| 1 1 1 1 1 1 2 2 254 254 254 264 364 273 1 1 1 44 44 44 44 44 44 44 45 291 121 46 46 41 45 46 45 45 45 46 46 46 45 1 45 45 45 268 268 1 268 268 267 268 268 268 268 45 45 45 44 45 273 273 273 273 273 273 252 273 273 273 272 273 273 273 5 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 44 45 45 45 42 42 41 1 1 42 42 42 42 42 1 1 1 1 1 1 1 1 495 291 291 291 291 291 497 308 308 497 291 291 291 290 497 494 496 496 42 496 60 60 60 55 60 55 262 53 45 45 45 53 258 258 258 46 2 2 2 2 42 42 3 42 4 2 2 2 2 2 2 2 2 2 273 273 272 273 273 273 273 273 273 273 273 272 253 253 2 2 23 23 17 91 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 7 1 1 1 82 1 83 83 2 2 2 1 2 2 1 1 2 314 1 1 1 3 1 1 1 1 1 1 1 2 1 1 1 2 2 1 3 3 2 1 2 2 4 2 2 2 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 298 1 298 298 1 314 42 41 1 1 1 1 1 1 42 253 253 253 253 45 45 45 45 45 45 253 253 253 253 253 253 262 262 262 262 45 45 45 45 6 6 46 46 46 46 46 46 46 46 46 46 46 46 46 6 6 46 46 13 13 261 262 262 261 262 262 1 262 262 46 46 46 46 46 46 46 46 14 262 262 262 262 262 262 262 262 262 262 262 262 45 45 45 45 42 42 41 41 41 12 12 12 12 12 12 12 12 12 12 12 12 40 4 4 12 12 12 4 4 12 12 12 254 254 254 254 254 254 253 253 253 253 272 45 45 46 46 46 45 45 46 46 45 6 6 6 6 45 45 45 45 45 45 45 45 45 45 45 45 45 45 44 45 45 45 45 5 5 5 5 5 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 263 263 263 263 263 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 211 42 42 211 252 252 252 252 263 263 263 263 263 263 4 263 263 263 263 221 263 263 263 263 262 263 262 263 263 263 262 263 262 263 262 263 263 263 263 263 262 262 262 263 263 103 254 254 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 252 42 252 252 252 252 252 252 252 252 254 252 254 254 254 254 254 254 254 254 254 254 254 254 254 254 254 254 254 254 254 254 253 254 254 254 254 8 8 1 1 1 1 1 1 1 1 1 1 1 7 7 7 6 6 6 7 1 7 7 1 1 1 1 1 1 33 25 33 33 33 33 1 2 31 257 257 42 42 41 42 42 41 42 45 45 45 2 45 2 2 2 2 42 42 41 42 42 1 3 3 45 45 45 45 45 45 3 3 42 42 3 41 42 42 42 42 42 42 41 31 42 42 42 42 45 45 55 55 16 55 6 6 6 6 6 24 24 24 1 23 23 23 22 23 23 23 23 23 18 18 45 31 31 44 45 31 45 42 42 42 42 42 42 45 45 4 1 1 2 2 1 42 45 45 45 45 45 45 42 45 2 2 43 2 2 2 43 43 43 42 2 45 45 45 45 44 45 45 45 45 45 45 45 44 45 44 45 45 45 45 45 45 45 45 45 45 42 42 42 42 42 44 44 44 44 253 253 253 253 253 253 253 253 253 43 252 252 252 1 1 253 349 349 349 349 349 276 349 349 349 255 7 2 7 7 7 7 7 7 7 7 7 7 7 7 7 4 4 4 4 4 4 4 4 7 4 261 262 263 263 263 7 258 7 263 263 263 263 263 263 263 263 7 7 3 7 6 7 7 1 1 1 4 45 45 103 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel-based Virtual Machine driver for Linux * * This module enables machines with Intel VT-x extensions to run virtual * machines without emulation or binary translation. * * Copyright (C) 2006 Qumranet, Inc. * Copyright 2010 Red Hat, Inc. and/or its affiliates. * * Authors: * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/highmem.h> #include <linux/hrtimer.h> #include <linux/kernel.h> #include <linux/kvm_host.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/mm.h> #include <linux/objtool.h> #include <linux/sched.h> #include <linux/sched/smt.h> #include <linux/slab.h> #include <linux/tboot.h> #include <linux/trace_events.h> #include <asm/apic.h> #include <asm/asm.h> #include <asm/cpu.h> #include <asm/cpu_device_id.h> #include <asm/cpuid/api.h> #include <asm/debugreg.h> #include <asm/desc.h> #include <asm/fpu/api.h> #include <asm/fpu/xstate.h> #include <asm/fred.h> #include <asm/idtentry.h> #include <asm/io.h> #include <asm/irq_remapping.h> #include <asm/reboot.h> #include <asm/perf_event.h> #include <asm/mmu_context.h> #include <asm/mshyperv.h> #include <asm/msr.h> #include <asm/mwait.h> #include <asm/spec-ctrl.h> #include <asm/virt.h> #include <asm/vmx.h> #include <trace/events/ipi.h> #include "capabilities.h" #include "common.h" #include "cpuid.h" #include "hyperv.h" #include "kvm_onhyperv.h" #include "irq.h" #include "regs.h" #include "lapic.h" #include "mmu.h" #include "nested.h" #include "pmu.h" #include "sgx.h" #include "trace.h" #include "vmcs.h" #include "vmcs12.h" #include "vmx.h" #include "x86.h" #include "x86_ops.h" #include "smm.h" #include "vmx_onhyperv.h" #include "vmenter.h" #include "posted_intr.h" #include "mmu/spte.h" MODULE_AUTHOR("Qumranet"); MODULE_DESCRIPTION("KVM support for VMX (Intel VT-x) extensions"); MODULE_LICENSE("GPL"); #ifdef MODULE static const struct x86_cpu_id vmx_cpu_id[] = { X86_MATCH_FEATURE(X86_FEATURE_VMX, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id); #endif bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); static bool __read_mostly enable_vnmi = 1; module_param_named(vnmi, enable_vnmi, bool, 0444); bool __read_mostly flexpriority_enabled = 1; module_param_named(flexpriority, flexpriority_enabled, bool, 0444); bool __read_mostly enable_ept = 1; module_param_named(ept, enable_ept, bool, 0444); bool __read_mostly enable_unrestricted_guest = 1; module_param_named(unrestricted_guest, enable_unrestricted_guest, bool, 0444); bool __read_mostly enable_ept_ad_bits = 1; module_param_named(eptad, enable_ept_ad_bits, bool, 0444); bool __read_mostly enable_cet = 1; module_param_named(cet, enable_cet, bool, 0444); static bool __read_mostly emulate_invalid_guest_state = true; module_param(emulate_invalid_guest_state, bool, 0444); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, 0444); bool __read_mostly enable_mbec = 1; module_param_named(mbec, enable_mbec, bool, 0444); module_param(enable_apicv, bool, 0444); module_param(enable_ipiv, bool, 0444); module_param(enable_device_posted_irqs, bool, 0444); /* * If nested=1, nested virtualization is supported, i.e., guests may use * VMX and be a hypervisor for its own guests. If nested=0, guests may not * use VMX instructions. */ static bool __read_mostly nested = 1; module_param(nested, bool, 0444); bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, 0444); static bool __read_mostly error_on_inconsistent_vmcs_config = true; module_param(error_on_inconsistent_vmcs_config, bool, 0444); static bool __read_mostly dump_invalid_vmcs = 0; module_param(dump_invalid_vmcs, bool, 0644); #define MSR_BITMAP_MODE_X2APIC 1 #define MSR_BITMAP_MODE_X2APIC_APICV 2 #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL /* Guest_tsc -> host_tsc conversion requires 64-bit division. */ static int __read_mostly cpu_preemption_timer_multi; static bool __read_mostly enable_preemption_timer = 1; #ifdef CONFIG_X86_64 module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); #endif extern bool __read_mostly allow_smaller_maxphyaddr; module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); module_param(enable_mediated_pmu, bool, 0444); #define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE #define KVM_VM_CR0_ALWAYS_ON \ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE) #define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE) #define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE) #define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM)) #define MSR_IA32_RTIT_STATUS_MASK (~(RTIT_STATUS_FILTEREN | \ RTIT_STATUS_CONTEXTEN | RTIT_STATUS_TRIGGEREN | \ RTIT_STATUS_ERROR | RTIT_STATUS_STOPPED | \ RTIT_STATUS_BYTECNT)) /* * These 2 parameters are used to config the controls for Pause-Loop Exiting: * ple_gap: upper bound on the amount of time between two successive * executions of PAUSE in a loop. Also indicate if ple enabled. * According to test, this time is usually smaller than 128 cycles. * ple_window: upper bound on the amount of time a guest is allowed to execute * in a PAUSE loop. Tests indicate that most spinlocks are held for * less than 2^12 cycles * Time is measured based on a counter that runs at the same rate as the TSC, * refer SDM volume 3b section 21.6.13 & 22.1.3. */ static unsigned int ple_gap = KVM_DEFAULT_PLE_GAP; module_param(ple_gap, uint, 0444); static unsigned int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; module_param(ple_window, uint, 0444); /* Default doubles per-vcpu window every exit. */ static unsigned int ple_window_grow = KVM_DEFAULT_PLE_WINDOW_GROW; module_param(ple_window_grow, uint, 0444); /* Default resets per-vcpu window every exit to ple_window. */ static unsigned int ple_window_shrink = KVM_DEFAULT_PLE_WINDOW_SHRINK; module_param(ple_window_shrink, uint, 0444); /* Default is to compute the maximum so we can never overflow. */ static unsigned int ple_window_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX; module_param(ple_window_max, uint, 0444); /* Default is SYSTEM mode, 1 for host-guest mode (which is BROKEN) */ int __read_mostly pt_mode = PT_MODE_SYSTEM; #ifdef CONFIG_BROKEN module_param(pt_mode, int, S_IRUGO); #endif struct x86_pmu_lbr __ro_after_init vmx_lbr_caps; #ifdef CONFIG_CPU_MITIGATIONS static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); static DEFINE_MUTEX(vmx_l1d_flush_mutex); /* Storage for pre module init parameter parsing */ static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO; static const struct { const char *option; bool for_parse; } vmentry_l1d_param[] = { [VMENTER_L1D_FLUSH_AUTO] = {"auto", true}, [VMENTER_L1D_FLUSH_NEVER] = {"never", true}, [VMENTER_L1D_FLUSH_COND] = {"cond", true}, [VMENTER_L1D_FLUSH_ALWAYS] = {"always", true}, [VMENTER_L1D_FLUSH_EPT_DISABLED] = {"EPT disabled", false}, [VMENTER_L1D_FLUSH_NOT_REQUIRED] = {"not required", false}, }; #define L1D_CACHE_ORDER 4 static void *vmx_l1d_flush_pages; static int __vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) { struct page *page; unsigned int i; if (!boot_cpu_has_bug(X86_BUG_L1TF)) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; return 0; } if (!enable_ept) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED; return 0; } if (kvm_host.arch_capabilities & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; return 0; } /* If set to auto use the default l1tf mitigation method */ if (l1tf == VMENTER_L1D_FLUSH_AUTO) { switch (l1tf_mitigation) { case L1TF_MITIGATION_OFF: l1tf = VMENTER_L1D_FLUSH_NEVER; break; case L1TF_MITIGATION_AUTO: case L1TF_MITIGATION_FLUSH_NOWARN: case L1TF_MITIGATION_FLUSH: case L1TF_MITIGATION_FLUSH_NOSMT: l1tf = VMENTER_L1D_FLUSH_COND; break; case L1TF_MITIGATION_FULL: case L1TF_MITIGATION_FULL_FORCE: l1tf = VMENTER_L1D_FLUSH_ALWAYS; break; } } else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) { l1tf = VMENTER_L1D_FLUSH_ALWAYS; } if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages && !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) { /* * This allocation for vmx_l1d_flush_pages is not tied to a VM * lifetime and so should not be charged to a memcg. */ page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER); if (!page) return -ENOMEM; vmx_l1d_flush_pages = page_address(page); /* * Initialize each page with a different pattern in * order to protect against KSM in the nested * virtualization case. */ for (i = 0; i < 1u << L1D_CACHE_ORDER; ++i) { memset(vmx_l1d_flush_pages + i * PAGE_SIZE, i + 1, PAGE_SIZE); } } l1tf_vmx_mitigation = l1tf; if (l1tf != VMENTER_L1D_FLUSH_NEVER) static_branch_enable(&vmx_l1d_should_flush); else static_branch_disable(&vmx_l1d_should_flush); if (l1tf == VMENTER_L1D_FLUSH_COND) static_branch_enable(&vmx_l1d_flush_cond); else static_branch_disable(&vmx_l1d_flush_cond); return 0; } static int vmx_setup_l1d_flush(void) { /* * Hand the parameter mitigation value in which was stored in the pre * module init parser. If no parameter was given, it will contain * 'auto' which will be turned into the default 'cond' mitigation mode. */ return __vmx_setup_l1d_flush(vmentry_l1d_flush_param); } static void vmx_cleanup_l1d_flush(void) { if (vmx_l1d_flush_pages) { free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER); vmx_l1d_flush_pages = NULL; } /* Restore state so sysfs ignores VMX */ l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; } static int vmentry_l1d_flush_parse(const char *s) { unsigned int i; if (s) { for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) { if (vmentry_l1d_param[i].for_parse && sysfs_streq(s, vmentry_l1d_param[i].option)) return i; } } return -EINVAL; } static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) { int l1tf, ret; l1tf = vmentry_l1d_flush_parse(s); if (l1tf < 0) return l1tf; if (!boot_cpu_has(X86_BUG_L1TF)) return 0; /* * Has vmx_init() run already? If not then this is the pre init * parameter parsing. In that case just store the value and let * vmx_init() do the proper setup after enable_ept has been * established. */ if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) { vmentry_l1d_flush_param = l1tf; return 0; } mutex_lock(&vmx_l1d_flush_mutex); ret = __vmx_setup_l1d_flush(l1tf); mutex_unlock(&vmx_l1d_flush_mutex); return ret; } static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) { if (WARN_ON_ONCE(l1tf_vmx_mitigation >= ARRAY_SIZE(vmentry_l1d_param))) return sysfs_emit(s, "???\n"); return sysfs_emit(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); } /* * Software based L1D cache flush which is used when microcode providing * the cache control MSR is not loaded. * * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to * flush it is required to read in 64 KiB because the replacement algorithm * is not exactly LRU. This could be sized at runtime via topology * information but as all relevant affected CPUs have 32KiB L1D cache size * there is no point in doing so. */ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) { int size = PAGE_SIZE << L1D_CACHE_ORDER; if (!static_branch_unlikely(&vmx_l1d_should_flush)) return; /* * This code is only executed when the flush mode is 'cond' or * 'always' */ if (static_branch_likely(&vmx_l1d_flush_cond)) { /* * Clear the per-cpu flush bit, it gets set again if the vCPU * is reloaded, i.e. if the vCPU is scheduled out or if KVM * exits to userspace, or if KVM reaches one of the unsafe * VMEXIT handlers, e.g. if KVM calls into the emulator, * or from the interrupt handlers. */ if (!kvm_get_cpu_l1tf_flush_l1d()) return; kvm_clear_cpu_l1tf_flush_l1d(); } vcpu->stat.l1d_flush++; if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) { native_wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH); return; } asm volatile( /* First ensure the pages are in the TLB */ "xorl %%eax, %%eax\n" ".Lpopulate_tlb:\n\t" "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" "addl $4096, %%eax\n\t" "cmpl %%eax, %[size]\n\t" "jne .Lpopulate_tlb\n\t" "xorl %%eax, %%eax\n\t" "cpuid\n\t" /* Now fill the cache */ "xorl %%eax, %%eax\n" ".Lfill_cache:\n" "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" "addl $64, %%eax\n\t" "cmpl %%eax, %[size]\n\t" "jne .Lfill_cache\n\t" "lfence\n" :: [flush_pages] "r" (vmx_l1d_flush_pages), [size] "r" (size) : "eax", "ebx", "ecx", "edx"); } #else /* CONFIG_CPU_MITIGATIONS*/ static int vmx_setup_l1d_flush(void) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NEVER; return 0; } static void vmx_cleanup_l1d_flush(void) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; } static __always_inline void vmx_l1d_flush(struct kvm_vcpu *vcpu) { } static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) { pr_warn_once("Kernel compiled without mitigations, ignoring vmentry_l1d_flush\n"); return 0; } static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) { return sysfs_emit(s, "never\n"); } #endif static const struct kernel_param_ops vmentry_l1d_flush_ops = { .set = vmentry_l1d_flush_set, .get = vmentry_l1d_flush_get, }; module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644); static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) { u64 msr; if (!vmx->disable_fb_clear) return; msr = native_rdmsrq(MSR_IA32_MCU_OPT_CTRL); msr |= FB_CLEAR_DIS; native_wrmsrq(MSR_IA32_MCU_OPT_CTRL, msr); /* Cache the MSR value to avoid reading it later */ vmx->msr_ia32_mcu_opt_ctrl = msr; } static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) { if (!vmx->disable_fb_clear) return; vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; native_wrmsrq(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); } static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { /* * Disable VERW's behavior of clearing CPU buffers for the guest if the * CPU isn't affected by MDS/TAA, and the host hasn't forcefully enabled * the mitigation. Disabling the clearing behavior provides a * performance boost for guests that aren't aware that manually clearing * CPU buffers is unnecessary, at the cost of MSR accesses on VM-Entry * and VM-Exit. */ vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && (kvm_host.arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && !boot_cpu_has_bug(X86_BUG_MDS) && !boot_cpu_has_bug(X86_BUG_TAA); /* * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS * at VMEntry. Skip the MSR read/write when a guest has no use case to * execute VERW. */ if ((vcpu->arch.arch_capabilities & ARCH_CAP_FB_CLEAR) || ((vcpu->arch.arch_capabilities & ARCH_CAP_MDS_NO) && (vcpu->arch.arch_capabilities & ARCH_CAP_TAA_NO) && (vcpu->arch.arch_capabilities & ARCH_CAP_PSDP_NO) && (vcpu->arch.arch_capabilities & ARCH_CAP_FBSDP_NO) && (vcpu->arch.arch_capabilities & ARCH_CAP_SBDR_SSDP_NO))) vmx->disable_fb_clear = false; } static u32 vmx_segment_access_rights(struct kvm_segment *var); void vmx_vmexit(void); #define vmx_insn_failed(fmt...) \ do { \ WARN_ONCE(1, fmt); \ pr_warn_ratelimited(fmt); \ } while (0) noinline void vmread_error(unsigned long field) { vmx_insn_failed("vmread failed: field=%lx\n", field); } #ifndef CONFIG_CC_HAS_ASM_GOTO_OUTPUT noinstr void vmread_error_trampoline2(unsigned long field, bool fault) { if (fault) { kvm_spurious_fault(); } else { instrumentation_begin(); vmread_error(field); instrumentation_end(); } } #endif noinline void vmwrite_error(unsigned long field, unsigned long value) { vmx_insn_failed("vmwrite failed: field=%lx val=%lx err=%u\n", field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr) { vmx_insn_failed("vmclear failed: %p/%llx err=%u\n", vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr) { vmx_insn_failed("vmptrld failed: %p/%llx err=%u\n", vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva) { vmx_insn_failed("invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", ext, vpid, gva); } noinline void invept_error(unsigned long ext, u64 eptp) { vmx_insn_failed("invept failed: ext=0x%lx eptp=%llx\n", ext, eptp); } DEFINE_PER_CPU(struct vmcs *, current_vmcs); /* * We maintain a per-CPU linked-list of VMCS loaded on that CPU. This is needed * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it. */ static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS); static DEFINE_SPINLOCK(vmx_vpid_lock); struct vmcs_config vmcs_config __ro_after_init; struct vmx_capability vmx_capability __ro_after_init; #define VMX_SEGMENT_FIELD(seg) \ [VCPU_SREG_##seg] = { \ .selector = GUEST_##seg##_SELECTOR, \ .base = GUEST_##seg##_BASE, \ .limit = GUEST_##seg##_LIMIT, \ .ar_bytes = GUEST_##seg##_AR_BYTES, \ } static const struct kvm_vmx_segment_field { unsigned selector; unsigned base; unsigned limit; unsigned ar_bytes; } kvm_vmx_segment_fields[] = { VMX_SEGMENT_FIELD(CS), VMX_SEGMENT_FIELD(DS), VMX_SEGMENT_FIELD(ES), VMX_SEGMENT_FIELD(FS), VMX_SEGMENT_FIELD(GS), VMX_SEGMENT_FIELD(SS), VMX_SEGMENT_FIELD(TR), VMX_SEGMENT_FIELD(LDTR), }; static unsigned long host_idt_base; #if IS_ENABLED(CONFIG_HYPERV) static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { struct hv_enlightened_vmcs *evmcs; hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu); if (partition_assist_page == INVALID_PAGE) return -ENOMEM; evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs; evmcs->partition_assist_page = partition_assist_page; evmcs->hv_vm_id = (unsigned long)vcpu->kvm; evmcs->hv_enlightenments_control.nested_flush_hypercall = 1; return 0; } static __init void hv_init_evmcs(void) { int cpu; if (!enlightened_vmcs) return; /* * Enlightened VMCS usage should be recommended and the host needs * to support eVMCS v1 or above. */ if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED && (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >= KVM_EVMCS_VERSION) { /* Check that we have assist pages on all online CPUs */ for_each_online_cpu(cpu) { if (!hv_get_vp_assist_page(cpu)) { enlightened_vmcs = false; break; } } if (enlightened_vmcs) { pr_info("Using Hyper-V Enlightened VMCS\n"); static_branch_enable(&__kvm_is_using_evmcs); } if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) vt_x86_ops.enable_l2_tlb_flush = hv_enable_l2_tlb_flush; } else { enlightened_vmcs = false; } } static void hv_reset_evmcs(void) { struct hv_vp_assist_page *vp_ap; if (!kvm_is_using_evmcs()) return; /* * KVM should enable eVMCS if and only if all CPUs have a VP assist * page, and should reject CPU onlining if eVMCS is enabled the CPU * doesn't have a VP assist page allocated. */ vp_ap = hv_get_vp_assist_page(smp_processor_id()); if (WARN_ON_ONCE(!vp_ap)) return; /* * Reset everything to support using non-enlightened VMCS access later * (e.g. when we reload the module with enlightened_vmcs=0) */ vp_ap->nested_control.features.directhypercall = 0; vp_ap->current_nested_vmcs = 0; vp_ap->enlighten_vmentry = 0; } #else /* IS_ENABLED(CONFIG_HYPERV) */ static void hv_init_evmcs(void) {} static void hv_reset_evmcs(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ /* * Comment's format: document - errata name - stepping - processor name. * Refer from * https://www.virtualbox.org/svn/vbox/trunk/src/VBox/VMM/VMMR0/HMR0.cpp */ static u32 vmx_preemption_cpu_tfms[] = { /* 323344.pdf - BA86 - D0 - Xeon 7500 Series */ 0x000206E6, /* 323056.pdf - AAX65 - C2 - Xeon L3406 */ /* 322814.pdf - AAT59 - C2 - i7-600, i5-500, i5-400 and i3-300 Mobile */ /* 322911.pdf - AAU65 - C2 - i5-600, i3-500 Desktop and Pentium G6950 */ 0x00020652, /* 322911.pdf - AAU65 - K0 - i5-600, i3-500 Desktop and Pentium G6950 */ 0x00020655, /* 322373.pdf - AAO95 - B1 - Xeon 3400 Series */ /* 322166.pdf - AAN92 - B1 - i7-800 and i5-700 Desktop */ /* * 320767.pdf - AAP86 - B1 - * i7-900 Mobile Extreme, i7-800 and i7-700 Mobile */ 0x000106E5, /* 321333.pdf - AAM126 - C0 - Xeon 3500 */ 0x000106A0, /* 321333.pdf - AAM126 - C1 - Xeon 3500 */ 0x000106A1, /* 320836.pdf - AAJ124 - C0 - i7-900 Desktop Extreme and i7-900 Desktop */ 0x000106A4, /* 321333.pdf - AAM126 - D0 - Xeon 3500 */ /* 321324.pdf - AAK139 - D0 - Xeon 5500 */ /* 320836.pdf - AAJ124 - D0 - i7-900 Extreme and i7-900 Desktop */ 0x000106A5, /* Xeon E3-1220 V2 */ 0x000306A8, }; static inline bool cpu_has_broken_vmx_preemption_timer(void) { u32 eax = cpuid_eax(0x00000001), i; /* Clear the reserved bits */ eax &= ~(0x3U << 14 | 0xfU << 28); for (i = 0; i < ARRAY_SIZE(vmx_preemption_cpu_tfms); i++) if (eax == vmx_preemption_cpu_tfms[i]) return true; return false; } static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu) { return flexpriority_enabled && lapic_in_kernel(vcpu); } struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) { int i; i = kvm_find_user_return_msr(msr); if (i >= 0) return &vmx->guest_uret_msrs[i]; return NULL; } static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, struct vmx_uret_msr *msr, u64 data) { unsigned int slot = msr - vmx->guest_uret_msrs; int ret = 0; if (msr->load_into_hardware) { preempt_disable(); ret = kvm_set_user_return_msr(slot, data, msr->mask); preempt_enable(); } if (!ret) msr->data = data; return ret; } void vmx_emergency_disable_virtualization_cpu(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), loaded_vmcss_on_cpu_link) { vmcs_clear(v->vmcs); if (v->shadow_vmcs) vmcs_clear(v->shadow_vmcs); } } static void __loaded_vmcs_clear(void *arg) { struct loaded_vmcs *loaded_vmcs = arg; int cpu = raw_smp_processor_id(); if (loaded_vmcs->cpu != cpu) return; /* vcpu migration can race with cpu offline */ if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs) per_cpu(current_vmcs, cpu) = NULL; vmcs_clear(loaded_vmcs->vmcs); if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched) vmcs_clear(loaded_vmcs->shadow_vmcs); list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link); /* * Ensure all writes to loaded_vmcs, including deleting it from its * current percpu list, complete before setting loaded_vmcs->cpu to * -1, otherwise a different cpu can see loaded_vmcs->cpu == -1 first * and add loaded_vmcs to its percpu list before it's deleted from this * cpu's list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs(). */ smp_wmb(); loaded_vmcs->cpu = -1; loaded_vmcs->launched = 0; } static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) { int cpu = loaded_vmcs->cpu; if (cpu != -1) smp_call_function_single(cpu, __loaded_vmcs_clear, loaded_vmcs, 1); } static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg, unsigned field) { bool ret; u32 mask = 1 << (seg * SEG_FIELD_NR + field); if (!kvm_register_is_available(&vmx->vcpu, VCPU_REG_SEGMENTS)) { kvm_register_mark_available(&vmx->vcpu, VCPU_REG_SEGMENTS); vmx->segment_cache.bitmask = 0; } ret = vmx->segment_cache.bitmask & mask; vmx->segment_cache.bitmask |= mask; return ret; } static u16 vmx_read_guest_seg_selector(struct vcpu_vmx *vmx, unsigned seg) { u16 *p = &vmx->segment_cache.seg[seg].selector; if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_SEL)) *p = vmcs_read16(kvm_vmx_segment_fields[seg].selector); return *p; } static ulong vmx_read_guest_seg_base(struct vcpu_vmx *vmx, unsigned seg) { ulong *p = &vmx->segment_cache.seg[seg].base; if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_BASE)) *p = vmcs_readl(kvm_vmx_segment_fields[seg].base); return *p; } static u32 vmx_read_guest_seg_limit(struct vcpu_vmx *vmx, unsigned seg) { u32 *p = &vmx->segment_cache.seg[seg].limit; if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_LIMIT)) *p = vmcs_read32(kvm_vmx_segment_fields[seg].limit); return *p; } static u32 vmx_read_guest_seg_ar(struct vcpu_vmx *vmx, unsigned seg) { u32 *p = &vmx->segment_cache.seg[seg].ar; if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_AR)) *p = vmcs_read32(kvm_vmx_segment_fields[seg].ar_bytes); return *p; } void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) { u32 eb; eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); /* * #VE isn't used for VMX. To test against unexpected changes * related to #VE for VMX, intercept unexpected #VE and warn on it. */ if (IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE)) eb |= 1u << VE_VECTOR; /* * Guest access to VMware backdoor ports could legitimately * trigger #GP because of TSS I/O permission bitmap. * We intercept those #GP and allow access to them anyway * as VMware does. */ if (enable_vmware_backdoor) eb |= (1u << GP_VECTOR); if ((vcpu->guest_debug & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) eb |= 1u << BP_VECTOR; if (to_vmx(vcpu)->rmode.vm86_active) eb = ~0; if (!vmx_need_pf_intercept(vcpu)) eb &= ~(1u << PF_VECTOR); /* When we are running a nested L2 guest and L1 specified for it a * certain exception bitmap, we must trap the same exceptions and pass * them to L1. When running L2, we will only handle the exceptions * specified above if L1 did not want them. */ if (is_guest_mode(vcpu)) eb |= get_vmcs12(vcpu)->exception_bitmap; else { int mask = 0, match = 0; if (enable_ept && (eb & (1u << PF_VECTOR))) { /* * If EPT is enabled, #PF is currently only intercepted * if MAXPHYADDR is smaller on the guest than on the * host. In that case we only care about present, * non-reserved faults. For vmcs02, however, PFEC_MASK * and PFEC_MATCH are set in prepare_vmcs02_rare. */ mask = PFERR_PRESENT_MASK | PFERR_RSVD_MASK; match = PFERR_PRESENT_MASK; } vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, mask); vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, match); } /* * Disabling xfd interception indicates that dynamic xfeatures * might be used in the guest. Always trap #NM in this case * to save guest xfd_err timely. */ if (vcpu->arch.xfd_no_write_intercept) eb |= (1u << NM_VECTOR); vmcs_write32(EXCEPTION_BITMAP, eb); } /* * Check if MSR is intercepted for currently loaded MSR bitmap. */ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr) { if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS)) return true; return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, msr); } unsigned int __vmx_vcpu_enter_flags(struct vcpu_vmx *vmx) { unsigned int flags = 0; if (vmx->loaded_vmcs->launched) flags |= KVM_ENTER_VMRESUME; /* * If writes to the SPEC_CTRL MSR aren't intercepted, the guest is free * to change it directly without causing a vmexit. In that case read * it after vmexit and store it in vmx->spec_ctrl. */ if (!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)) flags |= KVM_ENTER_SAVE_SPEC_CTRL; if (cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF_VM_MMIO) && kvm_vcpu_can_access_host_mmio(&vmx->vcpu)) flags |= KVM_ENTER_CLEAR_CPU_BUFFERS_FOR_MMIO; return flags; } static __always_inline void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { vm_entry_controls_clearbit(vmx, entry); vm_exit_controls_clearbit(vmx, exit); } static int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr) { unsigned int i; for (i = 0; i < m->nr; ++i) { if (m->val[i].index == msr) return i; } return -ENOENT; } static void vmx_remove_auto_msr(struct vmx_msrs *m, u32 msr, unsigned long vmcs_count_field) { int i; i = vmx_find_loadstore_msr_slot(m, msr); if (i < 0) return; --m->nr; m->val[i] = m->val[m->nr]; vmcs_write32(vmcs_count_field, m->nr); } static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) { struct msr_autoload *m = &vmx->msr_autoload; switch (msr) { case MSR_EFER: if (cpu_has_load_ia32_efer()) { clear_atomic_switch_msr_special(vmx, VM_ENTRY_LOAD_IA32_EFER, VM_EXIT_LOAD_IA32_EFER); return; } break; case MSR_CORE_PERF_GLOBAL_CTRL: if (cpu_has_load_perf_global_ctrl()) { clear_atomic_switch_msr_special(vmx, VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL); return; } break; } vmx_remove_auto_msr(&m->guest, msr, VM_ENTRY_MSR_LOAD_COUNT); vmx_remove_auto_msr(&m->host, msr, VM_EXIT_MSR_LOAD_COUNT); } static __always_inline void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit, unsigned long guest_val_vmcs, unsigned long host_val_vmcs, u64 guest_val, u64 host_val) { vmcs_write64(guest_val_vmcs, guest_val); if (host_val_vmcs != HOST_IA32_EFER) vmcs_write64(host_val_vmcs, host_val); vm_entry_controls_setbit(vmx, entry); vm_exit_controls_setbit(vmx, exit); } static void vmx_add_auto_msr(struct vmx_msrs *m, u32 msr, u64 value, unsigned long vmcs_count_field, struct kvm *kvm) { int i; i = vmx_find_loadstore_msr_slot(m, msr); if (i < 0) { if (KVM_BUG_ON(m->nr == MAX_NR_LOADSTORE_MSRS, kvm)) return; i = m->nr++; m->val[i].index = msr; vmcs_write32(vmcs_count_field, m->nr); } m->val[i].value = value; } static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, u64 guest_val, u64 host_val) { struct msr_autoload *m = &vmx->msr_autoload; struct kvm *kvm = vmx->vcpu.kvm; switch (msr) { case MSR_EFER: if (cpu_has_load_ia32_efer()) { add_atomic_switch_msr_special(vmx, VM_ENTRY_LOAD_IA32_EFER, VM_EXIT_LOAD_IA32_EFER, GUEST_IA32_EFER, HOST_IA32_EFER, guest_val, host_val); return; } break; case MSR_CORE_PERF_GLOBAL_CTRL: if (cpu_has_load_perf_global_ctrl()) { add_atomic_switch_msr_special(vmx, VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL, GUEST_IA32_PERF_GLOBAL_CTRL, HOST_IA32_PERF_GLOBAL_CTRL, guest_val, host_val); return; } break; case MSR_IA32_PEBS_ENABLE: /* PEBS needs a quiescent period after being disabled (to write * a record). Disabling PEBS through VMX MSR swapping doesn't * provide that period, so a CPU could write host's record into * guest's memory. */ wrmsrq(MSR_IA32_PEBS_ENABLE, 0); } vmx_add_auto_msr(&m->guest, msr, guest_val, VM_ENTRY_MSR_LOAD_COUNT, kvm); vmx_add_auto_msr(&m->host, msr, host_val, VM_EXIT_MSR_LOAD_COUNT, kvm); } static bool update_transition_efer(struct vcpu_vmx *vmx) { u64 guest_efer = vmx->vcpu.arch.efer; u64 ignore_bits = 0; int i; /* Shadow paging assumes NX to be available. */ if (!enable_ept) guest_efer |= EFER_NX; /* * LMA and LME handled by hardware; SCE meaningless outside long mode. */ ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif /* * On EPT, we can't emulate NX, so we must switch EFER atomically. * On CPUs that support "load IA32_EFER", always switch EFER * atomically, since it's faster than switching it manually. */ if (cpu_has_load_ia32_efer() || (enable_ept && ((vmx->vcpu.arch.efer ^ kvm_host.efer) & EFER_NX))) { if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != kvm_host.efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, kvm_host.efer); else clear_atomic_switch_msr(vmx, MSR_EFER); return false; } i = kvm_find_user_return_msr(MSR_EFER); if (i < 0) return false; clear_atomic_switch_msr(vmx, MSR_EFER); guest_efer &= ~ignore_bits; guest_efer |= kvm_host.efer & ignore_bits; vmx->guest_uret_msrs[i].data = guest_efer; vmx->guest_uret_msrs[i].mask = ~ignore_bits; return true; } static void vmx_add_autostore_msr(struct vcpu_vmx *vmx, u32 msr) { vmx_add_auto_msr(&vmx->msr_autostore, msr, 0, VM_EXIT_MSR_STORE_COUNT, vmx->vcpu.kvm); } static void vmx_remove_autostore_msr(struct vcpu_vmx *vmx, u32 msr) { vmx_remove_auto_msr(&vmx->msr_autostore, msr, VM_EXIT_MSR_STORE_COUNT); } #ifdef CONFIG_X86_32 /* * On 32-bit kernels, VM exits still load the FS and GS bases from the * VMCS rather than the segment table. KVM uses this helper to figure * out the current bases to poke them into the VMCS before entry. */ static unsigned long segment_base(u16 selector) { struct desc_struct *table; unsigned long v; if (!(selector & ~SEGMENT_RPL_MASK)) return 0; table = get_current_gdt_ro(); if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) { u16 ldt_selector = kvm_read_ldt(); if (!(ldt_selector & ~SEGMENT_RPL_MASK)) return 0; table = (struct desc_struct *)segment_base(ldt_selector); } v = get_desc_base(&table[selector >> 3]); return v; } #endif static inline bool pt_can_write_msr(struct vcpu_vmx *vmx) { return vmx_pt_mode_is_host_guest() && !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN); } static inline bool pt_output_base_valid(struct kvm_vcpu *vcpu, u64 base) { /* The base must be 128-byte aligned and a legal physical address. */ return kvm_vcpu_is_legal_aligned_gpa(vcpu, base, 128); } static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range) { u32 i; wrmsrq(MSR_IA32_RTIT_STATUS, ctx->status); wrmsrq(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); wrmsrq(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); wrmsrq(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); for (i = 0; i < addr_range; i++) { wrmsrq(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); wrmsrq(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); } } static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range) { u32 i; rdmsrq(MSR_IA32_RTIT_STATUS, ctx->status); rdmsrq(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); rdmsrq(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); rdmsrq(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); for (i = 0; i < addr_range; i++) { rdmsrq(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); rdmsrq(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); } } static void pt_guest_enter(struct vcpu_vmx *vmx) { if (vmx_pt_mode_is_system()) return; /* * GUEST_IA32_RTIT_CTL is already set in the VMCS. * Save host state before VM entry. */ rdmsrq(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { wrmsrq(MSR_IA32_RTIT_CTL, 0); pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.num_address_ranges); pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.num_address_ranges); } } static void pt_guest_exit(struct vcpu_vmx *vmx) { if (vmx_pt_mode_is_system()) return; if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.num_address_ranges); pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.num_address_ranges); } /* * KVM requires VM_EXIT_CLEAR_IA32_RTIT_CTL to expose PT to the guest, * i.e. RTIT_CTL is always cleared on VM-Exit. Restore it if necessary. */ if (vmx->pt_desc.host.ctl) wrmsrq(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); } void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, unsigned long fs_base, unsigned long gs_base) { if (unlikely(fs_sel != host->fs_sel)) { if (!(fs_sel & 7)) vmcs_write16(HOST_FS_SELECTOR, fs_sel); else vmcs_write16(HOST_FS_SELECTOR, 0); host->fs_sel = fs_sel; } if (unlikely(gs_sel != host->gs_sel)) { if (!(gs_sel & 7)) vmcs_write16(HOST_GS_SELECTOR, gs_sel); else vmcs_write16(HOST_GS_SELECTOR, 0); host->gs_sel = gs_sel; } if (unlikely(fs_base != host->fs_base)) { vmcs_writel(HOST_FS_BASE, fs_base); host->fs_base = fs_base; } if (unlikely(gs_base != host->gs_base)) { vmcs_writel(HOST_GS_BASE, gs_base); host->gs_base = gs_base; } } void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vcpu_vt *vt = to_vt(vcpu); struct vmcs_host_state *host_state; #ifdef CONFIG_X86_64 int cpu = raw_smp_processor_id(); #endif unsigned long fs_base, gs_base; u16 fs_sel, gs_sel; int i; /* * Note that guest MSRs to be saved/restored can also be changed * when guest state is loaded. This happens when guest transitions * to/from long-mode by setting MSR_EFER.LMA. */ if (!vmx->guest_uret_msrs_loaded) { vmx->guest_uret_msrs_loaded = true; for (i = 0; i < kvm_nr_uret_msrs; ++i) { if (!vmx->guest_uret_msrs[i].load_into_hardware) continue; kvm_set_user_return_msr(i, vmx->guest_uret_msrs[i].data, vmx->guest_uret_msrs[i].mask); } } if (vmx->nested.need_vmcs12_to_shadow_sync) nested_sync_vmcs12_to_shadow(vcpu); if (vt->guest_state_loaded) return; host_state = &vmx->loaded_vmcs->host_state; /* * Set host fs and gs selectors. Unfortunately, 22.2.3 does not * allow segment selectors with cpl > 0 or ti == 1. */ host_state->ldt_sel = kvm_read_ldt(); #ifdef CONFIG_X86_64 savesegment(ds, host_state->ds_sel); savesegment(es, host_state->es_sel); gs_base = cpu_kernelmode_gs_base(cpu); if (likely(is_64bit_mm(current->mm))) { current_save_fsgs(); fs_sel = current->thread.fsindex; gs_sel = current->thread.gsindex; fs_base = current->thread.fsbase; vt->msr_host_kernel_gs_base = current->thread.gsbase; } else { savesegment(fs, fs_sel); savesegment(gs, gs_sel); fs_base = read_msr(MSR_FS_BASE); vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); } wrmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #else savesegment(fs, fs_sel); savesegment(gs, gs_sel); fs_base = segment_base(fs_sel); gs_base = segment_base(gs_sel); #endif vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); vt->guest_state_loaded = true; } static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) { struct vmcs_host_state *host_state; if (!vmx->vt.guest_state_loaded) return; host_state = &vmx->loaded_vmcs->host_state; ++vmx->vcpu.stat.host_state_reload; #ifdef CONFIG_X86_64 rdmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #endif if (host_state->ldt_sel || (host_state->gs_sel & 7)) { kvm_load_ldt(host_state->ldt_sel); #ifdef CONFIG_X86_64 load_gs_index(host_state->gs_sel); #else loadsegment(gs, host_state->gs_sel); #endif } if (host_state->fs_sel & 7) loadsegment(fs, host_state->fs_sel); #ifdef CONFIG_X86_64 if (unlikely(host_state->ds_sel | host_state->es_sel)) { loadsegment(ds, host_state->ds_sel); loadsegment(es, host_state->es_sel); } #endif invalidate_tss_limit(); #ifdef CONFIG_X86_64 wrmsrq(MSR_KERNEL_GS_BASE, vmx->vt.msr_host_kernel_gs_base); #endif load_fixmap_gdt(raw_smp_processor_id()); vmx->vt.guest_state_loaded = false; vmx->guest_uret_msrs_loaded = false; } #ifdef CONFIG_X86_64 static u64 vmx_read_guest_host_msr(struct vcpu_vmx *vmx, u32 msr, u64 *cache) { preempt_disable(); if (vmx->vt.guest_state_loaded) *cache = read_msr(msr); preempt_enable(); return *cache; } static void vmx_write_guest_host_msr(struct vcpu_vmx *vmx, u32 msr, u64 data, u64 *cache) { preempt_disable(); if (vmx->vt.guest_state_loaded) wrmsrns(msr, data); preempt_enable(); *cache = data; } static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) { return vmx_read_guest_host_msr(vmx, MSR_KERNEL_GS_BASE, &vmx->msr_guest_kernel_gs_base); } static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data) { vmx_write_guest_host_msr(vmx, MSR_KERNEL_GS_BASE, data, &vmx->msr_guest_kernel_gs_base); } #endif static void grow_ple_window(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned int old = vmx->ple_window; vmx->ple_window = __grow_ple_window(old, ple_window, ple_window_grow, ple_window_max); if (vmx->ple_window != old) { vmx->ple_window_dirty = true; trace_kvm_ple_window_update(vcpu->vcpu_id, vmx->ple_window, old); } } static void shrink_ple_window(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned int old = vmx->ple_window; vmx->ple_window = __shrink_ple_window(old, ple_window, ple_window_shrink, ple_window); if (vmx->ple_window != old) { vmx->ple_window_dirty = true; trace_kvm_ple_window_update(vcpu->vcpu_id, vmx->ple_window, old); } } void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool already_loaded = vmx->loaded_vmcs->cpu == cpu; struct vmcs *prev; if (!already_loaded) { loaded_vmcs_clear(vmx->loaded_vmcs); local_irq_disable(); /* * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to * this cpu's percpu list, otherwise it may not yet be deleted * from its previous cpu's percpu list. Pairs with the * smb_wmb() in __loaded_vmcs_clear(). */ smp_rmb(); list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link, &per_cpu(loaded_vmcss_on_cpu, cpu)); local_irq_enable(); } prev = per_cpu(current_vmcs, cpu); if (prev != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); } if (!already_loaded) { void *gdt = get_current_gdt_ro(); /* * Flush all EPTP/VPID contexts, the new pCPU may have stale * TLB entries from its previous association with the vCPU. */ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); /* * Linux uses per-cpu TSS and GDT, so set these when switching * processors. See 22.2.4. */ vmcs_writel(HOST_TR_BASE, (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ if (IS_ENABLED(CONFIG_IA32_EMULATION) || IS_ENABLED(CONFIG_X86_32)) { /* 22.2.3 */ vmcs_writel(HOST_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1)); } vmx->loaded_vmcs->cpu = cpu; } } /* * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. */ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm)) shrink_ple_window(vcpu); vmx_vcpu_load_vmcs(vcpu, cpu); vmx_vcpu_pi_load(vcpu, cpu); } void vmx_vcpu_put(struct kvm_vcpu *vcpu) { vmx_vcpu_pi_put(vcpu); vmx_prepare_switch_to_host(to_vmx(vcpu)); } static void vmx_switch_loaded_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) { struct vcpu_vmx *vmx = to_vmx(vcpu); int cpu; cpu = get_cpu(); vmx->loaded_vmcs = vmcs; vmx_vcpu_load_vmcs(vcpu, cpu); put_cpu(); } static void vmx_load_vmcs01(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (!is_guest_mode(vcpu)) { WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01); return; } WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->nested.vmcs02); vmx_switch_loaded_vmcs(vcpu, &vmx->vmcs01); } static void vmx_put_vmcs01(struct kvm_vcpu *vcpu) { if (!is_guest_mode(vcpu)) return; vmx_switch_loaded_vmcs(vcpu, &to_vmx(vcpu)->nested.vmcs02); } DEFINE_GUARD(vmx_vmcs01, struct kvm_vcpu *, vmx_load_vmcs01(_T), vmx_put_vmcs01(_T)) bool vmx_emulation_required(struct kvm_vcpu *vcpu) { return emulate_invalid_guest_state && !vmx_guest_state_valid(vcpu); } unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long rflags, save_rflags; if (!kvm_register_is_available(vcpu, VCPU_REG_RFLAGS)) { kvm_register_mark_available(vcpu, VCPU_REG_RFLAGS); rflags = vmcs_readl(GUEST_RFLAGS); if (vmx->rmode.vm86_active) { rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS; save_rflags = vmx->rmode.save_rflags; rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; } vmx->rflags = rflags; } return vmx->rflags; } void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long old_rflags; /* * Unlike CR0 and CR4, RFLAGS handling requires checking if the vCPU * is an unrestricted guest in order to mark L2 as needing emulation * if L1 runs L2 as a restricted guest. */ if (is_unrestricted_guest(vcpu)) { kvm_register_mark_available(vcpu, VCPU_REG_RFLAGS); vmx->rflags = rflags; vmcs_writel(GUEST_RFLAGS, rflags); return; } old_rflags = vmx_get_rflags(vcpu); vmx->rflags = rflags; if (vmx->rmode.vm86_active) { vmx->rmode.save_rflags = rflags; rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; } vmcs_writel(GUEST_RFLAGS, rflags); if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) vmx->vt.emulation_required = vmx_emulation_required(vcpu); } bool vmx_get_if_flag(struct kvm_vcpu *vcpu) { return vmx_get_rflags(vcpu) & X86_EFLAGS_IF; } u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) { u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); int ret = 0; if (interruptibility & GUEST_INTR_STATE_STI) ret |= KVM_X86_SHADOW_INT_STI; if (interruptibility & GUEST_INTR_STATE_MOV_SS) ret |= KVM_X86_SHADOW_INT_MOV_SS; return ret; } void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) { u32 interruptibility_old = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); u32 interruptibility = interruptibility_old; interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS); if (mask & KVM_X86_SHADOW_INT_MOV_SS) interruptibility |= GUEST_INTR_STATE_MOV_SS; else if (mask & KVM_X86_SHADOW_INT_STI) interruptibility |= GUEST_INTR_STATE_STI; if ((interruptibility != interruptibility_old)) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, interruptibility); } static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long value; /* * Any MSR write that attempts to change bits marked reserved will * case a #GP fault. */ if (data & vmx->pt_desc.ctl_bitmask) return 1; /* * Any attempt to modify IA32_RTIT_CTL while TraceEn is set will * result in a #GP unless the same write also clears TraceEn. */ if ((vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) && (data & RTIT_CTL_TRACEEN) && data != vmx->pt_desc.guest.ctl) return 1; /* * WRMSR to IA32_RTIT_CTL that sets TraceEn but clears this bit * and FabricEn would cause #GP, if * CPUID.(EAX=14H, ECX=0):ECX.SNGLRGNOUT[bit 2] = 0 */ if ((data & RTIT_CTL_TRACEEN) && !(data & RTIT_CTL_TOPA) && !(data & RTIT_CTL_FABRIC_EN) && !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_single_range_output)) return 1; /* * MTCFreq, CycThresh and PSBFreq encodings check, any MSR write that * utilize encodings marked reserved will cause a #GP fault. */ value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc_periods); if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc) && !test_bit((data & RTIT_CTL_MTC_RANGE) >> RTIT_CTL_MTC_RANGE_OFFSET, &value)) return 1; value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cycle_thresholds); if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc) && !test_bit((data & RTIT_CTL_CYC_THRESH) >> RTIT_CTL_CYC_THRESH_OFFSET, &value)) return 1; value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_periods); if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc) && !test_bit((data & RTIT_CTL_PSB_FREQ) >> RTIT_CTL_PSB_FREQ_OFFSET, &value)) return 1; /* * If ADDRx_CFG is reserved or the encodings is >2 will * cause a #GP fault. */ value = (data & RTIT_CTL_ADDR0) >> RTIT_CTL_ADDR0_OFFSET; if ((value && (vmx->pt_desc.num_address_ranges < 1)) || (value > 2)) return 1; value = (data & RTIT_CTL_ADDR1) >> RTIT_CTL_ADDR1_OFFSET; if ((value && (vmx->pt_desc.num_address_ranges < 2)) || (value > 2)) return 1; value = (data & RTIT_CTL_ADDR2) >> RTIT_CTL_ADDR2_OFFSET; if ((value && (vmx->pt_desc.num_address_ranges < 3)) || (value > 2)) return 1; value = (data & RTIT_CTL_ADDR3) >> RTIT_CTL_ADDR3_OFFSET; if ((value && (vmx->pt_desc.num_address_ranges < 4)) || (value > 2)) return 1; return 0; } int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does * not point at the failing instruction, and even if it did, the code * stream is inaccessible. Inject #UD instead of exiting to userspace * so that guest userspace can't DoS the guest simply by triggering * emulation (enclaves are CPL3 only). */ if (vmx_get_exit_reason(vcpu).enclave_mode) { kvm_queue_exception(vcpu, UD_VECTOR); return X86EMUL_PROPAGATE_FAULT; } /* Check that emulation is possible during event vectoring */ if ((to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && !kvm_can_emulate_event_vectoring(emul_type)) return X86EMUL_UNHANDLEABLE_VECTORING; return X86EMUL_CONTINUE; } static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu); unsigned long rip, orig_rip; u32 instr_len; /* * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on * undefined behavior: Intel's SDM doesn't mandate the VMCS field be * set when EPT misconfig occurs. In practice, real hardware updates * VM_EXIT_INSTRUCTION_LEN on EPT misconfig, but other hypervisors * (namely Hyper-V) don't set it due to it being undefined behavior, * i.e. we end up advancing IP with some random value. */ if (!static_cpu_has(X86_FEATURE_HYPERVISOR) || exit_reason.basic != EXIT_REASON_EPT_MISCONFIG) { instr_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); /* * Emulating an enclave's instructions isn't supported as KVM * cannot access the enclave's memory or its true RIP, e.g. the * vmcs.GUEST_RIP points at the exit point of the enclave, not * the RIP that actually triggered the VM-Exit. But, because * most instructions that cause VM-Exit will #UD in an enclave, * most instruction-based VM-Exits simply do not occur. * * There are a few exceptions, notably the debug instructions * INT1ICEBRK and INT3, as they are allowed in debug enclaves * and generate #DB/#BP as expected, which KVM might intercept. * But again, the CPU does the dirty work and saves an instr * length of zero so VMMs don't shoot themselves in the foot. * WARN if KVM tries to skip a non-zero length instruction on * a VM-Exit from an enclave. */ if (!instr_len) goto rip_updated; WARN_ONCE(exit_reason.enclave_mode, "skipping instruction after SGX enclave VM-Exit"); orig_rip = kvm_rip_read(vcpu); rip = orig_rip + instr_len; #ifdef CONFIG_X86_64 /* * We need to mask out the high 32 bits of RIP if not in 64-bit * mode, but just finding out that we are in 64-bit mode is * quite expensive. Only do it if there was a carry. */ if (unlikely(((rip ^ orig_rip) >> 31) == 3) && !is_64_bit_mode(vcpu)) rip = (u32)rip; #endif kvm_rip_write(vcpu, rip); } else { if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) return 0; } rip_updated: /* skipping an emulated instruction also counts */ vmx_set_interrupt_shadow(vcpu, 0); return 1; } /* * Recognizes a pending MTF VM-exit and records the nested state for later * delivery. */ void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); if (!is_guest_mode(vcpu)) return; /* * Per the SDM, MTF takes priority over debug-trap exceptions besides * TSS T-bit traps and ICEBP (INT1). KVM doesn't emulate T-bit traps * or ICEBP (in the emulator proper), and skipping of ICEBP after an * intercepted #DB deliberately avoids single-step #DB and MTF updates * as ICEBP is higher priority than both. As instruction emulation is * completed at this point (i.e. KVM is at the instruction boundary), * any #DB exception pending delivery must be a debug-trap of lower * priority than MTF. Record the pending MTF state to be delivered in * vmx_check_nested_events(). */ if (nested_cpu_has_mtf(vmcs12) && (!vcpu->arch.exception.pending || vcpu->arch.exception.vector == DB_VECTOR) && (!vcpu->arch.exception_vmexit.pending || vcpu->arch.exception_vmexit.vector == DB_VECTOR)) { vmx->nested.mtf_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); } else { vmx->nested.mtf_pending = false; } } int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) { vmx_update_emulated_instruction(vcpu); return skip_emulated_instruction(vcpu); } static void vmx_clear_hlt(struct kvm_vcpu *vcpu) { /* * Ensure that we clear the HLT state in the VMCS. We don't need to * explicitly skip the instruction because if the HLT state is set, * then the instruction is already executing and RIP has already been * advanced. */ if (kvm_hlt_in_guest(vcpu->kvm) && vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); } void vmx_inject_exception(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; struct vcpu_vmx *vmx = to_vmx(vcpu); /* * When injecting a #DB, single-stepping is enabled in RFLAGS, and STI * or MOV-SS blocking is active, set vmcs.PENDING_DBG_EXCEPTIONS.BS to * prevent a false positive from VM-Entry consistency check. VM-Entry * asserts that a single-step #DB _must_ be pending in this scenario, * as the previous instruction cannot have toggled RFLAGS.TF 0=>1 * (because STI and POP/MOV don't modify RFLAGS), therefore the one * instruction delay when activating single-step breakpoints must have * already expired. However, the CPU isn't smart enough to peek at * vmcs.VM_ENTRY_INTR_INFO_FIELD and so doesn't realize that yes, there * is indeed a #DB pending/imminent. */ if (ex->vector == DB_VECTOR && (vmx_get_rflags(vcpu) & X86_EFLAGS_TF) && vmx_get_interrupt_shadow(vcpu)) vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS) | DR6_BS); kvm_deliver_exception_payload(vcpu, ex); if (ex->has_error_code) { /* * Despite the error code being architecturally defined as 32 * bits, and the VMCS field being 32 bits, Intel CPUs and thus * VMX don't actually supporting setting bits 31:16. Hardware * will (should) never provide a bogus error code, but AMD CPUs * do generate error codes with bits 31:16 set, and so KVM's * ABI lets userspace shove in arbitrary 32-bit values. Drop * the upper bits to avoid VM-Fail, losing information that * doesn't really exist is preferable to killing the VM. */ vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)ex->error_code); intr_info |= INTR_INFO_DELIVER_CODE_MASK; } if (vmx->rmode.vm86_active) { int inc_eip = 0; if (kvm_exception_is_soft(ex->vector)) inc_eip = vcpu->arch.event_exit_inst_len; kvm_inject_realmode_interrupt(vcpu, ex->vector, inc_eip); return; } WARN_ON_ONCE(vmx->vt.emulation_required); if (kvm_exception_is_soft(ex->vector)) { vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, vmx->vcpu.arch.event_exit_inst_len); intr_info |= INTR_TYPE_SOFT_EXCEPTION; } else intr_info |= INTR_TYPE_HARD_EXCEPTION; vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); vmx_clear_hlt(vcpu); } static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr, bool load_into_hardware) { struct vmx_uret_msr *uret_msr; uret_msr = vmx_find_uret_msr(vmx, msr); if (!uret_msr) return; uret_msr->load_into_hardware = load_into_hardware; } /* * Configuring user return MSRs to automatically save, load, and restore MSRs * that need to be shoved into hardware when running the guest. Note, omitting * an MSR here does _NOT_ mean it's not emulated, only that it will not be * loaded into hardware when running the guest. */ static void vmx_setup_uret_msrs(struct vcpu_vmx *vmx) { #ifdef CONFIG_X86_64 bool load_syscall_msrs; /* * The SYSCALL MSRs are only needed on long mode guests, and only * when EFER.SCE is set. */ load_syscall_msrs = is_long_mode(&vmx->vcpu) && (vmx->vcpu.arch.efer & EFER_SCE); vmx_setup_uret_msr(vmx, MSR_STAR, load_syscall_msrs); vmx_setup_uret_msr(vmx, MSR_LSTAR, load_syscall_msrs); vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK, load_syscall_msrs); #endif vmx_setup_uret_msr(vmx, MSR_EFER, update_transition_efer(vmx)); vmx_setup_uret_msr(vmx, MSR_TSC_AUX, guest_cpu_cap_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || guest_cpu_cap_has(&vmx->vcpu, X86_FEATURE_RDPID)); /* * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations of new * kernel and old userspace. If those guests run on a tsx=off host, do * allow guests to use TSX_CTRL, but don't change the value in hardware * so that TSX remains always disabled. */ vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL, boot_cpu_has(X86_FEATURE_RTM)); /* * The set of MSRs to load may have changed, reload MSRs before the * next VM-Enter. */ vmx->guest_uret_msrs_loaded = false; } u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETTING)) return vmcs12->tsc_offset; return 0; } u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETTING) && nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING)) return vmcs12->tsc_multiplier; return kvm_caps.default_tsc_scaling_ratio; } void vmx_write_tsc_offset(struct kvm_vcpu *vcpu) { vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); } void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu) { vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); } /* * Userspace is allowed to set any supported IA32_FEATURE_CONTROL regardless of * guest CPUID. Note, KVM allows userspace to set "VMX in SMX" to maintain * backwards compatibility even though KVM doesn't support emulating SMX. And * because userspace set "VMX in SMX", the guest must also be allowed to set it, * e.g. if the MSR is left unlocked and the guest does a RMW operation. */ #define KVM_SUPPORTED_FEATURE_CONTROL (FEAT_CTL_LOCKED | \ FEAT_CTL_VMX_ENABLED_INSIDE_SMX | \ FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX | \ FEAT_CTL_SGX_LC_ENABLED | \ FEAT_CTL_SGX_ENABLED | \ FEAT_CTL_LMCE_ENABLED) static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, struct msr_data *msr) { uint64_t valid_bits; /* * Ensure KVM_SUPPORTED_FEATURE_CONTROL is updated when new bits are * exposed to the guest. */ WARN_ON_ONCE(vmx->msr_ia32_feature_control_valid_bits & ~KVM_SUPPORTED_FEATURE_CONTROL); if (!msr->host_initiated && (vmx->msr_ia32_feature_control & FEAT_CTL_LOCKED)) return false; if (msr->host_initiated) valid_bits = KVM_SUPPORTED_FEATURE_CONTROL; else valid_bits = vmx->msr_ia32_feature_control_valid_bits; return !(msr->data & ~valid_bits); } int vmx_get_feature_msr(u32 msr, u64 *data) { switch (msr) { case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!nested) return 1; return vmx_get_vmx_msr(&vmcs_config.nested, msr, data); default: return KVM_MSR_RET_UNSUPPORTED; } } /* * Reads an msr value (of 'msr_info->index') into 'msr_info->data'. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_uret_msr *msr; u32 index; switch (msr_info->index) { #ifdef CONFIG_X86_64 case MSR_FS_BASE: msr_info->data = vmcs_readl(GUEST_FS_BASE); break; case MSR_GS_BASE: msr_info->data = vmcs_readl(GUEST_GS_BASE); break; case MSR_KERNEL_GS_BASE: msr_info->data = vmx_read_guest_kernel_gs_base(vmx); break; #endif case MSR_EFER: return kvm_get_msr_common(vcpu, msr_info); case MSR_IA32_TSX_CTRL: if (!msr_info->host_initiated && !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) return 1; goto find_uret_msr; case MSR_IA32_UMWAIT_CONTROL: if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx)) return 1; msr_info->data = vmx->msr_ia32_umwait_control; break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && !guest_has_spec_ctrl_msr(vcpu)) return 1; msr_info->data = to_vmx(vcpu)->spec_ctrl; break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; case MSR_IA32_SYSENTER_EIP: msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP); break; case MSR_IA32_SYSENTER_ESP: msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); break; case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_MPX))) return 1; msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; case MSR_IA32_MCG_EXT_CTL: if (!msr_info->host_initiated && !(vmx->msr_ia32_feature_control & FEAT_CTL_LMCE_ENABLED)) return 1; msr_info->data = vcpu->arch.mcg_ext_ctl; break; case MSR_IA32_FEAT_CTL: msr_info->data = vmx->msr_ia32_feature_control; break; case MSR_IA32_SGXLEPUBKEYHASH0 ... MSR_IA32_SGXLEPUBKEYHASH3: if (!msr_info->host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC)) return 1; msr_info->data = to_vmx(vcpu)->msr_ia32_sgxlepubkeyhash [msr_info->index - MSR_IA32_SGXLEPUBKEYHASH0]; break; case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return 1; if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data)) return 1; #ifdef CONFIG_KVM_HYPERV /* * Enlightened VMCS v1 doesn't have certain VMCS fields but * instead of just ignoring the features, different Hyper-V * versions are either trying to use them and fail or do some * sanity checking and refuse to boot. Filter all unsupported * features out. */ if (!msr_info->host_initiated && guest_cpu_cap_has_evmcs(vcpu)) nested_evmcs_filter_control_msr(vcpu, msr_info->index, &msr_info->data); #endif break; case MSR_IA32_RTIT_CTL: if (!vmx_pt_mode_is_host_guest()) return 1; msr_info->data = vmx->pt_desc.guest.ctl; break; case MSR_IA32_RTIT_STATUS: if (!vmx_pt_mode_is_host_guest()) return 1; msr_info->data = vmx->pt_desc.guest.status; break; case MSR_IA32_RTIT_CR3_MATCH: if (!vmx_pt_mode_is_host_guest() || !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cr3_filtering)) return 1; msr_info->data = vmx->pt_desc.guest.cr3_match; break; case MSR_IA32_RTIT_OUTPUT_BASE: if (!vmx_pt_mode_is_host_guest() || (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output) && !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_single_range_output))) return 1; msr_info->data = vmx->pt_desc.guest.output_base; break; case MSR_IA32_RTIT_OUTPUT_MASK: if (!vmx_pt_mode_is_host_guest() || (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output) && !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_single_range_output))) return 1; msr_info->data = vmx->pt_desc.guest.output_mask; break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; if (!vmx_pt_mode_is_host_guest() || (index >= 2 * vmx->pt_desc.num_address_ranges)) return 1; if (index % 2) msr_info->data = vmx->pt_desc.guest.addr_b[index / 2]; else msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; case MSR_IA32_S_CET: msr_info->data = vmcs_readl(GUEST_S_CET); break; case MSR_KVM_INTERNAL_GUEST_SSP: msr_info->data = vmcs_readl(GUEST_SSP); break; case MSR_IA32_INT_SSP_TAB: msr_info->data = vmcs_readl(GUEST_INTR_SSP_TABLE); break; case MSR_IA32_DEBUGCTLMSR: msr_info->data = vmx_guest_debugctl_read(); break; default: find_uret_msr: msr = vmx_find_uret_msr(vmx, msr_info->index); if (msr) { msr_info->data = msr->data; break; } return kvm_get_msr_common(vcpu, msr_info); } return 0; } static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, u64 data) { #ifdef CONFIG_X86_64 if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return (u32)data; #endif return (unsigned long)data; } u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) { u64 debugctl = 0; if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) && (host_initiated || guest_cpu_cap_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; if ((kvm_caps.supported_perf_cap & PERF_CAP_LBR_FMT) && (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; if (boot_cpu_has(X86_FEATURE_RTM) && (host_initiated || guest_cpu_cap_has(vcpu, X86_FEATURE_RTM))) debugctl |= DEBUGCTLMSR_RTM_DEBUG; return debugctl; } bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated) { u64 invalid; invalid = data & ~vmx_get_supported_debugctl(vcpu, host_initiated); if (invalid & (DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR)) { kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data); invalid &= ~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR); } return !invalid; } /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_uret_msr *msr; int ret = 0; u32 msr_index = msr_info->index; u64 data = msr_info->data; u32 index; switch (msr_index) { case MSR_EFER: ret = kvm_set_msr_common(vcpu, msr_info); break; #ifdef CONFIG_X86_64 case MSR_FS_BASE: vmx_segment_cache_clear(vmx); vmcs_writel(GUEST_FS_BASE, data); break; case MSR_GS_BASE: vmx_segment_cache_clear(vmx); vmcs_writel(GUEST_GS_BASE, data); break; case MSR_KERNEL_GS_BASE: vmx_write_guest_kernel_gs_base(vmx, data); break; case MSR_IA32_XFD: ret = kvm_set_msr_common(vcpu, msr_info); /* * Always intercepting WRMSR could incur non-negligible * overhead given xfd might be changed frequently in * guest context switch. Disable write interception * upon the first write with a non-zero value (indicating * potential usage on dynamic xfeatures). Also update * exception bitmap to trap #NM for proper virtualization * of guest xfd_err. */ if (!ret && data) { vmx_disable_intercept_for_msr(vcpu, MSR_IA32_XFD, MSR_TYPE_RW); vcpu->arch.xfd_no_write_intercept = true; vmx_update_exception_bitmap(vcpu); } break; #endif case MSR_IA32_SYSENTER_CS: if (is_guest_mode(vcpu)) get_vmcs12(vcpu)->guest_sysenter_cs = data; vmcs_write32(GUEST_SYSENTER_CS, data); break; case MSR_IA32_SYSENTER_EIP: if (is_guest_mode(vcpu)) { data = nested_vmx_truncate_sysenter_addr(vcpu, data); get_vmcs12(vcpu)->guest_sysenter_eip = data; } vmcs_writel(GUEST_SYSENTER_EIP, data); break; case MSR_IA32_SYSENTER_ESP: if (is_guest_mode(vcpu)) { data = nested_vmx_truncate_sysenter_addr(vcpu, data); get_vmcs12(vcpu)->guest_sysenter_esp = data; } vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_DEBUGCTLMSR: if (!vmx_is_valid_debugctl(vcpu, data, msr_info->host_initiated)) return 1; data &= vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data; vmx_guest_debugctl_write(vcpu, data); if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event && (data & DEBUGCTLMSR_LBR)) intel_pmu_create_guest_lbr_event(vcpu); return 0; case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_MPX))) return 1; if (is_noncanonical_msr_address(data & PAGE_MASK, vcpu) || (data & MSR_IA32_BNDCFGS_RSVD)) return 1; if (is_guest_mode(vcpu) && ((vmx->nested.msrs.entry_ctls_high & VM_ENTRY_LOAD_BNDCFGS) || (vmx->nested.msrs.exit_ctls_high & VM_EXIT_CLEAR_BNDCFGS))) get_vmcs12(vcpu)->guest_bndcfgs = data; vmcs_write64(GUEST_BNDCFGS, data); break; case MSR_IA32_UMWAIT_CONTROL: if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx)) return 1; /* The reserved bit 1 and non-32 bit [63:32] should be zero */ if (data & (BIT_ULL(1) | GENMASK_ULL(63, 32))) return 1; vmx->msr_ia32_umwait_control = data; break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && !guest_has_spec_ctrl_msr(vcpu)) return 1; if (kvm_spec_ctrl_test_value(data)) return 1; vmx->spec_ctrl = data; if (!data) break; /* * For non-nested: * When it's written (to non-zero) for the first time, pass * it through. * * For nested: * The handling of the MSR bitmap for L2 guests is done in * nested_vmx_prepare_msr_bitmap. We should not touch the * vmcs02.msr_bitmap here since it gets completely overwritten * in the merging. We update the vmcs01 here for L1 as well * since it will end up touching the MSR anyway now. */ vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); break; case MSR_IA32_TSX_CTRL: if (!msr_info->host_initiated && !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) return 1; if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR)) return 1; goto find_uret_msr; case MSR_IA32_CR_PAT: ret = kvm_set_msr_common(vcpu, msr_info); if (ret) break; if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) get_vmcs12(vcpu)->guest_ia32_pat = data; if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, data); break; case MSR_IA32_MCG_EXT_CTL: if ((!msr_info->host_initiated && !(to_vmx(vcpu)->msr_ia32_feature_control & FEAT_CTL_LMCE_ENABLED)) || (data & ~MCG_EXT_CTL_LMCE_EN)) return 1; vcpu->arch.mcg_ext_ctl = data; break; case MSR_IA32_FEAT_CTL: if (!is_vmx_feature_control_msr_valid(vmx, msr_info)) return 1; vmx->msr_ia32_feature_control = data; if (msr_info->host_initiated && data == 0) vmx_leave_nested(vcpu); /* SGX may be enabled/disabled by guest's firmware */ vmx_write_encls_bitmap(vcpu, NULL); break; case MSR_IA32_SGXLEPUBKEYHASH0 ... MSR_IA32_SGXLEPUBKEYHASH3: /* * On real hardware, the LE hash MSRs are writable before * the firmware sets bit 0 in MSR 0x7a ("activating" SGX), * at which point SGX related bits in IA32_FEATURE_CONTROL * become writable. * * KVM does not emulate SGX activation for simplicity, so * allow writes to the LE hash MSRs if IA32_FEATURE_CONTROL * is unlocked. This is technically not architectural * behavior, but it's close enough. */ if (!msr_info->host_initiated && (!guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC) || ((vmx->msr_ia32_feature_control & FEAT_CTL_LOCKED) && !(vmx->msr_ia32_feature_control & FEAT_CTL_SGX_LC_ENABLED)))) return 1; vmx->msr_ia32_sgxlepubkeyhash [msr_index - MSR_IA32_SGXLEPUBKEYHASH0] = data; break; case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!msr_info->host_initiated) return 1; /* they are read-only */ if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_RTIT_CTL: if (!vmx_pt_mode_is_host_guest() || vmx_rtit_ctl_check(vcpu, data) || vmx->nested.vmxon) return 1; vmcs_write64(GUEST_IA32_RTIT_CTL, data); vmx->pt_desc.guest.ctl = data; pt_update_intercept_for_msr(vcpu); break; case MSR_IA32_RTIT_STATUS: if (!pt_can_write_msr(vmx)) return 1; if (data & MSR_IA32_RTIT_STATUS_MASK) return 1; vmx->pt_desc.guest.status = data; break; case MSR_IA32_RTIT_CR3_MATCH: if (!pt_can_write_msr(vmx)) return 1; if (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cr3_filtering)) return 1; vmx->pt_desc.guest.cr3_match = data; break; case MSR_IA32_RTIT_OUTPUT_BASE: if (!pt_can_write_msr(vmx)) return 1; if (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output) && !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_single_range_output)) return 1; if (!pt_output_base_valid(vcpu, data)) return 1; vmx->pt_desc.guest.output_base = data; break; case MSR_IA32_RTIT_OUTPUT_MASK: if (!pt_can_write_msr(vmx)) return 1; if (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output) && !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_single_range_output)) return 1; vmx->pt_desc.guest.output_mask = data; break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: if (!pt_can_write_msr(vmx)) return 1; index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; if (index >= 2 * vmx->pt_desc.num_address_ranges) return 1; if (is_noncanonical_msr_address(data, vcpu)) return 1; if (index % 2) vmx->pt_desc.guest.addr_b[index / 2] = data; else vmx->pt_desc.guest.addr_a[index / 2] = data; break; case MSR_IA32_S_CET: vmcs_writel(GUEST_S_CET, data); break; case MSR_KVM_INTERNAL_GUEST_SSP: vmcs_writel(GUEST_SSP, data); break; case MSR_IA32_INT_SSP_TAB: vmcs_writel(GUEST_INTR_SSP_TABLE, data); break; case MSR_IA32_PERF_CAPABILITIES: if (data & PERF_CAP_LBR_FMT) { if ((data & PERF_CAP_LBR_FMT) != (kvm_caps.supported_perf_cap & PERF_CAP_LBR_FMT)) return 1; if (!cpuid_model_is_consistent(vcpu)) return 1; } if (data & PERF_CAP_PEBS_FORMAT) { if ((data & PERF_CAP_PEBS_MASK) != (kvm_caps.supported_perf_cap & PERF_CAP_PEBS_MASK)) return 1; if (!guest_cpu_cap_has(vcpu, X86_FEATURE_DS)) return 1; if (!guest_cpu_cap_has(vcpu, X86_FEATURE_DTES64)) return 1; if (!cpuid_model_is_consistent(vcpu)) return 1; } ret = kvm_set_msr_common(vcpu, msr_info); break; default: find_uret_msr: msr = vmx_find_uret_msr(vmx, msr_index); if (msr) ret = vmx_set_guest_uret_msr(vmx, msr, data); else ret = kvm_set_msr_common(vcpu, msr_info); } /* FB_CLEAR may have changed, also update the FB_CLEAR_DIS behavior */ if (msr_index == MSR_IA32_ARCH_CAPABILITIES) vmx_update_fb_clear_dis(vcpu, vmx); return ret; } void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { unsigned long guest_owned_bits; kvm_register_mark_available(vcpu, reg); switch (reg) { case VCPU_REGS_RSP: vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP); break; case VCPU_REG_RIP: vcpu->arch.rip = vmcs_readl(GUEST_RIP); break; case VCPU_REG_PDPTR: if (enable_ept) ept_save_pdptrs(vcpu); break; case VCPU_REG_CR0: guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; vcpu->arch.cr0 &= ~guest_owned_bits; vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & guest_owned_bits; break; case VCPU_REG_CR3: /* * When intercepting CR3 loads, e.g. for shadowing paging, KVM's * CR3 is loaded into hardware, not the guest's CR3. */ if (!