcan->flags = gwj->flags; /* add statistics if available */ if (gwj->handled_frames) { if (nla_put_u32(skb, CGW_HANDLED, gwj->handled_frames) < 0) goto cancel; } if (gwj->dropped_frames) { if (nla_put_u32(skb, CGW_DROPPED, gwj->dropped_frames) < 0) goto cancel; } if (gwj->deleted_frames) { if (nla_put_u32(skb, CGW_DELETED, gwj->deleted_frames) < 0) goto cancel; } /* check non default settings of attributes */ if (gwj->limit_hops) { if (nla_put_u8(skb, CGW_LIM_HOPS, gwj->limit_hops) < 0) goto cancel; } mod = cgw_job_cf_mod(gwj); if (gwj->flags & CGW_FLAGS_CAN_FD) { struct cgw_fdframe_mod mb; if (mod->modtype.and) { memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf)); mb.modtype = mod->modtype.and; if (nla_put(skb, CGW_FDMOD_AND, sizeof(mb), &mb) < 0) goto cancel; } if (mod->modtype.or) { memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf)); mb.modtype = mod->modtype.or; if (nla_put(skb, CGW_FDMOD_OR, sizeof(mb), &mb) < 0) goto cancel; } if (mod->modtype.xor) { memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf)); mb.modtype = mod->modtype.xor; if (nla_put(skb, CGW_FDMOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } if (mod->modtype.set) { memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf)); mb.modtype = mod->modtype.set; if (nla_put(skb, CGW_FDMOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } else { struct cgw_frame_mod mb; if (mod->modtype.and) { memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf)); mb.modtype = mod->modtype.and; if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0) goto cancel; } if (mod->modtype.or) { memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf)); mb.modtype = mod->modtype.or; if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0) goto cancel; } if (mod->modtype.xor) { memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf)); mb.modtype = mod->modtype.xor; if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } if (mod->modtype.set) { memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf)); mb.modtype = mod->modtype.set; if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } if (mod->uid) { if (nla_put_u32(skb, CGW_MOD_UID, mod->uid) < 0) goto cancel; } if (mod->csumfunc.crc8) { if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN, &mod->csum.crc8) < 0) goto cancel; } if (mod->csumfunc.xor) { if (nla_put(skb, CGW_CS_XOR, CGW_CS_XOR_LEN, &mod->csum.xor) < 0) goto cancel; } if (gwj->gwtype == CGW_TYPE_CAN_CAN) { if (gwj->ccgw.filter.can_id || gwj->ccgw.filter.can_mask) { if (nla_put(skb, CGW_FILTER, sizeof(struct can_filter), &gwj->ccgw.filter) < 0) goto cancel; } if (nla_put_u32(skb, CGW_SRC_IF, gwj->ccgw.src_idx) < 0) goto cancel; if (nla_put_u32(skb, CGW_DST_IF, gwj->ccgw.dst_idx) < 0) goto cancel; } nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } /* Dump information about all CAN gateway jobs, in response to RTM_GETROUTE */ static int cgw_dump_jobs(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct cgw_job *gwj = NULL; int idx = 0; int s_idx = cb->args[0]; rcu_read_lock(); hlist_for_each_entry_rcu(gwj, &net->can.cgw_list, list) { if (idx < s_idx) goto cont; if (cgw_put_job(skb, gwj, RTM_NEWROUTE, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) break; cont: idx++; } rcu_read_unlock(); cb->args[0] = idx; return skb->len; } static const struct nla_policy cgw_policy[CGW_MAX + 1] = { [CGW_MOD_AND] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_OR] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_XOR] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_SET] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_CS_XOR] = { .len = sizeof(struct cgw_csum_xor) }, [CGW_CS_CRC8] = { .len = sizeof(struct cgw_csum_crc8) }, [CGW_SRC_IF] = { .type = NLA_U32 }, [CGW_DST_IF] = { .type = NLA_U32 }, [CGW_FILTER] = { .len = sizeof(struct can_filter) }, [CGW_LIM_HOPS] = { .type = NLA_U8 }, [CGW_MOD_UID] = { .type = NLA_U32 }, [CGW_FDMOD_AND] = { .len = sizeof(struct cgw_fdframe_mod) }, [CGW_FDMOD_OR] = { .len = sizeof(struct cgw_fdframe_mod) }, [CGW_FDMOD_XOR] = { .len = sizeof(struct cgw_fdframe_mod) }, [CGW_FDMOD_SET] = { .len = sizeof(struct cgw_fdframe_mod) }, }; /* check for common and gwtype specific attributes */ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, u8 gwtype, void *gwtypeattr, u8 *limhops) { struct nlattr *tb[CGW_MAX + 1]; struct rtcanmsg *r = nlmsg_data(nlh); int modidx = 0; int err = 0; /* initialize modification & checksum data space */ memset(mod, 0, sizeof(*mod)); err = nlmsg_parse_deprecated(nlh, sizeof(struct rtcanmsg), tb, CGW_MAX, cgw_policy, NULL); if (err < 0) return err; if (tb[CGW_LIM_HOPS]) { *limhops = nla_get_u8(tb[CGW_LIM_HOPS]); if (*limhops < 1 || *limhops > max_hops) return -EINVAL; } /* check for AND/OR/XOR/SET modifications */ if (r->flags & CGW_FLAGS_CAN_FD) { struct cgw_fdframe_mod mb; if (tb[CGW_FDMOD_AND]) { nla_memcpy(&mb, tb[CGW_FDMOD_AND], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.and, &mb.cf); mod->modtype.and = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_and_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_and_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_and_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_and_fddata; } if (tb[CGW_FDMOD_OR]) { nla_memcpy(&mb, tb[CGW_FDMOD_OR], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.or, &mb.cf); mod->modtype.or = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_or_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_or_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_or_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_or_fddata; } if (tb[CGW_FDMOD_XOR]) { nla_memcpy(&mb, tb[CGW_FDMOD_XOR], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.xor, &mb.cf); mod->modtype.xor = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_xor_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_xor_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_xor_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_xor_fddata; } if (tb[CGW_FDMOD_SET]) { nla_memcpy(&mb, tb[CGW_FDMOD_SET], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.set, &mb.cf); mod->modtype.set = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_set_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_set_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_set_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_set_fddata; } } else { struct cgw_frame_mod mb; if (tb[CGW_MOD_AND]) { nla_memcpy(&mb, tb[CGW_MOD_AND], CGW_MODATTR_LEN); canframecpy(&mod->modframe.and, &mb.cf); mod->modtype.and = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_and_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_and_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_and_data; } if (tb[CGW_MOD_OR]) { nla_memcpy(&mb, tb[CGW_MOD_OR], CGW_MODATTR_LEN); canframecpy(&mod->modframe.or, &mb.cf); mod->modtype.or = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_or_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_or_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_or_data; } if (tb[CGW_MOD_XOR]) { nla_memcpy(&mb, tb[CGW_MOD_XOR], CGW_MODATTR_LEN); canframecpy(&mod->modframe.xor, &mb.cf); mod->modtype.xor = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_xor_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_xor_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_xor_data; } if (tb[CGW_MOD_SET]) { nla_memcpy(&mb, tb[CGW_MOD_SET], CGW_MODATTR_LEN); canframecpy(&mod->modframe.set, &mb.cf); mod->modtype.set = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_set_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_set_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_set_data; } } /* check for checksum operations after CAN frame modifications */ if (modidx) { if (tb[CGW_CS_CRC8]) { struct cgw_csum_crc8 *c = nla_data(tb[CGW_CS_CRC8]); err = cgw_chk_csum_parms(c->from_idx, c->to_idx, c->result_idx, r); if (err) return err; nla_memcpy(&mod->csum.crc8, tb[CGW_CS_CRC8], CGW_CS_CRC8_LEN); /* select dedicated processing function to reduce * runtime operations in receive hot path. */ if (c->from_idx < 0 || c->to_idx < 0 || c->result_idx < 0) mod->csumfunc.crc8 = cgw_csum_crc8_rel; else if (c->from_idx <= c->to_idx) mod->csumfunc.crc8 = cgw_csum_crc8_pos; else mod->csumfunc.crc8 = cgw_csum_crc8_neg; } if (tb[CGW_CS_XOR]) { struct cgw_csum_xor *c = nla_data(tb[CGW_CS_XOR]); err = cgw_chk_csum_parms(c->from_idx, c->to_idx, c->result_idx, r); if (err) return err; nla_memcpy(&mod->csum.xor, tb[CGW_CS_XOR], CGW_CS_XOR_LEN); /* select dedicated processing function to reduce * runtime operations in receive hot path. */ if (c->from_idx < 0 || c->to_idx < 0 || c->result_idx < 0) mod->csumfunc.xor = cgw_csum_xor_rel; else if (c->from_idx <= c->to_idx) mod->csumfunc.xor = cgw_csum_xor_pos; else mod->csumfunc.xor = cgw_csum_xor_neg; } if (tb[CGW_MOD_UID]) nla_memcpy(&mod->uid, tb[CGW_MOD_UID], sizeof(u32)); } if (gwtype == CGW_TYPE_CAN_CAN) { /* check CGW_TYPE_CAN_CAN specific attributes */ struct can_can_gw *ccgw = (struct can_can_gw *)gwtypeattr; memset(ccgw, 0, sizeof(*ccgw)); /* check for can_filter in attributes */ if (tb[CGW_FILTER]) nla_memcpy(&ccgw->filter, tb[CGW_FILTER], sizeof(struct can_filter)); err = -ENODEV; /* specifying two interfaces is mandatory */ if (!tb[CGW_SRC_IF] || !tb[CGW_DST_IF]) return err; ccgw->src_idx = nla_get_u32(tb[CGW_SRC_IF]); ccgw->dst_idx = nla_get_u32(tb[CGW_DST_IF]); /* both indices set to 0 for flushing all routing entries */ if (!ccgw->src_idx && !ccgw->dst_idx) return 0; /* only one index set to 0 is an error */ if (!ccgw->src_idx || !ccgw->dst_idx) return err; } /* add the checks for other gwtypes here */ return 0; } static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct rtcanmsg *r; struct cgw_job *gwj; struct cf_mod *mod; struct can_can_gw ccgw; u8 limhops = 0; int err = 0; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) return -EINVAL; r = nlmsg_data(nlh); if (r->can_family != AF_CAN) return -EPFNOSUPPORT; /* so far we only support CAN -> CAN routings */ if (r->gwtype != CGW_TYPE_CAN_CAN) return -EINVAL; mod = kmalloc_obj(*mod); if (!mod) return -ENOMEM; err = cgw_parse_attr(nlh, mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); if (err < 0) goto out_free_cf; if (mod->uid) { ASSERT_RTNL(); /* check for updating an existing job with identical uid */ hlist_for_each_entry(gwj, &net->can.cgw_list, list) { struct cf_mod *old_cf; old_cf = cgw_job_cf_mod(gwj); if (old_cf->uid != mod->uid) continue; /* interfaces & filters must be identical */ if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) { err = -EINVAL; goto out_free_cf; } rcu_assign_pointer(gwj->cf_mod, mod); kfree_rcu_mightsleep(old_cf); return 0; } } /* ifindex == 0 is not allowed for job creation */ if (!ccgw.src_idx || !ccgw.dst_idx) { err = -ENODEV; goto out_free_cf; } gwj = kmem_cache_alloc(cgw_cache, GFP_KERNEL); if (!gwj) { err = -ENOMEM; goto out_free_cf; } gwj->handled_frames = 0; gwj->dropped_frames = 0; gwj->deleted_frames = 0; gwj->flags = r->flags; gwj->gwtype = r->gwtype; gwj->limit_hops = limhops; /* insert already parsed information */ RCU_INIT_POINTER(gwj->cf_mod, mod); memcpy(&gwj->ccgw, &ccgw, sizeof(ccgw)); err = -ENODEV; gwj->src.dev = __dev_get_by_index(net, gwj->ccgw.src_idx); if (!gwj->src.dev) goto out; if (gwj->src.dev->type != ARPHRD_CAN) goto out; gwj->dst.dev = __dev_get_by_index(net, gwj->ccgw.dst_idx); if (!gwj->dst.dev) goto out; if (gwj->dst.dev->type != ARPHRD_CAN) goto out; /* is sending the skb back to the incoming interface intended? */ if (gwj->src.dev == gwj->dst.dev && !(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK)) { err = -EINVAL; goto out; } ASSERT_RTNL(); err = cgw_register_filter(net, gwj); if (!err) hlist_add_head_rcu(&gwj->list, &net->can.cgw_list); out: if (err) { kmem_cache_free(cgw_cache, gwj); out_free_cf: kfree(mod); } return err; } static void cgw_remove_all_jobs(struct net *net) { struct cgw_job *gwj = NULL; struct hlist_node *nx; ASSERT_RTNL(); hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); call_rcu(&gwj->rcu, cgw_job_free_rcu); } } static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct cgw_job *gwj = NULL; struct hlist_node *nx; struct rtcanmsg *r; struct cf_mod mod; struct can_can_gw ccgw; u8 limhops = 0; int err = 0; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) return -EINVAL; r = nlmsg_data(nlh); if (r->can_family != AF_CAN) return -EPFNOSUPPORT; /* so far we only support CAN -> CAN routings */ if (r->gwtype != CGW_TYPE_CAN_CAN) return -EINVAL; err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); if (err < 0) return err; /* two interface indices both set to 0 => remove all entries */ if (!ccgw.src_idx && !ccgw.dst_idx) { cgw_remove_all_jobs(net); return 0; } err = -EINVAL; ASSERT_RTNL(); /* remove only the first matching entry */ hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { struct cf_mod *cf_mod; if (gwj->flags != r->flags) continue; if (gwj->limit_hops != limhops) continue; cf_mod = cgw_job_cf_mod(gwj); /* we have a match when uid is enabled and identical */ if (cf_mod->uid || mod.uid) { if (cf_mod->uid != mod.uid) continue; } else { /* no uid => check for identical modifications */ if (memcmp(cf_mod, &mod, sizeof(mod))) continue; } /* if (r->gwtype == CGW_TYPE_CAN_CAN) - is made sure here */ if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) continue; hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); call_rcu(&gwj->rcu, cgw_job_free_rcu); err = 0; break; } return err; } static int __net_init cangw_pernet_init(struct net *net) { INIT_HLIST_HEAD(&net->can.cgw_list); return 0; } static void __net_exit cangw_pernet_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) cgw_remove_all_jobs(net); rtnl_unlock(); } static struct pernet_operations cangw_pernet_ops = { .init = cangw_pernet_init, .exit_batch = cangw_pernet_exit_batch, }; static const struct rtnl_msg_handler cgw_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_CAN, .msgtype = RTM_NEWROUTE, .doit = cgw_create_job}, {.owner = THIS_MODULE, .protocol = PF_CAN, .msgtype = RTM_DELROUTE, .doit = cgw_remove_job}, {.owner = THIS_MODULE, .protocol = PF_CAN, .msgtype = RTM_GETROUTE, .dumpit = cgw_dump_jobs}, }; static __init int cgw_module_init(void) { int ret; /* sanitize given module parameter */ max_hops = clamp_t(unsigned int, max_hops, CGW_MIN_HOPS, CGW_MAX_HOPS); pr_info("can: netlink gateway - max_hops=%d\n", max_hops); ret = register_pernet_subsys(&cangw_pernet_ops); if (ret) return ret; ret = -ENOMEM; cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job), 0, 0, NULL); if (!cgw_cache) goto out_cache_create; /* set notifier */ notifier.notifier_call = cgw_notifier; ret = register_netdevice_notifier(¬ifier); if (ret) goto out_register_notifier; ret = rtnl_register_many(cgw_rtnl_msg_handlers); if (ret) goto out_rtnl_register; return 0; out_rtnl_register: unregister_netdevice_notifier(¬ifier); out_register_notifier: kmem_cache_destroy(cgw_cache); out_cache_create: unregister_pernet_subsys(&cangw_pernet_ops); return ret; } static __exit void cgw_module_exit(void) { rtnl_unregister_all(PF_CAN); unregister_netdevice_notifier(¬ifier); unregister_pernet_subsys(&cangw_pernet_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ kmem_cache_destroy(cgw_cache); } module_init(cgw_module_init); module_exit(cgw_module_exit); |
| 98 100 100 99 99 92 3 7 8 19 1 17 17 1 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* ASN.1 Object identifier (OID) registry * * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/module.h> #include <linux/export.h> #include <linux/oid_registry.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/bug.h> #include <linux/asn1.h> #include "oid_registry_data.c" MODULE_DESCRIPTION("OID Registry"); MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); /** * look_up_OID - Find an OID registration for the specified data * @data: Binary representation of the OID * @datasize: Size of the binary representation */ enum OID look_up_OID(const void *data, size_t datasize) { const unsigned char *octets = data; enum OID oid; unsigned char xhash; unsigned i, j, k, hash; size_t len; /* Hash the OID data */ hash = datasize - 1; for (i = 0; i < datasize; i++) hash += octets[i] * 33; hash = (hash >> 24) ^ (hash >> 16) ^ (hash >> 8) ^ hash; hash &= 0xff; /* Binary search the OID registry. OIDs are stored in ascending order * of hash value then ascending order of size and then in ascending * order of reverse value. */ i = 0; k = OID__NR; while (i < k) { j = (i + k) / 2; xhash = oid_search_table[j].hash; if (xhash > hash) { k = j; continue; } if (xhash < hash) { i = j + 1; continue; } oid = oid_search_table[j].oid; len = oid_index[oid + 1] - oid_index[oid]; if (len > datasize) { k = j; continue; } if (len < datasize) { i = j + 1; continue; } /* Variation is most likely to be at the tail end of the * OID, so do the comparison in reverse. */ while (len > 0) { unsigned char a = oid_data[oid_index[oid] + --len]; unsigned char b = octets[len]; if (a > b) { k = j; goto next; } if (a < b) { i = j + 1; goto next; } } return oid; next: ; } return OID__NR; } EXPORT_SYMBOL_GPL(look_up_OID); /** * parse_OID - Parse an OID from a bytestream * @data: Binary representation of the header + OID * @datasize: Size of the binary representation * @oid: Pointer to oid to return result * * Parse an OID from a bytestream that holds the OID in the format * ASN1_OID | length | oid. The length indicator must equal to datasize - 2. * -EBADMSG is returned if the bytestream is too short. */ int parse_OID(const void *data, size_t datasize, enum OID *oid) { const unsigned char *v = data; /* we need 2 bytes of header and at least 1 byte for oid */ if (datasize < 3 || v[0] != ASN1_OID || v[1] != datasize - 2) return -EBADMSG; *oid = look_up_OID(data + 2, datasize - 2); return 0; } EXPORT_SYMBOL_GPL(parse_OID); /* * sprint_oid - Print an Object Identifier into a buffer * @data: The encoded OID to print * @datasize: The size of the encoded OID * @buffer: The buffer to render into * @bufsize: The size of the buffer * * The OID is rendered into the buffer in "a.b.c.d" format and the number of * bytes is returned. -EBADMSG is returned if the data could not be interpreted * and -ENOBUFS if the buffer was too small. */ int sprint_oid(const void *data, size_t datasize, char *buffer, size_t bufsize) { const unsigned char *v = data, *end = v + datasize; unsigned long num; unsigned char n; size_t ret; int count; if (v >= end) goto bad; n = *v++; ret = count = snprintf(buffer, bufsize, "%u.%u", n / 40, n % 40); if (count >= bufsize) return -ENOBUFS; buffer += count; bufsize -= count; while (v < end) { n = *v++; if (!(n & 0x80)) { num = n; } else { num = n & 0x7f; do { if (v >= end) goto bad; n = *v++; num <<= 7; num |= n & 0x7f; } while (n & 0x80); } ret += count = snprintf(buffer, bufsize, ".%lu", num); if (count >= bufsize) return -ENOBUFS; buffer += count; bufsize -= count; } return ret; bad: snprintf(buffer, bufsize, "(bad)"); return -EBADMSG; } EXPORT_SYMBOL_GPL(sprint_oid); |
| 31 18 9 12 12 12 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 | #ifndef __LINUX_MROUTE_BASE_H #define __LINUX_MROUTE_BASE_H #include <linux/netdevice.h> #include <linux/rhashtable-types.h> #include <linux/spinlock.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/fib_notifier.h> #include <net/ip_fib.h> /** * struct vif_device - interface representor for multicast routing * @dev: network device being used * @dev_tracker: refcount tracker for @dev reference * @bytes_in: statistic; bytes ingressing * @bytes_out: statistic; bytes egresing * @pkt_in: statistic; packets ingressing * @pkt_out: statistic; packets egressing * @rate_limit: Traffic shaping (NI) * @threshold: TTL threshold * @flags: Control flags * @link: Physical interface index * @dev_parent_id: device parent id * @local: Local address * @remote: Remote address for tunnels */ struct vif_device { struct net_device __rcu *dev; netdevice_tracker dev_tracker; unsigned long bytes_in, bytes_out; unsigned long pkt_in, pkt_out; unsigned long rate_limit; unsigned char threshold; unsigned short flags; int link; /* Currently only used by ipmr */ struct netdev_phys_item_id dev_parent_id; __be32 local, remote; }; struct vif_entry_notifier_info { struct fib_notifier_info info; struct net_device *dev; unsigned short vif_index; unsigned short vif_flags; u32 tb_id; }; static inline int mr_call_vif_notifier(struct notifier_block *nb, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, struct net_device *vif_dev, unsigned short vif_index, u32 tb_id, struct netlink_ext_ack *extack) { struct vif_entry_notifier_info info = { .info = { .family = family, .extack = extack, }, .dev = vif_dev, .vif_index = vif_index, .vif_flags = vif->flags, .tb_id = tb_id, }; return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_vif_notifiers(struct net *net, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, struct net_device *vif_dev, unsigned short vif_index, u32 tb_id, atomic_t *ipmr_seq) { struct vif_entry_notifier_info info = { .info = { .family = family, }, .dev = vif_dev, .vif_index = vif_index, .vif_flags = vif->flags, .tb_id = tb_id, }; ASSERT_RTNL(); atomic_inc(ipmr_seq); return call_fib_notifiers(net, event_type, &info.info); } #ifndef MAXVIFS /* This one is nasty; value is defined in uapi using different symbols for * mroute and morute6 but both map into same 32. */ #define MAXVIFS 32 #endif /* Note: This helper is deprecated. */ #define VIF_EXISTS(_mrt, _idx) (!!rcu_access_pointer((_mrt)->vif_table[_idx].dev)) /* mfc_flags: * MFC_STATIC - the entry was added statically (not by a routing daemon) * MFC_OFFLOAD - the entry was offloaded to the hardware */ enum { MFC_STATIC = BIT(0), MFC_OFFLOAD = BIT(1), }; /** * struct mr_mfc - common multicast routing entries * @mnode: rhashtable list * @mfc_parent: source interface (iif) * @mfc_flags: entry flags * @expires: unresolved entry expire time * @unresolved: unresolved cached skbs * @last_assert: time of last assert * @minvif: minimum VIF id * @maxvif: maximum VIF id * @bytes: bytes that have passed for this entry * @pkt: packets that have passed for this entry * @wrong_if: number of wrong source interface hits * @lastuse: time of last use of the group (traffic or update) * @ttls: OIF TTL threshold array * @refcount: reference count for this entry * @list: global entry list * @rcu: used for entry destruction * @free: Operation used for freeing an entry under RCU */ struct mr_mfc { struct rhlist_head mnode; unsigned short mfc_parent; int mfc_flags; union { struct { unsigned long expires; struct sk_buff_head unresolved; } unres; struct { unsigned long last_assert; int minvif; int maxvif; atomic_long_t bytes; atomic_long_t pkt; atomic_long_t wrong_if; unsigned long lastuse; unsigned char ttls[MAXVIFS]; refcount_t refcount; } res; } mfc_un; struct list_head list; struct rcu_head rcu; void (*free)(struct rcu_head *head); }; static inline void mr_cache_put(struct mr_mfc *c) { if (refcount_dec_and_test(&c->mfc_un.res.refcount)) call_rcu(&c->rcu, c->free); } static inline void mr_cache_hold(struct mr_mfc *c) { refcount_inc(&c->mfc_un.res.refcount); } struct mfc_entry_notifier_info { struct fib_notifier_info info; struct mr_mfc *mfc; u32 tb_id; }; static inline int mr_call_mfc_notifier(struct notifier_block *nb, unsigned short family, enum fib_event_type event_type, struct mr_mfc *mfc, u32 tb_id, struct netlink_ext_ack *extack) { struct mfc_entry_notifier_info info = { .info = { .family = family, .extack = extack, }, .mfc = mfc, .tb_id = tb_id }; return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_mfc_notifiers(struct net *net, unsigned short family, enum fib_event_type event_type, struct mr_mfc *mfc, u32 tb_id, atomic_t *ipmr_seq) { struct mfc_entry_notifier_info info = { .info = { .family = family, }, .mfc = mfc, .tb_id = tb_id }; atomic_inc(ipmr_seq); return call_fib_notifiers(net, event_type, &info.info); } struct mr_table; /** * struct mr_table_ops - callbacks and info for protocol-specific ops * @rht_params: parameters for accessing the MFC hash * @cmparg_any: a hash key to be used for matching on (*,*) routes */ struct mr_table_ops { const struct rhashtable_params *rht_params; void *cmparg_any; }; /** * struct mr_table - a multicast routing table * @work: used for table destruction * @list: entry within a list of multicast routing tables * @net: net where this table belongs * @ops: protocol specific operations * @id: identifier of the table * @mroute_sk: socket associated with the table * @ipmr_expire_timer: timer for handling unresolved routes * @mfc_unres_queue: list of unresolved MFC entries * @vif_table: array containing all possible vifs * @mfc_hash: Hash table of all resolved routes for easy lookup * @mfc_cache_list: list of resovled routes for possible traversal * @maxvif: Identifier of highest value vif currently in use * @cache_resolve_queue_len: current size of unresolved queue * @mroute_do_assert: Whether to inform userspace on wrong ingress * @mroute_do_pim: Whether to receive IGMP PIMv1 * @mroute_reg_vif_num: PIM-device vif index */ struct mr_table { struct rcu_work work; struct list_head list; possible_net_t net; struct mr_table_ops ops; u32 id; struct sock __rcu *mroute_sk; struct timer_list ipmr_expire_timer; struct list_head mfc_unres_queue; struct vif_device vif_table[MAXVIFS]; struct rhltable mfc_hash; struct list_head mfc_cache_list; int maxvif; u32 cache_resolve_queue_len; bool mroute_do_assert; bool mroute_do_pim; bool mroute_do_wrvifwhole; int mroute_reg_vif_num; }; static inline bool mr_can_free_table(struct net *net) { return !check_net(net) || !net_initialized(net); } #ifdef CONFIG_IP_MROUTE_COMMON void vif_device_init(struct vif_device *v, struct net_device *dev, unsigned long rate_limit, unsigned char threshold, unsigned short flags, unsigned short get_iflink_mask); void mr_table_free(struct mr_table *mrt); struct mr_table * mr_table_alloc(struct net *net, u32 id, struct mr_table_ops *ops, void (*expire_func)(struct timer_list *t), void (*table_set)(struct mr_table *mrt, struct net *net)); /* These actually return 'struct mr_mfc *', but to avoid need for explicit * castings they simply return void. */ void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent); void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi); void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg); int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mr_mfc *c, struct rtmsg *rtm); int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, struct netlink_callback *cb, int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), spinlock_t *lock, struct fib_dump_filter *filter); int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), spinlock_t *lock, struct fib_dump_filter *filter); int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), struct netlink_ext_ack *extack); #else static inline void vif_device_init(struct vif_device *v, struct net_device *dev, unsigned long rate_limit, unsigned char threshold, unsigned short flags, unsigned short get_iflink_mask) { } static inline void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent) { return NULL; } static inline void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi) { return NULL; } static inline struct mr_mfc *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg) { return NULL; } static inline int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mr_mfc *c, struct rtmsg *rtm) { return -EINVAL; } static inline int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), spinlock_t *lock, struct fib_dump_filter *filter) { return -EINVAL; } static inline int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), struct netlink_ext_ack *extack) { return -EINVAL; } #endif static inline void *mr_mfc_find(struct mr_table *mrt, void *hasharg) { return mr_mfc_find_parent(mrt, hasharg, -1); } #ifdef CONFIG_PROC_FS struct mr_vif_iter { struct seq_net_private p; struct mr_table *mrt; int ct; }; struct mr_mfc_iter { struct seq_net_private p; struct mr_table *mrt; struct list_head *cache; /* Lock protecting the mr_table's unresolved queue */ spinlock_t *lock; }; #ifdef CONFIG_IP_MROUTE_COMMON void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos); void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos); static inline void *mr_vif_seq_start(struct seq_file *seq, loff_t *pos) { return *pos ? mr_vif_seq_idx(seq_file_net(seq), seq->private, *pos - 1) : SEQ_START_TOKEN; } /* These actually return 'struct mr_mfc *', but to avoid need for explicit * castings they simply return void. */ void *mr_mfc_seq_idx(struct net *net, struct mr_mfc_iter *it, loff_t pos); void *mr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos); static inline void *mr_mfc_seq_start(struct seq_file *seq, loff_t *pos, struct mr_table *mrt, spinlock_t *lock) { struct mr_mfc_iter *it = seq->private; it->mrt = mrt; it->cache = NULL; it->lock = lock; return *pos ? mr_mfc_seq_idx(seq_file_net(seq), seq->private, *pos - 1) : SEQ_START_TOKEN; } static inline void mr_mfc_seq_stop(struct seq_file *seq, void *v) { struct mr_mfc_iter *it = seq->private; struct mr_table *mrt = it->mrt; if (it->cache == &mrt->mfc_unres_queue) spin_unlock_bh(it->lock); else if (it->cache == &mrt->mfc_cache_list) rcu_read_unlock(); } #else static inline void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos) { return NULL; } static inline void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return NULL; } static inline void *mr_vif_seq_start(struct seq_file *seq, loff_t *pos) { return NULL; } static inline void *mr_mfc_seq_idx(struct net *net, struct mr_mfc_iter *it, loff_t pos) { return NULL; } static inline void *mr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return NULL; } static inline void *mr_mfc_seq_start(struct seq_file *seq, loff_t *pos, struct mr_table *mrt, spinlock_t *lock) { return NULL; } static inline void mr_mfc_seq_stop(struct seq_file *seq, void *v) { } #endif #endif #endif |
| 20 20 1 5 4 2 5 4 5 2 1 3 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Bluetooth HCI UART driver * * Copyright (C) 2000-2001 Qualcomm Incorporated * Copyright (C) 2002-2003 Maxim Krasnyansky <maxk@qualcomm.com> * Copyright (C) 2004-2005 Marcel Holtmann <marcel@holtmann.org> */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/interrupt.h> #include <linux/ptrace.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/tty.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/signal.h> #include <linux/ioctl.h> #include <linux/skbuff.h> #include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include "hci_uart.h" struct h4_struct { struct sk_buff *rx_skb; struct sk_buff_head txq; }; /* Initialize protocol */ static int h4_open(struct hci_uart *hu) { struct h4_struct *h4; BT_DBG("hu %p", hu); h4 = kzalloc_obj(*h4); if (!h4) return -ENOMEM; skb_queue_head_init(&h4->txq); hu->priv = h4; return 0; } /* Flush protocol data */ static int h4_flush(struct hci_uart *hu) { struct h4_struct *h4 = hu->priv; BT_DBG("hu %p", hu); skb_queue_purge(&h4->txq); return 0; } /* Close protocol */ static int h4_close(struct hci_uart *hu) { struct h4_struct *h4 = hu->priv; BT_DBG("hu %p", hu); skb_queue_purge(&h4->txq); kfree_skb(h4->rx_skb); hu->priv = NULL; kfree(h4); return 0; } /* Enqueue frame for transmission (padding, crc, etc) */ static int h4_enqueue(struct hci_uart *hu, struct sk_buff *skb) { struct h4_struct *h4 = hu->priv; BT_DBG("hu %p skb %p", hu, skb); /* Prepend skb with frame type */ memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1); skb_queue_tail(&h4->txq, skb); return 0; } static const struct h4_recv_pkt h4_recv_pkts[] = { { H4_RECV_ACL, .recv = hci_recv_frame }, { H4_RECV_SCO, .recv = hci_recv_frame }, { H4_RECV_EVENT, .recv = hci_recv_frame }, { H4_RECV_ISO, .recv = hci_recv_frame }, }; /* Recv data */ static int h4_recv(struct hci_uart *hu, const void *data, int count) { struct h4_struct *h4 = hu->priv; if (!h4) return -ENODEV; h4->rx_skb = h4_recv_buf(hu, h4->rx_skb, data, count, h4_recv_pkts, ARRAY_SIZE(h4_recv_pkts)); if (IS_ERR(h4->rx_skb)) { int err = PTR_ERR(h4->rx_skb); bt_dev_err(hu->hdev, "Frame reassembly failed (%d)", err); h4->rx_skb = NULL; return err; } return count; } static struct sk_buff *h4_dequeue(struct hci_uart *hu) { struct h4_struct *h4 = hu->priv; return skb_dequeue(&h4->txq); } static const struct hci_uart_proto h4p = { .id = HCI_UART_H4, .name = "H4", .open = h4_open, .close = h4_close, .recv = h4_recv, .enqueue = h4_enqueue, .dequeue = h4_dequeue, .flush = h4_flush, }; int __init h4_init(void) { return hci_uart_register_proto(&h4p); } int __exit h4_deinit(void) { return hci_uart_unregister_proto(&h4p); } struct sk_buff *h4_recv_buf(struct hci_uart *hu, struct sk_buff *skb, const unsigned char *buffer, int count, const struct h4_recv_pkt *pkts, int pkts_count) { u8 alignment = hu->alignment ? hu->alignment : 1; struct hci_dev *hdev = hu->hdev; /* Check for error from previous call */ if (IS_ERR(skb)) skb = NULL; while (count) { int i, len; /* remove padding bytes from buffer */ for (; hu->padding && count > 0; hu->padding--) { count--; buffer++; } if (!count) break; if (!skb) { for (i = 0; i < pkts_count; i++) { if (buffer[0] != (&pkts[i])->type) continue; skb = bt_skb_alloc((&pkts[i])->maxlen, GFP_ATOMIC); if (!skb) return ERR_PTR(-ENOMEM); hci_skb_pkt_type(skb) = (&pkts[i])->type; hci_skb_expect(skb) = (&pkts[i])->hlen; break; } /* Check for invalid packet type */ if (!skb) return ERR_PTR(-EILSEQ); count -= 1; buffer += 1; } len = min_t(uint, hci_skb_expect(skb) - skb->len, count); skb_put_data(skb, buffer, len); count -= len; buffer += len; /* Check for partial packet */ if (skb->len < hci_skb_expect(skb)) continue; for (i = 0; i < pkts_count; i++) { if (hci_skb_pkt_type(skb) == (&pkts[i])->type) break; } if (i >= pkts_count) { kfree_skb(skb); return ERR_PTR(-EILSEQ); } if (skb->len == (&pkts[i])->hlen) { u16 dlen; switch ((&pkts[i])->lsize) { case 0: /* No variable data length */ dlen = 0; break; case 1: /* Single octet variable length */ dlen = skb->data[(&pkts[i])->loff]; hci_skb_expect(skb) += dlen; if (skb_tailroom(skb) < dlen) { kfree_skb(skb); return ERR_PTR(-EMSGSIZE); } break; case 2: /* Double octet variable length */ dlen = get_unaligned_le16(skb->data + (&pkts[i])->loff); hci_skb_expect(skb) += dlen; if (skb_tailroom(skb) < dlen) { kfree_skb(skb); return ERR_PTR(-EMSGSIZE); } break; default: /* Unsupported variable length */ kfree_skb(skb); return ERR_PTR(-EILSEQ); } if (!dlen) { hu->padding = (skb->len + 1) % alignment; hu->padding = (alignment - hu->padding) % alignment; /* No more data, complete frame */ (&pkts[i])->recv(hdev, skb); skb = NULL; } } else { hu->padding = (skb->len + 1) % alignment; hu->padding = (alignment - hu->padding) % alignment; /* Complete frame */ (&pkts[i])->recv(hdev, skb); skb = NULL; } } return skb; } EXPORT_SYMBOL_GPL(h4_recv_buf); |
| 8 4 9 4 10 10 7 7 5 5 10 10 10 7 4 1 10 6 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPVS: Weighted Round-Robin Scheduling module * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * * Changes: * Wensong Zhang : changed the ip_vs_wrr_schedule to return dest * Wensong Zhang : changed some comestics things for debugging * Wensong Zhang : changed for the d-linked destination list * Wensong Zhang : added the ip_vs_wrr_update_svc * Julian Anastasov : fixed the bug of returning destination * with weight 0 when all weights are zero */ #define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/net.h> #include <linux/gcd.h> #include <net/ip_vs.h> /* The WRR algorithm depends on some caclulations: * - mw: maximum weight * - di: weight step, greatest common divisor from all weights * - cw: current required weight * As result, all weights are in the [di..mw] range with a step=di. * * First, we start with cw = mw and select dests with weight >= cw. * Then cw is reduced with di and all dests are checked again. * Last pass should be with cw = di. We have mw/di passes in total: * * pass 1: cw = max weight * pass 2: cw = max weight - di * pass 3: cw = max weight - 2 * di * ... * last pass: cw = di * * Weights are supposed to be >= di but we run in parallel with * weight changes, it is possible some dest weight to be reduced * below di, bad if it is the only available dest. * * So, we modify how mw is calculated, now it is reduced with (di - 1), * so that last cw is 1 to catch such dests with weight below di: * pass 1: cw = max weight - (di - 1) * pass 2: cw = max weight - di - (di - 1) * pass 3: cw = max weight - 2 * di - (di - 1) * ... * last pass: cw = 1 * */ /* * current destination pointer for weighted round-robin scheduling */ struct ip_vs_wrr_mark { struct ip_vs_dest *cl; /* current dest or head */ int cw; /* current weight */ int mw; /* maximum weight */ int di; /* decreasing interval */ struct rcu_head rcu_head; }; static int ip_vs_wrr_gcd_weight(struct ip_vs_service *svc) { struct ip_vs_dest *dest; int weight; int g = 0; list_for_each_entry(dest, &svc->destinations, n_list) { weight = atomic_read(&dest->weight); if (weight > 0) { if (g > 0) g = gcd(weight, g); else g = weight; } } return g ? g : 1; } /* * Get the maximum weight of the service destinations. */ static int ip_vs_wrr_max_weight(struct ip_vs_service *svc) { struct ip_vs_dest *dest; int new_weight, weight = 0; list_for_each_entry(dest, &svc->destinations, n_list) { new_weight = atomic_read(&dest->weight); if (new_weight > weight) weight = new_weight; } return weight; } static int ip_vs_wrr_init_svc(struct ip_vs_service *svc) { struct ip_vs_wrr_mark *mark; /* * Allocate the mark variable for WRR scheduling */ mark = kmalloc_obj(struct ip_vs_wrr_mark); if (mark == NULL) return -ENOMEM; mark->cl = list_entry(&svc->destinations, struct ip_vs_dest, n_list); mark->di = ip_vs_wrr_gcd_weight(svc); mark->mw = ip_vs_wrr_max_weight(svc) - (mark->di - 1); mark->cw = mark->mw; svc->sched_data = mark; return 0; } static void ip_vs_wrr_done_svc(struct ip_vs_service *svc) { struct ip_vs_wrr_mark *mark = svc->sched_data; /* * Release the mark variable */ kfree_rcu(mark, rcu_head); } static int ip_vs_wrr_dest_changed(struct ip_vs_service *svc, struct ip_vs_dest *dest) { struct ip_vs_wrr_mark *mark = svc->sched_data; spin_lock_bh(&svc->sched_lock); mark->cl = list_entry(&svc->destinations, struct ip_vs_dest, n_list); mark->di = ip_vs_wrr_gcd_weight(svc); mark->mw = ip_vs_wrr_max_weight(svc) - (mark->di - 1); if (mark->cw > mark->mw || !mark->cw) mark->cw = mark->mw; else if (mark->di > 1) mark->cw = (mark->cw / mark->di) * mark->di + 1; spin_unlock_bh(&svc->sched_lock); return 0; } /* * Weighted Round-Robin Scheduling */ static struct ip_vs_dest * ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *last, *stop = NULL; struct ip_vs_wrr_mark *mark = svc->sched_data; bool last_pass = false, restarted = false; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); spin_lock_bh(&svc->sched_lock); dest = mark->cl; /* No available dests? */ if (mark->mw == 0) goto err_noavail; last = dest; /* Stop only after all dests were checked for weight >= 1 (last pass) */ while (1) { list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) { if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) && atomic_read(&dest->weight) >= mark->cw) goto found; if (dest == stop) goto err_over; } mark->cw -= mark->di; if (mark->cw <= 0) { mark->cw = mark->mw; /* Stop if we tried last pass from first dest: * 1. last_pass: we started checks when cw > di but * then all dests were checked for w >= 1 * 2. last was head: the first and only traversal * was for weight >= 1, for all dests. */ if (last_pass || &last->n_list == &svc->destinations) goto err_over; restarted = true; } last_pass = mark->cw <= mark->di; if (last_pass && restarted && &last->n_list != &svc->destinations) { /* First traversal was for w >= 1 but only * for dests after 'last', now do the same * for all dests up to 'last'. */ stop = last; } } found: IP_VS_DBG_BUF(6, "WRR: server %s:%u " "activeconns %d refcnt %d weight %d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->activeconns), refcount_read(&dest->refcnt), atomic_read(&dest->weight)); mark->cl = dest; out: spin_unlock_bh(&svc->sched_lock); return dest; err_noavail: mark->cl = dest; dest = NULL; ip_vs_scheduler_err(svc, "no destination available"); goto out; err_over: mark->cl = dest; dest = NULL; ip_vs_scheduler_err(svc, "no destination available: " "all destinations are overloaded"); goto out; } static struct ip_vs_scheduler ip_vs_wrr_scheduler = { .name = "wrr", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_wrr_scheduler.n_list), .init_service = ip_vs_wrr_init_svc, .done_service = ip_vs_wrr_done_svc, .add_dest = ip_vs_wrr_dest_changed, .del_dest = ip_vs_wrr_dest_changed, .upd_dest = ip_vs_wrr_dest_changed, .schedule = ip_vs_wrr_schedule, }; static int __init ip_vs_wrr_init(void) { return register_ip_vs_scheduler(&ip_vs_wrr_scheduler) ; } static void __exit ip_vs_wrr_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_wrr_scheduler); synchronize_rcu(); } module_init(ip_vs_wrr_init); module_exit(ip_vs_wrr_cleanup); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ipvs weighted round-robin scheduler"); |
| 1 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2020 Intel Corporation. */ #ifndef XSK_BUFF_POOL_H_ #define XSK_BUFF_POOL_H_ #include <linux/if_xdp.h> #include <linux/types.h> #include <linux/dma-mapping.h> #include <linux/bpf.h> #include <net/xdp.h> struct xsk_buff_pool; struct xdp_rxq_info; struct xsk_cb_desc; struct xsk_queue; struct xdp_desc; struct xdp_umem; struct xdp_sock; struct device; struct page; #define XSK_PRIV_MAX 24 struct xdp_buff_xsk { struct xdp_buff xdp; u8 cb[XSK_PRIV_MAX]; dma_addr_t dma; dma_addr_t frame_dma; struct xsk_buff_pool *pool; struct list_head list_node; } __aligned_largest; #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb)) #define XSK_TX_COMPL_FITS(t) BUILD_BUG_ON(sizeof(struct xsk_tx_metadata_compl) > sizeof(t)) struct xsk_dma_map { dma_addr_t *dma_pages; struct device *dev; struct net_device *netdev; refcount_t users; struct list_head list; /* Protected by the RTNL_LOCK */ u32 dma_pages_cnt; }; struct xsk_buff_pool { /* Members only used in the control path first. */ struct device *dev; struct net_device *netdev; struct list_head xsk_tx_list; /* Protects modifications to the xsk_tx_list */ spinlock_t xsk_tx_list_lock; refcount_t users; struct xdp_umem *umem; struct work_struct work; /* Protects generic receive in shared and non-shared umem mode. */ spinlock_t rx_lock; struct list_head free_list; struct list_head xskb_list; u32 heads_cnt; u16 queue_id; /* Data path members as close to free_heads at the end as possible. */ struct xsk_queue *fq ____cacheline_aligned_in_smp; struct xsk_queue *cq; /* For performance reasons, each buff pool has its own array of dma_pages * even when they are identical. */ dma_addr_t *dma_pages; struct xdp_buff_xsk *heads; struct xdp_desc *tx_descs; u64 chunk_mask; u64 addrs_cnt; u32 free_list_cnt; u32 dma_pages_cnt; u32 free_heads_cnt; u32 headroom; u32 chunk_size; u32 chunk_shift; u32 frame_len; u32 tx_descs_nentries; u32 reclaim_descs; u32 tx_zc_pending_descs; u32 xdp_zc_max_segs; u8 tx_metadata_len; /* inherited from umem */ u8 cached_need_wakeup; bool uses_need_wakeup; bool unaligned; bool tx_sw_csum; void *addrs; /* Mutual exclusion of the completion ring in the SKB mode. * Protect: NAPI TX thread and sendmsg error paths in the SKB * destructor callback. */ spinlock_t cq_prod_lock; struct xdp_buff_xsk *free_heads[]; }; /* Masks for xdp_umem_page flags. * The low 12-bits of the addr will be 0 since this is the page address, so we * can use them for flags. */ #define XSK_NEXT_PG_CONTIG_SHIFT 0 #define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT) /* AF_XDP core. */ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem, u32 max_segs); int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, u16 queue_id, u16 flags); int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_sock *umem_xs, struct net_device *dev, u16 queue_id); int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs, u32 max_segs); void xp_destroy(struct xsk_buff_pool *pool); void xp_get_pool(struct xsk_buff_pool *pool); bool xp_put_pool(struct xsk_buff_pool *pool); void xp_clear_dev(struct xsk_buff_pool *pool); void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); /* AF_XDP, and XDP core. */ void xp_free(struct xdp_buff_xsk *xskb); static inline void xp_init_xskb_addr(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool, u64 addr) { xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom; } static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool, dma_addr_t *dma_pages, u64 addr) { xskb->frame_dma = (dma_pages[addr >> PAGE_SHIFT] & ~XSK_NEXT_PG_CONTIG_MASK) + (addr & ~PAGE_MASK); xskb->dma = xskb->frame_dma + pool->headroom + XDP_PACKET_HEADROOM; } /* AF_XDP ZC drivers, via xdp_sock_buff.h */ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq); void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc); int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages); void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs); struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool); u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max); bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count); void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr); dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr); struct xdp_desc_ctx { dma_addr_t dma; struct xsk_tx_metadata *meta; }; struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr); static inline dma_addr_t xp_get_dma(struct xdp_buff_xsk *xskb) { return xskb->dma; } static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb) { return xskb->frame_dma; } static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb) { dma_sync_single_for_cpu(xskb->pool->dev, xskb->dma, xskb->pool->frame_len, DMA_BIDIRECTIONAL); } static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { dma_sync_single_for_device(pool->dev, dma, size, DMA_BIDIRECTIONAL); } static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool, u64 addr, u32 len) { bool cross_pg = (addr & (PAGE_SIZE - 1)) + len > PAGE_SIZE; if (likely(!cross_pg)) return false; return pool->dma_pages && !(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK); } static inline bool xp_mb_desc(const struct xdp_desc *desc) { return desc->options & XDP_PKT_CONTD; } static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr) { return addr & pool->chunk_mask; } static inline u64 xp_unaligned_extract_addr(u64 addr) { return addr & XSK_UNALIGNED_BUF_ADDR_MASK; } static inline u64 xp_unaligned_extract_offset(u64 addr) { return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT; } static inline u64 xp_unaligned_add_offset_to_addr(u64 addr) { return xp_unaligned_extract_addr(addr) + xp_unaligned_extract_offset(addr); } static inline u32 xp_aligned_extract_idx(struct xsk_buff_pool *pool, u64 addr) { return xp_aligned_extract_addr(pool, addr) >> pool->chunk_shift; } static inline void xp_release(struct xdp_buff_xsk *xskb) { if (xskb->pool->unaligned) xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb; } static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool) { u64 orig_addr = xskb->xdp.data - pool->addrs; u64 offset; if (!pool->unaligned) return orig_addr; offset = xskb->xdp.data - xskb->xdp.data_hard_start; offset += pool->headroom; orig_addr -= offset; return orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); } static inline bool xp_tx_metadata_enabled(const struct xsk_buff_pool *pool) { return pool->tx_metadata_len > 0; } #endif /* XSK_BUFF_POOL_H_ */ |
| 8 8 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 | // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2024-2025 Intel Corporation. All rights reserved. */ /* PCIe r7.0 section 6.33 Integrity & Data Encryption (IDE) */ #define dev_fmt(fmt) "PCI/IDE: " fmt #include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/pci.h> #include <linux/pci-ide.h> #include <linux/pci_regs.h> #include <linux/slab.h> #include <linux/sysfs.h> #include "pci.h" static int __sel_ide_offset(u16 ide_cap, u8 nr_link_ide, u8 stream_index, u8 nr_ide_mem) { u32 offset = ide_cap + PCI_IDE_LINK_STREAM_0 + nr_link_ide * PCI_IDE_LINK_BLOCK_SIZE; /* * Assume a constant number of address association resources per stream * index */ return offset + stream_index * PCI_IDE_SEL_BLOCK_SIZE(nr_ide_mem); } static int sel_ide_offset(struct pci_dev *pdev, struct pci_ide_partner *settings) { return __sel_ide_offset(pdev->ide_cap, pdev->nr_link_ide, settings->stream_index, pdev->nr_ide_mem); } static bool reserve_stream_index(struct pci_dev *pdev, u8 idx) { int ret; ret = ida_alloc_range(&pdev->ide_stream_ida, idx, idx, GFP_KERNEL); return ret >= 0; } static bool reserve_stream_id(struct pci_host_bridge *hb, u8 id) { int ret; ret = ida_alloc_range(&hb->ide_stream_ids_ida, id, id, GFP_KERNEL); return ret >= 0; } static bool claim_stream(struct pci_host_bridge *hb, u8 stream_id, struct pci_dev *pdev, u8 stream_idx) { dev_info(&hb->dev, "Stream ID %d active at init\n", stream_id); if (!reserve_stream_id(hb, stream_id)) { dev_info(&hb->dev, "Failed to claim %s Stream ID %d\n", stream_id == PCI_IDE_RESERVED_STREAM_ID ? "reserved" : "active", stream_id); return false; } /* No stream index to reserve in the Link IDE case */ if (!pdev) return true; if (!reserve_stream_index(pdev, stream_idx)) { pci_info(pdev, "Failed to claim active Selective Stream %d\n", stream_idx); return false; } return true; } void pci_ide_init(struct pci_dev *pdev) { struct pci_host_bridge *hb = pci_find_host_bridge(pdev->bus); u16 nr_link_ide, nr_ide_mem, nr_streams; u16 ide_cap; u32 val; /* * Unconditionally init so that ida idle state is consistent with * pdev->ide_cap. */ ida_init(&pdev->ide_stream_ida); if (!pci_is_pcie(pdev)) return; ide_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_IDE); if (!ide_cap) return; pci_read_config_dword(pdev, ide_cap + PCI_IDE_CAP, &val); if ((val & PCI_IDE_CAP_SELECTIVE) == 0) return; /* * Require endpoint IDE capability to be paired with IDE Root Port IDE * capability. */ if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ENDPOINT) { struct pci_dev *rp = pcie_find_root_port(pdev); if (!rp->ide_cap) return; } pdev->ide_cfg = FIELD_GET(PCI_IDE_CAP_SEL_CFG, val); pdev->ide_tee_limit = FIELD_GET(PCI_IDE_CAP_TEE_LIMITED, val); if (val & PCI_IDE_CAP_LINK) nr_link_ide = 1 + FIELD_GET(PCI_IDE_CAP_LINK_TC_NUM, val); else nr_link_ide = 0; nr_ide_mem = 0; nr_streams = 1 + FIELD_GET(PCI_IDE_CAP_SEL_NUM, val); for (u16 i = 0; i < nr_streams; i++) { int pos = __sel_ide_offset(ide_cap, nr_link_ide, i, nr_ide_mem); int nr_assoc; u32 val; u8 id; pci_read_config_dword(pdev, pos + PCI_IDE_SEL_CAP, &val); /* * Let's not entertain streams that do not have a constant * number of address association blocks */ nr_assoc = FIELD_GET(PCI_IDE_SEL_CAP_ASSOC_NUM, val); if (i && (nr_assoc != nr_ide_mem)) { pci_info(pdev, "Unsupported Selective Stream %d capability, SKIP the rest\n", i); nr_streams = i; break; } nr_ide_mem = nr_assoc; /* * Claim Stream IDs and Selective Stream blocks that are already * active on the device */ pci_read_config_dword(pdev, pos + PCI_IDE_SEL_CTL, &val); id = FIELD_GET(PCI_IDE_SEL_CTL_ID, val); if ((val & PCI_IDE_SEL_CTL_EN) && !claim_stream(hb, id, pdev, i)) return; } /* Reserve link stream-ids that are already active on the device */ for (u16 i = 0; i < nr_link_ide; ++i) { int pos = ide_cap + PCI_IDE_LINK_STREAM_0 + i * PCI_IDE_LINK_BLOCK_SIZE; u8 id; pci_read_config_dword(pdev, pos + PCI_IDE_LINK_CTL_0, &val); id = FIELD_GET(PCI_IDE_LINK_CTL_ID, val); if ((val & PCI_IDE_LINK_CTL_EN) && !claim_stream(hb, id, NULL, -1)) return; } for (u16 i = 0; i < nr_streams; i++) { int pos = __sel_ide_offset(ide_cap, nr_link_ide, i, nr_ide_mem); pci_read_config_dword(pdev, pos + PCI_IDE_SEL_CTL, &val); if (val & PCI_IDE_SEL_CTL_EN) continue; FIELD_MODIFY(PCI_IDE_SEL_CTL_ID, &val, PCI_IDE_RESERVED_STREAM_ID); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_CTL, val); } for (u16 i = 0; i < nr_link_ide; ++i) { int pos = ide_cap + PCI_IDE_LINK_STREAM_0 + i * PCI_IDE_LINK_BLOCK_SIZE; pci_read_config_dword(pdev, pos, &val); if (val & PCI_IDE_LINK_CTL_EN) continue; FIELD_MODIFY(PCI_IDE_LINK_CTL_ID, &val, PCI_IDE_RESERVED_STREAM_ID); pci_write_config_dword(pdev, pos, val); } pdev->ide_cap = ide_cap; pdev->nr_link_ide = nr_link_ide; pdev->nr_sel_ide = nr_streams; pdev->nr_ide_mem = nr_ide_mem; } struct stream_index { struct ida *ida; u8 stream_index; }; static void free_stream_index(struct stream_index *stream) { ida_free(stream->ida, stream->stream_index); } DEFINE_FREE(free_stream, struct stream_index *, if (_T) free_stream_index(_T)) static struct stream_index *alloc_stream_index(struct ida *ida, u16 max, struct stream_index *stream) { int id; if (!max) return NULL; id = ida_alloc_max(ida, max - 1, GFP_KERNEL); if (id < 0) return NULL; *stream = (struct stream_index) { .ida = ida, .stream_index = id, }; return stream; } /** * pci_ide_stream_alloc() - Reserve stream indices and probe for settings * @pdev: IDE capable PCIe Endpoint Physical Function * * Retrieve the Requester ID range of @pdev for programming its Root * Port IDE RID Association registers, and conversely retrieve the * Requester ID of the Root Port for programming @pdev's IDE RID * Association registers. * * Allocate a Selective IDE Stream Register Block instance per port. * * Allocate a platform stream resource from the associated host bridge. * Retrieve stream association parameters for Requester ID range and * address range restrictions for the stream. */ struct pci_ide *pci_ide_stream_alloc(struct pci_dev *pdev) { /* EP, RP, + HB Stream allocation */ struct stream_index __stream[PCI_IDE_HB + 1]; struct pci_bus_region pref_assoc = { 0, -1 }; struct pci_bus_region mem_assoc = { 0, -1 }; struct resource *mem, *pref; struct pci_host_bridge *hb; struct pci_dev *rp, *br; int num_vf, rid_end; if (!pci_is_pcie(pdev)) return NULL; if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ENDPOINT) return NULL; if (!pdev->ide_cap) return NULL; struct pci_ide *ide __free(kfree) = kzalloc_obj(*ide); if (!ide) return NULL; hb = pci_find_host_bridge(pdev->bus); struct stream_index *hb_stream __free(free_stream) = alloc_stream_index( &hb->ide_stream_ida, hb->nr_ide_streams, &__stream[PCI_IDE_HB]); if (!hb_stream) return NULL; rp = pcie_find_root_port(pdev); struct stream_index *rp_stream __free(free_stream) = alloc_stream_index( &rp->ide_stream_ida, rp->nr_sel_ide, &__stream[PCI_IDE_RP]); if (!rp_stream) return NULL; struct stream_index *ep_stream __free(free_stream) = alloc_stream_index( &pdev->ide_stream_ida, pdev->nr_sel_ide, &__stream[PCI_IDE_EP]); if (!ep_stream) return NULL; /* for SR-IOV case, cover all VFs */ num_vf = pci_num_vf(pdev); if (num_vf) rid_end = PCI_DEVID(pci_iov_virtfn_bus(pdev, num_vf - 1), pci_iov_virtfn_devfn(pdev, num_vf - 1)); else rid_end = pci_dev_id(pdev); br = pci_upstream_bridge(pdev); if (!br) return NULL; /* * Check if the device consumes memory and/or prefetch-memory. Setup * downstream address association ranges for each. */ mem = pci_resource_n(br, PCI_BRIDGE_MEM_WINDOW); pref = pci_resource_n(br, PCI_BRIDGE_PREF_MEM_WINDOW); if (resource_assigned(mem)) pcibios_resource_to_bus(br->bus, &mem_assoc, mem); if (resource_assigned(pref)) pcibios_resource_to_bus(br->bus, &pref_assoc, pref); *ide = (struct pci_ide) { .pdev = pdev, .partner = { [PCI_IDE_EP] = { .rid_start = pci_dev_id(rp), .rid_end = pci_dev_id(rp), .stream_index = no_free_ptr(ep_stream)->stream_index, /* Disable upstream address association */ .mem_assoc = { 0, -1 }, .pref_assoc = { 0, -1 }, }, [PCI_IDE_RP] = { .rid_start = pci_dev_id(pdev), .rid_end = rid_end, .stream_index = no_free_ptr(rp_stream)->stream_index, .mem_assoc = mem_assoc, .pref_assoc = pref_assoc, }, }, .host_bridge_stream = no_free_ptr(hb_stream)->stream_index, .stream_id = -1, }; return_ptr(ide); } EXPORT_SYMBOL_GPL(pci_ide_stream_alloc); /** * pci_ide_stream_free() - unwind pci_ide_stream_alloc() * @ide: idle IDE settings descriptor * * Free all of the stream index (register block) allocations acquired by * pci_ide_stream_alloc(). The stream represented by @ide is assumed to * be unregistered and not instantiated in any device. */ void pci_ide_stream_free(struct pci_ide *ide) { struct pci_dev *pdev = ide->pdev; struct pci_dev *rp = pcie_find_root_port(pdev); struct pci_host_bridge *hb = pci_find_host_bridge(pdev->bus); ida_free(&pdev->ide_stream_ida, ide->partner[PCI_IDE_EP].stream_index); ida_free(&rp->ide_stream_ida, ide->partner[PCI_IDE_RP].stream_index); ida_free(&hb->ide_stream_ida, ide->host_bridge_stream); kfree(ide); } EXPORT_SYMBOL_GPL(pci_ide_stream_free); /** * pci_ide_stream_release() - unwind and release an @ide context * @ide: partially or fully registered IDE settings descriptor * * In support of automatic cleanup of IDE setup routines perform IDE * teardown in expected reverse order of setup and with respect to which * aspects of IDE setup have successfully completed. * * Be careful that setup order mirrors this shutdown order. Otherwise, * open code releasing the IDE context. */ void pci_ide_stream_release(struct pci_ide *ide) { struct pci_dev *pdev = ide->pdev; struct pci_dev *rp = pcie_find_root_port(pdev); if (ide->partner[PCI_IDE_RP].enable) pci_ide_stream_disable(rp, ide); if (ide->partner[PCI_IDE_EP].enable) pci_ide_stream_disable(pdev, ide); if (ide->partner[PCI_IDE_RP].setup) pci_ide_stream_teardown(rp, ide); if (ide->partner[PCI_IDE_EP].setup) pci_ide_stream_teardown(pdev, ide); if (ide->name) pci_ide_stream_unregister(ide); pci_ide_stream_free(ide); } EXPORT_SYMBOL_GPL(pci_ide_stream_release); struct pci_ide_stream_id { struct pci_host_bridge *hb; u8 stream_id; }; static struct pci_ide_stream_id * request_stream_id(struct pci_host_bridge *hb, u8 stream_id, struct pci_ide_stream_id *sid) { if (!reserve_stream_id(hb, stream_id)) return NULL; *sid = (struct pci_ide_stream_id) { .hb = hb, .stream_id = stream_id, }; return sid; } DEFINE_FREE(free_stream_id, struct pci_ide_stream_id *, if (_T) ida_free(&_T->hb->ide_stream_ids_ida, _T->stream_id)) /** * pci_ide_stream_register() - Prepare to activate an IDE Stream * @ide: IDE settings descriptor * * After a Stream ID has been acquired for @ide, record the presence of * the stream in sysfs. The expectation is that @ide is immutable while * registered. */ int pci_ide_stream_register(struct pci_ide *ide) { struct pci_dev *pdev = ide->pdev; struct pci_host_bridge *hb = pci_find_host_bridge(pdev->bus); struct pci_ide_stream_id __sid; u8 ep_stream, rp_stream; int rc; if (ide->stream_id < 0 || ide->stream_id > U8_MAX) { pci_err(pdev, "Setup fail: Invalid Stream ID: %d\n", ide->stream_id); return -ENXIO; } struct pci_ide_stream_id *sid __free(free_stream_id) = request_stream_id(hb, ide->stream_id, &__sid); if (!sid) { pci_err(pdev, "Setup fail: Stream ID %d in use\n", ide->stream_id); return -EBUSY; } ep_stream = ide->partner[PCI_IDE_EP].stream_index; rp_stream = ide->partner[PCI_IDE_RP].stream_index; const char *name __free(kfree) = kasprintf(GFP_KERNEL, "stream%d.%d.%d", ide->host_bridge_stream, rp_stream, ep_stream); if (!name) return -ENOMEM; rc = sysfs_create_link(&hb->dev.kobj, &pdev->dev.kobj, name); if (rc) return rc; ide->name = no_free_ptr(name); /* Stream ID reservation recorded in @ide is now successfully registered */ retain_and_null_ptr(sid); return 0; } EXPORT_SYMBOL_GPL(pci_ide_stream_register); /** * pci_ide_stream_unregister() - unwind pci_ide_stream_register() * @ide: idle IDE settings descriptor * * In preparation for freeing @ide, remove sysfs enumeration for the * stream. */ void pci_ide_stream_unregister(struct pci_ide *ide) { struct pci_dev *pdev = ide->pdev; struct pci_host_bridge *hb = pci_find_host_bridge(pdev->bus); sysfs_remove_link(&hb->dev.kobj, ide->name); kfree(ide->name); ida_free(&hb->ide_stream_ids_ida, ide->stream_id); ide->name = NULL; } EXPORT_SYMBOL_GPL(pci_ide_stream_unregister); static int pci_ide_domain(struct pci_dev *pdev) { if (pdev->fm_enabled) return pci_domain_nr(pdev->bus); return 0; } struct pci_ide_partner *pci_ide_to_settings(struct pci_dev *pdev, struct pci_ide *ide) { if (!pci_is_pcie(pdev)) { pci_warn_once(pdev, "not a PCIe device\n"); return NULL; } switch (pci_pcie_type(pdev)) { case PCI_EXP_TYPE_ENDPOINT: if (pdev != ide->pdev) { pci_warn_once(pdev, "setup expected Endpoint: %s\n", pci_name(ide->pdev)); return NULL; } return &ide->partner[PCI_IDE_EP]; case PCI_EXP_TYPE_ROOT_PORT: { struct pci_dev *rp = pcie_find_root_port(ide->pdev); if (pdev != rp) { pci_warn_once(pdev, "setup expected Root Port: %s\n", pci_name(rp)); return NULL; } return &ide->partner[PCI_IDE_RP]; } default: pci_warn_once(pdev, "invalid device type\n"); return NULL; } } EXPORT_SYMBOL_GPL(pci_ide_to_settings); static void set_ide_sel_ctl(struct pci_dev *pdev, struct pci_ide *ide, struct pci_ide_partner *settings, int pos, bool enable) { u32 val = FIELD_PREP(PCI_IDE_SEL_CTL_ID, ide->stream_id) | FIELD_PREP(PCI_IDE_SEL_CTL_DEFAULT, settings->default_stream) | FIELD_PREP(PCI_IDE_SEL_CTL_CFG_EN, pdev->ide_cfg) | FIELD_PREP(PCI_IDE_SEL_CTL_TEE_LIMITED, pdev->ide_tee_limit) | FIELD_PREP(PCI_IDE_SEL_CTL_EN, enable); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_CTL, val); } #define SEL_ADDR1_LOWER GENMASK(31, 20) #define SEL_ADDR_UPPER GENMASK_ULL(63, 32) #define PREP_PCI_IDE_SEL_ADDR1(base, limit) \ (FIELD_PREP(PCI_IDE_SEL_ADDR_1_VALID, 1) | \ FIELD_PREP(PCI_IDE_SEL_ADDR_1_BASE_LOW, \ FIELD_GET(SEL_ADDR1_LOWER, (base))) | \ FIELD_PREP(PCI_IDE_SEL_ADDR_1_LIMIT_LOW, \ FIELD_GET(SEL_ADDR1_LOWER, (limit)))) static void mem_assoc_to_regs(struct pci_bus_region *region, struct pci_ide_regs *regs, int idx) { /* convert to u64 range for bitfield size checks */ struct range r = { region->start, region->end }; regs->addr[idx].assoc1 = PREP_PCI_IDE_SEL_ADDR1(r.start, r.end); regs->addr[idx].assoc2 = FIELD_GET(SEL_ADDR_UPPER, r.end); regs->addr[idx].assoc3 = FIELD_GET(SEL_ADDR_UPPER, r.start); } /** * pci_ide_stream_to_regs() - convert IDE settings to association register values * @pdev: PCIe device object for either a Root Port or Endpoint Partner Port * @ide: registered IDE settings descriptor * @regs: output register values */ static void pci_ide_stream_to_regs(struct pci_dev *pdev, struct pci_ide *ide, struct pci_ide_regs *regs) { struct pci_ide_partner *settings = pci_ide_to_settings(pdev, ide); int assoc_idx = 0; memset(regs, 0, sizeof(*regs)); if (!settings) return; regs->rid1 = FIELD_PREP(PCI_IDE_SEL_RID_1_LIMIT, settings->rid_end); regs->rid2 = FIELD_PREP(PCI_IDE_SEL_RID_2_VALID, 1) | FIELD_PREP(PCI_IDE_SEL_RID_2_BASE, settings->rid_start) | FIELD_PREP(PCI_IDE_SEL_RID_2_SEG, pci_ide_domain(pdev)); if (pdev->nr_ide_mem && pci_bus_region_size(&settings->mem_assoc)) { mem_assoc_to_regs(&settings->mem_assoc, regs, assoc_idx); assoc_idx++; } if (pdev->nr_ide_mem > assoc_idx && pci_bus_region_size(&settings->pref_assoc)) { mem_assoc_to_regs(&settings->pref_assoc, regs, assoc_idx); assoc_idx++; } regs->nr_addr = assoc_idx; } /** * pci_ide_stream_setup() - program settings to Selective IDE Stream registers * @pdev: PCIe device object for either a Root Port or Endpoint Partner Port * @ide: registered IDE settings descriptor * * When @pdev is a PCI_EXP_TYPE_ENDPOINT then the PCI_IDE_EP partner * settings are written to @pdev's Selective IDE Stream register block, * and when @pdev is a PCI_EXP_TYPE_ROOT_PORT, the PCI_IDE_RP settings * are selected. */ void pci_ide_stream_setup(struct pci_dev *pdev, struct pci_ide *ide) { struct pci_ide_partner *settings = pci_ide_to_settings(pdev, ide); struct pci_ide_regs regs; int pos; if (!settings) return; pci_ide_stream_to_regs(pdev, ide, ®s); pos = sel_ide_offset(pdev, settings); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_RID_1, regs.rid1); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_RID_2, regs.rid2); for (int i = 0; i < regs.nr_addr; i++) { pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_1(i), regs.addr[i].assoc1); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_2(i), regs.addr[i].assoc2); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_3(i), regs.addr[i].assoc3); } /* clear extra unused address association blocks */ for (int i = regs.nr_addr; i < pdev->nr_ide_mem; i++) { pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_1(i), 0); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_2(i), 0); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_3(i), 0); } /* * Setup control register early for devices that expect * stream_id is set during key programming. */ set_ide_sel_ctl(pdev, ide, settings, pos, false); settings->setup = 1; } EXPORT_SYMBOL_GPL(pci_ide_stream_setup); /** * pci_ide_stream_teardown() - disable the stream and clear all settings * @pdev: PCIe device object for either a Root Port or Endpoint Partner Port * @ide: registered IDE settings descriptor * * For stream destruction, zero all registers that may have been written * by pci_ide_stream_setup(). Consider pci_ide_stream_disable() to leave * settings in place while temporarily disabling the stream. */ void pci_ide_stream_teardown(struct pci_dev *pdev, struct pci_ide *ide) { struct pci_ide_partner *settings = pci_ide_to_settings(pdev, ide); int pos, i; if (!settings) return; pos = sel_ide_offset(pdev, settings); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_CTL, 0); for (i = 0; i < pdev->nr_ide_mem; i++) { pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_1(i), 0); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_2(i), 0); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_3(i), 0); } pci_write_config_dword(pdev, pos + PCI_IDE_SEL_RID_2, 0); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_RID_1, 0); settings->setup = 0; } EXPORT_SYMBOL_GPL(pci_ide_stream_teardown); /** * pci_ide_stream_enable() - enable a Selective IDE Stream * @pdev: PCIe device object for either a Root Port or Endpoint Partner Port * @ide: registered and setup IDE settings descriptor * * Activate the stream by writing to the Selective IDE Stream Control * Register. * * Return: 0 if the stream successfully entered the "secure" state, and -EINVAL * if @ide is invalid, and -ENXIO if the stream fails to enter the secure state. * * Note that the state may go "insecure" at any point after returning 0, but * those events are equivalent to a "link down" event and handled via * asynchronous error reporting. * * Caller is responsible to clear the enable bit in the -ENXIO case. */ int pci_ide_stream_enable(struct pci_dev *pdev, struct pci_ide *ide) { struct pci_ide_partner *settings = pci_ide_to_settings(pdev, ide); int pos; u32 val; if (!settings) return -EINVAL; pos = sel_ide_offset(pdev, settings); set_ide_sel_ctl(pdev, ide, settings, pos, true); settings->enable = 1; pci_read_config_dword(pdev, pos + PCI_IDE_SEL_STS, &val); if (FIELD_GET(PCI_IDE_SEL_STS_STATE, val) != PCI_IDE_SEL_STS_STATE_SECURE) return -ENXIO; return 0; } EXPORT_SYMBOL_GPL(pci_ide_stream_enable); /** * pci_ide_stream_disable() - disable a Selective IDE Stream * @pdev: PCIe device object for either a Root Port or Endpoint Partner Port * @ide: registered and setup IDE settings descriptor * * Clear the Selective IDE Stream Control Register, but leave all other * registers untouched. */ void pci_ide_stream_disable(struct pci_dev *pdev, struct pci_ide *ide) { struct pci_ide_partner *settings = pci_ide_to_settings(pdev, ide); int pos; if (!settings) return; pos = sel_ide_offset(pdev, settings); pci_write_config_dword(pdev, pos + PCI_IDE_SEL_CTL, 0); settings->enable = 0; } EXPORT_SYMBOL_GPL(pci_ide_stream_disable); void pci_ide_init_host_bridge(struct pci_host_bridge *hb) { hb->nr_ide_streams = 256; ida_init(&hb->ide_stream_ida); ida_init(&hb->ide_stream_ids_ida); reserve_stream_id(hb, PCI_IDE_RESERVED_STREAM_ID); } static ssize_t available_secure_streams_show(struct device *dev, struct device_attribute *attr, char *buf) { struct pci_host_bridge *hb = to_pci_host_bridge(dev); int nr = READ_ONCE(hb->nr_ide_streams); int avail = nr; if (!nr) return -ENXIO; /* * Yes, this is inefficient and racy, but it is only for occasional * platform resource surveys. Worst case is bounded to 256 streams. */ for (int i = 0; i < nr; i++) if (ida_exists(&hb->ide_stream_ida, i)) avail--; return sysfs_emit(buf, "%d\n", avail); } static DEVICE_ATTR_RO(available_secure_streams); static struct attribute *pci_ide_attrs[] = { &dev_attr_available_secure_streams.attr, NULL }; static umode_t pci_ide_attr_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = kobj_to_dev(kobj); struct pci_host_bridge *hb = to_pci_host_bridge(dev); if (a == &dev_attr_available_secure_streams.attr) if (!hb->nr_ide_streams) return 0; return a->mode; } const struct attribute_group pci_ide_attr_group = { .attrs = pci_ide_attrs, .is_visible = pci_ide_attr_visible, }; /** * pci_ide_set_nr_streams() - sets size of the pool of IDE Stream resources * @hb: host bridge boundary for the stream pool * @nr: number of streams * * Platform PCI init and/or expert test module use only. Limit IDE * Stream establishment by setting the number of stream resources * available at the host bridge. Platform init code must set this before * the first pci_ide_stream_alloc() call if the platform has less than the * default of 256 streams per host-bridge. * * The "PCI_IDE" symbol namespace is required because this is typically * a detail that is settled in early PCI init. I.e. this export is not * for endpoint drivers. */ void pci_ide_set_nr_streams(struct pci_host_bridge *hb, u16 nr) { hb->nr_ide_streams = min(nr, 256); WARN_ON_ONCE(!ida_is_empty(&hb->ide_stream_ida)); sysfs_update_group(&hb->dev.kobj, &pci_ide_attr_group); } EXPORT_SYMBOL_NS_GPL(pci_ide_set_nr_streams, "PCI_IDE"); void pci_ide_destroy(struct pci_dev *pdev) { ida_destroy(&pdev->ide_stream_ida); } |
| 2 9 10 10 10 10 10 10 10 10 10 10 9 10 10 10 10 2 8 2 8 8 11 1 2 8 8 8 8 8 11 1 11 11 3 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Red Hat, Inc. * Copyright (C) 2016-2023 Christoph Hellwig. */ #include <linux/iomap.h> #include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/swap.h> #include <linux/migrate.h> #include <linux/fserror.h> #include <linux/fsverity.h> #include "internal.h" #include "trace.h" #include "../internal.h" /* * Structure allocated for each folio to track per-block uptodate, dirty state * and I/O completions. */ struct iomap_folio_state { spinlock_t state_lock; unsigned int read_bytes_pending; atomic_t write_bytes_pending; /* * Each block has two bits in this bitmap: * Bits [0..blocks_per_folio) has the uptodate status. * Bits [b_p_f...(2*b_p_f)) has the dirty status. */ unsigned long state[]; }; static inline bool ifs_is_fully_uptodate(struct folio *folio, struct iomap_folio_state *ifs) { struct inode *inode = folio->mapping->host; return bitmap_full(ifs->state, i_blocks_per_folio(inode, folio)); } /* * Find the next uptodate block in the folio. end_blk is inclusive. * If no uptodate block is found, this will return end_blk + 1. */ static unsigned ifs_next_uptodate_block(struct folio *folio, unsigned start_blk, unsigned end_blk) { struct iomap_folio_state *ifs = folio->private; return find_next_bit(ifs->state, end_blk + 1, start_blk); } /* * Find the next non-uptodate block in the folio. end_blk is inclusive. * If no non-uptodate block is found, this will return end_blk + 1. */ static unsigned ifs_next_nonuptodate_block(struct folio *folio, unsigned start_blk, unsigned end_blk) { struct iomap_folio_state *ifs = folio->private; return find_next_zero_bit(ifs->state, end_blk + 1, start_blk); } static bool ifs_set_range_uptodate(struct folio *folio, struct iomap_folio_state *ifs, size_t off, size_t len) { struct inode *inode = folio->mapping->host; unsigned int first_blk, last_blk; if (len) { first_blk = off >> inode->i_blkbits; last_blk = (off + len - 1) >> inode->i_blkbits; bitmap_set(ifs->state, first_blk, last_blk - first_blk + 1); } return ifs_is_fully_uptodate(folio, ifs); } static void iomap_set_range_uptodate(struct folio *folio, size_t off, size_t len) { struct iomap_folio_state *ifs = folio->private; unsigned long flags; bool mark_uptodate = true; if (folio_test_uptodate(folio)) return; if (ifs) { spin_lock_irqsave(&ifs->state_lock, flags); /* * If a read with bytes pending is in progress, we must not call * folio_mark_uptodate(). The read completion path * (iomap_read_end()) will call folio_end_read(), which uses XOR * semantics to set the uptodate bit. If we set it here, the XOR * in folio_end_read() will clear it, leaving the folio not * uptodate. */ mark_uptodate = ifs_set_range_uptodate(folio, ifs, off, len) && !ifs->read_bytes_pending; spin_unlock_irqrestore(&ifs->state_lock, flags); } if (mark_uptodate) folio_mark_uptodate(folio); } /* * Find the next dirty block in the folio. end_blk is inclusive. * If no dirty block is found, this will return end_blk + 1. */ static unsigned ifs_next_dirty_block(struct folio *folio, unsigned start_blk, unsigned end_blk) { struct iomap_folio_state *ifs = folio->private; struct inode *inode = folio->mapping->host; unsigned int blks = i_blocks_per_folio(inode, folio); return find_next_bit(ifs->state, blks + end_blk + 1, blks + start_blk) - blks; } /* * Find the next clean block in the folio. end_blk is inclusive. * If no clean block is found, this will return end_blk + 1. */ static unsigned ifs_next_clean_block(struct folio *folio, unsigned start_blk, unsigned end_blk) { struct iomap_folio_state *ifs = folio->private; struct inode *inode = folio->mapping->host; unsigned int blks = i_blocks_per_folio(inode, folio); return find_next_zero_bit(ifs->state, blks + end_blk + 1, blks + start_blk) - blks; } static unsigned ifs_find_dirty_range(struct folio *folio, struct iomap_folio_state *ifs, u64 *range_start, u64 range_end) { struct inode *inode = folio->mapping->host; unsigned start_blk = offset_in_folio(folio, *range_start) >> inode->i_blkbits; unsigned end_blk = min_not_zero( offset_in_folio(folio, range_end) >> inode->i_blkbits, i_blocks_per_folio(inode, folio)) - 1; unsigned nblks; start_blk = ifs_next_dirty_block(folio, start_blk, end_blk); if (start_blk > end_blk) return 0; if (start_blk == end_blk) nblks = 1; else nblks = ifs_next_clean_block(folio, start_blk + 1, end_blk) - start_blk; *range_start = folio_pos(folio) + (start_blk << inode->i_blkbits); return nblks << inode->i_blkbits; } static unsigned iomap_find_dirty_range(struct folio *folio, u64 *range_start, u64 range_end) { struct iomap_folio_state *ifs = folio->private; if (*range_start >= range_end) return 0; if (ifs) return ifs_find_dirty_range(folio, ifs, range_start, range_end); return range_end - *range_start; } /* * Clear the per-block dirty bits for the range [@off, @off + @len) within a * folio. The range is rounded inwards so that only blocks fully covered by * the range are cleared. This is required for operations like folio * invalidation, where we must ensure a block is fully clean before discarding * it. */ static void ifs_clear_range_dirty(struct folio *folio, struct iomap_folio_state *ifs, size_t off, size_t len) { struct inode *inode = folio->mapping->host; unsigned int blks_per_folio = i_blocks_per_folio(inode, folio); unsigned int first_blk = round_up(off, i_blocksize(inode)) >> inode->i_blkbits; unsigned int last_blk = (off + len) >> inode->i_blkbits; unsigned long flags; if (first_blk >= last_blk) return; spin_lock_irqsave(&ifs->state_lock, flags); bitmap_clear(ifs->state, first_blk + blks_per_folio, last_blk - first_blk); spin_unlock_irqrestore(&ifs->state_lock, flags); } static void iomap_clear_range_dirty(struct folio *folio, size_t off, size_t len) { struct iomap_folio_state *ifs = folio->private; if (ifs) ifs_clear_range_dirty(folio, ifs, off, len); } /* * Set the per-block dirty bits for the range [@off, @off + @len) within a * folio. The range is rounded outwards so that any block partially touched * by the range is marked dirty. This ensures blocks containing even a * single dirty byte will be included in subsequent writeback, preventing * data loss when partial blocks are written. */ static void ifs_set_range_dirty(struct folio *folio, struct iomap_folio_state *ifs, size_t off, size_t len) { struct inode *inode = folio->mapping->host; unsigned int blks_per_folio = i_blocks_per_folio(inode, folio); unsigned int first_blk, last_blk; unsigned long flags; if (!len) return; first_blk = off >> inode->i_blkbits; last_blk = (off + len - 1) >> inode->i_blkbits; spin_lock_irqsave(&ifs->state_lock, flags); bitmap_set(ifs->state, first_blk + blks_per_folio, last_blk - first_blk + 1); spin_unlock_irqrestore(&ifs->state_lock, flags); } static void iomap_set_range_dirty(struct folio *folio, size_t off, size_t len) { struct iomap_folio_state *ifs = folio->private; if (ifs) ifs_set_range_dirty(folio, ifs, off, len); } static struct iomap_folio_state *ifs_alloc(struct inode *inode, struct folio *folio, unsigned int flags) { struct iomap_folio_state *ifs = folio->private; unsigned int nr_blocks = i_blocks_per_folio(inode, folio); gfp_t gfp; if (ifs || nr_blocks <= 1) return ifs; if (flags & IOMAP_NOWAIT) gfp = GFP_NOWAIT; else gfp = GFP_NOFS | __GFP_NOFAIL; /* * ifs->state tracks two sets of state flags when the * filesystem block size is smaller than the folio size. * The first state tracks per-block uptodate and the * second tracks per-block dirty state. */ ifs = kzalloc_flex(*ifs, state, BITS_TO_LONGS(2 * nr_blocks), gfp); if (!ifs) return ifs; spin_lock_init(&ifs->state_lock); if (folio_test_uptodate(folio)) bitmap_set(ifs->state, 0, nr_blocks); if (folio_test_dirty(folio)) bitmap_set(ifs->state, nr_blocks, nr_blocks); folio_attach_private(folio, ifs); return ifs; } static void ifs_free(struct folio *folio) { struct iomap_folio_state *ifs = folio_detach_private(folio); if (!ifs) return; WARN_ON_ONCE(ifs->read_bytes_pending != 0); WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending)); WARN_ON_ONCE(ifs_is_fully_uptodate(folio, ifs) != folio_test_uptodate(folio)); kfree(ifs); } /* * Calculate how many bytes to truncate based off the number of blocks to * truncate and the end position to start truncating from. */ static size_t iomap_bytes_to_truncate(loff_t end_pos, unsigned block_bits, unsigned blocks_truncated) { unsigned block_size = 1 << block_bits; unsigned block_offset = end_pos & (block_size - 1); if (!block_offset) return blocks_truncated << block_bits; return ((blocks_truncated - 1) << block_bits) + block_offset; } /* * Calculate the range inside the folio that we actually need to read. */ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, loff_t *pos, loff_t length, size_t *offp, size_t *lenp) { struct iomap_folio_state *ifs = folio->private; loff_t orig_pos = *pos; loff_t isize = i_size_read(inode); unsigned block_bits = inode->i_blkbits; unsigned block_size = (1 << block_bits); size_t poff = offset_in_folio(folio, *pos); size_t plen = min_t(loff_t, folio_size(folio) - poff, length); size_t orig_plen = plen; unsigned first = poff >> block_bits; unsigned last = (poff + plen - 1) >> block_bits; /* * If the block size is smaller than the page size, we need to check the * per-block uptodate status and adjust the offset and length if needed * to avoid reading in already uptodate ranges. */ if (ifs) { unsigned int next, blocks_skipped; next = ifs_next_nonuptodate_block(folio, first, last); blocks_skipped = next - first; if (blocks_skipped) { unsigned long block_offset = *pos & (block_size - 1); unsigned bytes_skipped = (blocks_skipped << block_bits) - block_offset; *pos += bytes_skipped; poff += bytes_skipped; plen -= bytes_skipped; } first = next; /* truncate len if we find any trailing uptodate block(s) */ if (++next <= last) { next = ifs_next_uptodate_block(folio, next, last); if (next <= last) { plen -= iomap_bytes_to_truncate(*pos + plen, block_bits, last - next + 1); last = next - 1; } } } /* * If the extent spans the block that contains the i_size, we need to * handle both halves separately so that we properly zero data in the * page cache for blocks that are entirely outside of i_size. */ if (orig_pos <= isize && orig_pos + orig_plen > isize) { unsigned end = offset_in_folio(folio, isize - 1) >> block_bits; if (first <= end && last > end) plen -= iomap_bytes_to_truncate(*pos + plen, block_bits, last - end); } *offp = poff; *lenp = plen; } static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter, loff_t pos) { const struct iomap *srcmap = iomap_iter_srcmap(iter); /* * If this block has not been written, there's nothing to read */ if (srcmap->type != IOMAP_MAPPED) return true; /* * Newly allocated blocks have not been written */ if (srcmap->flags & IOMAP_F_NEW) return true; /* * fsverity metadata is stored past i_size, we need to read it instead * of zeroing */ if (srcmap->flags & IOMAP_F_FSVERITY) return false; return pos >= i_size_read(iter->inode); } /** * iomap_read_inline_data - copy inline data into the page cache * @iter: iteration structure * @folio: folio to copy to * * Copy the inline data in @iter into @folio and zero out the rest of the folio. * Only a single IOMAP_INLINE extent is allowed at the end of each file. * Returns zero for success to complete the read, or the usual negative errno. */ static int iomap_read_inline_data(const struct iomap_iter *iter, struct folio *folio) { const struct iomap *iomap = iomap_iter_srcmap(iter); size_t size = i_size_read(iter->inode) - iomap->offset; size_t offset = offset_in_folio(folio, iomap->offset); if (WARN_ON_ONCE(!iomap->inline_data)) return -EIO; if (folio_test_uptodate(folio)) return 0; if (WARN_ON_ONCE(size > iomap->length)) { fserror_report_io(iter->inode, FSERR_BUFFERED_READ, iomap->offset, size, -EIO, GFP_NOFS); return -EIO; } if (offset > 0) ifs_alloc(iter->inode, folio, iter->flags); folio_fill_tail(folio, offset, iomap->inline_data, size); iomap_set_range_uptodate(folio, offset, folio_size(folio) - offset); return 0; } void iomap_finish_folio_read(struct folio *folio, size_t off, size_t len, int error) { struct iomap_folio_state *ifs = folio->private; bool uptodate = !error; bool finished = true; if (error) fserror_report_io(folio->mapping->host, FSERR_BUFFERED_READ, folio_pos(folio) + off, len, error, GFP_ATOMIC); if (ifs) { unsigned long flags; spin_lock_irqsave(&ifs->state_lock, flags); if (!error) uptodate = ifs_set_range_uptodate(folio, ifs, off, len); ifs->read_bytes_pending -= len; finished = !ifs->read_bytes_pending; spin_unlock_irqrestore(&ifs->state_lock, flags); } if (finished) folio_end_read(folio, uptodate); } EXPORT_SYMBOL_GPL(iomap_finish_folio_read); static void iomap_read_init(struct folio *folio) { struct iomap_folio_state *ifs = folio->private; if (ifs) { /* * ifs->read_bytes_pending is used to track how many bytes are * read in asynchronously by the IO helper. We need to track * this so that we can know when the IO helper has finished * reading in all the necessary ranges of the folio and can end * the read. * * Increase ->read_bytes_pending by the folio size to start. * We'll subtract any uptodate / zeroed ranges that did not * require IO in iomap_read_end() after we're done processing * the folio. * * We do this because otherwise, we would have to increment * ifs->read_bytes_pending every time a range in the folio needs * to be read in, which can get expensive since the spinlock * needs to be held whenever modifying ifs->read_bytes_pending. */ spin_lock_irq(&ifs->state_lock); WARN_ON_ONCE(ifs->read_bytes_pending != 0); ifs->read_bytes_pending = folio_size(folio); spin_unlock_irq(&ifs->state_lock); } } /* * This ends IO if no bytes were submitted to an IO helper. * * Otherwise, this calibrates ifs->read_bytes_pending to represent only the * submitted bytes (see comment in iomap_read_init()). If all bytes submitted * have already been completed by the IO helper, then this will end the read. * Else the IO helper will end the read after all submitted ranges have been * read. */ static void iomap_read_end(struct folio *folio, size_t bytes_submitted) { struct iomap_folio_state *ifs = folio->private; if (ifs) { bool end_read, uptodate; spin_lock_irq(&ifs->state_lock); if (!ifs->read_bytes_pending) { WARN_ON_ONCE(bytes_submitted); spin_unlock_irq(&ifs->state_lock); folio_unlock(folio); return; } /* * Subtract any bytes that were initially accounted to * read_bytes_pending but skipped for IO. */ ifs->read_bytes_pending -= folio_size(folio) - bytes_submitted; /* * If !ifs->read_bytes_pending, this means all pending reads by * the IO helper have already completed, which means we need to * end the folio read here. If ifs->read_bytes_pending != 0, * the IO helper will end the folio read. */ end_read = !ifs->read_bytes_pending; if (end_read) uptodate = ifs_is_fully_uptodate(folio, ifs); spin_unlock_irq(&ifs->state_lock); if (end_read) folio_end_read(folio, uptodate); } else { /* * If a folio without an ifs is submitted to the IO helper, the * read must be on the entire folio and the IO helper takes * ownership of the folio. This means we should only enter * iomap_read_end() for the !ifs case if no bytes were submitted * to the IO helper, in which case we are responsible for * unlocking the folio here. */ WARN_ON_ONCE(bytes_submitted); folio_unlock(folio); } } static int iomap_read_folio_iter(struct iomap_iter *iter, struct iomap_read_folio_ctx *ctx, size_t *bytes_submitted) { const struct iomap *iomap = &iter->iomap; loff_t pos = iter->pos; loff_t length = iomap_length(iter); struct folio *folio = ctx->cur_folio; size_t folio_len = folio_size(folio); struct iomap_folio_state *ifs; size_t poff, plen; loff_t pos_diff; int ret; if (iomap->type == IOMAP_INLINE) { ret = iomap_read_inline_data(iter, folio); if (ret) return ret; return iomap_iter_advance(iter, length); } ifs = ifs_alloc(iter->inode, folio, iter->flags); length = min_t(loff_t, length, folio_len - offset_in_folio(folio, pos)); while (length) { iomap_adjust_read_range(iter->inode, folio, &pos, length, &poff, &plen); pos_diff = pos - iter->pos; if (WARN_ON_ONCE(pos_diff + plen > length)) return -EIO; ret = iomap_iter_advance(iter, pos_diff); if (ret) return ret; if (plen == 0) return 0; /* * Handling of fsverity "holes". We hit this for two case: * 1. No need to go further, the hole after fsverity * descriptor is the end of the fsverity metadata. * * 2. This folio contains merkle tree blocks which need to be * synthesized. If we already have fsverity info (ctx->vi) * synthesize these blocks. */ if ((iomap->flags & IOMAP_F_FSVERITY) && iomap->type == IOMAP_HOLE) { if (ctx->vi) fsverity_fill_zerohash(folio, poff, plen, ctx->vi); iomap_set_range_uptodate(folio, poff, plen); } else if (iomap_block_needs_zeroing(iter, pos)) { /* zero post-eof blocks as the page may be mapped */ folio_zero_range(folio, poff, plen); if (ctx->vi && !fsverity_verify_blocks(ctx->vi, folio, plen, poff)) return -EIO; iomap_set_range_uptodate(folio, poff, plen); } else { if (!*bytes_submitted) iomap_read_init(folio); ret = ctx->ops->read_folio_range(iter, ctx, plen); if (ret < 0) fserror_report_io(iter->inode, FSERR_BUFFERED_READ, pos, plen, ret, GFP_NOFS); if (ret) return ret; *bytes_submitted += plen; /* * Hand off folio ownership to the IO helper when: * 1) The entire folio has been submitted for IO, or * 2) There is no ifs attached to the folio * * Case (2) occurs when 1 << i_blkbits matches the folio * size but the underlying filesystem or block device * uses a smaller granularity for IO. */ if (*bytes_submitted == folio_len || !ifs) ctx->cur_folio = NULL; } ret = iomap_iter_advance(iter, plen); if (ret) return ret; length -= pos_diff + plen; pos = iter->pos; } return 0; } void iomap_read_folio(const struct iomap_ops *ops, struct iomap_read_folio_ctx *ctx, void *private) { struct folio *folio = ctx->cur_folio; struct iomap_iter iter = { .inode = folio->mapping->host, .pos = folio_pos(folio), .len = folio_size(folio), .private = private, }; size_t bytes_submitted = 0; int ret; trace_iomap_readpage(iter.inode, 1); /* * Fetch fsverity_info for both data and fsverity metadata, as iomap * needs zeroed hash for merkle tree block synthesis */ ctx->vi = fsverity_get_info(iter.inode); if (ctx->vi && iter.pos < i_size_read(iter.inode)) fsverity_readahead(ctx->vi, folio->index, folio_nr_pages(folio)); while ((ret = iomap_iter(&iter, ops)) > 0) { iter.status = iomap_read_folio_iter(&iter, ctx, &bytes_submitted); if (ctx->read_ctx && ctx->ops->submit_read) ctx->ops->submit_read(&iter, ctx); } if (ctx->cur_folio) iomap_read_end(ctx->cur_folio, bytes_submitted); } EXPORT_SYMBOL_GPL(iomap_read_folio); static int iomap_readahead_iter(struct iomap_iter *iter, struct iomap_read_folio_ctx *ctx, size_t *cur_bytes_submitted) { int ret; while (iomap_length(iter)) { if (ctx->cur_folio && offset_in_folio(ctx->cur_folio, iter->pos) == 0) { iomap_read_end(ctx->cur_folio, *cur_bytes_submitted); ctx->cur_folio = NULL; } if (!ctx->cur_folio) { ctx->cur_folio = readahead_folio(ctx->rac); if (WARN_ON_ONCE(!ctx->cur_folio)) return -EINVAL; *cur_bytes_submitted = 0; } ret = iomap_read_folio_iter(iter, ctx, cur_bytes_submitted); if (ret) return ret; } return 0; } /** * iomap_readahead - Attempt to read pages from a file. * @ops: The operations vector for the filesystem. * @ctx: The ctx used for issuing readahead. * @private: The filesystem-specific information for issuing iomap_iter. * * This function is for filesystems to call to implement their readahead * address_space operation. * * Context: The @ops callbacks may submit I/O (eg to read the addresses of * blocks from disc), and may wait for it. The caller may be trying to * access a different page, and so sleeping excessively should be avoided. * It may allocate memory, but should avoid costly allocations. This * function is called with memalloc_nofs set, so allocations will not cause * the filesystem to be reentered. */ void iomap_readahead(const struct iomap_ops *ops, struct iomap_read_folio_ctx *ctx, void *private) { struct readahead_control *rac = ctx->rac; struct iomap_iter iter = { .inode = rac->mapping->host, .pos = readahead_pos(rac), .len = readahead_length(rac), .private = private, }; size_t cur_bytes_submitted; trace_iomap_readahead(rac->mapping->host, readahead_count(rac)); /* * Fetch fsverity_info for both data and fsverity metadata, as iomap * needs zeroed hash for merkle tree block synthesis */ ctx->vi = fsverity_get_info(iter.inode); if (ctx->vi && iter.pos < i_size_read(iter.inode)) fsverity_readahead(ctx->vi, readahead_index(rac), readahead_count(rac)); while (iomap_iter(&iter, ops) > 0) { iter.status = iomap_readahead_iter(&iter, ctx, &cur_bytes_submitted); if (ctx->read_ctx && ctx->ops->submit_read) ctx->ops->submit_read(&iter, ctx); } if (ctx->cur_folio) iomap_read_end(ctx->cur_folio, cur_bytes_submitted); } EXPORT_SYMBOL_GPL(iomap_readahead); /* * iomap_is_partially_uptodate checks whether blocks within a folio are * uptodate or not. * * Returns true if all blocks which correspond to the specified part * of the folio are uptodate. */ bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count) { struct iomap_folio_state *ifs = folio->private; struct inode *inode = folio->mapping->host; unsigned first, last; if (!ifs) return false; /* Caller's range may extend past the end of this folio */ count = min(folio_size(folio) - from, count); /* First and last blocks in range within folio */ first = from >> inode->i_blkbits; last = (from + count - 1) >> inode->i_blkbits; return ifs_next_nonuptodate_block(folio, first, last) > last; } EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate); /** * iomap_get_folio - get a folio reference for writing * @iter: iteration structure * @pos: start offset of write * @len: Suggested size of folio to create. * * Returns a locked reference to the folio at @pos, or an error pointer if the * folio could not be obtained. */ struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len) { fgf_t fgp = FGP_WRITEBEGIN | FGP_NOFS; if (iter->flags & IOMAP_NOWAIT) fgp |= FGP_NOWAIT; if (iter->flags & IOMAP_DONTCACHE) fgp |= FGP_DONTCACHE; fgp |= fgf_set_order(len); return __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT, fgp, mapping_gfp_mask(iter->inode->i_mapping)); } EXPORT_SYMBOL_GPL(iomap_get_folio); bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags) { trace_iomap_release_folio(folio->mapping->host, folio_pos(folio), folio_size(folio)); /* * If the folio is dirty, we refuse to release our metadata because * it may be partially dirty. Once we track per-block dirty state, * we can release the metadata if every block is dirty. */ if (folio_test_dirty(folio)) return false; ifs_free(folio); return true; } EXPORT_SYMBOL_GPL(iomap_release_folio); void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len) { trace_iomap_invalidate_folio(folio->mapping->host, folio_pos(folio) + offset, len); /* * If we're invalidating the entire folio, clear the dirty state * from it and release it to avoid unnecessary buildup of the LRU. */ if (offset == 0 && len == folio_size(folio)) { WARN_ON_ONCE(folio_test_writeback(folio)); folio_cancel_dirty(folio); ifs_free(folio); } else { iomap_clear_range_dirty(folio, offset, len); } } EXPORT_SYMBOL_GPL(iomap_invalidate_folio); bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio) { struct inode *inode = mapping->host; size_t len = folio_size(folio); ifs_alloc(inode, folio, 0); iomap_set_range_dirty(folio, 0, len); return filemap_dirty_folio(mapping, folio); } EXPORT_SYMBOL_GPL(iomap_dirty_folio); static void iomap_write_failed(struct inode *inode, loff_t pos, unsigned len) { loff_t i_size = i_size_read(inode); /* * Only truncate newly allocated pages beyoned EOF, even if the * write started inside the existing inode size. */ if (pos + len > i_size) truncate_pagecache_range(inode, max(pos, i_size), pos + len - 1); } static int __iomap_write_begin(const struct iomap_iter *iter, const struct iomap_write_ops *write_ops, size_t len, struct folio *folio) { struct iomap_folio_state *ifs; loff_t pos = iter->pos; loff_t block_size = i_blocksize(iter->inode); loff_t block_start = round_down(pos, block_size); loff_t block_end = round_up(pos + len, block_size); unsigned int nr_blocks = i_blocks_per_folio(iter->inode, folio); size_t from = offset_in_folio(folio, pos), to = from + len; size_t poff, plen; /* * If the write or zeroing completely overlaps the current folio, then * entire folio will be dirtied so there is no need for * per-block state tracking structures to be attached to this folio. * For the unshare case, we must read in the ondisk contents because we * are not changing pagecache contents. */ if (!(iter->flags & IOMAP_UNSHARE) && pos <= folio_pos(folio) && pos + len >= folio_next_pos(folio)) return 0; ifs = ifs_alloc(iter->inode, folio, iter->flags); if ((iter->flags & IOMAP_NOWAIT) && !ifs && nr_blocks > 1) return -EAGAIN; if (folio_test_uptodate(folio)) return 0; do { iomap_adjust_read_range(iter->inode, folio, &block_start, block_end - block_start, &poff, &plen); if (plen == 0) break; /* * If the read range will be entirely overwritten by the write, * we can skip having to zero/read it in. */ if (!(iter->flags & IOMAP_UNSHARE) && from <= poff && to >= poff + plen) continue; if (iomap_block_needs_zeroing(iter, block_start)) { if (WARN_ON_ONCE(iter->flags & IOMAP_UNSHARE)) return -EIO; folio_zero_segments(folio, poff, from, to, poff + plen); } else { const struct iomap *iomap = iomap_iter_srcmap(iter); int status; if (iter->flags & IOMAP_NOWAIT) return -EAGAIN; if (write_ops && write_ops->read_folio_range) status = write_ops->read_folio_range(iter, folio, block_start, plen); else status = iomap_bio_read_folio_range_sync(iter, folio, block_start, plen); if (status < 0) fserror_report_io(iter->inode, FSERR_BUFFERED_READ, pos, plen, status, GFP_NOFS); if (status) return status; if (iomap->flags & IOMAP_F_ZERO_TAIL) folio_zero_segment(folio, to, poff + plen); } iomap_set_range_uptodate(folio, poff, plen); } while ((block_start += plen) < block_end); return 0; } static struct folio *__iomap_get_folio(struct iomap_iter *iter, const struct iomap_write_ops *write_ops, size_t len) { loff_t pos = iter->pos; if (!mapping_large_folio_support(iter->inode->i_mapping)) len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos)); if (iter->iomap.flags & IOMAP_F_FOLIO_BATCH) { struct folio *folio = folio_batch_next(iter->fbatch); if (!folio) return NULL; /* * The folio mapping generally shouldn't have changed based on * fs locks, but be consistent with filemap lookup and retry * the iter if it does. */ folio_lock(folio); if (unlikely(folio->mapping != iter->inode->i_mapping)) { iter->iomap.flags |= IOMAP_F_STALE; folio_unlock(folio); return NULL; } folio_get(folio); folio_wait_stable(folio); return folio; } if (write_ops && write_ops->get_folio) return write_ops->get_folio(iter, pos, len); return iomap_get_folio(iter, pos, len); } static void __iomap_put_folio(struct iomap_iter *iter, const struct iomap_write_ops *write_ops, size_t ret, struct folio *folio) { loff_t pos = iter->pos; if (write_ops && write_ops->put_folio) { write_ops->put_folio(iter->inode, pos, ret, folio); } else { folio_unlock(folio); folio_put(folio); } } /* trim pos and bytes to within a given folio */ static loff_t iomap_trim_folio_range(struct iomap_iter *iter, struct folio *folio, size_t *offset, u64 *bytes) { loff_t pos = iter->pos; size_t fsize = folio_size(folio); WARN_ON_ONCE(pos < folio_pos(folio)); WARN_ON_ONCE(pos >= folio_pos(folio) + fsize); *offset = offset_in_folio(folio, pos); *bytes = min(*bytes, fsize - *offset); return pos; } static int iomap_write_begin_inline(const struct iomap_iter *iter, struct folio *folio) { /* needs more work for the tailpacking case; disable for now */ if (WARN_ON_ONCE(iomap_iter_srcmap(iter)->offset != 0)) return -EIO; return iomap_read_inline_data(iter, folio); } /* * Grab and prepare a folio for write based on iter state. Returns the folio, * offset, and length. Callers can optionally pass a max length *plen, * otherwise init to zero. */ static int iomap_write_begin(struct iomap_iter *iter, const struct iomap_write_ops *write_ops, struct folio **foliop, size_t *poffset, u64 *plen) { const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos; u64 len = min_t(u64, SIZE_MAX, iomap_length(iter)); struct folio *folio; int status = 0; len = min_not_zero(len, *plen); *foliop = NULL; *plen = 0; if (fatal_signal_pending(current)) return -EINTR; folio = __iomap_get_folio(iter, write_ops, len); if (IS_ERR(folio)) return PTR_ERR(folio); /* * No folio means we're done with a batch. We still have range to * process so return and let the caller iterate and refill the batch. */ if (!folio) { WARN_ON_ONCE(!(iter->iomap.flags & IOMAP_F_FOLIO_BATCH)); return 0; } /* * Now we have a locked folio, before we do anything with it we need to * check that the iomap we have cached is not stale. The inode extent * mapping can change due to concurrent IO in flight (e.g. * IOMAP_UNWRITTEN state can change and memory reclaim could have * reclaimed a previously partially written page at this index after IO * completion before this write reaches this file offset) and hence we * could do the wrong thing here (zero a page range incorrectly or fail * to zero) and corrupt data. */ if (write_ops && write_ops->iomap_valid) { bool iomap_valid = write_ops->iomap_valid(iter->inode, &iter->iomap); if (!iomap_valid) { iter->iomap.flags |= IOMAP_F_STALE; status = 0; goto out_unlock; } } /* * The folios in a batch may not be contiguous. If we've skipped * forward, advance the iter to the pos of the current folio. If the * folio starts beyond the end of the mapping, it may have been trimmed * since the lookup for whatever reason. Return a NULL folio to * terminate the op. */ if (folio_pos(folio) > iter->pos) { len = min_t(u64, folio_pos(folio) - iter->pos, iomap_length(iter)); status = iomap_iter_advance(iter, len); len = iomap_length(iter); if (status || !len) goto out_unlock; } pos = iomap_trim_folio_range(iter, folio, poffset, &len); if (srcmap->type == IOMAP_INLINE) status = iomap_write_begin_inline(iter, folio); else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) status = __block_write_begin_int(folio, pos, len, NULL, srcmap); else status = __iomap_write_begin(iter, write_ops, len, folio); if (unlikely(status)) goto out_unlock; *foliop = folio; *plen = len; return 0; out_unlock: __iomap_put_folio(iter, write_ops, 0, folio); return status; } static bool __iomap_write_end(struct inode *inode, loff_t pos, size_t len, size_t copied, struct folio *folio) { flush_dcache_folio(folio); /* * The blocks that were entirely written will now be uptodate, so we * don't have to worry about a read_folio reading them and overwriting a * partial write. However, if we've encountered a short write and only * partially written into a block, it will not be marked uptodate, so a * read_folio might come in and destroy our partial write. * * Do the simplest thing and just treat any short write to a * non-uptodate page as a zero-length write, and force the caller to * redo the whole thing. */ if (unlikely(copied < len && !folio_test_uptodate(folio))) return false; iomap_set_range_uptodate(folio, offset_in_folio(folio, pos), len); iomap_set_range_dirty(folio, offset_in_folio(folio, pos), copied); filemap_dirty_folio(inode->i_mapping, folio); return true; } static bool iomap_write_end_inline(const struct iomap_iter *iter, struct folio *folio, loff_t pos, size_t copied) { const struct iomap *iomap = &iter->iomap; void *addr; WARN_ON_ONCE(!folio_test_uptodate(folio)); if (WARN_ON_ONCE(!iomap->inline_data)) return false; flush_dcache_folio(folio); addr = kmap_local_folio(folio, pos); memcpy(iomap_inline_data(iomap, pos), addr, copied); kunmap_local(addr); mark_inode_dirty(iter->inode); return true; } /* * Returns true if all copied bytes have been written to the pagecache, * otherwise return false. */ static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied, struct folio *folio) { const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; if (srcmap->type == IOMAP_INLINE) return iomap_write_end_inline(iter, folio, pos, copied); if (srcmap->flags & IOMAP_F_BUFFER_HEAD) { size_t bh_written; bh_written = block_write_end(pos, len, copied, folio); WARN_ON_ONCE(bh_written != copied && bh_written != 0); return bh_written == copied; } return __iomap_write_end(iter->inode, pos, len, copied, folio); } static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i, const struct iomap_write_ops *write_ops) { ssize_t total_written = 0; int status = 0; struct address_space *mapping = iter->inode->i_mapping; size_t chunk = mapping_max_folio_size(mapping); unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0; do { struct folio *folio; loff_t old_size; size_t offset; /* Offset into folio */ u64 bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ u64 written; /* Bytes have been written */ loff_t pos; bytes = iov_iter_count(i); retry: offset = iter->pos & (chunk - 1); bytes = min(chunk - offset, bytes); status = balance_dirty_pages_ratelimited_flags(mapping, bdp_flags); if (unlikely(status)) break; if (bytes > iomap_length(iter)) bytes = iomap_length(iter); /* * Bring in the user page that we'll copy from _first_. * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. * * For async buffered writes the assumption is that the user * page has already been faulted in. This can be optimized by * faulting the user page. */ if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) { status = -EFAULT; break; } status = iomap_write_begin(iter, write_ops, &folio, &offset, &bytes); if (unlikely(status)) { iomap_write_failed(iter->inode, iter->pos, bytes); break; } if (iter->iomap.flags & IOMAP_F_STALE) break; pos = iter->pos; if (mapping_writably_mapped(mapping)) flush_dcache_folio(folio); copied = copy_folio_from_iter_atomic(folio, offset, bytes, i); written = iomap_write_end(iter, bytes, copied, folio) ? copied : 0; /* * Update the in-memory inode size after copying the data into * the page cache. It's up to the file system to write the * updated size to disk, preferably after I/O completion so that * no stale data is exposed. Only once that's done can we * unlock and release the folio. */ old_size = iter->inode->i_size; if (pos + written > old_size && !(iter->iomap.flags & IOMAP_F_FSVERITY)) { i_size_write(iter->inode, pos + written); iter->iomap.flags |= IOMAP_F_SIZE_CHANGED; } __iomap_put_folio(iter, write_ops, written, folio); if (old_size < pos && !(iter->iomap.flags & IOMAP_F_FSVERITY)) pagecache_isize_extended(iter->inode, old_size, pos); cond_resched(); if (unlikely(written == 0)) { /* * A short copy made iomap_write_end() reject the * thing entirely. Might be memory poisoning * halfway through, might be a race with munmap, * might be severe memory pressure. */ iomap_write_failed(iter->inode, pos, bytes); iov_iter_revert(i, copied); if (chunk > PAGE_SIZE) chunk /= 2; if (copied) { bytes = copied; goto retry; } } else { total_written += written; iomap_iter_advance(iter, written); } } while (iov_iter_count(i) && iomap_length(iter)); return total_written ? 0 : status; } ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops, void *private) { struct iomap_iter iter = { .inode = iocb->ki_filp->f_mapping->host, .pos = iocb->ki_pos, .len = iov_iter_count(i), .flags = IOMAP_WRITE, .private = private, }; ssize_t ret; if (iocb->ki_flags & IOCB_NOWAIT) iter.flags |= IOMAP_NOWAIT; if (iocb->ki_flags & IOCB_DONTCACHE) iter.flags |= IOMAP_DONTCACHE; while ((ret = iomap_iter(&iter, ops)) > 0) iter.status = iomap_write_iter(&iter, i, write_ops); if (unlikely(iter.pos == iocb->ki_pos)) return ret; ret = iter.pos - iocb->ki_pos; iocb->ki_pos = iter.pos; return ret; } EXPORT_SYMBOL_GPL(iomap_file_buffered_write); int iomap_fsverity_write(struct file *file, loff_t pos, size_t length, const void *buf, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops) { int ret; struct iov_iter iiter; struct kvec kvec = { .iov_base = (void *)buf, .iov_len = length, }; struct kiocb iocb = { .ki_filp = file, .ki_ioprio = get_current_ioprio(), .ki_pos = pos, }; iov_iter_kvec(&iiter, WRITE, &kvec, 1, length); ret = iomap_file_buffered_write(&iocb, &iiter, ops, write_ops, NULL); if (ret < 0) return ret; return ret == length ? 0 : -EIO; } EXPORT_SYMBOL_GPL(iomap_fsverity_write); static void iomap_write_delalloc_ifs_punch(struct inode *inode, struct folio *folio, loff_t start_byte, loff_t end_byte, struct iomap *iomap, iomap_punch_t punch) { unsigned int first_blk, last_blk; loff_t last_byte; u8 blkbits = inode->i_blkbits; struct iomap_folio_state *ifs; /* * When we have per-block dirty tracking, there can be * blocks within a folio which are marked uptodate * but not dirty. In that case it is necessary to punch * out such blocks to avoid leaking any delalloc blocks. */ ifs = folio->private; if (!ifs) return; last_byte = min_t(loff_t, end_byte - 1, folio_next_pos(folio) - 1); first_blk = offset_in_folio(folio, start_byte) >> blkbits; last_blk = offset_in_folio(folio, last_byte) >> blkbits; while ((first_blk = ifs_next_clean_block(folio, first_blk, last_blk)) <= last_blk) { punch(inode, folio_pos(folio) + (first_blk << blkbits), 1 << blkbits, iomap); first_blk++; } } static void iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, struct iomap *iomap, iomap_punch_t punch) { if (!folio_test_dirty(folio)) return; /* if dirty, punch up to offset */ if (start_byte > *punch_start_byte) { punch(inode, *punch_start_byte, start_byte - *punch_start_byte, iomap); } /* Punch non-dirty blocks within folio */ iomap_write_delalloc_ifs_punch(inode, folio, start_byte, end_byte, iomap, punch); /* * Make sure the next punch start is correctly bound to * the end of this data range, not the end of the folio. */ *punch_start_byte = min_t(loff_t, end_byte, folio_next_pos(folio)); } /* * Scan the data range passed to us for dirty page cache folios. If we find a * dirty folio, punch out the preceding range and update the offset from which * the next punch will start from. * * We can punch out storage reservations under clean pages because they either * contain data that has been written back - in which case the delalloc punch * over that range is a no-op - or they have been read faults in which case they * contain zeroes and we can remove the delalloc backing range and any new * writes to those pages will do the normal hole filling operation... * * This makes the logic simple: we only need to keep the delalloc extents only * over the dirty ranges of the page cache. * * This function uses [start_byte, end_byte) intervals (i.e. open ended) to * simplify range iterations. */ static void iomap_write_delalloc_scan(struct inode *inode, loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte, struct iomap *iomap, iomap_punch_t punch) { while (start_byte < end_byte) { struct folio *folio; /* grab locked page */ folio = filemap_lock_folio(inode->i_mapping, start_byte >> PAGE_SHIFT); if (IS_ERR(folio)) { start_byte = ALIGN_DOWN(start_byte, PAGE_SIZE) + PAGE_SIZE; continue; } iomap_write_delalloc_punch(inode, folio, punch_start_byte, start_byte, end_byte, iomap, punch); /* move offset to start of next folio in range */ start_byte = folio_next_pos(folio); folio_unlock(folio); folio_put(folio); } } /* * When a short write occurs, the filesystem might need to use ->iomap_end * to remove space reservations created in ->iomap_begin. * * For filesystems that use delayed allocation, there can be dirty pages over * the delalloc extent outside the range of a short write but still within the * delalloc extent allocated for this iomap if the write raced with page * faults. * * Punch out all the delalloc blocks in the range given except for those that * have dirty data still pending in the page cache - those are going to be * written and so must still retain the delalloc backing for writeback. * * The punch() callback *must* only punch delalloc extents in the range passed * to it. It must skip over all other types of extents in the range and leave * them completely unchanged. It must do this punch atomically with respect to * other extent modifications. * * The punch() callback may be called with a folio locked to prevent writeback * extent allocation racing at the edge of the range we are currently punching. * The locked folio may or may not cover the range being punched, so it is not * safe for the punch() callback to lock folios itself. * * Lock order is: * * inode->i_rwsem (shared or exclusive) * inode->i_mapping->invalidate_lock (exclusive) * folio_lock() * ->punch * internal filesystem allocation lock * * As we are scanning the page cache for data, we don't need to reimplement the * wheel - mapping_seek_hole_data() does exactly what we need to identify the * start and end of data ranges correctly even for sub-folio block sizes. This * byte range based iteration is especially convenient because it means we * don't have to care about variable size folios, nor where the start or end of * the data range lies within a folio, if they lie within the same folio or even * if there are multiple discontiguous data ranges within the folio. * * It should be noted that mapping_seek_hole_data() is not aware of EOF, and so * can return data ranges that exist in the cache beyond EOF. e.g. a page fault * spanning EOF will initialise the post-EOF data to zeroes and mark it up to * date. A write page fault can then mark it dirty. If we then fail a write() * beyond EOF into that up to date cached range, we allocate a delalloc block * beyond EOF and then have to punch it out. Because the range is up to date, * mapping_seek_hole_data() will return it, and we will skip the punch because * the folio is dirty. THis is incorrect - we always need to punch out delalloc * beyond EOF in this case as writeback will never write back and covert that * delalloc block beyond EOF. Hence we limit the cached data scan range to EOF, * resulting in always punching out the range from the EOF to the end of the * range the iomap spans. * * Intervals are of the form [start_byte, end_byte) (i.e. open ended) because it * matches the intervals returned by mapping_seek_hole_data(). i.e. SEEK_DATA * returns the start of a data range (start_byte), and SEEK_HOLE(start_byte) * returns the end of the data range (data_end). Using closed intervals would * require sprinkling this code with magic "+ 1" and "- 1" arithmetic and expose * the code to subtle off-by-one bugs.... */ void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, loff_t end_byte, unsigned flags, struct iomap *iomap, iomap_punch_t punch) { loff_t punch_start_byte = start_byte; loff_t scan_end_byte = min(i_size_read(inode), end_byte); /* * The caller must hold invalidate_lock to avoid races with page faults * re-instantiating folios and dirtying them via ->page_mkwrite whilst * we walk the cache and perform delalloc extent removal. Failing to do * this can leave dirty pages with no space reservation in the cache. */ lockdep_assert_held_write(&inode->i_mapping->invalidate_lock); while (start_byte < scan_end_byte) { loff_t data_end; start_byte = mapping_seek_hole_data(inode->i_mapping, start_byte, scan_end_byte, SEEK_DATA); /* * If there is no more data to scan, all that is left is to * punch out the remaining range. * * Note that mapping_seek_hole_data is only supposed to return * either an offset or -ENXIO, so WARN on any other error as * that would be an API change without updating the callers. */ if (start_byte == -ENXIO || start_byte == scan_end_byte) break; if (WARN_ON_ONCE(start_byte < 0)) return; WARN_ON_ONCE(start_byte < punch_start_byte); WARN_ON_ONCE(start_byte > scan_end_byte); /* * We find the end of this contiguous cached data range by * seeking from start_byte to the beginning of the next hole. */ data_end = mapping_seek_hole_data(inode->i_mapping, start_byte, scan_end_byte, SEEK_HOLE); if (WARN_ON_ONCE(data_end < 0)) return; /* * If we race with post-direct I/O invalidation of the page cache, * there might be no data left at start_byte. */ if (data_end == start_byte) continue; WARN_ON_ONCE(data_end < start_byte); WARN_ON_ONCE(data_end > scan_end_byte); iomap_write_delalloc_scan(inode, &punch_start_byte, start_byte, data_end, iomap, punch); /* The next data search starts at the end of this one. */ start_byte = data_end; } if (punch_start_byte < end_byte) punch(inode, punch_start_byte, end_byte - punch_start_byte, iomap); } EXPORT_SYMBOL_GPL(iomap_write_delalloc_release); static int iomap_unshare_iter(struct iomap_iter *iter, const struct iomap_write_ops *write_ops) { struct iomap *iomap = &iter->iomap; u64 bytes = iomap_length(iter); int status; if (!iomap_want_unshare_iter(iter)) return iomap_iter_advance(iter, bytes); do { struct folio *folio; size_t offset; bool ret; bytes = min_t(u64, SIZE_MAX, bytes); status = iomap_write_begin(iter, write_ops, &folio, &offset, &bytes); if (unlikely(status)) return status; if (iomap->flags & IOMAP_F_STALE) break; ret = iomap_write_end(iter, bytes, bytes, folio); __iomap_put_folio(iter, write_ops, bytes, folio); if (WARN_ON_ONCE(!ret)) return -EIO; cond_resched(); balance_dirty_pages_ratelimited(iter->inode->i_mapping); status = iomap_iter_advance(iter, bytes); if (status) break; } while ((bytes = iomap_length(iter)) > 0); return status; } int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops) { struct iomap_iter iter = { .inode = inode, .pos = pos, .flags = IOMAP_WRITE | IOMAP_UNSHARE, }; loff_t size = i_size_read(inode); int ret; if (pos < 0 || pos >= size) return 0; iter.len = min(len, size - pos); while ((ret = iomap_iter(&iter, ops)) > 0) iter.status = iomap_unshare_iter(&iter, write_ops); return ret; } EXPORT_SYMBOL_GPL(iomap_file_unshare); /* * Flush the remaining range of the iter and mark the current mapping stale. * This is used when zero range sees an unwritten mapping that may have had * dirty pagecache over it. */ static inline int iomap_zero_iter_flush_and_stale(struct iomap_iter *i) { struct address_space *mapping = i->inode->i_mapping; loff_t end = i->pos + i->len - 1; i->iomap.flags |= IOMAP_F_STALE; return filemap_write_and_wait_range(mapping, i->pos, end); } static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero, const struct iomap_write_ops *write_ops) { u64 bytes = iomap_length(iter); bool zeroed = false; int status; do { struct folio *folio; size_t offset; bool ret; balance_dirty_pages_ratelimited(iter->inode->i_mapping); bytes = min_t(u64, SIZE_MAX, bytes); status = iomap_write_begin(iter, write_ops, &folio, &offset, &bytes); if (status) return status; if (iter->iomap.flags & IOMAP_F_STALE) break; /* a NULL folio means we're done with a folio batch */ if (!folio) { status = iomap_iter_advance_full(iter); if (status) return status; break; } /* warn about zeroing folios beyond eof that won't write back */ WARN_ON_ONCE(folio_pos(folio) > iter->inode->i_size); trace_iomap_zero_iter(iter->inode, folio_pos(folio) + offset, bytes); folio_zero_range(folio, offset, bytes); zeroed = true; folio_mark_accessed(folio); ret = iomap_write_end(iter, bytes, bytes, folio); __iomap_put_folio(iter, write_ops, bytes, folio); if (WARN_ON_ONCE(!ret)) return -EIO; status = iomap_iter_advance(iter, bytes); if (status) return status; } while ((bytes = iomap_length(iter)) > 0); if (did_zero && zeroed) *did_zero = true; return status; } /** * iomap_fill_dirty_folios - fill a folio batch with dirty folios * @iter: Iteration structure * @start: Start offset of range. Updated based on lookup progress. * @end: End offset of range * @iomap_flags: Flags to set on the associated iomap to track the batch. * * Returns the folio count directly. Also returns the associated control flag if * the the batch lookup is performed and the expected offset of a subsequent * lookup via out params. The caller is responsible to set the flag on the * associated iomap. */ unsigned int iomap_fill_dirty_folios( struct iomap_iter *iter, loff_t *start, loff_t end, unsigned int *iomap_flags) { struct address_space *mapping = iter->inode->i_mapping; pgoff_t pstart = *start >> PAGE_SHIFT; pgoff_t pend = (end - 1) >> PAGE_SHIFT; unsigned int count; if (!iter->fbatch) { *start = end; return 0; } count = filemap_get_folios_dirty(mapping, &pstart, pend, iter->fbatch); *start = (pstart << PAGE_SHIFT); *iomap_flags |= IOMAP_F_FOLIO_BATCH; return count; } EXPORT_SYMBOL_GPL(iomap_fill_dirty_folios); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops, void *private) { struct folio_batch fbatch; struct iomap_iter iter = { .inode = inode, .pos = pos, .len = len, .flags = IOMAP_ZERO, .private = private, .fbatch = &fbatch, }; struct address_space *mapping = inode->i_mapping; int ret; bool range_dirty; folio_batch_init(&fbatch); /* * To avoid an unconditional flush, check pagecache state and only flush * if dirty and the fs returns a mapping that might convert on * writeback. */ range_dirty = filemap_range_needs_writeback(mapping, iter.pos, iter.pos + iter.len - 1); while ((ret = iomap_iter(&iter, ops)) > 0) { const struct iomap *srcmap = iomap_iter_srcmap(&iter); if (!(iter.iomap.flags & IOMAP_F_FOLIO_BATCH) && (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)) { s64 status; if (range_dirty && srcmap->type == IOMAP_UNWRITTEN) { range_dirty = false; status = iomap_zero_iter_flush_and_stale(&iter); } else { status = iomap_iter_advance_full(&iter); } iter.status = status; continue; } iter.status = iomap_zero_iter(&iter, did_zero, write_ops); } return ret; } EXPORT_SYMBOL_GPL(iomap_zero_range); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops, void *private) { unsigned int blocksize = i_blocksize(inode); unsigned int off = pos & (blocksize - 1); /* Block boundary? Nothing to do */ if (!off) return 0; return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops, write_ops, private); } EXPORT_SYMBOL_GPL(iomap_truncate_page); static int iomap_folio_mkwrite_iter(struct iomap_iter *iter, struct folio *folio) { loff_t length = iomap_length(iter); int ret; if (iter->iomap.flags & IOMAP_F_BUFFER_HEAD) { ret = __block_write_begin_int(folio, iter->pos, length, NULL, &iter->iomap); if (ret) return ret; block_commit_write(folio, 0, length); } else { WARN_ON_ONCE(!folio_test_uptodate(folio)); folio_mark_dirty(folio); } return iomap_iter_advance(iter, length); } vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops, void *private) { struct iomap_iter iter = { .inode = file_inode(vmf->vma->vm_file), .flags = IOMAP_WRITE | IOMAP_FAULT, .private = private, }; struct folio *folio = page_folio(vmf->page); ssize_t ret; folio_lock(folio); ret = folio_mkwrite_check_truncate(folio, iter.inode); if (ret < 0) goto out_unlock; iter.pos = folio_pos(folio); iter.len = ret; while ((ret = iomap_iter(&iter, ops)) > 0) iter.status = iomap_folio_mkwrite_iter(&iter, folio); if (ret < 0) goto out_unlock; folio_wait_stable(folio); return VM_FAULT_LOCKED; out_unlock: folio_unlock(folio); return vmf_fs_error(ret); } EXPORT_SYMBOL_GPL(iomap_page_mkwrite); static void iomap_writeback_init(struct inode *inode, struct folio *folio) { struct iomap_folio_state *ifs = folio->private; WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !ifs); if (ifs) { WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending) != 0); /* * Set this to the folio size. After processing the folio for * writeback in iomap_writeback_folio(), we'll subtract any * ranges not written back. * * We do this because otherwise, we would have to atomically * increment ifs->write_bytes_pending every time a range in the * folio needs to be written back. */ atomic_set(&ifs->write_bytes_pending, folio_size(folio)); } } void iomap_finish_folio_write(struct inode *inode, struct folio *folio, size_t len) { struct iomap_folio_state *ifs = folio->private; WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !ifs); WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) <= 0); if (!ifs || atomic_sub_and_test(len, &ifs->write_bytes_pending)) folio_end_writeback(folio); } EXPORT_SYMBOL_GPL(iomap_finish_folio_write); static int iomap_writeback_range(struct iomap_writepage_ctx *wpc, struct folio *folio, u64 pos, u32 rlen, u64 end_pos, size_t *bytes_submitted) { do { ssize_t ret; ret = wpc->ops->writeback_range(wpc, folio, pos, rlen, end_pos); if (WARN_ON_ONCE(ret == 0 || ret > rlen)) return -EIO; if (ret < 0) return ret; rlen -= ret; pos += ret; /* * Holes are not written back by ->writeback_range, so track * if we did handle anything that is not a hole here. */ if (wpc->iomap.type != IOMAP_HOLE) *bytes_submitted += ret; } while (rlen); return 0; } /* * Check interaction of the folio with the file end. * * If the folio is entirely beyond i_size, return false. If it straddles * i_size, adjust end_pos and zero all data beyond i_size. Don't skip fsverity * folios as those are beyond i_size. */ static bool iomap_writeback_handle_eof(struct folio *folio, struct iomap_writepage_ctx *wpc, u64 *end_pos) { struct inode *inode = wpc->inode; u64 isize = i_size_read(inode); if (wpc->iomap.flags & IOMAP_F_FSVERITY) { WARN_ON_ONCE(folio_pos(folio) < isize); return true; } if (*end_pos > isize) { size_t poff = offset_in_folio(folio, isize); pgoff_t end_index = isize >> PAGE_SHIFT; /* * If the folio is entirely ouside of i_size, skip it. * * This can happen due to a truncate operation that is in * progress and in that case truncate will finish it off once * we've dropped the folio lock. * * Note that the pgoff_t used for end_index is an unsigned long. * If the given offset is greater than 16TB on a 32-bit system, * then if we checked if the folio is fully outside i_size with * "if (folio->index >= end_index + 1)", "end_index + 1" would * overflow and evaluate to 0. Hence this folio would be * redirtied and written out repeatedly, which would result in * an infinite loop; the user program performing this operation * would hang. Instead, we can detect this situation by * checking if the folio is totally beyond i_size or if its * offset is just equal to the EOF. */ if (folio->index > end_index || (folio->index == end_index && poff == 0)) return false; /* * The folio straddles i_size. * * It must be zeroed out on each and every writepage invocation * because it may be mmapped: * * A file is mapped in multiples of the page size. For a * file that is not a multiple of the page size, the * remaining memory is zeroed when mapped, and writes to that * region are not written out to the file. * * Also adjust the end_pos to the end of file and skip writeback * for all blocks entirely beyond i_size. */ folio_zero_segment(folio, poff, folio_size(folio)); *end_pos = isize; } return true; } int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio) { struct iomap_folio_state *ifs = folio->private; struct inode *inode = wpc->inode; u64 pos = folio_pos(folio); u64 end_pos = pos + folio_size(folio); u64 end_aligned = 0; loff_t orig_pos = pos; size_t bytes_submitted = 0; int error = 0; u32 rlen; WARN_ON_ONCE(!folio_test_locked(folio)); WARN_ON_ONCE(folio_test_dirty(folio)); WARN_ON_ONCE(folio_test_writeback(folio)); trace_iomap_writeback_folio(inode, pos, folio_size(folio)); if (!iomap_writeback_handle_eof(folio, wpc, &end_pos)) return 0; WARN_ON_ONCE(end_pos <= pos); if (i_blocks_per_folio(inode, folio) > 1) { if (!ifs) { ifs = ifs_alloc(inode, folio, 0); iomap_set_range_dirty(folio, 0, end_pos - pos); } iomap_writeback_init(inode, folio); } /* * Set the writeback bit ASAP, as the I/O completion for the single * block per folio case happen hit as soon as we're submitting the bio. */ folio_start_writeback(folio); /* * Walk through the folio to find dirty areas to write back. */ end_aligned = round_up(end_pos, i_blocksize(inode)); while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) { error = iomap_writeback_range(wpc, folio, pos, rlen, end_pos, &bytes_submitted); if (error) break; pos += rlen; } if (bytes_submitted) wpc->nr_folios++; if (error && pos > orig_pos) fserror_report_io(inode, FSERR_BUFFERED_WRITE, orig_pos, 0, error, GFP_NOFS); /* * We can have dirty bits set past end of file in page_mkwrite path * while mapping the last partial folio. Hence it's better to clear * all the dirty bits in the folio here. */ iomap_clear_range_dirty(folio, 0, folio_size(folio)); /* * Usually the writeback bit is cleared by the I/O completion handler. * But we may end up either not actually writing any blocks, or (when * there are multiple blocks in a folio) all I/O might have finished * already at this point. In that case we need to clear the writeback * bit ourselves right after unlocking the page. */ if (ifs) { /* * Subtract any bytes that were initially accounted to * write_bytes_pending but skipped for writeback. */ size_t bytes_not_submitted = folio_size(folio) - bytes_submitted; if (bytes_not_submitted) iomap_finish_folio_write(inode, folio, bytes_not_submitted); } else if (!bytes_submitted) { folio_end_writeback(folio); } mapping_set_error(inode->i_mapping, error); return error; } EXPORT_SYMBOL_GPL(iomap_writeback_folio); int iomap_writepages(struct iomap_writepage_ctx *wpc) { struct address_space *mapping = wpc->inode->i_mapping; struct folio *folio = NULL; int error; /* * Writeback from reclaim context should never happen except in the case * of a VM regression so warn about it and refuse to write the data. */ if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC | PF_KSWAPD)) == PF_MEMALLOC)) return -EIO; while ((folio = writeback_iter(mapping, wpc->wbc, folio, &error))) { error = iomap_writeback_folio(wpc, folio); folio_unlock(folio); } /* * If @error is non-zero, it means that we have a situation where some * part of the submission process has failed after we've marked pages * for writeback. * * We cannot cancel the writeback directly in that case, so always call * ->writeback_submit to run the I/O completion handler to clear the * writeback bit and let the file system proess the errors. */ if (wpc->wb_ctx) return wpc->ops->writeback_submit(wpc, error); return error; } EXPORT_SYMBOL_GPL(iomap_writepages); |