(exec_controls_get(to_vmx(vcpu)) & CPU_BASED_CR3_LOAD_EXITING)) vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); break; case VCPU_REG_CR4: guest_owned_bits = vcpu->arch.cr4_guest_owned_bits; vcpu->arch.cr4 &= ~guest_owned_bits; vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & guest_owned_bits; break; default: KVM_BUG_ON(1, vcpu->kvm); break; } } /* * There is no X86_FEATURE for SGX yet, but anyway we need to query CPUID * directly instead of going through cpu_has(), to ensure KVM is trapping * ENCLS whenever it's supported in hardware. It does not matter whether * the host OS supports or has enabled SGX. */ static bool cpu_has_sgx(void) { return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0)); } static int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result) { u32 vmx_msr_low, vmx_msr_high; u32 ctl = ctl_min | ctl_opt; rdmsr(msr, vmx_msr_low, vmx_msr_high); ctl &= vmx_msr_high; /* bit == 0 in high word ==> must be zero */ ctl |= vmx_msr_low; /* bit == 1 in low word ==> must be one */ /* Ensure minimum (required) set of control bits are supported. */ if (ctl_min & ~ctl) return -EIO; *result = ctl; return 0; } static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) { u64 allowed; rdmsrq(msr, allowed); return ctl_opt & allowed; } #define vmx_check_entry_exit_pairs(pairs, entry_controls, exit_controls) \ ({ \ int i, r = 0; \ \ BUILD_BUG_ON(sizeof(pairs[0].entry_control) != sizeof(entry_controls)); \ BUILD_BUG_ON(sizeof(pairs[0].exit_control) != sizeof(exit_controls)); \ \ for (i = 0; i < ARRAY_SIZE(pairs); i++) { \ typeof(entry_controls) n_ctrl = pairs[i].entry_control; \ typeof(exit_controls) x_ctrl = pairs[i].exit_control; \ \ if (!(entry_controls & n_ctrl) == !(exit_controls & x_ctrl)) \ continue; \ \ pr_warn_once("Inconsistent VM-Entry/VM-Exit pair, " \ "entry = %llx (%llx), exit = %llx (%llx)\n", \ (u64)(entry_controls & n_ctrl), (u64)n_ctrl, \ (u64)(exit_controls & x_ctrl), (u64)x_ctrl); \ \ if (error_on_inconsistent_vmcs_config) \ r = -EIO; \ \ entry_controls &= ~n_ctrl; \ exit_controls &= ~x_ctrl; \ } \ r; \ }) static int setup_vmcs_config(struct vmcs_config *vmcs_conf, struct vmx_capability *vmx_cap) { u32 _pin_based_exec_control = 0; u32 _cpu_based_exec_control = 0; u32 _cpu_based_2nd_exec_control = 0; u64 _cpu_based_3rd_exec_control = 0; u32 _vmexit_control = 0; u32 _vmentry_control = 0; u64 basic_msr; u64 misc_msr; /* * LOAD/SAVE_DEBUG_CONTROLS are absent because both are mandatory. * SAVE_IA32_PAT and SAVE_IA32_EFER are absent because KVM always * intercepts writes to PAT and EFER, i.e. never enables those controls. */ struct { u32 entry_control; u32 exit_control; } const vmcs_entry_exit_pairs[] = { { VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL }, { VM_ENTRY_LOAD_IA32_PAT, VM_EXIT_LOAD_IA32_PAT }, { VM_ENTRY_LOAD_IA32_EFER, VM_EXIT_LOAD_IA32_EFER }, { VM_ENTRY_LOAD_BNDCFGS, VM_EXIT_CLEAR_BNDCFGS }, { VM_ENTRY_LOAD_IA32_RTIT_CTL, VM_EXIT_CLEAR_IA32_RTIT_CTL }, { VM_ENTRY_LOAD_CET_STATE, VM_EXIT_LOAD_CET_STATE }, }; memset(vmcs_conf, 0, sizeof(*vmcs_conf)); if (adjust_vmx_controls(KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL, KVM_OPTIONAL_VMX_CPU_BASED_VM_EXEC_CONTROL, MSR_IA32_VMX_PROCBASED_CTLS, &_cpu_based_exec_control)) return -EIO; if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) { if (adjust_vmx_controls(KVM_REQUIRED_VMX_SECONDARY_VM_EXEC_CONTROL, KVM_OPTIONAL_VMX_SECONDARY_VM_EXEC_CONTROL, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control)) return -EIO; } if (!IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE)) _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; #ifndef CONFIG_X86_64 if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) _cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW; #endif if (!(_cpu_based_exec_control & CPU_BASED_TPR_SHADOW)) _cpu_based_2nd_exec_control &= ~( SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP, &vmx_cap->ept, &vmx_cap->vpid); if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) && vmx_cap->ept) { pr_warn_once("EPT CAP should not exist if not support " "1-setting enable EPT VM-execution control\n"); if (error_on_inconsistent_vmcs_config) return -EIO; vmx_cap->ept = 0; _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_MODE_BASED_EPT_EXEC; _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; } if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) && vmx_cap->vpid) { pr_warn_once("VPID CAP should not exist if not support " "1-setting enable VPID VM-execution control\n"); if (error_on_inconsistent_vmcs_config) return -EIO; vmx_cap->vpid = 0; } /* * Virtualizing MBEC requires advanced vmexit information in order to * distinguish supervisor and user accesses. For simplicity and clarity * disable MBEC entirely if advanced vmexit information is not available, * this way mbec=1 in the kvm_intel module parameters implies availability * to nested guests as well. */ if (!(vmx_cap->ept & VMX_EPT_ADVANCED_VMEXIT_INFO_BIT)) _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_MODE_BASED_EPT_EXEC; if (!cpu_has_sgx()) _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_ENCLS_EXITING; if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) _cpu_based_3rd_exec_control = adjust_vmx_controls64(KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL, MSR_IA32_VMX_PROCBASED_CTLS3); if (adjust_vmx_controls(KVM_REQUIRED_VMX_VM_EXIT_CONTROLS, KVM_OPTIONAL_VMX_VM_EXIT_CONTROLS, MSR_IA32_VMX_EXIT_CTLS, &_vmexit_control)) return -EIO; if (adjust_vmx_controls(KVM_REQUIRED_VMX_PIN_BASED_VM_EXEC_CONTROL, KVM_OPTIONAL_VMX_PIN_BASED_VM_EXEC_CONTROL, MSR_IA32_VMX_PINBASED_CTLS, &_pin_based_exec_control)) return -EIO; if (cpu_has_broken_vmx_preemption_timer()) _pin_based_exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)) _pin_based_exec_control &= ~PIN_BASED_POSTED_INTR; if (adjust_vmx_controls(KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS, KVM_OPTIONAL_VMX_VM_ENTRY_CONTROLS, MSR_IA32_VMX_ENTRY_CTLS, &_vmentry_control)) return -EIO; if (vmx_check_entry_exit_pairs(vmcs_entry_exit_pairs, _vmentry_control, _vmexit_control)) return -EIO; /* * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they * can't be used due to an errata where VM Exit may incorrectly clear * IA32_PERF_GLOBAL_CTRL[34:32]. Workaround the errata by using the * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL. */ switch (boot_cpu_data.x86_vfm) { case INTEL_NEHALEM_EP: /* AAK155 */ case INTEL_NEHALEM: /* AAP115 */ case INTEL_WESTMERE: /* AAT100 */ case INTEL_WESTMERE_EP: /* BC86,AAY89,BD102 */ case INTEL_NEHALEM_EX: /* BA97 */ _vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; _vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; pr_warn_once("VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " "does not work properly. Using workaround\n"); break; default: break; } rdmsrq(MSR_IA32_VMX_BASIC, basic_msr); /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ if (vmx_basic_vmcs_size(basic_msr) > PAGE_SIZE) return -EIO; #ifdef CONFIG_X86_64 /* * KVM expects to be able to shove all legal physical addresses into * VMCS fields for 64-bit kernels, and per the SDM, "This bit is always * 0 for processors that support Intel 64 architecture". */ if (basic_msr & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EIO; #endif /* Require Write-Back (WB) memory type for VMCS accesses. */ if (vmx_basic_vmcs_mem_type(basic_msr) != X86_MEMTYPE_WB) return -EIO; rdmsrq(MSR_IA32_VMX_MISC, misc_msr); vmcs_conf->basic = basic_msr; vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control; vmcs_conf->cpu_based_3rd_exec_ctrl = _cpu_based_3rd_exec_control; vmcs_conf->vmexit_ctrl = _vmexit_control; vmcs_conf->vmentry_ctrl = _vmentry_control; vmcs_conf->misc = misc_msr; #if IS_ENABLED(CONFIG_HYPERV) if (enlightened_vmcs) evmcs_sanitize_exec_ctrls(vmcs_conf); #endif return 0; } static bool __kvm_is_vmx_supported(void) { int cpu = smp_processor_id(); if (!(cpuid_ecx(1) & feature_bit(VMX))) { pr_err("VMX not supported by CPU %d\n", cpu); return false; } if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL)) { pr_err("VMX not enabled (by BIOS) in MSR_IA32_FEAT_CTL on CPU %d\n", cpu); return false; } if (!this_cpu_has(X86_FEATURE_VMX)) { pr_err("VMX not fully enabled on CPU %d. Check kernel logs and/or BIOS\n", cpu); return false; } return true; } static bool kvm_is_vmx_supported(void) { bool supported; migrate_disable(); supported = __kvm_is_vmx_supported(); migrate_enable(); return supported; } int vmx_check_processor_compat(void) { int cpu = raw_smp_processor_id(); struct vmcs_config vmcs_conf; struct vmx_capability vmx_cap; if (!__kvm_is_vmx_supported()) return -EIO; if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) { pr_err("Failed to setup VMCS config on CPU %d\n", cpu); return -EIO; } if (nested) nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept); if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config))) { u32 *gold = (void *)&vmcs_config; u32 *mine = (void *)&vmcs_conf; int i; BUILD_BUG_ON(sizeof(struct vmcs_config) % sizeof(u32)); pr_err("VMCS config on CPU %d doesn't match reference config:", cpu); for (i = 0; i < sizeof(struct vmcs_config) / sizeof(u32); i++) { if (gold[i] == mine[i]) continue; pr_cont("\n Offset %u REF = 0x%08x, CPU%u = 0x%08x, mismatch = 0x%08x", i * (int)sizeof(u32), gold[i], cpu, mine[i], gold[i] ^ mine[i]); } pr_cont("\n"); return -EIO; } return 0; } int vmx_enable_virtualization_cpu(void) { int cpu = raw_smp_processor_id(); /* * This can happen if we hot-added a CPU but failed to allocate * VP assist page for it. */ if (kvm_is_using_evmcs() && !hv_get_vp_assist_page(cpu)) return -EFAULT; return x86_virt_get_ref(X86_FEATURE_VMX); } static void vmclear_local_loaded_vmcss(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v, *n; list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu), loaded_vmcss_on_cpu_link) __loaded_vmcs_clear(v); } void vmx_disable_virtualization_cpu(void) { vmclear_local_loaded_vmcss(); x86_virt_put_ref(X86_FEATURE_VMX); hv_reset_evmcs(); } struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) { int node = cpu_to_node(cpu); struct page *pages; struct vmcs *vmcs; pages = __alloc_pages_node(node, flags, 0); if (!pages) return NULL; vmcs = page_address(pages); memset(vmcs, 0, vmx_basic_vmcs_size(vmcs_config.basic)); /* KVM supports Enlightened VMCS v1 only */ if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = KVM_EVMCS_VERSION; else vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); if (shadow) vmcs->hdr.shadow_vmcs = 1; return vmcs; } void free_vmcs(struct vmcs *vmcs) { free_page((unsigned long)vmcs); } /* * Free a VMCS, but before that VMCLEAR it on the CPU where it was last loaded */ void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) { if (!loaded_vmcs->vmcs) return; loaded_vmcs_clear(loaded_vmcs); free_vmcs(loaded_vmcs->vmcs); loaded_vmcs->vmcs = NULL; if (loaded_vmcs->msr_bitmap) free_page((unsigned long)loaded_vmcs->msr_bitmap); WARN_ON(loaded_vmcs->shadow_vmcs != NULL); } int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) { loaded_vmcs->vmcs = alloc_vmcs(false); if (!loaded_vmcs->vmcs) return -ENOMEM; vmcs_clear(loaded_vmcs->vmcs); loaded_vmcs->shadow_vmcs = NULL; loaded_vmcs->hv_timer_soft_disabled = false; loaded_vmcs->cpu = -1; loaded_vmcs->launched = 0; if (cpu_has_vmx_msr_bitmap()) { loaded_vmcs->msr_bitmap = (unsigned long *) __get_free_page(GFP_KERNEL_ACCOUNT); if (!loaded_vmcs->msr_bitmap) goto out_vmcs; memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); } memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state)); memset(&loaded_vmcs->controls_shadow, 0, sizeof(struct vmcs_controls_shadow)); return 0; out_vmcs: free_loaded_vmcs(loaded_vmcs); return -ENOMEM; } static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg, struct kvm_segment *save) { if (!emulate_invalid_guest_state) { /* * CS and SS RPL should be equal during guest entry according * to VMX spec, but in reality it is not always so. Since vcpu * is in the middle of the transition from real mode to * protected mode it is safe to assume that RPL 0 is a good * default value. */ if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS) save->selector &= ~SEGMENT_RPL_MASK; save->dpl = save->selector & SEGMENT_RPL_MASK; save->s = 1; } __vmx_set_segment(vcpu, save, seg); } static void enter_pmode(struct kvm_vcpu *vcpu) { unsigned long flags; struct vcpu_vmx *vmx = to_vmx(vcpu); /* * Update real mode segment cache. It may be not up-to-date if segment * register was written while vcpu was in a guest mode. */ vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS); vmx->rmode.vm86_active = 0; __vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); flags = vmcs_readl(GUEST_RFLAGS); flags &= RMODE_GUEST_OWNED_EFLAGS_BITS; flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; vmcs_writel(GUEST_RFLAGS, flags); vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) | (vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME)); vmx_update_exception_bitmap(vcpu); fix_pmode_seg(vcpu, VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); fix_pmode_seg(vcpu, VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); fix_pmode_seg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]); fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); } static void fix_rmode_seg(int seg, struct kvm_segment *save) { const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; struct kvm_segment var = *save; var.dpl = 0x3; if (seg == VCPU_SREG_CS) var.type = 0x3; if (!emulate_invalid_guest_state) { var.selector = var.base >> 4; var.base = var.base & 0xffff0; var.limit = 0xffff; var.g = 0; var.db = 0; var.present = 1; var.s = 1; var.l = 0; var.unusable = 0; var.type = 0x3; var.avl = 0; if (save->base & 0xf) pr_warn_once("segment base is not paragraph aligned " "when entering protected mode (seg=%d)", seg); } vmcs_write16(sf->selector, var.selector); vmcs_writel(sf->base, var.base); vmcs_write32(sf->limit, var.limit); vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var)); } static void enter_rmode(struct kvm_vcpu *vcpu) { unsigned long flags; struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_vmx *kvm_vmx = to_kvm_vmx(vcpu->kvm); /* * KVM should never use VM86 to virtualize Real Mode when L2 is active, * as using VM86 is unnecessary if unrestricted guest is enabled, and * if unrestricted guest is disabled, VM-Enter (from L1) with CR0.PG=0 * should VM-Fail and KVM should reject userspace attempts to stuff * CR0.PG=0 when L2 is active. */ WARN_ON_ONCE(is_guest_mode(vcpu)); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS); vmx->rmode.vm86_active = 1; vmx_segment_cache_clear(vmx); vmcs_writel(GUEST_TR_BASE, kvm_vmx->tss_addr); vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1); vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); flags = vmcs_readl(GUEST_RFLAGS); vmx->rmode.save_rflags = flags; flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; vmcs_writel(GUEST_RFLAGS, flags); vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME); vmx_update_exception_bitmap(vcpu); fix_rmode_seg(VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); fix_rmode_seg(VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]); fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); } int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* Nothing to do if hardware doesn't support EFER. */ if (!vmx_find_uret_msr(vmx, MSR_EFER)) return 0; vcpu->arch.efer = efer; #ifdef CONFIG_X86_64 if (efer & EFER_LMA) vm_entry_controls_setbit(vmx, VM_ENTRY_IA32E_MODE); else vm_entry_controls_clearbit(vmx, VM_ENTRY_IA32E_MODE); #else if (KVM_BUG_ON(efer & EFER_LMA, vcpu->kvm)) return 1; #endif vmx_setup_uret_msrs(vmx); return 0; } #ifdef CONFIG_X86_64 static void enter_lmode(struct kvm_vcpu *vcpu) { u32 guest_tr_ar; vmx_segment_cache_clear(to_vmx(vcpu)); guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) { pr_debug_ratelimited("%s: tss fixup for long mode. \n", __func__); vmcs_write32(GUEST_TR_AR_BYTES, (guest_tr_ar & ~VMX_AR_TYPE_MASK) | VMX_AR_TYPE_BUSY_64_TSS); } vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA); } static void exit_lmode(struct kvm_vcpu *vcpu) { vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA); } #endif void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * INVEPT must be issued when EPT is enabled, irrespective of VPID, as * the CPU is not required to invalidate guest-physical mappings on * VM-Entry, even if VPID is disabled. Guest-physical mappings are * associated with the root EPT structure and not any particular VPID * (INVVPID also isn't required to invalidate guest-physical mappings). */ if (enable_ept) { ept_sync_global(); } else if (enable_vpid) { if (cpu_has_vmx_invvpid_global()) { vpid_sync_vcpu_global(); } else { vpid_sync_vcpu_single(vmx->vpid); vpid_sync_vcpu_single(vmx->nested.vpid02); } } } static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_cpu_has_vpid(get_vmcs12(vcpu))) return nested_get_vpid02(vcpu); return to_vmx(vcpu)->vpid; } static u64 construct_eptp(hpa_t root_hpa) { u64 eptp = root_hpa | VMX_EPTP_MT_WB; struct kvm_mmu_page *root; if (kvm_mmu_is_dummy_root(root_hpa)) return eptp | VMX_EPTP_PWL_4; /* * EPT roots should always have an associated MMU page. Return a "bad" * EPTP to induce VM-Fail instead of continuing on in a unknown state. */ root = root_to_sp(root_hpa); if (WARN_ON_ONCE(!root)) return INVALID_PAGE; eptp |= (root->role.level == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4; if (enable_ept_ad_bits && !root->role.ad_disabled) eptp |= VMX_EPTP_AD_ENABLE_BIT; return eptp; } static void vmx_flush_tlb_ept_root(hpa_t root_hpa) { u64 eptp = construct_eptp(root_hpa); if (VALID_PAGE(eptp)) ept_sync_context(eptp); else ept_sync_global(); } void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; u64 root_hpa = mmu->root.hpa; /* No flush required if the current context is invalid. */ if (!VALID_PAGE(root_hpa)) return; if (enable_ept) vmx_flush_tlb_ept_root(root_hpa); else vpid_sync_context(vmx_get_current_vpid(vcpu)); } void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) { /* * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in * vmx_flush_tlb_guest() for an explanation of why this is ok. */ vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr); } void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) { /* * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a * vpid couldn't be allocated for this vCPU. VM-Enter and VM-Exit are * required to flush GVA->{G,H}PA mappings from the TLB if vpid is * disabled (VM-Enter with vpid enabled and vpid==0 is disallowed), * i.e. no explicit INVVPID is necessary. */ vpid_sync_context(vmx_get_current_vpid(vcpu)); } void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu) { if (!kvm_register_is_dirty(vcpu, VCPU_REG_PDPTR)) return; if (is_pae_paging(vcpu)) { vmcs_write64(GUEST_PDPTR0, vcpu->arch.pdptrs[0]); vmcs_write64(GUEST_PDPTR1, vcpu->arch.pdptrs[1]); vmcs_write64(GUEST_PDPTR2, vcpu->arch.pdptrs[2]); vmcs_write64(GUEST_PDPTR3, vcpu->arch.pdptrs[3]); } } void ept_save_pdptrs(struct kvm_vcpu *vcpu) { if (WARN_ON_ONCE(!is_pae_paging(vcpu))) return; vcpu->arch.pdptrs[0] = vmcs_read64(GUEST_PDPTR0); vcpu->arch.pdptrs[1] = vmcs_read64(GUEST_PDPTR1); vcpu->arch.pdptrs[2] = vmcs_read64(GUEST_PDPTR2); vcpu->arch.pdptrs[3] = vmcs_read64(GUEST_PDPTR3); kvm_register_mark_available(vcpu, VCPU_REG_PDPTR); } #define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \ CPU_BASED_CR3_STORE_EXITING) bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { if (is_guest_mode(vcpu)) return nested_guest_cr0_valid(vcpu, cr0); if (to_vmx(vcpu)->nested.vmxon) return nested_host_cr0_valid(vcpu, cr0); return true; } void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long hw_cr0, old_cr0_pg; u32 tmp; old_cr0_pg = kvm_read_cr0_bits(vcpu, X86_CR0_PG); hw_cr0 = (cr0 & ~KVM_VM_CR0_ALWAYS_OFF); if (enable_unrestricted_guest) hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST; else { hw_cr0 |= KVM_VM_CR0_ALWAYS_ON; if (!enable_ept) hw_cr0 |= X86_CR0_WP; if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE)) enter_pmode(vcpu); if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE)) enter_rmode(vcpu); } vmcs_writel(CR0_READ_SHADOW, cr0); vmcs_writel(GUEST_CR0, hw_cr0); vcpu->arch.cr0 = cr0; kvm_register_mark_available(vcpu, VCPU_REG_CR0); #ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME) { if (!old_cr0_pg && (cr0 & X86_CR0_PG)) enter_lmode(vcpu); else if (old_cr0_pg && !(cr0 & X86_CR0_PG)) exit_lmode(vcpu); } #endif if (enable_ept && !enable_unrestricted_guest) { /* * Ensure KVM has an up-to-date snapshot of the guest's CR3. If * the below code _enables_ CR3 exiting, vmx_cache_reg() will * (correctly) stop reading vmcs.GUEST_CR3 because it thinks * KVM's CR3 is installed. */ if (!kvm_register_is_available(vcpu, VCPU_REG_CR3)) vmx_cache_reg(vcpu, VCPU_REG_CR3); /* * When running with EPT but not unrestricted guest, KVM must * intercept CR3 accesses when paging is _disabled_. This is * necessary because restricted guests can't actually run with * paging disabled, and so KVM stuffs its own CR3 in order to * run the guest when identity mapped page tables. * * Do _NOT_ check the old CR0.PG, e.g. to optimize away the * update, it may be stale with respect to CR3 interception, * e.g. after nested VM-Enter. * * Lastly, honor L1's desires, i.e. intercept CR3 loads and/or * stores to forward them to L1, even if KVM does not need to * intercept them to preserve its identity mapped page tables. */ if (!(cr0 & X86_CR0_PG)) { exec_controls_setbit(vmx, CR3_EXITING_BITS); } else if (!is_guest_mode(vcpu)) { exec_controls_clearbit(vmx, CR3_EXITING_BITS); } else { tmp = exec_controls_get(vmx); tmp &= ~CR3_EXITING_BITS; tmp |= get_vmcs12(vcpu)->cpu_based_vm_exec_control & CR3_EXITING_BITS; exec_controls_set(vmx, tmp); } /* Note, vmx_set_cr4() consumes the new vcpu->arch.cr0. */ if ((old_cr0_pg ^ cr0) & X86_CR0_PG) vmx_set_cr4(vcpu, kvm_read_cr4(vcpu)); /* * When !CR0_PG -> CR0_PG, vcpu->arch.cr3 becomes active, but * GUEST_CR3 is still vmx->ept_identity_map_addr if EPT + !URG. */ if (!(old_cr0_pg & X86_CR0_PG) && (cr0 & X86_CR0_PG)) kvm_register_mark_dirty(vcpu, VCPU_REG_CR3); } /* depends on vcpu->arch.cr0 to be set to a new value */ vmx->vt.emulation_required = vmx_emulation_required(vcpu); } static int vmx_get_max_ept_level(void) { if (cpu_has_vmx_ept_5levels()) return 5; return 4; } void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) { struct kvm *kvm = vcpu->kvm; bool update_guest_cr3 = true; unsigned long guest_cr3; if (enable_ept) { KVM_MMU_WARN_ON(root_to_sp(root_hpa) && root_level != root_to_sp(root_hpa)->role.level); vmcs_write64(EPT_POINTER, construct_eptp(root_hpa)); hv_track_root_tdp(vcpu, root_hpa); if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; else if (kvm_register_is_dirty(vcpu, VCPU_REG_CR3)) guest_cr3 = vcpu->arch.cr3; else /* vmcs.GUEST_CR3 is already up-to-date. */ update_guest_cr3 = false; vmx_ept_load_pdptrs(vcpu); } else { guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu) | kvm_get_active_cr3_lam_bits(vcpu); } if (update_guest_cr3) vmcs_writel(GUEST_CR3, guest_cr3); } bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { /* * We operate under the default treatment of SMM, so VMX cannot be * enabled under SMM. Note, whether or not VMXE is allowed at all, * i.e. is a reserved bit, is handled by common x86 code. */ if ((cr4 & X86_CR4_VMXE) && is_smm(vcpu)) return false; if (to_vmx(vcpu)->nested.vmxon && !nested_cr4_valid(vcpu, cr4)) return false; return true; } void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long hw_cr4; /* * Pass through host's Machine Check Enable value to hw_cr4, which * is in force while we are in guest mode. Do not let guests control * this bit, even if host CR4.MCE == 0. */ hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE); if (enable_unrestricted_guest) hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST; else if (vmx->rmode.vm86_active) hw_cr4 |= KVM_RMODE_VM_CR4_ALWAYS_ON; else hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON; if (vmx_umip_emulated()) { if (cr4 & X86_CR4_UMIP) { secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_DESC); hw_cr4 &= ~X86_CR4_UMIP; } else if (!is_guest_mode(vcpu) || !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) { secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_DESC); } } vcpu->arch.cr4 = cr4; kvm_register_mark_available(vcpu, VCPU_REG_CR4); if (!enable_unrestricted_guest) { if (enable_ept) { if (!is_paging(vcpu)) { hw_cr4 &= ~X86_CR4_PAE; hw_cr4 |= X86_CR4_PSE; } else if (!(cr4 & X86_CR4_PAE)) { hw_cr4 &= ~X86_CR4_PAE; } } /* * SMEP/SMAP/PKU is disabled if CPU is in non-paging mode in * hardware. To emulate this behavior, SMEP/SMAP/PKU needs * to be manually disabled when guest switches to non-paging * mode. * * If !enable_unrestricted_guest, the CPU is always running * with CR0.PG=1 and CR4 needs to be modified. * If enable_unrestricted_guest, the CPU automatically * disables SMEP/SMAP/PKU when the guest sets CR0.PG=0. */ if (!is_paging(vcpu)) hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE); } vmcs_writel(CR4_READ_SHADOW, cr4); vmcs_writel(GUEST_CR4, hw_cr4); if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE)) vcpu->arch.cpuid_dynamic_bits_dirty = true; } void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 ar; if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { *var = vmx->rmode.segs[seg]; if (seg == VCPU_SREG_TR || var->selector == vmx_read_guest_seg_selector(vmx, seg)) return; var->base = vmx_read_guest_seg_base(vmx, seg); var->selector = vmx_read_guest_seg_selector(vmx, seg); return; } var->base = vmx_read_guest_seg_base(vmx, seg); var->limit = vmx_read_guest_seg_limit(vmx, seg); var->selector = vmx_read_guest_seg_selector(vmx, seg); ar = vmx_read_guest_seg_ar(vmx, seg); var->unusable = (ar >> 16) & 1; var->type = ar & 15; var->s = (ar >> 4) & 1; var->dpl = (ar >> 5) & 3; /* * Some userspaces do not preserve unusable property. Since usable * segment has to be present according to VMX spec we can use present * property to amend userspace bug by making unusable segment always * nonpresent. vmx_segment_access_rights() already marks nonpresent * segment as unusable. */ var->present = !var->unusable; var->avl = (ar >> 12) & 1; var->l = (ar >> 13) & 1; var->db = (ar >> 14) & 1; var->g = (ar >> 15) & 1; } u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) { struct kvm_segment s; if (to_vmx(vcpu)->rmode.vm86_active) { vmx_get_segment(vcpu, &s, seg); return s.base; } return vmx_read_guest_seg_base(to_vmx(vcpu), seg); } static int __vmx_get_cpl(struct kvm_vcpu *vcpu, bool no_cache) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ar; if (unlikely(vmx->rmode.vm86_active)) return 0; if (no_cache) ar = vmcs_read32(GUEST_SS_AR_BYTES); else ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); return VMX_AR_DPL(ar); } int vmx_get_cpl(struct kvm_vcpu *vcpu) { return __vmx_get_cpl(vcpu, false); } int vmx_get_cpl_no_cache(struct kvm_vcpu *vcpu) { return __vmx_get_cpl(vcpu, true); } static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; ar = var->type & 15; ar |= (var->s & 1) << 4; ar |= (var->dpl & 3) << 5; ar |= (var->present & 1) << 7; ar |= (var->avl & 1) << 12; ar |= (var->l & 1) << 13; ar |= (var->db & 1) << 14; ar |= (var->g & 1) << 15; ar |= (var->unusable || !var->present) << 16; return ar; } void __vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { struct vcpu_vmx *vmx = to_vmx(vcpu); const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; vmx_segment_cache_clear(vmx); if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { vmx->rmode.segs[seg] = *var; if (seg == VCPU_SREG_TR) vmcs_write16(sf->selector, var->selector); else if (var->s) fix_rmode_seg(seg, &vmx->rmode.segs[seg]); return; } vmcs_writel(sf->base, var->base); vmcs_write32(sf->limit, var->limit); vmcs_write16(sf->selector, var->selector); /* * Fix the "Accessed" bit in AR field of segment registers for older * qemu binaries. * IA32 arch specifies that at the time of processor reset the * "Accessed" bit in the AR field of segment registers is 1. And qemu * is setting it to 0 in the userland code. This causes invalid guest * state vmexit when "unrestricted guest" mode is turned on. * Fix for this setup issue in cpu_reset is being pushed in the qemu * tree. Newer qemu binaries with that qemu fix would not need this * kvm hack. */ if (is_unrestricted_guest(vcpu) && (seg != VCPU_SREG_LDTR)) var->type |= 0x1; /* Accessed */ vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var)); } void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { __vmx_set_segment(vcpu, var, seg); to_vmx(vcpu)->vt.emulation_required = vmx_emulation_required(vcpu); } void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS); *db = (ar >> 14) & 1; *l = (ar >> 13) & 1; } void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { dt->size = vmcs_read32(GUEST_IDTR_LIMIT); dt->address = vmcs_readl(GUEST_IDTR_BASE); } void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { vmcs_write32(GUEST_IDTR_LIMIT, dt->size); vmcs_writel(GUEST_IDTR_BASE, dt->address); } void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { dt->size = vmcs_read32(GUEST_GDTR_LIMIT); dt->address = vmcs_readl(GUEST_GDTR_BASE); } void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { vmcs_write32(GUEST_GDTR_LIMIT, dt->size); vmcs_writel(GUEST_GDTR_BASE, dt->address); } static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg) { struct kvm_segment var; u32 ar; vmx_get_segment(vcpu, &var, seg); var.dpl = 0x3; if (seg == VCPU_SREG_CS) var.type = 0x3; ar = vmx_segment_access_rights(&var); if (var.base != (var.selector << 4)) return false; if (var.limit != 0xffff) return false; if (ar != 0xf3) return false; return true; } static bool code_segment_valid(struct kvm_vcpu *vcpu) { struct kvm_segment cs; unsigned int cs_rpl; vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); cs_rpl = cs.selector & SEGMENT_RPL_MASK; if (cs.unusable) return false; if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK)) return false; if (!cs.s) return false; if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) { if (cs.dpl > cs_rpl) return false; } else { if (cs.dpl != cs_rpl) return false; } if (!cs.present) return false; /* TODO: Add Reserved field check, this'll require a new member in the kvm_segment_field structure */ return true; } static bool stack_segment_valid(struct kvm_vcpu *vcpu) { struct kvm_segment ss; unsigned int ss_rpl; vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); ss_rpl = ss.selector & SEGMENT_RPL_MASK; if (ss.unusable) return true; if (ss.type != 3 && ss.type != 7) return false; if (!ss.s) return false; if (ss.dpl != ss_rpl) /* DPL != RPL */ return false; if (!ss.present) return false; return true; } static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) { struct kvm_segment var; unsigned int rpl; vmx_get_segment(vcpu, &var, seg); rpl = var.selector & SEGMENT_RPL_MASK; if (var.unusable) return true; if (!var.s) return false; if (!var.present) return false; if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) { if (var.dpl < rpl) /* DPL < RPL */ return false; } /* TODO: Add other members to kvm_segment_field to allow checking for other access * rights flags */ return true; } static bool tr_valid(struct kvm_vcpu *vcpu) { struct kvm_segment tr; vmx_get_segment(vcpu, &tr, VCPU_SREG_TR); if (tr.unusable) return false; if (tr.selector & SEGMENT_TI_MASK) /* TI = 1 */ return false; if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */ return false; if (!tr.present) return false; return true; } static bool ldtr_valid(struct kvm_vcpu *vcpu) { struct kvm_segment ldtr; vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR); if (ldtr.unusable) return true; if (ldtr.selector & SEGMENT_TI_MASK) /* TI = 1 */ return false; if (ldtr.type != 2) return false; if (!ldtr.present) return false; return true; } static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu) { struct kvm_segment cs, ss; vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); return ((cs.selector & SEGMENT_RPL_MASK) == (ss.selector & SEGMENT_RPL_MASK)); } /* * Check if guest state is valid. Returns true if valid, false if * not. * We assume that registers are always usable */ bool __vmx_guest_state_valid(struct kvm_vcpu *vcpu) { /* real mode guest state checks */ if (!is_protmode(vcpu) || (vmx_get_rflags(vcpu) & X86_EFLAGS_VM)) { if (!rmode_segment_valid(vcpu, VCPU_SREG_CS)) return false; if (!rmode_segment_valid(vcpu, VCPU_SREG_SS)) return false; if (!rmode_segment_valid(vcpu, VCPU_SREG_DS)) return false; if (!rmode_segment_valid(vcpu, VCPU_SREG_ES)) return false; if (!rmode_segment_valid(vcpu, VCPU_SREG_FS)) return false; if (!rmode_segment_valid(vcpu, VCPU_SREG_GS)) return false; } else { /* protected mode guest state checks */ if (!cs_ss_rpl_check(vcpu)) return false; if (!code_segment_valid(vcpu)) return false; if (!stack_segment_valid(vcpu)) return false; if (!data_segment_valid(vcpu, VCPU_SREG_DS)) return false; if (!data_segment_valid(vcpu, VCPU_SREG_ES)) return false; if (!data_segment_valid(vcpu, VCPU_SREG_FS)) return false; if (!data_segment_valid(vcpu, VCPU_SREG_GS)) return false; if (!tr_valid(vcpu)) return false; if (!ldtr_valid(vcpu)) return false; } /* TODO: * - Add checks on RIP * - Add checks on RFLAGS */ return true; } static int init_rmode_tss(struct kvm *kvm, void __user *ua) { const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0))); u16 data; int i; for (i = 0; i < 3; i++) { if (__copy_to_user(ua + PAGE_SIZE * i, zero_page, PAGE_SIZE)) return -EFAULT; } data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE; if (__copy_to_user(ua + TSS_IOPB_BASE_OFFSET, &data, sizeof(u16))) return -EFAULT; data = ~0; if (__copy_to_user(ua + RMODE_TSS_SIZE - 1, &data, sizeof(u8))) return -EFAULT; return 0; } static int init_rmode_identity_map(struct kvm *kvm) { struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); int i, r = 0; void __user *uaddr; u32 tmp; /* Protect kvm_vmx->ept_identity_pagetable_done. */ mutex_lock(&kvm->slots_lock); if (likely(kvm_vmx->ept_identity_pagetable_done)) goto out; if (!kvm_vmx->ept_identity_map_addr) kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; uaddr = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, kvm_vmx->ept_identity_map_addr, PAGE_SIZE); if (IS_ERR(uaddr)) { r = PTR_ERR(uaddr); goto out; } /* Set up identity-mapping pagetable for EPT in real mode */ for (i = 0; i < (PAGE_SIZE / sizeof(tmp)); i++) { tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); if (__copy_to_user(uaddr + i * sizeof(tmp), &tmp, sizeof(tmp))) { r = -EFAULT; goto out; } } kvm_vmx->ept_identity_pagetable_done = true; out: mutex_unlock(&kvm->slots_lock); return r; } static void seg_setup(int seg) { const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; unsigned int ar; vmcs_write16(sf->selector, 0); vmcs_writel(sf->base, 0); vmcs_write32(sf->limit, 0xffff); ar = 0x93; if (seg == VCPU_SREG_CS) ar |= 0x08; /* code segment */ vmcs_write32(sf->ar_bytes, ar); } int allocate_vpid(void) { int vpid; if (!enable_vpid) return 0; spin_lock(&vmx_vpid_lock); vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS); if (vpid < VMX_NR_VPIDS) __set_bit(vpid, vmx_vpid_bitmap); else vpid = 0; spin_unlock(&vmx_vpid_lock); return vpid; } void free_vpid(int vpid) { if (!enable_vpid || vpid == 0) return; spin_lock(&vmx_vpid_lock); __clear_bit(vpid, vmx_vpid_bitmap); spin_unlock(&vmx_vpid_lock); } static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) { /* * When KVM is a nested hypervisor on top of Hyper-V and uses * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR * bitmap has changed. */ if (kvm_is_using_evmcs()) { struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; if (evmcs->hv_enlightenments_control.msr_bitmap) evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; } vmx->nested.force_msr_bitmap_recalc = true; } void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; if (!cpu_has_vmx_msr_bitmap()) return; vmx_msr_bitmap_l01_changed(vmx); if (type & MSR_TYPE_R) { if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ)) vmx_clear_msr_bitmap_read(msr_bitmap, msr); else vmx_set_msr_bitmap_read(msr_bitmap, msr); } if (type & MSR_TYPE_W) { if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE)) vmx_clear_msr_bitmap_write(msr_bitmap, msr); else vmx_set_msr_bitmap_write(msr_bitmap, msr); } } static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu) { /* * x2APIC indices for 64-bit accesses into the RDMSR and WRMSR halves * of the MSR bitmap. KVM emulates APIC registers up through 0x3f0, * i.e. MSR 0x83f, and so only needs to dynamically manipulate 64 bits. */ const int read_idx = APIC_BASE_MSR / BITS_PER_LONG_LONG; const int write_idx = read_idx + (0x800 / sizeof(u64)); struct vcpu_vmx *vmx = to_vmx(vcpu); u64 *msr_bitmap = (u64 *)vmx->vmcs01.msr_bitmap; u8 mode; if (!cpu_has_vmx_msr_bitmap() || WARN_ON_ONCE(!lapic_in_kernel(vcpu))) return; if (cpu_has_secondary_exec_ctrls() && (secondary_exec_controls_get(vmx) & SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { mode = MSR_BITMAP_MODE_X2APIC; if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) mode |= MSR_BITMAP_MODE_X2APIC_APICV; } else { mode = 0; } if (mode == vmx->x2apic_msr_bitmap_mode) return; vmx->x2apic_msr_bitmap_mode = mode; /* * Reset the bitmap for MSRs 0x800 - 0x83f. Leave AMD's uber-extended * registers (0x840 and above) intercepted, KVM doesn't support them. * Intercept all writes by default and poke holes as needed. Pass * through reads for all valid registers by default in x2APIC+APICv * mode, only the current timer count needs on-demand emulation by KVM. */ if (mode & MSR_BITMAP_MODE_X2APIC_APICV) msr_bitmap[read_idx] = ~kvm_x2apic_disable_read_intercept_reg_mask(vcpu); else msr_bitmap[read_idx] = ~0ull; msr_bitmap[write_idx] = ~0ull; /* * TPR reads and writes can be virtualized even if virtual interrupt * delivery is not in use. */ vmx_set_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW, !(mode & MSR_BITMAP_MODE_X2APIC)); if (mode & MSR_BITMAP_MODE_X2APIC_APICV) { vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); if (enable_ipiv) vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_ICR), MSR_TYPE_RW); } } void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool flag = !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN); u32 i; vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_STATUS, MSR_TYPE_RW, flag); vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_BASE, MSR_TYPE_RW, flag); vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_MASK, MSR_TYPE_RW, flag); vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_CR3_MATCH, MSR_TYPE_RW, flag); for (i = 0; i < vmx->pt_desc.num_address_ranges; i++) { vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag); vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag); } } static void vmx_recalc_pmu_msr_intercepts(struct kvm_vcpu *vcpu) { u64 vm_exit_controls_bits = VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL; bool has_mediated_pmu = kvm_vcpu_has_mediated_pmu(vcpu); struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); bool intercept = !has_mediated_pmu; int i; if (!enable_mediated_pmu) return; if (!cpu_has_save_perf_global_ctrl()) { vm_exit_controls_bits &= ~VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL; if (has_mediated_pmu) vmx_add_autostore_msr(vmx, MSR_CORE_PERF_GLOBAL_CTRL); else vmx_remove_autostore_msr(vmx, MSR_CORE_PERF_GLOBAL_CTRL); } vm_entry_controls_changebit(vmx, VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, has_mediated_pmu); vm_exit_controls_changebit(vmx, vm_exit_controls_bits, has_mediated_pmu); for (i = 0; i < pmu->nr_arch_gp_counters; i++) { vmx_set_intercept_for_msr(vcpu, MSR_IA32_PERFCTR0 + i, MSR_TYPE_RW, intercept); vmx_set_intercept_for_msr(vcpu, MSR_IA32_PMC0 + i, MSR_TYPE_RW, intercept || !fw_writes_is_enabled(vcpu)); } for ( ; i < kvm_pmu_cap.num_counters_gp; i++) { vmx_set_intercept_for_msr(vcpu, MSR_IA32_PERFCTR0 + i, MSR_TYPE_RW, true); vmx_set_intercept_for_msr(vcpu, MSR_IA32_PMC0 + i, MSR_TYPE_RW, true); } for (i = 0; i < pmu->nr_arch_fixed_counters; i++) vmx_set_intercept_for_msr(vcpu, MSR_CORE_PERF_FIXED_CTR0 + i, MSR_TYPE_RW, intercept); for ( ; i < kvm_pmu_cap.num_counters_fixed; i++) vmx_set_intercept_for_msr(vcpu, MSR_CORE_PERF_FIXED_CTR0 + i, MSR_TYPE_RW, true); intercept = kvm_need_perf_global_ctrl_intercept(vcpu); vmx_set_intercept_for_msr(vcpu, MSR_CORE_PERF_GLOBAL_STATUS, MSR_TYPE_RW, intercept); vmx_set_intercept_for_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, MSR_TYPE_RW, intercept); vmx_set_intercept_for_msr(vcpu, MSR_CORE_PERF_GLOBAL_OVF_CTRL, MSR_TYPE_RW, intercept); } static void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu) { bool intercept; if (!cpu_has_vmx_msr_bitmap()) return; vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R); #ifdef CONFIG_X86_64 vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); #endif vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); if (kvm_cstate_in_guest(vcpu->kvm)) { vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R); vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R); vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R); } if (kvm_aperfmperf_in_guest(vcpu->kvm)) { vmx_disable_intercept_for_msr(vcpu, MSR_IA32_APERF, MSR_TYPE_R); vmx_disable_intercept_for_msr(vcpu, MSR_IA32_MPERF, MSR_TYPE_R); } /* PT MSRs can be passed through iff PT is exposed to the guest. */ if (vmx_pt_mode_is_host_guest()) pt_update_intercept_for_msr(vcpu); if (vcpu->arch.xfd_no_write_intercept) vmx_disable_intercept_for_msr(vcpu, MSR_IA32_XFD, MSR_TYPE_RW); vmx_set_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW, !to_vmx(vcpu)->spec_ctrl); if (kvm_cpu_cap_has(X86_FEATURE_XFD)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)); if (cpu_feature_enabled(X86_FEATURE_IBPB)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W, !guest_has_pred_cmd_msr(vcpu)); if (cpu_feature_enabled(X86_FEATURE_FLUSH_L1D)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W, !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) { intercept = !guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK); vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL0_SSP, MSR_TYPE_RW, intercept); vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL1_SSP, MSR_TYPE_RW, intercept); vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL2_SSP, MSR_TYPE_RW, intercept); vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL3_SSP, MSR_TYPE_RW, intercept); } if (kvm_cpu_cap_has(X86_FEATURE_SHSTK) || kvm_cpu_cap_has(X86_FEATURE_IBT)) { intercept = !guest_cpu_cap_has(vcpu, X86_FEATURE_IBT) && !guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK); vmx_set_intercept_for_msr(vcpu, MSR_IA32_U_CET, MSR_TYPE_RW, intercept); vmx_set_intercept_for_msr(vcpu, MSR_IA32_S_CET, MSR_TYPE_RW, intercept); } vmx_recalc_pmu_msr_intercepts(vcpu); /* * x2APIC and LBR MSR intercepts are modified on-demand and cannot be * filtered by userspace. */ } static void vmx_recalc_instruction_intercepts(struct kvm_vcpu *vcpu) { exec_controls_changebit(to_vmx(vcpu), CPU_BASED_RDPMC_EXITING, kvm_need_rdpmc_intercept(vcpu)); } void vmx_recalc_intercepts(struct kvm_vcpu *vcpu) { vmx_recalc_instruction_intercepts(vcpu); vmx_recalc_msr_intercepts(vcpu); } static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * DO NOT query the vCPU's vmcs12, as vmcs12 is dynamically allocated * and freed, and must not be accessed outside of vcpu->mutex. The * vCPU's cached PI NV is valid if and only if posted interrupts * enabled in its vmcs12, i.e. checking the vector also checks that * L1 has enabled posted interrupts for L2. */ if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { /* * If a posted intr is not recognized by hardware, * we will accomplish it in the next vmentry. */ vmx->nested.pi_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); /* * This pairs with the smp_mb_*() after setting vcpu->mode in * vcpu_enter_guest() to guarantee the vCPU sees the event * request if triggering a posted interrupt "fails" because * vcpu->mode != IN_GUEST_MODE. The extra barrier is needed as * the smb_wmb() in kvm_make_request() only ensures everything * done before making the request is visible when the request * is visible, it doesn't ensure ordering between the store to * vcpu->requests and the load from vcpu->mode. */ smp_mb__after_atomic(); /* the PIR and ON have been set by L1. */ kvm_vcpu_trigger_posted_interrupt(vcpu, POSTED_INTR_NESTED_VECTOR); return 0; } return -1; } /* * Send interrupt to vcpu via posted interrupt way. * 1. If target vcpu is running(non-root mode), send posted interrupt * notification to vcpu and hardware will sync PIR to vIRR atomically. * 2. If target vcpu isn't running(root mode), kick it to pick up the * interrupt from PIR in next vmentry. */ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { struct vcpu_vt *vt = to_vt(vcpu); int r; r = vmx_deliver_nested_posted_interrupt(vcpu, vector); if (!r) return 0; /* Note, this is called iff the local APIC is in-kernel. */ if (!vcpu->arch.apic->apicv_active) return -1; __vmx_deliver_posted_interrupt(vcpu, &vt->pi_desc, vector); return 0; } void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, int trig_mode, int vector) { struct kvm_vcpu *vcpu = apic->vcpu; if (vmx_deliver_posted_interrupt(vcpu, vector)) { kvm_lapic_set_irr(vector, apic); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } else { trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, trig_mode, vector); } } /* * Set up the vmcs's constant host-state fields, i.e., host-state fields that * will not change in the lifetime of the guest. * Note that host-state that does change is set elsewhere. E.g., host-state * that is set differently for each CPU is set in vmx_vcpu_load(), not here. */ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) { u32 low32, high32; unsigned long tmpl; unsigned long cr0, cr3, cr4; cr0 = read_cr0(); WARN_ON(cr0 & X86_CR0_TS); vmcs_writel(HOST_CR0, cr0); /* 22.2.3 */ /* * Save the most likely value for this task's CR3 in the VMCS. * We can't use __get_current_cr3_fast() because we're not atomic. */ cr3 = __read_cr3(); vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ vmx->loaded_vmcs->host_state.cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ vmx->loaded_vmcs->host_state.cr4 = cr4; vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ #ifdef CONFIG_X86_64 /* * Load null selectors, so we can avoid reloading them in * vmx_prepare_switch_to_host(), in case userspace uses * the null selectors too (the expected case). */ vmcs_write16(HOST_DS_SELECTOR, 0); vmcs_write16(HOST_ES_SELECTOR, 0); #else vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS); /* 22.2.4 */ #endif vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */ vmcs_writel(HOST_IDTR_BASE, host_idt_base); /* 22.2.4 */ vmcs_writel(HOST_RIP, (unsigned long)vmx_vmexit); /* 22.2.5 */ rdmsr(MSR_IA32_SYSENTER_CS, low32, high32); vmcs_write32(HOST_IA32_SYSENTER_CS, low32); /* * SYSENTER is used for 32-bit system calls on either 32-bit or * 64-bit kernels. It is always zero If neither is allowed, otherwise * vmx_vcpu_load_vmcs loads it with the per-CPU entry stack (and may * have already done so!). */ if (!IS_ENABLED(CONFIG_IA32_EMULATION) && !IS_ENABLED(CONFIG_X86_32)) vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); rdmsrq(MSR_IA32_SYSENTER_EIP, tmpl); vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) { rdmsr(MSR_IA32_CR_PAT, low32, high32); vmcs_write64(HOST_IA32_PAT, low32 | ((u64) high32 << 32)); } if (cpu_has_load_ia32_efer()) vmcs_write64(HOST_IA32_EFER, kvm_host.efer); /* * Supervisor shadow stack is not enabled on host side, i.e., * host IA32_S_CET.SHSTK_EN bit is guaranteed to 0 now, per SDM * description(RDSSP instruction), SSP is not readable in CPL0, * so resetting the two registers to 0s at VM-Exit does no harm * to kernel execution. When execution flow exits to userspace, * SSP is reloaded from IA32_PL3_SSP. Check SDM Vol.2A/B Chapter * 3 and 4 for details. */ if (enable_cet) { vmcs_writel(HOST_S_CET, kvm_host.s_cet); vmcs_writel(HOST_SSP, 0); vmcs_writel(HOST_INTR_SSP_TABLE, 0); } /* * When running a guest with a mediated PMU, guest state is resident in * hardware after VM-Exit. Zero PERF_GLOBAL_CTRL on exit so that host * activity doesn't bleed into the guest counters. When running with * an emulated PMU, PERF_GLOBAL_CTRL is dynamically computed on every * entry/exit to merge guest and host PMU usage. */ if (enable_mediated_pmu) vmcs_write64(HOST_IA32_PERF_GLOBAL_CTRL, 0); } void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) { struct kvm_vcpu *vcpu = &vmx->vcpu; vcpu->arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS & ~vcpu->arch.cr4_guest_rsvd_bits; if (!enable_ept) { vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_TLBFLUSH_BITS; vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_PDPTR_BITS; } if (is_guest_mode(&vmx->vcpu)) vcpu->arch.cr4_guest_owned_bits &= ~get_vmcs12(vcpu)->cr4_guest_host_mask; vmcs_writel(CR4_GUEST_HOST_MASK, ~vcpu->arch.cr4_guest_owned_bits); } static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) { u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; if (!kvm_vcpu_apicv_active(&vmx->vcpu)) pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; if (!enable_vnmi) pin_based_exec_ctrl &= ~PIN_BASED_VIRTUAL_NMIS; if (!enable_preemption_timer) pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER; return pin_based_exec_ctrl; } static u32 vmx_get_initial_vmentry_ctrl(void) { u32 vmentry_ctrl = vmcs_config.vmentry_ctrl; if (vmx_pt_mode_is_system()) vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | VM_ENTRY_LOAD_IA32_RTIT_CTL); if (!enable_cet) vmentry_ctrl &= ~VM_ENTRY_LOAD_CET_STATE; /* * IA32e mode, and loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically. */ vmentry_ctrl &= ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER | VM_ENTRY_IA32E_MODE); return vmentry_ctrl; } static u32 vmx_get_initial_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; if (!enable_cet) vmexit_ctrl &= ~VM_EXIT_LOAD_CET_STATE; /* * Not used by KVM and never set in vmcs01 or vmcs02, but emulated for * nested virtualization and thus allowed to be set in vmcs12. */ vmexit_ctrl &= ~(VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER | VM_EXIT_SAVE_VMX_PREEMPTION_TIMER); if (vmx_pt_mode_is_system()) vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | VM_EXIT_CLEAR_IA32_RTIT_CTL); /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ return vmexit_ctrl & ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL); } void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); guard(vmx_vmcs01)(vcpu); pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); secondary_exec_controls_changebit(vmx, SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY, kvm_vcpu_apicv_active(vcpu)); if (enable_ipiv) tertiary_exec_controls_changebit(vmx, TERTIARY_EXEC_IPI_VIRT, kvm_vcpu_apicv_active(vcpu)); vmx_update_msr_bitmap_x2apic(vcpu); } static u32 vmx_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_exec_ctrl; /* * Not used by KVM, but fully supported for nesting, i.e. are allowed in * vmcs12 and propagated to vmcs02 when set in vmcs12. */ exec_control &= ~(CPU_BASED_RDTSC_EXITING | CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG | CPU_BASED_PAUSE_EXITING); /* INTR_WINDOW_EXITING and NMI_WINDOW_EXITING are toggled dynamically */ exec_control &= ~(CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT) exec_control &= ~CPU_BASED_MOV_DR_EXITING; if (!cpu_need_tpr_shadow(&vmx->vcpu)) exec_control &= ~CPU_BASED_TPR_SHADOW; #ifdef CONFIG_X86_64 if (exec_control & CPU_BASED_TPR_SHADOW) exec_control &= ~(CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING); else exec_control |= CPU_BASED_CR8_STORE_EXITING | CPU_BASED_CR8_LOAD_EXITING; #endif /* No need to intercept CR3 access or INVPLG when using EPT. */ if (enable_ept) exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | CPU_BASED_INVLPG_EXITING); if (kvm_mwait_in_guest(vmx->vcpu.kvm)) exec_control &= ~(CPU_BASED_MWAIT_EXITING | CPU_BASED_MONITOR_EXITING); if (kvm_hlt_in_guest(vmx->vcpu.kvm)) exec_control &= ~CPU_BASED_HLT_EXITING; return exec_control; } static u64 vmx_tertiary_exec_control(struct vcpu_vmx *vmx) { u64 exec_control = vmcs_config.cpu_based_3rd_exec_ctrl; /* * IPI virtualization relies on APICv. Disable IPI virtualization if * APICv is inhibited. */ if (!enable_ipiv || !kvm_vcpu_apicv_active(&vmx->vcpu)) exec_control &= ~TERTIARY_EXEC_IPI_VIRT; return exec_control; } /* * Adjust a single secondary execution control bit to intercept/allow an * instruction in the guest. This is usually done based on whether or not a * feature has been exposed to the guest in order to correctly emulate faults. */ static inline void vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, u32 control, bool enabled, bool exiting) { /* * If the control is for an opt-in feature, clear the control if the * feature is not exposed to the guest, i.e. not enabled. If the * control is opt-out, i.e. an exiting control, clear the control if * the feature _is_ exposed to the guest, i.e. exiting/interception is * disabled for the associated instruction. Note, the caller is * responsible presetting exec_control to set all supported bits. */ if (enabled == exiting) *exec_control &= ~control; /* * Update the nested MSR settings so that a nested VMM can/can't set * controls for features that are/aren't exposed to the guest. */ if (nested && kvm_check_has_quirk(vmx->vcpu.kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) { /* * All features that can be added or removed to VMX MSRs must * be supported in the first place for nested virtualization. */ if (WARN_ON_ONCE(!(vmcs_config.nested.secondary_ctls_high & control))) enabled = false; if (enabled) vmx->nested.msrs.secondary_ctls_high |= control; else vmx->nested.msrs.secondary_ctls_high &= ~control; } } /* * Wrapper macro for the common case of adjusting a secondary execution control * based on a single guest CPUID bit, with a dedicated feature bit. This also * verifies that the control is actually supported by KVM and hardware. */ #define vmx_adjust_sec_exec_control(vmx, exec_control, name, feat_name, ctrl_name, exiting) \ ({ \ struct kvm_vcpu *__vcpu = &(vmx)->vcpu; \ bool __enabled; \ \ if (cpu_has_vmx_##name()) { \ __enabled = guest_cpu_cap_has(__vcpu, X86_FEATURE_##feat_name); \ vmx_adjust_secondary_exec_control(vmx, exec_control, SECONDARY_EXEC_##ctrl_name,\ __enabled, exiting); \ } \ }) /* More macro magic for ENABLE_/opt-in versus _EXITING/opt-out controls. */ #define vmx_adjust_sec_exec_feature(vmx, exec_control, lname, uname) \ vmx_adjust_sec_exec_control(vmx, exec_control, lname, uname, ENABLE_##uname, false) #define vmx_adjust_sec_exec_exiting(vmx, exec_control, lname, uname) \ vmx_adjust_sec_exec_control(vmx, exec_control, lname, uname, uname##_EXITING, true) static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) { struct kvm_vcpu *vcpu = &vmx->vcpu; u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; if (vmx_pt_mode_is_system()) exec_control &= ~(SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX); if (!cpu_need_virtualize_apic_accesses(vcpu)) exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (vmx->vpid == 0) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; enable_unrestricted_guest = 0; } if (!enable_unrestricted_guest) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; if (kvm_pause_in_guest(vmx->vcpu.kvm)) exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; if (!kvm_vcpu_apicv_active(vcpu)) exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; /* * KVM doesn't support VMFUNC for L1, but the control is set in KVM's * base configuration as KVM emulates VMFUNC[EPTP_SWITCHING] for L2. */ exec_control &= ~SECONDARY_EXEC_ENABLE_VMFUNC; if (!enable_mbec) exec_control &= ~SECONDARY_EXEC_MODE_BASED_EPT_EXEC; /* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP, * in vmx_set_cr4. */ exec_control &= ~SECONDARY_EXEC_DESC; /* SECONDARY_EXEC_SHADOW_VMCS is enabled when L1 executes VMPTRLD (handle_vmptrld). We can NOT enable shadow_vmcs here because we don't have yet a current VMCS12 */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; /* * PML is enabled/disabled when dirty logging of memsmlots changes, but * it needs to be set here when dirty logging is already active, e.g. * if this vCPU was created after dirty logging was enabled. */ if (!enable_pml || !atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) exec_control &= ~SECONDARY_EXEC_ENABLE_PML; vmx_adjust_sec_exec_feature(vmx, &exec_control, xsaves, XSAVES); /* * RDPID is also gated by ENABLE_RDTSCP, turn on the control if either * feature is exposed to the guest. This creates a virtualization hole * if both are supported in hardware but only one is exposed to the * guest, but letting the guest execute RDTSCP or RDPID when either one * is advertised is preferable to emulating the advertised instruction * in KVM on #UD, and obviously better than incorrectly injecting #UD. */ if (cpu_has_vmx_rdtscp()) { bool rdpid_or_rdtscp_enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) || guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID); vmx_adjust_secondary_exec_control(vmx, &exec_control, SECONDARY_EXEC_ENABLE_RDTSCP, rdpid_or_rdtscp_enabled, false); } vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdseed, RDSEED); vmx_adjust_sec_exec_control(vmx, &exec_control, waitpkg, WAITPKG, ENABLE_USR_WAIT_PAUSE, false); if (!vcpu->kvm->arch.bus_lock_detection_enabled) exec_control &= ~SECONDARY_EXEC_BUS_LOCK_DETECTION; if (!kvm_notify_vmexit_enabled(vcpu->kvm)) exec_control &= ~SECONDARY_EXEC_NOTIFY_VM_EXITING; return exec_control; } static inline int vmx_get_pid_table_order(struct kvm *kvm) { return get_order(kvm->arch.max_vcpu_ids * sizeof(*to_kvm_vmx(kvm)->pid_table)); } static int vmx_alloc_ipiv_pid_table(struct kvm *kvm) { struct page *pages; struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); if (!irqchip_in_kernel(kvm) || !enable_ipiv) return 0; if (kvm_vmx->pid_table) return 0; pages = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, vmx_get_pid_table_order(kvm)); if (!pages) return -ENOMEM; kvm_vmx->pid_table = (void *)page_address(pages); return 0; } int vmx_vcpu_precreate(struct kvm *kvm) { return vmx_alloc_ipiv_pid_table(kvm); } #define VMX_XSS_EXIT_BITMAP 0 static void init_vmcs(struct vcpu_vmx *vmx) { struct kvm *kvm = vmx->vcpu.kvm; struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); if (nested) nested_vmx_set_vmcs_shadowing_bitmap(); if (cpu_has_vmx_msr_bitmap()) vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA); /* 22.3.1.5 */ /* Control */ pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); exec_controls_set(vmx, vmx_exec_control(vmx)); if (cpu_has_secondary_exec_ctrls()) { secondary_exec_controls_set(vmx, vmx_secondary_exec_control(vmx)); if (vmx->ve_info) vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info)); } if (cpu_has_tertiary_exec_ctrls()) tertiary_exec_controls_set(vmx, vmx_tertiary_exec_control(vmx)); if (enable_apicv && lapic_in_kernel(&vmx->vcpu)) { vmcs_write64(EOI_EXIT_BITMAP0, 0); vmcs_write64(EOI_EXIT_BITMAP1, 0); vmcs_write64(EOI_EXIT_BITMAP2, 0); vmcs_write64(EOI_EXIT_BITMAP3, 0); vmcs_write16(GUEST_INTR_STATUS, 0); vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->vt.pi_desc))); } if (vmx_can_use_ipiv(&vmx->vcpu)) { vmcs_write64(PID_POINTER_TABLE, __pa(kvm_vmx->pid_table)); vmcs_write16(LAST_PID_POINTER_INDEX, kvm->arch.max_vcpu_ids - 1); } if (!kvm_pause_in_guest(kvm)) { vmcs_write32(PLE_GAP, ple_gap); vmx->ple_window = ple_window; vmx->ple_window_dirty = true; } if (kvm_notify_vmexit_enabled(kvm)) vmcs_write32(NOTIFY_WINDOW, kvm->arch.notify_window); vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0); vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0); vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ vmcs_write16(HOST_FS_SELECTOR, 0); /* 22.2.4 */ vmcs_write16(HOST_GS_SELECTOR, 0); /* 22.2.4 */ vmx_set_constant_host_state(vmx); vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */ vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */ if (cpu_has_vmx_vmfunc()) vmcs_write64(VM_FUNCTION_CONTROL, 0); vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); vmcs_write64(VM_EXIT_MSR_STORE_ADDR, __pa(vmx->msr_autostore.val)); vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val)); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val)); if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); vm_exit_controls_set(vmx, vmx_get_initial_vmexit_ctrl()); /* 22.2.1, 20.8.1 */ vm_entry_controls_set(vmx, vmx_get_initial_vmentry_ctrl()); vmx->vcpu.arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits); set_cr4_guest_host_mask(vmx); if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); if (cpu_has_vmx_xsaves()) vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP); if (enable_pml) { vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX); } vmx_write_encls_bitmap(&vmx->vcpu, NULL); if (vmx_pt_mode_is_host_guest()) { memset(&vmx->pt_desc, 0, sizeof(vmx->pt_desc)); /* Bit[6~0] are forced to 1, writes are ignored. */ vmx->pt_desc.guest.output_mask = 0x7F; vmcs_write64(GUEST_IA32_RTIT_CTL, 0); } vmcs_write32(GUEST_SYSENTER_CS, 0); vmcs_writel(GUEST_SYSENTER_ESP, 0); vmcs_writel(GUEST_SYSENTER_EIP, 0); vmx_guest_debugctl_write(&vmx->vcpu, 0); if (cpu_has_vmx_tpr_shadow()) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); if (cpu_need_tpr_shadow(&vmx->vcpu)) vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, __pa(vmx->vcpu.arch.apic->regs)); vmcs_write32(TPR_THRESHOLD, 0); } vmx_setup_uret_msrs(vmx); } static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); init_vmcs(vmx); if (nested && kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) memcpy(&vmx->nested.msrs, &vmcs_config.nested, sizeof(vmx->nested.msrs)); vcpu_setup_sgx_lepubkeyhash(vcpu); vmx->nested.posted_intr_nv = -1; vmx->nested.vmxon_ptr = INVALID_GPA; vmx->nested.current_vmptr = INVALID_GPA; #ifdef CONFIG_KVM_HYPERV vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; #endif if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; /* * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR * or POSTED_INTR_WAKEUP_VECTOR. */ vmx->vt.pi_desc.nv = POSTED_INTR_VECTOR; __pi_set_sn(&vmx->vt.pi_desc); } void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (!init_event) __vmx_vcpu_reset(vcpu); vmx->rmode.vm86_active = 0; vmx->spec_ctrl = 0; vmx->msr_ia32_umwait_control = 0; vmx->hv_deadline_tsc = -1; kvm_set_cr8(vcpu, 0); seg_setup(VCPU_SREG_CS); vmcs_write16(GUEST_CS_SELECTOR, 0xf000); vmcs_writel(GUEST_CS_BASE, 0xffff0000ul); seg_setup(VCPU_SREG_DS); seg_setup(VCPU_SREG_ES); seg_setup(VCPU_SREG_FS); seg_setup(VCPU_SREG_GS); seg_setup(VCPU_SREG_SS); vmcs_write16(GUEST_TR_SELECTOR, 0); vmcs_writel(GUEST_TR_BASE, 0); vmcs_write32(GUEST_TR_LIMIT, 0xffff); vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); vmcs_write16(GUEST_LDTR_SELECTOR, 0); vmcs_writel(GUEST_LDTR_BASE, 0); vmcs_write32(GUEST_LDTR_LIMIT, 0xffff); vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082); vmcs_writel(GUEST_GDTR_BASE, 0); vmcs_write32(GUEST_GDTR_LIMIT, 0xffff); vmcs_writel(GUEST_IDTR_BASE, 0); vmcs_write32(GUEST_IDTR_LIMIT, 0xffff); vmx_segment_cache_clear(vmx); kvm_register_mark_available(vcpu, VCPU_REG_SEGMENTS); vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0); if (kvm_mpx_supported()) vmcs_write64(GUEST_BNDCFGS, 0); vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) { vmcs_writel(GUEST_SSP, 0); vmcs_writel(GUEST_INTR_SSP_TABLE, 0); } if (kvm_cpu_cap_has(X86_FEATURE_IBT) || kvm_cpu_cap_has(X86_FEATURE_SHSTK)) vmcs_writel(GUEST_S_CET, 0); kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); vpid_sync_context(vmx->vpid); vmx_update_fb_clear_dis(vcpu, vmx); } void vmx_enable_irq_window(struct kvm_vcpu *vcpu) { exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); } void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) { if (!enable_vnmi || vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { vmx_enable_irq_window(vcpu); return; } exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); } void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { struct vcpu_vmx *vmx = to_vmx(vcpu); uint32_t intr; int irq = vcpu->arch.interrupt.nr; trace_kvm_inj_virq(irq, vcpu->arch.interrupt.soft, reinjected); ++vcpu->stat.irq_injections; if (vmx->rmode.vm86_active) { int inc_eip = 0; if (vcpu->arch.interrupt.soft) inc_eip = vcpu->arch.event_exit_inst_len; kvm_inject_realmode_interrupt(vcpu, irq, inc_eip); return; } intr = irq | INTR_INFO_VALID_MASK; if (vcpu->arch.interrupt.soft) { intr |= INTR_TYPE_SOFT_INTR; vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, vmx->vcpu.arch.event_exit_inst_len); } else intr |= INTR_TYPE_EXT_INTR; vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr); vmx_clear_hlt(vcpu); } void vmx_inject_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (!enable_vnmi) { /* * Tracking the NMI-blocked state in software is built upon * finding the next open IRQ window. This, in turn, depends on * well-behaving guests: They have to keep IRQs disabled at * least as long as the NMI handler runs. Otherwise we may * cause NMI nesting, maybe breaking the guest. But as this is * highly unlikely, we can live with the residual risk. */ vmx->loaded_vmcs->soft_vnmi_blocked = 1; vmx->loaded_vmcs->vnmi_blocked_time = 0; } ++vcpu->stat.nmi_injections; vmx->loaded_vmcs->nmi_known_unmasked = false; if (vmx->rmode.vm86_active) { kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0); return; } vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR); vmx_clear_hlt(vcpu); } bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool masked; if (!enable_vnmi) return vmx->loaded_vmcs->soft_vnmi_blocked; if (vmx->loaded_vmcs->nmi_known_unmasked) return false; masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI; vmx->loaded_vmcs->nmi_known_unmasked = !masked; return masked; } void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (!enable_vnmi) { if (vmx->loaded_vmcs->soft_vnmi_blocked != masked) { vmx->loaded_vmcs->soft_vnmi_blocked = masked; vmx->loaded_vmcs->vnmi_blocked_time = 0; } } else { vmx->loaded_vmcs->nmi_known_unmasked = !masked; if (masked) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); else vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); } } bool vmx_nmi_blocked(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_exit_on_nmi(vcpu)) return false; if (!enable_vnmi && to_vmx(vcpu)->loaded_vmcs->soft_vnmi_blocked) return true; return (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI | GUEST_INTR_STATE_NMI)); } int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (vcpu->arch.nested_run_pending) return -EBUSY; /* An NMI must not be injected into L2 if it's supposed to VM-Exit. */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_nmi(vcpu)) return -EBUSY; return !vmx_nmi_blocked(vcpu); } bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu) { return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); } bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) return false; return __vmx_interrupt_blocked(vcpu); } int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (vcpu->arch.nested_run_pending) return -EBUSY; /* * An IRQ must not be injected into L2 if it's supposed to VM-Exit, * e.g. if the IRQ arrived asynchronously after checking nested events. */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) return -EBUSY; return !vmx_interrupt_blocked(vcpu); } int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { void __user *ret; if (enable_unrestricted_guest) return 0; mutex_lock(&kvm->slots_lock); ret = __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, PAGE_SIZE * 3); mutex_unlock(&kvm->slots_lock); if (IS_ERR(ret)) return PTR_ERR(ret); to_kvm_vmx(kvm)->tss_addr = addr; return init_rmode_tss(kvm, ret); } int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { to_kvm_vmx(kvm)->ept_identity_map_addr = ident_addr; return 0; } static bool rmode_exception(struct kvm_vcpu *vcpu, int vec) { switch (vec) { case BP_VECTOR: /* * Update instruction length as we may reinject the exception * from user space while in guest debugging mode. */ to_vmx(vcpu)->vcpu.arch.event_exit_inst_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) return false; fallthrough; case DB_VECTOR: return !(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)); case DE_VECTOR: case OF_VECTOR: case BR_VECTOR: case UD_VECTOR: case DF_VECTOR: case SS_VECTOR: case GP_VECTOR: case MF_VECTOR: return true; } return false; } static int handle_rmode_exception(struct kvm_vcpu *vcpu, int vec, u32 err_code) { /* * Instruction with address size override prefix opcode 0x67 * Cause the #SS fault with 0 error code in VM86 mode. */ if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) { if (kvm_emulate_instruction(vcpu, 0)) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; return kvm_emulate_halt_noskip(vcpu); } return 1; } return 0; } /* * Forward all other exceptions that are valid in real mode. * FIXME: Breaks guest debugging in real mode, needs to be fixed with * the required debugging infrastructure rework. */ kvm_queue_exception(vcpu, vec); return 1; } static int handle_machine_check(struct kvm_vcpu *vcpu) { /* handled by vmx_vcpu_run() */ return 1; } /* * If the host has split lock detection disabled, then #AC is * unconditionally injected into the guest, which is the pre split lock * detection behaviour. * * If the host has split lock detection enabled then #AC is * only injected into the guest when: * - Guest CPL == 3 (user mode) * - Guest has #AC detection enabled in CR0 * - Guest EFLAGS has AC bit set */ bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu) { if (!boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) return true; return vmx_get_cpl(vcpu) == 3 && kvm_is_cr0_bit_set(vcpu, X86_CR0_AM) && (kvm_get_rflags(vcpu) & X86_EFLAGS_AC); } static bool is_xfd_nm_fault(struct kvm_vcpu *vcpu) { return vcpu->arch.guest_fpu.fpstate->xfd && !kvm_is_cr0_bit_set(vcpu, X86_CR0_TS); } static int vmx_handle_page_fault(struct kvm_vcpu *vcpu, u32 error_code) { unsigned long cr2 = vmx_get_exit_qual(vcpu); if (vcpu->arch.apf.host_apf_flags) goto handle_pf; /* When using EPT, KVM intercepts #PF only to detect illegal GPAs. */ WARN_ON_ONCE(enable_ept && !allow_smaller_maxphyaddr); /* * On SGX2 hardware, EPCM violations are delivered as #PF with the SGX * flag set in the error code (SGX1 hardware generates #GP(0)). EPCM * violations have nothing to do with shadow paging and can never be * resolved by KVM; always reflect them into the guest. */ if (error_code & PFERR_SGX_MASK) { WARN_ON_ONCE(!IS_ENABLED(CONFIG_X86_SGX_KVM) || !cpu_feature_enabled(X86_FEATURE_SGX2)); if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX2)) kvm_fixup_and_inject_pf_error(vcpu, cr2, error_code); else kvm_inject_gp(vcpu, 0); return 1; } /* * If EPT is enabled, fixup and inject the #PF. KVM intercepts #PFs * only to set PFERR_RSVD as appropriate (hardware won't set RSVD due * to the GPA being legal with respect to host.MAXPHYADDR). */ if (enable_ept) { kvm_fixup_and_inject_pf_error(vcpu, cr2, error_code); return 1; } handle_pf: return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0); } static int handle_exception_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_run *kvm_run = vcpu->run; u32 intr_info, ex_no, error_code; unsigned long dr6; u32 vect_info; vect_info = vmx->idt_vectoring_info; intr_info = vmx_get_intr_info(vcpu); /* * Machine checks are handled by handle_exception_irqoff(), or by * vmx_vcpu_run() if a #MC occurs on VM-Entry. NMIs are handled by * vmx_vcpu_enter_exit(). */ if (is_machine_check(intr_info) || is_nmi(intr_info)) return 1; /* * Queue the exception here instead of in handle_nm_fault_irqoff(). * This ensures the nested_vmx check is not skipped so vmexit can * be reflected to L1 (when it intercepts #NM) before reaching this * point. */ if (is_nm_fault(intr_info)) { kvm_queue_exception_p(vcpu, NM_VECTOR, is_xfd_nm_fault(vcpu) ? vcpu->arch.guest_fpu.xfd_err : 0); return 1; } if (is_invalid_opcode(intr_info)) return handle_ud(vcpu); if (WARN_ON_ONCE(is_ve_fault(intr_info))) { struct vmx_ve_information *ve_info = vmx->ve_info; WARN_ONCE(ve_info->exit_reason != EXIT_REASON_EPT_VIOLATION, "Unexpected #VE on VM-Exit reason 0x%x", ve_info->exit_reason); dump_vmcs(vcpu); kvm_mmu_print_sptes(vcpu, ve_info->guest_physical_address, "#VE"); return 1; } error_code = 0; if (intr_info & INTR_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) { WARN_ON_ONCE(!enable_vmware_backdoor); /* * VMware backdoor emulation on #GP interception only handles * IN{S}, OUT{S}, and RDPMC, none of which generate a non-zero * error code on #GP. */ if (error_code) { kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); return 1; } return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP); } /* * The #PF with PFEC.RSVD = 1 indicates the guest is accessing * MMIO, it is better to report an internal error. * See the comments in vmx_handle_exit. */ if ((vect_info & VECTORING_INFO_VALID_MASK) && !(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX; vcpu->run->internal.ndata = 4; vcpu->run->internal.data[0] = vect_info; vcpu->run->internal.data[1] = intr_info; vcpu->run->internal.data[2] = error_code; vcpu->run->internal.data[3] = vcpu->arch.last_vmentry_cpu; return 0; } if (is_page_fault(intr_info)) return vmx_handle_page_fault(vcpu, error_code); ex_no = intr_info & INTR_INFO_VECTOR_MASK; if (vmx->rmode.vm86_active && rmode_exception(vcpu, ex_no)) return handle_rmode_exception(vcpu, ex_no, error_code); switch (ex_no) { case DB_VECTOR: dr6 = vmx_get_exit_qual(vcpu); if (!(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { /* * If the #DB was due to ICEBP, a.k.a. INT1, skip the * instruction. ICEBP generates a trap-like #DB, but * despite its interception control being tied to #DB, * is an instruction intercept, i.e. the VM-Exit occurs * on the ICEBP itself. Use the inner "skip" helper to * avoid single-step #DB and MTF updates, as ICEBP is * higher priority. Note, skipping ICEBP still clears * STI and MOVSS blocking. */ if (is_icebp(intr_info)) WARN_ON(!skip_emulated_instruction(vcpu)); kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); return 1; } kvm_run->debug.arch.dr6 = dr6 | DR6_ACTIVE_LOW; kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); fallthrough; case BP_VECTOR: /* * Update instruction length as we may reinject #BP from * user space while in guest debugging mode. Reading it for * #DB as well causes no harm, it is not used in that case. */ vmx->vcpu.arch.event_exit_inst_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); kvm_run->exit_reason = KVM_EXIT_DEBUG; kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = ex_no; break; case AC_VECTOR: if (vmx_guest_inject_ac(vcpu)) { kvm_queue_exception_e(vcpu, AC_VECTOR, error_code); return 1; } /* * Handle split lock. Depending on detection mode this will * either warn and disable split lock detection for this * task or force SIGBUS on it. */ if (handle_guest_split_lock(kvm_rip_read(vcpu))) return 1; fallthrough; default: kvm_run->exit_reason = KVM_EXIT_EXCEPTION; kvm_run->ex.exception = ex_no; kvm_run->ex.error_code = error_code; break; } return 0; } static __always_inline int handle_external_interrupt(struct kvm_vcpu *vcpu) { ++vcpu->stat.irq_exits; return 1; } static int handle_triple_fault(struct kvm_vcpu *vcpu) { vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; vcpu->mmio_needed = 0; return 0; } static int handle_io(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; int size, in, string; unsigned port; exit_qualification = vmx_get_exit_qual(vcpu); string = (exit_qualification & 16) != 0; ++vcpu->stat.io_exits; if (string) return kvm_emulate_instruction(vcpu, 0); port = exit_qualification >> 16; size = (exit_qualification & 7) + 1; in = (exit_qualification & 8) != 0; return kvm_fast_pio(vcpu, size, port, in); } void vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) { /* * Patch in the VMCALL instruction: */ hypercall[0] = 0x0f; hypercall[1] = 0x01; hypercall[2] = 0xc1; } /* called to set cr0 as appropriate for a mov-to-cr0 exit. */ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) { if (is_guest_mode(vcpu)) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned long orig_val = val; /* * We get here when L2 changed cr0 in a way that did not change * any of L1's shadowed bits (see nested_vmx_exit_handled_cr), * but did change L0 shadowed bits. So we first calculate the * effective cr0 value that L1 would like to write into the * hardware. It consists of the L2-owned bits from the new * value combined with the L1-owned bits from L1's guest_cr0. */ val = (val & ~vmcs12->cr0_guest_host_mask) | (vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask); if (kvm_set_cr0(vcpu, val)) return 1; vmcs_writel(CR0_READ_SHADOW, orig_val); return 0; } else { return kvm_set_cr0(vcpu, val); } } static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) { if (is_guest_mode(vcpu)) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned long orig_val = val; /* analogously to handle_set_cr0 */ val = (val & ~vmcs12->cr4_guest_host_mask) | (vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask); if (kvm_set_cr4(vcpu, val)) return 1; vmcs_writel(CR4_READ_SHADOW, orig_val); return 0; } else return kvm_set_cr4(vcpu, val); } static int handle_desc(struct kvm_vcpu *vcpu) { /* * UMIP emulation relies on intercepting writes to CR4.UMIP, i.e. this * and other code needs to be updated if UMIP can be guest owned. */ BUILD_BUG_ON(KVM_POSSIBLE_CR4_GUEST_BITS & X86_CR4_UMIP); WARN_ON_ONCE(!kvm_is_cr4_bit_set(vcpu, X86_CR4_UMIP)); return kvm_emulate_instruction(vcpu, 0); } static int handle_cr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification, val; int cr; int reg; int err; int ret; exit_qualification = vmx_get_exit_qual(vcpu); cr = exit_qualification & 15; reg = (exit_qualification >> 8) & 15; switch ((exit_qualification >> 4) & 3) { case 0: /* mov to cr */ val = kvm_register_read(vcpu, reg); trace_kvm_cr_write(cr, val); switch (cr) { case 0: err = handle_set_cr0(vcpu, val); return kvm_complete_insn_gp(vcpu, err); case 3: WARN_ON_ONCE(enable_unrestricted_guest); err = kvm_set_cr3(vcpu, val); return kvm_complete_insn_gp(vcpu, err); case 4: err = handle_set_cr4(vcpu, val); return kvm_complete_insn_gp(vcpu, err); case 8: { u8 cr8_prev = kvm_get_cr8(vcpu); u8 cr8 = (u8)val; err = kvm_set_cr8(vcpu, cr8); ret = kvm_complete_insn_gp(vcpu, err); if (lapic_in_kernel(vcpu)) return ret; if (cr8_prev <= cr8) return ret; /* * TODO: we might be squashing a * KVM_GUESTDBG_SINGLESTEP-triggered * KVM_EXIT_DEBUG here. */ vcpu->run->exit_reason = KVM_EXIT_SET_TPR; return 0; } } break; case 2: /* clts */ KVM_BUG(1, vcpu->kvm, "Guest always owns CR0.TS"); return -EIO; case 1: /*mov from cr*/ switch (cr) { case 3: WARN_ON_ONCE(enable_unrestricted_guest); val = kvm_read_cr3(vcpu); kvm_register_write(vcpu, reg, val); trace_kvm_cr_read(cr, val); return kvm_skip_emulated_instruction(vcpu); case 8: val = kvm_get_cr8(vcpu); kvm_register_write(vcpu, reg, val); trace_kvm_cr_read(cr, val); return kvm_skip_emulated_instruction(vcpu); } break; case 3: /* lmsw */ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; trace_kvm_cr_write(0, (kvm_read_cr0_bits(vcpu, ~0xful) | val)); kvm_lmsw(vcpu, val); return kvm_skip_emulated_instruction(vcpu); default: break; } vcpu->run->exit_reason = 0; vcpu_unimpl(vcpu, "unhandled control register: op %d cr %d\n", (int)(exit_qualification >> 4) & 3, cr); return 0; } static int handle_dr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; int dr, dr7, reg; int err = 1; exit_qualification = vmx_get_exit_qual(vcpu); dr = exit_qualification & DEBUG_REG_ACCESS_NUM; /* First, if DR does not exist, trigger UD */ if (!kvm_require_dr(vcpu, dr)) return 1; if (vmx_get_cpl(vcpu) > 0) goto out; dr7 = vmcs_readl(GUEST_DR7); if (dr7 & DR7_GD) { /* * As the vm-exit takes precedence over the debug trap, we * need to emulate the latter, either for the host or the * guest debugging itself. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { vcpu->run->debug.arch.dr6 = DR6_BD | DR6_ACTIVE_LOW; vcpu->run->debug.arch.dr7 = dr7; vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu); vcpu->run->debug.arch.exception = DB_VECTOR; vcpu->run->exit_reason = KVM_EXIT_DEBUG; return 0; } else { kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BD); return 1; } } if (vcpu->guest_debug == 0) { exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING); /* * No more DR vmexits; force a reload of the debug registers * and reenter on this instruction. The next vmexit will * retrieve the full state of the debug registers. */ vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT; return 1; } reg = DEBUG_REG_ACCESS_REG(exit_qualification); if (exit_qualification & TYPE_MOV_FROM_DR) { kvm_register_write(vcpu, reg, kvm_get_dr(vcpu, dr)); err = 0; } else { err = kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg)); } out: return kvm_complete_insn_gp(vcpu, err); } void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { get_debugreg(vcpu->arch.db[0], 0); get_debugreg(vcpu->arch.db[1], 1); get_debugreg(vcpu->arch.db[2], 2); get_debugreg(vcpu->arch.db[3], 3); get_debugreg(vcpu->arch.dr6, 6); vcpu->arch.dr7 = vmcs_readl(GUEST_DR7); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT; exec_controls_setbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING); /* * exc_debug expects dr6 to be cleared after it runs, avoid that it sees * a stale dr6 from the guest. */ set_debugreg(DR6_RESERVED, 6); } void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); } static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) { kvm_apic_update_ppr(vcpu); return 1; } static int handle_interrupt_window(struct kvm_vcpu *vcpu) { exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); kvm_make_request(KVM_REQ_EVENT, vcpu); ++vcpu->stat.irq_window_exits; return 1; } static int handle_invlpg(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmx_get_exit_qual(vcpu); kvm_mmu_invlpg(vcpu, exit_qualification); return kvm_skip_emulated_instruction(vcpu); } static int handle_apic_access(struct kvm_vcpu *vcpu) { if (likely(fasteoi)) { unsigned long exit_qualification = vmx_get_exit_qual(vcpu); int access_type, offset; access_type = exit_qualification & APIC_ACCESS_TYPE; offset = exit_qualification & APIC_ACCESS_OFFSET; /* * Sane guest uses MOV to write EOI, with written value * not cared. So make a short-circuit here by avoiding * heavy instruction emulation. */ if ((access_type == TYPE_LINEAR_APIC_INST_WRITE) && (offset == APIC_EOI)) { kvm_lapic_set_eoi(vcpu); return kvm_skip_emulated_instruction(vcpu); } } return kvm_emulate_instruction(vcpu, 0); } static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmx_get_exit_qual(vcpu); int vector = exit_qualification & 0xff; /* EOI-induced VM exit is trap-like and thus no need to adjust IP */ kvm_apic_set_eoi_accelerated(vcpu, vector); return 1; } static int handle_apic_write(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmx_get_exit_qual(vcpu); /* * APIC-write VM-Exit is trap-like, KVM doesn't need to advance RIP and * hardware has done any necessary aliasing, offset adjustments, etc... * for the access. I.e. the correct value has already been written to * the vAPIC page for the correct 16-byte chunk. KVM needs only to * retrieve the register value and emulate the access. */ u32 offset = exit_qualification & 0xff0; kvm_apic_write_nodecode(vcpu, offset); return 1; } static int handle_task_switch(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qualification; bool has_error_code = false; u32 error_code = 0; u16 tss_selector; int reason, type, idt_v, idt_index; idt_v = (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK); idt_index = (vmx->idt_vectoring_info & VECTORING_INFO_VECTOR_MASK); type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK); exit_qualification = vmx_get_exit_qual(vcpu); reason = (u32)exit_qualification >> 30; if (reason == TASK_SWITCH_GATE && idt_v) { switch (type) { case INTR_TYPE_NMI_INTR: vcpu->arch.nmi_injected = false; vmx_set_nmi_mask(vcpu, true); break; case INTR_TYPE_EXT_INTR: case INTR_TYPE_SOFT_INTR: kvm_clear_interrupt_queue(vcpu); break; case INTR_TYPE_HARD_EXCEPTION: if (vmx->idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { has_error_code = true; error_code = vmcs_read32(IDT_VECTORING_ERROR_CODE); } fallthrough; case INTR_TYPE_SOFT_EXCEPTION: kvm_clear_exception_queue(vcpu); break; default: break; } } tss_selector = exit_qualification; if (!idt_v || (type != INTR_TYPE_HARD_EXCEPTION && type != INTR_TYPE_EXT_INTR && type != INTR_TYPE_NMI_INTR)) WARN_ON(!skip_emulated_instruction(vcpu)); /* * TODO: What about debug traps on tss switch? * Are we supposed to inject them and update dr6? */ return kvm_task_switch(vcpu, tss_selector, type == INTR_TYPE_SOFT_INTR ? idt_index : -1, reason, has_error_code, error_code); } static int handle_ept_violation(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmx_get_exit_qual(vcpu); gpa_t gpa; /* * EPT violation happened while executing iret from NMI, * "blocked by NMI" bit has to be set before next VM entry. * There are errata that may cause this bit to not be set: * AAK134, BY25. */ if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && enable_vnmi && (exit_qualification & INTR_INFO_UNBLOCK_NMI)) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); trace_kvm_page_fault(vcpu, gpa, exit_qualification); /* * Check that the GPA doesn't exceed physical memory limits, as that is * a guest page fault. We have to emulate the instruction here, because * if the illegal address is that of a paging structure, then * EPT_VIOLATION_ACC_WRITE bit is set. Alternatively, if supported we * would also use advanced VM-exit information for EPT violations to * reconstruct the page fault error code. */ if (unlikely(allow_smaller_maxphyaddr && !kvm_vcpu_is_legal_gpa(vcpu, gpa))) return kvm_emulate_instruction(vcpu, 0); return __vmx_handle_ept_violation(vcpu, gpa, exit_qualification); } static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { gpa_t gpa; if (vmx_check_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) return 1; /* * A nested guest cannot optimize MMIO vmexits, because we have an * nGPA here instead of the required GPA. */ gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); if (!is_guest_mode(vcpu) && !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { trace_kvm_fast_mmio(gpa); return kvm_skip_emulated_instruction(vcpu); } return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); } static int handle_nmi_window(struct kvm_vcpu *vcpu) { if (KVM_BUG_ON(!enable_vnmi, vcpu->kvm)) return -EIO; exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); ++vcpu->stat.nmi_window_exits; kvm_make_request(KVM_REQ_EVENT, vcpu); return 1; } /* * Returns true if emulation is required (due to the vCPU having invalid state * with unsrestricted guest mode disabled) and KVM can't faithfully emulate the * current vCPU state. */ static bool vmx_unhandleable_emulation_required(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (!vmx->vt.emulation_required) return false; /* * It is architecturally impossible for emulation to be required when a * nested VM-Enter is pending completion, as VM-Enter will VM-Fail if * guest state is invalid and unrestricted guest is disabled, i.e. KVM * should synthesize VM-Fail instead emulation L2 code. This path is * only reachable if userspace modifies L2 guest state after KVM has * performed the nested VM-Enter consistency checks. */ if (vcpu->arch.nested_run_pending) return true; /* * KVM only supports emulating exceptions if the vCPU is in Real Mode. * If emulation is required, KVM can't perform a successful VM-Enter to * inject the exception. */ return !vmx->rmode.vm86_active && (kvm_is_exception_pending(vcpu) || vcpu->arch.exception.injected); } static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool intr_window_requested; unsigned count = 130; intr_window_requested = exec_controls_get(vmx) & CPU_BASED_INTR_WINDOW_EXITING; while (vmx->vt.emulation_required && count-- != 0) { if (intr_window_requested && !vmx_interrupt_blocked(vcpu)) return handle_interrupt_window(&vmx->vcpu); if (kvm_test_request(KVM_REQ_EVENT, vcpu)) return 1; /* * Ensure that any updates to kvm->buses[] observed by the * previous instruction (emulated or otherwise) are also * visible to the instruction KVM is about to emulate. */ smp_rmb(); if (!kvm_emulate_instruction(vcpu, 0)) return 0; if (vmx_unhandleable_emulation_required(vcpu)) { kvm_prepare_emulation_failure_exit(vcpu); return 0; } if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; return kvm_emulate_halt_noskip(vcpu); } /* * Note, return 1 and not 0, vcpu_run() will invoke * xfer_to_guest_mode() which will create a proper return * code. */ if (__xfer_to_guest_mode_work_pending()) return 1; } return 1; } int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu) { if (vmx_unhandleable_emulation_required(vcpu)) { kvm_prepare_emulation_failure_exit(vcpu); return 0; } return 1; } /* * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE * exiting, so only get here on cpu with PAUSE-Loop-Exiting. */ static int handle_pause(struct kvm_vcpu *vcpu) { if (!kvm_pause_in_guest(vcpu->kvm)) grow_ple_window(vcpu); /* * Intel sdm vol3 ch-25.1.3 says: The "PAUSE-loop exiting" * VM-execution control is ignored if CPL > 0. OTOH, KVM * never set PAUSE_EXITING and just set PLE if supported, * so the vcpu must be CPL=0 if it gets a PAUSE exit. */ kvm_vcpu_on_spin(vcpu, true); return kvm_skip_emulated_instruction(vcpu); } static int handle_monitor_trap(struct kvm_vcpu *vcpu) { return 1; } static int handle_invpcid(struct kvm_vcpu *vcpu) { u32 vmx_instruction_info; unsigned long type; gva_t gva; struct { u64 pcid; u64 gla; } operand; int gpr_index; if (!guest_cpu_cap_has(vcpu, X86_FEATURE_INVPCID)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); type = kvm_register_read(vcpu, gpr_index); /* According to the Intel instruction reference, the memory operand * is read even if it isn't needed (e.g., for type==all) */ if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu), vmx_instruction_info, false, sizeof(operand), &gva)) return 1; return kvm_handle_invpcid(vcpu, type, gva); } static int handle_pml_full(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; trace_kvm_pml_full(vcpu->vcpu_id); exit_qualification = vmx_get_exit_qual(vcpu); /* * PML buffer FULL happened while executing iret from NMI, * "blocked by NMI" bit has to be set before next VM entry. */ if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && enable_vnmi && (exit_qualification & INTR_INFO_UNBLOCK_NMI)) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); /* * PML buffer already flushed at beginning of VMEXIT. Nothing to do * here.., and there's no userspace involvement needed for PML. */ return 1; } static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * In the *extremely* unlikely scenario that this is a spurious VM-Exit * due to the timer expiring while it was "soft" disabled, just eat the * exit and re-enter the guest. */ if (unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) return EXIT_FASTPATH_REENTER_GUEST; /* * If the timer expired because KVM used it to force an immediate exit, * then mission accomplished. */ if (force_immediate_exit) return EXIT_FASTPATH_EXIT_HANDLED; /* * If L2 is active, go down the slow path as emulating the guest timer * expiration likely requires synthesizing a nested VM-Exit. */ if (is_guest_mode(vcpu)) return EXIT_FASTPATH_NONE; kvm_lapic_expired_hv_timer(vcpu); return EXIT_FASTPATH_REENTER_GUEST; } static int handle_preemption_timer(struct kvm_vcpu *vcpu) { /* * This non-fastpath handler is reached if and only if the preemption * timer was being used to emulate a guest timer while L2 is active. * All other scenarios are supposed to be handled in the fastpath. */ WARN_ON_ONCE(!is_guest_mode(vcpu)); kvm_lapic_expired_hv_timer(vcpu); return 1; } /* * When nested=0, all VMX instruction VM Exits filter here. The handlers * are overwritten by nested_vmx_hardware_setup() when nested=1. */ static int handle_vmx_instruction(struct kvm_vcpu *vcpu) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } static int handle_tdx_instruction(struct kvm_vcpu *vcpu) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } #ifndef CONFIG_X86_SGX_KVM static int handle_encls(struct kvm_vcpu *vcpu) { /* * SGX virtualization is disabled. There is no software enable bit for * SGX, so KVM intercepts all ENCLS leafs and injects a #UD to prevent * the guest from executing ENCLS (when SGX is supported by hardware). */ kvm_queue_exception(vcpu, UD_VECTOR); return 1; } #endif /* CONFIG_X86_SGX_KVM */ static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu) { /* * Hardware may or may not set the BUS_LOCK_DETECTED flag on BUS_LOCK * VM-Exits. Unconditionally set the flag here and leave the handling to * vmx_handle_exit(). */ to_vt(vcpu)->exit_reason.bus_lock_detected = true; return 1; } static int handle_notify(struct kvm_vcpu *vcpu) { unsigned long exit_qual = vmx_get_exit_qual(vcpu); bool context_invalid = exit_qual & NOTIFY_VM_CONTEXT_INVALID; ++vcpu->stat.notify_window_exits; /* * Notify VM exit happened while executing iret from NMI, * "blocked by NMI" bit has to be set before next VM entry. */ if (enable_vnmi && (exit_qual & INTR_INFO_UNBLOCK_NMI)) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); if (vcpu->kvm->arch.notify_vmexit_flags & KVM_X86_NOTIFY_VMEXIT_USER || context_invalid) { vcpu->run->exit_reason = KVM_EXIT_NOTIFY; vcpu->run->notify.flags = context_invalid ? KVM_NOTIFY_CONTEXT_INVALID : 0; return 0; } return 1; } static int vmx_get_msr_imm_reg(struct kvm_vcpu *vcpu) { return vmx_get_instr_info_reg(vmcs_read32(VMX_INSTRUCTION_INFO)); } static int handle_rdmsr_imm(struct kvm_vcpu *vcpu) { return kvm_emulate_rdmsr_imm(vcpu, vmx_get_exit_qual(vcpu), vmx_get_msr_imm_reg(vcpu)); } static int handle_wrmsr_imm(struct kvm_vcpu *vcpu) { return kvm_emulate_wrmsr_imm(vcpu, vmx_get_exit_qual(vcpu), vmx_get_msr_imm_reg(vcpu)); } /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs * to be done to userspace and return 0. */ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EXCEPTION_NMI] = handle_exception_nmi, [EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt, [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault, [EXIT_REASON_NMI_WINDOW] = handle_nmi_window, [EXIT_REASON_IO_INSTRUCTION] = handle_io, [EXIT_REASON_CR_ACCESS] = handle_cr, [EXIT_REASON_DR_ACCESS] = handle_dr, [EXIT_REASON_CPUID] = kvm_emulate_cpuid, [EXIT_REASON_MSR_READ] = kvm_emulate_rdmsr, [EXIT_REASON_MSR_WRITE] = kvm_emulate_wrmsr, [EXIT_REASON_INTERRUPT_WINDOW] = handle_interrupt_window, [EXIT_REASON_HLT] = kvm_emulate_halt, [EXIT_REASON_INVD] = kvm_emulate_invd, [EXIT_REASON_INVLPG] = handle_invlpg, [EXIT_REASON_RDPMC] = kvm_emulate_rdpmc, [EXIT_REASON_VMCALL] = kvm_emulate_hypercall, [EXIT_REASON_VMCLEAR] = handle_vmx_instruction, [EXIT_REASON_VMLAUNCH] = handle_vmx_instruction, [EXIT_REASON_VMPTRLD] = handle_vmx_instruction, [EXIT_REASON_VMPTRST] = handle_vmx_instruction, [EXIT_REASON_VMREAD] = handle_vmx_instruction, [EXIT_REASON_VMRESUME] = handle_vmx_instruction, [EXIT_REASON_VMWRITE] = handle_vmx_instruction, [EXIT_REASON_VMOFF] = handle_vmx_instruction, [EXIT_REASON_VMON] = handle_vmx_instruction, [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold, [EXIT_REASON_APIC_ACCESS] = handle_apic_access, [EXIT_REASON_APIC_WRITE] = handle_apic_write, [EXIT_REASON_EOI_INDUCED] = handle_apic_eoi_induced, [EXIT_REASON_WBINVD] = kvm_emulate_wbinvd, [EXIT_REASON_XSETBV] = kvm_emulate_xsetbv, [EXIT_REASON_TASK_SWITCH] = handle_task_switch, [EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check, [EXIT_REASON_GDTR_IDTR] = handle_desc, [EXIT_REASON_LDTR_TR] = handle_desc, [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, [EXIT_REASON_MWAIT_INSTRUCTION] = kvm_emulate_mwait, [EXIT_REASON_MONITOR_TRAP_FLAG] = handle_monitor_trap, [EXIT_REASON_MONITOR_INSTRUCTION] = kvm_emulate_monitor, [EXIT_REASON_INVEPT] = handle_vmx_instruction, [EXIT_REASON_INVVPID] = handle_vmx_instruction, [EXIT_REASON_RDRAND] = kvm_handle_invalid_op, [EXIT_REASON_RDSEED] = kvm_handle_invalid_op, [EXIT_REASON_PML_FULL] = handle_pml_full, [EXIT_REASON_INVPCID] = handle_invpcid, [EXIT_REASON_VMFUNC] = handle_vmx_instruction, [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, [EXIT_REASON_ENCLS] = handle_encls, [EXIT_REASON_BUS_LOCK] = handle_bus_lock_vmexit, [EXIT_REASON_NOTIFY] = handle_notify, [EXIT_REASON_SEAMCALL] = handle_tdx_instruction, [EXIT_REASON_TDCALL] = handle_tdx_instruction, [EXIT_REASON_MSR_READ_IMM] = handle_rdmsr_imm, [EXIT_REASON_MSR_WRITE_IMM] = handle_wrmsr_imm, }; static const int kvm_vmx_max_exit_handlers = ARRAY_SIZE(kvm_vmx_exit_handlers); void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); *reason = vmx->vt.exit_reason.full; *info1 = vmx_get_exit_qual(vcpu); if (!(vmx->vt.exit_reason.failed_vmentry)) { *info2 = vmx->idt_vectoring_info; *intr_info = vmx_get_intr_info(vcpu); if (is_exception_with_error_code(*intr_info)) *error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); else *error_code = 0; } else { *info2 = 0; *intr_info = 0; *error_code = 0; } } void vmx_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code) { *intr_info = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD); if (is_exception_with_error_code(*intr_info)) *error_code = vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE); else *error_code = 0; } static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) { if (vmx->pml_pg) { __free_page(vmx->pml_pg); vmx->pml_pg = NULL; } } static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u16 pml_idx, pml_tail_index; u64 *pml_buf; int i; pml_idx = vmcs_read16(GUEST_PML_INDEX); /* Do nothing if PML buffer is empty */ if (pml_idx == PML_HEAD_INDEX) return; /* * PML index always points to the next available PML buffer entity * unless PML log has just overflowed. */ pml_tail_index = (pml_idx >= PML_LOG_NR_ENTRIES) ? 0 : pml_idx + 1; /* * PML log is written backwards: the CPU first writes the entry 511 * then the entry 510, and so on. * * Read the entries in the same order they were written, to ensure that * the dirty ring is filled in the same order the CPU wrote them. */ pml_buf = page_address(vmx->pml_pg); for (i = PML_HEAD_INDEX; i >= pml_tail_index; i--) { u64 gpa; gpa = pml_buf[i]; WARN_ON(gpa & (PAGE_SIZE - 1)); kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); } /* reset PML index */ vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX); } static void nested_vmx_mark_all_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); kvm_vcpu_map_mark_dirty(vcpu, &vmx->nested.apic_access_page_map); kvm_vcpu_map_mark_dirty(vcpu, &vmx->nested.virtual_apic_map); kvm_vcpu_map_mark_dirty(vcpu, &vmx->nested.pi_desc_map); } static void vmx_dump_sel(char *name, uint32_t sel) { pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", name, vmcs_read16(sel), vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); } static void vmx_dump_dtsel(char *name, uint32_t limit) { pr_err("%s limit=0x%08x, base=0x%016lx\n", name, vmcs_read32(limit), vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT)); } static void vmx_dump_msrs(char *name, struct vmx_msrs *m) { unsigned int i; struct vmx_msr_entry *e; pr_err("MSR %s:\n", name); for (i = 0, e = m->val; i < m->nr; ++i, ++e) pr_err(" %2d: msr=0x%08x value=0x%016llx\n", i, e->index, e->value); } void dump_vmcs(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 vmentry_ctl, vmexit_ctl; u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control; u64 tertiary_exec_control; unsigned long cr4; int efer_slot; if (!dump_invalid_vmcs) { pr_warn_ratelimited("set kvm_intel.dump_invalid_vmcs=1 to dump internal KVM state.\n"); return; } vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS); vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS); cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL); cr4 = vmcs_readl(GUEST_CR4); if (cpu_has_secondary_exec_ctrls()) secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); else secondary_exec_control = 0; if (cpu_has_tertiary_exec_ctrls()) tertiary_exec_control = vmcs_read64(TERTIARY_VM_EXEC_CONTROL); else tertiary_exec_control = 0; pr_err("VMCS %p, last attempted VM-entry on CPU %d\n", vmx->loaded_vmcs->vmcs, vcpu->arch.last_vmentry_cpu); pr_err("*** Guest State ***\n"); pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW), vmcs_readl(CR0_GUEST_HOST_MASK)); pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK)); pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3)); if (cpu_has_vmx_ept()) { pr_err("PDPTR0 = 0x%016llx PDPTR1 = 0x%016llx\n", vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1)); pr_err("PDPTR2 = 0x%016llx PDPTR3 = 0x%016llx\n", vmcs_read64(GUEST_PDPTR2), vmcs_read64(GUEST_PDPTR3)); } pr_err("RSP = 0x%016lx RIP = 0x%016lx\n", vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP)); pr_err("RFLAGS=0x%08lx DR7 = 0x%016lx\n", vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7)); pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", vmcs_readl(GUEST_SYSENTER_ESP), vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP)); vmx_dump_sel("CS: ", GUEST_CS_SELECTOR); vmx_dump_sel("DS: ", GUEST_DS_SELECTOR); vmx_dump_sel("SS: ", GUEST_SS_SELECTOR); vmx_dump_sel("ES: ", GUEST_ES_SELECTOR); vmx_dump_sel("FS: ", GUEST_FS_SELECTOR); vmx_dump_sel("GS: ", GUEST_GS_SELECTOR); vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT); vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR); vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT); vmx_dump_sel("TR: ", GUEST_TR_SELECTOR); efer_slot = vmx_find_loadstore_msr_slot(&vmx->msr_autoload.guest, MSR_EFER); if (vmentry_ctl & VM_ENTRY_LOAD_IA32_EFER) pr_err("EFER= 0x%016llx\n", vmcs_read64(GUEST_IA32_EFER)); else if (efer_slot >= 0) pr_err("EFER= 0x%016llx (autoload)\n", vmx->msr_autoload.guest.val[efer_slot].value); else if (vmentry_ctl & VM_ENTRY_IA32E_MODE) pr_err("EFER= 0x%016llx (effective)\n", vcpu->arch.efer | (EFER_LMA | EFER_LME)); else pr_err("EFER= 0x%016llx (effective)\n", vcpu->arch.efer & ~(EFER_LMA | EFER_LME)); if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PAT) pr_err("PAT = 0x%016llx\n", vmcs_read64(GUEST_IA32_PAT)); pr_err("DebugCtl = 0x%016llx DebugExceptions = 0x%016lx\n", vmcs_read64(GUEST_IA32_DEBUGCTL), vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS)); if (cpu_has_load_perf_global_ctrl() && vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) pr_err("PerfGlobCtl = 0x%016llx\n", vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL)); if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS) pr_err("BndCfgS = 0x%016llx\n", vmcs_read64(GUEST_BNDCFGS)); pr_err("Interruptibility = %08x ActivityState = %08x\n", vmcs_read32(GUEST_INTERRUPTIBILITY_INFO), vmcs_read32(GUEST_ACTIVITY_STATE)); if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) pr_err("InterruptStatus = %04x\n", vmcs_read16(GUEST_INTR_STATUS)); if (vmcs_read32(VM_ENTRY_MSR_LOAD_COUNT) > 0) vmx_dump_msrs("guest autoload", &vmx->msr_autoload.guest); if (vmcs_read32(VM_EXIT_MSR_STORE_COUNT) > 0) vmx_dump_msrs("autostore", &vmx->msr_autostore); if (vmentry_ctl & VM_ENTRY_LOAD_CET_STATE) pr_err("S_CET = 0x%016lx, SSP = 0x%016lx, SSP TABLE = 0x%016lx\n", vmcs_readl(GUEST_S_CET), vmcs_readl(GUEST_SSP), vmcs_readl(GUEST_INTR_SSP_TABLE)); pr_err("*** Host State ***\n"); pr_err("RIP = 0x%016lx RSP = 0x%016lx\n", vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP)); pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n", vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR), vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR), vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR), vmcs_read16(HOST_TR_SELECTOR)); pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n", vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE), vmcs_readl(HOST_TR_BASE)); pr_err("GDTBase=%016lx IDTBase=%016lx\n", vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE)); pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n", vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3), vmcs_readl(HOST_CR4)); pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", vmcs_readl(HOST_IA32_SYSENTER_ESP), vmcs_read32(HOST_IA32_SYSENTER_CS), vmcs_readl(HOST_IA32_SYSENTER_EIP)); if (vmexit_ctl & VM_EXIT_LOAD_IA32_EFER) pr_err("EFER= 0x%016llx\n", vmcs_read64(HOST_IA32_EFER)); if (vmexit_ctl & VM_EXIT_LOAD_IA32_PAT) pr_err("PAT = 0x%016llx\n", vmcs_read64(HOST_IA32_PAT)); if (cpu_has_load_perf_global_ctrl() && vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) pr_err("PerfGlobCtl = 0x%016llx\n", vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL)); if (vmcs_read32(VM_EXIT_MSR_LOAD_COUNT) > 0) vmx_dump_msrs("host autoload", &vmx->msr_autoload.host); if (vmexit_ctl & VM_EXIT_LOAD_CET_STATE) pr_err("S_CET = 0x%016lx, SSP = 0x%016lx, SSP TABLE = 0x%016lx\n", vmcs_readl(HOST_S_CET), vmcs_readl(HOST_SSP), vmcs_readl(HOST_INTR_SSP_TABLE)); pr_err("*** Control State ***\n"); pr_err("CPUBased=0x%08x SecondaryExec=0x%08x TertiaryExec=0x%016llx\n", cpu_based_exec_ctrl, secondary_exec_control, tertiary_exec_control); pr_err("PinBased=0x%08x EntryControls=%08x ExitControls=%08x\n", pin_based_exec_ctrl, vmentry_ctl, vmexit_ctl); pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n", vmcs_read32(EXCEPTION_BITMAP), vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK), vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH)); pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n", vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE), vmcs_read32(VM_ENTRY_INSTRUCTION_LEN)); pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n", vmcs_read32(VM_EXIT_INTR_INFO), vmcs_read32(VM_EXIT_INTR_ERROR_CODE), vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); pr_err(" reason=%08x qualification=%016lx\n", vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION)); pr_err("IDTVectoring: info=%08x errcode=%08x\n", vmcs_read32(IDT_VECTORING_INFO_FIELD), vmcs_read32(IDT_VECTORING_ERROR_CODE)); pr_err("TSC Offset = 0x%016llx\n", vmcs_read64(TSC_OFFSET)); if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING) pr_err("TSC Multiplier = 0x%016llx\n", vmcs_read64(TSC_MULTIPLIER)); if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW) { if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) { u16 status = vmcs_read16(GUEST_INTR_STATUS); pr_err("SVI|RVI = %02x|%02x ", status >> 8, status & 0xff); } pr_cont("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD)); if (secondary_exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) pr_err("APIC-access addr = 0x%016llx ", vmcs_read64(APIC_ACCESS_ADDR)); pr_cont("virt-APIC addr = 0x%016llx\n", vmcs_read64(VIRTUAL_APIC_PAGE_ADDR)); } if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR) pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV)); if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT)) pr_err("EPT pointer = 0x%016llx\n", vmcs_read64(EPT_POINTER)); if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING) pr_err("PLE Gap=%08x Window=%08x\n", vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW)); if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID) pr_err("Virtual processor ID = 0x%04x\n", vmcs_read16(VIRTUAL_PROCESSOR_ID)); if (secondary_exec_control & SECONDARY_EXEC_EPT_VIOLATION_VE) { struct vmx_ve_information *ve_info = vmx->ve_info; u64 ve_info_pa = vmcs_read64(VE_INFORMATION_ADDRESS); /* * If KVM is dumping the VMCS, then something has gone wrong * already. Derefencing an address from the VMCS, which could * very well be corrupted, is a terrible idea. The virtual * address is known so use it. */ pr_err("VE info address = 0x%016llx%s\n", ve_info_pa, ve_info_pa == __pa(ve_info) ? "" : "(corrupted!)"); pr_err("ve_info: 0x%08x 0x%08x 0x%016llx 0x%016llx 0x%016llx 0x%04x\n", ve_info->exit_reason, ve_info->delivery, ve_info->exit_qualification, ve_info->guest_linear_address, ve_info->guest_physical_address, ve_info->eptp_index); } } /* * The guest has exited. See if we can fix it or if we need userspace * assistance. */ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu); u32 vectoring_info = vmx->idt_vectoring_info; u16 exit_handler_index; /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before * querying dirty_bitmap, we only need to kick all vcpus out of guest * mode as if vcpus is in root mode, the PML buffer must has been * flushed already. Note, PML is never enabled in hardware while * running L2. */ if (enable_pml && !is_guest_mode(vcpu)) vmx_flush_pml_buffer(vcpu); if (unlikely(exit_fastpath == EXIT_FASTPATH_EXIT_USERSPACE)) return 0; /* * KVM should never reach this point with a pending nested VM-Enter. * More specifically, short-circuiting VM-Entry to emulate L2 due to * invalid guest state should never happen as that means KVM knowingly * allowed a nested VM-Enter with an invalid vmcs12. More below. */ if (KVM_BUG_ON(vcpu->arch.nested_run_pending, vcpu->kvm)) return -EIO; if (is_guest_mode(vcpu)) { /* * PML is never enabled when running L2, bail immediately if a * PML full exit occurs as something is horribly wrong. */ if (exit_reason.basic == EXIT_REASON_PML_FULL) goto unexpected_vmexit; /* * The host physical addresses of some pages of guest memory * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC * Page). The CPU may write to these pages via their host * physical address while L2 is running, bypassing any * address-translation-based dirty tracking (e.g. EPT write * protection). * * Mark them dirty on every exit from L2 to prevent them from * getting out of sync with dirty tracking. */ nested_vmx_mark_all_vmcs12_pages_dirty(vcpu); /* * Synthesize a triple fault if L2 state is invalid. In normal * operation, nested VM-Enter rejects any attempt to enter L2 * with invalid state. However, those checks are skipped if * state is being stuffed via RSM or KVM_SET_NESTED_STATE. If * L2 state is invalid, it means either L1 modified SMRAM state * or userspace provided bad state. Synthesize TRIPLE_FAULT as * doing so is architecturally allowed in the RSM case, and is * the least awful solution for the userspace case without * risking false positives. */ if (vmx->vt.emulation_required) { nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); return 1; } if (nested_vmx_reflect_vmexit(vcpu)) return 1; } /* If guest state is invalid, start emulating. L2 is handled above. */ if (vmx->vt.emulation_required) return handle_invalid_guest_state(vcpu); if (exit_reason.failed_vmentry) { dump_vmcs(vcpu); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason = exit_reason.full; vcpu->run->fail_entry.cpu = vcpu->arch.last_vmentry_cpu; return 0; } if (unlikely(vmx->fail)) { dump_vmcs(vcpu); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason = vmcs_read32(VM_INSTRUCTION_ERROR); vcpu->run->fail_entry.cpu = vcpu->arch.last_vmentry_cpu; return 0; } if ((vectoring_info & VECTORING_INFO_VALID_MASK) && (exit_reason.basic != EXIT_REASON_EXCEPTION_NMI && exit_reason.basic != EXIT_REASON_EPT_VIOLATION && exit_reason.basic != EXIT_REASON_PML_FULL && exit_reason.basic != EXIT_REASON_APIC_ACCESS && exit_reason.basic != EXIT_REASON_TASK_SWITCH && exit_reason.basic != EXIT_REASON_NOTIFY && exit_reason.basic != EXIT_REASON_EPT_MISCONFIG)) { kvm_prepare_event_vectoring_exit(vcpu, INVALID_GPA); return 0; } if (unlikely(!enable_vnmi && vmx->loaded_vmcs->soft_vnmi_blocked)) { if (!vmx_interrupt_blocked(vcpu)) { vmx->loaded_vmcs->soft_vnmi_blocked = 0; } else if (vmx->loaded_vmcs->vnmi_blocked_time > 1000000000LL && vcpu->arch.nmi_pending) { /* * This CPU don't support us in finding the end of an * NMI-blocked window if the guest runs with IRQs * disabled. So we pull the trigger after 1 s of * futile waiting, but inform the user about this. */ printk(KERN_WARNING "%s: Breaking out of NMI-blocked " "state on VCPU %d after 1 s timeout\n", __func__, vcpu->vcpu_id); vmx->loaded_vmcs->soft_vnmi_blocked = 0; } } if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; if (exit_reason.basic >= kvm_vmx_max_exit_handlers) goto unexpected_vmexit; #ifdef CONFIG_MITIGATION_RETPOLINE if (exit_reason.basic == EXIT_REASON_MSR_WRITE) return kvm_emulate_wrmsr(vcpu); else if (exit_reason.basic == EXIT_REASON_MSR_WRITE_IMM) return handle_wrmsr_imm(vcpu); else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER) return handle_preemption_timer(vcpu); else if (exit_reason.basic == EXIT_REASON_INTERRUPT_WINDOW) return handle_interrupt_window(vcpu); else if (exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) return handle_external_interrupt(vcpu); else if (exit_reason.basic == EXIT_REASON_HLT) return kvm_emulate_halt(vcpu); else if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) return handle_ept_misconfig(vcpu); #endif exit_handler_index = array_index_nospec((u16)exit_reason.basic, kvm_vmx_max_exit_handlers); if (!kvm_vmx_exit_handlers[exit_handler_index]) goto unexpected_vmexit; return kvm_vmx_exit_handlers[exit_handler_index](vcpu); unexpected_vmexit: dump_vmcs(vcpu); kvm_prepare_unexpected_reason_exit(vcpu, exit_reason.full); return 0; } int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { int ret = __vmx_handle_exit(vcpu, exit_fastpath); /* * Exit to user space when bus lock detected to inform that there is * a bus lock in guest. */ if (vmx_get_exit_reason(vcpu).bus_lock_detected) { if (ret > 0) vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK; return 0; } return ret; } void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { int tpr_threshold; if (is_guest_mode(vcpu) && nested_cpu_has(get_vmcs12(vcpu), CPU_BASED_TPR_SHADOW)) return; guard(vmx_vmcs01)(vcpu); tpr_threshold = (irr == -1 || tpr < irr) ? 0 : irr; vmcs_write32(TPR_THRESHOLD, tpr_threshold); } void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 sec_exec_control; if (!lapic_in_kernel(vcpu)) return; if (!flexpriority_enabled && !cpu_has_vmx_virtualize_x2apic_mode()) return; guard(vmx_vmcs01)(vcpu); sec_exec_control = secondary_exec_controls_get(vmx); sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); switch (kvm_get_apic_mode(vcpu)) { case LAPIC_MODE_INVALID: WARN_ONCE(true, "Invalid local APIC state"); break; case LAPIC_MODE_DISABLED: break; case LAPIC_MODE_XAPIC: if (flexpriority_enabled) { sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); /* * Flush the TLB, reloading the APIC access page will * only do so if its physical address has changed, but * the guest may have inserted a non-APIC mapping into * the TLB while the APIC access page was disabled. * * If L2 is active, immediately flush L1's TLB instead * of requesting a flush of the current TLB, because * the current TLB context is L2's. */ if (!is_guest_mode(vcpu)) kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); else if (!enable_ept) vpid_sync_context(vmx->vpid); else if (VALID_PAGE(vcpu->arch.root_mmu.root.hpa)) vmx_flush_tlb_ept_root(vcpu->arch.root_mmu.root.hpa); } break; case LAPIC_MODE_X2APIC: if (cpu_has_vmx_virtualize_x2apic_mode()) sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; break; } secondary_exec_controls_set(vmx, sec_exec_control); vmx_update_msr_bitmap_x2apic(vcpu); } void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) { const gfn_t gfn = APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT; struct kvm *kvm = vcpu->kvm; struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *slot; struct page *refcounted_page; unsigned long mmu_seq; kvm_pfn_t pfn; bool writable; /* Note, the VIRTUALIZE_APIC_ACCESSES check needs to query vmcs01. */ guard(vmx_vmcs01)(vcpu); if (!(secondary_exec_controls_get(to_vmx(vcpu)) & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) return; /* * Explicitly grab the memslot using KVM's internal slot ID to ensure * KVM doesn't unintentionally grab a userspace memslot. It _should_ * be impossible for userspace to create a memslot for the APIC when * APICv is enabled, but paranoia won't hurt in this case. */ slot = id_to_memslot(slots, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT); if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return; /* * Ensure that the mmu_notifier sequence count is read before KVM * retrieves the pfn from the primary MMU. Note, the memslot is * protected by SRCU, not the mmu_notifier. Pairs with the smp_wmb() * in kvm_mmu_invalidate_end(). */ mmu_seq = kvm->mmu_invalidate_seq; smp_rmb(); /* * No need to retry if the memslot does not exist or is invalid. KVM * controls the APIC-access page memslot, and only deletes the memslot * if APICv is permanently inhibited, i.e. the memslot won't reappear. */ pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, &writable, &refcounted_page); if (is_error_noslot_pfn(pfn)) return; read_lock(&vcpu->kvm->mmu_lock); if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); else vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(pfn)); /* * Do not pin the APIC access page in memory so that it can be freely * migrated, the MMU notifier will call us again if it is migrated or * swapped out. KVM backs the memslot with anonymous memory, the pfn * should always point at a refcounted page (if the pfn is valid). */ if (!WARN_ON_ONCE(!refcounted_page)) kvm_release_page_clean(refcounted_page); /* * No need for a manual TLB flush at this point, KVM has already done a * flush if there were SPTEs pointing at the previous page. */ read_unlock(&vcpu->kvm->mmu_lock); } void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) { u16 status; u8 old; if (max_isr == -1) max_isr = 0; /* * Always update SVI in vmcs01, as SVI is only relevant for L2 if and * only if Virtual Interrupt Delivery is enabled in vmcs12, and if VID * is enabled then L2 EOIs affect L2's vAPIC, not L1's vAPIC. */ guard(vmx_vmcs01)(vcpu); status = vmcs_read16(GUEST_INTR_STATUS); old = status >> 8; if (max_isr != old) { status &= 0xff; status |= max_isr << 8; vmcs_write16(GUEST_INTR_STATUS, status); } } static void vmx_set_rvi(int vector) { u16 status; u8 old; if (vector == -1) vector = 0; status = vmcs_read16(GUEST_INTR_STATUS); old = (u8)status & 0xff; if ((u8)vector != old) { status &= ~0xff; status |= (u8)vector; vmcs_write16(GUEST_INTR_STATUS, status); } } int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { struct vcpu_vt *vt = to_vt(vcpu); bool max_irr_is_from_pir; int max_irr; if (KVM_BUG_ON(!enable_apicv, vcpu->kvm)) return -EIO; if (pi_test_on(&vt->pi_desc)) { pi_clear_on(&vt->pi_desc); /* * IOMMU can write to PID.ON, so the barrier matters even on UP. * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); max_irr_is_from_pir = kvm_apic_update_irr(vcpu, vt->pi_desc.pir, &max_irr); } else { max_irr = kvm_lapic_find_highest_irr(vcpu); max_irr_is_from_pir = false; } /* * If APICv is enabled and L2 is not active, then update the Requesting * Virtual Interrupt (RVI) portion of vmcs01.GUEST_INTR_STATUS with the * highest priority IRR to deliver the IRQ via Virtual Interrupt * Delivery. Note, this is required even if the highest priority IRQ * was already pending in the IRR, as RVI isn't updated in lockstep with * the IRR (unlike apic->irr_pending). * * For the cases where Virtual Interrupt Delivery can't be used: * * 1) If L2 is running and the vCPU has a new pending interrupt. If L1 * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a * VM-Exit to L1. If L1 doesn't want to exit, the interrupt is injected * into L2, but KVM doesn't use virtual interrupt delivery to inject * interrupts into L2, and so KVM_REQ_EVENT is again needed. * * 2) If APICv is disabled for this vCPU, assigned devices may still * attempt to post interrupts. The posted interrupt vector will cause * a VM-Exit and the subsequent entry will call sync_pir_to_irr. * * In both cases, set KVM_REQ_EVENT if and only if the highest priority * pending IRQ came from the PIR, as setting KVM_REQ_EVENT if any IRQ * is pending may put the vCPU into an infinite loop, e.g. if the IRQ * is blocked, then it will stay pending until an IRQ window is opened. * * Note! It's possible that one or more IRQs were moved from the PIR * to the IRR _without_ max_irr_is_from_pir being true! I.e. if there * was a higher priority IRQ already pending in the IRR. Not setting * KVM_REQ_EVENT in this case is intentional and safe. If APICv is * inactive, or L2 is running with exit-on-interrupt off (in vmcs12), * i.e. without nested virtual interrupt delivery, then there's no need * to request an IRQ window as the lower priority IRQ only needs to be * delivered when the higher priority IRQ is dismissed from the ISR, * i.e. on the next EOI, and EOIs are always intercepted if APICv is * disabled or if L2 is running without nested VID. If L2 is running * exit-on-interrupt on (in vmcs12), then the higher priority IRQ will * trigger a nested VM-Exit, at which point KVM will re-evaluate L1's * pending IRQs. */ if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu)) vmx_set_rvi(max_irr); else if (max_irr_is_from_pir) kvm_make_request(KVM_REQ_EVENT, vcpu); return max_irr; } void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) return; vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]); vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]); vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) { /* * Save xfd_err to guest_fpu before interrupt is enabled, so the * MSR value is not clobbered by the host activity before the guest * has chance to consume it. * * Update the guest's XFD_ERR if and only if XFD is enabled, as the #NM * interception may have been caused by L1 interception. Per the SDM, * XFD_ERR is not modified for non-XFD #NM, i.e. if CR0.TS=1. * * Note, XFD_ERR is updated _before_ the #NM interception check, i.e. * unlike CR2 and DR6, the value is not a payload that is attached to * the #NM exception. */ if (is_xfd_nm_fault(vcpu)) rdmsrq(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); } static void handle_exception_irqoff(struct kvm_vcpu *vcpu, u32 intr_info) { /* if exit due to PF check for async PF */ if (is_page_fault(intr_info)) vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); /* if exit due to NM, handle before interrupts are enabled */ else if (is_nm_fault(intr_info)) handle_nm_fault_irqoff(vcpu); /* Handle machine checks before interrupts are enabled */ else if (is_machine_check(intr_info)) kvm_machine_check(); } static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu, u32 intr_info) { unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, "unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); x86_entry_from_kvm(EVENT_TYPE_EXTINT, vector); kvm_after_interrupt(vcpu); vcpu->arch.at_instruction_boundary = true; } void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) { if (to_vt(vcpu)->emulation_required) return; switch (vmx_get_exit_reason(vcpu).basic) { case EXIT_REASON_EXTERNAL_INTERRUPT: handle_external_interrupt_irqoff(vcpu, vmx_get_intr_info(vcpu)); break; case EXIT_REASON_EXCEPTION_NMI: handle_exception_irqoff(vcpu, vmx_get_intr_info(vcpu)); break; case EXIT_REASON_MCE_DURING_VMENTRY: kvm_machine_check(); break; default: break; } } /* * The kvm parameter can be NULL (module initialization, or invocation before * VM creation). Be sure to check the kvm parameter before using it. */ bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_SMBASE: if (!IS_ENABLED(CONFIG_KVM_SMM)) return false; /* * We cannot do SMM unless we can run the guest in big * real mode. */ return enable_unrestricted_guest || emulate_invalid_guest_state; case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: return nested; case MSR_AMD64_VIRT_SPEC_CTRL: case MSR_AMD64_TSC_RATIO: /* This is AMD only. */ return false; default: return true; } } static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { u32 exit_intr_info; bool unblock_nmi; u8 vector; bool idtv_info_valid; idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK; if (enable_vnmi) { if (vmx->loaded_vmcs->nmi_known_unmasked) return; exit_intr_info = vmx_get_intr_info(&vmx->vcpu); unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0; vector = exit_intr_info & INTR_INFO_VECTOR_MASK; /* * SDM 3: 27.7.1.2 (September 2008) * Re-set bit "block by NMI" before VM entry if vmexit caused by * a guest IRET fault. * SDM 3: 23.2.2 (September 2008) * Bit 12 is undefined in any of the following cases: * If the VM exit sets the valid bit in the IDT-vectoring * information field. * If the VM exit is due to a double fault. */ if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi && vector != DF_VECTOR && !idtv_info_valid) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); else vmx->loaded_vmcs->nmi_known_unmasked = !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI); } else if (unlikely(vmx->loaded_vmcs->soft_vnmi_blocked)) vmx->loaded_vmcs->vnmi_blocked_time += ktime_to_ns(ktime_sub(ktime_get(), vmx->loaded_vmcs->entry_time)); } static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, u32 idt_vectoring_info, int instr_len_field, int error_code_field) { u8 vector; int type; bool idtv_info_valid; idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK; vcpu->arch.nmi_injected = false; kvm_clear_exception_queue(vcpu); kvm_clear_interrupt_queue(vcpu); if (!idtv_info_valid) return; kvm_make_request(KVM_REQ_EVENT, vcpu); vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK; type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK; switch (type) { case INTR_TYPE_NMI_INTR: vcpu->arch.nmi_injected = true; /* * SDM 3: 27.7.1.2 (September 2008) * Clear bit "block by NMI" before VM entry if a NMI * delivery faulted. */ vmx_set_nmi_mask(vcpu, false); break; case INTR_TYPE_SOFT_EXCEPTION: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); fallthrough; case INTR_TYPE_HARD_EXCEPTION: { u32 error_code = 0; if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(error_code_field); kvm_requeue_exception(vcpu, vector, idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK, error_code); break; } case INTR_TYPE_SOFT_INTR: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); fallthrough; case INTR_TYPE_EXT_INTR: kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR); break; default: break; } } static void vmx_complete_interrupts(struct vcpu_vmx *vmx) { __vmx_complete_interrupts(&vmx->vcpu, vmx->idt_vectoring_info, VM_EXIT_INSTRUCTION_LEN, IDT_VECTORING_ERROR_CODE); } void vmx_cancel_injection(struct kvm_vcpu *vcpu) { __vmx_complete_interrupts(vcpu, vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), VM_ENTRY_INSTRUCTION_LEN, VM_ENTRY_EXCEPTION_ERROR_CODE); vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); } static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) { int i, nr_msrs; struct perf_guest_switch_msr *msrs; struct kvm_pmu *pmu = vcpu_to_pmu(&vmx->vcpu); if (kvm_vcpu_has_mediated_pmu(&vmx->vcpu)) return; pmu->host_cross_mapped_mask = 0; if (pmu->pebs_enable & pmu->global_ctrl) intel_pmu_cross_mapped_check(pmu); /* Note, nr_msrs may be garbage if perf_guest_get_msrs() returns NULL. */ msrs = perf_guest_get_msrs(&nr_msrs, (void *)pmu); if (!msrs) return; for (i = 0; i < nr_msrs; i++) if (msrs[i].host == msrs[i].guest) clear_atomic_switch_msr(vmx, msrs[i].msr); else add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest, msrs[i].host); } static void vmx_refresh_guest_perf_global_control(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); if (msr_write_intercepted(vmx, MSR_CORE_PERF_GLOBAL_CTRL)) return; if (!cpu_has_save_perf_global_ctrl()) { int slot = vmx_find_loadstore_msr_slot(&vmx->msr_autostore, MSR_CORE_PERF_GLOBAL_CTRL); if (WARN_ON_ONCE(slot < 0)) return; pmu->global_ctrl = vmx->msr_autostore.val[slot].value; vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL, pmu->global_ctrl); return; } pmu->global_ctrl = vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL); } static void vmx_update_hv_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 tscl; u32 delta_tsc; if (force_immediate_exit) { vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0); vmx->loaded_vmcs->hv_timer_soft_disabled = false; } else if (vmx->hv_deadline_tsc != -1) { tscl = rdtsc(); if (vmx->hv_deadline_tsc > tscl) /* set_hv_timer ensures the delta fits in 32-bits */ delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> cpu_preemption_timer_multi); else delta_tsc = 0; vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc); vmx->loaded_vmcs->hv_timer_soft_disabled = false; } else if (!vmx->loaded_vmcs->hv_timer_soft_disabled) { vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, -1); vmx->loaded_vmcs->hv_timer_soft_disabled = true; } } void noinstr vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) { if (unlikely(host_rsp != vmx->loaded_vmcs->host_state.rsp)) { vmx->loaded_vmcs->host_state.rsp = host_rsp; vmcs_writel(HOST_RSP, host_rsp); } } static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu, bool force_immediate_exit) { /* * If L2 is active, some VMX preemption timer exits can be handled in * the fastpath even, all other exits must use the slow path. */ if (is_guest_mode(vcpu) && vmx_get_exit_reason(vcpu).basic != EXIT_REASON_PREEMPTION_TIMER) return EXIT_FASTPATH_NONE; switch (vmx_get_exit_reason(vcpu).basic) { case EXIT_REASON_MSR_WRITE: return handle_fastpath_wrmsr(vcpu); case EXIT_REASON_MSR_WRITE_IMM: return handle_fastpath_wrmsr_imm(vcpu, vmx_get_exit_qual(vcpu), vmx_get_msr_imm_reg(vcpu)); case EXIT_REASON_PREEMPTION_TIMER: return handle_fastpath_preemption_timer(vcpu, force_immediate_exit); case EXIT_REASON_HLT: return handle_fastpath_hlt(vcpu); case EXIT_REASON_INVD: return handle_fastpath_invd(vcpu); default: return EXIT_FASTPATH_NONE; } } noinstr void vmx_handle_nmi(struct kvm_vcpu *vcpu) { if ((u16)vmx_get_exit_reason(vcpu).basic != EXIT_REASON_EXCEPTION_NMI || !is_nmi(vmx_get_intr_info(vcpu))) return; kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); x86_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR); kvm_after_interrupt(vcpu); } static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, unsigned int flags) { struct vcpu_vmx *vmx = to_vmx(vcpu); guest_state_enter_irqoff(); vmx_l1d_flush(vcpu); vmx_disable_fb_clear(vmx); if (vcpu->arch.cr2 != native_read_cr2()) native_write_cr2(vcpu->arch.cr2); vmx->fail = __vmx_vcpu_run(vmx, flags); vcpu->arch.cr2 = native_read_cr2(); kvm_clear_available_registers(vcpu, VMX_REGS_LAZY_LOAD_SET); vmx->idt_vectoring_info = 0; vmx_enable_fb_clear(vmx); if (unlikely(vmx->fail)) { vmx->vt.exit_reason.full = 0xdead; goto out; } vmx->vt.exit_reason.full = vmcs_read32(VM_EXIT_REASON); if (likely(!vmx_get_exit_reason(vcpu).failed_vmentry)) vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); vmx_handle_nmi(vcpu); out: guest_state_exit_irqoff(); } fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) { bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT; struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && vmx->loaded_vmcs->soft_vnmi_blocked)) vmx->loaded_vmcs->entry_time = ktime_get(); /* * Don't enter VMX if guest state is invalid, let the exit handler * start emulation until we arrive back to a valid state. Synthesize a * consistency check VM-Exit due to invalid guest state and bail. */ if (unlikely(vmx->vt.emulation_required)) { vmx->fail = 0; vmx->vt.exit_reason.full = EXIT_REASON_INVALID_STATE; vmx->vt.exit_reason.failed_vmentry = 1; kvm_register_mark_available(vcpu, VCPU_REG_EXIT_INFO_1); vmx->vt.exit_qualification = ENTRY_FAIL_DEFAULT; kvm_register_mark_available(vcpu, VCPU_REG_EXIT_INFO_2); vmx->vt.exit_intr_info = 0; return EXIT_FASTPATH_NONE; } trace_kvm_entry(vcpu, force_immediate_exit); if (vmx->ple_window_dirty) { vmx->ple_window_dirty = false; vmcs_write32(PLE_WINDOW, vmx->ple_window); } /* * We did this in prepare_switch_to_guest, because it needs to * be within srcu_read_lock. */ WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync); if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); if (kvm_register_is_dirty(vcpu, VCPU_REG_RIP)) vmcs_writel(GUEST_RIP, vcpu->arch.rip); kvm_reset_dirty_registers(vcpu); if (run_flags & KVM_RUN_LOAD_GUEST_DR6) set_debugreg(vcpu->arch.dr6, 6); if (run_flags & KVM_RUN_LOAD_DEBUGCTL) vmx_reload_guest_debugctl(vcpu); /* * Refresh vmcs.HOST_CR3 if necessary. This must be done immediately * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time * it switches back to the current->mm, which can occur in KVM context * when switching to a temporary mm to patch kernel code, e.g. if KVM * toggles a static key while handling a VM-Exit. */ cr3 = __get_current_cr3_fast(); if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { vmcs_writel(HOST_CR3, cr3); vmx->loaded_vmcs->host_state.cr3 = cr3; } cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); vmx->loaded_vmcs->host_state.cr4 = cr4; } /* When single-stepping over STI and MOV SS, we must clear the * corresponding interruptibility bits in the guest state. Otherwise * vmentry fails as it then expects bit 14 (BS) in pending debug * exceptions being set, but that's not correct for the guest debugging * case. */ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); pt_guest_enter(vmx); atomic_switch_perf_msrs(vmx); if (intel_pmu_lbr_is_enabled(vcpu)) vmx_passthrough_lbr_msrs(vcpu); if (enable_preemption_timer) vmx_update_hv_timer(vcpu, force_immediate_exit); else if (force_immediate_exit) smp_send_reschedule(vcpu->cpu); kvm_wait_lapic_expire(vcpu); /* The actual VMENTER/EXIT is in the .noinstr.text section. */ vmx_vcpu_enter_exit(vcpu, __vmx_vcpu_enter_flags(vmx)); /* All fields are clean at this point */ if (kvm_is_using_evmcs()) { current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; current_evmcs->hv_vp_id = kvm_hv_get_vpindex(vcpu); } /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ if (vcpu->arch.host_debugctl) update_debugctlmsr(vcpu->arch.host_debugctl); #ifndef CONFIG_X86_64 /* * The sysexit path does not restore ds/es, so we must set them to * a reasonable value ourselves. * * We can't defer this to vmx_prepare_switch_to_host() since that * function may be executed in interrupt context, which saves and * restore segments around it, nullifying its effect. */ loadsegment(ds, __USER_DS); loadsegment(es, __USER_DS); #endif pt_guest_exit(vmx); if (is_guest_mode(vcpu)) { /* * Track VMLAUNCH/VMRESUME that have made past guest state * checking. */ if (vcpu->arch.nested_run_pending && !vmx_get_exit_reason(vcpu).failed_vmentry) ++vcpu->stat.nested_run; vcpu->arch.nested_run_pending = 0; } if (unlikely(vmx->fail)) return EXIT_FASTPATH_NONE; trace_kvm_exit(vcpu, KVM_ISA_VMX); if (unlikely(vmx_get_exit_reason(vcpu).failed_vmentry)) return EXIT_FASTPATH_NONE; vmx->loaded_vmcs->launched = 1; vmx_refresh_guest_perf_global_control(vcpu); vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); return vmx_exit_handlers_fastpath(vcpu, force_immediate_exit); } void vmx_vcpu_free(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (enable_pml) vmx_destroy_pml_buffer(vmx); free_vpid(vmx->vpid); nested_vmx_free_vcpu(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); free_page((unsigned long)vmx->ve_info); } int vmx_vcpu_create(struct kvm_vcpu *vcpu) { struct vmx_uret_msr *tsx_ctrl; struct vcpu_vmx *vmx; int i, err; BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0); vmx = to_vmx(vcpu); INIT_LIST_HEAD(&vmx->vt.pi_wakeup_list); err = -ENOMEM; vmx->vpid = allocate_vpid(); /* * If PML is turned on, failure on enabling PML just results in failure * of creating the vcpu, therefore we can simplify PML logic (by * avoiding dealing with cases, such as enabling PML partially on vcpus * for the guest), etc. */ if (enable_pml) { vmx->pml_pg = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!vmx->pml_pg) goto free_vpid; } for (i = 0; i < kvm_nr_uret_msrs; ++i) vmx->guest_uret_msrs[i].mask = -1ull; if (boot_cpu_has(X86_FEATURE_RTM)) { /* * TSX_CTRL_CPUID_CLEAR is handled in the CPUID interception. * Keep the host value unchanged to avoid changing CPUID bits * under the host kernel's feet. */ tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (tsx_ctrl) tsx_ctrl->mask = ~(u64)TSX_CTRL_CPUID_CLEAR; } err = alloc_loaded_vmcs(&vmx->vmcs01); if (err < 0) goto free_pml; /* * Use Hyper-V 'Enlightened MSR Bitmap' feature when KVM runs as a * nested (L1) hypervisor and Hyper-V in L0 supports it. Enable the * feature only for vmcs01, KVM currently isn't equipped to realize any * performance benefits from enabling it for vmcs02. */ if (kvm_is_using_evmcs() && (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; evmcs->hv_enlightenments_control.msr_bitmap = 1; } vmx->loaded_vmcs = &vmx->vmcs01; if (cpu_need_virtualize_apic_accesses(vcpu)) { err = kvm_alloc_apic_access_page(vcpu->kvm); if (err) goto free_vmcs; } if (enable_ept && !enable_unrestricted_guest) { err = init_rmode_identity_map(vcpu->kvm); if (err) goto free_vmcs; } err = -ENOMEM; if (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_EPT_VIOLATION_VE) { struct page *page; BUILD_BUG_ON(sizeof(*vmx->ve_info) > PAGE_SIZE); /* ve_info must be page aligned. */ page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) goto free_vmcs; vmx->ve_info = page_to_virt(page); } if (vmx_can_use_ipiv(vcpu)) WRITE_ONCE(to_kvm_vmx(vcpu->kvm)->pid_table[vcpu->vcpu_id], __pa(&vmx->vt.pi_desc) | PID_TABLE_ENTRY_VALID); return 0; free_vmcs: free_loaded_vmcs(vmx->loaded_vmcs); free_pml: vmx_destroy_pml_buffer(vmx); free_vpid: free_vpid(vmx->vpid); return err; } #define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" #define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" int vmx_vm_init(struct kvm *kvm) { if (!ple_gap) kvm_disable_exits(kvm, KVM_X86_DISABLE_EXITS_PAUSE); if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) { switch (l1tf_mitigation) { case L1TF_MITIGATION_OFF: case L1TF_MITIGATION_FLUSH_NOWARN: /* 'I explicitly don't care' is set */ break; case L1TF_MITIGATION_AUTO: case L1TF_MITIGATION_FLUSH: case L1TF_MITIGATION_FLUSH_NOSMT: case L1TF_MITIGATION_FULL: /* * Warn upon starting the first VM in a potentially * insecure environment. */ if (sched_smt_active()) pr_warn_once(L1TF_MSG_SMT); if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER) pr_warn_once(L1TF_MSG_L1D); break; case L1TF_MITIGATION_FULL_FORCE: /* Flush is enforced */ break; } } if (enable_pml) kvm->arch.cpu_dirty_log_size = PML_LOG_NR_ENTRIES; return 0; } static inline bool vmx_ignore_guest_pat(struct kvm *kvm) { /* * Non-coherent DMA devices need the guest to flush CPU properly. * In that case it is not possible to map all guest RAM as WB, so * always trust guest PAT. */ return !kvm_arch_has_noncoherent_dma(kvm) && kvm_check_has_quirk(kvm, KVM_X86_QUIRK_IGNORE_GUEST_PAT); } u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { /* * Force UC for host MMIO regions, as allowing the guest to access MMIO * with cacheable accesses will result in Machine Checks. */ if (is_mmio) return MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; /* Force WB if ignoring guest PAT */ if (vmx_ignore_guest_pat(vcpu->kvm)) return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT); } static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl) { /* * These bits in the secondary execution controls field * are dynamic, the others are mostly based on the hypervisor * architecture and the guest's CPUID. Do not touch the * dynamic bits. */ u32 mask = SECONDARY_EXEC_SHADOW_VMCS | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_DESC; u32 cur_ctl = secondary_exec_controls_get(vmx); secondary_exec_controls_set(vmx, (new_ctl & ~mask) | (cur_ctl & mask)); } /* * Generate MSR_IA32_VMX_CR{0,4}_FIXED1 according to CPUID. Only set bits * (indicating "allowed-1") if they are supported in the guest's CPUID. */ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_cpuid_entry2 *entry; vmx->nested.msrs.cr0_fixed1 = 0xffffffff; vmx->nested.msrs.cr4_fixed1 = X86_CR4_PCE; #define cr4_fixed1_update(_cr4_mask, _reg, _cpuid_mask) do { \ if (entry && (entry->_reg & (_cpuid_mask))) \ vmx->nested.msrs.cr4_fixed1 |= (_cr4_mask); \ } while (0) entry = kvm_find_cpuid_entry(vcpu, 0x1); cr4_fixed1_update(X86_CR4_VME, edx, feature_bit(VME)); cr4_fixed1_update(X86_CR4_PVI, edx, feature_bit(VME)); cr4_fixed1_update(X86_CR4_TSD, edx, feature_bit(TSC)); cr4_fixed1_update(X86_CR4_DE, edx, feature_bit(DE)); cr4_fixed1_update(X86_CR4_PSE, edx, feature_bit(PSE)); cr4_fixed1_update(X86_CR4_PAE, edx, feature_bit(PAE)); cr4_fixed1_update(X86_CR4_MCE, edx, feature_bit(MCE)); cr4_fixed1_update(X86_CR4_PGE, edx, feature_bit(PGE)); cr4_fixed1_update(X86_CR4_OSFXSR, edx, feature_bit(FXSR)); cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, feature_bit(XMM)); cr4_fixed1_update(X86_CR4_VMXE, ecx, feature_bit(VMX)); cr4_fixed1_update(X86_CR4_SMXE, ecx, feature_bit(SMX)); cr4_fixed1_update(X86_CR4_PCIDE, ecx, feature_bit(PCID)); cr4_fixed1_update(X86_CR4_OSXSAVE, ecx, feature_bit(XSAVE)); entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 0); cr4_fixed1_update(X86_CR4_FSGSBASE, ebx, feature_bit(FSGSBASE)); cr4_fixed1_update(X86_CR4_SMEP, ebx, feature_bit(SMEP)); cr4_fixed1_update(X86_CR4_SMAP, ebx, feature_bit(SMAP)); cr4_fixed1_update(X86_CR4_PKE, ecx, feature_bit(PKU)); cr4_fixed1_update(X86_CR4_UMIP, ecx, feature_bit(UMIP)); cr4_fixed1_update(X86_CR4_LA57, ecx, feature_bit(LA57)); cr4_fixed1_update(X86_CR4_CET, ecx, feature_bit(SHSTK)); cr4_fixed1_update(X86_CR4_CET, edx, feature_bit(IBT)); entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 1); cr4_fixed1_update(X86_CR4_LAM_SUP, eax, feature_bit(LAM)); #undef cr4_fixed1_update } static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_cpuid_entry2 *best = NULL; int i; for (i = 0; i < PT_CPUID_LEAVES; i++) { best = kvm_find_cpuid_entry_index(vcpu, 0x14, i); if (!best) return; vmx->pt_desc.