| 135 135 135 135 135 135 135 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007 IBM Corporation * * Author: Cedric Le Goater <clg@fr.ibm.com> */ #include <linux/nsproxy.h> #include <linux/ipc_namespace.h> #include <linux/sysctl.h> #include <linux/stat.h> #include <linux/capability.h> #include <linux/slab.h> #include <linux/cred.h> static int msg_max_limit_min = MIN_MSGMAX; static int msg_max_limit_max = HARD_MSGMAX; static int msg_maxsize_limit_min = MIN_MSGSIZEMAX; static int msg_maxsize_limit_max = HARD_MSGSIZEMAX; static const struct ctl_table mq_sysctls[] = { { .procname = "queues_max", .data = &init_ipc_ns.mq_queues_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "msg_max", .data = &init_ipc_ns.mq_msg_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &msg_max_limit_min, .extra2 = &msg_max_limit_max, }, { .procname = "msgsize_max", .data = &init_ipc_ns.mq_msgsize_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &msg_maxsize_limit_min, .extra2 = &msg_maxsize_limit_max, }, { .procname = "msg_default", .data = &init_ipc_ns.mq_msg_default, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &msg_max_limit_min, .extra2 = &msg_max_limit_max, }, { .procname = "msgsize_default", .data = &init_ipc_ns.mq_msgsize_default, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &msg_maxsize_limit_min, .extra2 = &msg_maxsize_limit_max, }, }; static struct ctl_table_set *set_lookup(struct ctl_table_root *root) { return ¤t->nsproxy->ipc_ns->mq_set; } static int set_is_seen(struct ctl_table_set *set) { return ¤t->nsproxy->ipc_ns->mq_set == set; } static void mq_set_ownership(struct ctl_table_header *head, kuid_t *uid, kgid_t *gid) { struct ipc_namespace *ns = container_of(head->set, struct ipc_namespace, mq_set); kuid_t ns_root_uid = make_kuid(ns->user_ns, 0); kgid_t ns_root_gid = make_kgid(ns->user_ns, 0); *uid = uid_valid(ns_root_uid) ? ns_root_uid : GLOBAL_ROOT_UID; *gid = gid_valid(ns_root_gid) ? ns_root_gid : GLOBAL_ROOT_GID; } static int mq_permissions(struct ctl_table_header *head, const struct ctl_table *table) { int mode = table->mode; kuid_t ns_root_uid; kgid_t ns_root_gid; mq_set_ownership(head, &ns_root_uid, &ns_root_gid); if (uid_eq(current_euid(), ns_root_uid)) mode >>= 6; else if (in_egroup_p(ns_root_gid)) mode >>= 3; mode &= 7; return (mode << 6) | (mode << 3) | mode; } static struct ctl_table_root set_root = { .lookup = set_lookup, .permissions = mq_permissions, .set_ownership = mq_set_ownership, }; bool setup_mq_sysctls(struct ipc_namespace *ns) { struct ctl_table *tbl; setup_sysctl_set(&ns->mq_set, &set_root, set_is_seen); tbl = kmemdup(mq_sysctls, sizeof(mq_sysctls), GFP_KERNEL); if (tbl) { int i; for (i = 0; i < ARRAY_SIZE(mq_sysctls); i++) { if (tbl[i].data == &init_ipc_ns.mq_queues_max) tbl[i].data = &ns->mq_queues_max; else if (tbl[i].data == &init_ipc_ns.mq_msg_max) tbl[i].data = &ns->mq_msg_max; else if (tbl[i].data == &init_ipc_ns.mq_msgsize_max) tbl[i].data = &ns->mq_msgsize_max; else if (tbl[i].data == &init_ipc_ns.mq_msg_default) tbl[i].data = &ns->mq_msg_default; else if (tbl[i].data == &init_ipc_ns.mq_msgsize_default) tbl[i].data = &ns->mq_msgsize_default; else tbl[i].data = NULL; } ns->mq_sysctls = __register_sysctl_table(&ns->mq_set, "fs/mqueue", tbl, ARRAY_SIZE(mq_sysctls)); } if (!ns->mq_sysctls) { kfree(tbl); retire_sysctl_set(&ns->mq_set); return false; } return true; } void retire_mq_sysctls(struct ipc_namespace *ns) { const struct ctl_table *tbl; tbl = ns->mq_sysctls->ctl_table_arg; unregister_sysctl_table(ns->mq_sysctls); retire_sysctl_set(&ns->mq_set); kfree(tbl); } |
| 404 879 14 879 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_64_H #define _ASM_X86_UACCESS_64_H /* * User space memory access functions */ #include <linux/compiler.h> #include <linux/lockdep.h> #include <linux/kasan-checks.h> #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/page.h> #include <asm/percpu.h> #ifdef MODULE #define runtime_const_ptr(sym) (sym) #else #include <asm/runtime-const.h> #endif extern unsigned long USER_PTR_MAX; #ifdef CONFIG_ADDRESS_MASKING /* * Mask out tag bits from the address. */ static inline unsigned long __untagged_addr(unsigned long addr) { asm_inline (ALTERNATIVE("", "and " __percpu_arg([mask]) ", %[addr]", X86_FEATURE_LAM) : [addr] "+r" (addr) : [mask] "m" (__my_cpu_var(tlbstate_untag_mask))); return addr; } #define untagged_addr(addr) ({ \ unsigned long __addr = (__force unsigned long)(addr); \ (__force __typeof__(addr))__untagged_addr(__addr); \ }) static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, unsigned long addr) { mmap_assert_locked(mm); return addr & (mm)->context.untag_mask; } #define untagged_addr_remote(mm, addr) ({ \ unsigned long __addr = (__force unsigned long)(addr); \ (__force __typeof__(addr))__untagged_addr_remote(mm, __addr); \ }) #endif #define valid_user_address(x) \ likely((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX)) /* * Masking the user address is an alternative to a conditional * user_access_begin that can avoid the fencing. This only works * for dense accesses starting at the address. */ static inline void __user *mask_user_address(const void __user *ptr) { void __user *ret; asm("cmp %1,%0\n\t" "cmova %1,%0" :"=r" (ret) :"r" (runtime_const_ptr(USER_PTR_MAX)), "0" (ptr)); return ret; } #define masked_user_access_begin(x) ({ \ auto __masked_ptr = (x); \ __masked_ptr = mask_user_address(__masked_ptr); \ __uaccess_begin(); __masked_ptr; }) /* * User pointers can have tag bits on x86-64. This scheme tolerates * arbitrary values in those bits rather then masking them off. * * Enforce two rules: * 1. 'ptr' must be in the user part of the address space * 2. 'ptr+size' must not overflow into kernel addresses * * Note that we always have at least one guard page between the * max user address and the non-canonical gap, allowing us to * ignore small sizes entirely. * * In fact, we could probably remove the size check entirely, since * any kernel accesses will be in increasing address order starting * at 'ptr'. * * That's a separate optimization, for now just handle the small * constant case. */ static inline bool __access_ok(const void __user *ptr, unsigned long size) { if (__builtin_constant_p(size <= PAGE_SIZE) && size <= PAGE_SIZE) { return valid_user_address(ptr); } else { unsigned long sum = size + (__force unsigned long)ptr; return valid_user_address(sum) && sum >= (__force unsigned long)ptr; } } #define __access_ok __access_ok /* * Copy To/From Userspace */ /* Handles exceptions in both to and from, but doesn't do access_ok */ __must_check unsigned long rep_movs_alternative(void *to, const void *from, unsigned len); static __always_inline __must_check unsigned long copy_user_generic(void *to, const void *from, unsigned long len) { stac(); /* * If CPU has FSRM feature, use 'rep movs'. * Otherwise, use rep_movs_alternative. */ asm volatile( "1:\n\t" ALTERNATIVE("rep movsb", "call rep_movs_alternative", ALT_NOT(X86_FEATURE_FSRM)) "2:\n" _ASM_EXTABLE_UA(1b, 2b) :"+c" (len), "+D" (to), "+S" (from), ASM_CALL_CONSTRAINT : : "memory", "rax"); clac(); return len; } static __always_inline __must_check unsigned long raw_copy_from_user(void *dst, const void __user *src, unsigned long size) { return copy_user_generic(dst, (__force void *)src, size); } static __always_inline __must_check unsigned long raw_copy_to_user(void __user *dst, const void *src, unsigned long size) { return copy_user_generic((__force void *)dst, src, size); } #define copy_to_nontemporal copy_to_nontemporal extern size_t copy_to_nontemporal(void *dst, const void *src, size_t size); extern size_t copy_user_flushcache(void *dst, const void __user *src, size_t size); static inline int copy_from_user_inatomic_nontemporal(void *dst, const void __user *src, unsigned size) { long ret; kasan_check_write(dst, size); src = mask_user_address(src); stac(); ret = copy_to_nontemporal(dst, (__force const void *)src, size); clac(); return ret; } static inline size_t copy_from_user_flushcache(void *dst, const void __user *src, size_t size) { kasan_check_write(dst, size); return copy_user_flushcache(dst, src, size); } /* * Zero Userspace. */ __must_check unsigned long rep_stos_alternative(void __user *addr, unsigned long len); static __always_inline __must_check unsigned long __clear_user(void __user *addr, unsigned long size) { might_fault(); stac(); /* * No memory constraint because it doesn't change any memory gcc * knows about. */ asm volatile( "1:\n\t" ALTERNATIVE("rep stosb", "call rep_stos_alternative", ALT_NOT(X86_FEATURE_FSRS)) "2:\n" _ASM_EXTABLE_UA(1b, 2b) : "+c" (size), "+D" (addr), ASM_CALL_CONSTRAINT : "a" (0)); clac(); return size; } static __always_inline unsigned long clear_user(void __user *to, unsigned long n) { if (__access_ok(to, n)) return __clear_user(to, n); return n; } #endif /* _ASM_X86_UACCESS_64_H */ |
| 149 1658 1352 208 433 1341 149 420 1369 411 1091 708 924 926 1168 654 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 | // SPDX-License-Identifier: GPL-2.0 /* * arch/x86_64/lib/csum-partial.c * * This file contains network checksum routines that are better done * in an architecture-specific manner due to speed. */ #include <linux/compiler.h> #include <linux/export.h> #include <asm/checksum.h> #include <asm/word-at-a-time.h> static inline __wsum csum_finalize_sum(u64 temp64) { return (__force __wsum)((temp64 + ror64(temp64, 32)) >> 32); } static inline unsigned long update_csum_40b(unsigned long sum, const unsigned long m[5]) { asm("addq %1,%0\n\t" "adcq %2,%0\n\t" "adcq %3,%0\n\t" "adcq %4,%0\n\t" "adcq %5,%0\n\t" "adcq $0,%0" :"+r" (sum) :"m" (m[0]), "m" (m[1]), "m" (m[2]), "m" (m[3]), "m" (m[4])); return sum; } /* * Do a checksum on an arbitrary memory area. * Returns a 32bit checksum. * * This isn't as time critical as it used to be because many NICs * do hardware checksumming these days. * * Still, with CHECKSUM_COMPLETE this is called to compute * checksums on IPv6 headers (40 bytes) and other small parts. * it's best to have buff aligned on a 64-bit boundary */ __wsum csum_partial(const void *buff, int len, __wsum sum) { u64 temp64 = (__force u64)sum; /* Do two 40-byte chunks in parallel to get better ILP */ if (likely(len >= 80)) { u64 temp64_2 = 0; do { temp64 = update_csum_40b(temp64, buff); temp64_2 = update_csum_40b(temp64_2, buff + 40); buff += 80; len -= 80; } while (len >= 80); asm("addq %1,%0\n\t" "adcq $0,%0" :"+r" (temp64): "r" (temp64_2)); } /* * len == 40 is the hot case due to IPv6 headers, so return * early for that exact case without checking the tail bytes. */ if (len >= 40) { temp64 = update_csum_40b(temp64, buff); len -= 40; if (!len) return csum_finalize_sum(temp64); buff += 40; } if (len & 32) { asm("addq 0*8(%[src]),%[res]\n\t" "adcq 1*8(%[src]),%[res]\n\t" "adcq 2*8(%[src]),%[res]\n\t" "adcq 3*8(%[src]),%[res]\n\t" "adcq $0,%[res]" : [res] "+r"(temp64) : [src] "r"(buff), "m"(*(const char(*)[32])buff)); buff += 32; } if (len & 16) { asm("addq 0*8(%[src]),%[res]\n\t" "adcq 1*8(%[src]),%[res]\n\t" "adcq $0,%[res]" : [res] "+r"(temp64) : [src] "r"(buff), "m"(*(const char(*)[16])buff)); buff += 16; } if (len & 8) { asm("addq 0*8(%[src]),%[res]\n\t" "adcq $0,%[res]" : [res] "+r"(temp64) : [src] "r"(buff), "m"(*(const char(*)[8])buff)); buff += 8; } if (len & 7) { unsigned int shift = (-len << 3) & 63; unsigned long trail; trail = (load_unaligned_zeropad(buff) << shift) >> shift; asm("addq %[trail],%[res]\n\t" "adcq $0,%[res]" : [res] "+r"(temp64) : [trail] "r"(trail)); } return csum_finalize_sum(temp64); } EXPORT_SYMBOL(csum_partial); /* * this routine is used for miscellaneous IP-like checksums, mainly * in icmp.c */ __sum16 ip_compute_csum(const void *buff, int len) { return csum_fold(csum_partial(buff, len, 0)); } EXPORT_SYMBOL(ip_compute_csum); |
| 15 15 6 15 6 6 6 1 5 6 49 49 842 843 842 842 1 9 3 1 6 2 1 1 5 2 3 3 1 2 6 6 4 4 64 3 1 1 1 1 2 3 52 52 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1995 Linus Torvalds * * Pentium III FXSR, SSE support * Gareth Hughes <gareth@valinux.com>, May 2000 * * X86-64 port * Andi Kleen. * * CPU hotplug support - ashok.raj@intel.com */ /* * This file handles the architecture-dependent parts of process handling.. */ #include <linux/cpu.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/elfcore.h> #include <linux/smp.h> #include <linux/slab.h> #include <linux/user.h> #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/kvm_types.h> #include <linux/ptrace.h> #include <linux/notifier.h> #include <linux/kprobes.h> #include <linux/kdebug.h> #include <linux/prctl.h> #include <linux/uaccess.h> #include <linux/io.h> #include <linux/ftrace.h> #include <linux/syscalls.h> #include <linux/iommu.h> #include <asm/processor.h> #include <asm/pkru.h> #include <asm/fpu/sched.h> #include <asm/mmu_context.h> #include <asm/prctl.h> #include <asm/desc.h> #include <asm/proto.h> #include <asm/ia32.h> #include <asm/debugreg.h> #include <asm/switch_to.h> #include <asm/xen/hypervisor.h> #include <asm/vdso.h> #include <asm/resctrl.h> #include <asm/unistd.h> #include <asm/fsgsbase.h> #include <asm/fred.h> #include <asm/msr.h> #ifdef CONFIG_IA32_EMULATION /* Not included via unistd.h */ #include <asm/unistd_32_ia32.h> #endif #include "process.h" /* Prints also some state that isn't saved in the pt_regs */ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, const char *log_lvl) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs; unsigned long d0, d1, d2, d3, d6, d7; unsigned int fsindex, gsindex; unsigned int ds, es; show_iret_regs(regs, log_lvl); if (regs->orig_ax != -1) pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax); else pr_cont("\n"); printk("%sRAX: %016lx RBX: %016lx RCX: %016lx\n", log_lvl, regs->ax, regs->bx, regs->cx); printk("%sRDX: %016lx RSI: %016lx RDI: %016lx\n", log_lvl, regs->dx, regs->si, regs->di); printk("%sRBP: %016lx R08: %016lx R09: %016lx\n", log_lvl, regs->bp, regs->r8, regs->r9); printk("%sR10: %016lx R11: %016lx R12: %016lx\n", log_lvl, regs->r10, regs->r11, regs->r12); printk("%sR13: %016lx R14: %016lx R15: %016lx\n", log_lvl, regs->r13, regs->r14, regs->r15); if (mode == SHOW_REGS_SHORT) return; if (mode == SHOW_REGS_USER) { rdmsrq(MSR_FS_BASE, fs); rdmsrq(MSR_KERNEL_GS_BASE, shadowgs); printk("%sFS: %016lx GS: %016lx\n", log_lvl, fs, shadowgs); return; } savesegment(ds, ds); savesegment(es, es); savesegment(fs, fsindex); savesegment(gs, gsindex); rdmsrq(MSR_FS_BASE, fs); rdmsrq(MSR_GS_BASE, gs); rdmsrq(MSR_KERNEL_GS_BASE, shadowgs); cr0 = read_cr0(); cr2 = read_cr2(); cr3 = __read_cr3(); cr4 = __read_cr4(); printk("%sFS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", log_lvl, fs, fsindex, gs, gsindex, shadowgs); printk("%sCS: %04x DS: %04x ES: %04x CR0: %016lx\n", log_lvl, regs->cs, ds, es, cr0); printk("%sCR2: %016lx CR3: %016lx CR4: %016lx\n", log_lvl, cr2, cr3, cr4); get_debugreg(d0, 0); get_debugreg(d1, 1); get_debugreg(d2, 2); get_debugreg(d3, 3); get_debugreg(d6, 6); get_debugreg(d7, 7); /* Only print out debug registers if they are in their non-default state. */ if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))) { printk("%sDR0: %016lx DR1: %016lx DR2: %016lx\n", log_lvl, d0, d1, d2); printk("%sDR3: %016lx DR6: %016lx DR7: %016lx\n", log_lvl, d3, d6, d7); } if (cr4 & X86_CR4_PKE) printk("%sPKRU: %08x\n", log_lvl, read_pkru()); } void release_thread(struct task_struct *dead_task) { WARN_ON(dead_task->mm); } enum which_selector { FS, GS }; /* * Out of line to be protected from kprobes and tracing. If this would be * traced or probed than any access to a per CPU variable happens with * the wrong GS. * * It is not used on Xen paravirt. When paravirt support is needed, it * needs to be renamed with native_ prefix. */ static noinstr unsigned long __rdgsbase_inactive(void) { unsigned long gsbase; lockdep_assert_irqs_disabled(); /* * SWAPGS is no longer needed thus NOT allowed with FRED because * FRED transitions ensure that an operating system can _always_ * operate with its own GS base address: * - For events that occur in ring 3, FRED event delivery swaps * the GS base address with the IA32_KERNEL_GS_BASE MSR. * - ERETU (the FRED transition that returns to ring 3) also swaps * the GS base address with the IA32_KERNEL_GS_BASE MSR. * * And the operating system can still setup the GS segment for a * user thread without the need of loading a user thread GS with: * - Using LKGS, available with FRED, to modify other attributes * of the GS segment without compromising its ability always to * operate with its own GS base address. * - Accessing the GS segment base address for a user thread as * before using RDMSR or WRMSR on the IA32_KERNEL_GS_BASE MSR. * * Note, LKGS loads the GS base address into the IA32_KERNEL_GS_BASE * MSR instead of the GS segment’s descriptor cache. As such, the * operating system never changes its runtime GS base address. */ if (!cpu_feature_enabled(X86_FEATURE_FRED) && !cpu_feature_enabled(X86_FEATURE_XENPV)) { native_swapgs(); gsbase = rdgsbase(); native_swapgs(); } else { instrumentation_begin(); rdmsrq(MSR_KERNEL_GS_BASE, gsbase); instrumentation_end(); } return gsbase; } /* * Out of line to be protected from kprobes and tracing. If this would be * traced or probed than any access to a per CPU variable happens with * the wrong GS. * * It is not used on Xen paravirt. When paravirt support is needed, it * needs to be renamed with native_ prefix. */ static noinstr void __wrgsbase_inactive(unsigned long gsbase) { lockdep_assert_irqs_disabled(); if (!cpu_feature_enabled(X86_FEATURE_FRED) && !cpu_feature_enabled(X86_FEATURE_XENPV)) { native_swapgs(); wrgsbase(gsbase); native_swapgs(); } else { instrumentation_begin(); wrmsrq(MSR_KERNEL_GS_BASE, gsbase); instrumentation_end(); } } /* * Saves the FS or GS base for an outgoing thread if FSGSBASE extensions are * not available. The goal is to be reasonably fast on non-FSGSBASE systems. * It's forcibly inlined because it'll generate better code and this function * is hot. */ static __always_inline void save_base_legacy(struct task_struct *prev_p, unsigned short selector, enum which_selector which) { if (likely(selector == 0)) { /* * On Intel (without X86_BUG_NULL_SEG), the segment base could * be the pre-existing saved base or it could be zero. On AMD * (with X86_BUG_NULL_SEG), the segment base could be almost * anything. * * This branch is very hot (it's hit twice on almost every * context switch between 64-bit programs), and avoiding * the RDMSR helps a lot, so we just assume that whatever * value is already saved is correct. This matches historical * Linux behavior, so it won't break existing applications. * * To avoid leaking state, on non-X86_BUG_NULL_SEG CPUs, if we * report that the base is zero, it needs to actually be zero: * see the corresponding logic in load_seg_legacy. */ } else { /* * If the selector is 1, 2, or 3, then the base is zero on * !X86_BUG_NULL_SEG CPUs and could be anything on * X86_BUG_NULL_SEG CPUs. In the latter case, Linux * has never attempted to preserve the base across context * switches. * * If selector > 3, then it refers to a real segment, and * saving the base isn't necessary. */ if (which == FS) prev_p->thread.fsbase = 0; else prev_p->thread.gsbase = 0; } } static __always_inline void save_fsgs(struct task_struct *task) { savesegment(fs, task->thread.fsindex); savesegment(gs, task->thread.gsindex); if (static_cpu_has(X86_FEATURE_FSGSBASE)) { /* * If FSGSBASE is enabled, we can't make any useful guesses * about the base, and user code expects us to save the current * value. Fortunately, reading the base directly is efficient. */ task->thread.fsbase = rdfsbase(); task->thread.gsbase = __rdgsbase_inactive(); } else { save_base_legacy(task, task->thread.fsindex, FS); save_base_legacy(task, task->thread.gsindex, GS); } } /* * While a process is running,current->thread.fsbase and current->thread.gsbase * may not match the corresponding CPU registers (see save_base_legacy()). */ void current_save_fsgs(void) { unsigned long flags; /* Interrupts need to be off for FSGSBASE */ local_irq_save(flags); save_fsgs(current); local_irq_restore(flags); } EXPORT_SYMBOL_FOR_KVM(current_save_fsgs); static __always_inline void loadseg(enum which_selector which, unsigned short sel) { if (which == FS) loadsegment(fs, sel); else load_gs_index(sel); } static __always_inline void load_seg_legacy(unsigned short prev_index, unsigned long prev_base, unsigned short next_index, unsigned long next_base, enum which_selector which) { if (likely(next_index <= 3)) { /* * The next task is using 64-bit TLS, is not using this * segment at all, or is having fun with arcane CPU features. */ if (next_base == 0) { /* * Nasty case: on AMD CPUs, we need to forcibly zero * the base. */ if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { loadseg(which, __USER_DS); loadseg(which, next_index); } else { /* * We could try to exhaustively detect cases * under which we can skip the segment load, * but there's really only one case that matters * for performance: if both the previous and * next states are fully zeroed, we can skip * the load. * * (This assumes that prev_base == 0 has no * false positives. This is the case on * Intel-style CPUs.) */ if (likely(prev_index | next_index | prev_base)) loadseg(which, next_index); } } else { if (prev_index != next_index) loadseg(which, next_index); wrmsrq(which == FS ? MSR_FS_BASE : MSR_KERNEL_GS_BASE, next_base); } } else { /* * The next task is using a real segment. Loading the selector * is sufficient. */ loadseg(which, next_index); } } /* * Store prev's PKRU value and load next's PKRU value if they differ. PKRU * is not XSTATE managed on context switch because that would require a * lookup in the task's FPU xsave buffer and require to keep that updated * in various places. */ static __always_inline void x86_pkru_load(struct thread_struct *prev, struct thread_struct *next) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* Stash the prev task's value: */ prev->pkru = rdpkru(); /* * PKRU writes are slightly expensive. Avoid them when not * strictly necessary: */ if (prev->pkru != next->pkru) wrpkru(next->pkru); } static __always_inline void x86_fsgsbase_load(struct thread_struct *prev, struct thread_struct *next) { if (static_cpu_has(X86_FEATURE_FSGSBASE)) { /* Update the FS and GS selectors if they could have changed. */ if (unlikely(prev->fsindex || next->fsindex)) loadseg(FS, next->fsindex); if (unlikely(prev->gsindex || next->gsindex)) loadseg(GS, next->gsindex); /* Update the bases. */ wrfsbase(next->fsbase); __wrgsbase_inactive(next->gsbase); } else { load_seg_legacy(prev->fsindex, prev->fsbase, next->fsindex, next->fsbase, FS); load_seg_legacy(prev->gsindex, prev->gsbase, next->gsindex, next->gsbase, GS); } } unsigned long x86_fsgsbase_read_task(struct task_struct *task, unsigned short selector) { unsigned short idx = selector >> 3; unsigned long base; if (likely((selector & SEGMENT_TI_MASK) == 0)) { if (unlikely(idx >= GDT_ENTRIES)) return 0; /* * There are no user segments in the GDT with nonzero bases * other than the TLS segments. */ if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) return 0; idx -= GDT_ENTRY_TLS_MIN; base = get_desc_base(&task->thread.tls_array[idx]); } else { #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; /* * If performance here mattered, we could protect the LDT * with RCU. This is a slow path, though, so we can just * take the mutex. */ mutex_lock(&task->mm->context.lock); ldt = task->mm->context.ldt; if (unlikely(!ldt || idx >= ldt->nr_entries)) base = 0; else base = get_desc_base(ldt->entries + idx); mutex_unlock(&task->mm->context.lock); #else base = 0; #endif } return base; } unsigned long x86_gsbase_read_cpu_inactive(void) { unsigned long gsbase; if (boot_cpu_has(X86_FEATURE_FSGSBASE)) { unsigned long flags; local_irq_save(flags); gsbase = __rdgsbase_inactive(); local_irq_restore(flags); } else { rdmsrq(MSR_KERNEL_GS_BASE, gsbase); } return gsbase; } void x86_gsbase_write_cpu_inactive(unsigned long gsbase) { if (boot_cpu_has(X86_FEATURE_FSGSBASE)) { unsigned long flags; local_irq_save(flags); __wrgsbase_inactive(gsbase); local_irq_restore(flags); } else { wrmsrq(MSR_KERNEL_GS_BASE, gsbase); } } unsigned long x86_fsbase_read_task(struct task_struct *task) { unsigned long fsbase; if (task == current) fsbase = x86_fsbase_read_cpu(); else if (boot_cpu_has(X86_FEATURE_FSGSBASE) || (task->thread.fsindex == 0)) fsbase = task->thread.fsbase; else fsbase = x86_fsgsbase_read_task(task, task->thread.fsindex); return fsbase; } unsigned long x86_gsbase_read_task(struct task_struct *task) { unsigned long gsbase; if (task == current) gsbase = x86_gsbase_read_cpu_inactive(); else if (boot_cpu_has(X86_FEATURE_FSGSBASE) || (task->thread.gsindex == 0)) gsbase = task->thread.gsbase; else gsbase = x86_fsgsbase_read_task(task, task->thread.gsindex); return gsbase; } void x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase) { WARN_ON_ONCE(task == current); task->thread.fsbase = fsbase; } void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase) { WARN_ON_ONCE(task == current); task->thread.gsbase = gsbase; } static void start_thread_common(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp, u16 _cs, u16 _ss, u16 _ds) { WARN_ON_ONCE(regs != current_pt_regs()); if (static_cpu_has(X86_BUG_NULL_SEG)) { /* Loading zero below won't clear the base. */ loadsegment(fs, __USER_DS); load_gs_index(__USER_DS); } reset_thread_features(); loadsegment(fs, 0); loadsegment(es, _ds); loadsegment(ds, _ds); load_gs_index(0); regs->ip = new_ip; regs->sp = new_sp; regs->csx = _cs; regs->ssx = _ss; /* * Allow single-step trap and NMI when starting a new task, thus * once the new task enters user space, single-step trap and NMI * are both enabled immediately. * * Entering a new task is logically speaking a return from a * system call (exec, fork, clone, etc.). As such, if ptrace * enables single stepping a single step exception should be * allowed to trigger immediately upon entering user space. * This is not optional. * * NMI should *never* be disabled in user space. As such, this * is an optional, opportunistic way to catch errors. * * Paranoia: High-order 48 bits above the lowest 16 bit SS are * discarded by the legacy IRET instruction on all Intel, AMD, * and Cyrix/Centaur/VIA CPUs, thus can be set unconditionally, * even when FRED is not enabled. But we choose the safer side * to use these bits only when FRED is enabled. */ if (cpu_feature_enabled(X86_FEATURE_FRED)) { regs->fred_ss.swevent = true; regs->fred_ss.nmi = true; } regs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; } void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) { start_thread_common(regs, new_ip, new_sp, __USER_CS, __USER_DS, 0); } EXPORT_SYMBOL_GPL(start_thread); #ifdef CONFIG_COMPAT void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32) { start_thread_common(regs, new_ip, new_sp, x32 ? __USER_CS : __USER32_CS, __USER_DS, __USER_DS); } #endif /* * switch_to(x,y) should switch tasks from x to y. * * This could still be optimized: * - fold all the options into a flag word and test it with a single test. * - could test fs/gs bitsliced * * Kprobes not supported here. Set the probe on schedule instead. * Function graph tracer not supported too. */ __no_kmsan_checks __visible __notrace_funcgraph struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread; struct thread_struct *next = &next_p->thread; int cpu = smp_processor_id(); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && this_cpu_read(hardirq_stack_inuse)); switch_fpu(prev_p, cpu); /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). * * (e.g. xen_load_tls()) */ save_fsgs(prev_p); /* * Load TLS before restoring any segments so that segment loads * reference the correct GDT entries. */ load_TLS(next, cpu); /* * Leave lazy mode, flushing any hypercalls made here. This * must be done after loading TLS entries in the GDT but before * loading segments that might reference them. */ arch_end_context_switch(next_p); /* Switch DS and ES. * * Reading them only returns the selectors, but writing them (if * nonzero) loads the full descriptor from the GDT or LDT. The * LDT for next is loaded in switch_mm, and the GDT is loaded * above. * * We therefore need to write new values to the segment * registers on every context switch unless both the new and old * values are zero. * * Note that we don't need to do anything for CS and SS, as * those are saved and restored as part of pt_regs. */ savesegment(es, prev->es); if (unlikely(next->es | prev->es)) loadsegment(es, next->es); savesegment(ds, prev->ds); if (unlikely(next->ds | prev->ds)) loadsegment(ds, next->ds); x86_fsgsbase_load(prev, next); x86_pkru_load(prev, next); /* * Switch the PDA and FPU contexts. */ raw_cpu_write(current_task, next_p); raw_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p)); /* Reload sp0. */ update_task_stack(next_p); switch_to_extra(prev_p, next_p); if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) { /* * AMD CPUs have a misfeature: SYSRET sets the SS selector but * does not update the cached descriptor. As a result, if we * do SYSRET while SS is NULL, we'll end up in user mode with * SS apparently equal to __USER_DS but actually unusable. * * The straightforward workaround would be to fix it up just * before SYSRET, but that would slow down the system call * fast paths. Instead, we ensure that SS is never NULL in * system call context. We do this by replacing NULL SS * selectors at every context switch. SYSCALL sets up a valid * SS, so the only way to get NULL is to re-enter the kernel * from CPL 3 through an interrupt. Since that can't happen * in the same task as a running syscall, we are guaranteed to * context switch between every interrupt vector entry and a * subsequent SYSRET. * * We read SS first because SS reads are much faster than * writes. Out of caution, we force SS to __KERNEL_DS even if * it previously had a different non-NULL value. */ unsigned short ss_sel; savesegment(ss, ss_sel); if (ss_sel != __KERNEL_DS) loadsegment(ss, __KERNEL_DS); } /* Load the Intel cache allocation PQR MSR. */ resctrl_arch_sched_in(next_p); /* Reset hw history on AMD CPUs */ if (cpu_feature_enabled(X86_FEATURE_AMD_WORKLOAD_CLASS)) wrmsrq(MSR_AMD_WORKLOAD_HRST, 0x1); return prev_p; } void set_personality_64bit(void) { /* inherit personality from parent */ /* Make sure to be in 64bit mode */ clear_thread_flag(TIF_ADDR32); /* Pretend that this comes from a 64bit execve */ task_pt_regs(current)->orig_ax = __NR_execve; current_thread_info()->status &= ~TS_COMPAT; if (current->mm) __set_bit(MM_CONTEXT_HAS_VSYSCALL, ¤t->mm->context.flags); /* TBD: overwrites user setup. Should have two bits. But 64bit processes have always behaved this way, so it's not too bad. The main problem is just that 32bit children are affected again. */ current->personality &= ~READ_IMPLIES_EXEC; } static void __set_personality_x32(void) { #ifdef CONFIG_X86_X32_ABI if (current->mm) current->mm->context.flags = 0; current->personality &= ~READ_IMPLIES_EXEC; /* * in_32bit_syscall() uses the presence of the x32 syscall bit * flag to determine compat status. The x86 mmap() code relies on * the syscall bitness so set x32 syscall bit right here to make * in_32bit_syscall() work during exec(). * * Pretend to come from a x32 execve. */ task_pt_regs(current)->orig_ax = __NR_x32_execve | __X32_SYSCALL_BIT; current_thread_info()->status &= ~TS_COMPAT; #endif } static void __set_personality_ia32(void) { #ifdef CONFIG_IA32_EMULATION if (current->mm) { /* * uprobes applied to this MM need to know this and * cannot use user_64bit_mode() at that time. */ __set_bit(MM_CONTEXT_UPROBE_IA32, ¤t->mm->context.flags); } current->personality |= force_personality32; /* Prepare the first "return" to user space */ task_pt_regs(current)->orig_ax = __NR_ia32_execve; current_thread_info()->status |= TS_COMPAT; #endif } void set_personality_ia32(bool x32) { /* Make sure to be in 32bit mode */ set_thread_flag(TIF_ADDR32); if (x32) __set_personality_x32(); else __set_personality_ia32(); } EXPORT_SYMBOL_GPL(set_personality_ia32); #ifdef CONFIG_CHECKPOINT_RESTORE static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr) { int ret; ret = map_vdso_once(image, addr); if (ret) return ret; return (long)image->size; } #endif #ifdef CONFIG_ADDRESS_MASKING #define LAM_U57_BITS 6 static void enable_lam_func(void *__mm) { struct mm_struct *mm = __mm; unsigned long lam; if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm) { lam = mm_lam_cr3_mask(mm); write_cr3(__read_cr3() | lam); cpu_tlbstate_update_lam(lam, mm_untag_mask(mm)); } } static void mm_enable_lam(struct mm_struct *mm) { mm->context.lam_cr3_mask = X86_CR3_LAM_U57; mm->context.untag_mask = ~GENMASK(62, 57); /* * Even though the process must still be single-threaded at this * point, kernel threads may be using the mm. IPI those kernel * threads if they exist. */ on_each_cpu_mask(mm_cpumask(mm), enable_lam_func, mm, true); set_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags); } static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits) { if (!cpu_feature_enabled(X86_FEATURE_LAM)) return -ENODEV; /* PTRACE_ARCH_PRCTL */ if (current->mm != mm) return -EINVAL; if (mm_valid_pasid(mm) && !test_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &mm->context.flags)) return -EINVAL; if (mmap_write_lock_killable(mm)) return -EINTR; /* * MM_CONTEXT_LOCK_LAM is set on clone. Prevent LAM from * being enabled unless the process is single threaded: */ if (test_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags)) { mmap_write_unlock(mm); return -EBUSY; } if (!nr_bits || nr_bits > LAM_U57_BITS) { mmap_write_unlock(mm); return -EINVAL; } mm_enable_lam(mm); mmap_write_unlock(mm); return 0; } #endif long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) { int ret = 0; switch (option) { case ARCH_SET_GS: { if (unlikely(arg2 >= TASK_SIZE_MAX)) return -EPERM; preempt_disable(); /* * ARCH_SET_GS has always overwritten the index * and the base. Zero is the most sensible value * to put in the index, and is the only value that * makes any sense if FSGSBASE is unavailable. */ if (task == current) { loadseg(GS, 0); x86_gsbase_write_cpu_inactive(arg2); /* * On non-FSGSBASE systems, save_base_legacy() expects * that we also fill in thread.gsbase. */ task->thread.gsbase = arg2; } else { task->thread.gsindex = 0; x86_gsbase_write_task(task, arg2); } preempt_enable(); break; } case ARCH_SET_FS: { /* * Not strictly needed for %fs, but do it for symmetry * with %gs */ if (unlikely(arg2 >= TASK_SIZE_MAX)) return -EPERM; preempt_disable(); /* * Set the selector to 0 for the same reason * as %gs above. */ if (task == current) { loadseg(FS, 0); x86_fsbase_write_cpu(arg2); /* * On non-FSGSBASE systems, save_base_legacy() expects * that we also fill in thread.fsbase. */ task->thread.fsbase = arg2; } else { task->thread.fsindex = 0; x86_fsbase_write_task(task, arg2); } preempt_enable(); break; } case ARCH_GET_FS: { unsigned long base = x86_fsbase_read_task(task); ret = put_user(base, (unsigned long __user *)arg2); break; } case ARCH_GET_GS: { unsigned long base = x86_gsbase_read_task(task); ret = put_user(base, (unsigned long __user *)arg2); break; } #ifdef CONFIG_CHECKPOINT_RESTORE # ifdef CONFIG_X86_X32_ABI case ARCH_MAP_VDSO_X32: return prctl_map_vdso(&vdsox32_image, arg2); # endif # ifdef CONFIG_IA32_EMULATION case ARCH_MAP_VDSO_32: return prctl_map_vdso(&vdso32_image, arg2); # endif case ARCH_MAP_VDSO_64: return prctl_map_vdso(&vdso64_image, arg2); #endif #ifdef CONFIG_ADDRESS_MASKING case ARCH_GET_UNTAG_MASK: return put_user(task->mm->context.untag_mask, (unsigned long __user *)arg2); case ARCH_ENABLE_TAGGED_ADDR: return prctl_enable_tagged_addr(task->mm, arg2); case ARCH_FORCE_TAGGED_SVA: if (current != task) return -EINVAL; set_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &task->mm->context.flags); return 0; case ARCH_GET_MAX_TAG_BITS: if (!cpu_feature_enabled(X86_FEATURE_LAM)) return put_user(0, (unsigned long __user *)arg2); else return put_user(LAM_U57_BITS, (unsigned long __user *)arg2); #endif case ARCH_SHSTK_ENABLE: case ARCH_SHSTK_DISABLE: case ARCH_SHSTK_LOCK: case ARCH_SHSTK_UNLOCK: case ARCH_SHSTK_STATUS: return shstk_prctl(task, option, arg2); default: ret = -EINVAL; break; } return ret; } |
| 1049 2 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Access to user system call parameters and results * * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. * * See asm-generic/syscall.h for descriptions of what we must do here. */ #ifndef _ASM_X86_SYSCALL_H #define _ASM_X86_SYSCALL_H #include <uapi/linux/audit.h> #include <linux/sched.h> #include <linux/err.h> #include <asm/thread_info.h> /* for TS_COMPAT */ #include <asm/unistd.h> /* This is used purely for kernel/trace/trace_syscalls.c */ typedef long (*sys_call_ptr_t)(const struct pt_regs *); extern const sys_call_ptr_t sys_call_table[]; /* * These may not exist, but still put the prototypes in so we * can use IS_ENABLED(). */ extern long ia32_sys_call(const struct pt_regs *, unsigned int nr); extern long x32_sys_call(const struct pt_regs *, unsigned int nr); extern long x64_sys_call(const struct pt_regs *, unsigned int nr); /* * Only the low 32 bits of orig_ax are meaningful, so we return int. * This importantly ignores the high bits on 64-bit, so comparisons * sign-extend the low 32 bits. */ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { return regs->orig_ax; } static inline void syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr) { regs->orig_ax = nr; } static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { regs->ax = regs->orig_ax; } static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { unsigned long error = regs->ax; #ifdef CONFIG_IA32_EMULATION /* * TS_COMPAT is set for 32-bit syscall entries and then * remains set until we return to user mode. */ if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED)) /* * Sign-extend the value so (int)-EFOO becomes (long)-EFOO * and will match correctly in comparisons. */ error = (long) (int) error; #endif return IS_ERR_VALUE(error) ? error : 0; } static inline long syscall_get_return_value(struct task_struct *task, struct pt_regs *regs) { return regs->ax; } static inline void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, int error, long val) { regs->ax = (long) error ?: val; } #ifdef CONFIG_X86_32 static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, unsigned long *args) { args[0] = regs->bx; args[1] = regs->cx; args[2] = regs->dx; args[3] = regs->si; args[4] = regs->di; args[5] = regs->bp; } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, const unsigned long *args) { regs->bx = args[0]; regs->cx = args[1]; regs->dx = args[2]; regs->si = args[3]; regs->di = args[4]; regs->bp = args[5]; } static inline int syscall_get_arch(struct task_struct *task) { return AUDIT_ARCH_I386; } #else /* CONFIG_X86_64 */ static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION if (task->thread_info.status & TS_COMPAT) { *args++ = regs->bx; *args++ = regs->cx; *args++ = regs->dx; *args++ = regs->si; *args++ = regs->di; *args = regs->bp; } else # endif { *args++ = regs->di; *args++ = regs->si; *args++ = regs->dx; *args++ = regs->r10; *args++ = regs->r8; *args = regs->r9; } } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION if (task->thread_info.status & TS_COMPAT) { regs->bx = *args++; regs->cx = *args++; regs->dx = *args++; regs->si = *args++; regs->di = *args++; regs->bp = *args; } else # endif { regs->di = *args++; regs->si = *args++; regs->dx = *args++; regs->r10 = *args++; regs->r8 = *args++; regs->r9 = *args; } } static inline int syscall_get_arch(struct task_struct *task) { /* x32 tasks should be considered AUDIT_ARCH_X86_64. */ return (IS_ENABLED(CONFIG_IA32_EMULATION) && task->thread_info.status & TS_COMPAT) ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; } bool do_syscall_64(struct pt_regs *regs, int nr); void do_int80_emulation(struct pt_regs *regs); #endif /* CONFIG_X86_32 */ void do_int80_syscall_32(struct pt_regs *regs); bool do_fast_syscall_32(struct pt_regs *regs); bool do_SYSENTER_32(struct pt_regs *regs); #endif /* _ASM_X86_SYSCALL_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PCI_H #define _ASM_X86_PCI_H #include <linux/mm.h> /* for struct page */ #include <linux/types.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/scatterlist.h> #include <linux/numa.h> #include <asm/io.h> #include <asm/memtype.h> struct pci_sysdata { int domain; /* PCI domain */ int node; /* NUMA node */ #ifdef CONFIG_ACPI struct acpi_device *companion; /* ACPI companion device */ #endif #ifdef CONFIG_X86_64 void *iommu; /* IOMMU private data */ #endif #ifdef CONFIG_PCI_MSI void *fwnode; /* IRQ domain for MSI assignment */ #endif #if IS_ENABLED(CONFIG_VMD) struct pci_dev *vmd_dev; /* VMD Device if in Intel VMD domain */ #endif }; extern int pci_routeirq; extern int noioapicquirk; extern int noioapicreroute; static inline struct pci_sysdata *to_pci_sysdata(const struct pci_bus *bus) { return bus->sysdata; } #ifdef CONFIG_PCI #ifdef CONFIG_PCI_DOMAINS static inline int pci_domain_nr(struct pci_bus *bus) { return to_pci_sysdata(bus)->domain; } static inline int pci_proc_domain(struct pci_bus *bus) { return pci_domain_nr(bus); } #endif #ifdef CONFIG_PCI_MSI static inline void *_pci_root_bus_fwnode(struct pci_bus *bus) { return to_pci_sysdata(bus)->fwnode; } #define pci_root_bus_fwnode _pci_root_bus_fwnode #endif #if IS_ENABLED(CONFIG_VMD) static inline bool is_vmd(struct pci_bus *bus) { return to_pci_sysdata(bus)->vmd_dev != NULL; } #else #define is_vmd(bus) false #endif /* CONFIG_VMD */ /* Can be used to override the logic in pci_scan_bus for skipping already-configured bus numbers - to be used for buggy BIOSes or architectures with incomplete PCI setup by the loader */ extern unsigned int pcibios_assign_all_busses(void); extern int pci_legacy_init(void); #else static inline int pcibios_assign_all_busses(void) { return 0; } #endif extern unsigned long pci_mem_start; #define PCIBIOS_MIN_IO 0x1000 #define PCIBIOS_MIN_MEM (pci_mem_start) #define PCIBIOS_MIN_CARDBUS_IO 0x4000 extern int pcibios_enabled; void pcibios_scan_root(int bus); struct irq_routing_table *pcibios_get_irq_routing_table(void); int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); bool pci_dev_has_default_msi_parent_domain(struct pci_dev *dev); #define HAVE_PCI_MMAP #define arch_can_pci_mmap_wc() pat_enabled() #define ARCH_GENERIC_PCI_MMAP_RESOURCE #ifdef CONFIG_PCI extern void early_quirks(void); #else static inline void early_quirks(void) { } #endif extern void pci_iommu_alloc(void); #ifdef CONFIG_NUMA /* Returns the node based on pci bus */ static inline int __pcibus_to_node(const struct pci_bus *bus) { return to_pci_sysdata(bus)->node; } static inline const struct cpumask * cpumask_of_pcibus(const struct pci_bus *bus) { int node; node = __pcibus_to_node(bus); return (node == NUMA_NO_NODE) ? cpu_online_mask : cpumask_of_node(node); } #endif #endif /* _ASM_X86_PCI_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ #include <linux/types.h> #include <linux/bpf.h> #include <linux/bpf_local_storage.h> #include <uapi/linux/btf.h> #include <linux/btf_ids.h> DEFINE_BPF_STORAGE_CACHE(cgroup_cache); static struct bpf_local_storage __rcu **cgroup_storage_ptr(void *owner) { struct cgroup *cg = owner; return &cg->bpf_cgrp_storage; } void bpf_cgrp_storage_free(struct cgroup *cgroup) { struct bpf_local_storage *local_storage; rcu_read_lock(); local_storage = rcu_dereference(cgroup->bpf_cgrp_storage); if (!local_storage) goto out; bpf_local_storage_destroy(local_storage); out: rcu_read_unlock(); } static struct bpf_local_storage_data * cgroup_storage_lookup(struct cgroup *cgroup, struct bpf_map *map, bool cacheit_lockit) { struct bpf_local_storage *cgroup_storage; struct bpf_local_storage_map *smap; cgroup_storage = rcu_dereference_check(cgroup->bpf_cgrp_storage, bpf_rcu_lock_held()); if (!cgroup_storage) return NULL; smap = (struct bpf_local_storage_map *)map; return bpf_local_storage_lookup(cgroup_storage, smap, cacheit_lockit); } static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key) { struct bpf_local_storage_data *sdata; struct cgroup *cgroup; int fd; fd = *(int *)key; cgroup = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgroup)) return ERR_CAST(cgroup); sdata = cgroup_storage_lookup(cgroup, map, true); cgroup_put(cgroup); return sdata ? sdata->data : NULL; } static long bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct cgroup *cgroup; int fd; fd = *(int *)key; cgroup = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgroup)) return PTR_ERR(cgroup); sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map, value, map_flags, false); cgroup_put(cgroup); return PTR_ERR_OR_ZERO(sdata); } static int cgroup_storage_delete(struct cgroup *cgroup, struct bpf_map *map) { struct bpf_local_storage_data *sdata; sdata = cgroup_storage_lookup(cgroup, map, false); if (!sdata) return -ENOENT; return bpf_selem_unlink(SELEM(sdata)); } static long bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key) { struct cgroup *cgroup; int err, fd; fd = *(int *)key; cgroup = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgroup)) return PTR_ERR(cgroup); err = cgroup_storage_delete(cgroup, map); cgroup_put(cgroup); return err; } static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; } static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) { return bpf_local_storage_map_alloc(attr, &cgroup_cache); } static void cgroup_storage_map_free(struct bpf_map *map) { bpf_local_storage_map_free(map, &cgroup_cache); } BPF_CALL_4(bpf_cgrp_storage_get, struct bpf_map *, map, struct cgroup *, cgroup, void *, value, u64, flags) { struct bpf_local_storage_data *sdata; WARN_ON_ONCE(!bpf_rcu_lock_held()); if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) return (unsigned long)NULL; if (!cgroup) return (unsigned long)NULL; sdata = cgroup_storage_lookup(cgroup, map, true); if (sdata) goto out; /* only allocate new storage, when the cgroup is refcounted */ if (!percpu_ref_is_dying(&cgroup->self.refcnt) && (flags & BPF_LOCAL_STORAGE_GET_F_CREATE)) sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map, value, BPF_NOEXIST, false); out: return IS_ERR_OR_NULL(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; } BPF_CALL_2(bpf_cgrp_storage_delete, struct bpf_map *, map, struct cgroup *, cgroup) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!cgroup) return -EINVAL; return cgroup_storage_delete(cgroup, map); } const struct bpf_map_ops cgrp_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, .map_alloc = cgroup_storage_map_alloc, .map_free = cgroup_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_cgrp_storage_lookup_elem, .map_update_elem = bpf_cgrp_storage_update_elem, .map_delete_elem = bpf_cgrp_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, .map_mem_usage = bpf_local_storage_map_mem_usage, .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_owner_storage_ptr = cgroup_storage_ptr, }; const struct bpf_func_proto bpf_cgrp_storage_get_proto = { .func = bpf_cgrp_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &bpf_cgroup_btf_id[0], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_cgrp_storage_delete_proto = { .func = bpf_cgrp_storage_delete, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &bpf_cgroup_btf_id[0], }; |
| 15 17 1 16 16 8 9 7 9 6 1 3 2 7 9 13 10 7 13 9 13 7 7 7 14 57 4 2 136 135 97 61 95 136 135 128 100 4 134 2 2 2 43 135 135 126 8 133 3 1 125 8 8 128 8 2 8 129 15 129 2 129 18 18 11 4 4 1 3 15 15 3 9 2 7 2 2 14 18 37 19 4 19 19 18 19 19 10 1 7 12 45 27 21 45 39 21 4 6 3 1 7 1 96 96 94 24 28 28 20 7 20 28 30 2 28 5 21 6 17 11 28 2 4 4 4 4 7 4 6 363 362 363 53 104 23 8 129 53 30 7 3 1 3 8 1 4 1 1 1 2 2 3 28 450 450 3 16 14 47 4 60 33 37 286 90 56 266 52 98 317 52 42 89 137 247 81 378 412 378 36 296 392 63 36 301 416 416 389 6 3 395 397 395 47 365 408 7 3 10 390 363 408 26 26 22 13 6 3 9 2 9 26 58 1 4 11 4 1 42 2 46 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/madvise.c * * Copyright (C) 1999 Linus Torvalds * Copyright (C) 2002 Christoph Hellwig */ #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/mempolicy.h> #include <linux/page-isolation.h> #include <linux/page_idle.h> #include <linux/userfaultfd_k.h> #include <linux/hugetlb.h> #include <linux/falloc.h> #include <linux/fadvise.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mm_inline.h> #include <linux/mmu_context.h> #include <linux/string.h> #include <linux/uio.h> #include <linux/ksm.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/pagewalk.h> #include <linux/swap.h> #include <linux/leafops.h> #include <linux/shmem_fs.h> #include <linux/mmu_notifier.h> #include <asm/tlb.h> #include "internal.h" #include "swap.h" #define __MADV_SET_ANON_VMA_NAME (-1) /* * Maximum number of attempts we make to install guard pages before we give up * and return -ERESTARTNOINTR to have userspace try again. */ #define MAX_MADVISE_GUARD_RETRIES 3 struct madvise_walk_private { struct mmu_gather *tlb; bool pageout; }; enum madvise_lock_mode { MADVISE_NO_LOCK, MADVISE_MMAP_READ_LOCK, MADVISE_MMAP_WRITE_LOCK, MADVISE_VMA_READ_LOCK, }; struct madvise_behavior_range { unsigned long start; unsigned long end; }; struct madvise_behavior { struct mm_struct *mm; int behavior; struct mmu_gather *tlb; enum madvise_lock_mode lock_mode; struct anon_vma_name *anon_name; /* * The range over which the behaviour is currently being applied. If * traversing multiple VMAs, this is updated for each. */ struct madvise_behavior_range range; /* The VMA and VMA preceding it (if applicable) currently targeted. */ struct vm_area_struct *prev; struct vm_area_struct *vma; bool lock_dropped; }; #ifdef CONFIG_ANON_VMA_NAME static int madvise_walk_vmas(struct madvise_behavior *madv_behavior); struct anon_vma_name *anon_vma_name_alloc(const char *name) { struct anon_vma_name *anon_name; size_t count; /* Add 1 for NUL terminator at the end of the anon_name->name */ count = strlen(name) + 1; anon_name = kmalloc_flex(*anon_name, name, count); if (anon_name) { kref_init(&anon_name->kref); memcpy(anon_name->name, name, count); } return anon_name; } void anon_vma_name_free(struct kref *kref) { struct anon_vma_name *anon_name = container_of(kref, struct anon_vma_name, kref); kfree(anon_name); } struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { vma_assert_stabilised(vma); return vma->anon_name; } /* mmap_lock should be write-locked */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) { struct anon_vma_name *orig_name = anon_vma_name(vma); if (!anon_name) { vma->anon_name = NULL; anon_vma_name_put(orig_name); return 0; } if (anon_vma_name_eq(orig_name, anon_name)) return 0; vma->anon_name = anon_vma_name_reuse(anon_name); anon_vma_name_put(orig_name); return 0; } #else /* CONFIG_ANON_VMA_NAME */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) { if (anon_name) return -EINVAL; return 0; } #endif /* CONFIG_ANON_VMA_NAME */ /* * Update the vm_flags or anon_name on region of a vma, splitting it or merging * it as necessary. Must be called with mmap_lock held for writing. */ static int madvise_update_vma(vm_flags_t new_flags, struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; vma_flags_t new_vma_flags = legacy_to_vma_flags(new_flags); struct madvise_behavior_range *range = &madv_behavior->range; struct anon_vma_name *anon_name = madv_behavior->anon_name; bool set_new_anon_name = madv_behavior->behavior == __MADV_SET_ANON_VMA_NAME; VMA_ITERATOR(vmi, madv_behavior->mm, range->start); if (vma_flags_same_mask(&vma->flags, new_vma_flags) && (!set_new_anon_name || anon_vma_name_eq(anon_vma_name(vma), anon_name))) return 0; if (set_new_anon_name) vma = vma_modify_name(&vmi, madv_behavior->prev, vma, range->start, range->end, anon_name); else vma = vma_modify_flags(&vmi, madv_behavior->prev, vma, range->start, range->end, &new_vma_flags); if (IS_ERR(vma)) return PTR_ERR(vma); madv_behavior->vma = vma; /* vm_flags is protected by the mmap_lock held in write mode. */ vma_start_write(vma); vma->flags = new_vma_flags; if (set_new_anon_name) return replace_anon_vma_name(vma, anon_name); return 0; } #ifdef CONFIG_SWAP static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->private; struct swap_iocb *splug = NULL; pte_t *ptep = NULL; spinlock_t *ptl; unsigned long addr; for (addr = start; addr < end; addr += PAGE_SIZE) { pte_t pte; softleaf_t entry; struct folio *folio; if (!ptep++) { ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!ptep) break; } pte = ptep_get(ptep); entry = softleaf_from_pte(pte); if (unlikely(!softleaf_is_swap(entry))) continue; pte_unmap_unlock(ptep, ptl); ptep = NULL; folio = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, vma, addr, &splug); if (folio) folio_put(folio); } if (ptep) pte_unmap_unlock(ptep, ptl); swap_read_unplug(splug); cond_resched(); return 0; } static const struct mm_walk_ops swapin_walk_ops = { .pmd_entry = swapin_walk_pmd_entry, .walk_lock = PGWALK_RDLOCK, }; static void shmem_swapin_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct address_space *mapping) { XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start)); pgoff_t end_index = linear_page_index(vma, end) - 1; struct folio *folio; struct swap_iocb *splug = NULL; rcu_read_lock(); xas_for_each(&xas, folio, end_index) { unsigned long addr; swp_entry_t entry; if (!xa_is_value(folio)) continue; entry = radix_to_swp_entry(folio); /* There might be swapin error entries in shmem mapping. */ if (!softleaf_is_swap(entry)) continue; addr = vma->vm_start + ((xas.xa_index - vma->vm_pgoff) << PAGE_SHIFT); xas_pause(&xas); rcu_read_unlock(); folio = read_swap_cache_async(entry, mapping_gfp_mask(mapping), vma, addr, &splug); if (folio) folio_put(folio); rcu_read_lock(); } rcu_read_unlock(); swap_read_unplug(splug); } #endif /* CONFIG_SWAP */ static void mark_mmap_lock_dropped(struct madvise_behavior *madv_behavior) { VM_WARN_ON_ONCE(madv_behavior->lock_mode == MADVISE_VMA_READ_LOCK); madv_behavior->lock_dropped = true; } /* * Schedule all required I/O operations. Do not wait for completion. */ static long madvise_willneed(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct mm_struct *mm = madv_behavior->mm; struct file *file = vma->vm_file; unsigned long start = madv_behavior->range.start; unsigned long end = madv_behavior->range.end; loff_t offset; #ifdef CONFIG_SWAP if (!file) { walk_page_range_vma(vma, start, end, &swapin_walk_ops, vma); lru_add_drain(); /* Push any new pages onto the LRU now */ return 0; } if (shmem_mapping(file->f_mapping)) { shmem_swapin_range(vma, start, end, file->f_mapping); lru_add_drain(); /* Push any new pages onto the LRU now */ return 0; } #else if (!file) return -EBADF; #endif if (IS_DAX(file_inode(file))) { /* no bad return value, but ignore advice */ return 0; } /* * Filesystem's fadvise may need to take various locks. We need to * explicitly grab a reference because the vma (and hence the * vma's reference to the file) can go away as soon as we drop * mmap_lock. */ mark_mmap_lock_dropped(madv_behavior); get_file(file); offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); mmap_read_unlock(mm); vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); fput(file); mmap_read_lock(mm); return 0; } static inline bool can_do_file_pageout(struct vm_area_struct *vma) { if (!vma->vm_file) return false; /* * paging out pagecache only for non-anonymous mappings that correspond * to the files the calling process could (if tried) open for writing; * otherwise we'd be including shared non-exclusive mappings, which * opens a side channel. */ return file_owner_or_capable(vma->vm_file) || file_permission(vma->vm_file, MAY_WRITE) == 0; } static inline int madvise_folio_pte_batch(unsigned long addr, unsigned long end, struct folio *folio, pte_t *ptep, pte_t *ptentp) { int max_nr = (end - addr) / PAGE_SIZE; return folio_pte_batch_flags(folio, NULL, ptep, ptentp, max_nr, FPB_MERGE_YOUNG_DIRTY); } static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct madvise_walk_private *private = walk->private; struct mmu_gather *tlb = private->tlb; bool pageout = private->pageout; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; pte_t *start_pte, *pte, ptent; spinlock_t *ptl; struct folio *folio = NULL; LIST_HEAD(folio_list); bool pageout_anon_only_filter; unsigned int batch_count = 0; int nr; if (fatal_signal_pending(current)) return -EINTR; pageout_anon_only_filter = pageout && !vma_is_anonymous(vma) && !can_do_file_pageout(vma); #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(*pmd)) { pmd_t orig_pmd; unsigned long next = pmd_addr_end(addr, end); tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; orig_pmd = *pmd; if (is_huge_zero_pmd(orig_pmd)) goto huge_unlock; if (unlikely(!pmd_present(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !pmd_is_migration_entry(orig_pmd)); goto huge_unlock; } folio = pmd_folio(orig_pmd); /* Do not interfere with other mappings of this folio */ if (folio_maybe_mapped_shared(folio)) goto huge_unlock; if (pageout_anon_only_filter && !folio_test_anon(folio)) goto huge_unlock; if (next - addr != HPAGE_PMD_SIZE) { int err; folio_get(folio); spin_unlock(ptl); folio_lock(folio); err = split_folio(folio); folio_unlock(folio); folio_put(folio); if (!err) goto regular_folio; return 0; } if (!pageout && pmd_young(orig_pmd)) { pmdp_invalidate(vma, addr, pmd); orig_pmd = pmd_mkold(orig_pmd); set_pmd_at(mm, addr, pmd, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } folio_clear_referenced(folio); folio_test_clear_young(folio); if (folio_test_active(folio)) folio_set_workingset(folio); if (pageout) { if (folio_isolate_lru(folio)) { if (folio_test_unevictable(folio)) folio_putback_lru(folio); else list_add(&folio->lru, &folio_list); } } else folio_deactivate(folio); huge_unlock: spin_unlock(ptl); if (pageout) reclaim_pages(&folio_list); return 0; } regular_folio: #endif tlb_change_page_size(tlb, PAGE_SIZE); restart: start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!start_pte) return 0; flush_tlb_batched_pending(mm); lazy_mmu_mode_enable(); for (; addr < end; pte += nr, addr += nr * PAGE_SIZE) { nr = 1; ptent = ptep_get(pte); if (++batch_count == SWAP_CLUSTER_MAX) { batch_count = 0; if (need_resched()) { lazy_mmu_mode_disable(); pte_unmap_unlock(start_pte, ptl); cond_resched(); goto restart; } } if (pte_none(ptent)) continue; if (!pte_present(ptent)) continue; folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * If we encounter a large folio, only split it if it is not * fully mapped within the range we are operating on. Otherwise * leave it as is so that it can be swapped out whole. If we * fail to split a folio, leave it in place and advance to the * next pte in the range. */ if (folio_test_large(folio)) { nr = madvise_folio_pte_batch(addr, end, folio, pte, &ptent); if (nr < folio_nr_pages(folio)) { int err; if (folio_maybe_mapped_shared(folio)) continue; if (pageout_anon_only_filter && !folio_test_anon(folio)) continue; if (!folio_trylock(folio)) continue; folio_get(folio); lazy_mmu_mode_disable(); pte_unmap_unlock(start_pte, ptl); start_pte = NULL; err = split_folio(folio); folio_unlock(folio); folio_put(folio); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; flush_tlb_batched_pending(mm); lazy_mmu_mode_enable(); if (!err) nr = 0; continue; } } /* * Do not interfere with other mappings of this folio and * non-LRU folio. If we have a large folio at this point, we * know it is fully mapped so if its mapcount is the same as its * number of pages, it must be exclusive. */ if (!folio_test_lru(folio) || folio_mapcount(folio) != folio_nr_pages(folio)) continue; if (pageout_anon_only_filter && !folio_test_anon(folio)) continue; if (!pageout && pte_young(ptent)) { clear_young_dirty_ptes(vma, addr, pte, nr, CYDP_CLEAR_YOUNG); tlb_remove_tlb_entries(tlb, pte, nr, addr); } /* * We are deactivating a folio for accelerating reclaiming. * VM couldn't reclaim the folio unless we clear PG_young. * As a side effect, it makes confuse idle-page tracking * because they will miss recent referenced history. */ folio_clear_referenced(folio); folio_test_clear_young(folio); if (folio_test_active(folio)) folio_set_workingset(folio); if (pageout) { if (folio_isolate_lru(folio)) { if (folio_test_unevictable(folio)) folio_putback_lru(folio); else list_add(&folio->lru, &folio_list); } } else folio_deactivate(folio); } if (start_pte) { lazy_mmu_mode_disable(); pte_unmap_unlock(start_pte, ptl); } if (pageout) reclaim_pages(&folio_list); cond_resched(); return 0; } static const struct mm_walk_ops cold_walk_ops = { .pmd_entry = madvise_cold_or_pageout_pte_range, .walk_lock = PGWALK_RDLOCK, }; static void madvise_cold_page_range(struct mmu_gather *tlb, struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct madvise_behavior_range *range = &madv_behavior->range; struct madvise_walk_private walk_private = { .pageout = false, .tlb = tlb, }; tlb_start_vma(tlb, vma); walk_page_range_vma(vma, range->start, range->end, &cold_walk_ops, &walk_private); tlb_end_vma(tlb, vma); } static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { return !(vma->vm_flags & (VM_LOCKED|VM_PFNMAP|VM_HUGETLB)); } static long madvise_cold(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct mmu_gather tlb; if (!can_madv_lru_vma(vma)) return -EINVAL; lru_add_drain(); tlb_gather_mmu(&tlb, madv_behavior->mm); madvise_cold_page_range(&tlb, madv_behavior); tlb_finish_mmu(&tlb); return 0; } static void madvise_pageout_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, struct madvise_behavior_range *range) { struct madvise_walk_private walk_private = { .pageout = true, .tlb = tlb, }; tlb_start_vma(tlb, vma); walk_page_range_vma(vma, range->start, range->end, &cold_walk_ops, &walk_private); tlb_end_vma(tlb, vma); } static long madvise_pageout(struct madvise_behavior *madv_behavior) { struct mmu_gather tlb; struct vm_area_struct *vma = madv_behavior->vma; if (!can_madv_lru_vma(vma)) return -EINVAL; /* * If the VMA belongs to a private file mapping, there can be private * dirty pages which can be paged out if even this process is neither * owner nor write capable of the file. We allow private file mappings * further to pageout dirty anon pages. */ if (!vma_is_anonymous(vma) && (!can_do_file_pageout(vma) && (vma->vm_flags & VM_MAYSHARE))) return 0; lru_add_drain(); tlb_gather_mmu(&tlb, madv_behavior->mm); madvise_pageout_page_range(&tlb, vma, &madv_behavior->range); tlb_finish_mmu(&tlb); return 0; } static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { const cydp_t cydp_flags = CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY; struct mmu_gather *tlb = walk->private; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; pte_t *start_pte, *pte, ptent; struct folio *folio; int nr_swap = 0; unsigned long next; int nr, max_nr; next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd)) if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next)) return 0; tlb_change_page_size(tlb, PAGE_SIZE); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) return 0; flush_tlb_batched_pending(mm); lazy_mmu_mode_enable(); for (; addr != end; pte += nr, addr += PAGE_SIZE * nr) { nr = 1; ptent = ptep_get(pte); if (pte_none(ptent)) continue; /* * If the pte has swp_entry, just clear page table to * prevent swap-in which is more expensive rather than * (page allocation + zeroing). */ if (!pte_present(ptent)) { softleaf_t entry = softleaf_from_pte(ptent); if (softleaf_is_swap(entry)) { max_nr = (end - addr) / PAGE_SIZE; nr = swap_pte_batch(pte, max_nr, ptent); nr_swap -= nr; swap_put_entries_direct(entry, nr); clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm); } else if (softleaf_is_hwpoison(entry) || softleaf_is_poison_marker(entry)) { pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * If we encounter a large folio, only split it if it is not * fully mapped within the range we are operating on. Otherwise * leave it as is so that it can be marked as lazyfree. If we * fail to split a folio, leave it in place and advance to the * next pte in the range. */ if (folio_test_large(folio)) { nr = madvise_folio_pte_batch(addr, end, folio, pte, &ptent); if (nr < folio_nr_pages(folio)) { int err; if (folio_maybe_mapped_shared(folio)) continue; if (!folio_trylock(folio)) continue; folio_get(folio); lazy_mmu_mode_disable(); pte_unmap_unlock(start_pte, ptl); start_pte = NULL; err = split_folio(folio); folio_unlock(folio); folio_put(folio); pte = pte_offset_map_lock(mm, pmd, addr, &ptl); start_pte = pte; if (!start_pte) break; flush_tlb_batched_pending(mm); lazy_mmu_mode_enable(); if (!err) nr = 0; continue; } } if (folio_test_swapcache(folio) || folio_test_dirty(folio)) { if (!folio_trylock(folio)) continue; /* * If we have a large folio at this point, we know it is * fully mapped so if its mapcount is the same as its * number of pages, it must be exclusive. */ if (folio_mapcount(folio) != folio_nr_pages(folio)) { folio_unlock(folio); continue; } if (folio_test_swapcache(folio) && !folio_free_swap(folio)) { folio_unlock(folio); continue; } folio_clear_dirty(folio); folio_unlock(folio); } if (pte_young(ptent) || pte_dirty(ptent)) { clear_young_dirty_ptes(vma, addr, pte, nr, cydp_flags); tlb_remove_tlb_entries(tlb, pte, nr, addr); } folio_mark_lazyfree(folio); } if (nr_swap) add_mm_counter(mm, MM_SWAPENTS, nr_swap); if (start_pte) { lazy_mmu_mode_disable(); pte_unmap_unlock(start_pte, ptl); } cond_resched(); return 0; } static inline enum page_walk_lock get_walk_lock(enum madvise_lock_mode mode) { switch (mode) { case MADVISE_VMA_READ_LOCK: return PGWALK_VMA_RDLOCK_VERIFY; case MADVISE_MMAP_READ_LOCK: return PGWALK_RDLOCK; default: /* Other modes don't require fixing up the walk_lock */ WARN_ON_ONCE(1); return PGWALK_RDLOCK; } } static int madvise_free_single_vma(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; struct vm_area_struct *vma = madv_behavior->vma; struct mmu_notifier_range range = { .start = madv_behavior->range.start, .end = madv_behavior->range.end, }; struct mmu_gather *tlb = madv_behavior->tlb; struct mm_walk_ops walk_ops = { .pmd_entry = madvise_free_pte_range, }; /* MADV_FREE works for only anon vma at the moment */ if (!vma_is_anonymous(vma)) return -EINVAL; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, range.start, range.end); lru_add_drain(); update_hiwater_rss(mm); mmu_notifier_invalidate_range_start(&range); tlb_start_vma(tlb, vma); walk_ops.walk_lock = get_walk_lock(madv_behavior->lock_mode); walk_page_range_vma(vma, range.start, range.end, &walk_ops, tlb); tlb_end_vma(tlb, vma); mmu_notifier_invalidate_range_end(&range); return 0; } /* * Application no longer needs these pages. If the pages are dirty, * it's OK to just throw them away. The app will be more careful about * data it wants to keep. Be sure to free swap resources too. The * zap_vma_range call sets things up for shrink_active_list to actually * free these pages later if no one else has touched them in the meantime, * although we could add these pages to a global reuse list for * shrink_active_list to pick up before reclaiming other pages. * * NB: This interface discards data rather than pushes it out to swap, * as some implementations do. This has performance implications for * applications like large transactional databases which want to discard * pages in anonymous maps after committing to backing store the data * that was kept in them. There is no reason to write this data out to * the swap area if the application is discarding it. * * An interface that causes the system to free clean pages and flush * dirty pages is already available as msync(MS_INVALIDATE). */ static long madvise_dontneed_single_vma(struct madvise_behavior *madv_behavior) { struct madvise_behavior_range *range = &madv_behavior->range; struct zap_details details = { .reclaim_pt = true, }; zap_vma_range_batched(madv_behavior->tlb, madv_behavior->vma, range->start, range->end - range->start, &details); return 0; } static bool madvise_dontneed_free_valid_vma(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; int behavior = madv_behavior->behavior; struct madvise_behavior_range *range = &madv_behavior->range; if (!is_vm_hugetlb_page(vma)) { unsigned int forbidden = VM_PFNMAP; if (behavior != MADV_DONTNEED_LOCKED) forbidden |= VM_LOCKED; return !(vma->vm_flags & forbidden); } if (behavior != MADV_DONTNEED && behavior != MADV_DONTNEED_LOCKED) return false; if (range->start & ~huge_page_mask(hstate_vma(vma))) return false; /* * Madvise callers expect the length to be rounded up to PAGE_SIZE * boundaries, and may be unaware that this VMA uses huge pages. * Avoid unexpected data loss by rounding down the number of * huge pages freed. */ range->end = ALIGN_DOWN(range->end, huge_page_size(hstate_vma(vma))); return true; } static long madvise_dontneed_free(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; struct madvise_behavior_range *range = &madv_behavior->range; int behavior = madv_behavior->behavior; if (!madvise_dontneed_free_valid_vma(madv_behavior)) return -EINVAL; if (range->start == range->end) return 0; if (!userfaultfd_remove(madv_behavior->vma, range->start, range->end)) { struct vm_area_struct *vma; mark_mmap_lock_dropped(madv_behavior); mmap_read_lock(mm); madv_behavior->vma = vma = vma_lookup(mm, range->start); if (!vma) return -ENOMEM; /* * Potential end adjustment for hugetlb vma is OK as * the check below keeps end within vma. */ if (!madvise_dontneed_free_valid_vma(madv_behavior)) return -EINVAL; if (range->end > vma->vm_end) { /* * Don't fail if end > vma->vm_end. If the old * vma was split while the mmap_lock was * released the effect of the concurrent * operation may not cause madvise() to * have an undefined result. There may be an * adjacent next vma that we'll walk * next. userfaultfd_remove() will generate an * UFFD_EVENT_REMOVE repetition on the * end-vma->vm_end range, but the manager can * handle a repetition fine. */ range->end = vma->vm_end; } /* * If the memory region between start and end was * originally backed by 4kB pages and then remapped to * be backed by hugepages while mmap_lock was dropped, * the adjustment for hugetlb vma above may have rounded * end down to the start address. */ if (range->start == range->end) return 0; VM_WARN_ON(range->start > range->end); } if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED) return madvise_dontneed_single_vma(madv_behavior); else if (behavior == MADV_FREE) return madvise_free_single_vma(madv_behavior); else return -EINVAL; } static long madvise_populate(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; const bool write = madv_behavior->behavior == MADV_POPULATE_WRITE; int locked = 1; unsigned long start = madv_behavior->range.start; unsigned long end = madv_behavior->range.end; long pages; while (start < end) { /* Populate (prefault) page tables readable/writable. */ pages = faultin_page_range(mm, start, end, write, &locked); if (!locked) { mmap_read_lock(mm); locked = 1; } if (pages < 0) { switch (pages) { case -EINTR: return -EINTR; case -EINVAL: /* Incompatible mappings / permissions. */ return -EINVAL; case -EHWPOISON: return -EHWPOISON; case -EFAULT: /* VM_FAULT_SIGBUS or VM_FAULT_SIGSEGV */ return -EFAULT; default: pr_warn_once("%s: unhandled return value: %ld\n", __func__, pages); fallthrough; case -ENOMEM: /* No VMA or out of memory. */ return -ENOMEM; } } start += pages * PAGE_SIZE; } return 0; } /* * Application wants to free up the pages and associated backing store. * This is effectively punching a hole into the middle of a file. */ static long madvise_remove(struct madvise_behavior *madv_behavior) { loff_t offset; int error; struct file *f; struct mm_struct *mm = madv_behavior->mm; struct vm_area_struct *vma = madv_behavior->vma; unsigned long start = madv_behavior->range.start; unsigned long end = madv_behavior->range.end; mark_mmap_lock_dropped(madv_behavior); if (vma->vm_flags & VM_LOCKED) return -EINVAL; f = vma->vm_file; if (!f || !f->f_mapping || !f->f_mapping->host) { return -EINVAL; } if (!vma_is_shared_maywrite(vma)) return -EACCES; offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); /* * Filesystem's fallocate may need to take i_rwsem. We need to * explicitly grab a reference because the vma (and hence the * vma's reference to the file) can go away as soon as we drop * mmap_lock. */ get_file(f); if (userfaultfd_remove(vma, start, end)) { /* mmap_lock was not released by userfaultfd_remove() */ mmap_read_unlock(mm); } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); fput(f); mmap_read_lock(mm); return error; } static bool is_valid_guard_vma(struct vm_area_struct *vma, bool allow_locked) { vm_flags_t disallowed = VM_SPECIAL | VM_HUGETLB; /* * A user could lock after setting a guard range but that's fine, as * they'd not be able to fault in. The issue arises when we try to zap * existing locked VMAs. We don't want to do that. */ if (!allow_locked) disallowed |= VM_LOCKED; return !(vma->vm_flags & disallowed); } static bool is_guard_pte_marker(pte_t ptent) { const softleaf_t entry = softleaf_from_pte(ptent); return softleaf_is_guard_marker(entry); } static int guard_install_pud_entry(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk) { pud_t pudval = pudp_get(pud); /* If huge return >0 so we abort the operation + zap. */ return pud_trans_huge(pudval); } static int guard_install_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { pmd_t pmdval = pmdp_get(pmd); /* If huge return >0 so we abort the operation + zap. */ return pmd_trans_huge(pmdval); } static int guard_install_pte_entry(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { pte_t pteval = ptep_get(pte); unsigned long *nr_pages = (unsigned long *)walk->private; /* If there is already a guard page marker, we have nothing to do. */ if (is_guard_pte_marker(pteval)) { (*nr_pages)++; return 0; } /* If populated return >0 so we abort the operation + zap. */ return 1; } static int guard_install_set_pte(unsigned long addr, unsigned long next, pte_t *ptep, struct mm_walk *walk) { unsigned long *nr_pages = (unsigned long *)walk->private; /* Simply install a PTE marker, this causes segfault on access. */ *ptep = make_pte_marker(PTE_MARKER_GUARD); (*nr_pages)++; return 0; } static long madvise_guard_install(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct madvise_behavior_range *range = &madv_behavior->range; struct mm_walk_ops walk_ops = { .pud_entry = guard_install_pud_entry, .pmd_entry = guard_install_pmd_entry, .pte_entry = guard_install_pte_entry, .install_pte = guard_install_set_pte, .walk_lock = get_walk_lock(madv_behavior->lock_mode), }; long err; int i; if (!is_valid_guard_vma(vma, /* allow_locked = */false)) return -EINVAL; /* * Set atomically under read lock. All pertinent readers will need to * acquire an mmap/VMA write lock to read it. All remaining readers may * or may not see the flag set, but we don't care. */ vma_set_atomic_flag(vma, VMA_MAYBE_GUARD_BIT); /* * If anonymous and we are establishing page tables the VMA ought to * have an anon_vma associated with it. * * We will hold an mmap read lock if this is necessary, this is checked * as part of the VMA lock logic. */ if (vma_is_anonymous(vma)) { VM_WARN_ON_ONCE(!vma->anon_vma && madv_behavior->lock_mode != MADVISE_MMAP_READ_LOCK); err = anon_vma_prepare(vma); if (err) return err; } /* * Optimistically try to install the guard marker pages first. If any * non-guard pages or THP huge pages are encountered, give up and zap * the range before trying again. * * We try a few times before giving up and releasing back to userland to * loop around, releasing locks in the process to avoid contention. * * This would only happen due to races with e.g. page faults or * khugepaged. * * In most cases we should simply install the guard markers immediately * with no zap or looping. */ for (i = 0; i < MAX_MADVISE_GUARD_RETRIES; i++) { unsigned long nr_pages = 0; /* Returns < 0 on error, == 0 if success, > 0 if zap needed. */ if (madv_behavior->lock_mode == MADVISE_VMA_READ_LOCK) err = walk_page_range_vma_unsafe(madv_behavior->vma, range->start, range->end, &walk_ops, &nr_pages); else err = walk_page_range_mm_unsafe(vma->vm_mm, range->start, range->end, &walk_ops, &nr_pages); if (err < 0) return err; if (err == 0) { unsigned long nr_expected_pages = PHYS_PFN(range->end - range->start); VM_WARN_ON(nr_pages != nr_expected_pages); return 0; } /* * OK some of the range have non-guard pages mapped, zap * them. This leaves existing guard pages in place. */ zap_vma_range(vma, range->start, range->end - range->start); } /* * We were unable to install the guard pages, return to userspace and * immediately retry, relieving lock contention. */ return restart_syscall(); } static int guard_remove_pud_entry(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk) { pud_t pudval = pudp_get(pud); /* If huge, cannot have guard pages present, so no-op - skip. */ if (pud_trans_huge(pudval)) walk->action = ACTION_CONTINUE; return 0; } static int guard_remove_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { pmd_t pmdval = pmdp_get(pmd); /* If huge, cannot have guard pages present, so no-op - skip. */ if (pmd_trans_huge(pmdval)) walk->action = ACTION_CONTINUE; return 0; } static int guard_remove_pte_entry(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { pte_t ptent = ptep_get(pte); if (is_guard_pte_marker(ptent)) { /* Simply clear the PTE marker. */ pte_clear_not_present_full(walk->mm, addr, pte, false); update_mmu_cache(walk->vma, addr, pte); } return 0; } static long madvise_guard_remove(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct madvise_behavior_range *range = &madv_behavior->range; struct mm_walk_ops wallk_ops = { .pud_entry = guard_remove_pud_entry, .pmd_entry = guard_remove_pmd_entry, .pte_entry = guard_remove_pte_entry, .walk_lock = get_walk_lock(madv_behavior->lock_mode), }; /* * We're ok with removing guards in mlock()'d ranges, as this is a * non-destructive action. */ if (!is_valid_guard_vma(vma, /* allow_locked = */true)) return -EINVAL; return walk_page_range_vma(vma, range->start, range->end, &wallk_ops, NULL); } #ifdef CONFIG_64BIT /* Does the madvise operation result in discarding of mapped data? */ static bool is_discard(int behavior) { switch (behavior) { case MADV_FREE: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_REMOVE: case MADV_DONTFORK: case MADV_WIPEONFORK: case MADV_GUARD_INSTALL: return true; } return false; } /* * We are restricted from madvise()'ing mseal()'d VMAs only in very particular * circumstances - discarding of data from read-only anonymous SEALED mappings. * * This is because users cannot trivally discard data from these VMAs, and may * only do so via an appropriate madvise() call. */ static bool can_madvise_modify(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; /* If the VMA isn't sealed we're good. */ if (!vma_is_sealed(vma)) return true; /* For a sealed VMA, we only care about discard operations. */ if (!is_discard(madv_behavior->behavior)) return true; /* * We explicitly permit all file-backed mappings, whether MAP_SHARED or * MAP_PRIVATE. * * The latter causes some complications. Because now, one can mmap() * read/write a MAP_PRIVATE mapping, write to it, then mprotect() * read-only, mseal() and a discard will be permitted. * * However, in order to avoid issues with potential use of madvise(..., * MADV_DONTNEED) of mseal()'d .text mappings we, for the time being, * permit this. */ if (!vma_is_anonymous(vma)) return true; /* If the user could write to the mapping anyway, then this is fine. */ if ((vma->vm_flags & VM_WRITE) && arch_vma_access_permitted(vma, /* write= */ true, /* execute= */ false, /* foreign= */ false)) return true; /* Otherwise, we are not permitted to perform this operation. */ return false; } #else static bool can_madvise_modify(struct madvise_behavior *madv_behavior) { return true; } #endif /* * Apply an madvise behavior to a region of a vma. madvise_update_vma * will handle splitting a vm area into separate areas, each area with its own * behavior. */ static int madvise_vma_behavior(struct madvise_behavior *madv_behavior) { int behavior = madv_behavior->behavior; struct vm_area_struct *vma = madv_behavior->vma; vm_flags_t new_flags = vma->vm_flags; struct madvise_behavior_range *range = &madv_behavior->range; int error; if (unlikely(!can_madvise_modify(madv_behavior))) return -EPERM; switch (behavior) { case MADV_REMOVE: return madvise_remove(madv_behavior); case MADV_WILLNEED: return madvise_willneed(madv_behavior); case MADV_COLD: return madvise_cold(madv_behavior); case MADV_PAGEOUT: return madvise_pageout(madv_behavior); case MADV_FREE: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: return madvise_dontneed_free(madv_behavior); case MADV_COLLAPSE: return madvise_collapse(vma, range->start, range->end, &madv_behavior->lock_dropped); case MADV_GUARD_INSTALL: return madvise_guard_install(madv_behavior); case MADV_GUARD_REMOVE: return madvise_guard_remove(madv_behavior); /* The below behaviours update VMAs via madvise_update_vma(). */ case MADV_NORMAL: new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ; break; case MADV_SEQUENTIAL: new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ; break; case MADV_RANDOM: new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ; break; case MADV_DONTFORK: new_flags |= VM_DONTCOPY; break; case MADV_DOFORK: if (new_flags & VM_SPECIAL) return -EINVAL; new_flags &= ~VM_DONTCOPY; break; case MADV_WIPEONFORK: /* MADV_WIPEONFORK is only supported on anonymous memory. */ if (vma->vm_file || new_flags & VM_SHARED) return -EINVAL; new_flags |= VM_WIPEONFORK; break; case MADV_KEEPONFORK: if (new_flags & VM_DROPPABLE) return -EINVAL; new_flags &= ~VM_WIPEONFORK; break; case MADV_DONTDUMP: new_flags |= VM_DONTDUMP; break; case MADV_DODUMP: if ((!is_vm_hugetlb_page(vma) && (new_flags & VM_SPECIAL)) || (new_flags & VM_DROPPABLE)) return -EINVAL; new_flags &= ~VM_DONTDUMP; break; case MADV_MERGEABLE: case MADV_UNMERGEABLE: error = ksm_madvise(vma, range->start, range->end, behavior, &new_flags); if (error) goto out; break; case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: error = hugepage_madvise(vma, &new_flags, behavior); if (error) goto out; break; case __MADV_SET_ANON_VMA_NAME: /* Only anonymous mappings can be named */ if (vma->vm_file && !vma_is_anon_shmem(vma)) return -EBADF; break; } /* This is a write operation.*/ VM_WARN_ON_ONCE(madv_behavior->lock_mode != MADVISE_MMAP_WRITE_LOCK); error = madvise_update_vma(new_flags, madv_behavior); out: /* * madvise() returns EAGAIN if kernel resources, such as * slab, are temporarily unavailable. */ if (error == -ENOMEM) error = -EAGAIN; return error; } #ifdef CONFIG_MEMORY_FAILURE /* * Error injection support for memory error handling. */ static int madvise_inject_error(struct madvise_behavior *madv_behavior) { unsigned long size; unsigned long start = madv_behavior->range.start; unsigned long end = madv_behavior->range.end; if (!capable(CAP_SYS_ADMIN)) return -EPERM; for (; start < end; start += size) { unsigned long pfn; struct page *page; int ret; ret = get_user_pages_fast(start, 1, 0, &page); if (ret != 1) return ret; pfn = page_to_pfn(page); /* * When soft offlining hugepages, after migrating the page * we dissolve it, therefore in the second loop "page" will * no longer be a compound page. */ size = page_size(compound_head(page)); if (madv_behavior->behavior == MADV_SOFT_OFFLINE) { pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n", pfn, start); ret = soft_offline_page(pfn, MF_COUNT_INCREASED); } else { pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n", pfn, start); ret = memory_failure(pfn, MF_ACTION_REQUIRED | MF_COUNT_INCREASED | MF_SW_SIMULATED); if (ret == -EOPNOTSUPP) ret = 0; } if (ret) return ret; } return 0; } static bool is_memory_failure(struct madvise_behavior *madv_behavior) { switch (madv_behavior->behavior) { case MADV_HWPOISON: case MADV_SOFT_OFFLINE: return true; default: return false; } } #else static int madvise_inject_error(struct madvise_behavior *madv_behavior) { return 0; } static bool is_memory_failure(struct madvise_behavior *madv_behavior) { return false; } #endif /* CONFIG_MEMORY_FAILURE */ static bool madvise_behavior_valid(int behavior) { switch (behavior) { case MADV_DOFORK: case MADV_DONTFORK: case MADV_NORMAL: case MADV_SEQUENTIAL: case MADV_RANDOM: case MADV_REMOVE: case MADV_WILLNEED: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_FREE: case MADV_COLD: case MADV_PAGEOUT: case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: #ifdef CONFIG_KSM case MADV_MERGEABLE: case MADV_UNMERGEABLE: #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: case MADV_COLLAPSE: #endif case MADV_DONTDUMP: case MADV_DODUMP: case MADV_WIPEONFORK: case MADV_KEEPONFORK: case MADV_GUARD_INSTALL: case MADV_GUARD_REMOVE: #ifdef CONFIG_MEMORY_FAILURE case MADV_SOFT_OFFLINE: case MADV_HWPOISON: #endif return true; default: return false; } } /* Can we invoke process_madvise() on a remote mm for the specified behavior? */ static bool process_madvise_remote_valid(int behavior) { switch (behavior) { case MADV_COLD: case MADV_PAGEOUT: case MADV_WILLNEED: case MADV_COLLAPSE: return true; default: return false; } } /* Does this operation invoke anon_vma_prepare()? */ static bool prepares_anon_vma(int behavior) { switch (behavior) { case MADV_GUARD_INSTALL: return true; default: return false; } } /* * We have acquired a VMA read lock, is the VMA valid to be madvise'd under VMA * read lock only now we have a VMA to examine? */ static bool is_vma_lock_sufficient(struct vm_area_struct *vma, struct madvise_behavior *madv_behavior) { /* Must span only a single VMA.*/ if (madv_behavior->range.end > vma->vm_end) return false; /* Remote processes unsupported. */ if (current->mm != vma->vm_mm) return false; /* Userfaultfd unsupported. */ if (userfaultfd_armed(vma)) return false; /* * anon_vma_prepare() explicitly requires an mmap lock for * serialisation, so we cannot use a VMA lock in this case. * * Note we might race with anon_vma being set, however this makes this * check overly paranoid which is safe. */ if (vma_is_anonymous(vma) && prepares_anon_vma(madv_behavior->behavior) && !vma->anon_vma) return false; return true; } /* * Try to acquire a VMA read lock if possible. * * We only support this lock over a single VMA, which the input range must * span either partially or fully. * * This function always returns with an appropriate lock held. If a VMA read * lock could be acquired, we return true and set madv_behavior state * accordingly. * * If a VMA read lock could not be acquired, we return false and expect caller to * fallback to mmap lock behaviour. */ static bool try_vma_read_lock(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; struct vm_area_struct *vma; vma = lock_vma_under_rcu(mm, madv_behavior->range.start); if (!vma) goto take_mmap_read_lock; if (!is_vma_lock_sufficient(vma, madv_behavior)) { vma_end_read(vma); goto take_mmap_read_lock; } madv_behavior->vma = vma; return true; take_mmap_read_lock: mmap_read_lock(mm); madv_behavior->lock_mode = MADVISE_MMAP_READ_LOCK; return false; } /* * Walk the vmas in range [start,end), and call the madvise_vma_behavior * function on each one. The function will get start and end parameters that * cover the overlap between the current vma and the original range. Any * unmapped regions in the original range will result in this function returning * -ENOMEM while still calling the madvise_vma_behavior function on all of the * existing vmas in the range. Must be called with the mmap_lock held for * reading or writing. */ static int madvise_walk_vmas(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; struct madvise_behavior_range *range = &madv_behavior->range; /* range is updated to span each VMA, so store end of entire range. */ unsigned long last_end = range->end; int unmapped_error = 0; int error; struct vm_area_struct *prev, *vma; /* * If VMA read lock is supported, apply madvise to a single VMA * tentatively, avoiding walking VMAs. */ if (madv_behavior->lock_mode == MADVISE_VMA_READ_LOCK && try_vma_read_lock(madv_behavior)) { error = madvise_vma_behavior(madv_behavior); vma_end_read(madv_behavior->vma); return error; } vma = find_vma_prev(mm, range->start, &prev); if (vma && range->start > vma->vm_start) prev = vma; for (;;) { /* Still start < end. */ if (!vma) return -ENOMEM; /* Here start < (last_end|vma->vm_end). */ if (range->start < vma->vm_start) { /* * This indicates a gap between VMAs in the input * range. This does not cause the operation to abort, * rather we simply return -ENOMEM to indicate that this * has happened, but carry on. */ unmapped_error = -ENOMEM; range->start = vma->vm_start; if (range->start >= last_end) break; } /* Here vma->vm_start <= range->start < (last_end|vma->vm_end) */ range->end = min(vma->vm_end, last_end); /* Here vma->vm_start <= range->start < range->end <= (last_end|vma->vm_end). */ madv_behavior->prev = prev; madv_behavior->vma = vma; error = madvise_vma_behavior(madv_behavior); if (error) return error; if (madv_behavior->lock_dropped) { /* We dropped the mmap lock, we can't ref the VMA. */ prev = NULL; vma = NULL; madv_behavior->lock_dropped = false; } else { vma = madv_behavior->vma; prev = vma; } if (vma && range->end < vma->vm_end) range->end = vma->vm_end; if (range->end >= last_end) break; vma = find_vma(mm, vma ? vma->vm_end : range->end); range->start = range->end; } return unmapped_error; } /* * Any behaviour which results in changes to the vma->vm_flags needs to * take mmap_lock for writing. Others, which simply traverse vmas, need * to only take it for reading. */ static enum madvise_lock_mode get_lock_mode(struct madvise_behavior *madv_behavior) { if (is_memory_failure(madv_behavior)) return MADVISE_NO_LOCK; switch (madv_behavior->behavior) { case MADV_REMOVE: case MADV_WILLNEED: case MADV_COLD: case MADV_PAGEOUT: case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: case MADV_COLLAPSE: return MADVISE_MMAP_READ_LOCK; case MADV_GUARD_INSTALL: case MADV_GUARD_REMOVE: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_FREE: return MADVISE_VMA_READ_LOCK; default: return MADVISE_MMAP_WRITE_LOCK; } } static int madvise_lock(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; enum madvise_lock_mode lock_mode = get_lock_mode(madv_behavior); switch (lock_mode) { case MADVISE_NO_LOCK: break; case MADVISE_MMAP_WRITE_LOCK: if (mmap_write_lock_killable(mm)) return -EINTR; break; case MADVISE_MMAP_READ_LOCK: mmap_read_lock(mm); break; case MADVISE_VMA_READ_LOCK: /* We will acquire the lock per-VMA in madvise_walk_vmas(). */ break; } madv_behavior->lock_mode = lock_mode; return 0; } static void madvise_unlock(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; switch (madv_behavior->lock_mode) { case MADVISE_NO_LOCK: return; case MADVISE_MMAP_WRITE_LOCK: mmap_write_unlock(mm); break; case MADVISE_MMAP_READ_LOCK: mmap_read_unlock(mm); break; case MADVISE_VMA_READ_LOCK: /* We will drop the lock per-VMA in madvise_walk_vmas(). */ break; } madv_behavior->lock_mode = MADVISE_NO_LOCK; } static bool madvise_batch_tlb_flush(int behavior) { switch (behavior) { case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_FREE: return true; default: return false; } } static void madvise_init_tlb(struct madvise_behavior *madv_behavior) { if (madvise_batch_tlb_flush(madv_behavior->behavior)) tlb_gather_mmu(madv_behavior->tlb, madv_behavior->mm); } static void madvise_finish_tlb(struct madvise_behavior *madv_behavior) { if (madvise_batch_tlb_flush(madv_behavior->behavior)) tlb_finish_mmu(madv_behavior->tlb); } /** * check_input_range() - Check if the requested range is valid. * @start: Start address of madvise-requested address range. * @len_in: Length of madvise-requested address range. * * Returns: 0 if the input range is valid, otherwise an error code. */ static int check_input_range(unsigned long start, size_t len_in) { size_t len; if (!PAGE_ALIGNED(start)) return -EINVAL; len = PAGE_ALIGN(len_in); /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) return -EINVAL; if (start + len < start) return -EINVAL; return 0; } static bool is_madvise_populate(struct madvise_behavior *madv_behavior) { switch (madv_behavior->behavior) { case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: return true; default: return false; } } /* * untagged_addr_remote() assumes mmap_lock is already held. On * architectures like x86 and RISC-V, tagging is tricky because each * mm may have a different tagging mask. However, we might only hold * the per-VMA lock (currently only local processes are supported), * so untagged_addr is used to avoid the mmap_lock assertion for * local processes. */ static inline unsigned long get_untagged_addr(struct mm_struct *mm, unsigned long start) { return current->mm == mm ? untagged_addr(start) : untagged_addr_remote(mm, start); } static int madvise_do_behavior(unsigned long start, size_t len_in, struct madvise_behavior *madv_behavior) { struct blk_plug plug; int error; struct madvise_behavior_range *range = &madv_behavior->range; if (is_memory_failure(madv_behavior)) { range->start = start; range->end = start + len_in; return madvise_inject_error(madv_behavior); } range->start = get_untagged_addr(madv_behavior->mm, start); range->end = range->start + PAGE_ALIGN(len_in); blk_start_plug(&plug); if (is_madvise_populate(madv_behavior)) error = madvise_populate(madv_behavior); else error = madvise_walk_vmas(madv_behavior); blk_finish_plug(&plug); return error; } /* * The madvise(2) system call. * * Applications can use madvise() to advise the kernel how it should * handle paging I/O in this VM area. The idea is to help the kernel * use appropriate read-ahead and caching techniques. The information * provided is advisory only, and can be safely disregarded by the * kernel without affecting the correct operation of the application. * * behavior values: * MADV_NORMAL - the default behavior is to read clusters. This * results in some read-ahead and read-behind. * MADV_RANDOM - the system should read the minimum amount of data * on any access, since it is unlikely that the appli- * cation will need more than what it asks for. * MADV_SEQUENTIAL - pages in the given range will probably be accessed * once, so they can be aggressively read ahead, and * can be freed soon after they are accessed. * MADV_WILLNEED - the application is notifying the system to read * some pages ahead. * MADV_DONTNEED - the application is finished with the given range, * so the kernel can free resources associated with it. * MADV_FREE - the application marks pages in the given range as lazy free, * where actual purges are postponed until memory pressure happens. * MADV_REMOVE - the application wants to free up the given range of * pages and associated backing store. * MADV_DONTFORK - omit this area from child's address space when forking: * typically, to avoid COWing pages pinned by get_user_pages(). * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking. * MADV_WIPEONFORK - present the child process with zero-filled memory in this * range after a fork. * MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK * MADV_HWPOISON - trigger memory error handler as if the given memory range * were corrupted by unrecoverable hardware memory failure. * MADV_SOFT_OFFLINE - try to soft-offline the given range of memory. * MADV_MERGEABLE - the application recommends that KSM try to merge pages in * this area with pages of identical content from other such areas. * MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others. * MADV_HUGEPAGE - the application wants to back the given range by transparent * huge pages in the future. Existing pages might be coalesced and * new pages might be allocated as THP. * MADV_NOHUGEPAGE - mark the given range as not worth being backed by * transparent huge pages so the existing pages will not be * coalesced into THP and new pages will not be allocated as THP. * MADV_COLLAPSE - synchronously coalesce pages into new THP. * MADV_DONTDUMP - the application wants to prevent pages in the given range * from being included in its core dump. * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. * MADV_COLD - the application is not expected to use this memory soon, * deactivate pages in this range so that they can be reclaimed * easily if memory pressure happens. * MADV_PAGEOUT - the application is not expected to use this memory soon, * page out the pages in this range immediately. * MADV_POPULATE_READ - populate (prefault) page tables readable by * triggering read faults if required * MADV_POPULATE_WRITE - populate (prefault) page tables writable by * triggering write faults if required * * return values: * zero - success * -EINVAL - start + len < 0, start is not page-aligned, * "behavior" is not a valid value, or application * is attempting to release locked or shared pages, * or the specified address range includes file, Huge TLB, * MAP_SHARED or VMPFNMAP range. * -ENOMEM - addresses in the specified range are not currently * mapped, or are outside the AS of the process. * -EIO - an I/O error occurred while paging in data. * -EBADF - map exists, but area maps something that isn't a file. * -EAGAIN - a kernel resource was temporarily unavailable. * -EPERM - memory is sealed. */ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior) { int error; struct mmu_gather tlb; struct madvise_behavior madv_behavior = { .mm = mm, .behavior = behavior, .tlb = &tlb, }; if (!madvise_behavior_valid(behavior)) return -EINVAL; error = check_input_range(start, len_in); if (error || !len_in) return error; error = madvise_lock(&madv_behavior); if (error) return error; madvise_init_tlb(&madv_behavior); error = madvise_do_behavior(start, len_in, &madv_behavior); madvise_finish_tlb(&madv_behavior); madvise_unlock(&madv_behavior); return error; } SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) { return do_madvise(current->mm, start, len_in, behavior); } /* Perform an madvise operation over a vector of addresses and lengths. */ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter, int behavior) { ssize_t ret = 0; size_t total_len; struct mmu_gather tlb; struct madvise_behavior madv_behavior = { .mm = mm, .behavior = behavior, .tlb = &tlb, }; total_len = iov_iter_count(iter); ret = madvise_lock(&madv_behavior); if (ret) return ret; madvise_init_tlb(&madv_behavior); while (iov_iter_count(iter)) { unsigned long start = (unsigned long)iter_iov_addr(iter); size_t len_in = iter_iov_len(iter); int error; error = check_input_range(start, len_in); if (error || !len_in) ret = error; else ret = madvise_do_behavior(start, len_in, &madv_behavior); /* * An madvise operation is attempting to restart the syscall, * but we cannot proceed as it would not be correct to repeat * the operation in aggregate, and would be surprising to the * user. * * We drop and reacquire locks so it is safe to just loop and * try again. We check for fatal signals in case we need exit * early anyway. */ if (ret == -ERESTARTNOINTR) { if (fatal_signal_pending(current)) { ret = -EINTR; break; } /* Drop and reacquire lock to unwind race. */ madvise_finish_tlb(&madv_behavior); madvise_unlock(&madv_behavior); ret = madvise_lock(&madv_behavior); if (ret) goto out; madvise_init_tlb(&madv_behavior); continue; } if (ret < 0) break; iov_iter_advance(iter, iter_iov_len(iter)); } madvise_finish_tlb(&madv_behavior); madvise_unlock(&madv_behavior); out: ret = (total_len - iov_iter_count(iter)) ? : ret; return ret; } SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, size_t, vlen, int, behavior, unsigned int, flags) { ssize_t ret; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; struct task_struct *task; struct mm_struct *mm; unsigned int f_flags; if (flags != 0) { ret = -EINVAL; goto out; } ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) goto out; task = pidfd_get_task(pidfd, &f_flags); if (IS_ERR(task)) { ret = PTR_ERR(task); goto free_iov; } /* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR(mm)) { ret = PTR_ERR(mm); goto release_task; } if (!madvise_behavior_valid(behavior)) { ret = -EINVAL; goto release_mm; } /* * We need only perform this check if we are attempting to manipulate a * remote process's address space. */ if (mm != current->mm && !process_madvise_remote_valid(behavior)) { ret = -EINVAL; goto release_mm; } /* * Require CAP_SYS_NICE for influencing process performance. Note that * only non-destructive hints are currently supported for remote * processes. */ if (mm != current->mm && !capable(CAP_SYS_NICE)) { ret = -EPERM; goto release_mm; } ret = vector_madvise(mm, &iter, behavior); release_mm: mmput(mm); release_task: put_task_struct(task); free_iov: kfree(iov); out: return ret; } #ifdef CONFIG_ANON_VMA_NAME #define ANON_VMA_NAME_MAX_LEN 80 #define ANON_VMA_NAME_INVALID_CHARS "\\`$[]" static inline bool is_valid_name_char(char ch) { /* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */ return ch > 0x1f && ch < 0x7f && !strchr(ANON_VMA_NAME_INVALID_CHARS, ch); } static int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, struct anon_vma_name *anon_name) { unsigned long end; unsigned long len; int error; struct madvise_behavior madv_behavior = { .mm = mm, .behavior = __MADV_SET_ANON_VMA_NAME, .anon_name = anon_name, }; if (start & ~PAGE_MASK) return -EINVAL; len = (len_in + ~PAGE_MASK) & PAGE_MASK; /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) return -EINVAL; end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; madv_behavior.range.start = start; madv_behavior.range.end = end; error = madvise_lock(&madv_behavior); if (error) return error; error = madvise_walk_vmas(&madv_behavior); madvise_unlock(&madv_behavior); return error; } int set_anon_vma_name(unsigned long addr, unsigned long size, const char __user *uname) { struct anon_vma_name *anon_name = NULL; struct mm_struct *mm = current->mm; int error; if (uname) { char *name, *pch; name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); if (IS_ERR(name)) return PTR_ERR(name); for (pch = name; *pch != '\0'; pch++) { if (!is_valid_name_char(*pch)) { kfree(name); return -EINVAL; } } /* anon_vma has its own copy */ anon_name = anon_vma_name_alloc(name); kfree(name); if (!anon_name) return -ENOMEM; } error = madvise_set_anon_name(mm, addr, size, anon_name); anon_vma_name_put(anon_name); return error; } #endif |