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM] = best->eax; vmx->pt_desc.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM] = best->ebx; vmx->pt_desc.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM] = best->ecx; vmx->pt_desc.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM] = best->edx; } /* Get the number of configurable Address Ranges for filtering */ vmx->pt_desc.num_address_ranges = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_num_address_ranges); /* Initialize and clear the no dependency bits */ vmx->pt_desc.ctl_bitmask = ~(RTIT_CTL_TRACEEN | RTIT_CTL_OS | RTIT_CTL_USR | RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC | RTIT_CTL_BRANCH_EN); /* * If CPUID.(EAX=14H,ECX=0):EBX[0]=1 CR3Filter can be set otherwise * will inject an #GP */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cr3_filtering)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_CR3EN; /* * If CPUID.(EAX=14H,ECX=0):EBX[1]=1 CYCEn, CycThresh and * PSBFreq can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc)) vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_CYCLEACC | RTIT_CTL_CYC_THRESH | RTIT_CTL_PSB_FREQ); /* * If CPUID.(EAX=14H,ECX=0):EBX[3]=1 MTCEn and MTCFreq can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc)) vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_MTC_EN | RTIT_CTL_MTC_RANGE); /* If CPUID.(EAX=14H,ECX=0):EBX[4]=1 FUPonPTW and PTWEn can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_ptwrite)) vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_FUP_ON_PTW | RTIT_CTL_PTW_EN); /* If CPUID.(EAX=14H,ECX=0):EBX[5]=1 PwrEvEn can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_power_event_trace)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_PWR_EVT_EN; /* If CPUID.(EAX=14H,ECX=0):ECX[0]=1 ToPA can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_TOPA; /* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabricEn can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_output_subsys)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN; /* unmask address range configure area */ for (i = 0; i < vmx->pt_desc.num_address_ranges; i++) vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4)); } void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * XSAVES is effectively enabled if and only if XSAVE is also exposed * to the guest. XSAVES depends on CR4.OSXSAVE, and CR4.OSXSAVE can be * set if and only if XSAVE is supported. */ if (!guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVE)) guest_cpu_cap_clear(vcpu, X86_FEATURE_XSAVES); vmx_setup_uret_msrs(vmx); if (cpu_has_secondary_exec_ctrls()) vmcs_set_secondary_exec_control(vmx, vmx_secondary_exec_control(vmx)); if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; else vmx->msr_ia32_feature_control_valid_bits &= ~(FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX); if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) nested_vmx_cr_fixed1_bits_update(vcpu); if (boot_cpu_has(X86_FEATURE_INTEL_PT) && guest_cpu_cap_has(vcpu, X86_FEATURE_INTEL_PT)) update_intel_pt_cfg(vcpu); if (boot_cpu_has(X86_FEATURE_RTM)) { struct vmx_uret_msr *msr; msr = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (msr) { bool enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_RTM); vmx_set_guest_uret_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE); } } set_cr4_guest_host_mask(vmx); vmx_write_encls_bitmap(vcpu, NULL); if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_SGX_ENABLED; else vmx->msr_ia32_feature_control_valid_bits &= ~FEAT_CTL_SGX_ENABLED; if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_SGX_LC_ENABLED; else vmx->msr_ia32_feature_control_valid_bits &= ~FEAT_CTL_SGX_LC_ENABLED; /* Refresh #PF interception to account for MAXPHYADDR changes. */ vmx_update_exception_bitmap(vcpu); } static __init u64 vmx_get_perf_capabilities(void) { u64 perf_cap = PERF_CAP_FW_WRITES; u64 host_perf_cap = 0; if (!enable_pmu) return 0; if (boot_cpu_has(X86_FEATURE_PDCM)) rdmsrq(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR) && !enable_mediated_pmu) { x86_perf_get_lbr(&vmx_lbr_caps); /* * KVM requires LBR callstack support, as the overhead due to * context switching LBRs without said support is too high. * See intel_pmu_create_guest_lbr_event() for more info. */ if (!vmx_lbr_caps.has_callstack) memset(&vmx_lbr_caps, 0, sizeof(vmx_lbr_caps)); else if (vmx_lbr_caps.nr) perf_cap |= host_perf_cap & PERF_CAP_LBR_FMT; } if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; /* * Disallow adaptive PEBS as it is functionally broken, can be * used by the guest to read *host* LBRs, and can be used to * bypass userspace event filters. To correctly and safely * support adaptive PEBS, KVM needs to: * * 1. Account for the ADAPTIVE flag when (re)programming fixed * counters. * * 2. Gain support from perf (or take direct control of counter * programming) to support events without adaptive PEBS * enabled for the hardware counter. * * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with * adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1. * * 4. Document which PMU events are effectively exposed to the * guest via adaptive PEBS, and make adaptive PEBS mutually * exclusive with KVM_SET_PMU_EVENT_FILTER if necessary. */ perf_cap &= ~PERF_CAP_PEBS_BASELINE; } return perf_cap; } static __init void vmx_set_cpu_caps(void) { kvm_initialize_cpu_caps(); /* CPUID 0x1 */ if (nested) kvm_cpu_cap_set(X86_FEATURE_VMX); /* CPUID 0x7 */ if (kvm_mpx_supported()) kvm_cpu_cap_check_and_set(X86_FEATURE_MPX); if (!cpu_has_vmx_invpcid()) kvm_cpu_cap_clear(X86_FEATURE_INVPCID); if (vmx_pt_mode_is_host_guest()) kvm_cpu_cap_check_and_set(X86_FEATURE_INTEL_PT); if (vmx_pebs_supported()) { kvm_cpu_cap_check_and_set(X86_FEATURE_DS); kvm_cpu_cap_check_and_set(X86_FEATURE_DTES64); } if (!enable_pmu) kvm_cpu_cap_clear(X86_FEATURE_PDCM); kvm_caps.supported_perf_cap = vmx_get_perf_capabilities(); if (!enable_sgx) { kvm_cpu_cap_clear(X86_FEATURE_SGX); kvm_cpu_cap_clear(X86_FEATURE_SGX_LC); kvm_cpu_cap_clear(X86_FEATURE_SGX1); kvm_cpu_cap_clear(X86_FEATURE_SGX2); kvm_cpu_cap_clear(X86_FEATURE_SGX_EDECCSSA); } if (vmx_umip_emulated()) kvm_cpu_cap_set(X86_FEATURE_UMIP); /* CPUID 0xD.1 */ if (!cpu_has_vmx_xsaves()) kvm_cpu_cap_clear(X86_FEATURE_XSAVES); /* CPUID 0x80000001 and 0x7 (RDPID) */ if (!cpu_has_vmx_rdtscp()) { kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); kvm_cpu_cap_clear(X86_FEATURE_RDPID); } if (cpu_has_vmx_waitpkg()) kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); /* * Disable CET if unrestricted_guest is unsupported as KVM doesn't * enforce CET HW behaviors in emulator. On platforms with * VMX_BASIC[bit56] == 0, inject #CP at VMX entry with error code * fails, so disable CET in this case too. */ if (!enable_cet || !enable_unrestricted_guest || !cpu_has_vmx_basic_no_hw_errcode_cc()) { kvm_cpu_cap_clear(X86_FEATURE_SHSTK); kvm_cpu_cap_clear(X86_FEATURE_IBT); } kvm_setup_xss_caps(); kvm_finalize_cpu_caps(); } static bool vmx_is_io_intercepted(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, unsigned long *exit_qualification) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned short port; int size; bool imm; /* * If the 'use IO bitmaps' VM-execution control is 0, IO instruction * VM-exits depend on the 'unconditional IO exiting' VM-execution * control. * * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. */ if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); if (info->intercept == x86_intercept_in || info->intercept == x86_intercept_ins) { port = info->src_val; size = info->dst_bytes; imm = info->src_type == OP_IMM; } else { port = info->dst_val; size = info->src_bytes; imm = info->dst_type == OP_IMM; } *exit_qualification = ((unsigned long)port << 16) | (size - 1); if (info->intercept == x86_intercept_ins || info->intercept == x86_intercept_outs) *exit_qualification |= BIT(4); if (info->rep_prefix) *exit_qualification |= BIT(5); if (imm) *exit_qualification |= BIT(6); return nested_vmx_check_io_bitmaps(vcpu, port, size); } int vmx_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage, struct x86_exception *exception) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned long exit_qualification = 0; u32 vm_exit_reason; u64 exit_insn_len; switch (info->intercept) { case x86_intercept_rdpid: /* * RDPID causes #UD if not enabled through secondary execution * controls (ENABLE_RDTSCP). Note, the implicit MSR access to * TSC_AUX is NOT subject to interception, i.e. checking only * the dedicated execution control is architecturally correct. */ if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_RDTSCP)) { exception->vector = UD_VECTOR; exception->error_code_valid = false; return X86EMUL_PROPAGATE_FAULT; } return X86EMUL_CONTINUE; case x86_intercept_in: case x86_intercept_ins: case x86_intercept_out: case x86_intercept_outs: if (!vmx_is_io_intercepted(vcpu, info, &exit_qualification)) return X86EMUL_CONTINUE; vm_exit_reason = EXIT_REASON_IO_INSTRUCTION; break; case x86_intercept_lgdt: case x86_intercept_lidt: case x86_intercept_lldt: case x86_intercept_ltr: case x86_intercept_sgdt: case x86_intercept_sidt: case x86_intercept_sldt: case x86_intercept_str: if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC)) return X86EMUL_CONTINUE; if (info->intercept == x86_intercept_lldt || info->intercept == x86_intercept_ltr || info->intercept == x86_intercept_sldt || info->intercept == x86_intercept_str) vm_exit_reason = EXIT_REASON_LDTR_TR; else vm_exit_reason = EXIT_REASON_GDTR_IDTR; /* * FIXME: Decode the ModR/M to generate the correct exit * qualification for memory operands. */ break; case x86_intercept_hlt: if (!nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING)) return X86EMUL_CONTINUE; vm_exit_reason = EXIT_REASON_HLT; break; case x86_intercept_pause: /* * PAUSE is a single-byte NOP with a REPE prefix, i.e. collides * with vanilla NOPs in the emulator. Apply the interception * check only to actual PAUSE instructions. Don't check * PAUSE-loop-exiting, software can't expect a given PAUSE to * exit, i.e. KVM is within its rights to allow L2 to execute * the PAUSE. */ if ((info->rep_prefix != REPE_PREFIX) || !nested_cpu_has(vmcs12, CPU_BASED_PAUSE_EXITING)) return X86EMUL_CONTINUE; vm_exit_reason = EXIT_REASON_PAUSE_INSTRUCTION; break; /* TODO: check more intercepts... */ default: return X86EMUL_UNHANDLEABLE; } exit_insn_len = abs_diff((s64)info->next_rip, (s64)info->rip); if (!exit_insn_len || exit_insn_len > X86_MAX_INSTRUCTION_LENGTH) return X86EMUL_UNHANDLEABLE; __nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification, exit_insn_len); return X86EMUL_INTERCEPTED; } #ifdef CONFIG_X86_64 /* (a << shift) / divisor, return 1 if overflow otherwise 0 */ static inline int u64_shl_div_u64(u64 a, unsigned int shift, u64 divisor, u64 *result) { u64 low = a << shift, high = a >> (64 - shift); /* To avoid the overflow on divq */ if (high >= divisor) return 1; /* Low hold the result, high hold rem which is discarded */ asm("divq %2\n\t" : "=a" (low), "=d" (high) : "rm" (divisor), "0" (low), "1" (high)); *result = low; return 0; } int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, bool *expired) { struct vcpu_vmx *vmx; u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer; vmx = to_vmx(vcpu); tscl = rdtsc(); guest_tscl = kvm_read_l1_tsc(vcpu, tscl); delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; lapic_timer_advance_cycles = nsec_to_cycles(vcpu, ktimer->timer_advance_ns); if (delta_tsc > lapic_timer_advance_cycles) delta_tsc -= lapic_timer_advance_cycles; else delta_tsc = 0; /* Convert to host delta tsc if tsc scaling is enabled */ if (vcpu->arch.l1_tsc_scaling_ratio != kvm_caps.default_tsc_scaling_ratio && delta_tsc && u64_shl_div_u64(delta_tsc, kvm_caps.tsc_scaling_ratio_frac_bits, vcpu->arch.l1_tsc_scaling_ratio, &delta_tsc)) return -ERANGE; /* * If the delta tsc can't fit in the 32 bit after the multi shift, * we can't use the preemption timer. * It's possible that it fits on later vmentries, but checking * on every vmentry is costly so we just use an hrtimer. */ if (delta_tsc >> (cpu_preemption_timer_multi + 32)) return -ERANGE; vmx->hv_deadline_tsc = tscl + delta_tsc; *expired = !delta_tsc; return 0; } void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) { to_vmx(vcpu)->hv_deadline_tsc = -1; } #endif void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (WARN_ON_ONCE(!enable_pml)) return; guard(vmx_vmcs01)(vcpu); /* * Note, nr_memslots_dirty_logging can be changed concurrent with this * code, but in that case another update request will be made and so * the guest will never run with a stale PML value. */ if (atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_ENABLE_PML); else secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML); } void vmx_setup_mce(struct kvm_vcpu *vcpu) { if (vcpu->arch.mcg_cap & MCG_LMCE_P) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= FEAT_CTL_LMCE_ENABLED; else to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= ~FEAT_CTL_LMCE_ENABLED; } #ifdef CONFIG_KVM_SMM int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { /* we need a nested vmexit to enter SMM, postpone if run is pending */ if (vcpu->arch.nested_run_pending) return -EBUSY; return !is_smm(vcpu); } int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * TODO: Implement custom flows for forcing the vCPU out/in of L2 on * SMI and RSM. Using the common VM-Exit + VM-Enter routines is wrong * SMI and RSM only modify state that is saved and restored via SMRAM. * E.g. most MSRs are left untouched, but many are modified by VM-Exit * and VM-Enter, and thus L2's values may be corrupted on SMI+RSM. */ vmx->nested.smm.guest_mode = is_guest_mode(vcpu); if (vmx->nested.smm.guest_mode) nested_vmx_vmexit(vcpu, -1, 0, 0); vmx->nested.smm.vmxon = vmx->nested.vmxon; vmx->nested.vmxon = false; vmx_clear_hlt(vcpu); return 0; } int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; if (vmx->nested.smm.vmxon) { vmx->nested.vmxon = true; vmx->nested.smm.vmxon = false; } if (vmx->nested.smm.guest_mode) { /* Triple fault if the state is invalid. */ if (nested_vmx_check_restored_vmcs12(vcpu) < 0) return 1; ret = nested_vmx_enter_non_root_mode(vcpu, false); if (ret != NVMX_VMENTRY_SUCCESS) return 1; vcpu->arch.nested_run_pending = KVM_NESTED_RUN_PENDING; vmx->nested.smm.guest_mode = false; } return 0; } void vmx_enable_smi_window(struct kvm_vcpu *vcpu) { /* RSM will cause a vmexit anyway. */ } #endif bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { return to_vmx(vcpu)->nested.vmxon && !is_guest_mode(vcpu); } void vmx_migrate_timers(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { struct hrtimer *timer = &to_vmx(vcpu)->nested.preemption_timer; if (hrtimer_try_to_cancel(timer) == 1) hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED); } } void vmx_hardware_unsetup(void) { kvm_set_posted_intr_wakeup_handler(NULL); if (nested) nested_vmx_hardware_unsetup(); } void vmx_vm_destroy(struct kvm *kvm) { struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); free_pages((unsigned long)kvm_vmx->pid_table, vmx_get_pid_table_order(kvm)); } /* * Note, the SDM states that the linear address is masked *after* the modified * canonicality check, whereas KVM masks (untags) the address and then performs * a "normal" canonicality check. Functionally, the two methods are identical, * and when the masking occurs relative to the canonicality check isn't visible * to software, i.e. KVM's behavior doesn't violate the SDM. */ gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags) { int lam_bit; unsigned long cr3_bits; if (flags & (X86EMUL_F_FETCH | X86EMUL_F_IMPLICIT | X86EMUL_F_INVLPG)) return gva; if (!is_64_bit_mode(vcpu)) return gva; /* * Bit 63 determines if the address should be treated as user address * or a supervisor address. */ if (!(gva & BIT_ULL(63))) { cr3_bits = kvm_get_active_cr3_lam_bits(vcpu); if (!(cr3_bits & (X86_CR3_LAM_U57 | X86_CR3_LAM_U48))) return gva; /* LAM_U48 is ignored if LAM_U57 is set. */ lam_bit = cr3_bits & X86_CR3_LAM_U57 ? 56 : 47; } else { if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_LAM_SUP)) return gva; lam_bit = kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 56 : 47; } /* * Untag the address by sign-extending the lam_bit, but NOT to bit 63. * Bit 63 is retained from the raw virtual address so that untagging * doesn't change a user access to a supervisor access, and vice versa. */ return (sign_extend64(gva, lam_bit) & ~BIT_ULL(63)) | (gva & BIT_ULL(63)); } static unsigned int vmx_handle_intel_pt_intr(void) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); /* '0' on failure so that the !PT case can use a RET0 static call. */ if (!vcpu || !kvm_handling_nmi_from_guest(vcpu)) return 0; kvm_make_request(KVM_REQ_PMI, vcpu); __set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT, (unsigned long *)&vcpu->arch.pmu.global_status); return 1; } static __init void vmx_setup_user_return_msrs(void) { /* * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm * will emulate SYSCALL in legacy mode if the vendor string in guest * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To * support this emulation, MSR_STAR is included in the list for i386, * but is never loaded into hardware. MSR_CSTAR is also never loaded * into hardware and is here purely for emulation purposes. */ const u32 vmx_uret_msrs_list[] = { #ifdef CONFIG_X86_64 MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif MSR_EFER, MSR_TSC_AUX, MSR_STAR, MSR_IA32_TSX_CTRL, }; int i; BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS); for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) kvm_add_user_return_msr(vmx_uret_msrs_list[i]); } static void __init vmx_setup_me_spte_mask(void) { u64 me_mask = 0; /* * On pre-MKTME system, boot_cpu_data.x86_phys_bits equals to * kvm_host.maxphyaddr. On MKTME and/or TDX capable systems, * boot_cpu_data.x86_phys_bits holds the actual physical address * w/o the KeyID bits, and kvm_host.maxphyaddr equals to * MAXPHYADDR reported by CPUID. Those bits between are KeyID bits. */ if (boot_cpu_data.x86_phys_bits != kvm_host.maxphyaddr) me_mask = rsvd_bits(boot_cpu_data.x86_phys_bits, kvm_host.maxphyaddr - 1); /* * Unlike SME, host kernel doesn't support setting up any * MKTME KeyID on Intel platforms. No memory encryption * bits should be included into the SPTE. */ kvm_mmu_set_me_spte_mask(0, me_mask); } __init int vmx_hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; int r; store_idt(&dt); host_idt_base = dt.address; vmx_setup_user_return_msrs(); if (boot_cpu_has(X86_FEATURE_MPX)) { rdmsrq(MSR_IA32_BNDCFGS, host_bndcfgs); WARN_ONCE(host_bndcfgs, "BNDCFGS in host will be lost"); } if (!cpu_has_vmx_mpx()) kvm_caps.supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; if (!cpu_has_vmx_ept() || !cpu_has_vmx_ept_4levels() || !cpu_has_vmx_ept_mt_wb() || !cpu_has_vmx_invept_global()) enable_ept = 0; if (!cpu_has_load_cet_ctrl()) enable_cet = 0; /* NX support is required for shadow paging. */ if (!enable_ept && !boot_cpu_has(X86_FEATURE_NX)) { pr_err_ratelimited("NX (Execute Disable) not supported\n"); return -EOPNOTSUPP; } /* * Shadow paging doesn't have a (further) performance penalty * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it * by default */ if (!enable_ept) allow_smaller_maxphyaddr = true; if (!cpu_has_vmx_ept_ad_bits() || !enable_ept) enable_ept_ad_bits = 0; if (!cpu_has_ept_mbec() || !enable_ept) enable_mbec = 0; if (!cpu_has_vmx_unrestricted_guest() || !enable_ept) enable_unrestricted_guest = 0; if (!cpu_has_vmx_flexpriority()) flexpriority_enabled = 0; if (!cpu_has_virtual_nmis()) enable_vnmi = 0; #ifdef CONFIG_X86_SGX_KVM if (!cpu_has_vmx_encls_vmexit()) enable_sgx = false; #endif /* * set_apic_access_page_addr() is used to reload apic access * page upon invalidation. No need to do anything if not * using the APIC_ACCESS_ADDR VMCS field. */ if (!flexpriority_enabled) vt_x86_ops.set_apic_access_page_addr = NULL; if (!cpu_has_vmx_tpr_shadow()) vt_x86_ops.update_cr8_intercept = NULL; #if IS_ENABLED(CONFIG_HYPERV) if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH && enable_ept) { vt_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; vt_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; } #endif if (!cpu_has_vmx_ple()) { ple_gap = 0; ple_window = 0; ple_window_grow = 0; ple_window_max = 0; ple_window_shrink = 0; } if (!cpu_has_vmx_apicv()) enable_apicv = 0; if (!enable_apicv) vt_x86_ops.sync_pir_to_irr = NULL; if (!enable_apicv || !cpu_has_vmx_ipiv()) enable_ipiv = false; if (cpu_has_vmx_tsc_scaling()) kvm_caps.has_tsc_control = true; kvm_caps.max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; kvm_caps.tsc_scaling_ratio_frac_bits = 48; kvm_caps.has_bus_lock_exit = cpu_has_vmx_bus_lock_detection(); kvm_caps.has_notify_vmexit = cpu_has_notify_vmexit(); set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ if (enable_ept) kvm_mmu_set_ept_masks(enable_ept_ad_bits); else vt_x86_ops.get_mt_mask = NULL; /* * Setup shadow_me_value/shadow_me_mask to include MKTME KeyID * bits to shadow_zero_check. */ vmx_setup_me_spte_mask(); kvm_configure_mmu(enable_ept, 0, vmx_get_max_ept_level(), ept_caps_to_lpage_level(vmx_capability.ept)); /* * Only enable PML when hardware supports PML feature, and both EPT * and EPT A/D bit features are enabled -- PML depends on them to work. */ if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml()) enable_pml = 0; if (!cpu_has_vmx_preemption_timer()) enable_preemption_timer = false; if (enable_preemption_timer) { u64 use_timer_freq = 5000ULL * 1000 * 1000; cpu_preemption_timer_multi = vmx_misc_preemption_timer_rate(vmcs_config.misc); if (tsc_khz) use_timer_freq = (u64)tsc_khz * 1000; use_timer_freq >>= cpu_preemption_timer_multi; /* * KVM "disables" the preemption timer by setting it to its max * value. Don't use the timer if it might cause spurious exits * at a rate faster than 0.1 Hz (of uninterrupted guest time). */ if (use_timer_freq > 0xffffffffu / 10) enable_preemption_timer = false; } if (!enable_preemption_timer) { vt_x86_ops.set_hv_timer = NULL; vt_x86_ops.cancel_hv_timer = NULL; } kvm_caps.supported_mce_cap |= MCG_LMCE_P; kvm_caps.supported_mce_cap |= MCG_CMCI_P; if (pt_mode != PT_MODE_SYSTEM && pt_mode != PT_MODE_HOST_GUEST) return -EINVAL; if (!enable_ept || !enable_pmu || !cpu_has_vmx_intel_pt()) pt_mode = PT_MODE_SYSTEM; if (pt_mode == PT_MODE_HOST_GUEST) vt_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr; else vt_init_ops.handle_intel_pt_intr = NULL; setup_default_sgx_lepubkeyhash(); vmx_set_cpu_caps(); /* * Configure nested capabilities after core CPU capabilities so that * nested support can be conditional on base support, e.g. so that KVM * can hide/show features based on kvm_cpu_cap_has(). */ if (nested) { r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); if (r) return r; } kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler); /* * On Intel CPUs that lack self-snoop feature, letting the guest control * memory types may result in unexpected behavior. So always ignore guest * PAT on those CPUs and map VM as writeback, not allowing userspace to * disable the quirk. * * On certain Intel CPUs (e.g. SPR, ICX), though self-snoop feature is * supported, UC is slow enough to cause issues with some older guests (e.g. * an old version of bochs driver uses ioremap() instead of ioremap_wc() to * map the video RAM, causing wayland desktop to fail to get started * correctly). To avoid breaking those older guests that rely on KVM to force * memory type to WB, provide KVM_X86_QUIRK_IGNORE_GUEST_PAT to preserve the * safer (for performance) default behavior. * * On top of this, non-coherent DMA devices need the guest to flush CPU * caches properly. This also requires honoring guest PAT, and is forced * independent of the quirk in vmx_ignore_guest_pat(). */ if (!static_cpu_has(X86_FEATURE_SELFSNOOP)) kvm_caps.supported_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT; kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT; return 0; } void vmx_exit(void) { allow_smaller_maxphyaddr = false; vmx_cleanup_l1d_flush(); kvm_x86_vendor_exit(); } int __init vmx_init(void) { int r, cpu; KVM_SANITY_CHECK_VM_STRUCT_SIZE(kvm_vmx); if (!kvm_is_vmx_supported()) return -EOPNOTSUPP; /* * Note, VMCS and eVMCS configuration only touch VMX knobs/variables, * i.e. there's nothing to unwind if a later step fails. */ hv_init_evmcs(); /* * Parse the VMCS config and VMX capabilities before anything else, so * that the information is available to all setup flows. */ if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) return -EIO; r = kvm_x86_vendor_init(&vt_init_ops); if (r) return r; /* Must be called after common x86 init so enable_ept is setup. */ r = vmx_setup_l1d_flush(); if (r) goto err_l1d_flush; for_each_possible_cpu(cpu) { INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); pi_init_cpu(cpu); } vmx_check_vmcs12_offsets(); return 0; err_l1d_flush: kvm_x86_vendor_exit(); return r; } |
| 105 104 105 95 95 95 95 95 94 94 95 95 94 93 94 94 94 94 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * drm gem framebuffer helper functions * * Copyright (C) 2017 Noralf Trønnes */ #include <linux/export.h> #include <linux/slab.h> #include <linux/module.h> #include <drm/drm_damage_helper.h> #include <drm/drm_drv.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_gem.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_modeset_helper.h> #include <drm/drm_print.h> #include "drm_internal.h" MODULE_IMPORT_NS("DMA_BUF"); #define AFBC_HEADER_SIZE 16 #define AFBC_TH_LAYOUT_ALIGNMENT 8 #define AFBC_HDR_ALIGN 64 #define AFBC_SUPERBLOCK_PIXELS 256 #define AFBC_SUPERBLOCK_ALIGNMENT 128 #define AFBC_TH_BODY_START_ALIGNMENT 4096 /** * DOC: overview * * This library provides helpers for drivers that don't subclass * &drm_framebuffer and use &drm_gem_object for their backing storage. * * Drivers without additional needs to validate framebuffers can simply use * drm_gem_fb_create() and everything is wired up automatically. Other drivers * can use all parts independently. */ /** * drm_gem_fb_get_obj() - Get GEM object backing the framebuffer * @fb: Framebuffer * @plane: Plane index * * No additional reference is taken beyond the one that the &drm_frambuffer * already holds. * * Returns: * Pointer to &drm_gem_object for the given framebuffer and plane index or NULL * if it does not exist. */ struct drm_gem_object *drm_gem_fb_get_obj(struct drm_framebuffer *fb, unsigned int plane) { struct drm_device *dev = fb->dev; if (drm_WARN_ON_ONCE(dev, plane >= ARRAY_SIZE(fb->obj))) return NULL; else if (drm_WARN_ON_ONCE(dev, !fb->obj[plane])) return NULL; return fb->obj[plane]; } EXPORT_SYMBOL_GPL(drm_gem_fb_get_obj); static int drm_gem_fb_init(struct drm_device *dev, struct drm_framebuffer *fb, const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **obj, unsigned int num_planes, const struct drm_framebuffer_funcs *funcs) { unsigned int i; int ret; drm_helper_mode_fill_fb_struct(dev, fb, info, mode_cmd); for (i = 0; i < num_planes; i++) fb->obj[i] = obj[i]; ret = drm_framebuffer_init(dev, fb, funcs); if (ret) drm_err(dev, "Failed to init framebuffer: %d\n", ret); return ret; } /** * drm_gem_fb_destroy - Free GEM backed framebuffer * @fb: Framebuffer * * Frees a GEM backed framebuffer with its backing buffer(s) and the structure * itself. Drivers can use this as their &drm_framebuffer_funcs->destroy * callback. */ void drm_gem_fb_destroy(struct drm_framebuffer *fb) { unsigned int i; for (i = 0; i < fb->format->num_planes; i++) drm_gem_object_put(fb->obj[i]); drm_framebuffer_cleanup(fb); kfree(fb); } EXPORT_SYMBOL(drm_gem_fb_destroy); /** * drm_gem_fb_create_handle - Create handle for GEM backed framebuffer * @fb: Framebuffer * @file: DRM file to register the handle for * @handle: Pointer to return the created handle * * This function creates a handle for the GEM object backing the framebuffer. * Drivers can use this as their &drm_framebuffer_funcs->create_handle * callback. The GETFB IOCTL calls into this callback. * * Returns: * 0 on success or a negative error code on failure. */ int drm_gem_fb_create_handle(struct drm_framebuffer *fb, struct drm_file *file, unsigned int *handle) { return drm_gem_handle_create(file, fb->obj[0], handle); } EXPORT_SYMBOL(drm_gem_fb_create_handle); /** * drm_gem_fb_init_with_funcs() - Helper function for implementing * &drm_mode_config_funcs.fb_create * callback in cases when the driver * allocates a subclass of * struct drm_framebuffer * @dev: DRM device * @fb: framebuffer object * @file: DRM file that holds the GEM handle(s) backing the framebuffer * @info: pixel format information * @mode_cmd: Metadata from the userspace framebuffer creation request * @funcs: vtable to be used for the new framebuffer object * * This function can be used to set &drm_framebuffer_funcs for drivers that need * custom framebuffer callbacks. Use drm_gem_fb_create() if you don't need to * change &drm_framebuffer_funcs. The function does buffer size validation. * The buffer size validation is for a general case, though, so users should * pay attention to the checks being appropriate for them or, at least, * non-conflicting. * * Returns: * Zero or a negative error code. */ int drm_gem_fb_init_with_funcs(struct drm_device *dev, struct drm_framebuffer *fb, struct drm_file *file, const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, const struct drm_framebuffer_funcs *funcs) { struct drm_gem_object *objs[DRM_FORMAT_MAX_PLANES]; unsigned int i; int ret; if (drm_drv_uses_atomic_modeset(dev) && !drm_any_plane_has_format(dev, mode_cmd->pixel_format, mode_cmd->modifier[0])) { drm_dbg_kms(dev, "Unsupported pixel format %p4cc / modifier 0x%llx\n", &mode_cmd->pixel_format, mode_cmd->modifier[0]); return -EINVAL; } for (i = 0; i < info->num_planes; i++) { unsigned int width = drm_format_info_plane_width(info, mode_cmd->width, i); unsigned int height = drm_format_info_plane_height(info, mode_cmd->height, i); unsigned int min_size; objs[i] = drm_gem_object_lookup(file, mode_cmd->handles[i]); if (!objs[i]) { drm_dbg_kms(dev, "Failed to lookup GEM object\n"); ret = -ENOENT; goto err_gem_object_put; } min_size = (height - 1) * mode_cmd->pitches[i] + drm_format_info_min_pitch(info, i, width) + mode_cmd->offsets[i]; if (objs[i]->size < min_size) { drm_dbg_kms(dev, "GEM object size (%zu) smaller than minimum size (%u) for plane %d\n", objs[i]->size, min_size, i); drm_gem_object_put(objs[i]); ret = -EINVAL; goto err_gem_object_put; } } ret = drm_gem_fb_init(dev, fb, info, mode_cmd, objs, i, funcs); if (ret) goto err_gem_object_put; return 0; err_gem_object_put: while (i > 0) { --i; drm_gem_object_put(objs[i]); } return ret; } EXPORT_SYMBOL_GPL(drm_gem_fb_init_with_funcs); /** * drm_gem_fb_create_with_funcs() - Helper function for the * &drm_mode_config_funcs.fb_create * callback * @dev: DRM device * @file: DRM file that holds the GEM handle(s) backing the framebuffer * @info: pixel format information * @mode_cmd: Metadata from the userspace framebuffer creation request * @funcs: vtable to be used for the new framebuffer object * * This function can be used to set &drm_framebuffer_funcs for drivers that need * custom framebuffer callbacks. Use drm_gem_fb_create() if you don't need to * change &drm_framebuffer_funcs. The function does buffer size validation. * * Returns: * Pointer to a &drm_framebuffer on success or an error pointer on failure. */ struct drm_framebuffer * drm_gem_fb_create_with_funcs(struct drm_device *dev, struct drm_file *file, const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, const struct drm_framebuffer_funcs *funcs) { struct drm_framebuffer *fb; int ret; fb = kzalloc_obj(*fb); if (!fb) return ERR_PTR(-ENOMEM); ret = drm_gem_fb_init_with_funcs(dev, fb, file, info, mode_cmd, funcs); if (ret) { kfree(fb); return ERR_PTR(ret); } return fb; } EXPORT_SYMBOL_GPL(drm_gem_fb_create_with_funcs); static const struct drm_framebuffer_funcs drm_gem_fb_funcs = { .destroy = drm_gem_fb_destroy, .create_handle = drm_gem_fb_create_handle, }; /** * drm_gem_fb_create() - Helper function for the * &drm_mode_config_funcs.fb_create callback * @dev: DRM device * @file: DRM file that holds the GEM handle(s) backing the framebuffer * @info: pixel format information * @mode_cmd: Metadata from the userspace framebuffer creation request * * This function creates a new framebuffer object described by * &drm_mode_fb_cmd2. This description includes handles for the buffer(s) * backing the framebuffer. * * If your hardware has special alignment or pitch requirements these should be * checked before calling this function. The function does buffer size * validation. Use drm_gem_fb_create_with_dirty() if you need framebuffer * flushing. * * Drivers can use this as their &drm_mode_config_funcs.fb_create callback. * The ADDFB2 IOCTL calls into this callback. * * Returns: * Pointer to a &drm_framebuffer on success or an error pointer on failure. */ struct drm_framebuffer * drm_gem_fb_create(struct drm_device *dev, struct drm_file *file, const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd) { return drm_gem_fb_create_with_funcs(dev, file, info, mode_cmd, &drm_gem_fb_funcs); } EXPORT_SYMBOL_GPL(drm_gem_fb_create); static const struct drm_framebuffer_funcs drm_gem_fb_funcs_dirtyfb = { .destroy = drm_gem_fb_destroy, .create_handle = drm_gem_fb_create_handle, .dirty = drm_atomic_helper_dirtyfb, }; /** * drm_gem_fb_create_with_dirty() - Helper function for the * &drm_mode_config_funcs.fb_create callback * @dev: DRM device * @file: DRM file that holds the GEM handle(s) backing the framebuffer * @info: pixel format information * @mode_cmd: Metadata from the userspace framebuffer creation request * * This function creates a new framebuffer object described by * &drm_mode_fb_cmd2. This description includes handles for the buffer(s) * backing the framebuffer. drm_atomic_helper_dirtyfb() is used for the dirty * callback giving framebuffer flushing through the atomic machinery. Use * drm_gem_fb_create() if you don't need the dirty callback. * The function does buffer size validation. * * Drivers should also call drm_plane_enable_fb_damage_clips() on all planes * to enable userspace to use damage clips also with the ATOMIC IOCTL. * * Drivers can use this as their &drm_mode_config_funcs.fb_create callback. * The ADDFB2 IOCTL calls into this callback. * * Returns: * Pointer to a &drm_framebuffer on success or an error pointer on failure. */ struct drm_framebuffer * drm_gem_fb_create_with_dirty(struct drm_device *dev, struct drm_file *file, const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd) { return drm_gem_fb_create_with_funcs(dev, file, info, mode_cmd, &drm_gem_fb_funcs_dirtyfb); } EXPORT_SYMBOL_GPL(drm_gem_fb_create_with_dirty); /** * drm_gem_fb_vmap - maps all framebuffer BOs into kernel address space * @fb: the framebuffer * @map: returns the mapping's address for each BO * @data: returns the data address for each BO, can be NULL * * This function maps all buffer objects of the given framebuffer into * kernel address space and stores them in struct iosys_map. If the * mapping operation fails for one of the BOs, the function unmaps the * already established mappings automatically. * * Callers that want to access a BO's stored data should pass @data. * The argument returns the addresses of the data stored in each BO. This * is different from @map if the framebuffer's offsets field is non-zero. * * Both, @map and @data, must each refer to arrays with at least * fb->format->num_planes elements. * * See drm_gem_fb_vunmap() for unmapping. * * Returns: * 0 on success, or a negative errno code otherwise. */ int drm_gem_fb_vmap(struct drm_framebuffer *fb, struct iosys_map *map, struct iosys_map *data) { struct drm_gem_object *obj; unsigned int i; int ret; for (i = 0; i < fb->format->num_planes; ++i) { obj = drm_gem_fb_get_obj(fb, i); if (!obj) { ret = -EINVAL; goto err_drm_gem_vunmap; } ret = drm_gem_vmap(obj, &map[i]); if (ret) goto err_drm_gem_vunmap; } if (data) { for (i = 0; i < fb->format->num_planes; ++i) { memcpy(&data[i], &map[i], sizeof(data[i])); if (iosys_map_is_null(&data[i])) continue; iosys_map_incr(&data[i], fb->offsets[i]); } } return 0; err_drm_gem_vunmap: while (i) { --i; obj = drm_gem_fb_get_obj(fb, i); if (!obj) continue; drm_gem_vunmap(obj, &map[i]); } return ret; } EXPORT_SYMBOL(drm_gem_fb_vmap); /** * drm_gem_fb_vunmap - unmaps framebuffer BOs from kernel address space * @fb: the framebuffer * @map: mapping addresses as returned by drm_gem_fb_vmap() * * This function unmaps all buffer objects of the given framebuffer. * * See drm_gem_fb_vmap() for more information. */ void drm_gem_fb_vunmap(struct drm_framebuffer *fb, struct iosys_map *map) { unsigned int i = fb->format->num_planes; struct drm_gem_object *obj; while (i) { --i; obj = drm_gem_fb_get_obj(fb, i); if (!obj) continue; if (iosys_map_is_null(&map[i])) continue; drm_gem_vunmap(obj, &map[i]); } } EXPORT_SYMBOL(drm_gem_fb_vunmap); static void __drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir, unsigned int num_planes) { struct dma_buf_attachment *import_attach; struct drm_gem_object *obj; int ret; while (num_planes) { --num_planes; obj = drm_gem_fb_get_obj(fb, num_planes); if (!obj) continue; import_attach = obj->import_attach; if (!drm_gem_is_imported(obj)) continue; ret = dma_buf_end_cpu_access(import_attach->dmabuf, dir); if (ret) drm_err(fb->dev, "dma_buf_end_cpu_access(%u, %d) failed: %d\n", ret, num_planes, dir); } } /** * drm_gem_fb_begin_cpu_access - prepares GEM buffer objects for CPU access * @fb: the framebuffer * @dir: access mode * * Prepares a framebuffer's GEM buffer objects for CPU access. This function * must be called before accessing the BO data within the kernel. For imported * BOs, the function calls dma_buf_begin_cpu_access(). * * See drm_gem_fb_end_cpu_access() for signalling the end of CPU access. * * Returns: * 0 on success, or a negative errno code otherwise. */ int drm_gem_fb_begin_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir) { struct dma_buf_attachment *import_attach; struct drm_gem_object *obj; unsigned int i; int ret; for (i = 0; i < fb->format->num_planes; ++i) { obj = drm_gem_fb_get_obj(fb, i); if (!obj) { ret = -EINVAL; goto err___drm_gem_fb_end_cpu_access; } import_attach = obj->import_attach; if (!drm_gem_is_imported(obj)) continue; ret = dma_buf_begin_cpu_access(import_attach->dmabuf, dir); if (ret) goto err___drm_gem_fb_end_cpu_access; } return 0; err___drm_gem_fb_end_cpu_access: __drm_gem_fb_end_cpu_access(fb, dir, i); return ret; } EXPORT_SYMBOL(drm_gem_fb_begin_cpu_access); /** * drm_gem_fb_end_cpu_access - signals end of CPU access to GEM buffer objects * @fb: the framebuffer * @dir: access mode * * Signals the end of CPU access to the given framebuffer's GEM buffer objects. This * function must be paired with a corresponding call to drm_gem_fb_begin_cpu_access(). * For imported BOs, the function calls dma_buf_end_cpu_access(). * * See also drm_gem_fb_begin_cpu_access(). */ void drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir) { __drm_gem_fb_end_cpu_access(fb, dir, fb->format->num_planes); } EXPORT_SYMBOL(drm_gem_fb_end_cpu_access); // TODO Drop this function and replace by drm_format_info_bpp() once all // DRM_FORMAT_* provide proper block info in drivers/gpu/drm/drm_fourcc.c static __u32 drm_gem_afbc_get_bpp(struct drm_device *dev, const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd) { switch (info->format) { case DRM_FORMAT_YUV420_8BIT: return 12; case DRM_FORMAT_YUV420_10BIT: return 15; case DRM_FORMAT_VUY101010: return 30; default: return drm_format_info_bpp(info, 0); } } static int drm_gem_afbc_min_size(struct drm_device *dev, const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_afbc_framebuffer *afbc_fb) { __u32 n_blocks, w_alignment, h_alignment, hdr_alignment; /* remove bpp when all users properly encode cpp in drm_format_info */ __u32 bpp; switch (mode_cmd->modifier[0] & AFBC_FORMAT_MOD_BLOCK_SIZE_MASK) { case AFBC_FORMAT_MOD_BLOCK_SIZE_16x16: afbc_fb->block_width = 16; afbc_fb->block_height = 16; break; case AFBC_FORMAT_MOD_BLOCK_SIZE_32x8: afbc_fb->block_width = 32; afbc_fb->block_height = 8; break; /* no user exists yet - fall through */ case AFBC_FORMAT_MOD_BLOCK_SIZE_64x4: case AFBC_FORMAT_MOD_BLOCK_SIZE_32x8_64x4: default: drm_dbg_kms(dev, "Invalid AFBC_FORMAT_MOD_BLOCK_SIZE: %lld.\n", mode_cmd->modifier[0] & AFBC_FORMAT_MOD_BLOCK_SIZE_MASK); return -EINVAL; } /* tiled header afbc */ w_alignment = afbc_fb->block_width; h_alignment = afbc_fb->block_height; hdr_alignment = AFBC_HDR_ALIGN; if (mode_cmd->modifier[0] & AFBC_FORMAT_MOD_TILED) { w_alignment *= AFBC_TH_LAYOUT_ALIGNMENT; h_alignment *= AFBC_TH_LAYOUT_ALIGNMENT; hdr_alignment = AFBC_TH_BODY_START_ALIGNMENT; } afbc_fb->aligned_width = ALIGN(mode_cmd->width, w_alignment); afbc_fb->aligned_height = ALIGN(mode_cmd->height, h_alignment); afbc_fb->offset = mode_cmd->offsets[0]; bpp = drm_gem_afbc_get_bpp(dev, info, mode_cmd); if (!bpp) { drm_dbg_kms(dev, "Invalid AFBC bpp value: %d\n", bpp); return -EINVAL; } n_blocks = (afbc_fb->aligned_width * afbc_fb->aligned_height) / AFBC_SUPERBLOCK_PIXELS; afbc_fb->afbc_size = ALIGN(n_blocks * AFBC_HEADER_SIZE, hdr_alignment); afbc_fb->afbc_size += n_blocks * ALIGN(bpp * AFBC_SUPERBLOCK_PIXELS / 8, AFBC_SUPERBLOCK_ALIGNMENT); return 0; } /** * drm_gem_fb_afbc_init() - Helper function for drivers using afbc to * fill and validate all the afbc-specific * struct drm_afbc_framebuffer members * * @dev: DRM device * @afbc_fb: afbc-specific framebuffer * @info: pixel format information * @mode_cmd: Metadata from the userspace framebuffer creation request * @afbc_fb: afbc framebuffer * * This function can be used by drivers which support afbc to complete * the preparation of struct drm_afbc_framebuffer. It must be called after * allocating the said struct and calling drm_gem_fb_init_with_funcs(). * It is caller's responsibility to put afbc_fb->base.obj objects in case * the call is unsuccessful. * * Returns: * Zero on success or a negative error value on failure. */ int drm_gem_fb_afbc_init(struct drm_device *dev, const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_afbc_framebuffer *afbc_fb) { struct drm_gem_object **objs; int ret; objs = afbc_fb->base.obj; ret = drm_gem_afbc_min_size(dev, info, mode_cmd, afbc_fb); if (ret < 0) return ret; if (objs[0]->size < afbc_fb->afbc_size) { drm_dbg_kms(dev, "GEM object size (%zu) smaller than minimum afbc size (%u)\n", objs[0]->size, afbc_fb->afbc_size); return -EINVAL; } return 0; } EXPORT_SYMBOL_GPL(drm_gem_fb_afbc_init); |
| 4 11 4 11 11 11 11 11 11 4 4 4 4 4 11 11 11 4 7 4 4 4 4 4 4 4 4 4 120 120 120 3 3 120 120 120 97 3 3 97 120 24 24 24 21 21 24 2 2 2 19 18 19 19 19 6 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 | // SPDX-License-Identifier: GPL-2.0-only /* * LED Triggers Core * * Copyright 2005-2007 Openedhand Ltd. * * Author: Richard Purdie <rpurdie@openedhand.com> */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/device.h> #include <linux/timer.h> #include <linux/rwsem.h> #include <linux/leds.h> #include <linux/slab.h> #include <linux/mm.h> #include "leds.h" /* * Nests outside led_cdev->trigger_lock */ static DECLARE_RWSEM(triggers_list_lock); static LIST_HEAD(trigger_list); /* Used by LED Class */ static inline bool trigger_relevant(struct led_classdev *led_cdev, struct led_trigger *trig) { return !trig->trigger_type || trig->trigger_type == led_cdev->trigger_type; } ssize_t led_trigger_write(struct file *filp, struct kobject *kobj, const struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { struct device *dev = kobj_to_dev(kobj); struct led_classdev *led_cdev = dev_get_drvdata(dev); struct led_trigger *trig; int ret = count; mutex_lock(&led_cdev->led_access); if (led_sysfs_is_disabled(led_cdev)) { ret = -EBUSY; goto unlock; } if (sysfs_streq(buf, "none")) { led_trigger_remove(led_cdev); goto unlock; } if (sysfs_streq(buf, "default")) { led_trigger_set_default(led_cdev); goto unlock; } down_read(&triggers_list_lock); list_for_each_entry(trig, &trigger_list, next_trig) { if (sysfs_streq(buf, trig->name) && trigger_relevant(led_cdev, trig)) { down_write(&led_cdev->trigger_lock); led_trigger_set(led_cdev, trig); up_write(&led_cdev->trigger_lock); up_read(&triggers_list_lock); goto unlock; } } /* we come here only if buf matches no trigger */ ret = -EINVAL; up_read(&triggers_list_lock); unlock: mutex_unlock(&led_cdev->led_access); return ret; } EXPORT_SYMBOL_GPL(led_trigger_write); __printf(3, 4) static int led_trigger_snprintf(char *buf, ssize_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); if (size <= 0) i = vsnprintf(NULL, 0, fmt, args); else i = vscnprintf(buf, size, fmt, args); va_end(args); return i; } static int led_trigger_format(char *buf, size_t size, struct led_classdev *led_cdev) { struct led_trigger *trig; int len = led_trigger_snprintf(buf, size, "%s", led_cdev->trigger ? "none" : "[none]"); if (led_cdev->default_trigger) len += led_trigger_snprintf(buf + len, size - len, " default"); list_for_each_entry(trig, &trigger_list, next_trig) { bool hit; if (!trigger_relevant(led_cdev, trig)) continue; hit = led_cdev->trigger && !strcmp(led_cdev->trigger->name, trig->name); len += led_trigger_snprintf(buf + len, size - len, " %s%s%s", hit ? "[" : "", trig->name, hit ? "]" : ""); } len += led_trigger_snprintf(buf + len, size - len, "\n"); return len; } /* * It was stupid to create 10000 cpu triggers, but we are stuck with it now. * Don't make that mistake again. We work around it here by creating binary * attribute, which is not limited by length. This is _not_ good design, do not * copy it. */ ssize_t led_trigger_read(struct file *filp, struct kobject *kobj, const struct bin_attribute *attr, char *buf, loff_t pos, size_t count) { struct device *dev = kobj_to_dev(kobj); struct led_classdev *led_cdev = dev_get_drvdata(dev); void *data; int len; down_read(&triggers_list_lock); down_read(&led_cdev->trigger_lock); len = led_trigger_format(NULL, 0, led_cdev); data = kvmalloc(len + 1, GFP_KERNEL); if (!data) { up_read(&led_cdev->trigger_lock); up_read(&triggers_list_lock); return -ENOMEM; } len = led_trigger_format(data, len + 1, led_cdev); up_read(&led_cdev->trigger_lock); up_read(&triggers_list_lock); len = memory_read_from_buffer(buf, count, &pos, data, len); kvfree(data); return len; } EXPORT_SYMBOL_GPL(led_trigger_read); /* Caller must ensure led_cdev->trigger_lock held */ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) { char *event = NULL; char *envp[2]; const char *name; int ret; if (!led_cdev->trigger && !trig) return 0; name = trig ? trig->name : "none"; event = kasprintf(GFP_KERNEL, "TRIGGER=%s", name); /* Remove any existing trigger */ if (led_cdev->trigger) { spin_lock(&led_cdev->trigger->leddev_list_lock); list_del_rcu(&led_cdev->trig_list); spin_unlock(&led_cdev->trigger->leddev_list_lock); /* ensure it's no longer visible on the led_cdevs list */ synchronize_rcu(); cancel_work_sync(&led_cdev->set_brightness_work); led_stop_software_blink(led_cdev); device_remove_groups(led_cdev->dev, led_cdev->trigger->groups); if (led_cdev->trigger->deactivate) led_cdev->trigger->deactivate(led_cdev); led_cdev->trigger = NULL; led_cdev->trigger_data = NULL; led_cdev->activated = false; led_cdev->flags &= ~LED_INIT_DEFAULT_TRIGGER; led_set_brightness(led_cdev, LED_OFF); } if (trig) { spin_lock(&trig->leddev_list_lock); list_add_tail_rcu(&led_cdev->trig_list, &trig->led_cdevs); spin_unlock(&trig->leddev_list_lock); led_cdev->trigger = trig; /* * Some activate() calls use led_trigger_event() to initialize * the brightness of the LED for which the trigger is being set. * Ensure the led_cdev is visible on trig->led_cdevs for this. */ synchronize_rcu(); /* * If "set brightness to 0" is pending in workqueue, * we don't want that to be reordered after ->activate() */ flush_work(&led_cdev->set_brightness_work); ret = 0; if (trig->activate) ret = trig->activate(led_cdev); else led_set_brightness(led_cdev, trig->brightness); if (ret) goto err_activate; ret = device_add_groups(led_cdev->dev, trig->groups); if (ret) { dev_err(led_cdev->dev, "Failed to add trigger attributes\n"); goto err_add_groups; } } if (event) { envp[0] = event; envp[1] = NULL; if (kobject_uevent_env(&led_cdev->dev->kobj, KOBJ_CHANGE, envp)) dev_err(led_cdev->dev, "%s: Error sending uevent\n", __func__); kfree(event); } return 0; err_add_groups: if (trig->deactivate) trig->deactivate(led_cdev); err_activate: spin_lock(&led_cdev->trigger->leddev_list_lock); list_del_rcu(&led_cdev->trig_list); spin_unlock(&led_cdev->trigger->leddev_list_lock); synchronize_rcu(); led_cdev->trigger = NULL; led_cdev->trigger_data = NULL; led_set_brightness(led_cdev, LED_OFF); kfree(event); return ret; } EXPORT_SYMBOL_GPL(led_trigger_set); void led_trigger_remove(struct led_classdev *led_cdev) { down_write(&led_cdev->trigger_lock); led_trigger_set(led_cdev, NULL); up_write(&led_cdev->trigger_lock); } EXPORT_SYMBOL_GPL(led_trigger_remove); static bool led_match_default_trigger(struct led_classdev *led_cdev, struct led_trigger *trig) { if (!strcmp(led_cdev->default_trigger, trig->name) && trigger_relevant(led_cdev, trig)) { led_cdev->flags |= LED_INIT_DEFAULT_TRIGGER; led_trigger_set(led_cdev, trig); return true; } return false; } void led_trigger_set_default(struct led_classdev *led_cdev) { struct led_trigger *trig; bool found = false; if (!led_cdev->default_trigger) return; if (!strcmp(led_cdev->default_trigger, "none")) { led_trigger_remove(led_cdev); return; } down_read(&triggers_list_lock); down_write(&led_cdev->trigger_lock); list_for_each_entry(trig, &trigger_list, next_trig) { found = led_match_default_trigger(led_cdev, trig); if (found) break; } up_write(&led_cdev->trigger_lock); up_read(&triggers_list_lock); /* * If default trigger wasn't found, maybe trigger module isn't loaded yet. * Once loaded it will re-probe with all led_cdev's. */ if (!found) request_module_nowait("ledtrig:%s", led_cdev->default_trigger); } EXPORT_SYMBOL_GPL(led_trigger_set_default); /* LED Trigger Interface */ int led_trigger_register(struct led_trigger *trig) { struct led_classdev *led_cdev; struct led_trigger *_trig; spin_lock_init(&trig->leddev_list_lock); INIT_LIST_HEAD(&trig->led_cdevs); down_write(&triggers_list_lock); /* Make sure the trigger's name isn't already in use */ list_for_each_entry(_trig, &trigger_list, next_trig) { if (!strcmp(_trig->name, trig->name) && (trig->trigger_type == _trig->trigger_type || !trig->trigger_type || !_trig->trigger_type)) { up_write(&triggers_list_lock); return -EEXIST; } } /* Add to the list of led triggers */ list_add_tail(&trig->next_trig, &trigger_list); up_write(&triggers_list_lock); /* Register with any LEDs that have this as a default trigger */ down_read(&leds_list_lock); list_for_each_entry(led_cdev, &leds_list, node) { down_write(&led_cdev->trigger_lock); if (!led_cdev->trigger && led_cdev->default_trigger) led_match_default_trigger(led_cdev, trig); up_write(&led_cdev->trigger_lock); } up_read(&leds_list_lock); return 0; } EXPORT_SYMBOL_GPL(led_trigger_register); void led_trigger_unregister(struct led_trigger *trig) { struct led_classdev *led_cdev; if (list_empty_careful(&trig->next_trig)) return; /* Remove from the list of led triggers */ down_write(&triggers_list_lock); list_del_init(&trig->next_trig); up_write(&triggers_list_lock); /* Remove anyone actively using this trigger */ down_read(&leds_list_lock); list_for_each_entry(led_cdev, &leds_list, node) { down_write(&led_cdev->trigger_lock); if (led_cdev->trigger == trig) led_trigger_set(led_cdev, NULL); up_write(&led_cdev->trigger_lock); } up_read(&leds_list_lock); } EXPORT_SYMBOL_GPL(led_trigger_unregister); static void devm_led_trigger_release(struct device *dev, void *res) { led_trigger_unregister(*(struct led_trigger **)res); } int devm_led_trigger_register(struct device *dev, struct led_trigger *trig) { struct led_trigger **dr; int rc; dr = devres_alloc(devm_led_trigger_release, sizeof(*dr), GFP_KERNEL); if (!dr) return -ENOMEM; *dr = trig; rc = led_trigger_register(trig); if (rc) devres_free(dr); else devres_add(dev, dr); return rc; } EXPORT_SYMBOL_GPL(devm_led_trigger_register); /* Simple LED Trigger Interface */ void led_trigger_event(struct led_trigger *trig, enum led_brightness brightness) { struct led_classdev *led_cdev; if (!trig) return; trig->brightness = brightness; rcu_read_lock(); list_for_each_entry_rcu(led_cdev, &trig->led_cdevs, trig_list) led_set_brightness(led_cdev, brightness); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(led_trigger_event); void led_mc_trigger_event(struct led_trigger *trig, unsigned int *intensity_value, unsigned int num_colors, enum led_brightness brightness) { struct led_classdev *led_cdev; if (!trig) return; rcu_read_lock(); list_for_each_entry_rcu(led_cdev, &trig->led_cdevs, trig_list) { if (!(led_cdev->flags & LED_MULTI_COLOR)) continue; led_mc_set_brightness(led_cdev, intensity_value, num_colors, brightness); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(led_mc_trigger_event); static void led_trigger_blink_setup(struct led_trigger *trig, unsigned long delay_on, unsigned long delay_off, int oneshot, int invert) { struct led_classdev *led_cdev; if (!trig) return; rcu_read_lock(); list_for_each_entry_rcu(led_cdev, &trig->led_cdevs, trig_list) { if (oneshot) led_blink_set_oneshot(led_cdev, &delay_on, &delay_off, invert); else led_blink_set_nosleep(led_cdev, delay_on, delay_off); } rcu_read_unlock(); } void led_trigger_blink(struct led_trigger *trig, unsigned long delay_on, unsigned long delay_off) { led_trigger_blink_setup(trig, delay_on, delay_off, 0, 0); } EXPORT_SYMBOL_GPL(led_trigger_blink); void led_trigger_blink_oneshot(struct led_trigger *trig, unsigned long delay_on, unsigned long delay_off, int invert) { led_trigger_blink_setup(trig, delay_on, delay_off, 1, invert); } EXPORT_SYMBOL_GPL(led_trigger_blink_oneshot); void led_trigger_register_simple(const char *name, struct led_trigger **tp) { struct led_trigger *trig; int err; trig = kzalloc_obj(struct led_trigger); if (trig) { trig->name = name; err = led_trigger_register(trig); if (err < 0) { kfree(trig); trig = NULL; pr_warn("LED trigger %s failed to register (%d)\n", name, err); } } else { pr_warn("LED trigger %s failed to register (no memory)\n", name); } *tp = trig; } EXPORT_SYMBOL_GPL(led_trigger_register_simple); void led_trigger_unregister_simple(struct led_trigger *trig) { if (trig) led_trigger_unregister(trig); kfree(trig); } EXPORT_SYMBOL_GPL(led_trigger_unregister_simple); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "ratelimiter.h" #include <linux/siphash.h> #include <linux/mm.h> #include <linux/slab.h> #include <net/ip.h> static struct kmem_cache *entry_cache; static hsiphash_key_t key; static spinlock_t table_lock = __SPIN_LOCK_UNLOCKED("ratelimiter_table_lock"); static DEFINE_MUTEX(init_lock); static u64 init_refcnt; /* Protected by init_lock, hence not atomic. */ static atomic_t total_entries = ATOMIC_INIT(0); static unsigned int max_entries, table_size; static void wg_ratelimiter_gc_entries(struct work_struct *); static DECLARE_DEFERRABLE_WORK(gc_work, wg_ratelimiter_gc_entries); static struct hlist_head *table_v4; #if IS_ENABLED(CONFIG_IPV6) static struct hlist_head *table_v6; #endif struct ratelimiter_entry { u64 last_time_ns, tokens, ip; void *net; spinlock_t lock; struct hlist_node hash; struct rcu_head rcu; }; enum { PACKETS_PER_SECOND = 20, PACKETS_BURSTABLE = 5, PACKET_COST = NSEC_PER_SEC / PACKETS_PER_SECOND, TOKEN_MAX = PACKET_COST * PACKETS_BURSTABLE }; static void entry_free(struct rcu_head *rcu) { kmem_cache_free(entry_cache, container_of(rcu, struct ratelimiter_entry, rcu)); atomic_dec(&total_entries); } static void entry_uninit(struct ratelimiter_entry *entry) { hlist_del_rcu(&entry->hash); call_rcu(&entry->rcu, entry_free); } /* Calling this function with a NULL work uninits all entries. */ static void wg_ratelimiter_gc_entries(struct work_struct *work) { const u64 now = ktime_get_coarse_boottime_ns(); struct ratelimiter_entry *entry; struct hlist_node *temp; unsigned int i; for (i = 0; i < table_size; ++i) { spin_lock(&table_lock); hlist_for_each_entry_safe(entry, temp, &table_v4[i], hash) { if (unlikely(!work) || now - entry->last_time_ns > NSEC_PER_SEC) entry_uninit(entry); } #if IS_ENABLED(CONFIG_IPV6) hlist_for_each_entry_safe(entry, temp, &table_v6[i], hash) { if (unlikely(!work) || now - entry->last_time_ns > NSEC_PER_SEC) entry_uninit(entry); } #endif spin_unlock(&table_lock); if (likely(work)) cond_resched(); } if (likely(work)) queue_delayed_work(system_power_efficient_wq, &gc_work, HZ); } bool wg_ratelimiter_allow(struct sk_buff *skb, struct net *net) { /* We only take the bottom half of the net pointer, so that we can hash * 3 words in the end. This way, siphash's len param fits into the final * u32, and we don't incur an extra round. */ const u32 net_word = (unsigned long)net; struct ratelimiter_entry *entry; struct hlist_head *bucket; u64 ip; if (skb->protocol == htons(ETH_P_IP)) { ip = (u64 __force)ip_hdr(skb)->saddr; bucket = &table_v4[hsiphash_2u32(net_word, ip, &key) & (table_size - 1)]; } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { /* Only use 64 bits, so as to ratelimit the whole /64. */ memcpy(&ip, &ipv6_hdr(skb)->saddr, sizeof(ip)); bucket = &table_v6[hsiphash_3u32(net_word, ip >> 32, ip, &key) & (table_size - 1)]; } #endif else return false; rcu_read_lock(); hlist_for_each_entry_rcu(entry, bucket, hash) { if (entry->net == net && entry->ip == ip) { u64 now, tokens; bool ret; /* Quasi-inspired by nft_limit.c, but this is actually a * slightly different algorithm. Namely, we incorporate * the burst as part of the maximum tokens, rather than * as part of the rate. */ spin_lock(&entry->lock); now = ktime_get_coarse_boottime_ns(); tokens = min_t(u64, TOKEN_MAX, entry->tokens + now - entry->last_time_ns); entry->last_time_ns = now; ret = tokens >= PACKET_COST; entry->tokens = ret ? tokens - PACKET_COST : tokens; spin_unlock(&entry->lock); rcu_read_unlock(); return ret; } } rcu_read_unlock(); if (atomic_inc_return(&total_entries) > max_entries) goto err_oom; entry = kmem_cache_alloc(entry_cache, GFP_KERNEL); if (unlikely(!entry)) goto err_oom; entry->net = net; entry->ip = ip; INIT_HLIST_NODE(&entry->hash); spin_lock_init(&entry->lock); entry->last_time_ns = ktime_get_coarse_boottime_ns(); entry->tokens = TOKEN_MAX - PACKET_COST; spin_lock(&table_lock); hlist_add_head_rcu(&entry->hash, bucket); spin_unlock(&table_lock); return true; err_oom: atomic_dec(&total_entries); return false; } int wg_ratelimiter_init(void) { mutex_lock(&init_lock); if (++init_refcnt != 1) goto out; entry_cache = KMEM_CACHE(ratelimiter_entry, 0); if (!entry_cache) goto err; /* xt_hashlimit.c uses a slightly different algorithm for ratelimiting, * but what it shares in common is that it uses a massive hashtable. So, * we borrow their wisdom about good table sizes on different systems * dependent on RAM. This calculation here comes from there. */ table_size = (totalram_pages() > (1U << 30) / PAGE_SIZE) ? 8192 : max_t(unsigned long, 16, roundup_pow_of_two( (totalram_pages() << PAGE_SHIFT) / (1U << 14) / sizeof(struct hlist_head))); max_entries = table_size * 8; table_v4 = kvzalloc_objs(*table_v4, table_size); if (unlikely(!table_v4)) goto err_kmemcache; #if IS_ENABLED(CONFIG_IPV6) table_v6 = kvzalloc_objs(*table_v6, table_size); if (unlikely(!table_v6)) { kvfree(table_v4); goto err_kmemcache; } #endif queue_delayed_work(system_power_efficient_wq, &gc_work, HZ); get_random_bytes(&key, sizeof(key)); out: mutex_unlock(&init_lock); return 0; err_kmemcache: kmem_cache_destroy(entry_cache); err: --init_refcnt; mutex_unlock(&init_lock); return -ENOMEM; } void wg_ratelimiter_uninit(void) { mutex_lock(&init_lock); if (!init_refcnt || --init_refcnt) goto out; cancel_delayed_work_sync(&gc_work); wg_ratelimiter_gc_entries(NULL); rcu_barrier(); kvfree(table_v4); #if IS_ENABLED(CONFIG_IPV6) kvfree(table_v6); #endif kmem_cache_destroy(entry_cache); out: mutex_unlock(&init_lock); } #include "selftest/ratelimiter.c" |
| 551 101 548 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * The proc filesystem constants/structures */ #ifndef _LINUX_PROC_FS_H #define _LINUX_PROC_FS_H #include <linux/compiler.h> #include <linux/types.h> #include <linux/fs.h> struct proc_dir_entry; struct seq_file; struct seq_operations; enum { /* * All /proc entries using this ->proc_ops instance are never removed. * * If in doubt, ignore this flag. */ #ifdef MODULE PROC_ENTRY_PERMANENT = 0U, #else PROC_ENTRY_PERMANENT = 1U << 0, #endif PROC_ENTRY_proc_read_iter = 1U << 1, PROC_ENTRY_proc_compat_ioctl = 1U << 2, PROC_ENTRY_proc_lseek = 1U << 3, PROC_ENTRY_FORCE_LOOKUP = 1U << 7, }; struct proc_ops { unsigned int proc_flags; int (*proc_open)(struct inode *, struct file *); ssize_t (*proc_read)(struct file *, char __user *, size_t, loff_t *); ssize_t (*proc_read_iter)(struct kiocb *, struct iov_iter *); ssize_t (*proc_write)(struct file *, const char __user *, size_t, loff_t *); /* mandatory unless nonseekable_open() or equivalent is used */ loff_t (*proc_lseek)(struct file *, loff_t, int); int (*proc_release)(struct inode *, struct file *); __poll_t (*proc_poll)(struct file *, struct poll_table_struct *); long (*proc_ioctl)(struct file *, unsigned int, unsigned long); #ifdef CONFIG_COMPAT long (*proc_compat_ioctl)(struct file *, unsigned int, unsigned long); #endif int (*proc_mmap)(struct file *, struct vm_area_struct *); unsigned long (*proc_get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); } __randomize_layout; /* definitions for hide_pid field */ enum proc_hidepid { HIDEPID_OFF = 0, HIDEPID_NO_ACCESS = 1, HIDEPID_INVISIBLE = 2, HIDEPID_NOT_PTRACEABLE = 4, /* Limit pids to only ptraceable pids */ }; /* definitions for proc mount option pidonly */ enum proc_pidonly { PROC_PIDONLY_OFF = 0, PROC_PIDONLY_ON = 1, }; struct proc_fs_info { struct pid_namespace *pid_ns; kgid_t pid_gid; const struct cred *mounter_cred; enum proc_hidepid hide_pid; enum proc_pidonly pidonly; struct rcu_head rcu; }; static inline struct proc_fs_info *proc_sb_info(struct super_block *sb) { return sb->s_fs_info; } #ifdef CONFIG_PROC_FS typedef int (*proc_write_t)(struct file *, char *, size_t); extern void proc_root_init(void); extern void proc_flush_pid(struct pid *); extern struct proc_dir_entry *proc_symlink(const char *, struct proc_dir_entry *, const char *); struct proc_dir_entry *_proc_mkdir(const char *, umode_t, struct proc_dir_entry *, void *, bool); extern struct proc_dir_entry *proc_mkdir(const char *, struct proc_dir_entry *); extern struct proc_dir_entry *proc_mkdir_data(const char *, umode_t, struct proc_dir_entry *, void *); extern struct proc_dir_entry *proc_mkdir_mode(const char *, umode_t, struct proc_dir_entry *); struct proc_dir_entry *proc_create_mount_point(const char *name); struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, unsigned int state_size, void *data); #define proc_create_seq_data(name, mode, parent, ops, data) \ proc_create_seq_private(name, mode, parent, ops, 0, data) #define proc_create_seq(name, mode, parent, ops) \ proc_create_seq_private(name, mode, parent, ops, 0, NULL) struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), void *data); #define proc_create_single(name, mode, parent, show) \ proc_create_single_data(name, mode, parent, show, NULL) extern struct proc_dir_entry *proc_create_data(const char *, umode_t, struct proc_dir_entry *, const struct proc_ops *, void *); struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops); extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); /* * Obtain the private data passed by user through proc_create_data() or * related. */ static inline void *pde_data(const struct inode *inode) { return inode->i_private; } extern void *proc_get_parent_data(const struct inode *); extern void proc_remove(struct proc_dir_entry *); extern void remove_proc_entry(const char *, struct proc_dir_entry *); extern int remove_proc_subtree(const char *, struct proc_dir_entry *); struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, unsigned int state_size, void *data); #define proc_create_net(name, mode, parent, ops, state_size) \ proc_create_net_data(name, mode, parent, ops, state_size, NULL) struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), void *data); struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, proc_write_t write, unsigned int state_size, void *data); struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), proc_write_t write, void *data); extern struct pid *tgid_pidfd_to_pid(const struct file *file); struct bpf_iter_aux_info; extern int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux); extern void bpf_iter_fini_seq_net(void *priv_data); #ifdef CONFIG_PROC_PID_ARCH_STATUS /* * The architecture which selects CONFIG_PROC_PID_ARCH_STATUS must * provide proc_pid_arch_status() definition. */ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task); #endif /* CONFIG_PROC_PID_ARCH_STATUS */ void arch_report_meminfo(struct seq_file *m); void arch_proc_pid_thread_features(struct seq_file *m, struct task_struct *task); #else /* CONFIG_PROC_FS */ static inline void proc_root_init(void) { } static inline void proc_flush_pid(struct pid *pid) { } static inline struct proc_dir_entry *proc_symlink(const char *name, struct proc_dir_entry *parent,const char *dest) { return NULL;} static inline struct proc_dir_entry *proc_mkdir(const char *name, struct proc_dir_entry *parent) {return NULL;} static inline struct proc_dir_entry *proc_create_mount_point(const char *name) { return NULL; } static inline struct proc_dir_entry *_proc_mkdir(const char *name, umode_t mode, struct proc_dir_entry *parent, void *data, bool force_lookup) { return NULL; } static inline struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, struct proc_dir_entry *parent, void *data) { return NULL; } static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { return NULL; } #define proc_create_seq_private(name, mode, parent, ops, size, data) ({NULL;}) #define proc_create_seq_data(name, mode, parent, ops, data) ({NULL;}) #define proc_create_seq(name, mode, parent, ops) ({NULL;}) #define proc_create_single(name, mode, parent, show) ({NULL;}) #define proc_create_single_data(name, mode, parent, show, data) ({NULL;}) static inline struct proc_dir_entry * proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops) { return NULL; } static inline struct proc_dir_entry * proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops, void *data) { return NULL; } static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} static inline void *pde_data(const struct inode *inode) {BUG(); return NULL;} static inline void *proc_get_parent_data(const struct inode *inode) { BUG(); return NULL; } static inline void proc_remove(struct proc_dir_entry *de) {} #define remove_proc_entry(name, parent) do {} while (0) static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) { return 0; } #define proc_create_net_data(name, mode, parent, ops, state_size, data) ({NULL;}) #define proc_create_net_data_write(name, mode, parent, ops, write, state_size, data) ({NULL;}) #define proc_create_net(name, mode, parent, state_size, ops) ({NULL;}) #define proc_create_net_single(name, mode, parent, show, data) ({NULL;}) #define proc_create_net_single_write(name, mode, parent, show, write, data) ({NULL;}) static inline struct pid *tgid_pidfd_to_pid(const struct file *file) { return ERR_PTR(-EBADF); } #endif /* CONFIG_PROC_FS */ struct net; static inline struct proc_dir_entry *proc_net_mkdir( struct net *net, const char *name, struct proc_dir_entry *parent) { return _proc_mkdir(name, 0, parent, net, true); } struct ns_common; int open_related_ns(struct ns_common *ns, struct ns_common *(*get_ns)(struct ns_common *ns)); /* get the associated pid namespace for a file in procfs */ static inline struct pid_namespace *proc_pid_ns(struct super_block *sb) { return proc_sb_info(sb)->pid_ns; } bool proc_ns_file(const struct file *file); #if defined CONFIG_PROC_FS && !defined MODULE void impl_proc_make_permanent(struct proc_dir_entry *pde); #endif static inline void proc_make_permanent(struct proc_dir_entry *pde) { /* Don't give matches to modules. */ #if defined CONFIG_PROC_FS && !defined MODULE impl_proc_make_permanent(pde); #endif } #endif /* _LINUX_PROC_FS_H */ |