| 573 429 573 170 103 444 17 224 801 | 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 | /* SPDX-License-Identifier: GPL-2.0 * * Network memory * * Author: Mina Almasry <almasrymina@google.com> */ #ifndef _NET_NETMEM_H #define _NET_NETMEM_H #include <linux/dma-mapping.h> #include <linux/mm.h> #include <net/net_debug.h> /* These fields in struct page are used by the page_pool and net stack: * * struct { * unsigned long pp_magic; * struct page_pool *pp; * unsigned long _pp_mapping_pad; * unsigned long dma_addr; * atomic_long_t pp_ref_count; * }; * * We mirror the page_pool fields here so the page_pool can access these * fields without worrying whether the underlying fields belong to a * page or netmem_desc. * * CAUTION: Do not update the fields in netmem_desc without also * updating the anonymous aliasing union in struct net_iov. */ struct netmem_desc { unsigned long _flags; unsigned long pp_magic; struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; atomic_long_t pp_ref_count; }; #define NETMEM_DESC_ASSERT_OFFSET(pg, desc) \ static_assert(offsetof(struct page, pg) == \ offsetof(struct netmem_desc, desc)) NETMEM_DESC_ASSERT_OFFSET(flags, _flags); NETMEM_DESC_ASSERT_OFFSET(pp_magic, pp_magic); NETMEM_DESC_ASSERT_OFFSET(pp, pp); NETMEM_DESC_ASSERT_OFFSET(_pp_mapping_pad, _pp_mapping_pad); NETMEM_DESC_ASSERT_OFFSET(dma_addr, dma_addr); NETMEM_DESC_ASSERT_OFFSET(pp_ref_count, pp_ref_count); #undef NETMEM_DESC_ASSERT_OFFSET /* * Since struct netmem_desc uses the space in struct page, the size * should be checked, until struct netmem_desc has its own instance from * slab, to avoid conflicting with other members within struct page. */ static_assert(sizeof(struct netmem_desc) <= offsetof(struct page, _refcount)); /* net_iov */ DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers); /* We overload the LSB of the struct page pointer to indicate whether it's * a page or net_iov. */ #define NET_IOV 0x01UL enum net_iov_type { NET_IOV_DMABUF, NET_IOV_IOURING, }; /* A memory descriptor representing abstract networking I/O vectors, * generally for non-pages memory that doesn't have its corresponding * struct page and needs to be explicitly allocated through slab. * * net_iovs are allocated and used by networking code, and the size of * the chunk is PAGE_SIZE. * * This memory can be any form of non-struct paged memory. Examples * include imported dmabuf memory and imported io_uring memory. See * net_iov_type for all the supported types. * * @pp_magic: pp field, similar to the one in struct page/struct * netmem_desc. * @pp: the pp this net_iov belongs to, if any. * @dma_addr: the dma addrs of the net_iov. Needed for the network * card to send/receive this net_iov. * @pp_ref_count: the pp ref count of this net_iov, exactly the same * usage as struct page/struct netmem_desc. * @owner: the net_iov_area this net_iov belongs to, if any. * @type: the type of the memory. Different types of net_iovs are * supported. */ struct net_iov { struct netmem_desc desc; enum net_iov_type type; struct net_iov_area *owner; }; struct net_iov_area { /* Array of net_iovs for this area. */ struct net_iov *niovs; size_t num_niovs; /* Offset into the dma-buf where this chunk starts. */ unsigned long base_virtual; }; static inline struct net_iov_area *net_iov_owner(const struct net_iov *niov) { return niov->owner; } static inline unsigned int net_iov_idx(const struct net_iov *niov) { return niov - net_iov_owner(niov)->niovs; } /* Initialize a niov: stamp the owning area, the memory provider type. */ static inline void net_iov_init(struct net_iov *niov, struct net_iov_area *owner, enum net_iov_type type) { niov->owner = owner; niov->type = type; } /* netmem */ /** * typedef netmem_ref - a nonexistent type marking a reference to generic * network memory. * * A netmem_ref can be a struct page* or a struct net_iov* underneath. * * Use the supplied helpers to obtain the underlying memory pointer and fields. */ typedef unsigned long __bitwise netmem_ref; static inline bool netmem_is_net_iov(const netmem_ref netmem) { return (__force unsigned long)netmem & NET_IOV; } /** * __netmem_to_page - unsafely get pointer to the &page backing @netmem * @netmem: netmem reference to convert * * Unsafe version of netmem_to_page(). When @netmem is always page-backed, * e.g. when it's a header buffer, performs faster and generates smaller * object code (no check for the LSB, no WARN). When @netmem points to IOV, * provokes undefined behaviour. * * Return: pointer to the &page (garbage if @netmem is not page-backed). */ static inline struct page *__netmem_to_page(netmem_ref netmem) { return (__force struct page *)netmem; } static inline struct page *netmem_to_page(netmem_ref netmem) { if (WARN_ON_ONCE(netmem_is_net_iov(netmem))) return NULL; return __netmem_to_page(netmem); } static inline struct net_iov *netmem_to_net_iov(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV); DEBUG_NET_WARN_ON_ONCE(true); return NULL; } static inline netmem_ref net_iov_to_netmem(struct net_iov *niov) { return (__force netmem_ref)((unsigned long)niov | NET_IOV); } #define page_to_netmem(p) (_Generic((p), \ const struct page * : (__force const netmem_ref)(p), \ struct page * : (__force netmem_ref)(p))) /** * virt_to_netmem - convert virtual memory pointer to a netmem reference * @data: host memory pointer to convert * * Return: netmem reference to the &page backing this virtual address. */ static inline netmem_ref virt_to_netmem(const void *data) { return page_to_netmem(virt_to_page(data)); } static inline int netmem_ref_count(netmem_ref netmem) { /* The non-pp refcount of net_iov is always 1. On net_iov, we only * support pp refcounting which uses the pp_ref_count field. */ if (netmem_is_net_iov(netmem)) return 1; return page_ref_count(netmem_to_page(netmem)); } static inline unsigned long netmem_pfn_trace(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) return 0; return page_to_pfn(netmem_to_page(netmem)); } /* XXX: How to extract netmem_desc from page must be changed, once * netmem_desc no longer overlays on page and will be allocated through * slab. */ #define __pp_page_to_nmdesc(p) (_Generic((p), \ const struct page * : (const struct netmem_desc *)(p), \ struct page * : (struct netmem_desc *)(p))) /* CAUTION: Check if the page is a pp page before calling this helper or * know it's a pp page. */ #define pp_page_to_nmdesc(p) \ ({ \ DEBUG_NET_WARN_ON_ONCE(!page_pool_page_is_pp(p)); \ __pp_page_to_nmdesc(p); \ }) /** * __netmem_to_nmdesc - unsafely get pointer to the &netmem_desc backing * @netmem * @netmem: netmem reference to convert * * Unsafe version that can be used only when @netmem is always backed by * system memory, performs faster and generates smaller object code (no * check for the LSB, no WARN). When @netmem points to IOV, provokes * undefined behaviour. * * Return: pointer to the &netmem_desc (garbage if @netmem is not backed * by system memory). */ static inline struct netmem_desc *__netmem_to_nmdesc(netmem_ref netmem) { return (__force struct netmem_desc *)netmem; } /* netmem_to_nmdesc - convert netmem_ref to struct netmem_desc * for * access to common fields. * @netmem: netmem reference to get netmem_desc. * * All the sub types of netmem_ref (netmem_desc, net_iov) have the same * pp, pp_magic, dma_addr, and pp_ref_count fields via netmem_desc. * * Return: the pointer to struct netmem_desc * regardless of its * underlying type. */ static inline struct netmem_desc *netmem_to_nmdesc(netmem_ref netmem) { void *p = (void *)((__force unsigned long)netmem & ~NET_IOV); if (netmem_is_net_iov(netmem)) return &((struct net_iov *)p)->desc; return __pp_page_to_nmdesc((struct page *)p); } /** * __netmem_get_pp - unsafely get pointer to the &page_pool backing @netmem * @netmem: netmem reference to get the pointer from * * Unsafe version of netmem_get_pp(). When @netmem is always page-backed, * e.g. when it's a header buffer, performs faster and generates smaller * object code (avoids clearing the LSB). When @netmem points to IOV, * provokes invalid memory access. * * Return: pointer to the &page_pool (garbage if @netmem is not page-backed). */ static inline struct page_pool *__netmem_get_pp(netmem_ref netmem) { return __netmem_to_nmdesc(netmem)->pp; } static inline struct page_pool *netmem_get_pp(netmem_ref netmem) { return netmem_to_nmdesc(netmem)->pp; } static inline atomic_long_t *netmem_get_pp_ref_count_ref(netmem_ref netmem) { return &netmem_to_nmdesc(netmem)->pp_ref_count; } static inline bool netmem_is_pref_nid(netmem_ref netmem, int pref_nid) { /* NUMA node preference only makes sense if we're allocating * system memory. Memory providers (which give us net_iovs) * choose for us. */ if (netmem_is_net_iov(netmem)) return true; return page_to_nid(netmem_to_page(netmem)) == pref_nid; } static inline netmem_ref netmem_compound_head(netmem_ref netmem) { /* niov are never compounded */ if (netmem_is_net_iov(netmem)) return netmem; return page_to_netmem(compound_head(netmem_to_page(netmem))); } /** * __netmem_address - unsafely get pointer to the memory backing @netmem * @netmem: netmem reference to get the pointer for * * Unsafe version of netmem_address(). When @netmem is always page-backed, * e.g. when it's a header buffer, performs faster and generates smaller * object code (no check for the LSB). When @netmem points to IOV, provokes * undefined behaviour. * * Return: pointer to the memory (garbage if @netmem is not page-backed). */ static inline void *__netmem_address(netmem_ref netmem) { return page_address(__netmem_to_page(netmem)); } static inline void *netmem_address(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) return NULL; return __netmem_address(netmem); } /** * netmem_is_pfmemalloc - check if @netmem was allocated under memory pressure * @netmem: netmem reference to check * * Return: true if @netmem is page-backed and the page was allocated under * memory pressure, false otherwise. */ static inline bool netmem_is_pfmemalloc(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) return false; return page_is_pfmemalloc(netmem_to_page(netmem)); } static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) { return netmem_to_nmdesc(netmem)->dma_addr; } #if defined(CONFIG_NET_DEVMEM) static inline bool net_is_devmem_iov(const struct net_iov *niov) { return niov->type == NET_IOV_DMABUF; } #else static inline bool net_is_devmem_iov(const struct net_iov *niov) { return false; } #endif void __get_netmem(netmem_ref netmem); void __put_netmem(netmem_ref netmem); static __always_inline void get_netmem(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) __get_netmem(netmem); else get_page(netmem_to_page(netmem)); } static __always_inline void put_netmem(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) __put_netmem(netmem); else put_page(netmem_to_page(netmem)); } #define netmem_dma_unmap_addr_set(NETMEM, PTR, ADDR_NAME, VAL) \ do { \ if (!netmem_is_net_iov(NETMEM)) \ dma_unmap_addr_set(PTR, ADDR_NAME, VAL); \ else \ dma_unmap_addr_set(PTR, ADDR_NAME, 0); \ } while (0) static inline void netmem_dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { if (!addr) return; dma_unmap_page_attrs(dev, addr, size, dir, attrs); } #endif /* _NET_NETMEM_H */ |
| 48 48 48 29 19 19 95 66 29 28 1 29 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 | // SPDX-License-Identifier: GPL-2.0-or-later /* Instantiate a public key crypto key from an X.509 Certificate * * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) "X.509: "fmt #include <crypto/hash.h> #include <keys/asymmetric-parser.h> #include <keys/asymmetric-subtype.h> #include <keys/system_keyring.h> #include <linux/hex.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/string.h> #include "asymmetric_keys.h" #include "x509_parser.h" /* * Set up the signature parameters in an X.509 certificate. This involves * digesting the signed data and extracting the signature. */ int x509_get_sig_params(struct x509_certificate *cert) { struct public_key_signature *sig = cert->sig; struct crypto_shash *tfm; struct shash_desc *desc; size_t desc_size; int ret; pr_devel("==>%s()\n", __func__); /* Calculate a SHA256 hash of the TBS and check it against the * blacklist. */ sha256(cert->tbs, cert->tbs_size, cert->sha256); ret = is_hash_blacklisted(cert->sha256, sizeof(cert->sha256), BLACKLIST_HASH_X509_TBS); if (ret == -EKEYREJECTED) { pr_err("Cert %*phN is blacklisted\n", (int)sizeof(cert->sha256), cert->sha256); cert->blacklisted = true; ret = 0; } sig->s = kmemdup(cert->raw_sig, cert->raw_sig_size, GFP_KERNEL); if (!sig->s) return -ENOMEM; sig->s_size = cert->raw_sig_size; if (sig->algo_takes_data) { /* The signature algorithm does whatever passes for hashing. */ sig->m = (u8 *)cert->tbs; sig->m_size = cert->tbs_size; sig->m_free = false; goto out; } /* Allocate the hashing algorithm we're going to need and find out how * big the hash operational data will be. */ tfm = crypto_alloc_shash(sig->hash_algo, 0, 0); if (IS_ERR(tfm)) { if (PTR_ERR(tfm) == -ENOENT) { cert->unsupported_sig = true; return 0; } return PTR_ERR(tfm); } desc_size = crypto_shash_descsize(tfm) + sizeof(*desc); sig->m_size = crypto_shash_digestsize(tfm); ret = -ENOMEM; sig->m = kmalloc(sig->m_size, GFP_KERNEL); if (!sig->m) goto error; sig->m_free = true; desc = kzalloc(desc_size, GFP_KERNEL); if (!desc) goto error; desc->tfm = tfm; ret = crypto_shash_digest(desc, cert->tbs, cert->tbs_size, sig->m); if (ret < 0) goto error_2; error_2: kfree(desc); error: crypto_free_shash(tfm); out: pr_devel("<==%s() = %d\n", __func__, ret); return ret; } /* * Check for self-signedness in an X.509 cert and if found, check the signature * immediately if we can. */ int x509_check_for_self_signed(struct x509_certificate *cert) { int ret = 0; pr_devel("==>%s()\n", __func__); if (cert->raw_subject_size != cert->raw_issuer_size || memcmp(cert->raw_subject, cert->raw_issuer, cert->raw_issuer_size) != 0) goto not_self_signed; if (cert->sig->auth_ids[0] || cert->sig->auth_ids[1]) { /* If the AKID is present it may have one or two parts. If * both are supplied, both must match. */ bool a = asymmetric_key_id_same(cert->skid, cert->sig->auth_ids[1]); bool b = asymmetric_key_id_same(cert->id, cert->sig->auth_ids[0]); if (!a && !b) goto not_self_signed; ret = -EKEYREJECTED; if (((a && !b) || (b && !a)) && cert->sig->auth_ids[0] && cert->sig->auth_ids[1]) goto out; } if (cert->unsupported_sig) { ret = 0; goto out; } ret = public_key_verify_signature(cert->pub, cert->sig); if (ret < 0) { if (ret == -ENOPKG) { cert->unsupported_sig = true; ret = 0; } goto out; } pr_devel("Cert Self-signature verified"); cert->self_signed = true; out: pr_devel("<==%s() = %d\n", __func__, ret); return ret; not_self_signed: pr_devel("<==%s() = 0 [not]\n", __func__); return 0; } /* * Attempt to parse a data blob for a key as an X509 certificate. */ static int x509_key_preparse(struct key_preparsed_payload *prep) { struct x509_certificate *cert __free(x509_free_certificate) = NULL; struct asymmetric_key_ids *kids __free(kfree) = NULL; char *p, *desc __free(kfree) = NULL; const char *q; size_t srlen, sulen; cert = x509_cert_parse(prep->data, prep->datalen); if (IS_ERR(cert)) return PTR_ERR(cert); pr_devel("Cert Issuer: %s\n", cert->issuer); pr_devel("Cert Subject: %s\n", cert->subject); pr_devel("Cert Key Algo: %s\n", cert->pub->pkey_algo); pr_devel("Cert Valid period: %lld-%lld\n", cert->valid_from, cert->valid_to); cert->pub->id_type = "X509"; if (cert->unsupported_sig) { public_key_signature_free(cert->sig); cert->sig = NULL; } else { pr_devel("Cert Signature: %s + %s\n", cert->sig->pkey_algo, cert->sig->hash_algo); } /* Don't permit addition of blacklisted keys */ if (cert->blacklisted) return -EKEYREJECTED; /* Propose a description */ sulen = strlen(cert->subject); if (cert->raw_skid) { srlen = cert->raw_skid_size; q = cert->raw_skid; } else { srlen = cert->raw_serial_size; q = cert->raw_serial; } desc = kmalloc(sulen + 2 + srlen * 2 + 1, GFP_KERNEL); if (!desc) return -ENOMEM; p = memcpy(desc, cert->subject, sulen); p += sulen; *p++ = ':'; *p++ = ' '; p = bin2hex(p, q, srlen); *p = 0; kids = kmalloc_obj(struct asymmetric_key_ids); if (!kids) return -ENOMEM; kids->id[0] = cert->id; kids->id[1] = cert->skid; kids->id[2] = asymmetric_key_generate_id(cert->raw_subject, cert->raw_subject_size, "", 0); if (IS_ERR(kids->id[2])) return PTR_ERR(kids->id[2]); /* We're pinning the module by being linked against it */ __module_get(public_key_subtype.owner); prep->payload.data[asym_subtype] = &public_key_subtype; prep->payload.data[asym_key_ids] = kids; prep->payload.data[asym_crypto] = cert->pub; prep->payload.data[asym_auth] = cert->sig; prep->description = desc; prep->quotalen = 100; /* We've finished with the certificate */ cert->pub = NULL; cert->id = NULL; cert->skid = NULL; cert->sig = NULL; desc = NULL; kids = NULL; return 0; } static struct asymmetric_key_parser x509_key_parser = { .owner = THIS_MODULE, .name = "x509", .parse = x509_key_preparse, }; /* * Module stuff */ static int __init x509_key_init(void) { return register_asymmetric_key_parser(&x509_key_parser); } static void __exit x509_key_exit(void) { unregister_asymmetric_key_parser(&x509_key_parser); } module_init(x509_key_init); module_exit(x509_key_exit); MODULE_DESCRIPTION("X.509 certificate parser"); MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); |
| 2517 1747 9 1812 77 120 7 1603 10 20 3539 5075 1 187 8613 1944 143 3586 8 6 6357 788 905 787 13 3 17 131 71 245 139 571 1 3160 24 7 578 538 7417 3 3162 7715 7493 7511 23 211 | 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 | // SPDX-License-Identifier: GPL-2.0 // Generated by scripts/atomic/gen-atomic-instrumented.sh // DO NOT MODIFY THIS FILE DIRECTLY /* * This file provoides atomic operations with explicit instrumentation (e.g. * KASAN, KCSAN), which should be used unless it is necessary to avoid * instrumentation. Where it is necessary to aovid instrumenation, the * raw_atomic*() operations should be used. */ #ifndef _LINUX_ATOMIC_INSTRUMENTED_H #define _LINUX_ATOMIC_INSTRUMENTED_H #include <linux/build_bug.h> #include <linux/compiler.h> #include <linux/instrumented.h> /** * atomic_read() - atomic load with relaxed ordering * @v: pointer to atomic_t * * Atomically loads the value of @v with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_read() there. * * Return: The value loaded from @v. */ static __always_inline int atomic_read(const atomic_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic_read(v); } /** * atomic_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic_t * * Atomically loads the value of @v with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_read_acquire() there. * * Return: The value loaded from @v. */ static __always_inline int atomic_read_acquire(const atomic_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic_read_acquire(v); } /** * atomic_set() - atomic set with relaxed ordering * @v: pointer to atomic_t * @i: int value to assign * * Atomically sets @v to @i with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_set() there. * * Return: Nothing. */ static __always_inline void atomic_set(atomic_t *v, int i) { instrument_atomic_write(v, sizeof(*v)); raw_atomic_set(v, i); } /** * atomic_set_release() - atomic set with release ordering * @v: pointer to atomic_t * @i: int value to assign * * Atomically sets @v to @i with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_set_release() there. * * Return: Nothing. */ static __always_inline void atomic_set_release(atomic_t *v, int i) { kcsan_release(); instrument_atomic_write(v, sizeof(*v)); raw_atomic_set_release(v, i); } /** * atomic_add() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_add() there. * * Return: Nothing. */ static __always_inline void atomic_add(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_add(i, v); } /** * atomic_add_return() - atomic add with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_return() there. * * Return: The updated value of @v. */ static __always_inline int atomic_add_return(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_return(i, v); } /** * atomic_add_return_acquire() - atomic add with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline int atomic_add_return_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_return_acquire(i, v); } /** * atomic_add_return_release() - atomic add with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_return_release() there. * * Return: The updated value of @v. */ static __always_inline int atomic_add_return_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_return_release(i, v); } /** * atomic_add_return_relaxed() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline int atomic_add_return_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_return_relaxed(i, v); } /** * atomic_fetch_add() - atomic add with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add(i, v); } /** * atomic_fetch_add_acquire() - atomic add with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add_acquire(i, v); } /** * atomic_fetch_add_release() - atomic add with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add_release(i, v); } /** * atomic_fetch_add_relaxed() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add_relaxed(i, v); } /** * atomic_sub() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub() there. * * Return: Nothing. */ static __always_inline void atomic_sub(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_sub(i, v); } /** * atomic_sub_return() - atomic subtract with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_return() there. * * Return: The updated value of @v. */ static __always_inline int atomic_sub_return(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_return(i, v); } /** * atomic_sub_return_acquire() - atomic subtract with acquire ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline int atomic_sub_return_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_return_acquire(i, v); } /** * atomic_sub_return_release() - atomic subtract with release ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_return_release() there. * * Return: The updated value of @v. */ static __always_inline int atomic_sub_return_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_return_release(i, v); } /** * atomic_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline int atomic_sub_return_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_return_relaxed(i, v); } /** * atomic_fetch_sub() - atomic subtract with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_sub() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_sub(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_sub(i, v); } /** * atomic_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_sub_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_sub_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_sub_acquire(i, v); } /** * atomic_fetch_sub_release() - atomic subtract with release ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_sub_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_sub_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_sub_release(i, v); } /** * atomic_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_sub_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_sub_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_sub_relaxed(i, v); } /** * atomic_inc() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc() there. * * Return: Nothing. */ static __always_inline void atomic_inc(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_inc(v); } /** * atomic_inc_return() - atomic increment with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_return() there. * * Return: The updated value of @v. */ static __always_inline int atomic_inc_return(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_return(v); } /** * atomic_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline int atomic_inc_return_acquire(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_return_acquire(v); } /** * atomic_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_return_release() there. * * Return: The updated value of @v. */ static __always_inline int atomic_inc_return_release(atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_return_release(v); } /** * atomic_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline int atomic_inc_return_relaxed(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_return_relaxed(v); } /** * atomic_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_inc() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_inc(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_inc(v); } /** * atomic_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_inc_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_inc_acquire(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_inc_acquire(v); } /** * atomic_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_inc_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_inc_release(atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_inc_release(v); } /** * atomic_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_inc_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_inc_relaxed(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_inc_relaxed(v); } /** * atomic_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec() there. * * Return: Nothing. */ static __always_inline void atomic_dec(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_dec(v); } /** * atomic_dec_return() - atomic decrement with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_return() there. * * Return: The updated value of @v. */ static __always_inline int atomic_dec_return(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_return(v); } /** * atomic_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline int atomic_dec_return_acquire(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_return_acquire(v); } /** * atomic_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_return_release() there. * * Return: The updated value of @v. */ static __always_inline int atomic_dec_return_release(atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_return_release(v); } /** * atomic_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline int atomic_dec_return_relaxed(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_return_relaxed(v); } /** * atomic_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_dec() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_dec(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_dec(v); } /** * atomic_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_dec_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_dec_acquire(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_dec_acquire(v); } /** * atomic_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_dec_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_dec_release(atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_dec_release(v); } /** * atomic_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_dec_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_dec_relaxed(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_dec_relaxed(v); } /** * atomic_and() - atomic bitwise AND with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_and() there. * * Return: Nothing. */ static __always_inline void atomic_and(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_and(i, v); } /** * atomic_fetch_and() - atomic bitwise AND with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_and() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_and(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_and(i, v); } /** * atomic_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_and_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_and_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_and_acquire(i, v); } /** * atomic_fetch_and_release() - atomic bitwise AND with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_and_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_and_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_and_release(i, v); } /** * atomic_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_and_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_and_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_and_relaxed(i, v); } /** * atomic_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_andnot() there. * * Return: Nothing. */ static __always_inline void atomic_andnot(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_andnot(i, v); } /** * atomic_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_andnot(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_andnot(i, v); } /** * atomic_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_andnot_acquire(i, v); } /** * atomic_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_andnot_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_andnot_release(i, v); } /** * atomic_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_andnot_relaxed(i, v); } /** * atomic_or() - atomic bitwise OR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_or() there. * * Return: Nothing. */ static __always_inline void atomic_or(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_or(i, v); } /** * atomic_fetch_or() - atomic bitwise OR with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_or() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_or(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_or(i, v); } /** * atomic_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_or_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_or_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_or_acquire(i, v); } /** * atomic_fetch_or_release() - atomic bitwise OR with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_or_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_or_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_or_release(i, v); } /** * atomic_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_or_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_or_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_or_relaxed(i, v); } /** * atomic_xor() - atomic bitwise XOR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_xor() there. * * Return: Nothing. */ static __always_inline void atomic_xor(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_xor(i, v); } /** * atomic_fetch_xor() - atomic bitwise XOR with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_xor() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_xor(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_xor(i, v); } /** * atomic_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_xor_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_xor_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_xor_acquire(i, v); } /** * atomic_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_xor_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_xor_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_xor_release(i, v); } /** * atomic_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_xor_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_xor_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_xor_relaxed(i, v); } /** * atomic_xchg() - atomic exchange with full ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_xchg() there. * * Return: The original value of @v. */ static __always_inline int atomic_xchg(atomic_t *v, int new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_xchg(v, new); } /** * atomic_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_xchg_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_xchg_acquire(atomic_t *v, int new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_xchg_acquire(v, new); } /** * atomic_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_xchg_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_xchg_release(atomic_t *v, int new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_xchg_release(v, new); } /** * atomic_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_xchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_xchg_relaxed(atomic_t *v, int new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_xchg_relaxed(v, new); } /** * atomic_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg() there. * * Return: The original value of @v. */ static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_cmpxchg(v, old, new); } /** * atomic_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_cmpxchg_acquire(v, old, new); } /** * atomic_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_cmpxchg_release(atomic_t *v, int old, int new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_cmpxchg_release(v, old, new); } /** * atomic_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_cmpxchg_relaxed(v, old, new); } /** * atomic_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg(v, old, new); } /** * atomic_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_acquire() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_acquire(v, old, new); } /** * atomic_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_release() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_release(v, old, new); } /** * atomic_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_relaxed() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_relaxed(v, old, new); } /** * atomic_sub_and_test() - atomic subtract and test if zero with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_and_test(i, v); } /** * atomic_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_dec_and_test(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_and_test(v); } /** * atomic_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_inc_and_test(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_and_test(v); } /** * atomic_add_negative() - atomic add and test if negative with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_negative() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_add_negative(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_negative(i, v); } /** * atomic_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_negative_acquire() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_add_negative_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_negative_acquire(i, v); } /** * atomic_add_negative_release() - atomic add and test if negative with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_negative_release() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_add_negative_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_negative_release(i, v); } /** * atomic_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_negative_relaxed() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_add_negative_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_negative_relaxed(i, v); } /** * atomic_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_t * @a: int value to add * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_unless() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add_unless(v, a, u); } /** * atomic_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_t * @a: int value to add * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_add_unless() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_add_unless(atomic_t *v, int a, int u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_unless(v, a, u); } /** * atomic_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_inc_not_zero() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_inc_not_zero(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_not_zero(v); } /** * atomic_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_inc_unless_negative() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_inc_unless_negative(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_unless_negative(v); } /** * atomic_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_dec_unless_positive() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_dec_unless_positive(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_unless_positive(v); } /** * atomic_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_dec_if_positive() there. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline int atomic_dec_if_positive(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_if_positive(v); } /** * atomic64_read() - atomic load with relaxed ordering * @v: pointer to atomic64_t * * Atomically loads the value of @v with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_read() there. * * Return: The value loaded from @v. */ static __always_inline s64 atomic64_read(const atomic64_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic64_read(v); } /** * atomic64_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic64_t * * Atomically loads the value of @v with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_read_acquire() there. * * Return: The value loaded from @v. */ static __always_inline s64 atomic64_read_acquire(const atomic64_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic64_read_acquire(v); } /** * atomic64_set() - atomic set with relaxed ordering * @v: pointer to atomic64_t * @i: s64 value to assign * * Atomically sets @v to @i with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_set() there. * * Return: Nothing. */ static __always_inline void atomic64_set(atomic64_t *v, s64 i) { instrument_atomic_write(v, sizeof(*v)); raw_atomic64_set(v, i); } /** * atomic64_set_release() - atomic set with release ordering * @v: pointer to atomic64_t * @i: s64 value to assign * * Atomically sets @v to @i with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_set_release() there. * * Return: Nothing. */ static __always_inline void atomic64_set_release(atomic64_t *v, s64 i) { kcsan_release(); instrument_atomic_write(v, sizeof(*v)); raw_atomic64_set_release(v, i); } /** * atomic64_add() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add() there. * * Return: Nothing. */ static __always_inline void atomic64_add(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_add(i, v); } /** * atomic64_add_return() - atomic add with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_return() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_return(i, v); } /** * atomic64_add_return_acquire() - atomic add with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_add_return_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_return_acquire(i, v); } /** * atomic64_add_return_release() - atomic add with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_return_release() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_add_return_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_return_release(i, v); } /** * atomic64_add_return_relaxed() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_add_return_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_return_relaxed(i, v); } /** * atomic64_fetch_add() - atomic add with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add(i, v); } /** * atomic64_fetch_add_acquire() - atomic add with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add_acquire(i, v); } /** * atomic64_fetch_add_release() - atomic add with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add_release(i, v); } /** * atomic64_fetch_add_relaxed() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add_relaxed(i, v); } /** * atomic64_sub() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub() there. * * Return: Nothing. */ static __always_inline void atomic64_sub(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_sub(i, v); } /** * atomic64_sub_return() - atomic subtract with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_return() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_return(i, v); } /** * atomic64_sub_return_acquire() - atomic subtract with acquire ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_sub_return_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_return_acquire(i, v); } /** * atomic64_sub_return_release() - atomic subtract with release ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_return_release() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_sub_return_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_return_release(i, v); } /** * atomic64_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_sub_return_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_return_relaxed(i, v); } /** * atomic64_fetch_sub() - atomic subtract with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_sub(i, v); } /** * atomic64_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_sub_acquire(i, v); } /** * atomic64_fetch_sub_release() - atomic subtract with release ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_sub_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_sub_release(i, v); } /** * atomic64_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_sub_relaxed(i, v); } /** * atomic64_inc() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc() there. * * Return: Nothing. */ static __always_inline void atomic64_inc(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_inc(v); } /** * atomic64_inc_return() - atomic increment with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_return() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_inc_return(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_return(v); } /** * atomic64_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_inc_return_acquire(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_return_acquire(v); } /** * atomic64_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_return_release() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_inc_return_release(atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_return_release(v); } /** * atomic64_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_inc_return_relaxed(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_return_relaxed(v); } /** * atomic64_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_inc(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_inc(v); } /** * atomic64_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_inc_acquire(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_inc_acquire(v); } /** * atomic64_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_inc_release(atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_inc_release(v); } /** * atomic64_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_inc_relaxed(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_inc_relaxed(v); } /** * atomic64_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec() there. * * Return: Nothing. */ static __always_inline void atomic64_dec(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_dec(v); } /** * atomic64_dec_return() - atomic decrement with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_return() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_dec_return(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_return(v); } /** * atomic64_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_dec_return_acquire(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_return_acquire(v); } /** * atomic64_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_return_release() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_dec_return_release(atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_return_release(v); } /** * atomic64_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_dec_return_relaxed(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_return_relaxed(v); } /** * atomic64_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_dec(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_dec(v); } /** * atomic64_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_dec_acquire(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_dec_acquire(v); } /** * atomic64_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_dec_release(atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_dec_release(v); } /** * atomic64_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_dec_relaxed(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_dec_relaxed(v); } /** * atomic64_and() - atomic bitwise AND with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_and() there. * * Return: Nothing. */ static __always_inline void atomic64_and(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_and(i, v); } /** * atomic64_fetch_and() - atomic bitwise AND with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_and() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_and(i, v); } /** * atomic64_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_and_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_and_acquire(i, v); } /** * atomic64_fetch_and_release() - atomic bitwise AND with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_and_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_and_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_and_release(i, v); } /** * atomic64_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_and_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_and_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_and_relaxed(i, v); } /** * atomic64_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_andnot() there. * * Return: Nothing. */ static __always_inline void atomic64_andnot(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_andnot(i, v); } /** * atomic64_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_andnot(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_andnot(i, v); } /** * atomic64_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_andnot_acquire(i, v); } /** * atomic64_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_andnot_release(i, v); } /** * atomic64_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_andnot_relaxed(i, v); } /** * atomic64_or() - atomic bitwise OR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_or() there. * * Return: Nothing. */ static __always_inline void atomic64_or(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_or(i, v); } /** * atomic64_fetch_or() - atomic bitwise OR with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_or() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_or(i, v); } /** * atomic64_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_or_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_or_acquire(i, v); } /** * atomic64_fetch_or_release() - atomic bitwise OR with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_or_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_or_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_or_release(i, v); } /** * atomic64_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_or_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_or_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_or_relaxed(i, v); } /** * atomic64_xor() - atomic bitwise XOR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xor() there. * * Return: Nothing. */ static __always_inline void atomic64_xor(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_xor(i, v); } /** * atomic64_fetch_xor() - atomic bitwise XOR with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_xor(i, v); } /** * atomic64_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_xor_acquire(i, v); } /** * atomic64_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_xor_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_xor_release(i, v); } /** * atomic64_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_xor_relaxed(i, v); } /** * atomic64_xchg() - atomic exchange with full ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xchg() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_xchg(v, new); } /** * atomic64_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xchg_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_xchg_acquire(atomic64_t *v, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_xchg_acquire(v, new); } /** * atomic64_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xchg_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_xchg_release(atomic64_t *v, s64 new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_xchg_release(v, new); } /** * atomic64_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_xchg_relaxed(atomic64_t *v, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_xchg_relaxed(v, new); } /** * atomic64_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_cmpxchg(v, old, new); } /** * atomic64_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_cmpxchg_acquire(v, old, new); } /** * atomic64_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_cmpxchg_release(v, old, new); } /** * atomic64_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_cmpxchg_relaxed(v, old, new); } /** * atomic64_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg(v, old, new); } /** * atomic64_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_acquire() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_acquire(v, old, new); } /** * atomic64_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_release() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_release(v, old, new); } /** * atomic64_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_relaxed() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_relaxed(v, old, new); } /** * atomic64_sub_and_test() - atomic subtract and test if zero with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_and_test(i, v); } /** * atomic64_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic64_dec_and_test(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_and_test(v); } /** * atomic64_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic64_inc_and_test(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_and_test(v); } /** * atomic64_add_negative() - atomic add and test if negative with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_negative() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_negative(i, v); } /** * atomic64_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_negative_acquire() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic64_add_negative_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_negative_acquire(i, v); } /** * atomic64_add_negative_release() - atomic add and test if negative with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_negative_release() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic64_add_negative_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_negative_release(i, v); } /** * atomic64_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_negative_relaxed() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic64_add_negative_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_negative_relaxed(i, v); } /** * atomic64_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic64_t * @a: s64 value to add * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_unless() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add_unless(v, a, u); } /** * atomic64_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic64_t * @a: s64 value to add * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_add_unless() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_unless(v, a, u); } /** * atomic64_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic64_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_inc_not_zero() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_not_zero(v); } /** * atomic64_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic64_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_inc_unless_negative() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic64_inc_unless_negative(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_unless_negative(v); } /** * atomic64_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic64_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_dec_unless_positive() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic64_dec_unless_positive(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_unless_positive(v); } /** * atomic64_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic64_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_dec_if_positive() there. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_if_positive(v); } /** * atomic_long_read() - atomic load with relaxed ordering * @v: pointer to atomic_long_t * * Atomically loads the value of @v with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_read() there. * * Return: The value loaded from @v. */ static __always_inline long atomic_long_read(const atomic_long_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic_long_read(v); } /** * atomic_long_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic_long_t * * Atomically loads the value of @v with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_read_acquire() there. * * Return: The value loaded from @v. */ static __always_inline long atomic_long_read_acquire(const atomic_long_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic_long_read_acquire(v); } /** * atomic_long_set() - atomic set with relaxed ordering * @v: pointer to atomic_long_t * @i: long value to assign * * Atomically sets @v to @i with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_set() there. * * Return: Nothing. */ static __always_inline void atomic_long_set(atomic_long_t *v, long i) { instrument_atomic_write(v, sizeof(*v)); raw_atomic_long_set(v, i); } /** * atomic_long_set_release() - atomic set with release ordering * @v: pointer to atomic_long_t * @i: long value to assign * * Atomically sets @v to @i with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_set_release() there. * * Return: Nothing. */ static __always_inline void atomic_long_set_release(atomic_long_t *v, long i) { kcsan_release(); instrument_atomic_write(v, sizeof(*v)); raw_atomic_long_set_release(v, i); } /** * atomic_long_add() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add() there. * * Return: Nothing. */ static __always_inline void atomic_long_add(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_add(i, v); } /** * atomic_long_add_return() - atomic add with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_return() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_add_return(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_return(i, v); } /** * atomic_long_add_return_acquire() - atomic add with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_add_return_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_return_acquire(i, v); } /** * atomic_long_add_return_release() - atomic add with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_return_release() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_add_return_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_return_release(i, v); } /** * atomic_long_add_return_relaxed() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_add_return_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_return_relaxed(i, v); } /** * atomic_long_fetch_add() - atomic add with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add(i, v); } /** * atomic_long_fetch_add_acquire() - atomic add with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add_acquire(i, v); } /** * atomic_long_fetch_add_release() - atomic add with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add_release(i, v); } /** * atomic_long_fetch_add_relaxed() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add_relaxed(i, v); } /** * atomic_long_sub() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub() there. * * Return: Nothing. */ static __always_inline void atomic_long_sub(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_sub(i, v); } /** * atomic_long_sub_return() - atomic subtract with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_return() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_sub_return(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_return(i, v); } /** * atomic_long_sub_return_acquire() - atomic subtract with acquire ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_sub_return_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_return_acquire(i, v); } /** * atomic_long_sub_return_release() - atomic subtract with release ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_return_release() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_sub_return_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_return_release(i, v); } /** * atomic_long_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_sub_return_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_return_relaxed(i, v); } /** * atomic_long_fetch_sub() - atomic subtract with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_sub(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_sub(i, v); } /** * atomic_long_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_sub_acquire(i, v); } /** * atomic_long_fetch_sub_release() - atomic subtract with release ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_sub_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_sub_release(i, v); } /** * atomic_long_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_sub_relaxed(i, v); } /** * atomic_long_inc() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc() there. * * Return: Nothing. */ static __always_inline void atomic_long_inc(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_inc(v); } /** * atomic_long_inc_return() - atomic increment with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_return() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_inc_return(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_return(v); } /** * atomic_long_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_inc_return_acquire(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_return_acquire(v); } /** * atomic_long_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_return_release() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_inc_return_release(atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_return_release(v); } /** * atomic_long_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_inc_return_relaxed(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_return_relaxed(v); } /** * atomic_long_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_inc(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_inc(v); } /** * atomic_long_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_inc_acquire(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_inc_acquire(v); } /** * atomic_long_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_inc_release(atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_inc_release(v); } /** * atomic_long_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_inc_relaxed(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_inc_relaxed(v); } /** * atomic_long_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec() there. * * Return: Nothing. */ static __always_inline void atomic_long_dec(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_dec(v); } /** * atomic_long_dec_return() - atomic decrement with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_return() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_dec_return(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_return(v); } /** * atomic_long_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_dec_return_acquire(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_return_acquire(v); } /** * atomic_long_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_return_release() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_dec_return_release(atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_return_release(v); } /** * atomic_long_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_dec_return_relaxed(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_return_relaxed(v); } /** * atomic_long_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_dec(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_dec(v); } /** * atomic_long_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_dec_acquire(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_dec_acquire(v); } /** * atomic_long_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_dec_release(atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_dec_release(v); } /** * atomic_long_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_dec_relaxed(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_dec_relaxed(v); } /** * atomic_long_and() - atomic bitwise AND with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_and() there. * * Return: Nothing. */ static __always_inline void atomic_long_and(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_and(i, v); } /** * atomic_long_fetch_and() - atomic bitwise AND with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_and(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_and(i, v); } /** * atomic_long_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_and_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_and_acquire(i, v); } /** * atomic_long_fetch_and_release() - atomic bitwise AND with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_and_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_and_release(i, v); } /** * atomic_long_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_and_relaxed(i, v); } /** * atomic_long_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_andnot() there. * * Return: Nothing. */ static __always_inline void atomic_long_andnot(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_andnot(i, v); } /** * atomic_long_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_andnot(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_andnot(i, v); } /** * atomic_long_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_andnot_acquire(i, v); } /** * atomic_long_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_andnot_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_andnot_release(i, v); } /** * atomic_long_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_andnot_relaxed(i, v); } /** * atomic_long_or() - atomic bitwise OR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_or() there. * * Return: Nothing. */ static __always_inline void atomic_long_or(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_or(i, v); } /** * atomic_long_fetch_or() - atomic bitwise OR with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_or(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_or(i, v); } /** * atomic_long_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_or_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_or_acquire(i, v); } /** * atomic_long_fetch_or_release() - atomic bitwise OR with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_or_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_or_release(i, v); } /** * atomic_long_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_or_relaxed(i, v); } /** * atomic_long_xor() - atomic bitwise XOR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xor() there. * * Return: Nothing. */ static __always_inline void atomic_long_xor(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_xor(i, v); } /** * atomic_long_fetch_xor() - atomic bitwise XOR with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_xor(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_xor(i, v); } /** * atomic_long_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_xor_acquire(i, v); } /** * atomic_long_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_xor_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_xor_release(i, v); } /** * atomic_long_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_xor_relaxed(i, v); } /** * atomic_long_xchg() - atomic exchange with full ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xchg() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_xchg(atomic_long_t *v, long new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_xchg(v, new); } /** * atomic_long_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xchg_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_xchg_acquire(atomic_long_t *v, long new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_xchg_acquire(v, new); } /** * atomic_long_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xchg_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_xchg_release(atomic_long_t *v, long new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_xchg_release(v, new); } /** * atomic_long_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_xchg_relaxed(atomic_long_t *v, long new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_xchg_relaxed(v, new); } /** * atomic_long_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_cmpxchg(atomic_long_t *v, long old, long new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_cmpxchg(v, old, new); } /** * atomic_long_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_cmpxchg_acquire(v, old, new); } /** * atomic_long_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_cmpxchg_release(v, old, new); } /** * atomic_long_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_cmpxchg_relaxed(v, old, new); } /** * atomic_long_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg(v, old, new); } /** * atomic_long_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_acquire() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_acquire(v, old, new); } /** * atomic_long_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_release() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_release(v, old, new); } /** * atomic_long_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_relaxed() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_relaxed(v, old, new); } /** * atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_long_sub_and_test(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_and_test(i, v); } /** * atomic_long_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_long_dec_and_test(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_and_test(v); } /** * atomic_long_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_long_inc_and_test(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_and_test(v); } /** * atomic_long_add_negative() - atomic add and test if negative with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_negative() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_long_add_negative(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_negative(i, v); } /** * atomic_long_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_negative_acquire() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_long_add_negative_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_negative_acquire(i, v); } /** * atomic_long_add_negative_release() - atomic add and test if negative with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_negative_release() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_long_add_negative_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_negative_release(i, v); } /** * atomic_long_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_negative_relaxed() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_long_add_negative_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_negative_relaxed(i, v); } /** * atomic_long_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_long_t * @a: long value to add * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_unless() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add_unless(v, a, u); } /** * atomic_long_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_long_t * @a: long value to add * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_add_unless() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_long_add_unless(atomic_long_t *v, long a, long u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_unless(v, a, u); } /** * atomic_long_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic_long_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_not_zero() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_long_inc_not_zero(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_not_zero(v); } /** * atomic_long_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic_long_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_unless_negative() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_long_inc_unless_negative(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_unless_negative(v); } /** * atomic_long_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic_long_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_unless_positive() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_long_dec_unless_positive(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_unless_positive(v); } /** * atomic_long_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic_long_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_if_positive() there. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline long atomic_long_dec_if_positive(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_if_positive(v); } #define xchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_xchg(__ai_ptr, __VA_ARGS__); \ }) #define xchg_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_xchg_acquire(__ai_ptr, __VA_ARGS__); \ }) #define xchg_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_xchg_release(__ai_ptr, __VA_ARGS__); \ }) #define xchg_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_xchg_relaxed(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128_acquire(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128_relaxed(__ai_ptr, __VA_ARGS__); \ }) #define try_cmpxchg(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg_acquire(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg_release(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg_relaxed(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64_acquire(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64_release(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64_relaxed(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128_acquire(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128_release(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128_relaxed(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define cmpxchg_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg_local(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128_local(__ai_ptr, __VA_ARGS__); \ }) #define sync_cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) #define try_cmpxchg_local(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64_local(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128_local(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define sync_try_cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_sync_try_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ // 9dd948d3012b22c4e75933a5172983f912e46439 |
| 6 136 22 159 1 22 138 149 19 132 160 1 158 158 20 21 2 19 16 21 182 162 21 733 250 481 3 724 729 2 723 337 401 3 713 1 1 8 3 1 4 4 16 121 128 93 35 28 20 7 7 28 28 11 27 130 130 35 19 77 48 46 128 1 22 106 128 92 36 1 12 28 21 7 1399 1400 6 6 6 6 6 9 23 25 25 2 9 14 6 2 1 3 51 50 6 50 2941 137 2941 2938 1 2852 83 2941 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/file.c - kernfs file implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> */ #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> #include <linux/uio.h> #include "kernfs-internal.h" struct kernfs_open_node { struct rcu_head rcu_head; atomic_t event; wait_queue_head_t poll; struct list_head files; /* goes through kernfs_open_file.list */ unsigned int nr_mmapped; unsigned int nr_to_release; }; /* * kernfs_notify() may be called from any context and bounces notifications * through a work item. To minimize space overhead in kernfs_node, the * pending queue is implemented as a singly linked list of kernfs_nodes. * The list is terminated with the self pointer so that whether a * kernfs_node is on the list or not can be determined by testing the next * pointer for %NULL. */ #define KERNFS_NOTIFY_EOL ((void *)&kernfs_notify_list) static DEFINE_SPINLOCK(kernfs_notify_lock); static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL; /* Compatibility wrappers - use the common hashed node lock */ static inline struct mutex *kernfs_open_file_mutex_ptr(struct kernfs_node *kn) { return kernfs_node_lock_ptr(kn); } static inline struct mutex *kernfs_open_file_mutex_lock(struct kernfs_node *kn) { return kernfs_node_lock(kn); } /** * of_on - Get the kernfs_open_node of the specified kernfs_open_file * @of: target kernfs_open_file * * Return: the kernfs_open_node of the kernfs_open_file */ static struct kernfs_open_node *of_on(struct kernfs_open_file *of) { return rcu_dereference_protected(of->kn->attr.open, !list_empty(&of->list)); } /* Get active reference to kernfs node for an open file */ static struct kernfs_open_file *kernfs_get_active_of(struct kernfs_open_file *of) { /* Skip if file was already released */ if (unlikely(of->released)) return NULL; if (!kernfs_get_active(of->kn)) return NULL; return of; } static void kernfs_put_active_of(struct kernfs_open_file *of) { return kernfs_put_active(of->kn); } /** * kernfs_deref_open_node_locked - Get kernfs_open_node corresponding to @kn * * @kn: target kernfs_node. * * Fetch and return ->attr.open of @kn when caller holds the * kernfs_open_file_mutex_ptr(kn). * * Update of ->attr.open happens under kernfs_open_file_mutex_ptr(kn). So when * the caller guarantees that this mutex is being held, other updaters can't * change ->attr.open and this means that we can safely deref ->attr.open * outside RCU read-side critical section. * * The caller needs to make sure that kernfs_open_file_mutex is held. * * Return: @kn->attr.open when kernfs_open_file_mutex is held. */ static struct kernfs_open_node * kernfs_deref_open_node_locked(struct kernfs_node *kn) { return rcu_dereference_protected(kn->attr.open, lockdep_is_held(kernfs_open_file_mutex_ptr(kn))); } static struct kernfs_open_file *kernfs_of(struct file *file) { return ((struct seq_file *)file->private_data)->private; } /* * Determine the kernfs_ops for the given kernfs_node. This function must * be called while holding an active reference. */ static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn) { if (kn->flags & KERNFS_LOCKDEP) lockdep_assert_held(kn); return kn->attr.ops; } /* * As kernfs_seq_stop() is also called after kernfs_seq_start() or * kernfs_seq_next() failure, it needs to distinguish whether it's stopping * a seq_file iteration which is fully initialized with an active reference * or an aborted kernfs_seq_start() due to get_active failure. The * position pointer is the only context for each seq_file iteration and * thus the stop condition should be encoded in it. As the return value is * directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable * choice to indicate get_active failure. * * Unfortunately, this is complicated due to the optional custom seq_file * operations which may return ERR_PTR(-ENODEV) too. kernfs_seq_stop() * can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or * custom seq_file operations and thus can't decide whether put_active * should be performed or not only on ERR_PTR(-ENODEV). * * This is worked around by factoring out the custom seq_stop() and * put_active part into kernfs_seq_stop_active(), skipping it from * kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after * custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures * that kernfs_seq_stop_active() is skipped only after get_active failure. */ static void kernfs_seq_stop_active(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops = kernfs_ops(of->kn); if (ops->seq_stop) ops->seq_stop(sf, v); kernfs_put_active_of(of); } static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops; /* * @of->mutex nests outside active ref and is primarily to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active_of(of)) return ERR_PTR(-ENODEV); ops = kernfs_ops(of->kn); if (ops->seq_start) { void *next = ops->seq_start(sf, ppos); /* see the comment above kernfs_seq_stop_active() */ if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; } return single_start(sf, ppos); } static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops = kernfs_ops(of->kn); if (ops->seq_next) { void *next = ops->seq_next(sf, v, ppos); /* see the comment above kernfs_seq_stop_active() */ if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; } else { /* * The same behavior and code as single_open(), always * terminate after the initial read. */ ++*ppos; return NULL; } } static void kernfs_seq_stop(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; if (v != ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, v); mutex_unlock(&of->mutex); } static int kernfs_seq_show(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; of->event = atomic_read(&of_on(of)->event); return of->kn->attr.ops->seq_show(sf, v); } static const struct seq_operations kernfs_seq_ops = { .start = kernfs_seq_start, .next = kernfs_seq_next, .stop = kernfs_seq_stop, .show = kernfs_seq_show, }; /* * As reading a bin file can have side-effects, the exact offset and bytes * specified in read(2) call should be passed to the read callback making * it difficult to use seq_file. Implement simplistic custom buffering for * bin files. */ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); ssize_t len = min_t(size_t, iov_iter_count(iter), PAGE_SIZE); const struct kernfs_ops *ops; char *buf; buf = of->prealloc_buf; if (buf) mutex_lock(&of->prealloc_mutex); else buf = kmalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; /* * @of->mutex nests outside active ref and is used both to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active_of(of)) { len = -ENODEV; mutex_unlock(&of->mutex); goto out_free; } of->event = atomic_read(&of_on(of)->event); ops = kernfs_ops(of->kn); if (ops->read) len = ops->read(of, buf, len, iocb->ki_pos); else len = -EINVAL; kernfs_put_active_of(of); mutex_unlock(&of->mutex); if (len < 0) goto out_free; if (copy_to_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) mutex_unlock(&of->prealloc_mutex); else kfree(buf); return len; } static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter) { if (kernfs_of(iocb->ki_filp)->kn->flags & KERNFS_HAS_SEQ_SHOW) return seq_read_iter(iocb, iter); return kernfs_file_read_iter(iocb, iter); } /* * Copy data in from userland and pass it to the matching kernfs write * operation. * * There is no easy way for us to know if userspace is only doing a partial * write, so we don't support them. We expect the entire buffer to come on * the first write. Hint: if you're writing a value, first read the file, * modify only the value you're changing, then write entire buffer * back. */ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) { struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); ssize_t len = iov_iter_count(iter); const struct kernfs_ops *ops; char *buf; if (of->atomic_write_len) { if (len > of->atomic_write_len) return -E2BIG; } else { len = min_t(size_t, len, PAGE_SIZE); } buf = of->prealloc_buf; if (buf) mutex_lock(&of->prealloc_mutex); else buf = kmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } buf[len] = '\0'; /* guarantee string termination */ /* * @of->mutex nests outside active ref and is used both to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active_of(of)) { mutex_unlock(&of->mutex); len = -ENODEV; goto out_free; } ops = kernfs_ops(of->kn); if (ops->write) len = ops->write(of, buf, len, iocb->ki_pos); else len = -EINVAL; kernfs_put_active_of(of); mutex_unlock(&of->mutex); if (len > 0) iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) mutex_unlock(&of->prealloc_mutex); else kfree(buf); return len; } static void kernfs_vma_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); if (!of->vm_ops) return; if (!kernfs_get_active_of(of)) return; if (of->vm_ops->open) of->vm_ops->open(vma); kernfs_put_active_of(of); } static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); vm_fault_t ret; if (!of->vm_ops) return VM_FAULT_SIGBUS; if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS; ret = VM_FAULT_SIGBUS; if (of->vm_ops->fault) ret = of->vm_ops->fault(vmf); kernfs_put_active_of(of); return ret; } static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); vm_fault_t ret; if (!of->vm_ops) return VM_FAULT_SIGBUS; if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS; ret = 0; if (of->vm_ops->page_mkwrite) ret = of->vm_ops->page_mkwrite(vmf); else file_update_time(file); kernfs_put_active_of(of); return ret; } static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); int ret; if (!of->vm_ops) return -EINVAL; if (!kernfs_get_active_of(of)) return -EINVAL; ret = -EINVAL; if (of->vm_ops->access) ret = of->vm_ops->access(vma, addr, buf, len, write); kernfs_put_active_of(of); return ret; } static const struct vm_operations_struct kernfs_vm_ops = { .open = kernfs_vma_open, .fault = kernfs_vma_fault, .page_mkwrite = kernfs_vma_page_mkwrite, .access = kernfs_vma_access, }; static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) { struct kernfs_open_file *of = kernfs_of(file); const struct kernfs_ops *ops; int rc; /* * mmap path and of->mutex are prone to triggering spurious lockdep * warnings and we don't want to add spurious locking dependency * between the two. Check whether mmap is actually implemented * without grabbing @of->mutex by testing HAS_MMAP flag. See the * comment in kernfs_fop_open() for more details. */ if (!(of->kn->flags & KERNFS_HAS_MMAP)) return -ENODEV; mutex_lock(&of->mutex); rc = -ENODEV; if (!kernfs_get_active_of(of)) goto out_unlock; ops = kernfs_ops(of->kn); rc = ops->mmap(of, vma); if (rc) goto out_put; /* * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup() * to satisfy versions of X which crash if the mmap fails: that * substitutes a new vm_file, and we don't then want bin_vm_ops. */ if (vma->vm_file != file) goto out_put; rc = -EINVAL; if (of->mmapped && of->vm_ops != vma->vm_ops) goto out_put; /* * It is not possible to successfully wrap close. * So error if someone is trying to use close. */ if (vma->vm_ops && vma->vm_ops->close) goto out_put; rc = 0; if (!of->mmapped) { of->mmapped = true; of_on(of)->nr_mmapped++; of->vm_ops = vma->vm_ops; } vma->vm_ops = &kernfs_vm_ops; out_put: kernfs_put_active_of(of); out_unlock: mutex_unlock(&of->mutex); return rc; } /** * kernfs_get_open_node - get or create kernfs_open_node * @kn: target kernfs_node * @of: kernfs_open_file for this instance of open * * If @kn->attr.open exists, increment its reference count; otherwise, * create one. @of is chained to the files list. * * Locking: * Kernel thread context (may sleep). * * Return: * %0 on success, -errno on failure. */ static int kernfs_get_open_node(struct kernfs_node *kn, struct kernfs_open_file *of) { struct kernfs_open_node *on; struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); on = kernfs_deref_open_node_locked(kn); if (!on) { /* not there, initialize a new one */ on = kzalloc_obj(*on); if (!on) { mutex_unlock(mutex); return -ENOMEM; } atomic_set(&on->event, 1); init_waitqueue_head(&on->poll); INIT_LIST_HEAD(&on->files); rcu_assign_pointer(kn->attr.open, on); } list_add_tail(&of->list, &on->files); if (kn->flags & KERNFS_HAS_RELEASE) on->nr_to_release++; mutex_unlock(mutex); return 0; } /** * kernfs_unlink_open_file - Unlink @of from @kn. * * @kn: target kernfs_node * @of: associated kernfs_open_file * @open_failed: ->open() failed, cancel ->release() * * Unlink @of from list of @kn's associated open files. If list of * associated open files becomes empty, disassociate and free * kernfs_open_node. * * LOCKING: * None. */ static void kernfs_unlink_open_file(struct kernfs_node *kn, struct kernfs_open_file *of, bool open_failed) { struct kernfs_open_node *on; struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); on = kernfs_deref_open_node_locked(kn); if (!on) { mutex_unlock(mutex); return; } if (of) { if (kn->flags & KERNFS_HAS_RELEASE) { WARN_ON_ONCE(of->released == open_failed); if (open_failed) on->nr_to_release--; } if (of->mmapped) on->nr_mmapped--; list_del(&of->list); } if (list_empty(&on->files)) { rcu_assign_pointer(kn->attr.open, NULL); kfree_rcu(on, rcu_head); } mutex_unlock(mutex); } static int kernfs_fop_open(struct inode *inode, struct file *file) { struct kernfs_node *kn = inode->i_private; struct kernfs_root *root = kernfs_root(kn); const struct kernfs_ops *ops; struct kernfs_open_file *of; bool has_read, has_write, has_mmap; int error = -EACCES; if (!kernfs_get_active(kn)) return -ENODEV; ops = kernfs_ops(kn); has_read = ops->seq_show || ops->read || ops->mmap; has_write = ops->write || ops->mmap; has_mmap = ops->mmap; /* see the flag definition for details */ if (root->flags & KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK) { if ((file->f_mode & FMODE_WRITE) && (!(inode->i_mode & S_IWUGO) || !has_write)) goto err_out; if ((file->f_mode & FMODE_READ) && (!(inode->i_mode & S_IRUGO) || !has_read)) goto err_out; } /* allocate a kernfs_open_file for the file */ error = -ENOMEM; of = kzalloc_obj(struct kernfs_open_file); if (!of) goto err_out; /* * The following is done to give a different lockdep key to * @of->mutex for files which implement mmap. This is a rather * crude way to avoid false positive lockdep warning around * mm->mmap_lock - mmap nests @of->mutex under mm->mmap_lock and * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under * which mm->mmap_lock nests, while holding @of->mutex. As each * open file has a separate mutex, it's okay as long as those don't * happen on the same file. At this point, we can't easily give * each file a separate locking class. Let's differentiate on * whether the file has mmap or not for now. * * For similar reasons, writable and readonly files are given different * lockdep key, because the writable file /sys/power/resume may call vfs * lookup helpers for arbitrary paths and readonly files can be read by * overlayfs from vfs helpers when sysfs is a lower layer of overalyfs. * * All three cases look the same. They're supposed to * look that way and give @of->mutex different static lockdep keys. */ if (has_mmap) mutex_init(&of->mutex); else if (file->f_mode & FMODE_WRITE) mutex_init(&of->mutex); else mutex_init(&of->mutex); of->kn = kn; of->file = file; /* * Write path needs to atomic_write_len outside active reference. * Cache it in open_file. See kernfs_fop_write_iter() for details. */ of->atomic_write_len = ops->atomic_write_len; error = -EINVAL; /* * ->seq_show is incompatible with ->prealloc, * as seq_read does its own allocation. * ->read must be used instead. */ if (ops->prealloc && ops->seq_show) goto err_free; if (ops->prealloc) { int len = of->atomic_write_len ?: PAGE_SIZE; of->prealloc_buf = kmalloc(len + 1, GFP_KERNEL); error = -ENOMEM; if (!of->prealloc_buf) goto err_free; mutex_init(&of->prealloc_mutex); } /* * Always instantiate seq_file even if read access doesn't use * seq_file or is not requested. This unifies private data access * and readable regular files are the vast majority anyway. */ if (ops->seq_show) error = seq_open(file, &kernfs_seq_ops); else error = seq_open(file, NULL); if (error) goto err_free; of->seq_file = file->private_data; of->seq_file->private = of; /* seq_file clears PWRITE unconditionally, restore it if WRITE */ if (file->f_mode & FMODE_WRITE) file->f_mode |= FMODE_PWRITE; /* make sure we have open node struct */ error = kernfs_get_open_node(kn, of); if (error) goto err_seq_release; if (ops->open) { /* nobody has access to @of yet, skip @of->mutex */ error = ops->open(of); if (error) goto err_put_node; } /* open succeeded, put active references */ kernfs_put_active(kn); return 0; err_put_node: kernfs_unlink_open_file(kn, of, true); err_seq_release: seq_release(inode, file); err_free: kfree(of->prealloc_buf); kfree(of); err_out: kernfs_put_active(kn); return error; } /* used from release/drain to ensure that ->release() is called exactly once */ static void kernfs_release_file(struct kernfs_node *kn, struct kernfs_open_file *of) { /* * @of is guaranteed to have no other file operations in flight and * we just want to synchronize release and drain paths. * @kernfs_open_file_mutex_ptr(kn) is enough. @of->mutex can't be used * here because drain path may be called from places which can * cause circular dependency. */ lockdep_assert_held(kernfs_open_file_mutex_ptr(kn)); if (!of->released) { /* * A file is never detached without being released and we * need to be able to release files which are deactivated * and being drained. Don't use kernfs_ops(). */ kn->attr.ops->release(of); of->released = true; of_on(of)->nr_to_release--; } } static int kernfs_fop_release(struct inode *inode, struct file *filp) { struct kernfs_node *kn = inode->i_private; struct kernfs_open_file *of = kernfs_of(filp); if (kn->flags & KERNFS_HAS_RELEASE) { struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); kernfs_release_file(kn, of); mutex_unlock(mutex); } kernfs_unlink_open_file(kn, of, false); seq_release(inode, filp); kfree(of->prealloc_buf); kfree(of); return 0; } bool kernfs_should_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; bool ret; /* * @kn being deactivated guarantees that @kn->attr.open can't change * beneath us making the lockless test below safe. * Callers post kernfs_unbreak_active_protection may be counted in * kn->active by now, do not WARN_ON because of them. */ rcu_read_lock(); on = rcu_dereference(kn->attr.open); ret = on && (on->nr_mmapped || on->nr_to_release); rcu_read_unlock(); return ret; } void kernfs_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; struct kernfs_open_file *of; struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); on = kernfs_deref_open_node_locked(kn); if (!on) { mutex_unlock(mutex); return; } list_for_each_entry(of, &on->files, list) { struct inode *inode = file_inode(of->file); if (of->mmapped) { unmap_mapping_range(inode->i_mapping, 0, 0, 1); of->mmapped = false; on->nr_mmapped--; } if (kn->flags & KERNFS_HAS_RELEASE) kernfs_release_file(kn, of); } WARN_ON_ONCE(on->nr_mmapped || on->nr_to_release); mutex_unlock(mutex); } /* * Kernfs attribute files are pollable. The idea is that you read * the content and then you use 'poll' or 'select' to wait for * the content to change. When the content changes (assuming the * manager for the kobject supports notification), poll will * return EPOLLERR|EPOLLPRI, and select will return the fd whether * it is waiting for read, write, or exceptions. * Once poll/select indicates that the value has changed, you * need to close and re-open the file, or seek to 0 and read again. * Reminder: this only works for attributes which actively support * it, and it is not possible to test an attribute from userspace * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ __poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) { struct kernfs_open_node *on = of_on(of); poll_wait(of->file, &on->poll, wait); if (of->event != atomic_read(&on->event)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; return DEFAULT_POLLMASK; } static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); __poll_t ret; if (!kernfs_get_active_of(of)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; if (kn->attr.ops->poll) ret = kn->attr.ops->poll(of, wait); else ret = kernfs_generic_poll(of, wait); kernfs_put_active_of(of); return ret; } static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence) { struct kernfs_open_file *of = kernfs_of(file); const struct kernfs_ops *ops; loff_t ret; /* * @of->mutex nests outside active ref and is primarily to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active_of(of)) { mutex_unlock(&of->mutex); return -ENODEV; } ops = kernfs_ops(of->kn); if (ops->llseek) ret = ops->llseek(of, offset, whence); else ret = generic_file_llseek(file, offset, whence); kernfs_put_active_of(of); mutex_unlock(&of->mutex); return ret; } static void kernfs_notify_workfn(struct work_struct *work) { struct kernfs_node *kn; struct kernfs_super_info *info; struct kernfs_root *root; repeat: /* pop one off the notify_list */ spin_lock_irq(&kernfs_notify_lock); kn = kernfs_notify_list; if (kn == KERNFS_NOTIFY_EOL) { spin_unlock_irq(&kernfs_notify_lock); return; } kernfs_notify_list = kn->attr.notify_next; kn->attr.notify_next = NULL; spin_unlock_irq(&kernfs_notify_lock); root = kernfs_root(kn); /* kick fsnotify */ down_read(&root->kernfs_supers_rwsem); down_read(&root->kernfs_rwsem); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; struct inode *p_inode = NULL; const char *kn_name; struct inode *inode; struct qstr name; /* * We want fsnotify_modify() on @kn but as the * modifications aren't originating from userland don't * have the matching @file available. Look up the inodes * and generate the events manually. */ inode = ilookup(info->sb, kernfs_ino(kn)); if (!inode) continue; kn_name = kernfs_rcu_name(kn); name = QSTR(kn_name); parent = kernfs_get_parent(kn); if (parent) { p_inode = ilookup(info->sb, kernfs_ino(parent)); if (p_inode) { fsnotify(FS_MODIFY | FS_EVENT_ON_CHILD, inode, FSNOTIFY_EVENT_INODE, p_inode, &name, inode, 0); iput(p_inode); } kernfs_put(parent); } if (!p_inode) fsnotify_inode(inode, FS_MODIFY); iput(inode); } up_read(&root->kernfs_rwsem); up_read(&root->kernfs_supers_rwsem); kernfs_put(kn); goto repeat; } /** * kernfs_notify - notify a kernfs file * @kn: file to notify * * Notify @kn such that poll(2) on @kn wakes up. Maybe be called from any * context. */ void kernfs_notify(struct kernfs_node *kn) { static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn); unsigned long flags; struct kernfs_open_node *on; if (WARN_ON(kernfs_type(kn) != KERNFS_FILE)) return; /* kick poll immediately */ rcu_read_lock(); on = rcu_dereference(kn->attr.open); if (on) { atomic_inc(&on->event); wake_up_interruptible(&on->poll); } rcu_read_unlock(); /* schedule work to kick fsnotify */ spin_lock_irqsave(&kernfs_notify_lock, flags); if (!kn->attr.notify_next) { kernfs_get(kn); kn->attr.notify_next = kernfs_notify_list; kernfs_notify_list = kn; schedule_work(&kernfs_notify_work); } spin_unlock_irqrestore(&kernfs_notify_lock, flags); } EXPORT_SYMBOL_GPL(kernfs_notify); const struct file_operations kernfs_file_fops = { .read_iter = kernfs_fop_read_iter, .write_iter = kernfs_fop_write_iter, .llseek = kernfs_fop_llseek, .mmap = kernfs_fop_mmap, .open = kernfs_fop_open, .release = kernfs_fop_release, .poll = kernfs_fop_poll, .fsync = noop_fsync, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; /** * __kernfs_create_file - kernfs internal function to create a file * @parent: directory to create the file in * @name: name of the file * @mode: mode of the file * @uid: uid of the file * @gid: gid of the file * @size: size of the file * @ops: kernfs operations for the file * @priv: private data for the file * @ns: optional namespace tag of the file * @key: lockdep key for the file's active_ref, %NULL to disable lockdep * * Return: the created node on success, ERR_PTR() value on error. */ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const struct ns_common *ns, struct lock_class_key *key) { struct kernfs_node *kn; unsigned flags; int rc; flags = KERNFS_FILE; kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, uid, gid, flags); if (!kn) return ERR_PTR(-ENOMEM); kn->attr.ops = ops; kn->attr.size = size; kn->ns = ns; kn->priv = priv; #ifdef CONFIG_DEBUG_LOCK_ALLOC if (key) { lockdep_init_map(&kn->dep_map, "kn->active", key, 0); kn->flags |= KERNFS_LOCKDEP; } #endif /* * kn->attr.ops is accessible only while holding active ref. We * need to know whether some ops are implemented outside active * ref. Cache their existence in flags. */ if (ops->seq_show) kn->flags |= KERNFS_HAS_SEQ_SHOW; if (ops->mmap) kn->flags |= KERNFS_HAS_MMAP; if (ops->release) kn->flags |= KERNFS_HAS_RELEASE; rc = kernfs_add_one(kn); if (rc) { kernfs_put(kn); return ERR_PTR(rc); } return kn; } |
| 19 51 52 16 55 2 55 55 2 54 62 52 55 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/module.h> #include <linux/netfilter.h> #include <linux/rhashtable.h> #include <linux/netdevice.h> #include <net/flow_offload.h> #include <net/netfilter/nf_flow_table.h> struct flow_offload_xdp_ft { struct list_head head; struct nf_flowtable *ft; struct rcu_head rcuhead; }; struct flow_offload_xdp { struct hlist_node hnode; unsigned long net_device_addr; struct list_head head; }; #define NF_XDP_HT_BITS 4 static DEFINE_HASHTABLE(nf_xdp_hashtable, NF_XDP_HT_BITS); static DEFINE_MUTEX(nf_xdp_hashtable_lock); /* caller must hold rcu read lock */ struct nf_flowtable *nf_flowtable_by_dev(const struct net_device *dev) { unsigned long key = (unsigned long)dev; struct flow_offload_xdp *iter; hash_for_each_possible_rcu(nf_xdp_hashtable, iter, hnode, key) { if (key == iter->net_device_addr) { struct flow_offload_xdp_ft *ft_elem; /* The user is supposed to insert a given net_device * just into a single nf_flowtable so we always return * the first element here. */ ft_elem = list_first_or_null_rcu(&iter->head, struct flow_offload_xdp_ft, head); return ft_elem ? ft_elem->ft : NULL; } } return NULL; } static int nf_flowtable_by_dev_insert(struct nf_flowtable *ft, const struct net_device *dev) { struct flow_offload_xdp *iter, *elem = NULL; unsigned long key = (unsigned long)dev; struct flow_offload_xdp_ft *ft_elem; ft_elem = kzalloc_obj(*ft_elem, GFP_KERNEL_ACCOUNT); if (!ft_elem) return -ENOMEM; ft_elem->ft = ft; mutex_lock(&nf_xdp_hashtable_lock); hash_for_each_possible(nf_xdp_hashtable, iter, hnode, key) { if (key == iter->net_device_addr) { elem = iter; break; } } if (!elem) { elem = kzalloc_obj(*elem, GFP_KERNEL_ACCOUNT); if (!elem) goto err_unlock; elem->net_device_addr = key; INIT_LIST_HEAD(&elem->head); hash_add_rcu(nf_xdp_hashtable, &elem->hnode, key); } list_add_tail_rcu(&ft_elem->head, &elem->head); mutex_unlock(&nf_xdp_hashtable_lock); return 0; err_unlock: mutex_unlock(&nf_xdp_hashtable_lock); kfree(ft_elem); return -ENOMEM; } static void nf_flowtable_by_dev_remove(struct nf_flowtable *ft, const struct net_device *dev) { struct flow_offload_xdp *iter, *elem = NULL; unsigned long key = (unsigned long)dev; mutex_lock(&nf_xdp_hashtable_lock); hash_for_each_possible(nf_xdp_hashtable, iter, hnode, key) { if (key == iter->net_device_addr) { elem = iter; break; } } if (elem) { struct flow_offload_xdp_ft *ft_elem, *ft_next; list_for_each_entry_safe(ft_elem, ft_next, &elem->head, head) { if (ft_elem->ft == ft) { list_del_rcu(&ft_elem->head); kfree_rcu(ft_elem, rcuhead); } } if (list_empty(&elem->head)) hash_del_rcu(&elem->hnode); else elem = NULL; } mutex_unlock(&nf_xdp_hashtable_lock); if (elem) { synchronize_rcu(); kfree(elem); } } int nf_flow_offload_xdp_setup(struct nf_flowtable *flowtable, struct net_device *dev, enum flow_block_command cmd) { switch (cmd) { case FLOW_BLOCK_BIND: return nf_flowtable_by_dev_insert(flowtable, dev); case FLOW_BLOCK_UNBIND: nf_flowtable_by_dev_remove(flowtable, dev); return 0; } WARN_ON_ONCE(1); return 0; } |
| 5 5 1 5 5 5 5 5 5 4 22 4 4 20 16 16 12 7 16 12 7 7 7 7 7 6 1 1 1 1 1 1 2 2 2 2 1 2 2 1 1 1 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 1 1 1 3 3 3 3 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 3 3 3 3 3 2 2 2 2 5 3 3 2 1 2 1 1 1 1 1 1 1 10 10 10 10 16 16 10 12 12 6 6 12 16 16 10 12 14 1 13 9 2 8 2 1 1 3 2 1 1 1 1 1 1 1 1 1 1 1 2 2 4 4 4 4 4 7 4 5 5 5 5 5 1 5 5 5 3 4 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 4 4 7 7 6 6 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 | // SPDX-License-Identifier: GPL-2.0-or-later /* md.c : Multiple Devices driver for Linux Copyright (C) 1998, 1999, 2000 Ingo Molnar completely rewritten, based on the MD driver code from Marc Zyngier Changes: - RAID-1/RAID-5 extensions by Miguel de Icaza, Gadi Oxman, Ingo Molnar - RAID-6 extensions by H. Peter Anvin <hpa@zytor.com> - boot support for linear and striped mode by Harald Hoyer <HarryH@Royal.Net> - kerneld support by Boris Tobotras <boris@xtalk.msk.su> - kmod support by: Cyrus Durgin - RAID0 bugfixes: Mark Anthony Lisher <markal@iname.com> - Devfs support by Richard Gooch <rgooch@atnf.csiro.au> - lots of fixes and improvements to the RAID1/RAID5 and generic RAID code (such as request based resynchronization): Neil Brown <neilb@cse.unsw.edu.au>. - persistent bitmap code Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc. Errors, Warnings, etc. Please use: pr_crit() for error conditions that risk data loss pr_err() for error conditions that are unexpected, like an IO error or internal inconsistency pr_warn() for error conditions that could have been predicated, like adding a device to an array when it has incompatible metadata pr_info() for every interesting, very rare events, like an array starting or stopping, or resync starting or stopping pr_debug() for everything else. */ #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/kthread.h> #include <linux/blkdev.h> #include <linux/blk-integrity.h> #include <linux/badblocks.h> #include <linux/sysctl.h> #include <linux/seq_file.h> #include <linux/fs.h> #include <linux/poll.h> #include <linux/ctype.h> #include <linux/string.h> #include <linux/hdreg.h> #include <linux/proc_fs.h> #include <linux/random.h> #include <linux/major.h> #include <linux/module.h> #include <linux/reboot.h> #include <linux/file.h> #include <linux/compat.h> #include <linux/delay.h> #include <linux/raid/md_p.h> #include <linux/raid/md_u.h> #include <linux/raid/detect.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> #include <linux/part_stat.h> #include "md.h" #include "md-bitmap.h" #include "md-cluster.h" static const char *action_name[NR_SYNC_ACTIONS] = { [ACTION_RESYNC] = "resync", [ACTION_RECOVER] = "recover", [ACTION_CHECK] = "check", [ACTION_REPAIR] = "repair", [ACTION_RESHAPE] = "reshape", [ACTION_FROZEN] = "frozen", [ACTION_IDLE] = "idle", }; static DEFINE_XARRAY(md_submodule); static const struct kobj_type md_ktype; static DECLARE_WAIT_QUEUE_HEAD(resync_wait); /* * This workqueue is used for sync_work to register new sync_thread, and for * del_work to remove rdev, and for event_work that is only set by dm-raid. * * Noted that sync_work will grab reconfig_mutex, hence never flush this * workqueue whith reconfig_mutex grabbed. */ static struct workqueue_struct *md_misc_wq; static int remove_and_add_spares(struct mddev *mddev, struct md_rdev *this); static void mddev_detach(struct mddev *mddev); static void export_rdev(struct md_rdev *rdev); static void md_wakeup_thread_directly(struct md_thread __rcu **thread); /* * Default number of read corrections we'll attempt on an rdev * before ejecting it from the array. We divide the read error * count by 2 for every hour elapsed between read errors. */ #define MD_DEFAULT_MAX_CORRECTED_READ_ERRORS 20 /* Default safemode delay: 200 msec */ #define DEFAULT_SAFEMODE_DELAY ((200 * HZ)/1000 +1) /* * Current RAID-1,4,5,6,10 parallel reconstruction 'guaranteed speed limit' * is sysctl_speed_limit_min, 1000 KB/sec by default, so the extra system load * does not show up that much. Increase it if you want to have more guaranteed * speed. Note that the RAID driver will use the maximum bandwidth * sysctl_speed_limit_max, 200 MB/sec by default, if the IO subsystem is idle. * * Background sync IO speed control: * * - below speed min: * no limit; * - above speed min and below speed max: * a) if mddev is idle, then no limit; * b) if mddev is busy handling normal IO, then limit inflight sync IO * to sync_io_depth; * - above speed max: * sync IO can't be issued; * * Following configurations can be changed via /proc/sys/dev/raid/ for system * or /sys/block/mdX/md/ for one array. */ static int sysctl_speed_limit_min = 1000; static int sysctl_speed_limit_max = 200000; static int sysctl_sync_io_depth = 32; static int speed_min(struct mddev *mddev) { return mddev->sync_speed_min ? mddev->sync_speed_min : sysctl_speed_limit_min; } static int speed_max(struct mddev *mddev) { return mddev->sync_speed_max ? mddev->sync_speed_max : sysctl_speed_limit_max; } static int sync_io_depth(struct mddev *mddev) { return mddev->sync_io_depth ? mddev->sync_io_depth : sysctl_sync_io_depth; } static void rdev_uninit_serial(struct md_rdev *rdev) { if (!test_and_clear_bit(CollisionCheck, &rdev->flags)) return; kvfree(rdev->serial); rdev->serial = NULL; } static void rdevs_uninit_serial(struct mddev *mddev) { struct md_rdev *rdev; rdev_for_each(rdev, mddev) rdev_uninit_serial(rdev); } static int rdev_init_serial(struct md_rdev *rdev) { /* serial_nums equals with BARRIER_BUCKETS_NR */ int i, serial_nums = 1 << ((PAGE_SHIFT - ilog2(sizeof(atomic_t)))); struct serial_in_rdev *serial = NULL; if (test_bit(CollisionCheck, &rdev->flags)) return 0; serial = kvmalloc(sizeof(struct serial_in_rdev) * serial_nums, GFP_KERNEL); if (!serial) return -ENOMEM; for (i = 0; i < serial_nums; i++) { struct serial_in_rdev *serial_tmp = &serial[i]; spin_lock_init(&serial_tmp->serial_lock); serial_tmp->serial_rb = RB_ROOT_CACHED; } rdev->serial = serial; set_bit(CollisionCheck, &rdev->flags); return 0; } static int rdevs_init_serial(struct mddev *mddev) { struct md_rdev *rdev; int ret = 0; rdev_for_each(rdev, mddev) { ret = rdev_init_serial(rdev); if (ret) break; } /* Free all resources if pool is not existed */ if (ret && !mddev->serial_info_pool) rdevs_uninit_serial(mddev); return ret; } /* * rdev needs to enable serial stuffs if it meets the conditions: * 1. it is multi-queue device flaged with writemostly. * 2. the write-behind mode is enabled. */ static int rdev_need_serial(struct md_rdev *rdev) { return (rdev && rdev->mddev->bitmap_info.max_write_behind > 0 && rdev->bdev->bd_disk->queue->nr_hw_queues != 1 && test_bit(WriteMostly, &rdev->flags)); } /* * Init resource for rdev(s), then create serial_info_pool if: * 1. rdev is the first device which return true from rdev_enable_serial. * 2. rdev is NULL, means we want to enable serialization for all rdevs. */ void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev) { int ret = 0; if (rdev && !rdev_need_serial(rdev) && !test_bit(CollisionCheck, &rdev->flags)) return; if (!rdev) ret = rdevs_init_serial(mddev); else ret = rdev_init_serial(rdev); if (ret) return; if (mddev->serial_info_pool == NULL) { /* * already in memalloc noio context by * mddev_suspend() */ mddev->serial_info_pool = mempool_create_kmalloc_pool(NR_SERIAL_INFOS, sizeof(struct serial_info)); if (!mddev->serial_info_pool) { rdevs_uninit_serial(mddev); pr_err("can't alloc memory pool for serialization\n"); } } } /* * Free resource from rdev(s), and destroy serial_info_pool under conditions: * 1. rdev is the last device flaged with CollisionCheck. * 2. when bitmap is destroyed while policy is not enabled. * 3. for disable policy, the pool is destroyed only when no rdev needs it. */ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev) { if (rdev && !test_bit(CollisionCheck, &rdev->flags)) return; if (mddev->serial_info_pool) { struct md_rdev *temp; int num = 0; /* used to track if other rdevs need the pool */ rdev_for_each(temp, mddev) { if (!rdev) { if (!test_bit(MD_SERIALIZE_POLICY, &mddev->flags) || !rdev_need_serial(temp)) rdev_uninit_serial(temp); else num++; } else if (temp != rdev && test_bit(CollisionCheck, &temp->flags)) num++; } if (rdev) rdev_uninit_serial(rdev); if (num) pr_info("The mempool could be used by other devices\n"); else { mempool_destroy(mddev->serial_info_pool); mddev->serial_info_pool = NULL; } } } static struct ctl_table_header *raid_table_header; static const struct ctl_table raid_table[] = { { .procname = "speed_limit_min", .data = &sysctl_speed_limit_min, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "speed_limit_max", .data = &sysctl_speed_limit_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "sync_io_depth", .data = &sysctl_sync_io_depth, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static int start_readonly; /* * The original mechanism for creating an md device is to create * a device node in /dev and to open it. This causes races with device-close. * The preferred method is to write to the "new_array" module parameter. * This can avoid races. * Setting create_on_open to false disables the original mechanism * so all the races disappear. */ static bool create_on_open = true; static bool legacy_async_del_gendisk = true; static bool check_new_feature = true; /* * We have a system wide 'event count' that is incremented * on any 'interesting' event, and readers of /proc/mdstat * can use 'poll' or 'select' to find out when the event * count increases. * * Events are: * start array, stop array, error, add device, remove device, * start build, activate spare */ static DECLARE_WAIT_QUEUE_HEAD(md_event_waiters); static atomic_t md_event_count; void md_new_event(void) { atomic_inc(&md_event_count); wake_up(&md_event_waiters); } EXPORT_SYMBOL_GPL(md_new_event); /* * Enables to iterate over all existing md arrays * all_mddevs_lock protects this list. */ static LIST_HEAD(all_mddevs); static DEFINE_SPINLOCK(all_mddevs_lock); static bool is_md_suspended(struct mddev *mddev) { return percpu_ref_is_dying(&mddev->active_io); } /* Rather than calling directly into the personality make_request function, * IO requests come here first so that we can check if the device is * being suspended pending a reconfiguration. * We hold a refcount over the call to ->make_request. By the time that * call has finished, the bio has been linked into some internal structure * and so is visible to ->quiesce(), so we don't need the refcount any more. */ static bool is_suspended(struct mddev *mddev, struct bio *bio) { if (is_md_suspended(mddev)) return true; if (bio_data_dir(bio) != WRITE) return false; if (READ_ONCE(mddev->suspend_lo) >= READ_ONCE(mddev->suspend_hi)) return false; if (bio->bi_iter.bi_sector >= READ_ONCE(mddev->suspend_hi)) return false; if (bio_end_sector(bio) < READ_ONCE(mddev->suspend_lo)) return false; return true; } bool md_handle_request(struct mddev *mddev, struct bio *bio) { check_suspended: if (unlikely(md_cloned_bio(mddev, bio))) { /* * This bio is an MD cloned bio and already holds an * active_io reference, so percpu_ref_get() is safe here. */ percpu_ref_get(&mddev->active_io); } else { if (is_suspended(mddev, bio)) { /* Bail out if REQ_NOWAIT is set for the bio */ if (bio->bi_opf & REQ_NOWAIT) { bio_wouldblock_error(bio); return true; } wait_event(mddev->sb_wait, !is_suspended(mddev, bio)); } if (!percpu_ref_tryget_live(&mddev->active_io)) goto check_suspended; } if (!mddev->pers->make_request(mddev, bio)) { percpu_ref_put(&mddev->active_io); if (mddev_is_dm(mddev) && mddev->pers->prepare_suspend) return false; goto check_suspended; } percpu_ref_put(&mddev->active_io); return true; } EXPORT_SYMBOL(md_handle_request); static void md_submit_bio(struct bio *bio) { const int rw = bio_data_dir(bio); struct mddev *mddev = bio->bi_bdev->bd_disk->private_data; if (mddev == NULL || mddev->pers == NULL) { bio_io_error(bio); return; } if (unlikely(test_bit(MD_BROKEN, &mddev->flags)) && (rw == WRITE)) { bio_io_error(bio); return; } bio = bio_split_to_limits(bio); if (!bio) return; if (mddev->ro == MD_RDONLY && unlikely(rw == WRITE)) { if (bio_sectors(bio) != 0) bio->bi_status = BLK_STS_IOERR; bio_endio(bio); return; } /* bio could be mergeable after passing to underlayer */ bio->bi_opf &= ~REQ_NOMERGE; md_handle_request(mddev, bio); } /* * Make sure no new requests are submitted to the device, and any requests that * have been submitted are completely handled. */ int mddev_suspend(struct mddev *mddev, bool interruptible) { int err = 0; /* * hold reconfig_mutex to wait for normal io will deadlock, because * other context can't update super_block, and normal io can rely on * updating super_block. */ lockdep_assert_not_held(&mddev->reconfig_mutex); if (interruptible) err = mutex_lock_interruptible(&mddev->suspend_mutex); else mutex_lock(&mddev->suspend_mutex); if (err) return err; if (mddev->suspended) { WRITE_ONCE(mddev->suspended, mddev->suspended + 1); mutex_unlock(&mddev->suspend_mutex); return 0; } percpu_ref_kill(&mddev->active_io); /* * RAID456 IO can sleep in wait_for_reshape while still holding an * active_io reference. If reshape is already interrupted or frozen, * wake those waiters so they can abort and drop the reference instead * of deadlocking suspend. */ if (mddev->pers && mddev->pers->prepare_suspend && reshape_interrupted(mddev)) mddev->pers->prepare_suspend(mddev); if (interruptible) err = wait_event_interruptible(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io)); else wait_event(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io)); if (err) { percpu_ref_resurrect(&mddev->active_io); mutex_unlock(&mddev->suspend_mutex); return err; } /* * For raid456, io might be waiting for reshape to make progress, * allow new reshape to start while waiting for io to be done to * prevent deadlock. */ WRITE_ONCE(mddev->suspended, mddev->suspended + 1); /* restrict memory reclaim I/O during raid array is suspend */ mddev->noio_flag = memalloc_noio_save(); mutex_unlock(&mddev->suspend_mutex); return 0; } EXPORT_SYMBOL_GPL(mddev_suspend); static void __mddev_resume(struct mddev *mddev, bool recovery_needed) { lockdep_assert_not_held(&mddev->reconfig_mutex); mutex_lock(&mddev->suspend_mutex); WRITE_ONCE(mddev->suspended, mddev->suspended - 1); if (mddev->suspended) { mutex_unlock(&mddev->suspend_mutex); return; } /* entred the memalloc scope from mddev_suspend() */ memalloc_noio_restore(mddev->noio_flag); percpu_ref_resurrect(&mddev->active_io); wake_up(&mddev->sb_wait); if (recovery_needed) set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */ mutex_unlock(&mddev->suspend_mutex); } void mddev_resume(struct mddev *mddev) { return __mddev_resume(mddev, true); } EXPORT_SYMBOL_GPL(mddev_resume); /* sync bdev before setting device to readonly or stopping raid*/ static int mddev_set_closing_and_sync_blockdev(struct mddev *mddev, int opener_num) { mutex_lock(&mddev->open_mutex); if (mddev->pers && atomic_read(&mddev->openers) > opener_num) { mutex_unlock(&mddev->open_mutex); return -EBUSY; } if (test_and_set_bit(MD_CLOSING, &mddev->flags)) { mutex_unlock(&mddev->open_mutex); return -EBUSY; } mutex_unlock(&mddev->open_mutex); sync_blockdev(mddev->gendisk->part0); return 0; } /* * The only difference from bio_chain_endio() is that the current * bi_status of bio does not affect the bi_status of parent. */ static void md_end_flush(struct bio *bio) { struct bio *parent = bio->bi_private; /* * If any flush io error before the power failure, * disk data may be lost. */ if (bio->bi_status) pr_err("md: %pg flush io error %d\n", bio->bi_bdev, blk_status_to_errno(bio->bi_status)); bio_put(bio); bio_endio(parent); } bool md_flush_request(struct mddev *mddev, struct bio *bio) { struct md_rdev *rdev; struct bio *new; /* * md_flush_reqeust() should be called under md_handle_request() and * 'active_io' is already grabbed. Hence it's safe to get rdev directly * without rcu protection. */ WARN_ON(percpu_ref_is_zero(&mddev->active_io)); rdev_for_each(rdev, mddev) { if (rdev->raid_disk < 0 || test_bit(Faulty, &rdev->flags)) continue; new = bio_alloc_bioset(rdev->bdev, 0, REQ_OP_WRITE | REQ_PREFLUSH, GFP_NOIO, &mddev->bio_set); new->bi_private = bio; new->bi_end_io = md_end_flush; bio_inc_remaining(bio); submit_bio(new); } if (bio_sectors(bio) == 0) { bio_endio(bio); return true; } bio->bi_opf &= ~REQ_PREFLUSH; return false; } EXPORT_SYMBOL(md_flush_request); static inline struct mddev *mddev_get(struct mddev *mddev) { lockdep_assert_held(&all_mddevs_lock); if (test_bit(MD_DELETED, &mddev->flags)) return NULL; atomic_inc(&mddev->active); return mddev; } static void mddev_delayed_delete(struct work_struct *ws); static void __mddev_put(struct mddev *mddev) { if (mddev->raid_disks || !list_empty(&mddev->disks) || mddev->ctime || mddev->hold_active) return; /* * If array is freed by stopping array, MD_DELETED is set by * do_md_stop(), MD_DELETED is still set here in case mddev is freed * directly by closing a mddev that is created by create_on_open. */ set_bit(MD_DELETED, &mddev->flags); /* * Call queue_work inside the spinlock so that flush_workqueue() after * mddev_find will succeed in waiting for the work to be done. */ queue_work(md_misc_wq, &mddev->del_work); } static void mddev_put_locked(struct mddev *mddev) { if (atomic_dec_and_test(&mddev->active)) __mddev_put(mddev); } void mddev_put(struct mddev *mddev) { if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock)) return; __mddev_put(mddev); spin_unlock(&all_mddevs_lock); } static void md_safemode_timeout(struct timer_list *t); static void md_start_sync(struct work_struct *ws); static void active_io_release(struct percpu_ref *ref) { struct mddev *mddev = container_of(ref, struct mddev, active_io); wake_up(&mddev->sb_wait); } static void no_op(struct percpu_ref *r) {} static void md_bitmap_sysfs_add(struct mddev *mddev) { if (sysfs_update_groups(&mddev->kobj, mddev->bitmap_ops->groups)) pr_warn("md: cannot register extra bitmap attributes for %s\n", mdname(mddev)); else /* * Inform user with KOBJ_CHANGE about new bitmap * attributes. */ kobject_uevent(&mddev->kobj, KOBJ_CHANGE); } static void md_bitmap_sysfs_del(struct mddev *mddev) { int nr_groups = 0; for (nr_groups = 0; mddev->bitmap_ops->groups[nr_groups]; nr_groups++) ; while (--nr_groups >= 1) sysfs_unmerge_group(&mddev->kobj, mddev->bitmap_ops->groups[nr_groups]); sysfs_remove_group(&mddev->kobj, mddev->bitmap_ops->groups[0]); } bool mddev_set_bitmap_ops_nosysfs(struct mddev *mddev) { struct md_submodule_head *head; if (mddev->bitmap_ops && mddev->bitmap_ops->head.id == mddev->bitmap_id) return true; xa_lock(&md_submodule); head = xa_load(&md_submodule, mddev->bitmap_id); if (!head) { pr_warn("md: can't find bitmap id %d\n", mddev->bitmap_id); goto err; } if (head->type != MD_BITMAP) { pr_warn("md: invalid bitmap id %d\n", mddev->bitmap_id); goto err; } mddev->bitmap_ops = (void *)head; xa_unlock(&md_submodule); return true; err: xa_unlock(&md_submodule); return false; } int mddev_init(struct mddev *mddev) { int err = 0; if (!IS_ENABLED(CONFIG_MD_BITMAP)) mddev->bitmap_id = ID_BITMAP_NONE; else mddev->bitmap_id = ID_BITMAP; if (percpu_ref_init(&mddev->active_io, active_io_release, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) return -ENOMEM; if (percpu_ref_init(&mddev->writes_pending, no_op, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { err = -ENOMEM; goto exit_acitve_io; } err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (err) goto exit_writes_pending; err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (err) goto exit_bio_set; err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE, offsetof(struct md_io_clone, bio_clone), 0); if (err) goto exit_sync_set; /* We want to start with the refcount at zero */ percpu_ref_put(&mddev->writes_pending); mutex_init(&mddev->open_mutex); mutex_init(&mddev->reconfig_mutex); mutex_init(&mddev->suspend_mutex); mutex_init(&mddev->bitmap_info.mutex); INIT_LIST_HEAD(&mddev->disks); INIT_LIST_HEAD(&mddev->all_mddevs); INIT_LIST_HEAD(&mddev->deleting); timer_setup(&mddev->safemode_timer, md_safemode_timeout, 0); atomic_set(&mddev->active, 1); atomic_set(&mddev->openers, 0); atomic_set(&mddev->sync_seq, 0); spin_lock_init(&mddev->lock); init_waitqueue_head(&mddev->sb_wait); init_waitqueue_head(&mddev->recovery_wait); mddev->reshape_position = MaxSector; mddev->reshape_backwards = 0; mddev->last_sync_action = ACTION_IDLE; mddev->resync_min = 0; mddev->resync_max = MaxSector; mddev->level = LEVEL_NONE; INIT_WORK(&mddev->sync_work, md_start_sync); INIT_WORK(&mddev->del_work, mddev_delayed_delete); return 0; exit_sync_set: bioset_exit(&mddev->sync_set); exit_bio_set: bioset_exit(&mddev->bio_set); exit_writes_pending: percpu_ref_exit(&mddev->writes_pending); exit_acitve_io: percpu_ref_exit(&mddev->active_io); return err; } EXPORT_SYMBOL_GPL(mddev_init); void mddev_destroy(struct mddev *mddev) { bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); bioset_exit(&mddev->io_clone_set); percpu_ref_exit(&mddev->active_io); percpu_ref_exit(&mddev->writes_pending); } EXPORT_SYMBOL_GPL(mddev_destroy); static struct mddev *mddev_find_locked(dev_t unit) { struct mddev *mddev; list_for_each_entry(mddev, &all_mddevs, all_mddevs) if (mddev->unit == unit) return mddev; return NULL; } /* find an unused unit number */ static dev_t mddev_alloc_unit(void) { static int next_minor = 512; int start = next_minor; bool is_free = 0; dev_t dev = 0; while (!is_free) { dev = MKDEV(MD_MAJOR, next_minor); next_minor++; if (next_minor > MINORMASK) next_minor = 0; if (next_minor == start) return 0; /* Oh dear, all in use. */ is_free = !mddev_find_locked(dev); } return dev; } static struct mddev *mddev_alloc(dev_t unit) { struct mddev *new; int error; if (unit && MAJOR(unit) != MD_MAJOR) unit &= ~((1 << MdpMinorShift) - 1); new = kzalloc_obj(*new); if (!new) return ERR_PTR(-ENOMEM); error = mddev_init(new); if (error) goto out_free_new; spin_lock(&all_mddevs_lock); if (unit) { error = -EEXIST; if (mddev_find_locked(unit)) goto out_destroy_new; new->unit = unit; if (MAJOR(unit) == MD_MAJOR) new->md_minor = MINOR(unit); else new->md_minor = MINOR(unit) >> MdpMinorShift; new->hold_active = UNTIL_IOCTL; } else { error = -ENODEV; new->unit = mddev_alloc_unit(); if (!new->unit) goto out_destroy_new; new->md_minor = MINOR(new->unit); new->hold_active = UNTIL_STOP; } list_add(&new->all_mddevs, &all_mddevs); spin_unlock(&all_mddevs_lock); return new; out_destroy_new: spin_unlock(&all_mddevs_lock); mddev_destroy(new); out_free_new: kfree(new); return ERR_PTR(error); } static void mddev_free(struct mddev *mddev) { spin_lock(&all_mddevs_lock); list_del(&mddev->all_mddevs); spin_unlock(&all_mddevs_lock); mddev_destroy(mddev); kfree(mddev); } static const struct attribute_group md_redundancy_group; void mddev_unlock(struct mddev *mddev) { struct md_rdev *rdev; struct md_rdev *tmp; LIST_HEAD(delete); if (!list_empty(&mddev->deleting)) list_splice_init(&mddev->deleting, &delete); if (mddev->to_remove) { /* These cannot be removed under reconfig_mutex as * an access to the files will try to take reconfig_mutex * while holding the file unremovable, which leads to * a deadlock. * So hold set sysfs_active while the remove in happeing, * and anything else which might set ->to_remove or my * otherwise change the sysfs namespace will fail with * -EBUSY if sysfs_active is still set. * We set sysfs_active under reconfig_mutex and elsewhere * test it under the same mutex to ensure its correct value * is seen. */ const struct attribute_group *to_remove = mddev->to_remove; mddev->to_remove = NULL; mddev->sysfs_active = 1; mutex_unlock(&mddev->reconfig_mutex); if (mddev->kobj.sd) { if (to_remove != &md_redundancy_group) sysfs_remove_group(&mddev->kobj, to_remove); if (mddev->pers == NULL || mddev->pers->sync_request == NULL) { sysfs_remove_group(&mddev->kobj, &md_redundancy_group); if (mddev->sysfs_action) sysfs_put(mddev->sysfs_action); if (mddev->sysfs_completed) sysfs_put(mddev->sysfs_completed); if (mddev->sysfs_degraded) sysfs_put(mddev->sysfs_degraded); mddev->sysfs_action = NULL; mddev->sysfs_completed = NULL; mddev->sysfs_degraded = NULL; } } mddev->sysfs_active = 0; } else mutex_unlock(&mddev->reconfig_mutex); md_wakeup_thread(mddev->thread); wake_up(&mddev->sb_wait); list_for_each_entry_safe(rdev, tmp, &delete, same_set) { list_del_init(&rdev->same_set); kobject_del(&rdev->kobj); export_rdev(rdev); } if (!legacy_async_del_gendisk) { /* * Call del_gendisk after release reconfig_mutex to avoid * deadlock (e.g. call del_gendisk under the lock and an * access to sysfs files waits the lock) * And MD_DELETED is only used for md raid which is set in * do_md_stop. dm raid only uses md_stop to stop. So dm raid * doesn't need to check MD_DELETED when getting reconfig lock */ if (test_bit(MD_DELETED, &mddev->flags) && !test_and_set_bit(MD_DO_DELETE, &mddev->flags)) { kobject_del(&mddev->kobj); del_gendisk(mddev->gendisk); } } } EXPORT_SYMBOL_GPL(mddev_unlock); struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr) { struct md_rdev *rdev; rdev_for_each_rcu(rdev, mddev) if (rdev->desc_nr == nr) return rdev; return NULL; } EXPORT_SYMBOL_GPL(md_find_rdev_nr_rcu); static struct md_rdev *find_rdev(struct mddev *mddev, dev_t dev) { struct md_rdev *rdev; rdev_for_each(rdev, mddev) if (rdev->bdev->bd_dev == dev) return rdev; return NULL; } struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev) { struct md_rdev *rdev; rdev_for_each_rcu(rdev, mddev) if (rdev->bdev->bd_dev == dev) return rdev; return NULL; } EXPORT_SYMBOL_GPL(md_find_rdev_rcu); static struct md_personality *get_pers(int level, char *clevel) { struct md_personality *ret = NULL; struct md_submodule_head *head; unsigned long i; xa_lock(&md_submodule); xa_for_each(&md_submodule, i, head) { if (head->type != MD_PERSONALITY) continue; if ((level != LEVEL_NONE && head->id == level) || !strcmp(head->name, clevel)) { if (try_module_get(head->owner)) ret = (void *)head; break; } } xa_unlock(&md_submodule); if (!ret) { if (level != LEVEL_NONE) pr_warn("md: personality for level %d is not loaded!\n", level); else pr_warn("md: personality for level %s is not loaded!\n", clevel); } return ret; } static void put_pers(struct md_personality *pers) { module_put(pers->head.owner); } /* return the offset of the super block in 512byte sectors */ static inline sector_t calc_dev_sboffset(struct md_rdev *rdev) { return MD_NEW_SIZE_SECTORS(bdev_nr_sectors(rdev->bdev)); } static int alloc_disk_sb(struct md_rdev *rdev) { rdev->sb_page = alloc_page(GFP_KERNEL); if (!rdev->sb_page) return -ENOMEM; return 0; } void md_rdev_clear(struct md_rdev *rdev) { if (rdev->sb_page) { put_page(rdev->sb_page); rdev->sb_loaded = 0; rdev->sb_page = NULL; rdev->sb_start = 0; rdev->sectors = 0; } if (rdev->bb_page) { put_page(rdev->bb_page); rdev->bb_page = NULL; } badblocks_exit(&rdev->badblocks); } EXPORT_SYMBOL_GPL(md_rdev_clear); static void super_written(struct bio *bio) { struct md_rdev *rdev = bio->bi_private; struct mddev *mddev = rdev->mddev; if (bio->bi_status) { pr_err("md: %s gets error=%d\n", __func__, blk_status_to_errno(bio->bi_status)); md_error(mddev, rdev); if (!test_bit(Faulty, &rdev->flags) && (bio->bi_opf & MD_FAILFAST)) { set_bit(MD_SB_NEED_REWRITE, &mddev->sb_flags); set_bit(LastDev, &rdev->flags); } } else clear_bit(LastDev, &rdev->flags); bio_put(bio); rdev_dec_pending(rdev, mddev); if (atomic_dec_and_test(&mddev->pending_writes)) wake_up(&mddev->sb_wait); } /** * md_write_metadata - write metadata to underlying disk, including * array superblock, badblocks, bitmap superblock and bitmap bits. * @mddev: the array to write * @rdev: the underlying disk to write * @sector: the offset to @rdev * @size: the length of the metadata * @page: the metadata * @offset: the offset to @page * * Write @size bytes of @page start from @offset, to @sector of @rdev, Increment * mddev->pending_writes before returning, and decrement it on completion, * waking up sb_wait. Caller must call md_super_wait() after issuing io to all * rdev. If an error occurred, md_error() will be called, and the @rdev will be * kicked out from @mddev. */ void md_write_metadata(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page, unsigned int offset) { struct bio *bio; if (!page) return; if (test_bit(Faulty, &rdev->flags)) return; bio = bio_alloc_bioset(rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev, 1, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE | REQ_META | REQ_PREFLUSH | REQ_FUA, GFP_NOIO, &mddev->sync_set); atomic_inc(&rdev->nr_pending); bio->bi_iter.bi_sector = sector; __bio_add_page(bio, page, size, offset); bio->bi_private = rdev; bio->bi_end_io = super_written; if (test_bit(MD_FAILFAST_SUPPORTED, &mddev->flags) && test_bit(FailFast, &rdev->flags) && !test_bit(LastDev, &rdev->flags)) bio->bi_opf |= MD_FAILFAST; atomic_inc(&mddev->pending_writes); submit_bio(bio); } int md_super_wait(struct mddev *mddev) { /* wait for all superblock writes that were scheduled to complete */ wait_event(mddev->sb_wait, atomic_read(&mddev->pending_writes)==0); if (test_and_clear_bit(MD_SB_NEED_REWRITE, &mddev->sb_flags)) return -EAGAIN; return 0; } int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, struct page *page, blk_opf_t opf, bool metadata_op) { struct bio bio; struct bio_vec bvec; if (metadata_op && rdev->meta_bdev) bio_init(&bio, rdev->meta_bdev, &bvec, 1, opf); else bio_init(&bio, rdev->bdev, &bvec, 1, opf); if (metadata_op) bio.bi_iter.bi_sector = sector + rdev->sb_start; else if (rdev->mddev->reshape_position != MaxSector && (rdev->mddev->reshape_backwards == (sector >= rdev->mddev->reshape_position))) bio.bi_iter.bi_sector = sector + rdev->new_data_offset; else bio.bi_iter.bi_sector = sector + rdev->data_offset; __bio_add_page(&bio, page, size, 0); submit_bio_wait(&bio); return !bio.bi_status; } EXPORT_SYMBOL_GPL(sync_page_io); static int read_disk_sb(struct md_rdev *rdev, int size) { if (rdev->sb_loaded) return 0; if (!sync_page_io(rdev, 0, size, rdev->sb_page, REQ_OP_READ, true)) goto fail; rdev->sb_loaded = 1; return 0; fail: pr_err("md: disabled device %pg, could not read superblock.\n", rdev->bdev); return -EINVAL; } static int md_uuid_equal(mdp_super_t *sb1, mdp_super_t *sb2) { return sb1->set_uuid0 == sb2->set_uuid0 && sb1->set_uuid1 == sb2->set_uuid1 && sb1->set_uuid2 == sb2->set_uuid2 && sb1->set_uuid3 == sb2->set_uuid3; } static int md_sb_equal(mdp_super_t *sb1, mdp_super_t *sb2) { int ret; mdp_super_t *tmp1, *tmp2; tmp1 = kmalloc_obj(*tmp1); tmp2 = kmalloc_obj(*tmp2); if (!tmp1 || !tmp2) { ret = 0; goto abort; } *tmp1 = *sb1; *tmp2 = *sb2; /* * nr_disks is not constant */ tmp1->nr_disks = 0; tmp2->nr_disks = 0; ret = (memcmp(tmp1, tmp2, MD_SB_GENERIC_CONSTANT_WORDS * 4) == 0); abort: kfree(tmp1); kfree(tmp2); return ret; } static u32 md_csum_fold(u32 csum) { csum = (csum & 0xffff) + (csum >> 16); return (csum & 0xffff) + (csum >> 16); } static unsigned int calc_sb_csum(mdp_super_t *sb) { u64 newcsum = 0; u32 *sb32 = (u32*)sb; int i; unsigned int disk_csum, csum; disk_csum = sb->sb_csum; sb->sb_csum = 0; for (i = 0; i < MD_SB_BYTES/4 ; i++) newcsum += sb32[i]; csum = (newcsum & 0xffffffff) + (newcsum>>32); #ifdef CONFIG_ALPHA /* This used to use csum_partial, which was wrong for several * reasons including that different results are returned on * different architectures. It isn't critical that we get exactly * the same return value as before (we always csum_fold before * testing, and that removes any differences). However as we * know that csum_partial always returned a 16bit value on * alphas, do a fold to maximise conformity to previous behaviour. */ sb->sb_csum = md_csum_fold(disk_csum); #else sb->sb_csum = disk_csum; #endif return csum; } /* * Handle superblock details. * We want to be able to handle multiple superblock formats * so we have a common interface to them all, and an array of * different handlers. * We rely on user-space to write the initial superblock, and support * reading and updating of superblocks. * Interface methods are: * int load_super(struct md_rdev *dev, struct md_rdev *refdev, int minor_version) * loads and validates a superblock on dev. * if refdev != NULL, compare superblocks on both devices * Return: * 0 - dev has a superblock that is compatible with refdev * 1 - dev has a superblock that is compatible and newer than refdev * so dev should be used as the refdev in future * -EINVAL superblock incompatible or invalid * -othererror e.g. -EIO * * int validate_super(struct mddev *mddev, struct md_rdev *dev) * Verify that dev is acceptable into mddev. * The first time, mddev->raid_disks will be 0, and data from * dev should be merged in. Subsequent calls check that dev * is new enough. Return 0 or -EINVAL * * void sync_super(struct mddev *mddev, struct md_rdev *dev) * Update the superblock for rdev with data in mddev * This does not write to disc. * */ struct super_type { char *name; struct module *owner; int (*load_super)(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version); int (*validate_super)(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev); void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); unsigned long long (*rdev_size_change)(struct md_rdev *rdev, sector_t num_sectors); int (*allow_new_offset)(struct md_rdev *rdev, unsigned long long new_offset); }; /* * Check that the given mddev has no bitmap. * * This function is called from the run method of all personalities that do not * support bitmaps. It prints an error message and returns non-zero if mddev * has a bitmap. Otherwise, it returns 0. * */ int md_check_no_bitmap(struct mddev *mddev) { if (!mddev->bitmap_info.file && !mddev->bitmap_info.offset) return 0; pr_warn("%s: bitmaps are not supported for %s\n", mdname(mddev), mddev->pers->head.name); return 1; } EXPORT_SYMBOL(md_check_no_bitmap); /* * load_super for 0.90.0 */ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version) { mdp_super_t *sb; int ret; bool spare_disk = true; /* * Calculate the position of the superblock (512byte sectors), * it's at the end of the disk. * * It also happens to be a multiple of 4Kb. */ rdev->sb_start = calc_dev_sboffset(rdev); ret = read_disk_sb(rdev, MD_SB_BYTES); if (ret) return ret; ret = -EINVAL; sb = page_address(rdev->sb_page); if (sb->md_magic != MD_SB_MAGIC) { pr_warn("md: invalid raid superblock magic on %pg\n", rdev->bdev); goto abort; } if (sb->major_version != 0 || sb->minor_version < 90 || sb->minor_version > 91) { pr_warn("Bad version number %d.%d on %pg\n", sb->major_version, sb->minor_version, rdev->bdev); goto abort; } if (sb->raid_disks <= 0) goto abort; if (md_csum_fold(calc_sb_csum(sb)) != md_csum_fold(sb->sb_csum)) { pr_warn("md: invalid superblock checksum on %pg\n", rdev->bdev); goto abort; } rdev->preferred_minor = sb->md_minor; rdev->data_offset = 0; rdev->new_data_offset = 0; rdev->sb_size = MD_SB_BYTES; rdev->badblocks.shift = -1; rdev->desc_nr = sb->this_disk.number; /* not spare disk */ if (rdev->desc_nr >= 0 && rdev->desc_nr < MD_SB_DISKS && sb->disks[rdev->desc_nr].state & ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE))) spare_disk = false; if (!refdev) { if (!spare_disk) ret = 1; else ret = 0; } else { __u64 ev1, ev2; mdp_super_t *refsb = page_address(refdev->sb_page); if (!md_uuid_equal(refsb, sb)) { pr_warn("md: %pg has different UUID to %pg\n", rdev->bdev, refdev->bdev); goto abort; } if (!md_sb_equal(refsb, sb)) { pr_warn("md: %pg has same UUID but different superblock to %pg\n", rdev->bdev, refdev->bdev); goto abort; } ev1 = md_event(sb); ev2 = md_event(refsb); if (!spare_disk && ev1 > ev2) ret = 1; else ret = 0; } rdev->sectors = rdev->sb_start; /* Limit to 4TB as metadata cannot record more than that. * (not needed for Linear and RAID0 as metadata doesn't * record this size) */ if ((u64)rdev->sectors >= (2ULL << 32) && sb->level >= 1) rdev->sectors = (sector_t)(2ULL << 32) - 2; if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1) /* "this cannot possibly happen" ... */ ret = -EINVAL; abort: return ret; } static u64 md_bitmap_events_cleared(struct mddev *mddev) { struct md_bitmap_stats stats; int err; if (!md_bitmap_enabled(mddev, false)) return 0; err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats); if (err) return 0; return stats.events_cleared; } /* * validate_super for 0.90.0 * note: we are not using "freshest" for 0.9 superblock */ static int super_90_validate(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev) { mdp_disk_t *desc; mdp_super_t *sb = page_address(rdev->sb_page); __u64 ev1 = md_event(sb); rdev->raid_disk = -1; clear_bit(Faulty, &rdev->flags); clear_bit(In_sync, &rdev->flags); clear_bit(Bitmap_sync, &rdev->flags); clear_bit(WriteMostly, &rdev->flags); if (mddev->raid_disks == 0) { mddev->major_version = 0; mddev->minor_version = sb->minor_version; mddev->patch_version = sb->patch_version; mddev->external = 0; mddev->chunk_sectors = sb->chunk_size >> 9; mddev->ctime = sb->ctime; mddev->utime = sb->utime; mddev->level = sb->level; mddev->clevel[0] = 0; mddev->layout = sb->layout; mddev->raid_disks = sb->raid_disks; mddev->dev_sectors = ((sector_t)sb->size) * 2; mddev->events = ev1; mddev->bitmap_info.offset = 0; mddev->bitmap_info.space = 0; /* bitmap can use 60 K after the 4K superblocks */ mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9; mddev->bitmap_info.default_space = 64*2 - (MD_SB_BYTES >> 9); mddev->reshape_backwards = 0; if (mddev->minor_version >= 91) { mddev->reshape_position = sb->reshape_position; mddev->delta_disks = sb->delta_disks; mddev->new_level = sb->new_level; mddev->new_layout = sb->new_layout; mddev->new_chunk_sectors = sb->new_chunk >> 9; if (mddev->delta_disks < 0) mddev->reshape_backwards = 1; } else { mddev->reshape_position = MaxSector; mddev->delta_disks = 0; mddev->new_level = mddev->level; mddev->new_layout = mddev->layout; mddev->new_chunk_sectors = mddev->chunk_sectors; } if (mddev->level == 0) mddev->layout = -1; if (sb->state & (1<<MD_SB_CLEAN)) mddev->resync_offset = MaxSector; else { if (sb->events_hi == sb->cp_events_hi && sb->events_lo == sb->cp_events_lo) { mddev->resync_offset = sb->recovery_cp; } else mddev->resync_offset = 0; } memcpy(mddev->uuid+0, &sb->set_uuid0, 4); memcpy(mddev->uuid+4, &sb->set_uuid1, 4); memcpy(mddev->uuid+8, &sb->set_uuid2, 4); memcpy(mddev->uuid+12,&sb->set_uuid3, 4); mddev->max_disks = MD_SB_DISKS; if (sb->state & (1<<MD_SB_BITMAP_PRESENT) && mddev->bitmap_info.file == NULL) { mddev->bitmap_info.offset = mddev->bitmap_info.default_offset; mddev->bitmap_info.space = mddev->bitmap_info.default_space; } } else if (mddev->pers == NULL) { /* Insist on good event counter while assembling, except * for spares (which don't need an event count) */ ++ev1; if (sb->disks[rdev->desc_nr].state & ( (1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE))) if (ev1 < mddev->events) return -EINVAL; } else if (mddev->bitmap) { /* if adding to array with a bitmap, then we can accept an * older device ... but not too old. */ if (ev1 < md_bitmap_events_cleared(mddev)) return 0; if (ev1 < mddev->events) set_bit(Bitmap_sync, &rdev->flags); } else { if (ev1 < mddev->events) /* just a hot-add of a new device, leave raid_disk at -1 */ return 0; } desc = sb->disks + rdev->desc_nr; if (desc->state & (1<<MD_DISK_FAULTY)) set_bit(Faulty, &rdev->flags); else if (desc->state & (1<<MD_DISK_SYNC)) { set_bit(In_sync, &rdev->flags); rdev->raid_disk = desc->raid_disk; rdev->saved_raid_disk = desc->raid_disk; } else if (desc->state & (1<<MD_DISK_ACTIVE)) { /* active but not in sync implies recovery up to * reshape position. We don't know exactly where * that is, so set to zero for now */ if (mddev->minor_version >= 91) { rdev->recovery_offset = 0; rdev->raid_disk = desc->raid_disk; } } if (desc->state & (1<<MD_DISK_WRITEMOSTLY)) set_bit(WriteMostly, &rdev->flags); if (desc->state & (1<<MD_DISK_FAILFAST)) set_bit(FailFast, &rdev->flags); return 0; } /* * sync_super for 0.90.0 */ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev) { mdp_super_t *sb; struct md_rdev *rdev2; int next_spare = mddev->raid_disks; /* make rdev->sb match mddev data.. * * 1/ zero out disks * 2/ Add info for each disk, keeping track of highest desc_nr (next_spare); * 3/ any empty disks < next_spare become removed * * disks[0] gets initialised to REMOVED because * we cannot be sure from other fields if it has * been initialised or not. */ int i; int active=0, working=0,failed=0,spare=0,nr_disks=0; rdev->sb_size = MD_SB_BYTES; sb = page_address(rdev->sb_page); memset(sb, 0, sizeof(*sb)); sb->md_magic = MD_SB_MAGIC; sb->major_version = mddev->major_version; sb->patch_version = mddev->patch_version; sb->gvalid_words = 0; /* ignored */ memcpy(&sb->set_uuid0, mddev->uuid+0, 4); memcpy(&sb->set_uuid1, mddev->uuid+4, 4); memcpy(&sb->set_uuid2, mddev->uuid+8, 4); memcpy(&sb->set_uuid3, mddev->uuid+12,4); sb->ctime = clamp_t(time64_t, mddev->ctime, 0, U32_MAX); sb->level = mddev->level; sb->size = mddev->dev_sectors / 2; sb->raid_disks = mddev->raid_disks; sb->md_minor = mddev->md_minor; sb->not_persistent = 0; sb->utime = clamp_t(time64_t, mddev->utime, 0, U32_MAX); sb->state = 0; sb->events_hi = (mddev->events>>32); sb->events_lo = (u32)mddev->events; if (mddev->reshape_position == MaxSector) sb->minor_version = 90; else { sb->minor_version = 91; sb->reshape_position = mddev->reshape_position; sb->new_level = mddev->new_level; sb->delta_disks = mddev->delta_disks; sb->new_layout = mddev->new_layout; sb->new_chunk = mddev->new_chunk_sectors << 9; } mddev->minor_version = sb->minor_version; if (mddev->in_sync) { sb->recovery_cp = mddev->resync_offset; sb->cp_events_hi = (mddev->events>>32); sb->cp_events_lo = (u32)mddev->events; if (mddev->resync_offset == MaxSector) sb->state = (1<< MD_SB_CLEAN); } else sb->recovery_cp = 0; sb->layout = mddev->layout; sb->chunk_size = mddev->chunk_sectors << 9; if (mddev->bitmap && mddev->bitmap_info.file == NULL) sb->state |= (1<<MD_SB_BITMAP_PRESENT); sb->disks[0].state = (1<<MD_DISK_REMOVED); rdev_for_each(rdev2, mddev) { mdp_disk_t *d; int desc_nr; int is_active = test_bit(In_sync, &rdev2->flags); if (rdev2->raid_disk >= 0 && sb->minor_version >= 91) /* we have nowhere to store the recovery_offset, * but if it is not below the reshape_position, * we can piggy-back on that. */ is_active = 1; if (rdev2->raid_disk < 0 || test_bit(Faulty, &rdev2->flags)) is_active = 0; if (is_active) desc_nr = rdev2->raid_disk; else desc_nr = next_spare++; rdev2->desc_nr = desc_nr; d = &sb->disks[rdev2->desc_nr]; nr_disks++; d->number = rdev2->desc_nr; d->major = MAJOR(rdev2->bdev->bd_dev); d->minor = MINOR(rdev2->bdev->bd_dev); if (is_active) d->raid_disk = rdev2->raid_disk; else d->raid_disk = rdev2->desc_nr; /* compatibility */ if (test_bit(Faulty, &rdev2->flags)) d->state = (1<<MD_DISK_FAULTY); else if (is_active) { d->state = (1<<MD_DISK_ACTIVE); if (test_bit(In_sync, &rdev2->flags)) d->state |= (1<<MD_DISK_SYNC); active++; working++; } else { d->state = 0; spare++; working++; } if (test_bit(WriteMostly, &rdev2->flags)) d->state |= (1<<MD_DISK_WRITEMOSTLY); if (test_bit(FailFast, &rdev2->flags)) d->state |= (1<<MD_DISK_FAILFAST); } /* now set the "removed" and "faulty" bits on any missing devices */ for (i=0 ; i < mddev->raid_disks ; i++) { mdp_disk_t *d = &sb->disks[i]; if (d->state == 0 && d->number == 0) { d->number = i; d->raid_disk = i; d->state = (1<<MD_DISK_REMOVED); d->state |= (1<<MD_DISK_FAULTY); failed++; } } sb->nr_disks = nr_disks; sb->active_disks = active; sb->working_disks = working; sb->failed_disks = failed; sb->spare_disks = spare; sb->this_disk = sb->disks[rdev->desc_nr]; sb->sb_csum = calc_sb_csum(sb); } /* * rdev_size_change for 0.90.0 */ static unsigned long long super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) { if (num_sectors && num_sectors < rdev->mddev->dev_sectors) return 0; /* component must fit device */ if (rdev->mddev->bitmap_info.offset) return 0; /* can't move bitmap */ rdev->sb_start = calc_dev_sboffset(rdev); if (!num_sectors || num_sectors > rdev->sb_start) num_sectors = rdev->sb_start; /* Limit to 4TB as metadata cannot record more than that. * 4TB == 2^32 KB, or 2*2^32 sectors. */ if ((u64)num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1) num_sectors = (sector_t)(2ULL << 32) - 2; do { md_write_metadata(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size, rdev->sb_page, 0); } while (md_super_wait(rdev->mddev) < 0); return num_sectors; } static int super_90_allow_new_offset(struct md_rdev *rdev, unsigned long long new_offset) { /* non-zero offset changes not possible with v0.90 */ return new_offset == 0; } /* * version 1 superblock */ static __le32 calc_sb_1_csum(struct mdp_superblock_1 *sb) { __le32 disk_csum; u32 csum; unsigned long long newcsum; int size = 256 + le32_to_cpu(sb->max_dev)*2; __le32 *isuper = (__le32*)sb; disk_csum = sb->sb_csum; sb->sb_csum = 0; newcsum = 0; for (; size >= 4; size -= 4) newcsum += le32_to_cpu(*isuper++); if (size == 2) newcsum += le16_to_cpu(*(__le16*) isuper); csum = (newcsum & 0xffffffff) + (newcsum >> 32); sb->sb_csum = disk_csum; return cpu_to_le32(csum); } static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version) { struct mdp_superblock_1 *sb; int ret; sector_t sb_start; sector_t sectors; int bmask; bool spare_disk = true; /* * Calculate the position of the superblock in 512byte sectors. * It is always aligned to a 4K boundary and * depeding on minor_version, it can be: * 0: At least 8K, but less than 12K, from end of device * 1: At start of device * 2: 4K from start of device. */ switch(minor_version) { case 0: sb_start = bdev_nr_sectors(rdev->bdev) - 8 * 2; sb_start &= ~(sector_t)(4*2-1); break; case 1: sb_start = 0; break; case 2: sb_start = 8; break; default: return -EINVAL; } rdev->sb_start = sb_start; /* superblock is rarely larger than 1K, but it can be larger, * and it is safe to read 4k, so we do that */ ret = read_disk_sb(rdev, 4096); if (ret) return ret; sb = page_address(rdev->sb_page); if (sb->magic != cpu_to_le32(MD_SB_MAGIC) || sb->major_version != cpu_to_le32(1) || le32_to_cpu(sb->max_dev) > (4096-256)/2 || le64_to_cpu(sb->super_offset) != rdev->sb_start || (le32_to_cpu(sb->feature_map) & ~MD_FEATURE_ALL) != 0) return -EINVAL; if (calc_sb_1_csum(sb) != sb->sb_csum) { pr_warn("md: invalid superblock checksum on %pg\n", rdev->bdev); return -EINVAL; } if (le64_to_cpu(sb->data_size) < 10) { pr_warn("md: data_size too small on %pg\n", rdev->bdev); return -EINVAL; } if (sb->pad0 || sb->pad3[0] || memcmp(sb->pad3, sb->pad3+1, sizeof(sb->pad3) - sizeof(sb->pad3[1]))) { pr_warn("Some padding is non-zero on %pg, might be a new feature\n", rdev->bdev); if (check_new_feature) return -EINVAL; pr_warn("check_new_feature is disabled, data corruption possible\n"); } rdev->preferred_minor = 0xffff; rdev->data_offset = le64_to_cpu(sb->data_offset); rdev->new_data_offset = rdev->data_offset; if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE) && (le32_to_cpu(sb->feature_map) & MD_FEATURE_NEW_OFFSET)) rdev->new_data_offset += (s32)le32_to_cpu(sb->new_offset); atomic_set(&rdev->corrected_errors, le32_to_cpu(sb->cnt_corrected_read)); rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256; bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1; if (rdev->sb_size & bmask) rdev->sb_size = (rdev->sb_size | bmask) + 1; if (minor_version && rdev->data_offset < sb_start + (rdev->sb_size/512)) return -EINVAL; if (minor_version && rdev->new_data_offset < sb_start + (rdev->sb_size/512)) return -EINVAL; rdev->desc_nr = le32_to_cpu(sb->dev_number); if (!rdev->bb_page) { rdev->bb_page = alloc_page(GFP_KERNEL); if (!rdev->bb_page) return -ENOMEM; } if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BAD_BLOCKS) && rdev->badblocks.count == 0) { /* need to load the bad block list. * Currently we limit it to one page. */ s32 offset; sector_t bb_sector; __le64 *bbp; int i; int sectors = le16_to_cpu(sb->bblog_size); if (sectors > (PAGE_SIZE / 512)) return -EINVAL; offset = le32_to_cpu(sb->bblog_offset); if (offset == 0) return -EINVAL; bb_sector = (long long)offset; if (!sync_page_io(rdev, bb_sector, sectors << 9, rdev->bb_page, REQ_OP_READ, true)) return -EIO; bbp = (__le64 *)page_address(rdev->bb_page); rdev->badblocks.shift = sb->bblog_shift; for (i = 0 ; i < (sectors << (9-3)) ; i++, bbp++) { u64 bb = le64_to_cpu(*bbp); int count = bb & (0x3ff); u64 sector = bb >> 10; sector <<= sb->bblog_shift; count <<= sb->bblog_shift; if (bb + 1 == 0) break; if (!badblocks_set(&rdev->badblocks, sector, count, 1)) return -EINVAL; } } else if (sb->bblog_offset != 0) rdev->badblocks.shift = 0; if ((le32_to_cpu(sb->feature_map) & (MD_FEATURE_PPL | MD_FEATURE_MULTIPLE_PPLS))) { rdev->ppl.offset = (__s16)le16_to_cpu(sb->ppl.offset); rdev->ppl.size = le16_to_cpu(sb->ppl.size); rdev->ppl.sector = rdev->sb_start + rdev->ppl.offset; } if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT) && sb->level != 0) return -EINVAL; /* not spare disk */ if (rdev->desc_nr >= 0 && rdev->desc_nr < le32_to_cpu(sb->max_dev) && (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX || le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL)) spare_disk = false; if (!refdev) { if (!spare_disk) ret = 1; else ret = 0; } else { __u64 ev1, ev2; struct mdp_superblock_1 *refsb = page_address(refdev->sb_page); if (memcmp(sb->set_uuid, refsb->set_uuid, 16) != 0 || sb->level != refsb->level || sb->layout != refsb->layout || sb->chunksize != refsb->chunksize) { pr_warn("md: %pg has strangely different superblock to %pg\n", rdev->bdev, refdev->bdev); return -EINVAL; } ev1 = le64_to_cpu(sb->events); ev2 = le64_to_cpu(refsb->events); if (!spare_disk && ev1 > ev2) ret = 1; else ret = 0; } if (minor_version) sectors = bdev_nr_sectors(rdev->bdev) - rdev->data_offset; else sectors = rdev->sb_start; if (sectors < le64_to_cpu(sb->data_size)) return -EINVAL; rdev->sectors = le64_to_cpu(sb->data_size); return ret; } static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev) { struct mdp_superblock_1 *sb = page_address(rdev->sb_page); __u64 ev1 = le64_to_cpu(sb->events); int role; rdev->raid_disk = -1; clear_bit(Faulty, &rdev->flags); clear_bit(In_sync, &rdev->flags); clear_bit(Bitmap_sync, &rdev->flags); clear_bit(WriteMostly, &rdev->flags); if (mddev->raid_disks == 0) { mddev->major_version = 1; mddev->patch_version = 0; mddev->external = 0; mddev->chunk_sectors = le32_to_cpu(sb->chunksize); mddev->ctime = le64_to_cpu(sb->ctime); mddev->utime = le64_to_cpu(sb->utime); mddev->level = le32_to_cpu(sb->level); mddev->clevel[0] = 0; mddev->layout = le32_to_cpu(sb->layout); mddev->raid_disks = le32_to_cpu(sb->raid_disks); mddev->dev_sectors = le64_to_cpu(sb->size); mddev->events = ev1; mddev->bitmap_info.offset = 0; mddev->bitmap_info.space = 0; /* Default location for bitmap is 1K after superblock * using 3K - total of 4K */ mddev->bitmap_info.default_offset = 1024 >> 9; mddev->bitmap_info.default_space = (4096-1024) >> 9; mddev->reshape_backwards = 0; mddev->resync_offset = le64_to_cpu(sb->resync_offset); memcpy(mddev->uuid, sb->set_uuid, 16); mddev->max_disks = (4096-256)/2; if (!mddev->logical_block_size) mddev->logical_block_size = le32_to_cpu(sb->logical_block_size); if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) && mddev->bitmap_info.file == NULL) { mddev->bitmap_info.offset = (__s32)le32_to_cpu(sb->bitmap_offset); /* Metadata doesn't record how much space is available. * For 1.0, we assume we can use up to the superblock * if before, else to 4K beyond superblock. * For others, assume no change is possible. */ if (mddev->minor_version > 0) mddev->bitmap_info.space = 0; else if (mddev->bitmap_info.offset > 0) mddev->bitmap_info.space = 8 - mddev->bitmap_info.offset; else mddev->bitmap_info.space = -mddev->bitmap_info.offset; } if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) { mddev->reshape_position = le64_to_cpu(sb->reshape_position); mddev->delta_disks = le32_to_cpu(sb->delta_disks); mddev->new_level = le32_to_cpu(sb->new_level); mddev->new_layout = le32_to_cpu(sb->new_layout); mddev->new_chunk_sectors = le32_to_cpu(sb->new_chunk); if (mddev->delta_disks < 0 || (mddev->delta_disks == 0 && (le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_BACKWARDS))) mddev->reshape_backwards = 1; } else { mddev->reshape_position = MaxSector; mddev->delta_disks = 0; mddev->new_level = mddev->level; mddev->new_layout = mddev->layout; mddev->new_chunk_sectors = mddev->chunk_sectors; } if (mddev->level == 0 && !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT)) mddev->layout = -1; if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) set_bit(MD_HAS_JOURNAL, &mddev->flags); if (le32_to_cpu(sb->feature_map) & (MD_FEATURE_PPL | MD_FEATURE_MULTIPLE_PPLS)) { if (le32_to_cpu(sb->feature_map) & (MD_FEATURE_BITMAP_OFFSET | MD_FEATURE_JOURNAL)) return -EINVAL; if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_PPL) && (le32_to_cpu(sb->feature_map) & MD_FEATURE_MULTIPLE_PPLS)) return -EINVAL; set_bit(MD_HAS_PPL, &mddev->flags); } } else if (mddev->pers == NULL) { /* Insist of good event counter while assembling, except for * spares (which don't need an event count). * Similar to mdadm, we allow event counter difference of 1 * from the freshest device. */ if (rdev->desc_nr >= 0 && rdev->desc_nr < le32_to_cpu(sb->max_dev) && (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX || le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL)) if (ev1 + 1 < mddev->events) return -EINVAL; } else if (mddev->bitmap) { /* If adding to array with a bitmap, then we can accept an * older device, but not too old. */ if (ev1 < md_bitmap_events_cleared(mddev)) return 0; if (ev1 < mddev->events) set_bit(Bitmap_sync, &rdev->flags); } else { if (ev1 < mddev->events) /* just a hot-add of a new device, leave raid_disk at -1 */ return 0; } if (rdev->desc_nr < 0 || rdev->desc_nr >= le32_to_cpu(sb->max_dev)) { role = MD_DISK_ROLE_SPARE; rdev->desc_nr = -1; } else if (mddev->pers == NULL && freshest && ev1 < mddev->events) { /* * If we are assembling, and our event counter is smaller than the * highest event counter, we cannot trust our superblock about the role. * It could happen that our rdev was marked as Faulty, and all other * superblocks were updated with +1 event counter. * Then, before the next superblock update, which typically happens when * remove_and_add_spares() removes the device from the array, there was * a crash or reboot. * If we allow current rdev without consulting the freshest superblock, * we could cause data corruption. * Note that in this case our event counter is smaller by 1 than the * highest, otherwise, this rdev would not be allowed into array; * both kernel and mdadm allow event counter difference of 1. */ struct mdp_superblock_1 *freshest_sb = page_address(freshest->sb_page); u32 freshest_max_dev = le32_to_cpu(freshest_sb->max_dev); if (rdev->desc_nr >= freshest_max_dev) { /* this is unexpected, better not proceed */ pr_warn("md: %s: rdev[%pg]: desc_nr(%d) >= freshest(%pg)->sb->max_dev(%u)\n", mdname(mddev), rdev->bdev, rdev->desc_nr, freshest->bdev, freshest_max_dev); return -EUCLEAN; } role = le16_to_cpu(freshest_sb->dev_roles[rdev->desc_nr]); pr_debug("md: %s: rdev[%pg]: role=%d(0x%x) according to freshest %pg\n", mdname(mddev), rdev->bdev, role, role, freshest->bdev); } else { role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); } switch (role) { case MD_DISK_ROLE_SPARE: /* spare */ break; case MD_DISK_ROLE_FAULTY: /* faulty */ set_bit(Faulty, &rdev->flags); break; case MD_DISK_ROLE_JOURNAL: /* journal device */ if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)) { /* journal device without journal feature */ pr_warn("md: journal device provided without journal feature, ignoring the device\n"); return -EINVAL; } set_bit(Journal, &rdev->flags); rdev->journal_tail = le64_to_cpu(sb->journal_tail); rdev->raid_disk = 0; break; default: rdev->saved_raid_disk = role; if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RECOVERY_OFFSET)) { rdev->recovery_offset = le64_to_cpu(sb->recovery_offset); if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_RECOVERY_BITMAP)) rdev->saved_raid_disk = -1; } else { /* * If the array is FROZEN, then the device can't * be in_sync with rest of array. */ if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) set_bit(In_sync, &rdev->flags); } rdev->raid_disk = role; break; } if (sb->devflags & WriteMostly1) set_bit(WriteMostly, &rdev->flags); if (sb->devflags & FailFast1) set_bit(FailFast, &rdev->flags); if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT) set_bit(Replacement, &rdev->flags); return 0; } static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev) { struct mdp_superblock_1 *sb; struct md_rdev *rdev2; int max_dev, i; /* make rdev->sb match mddev and rdev data. */ sb = page_address(rdev->sb_page); sb->feature_map = 0; sb->pad0 = 0; sb->recovery_offset = cpu_to_le64(0); memset(sb->pad3, 0, sizeof(sb->pad3)); sb->utime = cpu_to_le64((__u64)mddev->utime); sb->events = cpu_to_le64(mddev->events); if (mddev->in_sync) sb->resync_offset = cpu_to_le64(mddev->resync_offset); else if (test_bit(MD_JOURNAL_CLEAN, &mddev->flags)) sb->resync_offset = cpu_to_le64(MaxSector); else sb->resync_offset = cpu_to_le64(0); sb->cnt_corrected_read = cpu_to_le32(atomic_read(&rdev->corrected_errors)); sb->raid_disks = cpu_to_le32(mddev->raid_disks); sb->size = cpu_to_le64(mddev->dev_sectors); sb->chunksize = cpu_to_le32(mddev->chunk_sectors); sb->level = cpu_to_le32(mddev->level); sb->layout = cpu_to_le32(mddev->layout); sb->logical_block_size = cpu_to_le32(mddev->logical_block_size); if (test_bit(FailFast, &rdev->flags)) sb->devflags |= FailFast1; else sb->devflags &= ~FailFast1; if (test_bit(WriteMostly, &rdev->flags)) sb->devflags |= WriteMostly1; else sb->devflags &= ~WriteMostly1; sb->data_offset = cpu_to_le64(rdev->data_offset); sb->data_size = cpu_to_le64(rdev->sectors); if (mddev->bitmap && mddev->bitmap_info.file == NULL) { sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_info.offset); sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET); } if (rdev->raid_disk >= 0 && !test_bit(Journal, &rdev->flags) && !test_bit(In_sync, &rdev->flags)) { sb->feature_map |= cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET); sb->recovery_offset = cpu_to_le64(rdev->recovery_offset); if (rdev->saved_raid_disk >= 0 && mddev->bitmap) sb->feature_map |= cpu_to_le32(MD_FEATURE_RECOVERY_BITMAP); } /* Note: recovery_offset and journal_tail share space */ if (test_bit(Journal, &rdev->flags)) sb->journal_tail = cpu_to_le64(rdev->journal_tail); if (test_bit(Replacement, &rdev->flags)) sb->feature_map |= cpu_to_le32(MD_FEATURE_REPLACEMENT); if (mddev->reshape_position != MaxSector) { sb->feature_map |= cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE); sb->reshape_position = cpu_to_le64(mddev->reshape_position); sb->new_layout = cpu_to_le32(mddev->new_layout); sb->delta_disks = cpu_to_le32(mddev->delta_disks); sb->new_level = cpu_to_le32(mddev->new_level); sb->new_chunk = cpu_to_le32(mddev->new_chunk_sectors); if (mddev->delta_disks == 0 && mddev->reshape_backwards) sb->feature_map |= cpu_to_le32(MD_FEATURE_RESHAPE_BACKWARDS); if (rdev->new_data_offset != rdev->data_offset) { sb->feature_map |= cpu_to_le32(MD_FEATURE_NEW_OFFSET); sb->new_offset = cpu_to_le32((__u32)(rdev->new_data_offset - rdev->data_offset)); } } if (mddev_is_clustered(mddev)) sb->feature_map |= cpu_to_le32(MD_FEATURE_CLUSTERED); if (rdev->badblocks.count == 0) /* Nothing to do for bad blocks*/ ; else if (sb->bblog_offset == 0) /* Cannot record bad blocks on this device */ md_error(mddev, rdev); else { struct badblocks *bb = &rdev->badblocks; __le64 *bbp = (__le64 *)page_address(rdev->bb_page); u64 *p = bb->page; sb->feature_map |= cpu_to_le32(MD_FEATURE_BAD_BLOCKS); if (bb->changed) { unsigned seq; retry: seq = read_seqbegin(&bb->lock); memset(bbp, 0xff, PAGE_SIZE); for (i = 0 ; i < bb->count ; i++) { u64 internal_bb = p[i]; u64 store_bb = ((BB_OFFSET(internal_bb) << 10) | BB_LEN(internal_bb)); bbp[i] = cpu_to_le64(store_bb); } bb->changed = 0; if (read_seqretry(&bb->lock, seq)) goto retry; bb->sector = (rdev->sb_start + (int)le32_to_cpu(sb->bblog_offset)); bb->size = le16_to_cpu(sb->bblog_size); } } max_dev = 0; rdev_for_each(rdev2, mddev) if (rdev2->desc_nr+1 > max_dev) max_dev = rdev2->desc_nr+1; if (max_dev > le32_to_cpu(sb->max_dev)) { int bmask; sb->max_dev = cpu_to_le32(max_dev); rdev->sb_size = max_dev * 2 + 256; bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1; if (rdev->sb_size & bmask) rdev->sb_size = (rdev->sb_size | bmask) + 1; } else max_dev = le32_to_cpu(sb->max_dev); for (i=0; i<max_dev;i++) sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_SPARE); if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) sb->feature_map |= cpu_to_le32(MD_FEATURE_JOURNAL); if (test_bit(MD_HAS_PPL, &mddev->flags)) { if (test_bit(MD_HAS_MULTIPLE_PPLS, &mddev->flags)) sb->feature_map |= cpu_to_le32(MD_FEATURE_MULTIPLE_PPLS); else sb->feature_map |= cpu_to_le32(MD_FEATURE_PPL); sb->ppl.offset = cpu_to_le16(rdev->ppl.offset); sb->ppl.size = cpu_to_le16(rdev->ppl.size); } rdev_for_each(rdev2, mddev) { i = rdev2->desc_nr; if (test_bit(Faulty, &rdev2->flags)) sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_FAULTY); else if (test_bit(In_sync, &rdev2->flags)) sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk); else if (test_bit(Journal, &rdev2->flags)) sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_JOURNAL); else if (rdev2->raid_disk >= 0) sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk); else sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_SPARE); } sb->sb_csum = calc_sb_1_csum(sb); } static sector_t super_1_choose_bm_space(sector_t dev_size) { sector_t bm_space; /* if the device is bigger than 8Gig, save 64k for bitmap * usage, if bigger than 200Gig, save 128k */ if (dev_size < 64*2) bm_space = 0; else if (dev_size - 64*2 >= 200*1024*1024*2) bm_space = 128*2; else if (dev_size - 4*2 > 8*1024*1024*2) bm_space = 64*2; else bm_space = 4*2; return bm_space; } static unsigned long long super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) { struct mdp_superblock_1 *sb; sector_t max_sectors; if (num_sectors && num_sectors < rdev->mddev->dev_sectors) return 0; /* component must fit device */ if (rdev->data_offset != rdev->new_data_offset) return 0; /* too confusing */ if (rdev->sb_start < rdev->data_offset) { /* minor versions 1 and 2; superblock before data */ max_sectors = bdev_nr_sectors(rdev->bdev) - rdev->data_offset; if (!num_sectors || num_sectors > max_sectors) num_sectors = max_sectors; } else if (rdev->mddev->bitmap_info.offset) { /* minor version 0 with bitmap we can't move */ return 0; } else { /* minor version 0; superblock after data */ sector_t sb_start, bm_space; sector_t dev_size = bdev_nr_sectors(rdev->bdev); /* 8K is for superblock */ sb_start = dev_size - 8*2; sb_start &= ~(sector_t)(4*2 - 1); bm_space = super_1_choose_bm_space(dev_size); /* Space that can be used to store date needs to decrease * superblock bitmap space and bad block space(4K) */ max_sectors = sb_start - bm_space - 4*2; if (!num_sectors || num_sectors > max_sectors) num_sectors = max_sectors; rdev->sb_start = sb_start; } sb = page_address(rdev->sb_page); sb->data_size = cpu_to_le64(num_sectors); sb->super_offset = cpu_to_le64(rdev->sb_start); sb->sb_csum = calc_sb_1_csum(sb); do { md_write_metadata(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size, rdev->sb_page, 0); } while (md_super_wait(rdev->mddev) < 0); return num_sectors; } static int super_1_allow_new_offset(struct md_rdev *rdev, unsigned long long new_offset) { struct mddev *mddev = rdev->mddev; /* All necessary checks on new >= old have been done */ if (new_offset >= rdev->data_offset) return 1; /* with 1.0 metadata, there is no metadata to tread on * so we can always move back */ if (mddev->minor_version == 0) return 1; /* otherwise we must be sure not to step on * any metadata, so stay: * 36K beyond start of superblock * beyond end of badblocks * beyond write-intent bitmap */ if (rdev->sb_start + (32+4)*2 > new_offset) return 0; if (md_bitmap_registered(mddev) && !mddev->bitmap_info.file) { struct md_bitmap_stats stats; int err; err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats); if (!err && rdev->sb_start + mddev->bitmap_info.offset + stats.file_pages * (PAGE_SIZE >> 9) > new_offset) return 0; } if (rdev->badblocks.sector + rdev->badblocks.size > new_offset) return 0; return 1; } static struct super_type super_types[] = { [0] = { .name = "0.90.0", .owner = THIS_MODULE, .load_super = super_90_load, .validate_super = super_90_validate, .sync_super = super_90_sync, .rdev_size_change = super_90_rdev_size_change, .allow_new_offset = super_90_allow_new_offset, }, [1] = { .name = "md-1", .owner = THIS_MODULE, .load_super = super_1_load, .validate_super = super_1_validate, .sync_super = super_1_sync, .rdev_size_change = super_1_rdev_size_change, .allow_new_offset = super_1_allow_new_offset, }, }; static void sync_super(struct mddev *mddev, struct md_rdev *rdev) { if (mddev->sync_super) { mddev->sync_super(mddev, rdev); return; } BUG_ON(mddev->major_version >= ARRAY_SIZE(super_types)); super_types[mddev->major_version].sync_super(mddev, rdev); } static int match_mddev_units(struct mddev *mddev1, struct mddev *mddev2) { struct md_rdev *rdev, *rdev2; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev1) { if (test_bit(Faulty, &rdev->flags) || test_bit(Journal, &rdev->flags) || rdev->raid_disk == -1) continue; rdev_for_each_rcu(rdev2, mddev2) { if (test_bit(Faulty, &rdev2->flags) || test_bit(Journal, &rdev2->flags) || rdev2->raid_disk == -1) continue; if (rdev->bdev->bd_disk == rdev2->bdev->bd_disk) { rcu_read_unlock(); return 1; } } } rcu_read_unlock(); return 0; } static LIST_HEAD(pending_raid_disks); /* * Try to register data integrity profile for an mddev * * This is called when an array is started and after a disk has been kicked * from the array. It only succeeds if all working and active component devices * are integrity capable with matching profiles. */ int md_integrity_register(struct mddev *mddev) { if (list_empty(&mddev->disks)) return 0; /* nothing to do */ if (mddev_is_dm(mddev) || !blk_get_integrity(mddev->gendisk)) return 0; /* shouldn't register */ pr_debug("md: data integrity enabled on %s\n", mdname(mddev)); return 0; } EXPORT_SYMBOL(md_integrity_register); static bool rdev_read_only(struct md_rdev *rdev) { return bdev_read_only(rdev->bdev) || (rdev->meta_bdev && bdev_read_only(rdev->meta_bdev)); } static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) { char b[BDEVNAME_SIZE]; int err; /* prevent duplicates */ if (find_rdev(mddev, rdev->bdev->bd_dev)) return -EEXIST; if (rdev_read_only(rdev) && mddev->pers) return -EROFS; /* make sure rdev->sectors exceeds mddev->dev_sectors */ if (!test_bit(Journal, &rdev->flags) && rdev->sectors && (mddev->dev_sectors == 0 || rdev->sectors < mddev->dev_sectors)) { if (mddev->pers) { /* Cannot change size, so fail * If mddev->level <= 0, then we don't care * about aligning sizes (e.g. linear) */ if (mddev->level > 0) return -ENOSPC; } else mddev->dev_sectors = rdev->sectors; } /* Verify rdev->desc_nr is unique. * If it is -1, assign a free number, else * check number is not in use */ rcu_read_lock(); if (rdev->desc_nr < 0) { int choice = 0; if (mddev->pers) choice = mddev->raid_disks; while (md_find_rdev_nr_rcu(mddev, choice)) choice++; rdev->desc_nr = choice; } else { if (md_find_rdev_nr_rcu(mddev, rdev->desc_nr)) { rcu_read_unlock(); return -EBUSY; } } rcu_read_unlock(); if (!test_bit(Journal, &rdev->flags) && mddev->max_disks && rdev->desc_nr >= mddev->max_disks) { pr_warn("md: %s: array is limited to %d devices\n", mdname(mddev), mddev->max_disks); return -EBUSY; } snprintf(b, sizeof(b), "%pg", rdev->bdev); strreplace(b, '/', '!'); rdev->mddev = mddev; pr_debug("md: bind<%s>\n", b); if (mddev->raid_disks) mddev_create_serial_pool(mddev, rdev); if ((err = kobject_add(&rdev->kobj, &mddev->kobj, "dev-%s", b))) goto fail; /* failure here is OK */ err = sysfs_create_link(&rdev->kobj, bdev_kobj(rdev->bdev), "block"); rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state"); rdev->sysfs_unack_badblocks = sysfs_get_dirent_safe(rdev->kobj.sd, "unacknowledged_bad_blocks"); rdev->sysfs_badblocks = sysfs_get_dirent_safe(rdev->kobj.sd, "bad_blocks"); list_add_rcu(&rdev->same_set, &mddev->disks); bd_link_disk_holder(rdev->bdev, mddev->gendisk); return 0; fail: pr_warn("md: failed to register dev-%s for %s\n", b, mdname(mddev)); mddev_destroy_serial_pool(mddev, rdev); return err; } void md_autodetect_dev(dev_t dev); /* just for claiming the bdev */ static struct md_rdev claim_rdev; static void export_rdev(struct md_rdev *rdev) { pr_debug("md: export_rdev(%pg)\n", rdev->bdev); md_rdev_clear(rdev); #ifndef MODULE if (test_bit(AutoDetected, &rdev->flags)) md_autodetect_dev(rdev->bdev->bd_dev); #endif fput(rdev->bdev_file); rdev->bdev = NULL; kobject_put(&rdev->kobj); } static void md_kick_rdev_from_array(struct md_rdev *rdev) { struct mddev *mddev = rdev->mddev; bd_unlink_disk_holder(rdev->bdev, rdev->mddev->gendisk); list_del_rcu(&rdev->same_set); pr_debug("md: unbind<%pg>\n", rdev->bdev); mddev_destroy_serial_pool(rdev->mddev, rdev); WRITE_ONCE(rdev->mddev, NULL); sysfs_remove_link(&rdev->kobj, "block"); sysfs_put(rdev->sysfs_state); sysfs_put(rdev->sysfs_unack_badblocks); sysfs_put(rdev->sysfs_badblocks); rdev->sysfs_state = NULL; rdev->sysfs_unack_badblocks = NULL; rdev->sysfs_badblocks = NULL; rdev->badblocks.count = 0; synchronize_rcu(); /* * kobject_del() will wait for all in progress writers to be done, where * reconfig_mutex is held, hence it can't be called under * reconfig_mutex and it's delayed to mddev_unlock(). */ list_add(&rdev->same_set, &mddev->deleting); } static void export_array(struct mddev *mddev) { struct md_rdev *rdev; while (!list_empty(&mddev->disks)) { rdev = list_first_entry(&mddev->disks, struct md_rdev, same_set); md_kick_rdev_from_array(rdev); } mddev->raid_disks = 0; mddev->major_version = 0; } static bool set_in_sync(struct mddev *mddev) { lockdep_assert_held(&mddev->lock); if (!mddev->in_sync) { mddev->sync_checkers++; spin_unlock(&mddev->lock); percpu_ref_switch_to_atomic_sync(&mddev->writes_pending); spin_lock(&mddev->lock); if (!mddev->in_sync && percpu_ref_is_zero(&mddev->writes_pending)) { mddev->in_sync = 1; /* * Ensure ->in_sync is visible before we clear * ->sync_checkers. */ smp_mb(); set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags); sysfs_notify_dirent_safe(mddev->sysfs_state); } if (--mddev->sync_checkers == 0) percpu_ref_switch_to_percpu(&mddev->writes_pending); } if (mddev->safemode == 1) mddev->safemode = 0; return mddev->in_sync; } static void sync_sbs(struct mddev *mddev, int nospares) { /* Update each superblock (in-memory image), but * if we are allowed to, skip spares which already * have the right event counter, or have one earlier * (which would mean they aren't being marked as dirty * with the rest of the array) */ struct md_rdev *rdev; rdev_for_each(rdev, mddev) { if (rdev->sb_events == mddev->events || (nospares && rdev->raid_disk < 0 && rdev->sb_events+1 == mddev->events)) { /* Don't update this superblock */ rdev->sb_loaded = 2; } else { sync_super(mddev, rdev); rdev->sb_loaded = 1; } } } static bool does_sb_need_changing(struct mddev *mddev) { struct md_rdev *rdev = NULL, *iter; struct mdp_superblock_1 *sb; int role; /* Find a good rdev */ rdev_for_each(iter, mddev) if ((iter->raid_disk >= 0) && !test_bit(Faulty, &iter->flags)) { rdev = iter; break; } /* No good device found. */ if (!rdev) return false; sb = page_address(rdev->sb_page); /* Check if a device has become faulty or a spare become active */ rdev_for_each(rdev, mddev) { role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); /* Device activated? */ if (role == MD_DISK_ROLE_SPARE && rdev->raid_disk >= 0 && !test_bit(Faulty, &rdev->flags)) return true; /* Device turned faulty? */ if (test_bit(Faulty, &rdev->flags) && (role < MD_DISK_ROLE_MAX)) return true; } /* Check if any mddev parameters have changed */ if ((mddev->dev_sectors != le64_to_cpu(sb->size)) || (mddev->reshape_position != le64_to_cpu(sb->reshape_position)) || (mddev->layout != le32_to_cpu(sb->layout)) || (mddev->raid_disks != le32_to_cpu(sb->raid_disks)) || (mddev->chunk_sectors != le32_to_cpu(sb->chunksize))) return true; return false; } void md_update_sb(struct mddev *mddev, int force_change) { struct md_rdev *rdev; int sync_req; int nospares = 0; int any_badblocks_changed = 0; int ret = -1; if (!md_is_rdwr(mddev)) { if (force_change) set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); if (!mddev_is_dm(mddev)) pr_err_ratelimited("%s: can't update sb for read-only array %s\n", __func__, mdname(mddev)); return; } repeat: if (mddev_is_clustered(mddev)) { if (test_and_clear_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags)) force_change = 1; if (test_and_clear_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags)) nospares = 1; ret = mddev->cluster_ops->metadata_update_start(mddev); /* Has someone else has updated the sb */ if (!does_sb_need_changing(mddev)) { if (ret == 0) mddev->cluster_ops->metadata_update_cancel(mddev); bit_clear_unless(&mddev->sb_flags, BIT(MD_SB_CHANGE_PENDING), BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_CLEAN)); return; } } /* * First make sure individual recovery_offsets are correct * curr_resync_completed can only be used during recovery. * During reshape/resync it might use array-addresses rather * that device addresses. */ rdev_for_each(rdev, mddev) { if (rdev->raid_disk >= 0 && mddev->delta_disks >= 0 && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && test_bit(MD_RECOVERY_RECOVER, &mddev->recovery) && !test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && !test_bit(Journal, &rdev->flags) && !test_bit(In_sync, &rdev->flags) && mddev->curr_resync_completed > rdev->recovery_offset) rdev->recovery_offset = mddev->curr_resync_completed; } if (!mddev->persistent) { clear_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags); clear_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); if (!mddev->external) { clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags); rdev_for_each(rdev, mddev) { if (rdev->badblocks.changed) { rdev->badblocks.changed = 0; ack_all_badblocks(&rdev->badblocks); md_error(mddev, rdev); } clear_bit(Blocked, &rdev->flags); clear_bit(BlockedBadBlocks, &rdev->flags); wake_up(&rdev->blocked_wait); } } wake_up(&mddev->sb_wait); return; } spin_lock(&mddev->lock); mddev->utime = ktime_get_real_seconds(); if (test_and_clear_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags)) force_change = 1; if (test_and_clear_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags)) /* just a clean<-> dirty transition, possibly leave spares alone, * though if events isn't the right even/odd, we will have to do * spares after all */ nospares = 1; if (force_change) nospares = 0; if (mddev->degraded) /* If the array is degraded, then skipping spares is both * dangerous and fairly pointless. * Dangerous because a device that was removed from the array * might have a event_count that still looks up-to-date, * so it can be re-added without a resync. * Pointless because if there are any spares to skip, * then a recovery will happen and soon that array won't * be degraded any more and the spare can go back to sleep then. */ nospares = 0; sync_req = mddev->in_sync; /* If this is just a dirty<->clean transition, and the array is clean * and 'events' is odd, we can roll back to the previous clean state */ if (nospares && (mddev->in_sync && mddev->resync_offset == MaxSector) && mddev->can_decrease_events && mddev->events != 1) { mddev->events--; mddev->can_decrease_events = 0; } else { /* otherwise we have to go forward and ... */ mddev->events ++; mddev->can_decrease_events = nospares; } /* * This 64-bit counter should never wrap. * Either we are in around ~1 trillion A.C., assuming * 1 reboot per second, or we have a bug... */ WARN_ON(mddev->events == 0); rdev_for_each(rdev, mddev) { if (rdev->badblocks.changed) any_badblocks_changed++; if (test_bit(Faulty, &rdev->flags)) set_bit(FaultRecorded, &rdev->flags); } sync_sbs(mddev, nospares); spin_unlock(&mddev->lock); pr_debug("md: updating %s RAID superblock on device (in sync %d)\n", mdname(mddev), mddev->in_sync); mddev_add_trace_msg(mddev, "md md_update_sb"); rewrite: if (md_bitmap_enabled(mddev, false)) mddev->bitmap_ops->update_sb(mddev->bitmap); rdev_for_each(rdev, mddev) { if (rdev->sb_loaded != 1) continue; /* no noise on spare devices */ if (!test_bit(Faulty, &rdev->flags)) { md_write_metadata(mddev, rdev, rdev->sb_start, rdev->sb_size, rdev->sb_page, 0); pr_debug("md: (write) %pg's sb offset: %llu\n", rdev->bdev, (unsigned long long)rdev->sb_start); rdev->sb_events = mddev->events; if (rdev->badblocks.size) { md_write_metadata(mddev, rdev, rdev->badblocks.sector, rdev->badblocks.size << 9, rdev->bb_page, 0); rdev->badblocks.size = 0; } } else pr_debug("md: %pg (skipping faulty)\n", rdev->bdev); } if (md_super_wait(mddev) < 0) goto rewrite; /* if there was a failure, MD_SB_CHANGE_DEVS was set, and we re-write super */ if (mddev_is_clustered(mddev) && ret == 0) mddev->cluster_ops->metadata_update_finish(mddev); if (mddev->in_sync != sync_req || !bit_clear_unless(&mddev->sb_flags, BIT(MD_SB_CHANGE_PENDING), BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_CLEAN))) /* have to write it out again */ goto repeat; wake_up(&mddev->sb_wait); if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) sysfs_notify_dirent_safe(mddev->sysfs_completed); rdev_for_each(rdev, mddev) { if (test_and_clear_bit(FaultRecorded, &rdev->flags)) clear_bit(Blocked, &rdev->flags); if (any_badblocks_changed) ack_all_badblocks(&rdev->badblocks); clear_bit(BlockedBadBlocks, &rdev->flags); wake_up(&rdev->blocked_wait); } } EXPORT_SYMBOL(md_update_sb); static int add_bound_rdev(struct md_rdev *rdev) { struct mddev *mddev = rdev->mddev; int err = 0; bool add_journal = test_bit(Journal, &rdev->flags); if (!mddev->pers->hot_remove_disk || add_journal) { /* If there is hot_add_disk but no hot_remove_disk * then added disks for geometry changes, * and should be added immediately. */ super_types[mddev->major_version]. validate_super(mddev, NULL/*freshest*/, rdev); err = mddev->pers->hot_add_disk(mddev, rdev); if (err) { md_kick_rdev_from_array(rdev); return err; } } sysfs_notify_dirent_safe(rdev->sysfs_state); set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); if (mddev->degraded) set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_new_event(); return 0; } /* words written to sysfs files may, or may not, be \n terminated. * We want to accept with case. For this we use cmd_match. */ static int cmd_match(const char *cmd, const char *str) { /* See if cmd, written into a sysfs file, matches * str. They must either be the same, or cmd can * have a trailing newline */ while (*cmd && *str && *cmd == *str) { cmd++; str++; } if (*cmd == '\n') cmd++; if (*str || *cmd) return 0; return 1; } struct rdev_sysfs_entry { struct attribute attr; ssize_t (*show)(struct md_rdev *, char *); ssize_t (*store)(struct md_rdev *, const char *, size_t); }; static ssize_t state_show(struct md_rdev *rdev, char *page) { char *sep = ","; size_t len = 0; unsigned long flags = READ_ONCE(rdev->flags); if (test_bit(Faulty, &flags) || (!test_bit(ExternalBbl, &flags) && rdev->badblocks.unacked_exist)) len += sprintf(page+len, "faulty%s", sep); if (test_bit(In_sync, &flags)) len += sprintf(page+len, "in_sync%s", sep); if (test_bit(Journal, &flags)) len += sprintf(page+len, "journal%s", sep); if (test_bit(WriteMostly, &flags)) len += sprintf(page+len, "write_mostly%s", sep); if (test_bit(Blocked, &flags) || (rdev->badblocks.unacked_exist && !test_bit(Faulty, &flags))) len += sprintf(page+len, "blocked%s", sep); if (!test_bit(Faulty, &flags) && !test_bit(Journal, &flags) && !test_bit(In_sync, &flags)) len += sprintf(page+len, "spare%s", sep); if (test_bit(WriteErrorSeen, &flags)) len += sprintf(page+len, "write_error%s", sep); if (test_bit(WantReplacement, &flags)) len += sprintf(page+len, "want_replacement%s", sep); if (test_bit(Replacement, &flags)) len += sprintf(page+len, "replacement%s", sep); if (test_bit(ExternalBbl, &flags)) len += sprintf(page+len, "external_bbl%s", sep); if (test_bit(FailFast, &flags)) len += sprintf(page+len, "failfast%s", sep); if (len) len -= strlen(sep); return len+sprintf(page+len, "\n"); } static ssize_t state_store(struct md_rdev *rdev, const char *buf, size_t len) { /* can write * faulty - simulates an error * remove - disconnects the device * writemostly - sets write_mostly * -writemostly - clears write_mostly * blocked - sets the Blocked flags * -blocked - clears the Blocked and possibly simulates an error * insync - sets Insync providing device isn't active * -insync - clear Insync for a device with a slot assigned, * so that it gets rebuilt based on bitmap * write_error - sets WriteErrorSeen * -write_error - clears WriteErrorSeen * {,-}failfast - set/clear FailFast */ struct mddev *mddev = rdev->mddev; int err = -EINVAL; bool need_update_sb = false; if (cmd_match(buf, "faulty") && rdev->mddev->pers) { md_error(rdev->mddev, rdev); if (test_bit(MD_BROKEN, &rdev->mddev->flags)) err = -EBUSY; else err = 0; } else if (cmd_match(buf, "remove")) { if (rdev->mddev->pers) { clear_bit(Blocked, &rdev->flags); remove_and_add_spares(rdev->mddev, rdev); } if (rdev->raid_disk >= 0) err = -EBUSY; else { err = 0; if (mddev_is_clustered(mddev)) err = mddev->cluster_ops->remove_disk(mddev, rdev); if (err == 0) { md_kick_rdev_from_array(rdev); if (mddev->pers) set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); md_new_event(); } } } else if (cmd_match(buf, "writemostly")) { set_bit(WriteMostly, &rdev->flags); mddev_create_serial_pool(rdev->mddev, rdev); need_update_sb = true; err = 0; } else if (cmd_match(buf, "-writemostly")) { mddev_destroy_serial_pool(rdev->mddev, rdev); clear_bit(WriteMostly, &rdev->flags); need_update_sb = true; err = 0; } else if (cmd_match(buf, "blocked")) { set_bit(Blocked, &rdev->flags); err = 0; } else if (cmd_match(buf, "-blocked")) { if (!test_bit(Faulty, &rdev->flags) && !test_bit(ExternalBbl, &rdev->flags) && rdev->badblocks.unacked_exist) { /* metadata handler doesn't understand badblocks, * so we need to fail the device */ md_error(rdev->mddev, rdev); } clear_bit(Blocked, &rdev->flags); clear_bit(BlockedBadBlocks, &rdev->flags); wake_up(&rdev->blocked_wait); set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); err = 0; } else if (cmd_match(buf, "insync") && rdev->raid_disk == -1) { set_bit(In_sync, &rdev->flags); err = 0; } else if (cmd_match(buf, "failfast")) { set_bit(FailFast, &rdev->flags); need_update_sb = true; err = 0; } else if (cmd_match(buf, "-failfast")) { clear_bit(FailFast, &rdev->flags); need_update_sb = true; err = 0; } else if (cmd_match(buf, "-insync") && rdev->raid_disk >= 0 && !test_bit(Journal, &rdev->flags)) { if (rdev->mddev->pers == NULL) { clear_bit(In_sync, &rdev->flags); rdev->saved_raid_disk = rdev->raid_disk; rdev->raid_disk = -1; err = 0; } } else if (cmd_match(buf, "write_error")) { set_bit(WriteErrorSeen, &rdev->flags); err = 0; } else if (cmd_match(buf, "-write_error")) { clear_bit(WriteErrorSeen, &rdev->flags); err = 0; } else if (cmd_match(buf, "want_replacement")) { /* Any non-spare device that is not a replacement can * become want_replacement at any time, but we then need to * check if recovery is needed. */ if (rdev->raid_disk >= 0 && !test_bit(Journal, &rdev->flags) && !test_bit(Replacement, &rdev->flags)) set_bit(WantReplacement, &rdev->flags); set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); err = 0; } else if (cmd_match(buf, "-want_replacement")) { /* Clearing 'want_replacement' is always allowed. * Once replacements starts it is too late though. */ err = 0; clear_bit(WantReplacement, &rdev->flags); } else if (cmd_match(buf, "replacement")) { /* Can only set a device as a replacement when array has not * yet been started. Once running, replacement is automatic * from spares, or by assigning 'slot'. */ if (rdev->mddev->pers) err = -EBUSY; else { set_bit(Replacement, &rdev->flags); err = 0; } } else if (cmd_match(buf, "-replacement")) { /* Similarly, can only clear Replacement before start */ if (rdev->mddev->pers) err = -EBUSY; else { clear_bit(Replacement, &rdev->flags); err = 0; } } else if (cmd_match(buf, "re-add")) { if (!rdev->mddev->pers) err = -EINVAL; else if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1) && rdev->saved_raid_disk >= 0) { /* clear_bit is performed _after_ all the devices * have their local Faulty bit cleared. If any writes * happen in the meantime in the local node, they * will land in the local bitmap, which will be synced * by this node eventually */ if (!mddev_is_clustered(rdev->mddev) || (err = mddev->cluster_ops->gather_bitmaps(rdev)) == 0) { clear_bit(Faulty, &rdev->flags); err = add_bound_rdev(rdev); } } else err = -EBUSY; } else if (cmd_match(buf, "external_bbl") && (rdev->mddev->external)) { set_bit(ExternalBbl, &rdev->flags); rdev->badblocks.shift = 0; err = 0; } else if (cmd_match(buf, "-external_bbl") && (rdev->mddev->external)) { clear_bit(ExternalBbl, &rdev->flags); err = 0; } if (need_update_sb) md_update_sb(mddev, 1); if (!err) sysfs_notify_dirent_safe(rdev->sysfs_state); return err ? err : len; } static struct rdev_sysfs_entry rdev_state = __ATTR_PREALLOC(state, S_IRUGO|S_IWUSR, state_show, state_store); static ssize_t errors_show(struct md_rdev *rdev, char *page) { return sprintf(page, "%d\n", atomic_read(&rdev->corrected_errors)); } static ssize_t errors_store(struct md_rdev *rdev, const char *buf, size_t len) { unsigned int n; int rv; rv = kstrtouint(buf, 10, &n); if (rv < 0) return rv; atomic_set(&rdev->corrected_errors, n); return len; } static struct rdev_sysfs_entry rdev_errors = __ATTR(errors, S_IRUGO|S_IWUSR, errors_show, errors_store); static ssize_t slot_show(struct md_rdev *rdev, char *page) { if (test_bit(Journal, &rdev->flags)) return sprintf(page, "journal\n"); else if (rdev->raid_disk < 0) return sprintf(page, "none\n"); else return sprintf(page, "%d\n", rdev->raid_disk); } static ssize_t slot_store(struct md_rdev *rdev, const char *buf, size_t len) { int slot; int err; if (test_bit(Journal, &rdev->flags)) return -EBUSY; if (strncmp(buf, "none", 4)==0) slot = -1; else { err = kstrtouint(buf, 10, (unsigned int *)&slot); if (err < 0) return err; if (slot < 0) /* overflow */ return -ENOSPC; } if (rdev->mddev->pers && slot == -1) { /* Setting 'slot' on an active array requires also * updating the 'rd%d' link, and communicating * with the personality with ->hot_*_disk. * For now we only support removing * failed/spare devices. This normally happens automatically, * but not when the metadata is externally managed. */ if (rdev->raid_disk == -1) return -EEXIST; /* personality does all needed checks */ if (rdev->mddev->pers->hot_remove_disk == NULL) return -EINVAL; clear_bit(Blocked, &rdev->flags); remove_and_add_spares(rdev->mddev, rdev); if (rdev->raid_disk >= 0) return -EBUSY; set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); } else if (rdev->mddev->pers) { /* Activating a spare .. or possibly reactivating * if we ever get bitmaps working here. */ int err; if (rdev->raid_disk != -1) return -EBUSY; if (test_bit(MD_RECOVERY_RUNNING, &rdev->mddev->recovery)) return -EBUSY; if (rdev->mddev->pers->hot_add_disk == NULL) return -EINVAL; if (slot >= rdev->mddev->raid_disks && slot >= rdev->mddev->raid_disks + rdev->mddev->delta_disks) return -ENOSPC; rdev->raid_disk = slot; if (test_bit(In_sync, &rdev->flags)) rdev->saved_raid_disk = slot; else rdev->saved_raid_disk = -1; clear_bit(In_sync, &rdev->flags); clear_bit(Bitmap_sync, &rdev->flags); err = rdev->mddev->pers->hot_add_disk(rdev->mddev, rdev); if (err) { rdev->raid_disk = -1; return err; } else sysfs_notify_dirent_safe(rdev->sysfs_state); /* failure here is OK */; sysfs_link_rdev(rdev->mddev, rdev); /* don't wakeup anyone, leave that to userspace. */ } else { if (slot >= rdev->mddev->raid_disks && slot >= rdev->mddev->raid_disks + rdev->mddev->delta_disks) return -ENOSPC; rdev->raid_disk = slot; /* assume it is working */ clear_bit(Faulty, &rdev->flags); clear_bit(WriteMostly, &rdev->flags); set_bit(In_sync, &rdev->flags); sysfs_notify_dirent_safe(rdev->sysfs_state); } return len; } static struct rdev_sysfs_entry rdev_slot = __ATTR(slot, S_IRUGO|S_IWUSR, slot_show, slot_store); static ssize_t offset_show(struct md_rdev *rdev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)rdev->data_offset); } static ssize_t offset_store(struct md_rdev *rdev, const char *buf, size_t len) { unsigned long long offset; if (kstrtoull(buf, 10, &offset) < 0) return -EINVAL; if (rdev->mddev->pers && rdev->raid_disk >= 0) return -EBUSY; if (rdev->sectors && rdev->mddev->external) /* Must set offset before size, so overlap checks * can be sane */ return -EBUSY; rdev->data_offset = offset; rdev->new_data_offset = offset; return len; } static struct rdev_sysfs_entry rdev_offset = __ATTR(offset, S_IRUGO|S_IWUSR, offset_show, offset_store); static ssize_t new_offset_show(struct md_rdev *rdev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)rdev->new_data_offset); } static ssize_t new_offset_store(struct md_rdev *rdev, const char *buf, size_t len) { unsigned long long new_offset; struct mddev *mddev = rdev->mddev; if (kstrtoull(buf, 10, &new_offset) < 0) return -EINVAL; if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return -EBUSY; if (new_offset == rdev->data_offset) /* reset is always permitted */ ; else if (new_offset > rdev->data_offset) { /* must not push array size beyond rdev_sectors */ if (new_offset - rdev->data_offset + mddev->dev_sectors > rdev->sectors) return -E2BIG; } /* Metadata worries about other space details. */ /* decreasing the offset is inconsistent with a backwards * reshape. */ if (new_offset < rdev->data_offset && mddev->reshape_backwards) return -EINVAL; /* Increasing offset is inconsistent with forwards * reshape. reshape_direction should be set to * 'backwards' first. */ if (new_offset > rdev->data_offset && !mddev->reshape_backwards) return -EINVAL; if (mddev->pers && mddev->persistent && !super_types[mddev->major_version] .allow_new_offset(rdev, new_offset)) return -E2BIG; rdev->new_data_offset = new_offset; if (new_offset > rdev->data_offset) mddev->reshape_backwards = 1; else if (new_offset < rdev->data_offset) mddev->reshape_backwards = 0; return len; } static struct rdev_sysfs_entry rdev_new_offset = __ATTR(new_offset, S_IRUGO|S_IWUSR, new_offset_show, new_offset_store); static ssize_t rdev_size_show(struct md_rdev *rdev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)rdev->sectors / 2); } static int md_rdevs_overlap(struct md_rdev *a, struct md_rdev *b) { /* check if two start/length pairs overlap */ if (a->data_offset + a->sectors <= b->data_offset) return false; if (b->data_offset + b->sectors <= a->data_offset) return false; return true; } static bool md_rdev_overlaps(struct md_rdev *rdev) { struct mddev *mddev; struct md_rdev *rdev2; spin_lock(&all_mddevs_lock); list_for_each_entry(mddev, &all_mddevs, all_mddevs) { if (test_bit(MD_DELETED, &mddev->flags)) continue; rdev_for_each(rdev2, mddev) { if (rdev != rdev2 && rdev->bdev == rdev2->bdev && md_rdevs_overlap(rdev, rdev2)) { spin_unlock(&all_mddevs_lock); return true; } } } spin_unlock(&all_mddevs_lock); return false; } static int strict_blocks_to_sectors(const char *buf, sector_t *sectors) { unsigned long long blocks; sector_t new; if (kstrtoull(buf, 10, &blocks) < 0) return -EINVAL; if (blocks & 1ULL << (8 * sizeof(blocks) - 1)) return -EINVAL; /* sector conversion overflow */ new = blocks * 2; if (new != blocks * 2) return -EINVAL; /* unsigned long long to sector_t overflow */ *sectors = new; return 0; } static ssize_t rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len) { struct mddev *my_mddev = rdev->mddev; sector_t oldsectors = rdev->sectors; sector_t sectors; if (test_bit(Journal, &rdev->flags)) return -EBUSY; if (strict_blocks_to_sectors(buf, §ors) < 0) return -EINVAL; if (rdev->data_offset != rdev->new_data_offset) return -EINVAL; /* too confusing */ if (my_mddev->pers && rdev->raid_disk >= 0) { if (my_mddev->persistent) { sectors = super_types[my_mddev->major_version]. rdev_size_change(rdev, sectors); if (!sectors) return -EBUSY; } else if (!sectors) sectors = bdev_nr_sectors(rdev->bdev) - rdev->data_offset; if (!my_mddev->pers->resize) /* Cannot change size for RAID0 or Linear etc */ return -EINVAL; } if (sectors < my_mddev->dev_sectors) return -EINVAL; /* component must fit device */ rdev->sectors = sectors; /* * Check that all other rdevs with the same bdev do not overlap. This * check does not provide a hard guarantee, it just helps avoid * dangerous mistakes. */ if (sectors > oldsectors && my_mddev->external && md_rdev_overlaps(rdev)) { /* * Someone else could have slipped in a size change here, but * doing so is just silly. We put oldsectors back because we * know it is safe, and trust userspace not to race with itself. */ rdev->sectors = oldsectors; return -EBUSY; } return len; } static struct rdev_sysfs_entry rdev_size = __ATTR(size, S_IRUGO|S_IWUSR, rdev_size_show, rdev_size_store); static ssize_t recovery_start_show(struct md_rdev *rdev, char *page) { unsigned long long recovery_start = rdev->recovery_offset; if (test_bit(In_sync, &rdev->flags) || recovery_start == MaxSector) return sprintf(page, "none\n"); return sprintf(page, "%llu\n", recovery_start); } static ssize_t recovery_start_store(struct md_rdev *rdev, const char *buf, size_t len) { unsigned long long recovery_start; if (cmd_match(buf, "none")) recovery_start = MaxSector; else if (kstrtoull(buf, 10, &recovery_start)) return -EINVAL; if (rdev->mddev->pers && rdev->raid_disk >= 0) return -EBUSY; rdev->recovery_offset = recovery_start; if (recovery_start == MaxSector) set_bit(In_sync, &rdev->flags); else clear_bit(In_sync, &rdev->flags); return len; } static struct rdev_sysfs_entry rdev_recovery_start = __ATTR(recovery_start, S_IRUGO|S_IWUSR, recovery_start_show, recovery_start_store); /* sysfs access to bad-blocks list. * We present two files. * 'bad-blocks' lists sector numbers and lengths of ranges that * are recorded as bad. The list is truncated to fit within * the one-page limit of sysfs. * Writing "sector length" to this file adds an acknowledged * bad block list. * 'unacknowledged-bad-blocks' lists bad blocks that have not yet * been acknowledged. Writing to this file adds bad blocks * without acknowledging them. This is largely for testing. */ static ssize_t bb_show(struct md_rdev *rdev, char *page) { return badblocks_show(&rdev->badblocks, page, 0); } static ssize_t bb_store(struct md_rdev *rdev, const char *page, size_t len) { int rv = badblocks_store(&rdev->badblocks, page, len, 0); /* Maybe that ack was all we needed */ if (test_and_clear_bit(BlockedBadBlocks, &rdev->flags)) wake_up(&rdev->blocked_wait); return rv; } static struct rdev_sysfs_entry rdev_bad_blocks = __ATTR(bad_blocks, S_IRUGO|S_IWUSR, bb_show, bb_store); static ssize_t ubb_show(struct md_rdev *rdev, char *page) { return badblocks_show(&rdev->badblocks, page, 1); } static ssize_t ubb_store(struct md_rdev *rdev, const char *page, size_t len) { return badblocks_store(&rdev->badblocks, page, len, 1); } static struct rdev_sysfs_entry rdev_unack_bad_blocks = __ATTR(unacknowledged_bad_blocks, S_IRUGO|S_IWUSR, ubb_show, ubb_store); static ssize_t ppl_sector_show(struct md_rdev *rdev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)rdev->ppl.sector); } static ssize_t ppl_sector_store(struct md_rdev *rdev, const char *buf, size_t len) { unsigned long long sector; if (kstrtoull(buf, 10, §or) < 0) return -EINVAL; if (sector != (sector_t)sector) return -EINVAL; if (rdev->mddev->pers && test_bit(MD_HAS_PPL, &rdev->mddev->flags) && rdev->raid_disk >= 0) return -EBUSY; if (rdev->mddev->persistent) { if (rdev->mddev->major_version == 0) return -EINVAL; if ((sector > rdev->sb_start && sector - rdev->sb_start > S16_MAX) || (sector < rdev->sb_start && rdev->sb_start - sector > -S16_MIN)) return -EINVAL; rdev->ppl.offset = sector - rdev->sb_start; } else if (!rdev->mddev->external) { return -EBUSY; } rdev->ppl.sector = sector; return len; } static struct rdev_sysfs_entry rdev_ppl_sector = __ATTR(ppl_sector, S_IRUGO|S_IWUSR, ppl_sector_show, ppl_sector_store); static ssize_t ppl_size_show(struct md_rdev *rdev, char *page) { return sprintf(page, "%u\n", rdev->ppl.size); } static ssize_t ppl_size_store(struct md_rdev *rdev, const char *buf, size_t len) { unsigned int size; if (kstrtouint(buf, 10, &size) < 0) return -EINVAL; if (rdev->mddev->pers && test_bit(MD_HAS_PPL, &rdev->mddev->flags) && rdev->raid_disk >= 0) return -EBUSY; if (rdev->mddev->persistent) { if (rdev->mddev->major_version == 0) return -EINVAL; if (size > U16_MAX) return -EINVAL; } else if (!rdev->mddev->external) { return -EBUSY; } rdev->ppl.size = size; return len; } static struct rdev_sysfs_entry rdev_ppl_size = __ATTR(ppl_size, S_IRUGO|S_IWUSR, ppl_size_show, ppl_size_store); static struct attribute *rdev_default_attrs[] = { &rdev_state.attr, &rdev_errors.attr, &rdev_slot.attr, &rdev_offset.attr, &rdev_new_offset.attr, &rdev_size.attr, &rdev_recovery_start.attr, &rdev_bad_blocks.attr, &rdev_unack_bad_blocks.attr, &rdev_ppl_sector.attr, &rdev_ppl_size.attr, NULL, }; ATTRIBUTE_GROUPS(rdev_default); static ssize_t rdev_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr); struct md_rdev *rdev = container_of(kobj, struct md_rdev, kobj); if (!entry->show) return -EIO; if (!rdev->mddev) return -ENODEV; return entry->show(rdev, page); } static ssize_t rdev_attr_store(struct kobject *kobj, struct attribute *attr, const char *page, size_t length) { struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr); struct md_rdev *rdev = container_of(kobj, struct md_rdev, kobj); struct kernfs_node *kn = NULL; bool suspend = false; ssize_t rv; struct mddev *mddev = READ_ONCE(rdev->mddev); if (!entry->store) return -EIO; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (!mddev) return -ENODEV; if (entry->store == state_store) { if (cmd_match(page, "remove")) kn = sysfs_break_active_protection(kobj, attr); if (cmd_match(page, "remove") || cmd_match(page, "re-add") || cmd_match(page, "writemostly") || cmd_match(page, "-writemostly")) suspend = true; } rv = suspend ? mddev_suspend_and_lock(mddev) : mddev_lock(mddev); if (!rv) { if (rdev->mddev == NULL) rv = -ENODEV; else rv = entry->store(rdev, page, length); suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev); } if (kn) sysfs_unbreak_active_protection(kn); return rv; } static void rdev_free(struct kobject *ko) { struct md_rdev *rdev = container_of(ko, struct md_rdev, kobj); kfree(rdev); } static const struct sysfs_ops rdev_sysfs_ops = { .show = rdev_attr_show, .store = rdev_attr_store, }; static const struct kobj_type rdev_ktype = { .release = rdev_free, .sysfs_ops = &rdev_sysfs_ops, .default_groups = rdev_default_groups, }; int md_rdev_init(struct md_rdev *rdev) { rdev->desc_nr = -1; rdev->saved_raid_disk = -1; rdev->raid_disk = -1; rdev->flags = 0; rdev->data_offset = 0; rdev->new_data_offset = 0; rdev->sb_events = 0; rdev->last_read_error = 0; rdev->sb_loaded = 0; rdev->bb_page = NULL; atomic_set(&rdev->nr_pending, 0); atomic_set(&rdev->read_errors, 0); atomic_set(&rdev->corrected_errors, 0); INIT_LIST_HEAD(&rdev->same_set); init_waitqueue_head(&rdev->blocked_wait); /* Add space to store bad block list. * This reserves the space even on arrays where it cannot * be used - I wonder if that matters */ return badblocks_init(&rdev->badblocks, 0); } EXPORT_SYMBOL_GPL(md_rdev_init); /* * Import a device. If 'super_format' >= 0, then sanity check the superblock * * mark the device faulty if: * * - the device is nonexistent (zero size) * - the device has no valid superblock * * a faulty rdev _never_ has rdev->sb set. */ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor) { struct md_rdev *rdev; sector_t size; int err; rdev = kzalloc_obj(*rdev); if (!rdev) return ERR_PTR(-ENOMEM); err = md_rdev_init(rdev); if (err) goto out_free_rdev; err = alloc_disk_sb(rdev); if (err) goto out_clear_rdev; rdev->bdev_file = bdev_file_open_by_dev(newdev, BLK_OPEN_READ | BLK_OPEN_WRITE, super_format == -2 ? &claim_rdev : rdev, NULL); if (IS_ERR(rdev->bdev_file)) { pr_warn("md: could not open device unknown-block(%u,%u).\n", MAJOR(newdev), MINOR(newdev)); err = PTR_ERR(rdev->bdev_file); goto out_clear_rdev; } rdev->bdev = file_bdev(rdev->bdev_file); kobject_init(&rdev->kobj, &rdev_ktype); size = bdev_nr_bytes(rdev->bdev) >> BLOCK_SIZE_BITS; if (!size) { pr_warn("md: %pg has zero or unknown size, marking faulty!\n", rdev->bdev); err = -EINVAL; goto out_blkdev_put; } if (super_format >= 0) { err = super_types[super_format]. load_super(rdev, NULL, super_minor); if (err == -EINVAL) { pr_warn("md: %pg does not have a valid v%d.%d superblock, not importing!\n", rdev->bdev, super_format, super_minor); goto out_blkdev_put; } if (err < 0) { pr_warn("md: could not read %pg's sb, not importing!\n", rdev->bdev); goto out_blkdev_put; } } return rdev; out_blkdev_put: fput(rdev->bdev_file); out_clear_rdev: md_rdev_clear(rdev); out_free_rdev: kfree(rdev); return ERR_PTR(err); } /* * Check a full RAID array for plausibility */ static int analyze_sbs(struct mddev *mddev) { struct md_rdev *rdev, *freshest, *tmp; freshest = NULL; rdev_for_each_safe(rdev, tmp, mddev) switch (super_types[mddev->major_version]. load_super(rdev, freshest, mddev->minor_version)) { case 1: freshest = rdev; break; case 0: break; default: pr_warn("md: fatal superblock inconsistency in %pg -- removing from array\n", rdev->bdev); md_kick_rdev_from_array(rdev); } /* Cannot find a valid fresh disk */ if (!freshest) { pr_warn("md: cannot find a valid disk\n"); return -EINVAL; } super_types[mddev->major_version]. validate_super(mddev, NULL/*freshest*/, freshest); rdev_for_each_safe(rdev, tmp, mddev) { if (mddev->max_disks && rdev->desc_nr >= mddev->max_disks) { pr_warn("md: %s: %pg: only %d devices permitted\n", mdname(mddev), rdev->bdev, mddev->max_disks); md_kick_rdev_from_array(rdev); continue; } if (rdev != freshest) { if (super_types[mddev->major_version]. validate_super(mddev, freshest, rdev)) { pr_warn("md: kicking non-fresh %pg from array!\n", rdev->bdev); md_kick_rdev_from_array(rdev); continue; } } if (rdev->raid_disk >= (mddev->raid_disks - min(0, mddev->delta_disks)) && !test_bit(Journal, &rdev->flags)) { rdev->raid_disk = -1; clear_bit(In_sync, &rdev->flags); } } return 0; } /* Read a fixed-point number. * Numbers in sysfs attributes should be in "standard" units where * possible, so time should be in seconds. * However we internally use a a much smaller unit such as * milliseconds or jiffies. * This function takes a decimal number with a possible fractional * component, and produces an integer which is the result of * multiplying that number by 10^'scale'. * all without any floating-point arithmetic. */ int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale) { unsigned long result = 0; long decimals = -1; while (isdigit(*cp) || (*cp == '.' && decimals < 0)) { if (*cp == '.') decimals = 0; else if (decimals < scale) { unsigned int value; value = *cp - '0'; result = result * 10 + value; if (decimals >= 0) decimals++; } cp++; } if (*cp == '\n') cp++; if (*cp) return -EINVAL; if (decimals < 0) decimals = 0; *res = result * int_pow(10, scale - decimals); return 0; } static ssize_t safe_delay_show(struct mddev *mddev, char *page) { unsigned int msec = ((unsigned long)mddev->safemode_delay*1000)/HZ; return sprintf(page, "%u.%03u\n", msec/1000, msec%1000); } static ssize_t safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len) { unsigned long msec; if (mddev_is_clustered(mddev)) { pr_warn("md: Safemode is disabled for clustered mode\n"); return -EINVAL; } if (strict_strtoul_scaled(cbuf, &msec, 3) < 0 || msec > UINT_MAX / HZ) return -EINVAL; if (msec == 0) mddev->safemode_delay = 0; else { unsigned long old_delay = mddev->safemode_delay; unsigned long new_delay = (msec*HZ)/1000; if (new_delay == 0) new_delay = 1; mddev->safemode_delay = new_delay; if (new_delay < old_delay || old_delay == 0) mod_timer(&mddev->safemode_timer, jiffies+1); } return len; } static struct md_sysfs_entry md_safe_delay = __ATTR(safe_mode_delay, S_IRUGO|S_IWUSR,safe_delay_show, safe_delay_store); static ssize_t level_show(struct mddev *mddev, char *page) { struct md_personality *p; int ret; spin_lock(&mddev->lock); p = mddev->pers; if (p) ret = sprintf(page, "%s\n", p->head.name); else if (mddev->clevel[0]) ret = sprintf(page, "%s\n", mddev->clevel); else if (mddev->level != LEVEL_NONE) ret = sprintf(page, "%d\n", mddev->level); else ret = 0; spin_unlock(&mddev->lock); return ret; } static ssize_t level_store(struct mddev *mddev, const char *buf, size_t len) { char clevel[16]; ssize_t rv; size_t slen = len; struct md_personality *pers, *oldpers; long level; void *priv, *oldpriv; struct md_rdev *rdev; if (slen == 0 || slen >= sizeof(clevel)) return -EINVAL; rv = mddev_suspend_and_lock(mddev); if (rv) return rv; if (mddev->pers == NULL) { memcpy(mddev->clevel, buf, slen); if (mddev->clevel[slen-1] == '\n') slen--; mddev->clevel[slen] = 0; mddev->level = LEVEL_NONE; rv = len; goto out_unlock; } rv = -EROFS; if (!md_is_rdwr(mddev)) goto out_unlock; /* request to change the personality. Need to ensure: * - array is not engaged in resync/recovery/reshape * - old personality can be suspended * - new personality will access other array. */ rv = -EBUSY; if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || mddev->reshape_position != MaxSector || mddev->sysfs_active) goto out_unlock; rv = -EINVAL; if (!mddev->pers->quiesce) { pr_warn("md: %s: %s does not support online personality change\n", mdname(mddev), mddev->pers->head.name); goto out_unlock; } /* Now find the new personality */ memcpy(clevel, buf, slen); if (clevel[slen-1] == '\n') slen--; clevel[slen] = 0; if (kstrtol(clevel, 10, &level)) level = LEVEL_NONE; if (request_module("md-%s", clevel) != 0) request_module("md-level-%s", clevel); pers = get_pers(level, clevel); if (!pers) { rv = -EINVAL; goto out_unlock; } if (pers == mddev->pers) { /* Nothing to do! */ put_pers(pers); rv = len; goto out_unlock; } if (!pers->takeover) { put_pers(pers); pr_warn("md: %s: %s does not support personality takeover\n", mdname(mddev), clevel); rv = -EINVAL; goto out_unlock; } rdev_for_each(rdev, mddev) rdev->new_raid_disk = rdev->raid_disk; /* ->takeover must set new_* and/or delta_disks * if it succeeds, and may set them when it fails. */ priv = pers->takeover(mddev); if (IS_ERR(priv)) { mddev->new_level = mddev->level; mddev->new_layout = mddev->layout; mddev->new_chunk_sectors = mddev->chunk_sectors; mddev->raid_disks -= mddev->delta_disks; mddev->delta_disks = 0; mddev->reshape_backwards = 0; put_pers(pers); pr_warn("md: %s: %s would not accept array\n", mdname(mddev), clevel); rv = PTR_ERR(priv); goto out_unlock; } /* Looks like we have a winner */ mddev_detach(mddev); spin_lock(&mddev->lock); oldpers = mddev->pers; oldpriv = mddev->private; mddev->pers = pers; mddev->private = priv; strscpy(mddev->clevel, pers->head.name, sizeof(mddev->clevel)); mddev->level = mddev->new_level; mddev->layout = mddev->new_layout; mddev->chunk_sectors = mddev->new_chunk_sectors; mddev->delta_disks = 0; mddev->reshape_backwards = 0; mddev->degraded = 0; spin_unlock(&mddev->lock); if (oldpers->sync_request == NULL && mddev->external) { /* We are converting from a no-redundancy array * to a redundancy array and metadata is managed * externally so we need to be sure that writes * won't block due to a need to transition * clean->dirty * until external management is started. */ mddev->in_sync = 0; mddev->safemode_delay = 0; mddev->safemode = 0; } oldpers->free(mddev, oldpriv); if (oldpers->sync_request == NULL && pers->sync_request != NULL) { /* need to add the md_redundancy_group */ if (sysfs_create_group(&mddev->kobj, &md_redundancy_group)) pr_warn("md: cannot register extra attributes for %s\n", mdname(mddev)); mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, "sync_action"); mddev->sysfs_completed = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_completed"); mddev->sysfs_degraded = sysfs_get_dirent_safe(mddev->kobj.sd, "degraded"); } if (oldpers->sync_request != NULL && pers->sync_request == NULL) { /* need to remove the md_redundancy_group */ if (mddev->to_remove == NULL) mddev->to_remove = &md_redundancy_group; } put_pers(oldpers); rdev_for_each(rdev, mddev) { if (rdev->raid_disk < 0) continue; if (rdev->new_raid_disk >= mddev->raid_disks) rdev->new_raid_disk = -1; if (rdev->new_raid_disk == rdev->raid_disk) continue; sysfs_unlink_rdev(mddev, rdev); } rdev_for_each(rdev, mddev) { if (rdev->raid_disk < 0) continue; if (rdev->new_raid_disk == rdev->raid_disk) continue; rdev->raid_disk = rdev->new_raid_disk; if (rdev->raid_disk < 0) clear_bit(In_sync, &rdev->flags); else { if (sysfs_link_rdev(mddev, rdev)) pr_warn("md: cannot register rd%d for %s after level change\n", rdev->raid_disk, mdname(mddev)); } } if (pers->sync_request == NULL) { /* this is now an array without redundancy, so * it must always be in_sync */ mddev->in_sync = 1; timer_delete_sync(&mddev->safemode_timer); } pers->run(mddev); set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); if (!mddev->thread) md_update_sb(mddev, 1); sysfs_notify_dirent_safe(mddev->sysfs_level); md_new_event(); rv = len; out_unlock: mddev_unlock_and_resume(mddev); return rv; } static struct md_sysfs_entry md_level = __ATTR(level, S_IRUGO|S_IWUSR, level_show, level_store); static ssize_t new_level_show(struct mddev *mddev, char *page) { return sprintf(page, "%d\n", mddev->new_level); } static ssize_t new_level_store(struct mddev *mddev, const char *buf, size_t len) { unsigned int n; int err; err = kstrtouint(buf, 10, &n); if (err < 0) return err; err = mddev_lock(mddev); if (err) return err; mddev->new_level = n; md_update_sb(mddev, 1); mddev_unlock(mddev); return len; } static struct md_sysfs_entry md_new_level = __ATTR(new_level, 0664, new_level_show, new_level_store); static ssize_t bitmap_type_show(struct mddev *mddev, char *page) { struct md_submodule_head *head; unsigned long i; ssize_t len = 0; if (mddev->bitmap_id == ID_BITMAP_NONE) len += sprintf(page + len, "[none] "); else len += sprintf(page + len, "none "); xa_lock(&md_submodule); xa_for_each(&md_submodule, i, head) { if (head->type != MD_BITMAP || head->id == ID_BITMAP_NONE) continue; if (mddev->bitmap_id == head->id) len += sprintf(page + len, "[%s] ", head->name); else len += sprintf(page + len, "%s ", head->name); } xa_unlock(&md_submodule); len += sprintf(page + len, "\n"); return len; } static ssize_t bitmap_type_store(struct mddev *mddev, const char *buf, size_t len) { struct md_submodule_head *head; enum md_submodule_id id; unsigned long i; int err = 0; xa_lock(&md_submodule); if (mddev->bitmap_ops) { err = -EBUSY; goto out; } if (cmd_match(buf, "none")) { mddev->bitmap_id = ID_BITMAP_NONE; goto out; } xa_for_each(&md_submodule, i, head) { if (head->type == MD_BITMAP && cmd_match(buf, head->name)) { mddev->bitmap_id = head->id; goto out; } } err = kstrtoint(buf, 10, &id); if (err) goto out; if (id == ID_BITMAP_NONE) { mddev->bitmap_id = id; goto out; } head = xa_load(&md_submodule, id); if (head && head->type == MD_BITMAP) { mddev->bitmap_id = id; goto out; } err = -ENOENT; out: xa_unlock(&md_submodule); return err ? err : len; } static struct md_sysfs_entry md_bitmap_type = __ATTR(bitmap_type, 0664, bitmap_type_show, bitmap_type_store); static ssize_t layout_show(struct mddev *mddev, char *page) { /* just a number, not meaningful for all levels */ if (mddev->reshape_position != MaxSector && mddev->layout != mddev->new_layout) return sprintf(page, "%d (%d)\n", mddev->new_layout, mddev->layout); return sprintf(page, "%d\n", mddev->layout); } static ssize_t layout_store(struct mddev *mddev, const char *buf, size_t len) { unsigned int n; int err; err = kstrtouint(buf, 10, &n); if (err < 0) return err; err = mddev_lock(mddev); if (err) return err; if (mddev->pers) { if (mddev->pers->check_reshape == NULL) err = -EBUSY; else if (!md_is_rdwr(mddev)) err = -EROFS; else { mddev->new_layout = n; err = mddev->pers->check_reshape(mddev); if (err) mddev->new_layout = mddev->layout; } } else { mddev->new_layout = n; if (mddev->reshape_position == MaxSector) mddev->layout = n; } mddev_unlock(mddev); return err ?: len; } static struct md_sysfs_entry md_layout = __ATTR(layout, S_IRUGO|S_IWUSR, layout_show, layout_store); static ssize_t raid_disks_show(struct mddev *mddev, char *page) { if (mddev->raid_disks == 0) return 0; if (mddev->reshape_position != MaxSector && mddev->delta_disks != 0) return sprintf(page, "%d (%d)\n", mddev->raid_disks, mddev->raid_disks - mddev->delta_disks); return sprintf(page, "%d\n", mddev->raid_disks); } static int update_raid_disks(struct mddev *mddev, int raid_disks); static ssize_t raid_disks_store(struct mddev *mddev, const char *buf, size_t len) { unsigned int n; int err; err = kstrtouint(buf, 10, &n); if (err < 0) return err; err = mddev_suspend_and_lock(mddev); if (err) return err; if (mddev->pers) { if (n != mddev->raid_disks) err = update_raid_disks(mddev, n); } else if (mddev->reshape_position != MaxSector) { struct md_rdev *rdev; int olddisks = mddev->raid_disks - mddev->delta_disks; err = -EINVAL; rdev_for_each(rdev, mddev) { if (olddisks < n && rdev->data_offset < rdev->new_data_offset) goto out_unlock; if (olddisks > n && rdev->data_offset > rdev->new_data_offset) goto out_unlock; } err = 0; mddev->delta_disks = n - olddisks; mddev->raid_disks = n; mddev->reshape_backwards = (mddev->delta_disks < 0); } else mddev->raid_disks = n; out_unlock: mddev_unlock_and_resume(mddev); return err ? err : len; } static struct md_sysfs_entry md_raid_disks = __ATTR(raid_disks, S_IRUGO|S_IWUSR, raid_disks_show, raid_disks_store); static ssize_t uuid_show(struct mddev *mddev, char *page) { return sprintf(page, "%pU\n", mddev->uuid); } static struct md_sysfs_entry md_uuid = __ATTR(uuid, S_IRUGO, uuid_show, NULL); static ssize_t chunk_size_show(struct mddev *mddev, char *page) { if (mddev->reshape_position != MaxSector && mddev->chunk_sectors != mddev->new_chunk_sectors) return sprintf(page, "%d (%d)\n", mddev->new_chunk_sectors << 9, mddev->chunk_sectors << 9); return sprintf(page, "%d\n", mddev->chunk_sectors << 9); } static ssize_t chunk_size_store(struct mddev *mddev, const char *buf, size_t len) { unsigned long n; int err; err = kstrtoul(buf, 10, &n); if (err < 0) return err; err = mddev_lock(mddev); if (err) return err; if (mddev->pers) { if (mddev->pers->check_reshape == NULL) err = -EBUSY; else if (!md_is_rdwr(mddev)) err = -EROFS; else { mddev->new_chunk_sectors = n >> 9; err = mddev->pers->check_reshape(mddev); if (err) mddev->new_chunk_sectors = mddev->chunk_sectors; } } else { mddev->new_chunk_sectors = n >> 9; if (mddev->reshape_position == MaxSector) mddev->chunk_sectors = n >> 9; } mddev_unlock(mddev); return err ?: len; } static struct md_sysfs_entry md_chunk_size = __ATTR(chunk_size, S_IRUGO|S_IWUSR, chunk_size_show, chunk_size_store); static ssize_t resync_start_show(struct mddev *mddev, char *page) { if (mddev->resync_offset == MaxSector) return sprintf(page, "none\n"); return sprintf(page, "%llu\n", (unsigned long long)mddev->resync_offset); } static ssize_t resync_start_store(struct mddev *mddev, const char *buf, size_t len) { unsigned long long n; int err; if (cmd_match(buf, "none")) n = MaxSector; else { err = kstrtoull(buf, 10, &n); if (err < 0) return err; if (n != (sector_t)n) return -EINVAL; } err = mddev_lock(mddev); if (err) return err; if (mddev->pers && !test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) err = -EBUSY; if (!err) { mddev->resync_offset = n; if (mddev->pers) set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags); } mddev_unlock(mddev); return err ?: len; } static struct md_sysfs_entry md_resync_start = __ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR, resync_start_show, resync_start_store); /* * The array state can be: * * clear * No devices, no size, no level * Equivalent to STOP_ARRAY ioctl * inactive * May have some settings, but array is not active * all IO results in error * When written, doesn't tear down array, but just stops it * suspended (not supported yet) * All IO requests will block. The array can be reconfigured. * Writing this, if accepted, will block until array is quiescent * readonly * no resync can happen. no superblocks get written. * write requests fail * read-auto * like readonly, but behaves like 'clean' on a write request. * * clean - no pending writes, but otherwise active. * When written to inactive array, starts without resync * If a write request arrives then * if metadata is known, mark 'dirty' and switch to 'active'. * if not known, block and switch to write-pending * If written to an active array that has pending writes, then fails. * active * fully active: IO and resync can be happening. * When written to inactive array, starts with resync * * write-pending * clean, but writes are blocked waiting for 'active' to be written. * * active-idle * like active, but no writes have been seen for a while (100msec). * * broken * Array is failed. It's useful because mounted-arrays aren't stopped * when array is failed, so this state will at least alert the user that * something is wrong. */ enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active, write_pending, active_idle, broken, bad_word}; static char *array_states[] = { "clear", "inactive", "suspended", "readonly", "read-auto", "clean", "active", "write-pending", "active-idle", "broken", NULL }; static int match_word(const char *word, char **list) { int n; for (n=0; list[n]; n++) if (cmd_match(word, list[n])) break; return n; } static ssize_t array_state_show(struct mddev *mddev, char *page) { enum array_state st = inactive; if (mddev->pers && !test_bit(MD_NOT_READY, &mddev->flags)) { switch(mddev->ro) { case MD_RDONLY: st = readonly; break; case MD_AUTO_READ: st = read_auto; break; case MD_RDWR: spin_lock(&mddev->lock); if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) st = write_pending; else if (mddev->in_sync) st = clean; else if (mddev->safemode) st = active_idle; else st = active; spin_unlock(&mddev->lock); } if (test_bit(MD_BROKEN, &mddev->flags) && st == clean) st = broken; } else { if (list_empty(&mddev->disks) && mddev->raid_disks == 0 && mddev->dev_sectors == 0) st = clear; else st = inactive; } return sprintf(page, "%s\n", array_states[st]); } static int do_md_stop(struct mddev *mddev, int ro); static int md_set_readonly(struct mddev *mddev); static int restart_array(struct mddev *mddev); static ssize_t array_state_store(struct mddev *mddev, const char *buf, size_t len) { int err = 0; enum array_state st = match_word(buf, array_states); /* No lock dependent actions */ switch (st) { case suspended: /* not supported yet */ case write_pending: /* cannot be set */ case active_idle: /* cannot be set */ case broken: /* cannot be set */ case bad_word: return -EINVAL; case clear: case readonly: case inactive: case read_auto: if (!mddev->pers || !md_is_rdwr(mddev)) break; /* write sysfs will not open mddev and opener should be 0 */ err = mddev_set_closing_and_sync_blockdev(mddev, 0); if (err) return err; break; default: break; } if (mddev->pers && (st == active || st == clean) && mddev->ro != MD_RDONLY) { /* don't take reconfig_mutex when toggling between * clean and active */ spin_lock(&mddev->lock); if (st == active) { restart_array(mddev); clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags); md_wakeup_thread(mddev->thread); wake_up(&mddev->sb_wait); } else /* st == clean */ { restart_array(mddev); if (!set_in_sync(mddev)) err = -EBUSY; } if (!err) sysfs_notify_dirent_safe(mddev->sysfs_state); spin_unlock(&mddev->lock); return err ?: len; } err = mddev_lock(mddev); if (err) return err; switch (st) { case inactive: /* stop an active array, return 0 otherwise */ if (mddev->pers) err = do_md_stop(mddev, 2); break; case clear: err = do_md_stop(mddev, 0); break; case readonly: if (mddev->pers) err = md_set_readonly(mddev); else { mddev->ro = MD_RDONLY; set_disk_ro(mddev->gendisk, 1); err = do_md_run(mddev); } break; case read_auto: if (mddev->pers) { if (md_is_rdwr(mddev)) err = md_set_readonly(mddev); else if (mddev->ro == MD_RDONLY) err = restart_array(mddev); if (err == 0) { mddev->ro = MD_AUTO_READ; set_disk_ro(mddev->gendisk, 0); } } else { mddev->ro = MD_AUTO_READ; err = do_md_run(mddev); } break; case clean: if (mddev->pers) { err = restart_array(mddev); if (err) break; spin_lock(&mddev->lock); if (!set_in_sync(mddev)) err = -EBUSY; spin_unlock(&mddev->lock); } else err = -EINVAL; break; case active: if (mddev->pers) { err = restart_array(mddev); if (err) break; clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags); wake_up(&mddev->sb_wait); err = 0; } else { mddev->ro = MD_RDWR; set_disk_ro(mddev->gendisk, 0); err = do_md_run(mddev); } break; default: err = -EINVAL; break; } if (!err) { if (mddev->hold_active == UNTIL_IOCTL) mddev->hold_active = 0; sysfs_notify_dirent_safe(mddev->sysfs_state); } mddev_unlock(mddev); if (st == readonly || st == read_auto || st == inactive || (err && st == clear)) clear_bit(MD_CLOSING, &mddev->flags); return err ?: len; } static struct md_sysfs_entry md_array_state = __ATTR_PREALLOC(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store); static ssize_t max_corrected_read_errors_show(struct mddev *mddev, char *page) { return sprintf(page, "%d\n", atomic_read(&mddev->max_corr_read_errors)); } static ssize_t max_corrected_read_errors_store(struct mddev *mddev, const char *buf, size_t len) { unsigned int n; int rv; rv = kstrtouint(buf, 10, &n); if (rv < 0) return rv; if (n > INT_MAX) return -EINVAL; atomic_set(&mddev->max_corr_read_errors, n); return len; } static struct md_sysfs_entry max_corr_read_errors = __ATTR(max_read_errors, S_IRUGO|S_IWUSR, max_corrected_read_errors_show, max_corrected_read_errors_store); static ssize_t null_show(struct mddev *mddev, char *page) { return -EINVAL; } static ssize_t new_dev_store(struct mddev *mddev, const char *buf, size_t len) { /* buf must be %d:%d\n? giving major and minor numbers */ /* The new device is added to the array. * If the array has a persistent superblock, we read the * superblock to initialise info and check validity. * Otherwise, only checking done is that in bind_rdev_to_array, * which mainly checks size. */ char *e; int major = simple_strtoul(buf, &e, 10); int minor; dev_t dev; struct md_rdev *rdev; int err; if (!*buf || *e != ':' || !e[1] || e[1] == '\n') return -EINVAL; minor = simple_strtoul(e+1, &e, 10); if (*e && *e != '\n') return -EINVAL; dev = MKDEV(major, minor); if (major != MAJOR(dev) || minor != MINOR(dev)) return -EOVERFLOW; err = mddev_suspend_and_lock(mddev); if (err) return err; if (mddev->persistent) { rdev = md_import_device(dev, mddev->major_version, mddev->minor_version); if (!IS_ERR(rdev) && !list_empty(&mddev->disks)) { struct md_rdev *rdev0 = list_entry(mddev->disks.next, struct md_rdev, same_set); err = super_types[mddev->major_version] .load_super(rdev, rdev0, mddev->minor_version); if (err < 0) goto out; } } else if (mddev->external) rdev = md_import_device(dev, -2, -1); else rdev = md_import_device(dev, -1, -1); if (IS_ERR(rdev)) { mddev_unlock_and_resume(mddev); return PTR_ERR(rdev); } err = bind_rdev_to_array(rdev, mddev); out: if (err) export_rdev(rdev); mddev_unlock_and_resume(mddev); if (!err) md_new_event(); return err ? err : len; } static struct md_sysfs_entry md_new_device = __ATTR(new_dev, S_IWUSR, null_show, new_dev_store); static ssize_t bitmap_store(struct mddev *mddev, const char *buf, size_t len) { char *end; unsigned long chunk, end_chunk; int err; if (!md_bitmap_enabled(mddev, false)) return len; err = mddev_lock(mddev); if (err) return err; if (!mddev->bitmap) goto out; /* buf should be <chunk> <chunk> ... or <chunk>-<chunk> ... (range) */ while (*buf) { chunk = end_chunk = simple_strtoul(buf, &end, 0); if (buf == end) break; if (*end == '-') { /* range */ buf = end + 1; end_chunk = simple_strtoul(buf, &end, 0); if (buf == end) break; } if (*end && !isspace(*end)) break; mddev->bitmap_ops->dirty_bits(mddev, chunk, end_chunk); buf = skip_spaces(end); } mddev->bitmap_ops->unplug(mddev, true); /* flush the bits to disk */ out: mddev_unlock(mddev); return len; } static struct md_sysfs_entry md_bitmap = __ATTR(bitmap_set_bits, S_IWUSR, null_show, bitmap_store); static ssize_t size_show(struct mddev *mddev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)mddev->dev_sectors / 2); } static int update_size(struct mddev *mddev, sector_t num_sectors); static ssize_t size_store(struct mddev *mddev, const char *buf, size_t len) { /* If array is inactive, we can reduce the component size, but * not increase it (except from 0). * If array is active, we can try an on-line resize */ sector_t sectors; int err = strict_blocks_to_sectors(buf, §ors); if (err < 0) return err; err = mddev_lock(mddev); if (err) return err; if (mddev->pers) { err = update_size(mddev, sectors); if (err == 0) md_update_sb(mddev, 1); } else { if (mddev->dev_sectors == 0 || mddev->dev_sectors > sectors) mddev->dev_sectors = sectors; else err = -ENOSPC; } mddev_unlock(mddev); return err ? err : len; } static struct md_sysfs_entry md_size = __ATTR(component_size, S_IRUGO|S_IWUSR, size_show, size_store); /* Metadata version. * This is one of * 'none' for arrays with no metadata (good luck...) * 'external' for arrays with externally managed metadata, * or N.M for internally known formats */ static ssize_t metadata_show(struct mddev *mddev, char *page) { if (mddev->persistent) return sprintf(page, "%d.