| 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Handle bridge arp/nd proxy/suppress * * Copyright (C) 2017 Cumulus Networks * Copyright (c) 2017 Roopa Prabhu <roopa@cumulusnetworks.com> * * Authors: * Roopa Prabhu <roopa@cumulusnetworks.com> */ #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/neighbour.h> #include <net/arp.h> #include <linux/if_vlan.h> #include <linux/inetdevice.h> #include <net/addrconf.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ip6_checksum.h> #endif #include "br_private.h" void br_recalculate_neigh_suppress_enabled(struct net_bridge *br) { struct net_bridge_port *p; bool neigh_suppress = false; list_for_each_entry(p, &br->port_list, list) { if (READ_ONCE(p->flags) & (BR_NEIGH_SUPPRESS | BR_NEIGH_VLAN_SUPPRESS)) { neigh_suppress = true; break; } } br_opt_toggle(br, BROPT_NEIGH_SUPPRESS_ENABLED, neigh_suppress); } #if IS_ENABLED(CONFIG_INET) static void br_arp_send(struct net_bridge *br, struct net_bridge_port *p, struct net_device *dev, __be32 dest_ip, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw, __be16 vlan_proto, u16 vlan_tci) { struct net_bridge_vlan_group *vg; struct sk_buff *skb; u16 pvid; netdev_dbg(dev, "arp send dev %s dst %pI4 dst_hw %pM src %pI4 src_hw %pM\n", dev->name, &dest_ip, dest_hw, &src_ip, src_hw); if (!vlan_tci) { arp_send(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip, dest_hw, src_hw, target_hw); return; } skb = arp_create(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip, dest_hw, src_hw, target_hw); if (!skb) return; if (p) vg = nbp_vlan_group_rcu(p); else vg = br_vlan_group_rcu(br); pvid = br_get_pvid(vg); if (pvid == (vlan_tci & VLAN_VID_MASK)) vlan_tci = 0; if (vlan_tci) __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); if (p) { arp_xmit(skb); } else { skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); skb->ip_summed = CHECKSUM_UNNECESSARY; skb->pkt_type = PACKET_HOST; netif_rx(skb); } } static int br_chk_addr_ip(struct net_device *dev, struct netdev_nested_priv *priv) { __be32 ip = *(__be32 *)priv->data; struct in_device *in_dev; __be32 addr = 0; in_dev = __in_dev_get_rcu(dev); if (in_dev) addr = inet_confirm_addr(dev_net(dev), in_dev, 0, ip, RT_SCOPE_HOST); if (addr == ip) return 1; return 0; } static bool br_is_local_ip(struct net_device *dev, __be32 ip) { struct netdev_nested_priv priv = { .data = (void *)&ip, }; if (br_chk_addr_ip(dev, &priv)) return true; /* check if ip is configured on upper dev */ if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &priv)) return true; return false; } void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, u16 vid, struct net_bridge_port *p) { struct net_device *dev = br->dev; struct net_device *vlandev = dev; struct neighbour *n; struct arphdr *parp; u8 *arpptr, *sha; __be32 sip, tip; BR_INPUT_SKB_CB(skb)->proxyarp_replied = 0; BR_INPUT_SKB_CB(skb)->grat_arp = 0; if ((dev->flags & IFF_NOARP) || !pskb_may_pull(skb, arp_hdr_len(dev))) return; parp = arp_hdr(skb); if (parp->ar_pro != htons(ETH_P_IP) || parp->ar_hln != dev->addr_len || parp->ar_pln != 4) return; arpptr = (u8 *)parp + sizeof(struct arphdr); sha = arpptr; arpptr += dev->addr_len; /* sha */ memcpy(&sip, arpptr, sizeof(sip)); arpptr += sizeof(sip); arpptr += dev->addr_len; /* tha */ memcpy(&tip, arpptr, sizeof(tip)); if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) return; if (br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) { if (br_is_neigh_suppress_enabled(p, vid)) return; if (is_unicast_ether_addr(eth_hdr(skb)->h_dest) && parp->ar_op == htons(ARPOP_REQUEST)) return; if (parp->ar_op != htons(ARPOP_RREQUEST) && parp->ar_op != htons(ARPOP_RREPLY) && sip == tip) { /* prevent flooding to neigh suppress ports */ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1; BR_INPUT_SKB_CB(skb)->grat_arp = 1; return; } } if (parp->ar_op != htons(ARPOP_REQUEST)) return; if (vid != 0) { vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto, vid); if (!vlandev) return; } if (br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && br_is_local_ip(vlandev, tip)) { /* its our local ip, so don't proxy reply * and don't forward to neigh suppress ports */ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1; return; } n = neigh_lookup(&arp_tbl, &tip, vlandev); if (n) { struct net_bridge_fdb_entry *f; if (!(READ_ONCE(n->nud_state) & NUD_VALID)) { neigh_release(n); return; } f = br_fdb_find_rcu(br, n->ha, vid); if (f) { const struct net_bridge_port *dst = READ_ONCE(f->dst); bool replied = false; if ((p && test_bit(BR_PROXYARP_BIT, &p->flags)) || (dst && test_bit(BR_PROXYARP_WIFI_BIT, &dst->flags)) || br_is_neigh_suppress_enabled(dst, vid)) { if (!vid) br_arp_send(br, p, skb->dev, sip, tip, sha, n->ha, sha, 0, 0); else br_arp_send(br, p, skb->dev, sip, tip, sha, n->ha, sha, skb->vlan_proto, skb_vlan_tag_get(skb)); replied = true; } /* If we have replied or as long as we know the * mac, indicate to arp replied */ if (replied || br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1; } neigh_release(n); } } #endif #if IS_ENABLED(CONFIG_IPV6) struct nd_msg *br_is_nd_neigh_msg(const struct sk_buff *skb, struct nd_msg *msg) { struct nd_msg *m; m = skb_header_pointer(skb, skb_network_offset(skb) + sizeof(struct ipv6hdr), sizeof(*msg), msg); if (!m) return NULL; if (m->icmph.icmp6_code != 0 || (m->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION && m->icmph.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT)) return NULL; return m; } static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p, struct sk_buff *request, struct neighbour *n, __be16 vlan_proto, u16 vlan_tci) { struct net_device *dev = request->dev; struct net_bridge_vlan_group *vg; struct nd_msg *na, *ns; struct sk_buff *reply; struct ipv6hdr *pip6; int na_olen = 8; /* opt hdr + ETH_ALEN for target */ int ns_olen; int i, len; u8 *daddr; bool dad; u16 pvid; if (!dev || skb_linearize(request)) return; len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) + sizeof(*na) + na_olen + dev->needed_tailroom; reply = alloc_skb(len, GFP_ATOMIC); if (!reply) return; reply->protocol = htons(ETH_P_IPV6); reply->dev = dev; skb_reserve(reply, LL_RESERVED_SPACE(dev)); skb_push(reply, sizeof(struct ethhdr)); skb_set_mac_header(reply, 0); daddr = eth_hdr(request)->h_source; ns = (struct nd_msg *)(skb_network_header(request) + sizeof(struct ipv6hdr)); /* Do we need option processing ? */ ns_olen = request->len - (skb_network_offset(request) + sizeof(struct ipv6hdr)) - sizeof(*ns); for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) { if (!ns->opt[i + 1] || i + (ns->opt[i + 1] << 3) > ns_olen) { kfree_skb(reply); return; } if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { if ((ns->opt[i + 1] << 3) >= sizeof(struct nd_opt_hdr) + ETH_ALEN) daddr = ns->opt + i + sizeof(struct nd_opt_hdr); break; } } dad = ipv6_addr_any(&ipv6_hdr(request)->saddr); /* Ethernet header */ if (dad) ipv6_eth_mc_map(&in6addr_linklocal_allnodes, eth_hdr(reply)->h_dest); else ether_addr_copy(eth_hdr(reply)->h_dest, daddr); ether_addr_copy(eth_hdr(reply)->h_source, n->ha); eth_hdr(reply)->h_proto = htons(ETH_P_IPV6); reply->protocol = htons(ETH_P_IPV6); skb_pull(reply, sizeof(struct ethhdr)); skb_set_network_header(reply, 0); skb_put(reply, sizeof(struct ipv6hdr)); /* IPv6 header */ pip6 = ipv6_hdr(reply); memset(pip6, 0, sizeof(struct ipv6hdr)); pip6->version = 6; pip6->priority = ipv6_hdr(request)->priority; pip6->nexthdr = IPPROTO_ICMPV6; pip6->hop_limit = 255; pip6->daddr = dad ? in6addr_linklocal_allnodes : ipv6_hdr(request)->saddr; pip6->saddr = *(struct in6_addr *)n->primary_key; skb_pull(reply, sizeof(struct ipv6hdr)); skb_set_transport_header(reply, 0); na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen); /* Neighbor Advertisement */ memset(na, 0, sizeof(*na) + na_olen); na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; na->icmph.icmp6_router = (n->flags & NTF_ROUTER) ? 1 : 0; na->icmph.icmp6_override = 1; na->icmph.icmp6_solicited = dad ? 0 : 1; na->target = ns->target; ether_addr_copy(&na->opt[2], n->ha); na->opt[0] = ND_OPT_TARGET_LL_ADDR; na->opt[1] = na_olen >> 3; na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, sizeof(*na) + na_olen, IPPROTO_ICMPV6, csum_partial(na, sizeof(*na) + na_olen, 0)); pip6->payload_len = htons(sizeof(*na) + na_olen); skb_push(reply, sizeof(struct ipv6hdr)); skb_push(reply, sizeof(struct ethhdr)); reply->ip_summed = CHECKSUM_UNNECESSARY; if (p) vg = nbp_vlan_group_rcu(p); else vg = br_vlan_group_rcu(br); pvid = br_get_pvid(vg); if (pvid == (vlan_tci & VLAN_VID_MASK)) vlan_tci = 0; if (vlan_tci) __vlan_hwaccel_put_tag(reply, vlan_proto, vlan_tci); netdev_dbg(dev, "nd send dev %s dst %pI6 dst_hw %pM src %pI6 src_hw %pM\n", dev->name, &pip6->daddr, daddr, &pip6->saddr, n->ha); if (p) { dev_queue_xmit(reply); } else { skb_reset_mac_header(reply); __skb_pull(reply, skb_network_offset(reply)); reply->ip_summed = CHECKSUM_UNNECESSARY; reply->pkt_type = PACKET_HOST; netif_rx(reply); } } static int br_chk_addr_ip6(struct net_device *dev, struct netdev_nested_priv *priv) { struct in6_addr *addr = (struct in6_addr *)priv->data; if (ipv6_chk_addr(dev_net(dev), addr, dev, 0)) return 1; return 0; } static bool br_is_local_ip6(struct net_device *dev, struct in6_addr *addr) { struct netdev_nested_priv priv = { .data = (void *)addr, }; if (br_chk_addr_ip6(dev, &priv)) return true; /* check if ip is configured on upper dev */ if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, &priv)) return true; return false; } void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br, u16 vid, struct net_bridge_port *p, struct nd_msg *msg) { struct net_device *dev = br->dev; struct net_device *vlandev = NULL; struct in6_addr *saddr, *daddr; struct ipv6hdr *iphdr; struct neighbour *n; BR_INPUT_SKB_CB(skb)->proxyarp_replied = 0; BR_INPUT_SKB_CB(skb)->grat_arp = 0; if (br_is_neigh_suppress_enabled(p, vid)) return; if (is_unicast_ether_addr(eth_hdr(skb)->h_dest) && msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) return; if (msg->icmph.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT && !msg->icmph.icmp6_solicited) { /* prevent flooding to neigh suppress ports */ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1; BR_INPUT_SKB_CB(skb)->grat_arp = 1; return; } if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) return; iphdr = ipv6_hdr(skb); saddr = &iphdr->saddr; daddr = &iphdr->daddr; if (!ipv6_addr_cmp(saddr, daddr)) { /* prevent flooding to neigh suppress ports */ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1; return; } if (vid != 0) { /* build neigh table lookup on the vlan device */ vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto, vid); if (!vlandev) return; } else { vlandev = dev; } if (br_is_local_ip6(vlandev, &msg->target)) { /* its our own ip, so don't proxy reply * and don't forward to arp suppress ports */ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1; return; } n = neigh_lookup(&nd_tbl, &msg->target, vlandev); if (n) { struct net_bridge_fdb_entry *f; if (!(READ_ONCE(n->nud_state) & NUD_VALID)) { neigh_release(n); return; } f = br_fdb_find_rcu(br, n->ha, vid); if (f) { const struct net_bridge_port *dst = READ_ONCE(f->dst); bool replied = false; if (br_is_neigh_suppress_enabled(dst, vid)) { if (vid != 0) br_nd_send(br, p, skb, n, skb->vlan_proto, skb_vlan_tag_get(skb)); else br_nd_send(br, p, skb, n, 0, 0); replied = true; } /* If we have replied or as long as we know the * mac, indicate to NEIGH_SUPPRESS ports that we * have replied */ if (replied || br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1; } neigh_release(n); } } #endif bool br_is_neigh_suppress_enabled(const struct net_bridge_port *p, u16 vid) { if (!p) return false; if (vid && test_bit(BR_NEIGH_VLAN_SUPPRESS_BIT, &p->flags)) { struct net_bridge_vlan_group *vg = nbp_vlan_group_rcu(p); struct net_bridge_vlan *v; v = br_vlan_find(vg, vid); if (!v) return false; return !!(v->priv_flags & BR_VLFLAG_NEIGH_SUPPRESS_ENABLED); } return test_bit(BR_NEIGH_SUPPRESS_BIT, &p->flags); } bool br_is_neigh_forward_grat_enabled(const struct net_bridge_port *p, u16 vid) { if (vid && test_bit(BR_NEIGH_VLAN_SUPPRESS_BIT, &p->flags)) { struct net_bridge_vlan_group *vg = nbp_vlan_group_rcu(p); struct net_bridge_vlan *v; v = br_vlan_find(vg, vid); if (!v) return false; return !!(v->priv_flags & BR_VLFLAG_NEIGH_FORWARD_GRAT_ENABLED); } return test_bit(BR_NEIGH_FORWARD_GRAT_BIT, &p->flags); } |
| 44 43 14 14 14 14 15 14 10 14 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 | /* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * linux/can/skb.h * * Definitions for the CAN network socket buffer * * Copyright (C) 2012 Oliver Hartkopp <socketcan@hartkopp.net> * */ #ifndef _CAN_SKB_H #define _CAN_SKB_H #include <linux/types.h> #include <linux/skbuff.h> #include <linux/can.h> #include <net/can.h> #include <net/sock.h> void can_flush_echo_skb(struct net_device *dev); int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx, unsigned int frame_len); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, unsigned int *len_ptr, unsigned int *frame_len_ptr); unsigned int __must_check can_get_echo_skb(struct net_device *dev, unsigned int idx, unsigned int *frame_len_ptr); void can_free_echo_skb(struct net_device *dev, unsigned int idx, unsigned int *frame_len_ptr); struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); struct sk_buff *alloc_canfd_skb(struct net_device *dev, struct canfd_frame **cfd); struct sk_buff *alloc_canxl_skb(struct net_device *dev, struct canxl_frame **cxl, unsigned int data_len); struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf); bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb); static inline struct can_skb_ext *can_skb_ext_add(struct sk_buff *skb) { struct can_skb_ext *csx = skb_ext_add(skb, SKB_EXT_CAN); /* skb_ext_add() returns uninitialized space */ if (csx) csx->can_gw_hops = 0; return csx; } static inline struct can_skb_ext *can_skb_ext_find(struct sk_buff *skb) { return skb_ext_find(skb, SKB_EXT_CAN); } static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk) { /* If the socket has already been closed by user space, the * refcount may already be 0 (and the socket will be freed * after the last TX skb has been freed). So only increase * socket refcount if the refcount is > 0. */ if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) { skb->destructor = sock_efree; skb->sk = sk; } } /* * returns an unshared skb owned by the original sock to be echo'ed back */ static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb) { struct sk_buff *nskb; nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) { kfree_skb(skb); return NULL; } can_skb_set_owner(nskb, skb->sk); consume_skb(skb); return nskb; } static inline bool can_is_can_skb(const struct sk_buff *skb) { struct can_frame *cf = (struct can_frame *)skb->data; /* the CAN specific type of skb is identified by its data length */ return (skb->len == CAN_MTU && cf->len <= CAN_MAX_DLEN); } static inline bool can_is_canfd_skb(const struct sk_buff *skb) { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; /* the CAN specific type of skb is identified by its data length */ return (skb->len == CANFD_MTU && cfd->len <= CANFD_MAX_DLEN); } static inline bool can_is_canxl_skb(const struct sk_buff *skb) { const struct canxl_frame *cxl = (struct canxl_frame *)skb->data; if (skb->len < CANXL_HDR_SIZE + CANXL_MIN_DLEN || skb->len > CANXL_MTU) return false; /* this also checks valid CAN XL data length boundaries */ if (skb->len != CANXL_HDR_SIZE + cxl->len) return false; return cxl->flags & CANXL_XLF; } /* get length element value from can[|fd|xl]_frame structure */ static inline unsigned int can_skb_get_len_val(struct sk_buff *skb) { const struct canxl_frame *cxl = (struct canxl_frame *)skb->data; const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; if (can_is_canxl_skb(skb)) return cxl->len; return cfd->len; } /* get needed data length inside CAN frame for all frame types (RTR aware) */ static inline unsigned int can_skb_get_data_len(struct sk_buff *skb) { unsigned int len = can_skb_get_len_val(skb); const struct can_frame *cf = (struct can_frame *)skb->data; /* RTR frames have an actual length of zero */ if (can_is_can_skb(skb) && cf->can_id & CAN_RTR_FLAG) return 0; return len; } #endif /* !_CAN_SKB_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_IOBITMAP_H #define _ASM_X86_IOBITMAP_H #include <linux/refcount.h> #include <asm/processor.h> struct io_bitmap { u64 sequence; refcount_t refcnt; /* The maximum number of bytes to copy so all zero bits are covered */ unsigned int max; unsigned long bitmap[IO_BITMAP_LONGS]; }; struct task_struct; #ifdef CONFIG_X86_IOPL_IOPERM void io_bitmap_share(struct task_struct *tsk); void io_bitmap_exit(struct task_struct *tsk); static inline void native_tss_invalidate_io_bitmap(void) { /* * Invalidate the I/O bitmap by moving io_bitmap_base outside the * TSS limit so any subsequent I/O access from user space will * trigger a #GP. * * This is correct even when VMEXIT rewrites the TSS limit * to 0x67 as the only requirement is that the base points * outside the limit. */ this_cpu_write(cpu_tss_rw.x86_tss.io_bitmap_base, IO_BITMAP_OFFSET_INVALID); } void native_tss_update_io_bitmap(void); #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define tss_update_io_bitmap native_tss_update_io_bitmap #define tss_invalidate_io_bitmap native_tss_invalidate_io_bitmap #endif #else static inline void io_bitmap_share(struct task_struct *tsk) { } static inline void io_bitmap_exit(struct task_struct *tsk) { } static inline void tss_update_io_bitmap(void) { } #endif #endif |
| 1067 1067 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sched/act_sample.c - Packet sampling tc action * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com> */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> #include <linux/gfp.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <linux/tc_act/tc_sample.h> #include <net/tc_act/tc_sample.h> #include <net/psample.h> #include <net/pkt_cls.h> #include <net/tc_wrapper.h> #include <linux/if_arp.h> static struct tc_action_ops act_sample_ops; static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = { [TCA_SAMPLE_PARMS] = { .len = sizeof(struct tc_sample) }, [TCA_SAMPLE_RATE] = { .type = NLA_U32 }, [TCA_SAMPLE_TRUNC_SIZE] = { .type = NLA_U32 }, [TCA_SAMPLE_PSAMPLE_GROUP] = { .type = NLA_U32 }, }; static int tcf_sample_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_sample_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_SAMPLE_MAX + 1]; struct psample_group *psample_group; u32 psample_group_num, rate, index; struct tcf_chain *goto_ch = NULL; struct tc_sample *parm; struct tcf_sample *s; bool exists = false; int ret, err; if (!nla) return -EINVAL; ret = nla_parse_nested_deprecated(tb, TCA_SAMPLE_MAX, nla, sample_policy, NULL); if (ret < 0) return ret; if (!tb[TCA_SAMPLE_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_SAMPLE_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_sample_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } if (!tb[TCA_SAMPLE_RATE] || !tb[TCA_SAMPLE_PSAMPLE_GROUP]) { NL_SET_ERR_MSG(extack, "sample rate and group are required"); err = -EINVAL; goto release_idr; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); if (!rate) { NL_SET_ERR_MSG(extack, "invalid sample rate"); err = -EINVAL; goto put_chain; } psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]); psample_group = psample_group_get(net, psample_group_num); if (!psample_group) { err = -ENOMEM; goto put_chain; } s = to_sample(*a); spin_lock_bh(&s->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); s->rate = rate; s->psample_group_num = psample_group_num; psample_group = rcu_replace_pointer(s->psample_group, psample_group, lockdep_is_held(&s->tcf_lock)); if (tb[TCA_SAMPLE_TRUNC_SIZE]) { s->truncate = true; s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]); } spin_unlock_bh(&s->tcf_lock); if (psample_group) psample_group_put(psample_group); if (goto_ch) tcf_chain_put_by_act(goto_ch); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static void tcf_sample_cleanup(struct tc_action *a) { struct tcf_sample *s = to_sample(a); struct psample_group *psample_group; /* last reference to action, no need to lock */ psample_group = rcu_dereference_protected(s->psample_group, 1); RCU_INIT_POINTER(s->psample_group, NULL); if (psample_group) psample_group_put(psample_group); } static bool tcf_sample_dev_ok_push(struct net_device *dev) { switch (dev->type) { case ARPHRD_TUNNEL: case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: return false; default: return true; } } TC_INDIRECT_SCOPE int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_sample *s = to_sample(a); struct psample_group *psample_group; u8 cookie_data[TC_COOKIE_MAX_SIZE]; struct psample_metadata md = {}; struct tc_cookie *user_cookie; int retval; tcf_lastuse_update(&s->tcf_tm); bstats_update(this_cpu_ptr(s->common.cpu_bstats), skb); retval = READ_ONCE(s->tcf_action); psample_group = rcu_dereference_bh(s->psample_group); /* randomly sample packets according to rate */ if (psample_group && (get_random_u32_below(s->rate) == 0)) { if (!skb_at_tc_ingress(skb)) { md.in_ifindex = skb->skb_iif; md.out_ifindex = skb->dev->ifindex; } else { md.in_ifindex = skb->dev->ifindex; } /* on ingress, the mac header gets popped, so push it back */ if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev)) skb_push(skb, skb->mac_len); rcu_read_lock(); user_cookie = rcu_dereference(a->user_cookie); if (user_cookie) { memcpy(cookie_data, user_cookie->data, user_cookie->len); md.user_cookie = cookie_data; md.user_cookie_len = user_cookie->len; } rcu_read_unlock(); md.trunc_size = s->truncate ? s->trunc_size : skb->len; psample_sample_packet(psample_group, skb, s->rate, &md); if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev)) skb_pull(skb, skb->mac_len); } return retval; } static void tcf_sample_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_sample *s = to_sample(a); struct tcf_t *tm = &s->tcf_tm; tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_sample *s = to_sample(a); struct tc_sample opt = { .index = s->tcf_index, .refcnt = refcount_read(&s->tcf_refcnt) - ref, .bindcnt = atomic_read(&s->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&s->tcf_lock); opt.action = s->tcf_action; if (nla_put(skb, TCA_SAMPLE_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &s->tcf_tm); if (nla_put_64bit(skb, TCA_SAMPLE_TM, sizeof(t), &t, TCA_SAMPLE_PAD)) goto nla_put_failure; if (nla_put_u32(skb, TCA_SAMPLE_RATE, s->rate)) goto nla_put_failure; if (s->truncate) if (nla_put_u32(skb, TCA_SAMPLE_TRUNC_SIZE, s->trunc_size)) goto nla_put_failure; if (nla_put_u32(skb, TCA_SAMPLE_PSAMPLE_GROUP, s->psample_group_num)) goto nla_put_failure; spin_unlock_bh(&s->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&s->tcf_lock); nlmsg_trim(skb, b); return -1; } static void tcf_psample_group_put(void *priv) { struct psample_group *group = priv; psample_group_put(group); } static struct psample_group * tcf_sample_get_group(const struct tc_action *a, tc_action_priv_destructor *destructor) { struct tcf_sample *s = to_sample(a); struct psample_group *group; group = rcu_dereference_protected(s->psample_group, lockdep_is_held(&s->tcf_lock)); if (group) { psample_group_take(group); *destructor = tcf_psample_group_put; } return group; } static void tcf_offload_sample_get_group(struct flow_action_entry *entry, const struct tc_action *act) { entry->sample.psample_group = act->ops->get_psample_group(act, &entry->destructor); entry->destructor_priv = entry->sample.psample_group; } static int tcf_sample_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { if (bind) { struct flow_action_entry *entry = entry_data; entry->id = FLOW_ACTION_SAMPLE; entry->sample.trunc_size = tcf_sample_trunc_size(act); entry->sample.truncate = tcf_sample_truncate(act); entry->sample.rate = tcf_sample_rate(act); tcf_offload_sample_get_group(entry, act); *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; fl_action->id = FLOW_ACTION_SAMPLE; } return 0; } static struct tc_action_ops act_sample_ops = { .kind = "sample", .id = TCA_ID_SAMPLE, .owner = THIS_MODULE, .act = tcf_sample_act, .stats_update = tcf_sample_stats_update, .dump = tcf_sample_dump, .init = tcf_sample_init, .cleanup = tcf_sample_cleanup, .get_psample_group = tcf_sample_get_group, .offload_act_setup = tcf_sample_offload_act_setup, .size = sizeof(struct tcf_sample), }; MODULE_ALIAS_NET_ACT("sample"); static __net_init int sample_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_sample_ops.net_id); return tc_action_net_init(net, tn, &act_sample_ops); } static void __net_exit sample_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_sample_ops.net_id); } static struct pernet_operations sample_net_ops = { .init = sample_init_net, .exit_batch = sample_exit_net, .id = &act_sample_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init sample_init_module(void) { return tcf_register_action(&act_sample_ops, &sample_net_ops); } static void __exit sample_cleanup_module(void) { tcf_unregister_action(&act_sample_ops, &sample_net_ops); } module_init(sample_init_module); module_exit(sample_cleanup_module); MODULE_AUTHOR("Yotam Gigi <yotam.gi@gmail.com>"); MODULE_DESCRIPTION("Packet sampling action"); MODULE_LICENSE("GPL v2"); |
| 91 1 91 15 554 554 6 5 4 4 2 5 4 2 1 1 1 1 1 1 2 1 3 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 | // SPDX-License-Identifier: GPL-2.0 /* * blk-integrity.c - Block layer data integrity extensions * * Copyright (C) 2007, 2008 Oracle Corporation * Written by: Martin K. Petersen <martin.petersen@oracle.com> */ #include <linux/blk-integrity.h> #include <linux/backing-dev.h> #include <linux/mempool.h> #include <linux/bio.h> #include <linux/scatterlist.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/t10-pi.h> #include "blk.h" /** * blk_rq_count_integrity_sg - Count number of integrity scatterlist elements * @q: request queue * @bio: bio with integrity metadata attached * * Description: Returns the number of elements required in a * scatterlist corresponding to the integrity metadata in a bio. */ int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *bio) { struct bio_vec iv, ivprv = { NULL }; unsigned int segments = 0; unsigned int seg_size = 0; struct bvec_iter iter; int prev = 0; bio_for_each_integrity_vec(iv, bio, iter) { if (prev) { if (!biovec_phys_mergeable(q, &ivprv, &iv)) goto new_segment; if (seg_size + iv.bv_len > queue_max_segment_size(q)) goto new_segment; seg_size += iv.bv_len; } else { new_segment: segments++; seg_size = iv.bv_len; } prev = 1; ivprv = iv; } return segments; } int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd, struct logical_block_metadata_cap __user *argp) { struct blk_integrity *bi; struct logical_block_metadata_cap meta_cap = {}; size_t usize = _IOC_SIZE(cmd); if (!extensible_ioctl_valid(cmd, FS_IOC_GETLBMD_CAP, LBMD_SIZE_VER0)) return -ENOIOCTLCMD; bi = blk_get_integrity(bdev->bd_disk); if (!bi) goto out; if (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) meta_cap.lbmd_flags |= LBMD_PI_CAP_INTEGRITY; if (bi->flags & BLK_INTEGRITY_REF_TAG) meta_cap.lbmd_flags |= LBMD_PI_CAP_REFTAG; meta_cap.lbmd_interval = 1 << bi->interval_exp; meta_cap.lbmd_size = bi->metadata_size; meta_cap.lbmd_pi_size = bi->pi_tuple_size; meta_cap.lbmd_pi_offset = bi->pi_offset; meta_cap.lbmd_opaque_size = bi->metadata_size - bi->pi_tuple_size; if (meta_cap.lbmd_opaque_size && !bi->pi_offset) meta_cap.lbmd_opaque_offset = bi->pi_tuple_size; switch (bi->csum_type) { case BLK_INTEGRITY_CSUM_NONE: meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_NONE; break; case BLK_INTEGRITY_CSUM_IP: meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_IP; break; case BLK_INTEGRITY_CSUM_CRC: meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_CRC16_T10DIF; break; case BLK_INTEGRITY_CSUM_CRC64: meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_CRC64_NVME; break; } if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE) meta_cap.lbmd_app_tag_size = 2; if (bi->flags & BLK_INTEGRITY_REF_TAG) { switch (bi->csum_type) { case BLK_INTEGRITY_CSUM_CRC64: meta_cap.lbmd_ref_tag_size = sizeof_field(struct crc64_pi_tuple, ref_tag); break; case BLK_INTEGRITY_CSUM_CRC: case BLK_INTEGRITY_CSUM_IP: meta_cap.lbmd_ref_tag_size = sizeof_field(struct t10_pi_tuple, ref_tag); break; default: break; } } out: return copy_struct_to_user(argp, usize, &meta_cap, sizeof(meta_cap), NULL); } int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, ssize_t bytes) { int ret; struct iov_iter iter; iov_iter_ubuf(&iter, rq_data_dir(rq), ubuf, bytes); ret = bio_integrity_map_user(rq->bio, &iter); if (ret) return ret; rq->nr_integrity_segments = blk_rq_count_integrity_sg(rq->q, rq->bio); rq->cmd_flags |= REQ_INTEGRITY; return 0; } EXPORT_SYMBOL_GPL(blk_rq_integrity_map_user); bool blk_integrity_merge_rq(struct request_queue *q, struct request *req, struct request *next) { struct bio_integrity_payload *bip, *bip_next; if (blk_integrity_rq(req) == 0 && blk_integrity_rq(next) == 0) return true; if (blk_integrity_rq(req) == 0 || blk_integrity_rq(next) == 0) return false; bip = bio_integrity(req->bio); bip_next = bio_integrity(next->bio); if (bip->bip_flags != bip_next->bip_flags) return false; if (bip->bip_flags & BIP_CHECK_APPTAG && bip->app_tag != bip_next->app_tag) return false; if (req->nr_integrity_segments + next->nr_integrity_segments > q->limits.max_integrity_segments) return false; if (integrity_req_gap_back_merge(req, next->bio)) return false; return true; } bool blk_integrity_merge_bio(struct request_queue *q, struct request *req, struct bio *bio) { struct bio_integrity_payload *bip, *bip_bio = bio_integrity(bio); int nr_integrity_segs; if (blk_integrity_rq(req) == 0 && bip_bio == NULL) return true; if (blk_integrity_rq(req) == 0 || bip_bio == NULL) return false; bip = bio_integrity(req->bio); if (bip->bip_flags != bip_bio->bip_flags) return false; if (bip->bip_flags & BIP_CHECK_APPTAG && bip->app_tag != bip_bio->app_tag) return false; nr_integrity_segs = blk_rq_count_integrity_sg(q, bio); if (req->nr_integrity_segments + nr_integrity_segs > q->limits.max_integrity_segments) return false; return true; } static inline struct blk_integrity *dev_to_bi(struct device *dev) { return &dev_to_disk(dev)->queue->limits.integrity; } const char *blk_integrity_profile_name(struct blk_integrity *bi) { switch (bi->csum_type) { case BLK_INTEGRITY_CSUM_IP: if (bi->flags & BLK_INTEGRITY_REF_TAG) return "T10-DIF-TYPE1-IP"; return "T10-DIF-TYPE3-IP"; case BLK_INTEGRITY_CSUM_CRC: if (bi->flags & BLK_INTEGRITY_REF_TAG) return "T10-DIF-TYPE1-CRC"; return "T10-DIF-TYPE3-CRC"; case BLK_INTEGRITY_CSUM_CRC64: if (bi->flags & BLK_INTEGRITY_REF_TAG) return "EXT-DIF-TYPE1-CRC64"; return "EXT-DIF-TYPE3-CRC64"; case BLK_INTEGRITY_CSUM_NONE: break; } return "nop"; } EXPORT_SYMBOL_GPL(blk_integrity_profile_name); static ssize_t flag_store(struct device *dev, const char *page, size_t count, unsigned char flag) { struct request_queue *q = dev_to_disk(dev)->queue; struct queue_limits lim; unsigned long val; int err; err = kstrtoul(page, 10, &val); if (err) return err; /* note that the flags are inverted vs the values in the sysfs files */ lim = queue_limits_start_update(q); if (val) lim.integrity.flags &= ~flag; else lim.integrity.flags |= flag; err = queue_limits_commit_update_frozen(q, &lim); if (err) return err; return count; } static ssize_t flag_show(struct device *dev, char *page, unsigned char flag) { struct blk_integrity *bi = dev_to_bi(dev); return sysfs_emit(page, "%d\n", !(bi->flags & flag)); } static ssize_t format_show(struct device *dev, struct device_attribute *attr, char *page) { struct blk_integrity *bi = dev_to_bi(dev); if (!bi->metadata_size) return sysfs_emit(page, "none\n"); return sysfs_emit(page, "%s\n", blk_integrity_profile_name(bi)); } static ssize_t tag_size_show(struct device *dev, struct device_attribute *attr, char *page) { struct blk_integrity *bi = dev_to_bi(dev); return sysfs_emit(page, "%u\n", bi->tag_size); } static ssize_t protection_interval_bytes_show(struct device *dev, struct device_attribute *attr, char *page) { struct blk_integrity *bi = dev_to_bi(dev); return sysfs_emit(page, "%u\n", bi->interval_exp ? 1 << bi->interval_exp : 0); } static ssize_t read_verify_store(struct device *dev, struct device_attribute *attr, const char *page, size_t count) { return flag_store(dev, page, count, BLK_INTEGRITY_NOVERIFY); } static ssize_t read_verify_show(struct device *dev, struct device_attribute *attr, char *page) { return flag_show(dev, page, BLK_INTEGRITY_NOVERIFY); } static ssize_t write_generate_store(struct device *dev, struct device_attribute *attr, const char *page, size_t count) { return flag_store(dev, page, count, BLK_INTEGRITY_NOGENERATE); } static ssize_t write_generate_show(struct device *dev, struct device_attribute *attr, char *page) { return flag_show(dev, page, BLK_INTEGRITY_NOGENERATE); } static ssize_t device_is_integrity_capable_show(struct device *dev, struct device_attribute *attr, char *page) { struct blk_integrity *bi = dev_to_bi(dev); return sysfs_emit(page, "%u\n", !!(bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE)); } static DEVICE_ATTR_RO(format); static DEVICE_ATTR_RO(tag_size); static DEVICE_ATTR_RO(protection_interval_bytes); static DEVICE_ATTR_RW(read_verify); static DEVICE_ATTR_RW(write_generate); static DEVICE_ATTR_RO(device_is_integrity_capable); static struct attribute *integrity_attrs[] = { &dev_attr_format.attr, &dev_attr_tag_size.attr, &dev_attr_protection_interval_bytes.attr, &dev_attr_read_verify.attr, &dev_attr_write_generate.attr, &dev_attr_device_is_integrity_capable.attr, NULL }; const struct attribute_group blk_integrity_attr_group = { .name = "integrity", .attrs = integrity_attrs, }; |
| 687 681 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGALLOC_H #define _ASM_X86_PGALLOC_H #include <linux/threads.h> #include <linux/mm.h> /* for struct page */ #include <linux/pagemap.h> #include <asm/cpufeature.h> #define __HAVE_ARCH_PTE_ALLOC_ONE #define __HAVE_ARCH_PGD_FREE #include <asm-generic/pgalloc.h> static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define paravirt_pgd_alloc(mm) __paravirt_pgd_alloc(mm) static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {} static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count) {} static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_release_pte(unsigned long pfn) {} static inline void paravirt_release_pmd(unsigned long pfn) {} static inline void paravirt_release_pud(unsigned long pfn) {} static inline void paravirt_release_p4d(unsigned long pfn) {} #endif /* * In case of Page Table Isolation active, we acquire two PGDs instead of one. * Being order-1, it is both 8k in size and 8k-aligned. That lets us just * flip bit 12 in a pointer to swap between the two 4k halves. */ static inline unsigned int pgd_allocation_order(void) { if (cpu_feature_enabled(X86_FEATURE_PTI)) return 1; return 0; } /* * Allocate and free page tables. */ extern pgd_t *pgd_alloc(struct mm_struct *); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); extern pgtable_t pte_alloc_one(struct mm_struct *); extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte); static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte, unsigned long address) { ___pte_free_tlb(tlb, pte); } static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } static inline void pmd_populate_kernel_safe(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); set_pmd_safe(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte) { unsigned long pfn = page_to_pfn(pte); paravirt_alloc_pte(mm, pfn); set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE)); } #if CONFIG_PGTABLE_LEVELS > 2 extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd); static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { ___pmd_free_tlb(tlb, pmd); } #ifdef CONFIG_X86_PAE extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd); #else /* !CONFIG_X86_PAE */ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))); } static inline void pud_populate_safe(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud_safe(pud, __pud(_PAGE_TABLE | __pa(pmd))); } #endif /* CONFIG_X86_PAE */ #if CONFIG_PGTABLE_LEVELS > 3 static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); set_p4d_safe(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } extern void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud); static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { ___pud_free_tlb(tlb, pud); } #if CONFIG_PGTABLE_LEVELS > 4 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d); static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long address) { if (pgtable_l5_enabled()) ___p4d_free_tlb(tlb, p4d); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #endif /* _ASM_X86_PGALLOC_H */ |
| 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2017-2018 Intel Corporation. All rights reserved. */ #include <linux/memremap.h> #include <linux/device.h> #include <linux/mutex.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/dax.h> #include <linux/io.h> #include "dax-private.h" #include "bus.h" static struct resource dax_regions = DEFINE_RES_MEM_NAMED(0, -1, "DAX Regions"); static DEFINE_MUTEX(dax_bus_lock); /* * All changes to the dax region configuration occur with this lock held * for write. */ DECLARE_RWSEM(dax_region_rwsem); /* * All changes to the dax device configuration occur with this lock held * for write. */ DECLARE_RWSEM(dax_dev_rwsem); #define DAX_NAME_LEN 30 struct dax_id { struct list_head list; char dev_name[DAX_NAME_LEN]; }; static int dax_bus_uevent(const struct device *dev, struct kobj_uevent_env *env) { /* * We only ever expect to handle device-dax instances, i.e. the * @type argument to MODULE_ALIAS_DAX_DEVICE() is always zero */ return add_uevent_var(env, "MODALIAS=" DAX_DEVICE_MODALIAS_FMT, 0); } static struct dax_id *__dax_match_id(const struct dax_device_driver *dax_drv, const char *dev_name) { struct dax_id *dax_id; lockdep_assert_held(&dax_bus_lock); list_for_each_entry(dax_id, &dax_drv->ids, list) if (sysfs_streq(dax_id->dev_name, dev_name)) return dax_id; return NULL; } static int dax_match_id(const struct dax_device_driver *dax_drv, struct device *dev) { int match; mutex_lock(&dax_bus_lock); match = !!__dax_match_id(dax_drv, dev_name(dev)); mutex_unlock(&dax_bus_lock); return match; } static int dax_match_type(const struct dax_device_driver *dax_drv, struct device *dev) { enum dax_driver_type type = DAXDRV_DEVICE_TYPE; struct dev_dax *dev_dax = to_dev_dax(dev); if (dev_dax->region->res.flags & IORESOURCE_DAX_KMEM) type = DAXDRV_KMEM_TYPE; if (dax_drv->type == type) return 1; /* default to device mode if dax_kmem is disabled */ if (dax_drv->type == DAXDRV_DEVICE_TYPE && !IS_ENABLED(CONFIG_DEV_DAX_KMEM)) return 1; return 0; } enum id_action { ID_REMOVE, ID_ADD, }; static ssize_t do_id_store(struct device_driver *drv, const char *buf, size_t count, enum id_action action) { struct dax_device_driver *dax_drv = to_dax_drv(drv); unsigned int region_id, id; char devname[DAX_NAME_LEN]; struct dax_id *dax_id; ssize_t rc = count; int fields; fields = sscanf(buf, "dax%d.%d", ®ion_id, &id); if (fields != 2) return -EINVAL; sprintf(devname, "dax%d.%d", region_id, id); if (!sysfs_streq(buf, devname)) return -EINVAL; mutex_lock(&dax_bus_lock); dax_id = __dax_match_id(dax_drv, buf); if (!dax_id) { if (action == ID_ADD) { dax_id = kzalloc_obj(*dax_id); if (dax_id) { strscpy(dax_id->dev_name, buf, DAX_NAME_LEN); list_add(&dax_id->list, &dax_drv->ids); } else rc = -ENOMEM; } } else if (action == ID_REMOVE) { list_del(&dax_id->list); kfree(dax_id); } mutex_unlock(&dax_bus_lock); if (rc < 0) return rc; if (action == ID_ADD) rc = driver_attach(drv); if (rc) return rc; return count; } static ssize_t new_id_store(struct device_driver *drv, const char *buf, size_t count) { return do_id_store(drv, buf, count, ID_ADD); } static DRIVER_ATTR_WO(new_id); static ssize_t remove_id_store(struct device_driver *drv, const char *buf, size_t count) { return do_id_store(drv, buf, count, ID_REMOVE); } static DRIVER_ATTR_WO(remove_id); static struct attribute *dax_drv_attrs[] = { &driver_attr_new_id.attr, &driver_attr_remove_id.attr, NULL, }; ATTRIBUTE_GROUPS(dax_drv); static int dax_bus_match(struct device *dev, const struct device_driver *drv); /* * Static dax regions are regions created by an external subsystem * nvdimm where a single range is assigned. Its boundaries are by the external * subsystem and are usually limited to one physical memory range. For example, * for PMEM it is usually defined by NVDIMM Namespace boundaries (i.e. a * single contiguous range) * * On dynamic dax regions, the assigned region can be partitioned by dax core * into multiple subdivisions. A subdivision is represented into one * /dev/daxN.M device composed by one or more potentially discontiguous ranges. * * When allocating a dax region, drivers must set whether it's static * (IORESOURCE_DAX_STATIC). On static dax devices, the @pgmap is pre-assigned * to dax core when calling devm_create_dev_dax(), whereas in dynamic dax * devices it is NULL but afterwards allocated by dax core on device ->probe(). * Care is needed to make sure that dynamic dax devices are torn down with a * cleared @pgmap field (see kill_dev_dax()). */ static bool is_static(struct dax_region *dax_region) { return (dax_region->res.flags & IORESOURCE_DAX_STATIC) != 0; } bool static_dev_dax(struct dev_dax *dev_dax) { return is_static(dev_dax->region); } EXPORT_SYMBOL_GPL(static_dev_dax); static u64 dev_dax_size(struct dev_dax *dev_dax) { u64 size = 0; int i; lockdep_assert_held(&dax_dev_rwsem); for (i = 0; i < dev_dax->nr_range; i++) size += range_len(&dev_dax->ranges[i].range); return size; } static int dax_bus_probe(struct device *dev) { struct dax_device_driver *dax_drv = to_dax_drv(dev->driver); struct dev_dax *dev_dax = to_dev_dax(dev); struct dax_region *dax_region = dev_dax->region; int rc; u64 size; rc = down_read_interruptible(&dax_dev_rwsem); if (rc) return rc; size = dev_dax_size(dev_dax); up_read(&dax_dev_rwsem); if (size == 0 || dev_dax->id < 0) return -ENXIO; rc = dax_drv->probe(dev_dax); if (rc || is_static(dax_region)) return rc; /* * Track new seed creation only after successful probe of the * previous seed. */ if (dax_region->seed == dev) dax_region->seed = NULL; return 0; } static void dax_bus_remove(struct device *dev) { struct dax_device_driver *dax_drv = to_dax_drv(dev->driver); struct dev_dax *dev_dax = to_dev_dax(dev); if (dax_drv->remove) dax_drv->remove(dev_dax); } static const struct bus_type dax_bus_type = { .name = "dax", .uevent = dax_bus_uevent, .match = dax_bus_match, .probe = dax_bus_probe, .remove = dax_bus_remove, .drv_groups = dax_drv_groups, }; static int dax_bus_match(struct device *dev, const struct device_driver *drv) { const struct dax_device_driver *dax_drv = to_dax_drv(drv); if (dax_match_id(dax_drv, dev)) return 1; return dax_match_type(dax_drv, dev); } /* * Rely on the fact that drvdata is set before the attributes are * registered, and that the attributes are unregistered before drvdata * is cleared to assume that drvdata is always valid. */ static ssize_t id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dax_region *dax_region = dev_get_drvdata(dev); return sysfs_emit(buf, "%d\n", dax_region->id); } static DEVICE_ATTR_RO(id); static ssize_t region_size_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dax_region *dax_region = dev_get_drvdata(dev); return sysfs_emit(buf, "%llu\n", (unsigned long long)resource_size(&dax_region->res)); } static struct device_attribute dev_attr_region_size = __ATTR(size, 0444, region_size_show, NULL); static ssize_t region_align_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dax_region *dax_region = dev_get_drvdata(dev); return sysfs_emit(buf, "%u\n", dax_region->align); } static struct device_attribute dev_attr_region_align = __ATTR(align, 0400, region_align_show, NULL); #define for_each_dax_region_resource(dax_region, res) \ for (res = (dax_region)->res.child; res; res = res->sibling) static unsigned long long dax_region_avail_size(struct dax_region *dax_region) { resource_size_t size = resource_size(&dax_region->res); struct resource *res; lockdep_assert_held(&dax_region_rwsem); for_each_dax_region_resource(dax_region, res) size -= resource_size(res); return size; } static ssize_t available_size_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dax_region *dax_region = dev_get_drvdata(dev); unsigned long long size; int rc; rc = down_read_interruptible(&dax_region_rwsem); if (rc) return rc; size = dax_region_avail_size(dax_region); up_read(&dax_region_rwsem); return sysfs_emit(buf, "%llu\n", size); } static DEVICE_ATTR_RO(available_size); static ssize_t seed_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dax_region *dax_region = dev_get_drvdata(dev); struct device *seed; ssize_t rc; if (is_static(dax_region)) return -EINVAL; rc = down_read_interruptible(&dax_region_rwsem); if (rc) return rc; seed = dax_region->seed; rc = sysfs_emit(buf, "%s\n", seed ? dev_name(seed) : ""); up_read(&dax_region_rwsem); return rc; } static DEVICE_ATTR_RO(seed); static ssize_t create_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dax_region *dax_region = dev_get_drvdata(dev); struct device *youngest; ssize_t rc; if (is_static(dax_region)) return -EINVAL; rc = down_read_interruptible(&dax_region_rwsem); if (rc) return rc; youngest = dax_region->youngest; rc = sysfs_emit(buf, "%s\n", youngest ? dev_name(youngest) : ""); up_read(&dax_region_rwsem); return rc; } static struct dev_dax *__devm_create_dev_dax(struct dev_dax_data *data); static ssize_t create_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct dax_region *dax_region = dev_get_drvdata(dev); unsigned long long avail; ssize_t rc; int val; if (is_static(dax_region)) return -EINVAL; rc = kstrtoint(buf, 0, &val); if (rc) return rc; if (val != 1) return -EINVAL; rc = down_write_killable(&dax_region_rwsem); if (rc) return rc; avail = dax_region_avail_size(dax_region); if (avail == 0) rc = -ENOSPC; else { struct dev_dax_data data = { .dax_region = dax_region, .size = 0, .id = -1, .memmap_on_memory = false, }; struct dev_dax *dev_dax = __devm_create_dev_dax(&data); if (IS_ERR(dev_dax)) rc = PTR_ERR(dev_dax); else { /* * In support of crafting multiple new devices * simultaneously multiple seeds can be created, * but only the first one that has not been * successfully bound is tracked as the region * seed. */ if (!dax_region->seed) dax_region->seed = &dev_dax->dev; dax_region->youngest = &dev_dax->dev; rc = len; } } up_write(&dax_region_rwsem); return rc; } static DEVICE_ATTR_RW(create); void kill_dev_dax(struct dev_dax *dev_dax) { struct dax_device *dax_dev = dev_dax->dax_dev; struct inode *inode = dax_inode(dax_dev); kill_dax(dax_dev); unmap_mapping_range(inode->i_mapping, 0, 0, 1); /* * Dynamic dax region have the pgmap allocated via dev_kzalloc() * and thus freed by devm. Clear the pgmap to not have stale pgmap * ranges on probe() from previous reconfigurations of region devices. */ if (!static_dev_dax(dev_dax)) dev_dax->pgmap = NULL; } EXPORT_SYMBOL_GPL(kill_dev_dax); static void trim_dev_dax_range(struct dev_dax *dev_dax) { int i = dev_dax->nr_range - 1; struct range *range = &dev_dax->ranges[i].range; struct dax_region *dax_region = dev_dax->region; lockdep_assert_held_write(&dax_region_rwsem); dev_dbg(&dev_dax->dev, "delete range[%d]: %#llx:%#llx\n", i, (unsigned long long)range->start, (unsigned long long)range->end); __release_region(&dax_region->res, range->start, range_len(range)); if (--dev_dax->nr_range == 0) { kfree(dev_dax->ranges); dev_dax->ranges = NULL; } } static void free_dev_dax_ranges(struct dev_dax *dev_dax) { while (dev_dax->nr_range) trim_dev_dax_range(dev_dax); } static void unregister_dev_dax(void *dev) { struct dev_dax *dev_dax = to_dev_dax(dev); dev_dbg(dev, "%s\n", __func__); down_write(&dax_region_rwsem); kill_dev_dax(dev_dax); device_del(dev); free_dev_dax_ranges(dev_dax); put_device(dev); up_write(&dax_region_rwsem); } static void dax_region_free(struct kref *kref) { struct dax_region *dax_region; dax_region = container_of(kref, struct dax_region, kref); kfree(dax_region); } static void dax_region_put(struct dax_region *dax_region) { kref_put(&dax_region->kref, dax_region_free); } /* a return value >= 0 indicates this invocation invalidated the id */ static int __free_dev_dax_id(struct dev_dax *dev_dax) { struct dax_region *dax_region; int rc = dev_dax->id; lockdep_assert_held_write(&dax_dev_rwsem); if (!dev_dax->dyn_id || dev_dax->id < 0) return -1; dax_region = dev_dax->region; ida_free(&dax_region->ida, dev_dax->id); dax_region_put(dax_region); dev_dax->id = -1; return rc; } static int free_dev_dax_id(struct dev_dax *dev_dax) { int rc; rc = down_write_killable(&dax_dev_rwsem); if (rc) return rc; rc = __free_dev_dax_id(dev_dax); up_write(&dax_dev_rwsem); return rc; } static int alloc_dev_dax_id(struct dev_dax *dev_dax) { struct dax_region *dax_region = dev_dax->region; int id; id = ida_alloc(&dax_region->ida, GFP_KERNEL); if (id < 0) return id; kref_get(&dax_region->kref); dev_dax->dyn_id = true; dev_dax->id = id; return id; } static ssize_t delete_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct dax_region *dax_region = dev_get_drvdata(dev); struct dev_dax *dev_dax; struct device *victim; bool do_del = false; int rc; if (is_static(dax_region)) return -EINVAL; victim = device_find_child_by_name(dax_region->dev, buf); if (!victim) return -ENXIO; device_lock(dev); device_lock(victim); dev_dax = to_dev_dax(victim); down_write(&dax_dev_rwsem); if (victim->driver || dev_dax_size(dev_dax)) rc = -EBUSY; else { /* * Invalidate the device so it does not become active * again, but always preserve device-id-0 so that * /sys/bus/dax/ is guaranteed to be populated while any * dax_region is registered. */ if (dev_dax->id > 0) { do_del = __free_dev_dax_id(dev_dax) >= 0; rc = len; if (dax_region->seed == victim) dax_region->seed = NULL; if (dax_region->youngest == victim) dax_region->youngest = NULL; } else rc = -EBUSY; } up_write(&dax_dev_rwsem); device_unlock(victim); /* won the race to invalidate the device, clean it up */ if (do_del) devm_release_action(dev, unregister_dev_dax, victim); device_unlock(dev); put_device(victim); return rc; } static DEVICE_ATTR_WO(delete); static umode_t dax_region_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = container_of(kobj, struct device, kobj); struct dax_region *dax_region = dev_get_drvdata(dev); if (is_static(dax_region)) if (a == &dev_attr_available_size.attr || a == &dev_attr_create.attr || a == &dev_attr_seed.attr || a == &dev_attr_delete.attr) return 0; return a->mode; } static struct attribute *dax_region_attributes[] = { &dev_attr_available_size.attr, &dev_attr_region_size.attr, &dev_attr_region_align.attr, &dev_attr_create.attr, &dev_attr_seed.attr, &dev_attr_delete.attr, &dev_attr_id.attr, NULL, }; static const struct attribute_group dax_region_attribute_group = { .name = "dax_region", .attrs = dax_region_attributes, .is_visible = dax_region_visible, }; static const struct attribute_group *dax_region_attribute_groups[] = { &dax_region_attribute_group, NULL, }; static void dax_region_unregister(void *region) { struct dax_region *dax_region = region; sysfs_remove_groups(&dax_region->dev->kobj, dax_region_attribute_groups); release_resource(&dax_region->res); dax_region_put(dax_region); } struct dax_region *alloc_dax_region(struct device *parent, int region_id, struct range *range, int target_node, unsigned int align, unsigned long flags) { struct dax_region *dax_region; int rc; /* * The DAX core assumes that it can store its private data in * parent->driver_data. This WARN is a reminder / safeguard for * developers of device-dax drivers. */ if (dev_get_drvdata(parent)) { dev_WARN(parent, "dax core failed to setup private data\n"); return NULL; } if (!IS_ALIGNED(range->start, align) || !IS_ALIGNED(range_len(range), align)) return NULL; dax_region = kzalloc_obj(*dax_region); if (!dax_region) return NULL; dev_set_drvdata(parent, dax_region); kref_init(&dax_region->kref); dax_region->id = region_id; dax_region->align = align; dax_region->dev = parent; dax_region->target_node = target_node; ida_init(&dax_region->ida); dax_region->res = (struct resource) { .start = range->start, .end = range->end, .flags = IORESOURCE_MEM | flags, }; rc = request_resource(&dax_regions, &dax_region->res); if (rc) { dev_err(parent, "dax_region resource conflict for %pR\n", &dax_region->res); goto err_res; } if (sysfs_create_groups(&parent->kobj, dax_region_attribute_groups)) goto err_sysfs; if (devm_add_action_or_reset(parent, dax_region_unregister, dax_region)) return NULL; return dax_region; err_sysfs: release_resource(&dax_region->res); err_res: dax_region_put(dax_region); return NULL; } EXPORT_SYMBOL_GPL(alloc_dax_region); static void dax_mapping_release(struct device *dev) { struct dax_mapping *mapping = to_dax_mapping(dev); struct device *parent = dev->parent; struct dev_dax *dev_dax = to_dev_dax(parent); ida_free(&dev_dax->ida, mapping->id); kfree(mapping); put_device(parent); } static void unregister_dax_mapping(void *data) { struct device *dev = data; struct dax_mapping *mapping = to_dax_mapping(dev); struct dev_dax *dev_dax = to_dev_dax(dev->parent); dev_dbg(dev, "%s\n", __func__); dev_dax->ranges[mapping->range_id].mapping = NULL; mapping->range_id = -1; device_unregister(dev); } static struct dev_dax_range *get_dax_range(struct device *dev) { struct dax_mapping *mapping = to_dax_mapping(dev); struct dev_dax *dev_dax = to_dev_dax(dev->parent); int rc; rc = down_write_killable(&dax_region_rwsem); if (rc) return NULL; if (mapping->range_id < 0) { up_write(&dax_region_rwsem); return NULL; } return &dev_dax->ranges[mapping->range_id]; } static void put_dax_range(void) { up_write(&dax_region_rwsem); } static ssize_t start_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_dax_range *dax_range; ssize_t rc; dax_range = get_dax_range(dev); if (!dax_range) return -ENXIO; rc = sysfs_emit(buf, "%#llx\n", dax_range->range.start); put_dax_range(); return rc; } static DEVICE_ATTR(start, 0400, start_show, NULL); static ssize_t end_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_dax_range *dax_range; ssize_t rc; dax_range = get_dax_range(dev); if (!dax_range) return -ENXIO; rc = sysfs_emit(buf, "%#llx\n", dax_range->range.end); put_dax_range(); return rc; } static DEVICE_ATTR(end, 0400, end_show, NULL); static ssize_t pgoff_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_dax_range *dax_range; ssize_t rc; dax_range = get_dax_range(dev); if (!dax_range) return -ENXIO; rc = sysfs_emit(buf, "%#lx\n", dax_range->pgoff); put_dax_range(); return rc; } static DEVICE_ATTR(page_offset, 0400, pgoff_show, NULL); static struct attribute *dax_mapping_attributes[] = { &dev_attr_start.attr, &dev_attr_end.attr, &dev_attr_page_offset.attr, NULL, }; static const struct attribute_group dax_mapping_attribute_group = { .attrs = dax_mapping_attributes, }; static const struct attribute_group *dax_mapping_attribute_groups[] = { &dax_mapping_attribute_group, NULL, }; static const struct device_type dax_mapping_type = { .release = dax_mapping_release, .groups = dax_mapping_attribute_groups, }; static int devm_register_dax_mapping(struct dev_dax *dev_dax, int range_id) { struct dax_region *dax_region = dev_dax->region; struct dax_mapping *mapping; struct device *dev; int rc; lockdep_assert_held_write(&dax_region_rwsem); if (dev_WARN_ONCE(&dev_dax->dev, !dax_region->dev->driver, "region disabled\n")) return -ENXIO; mapping = kzalloc_obj(*mapping); if (!mapping) return -ENOMEM; mapping->range_id = range_id; mapping->id = ida_alloc(&dev_dax->ida, GFP_KERNEL); if (mapping->id < 0) { kfree(mapping); return -ENOMEM; } dev_dax->ranges[range_id].mapping = mapping; dev = &mapping->dev; device_initialize(dev); dev->parent = &dev_dax->dev; get_device(dev->parent); dev->type = &dax_mapping_type; dev_set_name(dev, "mapping%d", mapping->id); rc = device_add(dev); if (rc) { put_device(dev); return rc; } rc = devm_add_action_or_reset(dax_region->dev, unregister_dax_mapping, dev); if (rc) return rc; return 0; } static int alloc_dev_dax_range(struct dev_dax *dev_dax, u64 start, resource_size_t size) { struct dax_region *dax_region = dev_dax->region; struct resource *res = &dax_region->res; struct device *dev = &dev_dax->dev; struct dev_dax_range *ranges; unsigned long pgoff = 0; struct resource *alloc; int i, rc; lockdep_assert_held_write(&dax_region_rwsem); /* handle the seed alloc special case */ if (!size) { if (dev_WARN_ONCE(dev, dev_dax->nr_range, "0-size allocation must be first\n")) return -EBUSY; /* nr_range == 0 is elsewhere special cased as 0-size device */ return 0; } alloc = __request_region(res, start, size, dev_name(dev), 0); if (!alloc) return -ENOMEM; ranges = krealloc(dev_dax->ranges, sizeof(*ranges) * (dev_dax->nr_range + 1), GFP_KERNEL); if (!ranges) { __release_region(res, alloc->start, resource_size(alloc)); return -ENOMEM; } for (i = 0; i < dev_dax->nr_range; i++) pgoff += PHYS_PFN(range_len(&ranges[i].range)); dev_dax->ranges = ranges; ranges[dev_dax->nr_range++] = (struct dev_dax_range) { .pgoff = pgoff, .range = { .start = alloc->start, .end = alloc->end, }, }; dev_dbg(dev, "alloc range[%d]: %pa:%pa\n", dev_dax->nr_range - 1, &alloc->start, &alloc->end); /* * A dev_dax instance must be registered before mapping device * children can be added. Defer to devm_create_dev_dax() to add * the initial mapping device. */ if (!device_is_registered(&dev_dax->dev)) return 0; rc = devm_register_dax_mapping(dev_dax, dev_dax->nr_range - 1); if (rc) trim_dev_dax_range(dev_dax); return rc; } static int adjust_dev_dax_range(struct dev_dax *dev_dax, struct resource *res, resource_size_t size) { int last_range = dev_dax->nr_range - 1; struct dev_dax_range *dax_range = &dev_dax->ranges[last_range]; bool is_shrink = resource_size(res) > size; struct range *range = &dax_range->range; struct device *dev = &dev_dax->dev; int rc; lockdep_assert_held_write(&dax_region_rwsem); if (dev_WARN_ONCE(dev, !size, "deletion is handled by dev_dax_shrink\n")) return -EINVAL; rc = adjust_resource(res, range->start, size); if (rc) return rc; *range = (struct range) { .start = range->start, .end = range->start + size - 1, }; dev_dbg(dev, "%s range[%d]: %#llx:%#llx\n", is_shrink ? "shrink" : "extend", last_range, (unsigned long long) range->start, (unsigned long long) range->end); return 0; } static ssize_t size_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_dax *dev_dax = to_dev_dax(dev); unsigned long long size; int rc; rc = down_read_interruptible(&dax_dev_rwsem); if (rc) return rc; size = dev_dax_size(dev_dax); up_read(&dax_dev_rwsem); return sysfs_emit(buf, "%llu\n", size); } static bool alloc_is_aligned(struct dev_dax *dev_dax, resource_size_t size) { /* * The minimum mapping granularity for a device instance is a * single subsection, unless the arch says otherwise. */ return IS_ALIGNED(size, max_t(unsigned long, dev_dax->align, memremap_compat_align())); } static int dev_dax_shrink(struct dev_dax *dev_dax, resource_size_t size) { resource_size_t to_shrink = dev_dax_size(dev_dax) - size; struct dax_region *dax_region = dev_dax->region; struct device *dev = &dev_dax->dev; int i; for (i = dev_dax->nr_range - 1; i >= 0; i--) { struct range *range = &dev_dax->ranges[i].range; struct dax_mapping *mapping = dev_dax->ranges[i].mapping; struct resource *adjust = NULL, *res; resource_size_t shrink; shrink = min_t(u64, to_shrink, range_len(range)); if (shrink >= range_len(range)) { devm_release_action(dax_region->dev, unregister_dax_mapping, &mapping->dev); trim_dev_dax_range(dev_dax); to_shrink -= shrink; if (!to_shrink) break; continue; } for_each_dax_region_resource(dax_region, res) if (strcmp(res->name, dev_name(dev)) == 0 && res->start == range->start) { adjust = res; break; } if (dev_WARN_ONCE(dev, !adjust || i != dev_dax->nr_range - 1, "failed to find matching resource\n")) return -ENXIO; return adjust_dev_dax_range(dev_dax, adjust, range_len(range) - shrink); } return 0; } /* * Only allow adjustments that preserve the relative pgoff of existing * allocations. I.e. the dev_dax->ranges array is ordered by increasing pgoff. */ static bool adjust_ok(struct dev_dax *dev_dax, struct resource *res) { struct dev_dax_range *last; int i; if (dev_dax->nr_range == 0) return false; if (strcmp(res->name, dev_name(&dev_dax->dev)) != 0) return false; last = &dev_dax->ranges[dev_dax->nr_range - 1]; if (last->range.start != res->start || last->range.end != res->end) return false; for (i = 0; i < dev_dax->nr_range - 1; i++) { struct dev_dax_range *dax_range = &dev_dax->ranges[i]; if (dax_range->pgoff > last->pgoff) return false; } return true; } static ssize_t dev_dax_resize(struct dax_region *dax_region, struct dev_dax *dev_dax, resource_size_t size) { resource_size_t avail = dax_region_avail_size(dax_region), to_alloc; resource_size_t dev_size = dev_dax_size(dev_dax); struct resource *region_res = &dax_region->res; struct device *dev = &dev_dax->dev; struct resource *res, *first; resource_size_t alloc = 0; int rc; if (dev->driver) return -EBUSY; if (size == dev_size) return 0; if (size > dev_size && size - dev_size > avail) return -ENOSPC; if (size < dev_size) return dev_dax_shrink(dev_dax, size); to_alloc = size - dev_size; if (dev_WARN_ONCE(dev, !alloc_is_aligned(dev_dax, to_alloc), "resize of %pa misaligned\n", &to_alloc)) return -ENXIO; /* * Expand the device into the unused portion of the region. This * may involve adjusting the end of an existing resource, or * allocating a new resource. */ retry: first = region_res->child; if (!first) return alloc_dev_dax_range(dev_dax, dax_region->res.start, to_alloc); rc = -ENOSPC; for (res = first; res; res = res->sibling) { struct resource *next = res->sibling; /* space at the beginning of the region */ if (res == first && res->start > dax_region->res.start) { alloc = min(res->start - dax_region->res.start, to_alloc); rc = alloc_dev_dax_range(dev_dax, dax_region->res.start, alloc); break; } alloc = 0; /* space between allocations */ if (next && next->start > res->end + 1) alloc = min(next->start - (res->end + 1), to_alloc); /* space at the end of the region */ if (!alloc && !next && res->end < region_res->end) alloc = min(region_res->end - res->end, to_alloc); if (!alloc) continue; if (adjust_ok(dev_dax, res)) { rc = adjust_dev_dax_range(dev_dax, res, resource_size(res) + alloc); break; } rc = alloc_dev_dax_range(dev_dax, res->end + 1, alloc); break; } if (rc) return rc; to_alloc -= alloc; if (to_alloc) goto retry; return 0; } static ssize_t size_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { ssize_t rc; unsigned long long val; struct dev_dax *dev_dax = to_dev_dax(dev); struct dax_region *dax_region = dev_dax->region; rc = kstrtoull(buf, 0, &val); if (rc) return rc; if (!alloc_is_aligned(dev_dax, val)) { dev_dbg(dev, "%s: size: %lld misaligned\n", __func__, val); return -EINVAL; } rc = down_write_killable(&dax_region_rwsem); if (rc) return rc; if (!dax_region->dev->driver) { rc = -ENXIO; goto err_region; } rc = down_write_killable(&dax_dev_rwsem); if (rc) goto err_dev; rc = dev_dax_resize(dax_region, dev_dax, val); err_dev: up_write(&dax_dev_rwsem); err_region: up_write(&dax_region_rwsem); if (rc == 0) return len; return rc; } static DEVICE_ATTR_RW(size); static ssize_t range_parse(const char *opt, size_t len, struct range *range) { unsigned long long addr = 0; char *start, *end, *str; ssize_t rc = -EINVAL; str = kstrdup(opt, GFP_KERNEL); if (!str) return rc; end = str; start = strsep(&end, "-"); if (!start || !end) goto err; rc = kstrtoull(start, 16, &addr); if (rc) goto err; range->start = addr; rc = kstrtoull(end, 16, &addr); if (rc) goto err; range->end = addr; err: kfree(str); return rc; } static ssize_t mapping_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct dev_dax *dev_dax = to_dev_dax(dev); struct dax_region *dax_region = dev_dax->region; size_t to_alloc; struct range r; ssize_t rc; rc = range_parse(buf, len, &r); if (rc) return rc; rc = down_write_killable(&dax_region_rwsem); if (rc) return rc; if (!dax_region->dev->driver) { up_write(&dax_region_rwsem); return rc; } rc = down_write_killable(&dax_dev_rwsem); if (rc) { up_write(&dax_region_rwsem); return rc; } to_alloc = range_len(&r); if (alloc_is_aligned(dev_dax, to_alloc)) rc = alloc_dev_dax_range(dev_dax, r.start, to_alloc); up_write(&dax_dev_rwsem); up_write(&dax_region_rwsem); return rc == 0 ? len : rc; } static DEVICE_ATTR_WO(mapping); static ssize_t align_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_dax *dev_dax = to_dev_dax(dev); return sysfs_emit(buf, "%d\n", dev_dax->align); } static ssize_t dev_dax_validate_align(struct dev_dax *dev_dax) { struct device *dev = &dev_dax->dev; int i; for (i = 0; i < dev_dax->nr_range; i++) { size_t len = range_len(&dev_dax->ranges[i].range); if (!alloc_is_aligned(dev_dax, len)) { dev_dbg(dev, "%s: align %u invalid for range %d\n", __func__, dev_dax->align, i); return -EINVAL; } } return 0; } static ssize_t align_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct dev_dax *dev_dax = to_dev_dax(dev); struct dax_region *dax_region = dev_dax->region; unsigned long val, align_save; ssize_t rc; rc = kstrtoul(buf, 0, &val); if (rc) return -ENXIO; if (!dax_align_valid(val)) return -EINVAL; rc = down_write_killable(&dax_region_rwsem); if (rc) return rc; if (!dax_region->dev->driver) { up_write(&dax_region_rwsem); return -ENXIO; } rc = down_write_killable(&dax_dev_rwsem); if (rc) { up_write(&dax_region_rwsem); return rc; } if (dev->driver) { rc = -EBUSY; goto out_unlock; } align_save = dev_dax->align; dev_dax->align = val; rc = dev_dax_validate_align(dev_dax); if (rc) dev_dax->align = align_save; out_unlock: up_write(&dax_dev_rwsem); up_write(&dax_region_rwsem); return rc == 0 ? len : rc; } static DEVICE_ATTR_RW(align); static int dev_dax_target_node(struct dev_dax *dev_dax) { struct dax_region *dax_region = dev_dax->region; return dax_region->target_node; } static ssize_t target_node_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_dax *dev_dax = to_dev_dax(dev); return sysfs_emit(buf, "%d\n", dev_dax_target_node(dev_dax)); } static DEVICE_ATTR_RO(target_node); static ssize_t resource_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_dax *dev_dax = to_dev_dax(dev); struct dax_region *dax_region = dev_dax->region; unsigned long long start; if (dev_dax->nr_range < 1) start = dax_region->res.start; else start = dev_dax->ranges[0].range.start; return sysfs_emit(buf, "%#llx\n", start); } static DEVICE_ATTR(resource, 0400, resource_show, NULL); static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, char *buf) { /* * We only ever expect to handle device-dax instances, i.e. the * @type argument to MODULE_ALIAS_DAX_DEVICE() is always zero */ return sysfs_emit(buf, DAX_DEVICE_MODALIAS_FMT "\n", 0); } 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 ssize_t memmap_on_memory_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_dax *dev_dax = to_dev_dax(dev); return sysfs_emit(buf, "%d\n", dev_dax->memmap_on_memory); } static ssize_t memmap_on_memory_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct dev_dax *dev_dax = to_dev_dax(dev); bool val; int rc; rc = kstrtobool(buf, &val); if (rc) return rc; if (val == true && !mhp_supports_memmap_on_memory()) { dev_dbg(dev, "memmap_on_memory is not available\n"); return -EOPNOTSUPP; } rc = down_write_killable(&dax_dev_rwsem); if (rc) return rc; if (dev_dax->memmap_on_memory != val && dev->driver && to_dax_drv(dev->driver)->type == DAXDRV_KMEM_TYPE) { up_write(&dax_dev_rwsem); return -EBUSY; } dev_dax->memmap_on_memory = val; up_write(&dax_dev_rwsem); return len; } static DEVICE_ATTR_RW(memmap_on_memory); static umode_t dev_dax_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = container_of(kobj, struct device, kobj); struct dev_dax *dev_dax = to_dev_dax(dev); struct dax_region *dax_region = dev_dax->region; if (a == &dev_attr_target_node.attr && dev_dax_target_node(dev_dax) < 0) return 0; if (a == &dev_attr_numa_node.attr && !IS_ENABLED(CONFIG_NUMA)) return 0; if (a == &dev_attr_mapping.attr && is_static(dax_region)) return 0; if ((a == &dev_attr_align.attr || a == &dev_attr_size.attr) && is_static(dax_region)) return 0444; return a->mode; } static struct attribute *dev_dax_attributes[] = { &dev_attr_modalias.attr, &dev_attr_size.attr, &dev_attr_mapping.attr, &dev_attr_target_node.attr, &dev_attr_align.attr, &dev_attr_resource.attr, &dev_attr_numa_node.attr, &dev_attr_memmap_on_memory.attr, NULL, }; static const struct attribute_group dev_dax_attribute_group = { .attrs = dev_dax_attributes, .is_visible = dev_dax_visible, }; static const struct attribute_group *dax_attribute_groups[] = { &dev_dax_attribute_group, NULL, }; static void dev_dax_release(struct device *dev) { struct dev_dax *dev_dax = to_dev_dax(dev); struct dax_device *dax_dev = dev_dax->dax_dev; put_dax(dax_dev); free_dev_dax_id(dev_dax); kfree(dev_dax->pgmap); kfree(dev_dax); } static const struct device_type dev_dax_type = { .release = dev_dax_release, .groups = dax_attribute_groups, }; /* see "strong" declaration in tools/testing/nvdimm/dax-dev.c */ __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff, unsigned long size) { for (int i = 0; i < dev_dax->nr_range; i++) { struct dev_dax_range *dax_range = &dev_dax->ranges[i]; struct range *range = &dax_range->range; phys_addr_t phys; if (!in_range(pgoff, dax_range->pgoff, PHYS_PFN(range_len(range)))) continue; phys = PFN_PHYS(pgoff - dax_range->pgoff) + range->start; if (phys + size - 1 <= range->end) return phys; break; } return -1; } EXPORT_SYMBOL_GPL(dax_pgoff_to_phys); static struct dev_dax *__devm_create_dev_dax(struct dev_dax_data *data) { struct dax_region *dax_region = data->dax_region; struct device *parent = dax_region->dev; struct dax_device *dax_dev; struct dev_dax *dev_dax; struct inode *inode; struct device *dev; int rc; dev_dax = kzalloc_obj(*dev_dax); if (!dev_dax) return ERR_PTR(-ENOMEM); dev_dax->region = dax_region; if (is_static(dax_region)) { if (dev_WARN_ONCE(parent, data->id < 0, "dynamic id specified to static region\n")) { rc = -EINVAL; goto err_id; } dev_dax->id = data->id; } else { if (dev_WARN_ONCE(parent, data->id >= 0, "static id specified to dynamic region\n")) { rc = -EINVAL; goto err_id; } rc = alloc_dev_dax_id(dev_dax); if (rc < 0) goto err_id; } dev = &dev_dax->dev; device_initialize(dev); dev_set_name(dev, "dax%d.%d", dax_region->id, dev_dax->id); rc = alloc_dev_dax_range(dev_dax, dax_region->res.start, data->size); if (rc) goto err_range; if (data->pgmap) { dev_WARN_ONCE(parent, !is_static(dax_region), "custom dev_pagemap requires a static dax_region\n"); dev_dax->pgmap = kmemdup(data->pgmap, sizeof(struct dev_pagemap), GFP_KERNEL); if (!dev_dax->pgmap) { rc = -ENOMEM; goto err_pgmap; } } /* * No dax_operations since there is no access to this device outside of * mmap of the resulting character device. */ dax_dev = alloc_dax(dev_dax, NULL); if (IS_ERR(dax_dev)) { rc = PTR_ERR(dax_dev); goto err_alloc_dax; } set_dax_synchronous(dax_dev); set_dax_nocache(dax_dev); set_dax_nomc(dax_dev); /* a device_dax instance is dead while the driver is not attached */ kill_dax(dax_dev); dev_dax->dax_dev = dax_dev; dev_dax->target_node = dax_region->target_node; dev_dax->align = dax_region->align; ida_init(&dev_dax->ida); dev_dax->memmap_on_memory = data->memmap_on_memory; inode = dax_inode(dax_dev); dev->devt = inode->i_rdev; dev->bus = &dax_bus_type; dev->parent = parent; dev->type = &dev_dax_type; rc = device_add(dev); if (rc) { kill_dev_dax(dev_dax); put_device(dev); return ERR_PTR(rc); } rc = devm_add_action_or_reset(dax_region->dev, unregister_dev_dax, dev); if (rc) return ERR_PTR(rc); /* register mapping device for the initial allocation range */ if (dev_dax->nr_range && range_len(&dev_dax->ranges[0].range)) { rc = devm_register_dax_mapping(dev_dax, 0); if (rc) return ERR_PTR(rc); } return dev_dax; err_alloc_dax: kfree(dev_dax->pgmap); err_pgmap: free_dev_dax_ranges(dev_dax); err_range: free_dev_dax_id(dev_dax); err_id: kfree(dev_dax); return ERR_PTR(rc); } struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) { struct dev_dax *dev_dax; down_write(&dax_region_rwsem); dev_dax = __devm_create_dev_dax(data); up_write(&dax_region_rwsem); return dev_dax; } EXPORT_SYMBOL_GPL(devm_create_dev_dax); int __dax_driver_register(struct dax_device_driver *dax_drv, struct module *module, const char *mod_name) { struct device_driver *drv = &dax_drv->drv; /* * dax_bus_probe() calls dax_drv->probe() unconditionally. * So better be safe than sorry and ensure it is provided. */ if (!dax_drv->probe) return -EINVAL; INIT_LIST_HEAD(&dax_drv->ids); drv->owner = module; drv->name = mod_name; drv->mod_name = mod_name; drv->bus = &dax_bus_type; return driver_register(drv); } EXPORT_SYMBOL_GPL(__dax_driver_register); void dax_driver_unregister(struct dax_device_driver *dax_drv) { struct device_driver *drv = &dax_drv->drv; struct dax_id *dax_id, *_id; mutex_lock(&dax_bus_lock); list_for_each_entry_safe(dax_id, _id, &dax_drv->ids, list) { list_del(&dax_id->list); kfree(dax_id); } mutex_unlock(&dax_bus_lock); driver_unregister(drv); } EXPORT_SYMBOL_GPL(dax_driver_unregister); int __init dax_bus_init(void) { return bus_register(&dax_bus_type); } void __exit dax_bus_exit(void) { bus_unregister(&dax_bus_type); } |