%d\n", mddev->major_version, mddev->minor_version); else if (mddev->external) return sprintf(page, "external:%s\n", mddev->metadata_type); else return sprintf(page, "none\n"); } static ssize_t metadata_store(struct mddev *mddev, const char *buf, size_t len) { int major, minor; char *e; int err; /* Changing the details of 'external' metadata is * always permitted. Otherwise there must be * no devices attached to the array. */ err = mddev_lock(mddev); if (err) return err; err = -EBUSY; if (mddev->external && strncmp(buf, "external:", 9) == 0) ; else if (!list_empty(&mddev->disks)) goto out_unlock; err = 0; if (cmd_match(buf, "none")) { mddev->persistent = 0; mddev->external = 0; mddev->major_version = 0; mddev->minor_version = 90; goto out_unlock; } if (strncmp(buf, "external:", 9) == 0) { size_t namelen = len-9; if (namelen >= sizeof(mddev->metadata_type)) namelen = sizeof(mddev->metadata_type)-1; memcpy(mddev->metadata_type, buf+9, namelen); mddev->metadata_type[namelen] = 0; if (namelen && mddev->metadata_type[namelen-1] == '\n') mddev->metadata_type[--namelen] = 0; mddev->persistent = 0; mddev->external = 1; mddev->major_version = 0; mddev->minor_version = 90; goto out_unlock; } major = simple_strtoul(buf, &e, 10); err = -EINVAL; if (e==buf || *e != '.') goto out_unlock; buf = e+1; minor = simple_strtoul(buf, &e, 10); if (e==buf || (*e && *e != '\n') ) goto out_unlock; err = -ENOENT; if (major >= ARRAY_SIZE(super_types) || super_types[major].name == NULL) goto out_unlock; mddev->major_version = major; mddev->minor_version = minor; mddev->persistent = 1; mddev->external = 0; err = 0; out_unlock: mddev_unlock(mddev); return err ?: len; } static struct md_sysfs_entry md_metadata = __ATTR_PREALLOC(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store); static bool rdev_needs_recovery(struct md_rdev *rdev, sector_t sectors) { return rdev->raid_disk >= 0 && !test_bit(Journal, &rdev->flags) && !test_bit(Faulty, &rdev->flags) && !test_bit(In_sync, &rdev->flags) && rdev->recovery_offset < sectors; } static enum sync_action md_get_active_sync_action(struct mddev *mddev) { struct md_rdev *rdev; bool is_recover = false; if (mddev->resync_offset < MaxSector) return ACTION_RESYNC; if (mddev->reshape_position != MaxSector) return ACTION_RESHAPE; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { if (rdev_needs_recovery(rdev, MaxSector)) { is_recover = true; break; } } rcu_read_unlock(); return is_recover ? ACTION_RECOVER : ACTION_IDLE; } enum sync_action md_sync_action(struct mddev *mddev) { unsigned long recovery = mddev->recovery; enum sync_action active_action; /* * frozen has the highest priority, means running sync_thread will be * stopped immediately, and no new sync_thread can start. */ if (test_bit(MD_RECOVERY_FROZEN, &recovery)) return ACTION_FROZEN; /* * read-only array can't register sync_thread, and it can only * add/remove spares. */ if (!md_is_rdwr(mddev)) return ACTION_IDLE; /* * idle means no sync_thread is running, and no new sync_thread is * requested. */ if (!test_bit(MD_RECOVERY_RUNNING, &recovery) && !test_bit(MD_RECOVERY_NEEDED, &recovery)) return ACTION_IDLE; /* * Check if any sync operation (resync/recover/reshape) is * currently active. This ensures that only one sync operation * can run at a time. Returns the type of active operation, or * ACTION_IDLE if none are active. */ active_action = md_get_active_sync_action(mddev); if (active_action != ACTION_IDLE) return active_action; if (test_bit(MD_RECOVERY_RESHAPE, &recovery)) return ACTION_RESHAPE; if (test_bit(MD_RECOVERY_RECOVER, &recovery)) return ACTION_RECOVER; if (test_bit(MD_RECOVERY_SYNC, &recovery)) { /* * MD_RECOVERY_CHECK must be paired with * MD_RECOVERY_REQUESTED. */ if (test_bit(MD_RECOVERY_CHECK, &recovery)) return ACTION_CHECK; if (test_bit(MD_RECOVERY_REQUESTED, &recovery)) return ACTION_REPAIR; return ACTION_RESYNC; } /* * MD_RECOVERY_NEEDED or MD_RECOVERY_RUNNING is set, however, no * sync_action is specified. */ return ACTION_IDLE; } enum sync_action md_sync_action_by_name(const char *page) { enum sync_action action; for (action = 0; action < NR_SYNC_ACTIONS; ++action) { if (cmd_match(page, action_name[action])) return action; } return NR_SYNC_ACTIONS; } const char *md_sync_action_name(enum sync_action action) { return action_name[action]; } static ssize_t action_show(struct mddev *mddev, char *page) { enum sync_action action = md_sync_action(mddev); return sprintf(page, "%s\n", md_sync_action_name(action)); } /** * stop_sync_thread() - wait for sync_thread to stop if it's running. * @mddev: the array. * @locked: if set, reconfig_mutex will still be held after this function * return; if not set, reconfig_mutex will be released after this * function return. */ static void stop_sync_thread(struct mddev *mddev, bool locked) { int sync_seq = atomic_read(&mddev->sync_seq); if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { if (!locked) mddev_unlock(mddev); return; } mddev_unlock(mddev); set_bit(MD_RECOVERY_INTR, &mddev->recovery); /* * Thread might be blocked waiting for metadata update which will now * never happen */ md_wakeup_thread_directly(&mddev->sync_thread); if (work_pending(&mddev->sync_work)) flush_work(&mddev->sync_work); wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery) && sync_seq != atomic_read(&mddev->sync_seq))); if (locked) mddev_lock_nointr(mddev); } void md_idle_sync_thread(struct mddev *mddev) { lockdep_assert_held(&mddev->reconfig_mutex); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); stop_sync_thread(mddev, true); } EXPORT_SYMBOL_GPL(md_idle_sync_thread); void md_frozen_sync_thread(struct mddev *mddev) { lockdep_assert_held(&mddev->reconfig_mutex); set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); stop_sync_thread(mddev, true); } EXPORT_SYMBOL_GPL(md_frozen_sync_thread); void md_unfrozen_sync_thread(struct mddev *mddev) { lockdep_assert_held(&mddev->reconfig_mutex); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); sysfs_notify_dirent_safe(mddev->sysfs_action); } EXPORT_SYMBOL_GPL(md_unfrozen_sync_thread); static int mddev_start_reshape(struct mddev *mddev) { int ret; if (mddev->pers->start_reshape == NULL) return -EINVAL; if (mddev->reshape_position == MaxSector || mddev->pers->check_reshape == NULL || mddev->pers->check_reshape(mddev)) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); ret = mddev->pers->start_reshape(mddev); if (ret) return ret; } else { /* * If reshape is still in progress, and md_check_recovery() can * continue to reshape, don't restart reshape because data can * be corrupted for raid456. */ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } sysfs_notify_dirent_safe(mddev->sysfs_degraded); return 0; } static ssize_t action_store(struct mddev *mddev, const char *page, size_t len) { int ret; enum sync_action action; if (!mddev->pers || !mddev->pers->sync_request) return -EINVAL; retry: if (work_busy(&mddev->sync_work)) flush_work(&mddev->sync_work); ret = mddev_lock(mddev); if (ret) return ret; if (work_busy(&mddev->sync_work)) { mddev_unlock(mddev); goto retry; } action = md_sync_action_by_name(page); /* TODO: mdadm rely on "idle" to start sync_thread. */ if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { switch (action) { case ACTION_FROZEN: md_frozen_sync_thread(mddev); ret = len; goto out; case ACTION_IDLE: md_idle_sync_thread(mddev); break; case ACTION_RESHAPE: case ACTION_RECOVER: case ACTION_CHECK: case ACTION_REPAIR: case ACTION_RESYNC: ret = -EBUSY; goto out; default: ret = -EINVAL; goto out; } } else { switch (action) { case ACTION_FROZEN: set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); ret = len; goto out; case ACTION_RESHAPE: clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); ret = mddev_start_reshape(mddev); if (ret) goto out; break; case ACTION_RECOVER: clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); break; case ACTION_CHECK: set_bit(MD_RECOVERY_CHECK, &mddev->recovery); fallthrough; case ACTION_REPAIR: set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); set_bit(MD_RECOVERY_SYNC, &mddev->recovery); fallthrough; case ACTION_RESYNC: case ACTION_IDLE: clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); break; default: ret = -EINVAL; goto out; } } if (mddev->ro == MD_AUTO_READ) { /* A write to sync_action is enough to justify * canceling read-auto mode */ mddev->ro = MD_RDWR; md_wakeup_thread(mddev->sync_thread); } set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); sysfs_notify_dirent_safe(mddev->sysfs_action); ret = len; out: mddev_unlock(mddev); return ret; } static struct md_sysfs_entry md_scan_mode = __ATTR_PREALLOC(sync_action, S_IRUGO|S_IWUSR, action_show, action_store); static ssize_t last_sync_action_show(struct mddev *mddev, char *page) { return sprintf(page, "%s\n", md_sync_action_name(mddev->last_sync_action)); } static struct md_sysfs_entry md_last_scan_mode = __ATTR_RO(last_sync_action); static ssize_t mismatch_cnt_show(struct mddev *mddev, char *page) { return sprintf(page, "%llu\n", (unsigned long long) atomic64_read(&mddev->resync_mismatches)); } static struct md_sysfs_entry md_mismatches = __ATTR_RO(mismatch_cnt); static ssize_t sync_min_show(struct mddev *mddev, char *page) { return sprintf(page, "%d (%s)\n", speed_min(mddev), mddev->sync_speed_min ? "local" : "system"); } static ssize_t sync_min_store(struct mddev *mddev, const char *buf, size_t len) { unsigned int min; int rv; if (strncmp(buf, "system", 6) == 0) { min = 0; } else { rv = kstrtouint(buf, 10, &min); if (rv < 0) return rv; if (min == 0) return -EINVAL; } mddev->sync_speed_min = min; return len; } static struct md_sysfs_entry md_sync_min = __ATTR(sync_speed_min, S_IRUGO|S_IWUSR, sync_min_show, sync_min_store); static ssize_t sync_max_show(struct mddev *mddev, char *page) { return sprintf(page, "%d (%s)\n", speed_max(mddev), mddev->sync_speed_max ? "local" : "system"); } static ssize_t sync_max_store(struct mddev *mddev, const char *buf, size_t len) { unsigned int max; int rv; if (strncmp(buf, "system", 6) == 0) { max = 0; } else { rv = kstrtouint(buf, 10, &max); if (rv < 0) return rv; if (max == 0) return -EINVAL; } mddev->sync_speed_max = max; return len; } static struct md_sysfs_entry md_sync_max = __ATTR(sync_speed_max, S_IRUGO|S_IWUSR, sync_max_show, sync_max_store); static ssize_t sync_io_depth_show(struct mddev *mddev, char *page) { return sprintf(page, "%d (%s)\n", sync_io_depth(mddev), mddev->sync_io_depth ? "local" : "system"); } static ssize_t sync_io_depth_store(struct mddev *mddev, const char *buf, size_t len) { unsigned int max; int rv; if (strncmp(buf, "system", 6) == 0) { max = 0; } else { rv = kstrtouint(buf, 10, &max); if (rv < 0) return rv; if (max == 0) return -EINVAL; } mddev->sync_io_depth = max; return len; } static struct md_sysfs_entry md_sync_io_depth = __ATTR_RW(sync_io_depth); static ssize_t degraded_show(struct mddev *mddev, char *page) { return sprintf(page, "%d\n", mddev->degraded); } static struct md_sysfs_entry md_degraded = __ATTR_RO(degraded); static ssize_t sync_force_parallel_show(struct mddev *mddev, char *page) { return sprintf(page, "%d\n", mddev->parallel_resync); } static ssize_t sync_force_parallel_store(struct mddev *mddev, const char *buf, size_t len) { long n; if (kstrtol(buf, 10, &n)) return -EINVAL; if (n != 0 && n != 1) return -EINVAL; mddev->parallel_resync = n; if (mddev->sync_thread) wake_up(&resync_wait); return len; } /* force parallel resync, even with shared block devices */ static struct md_sysfs_entry md_sync_force_parallel = __ATTR(sync_force_parallel, S_IRUGO|S_IWUSR, sync_force_parallel_show, sync_force_parallel_store); static ssize_t sync_speed_show(struct mddev *mddev, char *page) { unsigned long resync, dt, db; if (mddev->curr_resync == MD_RESYNC_NONE) return sprintf(page, "none\n"); resync = mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active); dt = (jiffies - mddev->resync_mark) / HZ; if (!dt) dt++; db = resync - mddev->resync_mark_cnt; return sprintf(page, "%lu\n", db/dt/2); /* K/sec */ } static struct md_sysfs_entry md_sync_speed = __ATTR_RO(sync_speed); static ssize_t sync_completed_show(struct mddev *mddev, char *page) { unsigned long long max_sectors, resync; if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return sprintf(page, "none\n"); if (mddev->curr_resync == MD_RESYNC_YIELDED || mddev->curr_resync == MD_RESYNC_DELAYED) return sprintf(page, "delayed\n"); if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) || test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) max_sectors = mddev->resync_max_sectors; else max_sectors = mddev->dev_sectors; resync = mddev->curr_resync_completed; return sprintf(page, "%llu / %llu\n", resync, max_sectors); } static struct md_sysfs_entry md_sync_completed = __ATTR_PREALLOC(sync_completed, S_IRUGO, sync_completed_show, NULL); static ssize_t min_sync_show(struct mddev *mddev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)mddev->resync_min); } static ssize_t min_sync_store(struct mddev *mddev, const char *buf, size_t len) { unsigned long long min; int err; if (kstrtoull(buf, 10, &min)) return -EINVAL; spin_lock(&mddev->lock); err = -EINVAL; if (min > mddev->resync_max) goto out_unlock; err = -EBUSY; if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) goto out_unlock; /* Round down to multiple of 4K for safety */ mddev->resync_min = round_down(min, 8); err = 0; out_unlock: spin_unlock(&mddev->lock); return err ?: len; } static struct md_sysfs_entry md_min_sync = __ATTR(sync_min, S_IRUGO|S_IWUSR, min_sync_show, min_sync_store); static ssize_t max_sync_show(struct mddev *mddev, char *page) { if (mddev->resync_max == MaxSector) return sprintf(page, "max\n"); else return sprintf(page, "%llu\n", (unsigned long long)mddev->resync_max); } static ssize_t max_sync_store(struct mddev *mddev, const char *buf, size_t len) { int err; spin_lock(&mddev->lock); if (strncmp(buf, "max", 3) == 0) mddev->resync_max = MaxSector; else { unsigned long long max; int chunk; err = -EINVAL; if (kstrtoull(buf, 10, &max)) goto out_unlock; if (max < mddev->resync_min) goto out_unlock; err = -EBUSY; if (max < mddev->resync_max && md_is_rdwr(mddev) && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) goto out_unlock; /* Must be a multiple of chunk_size */ chunk = mddev->chunk_sectors; if (chunk) { sector_t temp = max; err = -EINVAL; if (sector_div(temp, chunk)) goto out_unlock; } mddev->resync_max = max; } wake_up(&mddev->recovery_wait); err = 0; out_unlock: spin_unlock(&mddev->lock); return err ?: len; } static struct md_sysfs_entry md_max_sync = __ATTR(sync_max, S_IRUGO|S_IWUSR, max_sync_show, max_sync_store); static ssize_t suspend_lo_show(struct mddev *mddev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)READ_ONCE(mddev->suspend_lo)); } static ssize_t suspend_lo_store(struct mddev *mddev, const char *buf, size_t len) { unsigned long long new; int err; err = kstrtoull(buf, 10, &new); if (err < 0) return err; if (new != (sector_t)new) return -EINVAL; err = mddev_suspend(mddev, true); if (err) return err; WRITE_ONCE(mddev->suspend_lo, new); mddev_resume(mddev); return len; } static struct md_sysfs_entry md_suspend_lo = __ATTR(suspend_lo, S_IRUGO|S_IWUSR, suspend_lo_show, suspend_lo_store); static ssize_t suspend_hi_show(struct mddev *mddev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)READ_ONCE(mddev->suspend_hi)); } static ssize_t suspend_hi_store(struct mddev *mddev, const char *buf, size_t len) { unsigned long long new; int err; err = kstrtoull(buf, 10, &new); if (err < 0) return err; if (new != (sector_t)new) return -EINVAL; err = mddev_suspend(mddev, true); if (err) return err; WRITE_ONCE(mddev->suspend_hi, new); mddev_resume(mddev); return len; } static struct md_sysfs_entry md_suspend_hi = __ATTR(suspend_hi, S_IRUGO|S_IWUSR, suspend_hi_show, suspend_hi_store); static ssize_t reshape_position_show(struct mddev *mddev, char *page) { if (mddev->reshape_position != MaxSector) return sprintf(page, "%llu\n", (unsigned long long)mddev->reshape_position); strcpy(page, "none\n"); return 5; } static ssize_t reshape_position_store(struct mddev *mddev, const char *buf, size_t len) { struct md_rdev *rdev; unsigned long long new; int err; err = kstrtoull(buf, 10, &new); if (err < 0) return err; if (new != (sector_t)new) return -EINVAL; err = mddev_lock(mddev); if (err) return err; err = -EBUSY; if (mddev->pers) goto unlock; mddev->reshape_position = new; mddev->delta_disks = 0; mddev->reshape_backwards = 0; mddev->new_level = mddev->level; mddev->new_layout = mddev->layout; mddev->new_chunk_sectors = mddev->chunk_sectors; rdev_for_each(rdev, mddev) rdev->new_data_offset = rdev->data_offset; err = 0; unlock: mddev_unlock(mddev); return err ?: len; } static struct md_sysfs_entry md_reshape_position = __ATTR(reshape_position, S_IRUGO|S_IWUSR, reshape_position_show, reshape_position_store); static ssize_t reshape_direction_show(struct mddev *mddev, char *page) { return sprintf(page, "%s\n", mddev->reshape_backwards ? "backwards" : "forwards"); } static ssize_t reshape_direction_store(struct mddev *mddev, const char *buf, size_t len) { int backwards = 0; int err; if (cmd_match(buf, "forwards")) backwards = 0; else if (cmd_match(buf, "backwards")) backwards = 1; else return -EINVAL; if (mddev->reshape_backwards == backwards) return len; err = mddev_lock(mddev); if (err) return err; /* check if we are allowed to change */ if (mddev->delta_disks) err = -EBUSY; else if (mddev->persistent && mddev->major_version == 0) err = -EINVAL; else mddev->reshape_backwards = backwards; mddev_unlock(mddev); return err ?: len; } static struct md_sysfs_entry md_reshape_direction = __ATTR(reshape_direction, S_IRUGO|S_IWUSR, reshape_direction_show, reshape_direction_store); static ssize_t array_size_show(struct mddev *mddev, char *page) { if (mddev->external_size) return sprintf(page, "%llu\n", (unsigned long long)mddev->array_sectors/2); else return sprintf(page, "default\n"); } static ssize_t array_size_store(struct mddev *mddev, const char *buf, size_t len) { sector_t sectors; int err; err = mddev_lock(mddev); if (err) return err; /* cluster raid doesn't support change array_sectors */ if (mddev_is_clustered(mddev)) { mddev_unlock(mddev); return -EINVAL; } if (strncmp(buf, "default", 7) == 0) { if (mddev->pers) sectors = mddev->pers->size(mddev, 0, 0); else sectors = mddev->array_sectors; mddev->external_size = 0; } else { if (strict_blocks_to_sectors(buf, §ors) < 0) err = -EINVAL; else if (mddev->pers && mddev->pers->size(mddev, 0, 0) < sectors) err = -E2BIG; else mddev->external_size = 1; } if (!err) { mddev->array_sectors = sectors; if (mddev->pers) set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); } mddev_unlock(mddev); return err ?: len; } static struct md_sysfs_entry md_array_size = __ATTR(array_size, S_IRUGO|S_IWUSR, array_size_show, array_size_store); static ssize_t consistency_policy_show(struct mddev *mddev, char *page) { int ret; if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) { ret = sprintf(page, "journal\n"); } else if (test_bit(MD_HAS_PPL, &mddev->flags)) { ret = sprintf(page, "ppl\n"); } else if (mddev->bitmap) { ret = sprintf(page, "bitmap\n"); } else if (mddev->pers) { if (mddev->pers->sync_request) ret = sprintf(page, "resync\n"); else ret = sprintf(page, "none\n"); } else { ret = sprintf(page, "unknown\n"); } return ret; } static ssize_t consistency_policy_store(struct mddev *mddev, const char *buf, size_t len) { int err = 0; if (mddev->pers) { if (mddev->pers->change_consistency_policy) err = mddev->pers->change_consistency_policy(mddev, buf); else err = -EBUSY; } else if (mddev->external && strncmp(buf, "ppl", 3) == 0) { set_bit(MD_HAS_PPL, &mddev->flags); } else { err = -EINVAL; } return err ? err : len; } static struct md_sysfs_entry md_consistency_policy = __ATTR(consistency_policy, S_IRUGO | S_IWUSR, consistency_policy_show, consistency_policy_store); static ssize_t fail_last_dev_show(struct mddev *mddev, char *page) { return sprintf(page, "%d\n", test_bit(MD_FAILLAST_DEV, &mddev->flags)); } /* * Setting MD_FAILLAST_DEV to allow last device to be forcibly removed * from RAID1/RAID10. */ static ssize_t fail_last_dev_store(struct mddev *mddev, const char *buf, size_t len) { int ret; bool value; ret = kstrtobool(buf, &value); if (ret) return ret; if (value) set_bit(MD_FAILLAST_DEV, &mddev->flags); else clear_bit(MD_FAILLAST_DEV, &mddev->flags); return len; } static struct md_sysfs_entry md_fail_last_dev = __ATTR(fail_last_dev, S_IRUGO | S_IWUSR, fail_last_dev_show, fail_last_dev_store); static ssize_t serialize_policy_show(struct mddev *mddev, char *page) { if (mddev->pers == NULL || (mddev->pers->head.id != ID_RAID1)) return sprintf(page, "n/a\n"); else return sprintf(page, "%d\n", test_bit(MD_SERIALIZE_POLICY, &mddev->flags)); } /* * Setting MD_SERIALIZE_POLICY enforce write IO is not reordered * for raid1. */ static ssize_t serialize_policy_store(struct mddev *mddev, const char *buf, size_t len) { int err; bool value; err = kstrtobool(buf, &value); if (err) return err; if (value == test_bit(MD_SERIALIZE_POLICY, &mddev->flags)) return len; err = mddev_suspend_and_lock(mddev); if (err) return err; if (mddev->pers == NULL || (mddev->pers->head.id != ID_RAID1)) { pr_err("md: serialize_policy is only effective for raid1\n"); err = -EINVAL; goto unlock; } if (value) { mddev_create_serial_pool(mddev, NULL); set_bit(MD_SERIALIZE_POLICY, &mddev->flags); } else { mddev_destroy_serial_pool(mddev, NULL); clear_bit(MD_SERIALIZE_POLICY, &mddev->flags); } unlock: mddev_unlock_and_resume(mddev); return err ?: len; } static struct md_sysfs_entry md_serialize_policy = __ATTR(serialize_policy, S_IRUGO | S_IWUSR, serialize_policy_show, serialize_policy_store); static int mddev_set_logical_block_size(struct mddev *mddev, unsigned int lbs) { int err = 0; struct queue_limits lim; if (queue_logical_block_size(mddev->gendisk->queue) >= lbs) { pr_err("%s: Cannot set LBS smaller than mddev LBS %u\n", mdname(mddev), lbs); return -EINVAL; } lim = queue_limits_start_update(mddev->gendisk->queue); lim.logical_block_size = lbs; pr_info("%s: logical_block_size is changed, data may be lost\n", mdname(mddev)); err = queue_limits_commit_update(mddev->gendisk->queue, &lim); if (err) return err; mddev->logical_block_size = lbs; /* New lbs will be written to superblock after array is running */ set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); return 0; } static ssize_t lbs_show(struct mddev *mddev, char *page) { return sprintf(page, "%u\n", mddev->logical_block_size); } static ssize_t lbs_store(struct mddev *mddev, const char *buf, size_t len) { unsigned int lbs; int err = -EBUSY; /* Only 1.x meta supports configurable LBS */ if (mddev->major_version == 0) return -EINVAL; err = kstrtouint(buf, 10, &lbs); if (err < 0) return -EINVAL; if (mddev->pers) { unsigned int curr_lbs; if (mddev->logical_block_size) return -EBUSY; /* * To fix forward compatibility issues, LBS is not * configured for arrays from old kernels (<=6.18) by default. * If the user confirms no rollback to old kernels, * enable LBS by writing current LBS — to prevent data * loss from LBS changes. */ curr_lbs = queue_logical_block_size(mddev->gendisk->queue); if (lbs != curr_lbs) return -EINVAL; mddev->logical_block_size = curr_lbs; set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); pr_info("%s: logical block size configured successfully, array will not be assembled in old kernels (<= 6.18)\n", mdname(mddev)); return len; } err = mddev_lock(mddev); if (err) goto unlock; err = mddev_set_logical_block_size(mddev, lbs); unlock: mddev_unlock(mddev); return err ?: len; } static struct md_sysfs_entry md_logical_block_size = __ATTR(logical_block_size, 0644, lbs_show, lbs_store); static struct attribute *md_default_attrs[] = { &md_level.attr, &md_new_level.attr, &md_bitmap_type.attr, &md_layout.attr, &md_raid_disks.attr, &md_uuid.attr, &md_chunk_size.attr, &md_size.attr, &md_resync_start.attr, &md_metadata.attr, &md_new_device.attr, &md_safe_delay.attr, &md_array_state.attr, &md_reshape_position.attr, &md_reshape_direction.attr, &md_array_size.attr, &max_corr_read_errors.attr, &md_consistency_policy.attr, &md_fail_last_dev.attr, &md_serialize_policy.attr, &md_logical_block_size.attr, NULL, }; ATTRIBUTE_GROUPS(md_default); static struct attribute *md_redundancy_attrs[] = { &md_scan_mode.attr, &md_last_scan_mode.attr, &md_mismatches.attr, &md_sync_min.attr, &md_sync_max.attr, &md_sync_io_depth.attr, &md_sync_speed.attr, &md_sync_force_parallel.attr, &md_sync_completed.attr, &md_min_sync.attr, &md_max_sync.attr, &md_suspend_lo.attr, &md_suspend_hi.attr, &md_bitmap.attr, &md_degraded.attr, NULL, }; static const struct attribute_group md_redundancy_group = { .name = NULL, .attrs = md_redundancy_attrs, }; static ssize_t md_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { struct md_sysfs_entry *entry = container_of(attr, struct md_sysfs_entry, attr); struct mddev *mddev = container_of(kobj, struct mddev, kobj); ssize_t rv; if (!entry->show) return -EIO; spin_lock(&all_mddevs_lock); if (!mddev_get(mddev)) { spin_unlock(&all_mddevs_lock); return -EBUSY; } spin_unlock(&all_mddevs_lock); rv = entry->show(mddev, page); mddev_put(mddev); return rv; } static ssize_t md_attr_store(struct kobject *kobj, struct attribute *attr, const char *page, size_t length) { struct md_sysfs_entry *entry = container_of(attr, struct md_sysfs_entry, attr); struct mddev *mddev = container_of(kobj, struct mddev, kobj); ssize_t rv; struct kernfs_node *kn = NULL; if (!entry->store) return -EIO; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (entry->store == array_state_store && cmd_match(page, "clear")) kn = sysfs_break_active_protection(kobj, attr); spin_lock(&all_mddevs_lock); if (!mddev_get(mddev)) { spin_unlock(&all_mddevs_lock); if (kn) sysfs_unbreak_active_protection(kn); return -EBUSY; } spin_unlock(&all_mddevs_lock); rv = entry->store(mddev, page, length); /* * For "array_state=clear", dropping the extra kobject reference from * sysfs_break_active_protection() can trigger md kobject deletion. * Restore active protection before mddev_put() so deletion happens * after the sysfs write path fully unwinds. */ if (kn) sysfs_unbreak_active_protection(kn); mddev_put(mddev); return rv; } static void md_kobj_release(struct kobject *ko) { struct mddev *mddev = container_of(ko, struct mddev, kobj); if (legacy_async_del_gendisk) { if (mddev->sysfs_state) sysfs_put(mddev->sysfs_state); if (mddev->sysfs_level) sysfs_put(mddev->sysfs_level); del_gendisk(mddev->gendisk); } put_disk(mddev->gendisk); } static const struct sysfs_ops md_sysfs_ops = { .show = md_attr_show, .store = md_attr_store, }; static const struct kobj_type md_ktype = { .release = md_kobj_release, .sysfs_ops = &md_sysfs_ops, .default_groups = md_default_groups, }; int mdp_major = 0; /* stack the limit for all rdevs into lim */ int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim, unsigned int flags) { struct md_rdev *rdev; rdev_for_each(rdev, mddev) { queue_limits_stack_bdev(lim, rdev->bdev, rdev->data_offset, mddev->gendisk->disk_name); if ((flags & MDDEV_STACK_INTEGRITY) && !queue_limits_stack_integrity_bdev(lim, rdev->bdev)) return -EINVAL; } /* * Before RAID adding folio support, the logical_block_size * should be smaller than the page size. */ if (lim->logical_block_size > PAGE_SIZE) { pr_err("%s: logical_block_size must not larger than PAGE_SIZE\n", mdname(mddev)); return -EINVAL; } /* Only 1.x meta needs to set logical block size */ if (mddev->major_version == 0) return 0; /* * Fix forward compatibility issue. Only set LBS by default for * new arrays, mddev->events == 0 indicates the array was just * created. When assembling an array, read LBS from the superblock * instead — LBS is 0 in superblocks created by old kernels. */ if (!mddev->events) { pr_info("%s: array will not be assembled in old kernels that lack configurable LBS support (<= 6.18)\n", mdname(mddev)); mddev->logical_block_size = lim->logical_block_size; } if (!mddev->logical_block_size) pr_warn("%s: echo current LBS to md/logical_block_size to prevent data loss issues from LBS changes.\n" "\tNote: After setting, array will not be assembled in old kernels (<= 6.18)\n", mdname(mddev)); return 0; } EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits); /* apply the extra stacking limits from a new rdev into mddev */ int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev) { struct queue_limits lim; if (mddev_is_dm(mddev)) return 0; if (queue_logical_block_size(rdev->bdev->bd_disk->queue) > queue_logical_block_size(mddev->gendisk->queue)) { pr_err("%s: incompatible logical_block_size, can not add\n", mdname(mddev)); return -EINVAL; } lim = queue_limits_start_update(mddev->gendisk->queue); queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset, mddev->gendisk->disk_name); if (!queue_limits_stack_integrity_bdev(&lim, rdev->bdev)) { pr_err("%s: incompatible integrity profile for %pg\n", mdname(mddev), rdev->bdev); queue_limits_cancel_update(mddev->gendisk->queue); return -ENXIO; } return queue_limits_commit_update(mddev->gendisk->queue, &lim); } EXPORT_SYMBOL_GPL(mddev_stack_new_rdev); /* update the optimal I/O size after a reshape */ void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes) { struct queue_limits lim; if (mddev_is_dm(mddev)) return; /* don't bother updating io_opt if we can't suspend the array */ if (mddev_suspend(mddev, false) < 0) return; lim = queue_limits_start_update(mddev->gendisk->queue); lim.io_opt = lim.io_min * nr_stripes; queue_limits_commit_update(mddev->gendisk->queue, &lim); mddev_resume(mddev); } EXPORT_SYMBOL_GPL(mddev_update_io_opt); static void mddev_delayed_delete(struct work_struct *ws) { struct mddev *mddev = container_of(ws, struct mddev, del_work); kobject_put(&mddev->kobj); } void md_init_stacking_limits(struct queue_limits *lim) { blk_set_stacking_limits(lim); lim->features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT; } EXPORT_SYMBOL_GPL(md_init_stacking_limits); struct mddev *md_alloc(dev_t dev, char *name) { /* * If dev is zero, name is the name of a device to allocate with * an arbitrary minor number. It will be "md_???" * If dev is non-zero it must be a device number with a MAJOR of * MD_MAJOR or mdp_major. In this case, if "name" is NULL, then * the device is being created by opening a node in /dev. * If "name" is not NULL, the device is being created by * writing to /sys/module/md_mod/parameters/new_array. */ static DEFINE_MUTEX(disks_mutex); struct mddev *mddev; struct gendisk *disk; int partitioned; int shift; int unit; int error; /* * Wait for any previous instance of this device to be completely * removed (mddev_delayed_delete). */ flush_workqueue(md_misc_wq); mutex_lock(&disks_mutex); mddev = mddev_alloc(dev); if (IS_ERR(mddev)) { error = PTR_ERR(mddev); goto out_unlock; } partitioned = (MAJOR(mddev->unit) != MD_MAJOR); shift = partitioned ? MdpMinorShift : 0; unit = MINOR(mddev->unit) >> shift; if (name && !dev) { /* Need to ensure that 'name' is not a duplicate. */ struct mddev *mddev2; spin_lock(&all_mddevs_lock); list_for_each_entry(mddev2, &all_mddevs, all_mddevs) if (mddev2->gendisk && strcmp(mddev2->gendisk->disk_name, name) == 0) { spin_unlock(&all_mddevs_lock); error = -EEXIST; goto out_free_mddev; } spin_unlock(&all_mddevs_lock); } if (name && dev) /* * Creating /dev/mdNNN via "newarray", so adjust hold_active. */ mddev->hold_active = UNTIL_STOP; disk = blk_alloc_disk(NULL, NUMA_NO_NODE); if (IS_ERR(disk)) { error = PTR_ERR(disk); goto out_free_mddev; } disk->major = MAJOR(mddev->unit); disk->first_minor = unit << shift; disk->minors = 1 << shift; if (name) strcpy(disk->disk_name, name); else if (partitioned) sprintf(disk->disk_name, "md_d%d", unit); else sprintf(disk->disk_name, "md%d", unit); disk->fops = &md_fops; disk->private_data = mddev; disk->events |= DISK_EVENT_MEDIA_CHANGE; mddev->gendisk = disk; error = add_disk(disk); if (error) goto out_put_disk; kobject_init(&mddev->kobj, &md_ktype); error = kobject_add(&mddev->kobj, &disk_to_dev(disk)->kobj, "%s", "md"); if (error) { /* * The disk is already live at this point. Clear the hold flag * and let mddev_put take care of the deletion, as it isn't any * different from a normal close on last release now. */ mddev->hold_active = 0; mutex_unlock(&disks_mutex); mddev_put(mddev); return ERR_PTR(error); } kobject_uevent(&mddev->kobj, KOBJ_ADD); mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state"); mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level"); mutex_unlock(&disks_mutex); return mddev; out_put_disk: put_disk(disk); out_free_mddev: mddev_free(mddev); out_unlock: mutex_unlock(&disks_mutex); return ERR_PTR(error); } static int md_alloc_and_put(dev_t dev, char *name) { struct mddev *mddev = md_alloc(dev, name); if (legacy_async_del_gendisk) pr_warn("md: async del_gendisk mode will be removed in future, please upgrade to mdadm-4.5+\n"); if (IS_ERR(mddev)) return PTR_ERR(mddev); mddev_put(mddev); return 0; } static void md_probe(dev_t dev) { if (MAJOR(dev) == MD_MAJOR && MINOR(dev) >= 512) return; if (create_on_open) md_alloc_and_put(dev, NULL); } static int add_named_array(const char *val, const struct kernel_param *kp) { /* * val must be "md_*" or "mdNNN". * For "md_*" we allocate an array with a large free minor number, and * set the name to val. val must not already be an active name. * For "mdNNN" we allocate an array with the minor number NNN * which must not already be in use. */ int len = strlen(val); char buf[DISK_NAME_LEN]; unsigned long devnum; while (len && val[len-1] == '\n') len--; if (len >= DISK_NAME_LEN) return -E2BIG; strscpy(buf, val, len+1); if (strncmp(buf, "md_", 3) == 0) return md_alloc_and_put(0, buf); if (strncmp(buf, "md", 2) == 0 && isdigit(buf[2]) && kstrtoul(buf+2, 10, &devnum) == 0 && devnum <= MINORMASK) return md_alloc_and_put(MKDEV(MD_MAJOR, devnum), NULL); return -EINVAL; } static void md_safemode_timeout(struct timer_list *t) { struct mddev *mddev = timer_container_of(mddev, t, safemode_timer); mddev->safemode = 1; if (mddev->external) sysfs_notify_dirent_safe(mddev->sysfs_state); md_wakeup_thread(mddev->thread); } static int start_dirty_degraded; /* * Read bitmap superblock and return the bitmap_id based on disk version. * This is used as fallback when default bitmap version and on-disk version * doesn't match, and mdadm is not the latest version to set bitmap_type. */ static enum md_submodule_id md_bitmap_get_id_from_sb(struct mddev *mddev) { struct md_rdev *rdev; struct page *sb_page; bitmap_super_t *sb; enum md_submodule_id id = ID_BITMAP_NONE; sector_t sector; u32 version; if (!mddev->bitmap_info.offset) return ID_BITMAP_NONE; sb_page = alloc_page(GFP_KERNEL); if (!sb_page) { pr_warn("md: %s: failed to allocate memory for bitmap\n", mdname(mddev)); return ID_BITMAP_NONE; } sector = mddev->bitmap_info.offset; rdev_for_each(rdev, mddev) { u32 iosize; if (!test_bit(In_sync, &rdev->flags) || test_bit(Faulty, &rdev->flags) || test_bit(Bitmap_sync, &rdev->flags)) continue; iosize = roundup(sizeof(bitmap_super_t), bdev_logical_block_size(rdev->bdev)); if (sync_page_io(rdev, sector, iosize, sb_page, REQ_OP_READ, true)) goto read_ok; } pr_warn("md: %s: failed to read bitmap from any device\n", mdname(mddev)); goto out; read_ok: sb = kmap_local_page(sb_page); if (sb->magic != cpu_to_le32(BITMAP_MAGIC)) { pr_warn("md: %s: invalid bitmap magic 0x%x\n", mdname(mddev), le32_to_cpu(sb->magic)); goto out_unmap; } version = le32_to_cpu(sb->version); switch (version) { case BITMAP_MAJOR_LO: case BITMAP_MAJOR_HI: case BITMAP_MAJOR_CLUSTERED: id = ID_BITMAP; break; case BITMAP_MAJOR_LOCKLESS: id = ID_LLBITMAP; break; default: pr_warn("md: %s: unknown bitmap version %u\n", mdname(mddev), version); break; } out_unmap: kunmap_local(sb); out: __free_page(sb_page); return id; } int md_bitmap_create_nosysfs(struct mddev *mddev) { enum md_submodule_id orig_id = mddev->bitmap_id; enum md_submodule_id sb_id; int err; if (mddev->bitmap_id == ID_BITMAP_NONE) return -EINVAL; if (!mddev_set_bitmap_ops_nosysfs(mddev)) { mddev->bitmap_id = orig_id; return -ENOENT; } err = mddev->bitmap_ops->create(mddev); if (!err) return 0; /* * Create failed, if default bitmap version and on-disk version * doesn't match, and mdadm is not the latest version to set * bitmap_type, set bitmap_ops based on the disk version. */ mddev->bitmap_ops = NULL; sb_id = md_bitmap_get_id_from_sb(mddev); if (sb_id == ID_BITMAP_NONE || sb_id == orig_id) { mddev->bitmap_id = orig_id; return err; } pr_info("md: %s: bitmap version mismatch, switching from %d to %d\n", mdname(mddev), orig_id, sb_id); mddev->bitmap_id = sb_id; if (!mddev_set_bitmap_ops_nosysfs(mddev)) { mddev->bitmap_id = orig_id; return -ENOENT; } err = mddev->bitmap_ops->create(mddev); if (err) { mddev->bitmap_ops = NULL; mddev->bitmap_id = orig_id; } return err; } static int md_bitmap_create(struct mddev *mddev) { int err; err = md_bitmap_create_nosysfs(mddev); if (err) return err; if (!mddev_is_dm(mddev) && mddev->bitmap_ops->groups) md_bitmap_sysfs_add(mddev); return 0; } void md_bitmap_destroy_nosysfs(struct mddev *mddev) { if (!md_bitmap_registered(mddev)) return; mddev->bitmap_ops->destroy(mddev); mddev->bitmap_ops = NULL; } static void md_bitmap_destroy(struct mddev *mddev) { if (!mddev_is_dm(mddev) && mddev->bitmap_ops && mddev->bitmap_ops->groups) md_bitmap_sysfs_del(mddev); md_bitmap_destroy_nosysfs(mddev); } static void md_bitmap_set_none(struct mddev *mddev) { mddev->bitmap_id = ID_BITMAP_NONE; if (!mddev_set_bitmap_ops_nosysfs(mddev)) return; if (!mddev_is_dm(mddev) && mddev->bitmap_ops->groups) md_bitmap_sysfs_add(mddev); } int md_run(struct mddev *mddev) { int err; struct md_rdev *rdev; struct md_personality *pers; bool nowait = true; if (list_empty(&mddev->disks)) /* cannot run an array with no devices.. */ return -EINVAL; if (mddev->pers) return -EBUSY; /* Cannot run until previous stop completes properly */ if (mddev->sysfs_active) return -EBUSY; /* * Analyze all RAID superblock(s) */ if (!mddev->raid_disks) { if (!mddev->persistent) return -EINVAL; err = analyze_sbs(mddev); if (err) return -EINVAL; } if (mddev->level != LEVEL_NONE) request_module("md-level-%d", mddev->level); else if (mddev->clevel[0]) request_module("md-%s", mddev->clevel); /* * Drop all container device buffers, from now on * the only valid external interface is through the md * device. */ clear_bit(MD_HAS_SUPERBLOCK, &mddev->flags); rdev_for_each(rdev, mddev) { if (test_bit(Faulty, &rdev->flags)) continue; sync_blockdev(rdev->bdev); invalidate_bdev(rdev->bdev); if (mddev->ro != MD_RDONLY && rdev_read_only(rdev)) { mddev->ro = MD_RDONLY; if (!mddev_is_dm(mddev)) set_disk_ro(mddev->gendisk, 1); } if (rdev->sb_page) set_bit(MD_HAS_SUPERBLOCK, &mddev->flags); /* perform some consistency tests on the device. * We don't want the data to overlap the metadata, * Internal Bitmap issues have been handled elsewhere. */ if (rdev->meta_bdev) { /* Nothing to check */; } else if (rdev->data_offset < rdev->sb_start) { if (mddev->dev_sectors && rdev->data_offset + mddev->dev_sectors > rdev->sb_start) { pr_warn("md: %s: data overlaps metadata\n", mdname(mddev)); return -EINVAL; } } else { if (rdev->sb_start + rdev->sb_size/512 > rdev->data_offset) { pr_warn("md: %s: metadata overlaps data\n", mdname(mddev)); return -EINVAL; } } sysfs_notify_dirent_safe(rdev->sysfs_state); nowait = nowait && bdev_nowait(rdev->bdev); } pers = get_pers(mddev->level, mddev->clevel); if (!pers) return -EINVAL; if (mddev->level != pers->head.id) { mddev->level = pers->head.id; mddev->new_level = pers->head.id; } strscpy(mddev->clevel, pers->head.name, sizeof(mddev->clevel)); if (mddev->reshape_position != MaxSector && pers->start_reshape == NULL) { /* This personality cannot handle reshaping... */ put_pers(pers); return -EINVAL; } if (pers->sync_request) { /* Warn if this is a potentially silly * configuration. */ struct md_rdev *rdev2; int warned = 0; rdev_for_each(rdev, mddev) rdev_for_each(rdev2, mddev) { if (rdev < rdev2 && rdev->bdev->bd_disk == rdev2->bdev->bd_disk) { pr_warn("%s: WARNING: %pg appears to be on the same physical disk as %pg.\n", mdname(mddev), rdev->bdev, rdev2->bdev); warned = 1; } } if (warned) pr_warn("True protection against single-disk failure might be compromised.\n"); } /* dm-raid expect sync_thread to be frozen until resume */ if (!mddev_is_dm(mddev)) mddev->recovery = 0; /* may be over-ridden by personality */ mddev->resync_max_sectors = mddev->dev_sectors; mddev->ok_start_degraded = start_dirty_degraded; if (start_readonly && md_is_rdwr(mddev)) mddev->ro = MD_AUTO_READ; /* read-only, but switch on first write */ err = pers->run(mddev); if (err) pr_warn("md: pers->run() failed ...\n"); else if (pers->size(mddev, 0, 0) < mddev->array_sectors) { WARN_ONCE(!mddev->external_size, "%s: default size too small, but 'external_size' not in effect?\n", __func__); pr_warn("md: invalid array_size %llu > default size %llu\n", (unsigned long long)mddev->array_sectors / 2, (unsigned long long)pers->size(mddev, 0, 0) / 2); err = -EINVAL; } if (err == 0 && pers->sync_request && (mddev->bitmap_info.file || mddev->bitmap_info.offset)) { err = md_bitmap_create(mddev); if (err) pr_warn("%s: failed to create bitmap (%d)\n", mdname(mddev), err); } if (err) goto bitmap_abort; if (mddev->bitmap_info.max_write_behind > 0) { bool create_pool = false; rdev_for_each(rdev, mddev) { if (test_bit(WriteMostly, &rdev->flags) && rdev_init_serial(rdev)) create_pool = true; } if (create_pool && mddev->serial_info_pool == NULL) { mddev->serial_info_pool = mempool_create_kmalloc_pool(NR_SERIAL_INFOS, sizeof(struct serial_info)); if (!mddev->serial_info_pool) { err = -ENOMEM; goto bitmap_abort; } } } if (pers->sync_request) { if (mddev->kobj.sd && sysfs_create_group(&mddev->kobj, &md_redundancy_group)) pr_warn("md: cannot register extra attributes for %s\n", mdname(mddev)); mddev->sysfs_action = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_action"); mddev->sysfs_completed = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_completed"); mddev->sysfs_degraded = sysfs_get_dirent_safe(mddev->kobj.sd, "degraded"); } else if (mddev->ro == MD_AUTO_READ) mddev->ro = MD_RDWR; atomic_set(&mddev->max_corr_read_errors, MD_DEFAULT_MAX_CORRECTED_READ_ERRORS); mddev->safemode = 0; if (mddev_is_clustered(mddev)) mddev->safemode_delay = 0; else mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY; mddev->in_sync = 1; smp_wmb(); spin_lock(&mddev->lock); mddev->pers = pers; spin_unlock(&mddev->lock); rdev_for_each(rdev, mddev) if (rdev->raid_disk >= 0) sysfs_link_rdev(mddev, rdev); /* failure here is OK */ if (mddev->degraded && md_is_rdwr(mddev)) /* This ensures that recovering status is reported immediately * via sysfs - until a lack of spares is confirmed. */ set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); if (mddev->sb_flags) md_update_sb(mddev, 0); if (IS_ENABLED(CONFIG_MD_BITMAP) && !mddev->bitmap_info.file && !mddev->bitmap_info.offset) md_bitmap_set_none(mddev); md_new_event(); return 0; bitmap_abort: mddev_detach(mddev); if (mddev->private) pers->free(mddev, mddev->private); mddev->private = NULL; put_pers(pers); md_bitmap_destroy(mddev); return err; } EXPORT_SYMBOL_GPL(md_run); int do_md_run(struct mddev *mddev) { int err; set_bit(MD_NOT_READY, &mddev->flags); err = md_run(mddev); if (err) goto out; if (md_bitmap_registered(mddev)) { err = mddev->bitmap_ops->load(mddev); if (err) { md_bitmap_destroy(mddev); goto out; } } if (mddev_is_clustered(mddev)) md_allow_write(mddev); /* run start up tasks that require md_thread */ md_start(mddev); md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */ set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); clear_bit(MD_NOT_READY, &mddev->flags); mddev->changed = 1; kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE); sysfs_notify_dirent_safe(mddev->sysfs_state); sysfs_notify_dirent_safe(mddev->sysfs_action); sysfs_notify_dirent_safe(mddev->sysfs_degraded); out: clear_bit(MD_NOT_READY, &mddev->flags); return err; } int md_start(struct mddev *mddev) { int ret = 0; if (mddev->pers->start) { set_bit(MD_RECOVERY_WAIT, &mddev->recovery); ret = mddev->pers->start(mddev); clear_bit(MD_RECOVERY_WAIT, &mddev->recovery); md_wakeup_thread(mddev->sync_thread); } return ret; } EXPORT_SYMBOL_GPL(md_start); static int restart_array(struct mddev *mddev) { struct gendisk *disk = mddev->gendisk; struct md_rdev *rdev; bool has_journal = false; bool has_readonly = false; /* Complain if it has no devices */ if (list_empty(&mddev->disks)) return -ENXIO; if (!mddev->pers) return -EINVAL; if (md_is_rdwr(mddev)) return -EBUSY; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { if (test_bit(Journal, &rdev->flags) && !test_bit(Faulty, &rdev->flags)) has_journal = true; if (rdev_read_only(rdev)) has_readonly = true; } rcu_read_unlock(); if (test_bit(MD_HAS_JOURNAL, &mddev->flags) && !has_journal) /* Don't restart rw with journal missing/faulty */ return -EINVAL; if (has_readonly) return -EROFS; mddev->safemode = 0; mddev->ro = MD_RDWR; set_disk_ro(disk, 0); pr_debug("md: %s switched to read-write mode.\n", mdname(mddev)); /* Kick recovery or resync if necessary */ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->sync_thread); sysfs_notify_dirent_safe(mddev->sysfs_state); return 0; } static void md_clean(struct mddev *mddev) { mddev->array_sectors = 0; mddev->external_size = 0; mddev->dev_sectors = 0; mddev->raid_disks = 0; mddev->resync_offset = 0; mddev->resync_min = 0; mddev->resync_max = MaxSector; mddev->reshape_position = MaxSector; /* we still need mddev->external in export_rdev, do not clear it yet */ mddev->persistent = 0; mddev->level = LEVEL_NONE; mddev->clevel[0] = 0; /* * For legacy_async_del_gendisk mode, it can stop the array in the * middle of assembling it, then it still can access the array. So * it needs to clear MD_CLOSING. If not legacy_async_del_gendisk, * it can't open the array again after stopping it. So it doesn't * clear MD_CLOSING. */ if (legacy_async_del_gendisk && mddev->hold_active) { clear_bit(MD_CLOSING, &mddev->flags); } else { /* if UNTIL_STOP is set, it's cleared here */ mddev->hold_active = 0; /* Don't clear MD_CLOSING, or mddev can be opened again. */ mddev->flags &= BIT_ULL_MASK(MD_CLOSING); } mddev->sb_flags = 0; mddev->ro = MD_RDWR; mddev->metadata_type[0] = 0; mddev->chunk_sectors = 0; mddev->ctime = mddev->utime = 0; mddev->layout = 0; mddev->logical_block_size = 0; mddev->max_disks = 0; mddev->events = 0; mddev->can_decrease_events = 0; mddev->delta_disks = 0; mddev->reshape_backwards = 0; mddev->new_level = LEVEL_NONE; mddev->new_layout = 0; mddev->new_chunk_sectors = 0; mddev->curr_resync = MD_RESYNC_NONE; atomic64_set(&mddev->resync_mismatches, 0); mddev->suspend_lo = mddev->suspend_hi = 0; mddev->sync_speed_min = mddev->sync_speed_max = 0; mddev->recovery = 0; mddev->in_sync = 0; mddev->changed = 0; mddev->degraded = 0; mddev->safemode = 0; mddev->private = NULL; mddev->cluster_info = NULL; mddev->bitmap_info.offset = 0; mddev->bitmap_info.default_offset = 0; mddev->bitmap_info.default_space = 0; mddev->bitmap_info.chunksize = 0; mddev->bitmap_info.daemon_sleep = 0; mddev->bitmap_info.max_write_behind = 0; mddev->bitmap_info.nodes = 0; } static void __md_stop_writes(struct mddev *mddev) { timer_delete_sync(&mddev->safemode_timer); if (md_is_rdwr(mddev) || !mddev_is_dm(mddev)) { if (mddev->pers && mddev->pers->quiesce) { mddev->pers->quiesce(mddev, 1); mddev->pers->quiesce(mddev, 0); } if (md_bitmap_enabled(mddev, true)) mddev->bitmap_ops->flush(mddev); } if (md_is_rdwr(mddev) && ((!mddev->in_sync && !mddev_is_clustered(mddev)) || mddev->sb_flags)) { /* mark array as shutdown cleanly */ if (!mddev_is_clustered(mddev)) mddev->in_sync = 1; md_update_sb(mddev, 1); } /* disable policy to guarantee rdevs free resources for serialization */ clear_bit(MD_SERIALIZE_POLICY, &mddev->flags); mddev_destroy_serial_pool(mddev, NULL); } void md_stop_writes(struct mddev *mddev) { mddev_lock_nointr(mddev); set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); stop_sync_thread(mddev, true); __md_stop_writes(mddev); mddev_unlock(mddev); } EXPORT_SYMBOL_GPL(md_stop_writes); static void mddev_detach(struct mddev *mddev) { if (md_bitmap_enabled(mddev, false)) mddev->bitmap_ops->wait_behind_writes(mddev, false); if (mddev->pers && mddev->pers->quiesce && !is_md_suspended(mddev)) { mddev->pers->quiesce(mddev, 1); mddev->pers->quiesce(mddev, 0); } md_unregister_thread(mddev, &mddev->thread); /* the unplug fn references 'conf' */ if (!mddev_is_dm(mddev)) blk_sync_queue(mddev->gendisk->queue); } static void __md_stop(struct mddev *mddev) { struct md_personality *pers = mddev->pers; md_bitmap_destroy(mddev); mddev_detach(mddev); spin_lock(&mddev->lock); mddev->pers = NULL; spin_unlock(&mddev->lock); if (mddev->private) pers->free(mddev, mddev->private); mddev->private = NULL; put_pers(pers); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } void md_stop(struct mddev *mddev) { lockdep_assert_held(&mddev->reconfig_mutex); /* stop the array and free an attached data structures. * This is called from dm-raid */ __md_stop_writes(mddev); __md_stop(mddev); } EXPORT_SYMBOL_GPL(md_stop); /* ensure 'mddev->pers' exist before calling md_set_readonly() */ static int md_set_readonly(struct mddev *mddev) { int err = 0; int did_freeze = 0; if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) return -EBUSY; if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) { did_freeze = 1; set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } stop_sync_thread(mddev, false); wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); mddev_lock_nointr(mddev); if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { pr_warn("md: %s still in use.\n",mdname(mddev)); err = -EBUSY; goto out; } __md_stop_writes(mddev); if (mddev->ro == MD_RDONLY) { err = -ENXIO; goto out; } mddev->ro = MD_RDONLY; set_disk_ro(mddev->gendisk, 1); out: if (!err || did_freeze) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); sysfs_notify_dirent_safe(mddev->sysfs_state); } return err; } /* mode: * 0 - completely stop and dis-assemble array * 2 - stop but do not disassemble array */ static int do_md_stop(struct mddev *mddev, int mode) { struct gendisk *disk = mddev->gendisk; struct md_rdev *rdev; int did_freeze = 0; if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) { did_freeze = 1; set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } stop_sync_thread(mddev, true); if (mddev->sysfs_active || test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { pr_warn("md: %s still in use.\n",mdname(mddev)); if (did_freeze) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); } return -EBUSY; } if (mddev->pers) { if (!md_is_rdwr(mddev)) set_disk_ro(disk, 0); if (mode == 2 && mddev->pers->sync_request && mddev->to_remove == NULL) mddev->to_remove = &md_redundancy_group; __md_stop_writes(mddev); __md_stop(mddev); /* tell userspace to handle 'inactive' */ sysfs_notify_dirent_safe(mddev->sysfs_state); rdev_for_each(rdev, mddev) if (rdev->raid_disk >= 0) sysfs_unlink_rdev(mddev, rdev); set_capacity_and_notify(disk, 0); mddev->changed = 1; if (!md_is_rdwr(mddev)) mddev->ro = MD_RDWR; } /* * Free resources if final stop */ if (mode == 0) { pr_info("md: %s stopped.\n", mdname(mddev)); if (mddev->bitmap_info.file) { struct file *f = mddev->bitmap_info.file; spin_lock(&mddev->lock); mddev->bitmap_info.file = NULL; spin_unlock(&mddev->lock); fput(f); } mddev->bitmap_info.offset = 0; export_array(mddev); md_clean(mddev); if (!legacy_async_del_gendisk) set_bit(MD_DELETED, &mddev->flags); } md_new_event(); sysfs_notify_dirent_safe(mddev->sysfs_state); return 0; } #ifndef MODULE static void autorun_array(struct mddev *mddev) { struct md_rdev *rdev; int err; if (list_empty(&mddev->disks)) return; pr_info("md: running: "); rdev_for_each(rdev, mddev) { pr_cont("<%pg>", rdev->bdev); } pr_cont("\n"); err = do_md_run(mddev); if (err) { pr_warn("md: do_md_run() returned %d\n", err); do_md_stop(mddev, 0); } } /* * lets try to run arrays based on all disks that have arrived * until now. (those are in pending_raid_disks) * * the method: pick the first pending disk, collect all disks with * the same UUID, remove all from the pending list and put them into * the 'same_array' list. Then order this list based on superblock * update time (freshest comes first), kick out 'old' disks and * compare superblocks. If everything's fine then run it. * * If "unit" is allocated, then bump its reference count */ static void autorun_devices(int part) { struct md_rdev *rdev0, *rdev, *tmp; struct mddev *mddev; pr_info("md: autorun ...\n"); while (!list_empty(&pending_raid_disks)) { int unit; dev_t dev; LIST_HEAD(candidates); rdev0 = list_entry(pending_raid_disks.next, struct md_rdev, same_set); pr_debug("md: considering %pg ...\n", rdev0->bdev); INIT_LIST_HEAD(&candidates); rdev_for_each_list(rdev, tmp, &pending_raid_disks) if (super_90_load(rdev, rdev0, 0) >= 0) { pr_debug("md: adding %pg ...\n", rdev->bdev); list_move(&rdev->same_set, &candidates); } /* * now we have a set of devices, with all of them having * mostly sane superblocks. It's time to allocate the * mddev. */ if (part) { dev = MKDEV(mdp_major, rdev0->preferred_minor << MdpMinorShift); unit = MINOR(dev) >> MdpMinorShift; } else { dev = MKDEV(MD_MAJOR, rdev0->preferred_minor); unit = MINOR(dev); } if (rdev0->preferred_minor != unit) { pr_warn("md: unit number in %pg is bad: %d\n", rdev0->bdev, rdev0->preferred_minor); break; } mddev = md_alloc(dev, NULL); if (IS_ERR(mddev)) break; if (mddev_suspend_and_lock(mddev)) pr_warn("md: %s locked, cannot run\n", mdname(mddev)); else if (mddev->raid_disks || mddev->major_version || !list_empty(&mddev->disks)) { pr_warn("md: %s already running, cannot run %pg\n", mdname(mddev), rdev0->bdev); mddev_unlock_and_resume(mddev); } else { pr_debug("md: created %s\n", mdname(mddev)); mddev->persistent = 1; rdev_for_each_list(rdev, tmp, &candidates) { list_del_init(&rdev->same_set); if (bind_rdev_to_array(rdev, mddev)) export_rdev(rdev); } autorun_array(mddev); mddev_unlock_and_resume(mddev); } /* on success, candidates will be empty, on error * it won't... */ rdev_for_each_list(rdev, tmp, &candidates) { list_del_init(&rdev->same_set); export_rdev(rdev); } mddev_put(mddev); } pr_info("md: ... autorun DONE.\n"); } #endif /* !MODULE */ static int get_version(void __user *arg) { mdu_version_t ver; ver.major = MD_MAJOR_VERSION; ver.minor = MD_MINOR_VERSION; ver.patchlevel = MD_PATCHLEVEL_VERSION; if (copy_to_user(arg, &ver, sizeof(ver))) return -EFAULT; return 0; } static int get_array_info(struct mddev *mddev, void __user *arg) { mdu_array_info_t info; int nr,working,insync,failed,spare; struct md_rdev *rdev; nr = working = insync = failed = spare = 0; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { nr++; if (test_bit(Faulty, &rdev->flags)) failed++; else { working++; if (test_bit(In_sync, &rdev->flags)) insync++; else if (test_bit(Journal, &rdev->flags)) /* TODO: add journal count to md_u.h */ ; else spare++; } } rcu_read_unlock(); info.major_version = mddev->major_version; info.minor_version = mddev->minor_version; info.patch_version = MD_PATCHLEVEL_VERSION; info.ctime = clamp_t(time64_t, mddev->ctime, 0, U32_MAX); info.level = mddev->level; info.size = mddev->dev_sectors / 2; if (info.size != mddev->dev_sectors / 2) /* overflow */ info.size = -1; info.nr_disks = nr; info.raid_disks = mddev->raid_disks; info.md_minor = mddev->md_minor; info.not_persistent= !mddev->persistent; info.utime = clamp_t(time64_t, mddev->utime, 0, U32_MAX); info.state = 0; if (mddev->in_sync) info.state = (1<<MD_SB_CLEAN); if (mddev->bitmap && mddev->bitmap_info.offset) info.state |= (1<<MD_SB_BITMAP_PRESENT); if (mddev_is_clustered(mddev)) info.state |= (1<<MD_SB_CLUSTERED); info.active_disks = insync; info.working_disks = working; info.failed_disks = failed; info.spare_disks = spare; info.layout = mddev->layout; info.chunk_size = mddev->chunk_sectors << 9; if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; return 0; } static int get_bitmap_file(struct mddev *mddev, void __user * arg) { mdu_bitmap_file_t *file = NULL; /* too big for stack allocation */ char *ptr; int err; file = kzalloc_obj(*file, GFP_NOIO); if (!file) return -ENOMEM; err = 0; spin_lock(&mddev->lock); /* bitmap enabled */ if (mddev->bitmap_info.file) { ptr = file_path(mddev->bitmap_info.file, file->pathname, sizeof(file->pathname)); if (IS_ERR(ptr)) err = PTR_ERR(ptr); else memmove(file->pathname, ptr, sizeof(file->pathname)-(ptr-file->pathname)); } spin_unlock(&mddev->lock); if (err == 0 && copy_to_user(arg, file, sizeof(*file))) err = -EFAULT; kfree(file); return err; } static int get_disk_info(struct mddev *mddev, void __user * arg) { mdu_disk_info_t info; struct md_rdev *rdev; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; rcu_read_lock(); rdev = md_find_rdev_nr_rcu(mddev, info.number); if (rdev) { info.major = MAJOR(rdev->bdev->bd_dev); info.minor = MINOR(rdev->bdev->bd_dev); info.raid_disk = rdev->raid_disk; info.state = 0; if (test_bit(Faulty, &rdev->flags)) info.state |= (1<<MD_DISK_FAULTY); else if (test_bit(In_sync, &rdev->flags)) { info.state |= (1<<MD_DISK_ACTIVE); info.state |= (1<<MD_DISK_SYNC); } if (test_bit(Journal, &rdev->flags)) info.state |= (1<<MD_DISK_JOURNAL); if (test_bit(WriteMostly, &rdev->flags)) info.state |= (1<<MD_DISK_WRITEMOSTLY); if (test_bit(FailFast, &rdev->flags)) info.state |= (1<<MD_DISK_FAILFAST); } else { info.major = info.minor = 0; info.raid_disk = -1; info.state = (1<<MD_DISK_REMOVED); } rcu_read_unlock(); if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; return 0; } int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) { struct md_rdev *rdev; dev_t dev = MKDEV(info->major,info->minor); if (mddev_is_clustered(mddev) && !(info->state & ((1 << MD_DISK_CLUSTER_ADD) | (1 << MD_DISK_CANDIDATE)))) { pr_warn("%s: Cannot add to clustered mddev.\n", mdname(mddev)); return -EINVAL; } if (info->major != MAJOR(dev) || info->minor != MINOR(dev)) return -EOVERFLOW; if (!mddev->raid_disks) { int err; /* expecting a device which has a superblock */ rdev = md_import_device(dev, mddev->major_version, mddev->minor_version); if (IS_ERR(rdev)) { pr_warn("md: md_import_device returned %ld\n", PTR_ERR(rdev)); return PTR_ERR(rdev); } if (!list_empty(&mddev->disks)) { struct md_rdev *rdev0 = list_entry(mddev->disks.next, struct md_rdev, same_set); err = super_types[mddev->major_version] .load_super(rdev, rdev0, mddev->minor_version); if (err < 0) { pr_warn("md: %pg has different UUID to %pg\n", rdev->bdev, rdev0->bdev); export_rdev(rdev); return -EINVAL; } } err = bind_rdev_to_array(rdev, mddev); if (err) export_rdev(rdev); return err; } /* * md_add_new_disk can be used once the array is assembled * to add "hot spares". They must already have a superblock * written */ if (mddev->pers) { int err; if (!mddev->pers->hot_add_disk) { pr_warn("%s: personality does not support diskops!\n", mdname(mddev)); return -EINVAL; } if (mddev->persistent) rdev = md_import_device(dev, mddev->major_version, mddev->minor_version); else rdev = md_import_device(dev, -1, -1); if (IS_ERR(rdev)) { pr_warn("md: md_import_device returned %ld\n", PTR_ERR(rdev)); return PTR_ERR(rdev); } /* set saved_raid_disk if appropriate */ if (!mddev->persistent) { if (info->state & (1<<MD_DISK_SYNC) && info->raid_disk < mddev->raid_disks) { rdev->raid_disk = info->raid_disk; clear_bit(Bitmap_sync, &rdev->flags); } else rdev->raid_disk = -1; rdev->saved_raid_disk = rdev->raid_disk; } else super_types[mddev->major_version]. validate_super(mddev, NULL/*freshest*/, rdev); if ((info->state & (1<<MD_DISK_SYNC)) && rdev->raid_disk != info->raid_disk) { /* This was a hot-add request, but events doesn't * match, so reject it. */ export_rdev(rdev); return -EINVAL; } clear_bit(In_sync, &rdev->flags); /* just to be sure */ if (info->state & (1<<MD_DISK_WRITEMOSTLY)) set_bit(WriteMostly, &rdev->flags); else clear_bit(WriteMostly, &rdev->flags); if (info->state & (1<<MD_DISK_FAILFAST)) set_bit(FailFast, &rdev->flags); else clear_bit(FailFast, &rdev->flags); if (info->state & (1<<MD_DISK_JOURNAL)) { struct md_rdev *rdev2; bool has_journal = false; /* make sure no existing journal disk */ rdev_for_each(rdev2, mddev) { if (test_bit(Journal, &rdev2->flags)) { has_journal = true; break; } } if (has_journal || mddev->bitmap) { export_rdev(rdev); return -EBUSY; } set_bit(Journal, &rdev->flags); } /* * check whether the device shows up in other nodes */ if (mddev_is_clustered(mddev)) { if (info->state & (1 << MD_DISK_CANDIDATE)) set_bit(Candidate, &rdev->flags); else if (info->state & (1 << MD_DISK_CLUSTER_ADD)) { /* --add initiated by this node */ err = mddev->cluster_ops->add_new_disk(mddev, rdev); if (err) { export_rdev(rdev); return err; } } } rdev->raid_disk = -1; err = bind_rdev_to_array(rdev, mddev); if (err) export_rdev(rdev); if (mddev_is_clustered(mddev)) { if (info->state & (1 << MD_DISK_CANDIDATE)) { if (!err) { err = mddev->cluster_ops->new_disk_ack( mddev, err == 0); if (err) md_kick_rdev_from_array(rdev); } } else { if (err) mddev->cluster_ops->add_new_disk_cancel(mddev); else err = add_bound_rdev(rdev); } } else if (!err) err = add_bound_rdev(rdev); return err; } /* otherwise, md_add_new_disk is only allowed * for major_version==0 superblocks */ if (mddev->major_version != 0) { pr_warn("%s: ADD_NEW_DISK not supported\n", mdname(mddev)); return -EINVAL; } if (!(info->state & (1<<MD_DISK_FAULTY))) { int err; rdev = md_import_device(dev, -1, 0); if (IS_ERR(rdev)) { pr_warn("md: error, md_import_device() returned %ld\n", PTR_ERR(rdev)); return PTR_ERR(rdev); } rdev->desc_nr = info->number; if (info->raid_disk < mddev->raid_disks) rdev->raid_disk = info->raid_disk; else rdev->raid_disk = -1; if (rdev->raid_disk < mddev->raid_disks) if (info->state & (1<<MD_DISK_SYNC)) set_bit(In_sync, &rdev->flags); if (info->state & (1<<MD_DISK_WRITEMOSTLY)) set_bit(WriteMostly, &rdev->flags); if (info->state & (1<<MD_DISK_FAILFAST)) set_bit(FailFast, &rdev->flags); if (!mddev->persistent) { pr_debug("md: nonpersistent superblock ...\n"); rdev->sb_start = bdev_nr_sectors(rdev->bdev); } else rdev->sb_start = calc_dev_sboffset(rdev); rdev->sectors = rdev->sb_start; err = bind_rdev_to_array(rdev, mddev); if (err) { export_rdev(rdev); return err; } } return 0; } static int hot_remove_disk(struct mddev *mddev, dev_t dev) { struct md_rdev *rdev; if (!mddev->pers) return -ENODEV; rdev = find_rdev(mddev, dev); if (!rdev) return -ENXIO; if (rdev->raid_disk < 0) goto kick_rdev; clear_bit(Blocked, &rdev->flags); remove_and_add_spares(mddev, rdev); if (rdev->raid_disk >= 0) goto busy; kick_rdev: if (mddev_is_clustered(mddev) && mddev->cluster_ops->remove_disk(mddev, rdev)) goto busy; md_kick_rdev_from_array(rdev); set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); if (!mddev->thread) md_update_sb(mddev, 1); md_new_event(); return 0; busy: pr_debug("md: cannot remove active disk %pg from %s ...\n", rdev->bdev, mdname(mddev)); return -EBUSY; } static int hot_add_disk(struct mddev *mddev, dev_t dev) { int err; struct md_rdev *rdev; if (!mddev->pers) return -ENODEV; if (mddev->major_version != 0) { pr_warn("%s: HOT_ADD may only be used with version-0 superblocks.\n", mdname(mddev)); return -EINVAL; } if (!mddev->pers->hot_add_disk) { pr_warn("%s: personality does not support diskops!\n", mdname(mddev)); return -EINVAL; } rdev = md_import_device(dev, -1, 0); if (IS_ERR(rdev)) { pr_warn("md: error, md_import_device() returned %ld\n", PTR_ERR(rdev)); return -EINVAL; } if (mddev->persistent) rdev->sb_start = calc_dev_sboffset(rdev); else rdev->sb_start = bdev_nr_sectors(rdev->bdev); rdev->sectors = rdev->sb_start; if (test_bit(Faulty, &rdev->flags)) { pr_warn("md: can not hot-add faulty %pg disk to %s!\n", rdev->bdev, mdname(mddev)); err = -EINVAL; goto abort_export; } clear_bit(In_sync, &rdev->flags); rdev->desc_nr = -1; rdev->saved_raid_disk = -1; err = bind_rdev_to_array(rdev, mddev); if (err) goto abort_export; /* * The rest should better be atomic, we can have disk failures * noticed in interrupt contexts ... */ rdev->raid_disk = -1; set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); if (!mddev->thread) md_update_sb(mddev, 1); /* * Kick recovery, maybe this spare has to be added to the * array immediately. */ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_new_event(); return 0; abort_export: export_rdev(rdev); return err; } static int set_bitmap_file(struct mddev *mddev, int fd) { int err = 0; if (!md_bitmap_registered(mddev) || mddev->bitmap_id == ID_BITMAP_NONE) return -EINVAL; if (mddev->pers) { if (!mddev->pers->quiesce || !mddev->thread) return -EBUSY; if (mddev->recovery || mddev->sync_thread) return -EBUSY; /* we should be able to change the bitmap.. */ } if (fd >= 0) { struct inode *inode; struct file *f; if (mddev->bitmap || mddev->bitmap_info.file) return -EEXIST; /* cannot add when bitmap is present */ if (!IS_ENABLED(CONFIG_MD_BITMAP_FILE)) { pr_warn("%s: bitmap files not supported by this kernel\n", mdname(mddev)); return -EINVAL; } pr_warn("%s: using deprecated bitmap file support\n", mdname(mddev)); f = fget(fd); if (f == NULL) { pr_warn("%s: error: failed to get bitmap file\n", mdname(mddev)); return -EBADF; } inode = f->f_mapping->host; if (!S_ISREG(inode->i_mode)) { pr_warn("%s: error: bitmap file must be a regular file\n", mdname(mddev)); err = -EBADF; } else if (!(f->f_mode & FMODE_WRITE)) { pr_warn("%s: error: bitmap file must open for write\n", mdname(mddev)); err = -EBADF; } else if (atomic_read(&inode->i_writecount) != 1) { pr_warn("%s: error: bitmap file is already in use\n", mdname(mddev)); err = -EBUSY; } if (err) { fput(f); return err; } mddev->bitmap_info.file = f; mddev->bitmap_info.offset = 0; /* file overrides offset */ } else if (mddev->bitmap == NULL) return -ENOENT; /* cannot remove what isn't there */ err = 0; if (mddev->pers) { if (fd >= 0) { err = md_bitmap_create(mddev); if (!err) err = mddev->bitmap_ops->load(mddev); if (err) { md_bitmap_destroy(mddev); md_bitmap_set_none(mddev); fd = -1; } } else if (fd < 0) { md_bitmap_destroy(mddev); md_bitmap_set_none(mddev); } } if (fd < 0) { struct file *f = mddev->bitmap_info.file; if (f) { spin_lock(&mddev->lock); mddev->bitmap_info.file = NULL; spin_unlock(&mddev->lock); fput(f); } } return err; } /* * md_set_array_info is used two different ways * The original usage is when creating a new array. * In this usage, raid_disks is > 0 and it together with * level, size, not_persistent,layout,chunksize determine the * shape of the array. * This will always create an array with a type-0.90.0 superblock. * The newer usage is when assembling an array. * In this case raid_disks will be 0, and the major_version field is * use to determine which style super-blocks are to be found on the devices. * The minor and patch _version numbers are also kept incase the * super_block handler wishes to interpret them. */ int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info) { if (info->raid_disks == 0) { /* just setting version number for superblock loading */ if (info->major_version < 0 || info->major_version >= ARRAY_SIZE(super_types) || super_types[info->major_version].name == NULL) { /* maybe try to auto-load a module? */ pr_warn("md: superblock version %d not known\n", info->major_version); return -EINVAL; } mddev->major_version = info->major_version; mddev->minor_version = info->minor_version; mddev->patch_version = info->patch_version; mddev->persistent = !info->not_persistent; /* ensure mddev_put doesn't delete this now that there * is some minimal configuration. */ mddev->ctime = ktime_get_real_seconds(); return 0; } mddev->major_version = MD_MAJOR_VERSION; mddev->minor_version = MD_MINOR_VERSION; mddev->patch_version = MD_PATCHLEVEL_VERSION; mddev->ctime = ktime_get_real_seconds(); mddev->level = info->level; mddev->clevel[0] = 0; mddev->dev_sectors = 2 * (sector_t)info->size; mddev->raid_disks = info->raid_disks; /* don't set md_minor, it is determined by which /dev/md* was * openned */ if (info->state & (1<<MD_SB_CLEAN)) mddev->resync_offset = MaxSector; else mddev->resync_offset = 0; mddev->persistent = ! info->not_persistent; mddev->external = 0; mddev->layout = info->layout; if (mddev->level == 0) /* Cannot trust RAID0 layout info here */ mddev->layout = -1; mddev->chunk_sectors = info->chunk_size >> 9; if (mddev->persistent) { mddev->max_disks = MD_SB_DISKS; mddev->flags = 0; mddev->sb_flags = 0; } set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9; mddev->bitmap_info.default_space = 64*2 - (MD_SB_BYTES >> 9); mddev->bitmap_info.offset = 0; mddev->reshape_position = MaxSector; /* * Generate a 128 bit UUID */ get_random_bytes(mddev->uuid, 16); mddev->new_level = mddev->level; mddev->new_chunk_sectors = mddev->chunk_sectors; mddev->new_layout = mddev->layout; mddev->delta_disks = 0; mddev->reshape_backwards = 0; return 0; } void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors) { lockdep_assert_held(&mddev->reconfig_mutex); if (mddev->external_size) return; mddev->array_sectors = array_sectors; } EXPORT_SYMBOL(md_set_array_sectors); static int update_size(struct mddev *mddev, sector_t num_sectors) { struct md_rdev *rdev; int rv; int fit = (num_sectors == 0); sector_t old_dev_sectors = mddev->dev_sectors; if (mddev->pers->resize == NULL) return -EINVAL; /* The "num_sectors" is the number of sectors of each device that * is used. This can only make sense for arrays with redundancy. * linear and raid0 always use whatever space is available. We can only * consider changing this number if no resync or reconstruction is * happening, and if the new size is acceptable. It must fit before the * sb_start or, if that is <data_offset, it must fit before the size * of each device. If num_sectors is zero, we find the largest size * that fits. */ if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return -EBUSY; if (!md_is_rdwr(mddev)) return -EROFS; rdev_for_each(rdev, mddev) { sector_t avail = rdev->sectors; if (fit && (num_sectors == 0 || num_sectors > avail)) num_sectors = avail; if (avail < num_sectors) return -ENOSPC; } rv = mddev->pers->resize(mddev, num_sectors); if (!rv) { if (mddev_is_clustered(mddev)) mddev->cluster_ops->update_size(mddev, old_dev_sectors); else if (!mddev_is_dm(mddev)) set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); } return rv; } static int update_raid_disks(struct mddev *mddev, int raid_disks) { int rv; struct md_rdev *rdev; /* change the number of raid disks */ if (mddev->pers->check_reshape == NULL) return -EINVAL; if (!md_is_rdwr(mddev)) return -EROFS; if (raid_disks <= 0 || (mddev->max_disks && raid_disks >= mddev->max_disks)) return -EINVAL; if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) || mddev->reshape_position != MaxSector) return -EBUSY; rdev_for_each(rdev, mddev) { if (mddev->raid_disks < raid_disks && rdev->data_offset < rdev->new_data_offset) return -EINVAL; if (mddev->raid_disks > raid_disks && rdev->data_offset > rdev->new_data_offset) return -EINVAL; } mddev->delta_disks = raid_disks - mddev->raid_disks; if (mddev->delta_disks < 0) mddev->reshape_backwards = 1; else if (mddev->delta_disks > 0) mddev->reshape_backwards = 0; rv = mddev->pers->check_reshape(mddev); if (rv < 0) { mddev->delta_disks = 0; mddev->reshape_backwards = 0; } return rv; } static int get_cluster_ops(struct mddev *mddev) { xa_lock(&md_submodule); mddev->cluster_ops = xa_load(&md_submodule, ID_CLUSTER); if (mddev->cluster_ops && !try_module_get(mddev->cluster_ops->head.owner)) mddev->cluster_ops = NULL; xa_unlock(&md_submodule); return mddev->cluster_ops == NULL ? -ENOENT : 0; } static void put_cluster_ops(struct mddev *mddev) { if (!mddev->cluster_ops) return; mddev->cluster_ops->leave(mddev); module_put(mddev->cluster_ops->head.owner); mddev->cluster_ops = NULL; } /* * update_array_info is used to change the configuration of an * on-line array. * The version, ctime,level,size,raid_disks,not_persistent, layout,chunk_size * fields in the info are checked against the array. * Any differences that cannot be handled will cause an error. * Normally, only one change can be managed at a time. */ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) { int rv = 0; int cnt = 0; int state = 0; /* calculate expected state,ignoring low bits */ if (mddev->bitmap && mddev->bitmap_info.offset) state |= (1 << MD_SB_BITMAP_PRESENT); if (mddev->major_version != info->major_version || mddev->minor_version != info->minor_version || /* mddev->patch_version != info->patch_version || */ mddev->ctime != info->ctime || mddev->level != info->level || /* mddev->layout != info->layout || */ mddev->persistent != !info->not_persistent || mddev->chunk_sectors != info->chunk_size >> 9 || /* ignore bottom 8 bits of state, and allow SB_BITMAP_PRESENT to change */ ((state^info->state) & 0xfffffe00) ) return -EINVAL; /* Check there is only one change */ if (info->size >= 0 && mddev->dev_sectors / 2 != info->size) cnt++; if (mddev->raid_disks != info->raid_disks) cnt++; if (mddev->layout != info->layout) cnt++; if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) cnt++; if (cnt == 0) return 0; if (cnt > 1) return -EINVAL; if (mddev->layout != info->layout) { /* Change layout * we don't need to do anything at the md level, the * personality will take care of it all. */ if (mddev->pers->check_reshape == NULL) return -EINVAL; else { mddev->new_layout = info->layout; rv = mddev->pers->check_reshape(mddev); if (rv) mddev->new_layout = mddev->layout; return rv; } } if (info->size >= 0 && mddev->dev_sectors / 2 != info->size) rv = update_size(mddev, (sector_t)info->size * 2); if (mddev->raid_disks != info->raid_disks) rv = update_raid_disks(mddev, info->raid_disks); if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) { if (mddev->pers->quiesce == NULL || mddev->thread == NULL) { rv = -EINVAL; goto err; } if (mddev->recovery || mddev->sync_thread) { rv = -EBUSY; goto err; } if (info->state & (1<<MD_SB_BITMAP_PRESENT)) { /* add the bitmap */ if (mddev->bitmap) { rv = -EEXIST; goto err; } if (mddev->bitmap_info.default_offset == 0) { rv = -EINVAL; goto err; } mddev->bitmap_info.offset = mddev->bitmap_info.default_offset; mddev->bitmap_info.space = mddev->bitmap_info.default_space; mddev->bitmap_id = ID_BITMAP; rv = md_bitmap_create(mddev); if (!rv) rv = mddev->bitmap_ops->load(mddev); if (rv) { md_bitmap_destroy(mddev); mddev->bitmap_info.offset = 0; md_bitmap_set_none(mddev); } } else { struct md_bitmap_stats stats; rv = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats); if (rv) goto err; if (stats.file) { rv = -EINVAL; goto err; } if (mddev->bitmap_info.nodes) { /* hold PW on all the bitmap lock */ if (mddev->cluster_ops->lock_all_bitmaps(mddev) <= 0) { pr_warn("md: can't change bitmap to none since the array is in use by more than one node\n"); rv = -EPERM; mddev->cluster_ops->unlock_all_bitmaps(mddev); goto err; } mddev->bitmap_info.nodes = 0; put_cluster_ops(mddev); mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY; } md_bitmap_destroy(mddev); mddev->bitmap_info.offset = 0; md_bitmap_set_none(mddev); } } md_update_sb(mddev, 1); return rv; err: return rv; } static int set_disk_faulty(struct mddev *mddev, dev_t dev) { struct md_rdev *rdev; int err = 0; if (mddev->pers == NULL) return -ENODEV; rcu_read_lock(); rdev = md_find_rdev_rcu(mddev, dev); if (!rdev) err = -ENODEV; else { md_error(mddev, rdev); if (test_bit(MD_BROKEN, &mddev->flags)) err = -EBUSY; } rcu_read_unlock(); return err; } /* * We have a problem here : there is no easy way to give a CHS * virtual geometry. We currently pretend that we have a 2 heads * 4 sectors (with a BIG number of cylinders...). This drives * dosfs just mad... ;-) */ static int md_getgeo(struct gendisk *disk, struct hd_geometry *geo) { struct mddev *mddev = disk->private_data; geo->heads = 2; geo->sectors = 4; geo->cylinders = mddev->array_sectors / 8; return 0; } static inline int md_ioctl_valid(unsigned int cmd) { switch (cmd) { case GET_ARRAY_INFO: case GET_DISK_INFO: case RAID_VERSION: return 0; case ADD_NEW_DISK: case GET_BITMAP_FILE: case HOT_ADD_DISK: case HOT_REMOVE_DISK: case RESTART_ARRAY_RW: case RUN_ARRAY: case SET_ARRAY_INFO: case SET_BITMAP_FILE: case SET_DISK_FAULTY: case STOP_ARRAY: case STOP_ARRAY_RO: case CLUSTERED_DISK_NACK: if (!capable(CAP_SYS_ADMIN)) return -EACCES; return 0; default: return -ENOTTY; } } static bool md_ioctl_need_suspend(unsigned int cmd) { switch (cmd) { case ADD_NEW_DISK: case HOT_ADD_DISK: case HOT_REMOVE_DISK: case SET_BITMAP_FILE: case SET_ARRAY_INFO: return true; default: return false; } } static int __md_set_array_info(struct mddev *mddev, void __user *argp) { mdu_array_info_t info; int err; if (!argp) memset(&info, 0, sizeof(info)); else if (copy_from_user(&info, argp, sizeof(info))) return -EFAULT; if (mddev->pers) { err = update_array_info(mddev, &info); if (err) pr_warn("md: couldn't update array info. %d\n", err); return err; } if (!list_empty(&mddev->disks)) { pr_warn("md: array %s already has disks!\n", mdname(mddev)); return -EBUSY; } if (mddev->raid_disks) { pr_warn("md: array %s already initialised!\n", mdname(mddev)); return -EBUSY; } err = md_set_array_info(mddev, &info); if (err) pr_warn("md: couldn't set array info. %d\n", err); return err; } static int md_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { int err = 0; void __user *argp = (void __user *)arg; struct mddev *mddev = NULL; err = md_ioctl_valid(cmd); if (err) return err; /* * Commands dealing with the RAID driver but not any * particular array: */ if (cmd == RAID_VERSION) return get_version(argp); /* * Commands creating/starting a new array: */ mddev = bdev->bd_disk->private_data; /* Some actions do not requires the mutex */ switch (cmd) { case GET_ARRAY_INFO: if (!mddev->raid_disks && !mddev->external) return -ENODEV; return get_array_info(mddev, argp); case GET_DISK_INFO: if (!mddev->raid_disks && !mddev->external) return -ENODEV; return get_disk_info(mddev, argp); case SET_DISK_FAULTY: return set_disk_faulty(mddev, new_decode_dev(arg)); case GET_BITMAP_FILE: return get_bitmap_file(mddev, argp); } if (cmd == STOP_ARRAY || cmd == STOP_ARRAY_RO) { /* Need to flush page cache, and ensure no-one else opens * and writes */ err = mddev_set_closing_and_sync_blockdev(mddev, 1); if (err) return err; } if (!md_is_rdwr(mddev)) flush_work(&mddev->sync_work); err = md_ioctl_need_suspend(cmd) ? mddev_suspend_and_lock(mddev) : mddev_lock(mddev); if (err) { pr_debug("md: ioctl lock interrupted, reason %d, cmd %d\n", err, cmd); goto out; } if (cmd == SET_ARRAY_INFO) { err = __md_set_array_info(mddev, argp); goto unlock; } /* * Commands querying/configuring an existing array: */ /* if we are not initialised yet, only ADD_NEW_DISK, STOP_ARRAY, * RUN_ARRAY, and GET_ and SET_BITMAP_FILE are allowed */ if ((!mddev->raid_disks && !mddev->external) && cmd != ADD_NEW_DISK && cmd != STOP_ARRAY && cmd != RUN_ARRAY && cmd != SET_BITMAP_FILE && cmd != GET_BITMAP_FILE) { err = -ENODEV; goto unlock; } /* * Commands even a read-only array can execute: */ switch (cmd) { case RESTART_ARRAY_RW: err = restart_array(mddev); goto unlock; case STOP_ARRAY: err = do_md_stop(mddev, 0); goto unlock; case STOP_ARRAY_RO: if (mddev->pers) err = md_set_readonly(mddev); goto unlock; case HOT_REMOVE_DISK: err = hot_remove_disk(mddev, new_decode_dev(arg)); goto unlock; case ADD_NEW_DISK: /* We can support ADD_NEW_DISK on read-only arrays * only if we are re-adding a preexisting device. * So require mddev->pers and MD_DISK_SYNC. */ if (mddev->pers) { mdu_disk_info_t info; if (copy_from_user(&info, argp, sizeof(info))) err = -EFAULT; else if (!(info.state & (1<<MD_DISK_SYNC))) /* Need to clear read-only for this */ break; else err = md_add_new_disk(mddev, &info); goto unlock; } break; } /* * The remaining ioctls are changing the state of the * superblock, so we do not allow them on read-only arrays. */ if (!md_is_rdwr(mddev) && mddev->pers) { if (mddev->ro != MD_AUTO_READ) { err = -EROFS; goto unlock; } mddev->ro = MD_RDWR; sysfs_notify_dirent_safe(mddev->sysfs_state); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); /* mddev_unlock will wake thread */ /* If a device failed while we were read-only, we * need to make sure the metadata is updated now. */ if (test_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags)) { mddev_unlock(mddev); wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags) && !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); mddev_lock_nointr(mddev); } } switch (cmd) { case ADD_NEW_DISK: { mdu_disk_info_t info; if (copy_from_user(&info, argp, sizeof(info))) err = -EFAULT; else err = md_add_new_disk(mddev, &info); goto unlock; } case CLUSTERED_DISK_NACK: if (mddev_is_clustered(mddev)) mddev->cluster_ops->new_disk_ack(mddev, false); else err = -EINVAL; goto unlock; case HOT_ADD_DISK: err = hot_add_disk(mddev, new_decode_dev(arg)); goto unlock; case RUN_ARRAY: err = do_md_run(mddev); goto unlock; case SET_BITMAP_FILE: err = set_bitmap_file(mddev, (int)arg); goto unlock; default: err = -EINVAL; goto unlock; } unlock: if (mddev->hold_active == UNTIL_IOCTL && err != -EINVAL) mddev->hold_active = 0; md_ioctl_need_suspend(cmd) ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev); out: if (cmd == STOP_ARRAY_RO || (err && cmd == STOP_ARRAY)) clear_bit(MD_CLOSING, &mddev->flags); return err; } #ifdef CONFIG_COMPAT static int md_compat_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { switch (cmd) { case HOT_REMOVE_DISK: case HOT_ADD_DISK: case SET_DISK_FAULTY: case SET_BITMAP_FILE: /* These take in integer arg, do not convert */ break; default: arg = (unsigned long)compat_ptr(arg); break; } return md_ioctl(bdev, mode, cmd, arg); } #endif /* CONFIG_COMPAT */ static int md_set_read_only(struct block_device *bdev, bool ro) { struct mddev *mddev = bdev->bd_disk->private_data; int err; err = mddev_lock(mddev); if (err) return err; if (!mddev->raid_disks && !mddev->external) { err = -ENODEV; goto out_unlock; } /* * Transitioning to read-auto need only happen for arrays that call * md_write_start and which are not ready for writes yet. */ if (!ro && mddev->ro == MD_RDONLY && mddev->pers) { err = restart_array(mddev); if (err) goto out_unlock; mddev->ro = MD_AUTO_READ; } out_unlock: mddev_unlock(mddev); return err; } static int md_open(struct gendisk *disk, blk_mode_t mode) { struct mddev *mddev; int err; spin_lock(&all_mddevs_lock); mddev = mddev_get(disk->private_data); spin_unlock(&all_mddevs_lock); if (!mddev) return -ENODEV; err = mutex_lock_interruptible(&mddev->open_mutex); if (err) goto out; err = -ENODEV; if (test_bit(MD_CLOSING, &mddev->flags)) goto out_unlock; atomic_inc(&mddev->openers); mutex_unlock(&mddev->open_mutex); disk_check_media_change(disk); return 0; out_unlock: mutex_unlock(&mddev->open_mutex); out: mddev_put(mddev); return err; } static void md_release(struct gendisk *disk) { struct mddev *mddev = disk->private_data; BUG_ON(!mddev); atomic_dec(&mddev->openers); mddev_put(mddev); } static unsigned int md_check_events(struct gendisk *disk, unsigned int clearing) { struct mddev *mddev = disk->private_data; unsigned int ret = 0; if (mddev->changed) ret = DISK_EVENT_MEDIA_CHANGE; mddev->changed = 0; return ret; } static void md_free_disk(struct gendisk *disk) { struct mddev *mddev = disk->private_data; mddev_free(mddev); } const struct block_device_operations md_fops = { .owner = THIS_MODULE, .submit_bio = md_submit_bio, .open = md_open, .release = md_release, .ioctl = md_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = md_compat_ioctl, #endif .getgeo = md_getgeo, .check_events = md_check_events, .set_read_only = md_set_read_only, .free_disk = md_free_disk, }; static int md_thread(void *arg) { struct md_thread *thread = arg; /* * md_thread is a 'system-thread', it's priority should be very * high. We avoid resource deadlocks individually in each * raid personality. (RAID5 does preallocation) We also use RR and * the very same RT priority as kswapd, thus we will never get * into a priority inversion deadlock. * * we definitely have to have equal or higher priority than * bdflush, otherwise bdflush will deadlock if there are too * many dirty RAID5 blocks. */ allow_signal(SIGKILL); while (!kthread_should_stop()) { /* We need to wait INTERRUPTIBLE so that * we don't add to the load-average. * That means we need to be sure no signals are * pending */ if (signal_pending(current)) flush_signals(current); wait_event_interruptible_timeout (thread->wqueue, test_bit(THREAD_WAKEUP, &thread->flags) || kthread_should_stop() || kthread_should_park(), thread->timeout); clear_bit(THREAD_WAKEUP, &thread->flags); if (kthread_should_park()) kthread_parkme(); if (!kthread_should_stop()) thread->run(thread); } return 0; } static void md_wakeup_thread_directly(struct md_thread __rcu **thread) { struct md_thread *t; rcu_read_lock(); t = rcu_dereference(*thread); if (t) wake_up_process(t->tsk); rcu_read_unlock(); } void __md_wakeup_thread(struct md_thread __rcu *thread) { struct md_thread *t; t = rcu_dereference(thread); if (t) { pr_debug("md: waking up MD thread %s.\n", t->tsk->comm); set_bit(THREAD_WAKEUP, &t->flags); if (wq_has_sleeper(&t->wqueue)) wake_up(&t->wqueue); } } EXPORT_SYMBOL(__md_wakeup_thread); struct md_thread *md_register_thread(void (*run) (struct md_thread *), struct mddev *mddev, const char *name) { struct md_thread *thread; thread = kzalloc_obj(struct md_thread); if (!thread) return NULL; init_waitqueue_head(&thread->wqueue); thread->run = run; thread->mddev = mddev; thread->timeout = MAX_SCHEDULE_TIMEOUT; thread->tsk = kthread_run(md_thread, thread, "%s_%s", mdname(thread->mddev), name); if (IS_ERR(thread->tsk)) { kfree(thread); return NULL; } return thread; } EXPORT_SYMBOL(md_register_thread); void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **threadp) { struct md_thread *thread = rcu_dereference_protected(*threadp, lockdep_is_held(&mddev->reconfig_mutex)); if (!thread) return; rcu_assign_pointer(*threadp, NULL); synchronize_rcu(); pr_debug("interrupting MD-thread pid %d\n", task_pid_nr(thread->tsk)); kthread_stop(thread->tsk); kfree(thread); } EXPORT_SYMBOL(md_unregister_thread); void md_error(struct mddev *mddev, struct md_rdev *rdev) { if (!rdev || test_bit(Faulty, &rdev->flags)) return; if (!mddev->pers || !mddev->pers->error_handler) return; mddev->pers->error_handler(mddev, rdev); if (mddev->pers->head.id == ID_RAID0 || mddev->pers->head.id == ID_LINEAR) return; if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags)) set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); sysfs_notify_dirent_safe(rdev->sysfs_state); set_bit(MD_RECOVERY_INTR, &mddev->recovery); if (!test_bit(MD_BROKEN, &mddev->flags)) { set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); } if (mddev->event_work.func) queue_work(md_misc_wq, &mddev->event_work); md_new_event(); } EXPORT_SYMBOL(md_error); /* seq_file implementation /proc/mdstat */ static void status_unused(struct seq_file *seq) { int i = 0; struct md_rdev *rdev; seq_printf(seq, "unused devices: "); list_for_each_entry(rdev, &pending_raid_disks, same_set) { i++; seq_printf(seq, "%pg ", rdev->bdev); } if (!i) seq_printf(seq, "<none>"); seq_printf(seq, "\n"); } static void status_personalities(struct seq_file *seq) { struct md_submodule_head *head; unsigned long i; seq_puts(seq, "Personalities : "); xa_lock(&md_submodule); xa_for_each(&md_submodule, i, head) if (head->type == MD_PERSONALITY) seq_printf(seq, "[%s] ", head->name); xa_unlock(&md_submodule); seq_puts(seq, "\n"); } static int status_resync(struct seq_file *seq, struct mddev *mddev) { sector_t max_sectors, resync, res; unsigned long dt, db = 0; sector_t rt, curr_mark_cnt, resync_mark_cnt; int scale, recovery_active; unsigned int per_milli; if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) || test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) max_sectors = mddev->resync_max_sectors; else max_sectors = mddev->dev_sectors; resync = mddev->curr_resync; if (resync < MD_RESYNC_ACTIVE) { if (test_bit(MD_RECOVERY_DONE, &mddev->recovery)) /* Still cleaning up */ resync = max_sectors; } else if (resync > max_sectors) { resync = max_sectors; } else { res = atomic_read(&mddev->recovery_active); /* * Resync has started, but the subtraction has overflowed or * yielded one of the special values. Force it to active to * ensure the status reports an active resync. */ if (resync < res || resync - res < MD_RESYNC_ACTIVE) resync = MD_RESYNC_ACTIVE; else resync -= res; } if (resync == MD_RESYNC_NONE) { if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery)) { struct md_rdev *rdev; rdev_for_each(rdev, mddev) if (rdev->raid_disk >= 0 && !test_bit(Faulty, &rdev->flags) && rdev->recovery_offset != MaxSector && rdev->recovery_offset) { seq_printf(seq, "\trecover=REMOTE"); return 1; } if (mddev->reshape_position != MaxSector) seq_printf(seq, "\treshape=REMOTE"); else seq_printf(seq, "\tresync=REMOTE"); return 1; } if (mddev->resync_offset < MaxSector) { seq_printf(seq, "\tresync=PENDING"); return 1; } return 0; } if (resync < MD_RESYNC_ACTIVE) { seq_printf(seq, "\tresync=DELAYED"); return 1; } WARN_ON(max_sectors == 0); /* Pick 'scale' such that (resync>>scale)*1000 will fit * in a sector_t, and (max_sectors>>scale) will fit in a * u32, as those are the requirements for sector_div. * Thus 'scale' must be at least 10 */ scale = 10; if (sizeof(sector_t) > sizeof(unsigned long)) { while ( max_sectors/2 > (1ULL<<(scale+32))) scale++; } res = (resync>>scale)*1000; sector_div(res, (u32)((max_sectors>>scale)+1)); per_milli = res; { int i, x = per_milli/50, y = 20-x; seq_printf(seq, "["); for (i = 0; i < x; i++) seq_printf(seq, "="); seq_printf(seq, ">"); for (i = 0; i < y; i++) seq_printf(seq, "."); seq_printf(seq, "] "); } seq_printf(seq, " %s =%3u.%u%% (%llu/%llu)", (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)? "reshape" : (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)? "check" : (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ? "resync" : "recovery"))), per_milli/10, per_milli % 10, (unsigned long long) resync/2, (unsigned long long) max_sectors/2); /* * dt: time from mark until now * db: blocks written from mark until now * rt: remaining time * * rt is a sector_t, which is always 64bit now. We are keeping * the original algorithm, but it is not really necessary. * * Original algorithm: * So we divide before multiply in case it is 32bit and close * to the limit. * We scale the divisor (db) by 32 to avoid losing precision * near the end of resync when the number of remaining sectors * is close to 'db'. * We then divide rt by 32 after multiplying by db to compensate. * The '+1' avoids division by zero if db is very small. */ dt = ((jiffies - mddev->resync_mark) / HZ); if (!dt) dt++; curr_mark_cnt = mddev->curr_mark_cnt; recovery_active = atomic_read(&mddev->recovery_active); resync_mark_cnt = mddev->resync_mark_cnt; if (curr_mark_cnt >= (recovery_active + resync_mark_cnt)) db = curr_mark_cnt - (recovery_active + resync_mark_cnt); rt = max_sectors - resync; /* number of remaining sectors */ rt = div64_u64(rt, db/32+1); rt *= dt; rt >>= 5; seq_printf(seq, " finish=%lu.%lumin", (unsigned long)rt / 60, ((unsigned long)rt % 60)/6); seq_printf(seq, " speed=%ldK/sec", db/2/dt); return 1; } static void *md_seq_start(struct seq_file *seq, loff_t *pos) __acquires(&all_mddevs_lock) { seq->poll_event = atomic_read(&md_event_count); spin_lock(&all_mddevs_lock); return seq_list_start_head(&all_mddevs, *pos); } static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &all_mddevs, pos); } static void md_seq_stop(struct seq_file *seq, void *v) __releases(&all_mddevs_lock) { spin_unlock(&all_mddevs_lock); } static void md_bitmap_status(struct seq_file *seq, struct mddev *mddev) { struct md_bitmap_stats stats; unsigned long used_pages; unsigned long chunk_kb; int err; if (!md_bitmap_enabled(mddev, false)) return; err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats); if (err) return; chunk_kb = mddev->bitmap_info.chunksize >> 10; used_pages = stats.pages - stats.missing_pages; seq_printf(seq, "bitmap: %lu/%lu pages [%luKB], %lu%s chunk", used_pages, stats.pages, used_pages << (PAGE_SHIFT - 10), chunk_kb ? chunk_kb : mddev->bitmap_info.chunksize, chunk_kb ? "KB" : "B"); if (stats.file) { seq_puts(seq, ", file: "); seq_file_path(seq, stats.file, " \t\n"); } seq_putc(seq, '\n'); } static int md_seq_show(struct seq_file *seq, void *v) { struct mddev *mddev; sector_t sectors; struct md_rdev *rdev; if (v == &all_mddevs) { status_personalities(seq); if (list_empty(&all_mddevs)) status_unused(seq); return 0; } mddev = list_entry(v, struct mddev, all_mddevs); if (!mddev_get(mddev)) return 0; spin_unlock(&all_mddevs_lock); /* prevent bitmap to be freed after checking */ mutex_lock(&mddev->bitmap_info.mutex); spin_lock(&mddev->lock); if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) { seq_printf(seq, "%s : ", mdname(mddev)); if (mddev->pers) { if (test_bit(MD_BROKEN, &mddev->flags)) seq_printf(seq, "broken"); else seq_printf(seq, "active"); if (mddev->ro == MD_RDONLY) seq_printf(seq, " (read-only)"); if (mddev->ro == MD_AUTO_READ) seq_printf(seq, " (auto-read-only)"); seq_printf(seq, " %s", mddev->pers->head.name); } else { seq_printf(seq, "inactive"); } sectors = 0; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { seq_printf(seq, " %pg[%d]", rdev->bdev, rdev->desc_nr); if (test_bit(WriteMostly, &rdev->flags)) seq_printf(seq, "(W)"); if (test_bit(Journal, &rdev->flags)) seq_printf(seq, "(J)"); if (test_bit(Faulty, &rdev->flags)) { seq_printf(seq, "(F)"); continue; } if (rdev->raid_disk < 0) seq_printf(seq, "(S)"); /* spare */ if (test_bit(Replacement, &rdev->flags)) seq_printf(seq, "(R)"); sectors += rdev->sectors; } rcu_read_unlock(); if (!list_empty(&mddev->disks)) { if (mddev->pers) seq_printf(seq, "\n %llu blocks", (unsigned long long) mddev->array_sectors / 2); else seq_printf(seq, "\n %llu blocks", (unsigned long long)sectors / 2); } if (mddev->persistent) { if (mddev->major_version != 0 || mddev->minor_version != 90) { seq_printf(seq," super %d.%d", mddev->major_version, mddev->minor_version); } } else if (mddev->external) seq_printf(seq, " super external:%s", mddev->metadata_type); else seq_printf(seq, " super non-persistent"); if (mddev->pers) { mddev->pers->status(seq, mddev); seq_printf(seq, "\n "); if (mddev->pers->sync_request) { if (status_resync(seq, mddev)) seq_printf(seq, "\n "); } } else seq_printf(seq, "\n "); md_bitmap_status(seq, mddev); seq_printf(seq, "\n"); } spin_unlock(&mddev->lock); mutex_unlock(&mddev->bitmap_info.mutex); spin_lock(&all_mddevs_lock); if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs)) status_unused(seq); mddev_put_locked(mddev); return 0; } static const struct seq_operations md_seq_ops = { .start = md_seq_start, .next = md_seq_next, .stop = md_seq_stop, .show = md_seq_show, }; static int md_seq_open(struct inode *inode, struct file *file) { struct seq_file *seq; int error; error = seq_open(file, &md_seq_ops); if (error) return error; seq = file->private_data; seq->poll_event = atomic_read(&md_event_count); return error; } static int md_unloading; static __poll_t mdstat_poll(struct file *filp, poll_table *wait) { struct seq_file *seq = filp->private_data; __poll_t mask; if (md_unloading) return EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; poll_wait(filp, &md_event_waiters, wait); /* always allow read */ mask = EPOLLIN | EPOLLRDNORM; if (seq->poll_event != atomic_read(&md_event_count)) mask |= EPOLLERR | EPOLLPRI; return mask; } static const struct proc_ops mdstat_proc_ops = { .proc_open = md_seq_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = mdstat_poll, }; int register_md_submodule(struct md_submodule_head *msh) { return xa_insert(&md_submodule, msh->id, msh, GFP_KERNEL); } EXPORT_SYMBOL_GPL(register_md_submodule); void unregister_md_submodule(struct md_submodule_head *msh) { xa_erase(&md_submodule, msh->id); } EXPORT_SYMBOL_GPL(unregister_md_submodule); int md_setup_cluster(struct mddev *mddev, int nodes) { int ret = get_cluster_ops(mddev); if (ret) { request_module("md-cluster"); ret = get_cluster_ops(mddev); } /* ensure module won't be unloaded */ if (ret) { pr_warn("can't find md-cluster module or get its reference.\n"); return ret; } ret = mddev->cluster_ops->join(mddev, nodes); if (!ret) mddev->safemode_delay = 0; return ret; } void md_cluster_stop(struct mddev *mddev) { put_cluster_ops(mddev); } static bool is_rdev_holder_idle(struct md_rdev *rdev, bool init) { unsigned long last_events = rdev->last_events; if (!bdev_is_partition(rdev->bdev)) return true; /* * If rdev is partition, and user doesn't issue IO to the array, the * array is still not idle if user issues IO to other partitions. */ rdev->last_events = part_stat_read_accum(rdev->bdev->bd_disk->part0, sectors) - part_stat_read_accum(rdev->bdev, sectors); return init || rdev->last_events <= last_events; } /* * mddev is idle if following conditions are matched since last check: * 1) mddev doesn't have normal IO completed; * 2) mddev doesn't have inflight normal IO; * 3) if any member disk is partition, and other partitions don't have IO * completed; * * Noted this checking rely on IO accounting is enabled. */ static bool is_mddev_idle(struct mddev *mddev, int init) { unsigned long last_events = mddev->normal_io_events; struct gendisk *disk; struct md_rdev *rdev; bool idle = true; disk = mddev_is_dm(mddev) ? mddev->dm_gendisk : mddev->gendisk; if (!disk) return true; mddev->normal_io_events = part_stat_read_accum(disk->part0, sectors); if (!init && (mddev->normal_io_events > last_events || bdev_count_inflight(disk->part0))) idle = false; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) if (!is_rdev_holder_idle(rdev, init)) idle = false; rcu_read_unlock(); return idle; } void md_done_sync(struct mddev *mddev, int blocks) { /* another "blocks" (512byte) blocks have been synced */ atomic_sub(blocks, &mddev->recovery_active); wake_up(&mddev->recovery_wait); } EXPORT_SYMBOL(md_done_sync); void md_sync_error(struct mddev *mddev) { // stop recovery, signal do_sync .... set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_wakeup_thread(mddev->thread); } EXPORT_SYMBOL(md_sync_error); /* md_write_start(mddev, bi) * If we need to update some array metadata (e.g. 'active' flag * in superblock) before writing, schedule a superblock update * and wait for it to complete. * A return value of 'false' means that the write wasn't recorded * and cannot proceed as the array is being suspend. */ void md_write_start(struct mddev *mddev, struct bio *bi) { int did_change = 0; if (bio_data_dir(bi) != WRITE) return; BUG_ON(mddev->ro == MD_RDONLY); if (mddev->ro == MD_AUTO_READ) { /* need to switch to read/write */ mddev->ro = MD_RDWR; set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); md_wakeup_thread(mddev->sync_thread); did_change = 1; } rcu_read_lock(); percpu_ref_get(&mddev->writes_pending); smp_mb(); /* Match smp_mb in set_in_sync() */ if (mddev->safemode == 1) mddev->safemode = 0; /* sync_checkers is always 0 when writes_pending is in per-cpu mode */ if (mddev->in_sync || mddev->sync_checkers) { spin_lock(&mddev->lock); if (mddev->in_sync) { mddev->in_sync = 0; set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags); set_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags); md_wakeup_thread(mddev->thread); did_change = 1; } spin_unlock(&mddev->lock); } rcu_read_unlock(); if (did_change) sysfs_notify_dirent_safe(mddev->sysfs_state); if (!test_bit(MD_HAS_SUPERBLOCK, &mddev->flags)) return; wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); } EXPORT_SYMBOL(md_write_start); /* md_write_inc can only be called when md_write_start() has * already been called at least once of the current request. * It increments the counter and is useful when a single request * is split into several parts. Each part causes an increment and * so needs a matching md_write_end(). * Unlike md_write_start(), it is safe to call md_write_inc() inside * a spinlocked region. */ void md_write_inc(struct mddev *mddev, struct bio *bi) { if (bio_data_dir(bi) != WRITE) return; WARN_ON_ONCE(mddev->in_sync || !md_is_rdwr(mddev)); percpu_ref_get(&mddev->writes_pending); } EXPORT_SYMBOL(md_write_inc); void md_write_end(struct mddev *mddev) { percpu_ref_put(&mddev->writes_pending); if (mddev->safemode == 2) md_wakeup_thread(mddev->thread); else if (mddev->safemode_delay) /* The roundup() ensures this only performs locking once * every ->safemode_delay jiffies */ mod_timer(&mddev->safemode_timer, roundup(jiffies, mddev->safemode_delay) + mddev->safemode_delay); } EXPORT_SYMBOL(md_write_end); /* This is used by raid0 and raid10 */ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio, sector_t start, sector_t size) { struct bio *discard_bio = NULL; __blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO, &discard_bio); if (!discard_bio) return; bio_chain(discard_bio, bio); bio_clone_blkg_association(discard_bio, bio); mddev_trace_remap(mddev, discard_bio, bio->bi_iter.bi_sector); submit_bio_noacct(discard_bio); } EXPORT_SYMBOL_GPL(md_submit_discard_bio); static void md_bitmap_start(struct mddev *mddev, struct md_io_clone *md_io_clone) { md_bitmap_fn *fn = unlikely(md_io_clone->rw == STAT_DISCARD) ? mddev->bitmap_ops->start_discard : mddev->bitmap_ops->start_write; if (mddev->pers->bitmap_sector) mddev->pers->bitmap_sector(mddev, &md_io_clone->offset, &md_io_clone->sectors); fn(mddev, md_io_clone->offset, md_io_clone->sectors); } static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone) { md_bitmap_fn *fn = unlikely(md_io_clone->rw == STAT_DISCARD) ? mddev->bitmap_ops->end_discard : mddev->bitmap_ops->end_write; fn(mddev, md_io_clone->offset, md_io_clone->sectors); } static void md_end_clone_io(struct bio *bio) { struct md_io_clone *md_io_clone = container_of(bio, struct md_io_clone, bio_clone); struct bio *orig_bio = md_io_clone->orig_bio; struct mddev *mddev = md_io_clone->mddev; struct completion *reshape_completion = bio->bi_private; if (bio_data_dir(orig_bio) == WRITE && md_bitmap_enabled(mddev, false)) md_bitmap_end(mddev, md_io_clone); if (bio->bi_status && !orig_bio->bi_status) orig_bio->bi_status = bio->bi_status; if (md_io_clone->start_time) bio_end_io_acct(orig_bio, md_io_clone->start_time); bio_put(bio); if (unlikely(reshape_completion)) complete(reshape_completion); else bio_endio(orig_bio); percpu_ref_put(&mddev->active_io); } static void md_clone_bio(struct mddev *mddev, struct bio **bio) { struct block_device *bdev = (*bio)->bi_bdev; struct md_io_clone *md_io_clone; struct bio *clone = bio_alloc_clone(bdev, *bio, GFP_NOIO, &mddev->io_clone_set); md_io_clone = container_of(clone, struct md_io_clone, bio_clone); md_io_clone->orig_bio = *bio; md_io_clone->mddev = mddev; if (blk_queue_io_stat(bdev->bd_disk->queue)) md_io_clone->start_time = bio_start_io_acct(*bio); if (bio_data_dir(*bio) == WRITE && md_bitmap_enabled(mddev, false)) { md_io_clone->offset = (*bio)->bi_iter.bi_sector; md_io_clone->sectors = bio_sectors(*bio); md_io_clone->rw = op_stat_group(bio_op(*bio)); md_bitmap_start(mddev, md_io_clone); } clone->bi_end_io = md_end_clone_io; clone->bi_private = NULL; *bio = clone; } void md_account_bio(struct mddev *mddev, struct bio **bio) { percpu_ref_get(&mddev->active_io); md_clone_bio(mddev, bio); } EXPORT_SYMBOL_GPL(md_account_bio); /* md_allow_write(mddev) * Calling this ensures that the array is marked 'active' so that writes * may proceed without blocking. It is important to call this before * attempting a GFP_KERNEL allocation while holding the mddev lock. * Must be called with mddev_lock held. */ void md_allow_write(struct mddev *mddev) { if (!mddev->pers) return; if (!md_is_rdwr(mddev)) return; if (!mddev->pers->sync_request) return; spin_lock(&mddev->lock); if (mddev->in_sync) { mddev->in_sync = 0; set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags); set_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags); if (mddev->safemode_delay && mddev->safemode == 0) mddev->safemode = 1; spin_unlock(&mddev->lock); md_update_sb(mddev, 0); sysfs_notify_dirent_safe(mddev->sysfs_state); /* wait for the dirty state to be recorded in the metadata */ wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); } else spin_unlock(&mddev->lock); } EXPORT_SYMBOL_GPL(md_allow_write); static sector_t md_sync_max_sectors(struct mddev *mddev, enum sync_action action) { switch (action) { case ACTION_RESYNC: case ACTION_CHECK: case ACTION_REPAIR: atomic64_set(&mddev->resync_mismatches, 0); fallthrough; case ACTION_RESHAPE: return mddev->resync_max_sectors; case ACTION_RECOVER: return mddev->dev_sectors; default: return 0; } } /* * If lazy recovery is requested and all rdevs are in sync, select the rdev with * the higest index to perfore recovery to build initial xor data, this is the * same as old bitmap. */ static bool mddev_select_lazy_recover_rdev(struct mddev *mddev) { struct md_rdev *recover_rdev = NULL; struct md_rdev *rdev; bool ret = false; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { if (rdev->raid_disk < 0) continue; if (test_bit(Faulty, &rdev->flags) || !test_bit(In_sync, &rdev->flags)) break; if (!recover_rdev || recover_rdev->raid_disk < rdev->raid_disk) recover_rdev = rdev; } if (recover_rdev) { clear_bit(In_sync, &recover_rdev->flags); ret = true; } rcu_read_unlock(); return ret; } static sector_t md_sync_position(struct mddev *mddev, enum sync_action action) { sector_t start = 0; struct md_rdev *rdev; switch (action) { case ACTION_CHECK: case ACTION_REPAIR: return mddev->resync_min; case ACTION_RESYNC: if (!mddev->bitmap) return mddev->resync_offset; return 0; case ACTION_RESHAPE: /* * If the original node aborts reshaping then we continue the * reshaping, so set again to avoid restart reshape from the * first beginning */ if (mddev_is_clustered(mddev) && mddev->reshape_position != MaxSector) return mddev->reshape_position; return 0; case ACTION_RECOVER: start = MaxSector; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) if (rdev_needs_recovery(rdev, start)) start = rdev->recovery_offset; rcu_read_unlock(); /* * If there are no spares, and raid456 lazy initial recover is * requested. */ if (test_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery) && start == MaxSector && mddev_select_lazy_recover_rdev(mddev)) start = 0; /* If there is a bitmap, we need to make sure all * writes that started before we added a spare * complete before we start doing a recovery. * Otherwise the write might complete and (via * bitmap_endwrite) set a bit in the bitmap after the * recovery has checked that bit and skipped that * region. */ if (mddev->bitmap) { mddev->pers->quiesce(mddev, 1); mddev->pers->quiesce(mddev, 0); } return start; default: return MaxSector; } } static bool sync_io_within_limit(struct mddev *mddev) { /* * For raid456, sync IO is stripe(4k) per IO, for other levels, it's * RESYNC_PAGES(64k) per IO. */ return atomic_read(&mddev->recovery_active) < (raid_is_456(mddev) ? 8 : 128) * sync_io_depth(mddev); } /* * Update sync offset and mddev status when sync completes */ static void md_finish_sync(struct mddev *mddev, enum sync_action action) { struct md_rdev *rdev; switch (action) { case ACTION_RESYNC: case ACTION_REPAIR: if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) mddev->curr_resync = MaxSector; mddev->resync_offset = mddev->curr_resync; break; case ACTION_RECOVER: if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) mddev->curr_resync = MaxSector; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) if (mddev->delta_disks >= 0 && rdev_needs_recovery(rdev, mddev->curr_resync)) rdev->recovery_offset = mddev->curr_resync; rcu_read_unlock(); break; case ACTION_RESHAPE: if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) && mddev->delta_disks > 0 && mddev->pers->finish_reshape && mddev->pers->size && !mddev_is_dm(mddev)) { mddev_lock_nointr(mddev); md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0)); mddev_unlock(mddev); if (!mddev_is_clustered(mddev)) set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); } if (mddev->pers->finish_reshape) mddev->pers->finish_reshape(mddev); break; /* */ case ACTION_CHECK: default: break; } } #define SYNC_MARKS 10 #define SYNC_MARK_STEP (3*HZ) #define UPDATE_FREQUENCY (5*60*HZ) void md_do_sync(struct md_thread *thread) { struct mddev *mddev = thread->mddev; struct mddev *mddev2; unsigned int currspeed = 0, window; sector_t max_sectors,j, io_sectors, recovery_done; unsigned long mark[SYNC_MARKS]; unsigned long update_time; sector_t mark_cnt[SYNC_MARKS]; int last_mark,m; sector_t last_check; int skipped = 0; enum sync_action action; const char *desc; struct blk_plug plug; int ret; /* just incase thread restarts... */ if (test_bit(MD_RECOVERY_DONE, &mddev->recovery)) return; if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) goto skip; if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) || !md_is_rdwr(mddev)) {/* never try to sync a read-only array */ set_bit(MD_RECOVERY_INTR, &mddev->recovery); goto skip; } if (mddev_is_clustered(mddev)) { ret = mddev->cluster_ops->resync_start(mddev); if (ret) goto skip; set_bit(MD_CLUSTER_RESYNC_LOCKED, &mddev->flags); if (!(test_bit(MD_RECOVERY_SYNC, &mddev->recovery) || test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) || test_bit(MD_RECOVERY_RECOVER, &mddev->recovery)) && ((unsigned long long)mddev->curr_resync_completed < (unsigned long long)mddev->resync_max_sectors)) goto skip; } action = md_sync_action(mddev); if (action == ACTION_FROZEN || action == ACTION_IDLE) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); goto skip; } desc = md_sync_action_name(action); mddev->last_sync_action = action; /* * Before starting a resync we must have set curr_resync to * 2, and then checked that every "conflicting" array has curr_resync * less than ours. When we find one that is the same or higher * we wait on resync_wait. To avoid deadlock, we reduce curr_resync * to 1 if we choose to yield (based arbitrarily on address of mddev structure). * This will mean we have to start checking from the beginning again. * */ if (mddev_is_clustered(mddev)) mddev->cluster_ops->resync_start_notify(mddev); do { int mddev2_minor = -1; mddev->curr_resync = MD_RESYNC_DELAYED; try_again: if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) goto skip; spin_lock(&all_mddevs_lock); list_for_each_entry(mddev2, &all_mddevs, all_mddevs) { if (test_bit(MD_DELETED, &mddev2->flags)) continue; if (mddev2 == mddev) continue; if (!mddev->parallel_resync && mddev2->curr_resync && match_mddev_units(mddev, mddev2)) { DEFINE_WAIT(wq); if (mddev < mddev2 && mddev->curr_resync == MD_RESYNC_DELAYED) { /* arbitrarily yield */ mddev->curr_resync = MD_RESYNC_YIELDED; wake_up(&resync_wait); } if (mddev > mddev2 && mddev->curr_resync == MD_RESYNC_YIELDED) /* no need to wait here, we can wait the next * time 'round when curr_resync == 2 */ continue; /* We need to wait 'interruptible' so as not to * contribute to the load average, and not to * be caught by 'softlockup' */ prepare_to_wait(&resync_wait, &wq, TASK_INTERRUPTIBLE); if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) && mddev2->curr_resync >= mddev->curr_resync) { if (mddev2_minor != mddev2->md_minor) { mddev2_minor = mddev2->md_minor; pr_info("md: delaying %s of %s until %s has finished (they share one or more physical units)\n", desc, mdname(mddev), mdname(mddev2)); } spin_unlock(&all_mddevs_lock); if (signal_pending(current)) flush_signals(current); schedule(); finish_wait(&resync_wait, &wq); goto try_again; } finish_wait(&resync_wait, &wq); } } spin_unlock(&all_mddevs_lock); } while (mddev->curr_resync < MD_RESYNC_DELAYED); max_sectors = md_sync_max_sectors(mddev, action); j = md_sync_position(mddev, action); pr_info("md: %s of RAID array %s\n", desc, mdname(mddev)); pr_debug("md: minimum _guaranteed_ speed: %d KB/sec/disk.\n", speed_min(mddev)); pr_debug("md: using maximum available idle IO bandwidth (but not more than %d KB/sec) for %s.\n", speed_max(mddev), desc); is_mddev_idle(mddev, 1); /* this initializes IO event counters */ io_sectors = 0; for (m = 0; m < SYNC_MARKS; m++) { mark[m] = jiffies; mark_cnt[m] = io_sectors; } last_mark = 0; mddev->resync_mark = mark[last_mark]; mddev->resync_mark_cnt = mark_cnt[last_mark]; /* * Tune reconstruction: */ window = 32 * (PAGE_SIZE / 512); pr_debug("md: using %dk window, over a total of %lluk.\n", window/2, (unsigned long long)max_sectors/2); atomic_set(&mddev->recovery_active, 0); last_check = 0; if (j >= MD_RESYNC_ACTIVE) { pr_debug("md: resuming %s of %s from checkpoint.\n", desc, mdname(mddev)); mddev->curr_resync = j; } else mddev->curr_resync = MD_RESYNC_ACTIVE; /* no longer delayed */ mddev->curr_resync_completed = j; sysfs_notify_dirent_safe(mddev->sysfs_completed); md_new_event(); update_time = jiffies; blk_start_plug(&plug); while (j < max_sectors) { sector_t sectors; skipped = 0; if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && ((mddev->curr_resync > mddev->curr_resync_completed && (mddev->curr_resync - mddev->curr_resync_completed) > (max_sectors >> 4)) || time_after_eq(jiffies, update_time + UPDATE_FREQUENCY) || (j - mddev->curr_resync_completed)*2 >= mddev->resync_max - mddev->curr_resync_completed || mddev->curr_resync_completed > mddev->resync_max )) { /* time to update curr_resync_completed */ wait_event(mddev->recovery_wait, atomic_read(&mddev->recovery_active) == 0); mddev->curr_resync_completed = j; if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && j > mddev->resync_offset) mddev->resync_offset = j; update_time = jiffies; set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags); sysfs_notify_dirent_safe(mddev->sysfs_completed); } while (j >= mddev->resync_max && !test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { /* As this condition is controlled by user-space, * we can block indefinitely, so use '_interruptible' * to avoid triggering warnings. */ flush_signals(current); /* just in case */ wait_event_interruptible(mddev->recovery_wait, mddev->resync_max > j || test_bit(MD_RECOVERY_INTR, &mddev->recovery)); } if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) break; if (mddev->bitmap_ops && mddev->bitmap_ops->skip_sync_blocks) { sectors = mddev->bitmap_ops->skip_sync_blocks(mddev, j); if (sectors) goto update; } sectors = mddev->pers->sync_request(mddev, j, max_sectors, &skipped); if (sectors == 0) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); break; } if (!skipped) { /* actual IO requested */ io_sectors += sectors; atomic_add(sectors, &mddev->recovery_active); } if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) break; update: j += sectors; if (j > max_sectors) /* when skipping, extra large numbers can be returned. */ j = max_sectors; if (j >= MD_RESYNC_ACTIVE) mddev->curr_resync = j; mddev->curr_mark_cnt = io_sectors; if (last_check == 0) /* this is the earliest that rebuild will be * visible in /proc/mdstat */ md_new_event(); if (last_check + window > io_sectors || j == max_sectors) continue; last_check = io_sectors; repeat: if (time_after_eq(jiffies, mark[last_mark] + SYNC_MARK_STEP )) { /* step marks */ int next = (last_mark+1) % SYNC_MARKS; mddev->resync_mark = mark[next]; mddev->resync_mark_cnt = mark_cnt[next]; mark[next] = jiffies; mark_cnt[next] = io_sectors - atomic_read(&mddev->recovery_active); last_mark = next; } if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) break; /* * this loop exits only if either when we are slower than * the 'hard' speed limit, or the system was IO-idle for * a jiffy. * the system might be non-idle CPU-wise, but we only care * about not overloading the IO subsystem. (things like an * e2fsck being done on the RAID array should execute fast) */ cond_resched(); recovery_done = io_sectors - atomic_read(&mddev->recovery_active); currspeed = ((unsigned long)(recovery_done - mddev->resync_mark_cnt))/2 /((jiffies-mddev->resync_mark)/HZ +1) +1; if (currspeed > speed_min(mddev)) { if (currspeed > speed_max(mddev)) { msleep(500); goto repeat; } if (!sync_io_within_limit(mddev) && !is_mddev_idle(mddev, 0)) { /* * Give other IO more of a chance. * The faster the devices, the less we wait. */ wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); } } } pr_info("md: %s: %s %s.\n",mdname(mddev), desc, test_bit(MD_RECOVERY_INTR, &mddev->recovery) ? "interrupted" : "done"); /* * this also signals 'finished resyncing' to md_stop */ blk_finish_plug(&plug); wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && mddev->curr_resync >= MD_RESYNC_ACTIVE) { /* All sync IO completes after recovery_active becomes 0 */ mddev->curr_resync_completed = mddev->curr_resync; sysfs_notify_dirent_safe(mddev->sysfs_completed); } mddev->pers->sync_request(mddev, max_sectors, max_sectors, &skipped); if (mddev->curr_resync > MD_RESYNC_ACTIVE) md_finish_sync(mddev, action); skip: /* set CHANGE_PENDING here since maybe another update is needed, * so other nodes are informed. It should be harmless for normal * raid */ set_mask_bits(&mddev->sb_flags, 0, BIT(MD_SB_CHANGE_PENDING) | BIT(MD_SB_CHANGE_DEVS)); spin_lock(&mddev->lock); if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { /* We completed so min/max setting can be forgotten if used. */ if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) mddev->resync_min = 0; mddev->resync_max = MaxSector; } else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) mddev->resync_min = mddev->curr_resync_completed; set_bit(MD_RECOVERY_DONE, &mddev->recovery); mddev->curr_resync = MD_RESYNC_NONE; spin_unlock(&mddev->lock); wake_up(&resync_wait); md_wakeup_thread(mddev->thread); return; } EXPORT_SYMBOL_GPL(md_do_sync); static bool rdev_removeable(struct md_rdev *rdev) { /* rdev is not used. */ if (rdev->raid_disk < 0) return false; /* There are still inflight io, don't remove this rdev. */ if (atomic_read(&rdev->nr_pending)) return false; /* * An error occurred but has not yet been acknowledged by the metadata * handler, don't remove this rdev. */ if (test_bit(Blocked, &rdev->flags)) return false; /* Fautly rdev is not used, it's safe to remove it. */ if (test_bit(Faulty, &rdev->flags)) return true; /* Journal disk can only be removed if it's faulty. */ if (test_bit(Journal, &rdev->flags)) return false; /* * 'In_sync' is cleared while 'raid_disk' is valid, which means * replacement has just become active from pers->spare_active(), and * then pers->hot_remove_disk() will replace this rdev with replacement. */ if (!test_bit(In_sync, &rdev->flags)) return true; return false; } static bool rdev_is_spare(struct md_rdev *rdev) { return !test_bit(Candidate, &rdev->flags) && rdev->raid_disk >= 0 && !test_bit(In_sync, &rdev->flags) && !test_bit(Journal, &rdev->flags) && !test_bit(Faulty, &rdev->flags); } static bool rdev_addable(struct md_rdev *rdev) { struct mddev *mddev; mddev = READ_ONCE(rdev->mddev); if (!mddev) return false; /* rdev is already used, don't add it again. */ if (test_bit(Candidate, &rdev->flags) || rdev->raid_disk >= 0 || test_bit(Faulty, &rdev->flags)) return false; /* Allow to add journal disk. */ if (test_bit(Journal, &rdev->flags)) return true; /* Allow to add if array is read-write. */ if (md_is_rdwr(mddev)) return true; /* * For read-only array, only allow to readd a rdev. And if bitmap is * used, don't allow to readd a rdev that is too old. */ if (rdev->saved_raid_disk >= 0 && !test_bit(Bitmap_sync, &rdev->flags)) return true; return false; } static bool md_spares_need_change(struct mddev *mddev) { struct md_rdev *rdev; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { if (rdev_removeable(rdev) || rdev_addable(rdev)) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } static int remove_spares(struct mddev *mddev, struct md_rdev *this) { struct md_rdev *rdev; int removed = 0; rdev_for_each(rdev, mddev) { if ((this == NULL || rdev == this) && rdev_removeable(rdev) && !mddev->pers->hot_remove_disk(mddev, rdev)) { sysfs_unlink_rdev(mddev, rdev); rdev->saved_raid_disk = rdev->raid_disk; rdev->raid_disk = -1; removed++; } } if (removed && mddev->kobj.sd) sysfs_notify_dirent_safe(mddev->sysfs_degraded); return removed; } static int remove_and_add_spares(struct mddev *mddev, struct md_rdev *this) { struct md_rdev *rdev; int spares = 0; int removed = 0; if (this && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) /* Mustn't remove devices when resync thread is running */ return 0; removed = remove_spares(mddev, this); if (this && removed) goto no_add; rdev_for_each(rdev, mddev) { if (this && this != rdev) continue; if (rdev_is_spare(rdev)) spares++; if (!rdev_addable(rdev)) continue; if (!test_bit(Journal, &rdev->flags)) rdev->recovery_offset = 0; if (mddev->pers->hot_add_disk(mddev, rdev) == 0) { /* failure here is OK */ sysfs_link_rdev(mddev, rdev); if (!test_bit(Journal, &rdev->flags)) spares++; md_new_event(); set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); } } no_add: if (removed) set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); return spares; } static bool md_choose_sync_action(struct mddev *mddev, int *spares) { /* Check if reshape is in progress first. */ if (mddev->reshape_position != MaxSector) { if (mddev->pers->check_reshape == NULL || mddev->pers->check_reshape(mddev) != 0) return false; set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); clear_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery); return true; } /* Check if resync is in progress. */ if (mddev->resync_offset < MaxSector) { remove_spares(mddev, NULL); set_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); clear_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery); return true; } /* * Remove any failed drives, then add spares if possible. Spares are * also removed and re-added, to allow the personality to fail the * re-add. */ *spares = remove_and_add_spares(mddev, NULL); if (*spares || test_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery)) { clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); /* Start new recovery. */ set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); return true; } /* Delay to choose resync/check/repair in md_do_sync(). */ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) return true; /* Nothing to be done */ return false; } static void md_start_sync(struct work_struct *ws) { struct mddev *mddev = container_of(ws, struct mddev, sync_work); int spares = 0; bool suspend = false; char *name; /* * If reshape is still in progress, spares won't be added or removed * from conf until reshape is done. */ if (mddev->reshape_position == MaxSector && md_spares_need_change(mddev)) { suspend = true; mddev_suspend(mddev, false); } mddev_lock_nointr(mddev); if (!md_is_rdwr(mddev)) { /* * On a read-only array we can: * - remove failed devices * - add already-in_sync devices if the array itself is in-sync. * As we only add devices that are already in-sync, we can * activate the spares immediately. */ remove_and_add_spares(mddev, NULL); goto not_running; } if (!md_choose_sync_action(mddev, &spares)) goto not_running; if (!mddev->pers->sync_request) goto not_running; /* * We are adding a device or devices to an array which has the bitmap * stored on all devices. So make sure all bitmap pages get written. */ if (spares && md_bitmap_enabled(mddev, true)) mddev->bitmap_ops->write_all(mddev); name = test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ? "reshape" : "resync"; rcu_assign_pointer(mddev->sync_thread, md_register_thread(md_do_sync, mddev, name)); if (!mddev->sync_thread) { pr_warn("%s: could not start resync thread...