| 42 43 43 58 58 58 33 24 23 23 23 3 24 13 13 24 24 24 24 49 49 33 33 33 49 43 3 3 3 3 3 3 3 3 3 34 34 34 34 44 44 44 44 23 23 23 23 16 16 16 16 16 16 12 12 12 12 12 12 12 11 11 12 26 8 5 5 26 4 3 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 | /* * Copyright (c) 2006, 2020 Oracle and/or its affiliates. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/skbuff.h> #include <linux/list.h> #include <linux/errqueue.h> #include "rds.h" static unsigned int rds_exthdr_size[__RDS_EXTHDR_MAX] = { [RDS_EXTHDR_NONE] = 0, [RDS_EXTHDR_VERSION] = sizeof(struct rds_ext_header_version), [RDS_EXTHDR_RDMA] = sizeof(struct rds_ext_header_rdma), [RDS_EXTHDR_RDMA_DEST] = sizeof(struct rds_ext_header_rdma_dest), [RDS_EXTHDR_RDMA_BYTES] = sizeof(struct rds_ext_header_rdma_bytes), [RDS_EXTHDR_NPATHS] = sizeof(__be16), [RDS_EXTHDR_GEN_NUM] = sizeof(__be32), [RDS_EXTHDR_SPORT_IDX] = 1, }; void rds_message_addref(struct rds_message *rm) { rdsdebug("addref rm %p ref %d\n", rm, refcount_read(&rm->m_refcount)); refcount_inc(&rm->m_refcount); } EXPORT_SYMBOL_GPL(rds_message_addref); static inline bool rds_zcookie_add(struct rds_msg_zcopy_info *info, u32 cookie) { struct rds_zcopy_cookies *ck = &info->zcookies; int ncookies = ck->num; if (ncookies == RDS_MAX_ZCOOKIES) return false; ck->cookies[ncookies] = cookie; ck->num = ++ncookies; return true; } static struct rds_msg_zcopy_info *rds_info_from_znotifier(struct rds_znotifier *znotif) { return container_of(znotif, struct rds_msg_zcopy_info, znotif); } void rds_notify_msg_zcopy_purge(struct rds_msg_zcopy_queue *q) { unsigned long flags; LIST_HEAD(copy); struct rds_msg_zcopy_info *info, *tmp; spin_lock_irqsave(&q->lock, flags); list_splice(&q->zcookie_head, ©); INIT_LIST_HEAD(&q->zcookie_head); spin_unlock_irqrestore(&q->lock, flags); list_for_each_entry_safe(info, tmp, ©, rs_zcookie_next) { list_del(&info->rs_zcookie_next); kfree(info); } } static void rds_rm_zerocopy_callback(struct rds_sock *rs, struct rds_znotifier *znotif) { struct rds_msg_zcopy_info *info; struct rds_msg_zcopy_queue *q; u32 cookie = znotif->z_cookie; struct rds_zcopy_cookies *ck; struct list_head *head; unsigned long flags; mm_unaccount_pinned_pages(&znotif->z_mmp); q = &rs->rs_zcookie_queue; spin_lock_irqsave(&q->lock, flags); head = &q->zcookie_head; if (!list_empty(head)) { info = list_first_entry(head, struct rds_msg_zcopy_info, rs_zcookie_next); if (rds_zcookie_add(info, cookie)) { spin_unlock_irqrestore(&q->lock, flags); kfree(rds_info_from_znotifier(znotif)); /* caller invokes rds_wake_sk_sleep() */ return; } } info = rds_info_from_znotifier(znotif); ck = &info->zcookies; memset(ck, 0, sizeof(*ck)); WARN_ON(!rds_zcookie_add(info, cookie)); list_add_tail(&info->rs_zcookie_next, &q->zcookie_head); spin_unlock_irqrestore(&q->lock, flags); /* caller invokes rds_wake_sk_sleep() */ } /* * This relies on dma_map_sg() not touching sg[].page during merging. */ static void rds_message_purge(struct rds_message *rm) { struct rds_znotifier *znotifier; unsigned long i, flags; bool zcopy; if (unlikely(test_bit(RDS_MSG_PAGEVEC, &rm->m_flags))) return; spin_lock_irqsave(&rm->m_rs_lock, flags); znotifier = rm->data.op_mmp_znotifier; rm->data.op_mmp_znotifier = NULL; zcopy = !!znotifier; if (rm->m_rs) { struct rds_sock *rs = rm->m_rs; if (znotifier) { rds_rm_zerocopy_callback(rs, znotifier); rds_wake_sk_sleep(rs); } sock_put(rds_rs_to_sk(rs)); rm->m_rs = NULL; } else if (znotifier) { /* * Zerocopy can fail before the message is queued on the * socket, so there is no rs to carry the notification. */ mm_unaccount_pinned_pages(&znotifier->z_mmp); kfree(rds_info_from_znotifier(znotifier)); } spin_unlock_irqrestore(&rm->m_rs_lock, flags); for (i = 0; i < rm->data.op_nents; i++) { /* XXX will have to put_page for page refs */ if (!zcopy) __free_page(sg_page(&rm->data.op_sg[i])); else put_page(sg_page(&rm->data.op_sg[i])); } rm->data.op_nents = 0; if (rm->rdma.op_active) rds_rdma_free_op(&rm->rdma); if (rm->rdma.op_rdma_mr) kref_put(&rm->rdma.op_rdma_mr->r_kref, __rds_put_mr_final); if (rm->atomic.op_active) rds_atomic_free_op(&rm->atomic); if (rm->atomic.op_rdma_mr) kref_put(&rm->atomic.op_rdma_mr->r_kref, __rds_put_mr_final); } void rds_message_put(struct rds_message *rm) { rdsdebug("put rm %p ref %d\n", rm, refcount_read(&rm->m_refcount)); WARN(!refcount_read(&rm->m_refcount), "danger refcount zero on %p\n", rm); if (refcount_dec_and_test(&rm->m_refcount)) { BUG_ON(!list_empty(&rm->m_sock_item)); BUG_ON(!list_empty(&rm->m_conn_item)); rds_message_purge(rm); kfree(rm); } } EXPORT_SYMBOL_GPL(rds_message_put); void rds_message_populate_header(struct rds_header *hdr, __be16 sport, __be16 dport, u64 seq) { hdr->h_flags = 0; hdr->h_sport = sport; hdr->h_dport = dport; hdr->h_sequence = cpu_to_be64(seq); /* see rds_find_next_ext_space for reason why we memset the * ext header */ memset(hdr->h_exthdr, RDS_EXTHDR_NONE, RDS_HEADER_EXT_SPACE); } EXPORT_SYMBOL_GPL(rds_message_populate_header); /* * Find the next place we can add an RDS header extension with * specific length. Extension headers are pushed one after the * other. In the following, the number after the colon is the number * of bytes: * * [ type1:1 dta1:len1 [ type2:1 dta2:len2 ] ... ] RDS_EXTHDR_NONE * * If the extension headers fill the complete extension header space * (16 bytes), the trailing RDS_EXTHDR_NONE is omitted. */ static int rds_find_next_ext_space(struct rds_header *hdr, unsigned int len, u8 **ext_start) { unsigned int ext_len; unsigned int type; int ind = 0; while ((ind + 1 + len) <= RDS_HEADER_EXT_SPACE) { if (hdr->h_exthdr[ind] == RDS_EXTHDR_NONE) { *ext_start = hdr->h_exthdr + ind; return 0; } type = hdr->h_exthdr[ind]; ext_len = (type < __RDS_EXTHDR_MAX) ? rds_exthdr_size[type] : 0; WARN_ONCE(!ext_len, "Unknown ext hdr type %d\n", type); if (!ext_len) return -EINVAL; /* ind points to a valid ext hdr with known length */ ind += 1 + ext_len; } /* no room for extension */ return -ENOSPC; } /* The ext hdr space is prefilled with zero from the kzalloc() */ int rds_message_add_extension(struct rds_header *hdr, unsigned int type, const void *data) { unsigned char *dst; unsigned int len; len = (type < __RDS_EXTHDR_MAX) ? rds_exthdr_size[type] : 0; if (!len) return 0; if (rds_find_next_ext_space(hdr, len, &dst)) return 0; *dst++ = type; memcpy(dst, data, len); return 1; } EXPORT_SYMBOL_GPL(rds_message_add_extension); /* * If a message has extension headers, retrieve them here. * Call like this: * * unsigned int pos = 0; * * while (1) { * buflen = sizeof(buffer); * type = rds_message_next_extension(hdr, &pos, buffer, &buflen); * if (type == RDS_EXTHDR_NONE) * break; * ... * } */ int rds_message_next_extension(struct rds_header *hdr, unsigned int *pos, void *buf, unsigned int *buflen) { unsigned int offset, ext_type, ext_len; u8 *src = hdr->h_exthdr; offset = *pos; if (offset >= RDS_HEADER_EXT_SPACE) goto none; /* Get the extension type and length. For now, the * length is implied by the extension type. */ ext_type = src[offset++]; if (ext_type == RDS_EXTHDR_NONE || ext_type >= __RDS_EXTHDR_MAX) goto none; ext_len = rds_exthdr_size[ext_type]; if (offset + ext_len > RDS_HEADER_EXT_SPACE) goto none; *pos = offset + ext_len; if (ext_len < *buflen) *buflen = ext_len; memcpy(buf, src + offset, *buflen); return ext_type; none: *pos = RDS_HEADER_EXT_SPACE; *buflen = 0; return RDS_EXTHDR_NONE; } int rds_message_add_rdma_dest_extension(struct rds_header *hdr, u32 r_key, u32 offset) { struct rds_ext_header_rdma_dest ext_hdr; ext_hdr.h_rdma_rkey = cpu_to_be32(r_key); ext_hdr.h_rdma_offset = cpu_to_be32(offset); return rds_message_add_extension(hdr, RDS_EXTHDR_RDMA_DEST, &ext_hdr); } EXPORT_SYMBOL_GPL(rds_message_add_rdma_dest_extension); /* * Each rds_message is allocated with extra space for the scatterlist entries * rds ops will need. This is to minimize memory allocation count. Then, each rds op * can grab SGs when initializing its part of the rds_message. */ struct rds_message *rds_message_alloc(unsigned int extra_len, gfp_t gfp) { struct rds_message *rm; if (extra_len > KMALLOC_MAX_SIZE - sizeof(struct rds_message)) return NULL; rm = kzalloc(sizeof(struct rds_message) + extra_len, gfp); if (!rm) goto out; rm->m_used_sgs = 0; rm->m_total_sgs = extra_len / sizeof(struct scatterlist); refcount_set(&rm->m_refcount, 1); INIT_LIST_HEAD(&rm->m_sock_item); INIT_LIST_HEAD(&rm->m_conn_item); spin_lock_init(&rm->m_rs_lock); init_waitqueue_head(&rm->m_flush_wait); out: return rm; } /* * RDS ops use this to grab SG entries from the rm's sg pool. */ struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents) { struct scatterlist *sg_first = (struct scatterlist *) &rm[1]; struct scatterlist *sg_ret; if (nents <= 0) { pr_warn("rds: alloc sgs failed! nents <= 0\n"); return ERR_PTR(-EINVAL); } if (rm->m_used_sgs + nents > rm->m_total_sgs) { pr_warn("rds: alloc sgs failed! total %d used %d nents %d\n", rm->m_total_sgs, rm->m_used_sgs, nents); return ERR_PTR(-ENOMEM); } sg_ret = &sg_first[rm->m_used_sgs]; sg_init_table(sg_ret, nents); rm->m_used_sgs += nents; return sg_ret; } struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len) { struct rds_message *rm; unsigned int i; int num_sgs = DIV_ROUND_UP(total_len, PAGE_SIZE); int extra_bytes = num_sgs * sizeof(struct scatterlist); rm = rds_message_alloc(extra_bytes, GFP_NOWAIT); if (!rm) return ERR_PTR(-ENOMEM); set_bit(RDS_MSG_PAGEVEC, &rm->m_flags); rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len); rm->data.op_nents = DIV_ROUND_UP(total_len, PAGE_SIZE); rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); if (IS_ERR(rm->data.op_sg)) { void *err = ERR_CAST(rm->data.op_sg); rds_message_put(rm); return err; } for (i = 0; i < rm->data.op_nents; ++i) { sg_set_page(&rm->data.op_sg[i], virt_to_page((void *)page_addrs[i]), PAGE_SIZE, 0); } return rm; } static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter *from) { struct scatterlist *sg; int ret = 0; int length = iov_iter_count(from); struct rds_msg_zcopy_info *info; rm->m_inc.i_hdr.h_len = cpu_to_be32(iov_iter_count(from)); /* * now allocate and copy in the data payload. */ sg = rm->data.op_sg; info = kzalloc_obj(*info); if (!info) return -ENOMEM; INIT_LIST_HEAD(&info->rs_zcookie_next); rm->data.op_mmp_znotifier = &info->znotif; if (mm_account_pinned_pages(&rm->data.op_mmp_znotifier->z_mmp, length)) { ret = -ENOMEM; goto err; } while (iov_iter_count(from)) { struct page *pages; size_t start; ssize_t copied; copied = iov_iter_get_pages2(from, &pages, PAGE_SIZE, 1, &start); if (copied < 0) { struct mmpin *mmp; int i; for (i = 0; i < rm->data.op_nents; i++) put_page(sg_page(&rm->data.op_sg[i])); rm->data.op_nents = 0; mmp = &rm->data.op_mmp_znotifier->z_mmp; mm_unaccount_pinned_pages(mmp); ret = -EFAULT; goto err; } length -= copied; sg_set_page(sg, pages, copied, start); rm->data.op_nents++; sg++; } WARN_ON_ONCE(length != 0); return ret; err: kfree(info); rm->data.op_mmp_znotifier = NULL; return ret; } int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from, bool zcopy) { unsigned long to_copy, nbytes; unsigned long sg_off; struct scatterlist *sg; int ret = 0; rm->m_inc.i_hdr.h_len = cpu_to_be32(iov_iter_count(from)); /* now allocate and copy in the data payload. */ sg = rm->data.op_sg; sg_off = 0; /* Dear gcc, sg->page will be null from kzalloc. */ if (zcopy) return rds_message_zcopy_from_user(rm, from); while (iov_iter_count(from)) { if (!sg_page(sg)) { ret = rds_page_remainder_alloc(sg, iov_iter_count(from), GFP_HIGHUSER); if (ret) return ret; rm->data.op_nents++; sg_off = 0; } to_copy = min_t(unsigned long, iov_iter_count(from), sg->length - sg_off); rds_stats_add(s_copy_from_user, to_copy); nbytes = copy_page_from_iter(sg_page(sg), sg->offset + sg_off, to_copy, from); if (nbytes != to_copy) return -EFAULT; sg_off += to_copy; if (sg_off == sg->length) sg++; } return ret; } int rds_message_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to) { struct rds_message *rm; struct scatterlist *sg; unsigned long to_copy; unsigned long vec_off; int copied; int ret; u32 len; rm = container_of(inc, struct rds_message, m_inc); len = be32_to_cpu(rm->m_inc.i_hdr.h_len); sg = rm->data.op_sg; vec_off = 0; copied = 0; while (iov_iter_count(to) && copied < len) { to_copy = min_t(unsigned long, iov_iter_count(to), sg->length - vec_off); to_copy = min_t(unsigned long, to_copy, len - copied); rds_stats_add(s_copy_to_user, to_copy); ret = copy_page_to_iter(sg_page(sg), sg->offset + vec_off, to_copy, to); if (ret != to_copy) return -EFAULT; vec_off += to_copy; copied += to_copy; if (vec_off == sg->length) { vec_off = 0; sg++; } } return copied; } /* * If the message is still on the send queue, wait until the transport * is done with it. This is particularly important for RDMA operations. */ void rds_message_wait(struct rds_message *rm) { wait_event_interruptible(rm->m_flush_wait, !test_bit(RDS_MSG_MAPPED, &rm->m_flags)); } void rds_message_unmapped(struct rds_message *rm) { clear_bit(RDS_MSG_MAPPED, &rm->m_flags); wake_up_interruptible(&rm->m_flush_wait); } EXPORT_SYMBOL_GPL(rds_message_unmapped); |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * * This code builds two trees of free clusters extents. * Trees are sorted by start of extent and by length of extent. * NTFS_MAX_WND_EXTENTS defines the maximum number of elements in trees. * In extreme case code reads on-disk bitmap to find free clusters. * */ #include <linux/buffer_head.h> #include <linux/fs.h> #include <linux/kernel.h> #include "ntfs.h" #include "ntfs_fs.h" /* * Maximum number of extents in tree. */ #define NTFS_MAX_WND_EXTENTS (32u * 1024u) struct rb_node_key { struct rb_node node; size_t key; }; struct e_node { struct rb_node_key start; /* Tree sorted by start. */ struct rb_node_key count; /* Tree sorted by len. */ }; static int wnd_rescan(struct wnd_bitmap *wnd); static struct buffer_head *wnd_map(struct wnd_bitmap *wnd, size_t iw); static bool wnd_is_free_hlp(struct wnd_bitmap *wnd, size_t bit, size_t bits); static struct kmem_cache *ntfs_enode_cachep; int __init ntfs3_init_bitmap(void) { ntfs_enode_cachep = kmem_cache_create("ntfs3_enode_cache", sizeof(struct e_node), 0, SLAB_RECLAIM_ACCOUNT, NULL); return ntfs_enode_cachep ? 0 : -ENOMEM; } void ntfs3_exit_bitmap(void) { kmem_cache_destroy(ntfs_enode_cachep); } /* * wnd_scan * * b_pos + b_len - biggest fragment. * Scan range [wpos wbits) window @buf. * * Return: -1 if not found. */ static size_t wnd_scan(const void *buf, size_t wbit, u32 wpos, u32 wend, size_t to_alloc, size_t *prev_tail, size_t *b_pos, size_t *b_len) { while (wpos < wend) { size_t free_len; u32 free_bits, end; u32 used = find_next_zero_bit_le(buf, wend, wpos); if (used >= wend) { if (*b_len < *prev_tail) { *b_pos = wbit - *prev_tail; *b_len = *prev_tail; } *prev_tail = 0; return -1; } if (used > wpos) { wpos = used; if (*b_len < *prev_tail) { *b_pos = wbit - *prev_tail; *b_len = *prev_tail; } *prev_tail = 0; } /* * Now we have a fragment [wpos, wend) staring with 0. */ end = wpos + to_alloc - *prev_tail; free_bits = find_next_bit_le(buf, min(end, wend), wpos); free_len = *prev_tail + free_bits - wpos; if (*b_len < free_len) { *b_pos = wbit + wpos - *prev_tail; *b_len = free_len; } if (free_len >= to_alloc) return wbit + wpos - *prev_tail; if (free_bits >= wend) { *prev_tail += free_bits - wpos; return -1; } wpos = free_bits + 1; *prev_tail = 0; } return -1; } /* * wnd_close - Frees all resources. */ void wnd_close(struct wnd_bitmap *wnd) { struct rb_node *node, *next; kvfree(wnd->free_bits); wnd->free_bits = NULL; run_close(&wnd->run); node = rb_first(&wnd->start_tree); while (node) { next = rb_next(node); rb_erase(node, &wnd->start_tree); kmem_cache_free(ntfs_enode_cachep, rb_entry(node, struct e_node, start.node)); node = next; } } static struct rb_node *rb_lookup(struct rb_root *root, size_t v) { struct rb_node **p = &root->rb_node; struct rb_node *r = NULL; while (*p) { struct rb_node_key *k; k = rb_entry(*p, struct rb_node_key, node); if (v < k->key) { p = &(*p)->rb_left; } else if (v > k->key) { r = &k->node; p = &(*p)->rb_right; } else { return &k->node; } } return r; } /* * rb_insert_count - Helper function to insert special kind of 'count' tree. */ static inline bool rb_insert_count(struct rb_root *root, struct e_node *e) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; size_t e_ckey = e->count.key; size_t e_skey = e->start.key; while (*p) { struct e_node *k = rb_entry(parent = *p, struct e_node, count.node); if (e_ckey > k->count.key) { p = &(*p)->rb_left; } else if (e_ckey < k->count.key) { p = &(*p)->rb_right; } else if (e_skey < k->start.key) { p = &(*p)->rb_left; } else if (e_skey > k->start.key) { p = &(*p)->rb_right; } else { WARN_ON(1); return false; } } rb_link_node(&e->count.node, parent, p); rb_insert_color(&e->count.node, root); return true; } /* * rb_insert_start - Helper function to insert special kind of 'count' tree. */ static inline bool rb_insert_start(struct rb_root *root, struct e_node *e) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; size_t e_skey = e->start.key; while (*p) { struct e_node *k; parent = *p; k = rb_entry(parent, struct e_node, start.node); if (e_skey < k->start.key) { p = &(*p)->rb_left; } else if (e_skey > k->start.key) { p = &(*p)->rb_right; } else { WARN_ON(1); return false; } } rb_link_node(&e->start.node, parent, p); rb_insert_color(&e->start.node, root); return true; } /* * wnd_add_free_ext - Adds a new extent of free space. * @build: 1 when building tree. */ static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len, bool build) { struct e_node *e, *e0 = NULL; size_t ib, end_in = bit + len; struct rb_node *n; if (build) { /* Use extent_min to filter too short extents. */ if (wnd->count >= NTFS_MAX_WND_EXTENTS && len <= wnd->extent_min) { wnd->uptodated = -1; return; } } else { /* Try to find extent before 'bit'. */ n = rb_lookup(&wnd->start_tree, bit); if (!n) { n = rb_first(&wnd->start_tree); } else { e = rb_entry(n, struct e_node, start.node); n = rb_next(n); if (e->start.key + e->count.key == bit) { /* Remove left. */ bit = e->start.key; len += e->count.key; rb_erase(&e->start.node, &wnd->start_tree); rb_erase(&e->count.node, &wnd->count_tree); wnd->count -= 1; e0 = e; } } while (n) { size_t next_end; e = rb_entry(n, struct e_node, start.node); next_end = e->start.key + e->count.key; if (e->start.key > end_in) break; /* Remove right. */ n = rb_next(n); len += next_end - end_in; end_in = next_end; rb_erase(&e->start.node, &wnd->start_tree); rb_erase(&e->count.node, &wnd->count_tree); wnd->count -= 1; if (!e0) e0 = e; else kmem_cache_free(ntfs_enode_cachep, e); } if (wnd->uptodated != 1) { /* Check bits before 'bit'. */ ib = wnd->zone_bit == wnd->zone_end || bit < wnd->zone_end ? 0 : wnd->zone_end; while (bit > ib && wnd_is_free_hlp(wnd, bit - 1, 1)) { bit -= 1; len += 1; } /* Check bits after 'end_in'. */ ib = wnd->zone_bit == wnd->zone_end || end_in > wnd->zone_bit ? wnd->nbits : wnd->zone_bit; while (end_in < ib && wnd_is_free_hlp(wnd, end_in, 1)) { end_in += 1; len += 1; } } } /* Insert new fragment. */ if (wnd->count >= NTFS_MAX_WND_EXTENTS) { if (e0) kmem_cache_free(ntfs_enode_cachep, e0); wnd->uptodated = -1; /* Compare with smallest fragment. */ n = rb_last(&wnd->count_tree); e = rb_entry(n, struct e_node, count.node); if (len <= e->count.key) goto out; /* Do not insert small fragments. */ if (build) { struct e_node *e2; n = rb_prev(n); e2 = rb_entry(n, struct e_node, count.node); /* Smallest fragment will be 'e2->count.key'. */ wnd->extent_min = e2->count.key; } /* Replace smallest fragment by new one. */ rb_erase(&e->start.node, &wnd->start_tree); rb_erase(&e->count.node, &wnd->count_tree); wnd->count -= 1; } else { e = e0 ? e0 : kmem_cache_alloc(ntfs_enode_cachep, GFP_ATOMIC); if (!e) { wnd->uptodated = -1; goto out; } if (build && len <= wnd->extent_min) wnd->extent_min = len; } e->start.key = bit; e->count.key = len; if (len > wnd->extent_max) wnd->extent_max = len; rb_insert_start(&wnd->start_tree, e); rb_insert_count(&wnd->count_tree, e); wnd->count += 1; out:; } /* * wnd_remove_free_ext - Remove a run from the cached free space. */ static void wnd_remove_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len) { struct rb_node *n, *n3; struct e_node *e, *e3; size_t end_in = bit + len; size_t end3, end, new_key, new_len, max_new_len; /* Try to find extent before 'bit'. */ n = rb_lookup(&wnd->start_tree, bit); if (!n) return; e = rb_entry(n, struct e_node, start.node); end = e->start.key + e->count.key; new_key = new_len = 0; len = e->count.key; /* Range [bit,end_in) must be inside 'e' or outside 'e' and 'n'. */ if (e->start.key > bit) ; else if (end_in <= end) { /* Range [bit,end_in) inside 'e'. */ new_key = end_in; new_len = end - end_in; len = bit - e->start.key; } else if (bit > end) { bool bmax = false; n3 = rb_next(n); while (n3) { e3 = rb_entry(n3, struct e_node, start.node); if (e3->start.key >= end_in) break; if (e3->count.key == wnd->extent_max) bmax = true; end3 = e3->start.key + e3->count.key; if (end3 > end_in) { e3->start.key = end_in; rb_erase(&e3->count.node, &wnd->count_tree); e3->count.key = end3 - end_in; rb_insert_count(&wnd->count_tree, e3); break; } n3 = rb_next(n3); rb_erase(&e3->start.node, &wnd->start_tree); rb_erase(&e3->count.node, &wnd->count_tree); wnd->count -= 1; kmem_cache_free(ntfs_enode_cachep, e3); } if (!bmax) return; n3 = rb_first(&wnd->count_tree); wnd->extent_max = n3 ? rb_entry(n3, struct e_node, count.node)->count.key : 0; return; } if (e->count.key != wnd->extent_max) { ; } else if (rb_prev(&e->count.node)) { ; } else { n3 = rb_next(&e->count.node); max_new_len = max(len, new_len); if (!n3) { wnd->extent_max = max_new_len; } else { e3 = rb_entry(n3, struct e_node, count.node); wnd->extent_max = max(e3->count.key, max_new_len); } } if (!len) { if (new_len) { e->start.key = new_key; rb_erase(&e->count.node, &wnd->count_tree); e->count.key = new_len; rb_insert_count(&wnd->count_tree, e); } else { rb_erase(&e->start.node, &wnd->start_tree); rb_erase(&e->count.node, &wnd->count_tree); wnd->count -= 1; kmem_cache_free(ntfs_enode_cachep, e); } goto out; } rb_erase(&e->count.node, &wnd->count_tree); e->count.key = len; rb_insert_count(&wnd->count_tree, e); if (!new_len) goto out; if (wnd->count >= NTFS_MAX_WND_EXTENTS) { wnd->uptodated = -1; /* Get minimal extent. */ e = rb_entry(rb_last(&wnd->count_tree), struct e_node, count.node); if (e->count.key > new_len) goto out; /* Replace minimum. */ rb_erase(&e->start.node, &wnd->start_tree); rb_erase(&e->count.node, &wnd->count_tree); wnd->count -= 1; } else { e = kmem_cache_alloc(ntfs_enode_cachep, GFP_ATOMIC); if (!e) wnd->uptodated = -1; } if (e) { e->start.key = new_key; e->count.key = new_len; rb_insert_start(&wnd->start_tree, e); rb_insert_count(&wnd->count_tree, e); wnd->count += 1; } out: if (!wnd->count && 1 != wnd->uptodated) wnd_rescan(wnd); } /* * wnd_rescan - Scan all bitmap. Used while initialization. */ static int wnd_rescan(struct wnd_bitmap *wnd) { int err = 0; size_t prev_tail = 0; struct super_block *sb = wnd->sb; struct ntfs_sb_info *sbi = sb->s_fs_info; u64 lbo, len = 0; u32 blocksize = sb->s_blocksize; u8 cluster_bits = sbi->cluster_bits; u32 wbits = 8 * sb->s_blocksize; u32 used, frb; size_t wpos, wbit, iw, vbo; struct buffer_head *bh = NULL; CLST lcn, clen; struct file_ra_state *ra; struct address_space *mapping = sb->s_bdev->bd_mapping; wnd->uptodated = 0; wnd->extent_max = 0; wnd->extent_min = MINUS_ONE_T; wnd->total_zeroes = 0; vbo = 0; /* Allocate in memory instead of stack. Not critical if failed. */ ra = kzalloc_obj(*ra, GFP_NOFS); if (ra) { file_ra_state_init(ra, mapping); ra->ra_pages = (wnd->nbits / 8 + PAGE_SIZE - 1) >> PAGE_SHIFT; } for (iw = 0; iw < wnd->nwnd; iw++) { if (iw + 1 == wnd->nwnd) wbits = wnd->bits_last; if (wnd->inited) { if (!wnd->free_bits[iw]) { /* All ones. */ if (prev_tail) { wnd_add_free_ext(wnd, vbo * 8 - prev_tail, prev_tail, true); prev_tail = 0; } goto next_wnd; } if (wbits == wnd->free_bits[iw]) { /* All zeroes. */ prev_tail += wbits; wnd->total_zeroes += wbits; goto next_wnd; } } if (!len) { u32 off = vbo & sbi->cluster_mask; if (!run_lookup_entry(&wnd->run, vbo >> cluster_bits, &lcn, &clen, NULL)) { err = -ENOENT; goto out; } lbo = ((u64)lcn << cluster_bits) + off; len = ((u64)clen << cluster_bits) - off; } if (ra) { pgoff_t idx = lbo >> PAGE_SHIFT; if (!ra_has_index(ra, idx)) page_cache_sync_readahead(mapping, ra, NULL, idx, 1); } bh = ntfs_bread(sb, lbo >> sb->s_blocksize_bits); if (!bh) { err = -EIO; goto out; } used = ntfs_bitmap_weight_le(bh->b_data, wbits); if (used < wbits) { frb = wbits - used; wnd->free_bits[iw] = frb; wnd->total_zeroes += frb; } wpos = 0; wbit = vbo * 8; if (wbit + wbits > wnd->nbits) wbits = wnd->nbits - wbit; do { used = find_next_zero_bit_le(bh->b_data, wbits, wpos); if (used > wpos && prev_tail) { wnd_add_free_ext(wnd, wbit + wpos - prev_tail, prev_tail, true); prev_tail = 0; } wpos = used; if (wpos >= wbits) { /* No free blocks. */ prev_tail = 0; break; } frb = find_next_bit_le(bh->b_data, wbits, wpos); if (frb >= wbits) { /* Keep last free block. */ prev_tail += frb - wpos; break; } wnd_add_free_ext(wnd, wbit + wpos - prev_tail, frb + prev_tail - wpos, true); /* Skip free block and first '1'. */ wpos = frb + 1; /* Reset previous tail. */ prev_tail = 0; } while (wpos < wbits); next_wnd: if (bh) put_bh(bh); bh = NULL; vbo += blocksize; if (len) { len -= blocksize; lbo += blocksize; } } /* Add last block. */ if (prev_tail) wnd_add_free_ext(wnd, wnd->nbits - prev_tail, prev_tail, true); /* * Before init cycle wnd->uptodated was 0. * If any errors or limits occurs while initialization then * wnd->uptodated will be -1. * If 'uptodated' is still 0 then Tree is really updated. */ if (!wnd->uptodated) wnd->uptodated = 1; if (wnd->zone_bit != wnd->zone_end) { size_t zlen = wnd->zone_end - wnd->zone_bit; wnd->zone_end = wnd->zone_bit; wnd_zone_set(wnd, wnd->zone_bit, zlen); } out: kfree(ra); return err; } int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits) { int err; u32 blocksize = sb->s_blocksize; u32 wbits = blocksize * 8; init_rwsem(&wnd->rw_lock); wnd->sb = sb; wnd->nbits = nbits; wnd->total_zeroes = nbits; wnd->extent_max = MINUS_ONE_T; wnd->zone_bit = wnd->zone_end = 0; wnd->nwnd = bytes_to_block(sb, ntfs3_bitmap_size(nbits)); wnd->bits_last = nbits & (wbits - 1); if (!wnd->bits_last) wnd->bits_last = wbits; wnd->free_bits = kvmalloc_array(wnd->nwnd, sizeof(u16), GFP_KERNEL | __GFP_ZERO); if (!wnd->free_bits) return -ENOMEM; err = wnd_rescan(wnd); if (err) return err; wnd->inited = true; return 0; } /* * wnd_map - Call sb_bread for requested window. */ static struct buffer_head *wnd_map(struct wnd_bitmap *wnd, size_t iw) { size_t vbo; CLST lcn, clen; struct super_block *sb = wnd->sb; struct ntfs_sb_info *sbi; struct buffer_head *bh; u64 lbo; sbi = sb->s_fs_info; vbo = (u64)iw << sb->s_blocksize_bits; if (!run_lookup_entry(&wnd->run, vbo >> sbi->cluster_bits, &lcn, &clen, NULL)) { return ERR_PTR(-ENOENT); } lbo = ((u64)lcn << sbi->cluster_bits) + (vbo & sbi->cluster_mask); bh = ntfs_bread(wnd->sb, lbo >> sb->s_blocksize_bits); if (!bh) return ERR_PTR(-EIO); return bh; } /* * wnd_set_free - Mark the bits range from bit to bit + bits as free. */ int wnd_set_free(struct wnd_bitmap *wnd, size_t bit, size_t bits) { int err = 0; struct super_block *sb = wnd->sb; u32 wbits = 8 * sb->s_blocksize; size_t iw = bit >> (sb->s_blocksize_bits + 3); u32 wbit = bit & (wbits - 1); struct buffer_head *bh; u32 op; for (; iw < wnd->nwnd && bits; iw++, bit += op, bits -= op, wbit = 0) { if (iw + 1 == wnd->nwnd) wbits = wnd->bits_last; op = min_t(u32, wbits - wbit, bits); bh = wnd_map(wnd, iw); if (IS_ERR(bh)) { err = PTR_ERR(bh); break; } lock_buffer(bh); ntfs_bitmap_clear_le(bh->b_data, wbit, op); wnd->free_bits[iw] += op; wnd->total_zeroes += op; set_buffer_uptodate(bh); mark_buffer_dirty(bh); unlock_buffer(bh); put_bh(bh); wnd_add_free_ext(wnd, bit, op, false); } return err; } /* * wnd_set_used - Mark the bits range from bit to bit + bits as used. */ int wnd_set_used(struct wnd_bitmap *wnd, size_t bit, size_t bits) { int err = 0; struct super_block *sb = wnd->sb; size_t iw = bit >> (sb->s_blocksize_bits + 3); u32 wbits = 8 * sb->s_blocksize; u32 wbit = bit & (wbits - 1); struct buffer_head *bh; u32 op; for (; iw < wnd->nwnd && bits; iw++, bit += op, bits -= op, wbit = 0) { if (unlikely(iw + 1 == wnd->nwnd)) wbits = wnd->bits_last; op = min_t(u32, wbits - wbit, bits); bh = wnd_map(wnd, iw); if (IS_ERR(bh)) { err = PTR_ERR(bh); break; } lock_buffer(bh); ntfs_bitmap_set_le(bh->b_data, wbit, op); wnd->free_bits[iw] -= op; wnd->total_zeroes -= op; set_buffer_uptodate(bh); mark_buffer_dirty(bh); unlock_buffer(bh); put_bh(bh); if (!RB_EMPTY_ROOT(&wnd->start_tree)) wnd_remove_free_ext(wnd, bit, op); } return err; } /* * wnd_set_used_safe - Mark the bits range from bit to bit + bits as used. * * Unlikely wnd_set_used/wnd_set_free this function is not full trusted. * It scans every bit in bitmap and marks free bit as used. * @done - how many bits were marked as used. * * NOTE: normally *done should be 0. */ int wnd_set_used_safe(struct wnd_bitmap *wnd, size_t bit, size_t bits, size_t *done) { size_t i, from = 0, len = 0; int err = 0; *done = 0; for (i = 0; i < bits; i++) { if (wnd_is_free(wnd, bit + i, 1)) { if (!len) from = bit + i; len += 1; } else if (len) { err = wnd_set_used(wnd, from, len); *done += len; len = 0; if (err) break; } } if (len) { /* last fragment. */ err = wnd_set_used(wnd, from, len); *done += len; } return err; } /* * wnd_is_free_hlp * * Return: True if all clusters [bit, bit+bits) are free (bitmap only). */ static bool wnd_is_free_hlp(struct wnd_bitmap *wnd, size_t bit, size_t bits) { struct super_block *sb = wnd->sb; size_t iw = bit >> (sb->s_blocksize_bits + 3); u32 wbits = 8 * sb->s_blocksize; u32 wbit = bit & (wbits - 1); u32 op; for (; iw < wnd->nwnd && bits; iw++, bits -= op, wbit = 0) { if (unlikely(iw + 1 == wnd->nwnd)) wbits = wnd->bits_last; op = min_t(u32, wbits - wbit, bits); if (wbits != wnd->free_bits[iw]) { bool ret; struct buffer_head *bh = wnd_map(wnd, iw); if (IS_ERR(bh)) return false; ret = are_bits_clear(bh->b_data, wbit, op); put_bh(bh); if (!ret) return false; } } return true; } /* * wnd_is_free * * Return: True if all clusters [bit, bit+bits) are free. */ bool wnd_is_free(struct wnd_bitmap *wnd, size_t bit, size_t bits) { bool ret; struct rb_node *n; size_t end; struct e_node *e; if (RB_EMPTY_ROOT(&wnd->start_tree)) goto use_wnd; n = rb_lookup(&wnd->start_tree, bit); if (!n) goto use_wnd; e = rb_entry(n, struct e_node, start.node); end = e->start.key + e->count.key; if (bit < end && bit + bits <= end) return true; use_wnd: ret = wnd_is_free_hlp(wnd, bit, bits); return ret; } /* * wnd_is_used * * Return: True if all clusters [bit, bit+bits) are used. */ bool wnd_is_used(struct wnd_bitmap *wnd, size_t bit, size_t bits) { bool ret = false; struct super_block *sb = wnd->sb; size_t iw = bit >> (sb->s_blocksize_bits + 3); u32 wbits = 8 * sb->s_blocksize; u32 wbit = bit & (wbits - 1); u32 op; size_t end; struct rb_node *n; struct e_node *e; if (RB_EMPTY_ROOT(&wnd->start_tree)) goto use_wnd; end = bit + bits; n = rb_lookup(&wnd->start_tree, end - 1); if (!n) goto use_wnd; e = rb_entry(n, struct e_node, start.node); if (e->start.key + e->count.key > bit) return false; use_wnd: for (; iw < wnd->nwnd && bits; iw++, bits -= op, wbit = 0) { if (unlikely(iw + 1 == wnd->nwnd)) wbits = wnd->bits_last; op = min_t(u32, wbits - wbit, bits); if (wnd->free_bits[iw]) { bool ret; struct buffer_head *bh = wnd_map(wnd, iw); if (IS_ERR(bh)) goto out; ret = are_bits_set(bh->b_data, wbit, op); put_bh(bh); if (!ret) goto out; } } ret = true; out: return ret; } /* * wnd_find - Look for free space. * * - flags - BITMAP_FIND_XXX flags * * Return: 0 if not found. */ size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint, size_t flags, size_t *allocated) { struct super_block *sb; u32 wbits, wpos, wzbit, wzend; size_t fnd, max_alloc, b_len, b_pos; size_t iw, prev_tail, nwnd, wbit, ebit, zbit, zend; size_t to_alloc0 = to_alloc; const struct e_node *e; const struct rb_node *pr, *cr; u8 log2_bits; bool fbits_valid; struct buffer_head *bh; /* Fast checking for available free space. */ if (flags & BITMAP_FIND_FULL) { size_t zeroes = wnd_zeroes(wnd); zeroes -= wnd->zone_end - wnd->zone_bit; if (zeroes < to_alloc0) goto no_space; if (to_alloc0 > wnd->extent_max) goto no_space; } else { if (to_alloc > wnd->extent_max) to_alloc = wnd->extent_max; } if (wnd->zone_bit <= hint && hint < wnd->zone_end) hint = wnd->zone_end; max_alloc = wnd->nbits; b_len = b_pos = 0; if (hint >= max_alloc) hint = 0; if (RB_EMPTY_ROOT(&wnd->start_tree)) { if (wnd->uptodated == 1) { /* Extents tree is updated -> No free space. */ goto no_space; } goto scan_bitmap; } e = NULL; if (!hint) goto allocate_biggest; /* Use hint: Enumerate extents by start >= hint. */ pr = NULL; cr = wnd->start_tree.rb_node; for (;;) { e = rb_entry(cr, struct e_node, start.node); if (e->start.key == hint) break; if (e->start.key < hint) { pr = cr; cr = cr->rb_right; if (!cr) break; continue; } cr = cr->rb_left; if (!cr) { e = pr ? rb_entry(pr, struct e_node, start.node) : NULL; break; } } if (!e) goto allocate_biggest; if (e->start.key + e->count.key > hint) { /* We have found extension with 'hint' inside. */ size_t len = e->start.key + e->count.key - hint; if (len >= to_alloc && hint + to_alloc <= max_alloc) { fnd = hint; goto found; } if (!(flags & BITMAP_FIND_FULL)) { if (len > to_alloc) len = to_alloc; if (hint + len <= max_alloc) { fnd = hint; to_alloc = len; goto found; } } } allocate_biggest: /* Allocate from biggest free extent. */ e = rb_entry(rb_first(&wnd->count_tree), struct e_node, count.node); if (e->count.key != wnd->extent_max) wnd->extent_max = e->count.key; if (e->count.key < max_alloc) { if (e->count.key >= to_alloc) { ; } else if (flags & BITMAP_FIND_FULL) { if (e->count.key < to_alloc0) { /* Biggest free block is less then requested. */ goto no_space; } to_alloc = e->count.key; } else if (-1 != wnd->uptodated) { to_alloc = e->count.key; } else { /* Check if we can use more bits. */ size_t op, max_check; struct rb_root start_tree; memcpy(&start_tree, &wnd->start_tree, sizeof(struct rb_root)); memset(&wnd->start_tree, 0, sizeof(struct rb_root)); max_check = e->start.key + to_alloc; if (max_check > max_alloc) max_check = max_alloc; for (op = e->start.key + e->count.key; op < max_check; op++) { if (!wnd_is_free(wnd, op, 1)) break; } memcpy(&wnd->start_tree, &start_tree, sizeof(struct rb_root)); to_alloc = op - e->start.key; } /* Prepare to return. */ fnd = e->start.key; if (e->start.key + to_alloc > max_alloc) to_alloc = max_alloc - e->start.key; goto found; } if (wnd->uptodated == 1) { /* Extents tree is updated -> no free space. */ goto no_space; } b_len = e->count.key; b_pos = e->start.key; scan_bitmap: sb = wnd->sb; log2_bits = sb->s_blocksize_bits + 3; /* At most two ranges [hint, max_alloc) + [0, hint). */ Again: /* TODO: Optimize request for case nbits > wbits. */ iw = hint >> log2_bits; wbits = sb->s_blocksize * 8; wpos = hint & (wbits - 1); prev_tail = 0; fbits_valid = true; if (max_alloc == wnd->nbits) { nwnd = wnd->nwnd; } else { size_t t = max_alloc + wbits - 1; nwnd = likely(t > max_alloc) ? (t >> log2_bits) : wnd->nwnd; } /* Enumerate all windows. */ for (; iw < nwnd; iw++) { wbit = iw << log2_bits; if (!wnd->free_bits[iw]) { if (prev_tail > b_len) { b_pos = wbit - prev_tail; b_len = prev_tail; } /* Skip full used window. */ prev_tail = 0; wpos = 0; continue; } if (unlikely(iw + 1 == nwnd)) { if (max_alloc == wnd->nbits) { wbits = wnd->bits_last; } else { size_t t = max_alloc & (wbits - 1); if (t) { wbits = t; fbits_valid = false; } } } if (wnd->zone_end > wnd->zone_bit) { ebit = wbit + wbits; zbit = max(wnd->zone_bit, wbit); zend = min(wnd->zone_end, ebit); /* Here we have a window [wbit, ebit) and zone [zbit, zend). */ if (zend <= zbit) { /* Zone does not overlap window. */ } else { wzbit = zbit - wbit; wzend = zend - wbit; /* Zone overlaps window. */ if (wnd->free_bits[iw] == wzend - wzbit) { prev_tail = 0; wpos = 0; continue; } /* Scan two ranges window: [wbit, zbit) and [zend, ebit). */ bh = wnd_map(wnd, iw); if (IS_ERR(bh)) { /* TODO: Error */ prev_tail = 0; wpos = 0; continue; } /* Scan range [wbit, zbit). */ if (wpos < wzbit) { /* Scan range [wpos, zbit). */ fnd = wnd_scan(bh->b_data, wbit, wpos, wzbit, to_alloc, &prev_tail, &b_pos, &b_len); if (fnd != MINUS_ONE_T) { put_bh(bh); goto found; } } prev_tail = 0; /* Scan range [zend, ebit). */ if (wzend < wbits) { fnd = wnd_scan(bh->b_data, wbit, max(wzend, wpos), wbits, to_alloc, &prev_tail, &b_pos, &b_len); if (fnd != MINUS_ONE_T) { put_bh(bh); goto found; } } wpos = 0; put_bh(bh); continue; } } /* Current window does not overlap zone. */ if (!wpos && fbits_valid && wnd->free_bits[iw] == wbits) { /* Window is empty. */ if (prev_tail + wbits >= to_alloc) { fnd = wbit + wpos - prev_tail; goto found; } /* Increase 'prev_tail' and process next window. */ prev_tail += wbits; wpos = 0; continue; } /* Read window. */ bh = wnd_map(wnd, iw); if (IS_ERR(bh)) { // TODO: Error. prev_tail = 0; wpos = 0; continue; } /* Scan range [wpos, eBits). */ fnd = wnd_scan(bh->b_data, wbit, wpos, wbits, to_alloc, &prev_tail, &b_pos, &b_len); put_bh(bh); if (fnd != MINUS_ONE_T) goto found; } if (b_len < prev_tail) { /* The last fragment. */ b_len = prev_tail; b_pos = max_alloc - prev_tail; } if (hint) { /* * We have scanned range [hint max_alloc). * Prepare to scan range [0 hint + to_alloc). */ size_t nextmax = hint + to_alloc; if (likely(nextmax >= hint) && nextmax < max_alloc) max_alloc = nextmax; hint = 0; goto Again; } if (!b_len) goto no_space; wnd->extent_max = b_len; if (flags & BITMAP_FIND_FULL) goto no_space; fnd = b_pos; to_alloc = b_len; found: if (flags & BITMAP_FIND_MARK_AS_USED) { /* TODO: Optimize remove extent (pass 'e'?). */ if (wnd_set_used(wnd, fnd, to_alloc)) goto no_space; } else if (wnd->extent_max != MINUS_ONE_T && to_alloc > wnd->extent_max) { wnd->extent_max = to_alloc; } *allocated = fnd; return to_alloc; no_space: return 0; } /* * wnd_extend - Extend bitmap ($MFT bitmap). */ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits) { int err; struct super_block *sb = wnd->sb; struct ntfs_sb_info *sbi = sb->s_fs_info; u32 blocksize = sb->s_blocksize; u32 wbits = blocksize * 8; u32 b0, new_last; size_t bits, iw, new_wnd; size_t old_bits = wnd->nbits; u16 *new_free; if (new_bits <= old_bits) return -EINVAL; /* Align to 8 byte boundary. */ new_wnd = bytes_to_block(sb, ntfs3_bitmap_size(new_bits)); new_last = new_bits & (wbits - 1); if (!new_last) new_last = wbits; if (new_wnd != wnd->nwnd) { new_free = kmalloc_array(new_wnd, sizeof(u16), GFP_NOFS); if (!new_free) return -ENOMEM; memcpy(new_free, wnd->free_bits, wnd->nwnd * sizeof(short)); memset(new_free + wnd->nwnd, 0, (new_wnd - wnd->nwnd) * sizeof(short)); kvfree(wnd->free_bits); wnd->free_bits = new_free; } /* Zero bits [old_bits,new_bits). */ bits = new_bits - old_bits; b0 = old_bits & (wbits - 1); for (iw = old_bits >> (sb->s_blocksize_bits + 3); bits; iw += 1) { u32 op; size_t frb; u64 vbo, lbo, bytes; struct buffer_head *bh; if (iw + 1 == new_wnd) wbits = new_last; op = b0 + bits > wbits ? wbits - b0 : bits; vbo = (u64)iw * blocksize; err = ntfs_vbo_to_lbo(sbi, &wnd->run, vbo, &lbo, &bytes); if (err) return err; bh = ntfs_bread(sb, lbo >> sb->s_blocksize_bits); if (!bh) return -EIO; lock_buffer(bh); ntfs_bitmap_clear_le(bh->b_data, b0, blocksize * 8 - b0); frb = wbits - ntfs_bitmap_weight_le(bh->b_data, wbits); wnd->total_zeroes += frb - wnd->free_bits[iw]; wnd->free_bits[iw] = frb; set_buffer_uptodate(bh); mark_buffer_dirty(bh); unlock_buffer(bh); /* err = sync_dirty_buffer(bh); */ put_bh(bh); b0 = 0; bits -= op; } wnd->nbits = new_bits; wnd->nwnd = new_wnd; wnd->bits_last = new_last; wnd_add_free_ext(wnd, old_bits, new_bits - old_bits, false); return 0; } void wnd_zone_set(struct wnd_bitmap *wnd, size_t lcn, size_t len) { size_t zlen = wnd->zone_end - wnd->zone_bit; if (zlen) wnd_add_free_ext(wnd, wnd->zone_bit, zlen, false); if (!RB_EMPTY_ROOT(&wnd->start_tree) && len) wnd_remove_free_ext(wnd, lcn, len); wnd->zone_bit = lcn; wnd->zone_end = lcn + len; } int ntfs_trim_fs(struct ntfs_sb_info *sbi, struct fstrim_range *range) { int err = 0; struct super_block *sb = sbi->sb; struct wnd_bitmap *wnd = &sbi->used.bitmap; u32 wbits = 8 * sb->s_blocksize; CLST len = 0, lcn = 0, done = 0; CLST minlen = bytes_to_cluster(sbi, range->minlen); CLST lcn_from = bytes_to_cluster(sbi, range->start); size_t iw = lcn_from >> (sb->s_blocksize_bits + 3); u32 wbit = lcn_from & (wbits - 1); CLST lcn_to; if (!minlen) minlen = 1; if (range->len == (u64)-1) lcn_to = wnd->nbits; else lcn_to = bytes_to_cluster(sbi, range->start + range->len); down_read_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); for (; iw < wnd->nwnd; iw++, wbit = 0) { CLST lcn_wnd = iw * wbits; struct buffer_head *bh; if (lcn_wnd > lcn_to) break; if (!wnd->free_bits[iw]) continue; if (iw + 1 == wnd->nwnd) wbits = wnd->bits_last; if (lcn_wnd + wbits > lcn_to) wbits = lcn_to - lcn_wnd; bh = wnd_map(wnd, iw); if (IS_ERR(bh)) { err = PTR_ERR(bh); break; } for (; wbit < wbits; wbit++) { if (!test_bit_le(wbit, bh->b_data)) { if (!len) lcn = lcn_wnd + wbit; len += 1; continue; } if (len >= minlen) { err = ntfs_discard(sbi, lcn, len); if (err) goto out; done += len; } len = 0; } put_bh(bh); } /* Process the last fragment. */ if (len >= minlen) { err = ntfs_discard(sbi, lcn, len); if (err) goto out; done += len; } out: range->len = (u64)done << sbi->cluster_bits; up_read(&wnd->rw_lock); return err; } #if BITS_PER_LONG == 64 typedef __le64 bitmap_ulong; #define cpu_to_ul(x) cpu_to_le64(x) #define ul_to_cpu(x) le64_to_cpu(x) #else typedef __le32 bitmap_ulong; #define cpu_to_ul(x) cpu_to_le32(x) #define ul_to_cpu(x) le32_to_cpu(x) #endif void ntfs_bitmap_set_le(void *map, unsigned int start, int len) { bitmap_ulong *p = (bitmap_ulong *)map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); bitmap_ulong mask_to_set = cpu_to_ul(BITMAP_FIRST_WORD_MASK(start)); while (len - bits_to_set >= 0) { *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_LONG; mask_to_set = cpu_to_ul(~0UL); p++; } if (len) { mask_to_set &= cpu_to_ul(BITMAP_LAST_WORD_MASK(size)); *p |= mask_to_set; } } void ntfs_bitmap_clear_le(void *map, unsigned int start, int len) { bitmap_ulong *p = (bitmap_ulong *)map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); bitmap_ulong mask_to_clear = cpu_to_ul(BITMAP_FIRST_WORD_MASK(start)); while (len - bits_to_clear >= 0) { *p &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_LONG; mask_to_clear = cpu_to_ul(~0UL); p++; } if (len) { mask_to_clear &= cpu_to_ul(BITMAP_LAST_WORD_MASK(size)); *p &= ~mask_to_clear; } } unsigned int ntfs_bitmap_weight_le(const void *bitmap, int bits) { const ulong *bmp = bitmap; unsigned int k, lim = bits / BITS_PER_LONG; unsigned int w = 0; for (k = 0; k < lim; k++) w += hweight_long(bmp[k]); if (bits % BITS_PER_LONG) { w += hweight_long(ul_to_cpu(((bitmap_ulong *)bitmap)[k]) & BITMAP_LAST_WORD_MASK(bits)); } return w; } |
| 4 3 8 8 8 5 3 3 3 101 101 101 3 166 168 168 181 179 179 176 166 3 166 169 1 7 6 4 4 2 4 3 2 2 2 2 1 1 107 108 108 104 58 50 59 50 48 2 1 1 1 166 142 29 79 2 57 55 189 188 184 139 18 11 32 5 113 170 167 169 62 1 167 9 16 15 7 1 25 1 25 3 2 118 167 60 23 25 25 2 2 169 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 | // SPDX-License-Identifier: GPL-2.0-or-later /* Filesystem access-by-fd. * * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/syscalls.h> #include <linux/security.h> #include <linux/anon_inodes.h> #include <linux/namei.h> #include <linux/file.h> #include <uapi/linux/mount.h> #include "internal.h" #include "mount.h" static inline const char *fetch_message_locked(struct fc_log *log, size_t len, bool *need_free) { const char *p; int index; if (unlikely(log->head == log->tail)) return ERR_PTR(-ENODATA); index = log->tail & (ARRAY_SIZE(log->buffer) - 1); p = log->buffer[index]; if (unlikely(strlen(p) > len)) return ERR_PTR(-EMSGSIZE); log->buffer[index] = NULL; *need_free = log->need_free & (1 << index); log->need_free &= ~(1 << index); log->tail++; return p; } /* * Allow the user to read back any error, warning or informational messages. * Only one message is returned for each read(2) call. */ static ssize_t fscontext_read(struct file *file, char __user *_buf, size_t len, loff_t *pos) { struct fs_context *fc = file->private_data; ssize_t err; const char *p __free(kfree) = NULL, *message; bool need_free; int n; err = mutex_lock_interruptible(&fc->uapi_mutex); if (err < 0) return err; message = fetch_message_locked(fc->log.log, len, &need_free); mutex_unlock(&fc->uapi_mutex); if (IS_ERR(message)) return PTR_ERR(message); if (need_free) p = message; n = strlen(message); if (copy_to_user(_buf, message, n)) return -EFAULT; return n; } static int fscontext_release(struct inode *inode, struct file *file) { struct fs_context *fc = file->private_data; if (fc) { file->private_data = NULL; put_fs_context(fc); } return 0; } const struct file_operations fscontext_fops = { .read = fscontext_read, .release = fscontext_release, }; /* * Attach a filesystem context to a file and an fd. */ static int fscontext_create_fd(struct fs_context *fc, unsigned int o_flags) { int fd; fd = anon_inode_getfd("[fscontext]", &fscontext_fops, fc, O_RDWR | o_flags); if (fd < 0) put_fs_context(fc); return fd; } static int fscontext_alloc_log(struct fs_context *fc) { fc->log.log = kzalloc_obj(*fc->log.log); if (!fc->log.log) return -ENOMEM; refcount_set(&fc->log.log->usage, 1); fc->log.log->owner = fc->fs_type->owner; return 0; } /* * Open a filesystem by name so that it can be configured for mounting. * * We are allowed to specify a container in which the filesystem will be * opened, thereby indicating which namespaces will be used (notably, which * network namespace will be used for network filesystems). */ SYSCALL_DEFINE2(fsopen, const char __user *, _fs_name, unsigned int, flags) { struct file_system_type *fs_type; struct fs_context *fc; const char *fs_name; int ret; if (!may_mount()) return -EPERM; if (flags & ~FSOPEN_CLOEXEC) return -EINVAL; fs_name = strndup_user(_fs_name, PAGE_SIZE); if (IS_ERR(fs_name)) return PTR_ERR(fs_name); fs_type = get_fs_type(fs_name); kfree(fs_name); if (!fs_type) return -ENODEV; fc = fs_context_for_mount(fs_type, 0); put_filesystem(fs_type); if (IS_ERR(fc)) return PTR_ERR(fc); fc->phase = FS_CONTEXT_CREATE_PARAMS; ret = fscontext_alloc_log(fc); if (ret < 0) goto err_fc; return fscontext_create_fd(fc, flags & FSOPEN_CLOEXEC ? O_CLOEXEC : 0); err_fc: put_fs_context(fc); return ret; } /* * Pick a superblock into a context for reconfiguration. */ SYSCALL_DEFINE3(fspick, int, dfd, const char __user *, path, unsigned int, flags) { struct fs_context *fc; struct path target; unsigned int lookup_flags; int ret; if (!may_mount()) return -EPERM; if ((flags & ~(FSPICK_CLOEXEC | FSPICK_SYMLINK_NOFOLLOW | FSPICK_NO_AUTOMOUNT | FSPICK_EMPTY_PATH)) != 0) return -EINVAL; lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT; if (flags & FSPICK_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & FSPICK_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; CLASS(filename_flags, filename)(path, (flags & FSPICK_EMPTY_PATH) ? LOOKUP_EMPTY : 0); ret = filename_lookup(dfd, filename, lookup_flags, &target, NULL); if (ret < 0) goto err; ret = -EINVAL; if (target.mnt->mnt_root != target.dentry) goto err_path; fc = fs_context_for_reconfigure(target.dentry, 0, 0); if (IS_ERR(fc)) { ret = PTR_ERR(fc); goto err_path; } fc->phase = FS_CONTEXT_RECONF_PARAMS; ret = fscontext_alloc_log(fc); if (ret < 0) goto err_fc; path_put(&target); return fscontext_create_fd(fc, flags & FSPICK_CLOEXEC ? O_CLOEXEC : 0); err_fc: put_fs_context(fc); err_path: path_put(&target); err: return ret; } static int vfs_cmd_create(struct fs_context *fc, bool exclusive) { struct super_block *sb; int ret; if (fc->phase != FS_CONTEXT_CREATE_PARAMS) return -EBUSY; if (!mount_capable(fc)) return -EPERM; fc->phase = FS_CONTEXT_CREATING; fc->exclusive = exclusive; ret = vfs_get_tree(fc); if (ret) { fc->phase = FS_CONTEXT_FAILED; return ret; } sb = fc->root->d_sb; ret = security_sb_kern_mount(sb); if (unlikely(ret)) { fc_drop_locked(fc); fc->phase = FS_CONTEXT_FAILED; return ret; } /* vfs_get_tree() callchains will have grabbed @s_umount */ up_write(&sb->s_umount); fc->phase = FS_CONTEXT_AWAITING_MOUNT; return 0; } static int vfs_cmd_reconfigure(struct fs_context *fc) { struct super_block *sb; int ret; if (fc->phase != FS_CONTEXT_RECONF_PARAMS) return -EBUSY; fc->phase = FS_CONTEXT_RECONFIGURING; sb = fc->root->d_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { fc->phase = FS_CONTEXT_FAILED; return -EPERM; } down_write(&sb->s_umount); ret = reconfigure_super(fc); up_write(&sb->s_umount); if (ret) { fc->phase = FS_CONTEXT_FAILED; return ret; } vfs_clean_context(fc); return 0; } /* * Check the state and apply the configuration. Note that this function is * allowed to 'steal' the value by setting param->xxx to NULL before returning. */ static int vfs_fsconfig_locked(struct fs_context *fc, int cmd, struct fs_parameter *param) { int ret; ret = finish_clean_context(fc); if (ret) return ret; switch (cmd) { case FSCONFIG_CMD_CREATE: return vfs_cmd_create(fc, false); case FSCONFIG_CMD_CREATE_EXCL: return vfs_cmd_create(fc, true); case FSCONFIG_CMD_RECONFIGURE: return vfs_cmd_reconfigure(fc); default: if (fc->phase != FS_CONTEXT_CREATE_PARAMS && fc->phase != FS_CONTEXT_RECONF_PARAMS) return -EBUSY; return vfs_parse_fs_param(fc, param); } } /** * sys_fsconfig - Set parameters and trigger actions on a context * @fd: The filesystem context to act upon * @cmd: The action to take * @_key: Where appropriate, the parameter key to set * @_value: Where appropriate, the parameter value to set * @aux: Additional information for the value * * This system call is used to set parameters on a context, including * superblock settings, data source and security labelling. * * Actions include triggering the creation of a superblock and the * reconfiguration of the superblock attached to the specified context. * * When setting a parameter, @cmd indicates the type of value being proposed * and @_key indicates the parameter to be altered. * * @_value and @aux are used to specify the value, should a value be required: * * (*) fsconfig_set_flag: No value is specified. The parameter must be boolean * in nature. The key may be prefixed with "no" to invert the * setting. @_value must be NULL and @aux must be 0. * * (*) fsconfig_set_string: A string value is specified. The parameter can be * expecting boolean, integer, string or take a path. A conversion to an * appropriate type will be attempted (which may include looking up as a * path). @_value points to a NUL-terminated string and @aux must be 0. * * (*) fsconfig_set_binary: A binary blob is specified. @_value points to the * blob and @aux indicates its size. The parameter must be expecting a * blob. * * (*) fsconfig_set_path: A non-empty path is specified. The parameter must be * expecting a path object. @_value points to a NUL-terminated string that * is the path and @aux is a file descriptor at which to start a relative * lookup or AT_FDCWD. * * (*) fsconfig_set_path_empty: As fsconfig_set_path, but with AT_EMPTY_PATH * implied. * * (*) fsconfig_set_fd: An open file descriptor is specified. @_value must be * NULL and @aux indicates the file descriptor. */ SYSCALL_DEFINE5(fsconfig, int, fd, unsigned int, cmd, const char __user *, _key, const void __user *, _value, int, aux) { struct fs_context *fc; int ret; int lookup_flags = 0; struct fs_parameter param = { .type = fs_value_is_undefined, }; if (fd < 0) return -EINVAL; switch (cmd) { case FSCONFIG_SET_FLAG: if (!_key || _value || aux) return -EINVAL; break; case FSCONFIG_SET_STRING: if (!_key || !_value || aux) return -EINVAL; break; case FSCONFIG_SET_BINARY: if (!_key || !_value || aux <= 0 || aux > 1024 * 1024) return -EINVAL; break; case FSCONFIG_SET_PATH: case FSCONFIG_SET_PATH_EMPTY: if (!_key || !_value || (aux != AT_FDCWD && aux < 0)) return -EINVAL; break; case FSCONFIG_SET_FD: if (!_key || _value || aux < 0) return -EINVAL; break; case FSCONFIG_CMD_CREATE: case FSCONFIG_CMD_CREATE_EXCL: case FSCONFIG_CMD_RECONFIGURE: if (_key || _value || aux) return -EINVAL; break; default: return -EOPNOTSUPP; } CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_op != &fscontext_fops) return -EINVAL; fc = fd_file(f)->private_data; if (_key) { param.key = strndup_user(_key, 256); if (IS_ERR(param.key)) return PTR_ERR(param.key); } switch (cmd) { case FSCONFIG_SET_FLAG: param.type = fs_value_is_flag; break; case FSCONFIG_SET_STRING: param.type = fs_value_is_string; param.string = strndup_user(_value, 256); if (IS_ERR(param.string)) { ret = PTR_ERR(param.string); goto out_key; } param.size = strlen(param.string); break; case FSCONFIG_SET_BINARY: param.type = fs_value_is_blob; param.size = aux; param.blob = memdup_user_nul(_value, aux); if (IS_ERR(param.blob)) { ret = PTR_ERR(param.blob); goto out_key; } break; case FSCONFIG_SET_PATH_EMPTY: lookup_flags = LOOKUP_EMPTY; fallthrough; case FSCONFIG_SET_PATH: param.type = fs_value_is_filename; param.name = getname_flags(_value, lookup_flags); if (IS_ERR(param.name)) { ret = PTR_ERR(param.name); goto out_key; } param.dirfd = aux; param.size = strlen(param.name->name); break; case FSCONFIG_SET_FD: param.type = fs_value_is_file; ret = -EBADF; param.file = fget_raw(aux); if (!param.file) goto out_key; param.dirfd = aux; break; default: break; } ret = mutex_lock_interruptible(&fc->uapi_mutex); if (ret == 0) { ret = vfs_fsconfig_locked(fc, cmd, ¶m); mutex_unlock(&fc->uapi_mutex); } /* Clean up the our record of any value that we obtained from * userspace. Note that the value may have been stolen by the LSM or * filesystem, in which case the value pointer will have been cleared. */ switch (cmd) { case FSCONFIG_SET_STRING: case FSCONFIG_SET_BINARY: kfree(param.string); break; case FSCONFIG_SET_PATH: case FSCONFIG_SET_PATH_EMPTY: if (param.name) putname(param.name); break; case FSCONFIG_SET_FD: if (param.file) fput(param.file); break; default: break; } out_key: kfree(param.key); return ret; } |
| 222 224 224 224 223 222 224 2 2 2 222 222 222 222 118 176 176 16 16 14 160 160 160 160 160 160 160 160 160 160 160 17 1 17 17 17 16 16 16 16 17 17 17 5 12 12 12 12 12 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 160 118 118 118 118 117 118 118 118 117 118 118 118 118 118 118 118 118 118 118 160 160 160 160 160 160 160 160 160 160 160 160 222 222 222 222 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar * Copyright (C) 2005-2006 Thomas Gleixner * * This file contains driver APIs to the irq subsystem. */ #define pr_fmt(fmt) "genirq: " fmt #include <linux/irq.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/random.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/sched/task.h> #include <linux/sched/isolation.h> #include <uapi/linux/sched/types.h> #include <linux/task_work.h> #include "internals.h" #if defined(CONFIG_IRQ_FORCED_THREADING) && !defined(CONFIG_PREEMPT_RT) DEFINE_STATIC_KEY_FALSE(force_irqthreads_key); static int __init setup_forced_irqthreads(char *arg) { static_branch_enable(&force_irqthreads_key); return 0; } early_param("threadirqs", setup_forced_irqthreads); #endif #ifdef CONFIG_SMP static inline void synchronize_irqwork(struct irq_desc *desc) { /* Synchronize pending or on the fly redirect work */ irq_work_sync(&desc->redirect.work); } #else static inline void synchronize_irqwork(struct irq_desc *desc) { } #endif static int __irq_get_irqchip_state(struct irq_data *d, enum irqchip_irq_state which, bool *state); static void __synchronize_hardirq(struct irq_desc *desc, bool sync_chip) { struct irq_data *irqd = irq_desc_get_irq_data(desc); bool inprogress; do { /* * Wait until we're out of the critical section. This might * give the wrong answer due to the lack of memory barriers. */ while (irqd_irq_inprogress(&desc->irq_data)) cpu_relax(); /* Ok, that indicated we're done: double-check carefully. */ guard(raw_spinlock_irqsave)(&desc->lock); inprogress = irqd_irq_inprogress(&desc->irq_data); /* * If requested and supported, check at the chip whether it * is in flight at the hardware level, i.e. already pending * in a CPU and waiting for service and acknowledge. */ if (!inprogress && sync_chip) { /* * Ignore the return code. inprogress is only updated * when the chip supports it. */ __irq_get_irqchip_state(irqd, IRQCHIP_STATE_ACTIVE, &inprogress); } /* Oops, that failed? */ } while (inprogress); } /** * synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs) * @irq: interrupt number to wait for * * This function waits for any pending hard IRQ handlers for this interrupt * to complete before returning. If you use this function while holding a * resource the IRQ handler may need you will deadlock. It does not take * associated threaded handlers into account. * * Do not use this for shutdown scenarios where you must be sure that all * parts (hardirq and threaded handler) have completed. * * Returns: false if a threaded handler is active. * * This function may be called - with care - from IRQ context. * * It does not check whether there is an interrupt in flight at the * hardware level, but not serviced yet, as this might deadlock when called * with interrupts disabled and the target CPU of the interrupt is the * current CPU. */ bool synchronize_hardirq(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (desc) { __synchronize_hardirq(desc, false); return !atomic_read(&desc->threads_active); } return true; } EXPORT_SYMBOL(synchronize_hardirq); static void __synchronize_irq(struct irq_desc *desc) { synchronize_irqwork(desc); __synchronize_hardirq(desc, true); /* * We made sure that no hardirq handler is running. Now verify that no * threaded handlers are active. */ wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active)); } /** * synchronize_irq - wait for pending IRQ handlers (on other CPUs) * @irq: interrupt number to wait for * * This function waits for any pending IRQ handlers for this interrupt to * complete before returning. If you use this function while holding a * resource the IRQ handler may need you will deadlock. * * Can only be called from preemptible code as it might sleep when * an interrupt thread is associated to @irq. * * It optionally makes sure (when the irq chip supports that method) * that the interrupt is not pending in any CPU and waiting for * service. */ void synchronize_irq(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (desc) __synchronize_irq(desc); } EXPORT_SYMBOL(synchronize_irq); #ifdef CONFIG_SMP cpumask_var_t irq_default_affinity; static bool __irq_can_set_affinity(struct irq_desc *desc) { if (!desc || !irqd_can_balance(&desc->irq_data) || !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity) return false; return true; } /** * irq_can_set_affinity - Check if the affinity of a given irq can be set * @irq: Interrupt to check * */ int irq_can_set_affinity(unsigned int irq) { return __irq_can_set_affinity(irq_to_desc(irq)); } /** * irq_can_set_affinity_usr - Check if affinity of a irq can be set from user space * @irq: Interrupt to check * * Like irq_can_set_affinity() above, but additionally checks for the * AFFINITY_MANAGED flag. */ bool irq_can_set_affinity_usr(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); return __irq_can_set_affinity(desc) && !irqd_affinity_is_managed(&desc->irq_data); } /** * irq_set_thread_affinity - Notify irq threads to adjust affinity * @desc: irq descriptor which has affinity changed * * Just set IRQTF_AFFINITY and delegate the affinity setting to the * interrupt thread itself. We can not call set_cpus_allowed_ptr() here as * we hold desc->lock and this code can be called from hard interrupt * context. */ static void irq_set_thread_affinity(struct irq_desc *desc) { struct irqaction *action; for_each_action_of_desc(desc, action) { if (action->thread) { set_bit(IRQTF_AFFINITY, &action->thread_flags); wake_up_process(action->thread); } if (action->secondary && action->secondary->thread) { set_bit(IRQTF_AFFINITY, &action->secondary->thread_flags); wake_up_process(action->secondary->thread); } } } #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK static void irq_validate_effective_affinity(struct irq_data *data) { const struct cpumask *m = irq_data_get_effective_affinity_mask(data); struct irq_chip *chip = irq_data_get_irq_chip(data); if (!cpumask_empty(m)) return; pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n", chip->name, data->irq); } #else static inline void irq_validate_effective_affinity(struct irq_data *data) { } #endif static DEFINE_PER_CPU(struct cpumask, __tmp_mask); int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { struct cpumask *tmp_mask = this_cpu_ptr(&__tmp_mask); struct irq_desc *desc = irq_data_to_desc(data); struct irq_chip *chip = irq_data_get_irq_chip(data); const struct cpumask *prog_mask; int ret; if (!chip || !chip->irq_set_affinity) return -EINVAL; /* * If this is a managed interrupt and housekeeping is enabled on * it check whether the requested affinity mask intersects with * a housekeeping CPU. If so, then remove the isolated CPUs from * the mask and just keep the housekeeping CPU(s). This prevents * the affinity setter from routing the interrupt to an isolated * CPU to avoid that I/O submitted from a housekeeping CPU causes * interrupts on an isolated one. * * If the masks do not intersect or include online CPU(s) then * keep the requested mask. The isolated target CPUs are only * receiving interrupts when the I/O operation was submitted * directly from them. * * If all housekeeping CPUs in the affinity mask are offline, the * interrupt will be migrated by the CPU hotplug code once a * housekeeping CPU which belongs to the affinity mask comes * online. */ if (irqd_affinity_is_managed(data) && housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) { const struct cpumask *hk_mask; hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); cpumask_and(tmp_mask, mask, hk_mask); if (!cpumask_intersects(tmp_mask, cpu_online_mask)) prog_mask = mask; else prog_mask = tmp_mask; } else { prog_mask = mask; } /* * Make sure we only provide online CPUs to the irqchip, * unless we are being asked to force the affinity (in which * case we do as we are told). */ cpumask_and(tmp_mask, prog_mask, cpu_online_mask); if (!force && !cpumask_empty(tmp_mask)) ret = chip->irq_set_affinity(data, tmp_mask, force); else if (force) ret = chip->irq_set_affinity(data, mask, force); else ret = -EINVAL; switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: cpumask_copy(desc->irq_common_data.affinity, mask); fallthrough; case IRQ_SET_MASK_OK_NOCOPY: irq_validate_effective_affinity(data); irq_set_thread_affinity(desc); ret = 0; } return ret; } #ifdef CONFIG_GENERIC_PENDING_IRQ static inline int irq_set_affinity_pending(struct irq_data *data, const struct cpumask *dest) { struct irq_desc *desc = irq_data_to_desc(data); irqd_set_move_pending(data); irq_copy_pending(desc, dest); return 0; } #else static inline int irq_set_affinity_pending(struct irq_data *data, const struct cpumask *dest) { return -EBUSY; } #endif static int irq_try_set_affinity(struct irq_data *data, const struct cpumask *dest, bool force) { int ret = irq_do_set_affinity(data, dest, force); /* * In case that the underlying vector management is busy and the * architecture supports the generic pending mechanism then utilize * this to avoid returning an error to user space. */ if (ret == -EBUSY && !force) ret = irq_set_affinity_pending(data, dest); return ret; } static bool irq_set_affinity_deactivated(struct irq_data *data, const struct cpumask *mask) { struct irq_desc *desc = irq_data_to_desc(data); /* * Handle irq chips which can handle affinity only in activated * state correctly * * If the interrupt is not yet activated, just store the affinity * mask and do not call the chip driver at all. On activation the * driver has to make sure anyway that the interrupt is in a * usable state so startup works. */ if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || irqd_is_activated(data) || !irqd_affinity_on_activate(data)) return false; cpumask_copy(desc->irq_common_data.affinity, mask); irq_data_update_effective_affinity(data, mask); irqd_set(data, IRQD_AFFINITY_SET); return true; } /** * irq_affinity_schedule_notify_work - Schedule work to notify about affinity change * @desc: Interrupt descriptor whose affinity changed */ void irq_affinity_schedule_notify_work(struct irq_desc *desc) { lockdep_assert_held(&desc->lock); kref_get(&desc->affinity_notify->kref); if (!schedule_work(&desc->affinity_notify->work)) { /* Work was already scheduled, drop our extra ref */ kref_put(&desc->affinity_notify->kref, desc->affinity_notify->release); } } int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, bool force) { struct irq_chip *chip = irq_data_get_irq_chip(data); struct irq_desc *desc = irq_data_to_desc(data); int ret = 0; if (!chip || !chip->irq_set_affinity) return -EINVAL; if (irq_set_affinity_deactivated(data, mask)) return 0; if (irq_can_move_pcntxt(data) && !irqd_is_setaffinity_pending(data)) { ret = irq_try_set_affinity(data, mask, force); } else { irqd_set_move_pending(data); irq_copy_pending(desc, mask); } if (desc->affinity_notify) irq_affinity_schedule_notify_work(desc); irqd_set(data, IRQD_AFFINITY_SET); return ret; } /** * irq_update_affinity_desc - Update affinity management for an interrupt * @irq: The interrupt number to update * @affinity: Pointer to the affinity descriptor * * This interface can be used to configure the affinity management of * interrupts which have been allocated already. * * There are certain limitations on when it may be used - attempts to use it * for when the kernel is configured for generic IRQ reservation mode (in * config GENERIC_IRQ_RESERVATION_MODE) will fail, as it may conflict with * managed/non-managed interrupt accounting. In addition, attempts to use it on * an interrupt which is already started or which has already been configured * as managed will also fail, as these mean invalid init state or double init. */ int irq_update_affinity_desc(unsigned int irq, struct irq_affinity_desc *affinity) { /* * Supporting this with the reservation scheme used by x86 needs * some more thought. Fail it for now. */ if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE)) return -EOPNOTSUPP; scoped_irqdesc_get_and_buslock(irq, 0) { struct irq_desc *desc = scoped_irqdesc; bool activated; /* Requires the interrupt to be shut down */ if (irqd_is_started(&desc->irq_data)) return -EBUSY; /* Interrupts which are already managed cannot be modified */ if (irqd_affinity_is_managed(&desc->irq_data)) return -EBUSY; /* * Deactivate the interrupt. That's required to undo * anything an earlier activation has established. */ activated = irqd_is_activated(&desc->irq_data); if (activated) irq_domain_deactivate_irq(&desc->irq_data); if (affinity->is_managed) { irqd_set(&desc->irq_data, IRQD_AFFINITY_MANAGED); irqd_set(&desc->irq_data, IRQD_MANAGED_SHUTDOWN); } cpumask_copy(desc->irq_common_data.affinity, &affinity->mask); /* Restore the activation state */ if (activated) irq_domain_activate_irq(&desc->irq_data, false); return 0; } return -EINVAL; } static int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force) { struct irq_desc *desc = irq_to_desc(irq); if (!desc) return -EINVAL; guard(raw_spinlock_irqsave)(&desc->lock); return irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force); } /** * irq_set_affinity - Set the irq affinity of a given irq * @irq: Interrupt to set affinity * @cpumask: cpumask * * Fails if cpumask does not contain an online CPU */ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) { return __irq_set_affinity(irq, cpumask, false); } EXPORT_SYMBOL_GPL(irq_set_affinity); /** * irq_force_affinity - Force the irq affinity of a given irq * @irq: Interrupt to set affinity * @cpumask: cpumask * * Same as irq_set_affinity, but without checking the mask against * online cpus. * * Solely for low level cpu hotplug code, where we need to make per * cpu interrupts affine before the cpu becomes online. */ int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) { return __irq_set_affinity(irq, cpumask, true); } EXPORT_SYMBOL_GPL(irq_force_affinity); int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m, bool setaffinity) { int ret = -EINVAL; scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) { scoped_irqdesc->affinity_hint = m; ret = 0; } if (!ret && m && setaffinity) __irq_set_affinity(irq, m, false); return ret; } EXPORT_SYMBOL_GPL(__irq_apply_affinity_hint); static void irq_affinity_notify(struct work_struct *work) { struct irq_affinity_notify *notify = container_of(work, struct irq_affinity_notify, work); struct irq_desc *desc = irq_to_desc(notify->irq); cpumask_var_t cpumask; if (!desc || !alloc_cpumask_var(&cpumask, GFP_KERNEL)) goto out; scoped_guard(raw_spinlock_irqsave, &desc->lock) { if (irq_move_pending(&desc->irq_data)) irq_get_pending(cpumask, desc); else cpumask_copy(cpumask, desc->irq_common_data.affinity); } notify->notify(notify, cpumask); free_cpumask_var(cpumask); out: kref_put(¬ify->kref, notify->release); } /** * irq_set_affinity_notifier - control notification of IRQ affinity changes * @irq: Interrupt for which to enable/disable notification * @notify: Context for notification, or %NULL to disable * notification. Function pointers must be initialised; * the other fields will be initialised by this function. * * Must be called in process context. Notification may only be enabled * after the IRQ is allocated and must be disabled before the IRQ is freed * using free_irq(). */ int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) { struct irq_desc *desc = irq_to_desc(irq); struct irq_affinity_notify *old_notify; /* The release function is promised process context */ might_sleep(); if (!desc || irq_is_nmi(desc)) return -EINVAL; /* Complete initialisation of *notify */ if (notify) { notify->irq = irq; kref_init(¬ify->kref); INIT_WORK(¬ify->work, irq_affinity_notify); } scoped_guard(raw_spinlock_irq, &desc->lock) { old_notify = desc->affinity_notify; desc->affinity_notify = notify; } if (old_notify) { if (cancel_work_sync(&old_notify->work)) { /* Pending work had a ref, put that one too */ kref_put(&old_notify->kref, old_notify->release); } kref_put(&old_notify->kref, old_notify->release); } return 0; } EXPORT_SYMBOL_GPL(irq_set_affinity_notifier); #ifndef CONFIG_AUTO_IRQ_AFFINITY /* * Generic version of the affinity autoselector. */ int irq_setup_affinity(struct irq_desc *desc) { struct cpumask *set = irq_default_affinity; int node = irq_desc_get_node(desc); static DEFINE_RAW_SPINLOCK(mask_lock); static struct cpumask mask; /* Excludes PER_CPU and NO_BALANCE interrupts */ if (!