\n", mdname(mddev)); /* leave the spares where they are, it shouldn't hurt */ goto not_running; } mddev_unlock(mddev); /* * md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should * not set it again. Otherwise, we may cause issue like this one: * https://bugzilla.kernel.org/show_bug.cgi?id=218200 * Therefore, use __mddev_resume(mddev, false). */ if (suspend) __mddev_resume(mddev, false); md_wakeup_thread(mddev->sync_thread); sysfs_notify_dirent_safe(mddev->sysfs_action); md_new_event(); return; not_running: clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery); mddev_unlock(mddev); /* * md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should * not set it again. Otherwise, we may cause issue like this one: * https://bugzilla.kernel.org/show_bug.cgi?id=218200 * Therefore, use __mddev_resume(mddev, false). */ if (suspend) __mddev_resume(mddev, false); wake_up(&resync_wait); if (test_and_clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery) && mddev->sysfs_action) sysfs_notify_dirent_safe(mddev->sysfs_action); } static void unregister_sync_thread(struct mddev *mddev) { if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) { /* resync/recovery still happening */ clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); return; } if (WARN_ON_ONCE(!mddev->sync_thread)) return; md_reap_sync_thread(mddev); } static bool md_should_do_recovery(struct mddev *mddev) { /* * As long as one of the following flags is set, * recovery needs to do or cleanup. */ if (test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) || test_bit(MD_RECOVERY_DONE, &mddev->recovery)) return true; /* * If no flags are set and it is in read-only status, * there is nothing to do. */ if (!md_is_rdwr(mddev)) return false; /* * MD_SB_CHANGE_PENDING indicates that the array is switching from clean to * active, and no action is needed for now. * All other MD_SB_* flags require to update the superblock. */ if (mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING)) return true; /* * If the array is not using external metadata and there has been no data * written for some time, then the array's status needs to be set to * in_sync. */ if (mddev->external == 0 && mddev->safemode == 1) return true; /* * When the system is about to restart or the process receives an signal, * the array needs to be synchronized as soon as possible. * Once the data synchronization is completed, need to change the array * status to in_sync. */ if (mddev->safemode == 2 && !mddev->in_sync && mddev->resync_offset == MaxSector) return true; return false; } /* * This routine is regularly called by all per-raid-array threads to * deal with generic issues like resync and super-block update. * Raid personalities that don't have a thread (linear/raid0) do not * need this as they never do any recovery or update the superblock. * * It does not do any resync itself, but rather "forks" off other threads * to do that as needed. * When it is determined that resync is needed, we set MD_RECOVERY_RUNNING in * "->recovery" and create a thread at ->sync_thread. * When the thread finishes it sets MD_RECOVERY_DONE * and wakeups up this thread which will reap the thread and finish up. * This thread also removes any faulty devices (with nr_pending == 0). * * The overall approach is: * 1/ if the superblock needs updating, update it. * 2/ If a recovery thread is running, don't do anything else. * 3/ If recovery has finished, clean up, possibly marking spares active. * 4/ If there are any faulty devices, remove them. * 5/ If array is degraded, try to add spares devices * 6/ If array has spares or is not in-sync, start a resync thread. */ void md_check_recovery(struct mddev *mddev) { if (md_bitmap_enabled(mddev, false) && mddev->bitmap_ops->daemon_work) mddev->bitmap_ops->daemon_work(mddev); if (signal_pending(current)) { if (mddev->pers->sync_request && !mddev->external) { pr_debug("md: %s in immediate safe mode\n", mdname(mddev)); mddev->safemode = 2; } flush_signals(current); } if (!md_should_do_recovery(mddev)) return; if (mddev_trylock(mddev)) { bool try_set_sync = mddev->safemode != 0; if (!mddev->external && mddev->safemode == 1) mddev->safemode = 0; if (!md_is_rdwr(mddev)) { struct md_rdev *rdev; if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { unregister_sync_thread(mddev); goto unlock; } if (!mddev->external && mddev->in_sync) /* * 'Blocked' flag not needed as failed devices * will be recorded if array switched to read/write. * Leaving it set will prevent the device * from being removed. */ rdev_for_each(rdev, mddev) clear_bit(Blocked, &rdev->flags); /* * There is no thread, but we need to call * ->spare_active and clear saved_raid_disk */ set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_reap_sync_thread(mddev); /* * Let md_start_sync() to remove and add rdevs to the * array. */ if (md_spares_need_change(mddev)) { set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); queue_work(md_misc_wq, &mddev->sync_work); } clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); clear_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery); clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags); goto unlock; } if (mddev_is_clustered(mddev)) { struct md_rdev *rdev, *tmp; /* kick the device if another node issued a * remove disk. */ rdev_for_each_safe(rdev, tmp, mddev) { if (rdev->raid_disk < 0 && test_and_clear_bit(ClusterRemove, &rdev->flags)) md_kick_rdev_from_array(rdev); } } if (try_set_sync && !mddev->external && !mddev->in_sync) { spin_lock(&mddev->lock); set_in_sync(mddev); spin_unlock(&mddev->lock); } if (mddev->sb_flags) md_update_sb(mddev, 0); /* * Never start a new sync thread if MD_RECOVERY_RUNNING is * still set. */ if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { unregister_sync_thread(mddev); goto unlock; } /* Set RUNNING before clearing NEEDED to avoid * any transients in the value of "sync_action". */ mddev->curr_resync_completed = 0; spin_lock(&mddev->lock); set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); spin_unlock(&mddev->lock); /* Clear some bits that don't mean anything, but * might be left set */ clear_bit(MD_RECOVERY_INTR, &mddev->recovery); clear_bit(MD_RECOVERY_DONE, &mddev->recovery); if (test_and_clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery) && !test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) { queue_work(md_misc_wq, &mddev->sync_work); } else { clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery); wake_up(&resync_wait); } unlock: wake_up(&mddev->sb_wait); mddev_unlock(mddev); } } EXPORT_SYMBOL(md_check_recovery); void md_reap_sync_thread(struct mddev *mddev) { struct md_rdev *rdev; sector_t old_dev_sectors = mddev->dev_sectors; bool is_reshaped = test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); /* resync has finished, collect result */ md_unregister_thread(mddev, &mddev->sync_thread); atomic_inc(&mddev->sync_seq); if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && mddev->degraded != mddev->raid_disks) { /* success...*/ /* activate any spares */ if (mddev->pers->spare_active(mddev)) { sysfs_notify_dirent_safe(mddev->sysfs_degraded); set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); } } /* If array is no-longer degraded, then any saved_raid_disk * information must be scrapped. */ if (!mddev->degraded) rdev_for_each(rdev, mddev) rdev->saved_raid_disk = -1; md_update_sb(mddev, 1); /* MD_SB_CHANGE_PENDING should be cleared by md_update_sb, so we can * call resync_finish here if MD_CLUSTER_RESYNC_LOCKED is set by * clustered raid */ if (test_and_clear_bit(MD_CLUSTER_RESYNC_LOCKED, &mddev->flags)) mddev->cluster_ops->resync_finish(mddev); clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery); clear_bit(MD_RECOVERY_DONE, &mddev->recovery); clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); clear_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery); /* * We call mddev->cluster_ops->update_size here because sync_size could * be changed by md_update_sb, and MD_RECOVERY_RESHAPE is cleared, * so it is time to update size across cluster. */ if (mddev_is_clustered(mddev) && is_reshaped && mddev->pers->finish_reshape && !test_bit(MD_CLOSING, &mddev->flags)) mddev->cluster_ops->update_size(mddev, old_dev_sectors); /* flag recovery needed just to double check */ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); sysfs_notify_dirent_safe(mddev->sysfs_completed); sysfs_notify_dirent_safe(mddev->sysfs_action); md_new_event(); if (mddev->event_work.func) queue_work(md_misc_wq, &mddev->event_work); wake_up(&resync_wait); } EXPORT_SYMBOL(md_reap_sync_thread); void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev) { sysfs_notify_dirent_safe(rdev->sysfs_state); wait_event_timeout(rdev->blocked_wait, !rdev_blocked(rdev), msecs_to_jiffies(5000)); rdev_dec_pending(rdev, mddev); } EXPORT_SYMBOL(md_wait_for_blocked_rdev); void md_finish_reshape(struct mddev *mddev) { /* called be personality module when reshape completes. */ struct md_rdev *rdev; rdev_for_each(rdev, mddev) { if (rdev->data_offset > rdev->new_data_offset) rdev->sectors += rdev->data_offset - rdev->new_data_offset; else rdev->sectors -= rdev->new_data_offset - rdev->data_offset; rdev->data_offset = rdev->new_data_offset; } } EXPORT_SYMBOL(md_finish_reshape); /* Bad block management */ /* Returns true on success, false on failure */ bool rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new) { struct mddev *mddev = rdev->mddev; /* * Recording new badblocks for faulty rdev will force unnecessary * super block updating. This is fragile for external management because * userspace daemon may trying to remove this device and deadlock may * occur. This will be probably solved in the mdadm, but it is safer to * avoid it. */ if (test_bit(Faulty, &rdev->flags)) return true; if (is_new) s += rdev->new_data_offset; else s += rdev->data_offset; if (!badblocks_set(&rdev->badblocks, s, sectors, 0)) { /* * Mark the disk as Faulty when setting badblocks fails, * otherwise, bad sectors may be read. */ md_error(mddev, rdev); return false; } /* Make sure they get written out promptly */ if (test_bit(ExternalBbl, &rdev->flags)) sysfs_notify_dirent_safe(rdev->sysfs_unack_badblocks); sysfs_notify_dirent_safe(rdev->sysfs_state); set_mask_bits(&mddev->sb_flags, 0, BIT(MD_SB_CHANGE_CLEAN) | BIT(MD_SB_CHANGE_PENDING)); md_wakeup_thread(rdev->mddev->thread); return true; } EXPORT_SYMBOL_GPL(rdev_set_badblocks); void rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new) { if (is_new) s += rdev->new_data_offset; else s += rdev->data_offset; if (!badblocks_clear(&rdev->badblocks, s, sectors)) return; if (test_bit(ExternalBbl, &rdev->flags)) sysfs_notify_dirent_safe(rdev->sysfs_badblocks); } EXPORT_SYMBOL_GPL(rdev_clear_badblocks); static int md_notify_reboot(struct notifier_block *this, unsigned long code, void *x) { struct mddev *mddev; spin_lock(&all_mddevs_lock); list_for_each_entry(mddev, &all_mddevs, all_mddevs) { if (!mddev_get(mddev)) continue; spin_unlock(&all_mddevs_lock); if (mddev_trylock(mddev)) { if (mddev->pers) __md_stop_writes(mddev); if (mddev->persistent) mddev->safemode = 2; mddev_unlock(mddev); } spin_lock(&all_mddevs_lock); mddev_put_locked(mddev); } spin_unlock(&all_mddevs_lock); return NOTIFY_DONE; } static struct notifier_block md_notifier = { .notifier_call = md_notify_reboot, .next = NULL, .priority = INT_MAX, /* before any real devices */ }; static void md_geninit(void) { pr_debug("md: sizeof(mdp_super_t) = %d\n", (int)sizeof(mdp_super_t)); proc_create("mdstat", S_IRUGO, NULL, &mdstat_proc_ops); } static int __init md_init(void) { int ret = md_bitmap_init(); if (ret) return ret; ret = md_llbitmap_init(); if (ret) goto err_bitmap; ret = -ENOMEM; md_misc_wq = alloc_workqueue("md_misc", WQ_PERCPU, 0); if (!md_misc_wq) goto err_misc_wq; ret = __register_blkdev(MD_MAJOR, "md", md_probe); if (ret < 0) goto err_md; ret = __register_blkdev(0, "mdp", md_probe); if (ret < 0) goto err_mdp; mdp_major = ret; register_reboot_notifier(&md_notifier); raid_table_header = register_sysctl("dev/raid", raid_table); md_geninit(); return 0; err_mdp: unregister_blkdev(MD_MAJOR, "md"); err_md: destroy_workqueue(md_misc_wq); err_misc_wq: md_llbitmap_exit(); err_bitmap: md_bitmap_exit(); return ret; } static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) { struct mdp_superblock_1 *sb = page_address(rdev->sb_page); struct md_rdev *rdev2, *tmp; int role, ret; /* * If size is changed in another node then we need to * do resize as well. */ if (mddev->dev_sectors != le64_to_cpu(sb->size)) { ret = mddev->pers->resize(mddev, le64_to_cpu(sb->size)); if (ret) pr_info("md-cluster: resize failed\n"); else if (md_bitmap_enabled(mddev, false)) mddev->bitmap_ops->update_sb(mddev->bitmap); } /* Check for change of roles in the active devices */ rdev_for_each_safe(rdev2, tmp, mddev) { if (test_bit(Faulty, &rdev2->flags)) { if (test_bit(ClusterRemove, &rdev2->flags)) set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); continue; } /* Check if the roles changed */ role = le16_to_cpu(sb->dev_roles[rdev2->desc_nr]); if (test_bit(Candidate, &rdev2->flags)) { if (role == MD_DISK_ROLE_FAULTY) { pr_info("md: Removing Candidate device %pg because add failed\n", rdev2->bdev); md_kick_rdev_from_array(rdev2); continue; } else clear_bit(Candidate, &rdev2->flags); } if (role != rdev2->raid_disk) { /* * got activated except reshape is happening. */ if (rdev2->raid_disk == -1 && role != MD_DISK_ROLE_SPARE && !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE) && !mddev->cluster_ops->resync_status_get(mddev)) { /* * -1 to make raid1_add_disk() set conf->fullsync * to 1. This could avoid skipping sync when the * remote node is down during resyncing. */ if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RECOVERY_OFFSET)) rdev2->saved_raid_disk = -1; else rdev2->saved_raid_disk = role; ret = remove_and_add_spares(mddev, rdev2); pr_info("Activated spare: %pg\n", rdev2->bdev); /* wakeup mddev->thread here, so array could * perform resync with the new activated disk */ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); } /* device faulty * We just want to do the minimum to mark the disk * as faulty. The recovery is performed by the * one who initiated the error. */ if (role == MD_DISK_ROLE_FAULTY || role == MD_DISK_ROLE_JOURNAL) { md_error(mddev, rdev2); clear_bit(Blocked, &rdev2->flags); } } } if (mddev->raid_disks != le32_to_cpu(sb->raid_disks)) { ret = update_raid_disks(mddev, le32_to_cpu(sb->raid_disks)); if (ret) pr_warn("md: updating array disks failed. %d\n", ret); } /* * Since mddev->delta_disks has already updated in update_raid_disks, * so it is time to check reshape. */ if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) && (le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) { /* * reshape is happening in the remote node, we need to * update reshape_position and call start_reshape. */ mddev->reshape_position = le64_to_cpu(sb->reshape_position); if (mddev->pers->update_reshape_pos) mddev->pers->update_reshape_pos(mddev); if (mddev->pers->start_reshape) mddev->pers->start_reshape(mddev); } else if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) && mddev->reshape_position != MaxSector && !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) { /* reshape is just done in another node. */ mddev->reshape_position = MaxSector; if (mddev->pers->update_reshape_pos) mddev->pers->update_reshape_pos(mddev); } /* Finally set the event to be up to date */ mddev->events = le64_to_cpu(sb->events); } static int read_rdev(struct mddev *mddev, struct md_rdev *rdev) { int err; struct page *swapout = rdev->sb_page; struct mdp_superblock_1 *sb; /* Store the sb page of the rdev in the swapout temporary * variable in case we err in the future */ rdev->sb_page = NULL; err = alloc_disk_sb(rdev); if (err == 0) { ClearPageUptodate(rdev->sb_page); rdev->sb_loaded = 0; err = super_types[mddev->major_version]. load_super(rdev, NULL, mddev->minor_version); } if (err < 0) { pr_warn("%s: %d Could not reload rdev(%d) err: %d. Restoring old values\n", __func__, __LINE__, rdev->desc_nr, err); if (rdev->sb_page) put_page(rdev->sb_page); rdev->sb_page = swapout; rdev->sb_loaded = 1; return err; } sb = page_address(rdev->sb_page); /* Read the offset unconditionally, even if MD_FEATURE_RECOVERY_OFFSET * is not set */ if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RECOVERY_OFFSET)) rdev->recovery_offset = le64_to_cpu(sb->recovery_offset); /* The other node finished recovery, call spare_active to set * device In_sync and mddev->degraded */ if (rdev->recovery_offset == MaxSector && !test_bit(In_sync, &rdev->flags) && mddev->pers->spare_active(mddev)) sysfs_notify_dirent_safe(mddev->sysfs_degraded); put_page(swapout); return 0; } void md_reload_sb(struct mddev *mddev, int nr) { struct md_rdev *rdev = NULL, *iter; int err; /* Find the rdev */ rdev_for_each_rcu(iter, mddev) { if (iter->desc_nr == nr) { rdev = iter; break; } } if (!rdev) { pr_warn("%s: %d Could not find rdev with nr %d\n", __func__, __LINE__, nr); return; } err = read_rdev(mddev, rdev); if (err < 0) return; check_sb_changes(mddev, rdev); /* Read all rdev's to update recovery_offset */ rdev_for_each_rcu(rdev, mddev) { if (!test_bit(Faulty, &rdev->flags)) read_rdev(mddev, rdev); } } EXPORT_SYMBOL(md_reload_sb); #ifndef MODULE /* * Searches all registered partitions for autorun RAID arrays * at boot time. */ static DEFINE_MUTEX(detected_devices_mutex); static LIST_HEAD(all_detected_devices); struct detected_devices_node { struct list_head list; dev_t dev; }; void md_autodetect_dev(dev_t dev) { struct detected_devices_node *node_detected_dev; node_detected_dev = kzalloc_obj(*node_detected_dev); if (node_detected_dev) { node_detected_dev->dev = dev; mutex_lock(&detected_devices_mutex); list_add_tail(&node_detected_dev->list, &all_detected_devices); mutex_unlock(&detected_devices_mutex); } } void md_autostart_arrays(int part) { struct md_rdev *rdev; struct detected_devices_node *node_detected_dev; dev_t dev; int i_scanned, i_passed; i_scanned = 0; i_passed = 0; pr_info("md: Autodetecting RAID arrays.\n"); mutex_lock(&detected_devices_mutex); while (!list_empty(&all_detected_devices) && i_scanned < INT_MAX) { i_scanned++; node_detected_dev = list_entry(all_detected_devices.next, struct detected_devices_node, list); list_del(&node_detected_dev->list); dev = node_detected_dev->dev; kfree(node_detected_dev); mutex_unlock(&detected_devices_mutex); rdev = md_import_device(dev,0, 90); mutex_lock(&detected_devices_mutex); if (IS_ERR(rdev)) continue; if (test_bit(Faulty, &rdev->flags)) continue; set_bit(AutoDetected, &rdev->flags); list_add(&rdev->same_set, &pending_raid_disks); i_passed++; } mutex_unlock(&detected_devices_mutex); pr_debug("md: Scanned %d and added %d devices.\n", i_scanned, i_passed); autorun_devices(part); } #endif /* !MODULE */ static __exit void md_exit(void) { struct mddev *mddev; int delay = 1; unregister_blkdev(MD_MAJOR,"md"); unregister_blkdev(mdp_major, "mdp"); unregister_reboot_notifier(&md_notifier); unregister_sysctl_table(raid_table_header); /* We cannot unload the modules while some process is * waiting for us in select() or poll() - wake them up */ md_unloading = 1; while (waitqueue_active(&md_event_waiters)) { /* not safe to leave yet */ wake_up(&md_event_waiters); msleep(delay); delay += delay; } remove_proc_entry("mdstat", NULL); spin_lock(&all_mddevs_lock); list_for_each_entry(mddev, &all_mddevs, all_mddevs) { if (!mddev_get(mddev)) continue; spin_unlock(&all_mddevs_lock); export_array(mddev); mddev->ctime = 0; mddev->hold_active = 0; /* * As the mddev is now fully clear, mddev_put will schedule * the mddev for destruction by a workqueue, and the * destroy_workqueue() below will wait for that to complete. */ spin_lock(&all_mddevs_lock); mddev_put_locked(mddev); } spin_unlock(&all_mddevs_lock); destroy_workqueue(md_misc_wq); md_bitmap_exit(); } subsys_initcall(md_init); module_exit(md_exit) static int get_ro(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "%d\n", start_readonly); } static int set_ro(const char *val, const struct kernel_param *kp) { return kstrtouint(val, 10, (unsigned int *)&start_readonly); } module_param_call(start_ro, set_ro, get_ro, NULL, S_IRUSR|S_IWUSR); module_param(start_dirty_degraded, int, S_IRUGO|S_IWUSR); module_param_call(new_array, add_named_array, NULL, NULL, S_IWUSR); module_param(create_on_open, bool, S_IRUSR|S_IWUSR); module_param(legacy_async_del_gendisk, bool, 0600); module_param(check_new_feature, bool, 0600); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MD RAID framework"); MODULE_ALIAS("md"); MODULE_ALIAS_BLOCKDEV_MAJOR(MD_MAJOR); |
| 11 11 11 2 11 11 1 11 1 1 29 1 43 47 36 11 5 43 12 74 4 36 1 2 8 2 6 2 3 1 4 2 4 14 13 1 1 1 4 14 14 14 14 11 11 1 1 9 11 2 1 10 1 93 5 4 1 93 90 3 82 7 84 8 88 96 1 98 3 93 90 8 5 8 10 3 1 3 3 1 2 2 6 3 3 1 1 5 1 6 11 20 117 120 1 18 98 2 170 148 18 158 12 11 16 16 16 22 6 16 5 5 6 1 7 1 1 6 1 49 3 39 6 8 11 12 4 22 21 12 4 1 7 1 2 2 2 1 53 4 22 21 8 74 64 1 6 8 9 14 181 168 168 60 50 10 2 44 10 38 4 36 5 12 46 46 37 9 45 45 2 32 3 35 4 8 15 1 11 3 13 13 6 3 8 284 339 1 1 2 1 2 1 1 1 334 3 1 2 124 124 124 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 over IPv4 tunnel device - Simple Internet Transition (SIT) * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * * Changes: * Roger Venning <r.venning@telstra.com>: 6to4 support * Nate Thompson <nate@thebog.net>: 6to4 support * Fred Templin <fred.l.templin@boeing.com>: isatap support */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/string.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmp.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/ip.h> #include <net/udp.h> #include <net/icmp.h> #include <net/ip_tunnels.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/dsfield.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netdev_lock.h> #include <net/inet_dscp.h> /* This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c For comments look at net/ipv4/ip_gre.c --ANK */ #define IP6_SIT_HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static int ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); static void ipip6_dev_free(struct net_device *dev); static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, __be32 *v4dst); static struct rtnl_link_ops sit_link_ops __read_mostly; static unsigned int sit_net_id __read_mostly; struct sit_net { struct ip_tunnel __rcu *tunnels_r_l[IP6_SIT_HASH_SIZE]; struct ip_tunnel __rcu *tunnels_r[IP6_SIT_HASH_SIZE]; struct ip_tunnel __rcu *tunnels_l[IP6_SIT_HASH_SIZE]; struct ip_tunnel __rcu *tunnels_wc[1]; struct ip_tunnel __rcu **tunnels[4]; struct net_device *fb_tunnel_dev; }; static inline struct sit_net *dev_to_sit_net(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); return net_generic(t->net, sit_net_id); } /* * Must be invoked with rcu_read_lock */ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, struct net_device *dev, __be32 remote, __be32 local, int sifindex) { unsigned int h0 = HASH(remote); unsigned int h1 = HASH(local); struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); int ifindex = dev ? dev->ifindex : 0; for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (!dev || !t->parms.link || ifindex == t->parms.link || sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && (!dev || !t->parms.link || ifindex == t->parms.link || sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && (!dev || !t->parms.link || ifindex == t->parms.link || sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } t = rcu_dereference(sitn->tunnels_wc[0]); if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } static struct ip_tunnel __rcu ** __ipip6_bucket(struct sit_net *sitn, struct ip_tunnel_parm_kern *parms) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; unsigned int h = 0; int prio = 0; if (remote) { prio |= 2; h ^= HASH(remote); } if (local) { prio |= 1; h ^= HASH(local); } return &sitn->tunnels[prio][h]; } static inline struct ip_tunnel __rcu **ipip6_bucket(struct sit_net *sitn, struct ip_tunnel *t) { return __ipip6_bucket(sitn, &t->parms); } static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) { struct ip_tunnel __rcu **tp; struct ip_tunnel *iter; for (tp = ipip6_bucket(sitn, t); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { rcu_assign_pointer(*tp, t->next); break; } } } static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t) { struct ip_tunnel __rcu **tp = ipip6_bucket(sitn, t); rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) { #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel *t = netdev_priv(dev); if (dev == sitn->fb_tunnel_dev || !sitn->fb_tunnel_dev) { ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0); t->ip6rd.relay_prefix = 0; t->ip6rd.prefixlen = 16; t->ip6rd.relay_prefixlen = 0; } else { struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev); memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd)); } #endif } static int ipip6_tunnel_create(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct sit_net *sitn = net_generic(t->net, sit_net_id); int err; __dev_addr_set(dev, &t->parms.iph.saddr, 4); memcpy(dev->broadcast, &t->parms.iph.daddr, 4); if (test_bit(IP_TUNNEL_SIT_ISATAP_BIT, t->parms.i_flags)) dev->priv_flags |= IFF_ISATAP; dev->rtnl_link_ops = &sit_link_ops; err = register_netdevice(dev); if (err < 0) goto out; ipip6_tunnel_clone_6rd(dev, sitn); ipip6_tunnel_link(sitn, t); return 0; out: return err; } static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, struct ip_tunnel_parm_kern *parms, int create) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; struct ip_tunnel *t, *nt; struct ip_tunnel __rcu **tp; struct net_device *dev; char name[IFNAMSIZ]; struct sit_net *sitn = net_generic(net, sit_net_id); for (tp = __ipip6_bucket(sitn, parms); (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && parms->link == t->parms.link) { if (create) return NULL; else return t; } } if (!create) goto failed; if (parms->name[0]) { if (!dev_valid_name(parms->name)) goto failed; strscpy(name, parms->name); } else { strscpy(name, "sit%d"); } dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ipip6_tunnel_setup); if (!dev) return NULL; dev_net_set(dev, net); nt = netdev_priv(dev); nt->net = net; nt->parms = *parms; if (ipip6_tunnel_create(dev) < 0) goto failed_free; if (!parms->name[0]) strscpy(parms->name, dev->name); return nt; failed_free: free_netdev(dev); failed: return NULL; } #define for_each_prl_rcu(start) \ for (prl = rcu_dereference(start); \ prl; \ prl = rcu_dereference(prl->next)) static struct ip_tunnel_prl_entry * __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) { struct ip_tunnel_prl_entry *prl; for_each_prl_rcu(t->prl) if (prl->addr == addr) break; return prl; } static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __user *a) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_prl kprl, *kp; struct ip_tunnel_prl_entry *prl; unsigned int cmax, c = 0, ca, len; int ret; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) return -EINVAL; if (copy_from_user(&kprl, a, sizeof(kprl))) return -EFAULT; cmax = kprl.datalen / sizeof(kprl); if (cmax > 1 && kprl.addr != htonl(INADDR_ANY)) cmax = 1; /* For simple GET or for root users, * we try harder to allocate. */ kp = (cmax <= 1 || capable(CAP_NET_ADMIN)) ? kzalloc_objs(*kp, cmax, GFP_KERNEL_ACCOUNT | __GFP_NOWARN) : NULL; ca = min(t->prl_count, cmax); if (!kp) { /* We don't try hard to allocate much memory for * non-root users. * For root users, retry allocating enough memory for * the answer. */ kp = kzalloc_objs(*kp, ca, GFP_ATOMIC | __GFP_ACCOUNT | __GFP_NOWARN); if (!kp) { ret = -ENOMEM; goto out; } } rcu_read_lock(); for_each_prl_rcu(t->prl) { if (c >= cmax) break; if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr) continue; kp[c].addr = prl->addr; kp[c].flags = prl->flags; c++; if (kprl.addr != htonl(INADDR_ANY)) break; } rcu_read_unlock(); len = sizeof(*kp) * c; ret = 0; if ((len && copy_to_user(a + 1, kp, len)) || put_user(len, &a->datalen)) ret = -EFAULT; kfree(kp); out: return ret; } static int ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) { struct ip_tunnel_prl_entry *p; int err = 0; if (a->addr == htonl(INADDR_ANY)) return -EINVAL; ASSERT_RTNL(); for (p = rtnl_dereference(t->prl); p; p = rtnl_dereference(p->next)) { if (p->addr == a->addr) { if (chg) { p->flags = a->flags; goto out; } err = -EEXIST; goto out; } } if (chg) { err = -ENXIO; goto out; } p = kzalloc_obj(struct ip_tunnel_prl_entry); if (!p) { err = -ENOBUFS; goto out; } p->next = t->prl; p->addr = a->addr; p->flags = a->flags; t->prl_count++; rcu_assign_pointer(t->prl, p); out: return err; } static void prl_list_destroy_rcu(struct rcu_head *head) { struct ip_tunnel_prl_entry *p, *n; p = container_of(head, struct ip_tunnel_prl_entry, rcu_head); do { n = rcu_dereference_protected(p->next, 1); kfree(p); p = n; } while (p); } static int ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) { struct ip_tunnel_prl_entry *x; struct ip_tunnel_prl_entry __rcu **p; int err = 0; ASSERT_RTNL(); if (a && a->addr != htonl(INADDR_ANY)) { for (p = &t->prl; (x = rtnl_dereference(*p)) != NULL; p = &x->next) { if (x->addr == a->addr) { *p = x->next; kfree_rcu(x, rcu_head); t->prl_count--; goto out; } } err = -ENXIO; } else { x = rtnl_dereference(t->prl); if (x) { t->prl_count = 0; call_rcu(&x->rcu_head, prl_list_destroy_rcu); t->prl = NULL; } } out: return err; } static int ipip6_tunnel_prl_ctl(struct net_device *dev, struct ip_tunnel_prl __user *data, int cmd) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_prl prl; int err; if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) return -EINVAL; if (copy_from_user(&prl, data, sizeof(prl))) return -EFAULT; switch (cmd) { case SIOCDELPRL: err = ipip6_tunnel_del_prl(t, &prl); break; case SIOCADDPRL: case SIOCCHGPRL: err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL); break; } dst_cache_reset(&t->dst_cache); netdev_state_change(dev); return err; } static int isatap_chksrc(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *t) { struct ip_tunnel_prl_entry *p; int ok = 1; rcu_read_lock(); p = __ipip6_tunnel_locate_prl(t, iph->saddr); if (p) { if (p->flags & PRL_DEFAULT) skb->ndisc_nodetype = NDISC_NODETYPE_DEFAULT; else skb->ndisc_nodetype = NDISC_NODETYPE_NODEFAULT; } else { const struct in6_addr *addr6 = &ipv6_hdr(skb)->saddr; if (ipv6_addr_is_isatap(addr6) && (addr6->s6_addr32[3] == iph->saddr) && ipv6_chk_prefix(addr6, t->dev)) skb->ndisc_nodetype = NDISC_NODETYPE_HOST; else ok = 0; } rcu_read_unlock(); return ok; } static void ipip6_tunnel_uninit(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct sit_net *sitn = net_generic(tunnel->net, sit_net_id); if (dev == sitn->fb_tunnel_dev) { RCU_INIT_POINTER(sitn->tunnels_wc[0], NULL); } else { ipip6_tunnel_unlink(sitn, tunnel); ipip6_tunnel_del_prl(tunnel, NULL); } dst_cache_reset(&tunnel->dst_cache); netdev_put(dev, &tunnel->dev_tracker); } static int ipip6_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; unsigned int data_len = 0; struct ip_tunnel *t; int sifindex; int err; switch (type) { default: case ICMP_PARAMETERPROB: return 0; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: /* Impossible event. */ return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, I believe they are just ether pollution. --ANK */ break; } break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) return 0; data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ break; case ICMP_REDIRECT: break; } err = -ENOENT; sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->daddr, iph->saddr, sifindex); if (!t) goto out; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, t->parms.link, iph->protocol); err = 0; goto out; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, iph->protocol); err = 0; goto out; } err = 0; if (__in6_dev_get(skb->dev) && !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) goto out; if (t->parms.iph.daddr == 0) goto out; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) goto out; if (time_before(jiffies, READ_ONCE(t->err_time) + IPTUNNEL_ERR_TIMEO)) WRITE_ONCE(t->err_count, READ_ONCE(t->err_count) + 1); else WRITE_ONCE(t->err_count, 1); WRITE_ONCE(t->err_time, jiffies); out: return err; } static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr, const struct in6_addr *v6addr) { __be32 v4embed = 0; if (check_6rd(tunnel, v6addr, &v4embed) && v4addr != v4embed) return true; return false; } /* Checks if an address matches an address on the tunnel interface. * Used to detect the NAT of proto 41 packets and let them pass spoofing test. * Long story: * This function is called after we considered the packet as spoofed * in is_spoofed_6rd. * We may have a router that is doing NAT for proto 41 packets * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd * function will return true, dropping the packet. * But, we can still check if is spoofed against the IP * addresses associated with the interface. */ static bool only_dnatted(const struct ip_tunnel *tunnel, const struct in6_addr *v6dst) { int prefix_len; #ifdef CONFIG_IPV6_SIT_6RD prefix_len = tunnel->ip6rd.prefixlen + 32 - tunnel->ip6rd.relay_prefixlen; #else prefix_len = 48; #endif return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev); } /* Returns true if a packet is spoofed */ static bool packet_is_spoofed(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *tunnel) { const struct ipv6hdr *ipv6h; if (tunnel->dev->priv_flags & IFF_ISATAP) { if (!isatap_chksrc(skb, iph, tunnel)) return true; return false; } if (tunnel->dev->flags & IFF_POINTOPOINT) return false; ipv6h = ipv6_hdr(skb); if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) { net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n", &iph->saddr, &ipv6h->saddr, &iph->daddr, &ipv6h->daddr); return true; } if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr))) return false; if (only_dnatted(tunnel, &ipv6h->daddr)) return false; net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n", &iph->saddr, &ipv6h->saddr, &iph->daddr, &ipv6h->daddr); return true; } static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); struct ip_tunnel *tunnel; int sifindex; int err; sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr, sifindex); if (tunnel) { if (tunnel->parms.iph.protocol != IPPROTO_IPV6 && tunnel->parms.iph.protocol != 0) goto out; skb->mac_header = skb->network_header; skb_reset_network_header(skb); IPCB(skb)->flags = 0; skb->dev = tunnel->dev; if (packet_is_spoofed(skb, iph, tunnel)) { DEV_STATS_INC(tunnel->dev, rx_errors); goto out; } if (iptunnel_pull_header(skb, 0, htons(ETH_P_IPV6), !net_eq(tunnel->net, dev_net(tunnel->dev)))) goto out; /* skb can be uncloned in iptunnel_pull_header, so * old iph is no longer valid */ iph = (const struct iphdr *)skb_mac_header(skb); skb_reset_mac_header(skb); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &iph->saddr, iph->tos); if (err > 1) { DEV_STATS_INC(tunnel->dev, rx_frame_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto out; } } dev_sw_netstats_rx_add(tunnel->dev, skb->len); netif_rx(skb); return 0; } /* no tunnel matched, let upstream know, ipsec may handle it */ return 1; out: kfree_skb(skb); return 0; } static const struct tnl_ptk_info ipip_tpi = { /* no tunnel info required for ipip. */ .proto = htons(ETH_P_IP), }; #if IS_ENABLED(CONFIG_MPLS) static const struct tnl_ptk_info mplsip_tpi = { /* no tunnel info required for mplsip. */ .proto = htons(ETH_P_MPLS_UC), }; #endif static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { const struct iphdr *iph; struct ip_tunnel *tunnel; int sifindex; sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; iph = ip_hdr(skb); tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr, sifindex); if (tunnel) { const struct tnl_ptk_info *tpi; if (tunnel->parms.iph.protocol != ipproto && tunnel->parms.iph.protocol != 0) goto drop; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; #if IS_ENABLED(CONFIG_MPLS) if (ipproto == IPPROTO_MPLS) tpi = &mplsip_tpi; else #endif tpi = &ipip_tpi; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; skb_reset_mac_header(skb); return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error); } return 1; drop: kfree_skb(skb); return 0; } static int ipip_rcv(struct sk_buff *skb) { return sit_tunnel_rcv(skb, IPPROTO_IPIP); } #if IS_ENABLED(CONFIG_MPLS) static int mplsip_rcv(struct sk_buff *skb) { return sit_tunnel_rcv(skb, IPPROTO_MPLS); } #endif /* * If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function * stores the embedded IPv4 address in v4dst and returns true. */ static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, __be32 *v4dst) { #ifdef CONFIG_IPV6_SIT_6RD if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix, tunnel->ip6rd.prefixlen)) { unsigned int pbw0, pbi0; int pbi1; u32 d; pbw0 = tunnel->ip6rd.prefixlen >> 5; pbi0 = tunnel->ip6rd.prefixlen & 0x1f; d = tunnel->ip6rd.relay_prefixlen < 32 ? (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >> tunnel->ip6rd.relay_prefixlen : 0; pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen; if (pbi1 > 0) d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >> (32 - pbi1); *v4dst = tunnel->ip6rd.relay_prefix | htonl(d); return true; } #else if (v6dst->s6_addr16[0] == htons(0x2002)) { /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */ memcpy(v4dst, &v6dst->s6_addr16[1], 4); return true; } #endif return false; } static inline __be32 try_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst) { __be32 dst = 0; check_6rd(tunnel, v6dst, &dst); return dst; } static bool ipip6_tunnel_dst_find(struct sk_buff *skb, __be32 *dst, bool is_isatap) { const struct ipv6hdr *iph6 = ipv6_hdr(skb); struct neighbour *neigh = NULL; const struct in6_addr *addr6; bool found = false; int addr_type; if (skb_dst(skb)) neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (!neigh) { net_dbg_ratelimited("nexthop == NULL\n"); return false; } addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (is_isatap) { if ((addr_type & IPV6_ADDR_UNICAST) && ipv6_addr_is_isatap(addr6)) { *dst = addr6->s6_addr32[3]; found = true; } } else { if (addr_type == IPV6_ADDR_ANY) { addr6 = &ipv6_hdr(skb)->daddr; addr_type = ipv6_addr_type(addr6); } if ((addr_type & IPV6_ADDR_COMPATv4) != 0) { *dst = addr6->s6_addr32[3]; found = true; } } neigh_release(neigh); return found; } /* * This function assumes it is being called from dev_queue_xmit() * and that skb is filled properly by that function. */ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; const struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; int err_count, mtu; struct flowi4 fl4; u8 ttl; u8 protocol = IPPROTO_IPV6; int t_hlen = tunnel->hlen + sizeof(struct iphdr); if (tos == 1) tos = ipv6_get_dsfield(iph6); /* ISATAP (RFC4214) - must come before 6to4 */ if ((dev->priv_flags & IFF_ISATAP) && !ipip6_tunnel_dst_find(skb, &dst, true)) goto tx_error; if (!dst) dst = try_6rd(tunnel, &iph6->daddr); if (!dst && !ipip6_tunnel_dst_find(skb, &dst, false)) goto tx_error; flowi4_init_output(&fl4, tunnel->parms.link, tunnel->fwmark, tos & INET_DSCP_MASK, RT_SCOPE_UNIVERSE, IPPROTO_IPV6, 0, dst, tiph->saddr, 0, 0, sock_net_uid(tunnel->net, NULL)); rt = dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr); if (!rt) { rt = ip_route_output_flow(tunnel->net, &fl4, NULL); if (IS_ERR(rt)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr); } if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { ip_rt_put(rt); DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } tdev = rt->dst.dev; if (tdev == dev) { ip_rt_put(rt); DEV_STATS_INC(dev, collisions); goto tx_error; } if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) { ip_rt_put(rt); goto tx_error; } iph6 = ipv6_hdr(skb); if (df) { mtu = dst4_mtu(&rt->dst) - t_hlen; if (mtu < IPV4_MIN_MTU) { DEV_STATS_INC(dev, collisions); ip_rt_put(rt); goto tx_error; } if (mtu < IPV6_MIN_MTU) { mtu = IPV6_MIN_MTU; df = 0; } if (tunnel->parms.iph.daddr) skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len > mtu && !skb_is_gso(skb)) { icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; } } err_count = READ_ONCE(tunnel->err_count); if (err_count > 0) { if (time_before(jiffies, READ_ONCE(tunnel->err_time) + IPTUNNEL_ERR_TIMEO)) { WRITE_ONCE(tunnel->err_count, err_count - 1); dst_link_failure(skb); } else { WRITE_ONCE(tunnel->err_count, 0); } } /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom = LL_RESERVED_SPACE(tdev) + t_hlen; if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); dev_kfree_skb(skb); skb = new_skb; iph6 = ipv6_hdr(skb); } ttl = tiph->ttl; if (ttl == 0) ttl = iph6->hop_limit; tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) { ip_rt_put(rt); goto tx_error; } skb_set_inner_ipproto(skb, IPPROTO_IPV6); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev)), 0); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: kfree_skb(skb); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } static netdev_tx_t sit_tunnel_xmit__(struct sk_buff *skb, struct net_device *dev, u8 ipproto) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) goto tx_error; skb_set_inner_ipproto(skb, ipproto); ip_tunnel_xmit(skb, dev, tiph, ipproto); return NETDEV_TX_OK; tx_error: kfree_skb(skb); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { if (!pskb_inet_may_pull(skb)) goto tx_err; switch (skb->protocol) { case htons(ETH_P_IP): sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP); break; case htons(ETH_P_IPV6): ipip6_tunnel_xmit(skb, dev); break; #if IS_ENABLED(CONFIG_MPLS) case htons(ETH_P_MPLS_UC): sit_tunnel_xmit__(skb, dev, IPPROTO_MPLS); break; #endif default: goto tx_err; } return NETDEV_TX_OK; tx_err: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } static void ipip6_tunnel_bind_dev(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); struct net_device *tdev = NULL; int hlen = LL_MAX_HEADER; const struct iphdr *iph; struct flowi4 fl4; iph = &tunnel->parms.iph; if (iph->daddr) { struct rtable *rt = ip_route_output_ports(tunnel->net, &fl4, NULL, iph->daddr, iph->saddr, 0, 0, IPPROTO_IPV6, iph->tos & INET_DSCP_MASK, tunnel->parms.link); if (!IS_ERR(rt)) { tdev = rt->dst.dev; ip_rt_put(rt); } dev->flags |= IFF_POINTOPOINT; } if (!tdev && tunnel->parms.link) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev && !netif_is_l3_master(tdev)) { int mtu; mtu = tdev->mtu - t_hlen; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; WRITE_ONCE(dev->mtu, mtu); hlen = tdev->hard_header_len + tdev->needed_headroom; } dev->needed_headroom = t_hlen + hlen; } static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); ipip6_tunnel_unlink(sitn, t); synchronize_net(); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; __dev_addr_set(t->dev, &p->iph.saddr, 4); memcpy(t->dev->broadcast, &p->iph.daddr, 4); ipip6_tunnel_link(sitn, t); t->parms.iph.ttl = p->iph.ttl; t->parms.iph.tos = p->iph.tos; t->parms.iph.frag_off = p->iph.frag_off; if (t->parms.link != p->link || t->fwmark != fwmark) { t->parms.link = p->link; t->fwmark = fwmark; ipip6_tunnel_bind_dev(t->dev); } dst_cache_reset(&t->dst_cache); netdev_state_change(t->dev); } #ifdef CONFIG_IPV6_SIT_6RD static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, struct ip_tunnel_6rd *ip6rd) { struct in6_addr prefix; __be32 relay_prefix; if (ip6rd->relay_prefixlen > 32 || ip6rd->prefixlen + (32 - ip6rd->relay_prefixlen) > 64) return -EINVAL; ipv6_addr_prefix(&prefix, &ip6rd->prefix, ip6rd->prefixlen); if (!ipv6_addr_equal(&prefix, &ip6rd->prefix)) return -EINVAL; if (ip6rd->relay_prefixlen) relay_prefix = ip6rd->relay_prefix & htonl(0xffffffffUL << (32 - ip6rd->relay_prefixlen)); else relay_prefix = 0; if (relay_prefix != ip6rd->relay_prefix) return -EINVAL; t->ip6rd.prefix = prefix; t->ip6rd.relay_prefix = relay_prefix; t->ip6rd.prefixlen = ip6rd->prefixlen; t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; dst_cache_reset(&t->dst_cache); netdev_state_change(t->dev); return 0; } static int ipip6_tunnel_get6rd(struct net_device *dev, struct ip_tunnel_parm __user *data) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern p; struct ip_tunnel_6rd ip6rd; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { if (!ip_tunnel_parm_from_user(&p, data)) return -EFAULT; t = ipip6_tunnel_locate(t->net, &p, 0); } if (!t) t = netdev_priv(dev); ip6rd.prefix = t->ip6rd.prefix; ip6rd.relay_prefix = t->ip6rd.relay_prefix; ip6rd.prefixlen = t->ip6rd.prefixlen; ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen; if (copy_to_user(data, &ip6rd, sizeof(ip6rd))) return -EFAULT; return 0; } static int ipip6_tunnel_6rdctl(struct net_device *dev, struct ip_tunnel_6rd __user *data, int cmd) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_6rd ip6rd; int err; if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ip6rd, data, sizeof(ip6rd))) return -EFAULT; if (cmd != SIOCDEL6RD) { err = ipip6_tunnel_update_6rd(t, &ip6rd); if (err < 0) return err; } else ipip6_tunnel_clone_6rd(dev, dev_to_sit_net(dev)); return 0; } #endif /* CONFIG_IPV6_SIT_6RD */ static bool ipip6_valid_ip_proto(u8 ipproto) { return ipproto == IPPROTO_IPV6 || ipproto == IPPROTO_IPIP || #if IS_ENABLED(CONFIG_MPLS) ipproto == IPPROTO_MPLS || #endif ipproto == 0; } static int __ipip6_tunnel_ioctl_validate(struct net *net, struct ip_tunnel_parm_kern *p) { if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (!ipip6_valid_ip_proto(p->iph.protocol)) return -EINVAL; if (p->iph.version != 4 || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF))) return -EINVAL; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); return 0; } static int ipip6_tunnel_get(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) t = ipip6_tunnel_locate(t->net, p, 0); if (!t) t = netdev_priv(dev); memcpy(p, &t->parms, sizeof(*p)); return 0; } static int ipip6_tunnel_add(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); int err; err = __ipip6_tunnel_ioctl_validate(t->net, p); if (err) return err; t = ipip6_tunnel_locate(t->net, p, 1); if (!t) return -ENOBUFS; return 0; } static int ipip6_tunnel_change(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); int err; err = __ipip6_tunnel_ioctl_validate(t->net, p); if (err) return err; t = ipip6_tunnel_locate(t->net, p, 0); if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { if (!t) return -ENOENT; } else { if (t) { if (t->dev != dev) return -EEXIST; } else { if (((dev->flags & IFF_POINTOPOINT) && !p->iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p->iph.daddr)) return -EINVAL; t = netdev_priv(dev); } ipip6_tunnel_update(t, p, t->fwmark); } return 0; } static int ipip6_tunnel_del(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { t = ipip6_tunnel_locate(t->net, p, 0); if (!t) return -ENOENT; if (t == netdev_priv(dev_to_sit_net(dev)->fb_tunnel_dev)) return -EPERM; dev = t->dev; } unregister_netdevice(dev); return 0; } static int ipip6_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { switch (cmd) { case SIOCGETTUNNEL: return ipip6_tunnel_get(dev, p); case SIOCADDTUNNEL: return ipip6_tunnel_add(dev, p); case SIOCCHGTUNNEL: return ipip6_tunnel_change(dev, p); case SIOCDELTUNNEL: return ipip6_tunnel_del(dev, p); default: return -EINVAL; } } static int ipip6_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { switch (cmd) { case SIOCGETTUNNEL: case SIOCADDTUNNEL: case SIOCCHGTUNNEL: case SIOCDELTUNNEL: return ip_tunnel_siocdevprivate(dev, ifr, data, cmd); case SIOCGETPRL: return ipip6_tunnel_get_prl(dev, data); case SIOCADDPRL: case SIOCDELPRL: case SIOCCHGPRL: return ipip6_tunnel_prl_ctl(dev, data, cmd); #ifdef CONFIG_IPV6_SIT_6RD case SIOCGET6RD: return ipip6_tunnel_get6rd(dev, data); case SIOCADD6RD: case SIOCCHG6RD: case SIOCDEL6RD: return ipip6_tunnel_6rdctl(dev, data, cmd); #endif default: return -EINVAL; } } static const struct net_device_ops ipip6_netdev_ops = { .ndo_init = ipip6_tunnel_init, .ndo_uninit = ipip6_tunnel_uninit, .ndo_start_xmit = sit_tunnel_xmit, .ndo_siocdevprivate = ipip6_tunnel_siocdevprivate, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipip6_tunnel_ctl, }; static void ipip6_dev_free(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); dst_cache_destroy(&tunnel->dst_cache); } #define SIT_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_GSO_SOFTWARE | \ NETIF_F_HW_CSUM) static void ipip6_tunnel_setup(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->netdev_ops = &ipip6_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; dev->mtu = ETH_DATA_LEN - t_hlen; dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - t_hlen; dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; dev->lltx = true; dev->features |= SIT_FEATURES; dev->hw_features |= SIT_FEATURES; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; } static int ipip6_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); int err; tunnel->dev = dev; strscpy(tunnel->parms.name, dev->name); ipip6_tunnel_bind_dev(dev); err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (err) return err; netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); return 0; } static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); iph->version = 4; iph->protocol = IPPROTO_IPV6; iph->ihl = 5; iph->ttl = 64; rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); } static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { u8 proto; if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (!ipip6_valid_ip_proto(proto)) return -EINVAL; return 0; } static void ipip6_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); parms->iph.version = 4; parms->iph.protocol = IPPROTO_IPV6; parms->iph.ihl = 5; parms->iph.ttl = 64; if (!data) return; ip_tunnel_netlink_parms(data, parms); if (data[IFLA_IPTUN_FWMARK]) *fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } #ifdef CONFIG_IPV6_SIT_6RD /* This function returns true when 6RD attributes are present in the nl msg */ static bool ipip6_netlink_6rd_parms(struct nlattr *data[], struct ip_tunnel_6rd *ip6rd) { bool ret = false; memset(ip6rd, 0, sizeof(*ip6rd)); if (!data) return ret; if (data[IFLA_IPTUN_6RD_PREFIX]) { ret = true; ip6rd->prefix = nla_get_in6_addr(data[IFLA_IPTUN_6RD_PREFIX]); } if (data[IFLA_IPTUN_6RD_RELAY_PREFIX]) { ret = true; ip6rd->relay_prefix = nla_get_be32(data[IFLA_IPTUN_6RD_RELAY_PREFIX]); } if (data[IFLA_IPTUN_6RD_PREFIXLEN]) { ret = true; ip6rd->prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_PREFIXLEN]); } if (data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]) { ret = true; ip6rd->relay_prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]); } return ret; } #endif static int ipip6_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct ip_tunnel *nt; struct ip_tunnel_encap ipencap; #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; #endif struct net *net; int err; net = params->link_net ? : dev_net(dev); nt = netdev_priv(dev); nt->net = net; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { err = ip_tunnel_encap_setup(nt, &ipencap); if (err < 0) return err; } ipip6_netlink_parms(data, &nt->parms, &nt->fwmark); if (ipip6_tunnel_locate(net, &nt->parms, 0)) return -EEXIST; err = ipip6_tunnel_create(dev); if (err < 0) return err; if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); if (mtu >= IPV6_MIN_MTU && mtu <= IP6_MAX_MTU - dev->hard_header_len) dev->mtu = mtu; } #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) { err = ipip6_tunnel_update_6rd(nt, &ip6rd); if (err < 0) unregister_netdevice_queue(dev, NULL); } #endif return err; } static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_encap ipencap; struct ip_tunnel_parm_kern p; struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; #endif __u32 fwmark = t->fwmark; int err; if (!rtnl_dev_link_net_capable(dev, net)) return -EPERM; if (dev == sitn->fb_tunnel_dev) return -EINVAL; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } ipip6_netlink_parms(data, &p, &fwmark); if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) return -EINVAL; t = ipip6_tunnel_locate(net, &p, 0); if (t) { if (t->dev != dev) return -EEXIST; } else t = netdev_priv(dev); ipip6_tunnel_update(t, &p, fwmark); #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) return ipip6_tunnel_update_6rd(t, &ip6rd); #endif return 0; } static size_t ipip6_get_size(const struct net_device *dev) { return /* IFLA_IPTUN_LINK */ nla_total_size(4) + /* IFLA_IPTUN_LOCAL */ nla_total_size(4) + /* IFLA_IPTUN_REMOTE */ nla_total_size(4) + /* IFLA_IPTUN_TTL */ nla_total_size(1) + /* IFLA_IPTUN_TOS */ nla_total_size(1) + /* IFLA_IPTUN_PMTUDISC */ nla_total_size(1) + /* IFLA_IPTUN_FLAGS */ nla_total_size(2) + /* IFLA_IPTUN_PROTO */ nla_total_size(1) + #ifdef CONFIG_IPV6_SIT_6RD /* IFLA_IPTUN_6RD_PREFIX */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_6RD_RELAY_PREFIX */ nla_total_size(4) + /* IFLA_IPTUN_6RD_PREFIXLEN */ nla_total_size(2) + /* IFLA_IPTUN_6RD_RELAY_PREFIXLEN */ nla_total_size(2) + #endif /* IFLA_IPTUN_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_IPTUN_FWMARK */ nla_total_size(4) + 0; } static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_parm_kern *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, !!(parm->iph.frag_off & htons(IP_DF))) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || nla_put_be16(skb, IFLA_IPTUN_FLAGS, ip_tunnel_flags_to_be16(parm->i_flags)) || nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark)) goto nla_put_failure; #ifdef CONFIG_IPV6_SIT_6RD if (nla_put_in6_addr(skb, IFLA_IPTUN_6RD_PREFIX, &tunnel->ip6rd.prefix) || nla_put_in_addr(skb, IFLA_IPTUN_6RD_RELAY_PREFIX, tunnel->ip6rd.relay_prefix) || nla_put_u16(skb, IFLA_IPTUN_6RD_PREFIXLEN, tunnel->ip6rd.prefixlen) || nla_put_u16(skb, IFLA_IPTUN_6RD_RELAY_PREFIXLEN, tunnel->ip6rd.relay_prefixlen)) goto nla_put_failure; #endif if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, tunnel->encap.sport) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, tunnel->encap.dport) || nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, tunnel->encap.flags)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, [IFLA_IPTUN_LOCAL] = { .type = NLA_U32 }, [IFLA_IPTUN_REMOTE] = { .type = NLA_U32 }, [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, [IFLA_IPTUN_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, #ifdef CONFIG_IPV6_SIT_6RD [IFLA_IPTUN_6RD_PREFIX] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_6RD_RELAY_PREFIX] = { .type = NLA_U32 }, [IFLA_IPTUN_6RD_PREFIXLEN] = { .type = NLA_U16 }, [IFLA_IPTUN_6RD_RELAY_PREFIXLEN] = { .type = NLA_U16 }, #endif [IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_FWMARK] = { .type = NLA_U32 }, }; static void ipip6_dellink(struct net_device *dev, struct list_head *head) { struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); if (dev != sitn->fb_tunnel_dev) unregister_netdevice_queue(dev, head); } static struct rtnl_link_ops sit_link_ops __read_mostly = { .kind = "sit", .maxtype = IFLA_IPTUN_MAX, .policy = ipip6_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipip6_tunnel_setup, .validate = ipip6_validate, .newlink = ipip6_newlink, .changelink = ipip6_changelink, .get_size = ipip6_get_size, .fill_info = ipip6_fill_info, .dellink = ipip6_dellink, .get_link_net = ip_tunnel_get_link_net, }; static struct xfrm_tunnel sit_handler __read_mostly = { .handler = ipip6_rcv, .err_handler = ipip6_err, .priority = 1, }; static struct xfrm_tunnel ipip_handler __read_mostly = { .handler = ipip_rcv, .err_handler = ipip6_err, .priority = 2, }; #if IS_ENABLED(CONFIG_MPLS) static struct xfrm_tunnel mplsip_handler __read_mostly = { .handler = mplsip_rcv, .err_handler = ipip6_err, .priority = 2, }; #endif static void __net_exit sit_exit_rtnl_net(struct net *net, struct list_head *head) { struct sit_net *sitn = net_generic(net, sit_net_id); struct net_device *dev, *aux; int prio; for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &sit_link_ops) unregister_netdevice_queue(dev, head); for (prio = 0; prio < 4; prio++) { int h; for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) { struct ip_tunnel *t; t = rtnl_net_dereference(net, sitn->tunnels[prio][h]); while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, head); t = rtnl_net_dereference(net, t->next); } } } } static int __net_init sit_init_net(struct net *net) { struct sit_net *sitn = net_generic(net, sit_net_id); struct ip_tunnel *t; int err; sitn->tunnels[0] = sitn->tunnels_wc; sitn->tunnels[1] = sitn->tunnels_l; sitn->tunnels[2] = sitn->tunnels_r; sitn->tunnels[3] = sitn->tunnels_r_l; if (!net_has_fallback_tunnels(net)) return 0; sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0", NET_NAME_UNKNOWN, ipip6_tunnel_setup); if (!sitn->fb_tunnel_dev) { err = -ENOMEM; goto err_alloc_dev; } dev_net_set(sitn->fb_tunnel_dev, net); sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ sitn->fb_tunnel_dev->netns_immutable = true; t = netdev_priv(sitn->fb_tunnel_dev); t->net = net; err = register_netdev(sitn->fb_tunnel_dev); if (err) goto err_reg_dev; ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn); ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); strscpy(t->parms.name, sitn->fb_tunnel_dev->name); return 0; err_reg_dev: free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: return err; } static struct pernet_operations sit_net_ops = { .init = sit_init_net, .exit_rtnl = sit_exit_rtnl_net, .id = &sit_net_id, .size = sizeof(struct sit_net), }; static void __exit sit_cleanup(void) { rtnl_link_unregister(&sit_link_ops); xfrm4_tunnel_deregister(&sit_handler, AF_INET6); xfrm4_tunnel_deregister(&ipip_handler, AF_INET); #if IS_ENABLED(CONFIG_MPLS) xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); #endif unregister_pernet_device(&sit_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ } static int __init sit_init(void) { int err; pr_info("IPv6, IPv4 and MPLS over IPv4 tunneling driver\n"); err = register_pernet_device(&sit_net_ops); if (err < 0) return err; err = xfrm4_tunnel_register(&sit_handler, AF_INET6); if (err < 0) { pr_info("%s: can't register ip6ip4\n", __func__); goto xfrm_tunnel_failed; } err = xfrm4_tunnel_register(&ipip_handler, AF_INET); if (err < 0) { pr_info("%s: can't register ip4ip4\n", __func__); goto xfrm_tunnel4_failed; } #if IS_ENABLED(CONFIG_MPLS) err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS); if (err < 0) { pr_info("%s: can't register mplsip\n", __func__); goto xfrm_tunnel_mpls_failed; } #endif err = rtnl_link_register(&sit_link_ops); if (err < 0) goto rtnl_link_failed; out: return err; rtnl_link_failed: #if IS_ENABLED(CONFIG_MPLS) xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); xfrm_tunnel_mpls_failed: #endif xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm_tunnel4_failed: xfrm4_tunnel_deregister(&sit_handler, AF_INET6); xfrm_tunnel_failed: unregister_pernet_device(&sit_net_ops); goto out; } module_init(sit_init); module_exit(sit_cleanup); MODULE_DESCRIPTION("IPv6-in-IPv4 tunnel SIT driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("sit"); MODULE_ALIAS_NETDEV("sit0"); |
| 11019 317 3349 420 24476 267 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This file provides wrappers with sanitizer instrumentation for non-atomic * bit operations. * * To use this functionality, an arch's bitops.h file needs to define each of * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), * arch___set_bit(), etc.). */ #ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H #define _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H #include <linux/instrumented.h> /** * ___set_bit - Set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * * Unlike set_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static __always_inline void ___set_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___set_bit(nr, addr); } /** * ___clear_bit - Clears a bit in memory * @nr: the bit to clear * @addr: the address to start counting from * * Unlike clear_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static __always_inline void ___clear_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___clear_bit(nr, addr); } /** * ___change_bit - Toggle a bit in memory * @nr: the bit to change * @addr: the address to start counting from * * Unlike change_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static __always_inline void ___change_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___change_bit(nr, addr); } static __always_inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr) { if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) { /* * We treat non-atomic read-write bitops a little more special. * Given the operations here only modify a single bit, assuming * non-atomicity of the writer is sufficient may be reasonable * for certain usage (and follows the permissible nature of the * assume-plain-writes-atomic rule): * 1. report read-modify-write races -> check read; * 2. do not report races with marked readers, but do report * races with unmarked readers -> check "atomic" write. */ kcsan_check_read(addr + BIT_WORD(nr), sizeof(long)); /* * Use generic write instrumentation, in case other sanitizers * or tools are enabled alongside KCSAN. */ instrument_write(addr + BIT_WORD(nr), sizeof(long)); } else { instrument_read_write(addr + BIT_WORD(nr), sizeof(long)); } } /** * ___test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static __always_inline bool ___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_set_bit(nr, addr); } /** * ___test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static __always_inline bool ___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_clear_bit(nr, addr); } /** * ___test_and_change_bit - Change a bit and return its old value * @nr: Bit to change * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static __always_inline bool ___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_change_bit(nr, addr); } /** * _test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static __always_inline bool _test_bit(unsigned long nr, const volatile unsigned long *addr) { instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); return arch_test_bit(nr, addr); } /** * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static __always_inline bool _test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) { instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); return arch_test_bit_acquire(nr, addr); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ |
| 1 1 1 1 1 1 1 1 1 1 4 1 1 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_meta.h> #include <linux/if_bridge.h> #include <uapi/linux/netfilter_bridge.h> /* NF_BR_PRE_ROUTING */ #include "../br_private.h" static const struct net_device * nft_meta_get_bridge(const struct net_device *dev) { if (dev && netif_is_bridge_port(dev)) return netdev_master_upper_dev_get_rcu((struct net_device *)dev); return NULL; } static void nft_meta_bridge_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_meta *priv = nft_expr_priv(expr); const struct net_device *in = nft_in(pkt), *out = nft_out(pkt); u32 *dest = ®s->data[priv->dreg]; const struct net_device *br_dev; switch (priv->key) { case NFT_META_BRI_IIFNAME: br_dev = nft_meta_get_bridge(in); break; case NFT_META_BRI_OIFNAME: br_dev = nft_meta_get_bridge(out); break; case NFT_META_BRI_IIFPVID: { u16 p_pvid; br_dev = nft_meta_get_bridge(in); if (!br_dev || !br_vlan_enabled(br_dev)) goto err; if (br_vlan_get_pvid_rcu(in, &p_pvid)) goto err; nft_reg_store16(dest, p_pvid); return; } case NFT_META_BRI_IIFVPROTO: { u16 p_proto; br_dev = nft_meta_get_bridge(in); if (!br_dev || !br_vlan_enabled(br_dev)) goto err; br_vlan_get_proto(br_dev, &p_proto); nft_reg_store_be16(dest, htons(p_proto)); return; } case NFT_META_BRI_IIFHWADDR: br_dev = nft_meta_get_bridge(in); if (!br_dev) goto err; /* ETH_ALEN (6) is shorter than the destination register span (8) */ dest[1] = 0; memcpy(dest, br_dev->dev_addr, ETH_ALEN); return; default: return nft_meta_get_eval(expr, regs, pkt); } strscpy_pad((char *)dest, br_dev ? br_dev->name : "", IFNAMSIZ); return; err: regs->verdict.code = NFT_BREAK; } static int nft_meta_bridge_get_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int len; priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); switch (priv->key) { case NFT_META_BRI_IIFNAME: case NFT_META_BRI_OIFNAME: len = IFNAMSIZ; break; case NFT_META_BRI_IIFPVID: case NFT_META_BRI_IIFVPROTO: len = sizeof(u16); break; case NFT_META_BRI_IIFHWADDR: len = ETH_ALEN; break; default: return nft_meta_get_init(ctx, expr, tb); } priv->len = len; return nft_parse_register_store(ctx, tb[NFTA_META_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, len); } static int nft_meta_bridge_get_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int hooks; switch (priv->key) { case NFT_META_BRI_IIFHWADDR: hooks = 1 << NF_BR_PRE_ROUTING; break; default: return nft_meta_get_validate(ctx, expr); } return nft_chain_validate_hooks(ctx->chain, hooks); } static struct nft_expr_type nft_meta_bridge_type; static const struct nft_expr_ops nft_meta_bridge_get_ops = { .type = &nft_meta_bridge_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), .eval = nft_meta_bridge_get_eval, .init = nft_meta_bridge_get_init, .validate = nft_meta_bridge_get_validate, .dump = nft_meta_get_dump, }; static void nft_meta_bridge_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_meta *meta = nft_expr_priv(expr); u32 *sreg = ®s->data[meta->sreg]; struct sk_buff *skb = pkt->skb; u8 value8; switch (meta->key) { case NFT_META_BRI_BROUTE: value8 = nft_reg_load8(sreg); BR_INPUT_SKB_CB(skb)->br_netfilter_broute = !!value8; break; default: nft_meta_set_eval(expr, regs, pkt); } } static int nft_meta_bridge_set_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int len; int err; priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); switch (priv->key) { case NFT_META_BRI_BROUTE: len = sizeof(u8); break; default: return nft_meta_set_init(ctx, expr, tb); } priv->len = len; err = nft_parse_register_load(ctx, tb[NFTA_META_SREG], &priv->sreg, len); if (err < 0) return err; return 0; } static int nft_meta_bridge_set_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int hooks; switch (priv->key) { case NFT_META_BRI_BROUTE: hooks = 1 << NF_BR_PRE_ROUTING; break; default: return nft_meta_set_validate(ctx, expr); } return nft_chain_validate_hooks(ctx->chain, hooks); } static const struct nft_expr_ops nft_meta_bridge_set_ops = { .type = &nft_meta_bridge_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), .eval = nft_meta_bridge_set_eval, .init = nft_meta_bridge_set_init, .destroy = nft_meta_set_destroy, .dump = nft_meta_set_dump, .validate = nft_meta_bridge_set_validate, }; static const struct nft_expr_ops * nft_meta_bridge_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { if (tb[NFTA_META_KEY] == NULL) return ERR_PTR(-EINVAL); if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) return ERR_PTR(-EINVAL); if (tb[NFTA_META_DREG]) return &nft_meta_bridge_get_ops; if (tb[NFTA_META_SREG]) return &nft_meta_bridge_set_ops; return ERR_PTR(-EINVAL); } static struct nft_expr_type nft_meta_bridge_type __read_mostly = { .family = NFPROTO_BRIDGE, .name = "meta", .select_ops = nft_meta_bridge_select_ops, .policy = nft_meta_policy, .maxattr = NFTA_META_MAX, .owner = THIS_MODULE, }; static int __init nft_meta_bridge_module_init(void) { return nft_register_expr(&nft_meta_bridge_type); } static void __exit nft_meta_bridge_module_exit(void) { nft_unregister_expr(&nft_meta_bridge_type); } module_init(nft_meta_bridge_module_init); module_exit(nft_meta_bridge_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("wenxu <wenxu@ucloud.cn>"); MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta"); MODULE_DESCRIPTION("Support for bridge dedicated meta key"); |
| 44 3 1 44 13 30 28 2 13 13 6 6 6 6 3 6 3 2 4 1 1 1 1 1 1 1 1 1 1 1 1 25 25 25 1 1 1 1 1 1 1 1 1 1 1 1 416 321 99 98 2 3 98 1 33 8 23 3 1 30 13 17 13 3 3 13 13 2 3 8 11 6 1 13 4 12 5 15 2 13 4 25 154 8 146 9 9 9 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This is a module which is used for logging packets to userspace via * nfetlink. * * (C) 2005 by Harald Welte <laforge@netfilter.org> * (C) 2006-2012 Patrick McHardy <kaber@trash.net> * * Based on the old ipv4-only ipt_ULOG.c: * (C) 2000-2004 by Harald Welte <laforge@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/netfilter_bridge.h> #include <net/netlink.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_log.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/spinlock.h> #include <linux/sysctl.h> #include <linux/proc_fs.h> #include <linux/security.h> #include <linux/list.h> #include <linux/slab.h> #include <net/sock.h> #include <net/netfilter/nf_log.h> #include <net/netns/generic.h> #include <linux/atomic.h> #include <linux/refcount.h> #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) #include "../bridge/br_private.h" #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif #define NFULNL_COPY_DISABLED 0xff #define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ /* max packet size is limited by 16-bit struct nfattr nfa_len field */ #define NFULNL_COPY_RANGE_MAX (0xFFFF - NLA_HDRLEN) #define PRINTR(x, args...) do { if (net_ratelimit()) \ printk(x, ## args); } while (0); struct nfulnl_instance { struct hlist_node hlist; /* global list of instances */ spinlock_t lock; refcount_t use; /* use count */ unsigned int qlen; /* number of nlmsgs in skb */ struct sk_buff *skb; /* pre-allocatd skb */ struct timer_list timer; struct net *net; netns_tracker ns_tracker; struct user_namespace *peer_user_ns; /* User namespace of the peer process */ u32 peer_portid; /* PORTID of the peer process */ /* configurable parameters */ unsigned int flushtimeout; /* timeout until queue flush */ unsigned int nlbufsiz; /* netlink buffer allocation size */ unsigned int qthreshold; /* threshold of the queue */ u_int32_t copy_range; u_int32_t seq; /* instance-local sequential counter */ u_int16_t group_num; /* number of this queue */ u_int16_t flags; u_int8_t copy_mode; struct rcu_head rcu; }; #define INSTANCE_BUCKETS 16 static unsigned int nfnl_log_net_id __read_mostly; struct nfnl_log_net { spinlock_t instances_lock; struct hlist_head instance_table[INSTANCE_BUCKETS]; atomic_t global_seq; }; static struct nfnl_log_net *nfnl_log_pernet(struct net *net) { return net_generic(net, nfnl_log_net_id); } static inline u_int8_t instance_hashfn(u_int16_t group_num) { return ((group_num & 0xff) % INSTANCE_BUCKETS); } static struct nfulnl_instance * __instance_lookup(const struct nfnl_log_net *log, u16 group_num) { const struct hlist_head *head; struct nfulnl_instance *inst; head = &log->instance_table[instance_hashfn(group_num)]; hlist_for_each_entry_rcu(inst, head, hlist) { if (inst->group_num == group_num) return inst; } return NULL; } static inline void instance_get(struct nfulnl_instance *inst) { refcount_inc(&inst->use); } static struct nfulnl_instance * instance_lookup_get_rcu(const struct nfnl_log_net *log, u16 group_num) { struct nfulnl_instance *inst; inst = __instance_lookup(log, group_num); if (inst && !refcount_inc_not_zero(&inst->use)) inst = NULL; return inst; } static struct nfulnl_instance * instance_lookup_get(const struct nfnl_log_net *log, u16 group_num) { struct nfulnl_instance *inst; rcu_read_lock(); inst = instance_lookup_get_rcu(log, group_num); rcu_read_unlock(); return inst; } static void nfulnl_instance_free_rcu(struct rcu_head *head) { struct nfulnl_instance *inst = container_of(head, struct nfulnl_instance, rcu); put_net_track(inst->net, &inst->ns_tracker); kfree(inst); module_put(THIS_MODULE); } static void instance_put(struct nfulnl_instance *inst) { if (inst && refcount_dec_and_test(&inst->use)) call_rcu(&inst->rcu, nfulnl_instance_free_rcu); } static void nfulnl_timer(struct timer_list *t); static struct nfulnl_instance * instance_create(struct net *net, u_int16_t group_num, u32 portid, struct user_namespace *user_ns) { struct nfulnl_instance *inst; struct nfnl_log_net *log = nfnl_log_pernet(net); int err; spin_lock_bh(&log->instances_lock); if (__instance_lookup(log, group_num)) { err = -EEXIST; goto out_unlock; } inst = kzalloc_obj(*inst, GFP_ATOMIC); if (!inst) { err = -ENOMEM; goto out_unlock; } if (!try_module_get(THIS_MODULE)) { kfree(inst); err = -EAGAIN; goto out_unlock; } INIT_HLIST_NODE(&inst->hlist); spin_lock_init(&inst->lock); /* needs to be two, since we _put() after creation */ refcount_set(&inst->use, 2); timer_setup(&inst->timer, nfulnl_timer, 0); inst->net = get_net_track(net, &inst->ns_tracker, GFP_ATOMIC); inst->peer_user_ns = user_ns; inst->peer_portid = portid; inst->group_num = group_num; inst->qthreshold = NFULNL_QTHRESH_DEFAULT; inst->flushtimeout = NFULNL_TIMEOUT_DEFAULT; inst->nlbufsiz = NFULNL_NLBUFSIZ_DEFAULT; inst->copy_mode = NFULNL_COPY_PACKET; inst->copy_range = NFULNL_COPY_RANGE_MAX; hlist_add_head_rcu(&inst->hlist, &log->instance_table[instance_hashfn(group_num)]); spin_unlock_bh(&log->instances_lock); return inst; out_unlock: spin_unlock_bh(&log->instances_lock); return ERR_PTR(err); } static void __nfulnl_flush(struct nfulnl_instance *inst); /* called with BH disabled */ static void __instance_destroy(struct nfulnl_instance *inst) { /* first pull it out of the global list */ hlist_del_rcu(&inst->hlist); /* then flush all pending packets from skb */ spin_lock(&inst->lock); /* lockless readers wont be able to use us */ inst->copy_mode = NFULNL_COPY_DISABLED; if (inst->skb) __nfulnl_flush(inst); spin_unlock(&inst->lock); /* and finally put the refcount */ instance_put(inst); } static inline void instance_destroy(struct nfnl_log_net *log, struct nfulnl_instance *inst) { spin_lock_bh(&log->instances_lock); __instance_destroy(inst); spin_unlock_bh(&log->instances_lock); } static int nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode, unsigned int range) { int status = 0; spin_lock_bh(&inst->lock); switch (mode) { case NFULNL_COPY_NONE: case NFULNL_COPY_META: inst->copy_mode = mode; inst->copy_range = 0; break; case NFULNL_COPY_PACKET: inst->copy_mode = mode; if (range == 0) range = NFULNL_COPY_RANGE_MAX; inst->copy_range = min_t(unsigned int, range, NFULNL_COPY_RANGE_MAX); break; default: status = -EINVAL; break; } spin_unlock_bh(&inst->lock); return status; } static int nfulnl_set_nlbufsiz(struct nfulnl_instance *inst, u_int32_t nlbufsiz) { int status; spin_lock_bh(&inst->lock); if (nlbufsiz < NFULNL_NLBUFSIZ_DEFAULT) status = -ERANGE; else if (nlbufsiz > 131072) status = -ERANGE; else { inst->nlbufsiz = nlbufsiz; status = 0; } spin_unlock_bh(&inst->lock); return status; } static void nfulnl_set_timeout(struct nfulnl_instance *inst, u_int32_t timeout) { spin_lock_bh(&inst->lock); inst->flushtimeout = timeout; spin_unlock_bh(&inst->lock); } static void nfulnl_set_qthresh(struct nfulnl_instance *inst, u_int32_t qthresh) { spin_lock_bh(&inst->lock); inst->qthreshold = qthresh; spin_unlock_bh(&inst->lock); } static int nfulnl_set_flags(struct nfulnl_instance *inst, u_int16_t flags) { spin_lock_bh(&inst->lock); inst->flags = flags; spin_unlock_bh(&inst->lock); return 0; } static struct sk_buff * nfulnl_alloc_skb(struct net *net, u32 peer_portid, unsigned int inst_size, unsigned int pkt_size) { struct sk_buff *skb; unsigned int n; /* alloc skb which should be big enough for a whole multipart * message. WARNING: has to be <= 128k due to slab restrictions */ n = max(inst_size, pkt_size); skb = alloc_skb(n, GFP_ATOMIC | __GFP_NOWARN); if (!skb) { if (n > pkt_size) { /* try to allocate only as much as we need for current * packet */ skb = alloc_skb(pkt_size, GFP_ATOMIC); } } return skb; } static void __nfulnl_send(struct nfulnl_instance *inst) { if (inst->qlen > 1) { struct nlmsghdr *nlh = nfnl_msg_put(inst->skb, 0, 0, NLMSG_DONE, 0, AF_UNSPEC, NFNETLINK_V0, htons(inst->group_num)); if (WARN_ONCE(!nlh, "bad nlskb size: %u, tailroom %d\n", inst->skb->len, skb_tailroom(inst->skb))) { kfree_skb(inst->skb); goto out; } } nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid); out: inst->qlen = 0; inst->skb = NULL; } static void __nfulnl_flush(struct nfulnl_instance *inst) { /* timer holds a reference */ if (timer_delete(&inst->timer)) instance_put(inst); if (inst->skb) __nfulnl_send(inst); } static void nfulnl_timer(struct timer_list *t) { struct nfulnl_instance *inst = timer_container_of(inst, t, timer); spin_lock_bh(&inst->lock); if (inst->skb) __nfulnl_send(inst); spin_unlock_bh(&inst->lock); instance_put(inst); } static u32 nfulnl_get_bridge_size(const struct sk_buff *skb) { u32 mac_len, size = 0; if (!skb_mac_header_was_set(skb)) return 0; if (skb_vlan_tag_present(skb)) { size += nla_total_size(0); /* nested */ size += nla_total_size(sizeof(u16)); /* id */ size += nla_total_size(sizeof(u16)); /* tag */ } mac_len = skb_mac_header_len(skb); if (mac_len > 0) size += nla_total_size(mac_len); return size; } static int nfulnl_put_bridge(struct nfulnl_instance *inst, const struct sk_buff *skb) { u32 mac_len; if (!skb_mac_header_was_set(skb)) return 0; if (skb_vlan_tag_present(skb)) { struct nlattr *nest; nest = nla_nest_start(inst->skb, NFULA_VLAN); if (!nest) goto nla_put_failure; if (nla_put_be16(inst->skb, NFULA_VLAN_TCI, htons(skb->vlan_tci)) || nla_put_be16(inst->skb, NFULA_VLAN_PROTO, skb->vlan_proto)) goto nla_put_failure; nla_nest_end(inst->skb, nest); } mac_len = skb_mac_header_len(skb); if (mac_len > 0 && nla_put(inst->skb, NFULA_L2HDR, mac_len, skb_mac_header(skb))) goto nla_put_failure; return 0; nla_put_failure: return -1; } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static int nflog_put_master_ifindex(struct sk_buff *nlskb, int attr, const struct net_device *dev) { const struct net_device *upper; if (dev && !netif_is_bridge_port(dev)) return 0; upper = netdev_master_upper_dev_get_rcu((struct net_device *)dev); if (upper && nla_put_be32(nlskb, attr, htonl(upper->ifindex))) return -EMSGSIZE; return 0; } #endif /* This is an inline function, we don't really care about a long * list of arguments */ static inline int __build_packet_message(struct nfnl_log_net *log, struct nfulnl_instance *inst, const struct sk_buff *skb, unsigned int data_len, u_int8_t pf, unsigned int hooknum, const struct net_device *indev, const struct net_device *outdev, const char *prefix, unsigned int plen, const struct nfnl_ct_hook *nfnl_ct, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { struct nfulnl_msg_packet_hdr pmsg; struct nlmsghdr *nlh; sk_buff_data_t old_tail = inst->skb->tail; struct sock *sk; const unsigned char *hwhdrp; nlh = nfnl_msg_put(inst->skb, 0, 0, nfnl_msg_type(NFNL_SUBSYS_ULOG, NFULNL_MSG_PACKET), 0, pf, NFNETLINK_V0, htons(inst->group_num)); if (!nlh) return -1; memset(&pmsg, 0, sizeof(pmsg)); pmsg.hw_protocol = skb->protocol; pmsg.hook = hooknum; if (nla_put(inst->skb, NFULA_PACKET_HDR, sizeof(pmsg), &pmsg)) goto nla_put_failure; if (prefix && nla_put(inst->skb, NFULA_PREFIX, plen, prefix)) goto nla_put_failure; if (indev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; #else if (pf == PF_BRIDGE) { /* Case 1: outdev is physical input device, we need to * look for bridge group (when called from * netfilter_bridge) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, htonl(indev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by nf_hook_thresh or * nf_log_packet. */ nflog_put_master_ifindex(inst->skb, NFULA_IFINDEX_INDEV, indev)) goto nla_put_failure; } else { int physinif; /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; physinif = nf_bridge_get_physinif(skb); if (physinif && nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, htonl(physinif))) goto nla_put_failure; } #endif } if (outdev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; #else if (pf == PF_BRIDGE) { /* Case 1: outdev is physical output device, we need to * look for bridge group (when called from * netfilter_bridge) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, htonl(outdev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by nf_hook_thresh or * nf_log_packet. */ nflog_put_master_ifindex(inst->skb, NFULA_IFINDEX_OUTDEV, outdev)) goto nla_put_failure; } else { struct net_device *physoutdev; /* Case 2: indev is a bridge group, we need to look * for physical device (when called from ipv4) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; physoutdev = nf_bridge_get_physoutdev(skb); if (physoutdev && nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, htonl(physoutdev->ifindex))) goto nla_put_failure; } #endif } if (skb->mark && nla_put_be32(inst->skb, NFULA_MARK, htonl(skb->mark))) goto nla_put_failure; if (indev && skb->dev && skb_mac_header_was_set(skb) && skb_mac_header_len(skb) != 0) { struct nfulnl_msg_packet_hw phw; int len; memset(&phw, 0, sizeof(phw)); len = dev_parse_header(skb, phw.hw_addr); if (len > 0) { phw.hw_addrlen = htons(len); if (nla_put(inst->skb, NFULA_HWADDR, sizeof(phw), &phw)) goto nla_put_failure; } } if (indev && skb_mac_header_was_set(skb)) { if (nla_put_be16(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) || nla_put_be16(inst->skb, NFULA_HWLEN, htons(skb->dev->hard_header_len))) goto nla_put_failure; hwhdrp = skb_mac_header(skb); if (skb->dev->type == ARPHRD_SIT) hwhdrp -= ETH_HLEN; if (hwhdrp >= skb->head && nla_put(inst->skb, NFULA_HWHEADER, skb->dev->hard_header_len, hwhdrp)) goto nla_put_failure; } if (hooknum <= NF_INET_FORWARD) { struct timespec64 kts = ktime_to_timespec64(skb_tstamp_cond(skb, true)); struct nfulnl_msg_packet_timestamp ts; ts.sec = cpu_to_be64(kts.tv_sec); ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC); if (nla_put(inst->skb, NFULA_TIMESTAMP, sizeof(ts), &ts)) goto nla_put_failure; } /* UID */ sk = skb->sk; if (sk && sk_fullsock(sk)) { const struct socket *sock; const struct file *file; /* The sk pointer remains valid as long as the skb is. * The sk_socket and file pointer may become NULL * if the socket is closed. * Both structures (including file->cred) are RCU freed * which means they can be accessed within a RCU read section. */ sock = READ_ONCE(sk->sk_socket); file = sock ? READ_ONCE(sock->file) : NULL; if (file) { const struct cred *cred = file->f_cred; struct user_namespace *user_ns = inst->peer_user_ns; __be32 uid = htonl(from_kuid_munged(user_ns, cred->fsuid)); __be32 gid = htonl(from_kgid_munged(user_ns, cred->fsgid)); if (nla_put_be32(inst->skb, NFULA_UID, uid) || nla_put_be32(inst->skb, NFULA_GID, gid)) goto nla_put_failure; } } /* local sequence number */ if ((inst->flags & NFULNL_CFG_F_SEQ) && nla_put_be32(inst->skb, NFULA_SEQ, htonl(inst->seq++))) goto nla_put_failure; /* global sequence number */ if ((inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) && nla_put_be32(inst->skb, NFULA_SEQ_GLOBAL, htonl(atomic_inc_return(&log->global_seq)))) goto nla_put_failure; if (ct && nfnl_ct->build(inst->skb, ct, ctinfo, NFULA_CT, NFULA_CT_INFO) < 0) goto nla_put_failure; if ((pf == NFPROTO_NETDEV || pf == NFPROTO_BRIDGE) && nfulnl_put_bridge(inst, skb) < 0) goto nla_put_failure; if (data_len) { struct nlattr *nla; nla = nla_reserve(inst->skb, NFULA_PAYLOAD, data_len); if (!nla) goto nla_put_failure; if (skb_copy_bits(skb, 0, nla_data(nla), data_len)) goto nla_put_failure; } nlh->nlmsg_len = inst->skb->tail - old_tail; return 0; nla_put_failure: PRINTR(KERN_ERR "nfnetlink_log: error creating log nlmsg\n"); return -1; } static const struct nf_loginfo default_loginfo = { .type = NF_LOG_TYPE_ULOG, .u = { .ulog = { .copy_len = 0xffff, .group = 0, .qthreshold = 1, }, }, }; static unsigned int nfulnl_get_copy_len(const struct nf_loginfo *li, const struct sk_buff *skb, unsigned int copy_len) { unsigned int len = skb->len; if ((li->u.ulog.flags & NF_LOG_F_COPY_LEN) && li->u.ulog.copy_len < copy_len) copy_len = li->u.ulog.copy_len; if (!skb_frags_readable(skb)) len = skb_headlen(skb); return min(len, copy_len); } /* log handler for internal netfilter logging api */ static void nfulnl_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *li_user, const char *prefix) { size_t size; unsigned int data_len; struct nfulnl_instance *inst; const struct nf_loginfo *li; unsigned int qthreshold; unsigned int plen = 0; struct nfnl_log_net *log = nfnl_log_pernet(net); const struct nfnl_ct_hook *nfnl_ct = NULL; enum ip_conntrack_info ctinfo = 0; struct nf_conn *ct = NULL; if (li_user && li_user->type == NF_LOG_TYPE_ULOG) li = li_user; else li = &default_loginfo; inst = instance_lookup_get_rcu(log, li->u.ulog.group); if (!inst) return; if (prefix) plen = strlen(prefix) + 1; /* FIXME: do we want to make the size calculation conditional based on * what is actually present? way more branches and checks, but more * memory efficient... */ size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfulnl_msg_packet_hdr)) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #endif + nla_total_size(sizeof(u_int32_t)) /* mark */ + nla_total_size(sizeof(u_int32_t)) /* uid */ + nla_total_size(sizeof(u_int32_t)) /* gid */ + nla_total_size(plen) /* prefix */ + nla_total_size(sizeof(struct nfulnl_msg_packet_hw)) + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)) + nlmsg_total_size(sizeof(struct nfgenmsg)); /* NLMSG_DONE */ if (in && skb_mac_header_was_set(skb)) { size += nla_total_size(skb->dev->hard_header_len) + nla_total_size(sizeof(u_int16_t)) /* hwtype */ + nla_total_size(sizeof(u_int16_t)); /* hwlen */ } spin_lock_bh(&inst->lock); if (inst->flags & NFULNL_CFG_F_SEQ) size += nla_total_size(sizeof(u_int32_t)); if (inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) size += nla_total_size(sizeof(u_int32_t)); #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (inst->flags & NFULNL_CFG_F_CONNTRACK) { nfnl_ct = rcu_dereference(nfnl_ct_hook); if (nfnl_ct != NULL) { ct = nf_ct_get(skb, &ctinfo); if (ct != NULL) size += nfnl_ct->build_size(ct); } } #endif if (pf == NFPROTO_NETDEV || pf == NFPROTO_BRIDGE) size += nfulnl_get_bridge_size(skb); qthreshold = inst->qthreshold; /* per-rule qthreshold overrides per-instance */ if (li->u.ulog.qthreshold) if (qthreshold > li->u.ulog.qthreshold) qthreshold = li->u.ulog.qthreshold; switch (inst->copy_mode) { case NFULNL_COPY_META: case NFULNL_COPY_NONE: data_len = 0; break; case NFULNL_COPY_PACKET: data_len = nfulnl_get_copy_len(li, skb, inst->copy_range); size += nla_total_size(data_len); break; case NFULNL_COPY_DISABLED: default: goto unlock_and_release; } if (inst->skb && size > skb_tailroom(inst->skb)) { /* either the queue len is too high or we don't have * enough room in the skb left. flush to userspace. */ __nfulnl_flush(inst); } if (!inst->skb) { inst->skb = nfulnl_alloc_skb(net, inst->peer_portid, inst->nlbufsiz, size); if (!inst->skb) goto alloc_failure; } inst->qlen++; __build_packet_message(log, inst, skb, data_len, pf, hooknum, in, out, prefix, plen, nfnl_ct, ct, ctinfo); if (inst->qlen >= qthreshold) __nfulnl_flush(inst); /* timer_pending always called within inst->lock, so there * is no chance of a race here */ else if (!timer_pending(&inst->timer)) { instance_get(inst); inst->timer.expires = jiffies + (inst->flushtimeout*HZ/100); add_timer(&inst->timer); } unlock_and_release: spin_unlock_bh(&inst->lock); instance_put(inst); return; alloc_failure: /* FIXME: statistics */ goto unlock_and_release; } static int nfulnl_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netlink_notify *n = ptr; struct nfnl_log_net *log = nfnl_log_pernet(n->net); if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) { int i; /* destroy all instances for this portid */ spin_lock_bh(&log->instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct hlist_node *t2; struct nfulnl_instance *inst; struct hlist_head *head = &log->instance_table[i]; hlist_for_each_entry_safe(inst, t2, head, hlist) { if (n->portid == inst->peer_portid) __instance_destroy(inst); } } spin_unlock_bh(&log->instances_lock); } return NOTIFY_DONE; } static struct notifier_block nfulnl_rtnl_notifier = { .notifier_call = nfulnl_rcv_nl_event, }; static int nfulnl_recv_unsupp(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfula[]) { return -ENOTSUPP; } static struct nf_logger nfulnl_logger __read_mostly = { .name = "nfnetlink_log", .type = NF_LOG_TYPE_ULOG, .logfn = nfulnl_log_packet, .me = THIS_MODULE, }; static const struct nla_policy nfula_cfg_policy[NFULA_CFG_MAX+1] = { [NFULA_CFG_CMD] = { .len = sizeof(struct nfulnl_msg_config_cmd) }, [NFULA_CFG_MODE] = { .len = sizeof(struct nfulnl_msg_config_mode) }, [NFULA_CFG_TIMEOUT] = { .type = NLA_U32 }, [NFULA_CFG_QTHRESH] = { .type = NLA_U32 }, [NFULA_CFG_NLBUFSIZ] = { .type = NLA_U32 }, [NFULA_CFG_FLAGS] = NLA_POLICY_MASK(NLA_BE16, NFULNL_CFG_F_SEQ | NFULNL_CFG_F_SEQ_GLOBAL | NFULNL_CFG_F_CONNTRACK), }; static int nfulnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfula[]) { struct nfnl_log_net *log = nfnl_log_pernet(info->net); u_int16_t group_num = ntohs(info->nfmsg->res_id); struct nfulnl_msg_config_cmd *cmd = NULL; struct nfulnl_instance *inst; u16 flags = 0; int ret = 0; if (nfula[NFULA_CFG_CMD]) { u_int8_t pf = info->nfmsg->nfgen_family; cmd = nla_data(nfula[NFULA_CFG_CMD]); /* Commands without queue context */ switch (cmd->command) { case NFULNL_CFG_CMD_PF_BIND: return nf_log_bind_pf(info->net, pf, &nfulnl_logger); case NFULNL_CFG_CMD_PF_UNBIND: nf_log_unbind_pf(info->net, pf); return 0; } } inst = instance_lookup_get(log, group_num); if (inst && inst->peer_portid != NETLINK_CB(skb).portid) { ret = -EPERM; goto out_put; } /* Check if we support these flags in first place, dependencies should * be there too not to break atomicity. */ if (nfula[NFULA_CFG_FLAGS]) { flags = ntohs(nla_get_be16(nfula[NFULA_CFG_FLAGS])); if ((flags & NFULNL_CFG_F_CONNTRACK) && !rcu_access_pointer(nfnl_ct_hook)) { #ifdef CONFIG_MODULES nfnl_unlock(NFNL_SUBSYS_ULOG); request_module("ip_conntrack_netlink"); nfnl_lock(NFNL_SUBSYS_ULOG); if (rcu_access_pointer(nfnl_ct_hook)) { ret = -EAGAIN; goto out_put; } #endif ret = -EOPNOTSUPP; goto out_put; } } if (cmd != NULL) { switch (cmd->command) { case NFULNL_CFG_CMD_BIND: if (inst) { ret = -EBUSY; goto out_put; } inst = instance_create(info->net, group_num, NETLINK_CB(skb).portid, sk_user_ns(NETLINK_CB(skb).sk)); if (IS_ERR(inst)) { ret = PTR_ERR(inst); goto out; } break; case NFULNL_CFG_CMD_UNBIND: if (!inst) { ret = -ENODEV; goto out; } instance_destroy(log, inst); goto out_put; default: ret = -ENOTSUPP; goto out_put; } } else if (!inst) { ret = -ENODEV; goto out; } if (nfula[NFULA_CFG_MODE]) { struct nfulnl_msg_config_mode *params = nla_data(nfula[NFULA_CFG_MODE]); nfulnl_set_mode(inst, params->copy_mode, ntohl(params->copy_range)); } if (nfula[NFULA_CFG_TIMEOUT]) { __be32 timeout = nla_get_be32(nfula[NFULA_CFG_TIMEOUT]); nfulnl_set_timeout(inst, ntohl(timeout)); } if (nfula[NFULA_CFG_NLBUFSIZ]) { __be32 nlbufsiz = nla_get_be32(nfula[NFULA_CFG_NLBUFSIZ]); nfulnl_set_nlbufsiz(inst, ntohl(nlbufsiz)); } if (nfula[NFULA_CFG_QTHRESH]) { __be32 qthresh = nla_get_be32(nfula[NFULA_CFG_QTHRESH]); nfulnl_set_qthresh(inst, ntohl(qthresh)); } if (nfula[NFULA_CFG_FLAGS]) nfulnl_set_flags(inst, flags); out_put: instance_put(inst); out: return ret; } static const struct nfnl_callback nfulnl_cb[NFULNL_MSG_MAX] = { [NFULNL_MSG_PACKET] = { .call = nfulnl_recv_unsupp, .type = NFNL_CB_MUTEX, .attr_count = NFULA_MAX, }, [NFULNL_MSG_CONFIG] = { .call = nfulnl_recv_config, .type = NFNL_CB_MUTEX, .attr_count = NFULA_CFG_MAX, .policy = nfula_cfg_policy }, }; static const struct nfnetlink_subsystem nfulnl_subsys = { .name = "log", .subsys_id = NFNL_SUBSYS_ULOG, .cb_count = NFULNL_MSG_MAX, .cb = nfulnl_cb, }; #ifdef CONFIG_PROC_FS struct iter_state { struct seq_net_private p; unsigned int bucket; }; static struct hlist_node *get_first(struct net *net, struct iter_state *st) { struct nfnl_log_net *log; if (!st) return NULL; log = nfnl_log_pernet(net); for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) { struct hlist_head *head = &log->instance_table[st->bucket]; if (!hlist_empty(head)) return rcu_dereference(hlist_first_rcu(head)); } return NULL; } static struct hlist_node *get_next(struct net *net, struct iter_state *st, struct hlist_node *h) { h = rcu_dereference(hlist_next_rcu(h)); while (!h) { struct nfnl_log_net *log; struct hlist_head *head; if (++st->bucket >= INSTANCE_BUCKETS) return NULL; log = nfnl_log_pernet(net); head = &log->instance_table[st->bucket]; h = rcu_dereference(hlist_first_rcu(head)); } return h; } static struct hlist_node *get_idx(struct net *net, struct iter_state *st, loff_t pos) { struct hlist_node *head; head = get_first(net, st); if (head) while (pos && (head = get_next(net, st, head))) pos--; return pos ? NULL : head; } static void *seq_start(struct seq_file *s, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return get_idx(seq_file_net(s), s->private, *pos); } static void *seq_next(struct seq_file *s, void *v, loff_t *pos) { (*pos)++; return get_next(seq_file_net(s), s->private, v); } static void seq_stop(struct seq_file *s, void *v) __releases(rcu) { rcu_read_unlock(); } static int seq_show(struct seq_file *s, void *v) { const struct nfulnl_instance *inst = v; seq_printf(s, "%5u %6u %5u %1u %5u %6u %2u\n", inst->group_num, inst->peer_portid, inst->qlen, inst->copy_mode, inst->copy_range, inst->flushtimeout, refcount_read(&inst->use)); return 0; } static const struct seq_operations nful_seq_ops = { .start = seq_start, .next = seq_next, .stop = seq_stop, .show = seq_show, }; #endif /* PROC_FS */ static int __net_init nfnl_log_net_init(struct net *net) { unsigned int i; struct nfnl_log_net *log = nfnl_log_pernet(net); #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc; kuid_t root_uid; kgid_t root_gid; #endif for (i = 0; i < INSTANCE_BUCKETS; i++) INIT_HLIST_HEAD(&log->instance_table[i]); spin_lock_init(&log->instances_lock); #ifdef CONFIG_PROC_FS proc = proc_create_net("nfnetlink_log", 0440, net->nf.proc_netfilter, &nful_seq_ops, sizeof(struct iter_state)); if (!proc) return -ENOMEM; root_uid = make_kuid(net->user_ns, 0); root_gid = make_kgid(net->user_ns, 0); if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); #endif return 0; } static void __net_exit nfnl_log_net_pre_exit(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_log", net->nf.proc_netfilter); #endif nf_log_unset(net, &nfulnl_logger); } static void __net_exit nfnl_log_net_exit(struct net *net) { struct nfnl_log_net *log = nfnl_log_pernet(net); unsigned int i; for (i = 0; i < INSTANCE_BUCKETS; i++) WARN_ON_ONCE(!hlist_empty(&log->instance_table[i])); } static struct pernet_operations nfnl_log_net_ops = { .init = nfnl_log_net_init, .pre_exit = nfnl_log_net_pre_exit, .exit = nfnl_log_net_exit, .id = &nfnl_log_net_id, .size = sizeof(struct nfnl_log_net), }; static int __init nfnetlink_log_init(void) { int status; status = register_pernet_subsys(&nfnl_log_net_ops); if (status < 0) { pr_err("failed to register pernet ops\n"); goto out; } netlink_register_notifier(&nfulnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfulnl_subsys); if (status < 0) { pr_err("failed to create netlink socket\n"); goto cleanup_netlink_notifier; } status = nf_log_register(NFPROTO_UNSPEC, &nfulnl_logger); if (status < 0) { pr_err("failed to register logger\n"); goto cleanup_subsys; } return status; cleanup_subsys: nfnetlink_subsys_unregister(&nfulnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfulnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_log_net_ops); out: return status; } static void __exit nfnetlink_log_fini(void) { nfnetlink_subsys_unregister(&nfulnl_subsys); netlink_unregister_notifier(&nfulnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_log_net_ops); nf_log_unregister(&nfulnl_logger); } MODULE_DESCRIPTION("netfilter userspace logging"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ULOG); MODULE_ALIAS_NF_LOGGER(AF_INET, 1); MODULE_ALIAS_NF_LOGGER(AF_INET6, 1); MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 1); MODULE_ALIAS_NF_LOGGER(3, 1); /* NFPROTO_ARP */ MODULE_ALIAS_NF_LOGGER(5, 1); /* NFPROTO_NETDEV */ module_init(nfnetlink_log_init); module_exit(nfnetlink_log_fini); |
| 5 4 5 4 1 4 4 2 1 1 2 2 2 2447 2435 22 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 | /* Copyright 2011, Siemens AG * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ /* Based on patches from Jon Smirl <jonsmirl@gmail.com> * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 * as published by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ /* Jon's code is based on 6lowpan implementation for Contiki which is: * Copyright (c) 2008, Swedish Institute of Computer Science. * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the Institute nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/ieee802154.h> #include <linux/if_arp.h> #include <net/ipv6.h> #include <net/netdev_lock.h> #include "6lowpan_i.h" static int open_count; static const struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; static int lowpan_dev_init(struct net_device *ldev) { netdev_lockdep_set_classes(ldev); return 0; } static int lowpan_open(struct net_device *dev) { if (!open_count) lowpan_rx_init(); open_count++; return 0; } static int lowpan_stop(struct net_device *dev) { open_count--; if (!open_count) lowpan_rx_exit(); return 0; } static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n) { struct lowpan_802154_neigh *neigh = lowpan_802154_neigh(neighbour_priv(n)); /* default no short_addr is available for a neighbour */ neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC); return 0; } static int lowpan_get_iflink(const struct net_device *dev) { return READ_ONCE(lowpan_802154_dev(dev)->wdev->ifindex); } static const struct net_device_ops lowpan_netdev_ops = { .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_open = lowpan_open, .ndo_stop = lowpan_stop, .ndo_neigh_construct = lowpan_neigh_construct, .ndo_get_iflink = lowpan_get_iflink, }; static void lowpan_setup(struct net_device *ldev) { memset(ldev->broadcast, 0xff, IEEE802154_ADDR_LEN); /* We need an ipv6hdr as minimum len when calling xmit */ ldev->hard_header_len = sizeof(struct ipv6hdr); ldev->flags = IFF_BROADCAST | IFF_MULTICAST; ldev->priv_flags |= IFF_NO_QUEUE; ldev->netdev_ops = &lowpan_netdev_ops; ldev->header_ops = &lowpan_header_ops; ldev->needs_free_netdev = true; ldev->netns_immutable = true; } static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != IEEE802154_ADDR_LEN) return -EINVAL; } return 0; } static int lowpan_newlink(struct net_device *ldev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct nlattr **tb = params->tb; struct net_device *wdev; int ret; ASSERT_RTNL(); pr_debug("adding new link\n"); if (!tb[IFLA_LINK]) return -EINVAL; if (params->link_net && !net_eq(params->link_net, dev_net(ldev))) return -EINVAL; /* find and hold wpan device */ wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK])); if (!wdev) return -ENODEV; if (wdev->type != ARPHRD_IEEE802154) { dev_put(wdev); return -EINVAL; } if (wdev->ieee802154_ptr->lowpan_dev) { dev_put(wdev); return -EBUSY; } lowpan_802154_dev(ldev)->wdev = wdev; /* Set the lowpan hardware address to the wpan hardware address. */ __dev_addr_set(ldev, wdev->dev_addr, IEEE802154_ADDR_LEN); /* We need headroom for possible wpan_dev_hard_header call and tailroom * for encryption/fcs handling. The lowpan interface will replace * the IPv6 header with 6LoWPAN header. At worst case the 6LoWPAN * header has LOWPAN_IPHC_MAX_HEADER_LEN more bytes than the IPv6 * header. */ ldev->needed_headroom = LOWPAN_IPHC_MAX_HEADER_LEN + wdev->needed_headroom; ldev->needed_tailroom = wdev->needed_tailroom; ldev->neigh_priv_len = sizeof(struct lowpan_802154_neigh); ret = lowpan_register_netdevice(ldev, LOWPAN_LLTYPE_IEEE802154); if (ret < 0) { dev_put(wdev); return ret; } wdev->ieee802154_ptr->lowpan_dev = ldev; return 0; } static void lowpan_dellink(struct net_device *ldev, struct list_head *head) { struct net_device *wdev = lowpan_802154_dev(ldev)->wdev; ASSERT_RTNL(); wdev->ieee802154_ptr->lowpan_dev = NULL; lowpan_unregister_netdevice(ldev); dev_put(wdev); } static struct rtnl_link_ops lowpan_link_ops __read_mostly = { .kind = "lowpan", .priv_size = LOWPAN_PRIV_SIZE(sizeof(struct lowpan_802154_dev)), .setup = lowpan_setup, .newlink = lowpan_newlink, .dellink = lowpan_dellink, .validate = lowpan_validate, }; static inline int __init lowpan_netlink_init(void) { return rtnl_link_register(&lowpan_link_ops); } static inline void lowpan_netlink_fini(void) { rtnl_link_unregister(&lowpan_link_ops); } static int lowpan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct wpan_dev *wpan_dev; if (ndev->type != ARPHRD_IEEE802154) return NOTIFY_DONE; wpan_dev = ndev->ieee802154_ptr; if (!wpan_dev) return NOTIFY_DONE; switch (event) { case NETDEV_UNREGISTER: /* Check if wpan interface is unregistered that we * also delete possible lowpan interfaces which belongs * to the wpan interface. */ if (wpan_dev->lowpan_dev) lowpan_dellink(wpan_dev->lowpan_dev, NULL); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block lowpan_dev_notifier = { .notifier_call = lowpan_device_event, }; static int __init lowpan_init_module(void) { int err = 0; err = lowpan_net_frag_init(); if (err < 0) goto out; err = lowpan_netlink_init(); if (err < 0) goto out_frag; err = register_netdevice_notifier(&lowpan_dev_notifier); if (err < 0) goto out_pack; return 0; out_pack: lowpan_netlink_fini(); out_frag: lowpan_net_frag_exit(); out: return err; } static void __exit lowpan_cleanup_module(void) { lowpan_netlink_fini(); lowpan_net_frag_exit(); unregister_netdevice_notifier(&lowpan_dev_notifier); } module_init(lowpan_init_module); module_exit(lowpan_cleanup_module); MODULE_DESCRIPTION("IPv6 over Low power Wireless Personal Area Network IEEE 802.15.4 core"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("lowpan"); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include "devl_internal.h" static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = { { .name = "destination mac", .id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC, .bitwidth = 48, }, }; struct devlink_dpipe_header devlink_dpipe_header_ethernet = { .name = "ethernet", .id = DEVLINK_DPIPE_HEADER_ETHERNET, .fields = devlink_dpipe_fields_ethernet, .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ethernet), .global = true, }; EXPORT_SYMBOL_GPL(devlink_dpipe_header_ethernet); static struct devlink_dpipe_field devlink_dpipe_fields_ipv4[] = { { .name = "destination ip", .id = DEVLINK_DPIPE_FIELD_IPV4_DST_IP, .bitwidth = 32, }, }; struct devlink_dpipe_header devlink_dpipe_header_ipv4 = { .name = "ipv4", .id = DEVLINK_DPIPE_HEADER_IPV4, .fields = devlink_dpipe_fields_ipv4, .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv4), .global = true, }; EXPORT_SYMBOL_GPL(devlink_dpipe_header_ipv4); static struct devlink_dpipe_field devlink_dpipe_fields_ipv6[] = { { .name = "destination ip", .id = DEVLINK_DPIPE_FIELD_IPV6_DST_IP, .bitwidth = 128, }, }; struct devlink_dpipe_header devlink_dpipe_header_ipv6 = { .name = "ipv6", .id = DEVLINK_DPIPE_HEADER_IPV6, .fields = devlink_dpipe_fields_ipv6, .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv6), .global = true, }; EXPORT_SYMBOL_GPL(devlink_dpipe_header_ipv6); int devlink_dpipe_match_put(struct sk_buff *skb, struct devlink_dpipe_match *match) { struct devlink_dpipe_header *header = match->header; struct devlink_dpipe_field *field = &header->fields[match->field_id]; struct nlattr *match_attr; match_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_MATCH); if (!match_attr) return -EMSGSIZE; if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_MATCH_TYPE, match->type) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, match->header_index) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) goto nla_put_failure; nla_nest_end(skb, match_attr); return 0; nla_put_failure: nla_nest_cancel(skb, match_attr); return -EMSGSIZE; } EXPORT_SYMBOL_GPL(devlink_dpipe_match_put); static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table, struct sk_buff *skb) { struct nlattr *matches_attr; matches_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLE_MATCHES); if (!matches_attr) return -EMSGSIZE; if (table->table_ops->matches_dump(table->priv, skb)) goto nla_put_failure; nla_nest_end(skb, matches_attr); return 0; nla_put_failure: nla_nest_cancel(skb, matches_attr); return -EMSGSIZE; } int devlink_dpipe_action_put(struct sk_buff *skb, struct devlink_dpipe_action *action) { struct devlink_dpipe_header *header = action->header; struct devlink_dpipe_field *field = &header->fields[action->field_id]; struct nlattr *action_attr; action_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ACTION); if (!action_attr) return -EMSGSIZE; if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_ACTION_TYPE, action->type) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, action->header_index) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) goto nla_put_failure; nla_nest_end(skb, action_attr); return 0; nla_put_failure: nla_nest_cancel(skb, action_attr); return -EMSGSIZE; } EXPORT_SYMBOL_GPL(devlink_dpipe_action_put); static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table, struct sk_buff *skb) { struct nlattr *actions_attr; actions_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLE_ACTIONS); if (!actions_attr) return -EMSGSIZE; if (table->table_ops->actions_dump(table->priv, skb)) goto nla_put_failure; nla_nest_end(skb, actions_attr); return 0; nla_put_failure: nla_nest_cancel(skb, actions_attr); return -EMSGSIZE; } static int devlink_dpipe_table_put(struct sk_buff *skb, struct devlink_dpipe_table *table) { struct nlattr *table_attr; u64 table_size; table_size = table->table_ops->size_get(table->priv); table_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLE); if (!table_attr) return -EMSGSIZE; if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) || devlink_nl_put_u64(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table_size)) goto nla_put_failure; if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, table->counters_enabled)) goto nla_put_failure; if (table->resource_valid) { if (devlink_nl_put_u64(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, table->resource_id) || devlink_nl_put_u64(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS, table->resource_units)) goto nla_put_failure; } if (devlink_dpipe_matches_put(table, skb)) goto nla_put_failure; if (devlink_dpipe_actions_put(table, skb)) goto nla_put_failure; nla_nest_end(skb, table_attr); return 0; nla_put_failure: nla_nest_cancel(skb, table_attr); return -EMSGSIZE; } static int devlink_dpipe_send_and_alloc_skb(struct sk_buff **pskb, struct genl_info *info) { int err; if (*pskb) { err = genlmsg_reply(*pskb, info); if (err) return err; } *pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!*pskb) return -ENOMEM; return 0; } static int devlink_dpipe_tables_fill(struct genl_info *info, enum devlink_command cmd, int flags, struct list_head *dpipe_tables, const char *table_name) { struct devlink *devlink = info->user_ptr[0]; struct devlink_dpipe_table *table; struct nlattr *tables_attr; struct sk_buff *skb = NULL; struct nlmsghdr *nlh; bool incomplete; void *hdr; int i; int err; table = list_first_entry(dpipe_tables, struct devlink_dpipe_table, list); start_again: err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) return err; hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, &devlink_nl_family, NLM_F_MULTI, cmd); if (!hdr) { nlmsg_free(skb); return -EMSGSIZE; } if (devlink_nl_put_handle(skb, devlink)) goto nla_put_failure; tables_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLES); if (!tables_attr) goto nla_put_failure; i = 0; incomplete = false; list_for_each_entry_from(table, dpipe_tables, list) { if (!table_name) { err = devlink_dpipe_table_put(skb, table); if (err) { if (!i) goto err_table_put; incomplete = true; break; } } else { if (!strcmp(table->name, table_name)) { err = devlink_dpipe_table_put(skb, table); if (err) break; } } i++; } nla_nest_end(skb, tables_attr); genlmsg_end(skb, hdr); if (incomplete) goto start_again; send_done: nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) return err; goto send_done; } return genlmsg_reply(skb, info); nla_put_failure: err = -EMSGSIZE; err_table_put: nlmsg_free(skb); return err; } int devlink_nl_dpipe_table_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const char *table_name = NULL; if (info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]) table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); return devlink_dpipe_tables_fill(info, DEVLINK_CMD_DPIPE_TABLE_GET, 0, &devlink->dpipe_table_list, table_name); } static int devlink_dpipe_value_put(struct sk_buff *skb, struct devlink_dpipe_value *value) { if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE, value->value_size, value->value)) return -EMSGSIZE; if (value->mask) if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE_MASK, value->value_size, value->mask)) return -EMSGSIZE; if (value->mapping_valid) if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_VALUE_MAPPING, value->mapping_value)) return -EMSGSIZE; return 0; } static int devlink_dpipe_action_value_put(struct sk_buff *skb, struct devlink_dpipe_value *value) { if (!value->action) return -EINVAL; if (devlink_dpipe_action_put(skb, value->action)) return -EMSGSIZE; if (devlink_dpipe_value_put(skb, value)) return -EMSGSIZE; return 0; } static int devlink_dpipe_action_values_put(struct sk_buff *skb, struct devlink_dpipe_value *values, unsigned int values_count) { struct nlattr *action_attr; int i; int err; for (i = 0; i < values_count; i++) { action_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ACTION_VALUE); if (!action_attr) return -EMSGSIZE; err = devlink_dpipe_action_value_put(skb, &values[i]); if (err) goto err_action_value_put; nla_nest_end(skb, action_attr); } return 0; err_action_value_put: nla_nest_cancel(skb, action_attr); return err; } static int devlink_dpipe_match_value_put(struct sk_buff *skb, struct devlink_dpipe_value *value) { if (!value->match) return -EINVAL; if (devlink_dpipe_match_put(skb, value->match)) return -EMSGSIZE; if (devlink_dpipe_value_put(skb, value)) return -EMSGSIZE; return 0; } static int devlink_dpipe_match_values_put(struct sk_buff *skb, struct devlink_dpipe_value *values, unsigned int values_count) { struct nlattr *match_attr; int i; int err; for (i = 0; i < values_count; i++) { match_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_MATCH_VALUE); if (!match_attr) return -EMSGSIZE; err = devlink_dpipe_match_value_put(skb, &values[i]); if (err) goto err_match_value_put; nla_nest_end(skb, match_attr); } return 0; err_match_value_put: nla_nest_cancel(skb, match_attr); return err; } static int devlink_dpipe_entry_put(struct sk_buff *skb, struct devlink_dpipe_entry *entry) { struct nlattr *entry_attr, *matches_attr, *actions_attr; int err; entry_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ENTRY); if (!entry_attr) return -EMSGSIZE; if (devlink_nl_put_u64(skb, DEVLINK_ATTR_DPIPE_ENTRY_INDEX, entry->index)) goto nla_put_failure; if (entry->counter_valid) if (devlink_nl_put_u64(skb, DEVLINK_ATTR_DPIPE_ENTRY_COUNTER, entry->counter)) goto nla_put_failure; matches_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES); if (!matches_attr) goto nla_put_failure; err = devlink_dpipe_match_values_put(skb, entry->match_values, entry->match_values_count); if (err) { nla_nest_cancel(skb, matches_attr); goto err_match_values_put; } nla_nest_end(skb, matches_attr); actions_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES); if (!actions_attr) goto nla_put_failure; err = devlink_dpipe_action_values_put(skb, entry->action_values, entry->action_values_count); if (err) { nla_nest_cancel(skb, actions_attr); goto err_action_values_put; } nla_nest_end(skb, actions_attr); nla_nest_end(skb, entry_attr); return 0; nla_put_failure: err = -EMSGSIZE; err_match_values_put: err_action_values_put: nla_nest_cancel(skb, entry_attr); return err; } static struct devlink_dpipe_table * devlink_dpipe_table_find(struct list_head *dpipe_tables, const char *table_name, struct devlink *devlink) { struct devlink_dpipe_table *table; list_for_each_entry_rcu(table, dpipe_tables, list, lockdep_is_held(&devlink->lock)) { if (!strcmp(table->name, table_name)) return table; } return NULL; } int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx) { struct devlink *devlink; int err; err = devlink_dpipe_send_and_alloc_skb(&dump_ctx->skb, dump_ctx->info); if (err) return err; dump_ctx->hdr = genlmsg_put(dump_ctx->skb, dump_ctx->info->snd_portid, dump_ctx->info->snd_seq, &devlink_nl_family, NLM_F_MULTI, dump_ctx->cmd); if (!dump_ctx->hdr) goto nla_put_failure; devlink = dump_ctx->info->user_ptr[0]; if (devlink_nl_put_handle(dump_ctx->skb, devlink)) goto nla_put_failure; dump_ctx->nest = nla_nest_start_noflag(dump_ctx->skb, DEVLINK_ATTR_DPIPE_ENTRIES); if (!dump_ctx->nest) goto nla_put_failure; return 0; nla_put_failure: nlmsg_free(dump_ctx->skb); return -EMSGSIZE; } EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_prepare); int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx, struct devlink_dpipe_entry *entry) { return devlink_dpipe_entry_put(dump_ctx->skb, entry); } EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_append); int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx) { nla_nest_end(dump_ctx->skb, dump_ctx->nest); genlmsg_end(dump_ctx->skb, dump_ctx->hdr); return 0; } EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_close); void devlink_dpipe_entry_clear(struct devlink_dpipe_entry *entry) { unsigned int value_count, value_index; struct devlink_dpipe_value *value; value = entry->action_values; value_count = entry->action_values_count; for (value_index = 0; value_index < value_count; value_index++) { kfree(value[value_index].value); kfree(value[value_index].mask); } value = entry->match_values; value_count = entry->match_values_count; for (value_index = 0; value_index < value_count; value_index++) { kfree(value[value_index].value); kfree(value[value_index].mask); } } EXPORT_SYMBOL_GPL(devlink_dpipe_entry_clear); static int devlink_dpipe_entries_fill(struct genl_info *info, enum devlink_command cmd, int flags, struct devlink_dpipe_table *table) { struct devlink_dpipe_dump_ctx dump_ctx; struct nlmsghdr *nlh; int err; dump_ctx.skb = NULL; dump_ctx.cmd = cmd; dump_ctx.info = info; err = table->table_ops->entries_dump(table->priv, table->counters_enabled, &dump_ctx); if (err) return err; send_done: nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info); if (err) return err; goto send_done; } return genlmsg_reply(dump_ctx.skb, info); } int devlink_nl_dpipe_entries_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_dpipe_table *table; const char *table_name; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_DPIPE_TABLE_NAME)) return -EINVAL; table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name, devlink); if (!table) return -EINVAL; if (!table->table_ops->entries_dump) return -EINVAL; return devlink_dpipe_entries_fill(info, DEVLINK_CMD_DPIPE_ENTRIES_GET, 0, table); } static int devlink_dpipe_fields_put(struct sk_buff *skb, const struct devlink_dpipe_header *header) { struct devlink_dpipe_field *field; struct nlattr *field_attr; int i; for (i = 0; i < header->fields_count; i++) { field = &header->fields[i]; field_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_FIELD); if (!field_attr) return -EMSGSIZE; if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, field->bitwidth) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, field->mapping_type)) goto nla_put_failure; nla_nest_end(skb, field_attr); } return 0; nla_put_failure: nla_nest_cancel(skb, field_attr); return -EMSGSIZE; } static int devlink_dpipe_header_put(struct sk_buff *skb, struct devlink_dpipe_header *header) { struct nlattr *fields_attr, *header_attr; int err; header_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADER); if (!header_attr) return -EMSGSIZE; if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_HEADER_NAME, header->name) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) goto nla_put_failure; fields_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADER_FIELDS); if (!fields_attr) goto nla_put_failure; err = devlink_dpipe_fields_put(skb, header); if (err) { nla_nest_cancel(skb, fields_attr); goto nla_put_failure; } nla_nest_end(skb, fields_attr); nla_nest_end(skb, header_attr); return 0; nla_put_failure: err = -EMSGSIZE; nla_nest_cancel(skb, header_attr); return err; } static int devlink_dpipe_headers_fill(struct genl_info *info, enum devlink_command cmd, int flags, struct devlink_dpipe_headers * dpipe_headers) { struct devlink *devlink = info->user_ptr[0]; struct nlattr *headers_attr; struct sk_buff *skb = NULL; struct nlmsghdr *nlh; void *hdr; int i, j; int err; i = 0; start_again: err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) return err; hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, &devlink_nl_family, NLM_F_MULTI, cmd); if (!hdr) { nlmsg_free(skb); return -EMSGSIZE; } if (devlink_nl_put_handle(skb, devlink)) goto nla_put_failure; headers_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADERS); if (!headers_attr) goto nla_put_failure; j = 0; for (; i < dpipe_headers->headers_count; i++) { err = devlink_dpipe_header_put(skb, dpipe_headers->headers[i]); if (err) { if (!j) goto err_table_put; break; } j++; } nla_nest_end(skb, headers_attr); genlmsg_end(skb, hdr); if (i != dpipe_headers->headers_count) goto start_again; send_done: nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) return err; goto send_done; } return genlmsg_reply(skb, info); nla_put_failure: err = -EMSGSIZE; err_table_put: nlmsg_free(skb); return err; } int devlink_nl_dpipe_headers_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; if (!devlink->dpipe_headers) return -EOPNOTSUPP; return devlink_dpipe_headers_fill(info, DEVLINK_CMD_DPIPE_HEADERS_GET, 0, devlink->dpipe_headers); } static int devlink_dpipe_table_counters_set(struct devlink *devlink, const char *table_name, bool enable) { struct devlink_dpipe_table *table; table = devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name, devlink); if (!table) return -EINVAL; if (table->counter_control_extern) return -EOPNOTSUPP; if (!(table->counters_enabled ^ enable)) return 0; table->counters_enabled = enable; if (table->table_ops->counters_set_update) table->table_ops->counters_set_update(table->priv, enable); return 0; } int devlink_nl_dpipe_table_counters_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const char *table_name; bool counters_enable; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_DPIPE_TABLE_NAME) || GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED)) return -EINVAL; table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); counters_enable = !!nla_get_u8(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]); return devlink_dpipe_table_counters_set(devlink, table_name, counters_enable); } /** * devl_dpipe_headers_register - register dpipe headers * * @devlink: devlink * @dpipe_headers: dpipe header array * * Register the headers supported by hardware. */ void devl_dpipe_headers_register(struct devlink *devlink, struct devlink_dpipe_headers *dpipe_headers) { lockdep_assert_held(&devlink->lock); devlink->dpipe_headers = dpipe_headers; } EXPORT_SYMBOL_GPL(devl_dpipe_headers_register); /** * devl_dpipe_headers_unregister - unregister dpipe headers * * @devlink: devlink * * Unregister the headers supported by hardware. */ void devl_dpipe_headers_unregister(struct devlink *devlink) { lockdep_assert_held(&devlink->lock); devlink->dpipe_headers = NULL; } EXPORT_SYMBOL_GPL(devl_dpipe_headers_unregister); /** * devlink_dpipe_table_counter_enabled - check if counter allocation * required * @devlink: devlink * @table_name: tables name * * Used by driver to check if counter allocation is required. * After counter allocation is turned on the table entries * are updated to include counter statistics. * * After that point on the driver must respect the counter * state so that each entry added to the table is added * with a counter. */ bool devlink_dpipe_table_counter_enabled(struct devlink *devlink, const char *table_name) { struct devlink_dpipe_table *table; bool enabled; rcu_read_lock(); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name, devlink); enabled = false; if (table) enabled = table->counters_enabled; rcu_read_unlock(); return enabled; } EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled); /** * devl_dpipe_table_register - register dpipe table * * @devlink: devlink * @table_name: table name * @table_ops: table ops * @priv: priv * @counter_control_extern: external control for counters */ int devl_dpipe_table_register(struct devlink *devlink, const char *table_name, const struct devlink_dpipe_table_ops *table_ops, void *priv, bool counter_control_extern) { struct devlink_dpipe_table *table; lockdep_assert_held(&devlink->lock); if (WARN_ON(!table_ops->size_get)) return -EINVAL; if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name, devlink)) return -EEXIST; table = kzalloc_obj(*table); if (!table) return -ENOMEM; table->name = table_name; table->table_ops = table_ops; table->priv = priv; table->counter_control_extern = counter_control_extern; list_add_tail_rcu(&table->list, &devlink->dpipe_table_list); return 0; } EXPORT_SYMBOL_GPL(devl_dpipe_table_register); /** * devl_dpipe_table_unregister - unregister dpipe table * * @devlink: devlink * @table_name: table name */ void devl_dpipe_table_unregister(struct devlink *devlink, const char *table_name) { struct devlink_dpipe_table *table; lockdep_assert_held(&devlink->lock); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name, devlink); if (!table) return; list_del_rcu(&table->list); kfree_rcu(table, rcu); } EXPORT_SYMBOL_GPL(devl_dpipe_table_unregister); /** * devl_dpipe_table_resource_set - set the resource id * * @devlink: devlink * @table_name: table name * @resource_id: resource id * @resource_units: number of resource's units consumed per table's entry */ int devl_dpipe_table_resource_set(struct devlink *devlink, const char *table_name, u64 resource_id, u64 resource_units) { struct devlink_dpipe_table *table; table = devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name, devlink); if (!table) return -EINVAL; table->resource_id = resource_id; table->resource_units = resource_units; table->resource_valid = true; return 0; } EXPORT_SYMBOL_GPL(devl_dpipe_table_resource_set); |
| 55 9 133 44 40 13 10 14 10 13 19 4 65 64 65 65 65 6 65 64 65 14 19 30 2 19 3 61 27 3 2 1 6 6 59 56 2 124 22 1 2 105 67 59 5 3 65 3 2 41 41 1 58 87 6 12 9 3 9 59 74 74 37 1 65 56 3 59 6 64 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to mapping data to requests */ #include <linux/kernel.h> #include <linux/sched/task_stack.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/uio.h> #include "blk.h" struct bio_map_data { bool is_our_pages : 1; bool is_null_mapped : 1; struct iov_iter iter; struct iovec iov[]; }; static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data, gfp_t gfp_mask) { struct bio_map_data *bmd; if (data->nr_segs > UIO_MAXIOV) return NULL; bmd = kmalloc_flex(*bmd, iov, data->nr_segs, gfp_mask); if (!bmd) return NULL; bmd->iter = *data; if (iter_is_iovec(data)) { memcpy(bmd->iov, iter_iov(data), sizeof(struct iovec) * data->nr_segs); bmd->iter.__iov = bmd->iov; } return bmd; } static inline void blk_mq_map_bio_put(struct bio *bio) { bio_put(bio); } static struct bio *blk_rq_map_bio_alloc(struct request *rq, unsigned int nr_vecs, gfp_t gfp_mask) { struct block_device *bdev = rq->q->disk ? rq->q->disk->part0 : NULL; struct bio *bio; bio = bio_alloc_bioset(bdev, nr_vecs, rq->cmd_flags, gfp_mask, &fs_bio_set); if (!bio) return NULL; return bio; } /** * bio_copy_from_iter - copy all pages from iov_iter to bio * @bio: The &struct bio which describes the I/O as destination * @iter: iov_iter as source * * Copy all pages from iov_iter to bio. * Returns 0 on success, or error on failure. */ static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter) { struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { ssize_t ret; ret = copy_page_from_iter(bvec->bv_page, bvec->bv_offset, bvec->bv_len, iter); if (!iov_iter_count(iter)) break; if (ret < bvec->bv_len) return -EFAULT; } return 0; } /** * bio_copy_to_iter - copy all pages from bio to iov_iter * @bio: The &struct bio which describes the I/O as source * @iter: iov_iter as destination * * Copy all pages from bio to iov_iter. * Returns 0 on success, or error on failure. */ static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter) { struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { ssize_t ret; ret = copy_page_to_iter(bvec->bv_page, bvec->bv_offset, bvec->bv_len, &iter); if (!iov_iter_count(&iter)) break; if (ret < bvec->bv_len) return -EFAULT; } return 0; } /** * bio_uncopy_user - finish previously mapped bio * @bio: bio being terminated * * Free pages allocated from bio_copy_user_iov() and write back data * to user space in case of a read. */ static int bio_uncopy_user(struct bio *bio) { struct bio_map_data *bmd = bio->bi_private; int ret = 0; if (!bmd->is_null_mapped) { /* * if we're in a workqueue, the request is orphaned, so * don't copy into a random user address space, just free * and return -EINTR so user space doesn't expect any data. */ if (!current->mm) ret = -EINTR; else if (bio_data_dir(bio) == READ) ret = bio_copy_to_iter(bio, bmd->iter); if (bmd->is_our_pages) bio_free_pages(bio); } kfree(bmd); return ret; } static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, struct iov_iter *iter, gfp_t gfp_mask) { struct bio_map_data *bmd; struct page *page; struct bio *bio; int i = 0, ret; int nr_pages; unsigned int len = iter->count; unsigned int offset = map_data ? offset_in_page(map_data->offset) : 0; bmd = bio_alloc_map_data(iter, gfp_mask); if (!bmd) return -ENOMEM; /* * We need to do a deep copy of the iov_iter including the iovecs. * The caller provided iov might point to an on-stack or otherwise * shortlived one. */ bmd->is_our_pages = !map_data; bmd->is_null_mapped = (map_data && map_data->null_mapped); nr_pages = bio_max_segs(DIV_ROUND_UP(offset + len, PAGE_SIZE)); ret = -ENOMEM; bio = blk_rq_map_bio_alloc(rq, nr_pages, gfp_mask); if (!bio) goto out_bmd; if (map_data) { nr_pages = 1U << map_data->page_order; i = map_data->offset / PAGE_SIZE; } while (len) { unsigned int bytes = PAGE_SIZE; bytes -= offset; if (bytes > len) bytes = len; if (map_data) { if (i == map_data->nr_entries * nr_pages) { ret = -ENOMEM; goto cleanup; } page = map_data->pages[i / nr_pages]; page += (i % nr_pages); i++; } else { page = alloc_page(GFP_NOIO | gfp_mask); if (!page) { ret = -ENOMEM; goto cleanup; } } if (bio_add_page(bio, page, bytes, offset) < bytes) { if (!map_data) __free_page(page); break; } len -= bytes; offset = 0; } if (map_data) map_data->offset += bio->bi_iter.bi_size; /* * success */ if (iov_iter_rw(iter) == WRITE && (!map_data || !map_data->null_mapped)) { ret = bio_copy_from_iter(bio, iter); if (ret) goto cleanup; } else if (map_data && map_data->from_user) { struct iov_iter iter2 = *iter; /* This is the copy-in part of SG_DXFER_TO_FROM_DEV. */ iter2.data_source = ITER_SOURCE; ret = bio_copy_from_iter(bio, &iter2); if (ret) goto cleanup; } else { if (bmd->is_our_pages) zero_fill_bio(bio); iov_iter_advance(iter, bio->bi_iter.bi_size); } bio->bi_private = bmd; ret = blk_rq_append_bio(rq, bio); if (ret) goto cleanup; return 0; cleanup: if (!map_data) bio_free_pages(bio); blk_mq_map_bio_put(bio); out_bmd: kfree(bmd); return ret; } static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, gfp_t gfp_mask) { unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS); struct bio *bio; int ret; if (!iov_iter_count(iter)) return -EINVAL; bio = blk_rq_map_bio_alloc(rq, nr_vecs, gfp_mask); if (!bio) return -ENOMEM; /* * No alignment requirements on our part to support arbitrary * passthrough commands. */ ret = bio_iov_iter_get_pages(bio, iter, 0); if (ret) goto out_put; ret = blk_rq_append_bio(rq, bio); if (ret) goto out_release; return 0; out_release: bio_release_pages(bio, false); out_put: blk_mq_map_bio_put(bio); return ret; } static void bio_invalidate_vmalloc_pages(struct bio *bio) { #ifdef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE if (bio->bi_private && !op_is_write(bio_op(bio))) { unsigned long i, len = 0; for (i = 0; i < bio->bi_vcnt; i++) len += bio->bi_io_vec[i].bv_len; invalidate_kernel_vmap_range(bio->bi_private, len); } #endif } static void bio_map_kern_endio(struct bio *bio) { bio_invalidate_vmalloc_pages(bio); blk_mq_map_bio_put(bio); } static struct bio *bio_map_kern(struct request *rq, void *data, unsigned int len, gfp_t gfp_mask) { unsigned int nr_vecs = bio_add_max_vecs(data, len); struct bio *bio; bio = blk_rq_map_bio_alloc(rq, nr_vecs, gfp_mask); if (!bio) return ERR_PTR(-ENOMEM); if (is_vmalloc_addr(data)) { bio->bi_private = data; if (!bio_add_vmalloc(bio, data, len)) { blk_mq_map_bio_put(bio); return ERR_PTR(-EINVAL); } } else { bio_add_virt_nofail(bio, data, len); } bio->bi_end_io = bio_map_kern_endio; return bio; } static void bio_copy_kern_endio(struct bio *bio) { bio_free_pages(bio); blk_mq_map_bio_put(bio); } static void bio_copy_kern_endio_read(struct bio *bio) { char *p = bio->bi_private; struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { memcpy_from_bvec(p, bvec); p += bvec->bv_len; } bio_copy_kern_endio(bio); } /** * bio_copy_kern - copy kernel address into bio * @rq: request to fill * @data: pointer to buffer to copy * @len: length in bytes * @op: bio/request operation * @gfp_mask: allocation flags for bio and page allocation * * copy the kernel address into a bio suitable for io to a block * device. Returns an error pointer in case of error. */ static struct bio *bio_copy_kern(struct request *rq, void *data, unsigned int len, gfp_t gfp_mask) { enum req_op op = req_op(rq); unsigned long kaddr = (unsigned long)data; unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; unsigned long start = kaddr >> PAGE_SHIFT; struct bio *bio; void *p = data; int nr_pages = 0; /* * Overflow, abort */ if (end < start) return ERR_PTR(-EINVAL); nr_pages = end - start; bio = blk_rq_map_bio_alloc(rq, nr_pages, gfp_mask); if (!bio) return ERR_PTR(-ENOMEM); while (len) { struct page *page; unsigned int bytes = PAGE_SIZE; if (bytes > len) bytes = len; page = alloc_page(GFP_NOIO | __GFP_ZERO | gfp_mask); if (!page) goto cleanup; if (op_is_write(op)) memcpy(page_address(page), p, bytes); __bio_add_page(bio, page, bytes, 0); len -= bytes; p += bytes; } if (op_is_write(op)) { bio->bi_end_io = bio_copy_kern_endio; } else { bio->bi_end_io = bio_copy_kern_endio_read; bio->bi_private = data; } return bio; cleanup: bio_free_pages(bio); blk_mq_map_bio_put(bio); return ERR_PTR(-ENOMEM); } /* * Append a bio to a passthrough request. Only works if the bio can be merged * into the request based on the driver constraints. */ int blk_rq_append_bio(struct request *rq, struct bio *bio) { const struct queue_limits *lim = &rq->q->limits; unsigned int max_bytes = lim->max_hw_sectors << SECTOR_SHIFT; unsigned int nr_segs = 0; int ret; /* check that the data layout matches the hardware restrictions */ ret = bio_split_io_at(bio, lim, &nr_segs, max_bytes, 0); if (ret) { /* if we would have to split the bio, copy instead */ if (ret > 0) ret = -EREMOTEIO; return ret; } if (rq->bio) { if (!ll_back_merge_fn(rq, bio, nr_segs)) return -EINVAL; rq->phys_gap_bit = bio_seg_gap(rq->q, rq->biotail, bio, rq->phys_gap_bit); rq->biotail->bi_next = bio; rq->biotail = bio; rq->__data_len += bio->bi_iter.bi_size; bio_crypt_free_ctx(bio); return 0; } rq->nr_phys_segments = nr_segs; rq->bio = rq->biotail = bio; rq->__data_len = bio->bi_iter.bi_size; rq->phys_gap_bit = bio->bi_bvec_gap_bit; return 0; } EXPORT_SYMBOL(blk_rq_append_bio); /* Prepare bio for passthrough IO given ITER_BVEC iter */ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter) { unsigned int max_bytes = rq->q->limits.max_hw_sectors << SECTOR_SHIFT; struct bio *bio; int ret; if (!iov_iter_count(iter) || iov_iter_count(iter) > max_bytes) return -EINVAL; /* reuse the bvecs from the iterator instead of allocating new ones */ bio = blk_rq_map_bio_alloc(rq, 0, GFP_KERNEL); if (!bio) return -ENOMEM; bio_iov_bvec_set(bio, iter); ret = blk_rq_append_bio(rq, bio); if (ret) blk_mq_map_bio_put(bio); return ret; } /** * blk_rq_map_user_iov - map user data to a request, for passthrough requests * @q: request queue where request should be inserted * @rq: request to map data to * @map_data: pointer to the rq_map_data holding pages (if necessary) * @iter: iovec iterator * @gfp_mask: memory allocation flags * * Description: * Data will be mapped directly for zero copy I/O, if possible. Otherwise * a kernel bounce buffer is used. * * A matching blk_rq_unmap_user() must be issued at the end of I/O, while * still in process context. */ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, struct rq_map_data *map_data, const struct iov_iter *iter, gfp_t gfp_mask) { bool copy = false, map_bvec = false; unsigned long align = blk_lim_dma_alignment_and_pad(&q->limits); struct bio *bio = NULL; struct iov_iter i; int ret = -EINVAL; if (map_data) copy = true; else if (iov_iter_alignment(iter) & align) copy = true; else if (iov_iter_is_bvec(iter)) map_bvec = true; else if (!user_backed_iter(iter)) copy = true; else if (queue_virt_boundary(q)) copy = queue_virt_boundary(q) & iov_iter_gap_alignment(iter); if (map_bvec) { ret = blk_rq_map_user_bvec(rq, iter); if (!ret) return 0; if (ret != -EREMOTEIO) goto fail; /* fall back to copying the data on limits mismatches */ copy = true; } i = *iter; do { if (copy) ret = bio_copy_user_iov(rq, map_data, &i, gfp_mask); else ret = bio_map_user_iov(rq, &i, gfp_mask); if (ret) { if (ret == -EREMOTEIO) ret = -EINVAL; goto unmap_rq; } if (!bio) bio = rq->bio; } while (iov_iter_count(&i)); return 0; unmap_rq: blk_rq_unmap_user(bio); fail: rq->bio = NULL; return ret; } EXPORT_SYMBOL(blk_rq_map_user_iov); int blk_rq_map_user(struct request_queue *q, struct request *rq, struct rq_map_data *map_data, void __user *ubuf, unsigned long len, gfp_t gfp_mask) { struct iov_iter i; int ret = import_ubuf(rq_data_dir(rq), ubuf, len, &i); if (unlikely(ret < 0)) return ret; return blk_rq_map_user_iov(q, rq, map_data, &i, gfp_mask); } EXPORT_SYMBOL(blk_rq_map_user); int blk_rq_map_user_io(struct request *req, struct rq_map_data *map_data, void __user *ubuf, unsigned long buf_len, gfp_t gfp_mask, bool vec, int iov_count, bool check_iter_count, int rw) { int ret = 0; if (vec) { struct iovec fast_iov[UIO_FASTIOV]; struct iovec *iov = fast_iov; struct iov_iter iter; ret = import_iovec(rw, ubuf, iov_count ? iov_count : buf_len, UIO_FASTIOV, &iov, &iter); if (ret < 0) return ret; if (iov_count) { /* SG_IO howto says that the shorter of the two wins */ iov_iter_truncate(&iter, buf_len); if (check_iter_count && !iov_iter_count(&iter)) { kfree(iov); return -EINVAL; } } ret = blk_rq_map_user_iov(req->q, req, map_data, &iter, gfp_mask); kfree(iov); } else if (buf_len) { ret = blk_rq_map_user(req->q, req, map_data, ubuf, buf_len, gfp_mask); } return ret; } EXPORT_SYMBOL(blk_rq_map_user_io); /** * blk_rq_unmap_user - unmap a request with user data * @bio: start of bio list * * Description: * Unmap a rq previously mapped by blk_rq_map_user(). The caller must * supply the original rq->bio from the blk_rq_map_user() return, since * the I/O completion may have changed rq->bio. */ int blk_rq_unmap_user(struct bio *bio) { struct bio *next_bio; int ret = 0, ret2; while (bio) { if (bio->bi_private) { ret2 = bio_uncopy_user(bio); if (ret2 && !ret) ret = ret2; } else { bio_release_pages(bio, bio_data_dir(bio) == READ); } if (bio_integrity(bio)) bio_integrity_unmap_user(bio); next_bio = bio; bio = bio->bi_next; blk_mq_map_bio_put(next_bio); } return ret; } EXPORT_SYMBOL(blk_rq_unmap_user); /** * blk_rq_map_kern - map kernel data to a request, for passthrough requests * @rq: request to fill * @kbuf: the kernel buffer * @len: length of user data * @gfp_mask: memory allocation flags * * Description: * Data will be mapped directly if possible. Otherwise a bounce * buffer is used. Can be called multiple times to append multiple * buffers. */ int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, gfp_t gfp_mask) { unsigned long addr = (unsigned long) kbuf; bool do_copy; struct bio *bio; int ret; if (len > (queue_max_hw_sectors(rq->q) << SECTOR_SHIFT)) return -EINVAL; if (!len || !kbuf) return -EINVAL; do_copy = !blk_rq_aligned(rq->q, addr, len) || object_is_on_stack(kbuf); if (do_copy) bio = bio_copy_kern(rq, kbuf, len, gfp_mask); else bio = bio_map_kern(rq, kbuf, len, gfp_mask); if (IS_ERR(bio)) return PTR_ERR(bio); ret = blk_rq_append_bio(rq, bio); if (unlikely(ret)) { if (do_copy) bio_free_pages(bio); blk_mq_map_bio_put(bio); } return ret; } EXPORT_SYMBOL(blk_rq_map_kern); |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/virtio.h> #include <linux/virtio_anchor.h> bool virtio_require_restricted_mem_acc(struct virtio_device *dev) { return true; } EXPORT_SYMBOL_GPL(virtio_require_restricted_mem_acc); static bool virtio_no_restricted_mem_acc(struct virtio_device *dev) { return false; } bool (*virtio_check_mem_acc_cb)(struct virtio_device *dev) = virtio_no_restricted_mem_acc; EXPORT_SYMBOL_GPL(virtio_check_mem_acc_cb); |
| 4 101 450 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __SHMEM_FS_H #define __SHMEM_FS_H #include <linux/file.h> #include <linux/swap.h> #include <linux/mempolicy.h> #include <linux/pagemap.h> #include <linux/percpu_counter.h> #include <linux/xattr.h> #include <linux/fs_parser.h> #include <linux/userfaultfd_k.h> #include <linux/bits.h> struct swap_iocb; /* inode in-kernel data */ #ifdef CONFIG_TMPFS_QUOTA #define SHMEM_MAXQUOTAS 2 #endif /* Suppress pre-accounting of the entire object size. */ #define SHMEM_F_NORESERVE BIT(0) /* Disallow swapping. */ #define SHMEM_F_LOCKED BIT(1) /* * Disallow growing, shrinking, or hole punching in the inode. Combined with * folio pinning, makes sure the inode's mapping stays fixed. * * In some ways similar to F_SEAL_GROW | F_SEAL_SHRINK, but can be removed and * isn't directly visible to userspace. */ #define SHMEM_F_MAPPING_FROZEN BIT(2) struct shmem_inode_info { spinlock_t lock; unsigned int seals; /* shmem seals */ unsigned long flags; unsigned long alloced; /* data pages alloced to file */ unsigned long swapped; /* subtotal assigned to swap */ union { struct offset_ctx dir_offsets; /* stable directory offsets */ struct { struct list_head shrinklist; /* shrinkable hpage inodes */ struct list_head swaplist; /* chain of maybes on swap */ }; }; struct timespec64 i_crtime; /* file creation time */ struct shared_policy policy; /* NUMA memory alloc policy */ struct list_head xattrs; /* list of xattrs */ pgoff_t fallocend; /* highest fallocate endindex */ unsigned int fsflags; /* for FS_IOC_[SG]ETFLAGS */ atomic_t stop_eviction; /* hold when working on inode */ #ifdef CONFIG_TMPFS_QUOTA struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif struct inode vfs_inode; }; #define SHMEM_FL_USER_VISIBLE (FS_FL_USER_VISIBLE | FS_CASEFOLD_FL) #define SHMEM_FL_USER_MODIFIABLE \ (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) #define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) struct shmem_quota_limits { qsize_t usrquota_bhardlimit; /* Default user quota block hard limit */ qsize_t usrquota_ihardlimit; /* Default user quota inode hard limit */ qsize_t grpquota_bhardlimit; /* Default group quota block hard limit */ qsize_t grpquota_ihardlimit; /* Default group quota inode hard limit */ }; struct shmem_sb_info { unsigned long max_blocks; /* How many blocks are allowed */ struct percpu_counter used_blocks; /* How many are allocated */ unsigned long max_inodes; /* How many inodes are allowed */ unsigned long free_ispace; /* How much ispace left for allocation */ raw_spinlock_t stat_lock; /* Serialize shmem_sb_info changes */ umode_t mode; /* Mount mode for root directory */ unsigned char huge; /* Whether to try for hugepages */ kuid_t uid; /* Mount uid for root directory */ kgid_t gid; /* Mount gid for root directory */ bool full_inums; /* If i_ino should be uint or ino_t */ bool noswap; /* ignores VM reclaim / swap requests */ ino_t next_ino; /* The next per-sb inode number to use */ ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */ struct mempolicy *mpol; /* default memory policy for mappings */ spinlock_t shrinklist_lock; /* Protects shrinklist */ struct list_head shrinklist; /* List of shinkable inodes */ unsigned long shrinklist_len; /* Length of shrinklist */ struct shmem_quota_limits qlimits; /* Default quota limits */ struct simple_xattr_cache xa_cache; }; static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) { return container_of(inode, struct shmem_inode_info, vfs_inode); } /* * Functions in mm/shmem.c called directly from elsewhere: */ extern const struct fs_parameter_spec shmem_fs_parameters[]; extern void shmem_init(void); extern int shmem_init_fs_context(struct fs_context *fc); struct file *shmem_file_setup(const char *name, loff_t size, vma_flags_t flags); struct file *shmem_kernel_file_setup(const char *name, loff_t size, vma_flags_t vma_flags); extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt, const char *name, loff_t size, vma_flags_t flags); int shmem_zero_setup(struct vm_area_struct *vma); int shmem_zero_setup_desc(struct vm_area_desc *desc); extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct ucounts *ucounts); #ifdef CONFIG_SHMEM bool shmem_mapping(const struct address_space *mapping); #else static inline bool shmem_mapping(const struct address_space *mapping) { return false; } #endif /* CONFIG_SHMEM */ void shmem_unlock_mapping(struct address_space *mapping); struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); int shmem_writeout(struct folio *folio, struct swap_iocb **plug, struct list_head *folio_list); void shmem_truncate_range(struct inode *inode, loff_t start, uoff_t end); int shmem_unuse(unsigned int type); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SHMEM) unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, loff_t write_end, bool shmem_huge_force); bool shmem_hpage_pmd_enabled(void); #else static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, loff_t write_end, bool shmem_huge_force) { return 0; } static inline bool shmem_hpage_pmd_enabled(void) { return false; } #endif #ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); extern void shmem_uncharge(struct inode *inode, long pages); #else static inline unsigned long shmem_swap_usage(struct vm_area_struct *vma) { return 0; } static inline void shmem_uncharge(struct inode *inode, long pages) { } #endif extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); /* Flag allocation requirements to shmem_get_folio */ enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_NOALLOC, /* similar, but fail on hole or use fallocated page */ SGP_CACHE, /* don't exceed i_size, may allocate page */ SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */ SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; int shmem_get_folio(struct inode *inode, pgoff_t index, loff_t write_end, struct folio **foliop, enum sgp_type sgp); struct folio *shmem_read_folio_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp); static inline struct folio *shmem_read_folio(struct address_space *mapping, pgoff_t index) { return shmem_read_folio_gfp(mapping, index, mapping_gfp_mask(mapping)); } static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) { return shmem_read_mapping_page_gfp(mapping, index, mapping_gfp_mask(mapping)); } static inline bool shmem_file(struct file *file) { if (!IS_ENABLED(CONFIG_SHMEM)) return false; if (!file || !file->f_mapping) return false; return shmem_mapping(file->f_mapping); } /* Must be called with inode lock taken exclusive. */ static inline void shmem_freeze(struct inode *inode, bool freeze) { if (freeze) SHMEM_I(inode)->flags |= SHMEM_F_MAPPING_FROZEN; else SHMEM_I(inode)->flags &= ~SHMEM_F_MAPPING_FROZEN; } /* * If fallocate(FALLOC_FL_KEEP_SIZE) has been used, there may be pages * beyond i_size's notion of EOF, which fallocate has committed to reserving: * which split_huge_page() must therefore not delete. This use of a single * "fallocend" per inode errs on the side of not deleting a reservation when * in doubt: there are plenty of cases when it preserves unreserved pages. */ static inline pgoff_t shmem_fallocend(struct inode *inode, pgoff_t eof) { return max(eof, SHMEM_I(inode)->fallocend); } extern bool shmem_charge(struct inode *inode, long pages); /* * Used space is stored as unsigned 64-bit value in bytes but * quota core supports only signed 64-bit values so use that * as a limit */ #define SHMEM_QUOTA_MAX_SPC_LIMIT 0x7fffffffffffffffLL /* 2^63-1 */ #define SHMEM_QUOTA_MAX_INO_LIMIT 0x7fffffffffffffffLL #ifdef CONFIG_TMPFS_QUOTA extern const struct dquot_operations shmem_quota_operations; extern struct quota_format_type shmem_quota_format; #endif /* CONFIG_TMPFS_QUOTA */ #endif |
| 154 3 3 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 | // SPDX-License-Identifier: GPL-2.0+ /* * linux/net/sunrpc/gss_rpc_upcall.c * * Copyright (C) 2012 Simo Sorce <simo@redhat.com> */ #include <linux/types.h> #include <linux/un.h> #include <linux/sunrpc/svcauth.h> #include "gss_rpc_upcall.h" #define GSSPROXY_SOCK_PATHNAME "/var/run/gssproxy.sock" #define GSSPROXY_PROGRAM (400112u) #define GSSPROXY_VERS_1 (1u) /* * Encoding/Decoding functions */ enum { GSSX_NULL = 0, /* Unused */ GSSX_INDICATE_MECHS = 1, GSSX_GET_CALL_CONTEXT = 2, GSSX_IMPORT_AND_CANON_NAME = 3, GSSX_EXPORT_CRED = 4, GSSX_IMPORT_CRED = 5, GSSX_ACQUIRE_CRED = 6, GSSX_STORE_CRED = 7, GSSX_INIT_SEC_CONTEXT = 8, GSSX_ACCEPT_SEC_CONTEXT = 9, GSSX_RELEASE_HANDLE = 10, GSSX_GET_MIC = 11, GSSX_VERIFY = 12, GSSX_WRAP = 13, GSSX_UNWRAP = 14, GSSX_WRAP_SIZE_LIMIT = 15, }; #define PROC(proc, name) \ [GSSX_##proc] = { \ .p_proc = GSSX_##proc, \ .p_encode = gssx_enc_##name, \ .p_decode = gssx_dec_##name, \ .p_arglen = GSSX_ARG_##name##_sz, \ .p_replen = GSSX_RES_##name##_sz, \ .p_statidx = GSSX_##proc, \ .p_name = #proc, \ } static const struct rpc_procinfo gssp_procedures[] = { PROC(INDICATE_MECHS, indicate_mechs), PROC(GET_CALL_CONTEXT, get_call_context), PROC(IMPORT_AND_CANON_NAME, import_and_canon_name), PROC(EXPORT_CRED, export_cred), PROC(IMPORT_CRED, import_cred), PROC(ACQUIRE_CRED, acquire_cred), PROC(STORE_CRED, store_cred), PROC(INIT_SEC_CONTEXT, init_sec_context), PROC(ACCEPT_SEC_CONTEXT, accept_sec_context), PROC(RELEASE_HANDLE, release_handle), PROC(GET_MIC, get_mic), PROC(VERIFY, verify), PROC(WRAP, wrap), PROC(UNWRAP, unwrap), PROC(WRAP_SIZE_LIMIT, wrap_size_limit), }; /* * Common transport functions */ static const struct rpc_program gssp_program; static int gssp_rpc_create(struct net *net, struct rpc_clnt **_clnt) { static const struct sockaddr_un gssp_localaddr = { .sun_family = AF_LOCAL, .sun_path = GSSPROXY_SOCK_PATHNAME, }; struct rpc_create_args args = { .net = net, .protocol = XPRT_TRANSPORT_LOCAL, .address = (struct sockaddr *)&gssp_localaddr, .addrsize = sizeof(gssp_localaddr), .servername = "localhost", .program = &gssp_program, .version = GSSPROXY_VERS_1, .authflavor = RPC_AUTH_NULL, /* * Note we want connection to be done in the caller's * filesystem namespace. We therefore turn off the idle * timeout, which would result in reconnections being * done without the correct namespace: */ .flags = RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_CONNECTED | RPC_CLNT_CREATE_NO_IDLE_TIMEOUT }; struct rpc_clnt *clnt; int result = 0; clnt = rpc_create(&args); if (IS_ERR(clnt)) { dprintk("RPC: failed to create AF_LOCAL gssproxy " "client (errno %ld).\n", PTR_ERR(clnt)); result = PTR_ERR(clnt); *_clnt = NULL; goto out; } dprintk("RPC: created new gssp local client (gssp_local_clnt: " "%p)\n", clnt); *_clnt = clnt; out: return result; } void init_gssp_clnt(struct sunrpc_net *sn) { mutex_init(&sn->gssp_lock); sn->gssp_clnt = NULL; } int set_gssp_clnt(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_clnt *clnt; int ret; mutex_lock(&sn->gssp_lock); ret = gssp_rpc_create(net, &clnt); if (!ret) { if (sn->gssp_clnt) rpc_shutdown_client(sn->gssp_clnt); sn->gssp_clnt = clnt; } mutex_unlock(&sn->gssp_lock); return ret; } void clear_gssp_clnt(struct sunrpc_net *sn) { mutex_lock(&sn->gssp_lock); if (sn->gssp_clnt) { rpc_shutdown_client(sn->gssp_clnt); sn->gssp_clnt = NULL; } mutex_unlock(&sn->gssp_lock); } static struct rpc_clnt *get_gssp_clnt(struct sunrpc_net *sn) { struct rpc_clnt *clnt; mutex_lock(&sn->gssp_lock); clnt = sn->gssp_clnt; if (clnt) refcount_inc(&clnt->cl_count); mutex_unlock(&sn->gssp_lock); return clnt; } static int gssp_call(struct net *net, struct rpc_message *msg) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_clnt *clnt; int status; clnt = get_gssp_clnt(sn); if (!clnt) return -EIO; status = rpc_call_sync(clnt, msg, 0); if (status < 0) { dprintk("gssp: rpc_call returned error %d\n", -status); switch (status) { case -EPROTONOSUPPORT: status = -EINVAL; break; case -ECONNREFUSED: case -ETIMEDOUT: case -ENOTCONN: status = -EAGAIN; break; case -ERESTARTSYS: if (signalled ()) status = -EINTR; break; default: break; } } rpc_release_client(clnt); return status; } static void gssp_free_receive_pages(struct gssx_arg_accept_sec_context *arg) { unsigned int i; for (i = 0; i < arg->npages && arg->pages[i]; i++) __free_page(arg->pages[i]); kfree(arg->pages); } static int gssp_alloc_receive_pages(struct gssx_arg_accept_sec_context *arg) { unsigned int i; arg->npages = DIV_ROUND_UP(NGROUPS_MAX * 4, PAGE_SIZE); arg->pages = kzalloc_objs(struct page *, arg->npages); if (!arg->pages) return -ENOMEM; for (i = 0; i < arg->npages; i++) { arg->pages[i] = alloc_page(GFP_KERNEL); if (!arg->pages[i]) { gssp_free_receive_pages(arg); return -ENOMEM; } } return 0; } static char *gssp_stringify(struct xdr_netobj *netobj) { return kmemdup_nul(netobj->data, netobj->len, GFP_KERNEL); } static void gssp_hostbased_service(char **principal) { char *c; if (!*principal) return; /* terminate and remove realm part */ c = strchr(*principal, '@'); if (c) { *c = '\0'; /* change service-hostname delimiter */ c = strchr(*principal, '/'); if (c) *c = '@'; } if (!c) { /* not a service principal */ kfree(*principal); *principal = NULL; } } /* * Public functions */ /* numbers somewhat arbitrary but large enough for current needs */ #define GSSX_MAX_OUT_HANDLE 128 #define GSSX_MAX_SRC_PRINC 256 #define GSSX_KMEMBUF (GSSX_max_output_handle_sz + \ GSSX_max_oid_sz + \ GSSX_max_princ_sz + \ sizeof(struct svc_cred)) int gssp_accept_sec_context_upcall(struct net *net, struct gssp_upcall_data *data) { struct gssx_ctx ctxh = { .state = data->in_handle }; struct gssx_arg_accept_sec_context arg = { .input_token = data->in_token, }; struct gssx_ctx rctxh = { /* * pass in the max length we expect for each of these * buffers but let the xdr code kmalloc them: */ .exported_context_token.len = GSSX_max_output_handle_sz, .mech.len = GSS_OID_MAX_LEN, .targ_name.display_name.len = GSSX_max_princ_sz, .src_name.display_name.len = GSSX_max_princ_sz }; struct gssx_res_accept_sec_context res = { .context_handle = &rctxh, .output_token = &data->out_token }; struct rpc_message msg = { .rpc_proc = &gssp_procedures[GSSX_ACCEPT_SEC_CONTEXT], .rpc_argp = &arg, .rpc_resp = &res, .rpc_cred = NULL, /* FIXME ? */ }; struct xdr_netobj client_name = { 0 , NULL }; struct xdr_netobj target_name = { 0, NULL }; int ret; if (data->in_handle.len != 0) arg.context_handle = &ctxh; res.output_token->len = GSSX_max_output_token_sz; ret = gssp_alloc_receive_pages(&arg); if (ret) return ret; ret = gssp_call(net, &msg); gssp_free_receive_pages(&arg); /* we need to fetch all data even in case of error so * that we can free special strctures is they have been allocated */ data->major_status = res.status.major_status; data->minor_status = res.status.minor_status; if (res.context_handle) { data->out_handle = rctxh.exported_context_token; data->mech_oid.len = rctxh.mech.len; if (rctxh.mech.data) { memcpy(data->mech_oid.data, rctxh.mech.data, data->mech_oid.len); kfree(rctxh.mech.data); } client_name = rctxh.src_name.display_name; target_name = rctxh.targ_name.display_name; } if (res.options.count == 1) { gssx_buffer *value = &res.options.data[0].value; /* Currently we only decode CREDS_VALUE, if we add * anything else we'll have to loop and match on the * option name */ if (value->len == 1) { /* steal group info from struct svc_cred */ data->creds = *(struct svc_cred *)value->data; data->found_creds = 1; } /* whether we use it or not, free data */ kfree(value->data); } if (res.options.count != 0) { kfree(res.options.data); } /* convert to GSS_NT_HOSTBASED_SERVICE form and set into creds */ if (data->found_creds) { if (client_name.data) { data->creds.cr_raw_principal = gssp_stringify(&client_name); data->creds.cr_principal = gssp_stringify(&client_name); gssp_hostbased_service(&data->creds.cr_principal); } if (target_name.data) { data->creds.cr_targ_princ = gssp_stringify(&target_name); gssp_hostbased_service(&data->creds.cr_targ_princ); } } kfree(client_name.data); kfree(target_name.data); return ret; } void gssp_free_upcall_data(struct gssp_upcall_data *data) { kfree(data->in_handle.data); kfree(data->out_handle.data); kfree(data->out_token.data); free_svc_cred(&data->creds); } /* * Initialization stuff */ static unsigned int gssp_version1_counts[ARRAY_SIZE(gssp_procedures)]; static const struct rpc_version gssp_version1 = { .number = GSSPROXY_VERS_1, .nrprocs = ARRAY_SIZE(gssp_procedures), .procs = gssp_procedures, .counts = gssp_version1_counts, }; static const struct rpc_version *gssp_version[] = { NULL, &gssp_version1, }; static struct rpc_stat gssp_stats; static const struct rpc_program gssp_program = { .name = "gssproxy", .number = GSSPROXY_PROGRAM, .nrvers = ARRAY_SIZE(gssp_version), .version = gssp_version, .stats = &gssp_stats, }; |
| 8 13 10 6 5 6 4 20 24 2 1 1 20 8 3 5 5 2 2 3 5 5 26 4 26 28 6 22 4 1 22 25 25 13 1 12 1 2 3 8 5 1 3 1 2 5 6 6 1 1 19 1 3 1 2 16 15 1 3 1 1 1 15 9 6 6 2 3 3 1 2 11 12 10 6 5 11 2 2 11 10 1 10 8 7 7 35 15 27 28 12 30 1 30 2 7 8 10 6 3 1 1 1 1 15 1 14 1 1 1 1 1 1 1 2 1 1 1 1 12 1 1 2 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 | // SPDX-License-Identifier: GPL-2.0 /* * af_llc.c - LLC User Interface SAPs * Description: * Functions in this module are implementation of socket based llc * communications for the Linux operating system. Support of llc class * one and class two is provided via SOCK_DGRAM and SOCK_STREAM * respectively. * * An llc2 connection is (mac + sap), only one llc2 sap connection * is allowed per mac. Though one sap may have multiple mac + sap * connections. * * Copyright (c) 2001 by Jay Schulist <jschlst@samba.org> * 2002-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> */ #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/uio.h> #include <net/llc.h> #include <net/llc_sap.h> #include <net/llc_pdu.h> #include <net/llc_conn.h> #include <net/tcp_states.h> /* remember: uninitialized global data is zeroed because its in .bss */ static u16 llc_ui_sap_last_autoport = LLC_SAP_DYN_START; static u16 llc_ui_sap_link_no_max[256]; static struct sockaddr_llc llc_ui_addrnull; static const struct proto_ops llc_ui_ops; static bool llc_ui_wait_for_conn(struct sock *sk, long timeout); static int llc_ui_wait_for_disc(struct sock *sk, long timeout); static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout); #if 0 #define dprintk(args...) printk(KERN_DEBUG args) #else #define dprintk(args...) do {} while (0) #endif /* Maybe we'll add some more in the future. */ #define LLC_CMSG_PKTINFO 1 /** * llc_ui_next_link_no - return the next unused link number for a sap * @sap: Address of sap to get link number from. * * Return the next unused link number for a given sap. */ static inline u16 llc_ui_next_link_no(int sap) { return llc_ui_sap_link_no_max[sap]++; } /** * llc_proto_type - return eth protocol for ARP header type * @arphrd: ARP header type. * * Given an ARP header type return the corresponding ethernet protocol. */ static inline __be16 llc_proto_type(u16 arphrd) { return htons(ETH_P_802_2); } /** * llc_ui_addr_null - determines if a address structure is null * @addr: Address to test if null. */ static inline u8 llc_ui_addr_null(struct sockaddr_llc *addr) { return !memcmp(addr, &llc_ui_addrnull, sizeof(*addr)); } /** * llc_ui_header_len - return length of llc header based on operation * @sk: Socket which contains a valid llc socket type. * @addr: Complete sockaddr_llc structure received from the user. * * Provide the length of the llc header depending on what kind of * operation the user would like to perform and the type of socket. * Returns the correct llc header length. */ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) { u8 rc = LLC_PDU_LEN_U; if (addr->sllc_test) rc = LLC_PDU_LEN_U; else if (addr->sllc_xid) /* We need to expand header to sizeof(struct llc_xid_info) * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header * as XID PDU. In llc_ui_sendmsg() we reserved header size and then * filled all other space with user data. If we won't reserve this * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data */ rc = LLC_PDU_LEN_U_XID; else if (sk->sk_type == SOCK_STREAM) rc = LLC_PDU_LEN_I; return rc; } /** * llc_ui_send_data - send data via reliable llc2 connection * @sk: Connection the socket is using. * @skb: Data the user wishes to send. * @noblock: can we block waiting for data? * * Send data via reliable llc2 connection. * Returns 0 upon success, non-zero if action did not succeed. * * This function always consumes a reference to the skb. */ static int llc_ui_send_data(struct sock* sk, struct sk_buff *skb, int noblock) { struct llc_sock* llc = llc_sk(sk); if (unlikely(llc_data_accept_state(llc->state) || llc->remote_busy_flag || llc->p_flag)) { long timeout = sock_sndtimeo(sk, noblock); int rc; rc = llc_ui_wait_for_busy_core(sk, timeout); if (rc) { kfree_skb(skb); return rc; } } return llc_build_and_send_pkt(sk, skb); } static void llc_ui_sk_init(struct socket *sock, struct sock *sk) { sock_graft(sk, sock); sk->sk_type = sock->type; sock->ops = &llc_ui_ops; } static struct proto llc_proto = { .name = "LLC", .owner = THIS_MODULE, .obj_size = sizeof(struct llc_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, }; /** * llc_ui_create - alloc and init a new llc_ui socket * @net: network namespace (must be default network) * @sock: Socket to initialize and attach allocated sk to. * @protocol: Unused. * @kern: on behalf of kernel or userspace * * Allocate and initialize a new llc_ui socket, validate the user wants a * socket type we have available. * Returns 0 upon success, negative upon failure. */ static int llc_ui_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; int rc = -ESOCKTNOSUPPORT; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; if (likely(sock->type == SOCK_DGRAM || sock->type == SOCK_STREAM)) { rc = -ENOMEM; sk = llc_sk_alloc(net, PF_LLC, GFP_KERNEL, &llc_proto, kern); if (sk) { rc = 0; llc_ui_sk_init(sock, sk); } } return rc; } /** * llc_ui_release - shutdown socket * @sock: Socket to release. * * Shutdown and deallocate an existing socket. */ static int llc_ui_release(struct socket *sock) { struct sock *sk = sock->sk; struct llc_sock *llc; if (unlikely(sk == NULL)) goto out; sock_hold(sk); lock_sock(sk); llc = llc_sk(sk); dprintk("%s: closing local(%02X) remote(%02X)\n", __func__, llc->laddr.lsap, llc->daddr.lsap); if (!llc_send_disc(sk)) llc_ui_wait_for_disc(sk, READ_ONCE(sk->sk_rcvtimeo)); if (!sock_flag(sk, SOCK_ZAPPED)) { struct llc_sap *sap = llc->sap; /* Hold this for release_sock(), so that llc_backlog_rcv() * could still use it. */ llc_sap_hold(sap); llc_sap_remove_socket(llc->sap, sk); release_sock(sk); llc_sap_put(sap); } else { release_sock(sk); } netdev_put(llc->dev, &llc->dev_tracker); sock_put(sk); sock_orphan(sk); sock->sk = NULL; llc_sk_free(sk); out: return 0; } /** * llc_ui_autoport - provide dynamically allocate SAP number * * Provide the caller with a dynamically allocated SAP number according * to the rules that are set in this function. Returns: 0, upon failure, * SAP number otherwise. */ static int llc_ui_autoport(void) { struct llc_sap *sap; int i, tries = 0; while (tries < LLC_SAP_DYN_TRIES) { for (i = llc_ui_sap_last_autoport; i < LLC_SAP_DYN_STOP; i += 2) { sap = llc_sap_find(i); if (!sap) { llc_ui_sap_last_autoport = i + 2; goto out; } llc_sap_put(sap); } llc_ui_sap_last_autoport = LLC_SAP_DYN_START; tries++; } i = 0; out: return i; } /** * llc_ui_autobind - automatically bind a socket to a sap * @sock: socket to bind * @addr: address to connect to * * Used by llc_ui_connect and llc_ui_sendmsg when the user hasn't * specifically used llc_ui_bind to bind to an specific address/sap * * Returns: 0 upon success, negative otherwise. */ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); struct net_device *dev = NULL; struct llc_sap *sap; int rc = -EINVAL; if (!sock_flag(sk, SOCK_ZAPPED)) goto out; if (!addr->sllc_arphrd) addr->sllc_arphrd = ARPHRD_ETHER; if (addr->sllc_arphrd != ARPHRD_ETHER) goto out; rc = -ENODEV; if (sk->sk_bound_dev_if) { dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); if (dev && addr->sllc_arphrd != dev->type) { dev_put(dev); dev = NULL; } } else dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd); if (!dev) goto out; rc = -EUSERS; llc->laddr.lsap = llc_ui_autoport(); if (!llc->laddr.lsap) goto out; rc = -EBUSY; /* some other network layer is using the sap */ sap = llc_sap_open(llc->laddr.lsap, NULL); if (!sap) goto out; /* Note: We do not expect errors from this point. */ llc->dev = dev; netdev_tracker_alloc(llc->dev, &llc->dev_tracker, GFP_KERNEL); dev = NULL; memcpy(llc->laddr.mac, llc->dev->dev_addr, IFHWADDRLEN); memcpy(&llc->addr, addr, sizeof(llc->addr)); /* assign new connection to its SAP */ llc_sap_add_socket(sap, sk); sock_reset_flag(sk, SOCK_ZAPPED); llc_sap_put(sap); rc = 0; out: dev_put(dev); return rc; } /** * llc_ui_bind - bind a socket to a specific address. * @sock: Socket to bind an address to. * @uaddr: Address the user wants the socket bound to. * @addrlen: Length of the uaddr structure. * * Bind a socket to a specific address. For llc a user is able to bind to * a specific sap only or mac + sap. * If the user desires to bind to a specific mac + sap, it is possible to * have multiple sap connections via multiple macs. * Bind and autobind for that matter must enforce the correct sap usage * otherwise all hell will break loose. * Returns: 0 upon success, negative otherwise. */ static int llc_ui_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addrlen) { struct sockaddr_llc *addr = (struct sockaddr_llc *)uaddr; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); struct net_device *dev = NULL; struct llc_sap *sap; int rc = -EINVAL; lock_sock(sk); if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; if (!addr->sllc_arphrd) addr->sllc_arphrd = ARPHRD_ETHER; if (unlikely(addr->sllc_family != AF_LLC || addr->sllc_arphrd != ARPHRD_ETHER)) goto out; dprintk("%s: binding %02X\n", __func__, addr->sllc_sap); rc = -ENODEV; rcu_read_lock(); if (sk->sk_bound_dev_if) { dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); if (dev) { if (is_zero_ether_addr(addr->sllc_mac)) memcpy(addr->sllc_mac, dev->dev_addr, IFHWADDRLEN); if (addr->sllc_arphrd != dev->type || !ether_addr_equal(addr->sllc_mac, dev->dev_addr)) { rc = -EINVAL; dev = NULL; } } } else { dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd, addr->sllc_mac); } dev_hold(dev); rcu_read_unlock(); if (!dev) goto out; if (!addr->sllc_sap) { rc = -EUSERS; addr->sllc_sap = llc_ui_autoport(); if (!addr->sllc_sap) goto out; } sap = llc_sap_find(addr->sllc_sap); if (!sap) { sap = llc_sap_open(addr->sllc_sap, NULL); rc = -EBUSY; /* some other network layer is using the sap */ if (!sap) goto out; } else { struct llc_addr laddr, daddr; struct sock *ask; memset(&laddr, 0, sizeof(laddr)); memset(&daddr, 0, sizeof(daddr)); /* * FIXME: check if the address is multicast, * only SOCK_DGRAM can do this. */ memcpy(laddr.mac, addr->sllc_mac, IFHWADDRLEN); laddr.lsap = addr->sllc_sap; rc = -EADDRINUSE; /* mac + sap clash. */ ask = llc_lookup_established(sap, &daddr, &laddr, &init_net); if (ask) { sock_put(ask); goto out_put; } } /* Note: We do not expect errors from this point. */ llc->dev = dev; netdev_tracker_alloc(llc->dev, &llc->dev_tracker, GFP_KERNEL); dev = NULL; llc->laddr.lsap = addr->sllc_sap; memcpy(llc->laddr.mac, addr->sllc_mac, IFHWADDRLEN); memcpy(&llc->addr, addr, sizeof(llc->addr)); /* assign new connection to its SAP */ llc_sap_add_socket(sap, sk); sock_reset_flag(sk, SOCK_ZAPPED); rc = 0; out_put: llc_sap_put(sap); out: dev_put(dev); release_sock(sk); return rc; } /** * llc_ui_shutdown - shutdown a connect llc2 socket. * @sock: Socket to shutdown. * @how: What part of the socket to shutdown. * * Shutdown a connected llc2 socket. Currently this function only supports * shutting down both sends and receives (2), we could probably make this * function such that a user can shutdown only half the connection but not * right now. * Returns: 0 upon success, negative otherwise. */ static int llc_ui_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int rc = -ENOTCONN; lock_sock(sk); if (unlikely(sk->sk_state != TCP_ESTABLISHED)) goto out; rc = -EINVAL; if (how != 2) goto out; rc = llc_send_disc(sk); if (!rc) rc = llc_ui_wait_for_disc(sk, READ_ONCE(sk->sk_rcvtimeo)); /* Wake up anyone sleeping in poll */ sk->sk_state_change(sk); out: release_sock(sk); return rc; } /** * llc_ui_connect - Connect to a remote llc2 mac + sap. * @sock: Socket which will be connected to the remote destination. * @uaddr: Remote and possibly the local address of the new connection. * @addrlen: Size of uaddr structure. * @flags: Operational flags specified by the user. * * Connect to a remote llc2 mac + sap. The caller must specify the * destination mac and address to connect to. If the user hasn't previously * called bind(2) with a smac the address of the first interface of the * specified arp type will be used. * This function will autobind if user did not previously call bind. * Returns: 0 upon success, negative otherwise. */ static int llc_ui_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addrlen, int flags) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); struct sockaddr_llc *addr = (struct sockaddr_llc *)uaddr; int rc = -EINVAL; lock_sock(sk); if (unlikely(addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; if (unlikely(addr->sllc_family != AF_LLC)) goto out; if (unlikely(sk->sk_type != SOCK_STREAM)) goto out; rc = -EALREADY; if (unlikely(sock->state == SS_CONNECTING)) goto out; /* bind connection to sap if user hasn't done it. */ if (sock_flag(sk, SOCK_ZAPPED)) { /* bind to sap with null dev, exclusive */ rc = llc_ui_autobind(sock, addr); if (rc) goto out; } llc->daddr.lsap = addr->sllc_sap; memcpy(llc->daddr.mac, addr->sllc_mac, IFHWADDRLEN); sock->state = SS_CONNECTING; sk->sk_state = TCP_SYN_SENT; llc->link = llc_ui_next_link_no(llc->sap->laddr.lsap); rc = llc_establish_connection(sk, llc->dev->dev_addr, addr->sllc_mac, addr->sllc_sap); if (rc) { dprintk("%s: llc_ui_send_conn failed :-(\n", __func__); sock->state = SS_UNCONNECTED; sk->sk_state = TCP_CLOSE; goto out; } if (sk->sk_state == TCP_SYN_SENT) { const long timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); if (!timeo || !llc_ui_wait_for_conn(sk, timeo)) { rc = -EINPROGRESS; goto out; } rc = sock_intr_errno(timeo); if (signal_pending(current)) goto out; } if (sk->sk_state == TCP_CLOSE) goto sock_error; sock->state = SS_CONNECTED; rc = 0; out: release_sock(sk); return rc; sock_error: rc = sock_error(sk) ? : -ECONNABORTED; sock->state = SS_UNCONNECTED; goto out; } /** * llc_ui_listen - allow a normal socket to accept incoming connections * @sock: Socket to allow incoming connections on. * @backlog: Number of connections to queue. * * Allow a normal socket to accept incoming connections. * Returns 0 upon success, negative otherwise. */ static int llc_ui_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; int rc = -EINVAL; lock_sock(sk); if (unlikely(sock->state != SS_UNCONNECTED)) goto out; rc = -EOPNOTSUPP; if (unlikely(sk->sk_type != SOCK_STREAM)) goto out; rc = -EAGAIN; if (sock_flag(sk, SOCK_ZAPPED)) goto out; rc = 0; if (!(unsigned int)backlog) /* BSDism */ backlog = 1; sk->sk_max_ack_backlog = backlog; if (sk->sk_state != TCP_LISTEN) { sk->sk_ack_backlog = 0; sk->sk_state = TCP_LISTEN; } sk->sk_socket->flags |= __SO_ACCEPTCON; out: release_sock(sk); return rc; } static int llc_ui_wait_for_disc(struct sock *sk, long timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int rc = 0; add_wait_queue(sk_sleep(sk), &wait); while (1) { if (sk_wait_event(sk, &timeout, READ_ONCE(sk->sk_state) == TCP_CLOSE, &wait)) break; rc = -ERESTARTSYS; if (signal_pending(current)) break; rc = -EAGAIN; if (!timeout) break; rc = 0; } remove_wait_queue(sk_sleep(sk), &wait); return rc; } static bool llc_ui_wait_for_conn(struct sock *sk, long timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(sk_sleep(sk), &wait); while (1) { if (sk_wait_event(sk, &timeout, READ_ONCE(sk->sk_state) != TCP_SYN_SENT, &wait)) break; if (signal_pending(current) || !timeout) break; } remove_wait_queue(sk_sleep(sk), &wait); return timeout; } static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct llc_sock *llc = llc_sk(sk); int rc; add_wait_queue(sk_sleep(sk), &wait); while (1) { rc = 0; if (sk_wait_event(sk, &timeout, (READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN) || (!llc_data_accept_state(llc->state) && !llc->remote_busy_flag && !llc->p_flag), &wait)) break; rc = -ERESTARTSYS; if (signal_pending(current)) break; rc = -EAGAIN; if (!timeout) break; } remove_wait_queue(sk_sleep(sk), &wait); return rc; } static int llc_wait_data(struct sock *sk, long timeo) { int rc; while (1) { /* * POSIX 1003.1g mandates this order. */ rc = sock_error(sk); if (rc) break; rc = 0; if (sk->sk_shutdown & RCV_SHUTDOWN) break; rc = -EAGAIN; if (!timeo) break; rc = sock_intr_errno(timeo); if (signal_pending(current)) break; rc = 0; if (sk_wait_data(sk, &timeo, NULL)) break; } return rc; } static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(skb->sk); if (llc->cmsg_flags & LLC_CMSG_PKTINFO) { struct llc_pktinfo info; memset(&info, 0, sizeof(info)); info.lpi_ifindex = llc_sk(skb->sk)->dev->ifindex; llc_pdu_decode_dsap(skb, &info.lpi_sap); llc_pdu_decode_da(skb, info.lpi_mac); put_cmsg(msg, SOL_LLC, LLC_OPT_PKTINFO, sizeof(info), &info); } } /** * llc_ui_accept - accept a new incoming connection. * @sock: Socket which connections arrive on. * @newsock: Socket to move incoming connection to. * @arg: User specified arguments * * Accept a new incoming connection. * Returns 0 upon success, negative otherwise. */ static int llc_ui_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { struct sock *sk = sock->sk, *newsk; struct llc_sock *llc, *newllc; struct sk_buff *skb; int rc = -EOPNOTSUPP; dprintk("%s: accepting on %02X\n", __func__, llc_sk(sk)->laddr.lsap); lock_sock(sk); if (unlikely(sk->sk_type != SOCK_STREAM)) goto out; rc = -EINVAL; if (unlikely(sock->state != SS_UNCONNECTED || sk->sk_state != TCP_LISTEN)) goto out; /* wait for a connection to arrive. */ if (skb_queue_empty(&sk->sk_receive_queue)) { rc = llc_wait_data(sk, READ_ONCE(sk->sk_rcvtimeo)); if (rc) goto out; } dprintk("%s: got a new connection on %02X\n", __func__, llc_sk(sk)->laddr.lsap); skb = skb_dequeue(&sk->sk_receive_queue); rc = -EINVAL; if (!skb->sk) goto frees; rc = 0; newsk = skb->sk; /* attach connection to a new socket. */ llc_ui_sk_init(newsock, newsk); sock_reset_flag(newsk, SOCK_ZAPPED); newsk->sk_state = TCP_ESTABLISHED; newsock->state = SS_CONNECTED; llc = llc_sk(sk); newllc = llc_sk(newsk); memcpy(&newllc->addr, &llc->addr, sizeof(newllc->addr)); newllc->link = llc_ui_next_link_no(newllc->laddr.lsap); /* put original socket back into a clean listen state. */ sk->sk_state = TCP_LISTEN; sk_acceptq_removed(sk); dprintk("%s: ok success on %02X, client on %02X\n", __func__, llc_sk(sk)->addr.sllc_sap, newllc->daddr.lsap); frees: kfree_skb(skb); out: release_sock(sk); return rc; } /** * llc_ui_recvmsg - copy received data to the socket user. * @sock: Socket to copy data from. * @msg: Various user space related information. * @len: Size of user buffer. * @flags: User specified flags. * * Copy received data to the socket user. * Returns non-negative upon success, negative otherwise. */ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { DECLARE_SOCKADDR(struct sockaddr_llc *, uaddr, msg->msg_name); const int nonblock = flags & MSG_DONTWAIT; struct sk_buff *skb = NULL; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); size_t copied = 0; u32 peek_seq = 0; u32 *seq, skb_len; unsigned long used; int target; /* Read at least this many bytes */ long timeo; lock_sock(sk); copied = -ENOTCONN; if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN)) goto out; timeo = sock_rcvtimeo(sk, nonblock); seq = &llc->copied_seq; if (flags & MSG_PEEK) { peek_seq = llc->copied_seq; seq = &peek_seq; } target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); copied = 0; do { u32 offset; /* * We need to check signals first, to get correct SIGURG * handling. FIXME: Need to check this doesn't impact 1003.1g * and move it down to the bottom of the loop */ if (signal_pending(current)) { if (copied) break; copied = timeo ? sock_intr_errno(timeo) : -EAGAIN; break; } /* Next get a buffer. */ skb = skb_peek(&sk->sk_receive_queue); if (skb) { offset = *seq; goto found_ok_skb; } /* Well, if we have backlog, try to process it now yet. */ if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { if (sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || !timeo || (flags & MSG_PEEK)) 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_type == SOCK_STREAM && sk->sk_state == TCP_CLOSE) { if (!sock_flag(sk, SOCK_DONE)) { /* * This occurs when user tries to read * from never connected socket. */ copied = -ENOTCONN; break; } break; } if (!timeo) { copied = -EAGAIN; break; } } if (copied >= target) { /* Do not sleep, just process backlog. */ release_sock(sk); lock_sock(sk); } else sk_wait_data(sk, &timeo, NULL); if ((flags & MSG_PEEK) && peek_seq != llc->copied_seq) { net_dbg_ratelimited("LLC(%s:%d): Application bug, race in MSG_PEEK\n", current->comm, task_pid_nr(current)); peek_seq = llc->copied_seq; } continue; found_ok_skb: skb_len = skb->len; /* Ok so how much can we use? */ used = skb->len - offset; if (len < used) used = len; if (!(flags & MSG_TRUNC)) { int rc = skb_copy_datagram_msg(skb, offset, msg, used); if (rc) { /* Exception. Bailout! */ if (!copied) copied = -EFAULT; break; } } *seq += used; copied += used; len -= used; /* For non stream protcols we get one packet per recvmsg call */ if (sk->sk_type != SOCK_STREAM) goto copy_uaddr; /* Partial read */ if (used + offset < skb_len) continue; if (!(flags & MSG_PEEK)) { skb_unlink(skb, &sk->sk_receive_queue); kfree_skb(skb); *seq = 0; } } while (len > 0); out: release_sock(sk); return copied; copy_uaddr: if (uaddr != NULL && skb != NULL) { memcpy(uaddr, llc_ui_skb_cb(skb), sizeof(*uaddr)); msg->msg_namelen = sizeof(*uaddr); } if (llc_sk(sk)->cmsg_flags) llc_cmsg_rcv(msg, skb); if (!(flags & MSG_PEEK)) { skb_unlink(skb, &sk->sk_receive_queue); kfree_skb(skb); *seq = 0; } goto out; } /** * llc_ui_sendmsg - Transmit data provided by the socket user. * @sock: Socket to transmit data from. * @msg: Various user related information. * @len: Length of data to transmit. * * Transmit data provided by the socket user. * Returns non-negative upon success, negative otherwise. */ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; int rc = -EINVAL, copied = 0, hdrlen, hh_len; struct sk_buff *skb = NULL; struct net_device *dev; size_t size = 0; dprintk("%s: sending from %02X to %02X\n", __func__, llc->laddr.lsap, llc->daddr.lsap); lock_sock(sk); if (addr) { if (msg->msg_namelen < sizeof(*addr)) goto out; } else { if (llc_ui_addr_null(&llc->addr)) goto out; addr = &llc->addr; } /* must bind connection to sap if user hasn't done it. */ if (sock_flag(sk, SOCK_ZAPPED)) { /* bind to sap with null dev, exclusive. */ rc = llc_ui_autobind(sock, addr); if (rc) goto out; } dev = llc->dev; hh_len = LL_RESERVED_SPACE(dev); hdrlen = llc_ui_header_len(sk, addr); size = hdrlen + len; size = min_t(size_t, size, READ_ONCE(dev->mtu)); copied = size - hdrlen; rc = -EINVAL; if (copied < 0) goto out; release_sock(sk); skb = sock_alloc_send_skb(sk, hh_len + size, noblock, &rc); lock_sock(sk); if (!skb) goto out; if (sock_flag(sk, SOCK_ZAPPED) || llc->dev != dev || hdrlen != llc_ui_header_len(sk, addr) || hh_len != LL_RESERVED_SPACE(dev) || size > READ_ONCE(dev->mtu)) goto out; skb->dev = dev; skb->protocol = llc_proto_type(addr->sllc_arphrd); skb_reserve(skb, hh_len + hdrlen); rc = memcpy_from_msg(skb_put(skb, copied), msg, copied); if (rc) goto out; if (sk->sk_type == SOCK_DGRAM || addr->sllc_ua) { llc_build_and_send_ui_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); skb = NULL; goto out; } if (addr->sllc_test) { llc_build_and_send_test_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); skb = NULL; goto out; } if (addr->sllc_xid) { llc_build_and_send_xid_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); skb = NULL; goto out; } rc = -ENOPROTOOPT; if (!(sk->sk_type == SOCK_STREAM && !addr->sllc_ua)) goto out; rc = llc_ui_send_data(sk, skb, noblock); skb = NULL; out: kfree_skb(skb); if (rc) dprintk("%s: failed sending from %02X to %02X: %d\n", __func__, llc->laddr.lsap, llc->daddr.lsap, rc); release_sock(sk); return rc ? : copied; } /** * llc_ui_getname - return the address info of a socket * @sock: Socket to get address of. * @uaddr: Address structure to return information. * @peer: Does user want local or remote address information. * * Return the address information of a socket. */ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_llc sllc; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); int rc = -EBADF; memset(&sllc, 0, sizeof(sllc)); lock_sock(sk); if (sock_flag(sk, SOCK_ZAPPED)) goto out; if (peer) { rc = -ENOTCONN; if (sk->sk_state != TCP_ESTABLISHED) goto out; if(llc->dev) sllc.sllc_arphrd = llc->dev->type; sllc.sllc_sap = llc->daddr.lsap; memcpy(&sllc.sllc_mac, &llc->daddr.mac, IFHWADDRLEN); } else { rc = -EINVAL; if (!llc->sap) goto out; sllc.sllc_sap = llc->sap->laddr.lsap; if (llc->dev) { sllc.sllc_arphrd = llc->dev->type; memcpy(&sllc.sllc_mac, llc->dev->dev_addr, IFHWADDRLEN); } } sllc.sllc_family = AF_LLC; memcpy(uaddr, &sllc, sizeof(sllc)); rc = sizeof(sllc); out: release_sock(sk); return rc; } /** * llc_ui_ioctl - io controls for PF_LLC * @sock: Socket to get/set info * @cmd: command * @arg: optional argument for cmd * * get/set info on llc sockets */ static int llc_ui_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return -ENOIOCTLCMD; } /** * llc_ui_setsockopt - set various connection specific parameters. * @sock: Socket to set options on. * @level: Socket level user is requesting operations on. * @optname: Operation name. * @optval: User provided operation data. * @optlen: Length of optval. * * Set various connection specific parameters. */ static int llc_ui_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); unsigned int opt; int rc = -EINVAL; lock_sock(sk); if (unlikely(level != SOL_LLC || optlen != sizeof(int))) goto out; rc = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (rc) goto out; rc = -EINVAL; switch (optname) { case LLC_OPT_RETRY: if (opt > LLC_OPT_MAX_RETRY) goto out; llc->n2 = opt; break; case LLC_OPT_SIZE: if (opt > LLC_OPT_MAX_SIZE) goto out; llc->n1 = opt; break; case LLC_OPT_ACK_TMR_EXP: if (opt > LLC_OPT_MAX_ACK_TMR_EXP) goto out; llc->ack_timer.expire = opt * HZ; break; case LLC_OPT_P_TMR_EXP: if (opt > LLC_OPT_MAX_P_TMR_EXP) goto out; llc->pf_cycle_timer.expire = opt * HZ; break; case LLC_OPT_REJ_TMR_EXP: if (opt > LLC_OPT_MAX_REJ_TMR_EXP) goto out; llc->rej_sent_timer.expire = opt * HZ; break; case LLC_OPT_BUSY_TMR_EXP: if (opt > LLC_OPT_MAX_BUSY_TMR_EXP) goto out; llc->busy_state_timer.expire = opt * HZ; break; case LLC_OPT_TX_WIN: if (opt > LLC_OPT_MAX_WIN) goto out; llc->k = opt; break; case LLC_OPT_RX_WIN: if (opt > LLC_OPT_MAX_WIN) goto out; llc->rw = opt; break; case LLC_OPT_PKTINFO: if (opt) llc->cmsg_flags |= LLC_CMSG_PKTINFO; else llc->cmsg_flags &= ~LLC_CMSG_PKTINFO; break; default: rc = -ENOPROTOOPT; goto out; } rc = 0; out: release_sock(sk); return rc; } /** * llc_ui_getsockopt - get connection specific socket info * @sock: Socket to get information from. * @level: Socket level user is requesting operations on. * @optname: Operation name. * @opt: sockopt context with iterator and length for returning data. * * Get connection specific socket information. */ static int llc_ui_getsockopt(struct socket *sock, int level, int optname, sockopt_t *opt) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); int val = 0, len, rc = -EINVAL; lock_sock(sk); if (unlikely(level != SOL_LLC)) goto out; len = opt->optlen; if (len != sizeof(int)) goto out; switch (optname) { case LLC_OPT_RETRY: val = llc->n2; break; case LLC_OPT_SIZE: val = llc->n1; break; case LLC_OPT_ACK_TMR_EXP: val = llc->ack_timer.expire / HZ; break; case LLC_OPT_P_TMR_EXP: val = llc->pf_cycle_timer.expire / HZ; break; case LLC_OPT_REJ_TMR_EXP: val = llc->rej_sent_timer.expire / HZ; break; case LLC_OPT_BUSY_TMR_EXP: val = llc->busy_state_timer.expire / HZ; break; case LLC_OPT_TX_WIN: val = llc->k; break; case LLC_OPT_RX_WIN: val = llc->rw; break; case LLC_OPT_PKTINFO: val = (llc->cmsg_flags & LLC_CMSG_PKTINFO) != 0; break; default: rc = -ENOPROTOOPT; goto out; } rc = 0; opt->optlen = len; if (copy_to_iter(&val, len, &opt->iter_out) != len) rc = -EFAULT; out: release_sock(sk); return rc; } static const struct net_proto_family llc_ui_family_ops = { .family = PF_LLC, .create = llc_ui_create, .owner = THIS_MODULE, }; static const struct proto_ops llc_ui_ops = { .family = PF_LLC, .owner = THIS_MODULE, .release = llc_ui_release, .bind = llc_ui_bind, .connect = llc_ui_connect, .socketpair = sock_no_socketpair, .accept = llc_ui_accept, .getname = llc_ui_getname, .poll = datagram_poll, .ioctl = llc_ui_ioctl, .listen = llc_ui_listen, .shutdown = llc_ui_shutdown, .setsockopt = llc_ui_setsockopt, .getsockopt_iter = llc_ui_getsockopt, .sendmsg = llc_ui_sendmsg, .recvmsg = llc_ui_recvmsg, .mmap = sock_no_mmap, }; static const char llc_proc_err_msg[] __initconst = KERN_CRIT "LLC: Unable to register the proc_fs entries\n"; static const char llc_sysctl_err_msg[] __initconst = KERN_CRIT "LLC: Unable to register the sysctl entries\n"; static const char llc_sock_err_msg[] __initconst = KERN_CRIT "LLC: Unable to register the network family\n"; static int __init llc2_init(void) { int rc = proto_register(&llc_proto, 0); if (rc != 0) goto out; llc_build_offset_table(); llc_station_init(); llc_ui_sap_last_autoport = LLC_SAP_DYN_START; rc = llc_proc_init(); if (rc != 0) { printk(llc_proc_err_msg); goto out_station; } rc = llc_sysctl_init(); if (rc) { printk(llc_sysctl_err_msg); goto out_proc; } rc = sock_register(&llc_ui_family_ops); if (rc) { printk(llc_sock_err_msg); goto out_sysctl; } llc_add_pack(LLC_DEST_SAP, llc_sap_handler); llc_add_pack(LLC_DEST_CONN, llc_conn_handler); out: return rc; out_sysctl: llc_sysctl_exit(); out_proc: llc_proc_exit(); out_station: llc_station_exit(); proto_unregister(&llc_proto); goto out; } static void __exit llc2_exit(void) { llc_station_exit(); llc_remove_pack(LLC_DEST_SAP); llc_remove_pack(LLC_DEST_CONN); sock_unregister(PF_LLC); llc_proc_exit(); llc_sysctl_exit(); proto_unregister(&llc_proto); } module_init(llc2_init); module_exit(llc2_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Procom 1997, Jay Schullist 2001, Arnaldo C. Melo 2001-2003"); MODULE_DESCRIPTION("IEEE 802.2 PF_LLC support"); MODULE_ALIAS_NETPROTO(PF_LLC); |
| 15 18 4 14 14 14 15 15 15 15 15 15 15 15 15 14 15 15 15 15 15 13 13 13 5 5 5 5 19 19 4 7 5 1 2 2 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 | // SPDX-License-Identifier: GPL-2.0-or-later /* * CCM: Counter with CBC-MAC * * (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com> */ #include <crypto/internal/aead.h> #include <crypto/internal/cipher.h> #include <crypto/internal/hash.h> #include <crypto/internal/skcipher.h> #include <crypto/scatterwalk.h> #include <crypto/utils.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/string.h> struct ccm_instance_ctx { struct crypto_skcipher_spawn ctr; struct crypto_ahash_spawn mac; }; struct crypto_ccm_ctx { struct crypto_ahash *mac; struct crypto_skcipher *ctr; }; struct crypto_rfc4309_ctx { struct crypto_aead *child; u8 nonce[3]; }; struct crypto_rfc4309_req_ctx { struct scatterlist src[3]; struct scatterlist dst[3]; struct aead_request subreq; }; struct crypto_ccm_req_priv_ctx { u8 odata[16]; u8 idata[16]; u8 auth_tag[16]; u32 flags; struct scatterlist src[3]; struct scatterlist dst[3]; union { struct ahash_request ahreq; struct skcipher_request skreq; }; }; struct cbcmac_tfm_ctx { struct crypto_cipher *child; }; static inline struct crypto_ccm_req_priv_ctx *crypto_ccm_reqctx( struct aead_request *req) { unsigned long align = crypto_aead_alignmask(crypto_aead_reqtfm(req)); return (void *)PTR_ALIGN((u8 *)aead_request_ctx(req), align + 1); } static int set_msg_len(u8 *block, unsigned int msglen, int csize) { __be32 data; memset(block, 0, csize); block += csize; if (csize >= 4) csize = 4; else if (msglen > (1 << (8 * csize))) return -EOVERFLOW; data = cpu_to_be32(msglen); memcpy(block - csize, (u8 *)&data + 4 - csize, csize); return 0; } static int crypto_ccm_setkey(struct crypto_aead *aead, const u8 *key, unsigned int keylen) { struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead); struct crypto_skcipher *ctr = ctx->ctr; struct crypto_ahash *mac = ctx->mac; int err; crypto_skcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK); crypto_skcipher_set_flags(ctr, crypto_aead_get_flags(aead) & CRYPTO_TFM_REQ_MASK); err = crypto_skcipher_setkey(ctr, key, keylen); if (err) return err; crypto_ahash_clear_flags(mac, CRYPTO_TFM_REQ_MASK); crypto_ahash_set_flags(mac, crypto_aead_get_flags(aead) & CRYPTO_TFM_REQ_MASK); return crypto_ahash_setkey(mac, key, keylen); } static int crypto_ccm_setauthsize(struct crypto_aead *tfm, unsigned int authsize) { switch (authsize) { case 4: case 6: case 8: case 10: case 12: case 14: case 16: break; default: return -EINVAL; } return 0; } static int format_input(u8 *info, struct aead_request *req, unsigned int cryptlen) { struct crypto_aead *aead = crypto_aead_reqtfm(req); unsigned int lp = req->iv[0]; unsigned int l = lp + 1; unsigned int m; m = crypto_aead_authsize(aead); memcpy(info, req->iv, 16); /* format control info per RFC 3610 and * NIST Special Publication 800-38C */ *info |= (8 * ((m - 2) / 2)); if (req->assoclen) *info |= 64; return set_msg_len(info + 16 - l, cryptlen, l); } static int format_adata(u8 *adata, unsigned int a) { int len = 0; /* add control info for associated data * RFC 3610 and NIST Special Publication 800-38C */ if (a < 65280) { *(__be16 *)adata = cpu_to_be16(a); len = 2; } else { *(__be16 *)adata = cpu_to_be16(0xfffe); *(__be32 *)&adata[2] = cpu_to_be32(a); len = 6; } return len; } static int crypto_ccm_auth(struct aead_request *req, struct scatterlist *plain, unsigned int cryptlen) { struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead); struct ahash_request *ahreq = &pctx->ahreq; unsigned int assoclen = req->assoclen; struct scatterlist sg[3]; u8 *odata = pctx->odata; u8 *idata = pctx->idata; int ilen, err; /* format control data for input */ err = format_input(odata, req, cryptlen); if (err) goto out; sg_init_table(sg, 3); sg_set_buf(&sg[0], odata, 16); /* format associated data and compute into mac */ if (assoclen) { ilen = format_adata(idata, assoclen); sg_set_buf(&sg[1], idata, ilen); sg_chain(sg, 3, req->src); } else { ilen = 0; sg_chain(sg, 2, req->src); } ahash_request_set_tfm(ahreq, ctx->mac); ahash_request_set_callback(ahreq, pctx->flags, NULL, NULL); ahash_request_set_crypt(ahreq, sg, NULL, assoclen + ilen + 16); err = crypto_ahash_init(ahreq); if (err) goto out; err = crypto_ahash_update(ahreq); if (err) goto out; /* we need to pad the MAC input to a round multiple of the block size */ ilen = 16 - (assoclen + ilen) % 16; if (ilen < 16) { memset(idata, 0, ilen); sg_init_table(sg, 2); sg_set_buf(&sg[0], idata, ilen); if (plain) sg_chain(sg, 2, plain); plain = sg; cryptlen += ilen; } ahash_request_set_crypt(ahreq, plain, odata, cryptlen); err = crypto_ahash_finup(ahreq); out: return err; } static void crypto_ccm_encrypt_done(void *data, int err) { struct aead_request *req = data; struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); u8 *odata = pctx->odata; if (!err) scatterwalk_map_and_copy(odata, req->dst, req->assoclen + req->cryptlen, crypto_aead_authsize(aead), 1); aead_request_complete(req, err); } static inline int crypto_ccm_check_iv(const u8 *iv) { /* 2 <= L <= 8, so 1 <= L' <= 7. */ if (1 > iv[0] || iv[0] > 7) return -EINVAL; return 0; } static int crypto_ccm_init_crypt(struct aead_request *req, u8 *tag) { struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct scatterlist *sg; u8 *iv = req->iv; int err; err = crypto_ccm_check_iv(iv); if (err) return err; pctx->flags = aead_request_flags(req); /* Note: rfc 3610 and NIST 800-38C require counter of * zero to encrypt auth tag. */ memset(iv + 15 - iv[0], 0, iv[0] + 1); sg_init_table(pctx->src, 3); sg_set_buf(pctx->src, tag, 16); sg = scatterwalk_ffwd(pctx->src + 1, req->src, req->assoclen); if (sg != pctx->src + 1) sg_chain(pctx->src, 2, sg); if (req->src != req->dst) { sg_init_table(pctx->dst, 3); sg_set_buf(pctx->dst, tag, 16); sg = scatterwalk_ffwd(pctx->dst + 1, req->dst, req->assoclen); if (sg != pctx->dst + 1) sg_chain(pctx->dst, 2, sg); } return 0; } static int crypto_ccm_encrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead); struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct skcipher_request *skreq = &pctx->skreq; struct scatterlist *dst; unsigned int cryptlen = req->cryptlen; u8 *odata = pctx->odata; u8 *iv = req->iv; int err; err = crypto_ccm_init_crypt(req, odata); if (err) return err; err = crypto_ccm_auth(req, sg_next(pctx->src), cryptlen); if (err) return err; dst = pctx->src; if (req->src != req->dst) dst = pctx->dst; skcipher_request_set_tfm(skreq, ctx->ctr); skcipher_request_set_callback(skreq, pctx->flags, crypto_ccm_encrypt_done, req); skcipher_request_set_crypt(skreq, pctx->src, dst, cryptlen + 16, iv); err = crypto_skcipher_encrypt(skreq); if (err) return err; /* copy authtag to end of dst */ scatterwalk_map_and_copy(odata, sg_next(dst), cryptlen, crypto_aead_authsize(aead), 1); return err; } static void crypto_ccm_decrypt_done(void *data, int err) { struct aead_request *req = data; struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct crypto_aead *aead = crypto_aead_reqtfm(req); unsigned int authsize = crypto_aead_authsize(aead); unsigned int cryptlen = req->cryptlen - authsize; struct scatterlist *dst; pctx->flags = 0; dst = sg_next(req->src == req->dst ? pctx->src : pctx->dst); if (!err) { err = crypto_ccm_auth(req, dst, cryptlen); if (!err && crypto_memneq(pctx->auth_tag, pctx->odata, authsize)) err = -EBADMSG; } aead_request_complete(req, err); } static int crypto_ccm_decrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead); struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req); struct skcipher_request *skreq = &pctx->skreq; struct scatterlist *dst; unsigned int authsize = crypto_aead_authsize(aead); unsigned int cryptlen = req->cryptlen; u8 *authtag = pctx->auth_tag; u8 *odata = pctx->odata; u8 *iv = pctx->idata; int err; cryptlen -= authsize; err = crypto_ccm_init_crypt(req, authtag); if (err) return err; scatterwalk_map_and_copy(authtag, sg_next(pctx->src), cryptlen, authsize, 0); dst = pctx->src; if (req->src != req->dst) dst = pctx->dst; memcpy(iv, req->iv, 16); skcipher_request_set_tfm(skreq, ctx->ctr); skcipher_request_set_callback(skreq, pctx->flags, crypto_ccm_decrypt_done, req); skcipher_request_set_crypt(skreq, pctx->src, dst, cryptlen + 16, iv); err = crypto_skcipher_decrypt(skreq); if (err) return err; err = crypto_ccm_auth(req, sg_next(dst), cryptlen); if (err) return err; /* verify */ if (crypto_memneq(authtag, odata, authsize)) return -EBADMSG; return err; } static int crypto_ccm_init_tfm(struct crypto_aead *tfm) { struct aead_instance *inst = aead_alg_instance(tfm); struct ccm_instance_ctx *ictx = aead_instance_ctx(inst); struct crypto_ccm_ctx *ctx = crypto_aead_ctx(tfm); struct crypto_ahash *mac; struct crypto_skcipher *ctr; unsigned long align; int err; mac = crypto_spawn_ahash(&ictx->mac); if (IS_ERR(mac)) return PTR_ERR(mac); ctr = crypto_spawn_skcipher(&ictx->ctr); err = PTR_ERR(ctr); if (IS_ERR(ctr)) goto err_free_mac; ctx->mac = mac; ctx->ctr = ctr; align = crypto_aead_alignmask(tfm); align &= ~(crypto_tfm_ctx_alignment() - 1); crypto_aead_set_reqsize( tfm, align + sizeof(struct crypto_ccm_req_priv_ctx) + max(crypto_ahash_reqsize(mac), crypto_skcipher_reqsize(ctr))); return 0; err_free_mac: crypto_free_ahash(mac); return err; } static void crypto_ccm_exit_tfm(struct crypto_aead *tfm) { struct crypto_ccm_ctx *ctx = crypto_aead_ctx(tfm); crypto_free_ahash(ctx->mac); crypto_free_skcipher(ctx->ctr); } static void crypto_ccm_free(struct aead_instance *inst) { struct ccm_instance_ctx *ctx = aead_instance_ctx(inst); crypto_drop_ahash(&ctx->mac); crypto_drop_skcipher(&ctx->ctr); kfree(inst); } static int crypto_ccm_create_common(struct crypto_template *tmpl, struct rtattr **tb, const char *ctr_name, const char *mac_name) { struct skcipher_alg_common *ctr; u32 mask; struct aead_instance *inst; struct ccm_instance_ctx *ictx; struct hash_alg_common *mac; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_AEAD, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*ictx), GFP_KERNEL); if (!inst) return -ENOMEM; ictx = aead_instance_ctx(inst); err = crypto_grab_ahash(&ictx->mac, aead_crypto_instance(inst), mac_name, 0, mask | CRYPTO_ALG_ASYNC); if (err) goto err_free_inst; mac = crypto_spawn_ahash_alg(&ictx->mac); err = -EINVAL; if (strncmp(mac->base.cra_name, "cbcmac(", 7) != 0 || mac->digestsize != 16) goto err_free_inst; err = crypto_grab_skcipher(&ictx->ctr, aead_crypto_instance(inst), ctr_name, 0, mask); if (err) goto err_free_inst; ctr = crypto_spawn_skcipher_alg_common(&ictx->ctr); /* The skcipher algorithm must be CTR mode, using 16-byte blocks. */ err = -EINVAL; if (strncmp(ctr->base.cra_name, "ctr(", 4) != 0 || ctr->ivsize != 16 || ctr->base.cra_blocksize != 1) goto err_free_inst; /* ctr and cbcmac must use the same underlying block cipher. */ if (strcmp(ctr->base.cra_name + 4, mac->base.cra_name + 7) != 0) goto err_free_inst; err = -ENAMETOOLONG; if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, "ccm(%s", ctr->base.cra_name + 4) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "ccm_base(%s,%s)", ctr->base.cra_driver_name, mac->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; inst->alg.base.cra_priority = (mac->base.cra_priority + ctr->base.cra_priority) / 2; inst->alg.base.cra_blocksize = 1; inst->alg.base.cra_alignmask = ctr->base.cra_alignmask; inst->alg.ivsize = 16; inst->alg.chunksize = ctr->chunksize; inst->alg.maxauthsize = 16; inst->alg.base.cra_ctxsize = sizeof(struct crypto_ccm_ctx); inst->alg.init = crypto_ccm_init_tfm; inst->alg.exit = crypto_ccm_exit_tfm; inst->alg.setkey = crypto_ccm_setkey; inst->alg.setauthsize = crypto_ccm_setauthsize; inst->alg.encrypt = crypto_ccm_encrypt; inst->alg.decrypt = crypto_ccm_decrypt; inst->free = crypto_ccm_free; err = aead_register_instance(tmpl, inst); if (err) { err_free_inst: crypto_ccm_free(inst); } return err; } static int crypto_ccm_create(struct crypto_template *tmpl, struct rtattr **tb) { const char *cipher_name; char ctr_name[CRYPTO_MAX_ALG_NAME]; char mac_name[CRYPTO_MAX_ALG_NAME]; cipher_name = crypto_attr_alg_name(tb[1]); if (IS_ERR(cipher_name)) return PTR_ERR(cipher_name); if (snprintf(ctr_name, CRYPTO_MAX_ALG_NAME, "ctr(%s)", cipher_name) >= CRYPTO_MAX_ALG_NAME) return -ENAMETOOLONG; if (snprintf(mac_name, CRYPTO_MAX_ALG_NAME, "cbcmac(%s)", cipher_name) >= CRYPTO_MAX_ALG_NAME) return -ENAMETOOLONG; return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name); } static int crypto_ccm_base_create(struct crypto_template *tmpl, struct rtattr **tb) { const char *ctr_name; const char *mac_name; ctr_name = crypto_attr_alg_name(tb[1]); if (IS_ERR(ctr_name)) return PTR_ERR(ctr_name); mac_name = crypto_attr_alg_name(tb[2]); if (IS_ERR(mac_name)) return PTR_ERR(mac_name); return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name); } static int crypto_rfc4309_setkey(struct crypto_aead *parent, const u8 *key, unsigned int keylen) { struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(parent); struct crypto_aead *child = ctx->child; if (keylen < 3) return -EINVAL; keylen -= 3; memcpy(ctx->nonce, key + keylen, 3); crypto_aead_clear_flags(child, CRYPTO_TFM_REQ_MASK); crypto_aead_set_flags(child, crypto_aead_get_flags(parent) & CRYPTO_TFM_REQ_MASK); return crypto_aead_setkey(child, key, keylen); } static int crypto_rfc4309_setauthsize(struct crypto_aead *parent, unsigned int authsize) { struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(parent); switch (authsize) { case 8: case 12: case 16: break; default: return -EINVAL; } return crypto_aead_setauthsize(ctx->child, authsize); } static struct aead_request *crypto_rfc4309_crypt(struct aead_request *req) { struct crypto_rfc4309_req_ctx *rctx = aead_request_ctx(req); struct aead_request *subreq = &rctx->subreq; struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(aead); struct crypto_aead *child = ctx->child; struct scatterlist *sg; u8 *iv = PTR_ALIGN((u8 *)(subreq + 1) + crypto_aead_reqsize(child), crypto_aead_alignmask(child) + 1); /* L' */ iv[0] = 3; memcpy(iv + 1, ctx->nonce, 3); memcpy(iv + 4, req->iv, 8); scatterwalk_map_and_copy(iv + 16, req->src, 0, req->assoclen - 8, 0); sg_init_table(rctx->src, 3); sg_set_buf(rctx->src, iv + 16, req->assoclen - 8); sg = scatterwalk_ffwd(rctx->src + 1, req->src, req->assoclen); if (sg != rctx->src + 1) sg_chain(rctx->src, 2, sg); if (req->src != req->dst) { sg_init_table(rctx->dst, 3); sg_set_buf(rctx->dst, iv + 16, req->assoclen - 8); sg = scatterwalk_ffwd(rctx->dst + 1, req->dst, req->assoclen); if (sg != rctx->dst + 1) sg_chain(rctx->dst, 2, sg); } aead_request_set_tfm(subreq, child); aead_request_set_callback(subreq, req->base.flags, req->base.complete, req->base.data); aead_request_set_crypt(subreq, rctx->src, req->src == req->dst ? rctx->src : rctx->dst, req->cryptlen, iv); aead_request_set_ad(subreq, req->assoclen - 8); return subreq; } static int crypto_rfc4309_encrypt(struct aead_request *req) { if (req->assoclen != 16 && req->assoclen != 20) return -EINVAL; req = crypto_rfc4309_crypt(req); return crypto_aead_encrypt(req); } static int crypto_rfc4309_decrypt(struct aead_request *req) { if (req->assoclen != 16 && req->assoclen != 20) return -EINVAL; req = crypto_rfc4309_crypt(req); return crypto_aead_decrypt(req); } static int crypto_rfc4309_init_tfm(struct crypto_aead *tfm) { struct aead_instance *inst = aead_alg_instance(tfm); struct crypto_aead_spawn *spawn = aead_instance_ctx(inst); struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(tfm); struct crypto_aead *aead; unsigned long align; aead = crypto_spawn_aead(spawn); if (IS_ERR(aead)) return PTR_ERR(aead); ctx->child = aead; align = crypto_aead_alignmask(aead); align &= ~(crypto_tfm_ctx_alignment() - 1); crypto_aead_set_reqsize( tfm, sizeof(struct crypto_rfc4309_req_ctx) + ALIGN(crypto_aead_reqsize(aead), crypto_tfm_ctx_alignment()) + align + 32); return 0; } static void crypto_rfc4309_exit_tfm(struct crypto_aead *tfm) { struct crypto_rfc4309_ctx *ctx = crypto_aead_ctx(tfm); crypto_free_aead(ctx->child); } static void crypto_rfc4309_free(struct aead_instance *inst) { crypto_drop_aead(aead_instance_ctx(inst)); kfree(inst); } static int crypto_rfc4309_create(struct crypto_template *tmpl, struct rtattr **tb) { u32 mask; struct aead_instance *inst; struct crypto_aead_spawn *spawn; struct aead_alg *alg; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_AEAD, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return -ENOMEM; spawn = aead_instance_ctx(inst); err = crypto_grab_aead(spawn, aead_crypto_instance(inst), crypto_attr_alg_name(tb[1]), 0, mask); if (err) goto err_free_inst; alg = crypto_spawn_aead_alg(spawn); err = -EINVAL; /* We only support 16-byte blocks. */ if (crypto_aead_alg_ivsize(alg) != 16) goto err_free_inst; /* Not a stream cipher? */ if (alg->base.cra_blocksize != 1) goto err_free_inst; err = -ENAMETOOLONG; if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, "rfc4309(%s)", alg->base.cra_name) >= CRYPTO_MAX_ALG_NAME || snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "rfc4309(%s)", alg->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; inst->alg.base.cra_priority = alg->base.cra_priority; inst->alg.base.cra_blocksize = 1; inst->alg.base.cra_alignmask = alg->base.cra_alignmask; inst->alg.ivsize = 8; inst->alg.chunksize = crypto_aead_alg_chunksize(alg); inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg); inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4309_ctx); inst->alg.init = crypto_rfc4309_init_tfm; inst->alg.exit = crypto_rfc4309_exit_tfm; inst->alg.setkey = crypto_rfc4309_setkey; inst->alg.setauthsize = crypto_rfc4309_setauthsize; inst->alg.encrypt = crypto_rfc4309_encrypt; inst->alg.decrypt = crypto_rfc4309_decrypt; inst->free = crypto_rfc4309_free; err = aead_register_instance(tmpl, inst); if (err) { err_free_inst: crypto_rfc4309_free(inst); } return err; } static int crypto_cbcmac_digest_setkey(struct crypto_shash *parent, const u8 *inkey, unsigned int keylen) { struct cbcmac_tfm_ctx *ctx = crypto_shash_ctx(parent); return crypto_cipher_setkey(ctx->child, inkey, keylen); } static int crypto_cbcmac_digest_init(struct shash_desc *pdesc) { int bs = crypto_shash_digestsize(pdesc->tfm); u8 *dg = shash_desc_ctx(pdesc); memset(dg, 0, bs); return 0; } static int crypto_cbcmac_digest_update(struct shash_desc *pdesc, const u8 *p, unsigned int len) { struct crypto_shash *parent = pdesc->tfm; struct cbcmac_tfm_ctx *tctx = crypto_shash_ctx(parent); struct crypto_cipher *tfm = tctx->child; int bs = crypto_shash_digestsize(parent); u8 *dg = shash_desc_ctx(pdesc); do { crypto_xor(dg, p, bs); crypto_cipher_encrypt_one(tfm, dg, dg); p += bs; len -= bs; } while (len >= bs); return len; } static int crypto_cbcmac_digest_finup(struct shash_desc *pdesc, const u8 *src, unsigned int len, u8 *out) { struct crypto_shash *parent = pdesc->tfm; struct cbcmac_tfm_ctx *tctx = crypto_shash_ctx(parent); struct crypto_cipher *tfm = tctx->child; int bs = crypto_shash_digestsize(parent); u8 *dg = shash_desc_ctx(pdesc); if (len) { crypto_xor(dg, src, len); crypto_cipher_encrypt_one(tfm, out, dg); return 0; } memcpy(out, dg, bs); return 0; } static int cbcmac_init_tfm(struct crypto_tfm *tfm) { struct crypto_cipher *cipher; struct crypto_instance *inst = (void *)tfm->__crt_alg; struct crypto_cipher_spawn *spawn = crypto_instance_ctx(inst); struct cbcmac_tfm_ctx *ctx = crypto_tfm_ctx(tfm); cipher = crypto_spawn_cipher(spawn); if (IS_ERR(cipher)) return PTR_ERR(cipher); ctx->child = cipher; return 0; }; static void cbcmac_exit_tfm(struct crypto_tfm *tfm) { struct cbcmac_tfm_ctx *ctx = crypto_tfm_ctx(tfm); crypto_free_cipher(ctx->child); } static int cbcmac_create(struct crypto_template *tmpl, struct rtattr **tb) { struct shash_instance *inst; struct crypto_cipher_spawn *spawn; struct crypto_alg *alg; u32 mask; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SHASH, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return -ENOMEM; spawn = shash_instance_ctx(inst); err = crypto_grab_cipher(spawn, shash_crypto_instance(inst), crypto_attr_alg_name(tb[1]), 0, mask); if (err) goto err_free_inst; alg = crypto_spawn_cipher_alg(spawn); err = crypto_inst_setname(shash_crypto_instance(inst), tmpl->name, alg); if (err) goto err_free_inst; inst->alg.base.cra_priority = alg->cra_priority; inst->alg.base.cra_blocksize = alg->cra_blocksize; inst->alg.digestsize = alg->cra_blocksize; inst->alg.descsize = alg->cra_blocksize; inst->alg.base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY; inst->alg.base.cra_ctxsize = sizeof(struct cbcmac_tfm_ctx); inst->alg.base.cra_init = cbcmac_init_tfm; inst->alg.base.cra_exit = cbcmac_exit_tfm; inst->alg.init = crypto_cbcmac_digest_init; inst->alg.update = crypto_cbcmac_digest_update; inst->alg.finup = crypto_cbcmac_digest_finup; inst->alg.setkey = crypto_cbcmac_digest_setkey; inst->free = shash_free_singlespawn_instance; err = shash_register_instance(tmpl, inst); if (err) { err_free_inst: shash_free_singlespawn_instance(inst); } return err; } static struct crypto_template crypto_ccm_tmpls[] = { { .name = "cbcmac", .create = cbcmac_create, .module = THIS_MODULE, }, { .name = "ccm_base", .create = crypto_ccm_base_create, .module = THIS_MODULE, }, { .name = "ccm", .create = crypto_ccm_create, .module = THIS_MODULE, }, { .name = "rfc4309", .create = crypto_rfc4309_create, .module = THIS_MODULE, }, }; static int __init crypto_ccm_module_init(void) { return crypto_register_templates(crypto_ccm_tmpls, ARRAY_SIZE(crypto_ccm_tmpls)); } static void __exit crypto_ccm_module_exit(void) { crypto_unregister_templates(crypto_ccm_tmpls, ARRAY_SIZE(crypto_ccm_tmpls)); } module_init(crypto_ccm_module_init); module_exit(crypto_ccm_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Counter with CBC MAC"); MODULE_ALIAS_CRYPTO("ccm_base"); MODULE_ALIAS_CRYPTO("rfc4309"); MODULE_ALIAS_CRYPTO("ccm"); MODULE_ALIAS_CRYPTO("cbcmac"); MODULE_IMPORT_NS("CRYPTO_INTERNAL"); |
| 10 7 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 | // SPDX-License-Identifier: GPL-2.0-only /* * The Virtio 9p transport driver * * This is a block based transport driver based on the lguest block driver * code. * * Copyright (C) 2007, 2008 Eric Van Hensbergen, IBM Corporation * * Based on virtio console driver * Copyright (C) 2006, 2007 Rusty Russell, IBM Corporation */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/in.h> #include <linux/module.h> #include <linux/net.h> #include <linux/ipv6.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/un.h> #include <linux/uaccess.h> #include <linux/inet.h> #include <linux/file.h> #include <linux/highmem.h> #include <linux/slab.h> #include <net/9p/9p.h> #include <linux/fs_context.h> #include <net/9p/client.h> #include <net/9p/transport.h> #include <linux/scatterlist.h> #include <linux/swap.h> #include <linux/virtio.h> #include <linux/virtio_9p.h> #include "trans_common.h" #define VIRTQUEUE_NUM 128 /* a single mutex to manage channel initialization and attachment */ static DEFINE_MUTEX(virtio_9p_lock); static DECLARE_WAIT_QUEUE_HEAD(vp_wq); static atomic_t vp_pinned = ATOMIC_INIT(0); /** * struct virtio_chan - per-instance transport information * @inuse: whether the channel is in use * @lock: protects multiple elements within this structure * @client: client instance * @vdev: virtio dev associated with this channel * @vq: virtio queue associated with this channel * @ring_bufs_avail: flag to indicate there is some available in the ring buf * @vc_wq: wait queue for waiting for thing to be added to ring buf * @p9_max_pages: maximum number of pinned pages * @sg: scatter gather list which is used to pack a request (protected?) * @chan_list: linked list of channels * * We keep all per-channel information in a structure. * This structure is allocated within the devices dev->mem space. * A pointer to the structure will get put in the transport private. * */ struct virtio_chan { bool inuse; spinlock_t lock; struct p9_client *client; struct virtio_device *vdev; struct virtqueue *vq; int ring_bufs_avail; wait_queue_head_t *vc_wq; /* This is global limit. Since we don't have a global structure, * will be placing it in each channel. */ unsigned long p9_max_pages; /* Scatterlist: can be too big for stack. */ struct scatterlist sg[VIRTQUEUE_NUM]; /** * @tag: name to identify a mount null terminated */ char *tag; struct list_head chan_list; }; static struct list_head virtio_chan_list; /* How many bytes left in this page. */ static unsigned int rest_of_page(void *data) { return PAGE_SIZE - offset_in_page(data); } /** * p9_virtio_close - reclaim resources of a channel * @client: client instance * * This reclaims a channel by freeing its resources and * resetting its inuse flag. * */ static void p9_virtio_close(struct p9_client *client) { struct virtio_chan *chan = client->trans; mutex_lock(&virtio_9p_lock); if (chan) chan->inuse = false; mutex_unlock(&virtio_9p_lock); } /** * req_done - callback which signals activity from the server * @vq: virtio queue activity was received on * * This notifies us that the server has triggered some activity * on the virtio channel - most likely a response to request we * sent. Figure out which requests now have responses and wake up * those threads. * * Bugs: could do with some additional sanity checking, but appears to work. * */ static void req_done(struct virtqueue *vq) { struct virtio_chan *chan = vq->vdev->priv; unsigned int len; struct p9_req_t *req; bool need_wakeup = false; unsigned long flags; p9_debug(P9_DEBUG_TRANS, ": request done\n"); spin_lock_irqsave(&chan->lock, flags); while ((req = virtqueue_get_buf(chan->vq, &len)) != NULL) { if (!chan->ring_bufs_avail) { chan->ring_bufs_avail = 1; need_wakeup = true; } if (len) { req->rc.size = len; p9_client_cb(chan->client, req, REQ_STATUS_RCVD); } } spin_unlock_irqrestore(&chan->lock, flags); /* Wakeup if anyone waiting for VirtIO ring space. */ if (need_wakeup) wake_up(chan->vc_wq); } /** * pack_sg_list - pack a scatter gather list from a linear buffer * @sg: scatter/gather list to pack into * @start: which segment of the sg_list to start at * @limit: maximum segment to pack data to * @data: data to pack into scatter/gather list * @count: amount of data to pack into the scatter/gather list * * sg_lists have multiple segments of various sizes. This will pack * arbitrary data into an existing scatter gather list, segmenting the * data as necessary within constraints. * */ static int pack_sg_list(struct scatterlist *sg, int start, int limit, char *data, int count) { int s; int index = start; while (count) { s = rest_of_page(data); if (s > count) s = count; BUG_ON(index >= limit); /* Make sure we don't terminate early. */ sg_unmark_end(&sg[index]); sg_set_buf(&sg[index++], data, s); count -= s; data += s; } if (index-start) sg_mark_end(&sg[index - 1]); return index-start; } /* We don't currently allow canceling of virtio requests */ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req) { return 1; } /* Reply won't come, so drop req ref */ static int p9_virtio_cancelled(struct p9_client *client, struct p9_req_t *req) { p9_req_put(client, req); return 0; } /** * pack_sg_list_p - Just like pack_sg_list. Instead of taking a buffer, * this takes a list of pages. * @sg: scatter/gather list to pack into * @start: which segment of the sg_list to start at * @limit: maximum number of pages in sg list. * @pdata: a list of pages to add into sg. * @nr_pages: number of pages to pack into the scatter/gather list * @offs: amount of data in the beginning of first page _not_ to pack * @count: amount of data to pack into the scatter/gather list */ static int pack_sg_list_p(struct scatterlist *sg, int start, int limit, struct page **pdata, int nr_pages, size_t offs, int count) { int i = 0, s; int data_off = offs; int index = start; BUG_ON(nr_pages > (limit - start)); /* * if the first page doesn't start at * page boundary find the offset */ while (nr_pages) { s = PAGE_SIZE - data_off; if (s > count) s = count; BUG_ON(index >= limit); /* Make sure we don't terminate early. */ sg_unmark_end(&sg[index]); sg_set_page(&sg[index++], pdata[i++], s, data_off); data_off = 0; count -= s; nr_pages--; } if (index-start) sg_mark_end(&sg[index - 1]); return index - start; } /** * p9_virtio_request - issue a request * @client: client instance issuing the request * @req: request to be issued * */ static int p9_virtio_request(struct p9_client *client, struct p9_req_t *req) { int err; int in, out, out_sgs, in_sgs; unsigned long flags; struct virtio_chan *chan = client->trans; struct scatterlist *sgs[2]; p9_debug(P9_DEBUG_TRANS, "9p debug: virtio request\n"); WRITE_ONCE(req->status, REQ_STATUS_SENT); req_retry: spin_lock_irqsave(&chan->lock, flags); out_sgs = in_sgs = 0; /* Handle out VirtIO ring buffers */ out = pack_sg_list(chan->sg, 0, VIRTQUEUE_NUM, req->tc.sdata, req->tc.size); if (out) sgs[out_sgs++] = chan->sg; in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, req->rc.sdata, req->rc.capacity); if (in) sgs[out_sgs + in_sgs++] = chan->sg + out; err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req, GFP_ATOMIC); if (err < 0) { if (err == -ENOSPC) { chan->ring_bufs_avail = 0; spin_unlock_irqrestore(&chan->lock, flags); err = io_wait_event_killable(*chan->vc_wq, chan->ring_bufs_avail); if (err == -ERESTARTSYS) return err; p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n"); goto req_retry; } else { spin_unlock_irqrestore(&chan->lock, flags); p9_debug(P9_DEBUG_TRANS, "virtio rpc add_sgs returned failure\n"); return -EIO; } } virtqueue_kick(chan->vq); spin_unlock_irqrestore(&chan->lock, flags); p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n"); return 0; } static int p9_get_mapped_pages(struct virtio_chan *chan, struct page ***pages, struct iov_iter *data, int count, size_t *offs, int *need_drop) { int nr_pages; int err; if (!iov_iter_count(data)) return 0; if (!iov_iter_is_kvec(data)) { int n; /* * We allow only p9_max_pages pinned. We wait for the * Other zc request to finish here */ if (atomic_read(&vp_pinned) >= chan->p9_max_pages) { err = io_wait_event_killable(vp_wq, (atomic_read(&vp_pinned) < chan->p9_max_pages)); if (err == -ERESTARTSYS) return err; } n = iov_iter_get_pages_alloc2(data, pages, count, offs); if (n < 0) return n; *need_drop = 1; nr_pages = DIV_ROUND_UP(n + *offs, PAGE_SIZE); atomic_add(nr_pages, &vp_pinned); return n; } else { /* kernel buffer, no need to pin pages */ int index; size_t len; void *p; /* we'd already checked that it's non-empty */ while (1) { len = iov_iter_single_seg_count(data); if (likely(len)) { p = data->kvec->iov_base + data->iov_offset; break; } iov_iter_advance(data, 0); } if (len > count) len = count; nr_pages = DIV_ROUND_UP((unsigned long)p + len, PAGE_SIZE) - (unsigned long)p / PAGE_SIZE; *pages = kmalloc_objs(struct page *, nr_pages, GFP_NOFS); if (!*pages) return -ENOMEM; *need_drop = 0; p -= (*offs = offset_in_page(p)); for (index = 0; index < nr_pages; index++) { if (is_vmalloc_addr(p)) (*pages)[index] = vmalloc_to_page(p); else (*pages)[index] = kmap_to_page(p); p += PAGE_SIZE; } iov_iter_advance(data, len); return len; } } static void handle_rerror(struct p9_req_t *req, int in_hdr_len, size_t offs, struct page **pages) { unsigned size, n; void *to = req->rc.sdata + in_hdr_len; // Fits entirely into the static data? Nothing to do. if (req->rc.size < in_hdr_len || !pages) return; // Really long error message? Tough, truncate the reply. Might get // rejected (we can't be arsed to adjust the size encoded in header, // or string size for that matter), but it wouldn't be anything valid // anyway. if (unlikely(req->rc.size > P9_ZC_HDR_SZ)) req->rc.size = P9_ZC_HDR_SZ; // data won't span more than two pages size = req->rc.size - in_hdr_len; n = PAGE_SIZE - offs; if (size > n) { memcpy_from_page(to, *pages++, offs, n); offs = 0; to += n; size -= n; } memcpy_from_page(to, *pages, offs, size); } /** * p9_virtio_zc_request - issue a zero copy request * @client: client instance issuing the request * @req: request to be issued * @uidata: user buffer that should be used for zero copy read * @uodata: user buffer that should be used for zero copy write * @inlen: read buffer size * @outlen: write buffer size * @in_hdr_len: reader header size, This is the size of response protocol data * */ static int p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req, struct iov_iter *uidata, struct iov_iter *uodata, int inlen, int outlen, int in_hdr_len) { int in, out, err, out_sgs, in_sgs; unsigned long flags; int in_nr_pages = 0, out_nr_pages = 0; struct page **in_pages = NULL, **out_pages = NULL; struct virtio_chan *chan = client->trans; struct scatterlist *sgs[4]; size_t offs = 0; int need_drop = 0; int kicked = 0; p9_debug(P9_DEBUG_TRANS, "virtio request\n"); if (uodata) { __le32 sz; int n = p9_get_mapped_pages(chan, &out_pages, uodata, outlen, &offs, &need_drop); if (n < 0) { err = n; goto err_out; } out_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE); if (n != outlen) { __le32 v = cpu_to_le32(n); memcpy(&req->tc.sdata[req->tc.size - 4], &v, 4); outlen = n; } /* The size field of the message must include the length of the * header and the length of the data. We didn't actually know * the length of the data until this point so add it in now. */ sz = cpu_to_le32(req->tc.size + outlen); memcpy(&req->tc.sdata[0], &sz, sizeof(sz)); } else if (uidata) { int n = p9_get_mapped_pages(chan, &in_pages, uidata, inlen, &offs, &need_drop); if (n < 0) { err = n; goto err_out; } in_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE); if (n != inlen) { __le32 v = cpu_to_le32(n); memcpy(&req->tc.sdata[req->tc.size - 4], &v, 4); inlen = n; } } WRITE_ONCE(req->status, REQ_STATUS_SENT); req_retry_pinned: spin_lock_irqsave(&chan->lock, flags); out_sgs = in_sgs = 0; /* out data */ out = pack_sg_list(chan->sg, 0, VIRTQUEUE_NUM, req->tc.sdata, req->tc.size); if (out) sgs[out_sgs++] = chan->sg; if (out_pages) { sgs[out_sgs++] = chan->sg + out; out += pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM, out_pages, out_nr_pages, offs, outlen); } /* * Take care of in data * For example TREAD have 11. * 11 is the read/write header = PDU Header(7) + IO Size (4). * Arrange in such a way that server places header in the * allocated memory and payload onto the user buffer. */ in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, req->rc.sdata, in_hdr_len); if (in) sgs[out_sgs + in_sgs++] = chan->sg + out; if (in_pages) { sgs[out_sgs + in_sgs++] = chan->sg + out + in; pack_sg_list_p(chan->sg, out + in, VIRTQUEUE_NUM, in_pages, in_nr_pages, offs, inlen); } BUG_ON(out_sgs + in_sgs > ARRAY_SIZE(sgs)); err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req, GFP_ATOMIC); if (err < 0) { if (err == -ENOSPC) { chan->ring_bufs_avail = 0; spin_unlock_irqrestore(&chan->lock, flags); err = io_wait_event_killable(*chan->vc_wq, chan->ring_bufs_avail); if (err == -ERESTARTSYS) goto err_out; p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n"); goto req_retry_pinned; } else { spin_unlock_irqrestore(&chan->lock, flags); p9_debug(P9_DEBUG_TRANS, "virtio rpc add_sgs returned failure\n"); err = -EIO; goto err_out; } } virtqueue_kick(chan->vq); spin_unlock_irqrestore(&chan->lock, flags); kicked = 1; p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n"); err = io_wait_event_killable(req->wq, READ_ONCE(req->status) >= REQ_STATUS_RCVD); /* * Make sure our req is coherent with regard to updates in other * threads - echoes to wmb() in the callback */ smp_rmb(); // RERROR needs reply (== error string) in static data if (READ_ONCE(req->status) == REQ_STATUS_RCVD && unlikely(req->rc.sdata[4] == P9_RERROR)) handle_rerror(req, in_hdr_len, offs, in_pages); /* * Non kernel buffers are pinned, unpin them */ err_out: if (need_drop) { if (in_pages) { p9_release_pages(in_pages, in_nr_pages); atomic_sub(in_nr_pages, &vp_pinned); } if (out_pages) { p9_release_pages(out_pages, out_nr_pages); atomic_sub(out_nr_pages, &vp_pinned); } /* wakeup anybody waiting for slots to pin pages */ wake_up(&vp_wq); } kvfree(in_pages); kvfree(out_pages); if (!kicked) { /* reply won't come */ p9_req_put(client, req); } return err; } static ssize_t p9_mount_tag_show(struct device *dev, struct device_attribute *attr, char *buf) { struct virtio_chan *chan; struct virtio_device *vdev; int tag_len; vdev = dev_to_virtio(dev); chan = vdev->priv; tag_len = strlen(chan->tag); memcpy(buf, chan->tag, tag_len + 1); return tag_len + 1; } static DEVICE_ATTR(mount_tag, 0444, p9_mount_tag_show, NULL); /** * p9_virtio_probe - probe for existence of 9P virtio channels * @vdev: virtio device to probe * * This probes for existing virtio channels. * */ static int p9_virtio_probe(struct virtio_device *vdev) { __u16 tag_len; char *tag; int err; struct virtio_chan *chan; if (!vdev->config->get) { dev_err(&vdev->dev, "%s failure: config access disabled\n", __func__); return -EINVAL; } chan = kmalloc_obj(struct virtio_chan); if (!chan) { pr_err("Failed to allocate virtio 9P channel\n"); err = -ENOMEM; goto fail; } chan->vdev = vdev; /* We expect one virtqueue, for requests. */ chan->vq = virtio_find_single_vq(vdev, req_done, "requests"); if (IS_ERR(chan->vq)) { err = PTR_ERR(chan->vq); goto out_free_chan; } chan->vq->vdev->priv = chan; spin_lock_init(&chan->lock); sg_init_table(chan->sg, VIRTQUEUE_NUM); chan->inuse = false; if (virtio_has_feature(vdev, VIRTIO_9P_MOUNT_TAG)) { virtio_cread(vdev, struct virtio_9p_config, tag_len, &tag_len); } else { err = -EINVAL; goto out_free_vq; } tag = kzalloc(tag_len + 1, GFP_KERNEL); if (!tag) { err = -ENOMEM; goto out_free_vq; } virtio_cread_bytes(vdev, offsetof(struct virtio_9p_config, tag), tag, tag_len); chan->tag = tag; err = sysfs_create_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr); if (err) { goto out_free_tag; } chan->vc_wq = kmalloc_obj(wait_queue_head_t); if (!chan->vc_wq) { err = -ENOMEM; goto out_remove_file; } init_waitqueue_head(chan->vc_wq); chan->ring_bufs_avail = 1; /* Ceiling limit to avoid denial of service attacks */ chan->p9_max_pages = nr_free_buffer_pages()/4; virtio_device_ready(vdev); mutex_lock(&virtio_9p_lock); list_add_tail(&chan->chan_list, &virtio_chan_list); mutex_unlock(&virtio_9p_lock); /* Let udev rules use the new mount_tag attribute. */ kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE); return 0; out_remove_file: sysfs_remove_file(&vdev->dev.kobj, &dev_attr_mount_tag.attr); out_free_tag: kfree(tag); out_free_vq: vdev->config->del_vqs(vdev); out_free_chan: kfree(chan); fail: return err; } /** * p9_virtio_create - allocate a new virtio channel * @client: client instance invoking this transport * @fc: the filesystem context * * This sets up a transport channel for 9p communication. Right now * we only match the first available channel, but eventually we could look up * alternate channels by matching devname versus a virtio_config entry. * We use a simple reference count mechanism to ensure that only a single * mount has a channel open at a time. * */ static int p9_virtio_create(struct p9_client *client, struct fs_context *fc) { const char *devname = fc->source; struct virtio_chan *chan; int ret = -ENOENT; int found = 0; if (devname == NULL) return -EINVAL; mutex_lock(&virtio_9p_lock); list_for_each_entry(chan, &virtio_chan_list, chan_list) { if (!strcmp(devname, chan->tag)) { if (!chan->inuse) { chan->inuse = true; found = 1; break; } ret = -EBUSY; } } mutex_unlock(&virtio_9p_lock); if (!found) { pr_err("no channels available for device %s\n", devname); return ret; } client->trans = (void *)chan; client->status = Connected; chan->client = client; return 0; } /** * p9_virtio_remove - clean up resources associated with a virtio device * @vdev: virtio device to remove * */ static void p9_virtio_remove(struct virtio_device *vdev) { struct virtio_chan *chan = vdev->priv; unsigned long warning_time; mutex_lock(&virtio_9p_lock); /* Remove self from list so we don't get new users. */ list_del(&chan->chan_list); warning_time = jiffies; /* Wait for existing users to close. */ while (chan->inuse) { mutex_unlock(&virtio_9p_lock); msleep(250); if (time_after(jiffies, warning_time + 10 * HZ)) { dev_emerg(&vdev->dev, "p9_virtio_remove: waiting for device in use.\n"); warning_time = jiffies; } mutex_lock(&virtio_9p_lock); } mutex_unlock(&virtio_9p_lock); virtio_reset_device(vdev); vdev->config->del_vqs(vdev); sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr); kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE); kfree(chan->tag); kfree(chan->vc_wq); kfree(chan); } static struct virtio_device_id id_table[] = { { VIRTIO_ID_9P, VIRTIO_DEV_ANY_ID }, { 0 }, }; static unsigned int features[] = { VIRTIO_9P_MOUNT_TAG, }; /* The standard "struct lguest_driver": */ static struct virtio_driver p9_virtio_drv = { .feature_table = features, .feature_table_size = ARRAY_SIZE(features), .driver.name = KBUILD_MODNAME, .id_table = id_table, .probe = p9_virtio_probe, .remove = p9_virtio_remove, }; static struct p9_trans_module p9_virtio_trans = { .name = "virtio", .create = p9_virtio_create, .close = p9_virtio_close, .request = p9_virtio_request, .zc_request = p9_virtio_zc_request, .cancel = p9_virtio_cancel, .cancelled = p9_virtio_cancelled, /* * We leave one entry for input and one entry for response * headers. We also skip one more entry to accommodate, address * that are not at page boundary, that can result in an extra * page in zero copy. */ .maxsize = PAGE_SIZE * (VIRTQUEUE_NUM - 3), .pooled_rbuffers = false, .def = true, .supports_vmalloc = false, .owner = THIS_MODULE, }; /* The standard init function */ static int __init p9_virtio_init(void) { int rc; INIT_LIST_HEAD(&virtio_chan_list); v9fs_register_trans(&p9_virtio_trans); rc = register_virtio_driver(&p9_virtio_drv); if (rc) v9fs_unregister_trans(&p9_virtio_trans); return rc; } static void __exit p9_virtio_cleanup(void) { unregister_virtio_driver(&p9_virtio_drv); v9fs_unregister_trans(&p9_virtio_trans); } module_init(p9_virtio_init); module_exit(p9_virtio_cleanup); MODULE_ALIAS_9P("virtio"); MODULE_DEVICE_TABLE(virtio, id_table); MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>"); MODULE_DESCRIPTION("Virtio 9p Transport"); MODULE_LICENSE("GPL"); |