__irq_can_set_affinity(desc)) return 0; guard(raw_spinlock)(&mask_lock); /* * Preserve the managed affinity setting and a userspace affinity * setup, but make sure that one of the targets is online. */ if (irqd_affinity_is_managed(&desc->irq_data) || irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) { if (cpumask_intersects(desc->irq_common_data.affinity, cpu_online_mask)) set = desc->irq_common_data.affinity; else irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET); } cpumask_and(&mask, cpu_online_mask, set); if (cpumask_empty(&mask)) cpumask_copy(&mask, cpu_online_mask); if (node != NUMA_NO_NODE) { const struct cpumask *nodemask = cpumask_of_node(node); /* make sure at least one of the cpus in nodemask is online */ if (cpumask_intersects(&mask, nodemask)) cpumask_and(&mask, &mask, nodemask); } return irq_do_set_affinity(&desc->irq_data, &mask, false); } #else /* Wrapper for ALPHA specific affinity selector magic */ int irq_setup_affinity(struct irq_desc *desc) { return irq_select_affinity(irq_desc_get_irq(desc)); } #endif /* CONFIG_AUTO_IRQ_AFFINITY */ #endif /* CONFIG_SMP */ /** * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt * @irq: interrupt number to set affinity * @vcpu_info: vCPU specific data or pointer to a percpu array of vCPU * specific data for percpu_devid interrupts * * This function uses the vCPU specific data to set the vCPU affinity for * an irq. The vCPU specific data is passed from outside, such as KVM. One * example code path is as below: KVM -> IOMMU -> irq_set_vcpu_affinity(). */ int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info) { scoped_irqdesc_get_and_lock(irq, 0) { struct irq_desc *desc = scoped_irqdesc; struct irq_data *data; struct irq_chip *chip; data = irq_desc_get_irq_data(desc); do { chip = irq_data_get_irq_chip(data); if (chip && chip->irq_set_vcpu_affinity) break; data = irqd_get_parent_data(data); } while (data); if (!data) return -ENOSYS; return chip->irq_set_vcpu_affinity(data, vcpu_info); } return -EINVAL; } EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity); void __disable_irq(struct irq_desc *desc) { if (!desc->depth++) irq_disable(desc); } static int __disable_irq_nosync(unsigned int irq) { scoped_irqdesc_get_and_buslock(irq, IRQ_GET_DESC_CHECK_GLOBAL) { __disable_irq(scoped_irqdesc); return 0; } return -EINVAL; } /** * disable_irq_nosync - disable an irq without waiting * @irq: Interrupt to disable * * Disable the selected interrupt line. Disables and Enables are * nested. * Unlike disable_irq(), this function does not ensure existing * instances of the IRQ handler have completed before returning. * * This function may be called from IRQ context. */ void disable_irq_nosync(unsigned int irq) { __disable_irq_nosync(irq); } EXPORT_SYMBOL(disable_irq_nosync); /** * disable_irq - disable an irq and wait for completion * @irq: Interrupt to disable * * Disable the selected interrupt line. Enables and Disables are nested. * * This function waits for any pending IRQ handlers for this interrupt to * complete before returning. If you use this function while holding a * resource the IRQ handler may need you will deadlock. * * Can only be called from preemptible code as it might sleep when an * interrupt thread is associated to @irq. * */ void disable_irq(unsigned int irq) { might_sleep(); if (!__disable_irq_nosync(irq)) synchronize_irq(irq); } EXPORT_SYMBOL(disable_irq); /** * disable_hardirq - disables an irq and waits for hardirq completion * @irq: Interrupt to disable * * Disable the selected interrupt line. Enables and Disables are nested. * * This function waits for any pending hard IRQ handlers for this interrupt * to complete before returning. If you use this function while holding a * resource the hard IRQ handler may need you will deadlock. * * When used to optimistically disable an interrupt from atomic context the * return value must be checked. * * Returns: false if a threaded handler is active. * * This function may be called - with care - from IRQ context. */ bool disable_hardirq(unsigned int irq) { if (!__disable_irq_nosync(irq)) return synchronize_hardirq(irq); return false; } EXPORT_SYMBOL_GPL(disable_hardirq); /** * disable_nmi_nosync - disable an nmi without waiting * @irq: Interrupt to disable * * Disable the selected interrupt line. Disables and enables are nested. * * The interrupt to disable must have been requested through request_nmi. * Unlike disable_nmi(), this function does not ensure existing * instances of the IRQ handler have completed before returning. */ void disable_nmi_nosync(unsigned int irq) { disable_irq_nosync(irq); } void __enable_irq(struct irq_desc *desc) { switch (desc->depth) { case 0: err_out: WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq_desc_get_irq(desc)); break; case 1: { if (desc->istate & IRQS_SUSPENDED) goto err_out; /* Prevent probing on this irq: */ irq_settings_set_noprobe(desc); /* * Call irq_startup() not irq_enable() here because the * interrupt might be marked NOAUTOEN so irq_startup() * needs to be invoked when it gets enabled the first time. * This is also required when __enable_irq() is invoked for * a managed and shutdown interrupt from the S3 resume * path. * * If it was already started up, then irq_startup() will * invoke irq_enable() under the hood. */ irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE); break; } default: desc->depth--; } } /** * enable_irq - enable handling of an irq * @irq: Interrupt to enable * * Undoes the effect of one call to disable_irq(). If this matches the * last disable, processing of interrupts on this IRQ line is re-enabled. * * This function may be called from IRQ context only when * desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL ! */ void enable_irq(unsigned int irq) { scoped_irqdesc_get_and_buslock(irq, IRQ_GET_DESC_CHECK_GLOBAL) { struct irq_desc *desc = scoped_irqdesc; if (WARN(!desc->irq_data.chip, "enable_irq before setup/request_irq: irq %u\n", irq)) return; __enable_irq(desc); } } EXPORT_SYMBOL(enable_irq); /** * enable_nmi - enable handling of an nmi * @irq: Interrupt to enable * * The interrupt to enable must have been requested through request_nmi. * Undoes the effect of one call to disable_nmi(). If this matches the last * disable, processing of interrupts on this IRQ line is re-enabled. */ void enable_nmi(unsigned int irq) { enable_irq(irq); } static int set_irq_wake_real(unsigned int irq, unsigned int on) { struct irq_desc *desc = irq_to_desc(irq); int ret = -ENXIO; if (irq_desc_get_chip(desc)->flags & IRQCHIP_SKIP_SET_WAKE) return 0; if (desc->irq_data.chip->irq_set_wake) ret = desc->irq_data.chip->irq_set_wake(&desc->irq_data, on); return ret; } /** * irq_set_irq_wake - control irq power management wakeup * @irq: interrupt to control * @on: enable/disable power management wakeup * * Enable/disable power management wakeup mode, which is disabled by * default. Enables and disables must match, just as they match for * non-wakeup mode support. * * Wakeup mode lets this IRQ wake the system from sleep states like * "suspend to RAM". * * Note: irq enable/disable state is completely orthogonal to the * enable/disable state of irq wake. An irq can be disabled with * disable_irq() and still wake the system as long as the irq has wake * enabled. If this does not hold, then the underlying irq chip and the * related driver need to be investigated. */ int irq_set_irq_wake(unsigned int irq, unsigned int on) { scoped_irqdesc_get_and_buslock(irq, IRQ_GET_DESC_CHECK_GLOBAL) { struct irq_desc *desc = scoped_irqdesc; int ret = 0; /* Don't use NMIs as wake up interrupts please */ if (irq_is_nmi(desc)) return -EINVAL; /* * wakeup-capable irqs can be shared between drivers that * don't need to have the same sleep mode behaviors. */ if (on) { if (desc->wake_depth++ == 0) { ret = set_irq_wake_real(irq, on); if (ret) desc->wake_depth = 0; else irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE); } } else { if (desc->wake_depth == 0) { WARN(1, "Unbalanced IRQ %d wake disable\n", irq); } else if (--desc->wake_depth == 0) { ret = set_irq_wake_real(irq, on); if (ret) desc->wake_depth = 1; else irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE); } } return ret; } return -EINVAL; } EXPORT_SYMBOL(irq_set_irq_wake); /* * Internal function that tells the architecture code whether a * particular irq has been exclusively allocated or is available * for driver use. */ bool can_request_irq(unsigned int irq, unsigned long irqflags) { scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) { struct irq_desc *desc = scoped_irqdesc; if (irq_settings_can_request(desc)) { if (!desc->action || irqflags & desc->action->flags & IRQF_SHARED) return true; } } return false; } int __irq_set_trigger(struct irq_desc *desc, unsigned long flags) { struct irq_chip *chip = desc->irq_data.chip; int ret, unmask = 0; if (!chip || !chip->irq_set_type) { /* * IRQF_TRIGGER_* but the PIC does not support multiple * flow-types? */ pr_debug("No set_type function for IRQ %d (%s)\n", irq_desc_get_irq(desc), chip ? (chip->name ? : "unknown") : "unknown"); return 0; } if (chip->flags & IRQCHIP_SET_TYPE_MASKED) { if (!irqd_irq_masked(&desc->irq_data)) mask_irq(desc); if (!irqd_irq_disabled(&desc->irq_data)) unmask = 1; } /* Mask all flags except trigger mode */ flags &= IRQ_TYPE_SENSE_MASK; ret = chip->irq_set_type(&desc->irq_data, flags); switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK); irqd_set(&desc->irq_data, flags); fallthrough; case IRQ_SET_MASK_OK_NOCOPY: flags = irqd_get_trigger_type(&desc->irq_data); irq_settings_set_trigger_mask(desc, flags); irqd_clear(&desc->irq_data, IRQD_LEVEL); irq_settings_clr_level(desc); if (flags & IRQ_TYPE_LEVEL_MASK) { irq_settings_set_level(desc); irqd_set(&desc->irq_data, IRQD_LEVEL); } ret = 0; break; default: pr_err("Setting trigger mode %lu for irq %u failed (%pS)\n", flags, irq_desc_get_irq(desc), chip->irq_set_type); } if (unmask) unmask_irq(desc); return ret; } #ifdef CONFIG_HARDIRQS_SW_RESEND int irq_set_parent(int irq, int parent_irq) { scoped_irqdesc_get_and_lock(irq, 0) { scoped_irqdesc->parent_irq = parent_irq; return 0; } return -EINVAL; } EXPORT_SYMBOL_GPL(irq_set_parent); #endif /* * Default primary interrupt handler for threaded interrupts. Is * assigned as primary handler when request_threaded_irq is called * with handler == NULL. Useful for oneshot interrupts. */ static irqreturn_t irq_default_primary_handler(int irq, void *dev_id) { return IRQ_WAKE_THREAD; } /* * Primary handler for nested threaded interrupts. Should never be * called. */ static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id) { WARN(1, "Primary handler called for nested irq %d\n", irq); return IRQ_NONE; } static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id) { WARN(1, "Secondary action handler called for irq %d\n", irq); return IRQ_NONE; } #ifdef CONFIG_SMP /* * Check whether we need to change the affinity of the interrupt thread. */ static void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { cpumask_var_t mask; if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags)) return; __set_current_state(TASK_RUNNING); /* * In case we are out of memory we set IRQTF_AFFINITY again and * try again next time */ if (!alloc_cpumask_var(&mask, GFP_KERNEL)) { set_bit(IRQTF_AFFINITY, &action->thread_flags); return; } scoped_guard(raw_spinlock_irq, &desc->lock) { const struct cpumask *m; m = irq_data_get_effective_affinity_mask(&desc->irq_data); cpumask_copy(mask, m); } set_cpus_allowed_ptr(current, mask); free_cpumask_var(mask); } #else static inline void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { } #endif static int irq_wait_for_interrupt(struct irq_desc *desc, struct irqaction *action) { for (;;) { set_current_state(TASK_INTERRUPTIBLE); irq_thread_check_affinity(desc, action); if (kthread_should_stop()) { /* may need to run one last time */ if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) { __set_current_state(TASK_RUNNING); return 0; } __set_current_state(TASK_RUNNING); return -1; } if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) { __set_current_state(TASK_RUNNING); return 0; } schedule(); } } /* * Oneshot interrupts keep the irq line masked until the threaded * handler finished. unmask if the interrupt has not been disabled and * is marked MASKED. */ static void irq_finalize_oneshot(struct irq_desc *desc, struct irqaction *action) { if (!(desc->istate & IRQS_ONESHOT) || action->handler == irq_forced_secondary_handler) return; again: chip_bus_lock(desc); raw_spin_lock_irq(&desc->lock); /* * Implausible though it may be we need to protect us against * the following scenario: * * The thread is faster done than the hard interrupt handler * on the other CPU. If we unmask the irq line then the * interrupt can come in again and masks the line, leaves due * to IRQS_INPROGRESS and the irq line is masked forever. * * This also serializes the state of shared oneshot handlers * versus "desc->threads_oneshot |= action->thread_mask;" in * irq_wake_thread(). See the comment there which explains the * serialization. */ if (unlikely(irqd_irq_inprogress(&desc->irq_data))) { raw_spin_unlock_irq(&desc->lock); chip_bus_sync_unlock(desc); cpu_relax(); goto again; } /* * Now check again, whether the thread should run. Otherwise * we would clear the threads_oneshot bit of this thread which * was just set. */ if (test_bit(IRQTF_RUNTHREAD, &action->thread_flags)) goto out_unlock; desc->threads_oneshot &= ~action->thread_mask; if (!desc->threads_oneshot && !irqd_irq_disabled(&desc->irq_data) && irqd_irq_masked(&desc->irq_data)) unmask_threaded_irq(desc); out_unlock: raw_spin_unlock_irq(&desc->lock); chip_bus_sync_unlock(desc); } /* * Interrupts explicitly requested as threaded interrupts want to be * preemptible - many of them need to sleep and wait for slow busses to * complete. */ static irqreturn_t irq_thread_fn(struct irq_desc *desc, struct irqaction *action) { irqreturn_t ret = action->thread_fn(action->irq, action->dev_id); if (ret == IRQ_HANDLED) atomic_inc(&desc->threads_handled); irq_finalize_oneshot(desc, action); return ret; } /* * Interrupts which are not explicitly requested as threaded * interrupts rely on the implicit bh/preempt disable of the hard irq * context. So we need to disable bh here to avoid deadlocks and other * side effects. */ static irqreturn_t irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) { irqreturn_t ret; local_bh_disable(); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_disable(); ret = irq_thread_fn(desc, action); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_enable(); local_bh_enable(); return ret; } void wake_threads_waitq(struct irq_desc *desc) { if (atomic_dec_and_test(&desc->threads_active)) wake_up(&desc->wait_for_threads); } static void irq_thread_dtor(struct callback_head *unused) { struct task_struct *tsk = current; struct irq_desc *desc; struct irqaction *action; if (WARN_ON_ONCE(!(current->flags & PF_EXITING))) return; action = kthread_data(tsk); pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n", tsk->comm, tsk->pid, action->irq); desc = irq_to_desc(action->irq); /* * If IRQTF_RUNTHREAD is set, we need to decrement * desc->threads_active and wake possible waiters. */ if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) wake_threads_waitq(desc); /* Prevent a stale desc->threads_oneshot */ irq_finalize_oneshot(desc, action); } static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action) { struct irqaction *secondary = action->secondary; if (WARN_ON_ONCE(!secondary)) return; guard(raw_spinlock_irq)(&desc->lock); __irq_wake_thread(desc, secondary); } /* * Internal function to notify that a interrupt thread is ready. */ static void irq_thread_set_ready(struct irq_desc *desc, struct irqaction *action) { set_bit(IRQTF_READY, &action->thread_flags); wake_up(&desc->wait_for_threads); } /* * Internal function to wake up a interrupt thread and wait until it is * ready. */ static void wake_up_and_wait_for_irq_thread_ready(struct irq_desc *desc, struct irqaction *action) { if (!action || !action->thread) return; wake_up_process(action->thread); wait_event(desc->wait_for_threads, test_bit(IRQTF_READY, &action->thread_flags)); } /* * Interrupt handler thread */ static int irq_thread(void *data) { struct callback_head on_exit_work; struct irqaction *action = data; struct irq_desc *desc = irq_to_desc(action->irq); irqreturn_t (*handler_fn)(struct irq_desc *desc, struct irqaction *action); irq_thread_set_ready(desc, action); if (action->handler == irq_forced_secondary_handler) sched_set_fifo_secondary(current); else sched_set_fifo(current); if (force_irqthreads() && test_bit(IRQTF_FORCED_THREAD, &action->thread_flags)) handler_fn = irq_forced_thread_fn; else handler_fn = irq_thread_fn; init_task_work(&on_exit_work, irq_thread_dtor); task_work_add(current, &on_exit_work, TWA_NONE); while (!irq_wait_for_interrupt(desc, action)) { irqreturn_t action_ret; action_ret = handler_fn(desc, action); if (action_ret == IRQ_WAKE_THREAD) irq_wake_secondary(desc, action); wake_threads_waitq(desc); } /* * This is the regular exit path. __free_irq() is stopping the * thread via kthread_stop() after calling * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the * oneshot mask bit can be set. */ task_work_cancel_func(current, irq_thread_dtor); return 0; } /** * irq_wake_thread - wake the irq thread for the action identified by dev_id * @irq: Interrupt line * @dev_id: Device identity for which the thread should be woken */ void irq_wake_thread(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action; if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc))) return; guard(raw_spinlock_irqsave)(&desc->lock); for_each_action_of_desc(desc, action) { if (action->dev_id == dev_id) { if (action->thread) __irq_wake_thread(desc, action); break; } } } EXPORT_SYMBOL_GPL(irq_wake_thread); static int irq_setup_forced_threading(struct irqaction *new) { if (!force_irqthreads()) return 0; if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)) return 0; /* * No further action required for interrupts which are requested as * threaded interrupts already */ if (new->handler == irq_default_primary_handler) return 0; new->flags |= IRQF_ONESHOT; /* * Handle the case where we have a real primary handler and a * thread handler. We force thread them as well by creating a * secondary action. */ if (new->handler && new->thread_fn) { /* Allocate the secondary action */ new->secondary = kzalloc_obj(struct irqaction); if (!new->secondary) return -ENOMEM; new->secondary->handler = irq_forced_secondary_handler; new->secondary->thread_fn = new->thread_fn; new->secondary->dev_id = new->dev_id; new->secondary->irq = new->irq; new->secondary->name = new->name; } /* Deal with the primary handler */ set_bit(IRQTF_FORCED_THREAD, &new->thread_flags); new->thread_fn = new->handler; new->handler = irq_default_primary_handler; return 0; } static int irq_request_resources(struct irq_desc *desc) { struct irq_data *d = &desc->irq_data; struct irq_chip *c = d->chip; return c->irq_request_resources ? c->irq_request_resources(d) : 0; } static void irq_release_resources(struct irq_desc *desc) { struct irq_data *d = &desc->irq_data; struct irq_chip *c = d->chip; if (c->irq_release_resources) c->irq_release_resources(d); } static bool irq_supports_nmi(struct irq_desc *desc) { struct irq_data *d = irq_desc_get_irq_data(desc); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY /* Only IRQs directly managed by the root irqchip can be set as NMI */ if (d->parent_data) return false; #endif /* Don't support NMIs for chips behind a slow bus */ if (d->chip->irq_bus_lock || d->chip->irq_bus_sync_unlock) return false; return d->chip->flags & IRQCHIP_SUPPORTS_NMI; } static int irq_nmi_setup(struct irq_desc *desc) { struct irq_data *d = irq_desc_get_irq_data(desc); struct irq_chip *c = d->chip; return c->irq_nmi_setup ? c->irq_nmi_setup(d) : -EINVAL; } static void irq_nmi_teardown(struct irq_desc *desc) { struct irq_data *d = irq_desc_get_irq_data(desc); struct irq_chip *c = d->chip; if (c->irq_nmi_teardown) c->irq_nmi_teardown(d); } static int setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary) { struct task_struct *t; if (!secondary) { t = kthread_create(irq_thread, new, "irq/%d-%s", irq, new->name); } else { t = kthread_create(irq_thread, new, "irq/%d-s-%s", irq, new->name); } if (IS_ERR(t)) return PTR_ERR(t); /* * We keep the reference to the task struct even if * the thread dies to avoid that the interrupt code * references an already freed task_struct. */ new->thread = get_task_struct(t); /* * The affinity can not be established yet, but it will be once the * interrupt is enabled. Delay and defer the actual setting to the * thread itself once it is ready to run. In the meantime, prevent * it from ever being re-affined directly by cpuset or * housekeeping. The proper way to do it is to re-affine the whole * vector. */ kthread_bind_mask(t, cpu_possible_mask); /* * Ensure the thread adjusts the affinity once it reaches the * thread function. */ set_bit(IRQTF_AFFINITY, &new->thread_flags); return 0; } static bool valid_percpu_irqaction(struct irqaction *old, struct irqaction *new) { do { if (cpumask_intersects(old->affinity, new->affinity) || old->percpu_dev_id == new->percpu_dev_id) return false; old = old->next; } while (old); return true; } /* * Internal function to register an irqaction - typically used to * allocate special interrupts that are part of the architecture. * * Locking rules: * * desc->request_mutex Provides serialization against a concurrent free_irq() * chip_bus_lock Provides serialization for slow bus operations * desc->lock Provides serialization against hard interrupts * * chip_bus_lock and desc->lock are sufficient for all other management and * interrupt related functions. desc->request_mutex solely serializes * request/free_irq(). */ static int __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) { struct irqaction *old, **old_ptr; unsigned long flags, thread_mask = 0; int ret, nested, shared = 0; bool per_cpu_devid; if (!desc) return -EINVAL; if (desc->irq_data.chip == &no_irq_chip) return -ENOSYS; if (!try_module_get(desc->owner)) return -ENODEV; per_cpu_devid = irq_settings_is_per_cpu_devid(desc); new->irq = irq; /* * If the trigger type is not specified by the caller, * then use the default for this interrupt. */ if (!(new->flags & IRQF_TRIGGER_MASK)) new->flags |= irqd_get_trigger_type(&desc->irq_data); /* * IRQF_ONESHOT means the interrupt source in the IRQ chip will be * masked until the threaded handled is done. If there is no thread * handler then it makes no sense to have IRQF_ONESHOT. */ WARN_ON_ONCE(new->flags & IRQF_ONESHOT && !new->thread_fn); /* * Check whether the interrupt nests into another interrupt * thread. */ nested = irq_settings_is_nested_thread(desc); if (nested) { if (!new->thread_fn) { ret = -EINVAL; goto out_mput; } /* * Replace the primary handler which was provided from * the driver for non nested interrupt handling by the * dummy function which warns when called. */ new->handler = irq_nested_primary_handler; } else { if (irq_settings_can_thread(desc)) { ret = irq_setup_forced_threading(new); if (ret) goto out_mput; } } /* * Create a handler thread when a thread function is supplied * and the interrupt does not nest into another interrupt * thread. */ if (new->thread_fn && !nested) { ret = setup_irq_thread(new, irq, false); if (ret) goto out_mput; if (new->secondary) { ret = setup_irq_thread(new->secondary, irq, true); if (ret) goto out_thread; } } /* * Drivers are often written to work w/o knowledge about the * underlying irq chip implementation, so a request for a * threaded irq without a primary hard irq context handler * requires the ONESHOT flag to be set. Some irq chips like * MSI based interrupts are per se one shot safe. Check the * chip flags, so we can avoid the unmask dance at the end of * the threaded handler for those. */ if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE) new->flags &= ~IRQF_ONESHOT; /* * Protects against a concurrent __free_irq() call which might wait * for synchronize_hardirq() to complete without holding the optional * chip bus lock and desc->lock. Also protects against handing out * a recycled oneshot thread_mask bit while it's still in use by * its previous owner. */ mutex_lock(&desc->request_mutex); /* * Acquire bus lock as the irq_request_resources() callback below * might rely on the serialization or the magic power management * functions which are abusing the irq_bus_lock() callback, */ chip_bus_lock(desc); /* First installed action requests resources. */ if (!desc->action) { ret = irq_request_resources(desc); if (ret) { pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n", new->name, irq, desc->irq_data.chip->name); goto out_bus_unlock; } } /* * The following block of code has to be executed atomically * protected against a concurrent interrupt and any of the other * management calls which are not serialized via * desc->request_mutex or the optional bus lock. */ raw_spin_lock_irqsave(&desc->lock, flags); old_ptr = &desc->action; old = *old_ptr; if (old) { /* * Can't share interrupts unless both agree to and are * the same type (level, edge, polarity). So both flag * fields must have IRQF_SHARED set and the bits which * set the trigger type must match. Also all must * agree on ONESHOT. * Interrupt lines used for NMIs cannot be shared. */ unsigned int oldtype; if (irq_is_nmi(desc) && !per_cpu_devid) { pr_err("Invalid attempt to share NMI for %s (irq %d) on irqchip %s.\n", new->name, irq, desc->irq_data.chip->name); ret = -EINVAL; goto out_unlock; } if (per_cpu_devid && !valid_percpu_irqaction(old, new)) { pr_err("Overlapping affinities for %s (irq %d) on irqchip %s.\n", new->name, irq, desc->irq_data.chip->name); ret = -EINVAL; goto out_unlock; } /* * If nobody did set the configuration before, inherit * the one provided by the requester. */ if (irqd_trigger_type_was_set(&desc->irq_data)) { oldtype = irqd_get_trigger_type(&desc->irq_data); } else { oldtype = new->flags & IRQF_TRIGGER_MASK; irqd_set_trigger_type(&desc->irq_data, oldtype); } if (!((old->flags & new->flags) & IRQF_SHARED) || (oldtype != (new->flags & IRQF_TRIGGER_MASK))) goto mismatch; if ((old->flags & IRQF_ONESHOT) && (new->flags & IRQF_COND_ONESHOT)) new->flags |= IRQF_ONESHOT; else if ((old->flags ^ new->flags) & IRQF_ONESHOT) goto mismatch; /* All handlers must agree on per-cpuness */ if ((old->flags & IRQF_PERCPU) != (new->flags & IRQF_PERCPU)) goto mismatch; /* add new interrupt at end of irq queue */ do { /* * Or all existing action->thread_mask bits, * so we can find the next zero bit for this * new action. */ thread_mask |= old->thread_mask; old_ptr = &old->next; old = *old_ptr; } while (old); shared = 1; } /* * Setup the thread mask for this irqaction for ONESHOT. For * !ONESHOT irqs the thread mask is 0 so we can avoid a * conditional in irq_wake_thread(). */ if (new->flags & IRQF_ONESHOT) { /* * Unlikely to have 32 resp 64 irqs sharing one line, * but who knows. */ if (thread_mask == ~0UL) { ret = -EBUSY; goto out_unlock; } /* * The thread_mask for the action is or'ed to * desc->thread_active to indicate that the * IRQF_ONESHOT thread handler has been woken, but not * yet finished. The bit is cleared when a thread * completes. When all threads of a shared interrupt * line have completed desc->threads_active becomes * zero and the interrupt line is unmasked. See * handle.c:irq_wake_thread() for further information. * * If no thread is woken by primary (hard irq context) * interrupt handlers, then desc->threads_active is * also checked for zero to unmask the irq line in the * affected hard irq flow handlers * (handle_[fasteoi|level]_irq). * * The new action gets the first zero bit of * thread_mask assigned. See the loop above which or's * all existing action->thread_mask bits. */ new->thread_mask = 1UL << ffz(thread_mask); } else if (new->handler == irq_default_primary_handler && !(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) { /* * The interrupt was requested with handler = NULL, so * we use the default primary handler for it. But it * does not have the oneshot flag set. In combination * with level interrupts this is deadly, because the * default primary handler just wakes the thread, then * the irq lines is reenabled, but the device still * has the level irq asserted. Rinse and repeat.... * * While this works for edge type interrupts, we play * it safe and reject unconditionally because we can't * say for sure which type this interrupt really * has. The type flags are unreliable as the * underlying chip implementation can override them. */ pr_err("Threaded irq requested with handler=NULL and !ONESHOT for %s (irq %d)\n", new->name, irq); ret = -EINVAL; goto out_unlock; } if (!shared) { /* Setup the type (level, edge polarity) if configured: */ if (new->flags & IRQF_TRIGGER_MASK) { ret = __irq_set_trigger(desc, new->flags & IRQF_TRIGGER_MASK); if (ret) goto out_unlock; } /* * Activate the interrupt. That activation must happen * independently of IRQ_NOAUTOEN. request_irq() can fail * and the callers are supposed to handle * that. enable_irq() of an interrupt requested with * IRQ_NOAUTOEN is not supposed to fail. The activation * keeps it in shutdown mode, it merily associates * resources if necessary and if that's not possible it * fails. Interrupts which are in managed shutdown mode * will simply ignore that activation request. */ ret = irq_activate(desc); if (ret) goto out_unlock; desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \ IRQS_ONESHOT | IRQS_WAITING); irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); if (new->flags & IRQF_PERCPU) { irqd_set(&desc->irq_data, IRQD_PER_CPU); irq_settings_set_per_cpu(desc); if (new->flags & IRQF_NO_DEBUG) irq_settings_set_no_debug(desc); } if (noirqdebug) irq_settings_set_no_debug(desc); if (new->flags & IRQF_ONESHOT) desc->istate |= IRQS_ONESHOT; /* Exclude IRQ from balancing if requested */ if (new->flags & IRQF_NOBALANCING) { irq_settings_set_no_balancing(desc); irqd_set(&desc->irq_data, IRQD_NO_BALANCING); } if (!(new->flags & IRQF_NO_AUTOEN) && irq_settings_can_autoenable(desc)) { irq_startup(desc, IRQ_RESEND, IRQ_START_COND); } else if (!per_cpu_devid) { /* * Shared interrupts do not go well with disabling * auto enable. The sharing interrupt might request * it while it's still disabled and then wait for * interrupts forever. */ WARN_ON_ONCE(new->flags & IRQF_SHARED); /* Undo nested disables: */ desc->depth = 1; } } else if (new->flags & IRQF_TRIGGER_MASK) { unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK; unsigned int omsk = irqd_get_trigger_type(&desc->irq_data); if (nmsk != omsk) /* hope the handler works with current trigger mode */ pr_warn("irq %d uses trigger mode %u; requested %u\n", irq, omsk, nmsk); } *old_ptr = new; irq_pm_install_action(desc, new); /* Reset broken irq detection when installing new handler */ desc->irq_count = 0; desc->irqs_unhandled = 0; /* * Check whether we disabled the irq via the spurious handler * before. Reenable it and give it another chance. */ if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) { desc->istate &= ~IRQS_SPURIOUS_DISABLED; __enable_irq(desc); } irq_proc_update_valid(desc); raw_spin_unlock_irqrestore(&desc->lock, flags); chip_bus_sync_unlock(desc); mutex_unlock(&desc->request_mutex); wake_up_and_wait_for_irq_thread_ready(desc, new); wake_up_and_wait_for_irq_thread_ready(desc, new->secondary); register_irq_proc(irq, desc); new->dir = NULL; register_handler_proc(irq, new); return 0; mismatch: if (!(new->flags & IRQF_PROBE_SHARED)) { pr_err("Flags mismatch irq %d. %08x (%s) vs. %08x (%s)\n", irq, new->flags, new->name, old->flags, old->name); #ifdef CONFIG_DEBUG_SHIRQ dump_stack(); #endif } ret = -EBUSY; out_unlock: raw_spin_unlock_irqrestore(&desc->lock, flags); if (!desc->action) irq_release_resources(desc); out_bus_unlock: chip_bus_sync_unlock(desc); mutex_unlock(&desc->request_mutex); out_thread: if (new->thread) { struct task_struct *t = new->thread; new->thread = NULL; kthread_stop_put(t); } if (new->secondary && new->secondary->thread) { struct task_struct *t = new->secondary->thread; new->secondary->thread = NULL; kthread_stop_put(t); } out_mput: module_put(desc->owner); return ret; } /* * Internal function to unregister an irqaction - used to free * regular and special interrupts that are part of the architecture. */ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) { unsigned irq = desc->irq_data.irq; struct irqaction *action, **action_ptr; unsigned long flags; WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); mutex_lock(&desc->request_mutex); chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, flags); /* * There can be multiple actions per IRQ descriptor, find the right * one based on the dev_id: */ action_ptr = &desc->action; for (;;) { action = *action_ptr; if (!action) { WARN(1, "Trying to free already-free IRQ %d\n", irq); raw_spin_unlock_irqrestore(&desc->lock, flags); chip_bus_sync_unlock(desc); mutex_unlock(&desc->request_mutex); return NULL; } if (action->dev_id == dev_id) break; action_ptr = &action->next; } /* Found it - now remove it from the list of entries: */ *action_ptr = action->next; irq_pm_remove_action(desc, action); /* If this was the last handler, shut down the IRQ line: */ if (!desc->action) { irq_settings_clr_disable_unlazy(desc); /* Only shutdown. Deactivate after synchronize_hardirq() */ irq_shutdown(desc); } #ifdef CONFIG_SMP /* make sure affinity_hint is cleaned up */ if (WARN_ON_ONCE(desc->affinity_hint)) desc->affinity_hint = NULL; #endif irq_proc_update_valid(desc); raw_spin_unlock_irqrestore(&desc->lock, flags); /* * Drop bus_lock here so the changes which were done in the chip * callbacks above are synced out to the irq chips which hang * behind a slow bus (I2C, SPI) before calling synchronize_hardirq(). * * Aside of that the bus_lock can also be taken from the threaded * handler in irq_finalize_oneshot() which results in a deadlock * because kthread_stop() would wait forever for the thread to * complete, which is blocked on the bus lock. * * The still held desc->request_mutex() protects against a * concurrent request_irq() of this irq so the release of resources * and timing data is properly serialized. */ chip_bus_sync_unlock(desc); unregister_handler_proc(irq, action); /* * Make sure it's not being used on another CPU and if the chip * supports it also make sure that there is no (not yet serviced) * interrupt in flight at the hardware level. */ __synchronize_irq(desc); #ifdef CONFIG_DEBUG_SHIRQ /* * It's a shared IRQ -- the driver ought to be prepared for an IRQ * event to happen even now it's being freed, so let's make sure that * is so by doing an extra call to the handler .... * * ( We do this after actually deregistering it, to make sure that a * 'real' IRQ doesn't run in parallel with our fake. ) */ if (action->flags & IRQF_SHARED) { local_irq_save(flags); action->handler(irq, dev_id); local_irq_restore(flags); } #endif /* * The action has already been removed above, but the thread writes * its oneshot mask bit when it completes. Though request_mutex is * held across this which prevents __setup_irq() from handing out * the same bit to a newly requested action. */ if (action->thread) { kthread_stop_put(action->thread); if (action->secondary && action->secondary->thread) kthread_stop_put(action->secondary->thread); } /* Last action releases resources */ if (!desc->action) { /* * Reacquire bus lock as irq_release_resources() might * require it to deallocate resources over the slow bus. */ chip_bus_lock(desc); /* * There is no interrupt on the fly anymore. Deactivate it * completely. */ scoped_guard(raw_spinlock_irqsave, &desc->lock) irq_domain_deactivate_irq(&desc->irq_data); irq_release_resources(desc); chip_bus_sync_unlock(desc); } mutex_unlock(&desc->request_mutex); irq_chip_pm_put(&desc->irq_data); module_put(desc->owner); kfree(action->secondary); return action; } /** * free_irq - free an interrupt allocated with request_irq * @irq: Interrupt line to free * @dev_id: Device identity to free * * Remove an interrupt handler. The handler is removed and if the interrupt * line is no longer in use by any driver it is disabled. On a shared IRQ * the caller must ensure the interrupt is disabled on the card it drives * before calling this function. The function does not return until any * executing interrupts for this IRQ have completed. * * This function must not be called from interrupt context. * * Returns the devname argument passed to request_irq. */ const void *free_irq(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action; const char *devname; if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc))) return NULL; #ifdef CONFIG_SMP if (WARN_ON(desc->affinity_notify)) desc->affinity_notify = NULL; #endif action = __free_irq(desc, dev_id); if (!action) return NULL; devname = action->name; kfree(action); return devname; } EXPORT_SYMBOL(free_irq); static const void *__cleanup_nmi(unsigned int irq, struct irq_desc *desc) { struct irqaction *action = NULL; const char *devname = NULL; scoped_guard(raw_spinlock_irqsave, &desc->lock) { irq_nmi_teardown(desc); desc->istate &= ~IRQS_NMI; if (!WARN_ON(desc->action == NULL)) { action = desc->action; irq_pm_remove_action(desc, action); devname = action->name; } desc->action = NULL; irq_settings_clr_disable_unlazy(desc); irq_shutdown_and_deactivate(desc); } irq_proc_update_valid(desc); if (action) unregister_handler_proc(irq, action); kfree(action); irq_release_resources(desc); irq_chip_pm_put(&desc->irq_data); module_put(desc->owner); return devname; } const void *free_nmi(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || WARN_ON(!irq_is_nmi(desc))) return NULL; if (WARN_ON(irq_settings_is_per_cpu_devid(desc))) return NULL; /* NMI still enabled */ if (WARN_ON(desc->depth == 0)) disable_nmi_nosync(irq); return __cleanup_nmi(irq, desc); } /** * request_threaded_irq - allocate an interrupt line * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * Primary handler for threaded interrupts. * If handler is NULL and thread_fn != NULL * the default primary handler is installed. * @thread_fn: Function called from the irq handler thread * If NULL, no irq thread is created * @irqflags: Interrupt type flags * @devname: An ascii name for the claiming device * @dev_id: A cookie passed back to the handler function * * This call allocates interrupt resources and enables the interrupt line * and IRQ handling. From the point this call is made your handler function * may be invoked. Since your handler function must clear any interrupt the * board raises, you must take care both to initialise your hardware and to * set up the interrupt handler in the right order. * * If you want to set up a threaded irq handler for your device then you * need to supply @handler and @thread_fn. @handler is still called in hard * interrupt context and has to check whether the interrupt originates from * the device. If yes it needs to disable the interrupt on the device and * return IRQ_WAKE_THREAD which will wake up the handler thread and run * @thread_fn. This split handler design is necessary to support shared * interrupts. * * @dev_id must be globally unique. Normally the address of the device data * structure is used as the cookie. Since the handler receives this value * it makes sense to use it. * * If your interrupt is shared you must pass a non NULL dev_id as this is * required when freeing the interrupt. * * Flags: * * IRQF_SHARED Interrupt is shared * IRQF_TRIGGER_* Specify active edge(s) or level * IRQF_ONESHOT Run thread_fn with interrupt line masked */ int request_threaded_irq(unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, unsigned long irqflags, const char *devname, void *dev_id) { struct irqaction *action; struct irq_desc *desc; int retval; if (irq == IRQ_NOTCONNECTED) return -ENOTCONN; /* * Sanity-check: shared interrupts must pass in a real dev-ID, * otherwise we'll have trouble later trying to figure out * which interrupt is which (messes up the interrupt freeing * logic etc). * * Also shared interrupts do not go well with disabling auto enable. * The sharing interrupt might request it while it's still disabled * and then wait for interrupts forever. * * Also IRQF_COND_SUSPEND only makes sense for shared interrupts and * it cannot be set along with IRQF_NO_SUSPEND. */ if (((irqflags & IRQF_SHARED) && !dev_id) || ((irqflags & IRQF_SHARED) && (irqflags & IRQF_NO_AUTOEN)) || (!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) || ((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND))) return -EINVAL; desc = irq_to_desc(irq); if (!desc) return -EINVAL; if (!irq_settings_can_request(desc) || WARN_ON(irq_settings_is_per_cpu_devid(desc))) return -EINVAL; if (!handler) { if (!thread_fn) return -EINVAL; handler = irq_default_primary_handler; } action = kzalloc_obj(struct irqaction); if (!action) return -ENOMEM; action->handler = handler; action->thread_fn = thread_fn; action->flags = irqflags; action->name = devname; action->dev_id = dev_id; retval = irq_chip_pm_get(&desc->irq_data); if (retval < 0) { kfree(action); return retval; } retval = __setup_irq(irq, desc, action); if (retval) { irq_chip_pm_put(&desc->irq_data); kfree(action->secondary); kfree(action); } #ifdef CONFIG_DEBUG_SHIRQ_FIXME if (!retval && (irqflags & IRQF_SHARED)) { /* * It's a shared IRQ -- the driver ought to be prepared for it * to happen immediately, so let's make sure.... * We disable the irq to make sure that a 'real' IRQ doesn't * run in parallel with our fake. */ unsigned long flags; disable_irq(irq); local_irq_save(flags); handler(irq, dev_id); local_irq_restore(flags); enable_irq(irq); } #endif return retval; } EXPORT_SYMBOL(request_threaded_irq); /** * request_any_context_irq - allocate an interrupt line * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * Threaded handler for threaded interrupts. * @flags: Interrupt type flags * @name: An ascii name for the claiming device * @dev_id: A cookie passed back to the handler function * * This call allocates interrupt resources and enables the interrupt line * and IRQ handling. It selects either a hardirq or threaded handling * method depending on the context. * * Returns: On failure, it returns a negative value. On success, it returns either * IRQC_IS_HARDIRQ or IRQC_IS_NESTED. */ int request_any_context_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev_id) { struct irq_desc *desc; int ret; if (irq == IRQ_NOTCONNECTED) return -ENOTCONN; desc = irq_to_desc(irq); if (!desc) return -EINVAL; if (irq_settings_is_nested_thread(desc)) { ret = request_threaded_irq(irq, NULL, handler, flags, name, dev_id); return !ret ? IRQC_IS_NESTED : ret; } ret = request_irq(irq, handler, flags, name, dev_id); return !ret ? IRQC_IS_HARDIRQ : ret; } EXPORT_SYMBOL_GPL(request_any_context_irq); /** * request_nmi - allocate an interrupt line for NMI delivery * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * Threaded handler for threaded interrupts. * @irqflags: Interrupt type flags * @name: An ascii name for the claiming device * @dev_id: A cookie passed back to the handler function * * This call allocates interrupt resources and enables the interrupt line * and IRQ handling. It sets up the IRQ line to be handled as an NMI. * * An interrupt line delivering NMIs cannot be shared and IRQ handling * cannot be threaded. * * Interrupt lines requested for NMI delivering must produce per cpu * interrupts and have auto enabling setting disabled. * * @dev_id must be globally unique. Normally the address of the device data * structure is used as the cookie. Since the handler receives this value * it makes sense to use it. * * If the interrupt line cannot be used to deliver NMIs, function will fail * and return a negative value. */ int request_nmi(unsigned int irq, irq_handler_t handler, unsigned long irqflags, const char *name, void *dev_id) { struct irqaction *action; struct irq_desc *desc; int retval; if (irq == IRQ_NOTCONNECTED) return -ENOTCONN; /* NMI cannot be shared, used for Polling */ if (irqflags & (IRQF_SHARED | IRQF_COND_SUSPEND | IRQF_IRQPOLL)) return -EINVAL; if (!(irqflags & IRQF_PERCPU)) return -EINVAL; if (!handler) return -EINVAL; desc = irq_to_desc(irq); if (!desc || (irq_settings_can_autoenable(desc) && !(irqflags & IRQF_NO_AUTOEN)) || !irq_settings_can_request(desc) || WARN_ON(irq_settings_is_per_cpu_devid(desc)) || !irq_supports_nmi(desc)) return -EINVAL; action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!action) return -ENOMEM; action->handler = handler; action->flags = irqflags | IRQF_NO_THREAD | IRQF_NOBALANCING; action->name = name; action->dev_id = dev_id; retval = irq_chip_pm_get(&desc->irq_data); if (retval < 0) goto err_out; retval = __setup_irq(irq, desc, action); if (retval) goto err_irq_setup; scoped_guard(raw_spinlock_irqsave, &desc->lock) { /* Setup NMI state */ desc->istate |= IRQS_NMI; retval = irq_nmi_setup(desc); } if (retval) { __cleanup_nmi(irq, desc); return -EINVAL; } return 0; err_irq_setup: irq_chip_pm_put(&desc->irq_data); err_out: kfree(action); return retval; } void enable_percpu_irq(unsigned int irq, unsigned int type) { scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) { struct irq_desc *desc = scoped_irqdesc; /* * If the trigger type is not specified by the caller, then * use the default for this interrupt. */ type &= IRQ_TYPE_SENSE_MASK; if (type == IRQ_TYPE_NONE) type = irqd_get_trigger_type(&desc->irq_data); if (type != IRQ_TYPE_NONE) { if (__irq_set_trigger(desc, type)) { WARN(1, "failed to set type for IRQ%d\n", irq); return; } } irq_percpu_enable(desc, smp_processor_id()); } } EXPORT_SYMBOL_GPL(enable_percpu_irq); void enable_percpu_nmi(unsigned int irq, unsigned int type) { enable_percpu_irq(irq, type); } /** * irq_percpu_is_enabled - Check whether the per cpu irq is enabled * @irq: Linux irq number to check for * * Must be called from a non migratable context. Returns the enable * state of a per cpu interrupt on the current cpu. */ bool irq_percpu_is_enabled(unsigned int irq) { scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) return cpumask_test_cpu(smp_processor_id(), scoped_irqdesc->percpu_enabled); return false; } EXPORT_SYMBOL_GPL(irq_percpu_is_enabled); void disable_percpu_irq(unsigned int irq) { scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) irq_percpu_disable(scoped_irqdesc, smp_processor_id()); } EXPORT_SYMBOL_GPL(disable_percpu_irq); void disable_percpu_nmi(unsigned int irq) { disable_percpu_irq(irq); } /* * Internal function to unregister a percpu irqaction. */ static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_id) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action, **action_ptr; WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); if (!desc) return NULL; scoped_guard(raw_spinlock_irqsave, &desc->lock) { action_ptr = &desc->action; for (;;) { action = *action_ptr; if (!action) { WARN(1, "Trying to free already-free IRQ %d\n", irq); return NULL; } if (action->percpu_dev_id == dev_id) break; action_ptr = &action->next; } if (cpumask_intersects(desc->percpu_enabled, action->affinity)) { WARN(1, "percpu IRQ %d still enabled on CPU%d!\n", irq, cpumask_first_and(desc->percpu_enabled, action->affinity)); return NULL; } /* Found it - now remove it from the list of entries: */ *action_ptr = action->next; /* Demote from NMI if we killed the last action */ if (!desc->action) { desc->istate &= ~IRQS_NMI; irq_proc_update_valid(desc); } } unregister_handler_proc(irq, action); irq_chip_pm_put(&desc->irq_data); module_put(desc->owner); return action; } /** * free_percpu_irq - free an interrupt allocated with request_percpu_irq * @irq: Interrupt line to free * @dev_id: Device identity to free * * Remove a percpu interrupt handler. The handler is removed, but the * interrupt line is not disabled. This must be done on each CPU before * calling this function. The function does not return until any executing * interrupts for this IRQ have completed. * * This function must not be called from interrupt context. */ void free_percpu_irq(unsigned int irq, void __percpu *dev_id) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !irq_settings_is_per_cpu_devid(desc)) return; chip_bus_lock(desc); kfree(__free_percpu_irq(irq, dev_id)); chip_bus_sync_unlock(desc); } EXPORT_SYMBOL_GPL(free_percpu_irq); void free_percpu_nmi(unsigned int irq, void __percpu *dev_id) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !irq_settings_is_per_cpu_devid(desc)) return; if (WARN_ON(!irq_is_nmi(desc))) return; kfree(__free_percpu_irq(irq, dev_id)); } static struct irqaction *create_percpu_irqaction(irq_handler_t handler, unsigned long flags, const char *devname, const cpumask_t *affinity, void __percpu *dev_id) { struct irqaction *action; if (!affinity) affinity = cpu_possible_mask; action = kzalloc_obj(struct irqaction); if (!action) return NULL; action->handler = handler; action->flags = flags | IRQF_PERCPU | IRQF_NO_SUSPEND; action->name = devname; action->percpu_dev_id = dev_id; action->affinity = affinity; /* * We allow some form of sharing for non-overlapping affinity * masks. Obviously, covering all CPUs prevents any sharing in * the first place. */ if (!cpumask_equal(affinity, cpu_possible_mask)) action->flags |= IRQF_SHARED; return action; } /** * request_percpu_irq_affinity - allocate a percpu interrupt line * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * @devname: An ascii name for the claiming device * @affinity: A cpumask describing the target CPUs for this interrupt * @dev_id: A percpu cookie passed back to the handler function * * This call allocates interrupt resources, but doesn't enable the interrupt * on any CPU, as all percpu-devid interrupts are flagged with IRQ_NOAUTOEN. * It has to be done on each CPU using enable_percpu_irq(). * * @dev_id must be globally unique. It is a per-cpu variable, and * the handler gets called with the interrupted CPU's instance of * that variable. */ int request_percpu_irq_affinity(unsigned int irq, irq_handler_t handler, const char *devname, const cpumask_t *affinity, void __percpu *dev_id) { struct irqaction *action; struct irq_desc *desc; int retval; if (!dev_id) return -EINVAL; desc = irq_to_desc(irq); if (!desc || !irq_settings_can_request(desc) || !irq_settings_is_per_cpu_devid(desc)) return -EINVAL; action = create_percpu_irqaction(handler, 0, devname, affinity, dev_id); if (!action) return -ENOMEM; retval = irq_chip_pm_get(&desc->irq_data); if (retval < 0) { kfree(action); return retval; } retval = __setup_irq(irq, desc, action); if (retval) { irq_chip_pm_put(&desc->irq_data); kfree(action); } return retval; } EXPORT_SYMBOL_GPL(request_percpu_irq_affinity); /** * request_percpu_nmi - allocate a percpu interrupt line for NMI delivery * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * @name: An ascii name for the claiming device * @affinity: A cpumask describing the target CPUs for this interrupt * @dev_id: A percpu cookie passed back to the handler function * * This call allocates interrupt resources for a per CPU NMI. Per CPU NMIs * have to be setup on each CPU by calling prepare_percpu_nmi() before * being enabled on the same CPU by using enable_percpu_nmi(). * * @dev_id must be globally unique. It is a per-cpu variable, and the * handler gets called with the interrupted CPU's instance of that * variable. * * Interrupt lines requested for NMI delivering should have auto enabling * setting disabled. * * If the interrupt line cannot be used to deliver NMIs, function * will fail returning a negative value. */ int request_percpu_nmi(unsigned int irq, irq_handler_t handler, const char *name, const struct cpumask *affinity, void __percpu *dev_id) { struct irqaction *action; struct irq_desc *desc; int retval; if (!handler) return -EINVAL; desc = irq_to_desc(irq); if (!desc || !irq_settings_can_request(desc) || !irq_settings_is_per_cpu_devid(desc) || irq_settings_can_autoenable(desc) || !irq_supports_nmi(desc)) return -EINVAL; /* The line cannot be NMI already if the new request covers all CPUs */ if (irq_is_nmi(desc) && (!affinity || cpumask_equal(affinity, cpu_possible_mask))) return -EINVAL; action = create_percpu_irqaction(handler, IRQF_NO_THREAD | IRQF_NOBALANCING, name, affinity, dev_id); if (!action) return -ENOMEM; retval = irq_chip_pm_get(&desc->irq_data); if (retval < 0) goto err_out; retval = __setup_irq(irq, desc, action); if (retval) goto err_irq_setup; scoped_guard(raw_spinlock_irqsave, &desc->lock) desc->istate |= IRQS_NMI; return 0; err_irq_setup: irq_chip_pm_put(&desc->irq_data); err_out: kfree(action); return retval; } /** * prepare_percpu_nmi - performs CPU local setup for NMI delivery * @irq: Interrupt line to prepare for NMI delivery * * This call prepares an interrupt line to deliver NMI on the current CPU, * before that interrupt line gets enabled with enable_percpu_nmi(). * * As a CPU local operation, this should be called from non-preemptible * context. * * If the interrupt line cannot be used to deliver NMIs, function will fail * returning a negative value. */ int prepare_percpu_nmi(unsigned int irq) { int ret = -EINVAL; WARN_ON(preemptible()); scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) { if (WARN(!irq_is_nmi(scoped_irqdesc), "prepare_percpu_nmi called for a non-NMI interrupt: irq %u\n", irq)) return -EINVAL; ret = irq_nmi_setup(scoped_irqdesc); if (ret) pr_err("Failed to setup NMI delivery: irq %u\n", irq); } return ret; } /** * teardown_percpu_nmi - undoes NMI setup of IRQ line * @irq: Interrupt line from which CPU local NMI configuration should be removed * * This call undoes the setup done by prepare_percpu_nmi(). * * IRQ line should not be enabled for the current CPU. * As a CPU local operation, this should be called from non-preemptible * context. */ void teardown_percpu_nmi(unsigned int irq) { WARN_ON(preemptible()); scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) { if (WARN_ON(!irq_is_nmi(scoped_irqdesc))) return; irq_nmi_teardown(scoped_irqdesc); } } static int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which, bool *state) { struct irq_chip *chip; int err = -EINVAL; do { chip = irq_data_get_irq_chip(data); if (WARN_ON_ONCE(!chip)) return -ENODEV; if (chip->irq_get_irqchip_state) break; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY data = data->parent_data; #else data = NULL; #endif } while (data); if (data) err = chip->irq_get_irqchip_state(data, which, state); return err; } /** * irq_get_irqchip_state - returns the irqchip state of a interrupt. * @irq: Interrupt line that is forwarded to a VM * @which: One of IRQCHIP_STATE_* the caller wants to know about * @state: a pointer to a boolean where the state is to be stored * * This call snapshots the internal irqchip state of an interrupt, * returning into @state the bit corresponding to stage @which * * This function should be called with preemption disabled if the interrupt * controller has per-cpu registers. */ int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which, bool *state) { scoped_irqdesc_get_and_buslock(irq, 0) { struct irq_data *data = irq_desc_get_irq_data(scoped_irqdesc); return __irq_get_irqchip_state(data, which, state); } return -EINVAL; } EXPORT_SYMBOL_GPL(irq_get_irqchip_state); /** * irq_set_irqchip_state - set the state of a forwarded interrupt. * @irq: Interrupt line that is forwarded to a VM * @which: State to be restored (one of IRQCHIP_STATE_*) * @val: Value corresponding to @which * * This call sets the internal irqchip state of an interrupt, depending on * the value of @which. * * This function should be called with migration disabled if the interrupt * controller has per-cpu registers. */ int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, bool val) { scoped_irqdesc_get_and_buslock(irq, 0) { struct irq_data *data = irq_desc_get_irq_data(scoped_irqdesc); struct irq_chip *chip; do { chip = irq_data_get_irq_chip(data); if (WARN_ON_ONCE(!chip)) return -ENODEV; if (chip->irq_set_irqchip_state) break; data = irqd_get_parent_data(data); } while (data); if (data) return chip->irq_set_irqchip_state(data, which, val); } return -EINVAL; } EXPORT_SYMBOL_GPL(irq_set_irqchip_state); /** * irq_has_action - Check whether an interrupt is requested * @irq: The linux irq number * * Returns: A snapshot of the current state */ bool irq_has_action(unsigned int irq) { bool res; rcu_read_lock(); res = irq_desc_has_action(irq_to_desc(irq)); rcu_read_unlock(); return res; } EXPORT_SYMBOL_GPL(irq_has_action); /** * irq_check_status_bit - Check whether bits in the irq descriptor status are set * @irq: The linux irq number * @bitmask: The bitmask to evaluate * * Returns: True if one of the bits in @bitmask is set */ bool irq_check_status_bit(unsigned int irq, unsigned int bitmask) { struct irq_desc *desc; bool res = false; rcu_read_lock(); desc = irq_to_desc(irq); if (desc) res = !!(desc->status_use_accessors & bitmask); rcu_read_unlock(); return res; } EXPORT_SYMBOL_GPL(irq_check_status_bit); |
| 45 60 12 12 10 307 308 300 51 51 46 45 44 45 45 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * The "user cache". * * (C) Copyright 1991-2000 Linus Torvalds * * We have a per-user structure to keep track of how many * processes, files etc the user has claimed, in order to be * able to have per-user limits for system resources. */ #include <linux/init.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/bitops.h> #include <linux/key.h> #include <linux/sched/user.h> #include <linux/interrupt.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/proc_ns.h> #if IS_ENABLED(CONFIG_BINFMT_MISC) struct binfmt_misc init_binfmt_misc = { .entries = LIST_HEAD_INIT(init_binfmt_misc.entries), .enabled = true, .entries_lock = __RW_LOCK_UNLOCKED(init_binfmt_misc.entries_lock), }; EXPORT_SYMBOL_GPL(init_binfmt_misc); #endif /* * userns count is 1 for root user, 1 for init_uts_ns, * and 1 for... ? */ struct user_namespace init_user_ns = { .ns = NS_COMMON_INIT(init_user_ns), .uid_map = { { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, .nr_extents = 1, }, }, .gid_map = { { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, .nr_extents = 1, }, }, .projid_map = { { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, .nr_extents = 1, }, }, .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, .flags = USERNS_INIT_FLAGS, #ifdef CONFIG_KEYS .keyring_name_list = LIST_HEAD_INIT(init_user_ns.keyring_name_list), .keyring_sem = __RWSEM_INITIALIZER(init_user_ns.keyring_sem), #endif #if IS_ENABLED(CONFIG_BINFMT_MISC) .binfmt_misc = &init_binfmt_misc, #endif }; EXPORT_SYMBOL_GPL(init_user_ns); /* * UID task count cache, to get fast user lookup in "alloc_uid" * when changing user ID's (ie setuid() and friends). */ #define UIDHASH_BITS (IS_ENABLED(CONFIG_BASE_SMALL) ? 3 : 7) #define UIDHASH_SZ (1 << UIDHASH_BITS) #define UIDHASH_MASK (UIDHASH_SZ - 1) #define __uidhashfn(uid) (((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK) #define uidhashentry(uid) (uidhash_table + __uidhashfn((__kuid_val(uid)))) static struct kmem_cache *uid_cachep; static struct hlist_head uidhash_table[UIDHASH_SZ]; /* * The uidhash_lock is mostly taken from process context, but it is * occasionally also taken from softirq/tasklet context, when * task-structs get RCU-freed. Hence all locking must be softirq-safe. * But free_uid() is also called with local interrupts disabled, and running * local_bh_enable() with local interrupts disabled is an error - we'll run * softirq callbacks, and they can unconditionally enable interrupts, and * the caller of free_uid() didn't expect that.. */ static DEFINE_SPINLOCK(uidhash_lock); /* root_user.__count is 1, for init task cred */ struct user_struct root_user = { .__count = REFCOUNT_INIT(1), .uid = GLOBAL_ROOT_UID, .ratelimit = RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0), }; /* * These routines must be called with the uidhash spinlock held! */ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent) { hlist_add_head(&up->uidhash_node, hashent); } static void uid_hash_remove(struct user_struct *up) { hlist_del_init(&up->uidhash_node); } static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent) { struct user_struct *user; hlist_for_each_entry(user, hashent, uidhash_node) { if (uid_eq(user->uid, uid)) { refcount_inc(&user->__count); return user; } } return NULL; } static int user_epoll_alloc(struct user_struct *up) { #ifdef CONFIG_EPOLL return percpu_counter_init(&up->epoll_watches, 0, GFP_KERNEL); #else return 0; #endif } static void user_epoll_free(struct user_struct *up) { #ifdef CONFIG_EPOLL percpu_counter_destroy(&up->epoll_watches); #endif } /* IRQs are disabled and uidhash_lock is held upon function entry. * IRQ state (as stored in flags) is restored and uidhash_lock released * upon function exit. */ static void free_user(struct user_struct *up, unsigned long flags) __releases(&uidhash_lock) { uid_hash_remove(up); spin_unlock_irqrestore(&uidhash_lock, flags); user_epoll_free(up); kmem_cache_free(uid_cachep, up); } /* * Locate the user_struct for the passed UID. If found, take a ref on it. The * caller must undo that ref with free_uid(). * * If the user_struct could not be found, return NULL. */ struct user_struct *find_user(kuid_t uid) { struct user_struct *ret; unsigned long flags; spin_lock_irqsave(&uidhash_lock, flags); ret = uid_hash_find(uid, uidhashentry(uid)); spin_unlock_irqrestore(&uidhash_lock, flags); return ret; } void free_uid(struct user_struct *up) { unsigned long flags; if (!up) return; if (refcount_dec_and_lock_irqsave(&up->__count, &uidhash_lock, &flags)) free_user(up, flags); } EXPORT_SYMBOL_GPL(free_uid); struct user_struct *alloc_uid(kuid_t uid) { struct hlist_head *hashent = uidhashentry(uid); struct user_struct *up, *new; spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); spin_unlock_irq(&uidhash_lock); if (!up) { new = kmem_cache_zalloc(uid_cachep, GFP_KERNEL); if (!new) return NULL; new->uid = uid; refcount_set(&new->__count, 1); if (user_epoll_alloc(new)) { kmem_cache_free(uid_cachep, new); return NULL; } ratelimit_state_init(&new->ratelimit, HZ, 100); ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE); /* * Before adding this, check whether we raced * on adding the same user already.. */ spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); if (up) { user_epoll_free(new); kmem_cache_free(uid_cachep, new); } else { uid_hash_insert(new, hashent); up = new; } spin_unlock_irq(&uidhash_lock); } return up; } static int __init uid_cache_init(void) { int n; uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); for(n = 0; n < UIDHASH_SZ; ++n) INIT_HLIST_HEAD(uidhash_table + n); if (user_epoll_alloc(&root_user)) panic("root_user epoll percpu counter alloc failed"); /* Insert the root user immediately (init already runs as root) */ spin_lock_irq(&uidhash_lock); uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID)); spin_unlock_irq(&uidhash_lock); return 0; } subsys_initcall(uid_cache_init); |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(c) 2014 Intel Mobile Communications GmbH * Copyright(c) 2015 Intel Deutschland GmbH * * Author: Johannes Berg <johannes@sipsolutions.net> */ #include <linux/module.h> #include <linux/device.h> #include <linux/devcoredump.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/workqueue.h> static struct class devcd_class; /* global disable flag, for security purposes */ static bool devcd_disabled; struct devcd_entry { struct device devcd_dev; void *data; size_t datalen; /* * There are 2 races for which mutex is required. * * The first race is between device creation and userspace writing to * schedule immediately destruction. * * This race is handled by arming the timer before device creation, but * when device creation fails the timer still exists. * * To solve this, hold the mutex during device_add(), and set * init_completed on success before releasing the mutex. * * That way the timer will never fire until device_add() is called, * it will do nothing if init_completed is not set. The timer is also * cancelled in that case. * * The second race involves multiple parallel invocations of devcd_free(), * add a deleted flag so only 1 can call the destructor. */ struct mutex mutex; bool init_completed, deleted; struct module *owner; ssize_t (*read)(char *buffer, loff_t offset, size_t count, void *data, size_t datalen); void (*free)(void *data); /* * If nothing interferes and device_add() was returns success, * del_wk will destroy the device after the timer fires. * * Multiple userspace processes can interfere in the working of the timer: * - Writing to the coredump will reschedule the timer to run immediately, * if still armed. * * This is handled by using "if (cancel_delayed_work()) { * schedule_delayed_work() }", to prevent re-arming after having * been previously fired. * - Writing to /sys/class/devcoredump/disabled will destroy the * coredump synchronously. * This is handled by using disable_delayed_work_sync(), and then * checking if deleted flag is set with &devcd->mutex held. */ struct delayed_work del_wk; struct device *failing_dev; }; static struct devcd_entry *dev_to_devcd(struct device *dev) { return container_of(dev, struct devcd_entry, devcd_dev); } static void devcd_dev_release(struct device *dev) { struct devcd_entry *devcd = dev_to_devcd(dev); devcd->free(devcd->data); module_put(devcd->owner); /* * this seems racy, but I don't see a notifier or such on * a struct device to know when it goes away? */ if (devcd->failing_dev->kobj.sd) sysfs_delete_link(&devcd->failing_dev->kobj, &dev->kobj, "devcoredump"); put_device(devcd->failing_dev); kfree(devcd); } static void __devcd_del(struct devcd_entry *devcd) { devcd->deleted = true; device_del(&devcd->devcd_dev); put_device(&devcd->devcd_dev); } static void devcd_del(struct work_struct *wk) { struct devcd_entry *devcd; bool init_completed; devcd = container_of(wk, struct devcd_entry, del_wk.work); /* devcd->mutex serializes against dev_coredumpm_timeout */ mutex_lock(&devcd->mutex); init_completed = devcd->init_completed; mutex_unlock(&devcd->mutex); if (init_completed) __devcd_del(devcd); } static ssize_t devcd_data_read(struct file *filp, struct kobject *kobj, const struct bin_attribute *bin_attr, char *buffer, loff_t offset, size_t count) { struct device *dev = kobj_to_dev(kobj); struct devcd_entry *devcd = dev_to_devcd(dev); return devcd->read(buffer, offset, count, devcd->data, devcd->datalen); } static ssize_t devcd_data_write(struct file *filp, struct kobject *kobj, const struct bin_attribute *bin_attr, char *buffer, loff_t offset, size_t count) { struct device *dev = kobj_to_dev(kobj); struct devcd_entry *devcd = dev_to_devcd(dev); /* * Although it's tempting to use mod_delayed work here, * that will cause a reschedule if the timer already fired. */ if (cancel_delayed_work(&devcd->del_wk)) schedule_delayed_work(&devcd->del_wk, 0); return count; } static const struct bin_attribute devcd_attr_data = __BIN_ATTR(data, 0600, devcd_data_read, devcd_data_write, 0); static const struct bin_attribute *const devcd_dev_bin_attrs[] = { &devcd_attr_data, NULL, }; static const struct attribute_group devcd_dev_group = { .bin_attrs = devcd_dev_bin_attrs, }; static const struct attribute_group *devcd_dev_groups[] = { &devcd_dev_group, NULL, }; static int devcd_free(struct device *dev, void *data) { struct devcd_entry *devcd = dev_to_devcd(dev); /* * To prevent a race with devcd_data_write(), disable work and * complete manually instead. * * We cannot rely on the return value of * disable_delayed_work_sync() here, because it might be in the * middle of a cancel_delayed_work + schedule_delayed_work pair. * * devcd->mutex here guards against multiple parallel invocations * of devcd_free(). */ disable_delayed_work_sync(&devcd->del_wk); mutex_lock(&devcd->mutex); if (!devcd->deleted) __devcd_del(devcd); mutex_unlock(&devcd->mutex); return 0; } static ssize_t disabled_show(const struct class *class, const struct class_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", devcd_disabled); } /* * * disabled_store() worker() * class_for_each_device(&devcd_class, * NULL, NULL, devcd_free) * ... * ... * while ((dev = class_dev_iter_next(&iter)) * devcd_del() * device_del() * put_device() <- last reference * error = fn(dev, data) devcd_dev_release() * devcd_free(dev, data) kfree(devcd) * * * In the above diagram, it looks like disabled_store() would be racing with parallelly * running devcd_del() and result in memory abort after dropping its last reference with * put_device(). However, this will not happens as fn(dev, data) runs * with its own reference to device via klist_node so it is not its last reference. * so, above situation would not occur. */ static ssize_t disabled_store(const struct class *class, const struct class_attribute *attr, const char *buf, size_t count) { long tmp = simple_strtol(buf, NULL, 10); /* * This essentially makes the attribute write-once, since you can't * go back to not having it disabled. This is intentional, it serves * as a system lockdown feature. */ if (tmp != 1) return -EINVAL; devcd_disabled = true; class_for_each_device(&devcd_class, NULL, NULL, devcd_free); return count; } static CLASS_ATTR_RW(disabled); static struct attribute *devcd_class_attrs[] = { &class_attr_disabled.attr, NULL, }; ATTRIBUTE_GROUPS(devcd_class); static struct class devcd_class = { .name = "devcoredump", .dev_release = devcd_dev_release, .dev_groups = devcd_dev_groups, .class_groups = devcd_class_groups, }; static ssize_t devcd_readv(char *buffer, loff_t offset, size_t count, void *data, size_t datalen) { return memory_read_from_buffer(buffer, count, &offset, data, datalen); } static void devcd_freev(void *data) { vfree(data); } /** * dev_coredumpv - create device coredump with vmalloc data * @dev: the struct device for the crashed device * @data: vmalloc data containing the device coredump * @datalen: length of the data * @gfp: allocation flags * * This function takes ownership of the vmalloc'ed data and will free * it when it is no longer used. See dev_coredumpm() for more information. */ void dev_coredumpv(struct device *dev, void *data, size_t datalen, gfp_t gfp) { dev_coredumpm(dev, NULL, data, datalen, gfp, devcd_readv, devcd_freev); } EXPORT_SYMBOL_GPL(dev_coredumpv); static int devcd_match_failing(struct device *dev, const void *failing) { struct devcd_entry *devcd = dev_to_devcd(dev); return devcd->failing_dev == failing; } /** * devcd_free_sgtable - free all the memory of the given scatterlist table * (i.e. both pages and scatterlist instances) * NOTE: if two tables allocated with devcd_alloc_sgtable and then chained * using the sg_chain function then that function should be called only once * on the chained table * @data: pointer to sg_table to free */ static void devcd_free_sgtable(void *data) { _devcd_free_sgtable(data); } /** * devcd_read_from_sgtable - copy data from sg_table to a given buffer * and return the number of bytes read * @buffer: the buffer to copy the data to it * @buf_len: the length of the buffer * @data: the scatterlist table to copy from * @offset: start copy from @offset@ bytes from the head of the data * in the given scatterlist * @data_len: the length of the data in the sg_table * * Returns: the number of bytes copied */ static ssize_t devcd_read_from_sgtable(char *buffer, loff_t offset, size_t buf_len, void *data, size_t data_len) { struct scatterlist *table = data; if (offset > data_len) return -EINVAL; if (offset + buf_len > data_len) buf_len = data_len - offset; return sg_pcopy_to_buffer(table, sg_nents(table), buffer, buf_len, offset); } /** * dev_coredump_put - remove device coredump * @dev: the struct device for the crashed device * * dev_coredump_put() removes coredump, if exists, for a given device from * the file system and free its associated data otherwise, does nothing. * * It is useful for modules that do not want to keep coredump * available after its unload. */ void dev_coredump_put(struct device *dev) { struct device *existing; existing = class_find_device(&devcd_class, NULL, dev, devcd_match_failing); if (existing) { devcd_free(existing, NULL); put_device(existing); } } EXPORT_SYMBOL_GPL(dev_coredump_put); /** * dev_coredumpm_timeout - create device coredump with read/free methods with a * custom timeout. * @dev: the struct device for the crashed device * @owner: the module that contains the read/free functions, use %THIS_MODULE * @data: data cookie for the @read/@free functions * @datalen: length of the data * @gfp: allocation flags * @read: function to read from the given buffer * @free: function to free the given buffer * @timeout: time in jiffies to remove coredump * * Creates a new device coredump for the given device. If a previous one hasn't * been read yet, the new coredump is discarded. The data lifetime is determined * by the device coredump framework and when it is no longer needed the @free * function will be called to free the data. */ void dev_coredumpm_timeout(struct device *dev, struct module *owner, void *data, size_t datalen, gfp_t gfp, ssize_t (*read)(char *buffer, loff_t offset, size_t count, void *data, size_t datalen), void (*free)(void *data), unsigned long timeout) { static atomic_t devcd_count = ATOMIC_INIT(0); struct devcd_entry *devcd; struct device *existing; if (devcd_disabled) goto free; existing = class_find_device(&devcd_class, NULL, dev, devcd_match_failing); if (existing) { put_device(existing); goto free; } if (!try_module_get(owner)) goto free; devcd = kzalloc_obj(*devcd, gfp); if (!devcd) goto put_module; devcd->owner = owner; devcd->data = data; devcd->datalen = datalen; devcd->read = read; devcd->free = free; devcd->failing_dev = get_device(dev); devcd->deleted = false; mutex_init(&devcd->mutex); device_initialize(&devcd->devcd_dev); dev_set_name(&devcd->devcd_dev, "devcd%d", atomic_inc_return(&devcd_count)); devcd->devcd_dev.class = &devcd_class; dev_set_uevent_suppress(&devcd->devcd_dev, true); /* devcd->mutex prevents devcd_del() completing until init finishes */ mutex_lock(&devcd->mutex); devcd->init_completed = false; INIT_DELAYED_WORK(&devcd->del_wk, devcd_del); schedule_delayed_work(&devcd->del_wk, timeout); if (device_add(&devcd->devcd_dev)) goto put_device; /* * These should normally not fail, but there is no problem * continuing without the links, so just warn instead of * failing. */ if (sysfs_create_link(&devcd->devcd_dev.kobj, &dev->kobj, "failing_device") || sysfs_create_link(&dev->kobj, &devcd->devcd_dev.kobj, "devcoredump")) dev_warn(dev, "devcoredump create_link failed\n"); dev_set_uevent_suppress(&devcd->devcd_dev, false); kobject_uevent(&devcd->devcd_dev.kobj, KOBJ_ADD); /* * Safe to run devcd_del() now that we are done with devcd_dev. * Alternatively we could have taken a ref on devcd_dev before * dropping the lock. */ devcd->init_completed = true; mutex_unlock(&devcd->mutex); return; put_device: mutex_unlock(&devcd->mutex); cancel_delayed_work_sync(&devcd->del_wk); put_device(&devcd->devcd_dev); put_module: module_put(owner); free: free(data); } EXPORT_SYMBOL_GPL(dev_coredumpm_timeout); /** * dev_coredumpsg - create device coredump that uses scatterlist as data * parameter * @dev: the struct device for the crashed device * @table: the dump data * @datalen: length of the data * @gfp: allocation flags * * Creates a new device coredump for the given device. If a previous one hasn't * been read yet, the new coredump is discarded. The data lifetime is determined * by the device coredump framework and when it is no longer needed * it will free the data. */ void dev_coredumpsg(struct device *dev, struct scatterlist *table, size_t datalen, gfp_t gfp) { dev_coredumpm(dev, NULL, table, datalen, gfp, devcd_read_from_sgtable, devcd_free_sgtable); } EXPORT_SYMBOL_GPL(dev_coredumpsg); static int __init devcoredump_init(void) { return class_register(&devcd_class); } __initcall(devcoredump_init); |