| 104 3 122 122 2 122 122 122 122 2 2 86 87 87 2 2 2 1 86 87 2 2 2 1 1 2 2 1 17 1 3 10 3 6 3 1 1 2 122 121 127 92 92 1 16 15 2 92 127 2 127 7 50 19 32 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 | /* * net/tipc/bcast.c: TIPC broadcast code * * Copyright (c) 2004-2006, 2014-2017, Ericsson AB * Copyright (c) 2004, Intel Corporation. * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include <linux/tipc_config.h> #include "socket.h" #include "msg.h" #include "bcast.h" #include "link.h" #include "name_table.h" #define BCLINK_WIN_DEFAULT 50 /* bcast link window size (default) */ #define BCLINK_WIN_MIN 32 /* bcast minimum link window size */ const char tipc_bclink_name[] = "broadcast-link"; unsigned long sysctl_tipc_bc_retruni __read_mostly; /** * struct tipc_bc_base - base structure for keeping broadcast send state * @link: broadcast send link structure * @inputq: data input queue; will only carry SOCK_WAKEUP messages * @dests: array keeping number of reachable destinations per bearer * @primary_bearer: a bearer having links to all broadcast destinations, if any * @bcast_support: indicates if primary bearer, if any, supports broadcast * @force_bcast: forces broadcast for multicast traffic * @rcast_support: indicates if all peer nodes support replicast * @force_rcast: forces replicast for multicast traffic * @rc_ratio: dest count as percentage of cluster size where send method changes * @bc_threshold: calculated from rc_ratio; if dests > threshold use broadcast */ struct tipc_bc_base { struct tipc_link *link; struct sk_buff_head inputq; int dests[MAX_BEARERS]; int primary_bearer; bool bcast_support; bool force_bcast; bool rcast_support; bool force_rcast; int rc_ratio; int bc_threshold; }; static struct tipc_bc_base *tipc_bc_base(struct net *net) { return tipc_net(net)->bcbase; } /* tipc_bcast_get_mtu(): -get the MTU currently used by broadcast link * Note: the MTU is decremented to give room for a tunnel header, in * case the message needs to be sent as replicast */ int tipc_bcast_get_mtu(struct net *net) { return tipc_link_mss(tipc_bc_sndlink(net)); } void tipc_bcast_toggle_rcast(struct net *net, bool supp) { tipc_bc_base(net)->rcast_support = supp; } static void tipc_bcbase_calc_bc_threshold(struct net *net) { struct tipc_bc_base *bb = tipc_bc_base(net); int cluster_size = tipc_link_bc_peers(tipc_bc_sndlink(net)); bb->bc_threshold = 1 + (cluster_size * bb->rc_ratio / 100); } /* tipc_bcbase_select_primary(): find a bearer with links to all destinations, * if any, and make it primary bearer */ static void tipc_bcbase_select_primary(struct net *net) { struct tipc_bc_base *bb = tipc_bc_base(net); int all_dests = tipc_link_bc_peers(bb->link); int max_win = tipc_link_max_win(bb->link); int min_win = tipc_link_min_win(bb->link); int i, mtu, prim; bb->primary_bearer = INVALID_BEARER_ID; bb->bcast_support = true; if (!all_dests) return; for (i = 0; i < MAX_BEARERS; i++) { if (!bb->dests[i]) continue; mtu = tipc_bearer_mtu(net, i); if (mtu < tipc_link_mtu(bb->link)) { tipc_link_set_mtu(bb->link, mtu); tipc_link_set_queue_limits(bb->link, min_win, max_win); } bb->bcast_support &= tipc_bearer_bcast_support(net, i); if (bb->dests[i] < all_dests) continue; bb->primary_bearer = i; /* Reduce risk that all nodes select same primary */ if ((i ^ tipc_own_addr(net)) & 1) break; } prim = bb->primary_bearer; if (prim != INVALID_BEARER_ID) bb->bcast_support = tipc_bearer_bcast_support(net, prim); } void tipc_bcast_inc_bearer_dst_cnt(struct net *net, int bearer_id) { struct tipc_bc_base *bb = tipc_bc_base(net); tipc_bcast_lock(net); bb->dests[bearer_id]++; tipc_bcbase_select_primary(net); tipc_bcast_unlock(net); } void tipc_bcast_dec_bearer_dst_cnt(struct net *net, int bearer_id) { struct tipc_bc_base *bb = tipc_bc_base(net); tipc_bcast_lock(net); bb->dests[bearer_id]--; tipc_bcbase_select_primary(net); tipc_bcast_unlock(net); } /* tipc_bcbase_xmit - broadcast a packet queue across one or more bearers * * Note that number of reachable destinations, as indicated in the dests[] * array, may transitionally differ from the number of destinations indicated * in each sent buffer. We can sustain this. Excess destination nodes will * drop and never acknowledge the unexpected packets, and missing destinations * will either require retransmission (if they are just about to be added to * the bearer), or be removed from the buffer's 'ackers' counter (if they * just went down) */ static void tipc_bcbase_xmit(struct net *net, struct sk_buff_head *xmitq) { int bearer_id; struct tipc_bc_base *bb = tipc_bc_base(net); struct sk_buff *skb, *_skb; struct sk_buff_head _xmitq; if (skb_queue_empty(xmitq)) return; /* The typical case: at least one bearer has links to all nodes */ bearer_id = bb->primary_bearer; if (bearer_id >= 0) { tipc_bearer_bc_xmit(net, bearer_id, xmitq); return; } /* We have to transmit across all bearers */ __skb_queue_head_init(&_xmitq); for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { if (!bb->dests[bearer_id]) continue; skb_queue_walk(xmitq, skb) { _skb = pskb_copy_for_clone(skb, GFP_ATOMIC); if (!_skb) break; __skb_queue_tail(&_xmitq, _skb); } tipc_bearer_bc_xmit(net, bearer_id, &_xmitq); } __skb_queue_purge(xmitq); __skb_queue_purge(&_xmitq); } static void tipc_bcast_select_xmit_method(struct net *net, int dests, struct tipc_mc_method *method) { struct tipc_bc_base *bb = tipc_bc_base(net); unsigned long exp = method->expires; /* Broadcast supported by used bearer/bearers? */ if (!bb->bcast_support) { method->rcast = true; return; } /* Any destinations which don't support replicast ? */ if (!bb->rcast_support) { method->rcast = false; return; } /* Can current method be changed ? */ method->expires = jiffies + TIPC_METHOD_EXPIRE; if (method->mandatory) return; if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL) && time_before(jiffies, exp)) return; /* Configuration as force 'broadcast' method */ if (bb->force_bcast) { method->rcast = false; return; } /* Configuration as force 'replicast' method */ if (bb->force_rcast) { method->rcast = true; return; } /* Configuration as 'autoselect' or default method */ /* Determine method to use now */ method->rcast = dests <= bb->bc_threshold; } /* tipc_bcast_xmit - broadcast the buffer chain to all external nodes * @net: the applicable net namespace * @pkts: chain of buffers containing message * @cong_link_cnt: set to 1 if broadcast link is congested, otherwise 0 * Consumes the buffer chain. * Returns 0 if success, otherwise errno: -EHOSTUNREACH,-EMSGSIZE */ int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts, u16 *cong_link_cnt) { struct tipc_link *l = tipc_bc_sndlink(net); struct sk_buff_head xmitq; int rc = 0; __skb_queue_head_init(&xmitq); tipc_bcast_lock(net); if (tipc_link_bc_peers(l)) rc = tipc_link_xmit(l, pkts, &xmitq); tipc_bcast_unlock(net); tipc_bcbase_xmit(net, &xmitq); __skb_queue_purge(pkts); if (rc == -ELINKCONG) { *cong_link_cnt = 1; rc = 0; } return rc; } /* tipc_rcast_xmit - replicate and send a message to given destination nodes * @net: the applicable net namespace * @pkts: chain of buffers containing message * @dests: list of destination nodes * @cong_link_cnt: returns number of congested links * @cong_links: returns identities of congested links * Returns 0 if success, otherwise errno */ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, struct tipc_nlist *dests, u16 *cong_link_cnt) { struct tipc_dest *dst, *tmp; struct sk_buff_head _pkts; u32 dnode, selector; selector = msg_link_selector(buf_msg(skb_peek(pkts))); __skb_queue_head_init(&_pkts); list_for_each_entry_safe(dst, tmp, &dests->list, list) { dnode = dst->node; if (!tipc_msg_pskb_copy(dnode, pkts, &_pkts)) return -ENOMEM; /* Any other return value than -ELINKCONG is ignored */ if (tipc_node_xmit(net, &_pkts, dnode, selector) == -ELINKCONG) (*cong_link_cnt)++; } return 0; } /* tipc_mcast_send_sync - deliver a dummy message with SYN bit * @net: the applicable net namespace * @skb: socket buffer to copy * @method: send method to be used * @dests: destination nodes for message. * Returns 0 if success, otherwise errno */ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, struct tipc_mc_method *method, struct tipc_nlist *dests) { struct tipc_msg *hdr, *_hdr; struct sk_buff_head tmpq; u16 cong_link_cnt = 0; struct sk_buff *_skb; int rc = 0; /* Is a cluster supporting with new capabilities ? */ if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL)) return 0; hdr = buf_msg(skb); if (msg_user(hdr) == MSG_FRAGMENTER) hdr = msg_inner_hdr(hdr); if (msg_type(hdr) != TIPC_MCAST_MSG) return 0; /* Allocate dummy message */ _skb = tipc_buf_acquire(MCAST_H_SIZE, GFP_KERNEL); if (!_skb) return -ENOMEM; /* Preparing for 'synching' header */ msg_set_syn(hdr, 1); /* Copy skb's header into a dummy header */ skb_copy_to_linear_data(_skb, hdr, MCAST_H_SIZE); skb_orphan(_skb); /* Reverse method for dummy message */ _hdr = buf_msg(_skb); msg_set_size(_hdr, MCAST_H_SIZE); msg_set_is_rcast(_hdr, !msg_is_rcast(hdr)); msg_set_errcode(_hdr, TIPC_ERR_NO_PORT); __skb_queue_head_init(&tmpq); __skb_queue_tail(&tmpq, _skb); if (method->rcast) rc = tipc_bcast_xmit(net, &tmpq, &cong_link_cnt); else rc = tipc_rcast_xmit(net, &tmpq, dests, &cong_link_cnt); /* This queue should normally be empty by now */ __skb_queue_purge(&tmpq); return rc; } /* tipc_mcast_xmit - deliver message to indicated destination nodes * and to identified node local sockets * @net: the applicable net namespace * @pkts: chain of buffers containing message * @method: send method to be used * @dests: destination nodes for message. * @cong_link_cnt: returns number of encountered congested destination links * Consumes buffer chain. * Returns 0 if success, otherwise errno */ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, struct tipc_mc_method *method, struct tipc_nlist *dests, u16 *cong_link_cnt) { struct sk_buff_head inputq, localq; bool rcast = method->rcast; struct tipc_msg *hdr; struct sk_buff *skb; int rc = 0; skb_queue_head_init(&inputq); __skb_queue_head_init(&localq); /* Clone packets before they are consumed by next call */ if (dests->local && !tipc_msg_reassemble(pkts, &localq)) { rc = -ENOMEM; goto exit; } /* Send according to determined transmit method */ if (dests->remote) { tipc_bcast_select_xmit_method(net, dests->remote, method); skb = skb_peek(pkts); hdr = buf_msg(skb); if (msg_user(hdr) == MSG_FRAGMENTER) hdr = msg_inner_hdr(hdr); msg_set_is_rcast(hdr, method->rcast); /* Switch method ? */ if (rcast != method->rcast) { rc = tipc_mcast_send_sync(net, skb, method, dests); if (unlikely(rc)) { pr_err("Unable to send SYN: method %d, rc %d\n", rcast, rc); goto exit; } } if (method->rcast) rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt); else rc = tipc_bcast_xmit(net, pkts, cong_link_cnt); } if (dests->local) { tipc_loopback_trace(net, &localq); tipc_sk_mcast_rcv(net, &localq, &inputq); } exit: /* This queue should normally be empty by now */ __skb_queue_purge(pkts); return rc; } /* tipc_bcast_rcv - receive a broadcast packet, and deliver to rcv link * * RCU is locked, no other locks set */ int tipc_bcast_rcv(struct net *net, struct tipc_link *l, struct sk_buff *skb) { struct tipc_msg *hdr = buf_msg(skb); struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq; struct sk_buff_head xmitq; int rc; __skb_queue_head_init(&xmitq); if (msg_mc_netid(hdr) != tipc_netid(net) || !tipc_link_is_up(l)) { kfree_skb(skb); return 0; } tipc_bcast_lock(net); if (msg_user(hdr) == BCAST_PROTOCOL) rc = tipc_link_bc_nack_rcv(l, skb, &xmitq); else rc = tipc_link_rcv(l, skb, NULL); tipc_bcast_unlock(net); tipc_bcbase_xmit(net, &xmitq); /* Any socket wakeup messages ? */ if (!skb_queue_empty(inputq)) tipc_sk_rcv(net, inputq); return rc; } /* tipc_bcast_ack_rcv - receive and handle a broadcast acknowledge * * RCU is locked, no other locks set */ void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l, struct tipc_msg *hdr) { struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq; u16 acked = msg_bcast_ack(hdr); struct sk_buff_head xmitq; /* Ignore bc acks sent by peer before bcast synch point was received */ if (msg_bc_ack_invalid(hdr)) return; __skb_queue_head_init(&xmitq); tipc_bcast_lock(net); tipc_link_bc_ack_rcv(l, acked, 0, NULL, &xmitq, NULL); tipc_bcast_unlock(net); tipc_bcbase_xmit(net, &xmitq); /* Any socket wakeup messages ? */ if (!skb_queue_empty(inputq)) tipc_sk_rcv(net, inputq); } /* tipc_bcast_synch_rcv - check and update rcv link with peer's send state * * RCU is locked, no other locks set */ int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l, struct tipc_msg *hdr, struct sk_buff_head *retrq, bool *valid) { struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq; struct tipc_gap_ack_blks *ga; struct sk_buff_head xmitq; int rc = 0; u16 glen; __skb_queue_head_init(&xmitq); tipc_bcast_lock(net); if (msg_type(hdr) != STATE_MSG) { tipc_link_bc_init_rcv(l, hdr); } else if (!msg_bc_ack_invalid(hdr)) { glen = tipc_get_gap_ack_blks(&ga, l, hdr, false); if (glen > msg_data_sz(hdr)) { /* Malformed Gap ACK blocks; caller drops the msg */ *valid = false; } else { if (!sysctl_tipc_bc_retruni) retrq = &xmitq; rc = tipc_link_bc_ack_rcv(l, msg_bcast_ack(hdr), msg_bc_gap(hdr), ga, &xmitq, retrq); rc |= tipc_link_bc_sync_rcv(l, hdr, &xmitq); } } tipc_bcast_unlock(net); tipc_bcbase_xmit(net, &xmitq); /* Any socket wakeup messages ? */ if (!skb_queue_empty(inputq)) tipc_sk_rcv(net, inputq); return rc; } /* tipc_bcast_add_peer - add a peer node to broadcast link and bearer * * RCU is locked, node lock is set */ void tipc_bcast_add_peer(struct net *net, struct tipc_link *uc_l, struct sk_buff_head *xmitq) { struct tipc_link *snd_l = tipc_bc_sndlink(net); tipc_bcast_lock(net); tipc_link_add_bc_peer(snd_l, uc_l, xmitq); tipc_bcbase_select_primary(net); tipc_bcbase_calc_bc_threshold(net); tipc_bcast_unlock(net); } /* tipc_bcast_remove_peer - remove a peer node from broadcast link and bearer * * RCU is locked, node lock is set */ void tipc_bcast_remove_peer(struct net *net, struct tipc_link *rcv_l) { struct tipc_link *snd_l = tipc_bc_sndlink(net); struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq; struct sk_buff_head xmitq; __skb_queue_head_init(&xmitq); tipc_bcast_lock(net); tipc_link_remove_bc_peer(snd_l, rcv_l, &xmitq); tipc_bcbase_select_primary(net); tipc_bcbase_calc_bc_threshold(net); tipc_bcast_unlock(net); tipc_bcbase_xmit(net, &xmitq); /* Any socket wakeup messages ? */ if (!skb_queue_empty(inputq)) tipc_sk_rcv(net, inputq); } int tipc_bclink_reset_stats(struct net *net, struct tipc_link *l) { if (!l) return -ENOPROTOOPT; tipc_bcast_lock(net); tipc_link_reset_stats(l); tipc_bcast_unlock(net); return 0; } static int tipc_bc_link_set_queue_limits(struct net *net, u32 max_win) { struct tipc_link *l = tipc_bc_sndlink(net); if (!l) return -ENOPROTOOPT; if (max_win < BCLINK_WIN_MIN) max_win = BCLINK_WIN_MIN; if (max_win > TIPC_MAX_LINK_WIN) return -EINVAL; tipc_bcast_lock(net); tipc_link_set_queue_limits(l, tipc_link_min_win(l), max_win); tipc_bcast_unlock(net); return 0; } static int tipc_bc_link_set_broadcast_mode(struct net *net, u32 bc_mode) { struct tipc_bc_base *bb = tipc_bc_base(net); switch (bc_mode) { case BCLINK_MODE_BCAST: if (!bb->bcast_support) return -ENOPROTOOPT; bb->force_bcast = true; bb->force_rcast = false; break; case BCLINK_MODE_RCAST: if (!bb->rcast_support) return -ENOPROTOOPT; bb->force_bcast = false; bb->force_rcast = true; break; case BCLINK_MODE_SEL: if (!bb->bcast_support || !bb->rcast_support) return -ENOPROTOOPT; bb->force_bcast = false; bb->force_rcast = false; break; default: return -EINVAL; } return 0; } static int tipc_bc_link_set_broadcast_ratio(struct net *net, u32 bc_ratio) { struct tipc_bc_base *bb = tipc_bc_base(net); if (!bb->bcast_support || !bb->rcast_support) return -ENOPROTOOPT; if (bc_ratio > 100 || bc_ratio <= 0) return -EINVAL; bb->rc_ratio = bc_ratio; tipc_bcast_lock(net); tipc_bcbase_calc_bc_threshold(net); tipc_bcast_unlock(net); return 0; } int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]) { int err; u32 win; u32 bc_mode; u32 bc_ratio; struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; if (!attrs[TIPC_NLA_LINK_PROP]) return -EINVAL; err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_LINK_PROP], props); if (err) return err; if (!props[TIPC_NLA_PROP_WIN] && !props[TIPC_NLA_PROP_BROADCAST] && !props[TIPC_NLA_PROP_BROADCAST_RATIO]) { return -EOPNOTSUPP; } if (props[TIPC_NLA_PROP_BROADCAST]) { bc_mode = nla_get_u32(props[TIPC_NLA_PROP_BROADCAST]); err = tipc_bc_link_set_broadcast_mode(net, bc_mode); } if (!err && props[TIPC_NLA_PROP_BROADCAST_RATIO]) { bc_ratio = nla_get_u32(props[TIPC_NLA_PROP_BROADCAST_RATIO]); err = tipc_bc_link_set_broadcast_ratio(net, bc_ratio); } if (!err && props[TIPC_NLA_PROP_WIN]) { win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); err = tipc_bc_link_set_queue_limits(net, win); } return err; } int tipc_bcast_init(struct net *net) { struct tipc_net *tn = tipc_net(net); struct tipc_bc_base *bb = NULL; struct tipc_link *l = NULL; bb = kzalloc_obj(*bb); if (!bb) goto enomem; tn->bcbase = bb; spin_lock_init(&tipc_net(net)->bclock); if (!tipc_link_bc_create(net, 0, 0, NULL, one_page_mtu, BCLINK_WIN_DEFAULT, BCLINK_WIN_DEFAULT, 0, &bb->inputq, NULL, NULL, &l)) goto enomem; bb->link = l; tn->bcl = l; bb->rc_ratio = 10; bb->rcast_support = true; return 0; enomem: kfree(bb); kfree(l); return -ENOMEM; } void tipc_bcast_stop(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); synchronize_net(); kfree(tn->bcbase); kfree(tn->bcl); } void tipc_nlist_init(struct tipc_nlist *nl, u32 self) { memset(nl, 0, sizeof(*nl)); INIT_LIST_HEAD(&nl->list); nl->self = self; } void tipc_nlist_add(struct tipc_nlist *nl, u32 node) { if (node == nl->self) nl->local = true; else if (tipc_dest_push(&nl->list, node, 0)) nl->remote++; } void tipc_nlist_del(struct tipc_nlist *nl, u32 node) { if (node == nl->self) nl->local = false; else if (tipc_dest_del(&nl->list, node, 0)) nl->remote--; } void tipc_nlist_purge(struct tipc_nlist *nl) { tipc_dest_list_purge(&nl->list); nl->remote = 0; nl->local = false; } u32 tipc_bcast_get_mode(struct net *net) { struct tipc_bc_base *bb = tipc_bc_base(net); if (bb->force_bcast) return BCLINK_MODE_BCAST; if (bb->force_rcast) return BCLINK_MODE_RCAST; if (bb->bcast_support && bb->rcast_support) return BCLINK_MODE_SEL; return 0; } u32 tipc_bcast_get_broadcast_ratio(struct net *net) { struct tipc_bc_base *bb = tipc_bc_base(net); return bb->rc_ratio; } void tipc_mcast_filter_msg(struct net *net, struct sk_buff_head *defq, struct sk_buff_head *inputq) { struct sk_buff *skb, *_skb, *tmp; struct tipc_msg *hdr, *_hdr; bool match = false; u32 node, port; skb = skb_peek(inputq); if (!skb) return; hdr = buf_msg(skb); if (likely(!msg_is_syn(hdr) && skb_queue_empty(defq))) return; node = msg_orignode(hdr); if (node == tipc_own_addr(net)) return; port = msg_origport(hdr); /* Has the twin SYN message already arrived ? */ skb_queue_walk(defq, _skb) { _hdr = buf_msg(_skb); if (msg_orignode(_hdr) != node) continue; if (msg_origport(_hdr) != port) continue; match = true; break; } if (!match) { if (!msg_is_syn(hdr)) return; __skb_dequeue(inputq); __skb_queue_tail(defq, skb); return; } /* Deliver non-SYN message from other link, otherwise queue it */ if (!msg_is_syn(hdr)) { if (msg_is_rcast(hdr) != msg_is_rcast(_hdr)) return; __skb_dequeue(inputq); __skb_queue_tail(defq, skb); return; } /* Queue non-SYN/SYN message from same link */ if (msg_is_rcast(hdr) == msg_is_rcast(_hdr)) { __skb_dequeue(inputq); __skb_queue_tail(defq, skb); return; } /* Matching SYN messages => return the one with data, if any */ __skb_unlink(_skb, defq); if (msg_data_sz(hdr)) { kfree_skb(_skb); } else { __skb_dequeue(inputq); kfree_skb(skb); __skb_queue_tail(inputq, _skb); } /* Deliver subsequent non-SYN messages from same peer */ skb_queue_walk_safe(defq, _skb, tmp) { _hdr = buf_msg(_skb); if (msg_orignode(_hdr) != node) continue; if (msg_origport(_hdr) != port) continue; if (msg_is_syn(_hdr)) break; __skb_unlink(_skb, defq); __skb_queue_tail(inputq, _skb); } } |
| 38769 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CPUFEATURE_H #define _ASM_X86_CPUFEATURE_H #include <asm/processor.h> #if defined(__KERNEL__) && !defined(__ASSEMBLER__) #include <asm/asm.h> #include <linux/bitops.h> #include <asm/alternative.h> #include <asm/cpufeaturemasks.h> enum cpuid_leafs { CPUID_1_EDX = 0, CPUID_8000_0001_EDX, CPUID_8086_0001_EDX, CPUID_LNX_1, CPUID_1_ECX, CPUID_C000_0001_EDX, CPUID_8000_0001_ECX, CPUID_LNX_2, CPUID_LNX_3, CPUID_7_0_EBX, CPUID_D_1_EAX, CPUID_LNX_4, CPUID_7_1_EAX, CPUID_8000_0008_EBX, CPUID_6_EAX, CPUID_8000_000A_EDX, CPUID_7_ECX, CPUID_LNX_6, CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, CPUID_LNX_5, NR_CPUID_WORDS, }; extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; /* * In order to save room, we index into this array by doing * X86_BUG_<name> - NCAPINTS*32. */ extern const char * const x86_bug_flags[NBUGINTS*32]; #define x86_bug_flag(flag) x86_bug_flags[flag] #define test_cpu_cap(c, bit) \ arch_test_bit(bit, (unsigned long *)((c)->x86_capability)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ test_cpu_cap(c, bit)) #define this_cpu_has(bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ x86_this_cpu_test_bit(bit, cpu_info.x86_capability)) /* * This is the default CPU features testing macro to use in code. * * It is for detection of features which need kernel infrastructure to be * used. It may *not* directly test the CPU itself. Use the cpu_has() family * if you want true runtime testing of CPU features, like in hypervisor code * where you are supporting a possible guest feature where host support for it * is not relevant. */ #define cpu_feature_enabled(bit) \ (__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : static_cpu_has(bit)) #define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) #define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability)) extern void setup_clear_cpu_cap(unsigned int bit); extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); void check_cpufeature_deps(struct cpuinfo_x86 *c); #define setup_force_cpu_cap(bit) do { \ \ if (!boot_cpu_has(bit)) \ WARN_ON(alternatives_patched); \ \ set_cpu_cap(&boot_cpu_data, bit); \ set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) /* * Do not use an "m" constraint for [cap_byte] here: gcc doesn't know * that this is only used on a fallback path and will sometimes cause * it to manifest the address of boot_cpu_data in a register, fouling * the mainline (post-initialization) code. */ static __always_inline bool _static_cpu_has(u16 bit) { asm goto(ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]") ".pushsection .altinstr_aux,\"ax\"\n" "6:\n" ANNOTATE_DATA_SPECIAL "\n" " testb %[bitnum], %a[cap_byte]\n" " jnz %l[t_yes]\n" " jmp %l[t_no]\n" ".popsection\n" : : [feature] "i" (bit), [bitnum] "i" (1 << (bit & 7)), [cap_byte] "i" (&((const char *)boot_cpu_data.x86_capability)[bit >> 3]) : : t_yes, t_no); t_yes: return true; t_no: return false; } #define static_cpu_has(bit) \ ( \ __builtin_constant_p(boot_cpu_has(bit)) ? \ boot_cpu_has(bit) : \ _static_cpu_has(bit) \ ) #define cpu_has_bug(c, bit) cpu_has(c, (bit)) #define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) #define static_cpu_has_bug(bit) static_cpu_has((bit)) #define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit)) #define boot_cpu_set_bug(bit) set_cpu_cap(&boot_cpu_data, (bit)) #define MAX_CPU_FEATURES (NCAPINTS * 32) #define cpu_have_feature boot_cpu_has #define CPU_FEATURE_TYPEFMT "x86,ven%04Xfam%04Xmod%04X" #define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \ boot_cpu_data.x86_model #endif /* defined(__KERNEL__) && !defined(__ASSEMBLER__) */ #endif /* _ASM_X86_CPUFEATURE_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* Kernel module to match packet length. */ /* (C) 1999-2001 James Morris <jmorros@intercode.com.au> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ipv6.h> #include <net/ip.h> #include <linux/netfilter/xt_length.h> #include <linux/netfilter/x_tables.h> MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); MODULE_DESCRIPTION("Xtables: Packet length (Layer3,4,5) match"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_length"); MODULE_ALIAS("ip6t_length"); static bool length_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_length_info *info = par->matchinfo; u32 pktlen = skb_ip_totlen(skb); return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; } static bool length_mt6(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_length_info *info = par->matchinfo; u32 pktlen = skb->len; return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; } static struct xt_match length_mt_reg[] __read_mostly = { { .name = "length", .family = NFPROTO_IPV4, .match = length_mt, .matchsize = sizeof(struct xt_length_info), .me = THIS_MODULE, }, { .name = "length", .family = NFPROTO_IPV6, .match = length_mt6, .matchsize = sizeof(struct xt_length_info), .me = THIS_MODULE, }, }; static int __init length_mt_init(void) { return xt_register_matches(length_mt_reg, ARRAY_SIZE(length_mt_reg)); } static void __exit length_mt_exit(void) { xt_unregister_matches(length_mt_reg, ARRAY_SIZE(length_mt_reg)); } module_init(length_mt_init); module_exit(length_mt_exit); |
| 2 3 5 5 25 12 17 2 3 2 1 1 8 25 34 1 25 10 5 5 1 5 5 5 5 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/acct.c * * BSD Process Accounting for Linux * * Author: Marco van Wieringen <mvw@planets.elm.net> * * Some code based on ideas and code from: * Thomas K. Dyas <tdyas@eden.rutgers.edu> * * This file implements BSD-style process accounting. Whenever any * process exits, an accounting record of type "struct acct" is * written to the file specified with the acct() system call. It is * up to user-level programs to do useful things with the accounting * log. The kernel just provides the raw accounting information. * * (C) Copyright 1995 - 1997 Marco van Wieringen - ELM Consultancy B.V. * * Plugged two leaks. 1) It didn't return acct_file into the free_filps if * the file happened to be read-only. 2) If the accounting was suspended * due to the lack of space it happily allowed to reopen it and completely * lost the old acct_file. 3/10/98, Al Viro. * * Now we silently close acct_file on attempt to reopen. Cleaned sys_acct(). * XTerms and EMACS are manifestations of pure evil. 21/10/98, AV. * * Fixed a nasty interaction with sys_umount(). If the accounting * was suspeneded we failed to stop it on umount(). Messy. * Another one: remount to readonly didn't stop accounting. * Question: what should we do if we have CAP_SYS_ADMIN but not * CAP_SYS_PACCT? Current code does the following: umount returns -EBUSY * unless we are messing with the root. In that case we are getting a * real mess with do_remount_sb(). 9/11/98, AV. * * Fixed a bunch of races (and pair of leaks). Probably not the best way, * but this one obviously doesn't introduce deadlocks. Later. BTW, found * one race (and leak) in BSD implementation. * OK, that's better. ANOTHER race and leak in BSD variant. There always * is one more bug... 10/11/98, AV. * * Oh, fsck... Oopsable SMP race in do_process_acct() - we must hold * ->mmap_lock to walk the vma list of current->mm. Nasty, since it leaks * a struct file opened for write. Fixed. 2/6/2000, AV. */ #include <linux/slab.h> #include <linux/acct.h> #include <linux/capability.h> #include <linux/tty.h> #include <linux/statfs.h> #include <linux/jiffies.h> #include <linux/syscalls.h> #include <linux/namei.h> #include <linux/sched/cputime.h> #include <asm/div64.h> #include <linux/pid_namespace.h> #include <linux/fs_pin.h> /* * These constants control the amount of freespace that suspend and * resume the process accounting system, and the time delay between * each check. * Turned into sysctl-controllable parameters. AV, 12/11/98 */ static int acct_parm[3] = {4, 2, 30}; #define RESUME (acct_parm[0]) /* >foo% free space - resume */ #define SUSPEND (acct_parm[1]) /* <foo% free space - suspend */ #define ACCT_TIMEOUT (acct_parm[2]) /* foo second timeout between checks */ #ifdef CONFIG_SYSCTL static const struct ctl_table kern_acct_table[] = { { .procname = "acct", .data = &acct_parm, .maxlen = 3*sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static __init int kernel_acct_sysctls_init(void) { register_sysctl_init("kernel", kern_acct_table); return 0; } late_initcall(kernel_acct_sysctls_init); #endif /* CONFIG_SYSCTL */ /* * External references and all of the globals. */ struct bsd_acct_struct { struct fs_pin pin; atomic_long_t count; struct rcu_head rcu; struct mutex lock; bool active; bool check_space; unsigned long needcheck; struct file *file; struct pid_namespace *ns; struct work_struct work; struct completion done; acct_t ac; }; static void fill_ac(struct bsd_acct_struct *acct); static void acct_write_process(struct bsd_acct_struct *acct); /* * Check the amount of free space and suspend/resume accordingly. */ static bool check_free_space(struct bsd_acct_struct *acct) { struct kstatfs sbuf; if (!acct->check_space) return acct->active; /* May block */ if (vfs_statfs(&acct->file->f_path, &sbuf)) return acct->active; if (acct->active) { u64 suspend = sbuf.f_blocks * SUSPEND; do_div(suspend, 100); if (sbuf.f_bavail <= suspend) { acct->active = false; pr_info("Process accounting paused\n"); } } else { u64 resume = sbuf.f_blocks * RESUME; do_div(resume, 100); if (sbuf.f_bavail >= resume) { acct->active = true; pr_info("Process accounting resumed\n"); } } acct->needcheck = jiffies + ACCT_TIMEOUT*HZ; return acct->active; } static void acct_put(struct bsd_acct_struct *p) { if (atomic_long_dec_and_test(&p->count)) kfree_rcu(p, rcu); } static inline struct bsd_acct_struct *to_acct(struct fs_pin *p) { return p ? container_of(p, struct bsd_acct_struct, pin) : NULL; } static struct bsd_acct_struct *acct_get(struct pid_namespace *ns) { struct bsd_acct_struct *res; again: smp_rmb(); rcu_read_lock(); res = to_acct(READ_ONCE(ns->bacct)); if (!res) { rcu_read_unlock(); return NULL; } if (!atomic_long_inc_not_zero(&res->count)) { rcu_read_unlock(); cpu_relax(); goto again; } rcu_read_unlock(); mutex_lock(&res->lock); if (res != to_acct(READ_ONCE(ns->bacct))) { mutex_unlock(&res->lock); acct_put(res); goto again; } return res; } static void acct_pin_kill(struct fs_pin *pin) { struct bsd_acct_struct *acct = to_acct(pin); mutex_lock(&acct->lock); /* * Fill the accounting struct with the exiting task's info * before punting to the workqueue. */ fill_ac(acct); schedule_work(&acct->work); wait_for_completion(&acct->done); cmpxchg(&acct->ns->bacct, pin, NULL); mutex_unlock(&acct->lock); pin_remove(pin); acct_put(acct); } static void close_work(struct work_struct *work) { struct bsd_acct_struct *acct = container_of(work, struct bsd_acct_struct, work); struct file *file = acct->file; /* We were fired by acct_pin_kill() which holds acct->lock. */ acct_write_process(acct); if (file->f_op->flush) file->f_op->flush(file, NULL); __fput_sync(file); complete(&acct->done); } DEFINE_FREE(fput_sync, struct file *, if (!IS_ERR_OR_NULL(_T)) __fput_sync(_T)) static int acct_on(const char __user *name) { /* Difference from BSD - they don't do O_APPEND */ const int open_flags = O_WRONLY|O_APPEND|O_LARGEFILE; struct pid_namespace *ns = task_active_pid_ns(current); struct file *original_file __free(fput) = NULL; // in that order struct path internal __free(path_put) = {}; // in that order struct file *file __free(fput_sync) = NULL; // in that order struct bsd_acct_struct *acct; struct vfsmount *mnt; struct fs_pin *old; CLASS(filename, pathname)(name); original_file = file_open_name(pathname, open_flags, 0); if (IS_ERR(original_file)) return PTR_ERR(original_file); mnt = mnt_clone_internal(&original_file->f_path); if (IS_ERR(mnt)) return PTR_ERR(mnt); internal.mnt = mnt; internal.dentry = dget(mnt->mnt_root); file = dentry_open(&internal, open_flags, current_cred()); if (IS_ERR(file)) return PTR_ERR(file); if (!S_ISREG(file_inode(file)->i_mode)) return -EACCES; /* Exclude kernel internal filesystems. */ if (file_inode(file)->i_sb->s_flags & (SB_NOUSER | SB_KERNMOUNT)) return -EINVAL; /* Exclude procfs and sysfs. */ if (file_inode(file)->i_sb->s_type->fs_flags & FS_USERNS_MOUNT_RESTRICTED) return -EINVAL; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EIO; acct = kzalloc_obj(struct bsd_acct_struct); if (!acct) return -ENOMEM; atomic_long_set(&acct->count, 1); init_fs_pin(&acct->pin, acct_pin_kill); acct->file = no_free_ptr(file); acct->needcheck = jiffies; acct->ns = ns; mutex_init(&acct->lock); INIT_WORK(&acct->work, close_work); init_completion(&acct->done); mutex_lock_nested(&acct->lock, 1); /* nobody has seen it yet */ pin_insert(&acct->pin, original_file->f_path.mnt); rcu_read_lock(); old = xchg(&ns->bacct, &acct->pin); mutex_unlock(&acct->lock); pin_kill(old); return 0; } static DEFINE_MUTEX(acct_on_mutex); /** * sys_acct - enable/disable process accounting * @name: file name for accounting records or NULL to shutdown accounting * * sys_acct() is the only system call needed to implement process * accounting. It takes the name of the file where accounting records * should be written. If the filename is NULL, accounting will be * shutdown. * * Returns: 0 for success or negative errno values for failure. */ SYSCALL_DEFINE1(acct, const char __user *, name) { int error = 0; if (!capable(CAP_SYS_PACCT)) return -EPERM; if (name) { mutex_lock(&acct_on_mutex); error = acct_on(name); mutex_unlock(&acct_on_mutex); } else { rcu_read_lock(); pin_kill(task_active_pid_ns(current)->bacct); } return error; } void acct_exit_ns(struct pid_namespace *ns) { rcu_read_lock(); pin_kill(ns->bacct); } /* * encode an u64 into a comp_t * * This routine has been adopted from the encode_comp_t() function in * the kern_acct.c file of the FreeBSD operating system. The encoding * is a 13-bit fraction with a 3-bit (base 8) exponent. */ #define MANTSIZE 13 /* 13 bit mantissa. */ #define EXPSIZE 3 /* Base 8 (3 bit) exponent. */ #define MAXFRACT ((1 << MANTSIZE) - 1) /* Maximum fractional value. */ static comp_t encode_comp_t(u64 value) { int exp, rnd; exp = rnd = 0; while (value > MAXFRACT) { rnd = value & (1 << (EXPSIZE - 1)); /* Round up? */ value >>= EXPSIZE; /* Base 8 exponent == 3 bit shift. */ exp++; } /* * If we need to round up, do it (and handle overflow correctly). */ if (rnd && (++value > MAXFRACT)) { value >>= EXPSIZE; exp++; } if (exp > (((comp_t) ~0U) >> MANTSIZE)) return (comp_t) ~0U; /* * Clean it up and polish it off. */ exp <<= MANTSIZE; /* Shift the exponent into place */ exp += value; /* and add on the mantissa. */ return exp; } #if ACCT_VERSION == 1 || ACCT_VERSION == 2 /* * encode an u64 into a comp2_t (24 bits) * * Format: 5 bit base 2 exponent, 20 bits mantissa. * The leading bit of the mantissa is not stored, but implied for * non-zero exponents. * Largest encodable value is 50 bits. */ #define MANTSIZE2 20 /* 20 bit mantissa. */ #define EXPSIZE2 5 /* 5 bit base 2 exponent. */ #define MAXFRACT2 ((1ul << MANTSIZE2) - 1) /* Maximum fractional value. */ #define MAXEXP2 ((1 << EXPSIZE2) - 1) /* Maximum exponent. */ static comp2_t encode_comp2_t(u64 value) { int exp, rnd; exp = (value > (MAXFRACT2>>1)); rnd = 0; while (value > MAXFRACT2) { rnd = value & 1; value >>= 1; exp++; } /* * If we need to round up, do it (and handle overflow correctly). */ if (rnd && (++value > MAXFRACT2)) { value >>= 1; exp++; } if (exp > MAXEXP2) { /* Overflow. Return largest representable number instead. */ return (1ul << (MANTSIZE2+EXPSIZE2-1)) - 1; } else { return (value & (MAXFRACT2>>1)) | (exp << (MANTSIZE2-1)); } } #elif ACCT_VERSION == 3 /* * encode an u64 into a 32 bit IEEE float */ static u32 encode_float(u64 value) { unsigned exp = 190; unsigned u; if (value == 0) return 0; while ((s64)value > 0) { value <<= 1; exp--; } u = (u32)(value >> 40) & 0x7fffffu; return u | (exp << 23); } #endif /* * Write an accounting entry for an exiting process * * The acct_process() call is the workhorse of the process * accounting system. The struct acct is built here and then written * into the accounting file. This function should only be called from * do_exit() or when switching to a different output file. */ static void fill_ac(struct bsd_acct_struct *acct) { struct pacct_struct *pacct = ¤t->signal->pacct; struct file *file = acct->file; acct_t *ac = &acct->ac; u64 elapsed, run_time; time64_t btime; struct tty_struct *tty; lockdep_assert_held(&acct->lock); if (time_is_after_jiffies(acct->needcheck)) { acct->check_space = false; /* Don't fill in @ac if nothing will be written. */ if (!acct->active) return; } else { acct->check_space = true; } /* * Fill the accounting struct with the needed info as recorded * by the different kernel functions. */ memset(ac, 0, sizeof(acct_t)); ac->ac_version = ACCT_VERSION | ACCT_BYTEORDER; strscpy(ac->ac_comm, current->comm, sizeof(ac->ac_comm)); /* calculate run_time in nsec*/ run_time = ktime_get_ns(); run_time -= current->group_leader->start_time; /* convert nsec -> AHZ */ elapsed = nsec_to_AHZ(run_time); #if ACCT_VERSION == 3 ac->ac_etime = encode_float(elapsed); #else ac->ac_etime = encode_comp_t(elapsed < (unsigned long) -1l ? (unsigned long) elapsed : (unsigned long) -1l); #endif #if ACCT_VERSION == 1 || ACCT_VERSION == 2 { /* new enlarged etime field */ comp2_t etime = encode_comp2_t(elapsed); ac->ac_etime_hi = etime >> 16; ac->ac_etime_lo = (u16) etime; } #endif do_div(elapsed, AHZ); btime = ktime_get_real_seconds() - elapsed; ac->ac_btime = clamp_t(time64_t, btime, 0, U32_MAX); #if ACCT_VERSION == 2 ac->ac_ahz = AHZ; #endif spin_lock_irq(¤t->sighand->siglock); tty = current->signal->tty; /* Safe as we hold the siglock */ ac->ac_tty = tty ? old_encode_dev(tty_devnum(tty)) : 0; ac->ac_utime = encode_comp_t(nsec_to_AHZ(pacct->ac_utime)); ac->ac_stime = encode_comp_t(nsec_to_AHZ(pacct->ac_stime)); ac->ac_flag = pacct->ac_flag; ac->ac_mem = encode_comp_t(pacct->ac_mem); ac->ac_minflt = encode_comp_t(pacct->ac_minflt); ac->ac_majflt = encode_comp_t(pacct->ac_majflt); ac->ac_exitcode = pacct->ac_exitcode; spin_unlock_irq(¤t->sighand->siglock); /* we really need to bite the bullet and change layout */ ac->ac_uid = from_kuid_munged(file->f_cred->user_ns, current_uid()); ac->ac_gid = from_kgid_munged(file->f_cred->user_ns, current_gid()); #if ACCT_VERSION == 1 || ACCT_VERSION == 2 /* backward-compatible 16 bit fields */ ac->ac_uid16 = ac->ac_uid; ac->ac_gid16 = ac->ac_gid; #elif ACCT_VERSION == 3 { struct pid_namespace *ns = acct->ns; ac->ac_pid = task_tgid_nr_ns(current, ns); rcu_read_lock(); ac->ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), ns); rcu_read_unlock(); } #endif } static void acct_write_process(struct bsd_acct_struct *acct) { struct file *file = acct->file; acct_t *ac = &acct->ac; /* Perform file operations on behalf of whoever enabled accounting */ scoped_with_creds(file->f_cred) { /* * First check to see if there is enough free_space to continue * the process accounting system. Then get freeze protection. If * the fs is frozen, just skip the write as we could deadlock * the system otherwise. */ if (check_free_space(acct) && file_start_write_trylock(file)) { /* it's been opened O_APPEND, so position is irrelevant */ loff_t pos = 0; __kernel_write(file, ac, sizeof(acct_t), &pos); file_end_write(file); } } } static void do_acct_process(struct bsd_acct_struct *acct) { unsigned long flim; /* Accounting records are not subject to resource limits. */ flim = rlimit(RLIMIT_FSIZE); current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; fill_ac(acct); acct_write_process(acct); current->signal->rlim[RLIMIT_FSIZE].rlim_cur = flim; } /** * acct_collect - collect accounting information into pacct_struct * @exitcode: task exit code * @group_dead: not 0, if this thread is the last one in the process. */ void acct_collect(long exitcode, int group_dead) { struct pacct_struct *pacct = ¤t->signal->pacct; u64 utime, stime; unsigned long vsize = 0; if (group_dead && current->mm) { struct mm_struct *mm = current->mm; VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; mmap_read_lock(mm); for_each_vma(vmi, vma) vsize += vma->vm_end - vma->vm_start; mmap_read_unlock(mm); } spin_lock_irq(¤t->sighand->siglock); if (group_dead) pacct->ac_mem = vsize / 1024; if (thread_group_leader(current)) { pacct->ac_exitcode = exitcode; if (current->flags & PF_FORKNOEXEC) pacct->ac_flag |= AFORK; } if (current->flags & PF_SUPERPRIV) pacct->ac_flag |= ASU; if (current->flags & PF_DUMPCORE) pacct->ac_flag |= ACORE; if (current->flags & PF_SIGNALED) pacct->ac_flag |= AXSIG; task_cputime(current, &utime, &stime); pacct->ac_utime += utime; pacct->ac_stime += stime; pacct->ac_minflt += current->min_flt; pacct->ac_majflt += current->maj_flt; spin_unlock_irq(¤t->sighand->siglock); } static void slow_acct_process(struct pid_namespace *ns) { for ( ; ns; ns = ns->parent) { struct bsd_acct_struct *acct = acct_get(ns); if (acct) { do_acct_process(acct); mutex_unlock(&acct->lock); acct_put(acct); } } } /** * acct_process - handles process accounting for an exiting task */ void acct_process(void) { struct pid_namespace *ns; /* * This loop is safe lockless, since current is still * alive and holds its namespace, which in turn holds * its parent. */ for (ns = task_active_pid_ns(current); ns != NULL; ns = ns->parent) { if (ns->bacct) break; } if (unlikely(ns)) slow_acct_process(ns); } |
| 2 1 1 10 8 2 11 1 3 1 3 3 1 11 1 3 8 2 2 10 1 1 10 2 2 9 10 10 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/nospec.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "filetable.h" #include "sqpoll.h" #include "fdinfo.h" #include "cancel.h" #include "rsrc.h" #include "opdef.h" #ifdef CONFIG_NET_RX_BUSY_POLL static __cold void common_tracking_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m, const char *tracking_strategy) { seq_puts(m, "NAPI:\tenabled\n"); seq_printf(m, "napi tracking:\t%s\n", tracking_strategy); seq_printf(m, "napi_busy_poll_dt:\t%llu\n", ctx->napi_busy_poll_dt); if (ctx->napi_prefer_busy_poll) seq_puts(m, "napi_prefer_busy_poll:\ttrue\n"); else seq_puts(m, "napi_prefer_busy_poll:\tfalse\n"); } static __cold void napi_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) { unsigned int mode = READ_ONCE(ctx->napi_track_mode); switch (mode) { case IO_URING_NAPI_TRACKING_INACTIVE: seq_puts(m, "NAPI:\tdisabled\n"); break; case IO_URING_NAPI_TRACKING_DYNAMIC: common_tracking_show_fdinfo(ctx, m, "dynamic"); break; case IO_URING_NAPI_TRACKING_STATIC: common_tracking_show_fdinfo(ctx, m, "static"); break; default: seq_printf(m, "NAPI:\tunknown mode (%u)\n", mode); } } #else static inline void napi_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) { } #endif static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) { struct io_overflow_cqe *ocqe; struct io_rings *r = ctx->rings; unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1; unsigned int sq_head = READ_ONCE(r->sq.head); unsigned int sq_tail = READ_ONCE(r->sq.tail); unsigned int cq_head = READ_ONCE(r->cq.head); unsigned int cq_tail = READ_ONCE(r->cq.tail); unsigned int sq_shift = 0; unsigned int cq_entries, sq_entries; int sq_pid = -1, sq_cpu = -1; u64 sq_total_time = 0, sq_work_time = 0; unsigned int i; if (ctx->flags & IORING_SETUP_SQE128) sq_shift = 1; /* * we may get imprecise sqe and cqe info if uring is actively running * since we get cached_sq_head and cached_cq_tail without uring_lock * and sq_tail and cq_head are changed by userspace. But it's ok since * we usually use these info when it is stuck. */ seq_printf(m, "SqMask:\t0x%x\n", sq_mask); seq_printf(m, "SqHead:\t%u\n", sq_head); seq_printf(m, "SqTail:\t%u\n", sq_tail); seq_printf(m, "CachedSqHead:\t%u\n", data_race(ctx->cached_sq_head)); seq_printf(m, "CqMask:\t0x%x\n", cq_mask); seq_printf(m, "CqHead:\t%u\n", cq_head); seq_printf(m, "CqTail:\t%u\n", cq_tail); seq_printf(m, "CachedCqTail:\t%u\n", data_race(ctx->cached_cq_tail)); seq_printf(m, "SQEs:\t%u\n", sq_tail - sq_head); sq_entries = min(sq_tail - sq_head, ctx->sq_entries); for (i = 0; i < sq_entries; i++) { unsigned int entry = i + sq_head; struct io_uring_sqe *sqe; unsigned int sq_idx; bool sqe128 = false; u8 opcode; if (ctx->flags & IORING_SETUP_NO_SQARRAY) sq_idx = entry & sq_mask; else sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]); if (sq_idx > sq_mask) continue; sqe = &ctx->sq_sqes[sq_idx << sq_shift]; opcode = READ_ONCE(sqe->opcode); if (opcode >= IORING_OP_LAST) continue; opcode = array_index_nospec(opcode, IORING_OP_LAST); if (sq_shift) { sqe128 = true; } else if (io_issue_defs[opcode].is_128) { if (!(ctx->flags & IORING_SETUP_SQE_MIXED)) { seq_printf(m, "%5u: invalid sqe, 128B entry on non-mixed sq\n", sq_idx); break; } if (sq_idx == sq_mask) { seq_printf(m, "%5u: corrupted sqe, wrapping 128B entry\n", sq_idx); break; } sq_head++; i++; sqe128 = true; } seq_printf(m, "%5u: opcode:%s, fd:%d, flags:%x, off:%llu, " "addr:0x%llx, rw_flags:0x%x, buf_index:%d " "user_data:%llu", sq_idx, io_uring_get_opcode(opcode), sqe->fd, sqe->flags, (unsigned long long) sqe->off, (unsigned long long) sqe->addr, sqe->rw_flags, sqe->buf_index, sqe->user_data); if (sqe128) { u64 *sqeb = (void *) (sqe + 1); int size = sizeof(struct io_uring_sqe) / sizeof(u64); int j; for (j = 0; j < size; j++) { seq_printf(m, ", e%d:0x%llx", j, (unsigned long long) *sqeb); sqeb++; } } seq_printf(m, "\n"); cond_resched(); } seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head); cq_entries = min(cq_tail - cq_head, ctx->cq_entries); for (i = 0; i < cq_entries; i++) { struct io_uring_cqe *cqe; bool cqe32 = false; cqe = &r->cqes[(cq_head & cq_mask)]; if (cqe->flags & IORING_CQE_F_32 || ctx->flags & IORING_SETUP_CQE32) cqe32 = true; seq_printf(m, "%5u: user_data:%llu, res:%d, flags:%x", cq_head & cq_mask, cqe->user_data, cqe->res, cqe->flags); if (cqe32) seq_printf(m, ", extra1:%llu, extra2:%llu", cqe->big_cqe[0], cqe->big_cqe[1]); seq_printf(m, "\n"); cq_head++; if (cqe32) { cq_head++; i++; } cond_resched(); } if (ctx->flags & IORING_SETUP_SQPOLL) { struct io_sq_data *sq = ctx->sq_data; struct task_struct *tsk; rcu_read_lock(); tsk = rcu_dereference(sq->thread); /* * sq->thread might be NULL if we raced with the sqpoll * thread termination. */ if (tsk) { u64 usec; get_task_struct(tsk); rcu_read_unlock(); usec = io_sq_cpu_usec(tsk); sq_pid = task_pid_nr_ns(tsk, proc_pid_ns(file_inode(m->file)->i_sb)); put_task_struct(tsk); sq_cpu = sq->sq_cpu; sq_total_time = usec; sq_work_time = sq->work_time; } else { rcu_read_unlock(); } } seq_printf(m, "SqThread:\t%d\n", sq_pid); seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu); seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time); seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time); seq_printf(m, "UserFiles:\t%u\n", ctx->file_table.data.nr); for (i = 0; i < ctx->file_table.data.nr; i++) { struct file *f = NULL; if (ctx->file_table.data.nodes[i]) f = io_slot_file(ctx->file_table.data.nodes[i]); if (f) { seq_printf(m, "%5u: ", i); seq_file_path(m, f, " \t\n\\"); seq_puts(m, "\n"); } } seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.nr); for (i = 0; i < ctx->buf_table.nr; i++) { struct io_mapped_ubuf *buf = NULL; if (ctx->buf_table.nodes[i]) buf = ctx->buf_table.nodes[i]->buf; if (buf) seq_printf(m, "%5u: 0x%llx/%zu\n", i, buf->ubuf, buf->len); else seq_printf(m, "%5u: <none>\n", i); } seq_puts(m, "PollList:\n"); for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) { struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i]; struct io_kiocb *req; hlist_for_each_entry(req, &hb->list, hash_node) seq_printf(m, " op=%d, task_works=%d\n", req->opcode, task_work_pending(req->tctx->task)); } seq_puts(m, "CqOverflowList:\n"); spin_lock(&ctx->completion_lock); list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) { struct io_uring_cqe *cqe = &ocqe->cqe; seq_printf(m, " user_data=%llu, res=%d, flags=%x\n", cqe->user_data, cqe->res, cqe->flags); } spin_unlock(&ctx->completion_lock); napi_show_fdinfo(ctx, m); } /* * Caller holds a reference to the file already, we don't need to do * anything else to get an extra reference. */ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) { struct io_ring_ctx *ctx = file->private_data; /* * Avoid ABBA deadlock between the seq lock and the io_uring mutex, * since fdinfo case grabs it in the opposite direction of normal use * cases. */ if (mutex_trylock(&ctx->uring_lock)) { __io_uring_show_fdinfo(ctx, m); mutex_unlock(&ctx->uring_lock); } } |
| 2 87 45 59 137 8021 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TRACE_EVENT_H #define _LINUX_TRACE_EVENT_H #include <linux/ring_buffer.h> #include <linux/trace_seq.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/perf_event.h> #include <linux/tracepoint.h> struct trace_array; struct array_buffer; struct tracer; struct dentry; struct bpf_prog; union bpf_attr; /* Used for event string fields when they are NULL */ #define EVENT_NULL_STR "(null)" const char *trace_print_flags_seq(struct trace_seq *p, const char *delim, unsigned long flags, const struct trace_print_flags *flag_array, size_t flag_array_size); const char *trace_print_symbols_seq(struct trace_seq *p, unsigned long val, const struct trace_print_flags *symbol_array, size_t symbol_array_size); #if BITS_PER_LONG == 32 const char *trace_print_flags_seq_u64(struct trace_seq *p, const char *delim, unsigned long long flags, const struct trace_print_flags_u64 *flag_array, size_t flag_array_size); const char *trace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val, const struct trace_print_flags_u64 *symbol_array, size_t symbol_array_size); #endif struct trace_iterator; struct trace_event; const char *trace_print_bitmask_seq(struct trace_iterator *iter, void *bitmask_ptr, unsigned int bitmask_size); const char *trace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int len, bool concatenate); const char *trace_print_array_seq(struct trace_seq *p, const void *buf, int count, size_t el_size); const char * trace_print_hex_dump_seq(struct trace_seq *p, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii); int trace_raw_output_prep(struct trace_iterator *iter, struct trace_event *event); extern __printf(2, 3) void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...); /* Used to find the offset and length of dynamic fields in trace events */ struct trace_dynamic_info { #ifdef CONFIG_CPU_BIG_ENDIAN u16 len; u16 offset; #else u16 offset; u16 len; #endif } __packed; /* * The trace entry - the most basic unit of tracing. This is what * is printed in the end as a single line in the trace output, such as: * * bash-15816 [01] 235.197585: idle_cpu <- irq_enter */ struct trace_entry { unsigned short type; unsigned char flags; unsigned char preempt_count; int pid; }; #define TRACE_EVENT_TYPE_MAX \ ((1 << (sizeof(((struct trace_entry *)0)->type) * 8)) - 1) /* * Trace iterator - used by printout routines who present trace * results to users and which routines might sleep, etc: */ struct trace_iterator { struct trace_array *tr; struct tracer *trace; struct array_buffer *array_buffer; void *private; int cpu_file; struct mutex mutex; struct ring_buffer_iter **buffer_iter; unsigned long iter_flags; void *temp; /* temp holder */ unsigned int temp_size; char *fmt; /* modified format holder */ unsigned int fmt_size; atomic_t wait_index; /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; cpumask_var_t started; /* Set when the file is closed to prevent new waiters */ bool closed; /* it's true when current open file is snapshot */ bool snapshot; /* The below is zeroed out in pipe_read */ struct trace_seq seq; struct trace_entry *ent; unsigned long lost_events; int leftover; int ent_size; int cpu; u64 ts; loff_t pos; long idx; /* All new field here will be zeroed out in pipe_read */ }; enum trace_iter_flags { TRACE_FILE_LAT_FMT = 1, TRACE_FILE_ANNOTATE = 2, TRACE_FILE_TIME_IN_NS = 4, TRACE_FILE_PAUSE = 8, }; typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter, int flags, struct trace_event *event); struct trace_event_functions { trace_print_func trace; trace_print_func raw; trace_print_func hex; trace_print_func binary; }; struct trace_event { struct hlist_node node; int type; struct trace_event_functions *funcs; }; extern int register_trace_event(struct trace_event *event); extern int unregister_trace_event(struct trace_event *event); /* Return values for print_line callback */ enum print_line_t { TRACE_TYPE_PARTIAL_LINE = 0, /* Retry after flushing the seq */ TRACE_TYPE_HANDLED = 1, TRACE_TYPE_UNHANDLED = 2, /* Relay to other output functions */ TRACE_TYPE_NO_CONSUME = 3 /* Handled but ask to not consume */ }; enum print_line_t trace_handle_return(struct trace_seq *s); static inline void tracing_generic_entry_update(struct trace_entry *entry, unsigned short type, unsigned int trace_ctx) { entry->preempt_count = trace_ctx & 0xff; entry->pid = current->pid; entry->type = type; entry->flags = trace_ctx >> 16; } unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status); enum trace_flag_type { TRACE_FLAG_IRQS_OFF = 0x01, TRACE_FLAG_NEED_RESCHED_LAZY = 0x02, TRACE_FLAG_NEED_RESCHED = 0x04, TRACE_FLAG_HARDIRQ = 0x08, TRACE_FLAG_SOFTIRQ = 0x10, TRACE_FLAG_PREEMPT_RESCHED = 0x20, TRACE_FLAG_NMI = 0x40, TRACE_FLAG_BH_OFF = 0x80, }; static inline unsigned int tracing_gen_ctx_flags(unsigned long irqflags) { unsigned int irq_status = irqs_disabled_flags(irqflags) ? TRACE_FLAG_IRQS_OFF : 0; return tracing_gen_ctx_irq_test(irq_status); } static inline unsigned int tracing_gen_ctx(void) { unsigned long irqflags; local_save_flags(irqflags); return tracing_gen_ctx_flags(irqflags); } static inline unsigned int tracing_gen_ctx_dec(void) { unsigned int trace_ctx; trace_ctx = tracing_gen_ctx(); /* * Subtract one from the preemption counter if preemption is enabled, * see trace_event_buffer_reserve()for details. */ if (IS_ENABLED(CONFIG_PREEMPTION)) trace_ctx--; return trace_ctx; } struct trace_event_file; struct ring_buffer_event * trace_event_buffer_lock_reserve(struct trace_buffer **current_buffer, struct trace_event_file *trace_file, int type, unsigned long len, unsigned int trace_ctx); #define TRACE_RECORD_CMDLINE BIT(0) #define TRACE_RECORD_TGID BIT(1) void tracing_record_taskinfo(struct task_struct *task, int flags); void tracing_record_taskinfo_sched_switch(struct task_struct *prev, struct task_struct *next, int flags); void tracing_record_cmdline(struct task_struct *task); void tracing_record_tgid(struct task_struct *task); int trace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...) __printf(3, 4); struct event_filter; enum trace_reg { TRACE_REG_REGISTER, TRACE_REG_UNREGISTER, #ifdef CONFIG_PERF_EVENTS TRACE_REG_PERF_REGISTER, TRACE_REG_PERF_UNREGISTER, TRACE_REG_PERF_OPEN, TRACE_REG_PERF_CLOSE, /* * These (ADD/DEL) use a 'boolean' return value, where 1 (true) means a * custom action was taken and the default action is not to be * performed. */ TRACE_REG_PERF_ADD, TRACE_REG_PERF_DEL, #endif }; struct trace_event_call; #define TRACE_FUNCTION_TYPE ((const char *)~0UL) struct trace_event_fields { const char *type; union { struct { const char *name; const int size; const int align; const unsigned int is_signed:1; unsigned int needs_test:1; const int filter_type; const int len; }; int (*define_fields)(struct trace_event_call *); }; }; struct trace_event_class { const char *system; void *probe; #ifdef CONFIG_PERF_EVENTS void *perf_probe; #endif int (*reg)(struct trace_event_call *event, enum trace_reg type, void *data); struct trace_event_fields *fields_array; struct list_head *(*get_fields)(struct trace_event_call *); struct list_head fields; int (*raw_init)(struct trace_event_call *); }; extern int trace_event_reg(struct trace_event_call *event, enum trace_reg type, void *data); struct trace_event_buffer { struct trace_buffer *buffer; struct ring_buffer_event *event; struct trace_event_file *trace_file; void *entry; unsigned int trace_ctx; struct pt_regs *regs; }; void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, struct trace_event_file *trace_file, unsigned long len); void trace_event_buffer_commit(struct trace_event_buffer *fbuffer); enum { TRACE_EVENT_FL_CAP_ANY_BIT, TRACE_EVENT_FL_NO_SET_FILTER_BIT, TRACE_EVENT_FL_IGNORE_ENABLE_BIT, TRACE_EVENT_FL_TRACEPOINT_BIT, TRACE_EVENT_FL_DYNAMIC_BIT, TRACE_EVENT_FL_KPROBE_BIT, TRACE_EVENT_FL_UPROBE_BIT, TRACE_EVENT_FL_EPROBE_BIT, TRACE_EVENT_FL_FPROBE_BIT, TRACE_EVENT_FL_CUSTOM_BIT, TRACE_EVENT_FL_TEST_STR_BIT, }; /* * Event flags: * CAP_ANY - Any user can enable for perf * NO_SET_FILTER - Set when filter has error and is to be ignored * IGNORE_ENABLE - For trace internal events, do not enable with debugfs file * TRACEPOINT - Event is a tracepoint * DYNAMIC - Event is a dynamic event (created at run time) * KPROBE - Event is a kprobe * UPROBE - Event is a uprobe * EPROBE - Event is an event probe * FPROBE - Event is an function probe * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) * This is set when the custom event has not been attached * to a tracepoint yet, then it is cleared when it is. * TEST_STR - The event has a "%s" that points to a string outside the event */ enum { TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), TRACE_EVENT_FL_NO_SET_FILTER = (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT), TRACE_EVENT_FL_IGNORE_ENABLE = (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT), TRACE_EVENT_FL_TRACEPOINT = (1 << TRACE_EVENT_FL_TRACEPOINT_BIT), TRACE_EVENT_FL_DYNAMIC = (1 << TRACE_EVENT_FL_DYNAMIC_BIT), TRACE_EVENT_FL_KPROBE = (1 << TRACE_EVENT_FL_KPROBE_BIT), TRACE_EVENT_FL_UPROBE = (1 << TRACE_EVENT_FL_UPROBE_BIT), TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), TRACE_EVENT_FL_FPROBE = (1 << TRACE_EVENT_FL_FPROBE_BIT), TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), TRACE_EVENT_FL_TEST_STR = (1 << TRACE_EVENT_FL_TEST_STR_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) struct trace_event_call { struct list_head list; struct trace_event_class *class; union { const char *name; /* Set TRACE_EVENT_FL_TRACEPOINT flag when using "tp" */ struct tracepoint *tp; }; struct trace_event event; char *print_fmt; /* * Static events can disappear with modules, * where as dynamic ones need their own ref count. */ union { void *module; atomic_t refcnt; }; void *data; /* See the TRACE_EVENT_FL_* flags above */ int flags; /* static flags of different events */ #ifdef CONFIG_PERF_EVENTS int perf_refcount; struct hlist_head __percpu *perf_events; struct bpf_prog_array __rcu *prog_array; int (*perf_perm)(struct trace_event_call *, struct perf_event *); #endif }; #ifdef CONFIG_DYNAMIC_EVENTS bool trace_event_dyn_try_get_ref(struct trace_event_call *call); void trace_event_dyn_put_ref(struct trace_event_call *call); bool trace_event_dyn_busy(struct trace_event_call *call); #else static inline bool trace_event_dyn_try_get_ref(struct trace_event_call *call) { /* Without DYNAMIC_EVENTS configured, nothing should be calling this */ return false; } static inline void trace_event_dyn_put_ref(struct trace_event_call *call) { } static inline bool trace_event_dyn_busy(struct trace_event_call *call) { /* Nothing should call this without DYNAIMIC_EVENTS configured. */ return true; } #endif static inline bool trace_event_try_get_ref(struct trace_event_call *call) { if (call->flags & TRACE_EVENT_FL_DYNAMIC) return trace_event_dyn_try_get_ref(call); else return try_module_get(call->module); } static inline void trace_event_put_ref(struct trace_event_call *call) { if (call->flags & TRACE_EVENT_FL_DYNAMIC) trace_event_dyn_put_ref(call); else module_put(call->module); } #ifdef CONFIG_PERF_EVENTS static inline bool bpf_prog_array_valid(struct trace_event_call *call) { /* * This inline function checks whether call->prog_array * is valid or not. The function is called in various places, * outside rcu_read_lock/unlock, as a heuristic to speed up execution. * * If this function returns true, and later call->prog_array * becomes false inside rcu_read_lock/unlock region, * we bail out then. If this function return false, * there is a risk that we might miss a few events if the checking * were delayed until inside rcu_read_lock/unlock region and * call->prog_array happened to become non-NULL then. * * Here, READ_ONCE() is used instead of rcu_access_pointer(). * rcu_access_pointer() requires the actual definition of * "struct bpf_prog_array" while READ_ONCE() only needs * a declaration of the same type. */ return !!READ_ONCE(call->prog_array); } #endif static inline const char * trace_event_name(struct trace_event_call *call) { if (call->flags & TRACE_EVENT_FL_CUSTOM) return call->name; else if (call->flags & TRACE_EVENT_FL_TRACEPOINT) return call->tp ? call->tp->name : NULL; else return call->name; } static inline struct list_head * trace_get_fields(struct trace_event_call *event_call) { if (!event_call->class->get_fields) return &event_call->class->fields; return event_call->class->get_fields(event_call); } struct trace_subsystem_dir; enum { EVENT_FILE_FL_ENABLED_BIT, EVENT_FILE_FL_RECORDED_CMD_BIT, EVENT_FILE_FL_RECORDED_TGID_BIT, EVENT_FILE_FL_FILTERED_BIT, EVENT_FILE_FL_NO_SET_FILTER_BIT, EVENT_FILE_FL_SOFT_DISABLED_BIT, EVENT_FILE_FL_TRIGGER_MODE_BIT, EVENT_FILE_FL_TRIGGER_COND_BIT, EVENT_FILE_FL_PID_FILTER_BIT, EVENT_FILE_FL_WAS_ENABLED_BIT, EVENT_FILE_FL_FREED_BIT, }; extern struct trace_event_file *trace_get_event_file(const char *instance, const char *system, const char *event); extern void trace_put_event_file(struct trace_event_file *file); #define MAX_DYNEVENT_CMD_LEN (2048) enum dynevent_type { DYNEVENT_TYPE_SYNTH = 1, DYNEVENT_TYPE_KPROBE, DYNEVENT_TYPE_NONE, }; struct dynevent_cmd; typedef int (*dynevent_create_fn_t)(struct dynevent_cmd *cmd); struct dynevent_cmd { struct seq_buf seq; const char *event_name; unsigned int n_fields; enum dynevent_type type; dynevent_create_fn_t run_command; void *private_data; }; extern int dynevent_create(struct dynevent_cmd *cmd); extern int synth_event_delete(const char *name); extern void synth_event_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen); extern int __synth_event_gen_cmd_start(struct dynevent_cmd *cmd, const char *name, struct module *mod, ...); #define synth_event_gen_cmd_start(cmd, name, mod, ...) \ __synth_event_gen_cmd_start(cmd, name, mod, ## __VA_ARGS__, NULL) struct synth_field_desc { const char *type; const char *name; }; extern int synth_event_gen_cmd_array_start(struct dynevent_cmd *cmd, const char *name, struct module *mod, struct synth_field_desc *fields, unsigned int n_fields); extern int synth_event_create(const char *name, struct synth_field_desc *fields, unsigned int n_fields, struct module *mod); extern int synth_event_add_field(struct dynevent_cmd *cmd, const char *type, const char *name); extern int synth_event_add_field_str(struct dynevent_cmd *cmd, const char *type_name); extern int synth_event_add_fields(struct dynevent_cmd *cmd, struct synth_field_desc *fields, unsigned int n_fields); #define synth_event_gen_cmd_end(cmd) \ dynevent_create(cmd) struct synth_event; struct synth_event_trace_state { struct trace_event_buffer fbuffer; struct synth_trace_event *entry; struct trace_buffer *buffer; struct synth_event *event; unsigned int cur_field; unsigned int n_u64; bool disabled; bool add_next; bool add_name; }; extern int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...); extern int synth_event_trace_array(struct trace_event_file *file, u64 *vals, unsigned int n_vals); extern int synth_event_trace_start(struct trace_event_file *file, struct synth_event_trace_state *trace_state); extern int synth_event_add_next_val(u64 val, struct synth_event_trace_state *trace_state); extern int synth_event_add_val(const char *field_name, u64 val, struct synth_event_trace_state *trace_state); extern int synth_event_trace_end(struct synth_event_trace_state *trace_state); extern int kprobe_event_delete(const char *name); extern void kprobe_event_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen); #define kprobe_event_gen_cmd_start(cmd, name, loc, ...) \ __kprobe_event_gen_cmd_start(cmd, false, name, loc, ## __VA_ARGS__, NULL) #define kretprobe_event_gen_cmd_start(cmd, name, loc, ...) \ __kprobe_event_gen_cmd_start(cmd, true, name, loc, ## __VA_ARGS__, NULL) extern int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe, const char *name, const char *loc, ...); #define kprobe_event_add_fields(cmd, ...) \ __kprobe_event_add_fields(cmd, ## __VA_ARGS__, NULL) #define kprobe_event_add_field(cmd, field) \ __kprobe_event_add_fields(cmd, field, NULL) extern int __kprobe_event_add_fields(struct dynevent_cmd *cmd, ...); #define kprobe_event_gen_cmd_end(cmd) \ dynevent_create(cmd) #define kretprobe_event_gen_cmd_end(cmd) \ dynevent_create(cmd) /* * Event file flags: * ENABLED - The event is enabled * RECORDED_CMD - The comms should be recorded at sched_switch * RECORDED_TGID - The tgids should be recorded at sched_switch * FILTERED - The event has a filter attached * NO_SET_FILTER - Set when filter has error and is to be ignored * SOFT_DISABLED - When set, do not trace the event (even though its * tracepoint may be enabled) * TRIGGER_MODE - When set, invoke the triggers associated with the event * TRIGGER_COND - When set, one or more triggers has an associated filter * PID_FILTER - When set, the event is filtered based on pid * WAS_ENABLED - Set when enabled to know to clear trace on module removal * FREED - File descriptor is freed, all fields should be considered invalid */ enum { EVENT_FILE_FL_ENABLED = (1 << EVENT_FILE_FL_ENABLED_BIT), EVENT_FILE_FL_RECORDED_CMD = (1 << EVENT_FILE_FL_RECORDED_CMD_BIT), EVENT_FILE_FL_RECORDED_TGID = (1 << EVENT_FILE_FL_RECORDED_TGID_BIT), EVENT_FILE_FL_FILTERED = (1 << EVENT_FILE_FL_FILTERED_BIT), EVENT_FILE_FL_NO_SET_FILTER = (1 << EVENT_FILE_FL_NO_SET_FILTER_BIT), EVENT_FILE_FL_SOFT_DISABLED = (1 << EVENT_FILE_FL_SOFT_DISABLED_BIT), EVENT_FILE_FL_TRIGGER_MODE = (1 << EVENT_FILE_FL_TRIGGER_MODE_BIT), EVENT_FILE_FL_TRIGGER_COND = (1 << EVENT_FILE_FL_TRIGGER_COND_BIT), EVENT_FILE_FL_PID_FILTER = (1 << EVENT_FILE_FL_PID_FILTER_BIT), EVENT_FILE_FL_WAS_ENABLED = (1 << EVENT_FILE_FL_WAS_ENABLED_BIT), EVENT_FILE_FL_FREED = (1 << EVENT_FILE_FL_FREED_BIT), }; struct trace_event_file { struct list_head list; struct trace_event_call *event_call; struct event_filter __rcu *filter; struct eventfs_inode *ei; struct trace_array *tr; struct trace_subsystem_dir *system; struct list_head triggers; /* * 32 bit flags: * bit 0: enabled * bit 1: enabled cmd record * bit 2: enable/disable with the soft disable bit * bit 3: soft disabled * bit 4: trigger enabled * * Note: The bits must be set atomically to prevent races * from other writers. Reads of flags do not need to be in * sync as they occur in critical sections. But the way flags * is currently used, these changes do not affect the code * except that when a change is made, it may have a slight * delay in propagating the changes to other CPUs due to * caching and such. Which is mostly OK ;-) */ unsigned long flags; refcount_t ref; /* ref count for opened files */ atomic_t sm_ref; /* soft-mode reference counter */ atomic_t tm_ref; /* trigger-mode reference counter */ }; #ifdef CONFIG_HIST_TRIGGERS extern struct irq_work hist_poll_work; extern wait_queue_head_t hist_poll_wq; static inline void hist_poll_wakeup(void) { if (wq_has_sleeper(&hist_poll_wq)) irq_work_queue(&hist_poll_work); } #define hist_poll_wait(file, wait) \ poll_wait(file, &hist_poll_wq, wait) #else static inline void hist_poll_wakeup(void) { } #endif #define __TRACE_EVENT_FLAGS(name, value) \ static int __init trace_init_flags_##name(void) \ { \ event_##name.flags |= value; \ return 0; \ } \ early_initcall(trace_init_flags_##name); #define __TRACE_EVENT_PERF_PERM(name, expr...) \ static int perf_perm_##name(struct trace_event_call *tp_event, \ struct perf_event *p_event) \ { \ return ({ expr; }); \ } \ static int __init trace_init_perf_perm_##name(void) \ { \ event_##name.perf_perm = &perf_perm_##name; \ return 0; \ } \ early_initcall(trace_init_perf_perm_##name); #define PERF_MAX_TRACE_SIZE 8192 #define MAX_FILTER_STR_VAL 256U /* Should handle KSYM_SYMBOL_LEN */ enum event_trigger_type { ETT_NONE = (0), ETT_TRACE_ONOFF = (1 << 0), ETT_SNAPSHOT = (1 << 1), ETT_STACKTRACE = (1 << 2), ETT_EVENT_ENABLE = (1 << 3), ETT_EVENT_HIST = (1 << 4), ETT_HIST_ENABLE = (1 << 5), ETT_EVENT_EPROBE = (1 << 6), }; extern int filter_match_preds(struct event_filter *filter, void *rec); extern enum event_trigger_type event_triggers_call(struct trace_event_file *file, struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event); extern void event_triggers_post_call(struct trace_event_file *file, enum event_trigger_type tt); bool trace_event_ignore_this_pid(struct trace_event_file *trace_file); bool __trace_trigger_soft_disabled(struct trace_event_file *file); /** * trace_trigger_soft_disabled - do triggers and test if soft disabled * @file: The file pointer of the event to test * * If any triggers without filters are attached to this event, they * will be called here. If the event is soft disabled and has no * triggers that require testing the fields, it will return true, * otherwise false. */ static __always_inline bool trace_trigger_soft_disabled(struct trace_event_file *file) { unsigned long eflags = file->flags; if (likely(!(eflags & (EVENT_FILE_FL_TRIGGER_MODE | EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_PID_FILTER)))) return false; if (likely(eflags & EVENT_FILE_FL_TRIGGER_COND)) return false; return __trace_trigger_soft_disabled(file); } #ifdef CONFIG_BPF_EVENTS unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx); unsigned int trace_call_bpf_faultable(struct trace_event_call *call, void *ctx); int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_detach_bpf_prog(struct perf_event *event); int perf_event_query_prog_array(struct perf_event *event, void __user *info); struct bpf_raw_tp_link; int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, u64 *probe_addr, unsigned long *missed); int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr); #else static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { return 1; } static inline unsigned int trace_call_bpf_faultable(struct trace_event_call *call, void *ctx) { return 1; } static inline int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie) { return -EOPNOTSUPP; } static inline void perf_event_detach_bpf_prog(struct perf_event *event) { } static inline int perf_event_query_prog_array(struct perf_event *event, void __user *info) { return -EOPNOTSUPP; } struct bpf_raw_tp_link; static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } static inline struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name) { return NULL; } static inline void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) { } static inline int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, u64 *probe_addr, unsigned long *missed) { return -EOPNOTSUPP; } static inline int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } static inline int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } static inline int bpf_tracing_multi_attach(struct bpf_prog *prog, const union bpf_attr *attr) { return -EOPNOTSUPP; } #endif enum { FILTER_OTHER = 0, FILTER_STATIC_STRING, FILTER_DYN_STRING, FILTER_RDYN_STRING, FILTER_PTR_STRING, FILTER_TRACE_FN, FILTER_CPUMASK, FILTER_COMM, FILTER_CPU, FILTER_STACKTRACE, }; extern int trace_event_raw_init(struct trace_event_call *call); extern int trace_define_field(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type); extern int trace_add_event_call(struct trace_event_call *call); extern int trace_remove_event_call(struct trace_event_call *call); extern int trace_event_get_offsets(struct trace_event_call *call); int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set); int trace_set_clr_event(const char *system, const char *event, int set); int trace_array_set_clr_event(struct trace_array *tr, const char *system, const char *event, bool enable); #ifdef CONFIG_PERF_EVENTS struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); extern int perf_trace_init(struct perf_event *event); extern void perf_trace_destroy(struct perf_event *event); extern int perf_trace_add(struct perf_event *event, int flags); extern void perf_trace_del(struct perf_event *event, int flags); #ifdef CONFIG_KPROBE_EVENTS extern int perf_kprobe_init(struct perf_event *event, bool is_retprobe); extern void perf_kprobe_destroy(struct perf_event *event); extern int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, const char **symbol, u64 *probe_offset, u64 *probe_addr, unsigned long *missed, bool perf_type_tracepoint); #endif #ifdef CONFIG_UPROBE_EVENTS extern int perf_uprobe_init(struct perf_event *event, unsigned long ref_ctr_offset, bool is_retprobe); extern void perf_uprobe_destroy(struct perf_event *event); extern int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, u64 *probe_offset, u64 *probe_addr, bool perf_type_tracepoint); #endif extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); extern void ftrace_profile_free_filter(struct perf_event *event); void perf_trace_buf_update(void *record, u16 type); void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp); int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_free_bpf_prog(struct perf_event *event); void bpf_trace_run1(struct bpf_raw_tp_link *link, u64 arg1); void bpf_trace_run2(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2); void bpf_trace_run3(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3); void bpf_trace_run4(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4); void bpf_trace_run5(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5); void bpf_trace_run6(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6); void bpf_trace_run7(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7); void bpf_trace_run8(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8); void bpf_trace_run9(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9); void bpf_trace_run10(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10); void bpf_trace_run11(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11); void bpf_trace_run12(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11, u64 arg12); void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, struct trace_event_call *call, u64 count, struct pt_regs *regs, struct hlist_head *head, struct task_struct *task); static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type, u64 count, struct pt_regs *regs, void *head, struct task_struct *task) { perf_tp_event(type, count, raw_data, size, regs, head, rctx, task); } #endif #define TRACE_EVENT_STR_MAX 512 /* * gcc warns that you can not use a va_list in an inlined * function. But lets me make it into a macro :-/ */ #define __trace_event_vstr_len(fmt, va) \ ({ \ va_list __ap; \ int __ret; \ \ va_copy(__ap, *(va)); \ __ret = vsnprintf(NULL, 0, fmt, __ap) + 1; \ va_end(__ap); \ \ min(__ret, TRACE_EVENT_STR_MAX); \ }) #endif /* _LINUX_TRACE_EVENT_H */ /* * Note: we keep the TRACE_CUSTOM_EVENT outside the include file ifdef protection. * This is due to the way trace custom events work. If a file includes two * trace event headers under one "CREATE_CUSTOM_TRACE_EVENTS" the first include * will override the TRACE_CUSTOM_EVENT and break the second include. */ #ifndef TRACE_CUSTOM_EVENT #define DECLARE_CUSTOM_EVENT_CLASS(name, proto, args, tstruct, assign, print) #define DEFINE_CUSTOM_EVENT(template, name, proto, args) #define TRACE_CUSTOM_EVENT(name, proto, args, struct, assign, print) #endif /* ifdef TRACE_CUSTOM_EVENT (see note above) */ |
| 36 36 36 36 1 35 36 1 1 36 9 8 38 32 32 31 4 27 27 12 2 8 10 2 2 6 7 1 8 2 6 2 2 33 1 1 23 1 6 6 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_red.c Random Early Detection queue. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Changes: * J Hadi Salim 980914: computation fixes * Alexey Makarenko <makar@phoenix.kharkov.ua> 990814: qave on idle link was calculated incorrectly. * J Hadi Salim 980816: ECN support */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/inet_ecn.h> #include <net/red.h> /* Parameters, settable by user: ----------------------------- limit - bytes (must be > qth_max + burst) Hard limit on queue length, should be chosen >qth_max to allow packet bursts. This parameter does not affect the algorithms behaviour and can be chosen arbitrarily high (well, less than ram size) Really, this limit will never be reached if RED works correctly. */ struct red_sched_data { u32 limit; /* HARD maximal queue length */ unsigned char flags; /* Non-flags in tc_red_qopt.flags. */ unsigned char userbits; struct timer_list adapt_timer; struct Qdisc *sch; struct red_parms parms; struct red_vars vars; struct red_stats stats; struct Qdisc *qdisc; struct tcf_qevent qe_early_drop; struct tcf_qevent qe_mark; }; #define TC_RED_SUPPORTED_FLAGS (TC_RED_HISTORIC_FLAGS | TC_RED_NODROP) static inline int red_use_ecn(struct red_sched_data *q) { return q->flags & TC_RED_ECN; } static inline int red_use_harddrop(struct red_sched_data *q) { return q->flags & TC_RED_HARDDROP; } static int red_use_nodrop(struct red_sched_data *q) { return q->flags & TC_RED_NODROP; } static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { enum qdisc_drop_reason reason = QDISC_DROP_CONGESTED; struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; unsigned int len; int ret; q->vars.qavg = red_calc_qavg(&q->parms, &q->vars, child->qstats.backlog); if (red_is_idling(&q->vars)) red_end_of_idle_period(&q->vars); switch (red_action(&q->parms, &q->vars, q->vars.qavg)) { case RED_DONT_MARK: break; case RED_PROB_MARK: qdisc_qstats_overlimit(sch); if (!red_use_ecn(q)) { WRITE_ONCE(q->stats.prob_drop, q->stats.prob_drop + 1); goto congestion_drop; } if (INET_ECN_set_ce(skb)) { WRITE_ONCE(q->stats.prob_mark, q->stats.prob_mark + 1); skb = tcf_qevent_handle(&q->qe_mark, sch, skb, to_free, &ret); if (!skb) return NET_XMIT_CN | ret; } else if (!red_use_nodrop(q)) { WRITE_ONCE(q->stats.prob_drop, q->stats.prob_drop + 1); goto congestion_drop; } /* Non-ECT packet in ECN nodrop mode: queue it. */ break; case RED_HARD_MARK: reason = QDISC_DROP_OVERLIMIT; qdisc_qstats_overlimit(sch); if (red_use_harddrop(q) || !red_use_ecn(q)) { WRITE_ONCE(q->stats.forced_drop, q->stats.forced_drop + 1); goto congestion_drop; } if (INET_ECN_set_ce(skb)) { WRITE_ONCE(q->stats.forced_mark, q->stats.forced_mark + 1); skb = tcf_qevent_handle(&q->qe_mark, sch, skb, to_free, &ret); if (!skb) return NET_XMIT_CN | ret; } else if (!red_use_nodrop(q)) { WRITE_ONCE(q->stats.forced_drop, q->stats.forced_drop + 1); goto congestion_drop; } /* Non-ECT packet in ECN nodrop mode: queue it. */ break; } len = qdisc_pkt_len(skb); ret = qdisc_enqueue(skb, child, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { qstats_backlog_add(sch, len); qdisc_qlen_inc(sch); } else if (net_xmit_drop_count(ret)) { WRITE_ONCE(q->stats.pdrop, q->stats.pdrop + 1); qdisc_qstats_drop(sch); } return ret; congestion_drop: skb = tcf_qevent_handle(&q->qe_early_drop, sch, skb, to_free, &ret); if (!skb) return NET_XMIT_CN | ret; qdisc_drop_reason(skb, sch, to_free, reason); return NET_XMIT_CN; } static struct sk_buff *red_dequeue(struct Qdisc *sch) { struct sk_buff *skb; struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; skb = qdisc_dequeue_peeked(child); if (skb) { qdisc_bstats_update(sch, skb); qdisc_qstats_backlog_dec(sch, skb); qdisc_qlen_dec(sch); } else { if (!red_is_idling(&q->vars)) red_start_of_idle_period(&q->vars); } return skb; } static struct sk_buff *red_peek(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; return child->ops->peek(child); } static void red_reset(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); qdisc_reset(q->qdisc); red_restart(&q->vars); } static int red_offload(struct Qdisc *sch, bool enable) { struct red_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct tc_red_qopt_offload opt = { .handle = sch->handle, .parent = sch->parent, }; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; if (enable) { opt.command = TC_RED_REPLACE; opt.set.min = q->parms.qth_min >> q->parms.Wlog; opt.set.max = q->parms.qth_max >> q->parms.Wlog; opt.set.probability = q->parms.max_P; opt.set.limit = q->limit; opt.set.is_ecn = red_use_ecn(q); opt.set.is_harddrop = red_use_harddrop(q); opt.set.is_nodrop = red_use_nodrop(q); opt.set.qstats = &sch->qstats; } else { opt.command = TC_RED_DESTROY; } return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt); } static void red_destroy(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); tcf_qevent_destroy(&q->qe_mark, sch); tcf_qevent_destroy(&q->qe_early_drop, sch); timer_delete_sync(&q->adapt_timer); red_offload(sch, false); qdisc_put(q->qdisc); } static const struct nla_policy red_policy[TCA_RED_MAX + 1] = { [TCA_RED_UNSPEC] = { .strict_start_type = TCA_RED_FLAGS }, [TCA_RED_PARMS] = { .len = sizeof(struct tc_red_qopt) }, [TCA_RED_STAB] = { .len = RED_STAB_SIZE }, [TCA_RED_MAX_P] = { .type = NLA_U32 }, [TCA_RED_FLAGS] = NLA_POLICY_BITFIELD32(TC_RED_SUPPORTED_FLAGS), [TCA_RED_EARLY_DROP_BLOCK] = { .type = NLA_U32 }, [TCA_RED_MARK_BLOCK] = { .type = NLA_U32 }, }; static int __red_change(struct Qdisc *sch, struct nlattr **tb, struct netlink_ext_ack *extack) { struct Qdisc *old_child = NULL, *child = NULL; struct red_sched_data *q = qdisc_priv(sch); struct nla_bitfield32 flags_bf; struct tc_red_qopt *ctl; unsigned char userbits; unsigned char flags; int err; u32 max_P; u8 *stab; if (tb[TCA_RED_PARMS] == NULL || tb[TCA_RED_STAB] == NULL) return -EINVAL; max_P = nla_get_u32_default(tb[TCA_RED_MAX_P], 0); ctl = nla_data(tb[TCA_RED_PARMS]); stab = nla_data(tb[TCA_RED_STAB]); if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) return -EINVAL; err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS, tb[TCA_RED_FLAGS], TC_RED_SUPPORTED_FLAGS, &flags_bf, &userbits, extack); if (err) return err; if (ctl->limit > 0) { child = fifo_create_dflt(sch, &bfifo_qdisc_ops, ctl->limit, extack); if (IS_ERR(child)) return PTR_ERR(child); /* child is fifo, no need to check for noop_qdisc */ qdisc_hash_add(child, true); } sch_tree_lock(sch); flags = (q->flags & ~flags_bf.selector) | flags_bf.value; err = red_validate_flags(flags, extack); if (err) goto unlock_out; q->flags = flags; q->userbits = userbits; q->limit = ctl->limit; if (child) { qdisc_purge_queue(q->qdisc); old_child = q->qdisc; q->qdisc = child; } red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, stab, max_P); red_set_vars(&q->vars); timer_delete(&q->adapt_timer); if (ctl->flags & TC_RED_ADAPTATIVE) mod_timer(&q->adapt_timer, jiffies + HZ/2); if (!q->qdisc->q.qlen) red_start_of_idle_period(&q->vars); sch_tree_unlock(sch); red_offload(sch, true); if (old_child) qdisc_put(old_child); return 0; unlock_out: sch_tree_unlock(sch); if (child) qdisc_put(child); return err; } static inline void red_adaptative_timer(struct timer_list *t) { struct red_sched_data *q = timer_container_of(q, t, adapt_timer); struct Qdisc *sch = q->sch; spinlock_t *root_lock; rcu_read_lock(); root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); red_adaptative_algo(&q->parms, &q->vars); mod_timer(&q->adapt_timer, jiffies + HZ/2); spin_unlock(root_lock); rcu_read_unlock(); } static int red_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct red_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_RED_MAX + 1]; int err; q->qdisc = &noop_qdisc; q->sch = sch; timer_setup(&q->adapt_timer, red_adaptative_timer, 0); if (!opt) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_RED_MAX, opt, red_policy, extack); if (err < 0) return err; err = __red_change(sch, tb, extack); if (err) return err; err = tcf_qevent_init(&q->qe_early_drop, sch, FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP, tb[TCA_RED_EARLY_DROP_BLOCK], extack); if (err) return err; return tcf_qevent_init(&q->qe_mark, sch, FLOW_BLOCK_BINDER_TYPE_RED_MARK, tb[TCA_RED_MARK_BLOCK], extack); } static int red_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct red_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_RED_MAX + 1]; int err; err = nla_parse_nested_deprecated(tb, TCA_RED_MAX, opt, red_policy, extack); if (err < 0) return err; err = tcf_qevent_validate_change(&q->qe_early_drop, tb[TCA_RED_EARLY_DROP_BLOCK], extack); if (err) return err; err = tcf_qevent_validate_change(&q->qe_mark, tb[TCA_RED_MARK_BLOCK], extack); if (err) return err; return __red_change(sch, tb, extack); } static int red_dump_offload_stats(struct Qdisc *sch) { struct tc_red_qopt_offload hw_stats = { .command = TC_RED_STATS, .handle = sch->handle, .parent = sch->parent, { .stats.bstats = &sch->bstats, .stats.qstats = &sch->qstats, }, }; return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_RED, &hw_stats); } static int red_dump(struct Qdisc *sch, struct sk_buff *skb) { struct red_sched_data *q = qdisc_priv(sch); struct nlattr *opts = NULL; struct tc_red_qopt opt = { .limit = q->limit, .flags = (q->flags & TC_RED_HISTORIC_FLAGS) | q->userbits, .qth_min = q->parms.qth_min >> q->parms.Wlog, .qth_max = q->parms.qth_max >> q->parms.Wlog, .Wlog = q->parms.Wlog, .Plog = q->parms.Plog, .Scell_log = q->parms.Scell_log, }; int err; err = red_dump_offload_stats(sch); if (err) goto nla_put_failure; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_RED_PARMS, sizeof(opt), &opt) || nla_put_u32(skb, TCA_RED_MAX_P, q->parms.max_P) || nla_put_bitfield32(skb, TCA_RED_FLAGS, q->flags, TC_RED_SUPPORTED_FLAGS) || tcf_qevent_dump(skb, TCA_RED_MARK_BLOCK, &q->qe_mark) || tcf_qevent_dump(skb, TCA_RED_EARLY_DROP_BLOCK, &q->qe_early_drop)) goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: nla_nest_cancel(skb, opts); return -EMSGSIZE; } static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct red_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct tc_red_xstats st = {0}; if (sch->flags & TCQ_F_OFFLOADED) { struct tc_red_qopt_offload hw_stats_request = { .command = TC_RED_XSTATS, .handle = sch->handle, .parent = sch->parent, { .xstats = &q->stats, }, }; dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &hw_stats_request); } st.early = READ_ONCE(q->stats.prob_drop) + READ_ONCE(q->stats.forced_drop); st.pdrop = READ_ONCE(q->stats.pdrop); st.marked = READ_ONCE(q->stats.prob_mark) + READ_ONCE(q->stats.forced_mark); return gnet_stats_copy_app(d, &st, sizeof(st)); } static int red_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct red_sched_data *q = qdisc_priv(sch); tcm->tcm_handle |= TC_H_MIN(1); tcm->tcm_info = q->qdisc->handle; return 0; } static void red_graft_offload(struct Qdisc *sch, struct Qdisc *new, struct Qdisc *old, struct netlink_ext_ack *extack) { struct tc_red_qopt_offload graft_offload = { .handle = sch->handle, .parent = sch->parent, .child_handle = new->handle, .command = TC_RED_GRAFT, }; qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, old, TC_SETUP_QDISC_RED, &graft_offload, extack); } static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct red_sched_data *q = qdisc_priv(sch); if (new == NULL) new = &noop_qdisc; *old = qdisc_replace(sch, new, &q->qdisc); red_graft_offload(sch, new, *old, extack); return 0; } static struct Qdisc *red_leaf(struct Qdisc *sch, unsigned long arg) { struct red_sched_data *q = qdisc_priv(sch); return q->qdisc; } static unsigned long red_find(struct Qdisc *sch, u32 classid) { return 1; } static void red_walk(struct Qdisc *sch, struct qdisc_walker *walker) { if (!walker->stop) { tc_qdisc_stats_dump(sch, 1, walker); } } static const struct Qdisc_class_ops red_class_ops = { .graft = red_graft, .leaf = red_leaf, .find = red_find, .walk = red_walk, .dump = red_dump_class, }; static struct Qdisc_ops red_qdisc_ops __read_mostly = { .id = "red", .priv_size = sizeof(struct red_sched_data), .cl_ops = &red_class_ops, .enqueue = red_enqueue, .dequeue = red_dequeue, .peek = red_peek, .init = red_init, .reset = red_reset, .destroy = red_destroy, .change = red_change, .dump = red_dump, .dump_stats = red_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("red"); static int __init red_module_init(void) { return register_qdisc(&red_qdisc_ops); } static void __exit red_module_exit(void) { unregister_qdisc(&red_qdisc_ops); } module_init(red_module_init) module_exit(red_module_exit) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Random Early Detection qdisc"); |
| 231 34 288 248 40 2 10 5 696 18 182 265 4 548 2 500 10 76 16 304 2 2 391 352 253 58 392 783 655 2 617 715 7 38 30 8 4 31 6 33 33 30 7 78 3 16 3 47 16 73 11 62 12 3 9 8 1 1 40 6 5 10 7 4 1 7 1117 22 215 207 6 1 3 237 1303 1090 1 319 7 54 360 1309 14 23 1281 11 10 10 1 2 2 3 7 1 1 5 6 7 7 14 14 7 13 329 315 16 19 16 3 11 8 19 19 11 1 20 46 11 74 2 2 28 45 30 11 72 237 237 222 22 104 59 80 104 83 12 34 34 34 2 7 25 96 32 104 92 91 2 62 6 59 25 4 29 29 152 133 125 28 16 1 22 27 22 27 27 27 27 27 27 6 43 4 45 15 60 1 59 15 49 6 43 16 2 25 538 449 219 218 445 6 535 1 223 263 197 45 301 222 532 3 162 122 35 122 6 58 151 444 50 197 37 106 3 402 37 161 301 332 325 457 435 2 102 328 308 54 32 22 97 12 14 76 1 10 2 308 312 90 321 1 1 58 58 59 279 84 43 1 222 22 237 283 2 284 277 17 322 17 1 1 323 1 325 328 493 190 145 508 522 181 343 21 16 5 41 9 9 323 44 27 13 7 7 366 366 1 101 289 364 8 2 29 1 349 2 2 6 27 352 326 30 134 3 223 217 7 24 257 71 366 366 366 99 99 78 2 2 67 8 41 33 13 40 115 121 20 103 115 40 123 123 12 87 125 124 121 50 119 22 123 54 111 123 48 150 50 152 21 1 27 27 16 133 140 87 41 16 25 127 32 34 219 219 219 157 78 155 7 21 55 47 2 6 24 51 219 219 237 234 34 248 388 30 2 6 1 60 43 252 64 7 326 301 1 325 7 835 74 26 70 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/xattr.c * * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> * * Fix by Harrison Xing <harrison@mountainviewdata.com>. * Ext4 code with a lot of help from Eric Jarman <ejarman@acm.org>. * Extended attributes for symlinks and special files added per * suggestion of Luka Renko <luka.renko@hermes.si>. * xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>, * Red Hat Inc. * ea-in-inode support by Alex Tomas <alex@clusterfs.com> aka bzzz * and Andreas Gruenbacher <agruen@suse.de>. */ /* * Extended attributes are stored directly in inodes (on file systems with * inodes bigger than 128 bytes) and on additional disk blocks. The i_file_acl * field contains the block number if an inode uses an additional block. All * attributes must fit in the inode and one additional block. Blocks that * contain the identical set of attributes may be shared among several inodes. * Identical blocks are detected by keeping a cache of blocks that have * recently been accessed. * * The attributes in inodes and on blocks have a different header; the entries * are stored in the same format: * * +------------------+ * | header | * | entry 1 | | * | entry 2 | | growing downwards * | entry 3 | v * | four null bytes | * | . . . | * | value 1 | ^ * | value 3 | | growing upwards * | value 2 | | * +------------------+ * * The header is followed by multiple entry descriptors. In disk blocks, the * entry descriptors are kept sorted. In inodes, they are unsorted. The * attribute values are aligned to the end of the block in no specific order. * * Locking strategy * ---------------- * EXT4_I(inode)->i_file_acl is protected by EXT4_I(inode)->xattr_sem. * EA blocks are only changed if they are exclusive to an inode, so * holding xattr_sem also means that nothing but the EA block's reference * count can change. Multiple writers to the same block are synchronized * by the buffer lock. */ #include <linux/init.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/mbcache.h> #include <linux/quotaops.h> #include <linux/iversion.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" #include "acl.h" #ifdef EXT4_XATTR_DEBUG # define ea_idebug(inode, fmt, ...) \ printk(KERN_DEBUG "inode %s:%llu: " fmt "\n", \ inode->i_sb->s_id, inode->i_ino, ##__VA_ARGS__) # define ea_bdebug(bh, fmt, ...) \ printk(KERN_DEBUG "block %pg:%lu: " fmt "\n", \ bh->b_bdev, (unsigned long)bh->b_blocknr, ##__VA_ARGS__) #else # define ea_idebug(inode, fmt, ...) no_printk(fmt, ##__VA_ARGS__) # define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif static void ext4_xattr_block_cache_insert(struct mb_cache *, struct buffer_head *); static struct buffer_head * ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *, struct mb_cache_entry **); static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, size_t value_count); static __le32 ext4_xattr_hash_entry_signed(char *name, size_t name_len, __le32 *value, size_t value_count); static void ext4_xattr_rehash(struct ext4_xattr_header *); static const struct xattr_handler * const ext4_xattr_handler_map[] = { [EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler, #ifdef CONFIG_EXT4_FS_POSIX_ACL [EXT4_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, [EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default, #endif [EXT4_XATTR_INDEX_TRUSTED] = &ext4_xattr_trusted_handler, #ifdef CONFIG_EXT4_FS_SECURITY [EXT4_XATTR_INDEX_SECURITY] = &ext4_xattr_security_handler, #endif [EXT4_XATTR_INDEX_HURD] = &ext4_xattr_hurd_handler, }; const struct xattr_handler * const ext4_xattr_handlers[] = { &ext4_xattr_user_handler, &ext4_xattr_trusted_handler, #ifdef CONFIG_EXT4_FS_SECURITY &ext4_xattr_security_handler, #endif &ext4_xattr_hurd_handler, NULL }; #define EA_BLOCK_CACHE(inode) (((struct ext4_sb_info *) \ inode->i_sb->s_fs_info)->s_ea_block_cache) #define EA_INODE_CACHE(inode) (((struct ext4_sb_info *) \ inode->i_sb->s_fs_info)->s_ea_inode_cache) static int ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, struct inode *inode); #ifdef CONFIG_LOCKDEP void ext4_xattr_inode_set_class(struct inode *ea_inode) { struct ext4_inode_info *ei = EXT4_I(ea_inode); lockdep_set_subclass(&ea_inode->i_rwsem, 1); (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ lockdep_set_subclass(&ei->i_data_sem, I_DATA_SEM_EA); } #endif static __le32 ext4_xattr_block_csum(struct inode *inode, sector_t block_nr, struct ext4_xattr_header *hdr) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; __le64 dsk_block_nr = cpu_to_le64(block_nr); __u32 dummy_csum = 0; int offset = offsetof(struct ext4_xattr_header, h_checksum); csum = ext4_chksum(sbi->s_csum_seed, (__u8 *)&dsk_block_nr, sizeof(dsk_block_nr)); csum = ext4_chksum(csum, (__u8 *)hdr, offset); csum = ext4_chksum(csum, (__u8 *)&dummy_csum, sizeof(dummy_csum)); offset += sizeof(dummy_csum); csum = ext4_chksum(csum, (__u8 *)hdr + offset, EXT4_BLOCK_SIZE(inode->i_sb) - offset); return cpu_to_le32(csum); } static int ext4_xattr_block_csum_verify(struct inode *inode, struct buffer_head *bh) { struct ext4_xattr_header *hdr = BHDR(bh); int ret = 1; if (ext4_has_feature_metadata_csum(inode->i_sb)) { lock_buffer(bh); ret = (hdr->h_checksum == ext4_xattr_block_csum(inode, bh->b_blocknr, hdr)); unlock_buffer(bh); } return ret; } static void ext4_xattr_block_csum_set(struct inode *inode, struct buffer_head *bh) { if (ext4_has_feature_metadata_csum(inode->i_sb)) BHDR(bh)->h_checksum = ext4_xattr_block_csum(inode, bh->b_blocknr, BHDR(bh)); } static inline const char *ext4_xattr_prefix(int name_index, struct dentry *dentry) { const struct xattr_handler *handler = NULL; if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map)) handler = ext4_xattr_handler_map[name_index]; if (!xattr_handler_can_list(handler, dentry)) return NULL; return xattr_prefix(handler); } static int check_xattrs(struct inode *inode, struct buffer_head *bh, struct ext4_xattr_entry *entry, void *end, void *value_start, const char *function, unsigned int line) { struct ext4_xattr_entry *e = entry; int err = -EFSCORRUPTED; char *err_str; if (bh) { if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || BHDR(bh)->h_blocks != cpu_to_le32(1)) { err_str = "invalid header"; goto errout; } if (buffer_verified(bh)) return 0; if (!ext4_xattr_block_csum_verify(inode, bh)) { err = -EFSBADCRC; err_str = "invalid checksum"; goto errout; } } else { struct ext4_xattr_ibody_header *header = value_start; header -= 1; if (end - (void *)header < sizeof(*header) + sizeof(u32)) { err_str = "in-inode xattr block too small"; goto errout; } if (header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) { err_str = "bad magic number in in-inode xattr"; goto errout; } } /* Find the end of the names list */ while (!IS_LAST_ENTRY(e)) { struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e); if ((void *)next + sizeof(u32) > end) { err_str = "e_name out of bounds"; goto errout; } if (strnlen(e->e_name, e->e_name_len) != e->e_name_len) { err_str = "bad e_name length"; goto errout; } e = next; } /* Check the values */ while (!IS_LAST_ENTRY(entry)) { u32 size = le32_to_cpu(entry->e_value_size); unsigned long ea_ino = le32_to_cpu(entry->e_value_inum); if (!ext4_has_feature_ea_inode(inode->i_sb) && ea_ino) { err_str = "ea_inode specified without ea_inode feature enabled"; goto errout; } if (ea_ino && ((ea_ino == EXT4_ROOT_INO) || !ext4_valid_inum(inode->i_sb, ea_ino))) { err_str = "invalid ea_ino"; goto errout; } if (ea_ino && !size) { err_str = "invalid size in ea xattr"; goto errout; } if (size > EXT4_XATTR_SIZE_MAX) { err_str = "e_value size too large"; goto errout; } if (size != 0 && entry->e_value_inum == 0) { u16 offs = le16_to_cpu(entry->e_value_offs); void *value; /* * The value cannot overlap the names, and the value * with padding cannot extend beyond 'end'. Check both * the padded and unpadded sizes, since the size may * overflow to 0 when adding padding. */ if (offs > end - value_start) { err_str = "e_value out of bounds"; goto errout; } value = value_start + offs; if (value < (void *)e + sizeof(u32) || size > end - value || EXT4_XATTR_SIZE(size) > end - value) { err_str = "overlapping e_value "; goto errout; } } entry = EXT4_XATTR_NEXT(entry); } if (bh) set_buffer_verified(bh); return 0; errout: if (bh) __ext4_error_inode(inode, function, line, 0, -err, "corrupted xattr block %llu: %s", (unsigned long long) bh->b_blocknr, err_str); else __ext4_error_inode(inode, function, line, 0, -err, "corrupted in-inode xattr: %s", err_str); return err; } static inline int __ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh, const char *function, unsigned int line) { return check_xattrs(inode, bh, BFIRST(bh), bh->b_data + bh->b_size, bh->b_data, function, line); } #define ext4_xattr_check_block(inode, bh) \ __ext4_xattr_check_block((inode), (bh), __func__, __LINE__) int __xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header, void *end, const char *function, unsigned int line) { return check_xattrs(inode, NULL, IFIRST(header), end, IFIRST(header), function, line); } static int xattr_find_entry(struct inode *inode, struct ext4_xattr_entry **pentry, void *end, int name_index, const char *name, int sorted) { struct ext4_xattr_entry *entry, *next; size_t name_len; int cmp = 1; if (name == NULL) return -EINVAL; name_len = strlen(name); for (entry = *pentry; !IS_LAST_ENTRY(entry); entry = next) { next = EXT4_XATTR_NEXT(entry); if ((void *) next >= end) { EXT4_ERROR_INODE(inode, "corrupted xattr entries"); return -EFSCORRUPTED; } cmp = name_index - entry->e_name_index; if (!cmp) cmp = name_len - entry->e_name_len; if (!cmp) cmp = memcmp(name, entry->e_name, name_len); if (!cmp || (cmp < 0 && sorted)) break; } *pentry = entry; return cmp ? -ENODATA : 0; } static u32 ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size) { return ext4_chksum(sbi->s_csum_seed, buffer, size); } static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode) { return ((u64) inode_get_ctime_sec(ea_inode) << 32) | (u32) inode_peek_iversion_raw(ea_inode); } static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count) { inode_set_ctime(ea_inode, (u32)(ref_count >> 32), 0); inode_set_iversion_raw(ea_inode, ref_count & 0xffffffff); } static u32 ext4_xattr_inode_get_hash(struct inode *ea_inode) { return (u32) inode_get_atime_sec(ea_inode); } static void ext4_xattr_inode_set_hash(struct inode *ea_inode, u32 hash) { inode_set_atime(ea_inode, hash, 0); } /* * Read the EA value from an inode. */ static int ext4_xattr_inode_read(struct inode *ea_inode, void *buf, size_t size) { int blocksize = 1 << ea_inode->i_blkbits; int bh_count = (size + blocksize - 1) >> ea_inode->i_blkbits; int tail_size = (size % blocksize) ?: blocksize; struct buffer_head *bhs_inline[8]; struct buffer_head **bhs = bhs_inline; int i, ret; if (bh_count > ARRAY_SIZE(bhs_inline)) { bhs = kmalloc_objs(*bhs, bh_count, GFP_NOFS); if (!bhs) return -ENOMEM; } ret = ext4_bread_batch(ea_inode, 0 /* block */, bh_count, true /* wait */, bhs); if (ret) goto free_bhs; for (i = 0; i < bh_count; i++) { /* There shouldn't be any holes in ea_inode. */ if (!bhs[i]) { ret = -EFSCORRUPTED; goto put_bhs; } memcpy((char *)buf + blocksize * i, bhs[i]->b_data, i < bh_count - 1 ? blocksize : tail_size); } ret = 0; put_bhs: for (i = 0; i < bh_count; i++) brelse(bhs[i]); free_bhs: if (bhs != bhs_inline) kfree(bhs); return ret; } #define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode_get_mtime_sec(inode))) static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, u32 ea_inode_hash, struct inode **ea_inode) { struct inode *inode; int err; /* * We have to check for this corruption early as otherwise * iget_locked() could wait indefinitely for the state of our * parent inode. */ if (parent->i_ino == ea_ino) { ext4_error(parent->i_sb, "Parent and EA inode have the same ino %lu", ea_ino); return -EFSCORRUPTED; } inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_EA_INODE); if (IS_ERR(inode)) { err = PTR_ERR(inode); ext4_error(parent->i_sb, "error while reading EA inode %lu err=%d", ea_ino, err); return err; } ext4_xattr_inode_set_class(inode); /* * Check whether this is an old Lustre-style xattr inode. Lustre * implementation does not have hash validation, rather it has a * backpointer from ea_inode to the parent inode. */ if (ea_inode_hash != ext4_xattr_inode_get_hash(inode) && EXT4_XATTR_INODE_GET_PARENT(inode) == parent->i_ino && inode->i_generation == parent->i_generation) { ext4_set_inode_state(inode, EXT4_STATE_LUSTRE_EA_INODE); ext4_xattr_inode_set_ref(inode, 1); } else { inode_lock_nested(inode, I_MUTEX_XATTR); inode->i_flags |= S_NOQUOTA; inode_unlock(inode); } *ea_inode = inode; return 0; } /* Remove entry from mbcache when EA inode is getting evicted */ void ext4_evict_ea_inode(struct inode *inode) { struct mb_cache_entry *oe; if (!EA_INODE_CACHE(inode)) return; /* Wait for entry to get unused so that we can remove it */ while ((oe = mb_cache_entry_delete_or_get(EA_INODE_CACHE(inode), ext4_xattr_inode_get_hash(inode), inode->i_ino))) { mb_cache_entry_wait_unused(oe); mb_cache_entry_put(EA_INODE_CACHE(inode), oe); } } static int ext4_xattr_inode_verify_hashes(struct inode *ea_inode, struct ext4_xattr_entry *entry, void *buffer, size_t size) { u32 hash; /* Verify stored hash matches calculated hash. */ hash = ext4_xattr_inode_hash(EXT4_SB(ea_inode->i_sb), buffer, size); if (hash != ext4_xattr_inode_get_hash(ea_inode)) return -EFSCORRUPTED; if (entry) { __le32 e_hash, tmp_data; /* Verify entry hash. */ tmp_data = cpu_to_le32(hash); e_hash = ext4_xattr_hash_entry(entry->e_name, entry->e_name_len, &tmp_data, 1); /* All good? */ if (e_hash == entry->e_hash) return 0; /* * Not good. Maybe the entry hash was calculated * using the buggy signed char version? */ e_hash = ext4_xattr_hash_entry_signed(entry->e_name, entry->e_name_len, &tmp_data, 1); /* Still no match - bad */ if (e_hash != entry->e_hash) return -EFSCORRUPTED; /* Let people know about old hash */ pr_warn_once("ext4: filesystem with signed xattr name hash"); } return 0; } /* * Read xattr value from the EA inode. */ static int ext4_xattr_inode_get(struct inode *inode, struct ext4_xattr_entry *entry, void *buffer, size_t size) { struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode); struct inode *ea_inode; int err; err = ext4_xattr_inode_iget(inode, le32_to_cpu(entry->e_value_inum), le32_to_cpu(entry->e_hash), &ea_inode); if (err) { ea_inode = NULL; goto out; } if (i_size_read(ea_inode) != size) { ext4_warning_inode(ea_inode, "ea_inode file size=%llu entry size=%zu", i_size_read(ea_inode), size); err = -EFSCORRUPTED; goto out; } err = ext4_xattr_inode_read(ea_inode, buffer, size); if (err) goto out; if (!ext4_test_inode_state(ea_inode, EXT4_STATE_LUSTRE_EA_INODE)) { err = ext4_xattr_inode_verify_hashes(ea_inode, entry, buffer, size); if (err) { ext4_warning_inode(ea_inode, "EA inode hash validation failed"); goto out; } if (ea_inode_cache) mb_cache_entry_create(ea_inode_cache, GFP_NOFS, ext4_xattr_inode_get_hash(ea_inode), ea_inode->i_ino, true /* reusable */); } out: iput(ea_inode); return err; } static int ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { struct buffer_head *bh = NULL; struct ext4_xattr_entry *entry; size_t size; void *end; int error; struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", name_index, name, buffer, (long)buffer_size); if (!EXT4_I(inode)->i_file_acl) return -ENODATA; ea_idebug(inode, "reading block %llu", (unsigned long long)EXT4_I(inode)->i_file_acl); bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) return PTR_ERR(bh); ea_bdebug(bh, "b_count=%d, refcount=%d", atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); error = ext4_xattr_check_block(inode, bh); if (error) goto cleanup; ext4_xattr_block_cache_insert(ea_block_cache, bh); entry = BFIRST(bh); end = bh->b_data + bh->b_size; error = xattr_find_entry(inode, &entry, end, name_index, name, 1); if (error) goto cleanup; size = le32_to_cpu(entry->e_value_size); error = -ERANGE; if (unlikely(size > EXT4_XATTR_SIZE_MAX)) goto cleanup; if (buffer) { if (size > buffer_size) goto cleanup; if (entry->e_value_inum) { error = ext4_xattr_inode_get(inode, entry, buffer, size); if (error) goto cleanup; } else { u16 offset = le16_to_cpu(entry->e_value_offs); void *p = bh->b_data + offset; if (unlikely(p + size > end)) goto cleanup; memcpy(buffer, p, size); } } error = size; cleanup: brelse(bh); return error; } int ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; struct ext4_inode *raw_inode; struct ext4_iloc iloc; size_t size; void *end; int error; if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR)) return -ENODATA; error = ext4_get_inode_loc(inode, &iloc); if (error) return error; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); end = ITAIL(inode, raw_inode); entry = IFIRST(header); error = xattr_find_entry(inode, &entry, end, name_index, name, 0); if (error) goto cleanup; size = le32_to_cpu(entry->e_value_size); error = -ERANGE; if (unlikely(size > EXT4_XATTR_SIZE_MAX)) goto cleanup; if (buffer) { if (size > buffer_size) goto cleanup; if (entry->e_value_inum) { error = ext4_xattr_inode_get(inode, entry, buffer, size); if (error) goto cleanup; } else { u16 offset = le16_to_cpu(entry->e_value_offs); void *p = (void *)IFIRST(header) + offset; if (unlikely(p + size > end)) goto cleanup; memcpy(buffer, p, size); } } error = size; cleanup: brelse(iloc.bh); return error; } /* * ext4_xattr_get() * * Copy an extended attribute into the buffer * provided, or compute the buffer size required. * Buffer is NULL to compute the size of the buffer required. * * Returns a negative error number on failure, or the number of bytes * used / required on success. */ int ext4_xattr_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { int error; if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; if (strlen(name) > 255) return -ERANGE; down_read(&EXT4_I(inode)->xattr_sem); error = ext4_xattr_ibody_get(inode, name_index, name, buffer, buffer_size); if (error == -ENODATA) error = ext4_xattr_block_get(inode, name_index, name, buffer, buffer_size); up_read(&EXT4_I(inode)->xattr_sem); return error; } static int ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry, char *buffer, size_t buffer_size) { size_t rest = buffer_size; for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { const char *prefix; prefix = ext4_xattr_prefix(entry->e_name_index, dentry); if (prefix) { size_t prefix_len = strlen(prefix); size_t size = prefix_len + entry->e_name_len + 1; if (buffer) { if (size > rest) return -ERANGE; memcpy(buffer, prefix, prefix_len); buffer += prefix_len; memcpy(buffer, entry->e_name, entry->e_name_len); buffer += entry->e_name_len; *buffer++ = 0; } rest -= size; } } return buffer_size - rest; /* total size */ } static int ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) { struct inode *inode = d_inode(dentry); struct buffer_head *bh = NULL; int error; ea_idebug(inode, "buffer=%p, buffer_size=%ld", buffer, (long)buffer_size); if (!EXT4_I(inode)->i_file_acl) return 0; ea_idebug(inode, "reading block %llu", (unsigned long long)EXT4_I(inode)->i_file_acl); bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) return PTR_ERR(bh); ea_bdebug(bh, "b_count=%d, refcount=%d", atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); error = ext4_xattr_check_block(inode, bh); if (error) goto cleanup; ext4_xattr_block_cache_insert(EA_BLOCK_CACHE(inode), bh); error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size); cleanup: brelse(bh); return error; } static int ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size) { struct inode *inode = d_inode(dentry); struct ext4_xattr_ibody_header *header; struct ext4_inode *raw_inode; struct ext4_iloc iloc; int error; if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR)) return 0; error = ext4_get_inode_loc(inode, &iloc); if (error) return error; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); error = ext4_xattr_list_entries(dentry, IFIRST(header), buffer, buffer_size); brelse(iloc.bh); return error; } /* * Inode operation listxattr() * * d_inode(dentry)->i_rwsem: don't care * * Copy a list of attribute names into the buffer * provided, or compute the buffer size required. * Buffer is NULL to compute the size of the buffer required. * * Returns a negative error number on failure, or the number of bytes * used / required on success. */ ssize_t ext4_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { int ret, ret2; down_read(&EXT4_I(d_inode(dentry))->xattr_sem); ret = ret2 = ext4_xattr_ibody_list(dentry, buffer, buffer_size); if (ret < 0) goto errout; if (buffer) { buffer += ret; buffer_size -= ret; } ret = ext4_xattr_block_list(dentry, buffer, buffer_size); if (ret < 0) goto errout; ret += ret2; errout: up_read(&EXT4_I(d_inode(dentry))->xattr_sem); return ret; } /* * If the EXT4_FEATURE_COMPAT_EXT_ATTR feature of this file system is * not set, set it. */ static void ext4_xattr_update_super_block(handle_t *handle, struct super_block *sb) { if (ext4_has_feature_xattr(sb)) return; BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access"); if (ext4_journal_get_write_access(handle, sb, EXT4_SB(sb)->s_sbh, EXT4_JTR_NONE) == 0) { lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_xattr(sb); ext4_superblock_csum_set(sb); unlock_buffer(EXT4_SB(sb)->s_sbh); ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); } } int ext4_get_inode_usage(struct inode *inode, qsize_t *usage) { struct ext4_iloc iloc = { .bh = NULL }; struct buffer_head *bh = NULL; struct ext4_inode *raw_inode; struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; qsize_t ea_inode_refs = 0; int ret; lockdep_assert_held_read(&EXT4_I(inode)->xattr_sem); if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { ret = ext4_get_inode_loc(inode, &iloc); if (ret) goto out; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); for (entry = IFIRST(header); !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) if (entry->e_value_inum) ea_inode_refs++; } if (EXT4_I(inode)->i_file_acl) { bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { ret = PTR_ERR(bh); bh = NULL; goto out; } ret = ext4_xattr_check_block(inode, bh); if (ret) goto out; for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) if (entry->e_value_inum) ea_inode_refs++; } *usage = ea_inode_refs + 1; ret = 0; out: brelse(iloc.bh); brelse(bh); return ret; } static inline size_t round_up_cluster(struct inode *inode, size_t length) { struct super_block *sb = inode->i_sb; size_t cluster_size = 1 << (EXT4_SB(sb)->s_cluster_bits + inode->i_blkbits); size_t mask = ~(cluster_size - 1); return (length + cluster_size - 1) & mask; } static int ext4_xattr_inode_alloc_quota(struct inode *inode, size_t len) { int err; err = dquot_alloc_inode(inode); if (err) return err; err = dquot_alloc_space_nodirty(inode, round_up_cluster(inode, len)); if (err) dquot_free_inode(inode); return err; } static void ext4_xattr_inode_free_quota(struct inode *parent, struct inode *ea_inode, size_t len) { if (ea_inode && ext4_test_inode_state(ea_inode, EXT4_STATE_LUSTRE_EA_INODE)) return; dquot_free_space_nodirty(parent, round_up_cluster(parent, len)); dquot_free_inode(parent); } int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode, struct buffer_head *block_bh, size_t value_len, bool is_create) { int credits; int blocks; /* * 1) Owner inode update * 2) Ref count update on old xattr block * 3) new xattr block * 4) block bitmap update for new xattr block * 5) group descriptor for new xattr block * 6) block bitmap update for old xattr block * 7) group descriptor for old block * * 6 & 7 can happen if we have two racing threads T_a and T_b * which are each trying to set an xattr on inodes I_a and I_b * which were both initially sharing an xattr block. */ credits = 7; /* Quota updates. */ credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(sb); /* * In case of inline data, we may push out the data to a block, * so we need to reserve credits for this eventuality */ if (inode && ext4_has_inline_data(inode)) credits += ext4_chunk_trans_extent(inode, 1) + 1; /* We are done if ea_inode feature is not enabled. */ if (!ext4_has_feature_ea_inode(sb)) return credits; /* New ea_inode, inode map, block bitmap, group descriptor. */ credits += 4; /* Data blocks. */ blocks = (value_len + sb->s_blocksize - 1) >> sb->s_blocksize_bits; /* Indirection block or one level of extent tree. */ blocks += 1; /* Block bitmap and group descriptor updates for each block. */ credits += blocks * 2; /* Blocks themselves. */ credits += blocks; if (!is_create) { /* Dereference ea_inode holding old xattr value. * Old ea_inode, inode map, block bitmap, group descriptor. */ credits += 4; /* Data blocks for old ea_inode. */ blocks = XATTR_SIZE_MAX >> sb->s_blocksize_bits; /* Indirection block or one level of extent tree for old * ea_inode. */ blocks += 1; /* Block bitmap and group descriptor updates for each block. */ credits += blocks * 2; } /* We may need to clone the existing xattr block in which case we need * to increment ref counts for existing ea_inodes referenced by it. */ if (block_bh) { struct ext4_xattr_entry *entry = BFIRST(block_bh); for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) if (entry->e_value_inum) /* Ref count update on ea_inode. */ credits += 1; } return credits; } static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, int ref_change) { struct ext4_iloc iloc; u64 ref_count; int ret; inode_lock_nested(ea_inode, I_MUTEX_XATTR); ret = ext4_reserve_inode_write(handle, ea_inode, &iloc); if (ret) goto out; ref_count = ext4_xattr_inode_get_ref(ea_inode); if ((ref_count == 0 && ref_change < 0) || (ref_count == U64_MAX && ref_change > 0)) { ext4_error_inode(ea_inode, __func__, __LINE__, 0, "EA inode %llu ref wraparound: ref_count=%lld ref_change=%d", ea_inode->i_ino, ref_count, ref_change); brelse(iloc.bh); ret = -EFSCORRUPTED; goto out; } ref_count += ref_change; ext4_xattr_inode_set_ref(ea_inode, ref_count); if (ref_change > 0) { if (ref_count == 1) { WARN_ONCE(ea_inode->i_nlink, "EA inode %llu i_nlink=%u", ea_inode->i_ino, ea_inode->i_nlink); set_nlink(ea_inode, 1); ext4_orphan_del(handle, ea_inode); } } else { if (ref_count == 0) { WARN_ONCE(ea_inode->i_nlink != 1, "EA inode %llu i_nlink=%u", ea_inode->i_ino, ea_inode->i_nlink); clear_nlink(ea_inode); ext4_orphan_add(handle, ea_inode); } } ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc); if (ret) ext4_warning_inode(ea_inode, "ext4_mark_iloc_dirty() failed ret=%d", ret); out: inode_unlock(ea_inode); return ret; } static int ext4_xattr_inode_inc_ref(handle_t *handle, struct inode *ea_inode) { return ext4_xattr_inode_update_ref(handle, ea_inode, 1); } static int ext4_xattr_inode_dec_ref(handle_t *handle, struct inode *ea_inode) { return ext4_xattr_inode_update_ref(handle, ea_inode, -1); } static int ext4_xattr_inode_inc_ref_all(handle_t *handle, struct inode *parent, struct ext4_xattr_entry *first) { struct inode *ea_inode; struct ext4_xattr_entry *entry; struct ext4_xattr_entry *failed_entry; unsigned int ea_ino; int err, saved_err; for (entry = first; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; ea_ino = le32_to_cpu(entry->e_value_inum); err = ext4_xattr_inode_iget(parent, ea_ino, le32_to_cpu(entry->e_hash), &ea_inode); if (err) goto cleanup; err = ext4_xattr_inode_inc_ref(handle, ea_inode); if (err) { ext4_warning_inode(ea_inode, "inc ref error %d", err); iput(ea_inode); goto cleanup; } iput(ea_inode); } return 0; cleanup: saved_err = err; failed_entry = entry; for (entry = first; entry != failed_entry; entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; ea_ino = le32_to_cpu(entry->e_value_inum); err = ext4_xattr_inode_iget(parent, ea_ino, le32_to_cpu(entry->e_hash), &ea_inode); if (err) { ext4_warning(parent->i_sb, "cleanup ea_ino %u iget error %d", ea_ino, err); continue; } err = ext4_xattr_inode_dec_ref(handle, ea_inode); if (err) ext4_warning_inode(ea_inode, "cleanup dec ref error %d", err); iput(ea_inode); } return saved_err; } static int ext4_xattr_restart_fn(handle_t *handle, struct inode *inode, struct buffer_head *bh, bool block_csum, bool dirty) { int error; if (bh && dirty) { if (block_csum) ext4_xattr_block_csum_set(inode, bh); error = ext4_handle_dirty_metadata(handle, NULL, bh); if (error) { ext4_warning(inode->i_sb, "Handle metadata (error %d)", error); return error; } } return 0; } static void ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent, struct buffer_head *bh, struct ext4_xattr_entry *first, bool block_csum, struct ext4_xattr_inode_array **ea_inode_array, int extra_credits, bool skip_quota) { struct inode *ea_inode; struct ext4_xattr_entry *entry; struct ext4_iloc iloc = { .bh = NULL }; bool dirty = false; unsigned int ea_ino; int err; int credits; void *end; if (block_csum) end = (void *)bh->b_data + bh->b_size; else { err = ext4_get_inode_loc(parent, &iloc); if (err) { EXT4_ERROR_INODE(parent, "parent inode loc (error %d)", err); return; } end = (void *)ext4_raw_inode(&iloc) + EXT4_SB(parent->i_sb)->s_inode_size; } /* One credit for dec ref on ea_inode, one for orphan list addition, */ credits = 2 + extra_credits; for (entry = first; (void *)entry < end && !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; ea_ino = le32_to_cpu(entry->e_value_inum); err = ext4_xattr_inode_iget(parent, ea_ino, le32_to_cpu(entry->e_hash), &ea_inode); if (err) continue; err = ext4_expand_inode_array(ea_inode_array, ea_inode); if (err) { ext4_warning_inode(ea_inode, "Expand inode array err=%d", err); iput(ea_inode); continue; } err = ext4_journal_ensure_credits_fn(handle, credits, credits, ext4_free_metadata_revoke_credits(parent->i_sb, 1), ext4_xattr_restart_fn(handle, parent, bh, block_csum, dirty)); if (err < 0) { ext4_warning_inode(ea_inode, "Ensure credits err=%d", err); continue; } if (err > 0) { err = ext4_journal_get_write_ac |