| 2598 158 13798 12256 729 1742 14 26 2702 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * kref.h - library routines for handling generic reference counted objects * * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Corp. * * based on kobject.h which was: * Copyright (C) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (C) 2002-2003 Open Source Development Labs */ #ifndef _KREF_H_ #define _KREF_H_ #include <linux/spinlock.h> #include <linux/refcount.h> struct kref { refcount_t refcount; }; #define KREF_INIT(n) { .refcount = REFCOUNT_INIT(n), } /** * kref_init - initialize object. * @kref: object in question. */ static inline void kref_init(struct kref *kref) { refcount_set(&kref->refcount, 1); } static inline unsigned int kref_read(const struct kref *kref) { return refcount_read(&kref->refcount); } /** * kref_get - increment refcount for object. * @kref: object. */ static inline void kref_get(struct kref *kref) { refcount_inc(&kref->refcount); } /** * kref_put - Decrement refcount for object * @kref: Object * @release: Pointer to the function that will clean up the object when the * last reference to the object is released. * * Decrement the refcount, and if 0, call @release. The caller may not * pass NULL or kfree() as the release function. * * Return: 1 if this call removed the object, otherwise return 0. Beware, * if this function returns 0, another caller may have removed the object * by the time this function returns. The return value is only certain * if you want to see if the object is definitely released. */ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { if (refcount_dec_and_test(&kref->refcount)) { release(kref); return 1; } return 0; } /** * kref_put_mutex - Decrement refcount for object * @kref: Object * @release: Pointer to the function that will clean up the object when the * last reference to the object is released. * @mutex: Mutex which protects the release function. * * This variant of kref_lock() calls the @release function with the @mutex * held. The @release function will release the mutex. */ static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *mutex) __cond_acquires(true, mutex) { if (refcount_dec_and_mutex_lock(&kref->refcount, mutex)) { release(kref); return 1; } return 0; } /** * kref_put_lock - Decrement refcount for object * @kref: Object * @release: Pointer to the function that will clean up the object when the * last reference to the object is released. * @lock: Spinlock which protects the release function. * * This variant of kref_lock() calls the @release function with the @lock * held. The @release function will release the lock. */ static inline int kref_put_lock(struct kref *kref, void (*release)(struct kref *kref), spinlock_t *lock) __cond_acquires(true, lock) { if (refcount_dec_and_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } /** * kref_get_unless_zero - Increment refcount for object unless it is zero. * @kref: object. * * This function is intended to simplify locking around refcounting for * objects that can be looked up from a lookup structure, and which are * removed from that lookup structure in the object destructor. * Operations on such objects require at least a read lock around * lookup + kref_get, and a write lock around kref_put + remove from lookup * structure. Furthermore, RCU implementations become extremely tricky. * With a lookup followed by a kref_get_unless_zero *with return value check* * locking in the kref_put path can be deferred to the actual removal from * the lookup structure and RCU lookups become trivial. * * Return: non-zero if the increment succeeded. Otherwise return 0. */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { return refcount_inc_not_zero(&kref->refcount); } #endif /* _KREF_H_ */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/prandom.h * * Include file for the fast pseudo-random 32-bit * generation. */ #ifndef _LINUX_PRANDOM_H #define _LINUX_PRANDOM_H #include <linux/types.h> #include <linux/once.h> #include <linux/percpu.h> #include <linux/random.h> struct rnd_state { __u32 s1, s2, s3, s4; }; u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); #define prandom_init_once(pcpu_state) \ DO_ONCE(prandom_seed_full_state, (pcpu_state)) /* * Handle minimum values for seeds */ static inline u32 __seed(u32 x, u32 m) { return (x < m) ? x + m : x; } /** * prandom_seed_state - set seed for prandom_u32_state(). * @state: pointer to state structure to receive the seed. * @seed: arbitrary 64-bit value to use as a seed. */ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) { u32 i = ((seed >> 32) ^ (seed << 10) ^ seed) & 0xffffffffUL; state->s1 = __seed(i, 2U); state->s2 = __seed(i, 8U); state->s3 = __seed(i, 16U); state->s4 = __seed(i, 128U); } #endif |
| 6 6 9 9 9 6 6 9 9 1067 1067 1067 1067 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 | /* * Copyright (c) 2006,2007 The Regents of the University of Michigan. * All rights reserved. * * Andy Adamson <andros@citi.umich.edu> * Fred Isaman <iisaman@umich.edu> * * permission is granted to use, copy, create derivative works and * redistribute this software and such derivative works for any purpose, * so long as the name of the university of michigan is not used in * any advertising or publicity pertaining to the use or distribution * of this software without specific, written prior authorization. if * the above copyright notice or any other identification of the * university of michigan is included in any copy of any portion of * this software, then the disclaimer below must also be included. * * this software is provided as is, without representation from the * university of michigan as to its fitness for any purpose, and without * warranty by the university of michigan of any kind, either express * or implied, including without limitation the implied warranties of * merchantability and fitness for a particular purpose. the regents * of the university of michigan shall not be liable for any damages, * including special, indirect, incidental, or consequential damages, * with respect to any claim arising out or in connection with the use * of the software, even if it has been or is hereafter advised of the * possibility of such damages. */ #include <linux/module.h> #include <linux/blkdev.h> #include "blocklayout.h" #define NFSDBG_FACILITY NFSDBG_PNFS_LD static void nfs4_encode_simple(__be32 *p, struct pnfs_block_volume *b) { int i; *p++ = cpu_to_be32(1); *p++ = cpu_to_be32(b->type); *p++ = cpu_to_be32(b->simple.nr_sigs); for (i = 0; i < b->simple.nr_sigs; i++) { p = xdr_encode_hyper(p, b->simple.sigs[i].offset); p = xdr_encode_opaque(p, b->simple.sigs[i].sig, b->simple.sigs[i].sig_len); } } dev_t bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b, gfp_t gfp_mask) { struct net *net = server->nfs_client->cl_net; struct nfs_net *nn = net_generic(net, nfs_net_id); struct bl_dev_msg *reply = &nn->bl_mount_reply; struct bl_pipe_msg bl_pipe_msg; struct rpc_pipe_msg *msg = &bl_pipe_msg.msg; struct bl_msg_hdr *bl_msg; DECLARE_WAITQUEUE(wq, current); dev_t dev = 0; int rc; dprintk("%s CREATING PIPEFS MESSAGE\n", __func__); mutex_lock(&nn->bl_mutex); bl_pipe_msg.bl_wq = &nn->bl_wq; b->simple.len += 4; /* single volume */ if (b->simple.len > PAGE_SIZE) goto out_unlock; memset(msg, 0, sizeof(*msg)); msg->len = sizeof(*bl_msg) + b->simple.len; msg->data = kzalloc(msg->len, gfp_mask); if (!msg->data) goto out_unlock; bl_msg = msg->data; bl_msg->type = BL_DEVICE_MOUNT; bl_msg->totallen = b->simple.len; nfs4_encode_simple(msg->data + sizeof(*bl_msg), b); dprintk("%s CALLING USERSPACE DAEMON\n", __func__); add_wait_queue(&nn->bl_wq, &wq); rc = rpc_queue_upcall(nn->bl_device_pipe, msg); if (rc < 0) { remove_wait_queue(&nn->bl_wq, &wq); goto out_free_data; } set_current_state(TASK_UNINTERRUPTIBLE); schedule(); remove_wait_queue(&nn->bl_wq, &wq); if (reply->status != BL_DEVICE_REQUEST_PROC) { printk(KERN_WARNING "%s failed to decode device: %d\n", __func__, reply->status); goto out_free_data; } dev = MKDEV(reply->major, reply->minor); out_free_data: kfree(msg->data); out_unlock: mutex_unlock(&nn->bl_mutex); return dev; } static ssize_t bl_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { struct nfs_net *nn = net_generic(file_inode(filp)->i_sb->s_fs_info, nfs_net_id); if (mlen != sizeof (struct bl_dev_msg)) return -EINVAL; if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0) return -EFAULT; wake_up(&nn->bl_wq); return mlen; } static void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg) { struct bl_pipe_msg *bl_pipe_msg = container_of(msg, struct bl_pipe_msg, msg); if (msg->errno >= 0) return; wake_up(bl_pipe_msg->bl_wq); } static const struct rpc_pipe_ops bl_upcall_ops = { .upcall = rpc_pipe_generic_upcall, .downcall = bl_pipe_downcall, .destroy_msg = bl_pipe_destroy_msg, }; static int nfs4blocklayout_register_sb(struct super_block *sb, struct rpc_pipe *pipe) { struct dentry *dir; int err; dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME); if (dir == NULL) return -ENOENT; err = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe); dput(dir); return err; } static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct super_block *sb = ptr; struct net *net = sb->s_fs_info; struct nfs_net *nn = net_generic(net, nfs_net_id); int ret = 0; if (!try_module_get(THIS_MODULE)) return 0; if (nn->bl_device_pipe == NULL) { module_put(THIS_MODULE); return 0; } switch (event) { case RPC_PIPEFS_MOUNT: ret = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe); break; case RPC_PIPEFS_UMOUNT: rpc_unlink(nn->bl_device_pipe); break; default: ret = -ENOTSUPP; break; } module_put(THIS_MODULE); return ret; } static struct notifier_block nfs4blocklayout_block = { .notifier_call = rpc_pipefs_event, }; static int nfs4blocklayout_register_net(struct net *net, struct rpc_pipe *pipe) { struct super_block *pipefs_sb; int ret; pipefs_sb = rpc_get_sb_net(net); if (!pipefs_sb) return 0; ret = nfs4blocklayout_register_sb(pipefs_sb, pipe); rpc_put_sb_net(net); return ret; } static void nfs4blocklayout_unregister_net(struct net *net, struct rpc_pipe *pipe) { struct super_block *pipefs_sb; pipefs_sb = rpc_get_sb_net(net); if (pipefs_sb) { rpc_unlink(pipe); rpc_put_sb_net(net); } } static int nfs4blocklayout_net_init(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); int err; mutex_init(&nn->bl_mutex); init_waitqueue_head(&nn->bl_wq); nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0); if (IS_ERR(nn->bl_device_pipe)) return PTR_ERR(nn->bl_device_pipe); err = nfs4blocklayout_register_net(net, nn->bl_device_pipe); if (unlikely(err)) rpc_destroy_pipe_data(nn->bl_device_pipe); return err; } static void nfs4blocklayout_net_exit(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); nfs4blocklayout_unregister_net(net, nn->bl_device_pipe); rpc_destroy_pipe_data(nn->bl_device_pipe); nn->bl_device_pipe = NULL; } static struct pernet_operations nfs4blocklayout_net_ops = { .init = nfs4blocklayout_net_init, .exit = nfs4blocklayout_net_exit, }; int __init bl_init_pipefs(void) { int ret; ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block); if (ret) goto out; ret = register_pernet_subsys(&nfs4blocklayout_net_ops); if (ret) goto out_unregister_notifier; return 0; out_unregister_notifier: rpc_pipefs_notifier_unregister(&nfs4blocklayout_block); out: return ret; } void bl_cleanup_pipefs(void) { rpc_pipefs_notifier_unregister(&nfs4blocklayout_block); unregister_pernet_subsys(&nfs4blocklayout_net_ops); } |
| 8 23 6 24 22 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * vivid-core.h - core datastructures * * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved. */ #ifndef _VIVID_CORE_H_ #define _VIVID_CORE_H_ #include <linux/fb.h> #include <linux/workqueue.h> #include <media/cec.h> #include <media/videobuf2-v4l2.h> #include <media/v4l2-device.h> #include <media/v4l2-dev.h> #include <media/v4l2-ctrls.h> #include <media/tpg/v4l2-tpg.h> #include "vivid-rds-gen.h" #include "vivid-vbi-gen.h" #define dprintk(dev, level, fmt, arg...) \ v4l2_dbg(level, vivid_debug, &dev->v4l2_dev, fmt, ## arg) /* The maximum number of inputs */ #define MAX_INPUTS 16 /* The maximum number of outputs */ #define MAX_OUTPUTS 16 /* The maximum number of video capture buffers */ #define MAX_VID_CAP_BUFFERS 64 /* The maximum up or down scaling factor is 4 */ #define MAX_ZOOM 4 /* The maximum image width/height are set to 4K DMT */ #define MAX_WIDTH 4096 #define MAX_HEIGHT 2160 /* The minimum image width/height */ #define MIN_WIDTH 16 #define MIN_HEIGHT MIN_WIDTH /* Pixel Array control divider */ #define PIXEL_ARRAY_DIV MIN_WIDTH /* The data_offset of plane 0 for the multiplanar formats */ #define PLANE0_DATA_OFFSET 128 /* The supported TV frequency range in MHz */ #define MIN_TV_FREQ (44U * 16U) #define MAX_TV_FREQ (958U * 16U) /* The number of samples returned in every SDR buffer */ #define SDR_CAP_SAMPLES_PER_BUF 0x4000 /* used by the threads to know when to resync internal counters */ #define JIFFIES_PER_DAY (3600U * 24U * HZ) #define JIFFIES_RESYNC (JIFFIES_PER_DAY * (0xf0000000U / JIFFIES_PER_DAY)) /* * Maximum number of HDMI inputs allowed by vivid, due to limitations * of the Physical Address in the EDID and used by CEC we stop at 15 * inputs and outputs. */ #define MAX_HDMI_INPUTS 15 #define MAX_HDMI_OUTPUTS 15 /* Maximum number of S-Video inputs allowed by vivid */ #define MAX_SVID_INPUTS 16 /* The maximum number of items in a menu control */ #define MAX_MENU_ITEMS BITS_PER_LONG_LONG /* Number of fixed menu items in the 'Connected To' menu controls */ #define FIXED_MENU_ITEMS 2 /* The maximum number of vivid devices */ #define VIVID_MAX_DEVS CONFIG_VIDEO_VIVID_MAX_DEVS extern const struct v4l2_rect vivid_min_rect; extern const struct v4l2_rect vivid_max_rect; extern unsigned vivid_debug; /* * NULL-terminated string array for the HDMI 'Connected To' menu controls * with the list of possible HDMI outputs. * * The first two items are fixed ("TPG" and "None"). */ extern char *vivid_ctrl_hdmi_to_output_strings[1 + MAX_MENU_ITEMS]; /* Menu control skip mask of all HDMI outputs that are in use */ extern u64 hdmi_to_output_menu_skip_mask; /* * Bitmask of which vivid instances need to update any connected * HDMI outputs. */ extern u64 hdmi_input_update_outputs_mask; /* * Spinlock for access to hdmi_to_output_menu_skip_mask and * hdmi_input_update_outputs_mask. */ extern spinlock_t hdmi_output_skip_mask_lock; /* * Workqueue that updates the menu controls whenever the HDMI menu skip mask * changes. */ extern struct workqueue_struct *update_hdmi_ctrls_workqueue; /* * The HDMI menu control value (index in the menu list) maps to an HDMI * output that is part of the given vivid_dev instance and has the given * output index (as returned by VIDIOC_G_OUTPUT). * * NULL/0 if not available. */ extern struct vivid_dev *vivid_ctrl_hdmi_to_output_instance[MAX_MENU_ITEMS]; extern unsigned int vivid_ctrl_hdmi_to_output_index[MAX_MENU_ITEMS]; /* * NULL-terminated string array for the S-Video 'Connected To' menu controls * with the list of possible S-Video outputs. * * The first two items are fixed ("TPG" and "None"). */ extern char *vivid_ctrl_svid_to_output_strings[1 + MAX_MENU_ITEMS]; /* Menu control skip mask of all S-Video outputs that are in use */ extern u64 svid_to_output_menu_skip_mask; /* Spinlock for access to svid_to_output_menu_skip_mask */ extern spinlock_t svid_output_skip_mask_lock; /* * Workqueue that updates the menu controls whenever the S-Video menu skip mask * changes. */ extern struct workqueue_struct *update_svid_ctrls_workqueue; /* * The S-Video menu control value (index in the menu list) maps to an S-Video * output that is part of the given vivid_dev instance and has the given * output index (as returned by VIDIOC_G_OUTPUT). * * NULL/0 if not available. */ extern struct vivid_dev *vivid_ctrl_svid_to_output_instance[MAX_MENU_ITEMS]; extern unsigned int vivid_ctrl_svid_to_output_index[MAX_MENU_ITEMS]; extern struct vivid_dev *vivid_devs[VIVID_MAX_DEVS]; extern unsigned int n_devs; struct vivid_fmt { u32 fourcc; /* v4l2 format id */ enum tgp_color_enc color_enc; bool can_do_overlay; u8 vdownsampling[TPG_MAX_PLANES]; u32 alpha_mask; u8 planes; u8 buffers; u32 data_offset[TPG_MAX_PLANES]; u32 bit_depth[TPG_MAX_PLANES]; }; extern struct vivid_fmt vivid_formats[]; /* buffer for one video frame */ struct vivid_buffer { /* common v4l buffer stuff -- must be first */ struct vb2_v4l2_buffer vb; struct list_head list; }; enum vivid_input { WEBCAM, TV, SVID, HDMI, }; enum vivid_signal_mode { CURRENT_DV_TIMINGS, CURRENT_STD = CURRENT_DV_TIMINGS, NO_SIGNAL, NO_LOCK, OUT_OF_RANGE, SELECTED_DV_TIMINGS, SELECTED_STD = SELECTED_DV_TIMINGS, CYCLE_DV_TIMINGS, CYCLE_STD = CYCLE_DV_TIMINGS, CUSTOM_DV_TIMINGS, }; enum vivid_colorspace { VIVID_CS_170M, VIVID_CS_709, VIVID_CS_SRGB, VIVID_CS_OPRGB, VIVID_CS_2020, VIVID_CS_DCI_P3, VIVID_CS_240M, VIVID_CS_SYS_M, VIVID_CS_SYS_BG, }; #define VIVID_INVALID_SIGNAL(mode) \ ((mode) == NO_SIGNAL || (mode) == NO_LOCK || (mode) == OUT_OF_RANGE) struct vivid_cec_xfer { struct cec_adapter *adap; u8 msg[CEC_MAX_MSG_SIZE]; u32 len; u32 sft; }; struct vivid_dev { u8 inst; struct v4l2_device v4l2_dev; #ifdef CONFIG_MEDIA_CONTROLLER struct media_device mdev; struct media_pad vid_cap_pad; struct media_pad vid_out_pad; struct media_pad vbi_cap_pad; struct media_pad vbi_out_pad; struct media_pad sdr_cap_pad; struct media_pad meta_cap_pad; struct media_pad meta_out_pad; struct media_pad touch_cap_pad; #endif struct v4l2_ctrl_handler ctrl_hdl_user_gen; struct v4l2_ctrl_handler ctrl_hdl_user_vid; struct v4l2_ctrl_handler ctrl_hdl_user_aud; struct v4l2_ctrl_handler ctrl_hdl_streaming; struct v4l2_ctrl_handler ctrl_hdl_sdtv_cap; struct v4l2_ctrl_handler ctrl_hdl_loop_cap; struct v4l2_ctrl_handler ctrl_hdl_fb; struct video_device vid_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_vid_cap; struct video_device vid_out_dev; struct v4l2_ctrl_handler ctrl_hdl_vid_out; struct video_device vbi_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_vbi_cap; struct video_device vbi_out_dev; struct v4l2_ctrl_handler ctrl_hdl_vbi_out; struct video_device radio_rx_dev; struct v4l2_ctrl_handler ctrl_hdl_radio_rx; struct video_device radio_tx_dev; struct v4l2_ctrl_handler ctrl_hdl_radio_tx; struct video_device sdr_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_sdr_cap; struct video_device meta_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_meta_cap; struct video_device meta_out_dev; struct v4l2_ctrl_handler ctrl_hdl_meta_out; struct video_device touch_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_touch_cap; spinlock_t slock; struct mutex mutex; struct work_struct update_hdmi_ctrl_work; struct work_struct update_svid_ctrl_work; /* capabilities */ u32 vid_cap_caps; u32 vid_out_caps; u32 vbi_cap_caps; u32 vbi_out_caps; u32 sdr_cap_caps; u32 radio_rx_caps; u32 radio_tx_caps; u32 meta_cap_caps; u32 meta_out_caps; u32 touch_cap_caps; /* supported features */ bool multiplanar; u8 num_inputs; u8 num_hdmi_inputs; u8 num_svid_inputs; u8 input_type[MAX_INPUTS]; u8 input_name_counter[MAX_INPUTS]; u8 num_outputs; u8 num_hdmi_outputs; u8 output_type[MAX_OUTPUTS]; u8 output_name_counter[MAX_OUTPUTS]; bool has_audio_inputs; bool has_audio_outputs; bool has_vid_cap; bool has_vid_out; bool has_vbi_cap; bool has_raw_vbi_cap; bool has_sliced_vbi_cap; bool has_vbi_out; bool has_raw_vbi_out; bool has_sliced_vbi_out; bool has_radio_rx; bool has_radio_tx; bool has_sdr_cap; bool has_fb; bool has_meta_cap; bool has_meta_out; bool has_tv_tuner; bool has_touch_cap; /* Output index (0-MAX_OUTPUTS) to vivid instance of connected input */ struct vivid_dev *output_to_input_instance[MAX_OUTPUTS]; /* Output index (0-MAX_OUTPUTS) to input index (0-MAX_INPUTS) of connected input */ u8 output_to_input_index[MAX_OUTPUTS]; /* Output index (0-MAX_OUTPUTS) to HDMI or S-Video output index (0-MAX_HDMI/SVID_OUTPUTS) */ u8 output_to_iface_index[MAX_OUTPUTS]; /* ctrl_hdmi_to_output or ctrl_svid_to_output control value for each input */ s32 input_is_connected_to_output[MAX_INPUTS]; /* HDMI index (0-MAX_HDMI_OUTPUTS) to output index (0-MAX_OUTPUTS) */ u8 hdmi_index_to_output_index[MAX_HDMI_OUTPUTS]; /* HDMI index (0-MAX_HDMI_INPUTS) to input index (0-MAX_INPUTS) */ u8 hdmi_index_to_input_index[MAX_HDMI_INPUTS]; /* S-Video index (0-MAX_SVID_INPUTS) to input index (0-MAX_INPUTS) */ u8 svid_index_to_input_index[MAX_SVID_INPUTS]; /* controls */ struct v4l2_ctrl *brightness; struct v4l2_ctrl *contrast; struct v4l2_ctrl *saturation; struct v4l2_ctrl *hue; struct { /* autogain/gain cluster */ struct v4l2_ctrl *autogain; struct v4l2_ctrl *gain; }; struct v4l2_ctrl *volume; struct v4l2_ctrl *mute; struct v4l2_ctrl *alpha; struct v4l2_ctrl *button; struct v4l2_ctrl *boolean; struct v4l2_ctrl *int32; struct v4l2_ctrl *int64; struct v4l2_ctrl *menu; struct v4l2_ctrl *string; struct v4l2_ctrl *bitmask; struct v4l2_ctrl *int_menu; struct v4l2_ctrl *ro_int32; struct v4l2_ctrl *pixel_array; struct v4l2_ctrl *test_pattern; struct v4l2_ctrl *colorspace; struct v4l2_ctrl *rgb_range_cap; struct v4l2_ctrl *real_rgb_range_cap; struct { /* std_signal_mode/standard cluster */ struct v4l2_ctrl *ctrl_std_signal_mode; struct v4l2_ctrl *ctrl_standard; }; struct { /* dv_timings_signal_mode/timings cluster */ struct v4l2_ctrl *ctrl_dv_timings_signal_mode; struct v4l2_ctrl *ctrl_dv_timings; }; struct v4l2_ctrl *ctrl_has_crop_cap; struct v4l2_ctrl *ctrl_has_compose_cap; struct v4l2_ctrl *ctrl_has_scaler_cap; struct v4l2_ctrl *ctrl_has_crop_out; struct v4l2_ctrl *ctrl_has_compose_out; struct v4l2_ctrl *ctrl_has_scaler_out; struct v4l2_ctrl *ctrl_tx_mode; struct v4l2_ctrl *ctrl_tx_rgb_range; struct v4l2_ctrl *ctrl_tx_edid_present; struct v4l2_ctrl *ctrl_tx_hotplug; struct v4l2_ctrl *ctrl_tx_rxsense; struct v4l2_ctrl *ctrl_rx_power_present; struct v4l2_ctrl *radio_tx_rds_pi; struct v4l2_ctrl *radio_tx_rds_pty; struct v4l2_ctrl *radio_tx_rds_mono_stereo; struct v4l2_ctrl *radio_tx_rds_art_head; struct v4l2_ctrl *radio_tx_rds_compressed; struct v4l2_ctrl *radio_tx_rds_dyn_pty; struct v4l2_ctrl *radio_tx_rds_ta; struct v4l2_ctrl *radio_tx_rds_tp; struct v4l2_ctrl *radio_tx_rds_ms; struct v4l2_ctrl *radio_tx_rds_psname; struct v4l2_ctrl *radio_tx_rds_radiotext; struct v4l2_ctrl *radio_rx_rds_pty; struct v4l2_ctrl *radio_rx_rds_ta; struct v4l2_ctrl *radio_rx_rds_tp; struct v4l2_ctrl *radio_rx_rds_ms; struct v4l2_ctrl *radio_rx_rds_psname; struct v4l2_ctrl *radio_rx_rds_radiotext; struct v4l2_ctrl *ctrl_hdmi_to_output[MAX_HDMI_INPUTS]; char ctrl_hdmi_to_output_names[MAX_HDMI_INPUTS][32]; struct v4l2_ctrl *ctrl_svid_to_output[MAX_SVID_INPUTS]; char ctrl_svid_to_output_names[MAX_SVID_INPUTS][32]; unsigned input_brightness[MAX_INPUTS]; unsigned osd_mode; unsigned button_pressed; bool sensor_hflip; bool sensor_vflip; bool hflip; bool vflip; bool vbi_cap_interlaced; bool loop_video; bool reduced_fps; /* Framebuffer */ unsigned long video_pbase; void *video_vbase; u32 video_buffer_size; int display_width; int display_height; int display_byte_stride; int bits_per_pixel; int bytes_per_pixel; #ifdef CONFIG_VIDEO_VIVID_OSD struct fb_info fb_info; struct fb_var_screeninfo fb_defined; struct fb_fix_screeninfo fb_fix; #endif /* Error injection */ bool disconnect_error; bool queue_setup_error; bool buf_prepare_error; bool start_streaming_error; bool dqbuf_error; bool req_validate_error; bool seq_wrap; u64 time_wrap; u64 time_wrap_offset; unsigned perc_dropped_buffers; enum vivid_signal_mode std_signal_mode[MAX_INPUTS]; unsigned int query_std_last[MAX_INPUTS]; v4l2_std_id query_std[MAX_INPUTS]; enum tpg_video_aspect std_aspect_ratio[MAX_INPUTS]; enum vivid_signal_mode dv_timings_signal_mode[MAX_INPUTS]; char **query_dv_timings_qmenu; char *query_dv_timings_qmenu_strings; unsigned query_dv_timings_size; unsigned int query_dv_timings_last[MAX_INPUTS]; unsigned int query_dv_timings[MAX_INPUTS]; enum tpg_video_aspect dv_timings_aspect_ratio[MAX_INPUTS]; /* Input */ unsigned input; v4l2_std_id std_cap[MAX_INPUTS]; struct v4l2_dv_timings dv_timings_cap[MAX_INPUTS]; int dv_timings_cap_sel[MAX_INPUTS]; u32 service_set_cap; struct vivid_vbi_gen_data vbi_gen; u8 *edid; unsigned edid_blocks; unsigned edid_max_blocks; unsigned webcam_size_idx; unsigned webcam_ival_idx; unsigned tv_freq; unsigned tv_audmode; unsigned tv_field_cap; unsigned tv_audio_input; u32 power_present; /* Output */ unsigned output; v4l2_std_id std_out; struct v4l2_dv_timings dv_timings_out; u32 colorspace_out; u32 ycbcr_enc_out; u32 hsv_enc_out; u32 quantization_out; u32 xfer_func_out; u32 service_set_out; unsigned bytesperline_out[TPG_MAX_PLANES]; unsigned tv_field_out; unsigned tv_audio_output; bool vbi_out_have_wss; u8 vbi_out_wss[2]; bool vbi_out_have_cc[2]; u8 vbi_out_cc[2][2]; bool dvi_d_out; u8 *scaled_line; u8 *blended_line; unsigned cur_scaled_line; /* Output Overlay */ void *fb_vbase_out; bool overlay_out_enabled; int overlay_out_top, overlay_out_left; unsigned fbuf_out_flags; u32 chromakey_out; u8 global_alpha_out; /* video capture */ struct tpg_data tpg; unsigned ms_vid_cap; bool must_blank[MAX_VID_CAP_BUFFERS]; const struct vivid_fmt *fmt_cap; struct v4l2_fract timeperframe_vid_cap; enum v4l2_field field_cap; struct v4l2_rect src_rect; struct v4l2_rect fmt_cap_rect; struct v4l2_rect crop_cap; struct v4l2_rect compose_cap; struct v4l2_rect crop_bounds_cap; struct vb2_queue vb_vid_cap_q; struct list_head vid_cap_active; struct vb2_queue vb_vbi_cap_q; struct list_head vbi_cap_active; struct vb2_queue vb_meta_cap_q; struct list_head meta_cap_active; struct vb2_queue vb_touch_cap_q; struct list_head touch_cap_active; /* thread for generating video capture stream */ struct task_struct *kthread_vid_cap; unsigned long jiffies_vid_cap; u64 cap_stream_start; u64 cap_frame_period; u64 cap_frame_eof_offset; u32 cap_seq_offset; u32 cap_seq_count; bool cap_seq_resync; u32 vid_cap_seq_start; u32 vid_cap_seq_count; bool vid_cap_streaming; u32 vbi_cap_seq_start; u32 vbi_cap_seq_count; bool vbi_cap_streaming; u32 meta_cap_seq_start; u32 meta_cap_seq_count; bool meta_cap_streaming; /* Touch capture */ struct task_struct *kthread_touch_cap; unsigned long jiffies_touch_cap; u64 touch_cap_stream_start; u32 touch_cap_seq_offset; bool touch_cap_seq_resync; u32 touch_cap_seq_start; u32 touch_cap_seq_count; u32 touch_cap_with_seq_wrap_count; bool touch_cap_streaming; struct v4l2_fract timeperframe_tch_cap; struct v4l2_pix_format tch_format; int tch_pat_random; /* video output */ const struct vivid_fmt *fmt_out; struct v4l2_fract timeperframe_vid_out; enum v4l2_field field_out; struct v4l2_rect sink_rect; struct v4l2_rect fmt_out_rect; struct v4l2_rect crop_out; struct v4l2_rect compose_out; struct v4l2_rect compose_bounds_out; struct vb2_queue vb_vid_out_q; struct list_head vid_out_active; struct vb2_queue vb_vbi_out_q; struct list_head vbi_out_active; struct vb2_queue vb_meta_out_q; struct list_head meta_out_active; /* video loop precalculated rectangles */ /* * Intersection between what the output side composes and the capture side * crops. I.e., what actually needs to be copied from the output buffer to * the capture buffer. */ struct v4l2_rect loop_vid_copy; /* The part of the output buffer that (after scaling) corresponds to loop_vid_copy. */ struct v4l2_rect loop_vid_out; /* The part of the capture buffer that (after scaling) corresponds to loop_vid_copy. */ struct v4l2_rect loop_vid_cap; /* * The intersection of the framebuffer, the overlay output window and * loop_vid_copy. I.e., the part of the framebuffer that actually should be * blended with the compose_out rectangle. This uses the framebuffer origin. */ struct v4l2_rect loop_fb_copy; /* The same as loop_fb_copy but with compose_out origin. */ struct v4l2_rect loop_vid_overlay; /* * The part of the capture buffer that (after scaling) corresponds * to loop_vid_overlay. */ struct v4l2_rect loop_vid_overlay_cap; /* thread for generating video output stream */ struct task_struct *kthread_vid_out; unsigned long jiffies_vid_out; u32 out_seq_offset; u32 out_seq_count; bool out_seq_resync; u32 vid_out_seq_start; u32 vid_out_seq_count; bool vid_out_streaming; u32 vbi_out_seq_start; u32 vbi_out_seq_count; bool vbi_out_streaming; bool stream_sliced_vbi_out; u32 meta_out_seq_start; u32 meta_out_seq_count; bool meta_out_streaming; /* SDR capture */ struct vb2_queue vb_sdr_cap_q; struct list_head sdr_cap_active; u32 sdr_pixelformat; /* v4l2 format id */ unsigned sdr_buffersize; unsigned sdr_adc_freq; unsigned sdr_fm_freq; unsigned sdr_fm_deviation; int sdr_fixp_src_phase; int sdr_fixp_mod_phase; bool tstamp_src_is_soe; bool has_crop_cap; bool has_compose_cap; bool has_scaler_cap; bool has_crop_out; bool has_compose_out; bool has_scaler_out; /* thread for generating SDR stream */ struct task_struct *kthread_sdr_cap; unsigned long jiffies_sdr_cap; u32 sdr_cap_seq_offset; u32 sdr_cap_seq_start; u32 sdr_cap_seq_count; u32 sdr_cap_with_seq_wrap_count; bool sdr_cap_seq_resync; /* RDS generator */ struct vivid_rds_gen rds_gen; /* Radio receiver */ unsigned radio_rx_freq; unsigned radio_rx_audmode; int radio_rx_sig_qual; unsigned radio_rx_hw_seek_mode; bool radio_rx_hw_seek_prog_lim; bool radio_rx_rds_controls; bool radio_rx_rds_enabled; unsigned radio_rx_rds_use_alternates; unsigned radio_rx_rds_last_block; struct v4l2_fh *radio_rx_rds_owner; /* Radio transmitter */ unsigned radio_tx_freq; unsigned radio_tx_subchans; bool radio_tx_rds_controls; unsigned radio_tx_rds_last_block; struct v4l2_fh *radio_tx_rds_owner; /* Shared between radio receiver and transmitter */ bool radio_rds_loop; ktime_t radio_rds_init_time; /* CEC */ struct cec_adapter *cec_rx_adap; struct cec_adapter *cec_tx_adap[MAX_HDMI_OUTPUTS]; struct task_struct *kthread_cec; wait_queue_head_t kthread_waitq_cec; struct vivid_cec_xfer xfers[MAX_OUTPUTS]; spinlock_t cec_xfers_slock; /* read and write cec messages */ u32 cec_sft; /* bus signal free time, in bit periods */ u8 last_initiator; /* CEC OSD String */ char osd[14]; unsigned long osd_jiffies; bool meta_pts; bool meta_scr; }; static inline bool vivid_is_webcam(const struct vivid_dev *dev) { return dev->input_type[dev->input] == WEBCAM; } static inline bool vivid_is_tv_cap(const struct vivid_dev *dev) { return dev->input_type[dev->input] == TV; } static inline bool vivid_is_svid_cap(const struct vivid_dev *dev) { return dev->input_type[dev->input] == SVID; } static inline bool vivid_is_hdmi_cap(const struct vivid_dev *dev) { return dev->input_type[dev->input] == HDMI; } static inline bool vivid_is_sdtv_cap(const struct vivid_dev *dev) { return vivid_is_tv_cap(dev) || vivid_is_svid_cap(dev); } static inline bool vivid_is_svid_out(const struct vivid_dev *dev) { return dev->output_type[dev->output] == SVID; } static inline bool vivid_is_hdmi_out(const struct vivid_dev *dev) { return dev->output_type[dev->output] == HDMI; } #endif |
| 3 3 2 1 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ec.c - ACPI Embedded Controller Driver (v3) * * Copyright (C) 2001-2015 Intel Corporation * Author: 2014, 2015 Lv Zheng <lv.zheng@intel.com> * 2006, 2007 Alexey Starikovskiy <alexey.y.starikovskiy@intel.com> * 2006 Denis Sadykov <denis.m.sadykov@intel.com> * 2004 Luming Yu <luming.yu@intel.com> * 2001, 2002 Andy Grover <andrew.grover@intel.com> * 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> * Copyright (C) 2008 Alexey Starikovskiy <astarikovskiy@suse.de> */ /* Uncomment next line to get verbose printout */ /* #define DEBUG */ #define pr_fmt(fmt) "ACPI: EC: " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/types.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/list.h> #include <linux/platform_device.h> #include <linux/printk.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/suspend.h> #include <linux/acpi.h> #include <linux/dmi.h> #include <asm/io.h> #include "internal.h" /* EC status register */ #define ACPI_EC_FLAG_OBF 0x01 /* Output buffer full */ #define ACPI_EC_FLAG_IBF 0x02 /* Input buffer full */ #define ACPI_EC_FLAG_CMD 0x08 /* Input buffer contains a command */ #define ACPI_EC_FLAG_BURST 0x10 /* burst mode */ #define ACPI_EC_FLAG_SCI 0x20 /* EC-SCI occurred */ /* * The SCI_EVT clearing timing is not defined by the ACPI specification. * This leads to lots of practical timing issues for the host EC driver. * The following variations are defined (from the target EC firmware's * perspective): * STATUS: After indicating SCI_EVT edge triggered IRQ to the host, the * target can clear SCI_EVT at any time so long as the host can see * the indication by reading the status register (EC_SC). So the * host should re-check SCI_EVT after the first time the SCI_EVT * indication is seen, which is the same time the query request * (QR_EC) is written to the command register (EC_CMD). SCI_EVT set * at any later time could indicate another event. Normally such * kind of EC firmware has implemented an event queue and will * return 0x00 to indicate "no outstanding event". * QUERY: After seeing the query request (QR_EC) written to the command * register (EC_CMD) by the host and having prepared the responding * event value in the data register (EC_DATA), the target can safely * clear SCI_EVT because the target can confirm that the current * event is being handled by the host. The host then should check * SCI_EVT right after reading the event response from the data * register (EC_DATA). * EVENT: After seeing the event response read from the data register * (EC_DATA) by the host, the target can clear SCI_EVT. As the * target requires time to notice the change in the data register * (EC_DATA), the host may be required to wait additional guarding * time before checking the SCI_EVT again. Such guarding may not be * necessary if the host is notified via another IRQ. */ #define ACPI_EC_EVT_TIMING_STATUS 0x00 #define ACPI_EC_EVT_TIMING_QUERY 0x01 #define ACPI_EC_EVT_TIMING_EVENT 0x02 /* EC commands */ enum ec_command { ACPI_EC_COMMAND_READ = 0x80, ACPI_EC_COMMAND_WRITE = 0x81, ACPI_EC_BURST_ENABLE = 0x82, ACPI_EC_BURST_DISABLE = 0x83, ACPI_EC_COMMAND_QUERY = 0x84, }; #define ACPI_EC_DELAY 500 /* Wait 500ms max. during EC ops */ #define ACPI_EC_UDELAY_GLK 1000 /* Wait 1ms max. to get global lock */ #define ACPI_EC_UDELAY_POLL 550 /* Wait 1ms for EC transaction polling */ #define ACPI_EC_CLEAR_MAX 100 /* Maximum number of events to query * when trying to clear the EC */ #define ACPI_EC_MAX_QUERIES 16 /* Maximum number of parallel queries */ enum { EC_FLAGS_QUERY_ENABLED, /* Query is enabled */ EC_FLAGS_EVENT_HANDLER_INSTALLED, /* Event handler installed */ EC_FLAGS_EC_HANDLER_INSTALLED, /* OpReg handler installed */ EC_FLAGS_EC_REG_CALLED, /* OpReg ACPI _REG method called */ EC_FLAGS_QUERY_METHODS_INSTALLED, /* _Qxx handlers installed */ EC_FLAGS_STARTED, /* Driver is started */ EC_FLAGS_STOPPED, /* Driver is stopped */ EC_FLAGS_EVENTS_MASKED, /* Events masked */ }; #define ACPI_EC_COMMAND_POLL 0x01 /* Available for command byte */ #define ACPI_EC_COMMAND_COMPLETE 0x02 /* Completed last byte */ /* ec.c is compiled in acpi namespace so this shows up as acpi.ec_delay param */ static unsigned int ec_delay __read_mostly = ACPI_EC_DELAY; module_param(ec_delay, uint, 0644); MODULE_PARM_DESC(ec_delay, "Timeout(ms) waited until an EC command completes"); static unsigned int ec_max_queries __read_mostly = ACPI_EC_MAX_QUERIES; module_param(ec_max_queries, uint, 0644); MODULE_PARM_DESC(ec_max_queries, "Maximum parallel _Qxx evaluations"); static bool ec_busy_polling __read_mostly; module_param(ec_busy_polling, bool, 0644); MODULE_PARM_DESC(ec_busy_polling, "Use busy polling to advance EC transaction"); static unsigned int ec_polling_guard __read_mostly = ACPI_EC_UDELAY_POLL; module_param(ec_polling_guard, uint, 0644); MODULE_PARM_DESC(ec_polling_guard, "Guard time(us) between EC accesses in polling modes"); static unsigned int ec_event_clearing __read_mostly = ACPI_EC_EVT_TIMING_QUERY; /* * If the number of false interrupts per one transaction exceeds * this threshold, will think there is a GPE storm happened and * will disable the GPE for normal transaction. */ static unsigned int ec_storm_threshold __read_mostly = 8; module_param(ec_storm_threshold, uint, 0644); MODULE_PARM_DESC(ec_storm_threshold, "Maxim false GPE numbers not considered as GPE storm"); static bool ec_freeze_events __read_mostly; module_param(ec_freeze_events, bool, 0644); MODULE_PARM_DESC(ec_freeze_events, "Disabling event handling during suspend/resume"); static bool ec_no_wakeup __read_mostly; module_param(ec_no_wakeup, bool, 0644); MODULE_PARM_DESC(ec_no_wakeup, "Do not wake up from suspend-to-idle"); struct acpi_ec_query_handler { struct list_head node; acpi_ec_query_func func; acpi_handle handle; void *data; u8 query_bit; struct kref kref; }; struct transaction { const u8 *wdata; u8 *rdata; unsigned short irq_count; u8 command; u8 wi; u8 ri; u8 wlen; u8 rlen; u8 flags; }; struct acpi_ec_query { struct transaction transaction; struct work_struct work; struct acpi_ec_query_handler *handler; struct acpi_ec *ec; }; static int acpi_ec_submit_query(struct acpi_ec *ec); static void advance_transaction(struct acpi_ec *ec, bool interrupt); static void acpi_ec_event_handler(struct work_struct *work); struct acpi_ec *first_ec; EXPORT_SYMBOL(first_ec); static struct acpi_ec *boot_ec; static bool boot_ec_is_ecdt; static struct workqueue_struct *ec_wq; static struct workqueue_struct *ec_query_wq; static int EC_FLAGS_CORRECT_ECDT; /* Needs ECDT port address correction */ static int EC_FLAGS_TRUST_DSDT_GPE; /* Needs DSDT GPE as correction setting */ static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */ /* -------------------------------------------------------------------------- * Logging/Debugging * -------------------------------------------------------------------------- */ /* * Splitters used by the developers to track the boundary of the EC * handling processes. */ #ifdef DEBUG #define EC_DBG_SEP " " #define EC_DBG_DRV "+++++" #define EC_DBG_STM "=====" #define EC_DBG_REQ "*****" #define EC_DBG_EVT "#####" #else #define EC_DBG_SEP "" #define EC_DBG_DRV #define EC_DBG_STM #define EC_DBG_REQ #define EC_DBG_EVT #endif #define ec_log_raw(fmt, ...) \ pr_info(fmt "\n", ##__VA_ARGS__) #define ec_dbg_raw(fmt, ...) \ pr_debug(fmt "\n", ##__VA_ARGS__) #define ec_log(filter, fmt, ...) \ ec_log_raw(filter EC_DBG_SEP fmt EC_DBG_SEP filter, ##__VA_ARGS__) #define ec_dbg(filter, fmt, ...) \ ec_dbg_raw(filter EC_DBG_SEP fmt EC_DBG_SEP filter, ##__VA_ARGS__) #define ec_log_drv(fmt, ...) \ ec_log(EC_DBG_DRV, fmt, ##__VA_ARGS__) #define ec_dbg_drv(fmt, ...) \ ec_dbg(EC_DBG_DRV, fmt, ##__VA_ARGS__) #define ec_dbg_stm(fmt, ...) \ ec_dbg(EC_DBG_STM, fmt, ##__VA_ARGS__) #define ec_dbg_req(fmt, ...) \ ec_dbg(EC_DBG_REQ, fmt, ##__VA_ARGS__) #define ec_dbg_evt(fmt, ...) \ ec_dbg(EC_DBG_EVT, fmt, ##__VA_ARGS__) #define ec_dbg_ref(ec, fmt, ...) \ ec_dbg_raw("%lu: " fmt, ec->reference_count, ## __VA_ARGS__) /* -------------------------------------------------------------------------- * Device Flags * -------------------------------------------------------------------------- */ static bool acpi_ec_started(struct acpi_ec *ec) { return test_bit(EC_FLAGS_STARTED, &ec->flags) && !test_bit(EC_FLAGS_STOPPED, &ec->flags); } static bool acpi_ec_event_enabled(struct acpi_ec *ec) { /* * There is an OSPM early stage logic. During the early stages * (boot/resume), OSPMs shouldn't enable the event handling, only * the EC transactions are allowed to be performed. */ if (!test_bit(EC_FLAGS_QUERY_ENABLED, &ec->flags)) return false; /* * However, disabling the event handling is experimental for late * stage (suspend), and is controlled by the boot parameter of * "ec_freeze_events": * 1. true: The EC event handling is disabled before entering * the noirq stage. * 2. false: The EC event handling is automatically disabled as * soon as the EC driver is stopped. */ if (ec_freeze_events) return acpi_ec_started(ec); else return test_bit(EC_FLAGS_STARTED, &ec->flags); } static bool acpi_ec_flushed(struct acpi_ec *ec) { return ec->reference_count == 1; } /* -------------------------------------------------------------------------- * EC Registers * -------------------------------------------------------------------------- */ static inline u8 acpi_ec_read_status(struct acpi_ec *ec) { u8 x = inb(ec->command_addr); ec_dbg_raw("EC_SC(R) = 0x%2.2x " "SCI_EVT=%d BURST=%d CMD=%d IBF=%d OBF=%d", x, !!(x & ACPI_EC_FLAG_SCI), !!(x & ACPI_EC_FLAG_BURST), !!(x & ACPI_EC_FLAG_CMD), !!(x & ACPI_EC_FLAG_IBF), !!(x & ACPI_EC_FLAG_OBF)); return x; } static inline u8 acpi_ec_read_data(struct acpi_ec *ec) { u8 x = inb(ec->data_addr); ec->timestamp = jiffies; ec_dbg_raw("EC_DATA(R) = 0x%2.2x", x); return x; } static inline void acpi_ec_write_cmd(struct acpi_ec *ec, u8 command) { ec_dbg_raw("EC_SC(W) = 0x%2.2x", command); outb(command, ec->command_addr); ec->timestamp = jiffies; } static inline void acpi_ec_write_data(struct acpi_ec *ec, u8 data) { ec_dbg_raw("EC_DATA(W) = 0x%2.2x", data); outb(data, ec->data_addr); ec->timestamp = jiffies; } #if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) static const char *acpi_ec_cmd_string(u8 cmd) { switch (cmd) { case 0x80: return "RD_EC"; case 0x81: return "WR_EC"; case 0x82: return "BE_EC"; case 0x83: return "BD_EC"; case 0x84: return "QR_EC"; } return "UNKNOWN"; } #else #define acpi_ec_cmd_string(cmd) "UNDEF" #endif /* -------------------------------------------------------------------------- * GPE Registers * -------------------------------------------------------------------------- */ static inline bool acpi_ec_gpe_status_set(struct acpi_ec *ec) { acpi_event_status gpe_status = 0; (void)acpi_get_gpe_status(NULL, ec->gpe, &gpe_status); return !!(gpe_status & ACPI_EVENT_FLAG_STATUS_SET); } static inline void acpi_ec_enable_gpe(struct acpi_ec *ec, bool open) { if (open) acpi_enable_gpe(NULL, ec->gpe); else { BUG_ON(ec->reference_count < 1); acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_ENABLE); } if (acpi_ec_gpe_status_set(ec)) { /* * On some platforms, EN=1 writes cannot trigger GPE. So * software need to manually trigger a pseudo GPE event on * EN=1 writes. */ ec_dbg_raw("Polling quirk"); advance_transaction(ec, false); } } static inline void acpi_ec_disable_gpe(struct acpi_ec *ec, bool close) { if (close) acpi_disable_gpe(NULL, ec->gpe); else { BUG_ON(ec->reference_count < 1); acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_DISABLE); } } /* -------------------------------------------------------------------------- * Transaction Management * -------------------------------------------------------------------------- */ static void acpi_ec_submit_request(struct acpi_ec *ec) { ec->reference_count++; if (test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags) && ec->gpe >= 0 && ec->reference_count == 1) acpi_ec_enable_gpe(ec, true); } static void acpi_ec_complete_request(struct acpi_ec *ec) { bool flushed = false; ec->reference_count--; if (test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags) && ec->gpe >= 0 && ec->reference_count == 0) acpi_ec_disable_gpe(ec, true); flushed = acpi_ec_flushed(ec); if (flushed) wake_up(&ec->wait); } static void acpi_ec_mask_events(struct acpi_ec *ec) { if (!test_bit(EC_FLAGS_EVENTS_MASKED, &ec->flags)) { if (ec->gpe >= 0) acpi_ec_disable_gpe(ec, false); else disable_irq_nosync(ec->irq); ec_dbg_drv("Polling enabled"); set_bit(EC_FLAGS_EVENTS_MASKED, &ec->flags); } } static void acpi_ec_unmask_events(struct acpi_ec *ec) { if (test_bit(EC_FLAGS_EVENTS_MASKED, &ec->flags)) { clear_bit(EC_FLAGS_EVENTS_MASKED, &ec->flags); if (ec->gpe >= 0) acpi_ec_enable_gpe(ec, false); else enable_irq(ec->irq); ec_dbg_drv("Polling disabled"); } } /* * acpi_ec_submit_flushable_request() - Increase the reference count unless * the flush operation is not in * progress * @ec: the EC device * * This function must be used before taking a new action that should hold * the reference count. If this function returns false, then the action * must be discarded or it will prevent the flush operation from being * completed. */ static bool acpi_ec_submit_flushable_request(struct acpi_ec *ec) { if (!acpi_ec_started(ec)) return false; acpi_ec_submit_request(ec); return true; } static void acpi_ec_submit_event(struct acpi_ec *ec) { /* * It is safe to mask the events here, because acpi_ec_close_event() * will run at least once after this. */ acpi_ec_mask_events(ec); if (!acpi_ec_event_enabled(ec)) return; if (ec->event_state != EC_EVENT_READY) return; ec_dbg_evt("Command(%s) submitted/blocked", acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY)); ec->event_state = EC_EVENT_IN_PROGRESS; /* * If events_to_process is greater than 0 at this point, the while () * loop in acpi_ec_event_handler() is still running and incrementing * events_to_process will cause it to invoke acpi_ec_submit_query() once * more, so it is not necessary to queue up the event work to start the * same loop again. */ if (ec->events_to_process++ > 0) return; ec->events_in_progress++; queue_work(ec_wq, &ec->work); } static void acpi_ec_complete_event(struct acpi_ec *ec) { if (ec->event_state == EC_EVENT_IN_PROGRESS) ec->event_state = EC_EVENT_COMPLETE; } static void acpi_ec_close_event(struct acpi_ec *ec) { if (ec->event_state != EC_EVENT_READY) ec_dbg_evt("Command(%s) unblocked", acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY)); ec->event_state = EC_EVENT_READY; acpi_ec_unmask_events(ec); } static inline void __acpi_ec_enable_event(struct acpi_ec *ec) { if (!test_and_set_bit(EC_FLAGS_QUERY_ENABLED, &ec->flags)) ec_log_drv("event unblocked"); /* * Unconditionally invoke this once after enabling the event * handling mechanism to detect the pending events. */ advance_transaction(ec, false); } static inline void __acpi_ec_disable_event(struct acpi_ec *ec) { if (test_and_clear_bit(EC_FLAGS_QUERY_ENABLED, &ec->flags)) ec_log_drv("event blocked"); } /* * Process _Q events that might have accumulated in the EC. * Run with locked ec mutex. */ static void acpi_ec_clear(struct acpi_ec *ec) { int i; for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) { if (acpi_ec_submit_query(ec)) break; } if (unlikely(i == ACPI_EC_CLEAR_MAX)) pr_warn("Warning: Maximum of %d stale EC events cleared\n", i); else pr_info("%d stale EC events cleared\n", i); } static void acpi_ec_enable_event(struct acpi_ec *ec) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); if (acpi_ec_started(ec)) __acpi_ec_enable_event(ec); spin_unlock_irqrestore(&ec->lock, flags); /* Drain additional events if hardware requires that */ if (EC_FLAGS_CLEAR_ON_RESUME) acpi_ec_clear(ec); } #ifdef CONFIG_PM_SLEEP static void __acpi_ec_flush_work(void) { flush_workqueue(ec_wq); /* flush ec->work */ flush_workqueue(ec_query_wq); /* flush queries */ } static void acpi_ec_disable_event(struct acpi_ec *ec) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); __acpi_ec_disable_event(ec); spin_unlock_irqrestore(&ec->lock, flags); /* * When ec_freeze_events is true, we need to flush events in * the proper position before entering the noirq stage. */ __acpi_ec_flush_work(); } void acpi_ec_flush_work(void) { /* Without ec_wq there is nothing to flush. */ if (!ec_wq) return; __acpi_ec_flush_work(); } #endif /* CONFIG_PM_SLEEP */ static bool acpi_ec_guard_event(struct acpi_ec *ec) { unsigned long flags; bool guarded; spin_lock_irqsave(&ec->lock, flags); /* * If firmware SCI_EVT clearing timing is "event", we actually * don't know when the SCI_EVT will be cleared by firmware after * evaluating _Qxx, so we need to re-check SCI_EVT after waiting an * acceptable period. * * The guarding period is applicable if the event state is not * EC_EVENT_READY, but otherwise if the current transaction is of the * ACPI_EC_COMMAND_QUERY type, the guarding should have elapsed already * and it should not be applied to let the transaction transition into * the ACPI_EC_COMMAND_POLL state immediately. */ guarded = ec_event_clearing == ACPI_EC_EVT_TIMING_EVENT && ec->event_state != EC_EVENT_READY && (!ec->curr || ec->curr->command != ACPI_EC_COMMAND_QUERY); spin_unlock_irqrestore(&ec->lock, flags); return guarded; } static int ec_transaction_polled(struct acpi_ec *ec) { unsigned long flags; int ret = 0; spin_lock_irqsave(&ec->lock, flags); if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_POLL)) ret = 1; spin_unlock_irqrestore(&ec->lock, flags); return ret; } static int ec_transaction_completed(struct acpi_ec *ec) { unsigned long flags; int ret = 0; spin_lock_irqsave(&ec->lock, flags); if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_COMPLETE)) ret = 1; spin_unlock_irqrestore(&ec->lock, flags); return ret; } static inline void ec_transaction_transition(struct acpi_ec *ec, unsigned long flag) { ec->curr->flags |= flag; if (ec->curr->command != ACPI_EC_COMMAND_QUERY) return; switch (ec_event_clearing) { case ACPI_EC_EVT_TIMING_STATUS: if (flag == ACPI_EC_COMMAND_POLL) acpi_ec_close_event(ec); return; case ACPI_EC_EVT_TIMING_QUERY: if (flag == ACPI_EC_COMMAND_COMPLETE) acpi_ec_close_event(ec); return; case ACPI_EC_EVT_TIMING_EVENT: if (flag == ACPI_EC_COMMAND_COMPLETE) acpi_ec_complete_event(ec); } } static void acpi_ec_spurious_interrupt(struct acpi_ec *ec, struct transaction *t) { if (t->irq_count < ec_storm_threshold) ++t->irq_count; /* Trigger if the threshold is 0 too. */ if (t->irq_count == ec_storm_threshold) acpi_ec_mask_events(ec); } static void advance_transaction(struct acpi_ec *ec, bool interrupt) { struct transaction *t = ec->curr; bool wakeup = false; u8 status; ec_dbg_stm("%s (%d)", interrupt ? "IRQ" : "TASK", smp_processor_id()); status = acpi_ec_read_status(ec); /* * Another IRQ or a guarded polling mode advancement is detected, * the next QR_EC submission is then allowed. */ if (!t || !(t->flags & ACPI_EC_COMMAND_POLL)) { if (ec_event_clearing == ACPI_EC_EVT_TIMING_EVENT && ec->event_state == EC_EVENT_COMPLETE) acpi_ec_close_event(ec); if (!t) goto out; } if (t->flags & ACPI_EC_COMMAND_POLL) { if (t->wlen > t->wi) { if (!(status & ACPI_EC_FLAG_IBF)) acpi_ec_write_data(ec, t->wdata[t->wi++]); else if (interrupt && !(status & ACPI_EC_FLAG_SCI)) acpi_ec_spurious_interrupt(ec, t); } else if (t->rlen > t->ri) { if (status & ACPI_EC_FLAG_OBF) { t->rdata[t->ri++] = acpi_ec_read_data(ec); if (t->rlen == t->ri) { ec_transaction_transition(ec, ACPI_EC_COMMAND_COMPLETE); wakeup = true; if (t->command == ACPI_EC_COMMAND_QUERY) ec_dbg_evt("Command(%s) completed by hardware", acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY)); } } else if (interrupt && !(status & ACPI_EC_FLAG_SCI)) { acpi_ec_spurious_interrupt(ec, t); } } else if (t->wlen == t->wi && !(status & ACPI_EC_FLAG_IBF)) { ec_transaction_transition(ec, ACPI_EC_COMMAND_COMPLETE); wakeup = true; } } else if (!(status & ACPI_EC_FLAG_IBF)) { acpi_ec_write_cmd(ec, t->command); ec_transaction_transition(ec, ACPI_EC_COMMAND_POLL); } out: if (status & ACPI_EC_FLAG_SCI) acpi_ec_submit_event(ec); if (wakeup && interrupt) wake_up(&ec->wait); } static void start_transaction(struct acpi_ec *ec) { ec->curr->irq_count = ec->curr->wi = ec->curr->ri = 0; ec->curr->flags = 0; } static int ec_guard(struct acpi_ec *ec) { unsigned long guard = usecs_to_jiffies(ec->polling_guard); unsigned long timeout = ec->timestamp + guard; /* Ensure guarding period before polling EC status */ do { if (ec->busy_polling) { /* Perform busy polling */ if (ec_transaction_completed(ec)) return 0; udelay(jiffies_to_usecs(guard)); } else { /* * Perform wait polling * 1. Wait the transaction to be completed by the * GPE handler after the transaction enters * ACPI_EC_COMMAND_POLL state. * 2. A special guarding logic is also required * for event clearing mode "event" before the * transaction enters ACPI_EC_COMMAND_POLL * state. */ if (!ec_transaction_polled(ec) && !acpi_ec_guard_event(ec)) break; if (wait_event_timeout(ec->wait, ec_transaction_completed(ec), guard)) return 0; } } while (time_before(jiffies, timeout)); return -ETIME; } static int ec_poll(struct acpi_ec *ec) { unsigned long flags; int repeat = 5; /* number of command restarts */ while (repeat--) { unsigned long delay = jiffies + msecs_to_jiffies(ec_delay); do { if (!ec_guard(ec)) return 0; spin_lock_irqsave(&ec->lock, flags); advance_transaction(ec, false); spin_unlock_irqrestore(&ec->lock, flags); } while (time_before(jiffies, delay)); pr_debug("controller reset, restart transaction\n"); spin_lock_irqsave(&ec->lock, flags); start_transaction(ec); spin_unlock_irqrestore(&ec->lock, flags); } return -ETIME; } static int acpi_ec_transaction_unlocked(struct acpi_ec *ec, struct transaction *t) { unsigned long tmp; int ret = 0; if (t->rdata) memset(t->rdata, 0, t->rlen); /* start transaction */ spin_lock_irqsave(&ec->lock, tmp); /* Enable GPE for command processing (IBF=0/OBF=1) */ if (!acpi_ec_submit_flushable_request(ec)) { ret = -EINVAL; goto unlock; } ec_dbg_ref(ec, "Increase command"); /* following two actions should be kept atomic */ ec->curr = t; ec_dbg_req("Command(%s) started", acpi_ec_cmd_string(t->command)); start_transaction(ec); spin_unlock_irqrestore(&ec->lock, tmp); ret = ec_poll(ec); spin_lock_irqsave(&ec->lock, tmp); if (t->irq_count == ec_storm_threshold) acpi_ec_unmask_events(ec); ec_dbg_req("Command(%s) stopped", acpi_ec_cmd_string(t->command)); ec->curr = NULL; /* Disable GPE for command processing (IBF=0/OBF=1) */ acpi_ec_complete_request(ec); ec_dbg_ref(ec, "Decrease command"); unlock: spin_unlock_irqrestore(&ec->lock, tmp); return ret; } static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t) { int status; u32 glk; if (!ec || (!t) || (t->wlen && !t->wdata) || (t->rlen && !t->rdata)) return -EINVAL; mutex_lock(&ec->mutex); if (ec->global_lock) { status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk); if (ACPI_FAILURE(status)) { status = -ENODEV; goto unlock; } } status = acpi_ec_transaction_unlocked(ec, t); if (ec->global_lock) acpi_release_global_lock(glk); unlock: mutex_unlock(&ec->mutex); return status; } static int acpi_ec_burst_enable(struct acpi_ec *ec) { u8 d; struct transaction t = {.command = ACPI_EC_BURST_ENABLE, .wdata = NULL, .rdata = &d, .wlen = 0, .rlen = 1}; return acpi_ec_transaction_unlocked(ec, &t); } static int acpi_ec_burst_disable(struct acpi_ec *ec) { struct transaction t = {.command = ACPI_EC_BURST_DISABLE, .wdata = NULL, .rdata = NULL, .wlen = 0, .rlen = 0}; return (acpi_ec_read_status(ec) & ACPI_EC_FLAG_BURST) ? acpi_ec_transaction_unlocked(ec, &t) : 0; } static int acpi_ec_read(struct acpi_ec *ec, u8 address, u8 *data) { int result; u8 d; struct transaction t = {.command = ACPI_EC_COMMAND_READ, .wdata = &address, .rdata = &d, .wlen = 1, .rlen = 1}; result = acpi_ec_transaction(ec, &t); *data = d; return result; } static int acpi_ec_read_unlocked(struct acpi_ec *ec, u8 address, u8 *data) { int result; u8 d; struct transaction t = {.command = ACPI_EC_COMMAND_READ, .wdata = &address, .rdata = &d, .wlen = 1, .rlen = 1}; result = acpi_ec_transaction_unlocked(ec, &t); *data = d; return result; } static int acpi_ec_write(struct acpi_ec *ec, u8 address, u8 data) { u8 wdata[2] = { address, data }; struct transaction t = {.command = ACPI_EC_COMMAND_WRITE, .wdata = wdata, .rdata = NULL, .wlen = 2, .rlen = 0}; return acpi_ec_transaction(ec, &t); } static int acpi_ec_write_unlocked(struct acpi_ec *ec, u8 address, u8 data) { u8 wdata[2] = { address, data }; struct transaction t = {.command = ACPI_EC_COMMAND_WRITE, .wdata = wdata, .rdata = NULL, .wlen = 2, .rlen = 0}; return acpi_ec_transaction_unlocked(ec, &t); } int ec_read(u8 addr, u8 *val) { int err; u8 temp_data; if (!first_ec) return -ENODEV; err = acpi_ec_read(first_ec, addr, &temp_data); if (!err) { *val = temp_data; return 0; } return err; } EXPORT_SYMBOL(ec_read); int ec_write(u8 addr, u8 val) { if (!first_ec) return -ENODEV; return acpi_ec_write(first_ec, addr, val); } EXPORT_SYMBOL(ec_write); int ec_transaction(u8 command, const u8 *wdata, unsigned wdata_len, u8 *rdata, unsigned rdata_len) { struct transaction t = {.command = command, .wdata = wdata, .rdata = rdata, .wlen = wdata_len, .rlen = rdata_len}; if (!first_ec) return -ENODEV; return acpi_ec_transaction(first_ec, &t); } EXPORT_SYMBOL(ec_transaction); /* Get the handle to the EC device */ acpi_handle ec_get_handle(void) { if (!first_ec) return NULL; return first_ec->handle; } EXPORT_SYMBOL(ec_get_handle); static void acpi_ec_start(struct acpi_ec *ec, bool resuming) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); if (!test_and_set_bit(EC_FLAGS_STARTED, &ec->flags)) { ec_dbg_drv("Starting EC"); /* Enable GPE for event processing (SCI_EVT=1) */ if (!resuming) { acpi_ec_submit_request(ec); ec_dbg_ref(ec, "Increase driver"); } ec_log_drv("EC started"); } spin_unlock_irqrestore(&ec->lock, flags); } static bool acpi_ec_stopped(struct acpi_ec *ec) { unsigned long flags; bool flushed; spin_lock_irqsave(&ec->lock, flags); flushed = acpi_ec_flushed(ec); spin_unlock_irqrestore(&ec->lock, flags); return flushed; } static void acpi_ec_stop(struct acpi_ec *ec, bool suspending) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); if (acpi_ec_started(ec)) { ec_dbg_drv("Stopping EC"); set_bit(EC_FLAGS_STOPPED, &ec->flags); spin_unlock_irqrestore(&ec->lock, flags); wait_event(ec->wait, acpi_ec_stopped(ec)); spin_lock_irqsave(&ec->lock, flags); /* Disable GPE for event processing (SCI_EVT=1) */ if (!suspending) { acpi_ec_complete_request(ec); ec_dbg_ref(ec, "Decrease driver"); } else if (!ec_freeze_events) __acpi_ec_disable_event(ec); clear_bit(EC_FLAGS_STARTED, &ec->flags); clear_bit(EC_FLAGS_STOPPED, &ec->flags); ec_log_drv("EC stopped"); } spin_unlock_irqrestore(&ec->lock, flags); } static void acpi_ec_enter_noirq(struct acpi_ec *ec) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); ec->busy_polling = true; ec->polling_guard = 0; ec_log_drv("interrupt blocked"); spin_unlock_irqrestore(&ec->lock, flags); } static void acpi_ec_leave_noirq(struct acpi_ec *ec) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); ec->busy_polling = ec_busy_polling; ec->polling_guard = ec_polling_guard; ec_log_drv("interrupt unblocked"); spin_unlock_irqrestore(&ec->lock, flags); } void acpi_ec_block_transactions(void) { struct acpi_ec *ec = first_ec; if (!ec) return; mutex_lock(&ec->mutex); /* Prevent transactions from being carried out */ acpi_ec_stop(ec, true); mutex_unlock(&ec->mutex); } void acpi_ec_unblock_transactions(void) { /* * Allow transactions to happen again (this function is called from * atomic context during wakeup, so we don't need to acquire the mutex). */ if (first_ec) acpi_ec_start(first_ec, true); } /* -------------------------------------------------------------------------- Event Management -------------------------------------------------------------------------- */ static struct acpi_ec_query_handler * acpi_ec_get_query_handler_by_value(struct acpi_ec *ec, u8 value) { struct acpi_ec_query_handler *handler; mutex_lock(&ec->mutex); list_for_each_entry(handler, &ec->list, node) { if (value == handler->query_bit) { kref_get(&handler->kref); mutex_unlock(&ec->mutex); return handler; } } mutex_unlock(&ec->mutex); return NULL; } static void acpi_ec_query_handler_release(struct kref *kref) { struct acpi_ec_query_handler *handler = container_of(kref, struct acpi_ec_query_handler, kref); kfree(handler); } static void acpi_ec_put_query_handler(struct acpi_ec_query_handler *handler) { kref_put(&handler->kref, acpi_ec_query_handler_release); } int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, acpi_handle handle, acpi_ec_query_func func, void *data) { struct acpi_ec_query_handler *handler; if (!handle && !func) return -EINVAL; handler = kzalloc_obj(*handler); if (!handler) return -ENOMEM; handler->query_bit = query_bit; handler->handle = handle; handler->func = func; handler->data = data; mutex_lock(&ec->mutex); kref_init(&handler->kref); list_add(&handler->node, &ec->list); mutex_unlock(&ec->mutex); return 0; } EXPORT_SYMBOL_GPL(acpi_ec_add_query_handler); static void acpi_ec_remove_query_handlers(struct acpi_ec *ec, bool remove_all, u8 query_bit) { struct acpi_ec_query_handler *handler, *tmp; LIST_HEAD(free_list); mutex_lock(&ec->mutex); list_for_each_entry_safe(handler, tmp, &ec->list, node) { /* * When remove_all is false, only remove custom query handlers * which have handler->func set. This is done to preserve query * handlers discovered thru ACPI, as they should continue handling * EC queries. */ if (remove_all || (handler->func && handler->query_bit == query_bit)) { list_del_init(&handler->node); list_add(&handler->node, &free_list); } } mutex_unlock(&ec->mutex); list_for_each_entry_safe(handler, tmp, &free_list, node) acpi_ec_put_query_handler(handler); } void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit) { acpi_ec_remove_query_handlers(ec, false, query_bit); flush_workqueue(ec_query_wq); } EXPORT_SYMBOL_GPL(acpi_ec_remove_query_handler); static void acpi_ec_event_processor(struct work_struct *work) { struct acpi_ec_query *q = container_of(work, struct acpi_ec_query, work); struct acpi_ec_query_handler *handler = q->handler; struct acpi_ec *ec = q->ec; ec_dbg_evt("Query(0x%02x) started", handler->query_bit); if (handler->func) handler->func(handler->data); else if (handler->handle) acpi_evaluate_object(handler->handle, NULL, NULL, NULL); ec_dbg_evt("Query(0x%02x) stopped", handler->query_bit); spin_lock_irq(&ec->lock); ec->queries_in_progress--; spin_unlock_irq(&ec->lock); acpi_ec_put_query_handler(handler); kfree(q); } static struct acpi_ec_query *acpi_ec_create_query(struct acpi_ec *ec, u8 *pval) { struct acpi_ec_query *q; struct transaction *t; q = kzalloc_obj(struct acpi_ec_query); if (!q) return NULL; INIT_WORK(&q->work, acpi_ec_event_processor); t = &q->transaction; t->command = ACPI_EC_COMMAND_QUERY; t->rdata = pval; t->rlen = 1; q->ec = ec; return q; } static int acpi_ec_submit_query(struct acpi_ec *ec) { struct acpi_ec_query *q; u8 value = 0; int result; q = acpi_ec_create_query(ec, &value); if (!q) return -ENOMEM; /* * Query the EC to find out which _Qxx method we need to evaluate. * Note that successful completion of the query causes the ACPI_EC_SCI * bit to be cleared (and thus clearing the interrupt source). */ result = acpi_ec_transaction(ec, &q->transaction); if (result) goto err_exit; if (!value) { result = -ENODATA; goto err_exit; } q->handler = acpi_ec_get_query_handler_by_value(ec, value); if (!q->handler) { result = -ENODATA; goto err_exit; } /* * It is reported that _Qxx are evaluated in a parallel way on Windows: * https://bugzilla.kernel.org/show_bug.cgi?id=94411 * * Put this log entry before queue_work() to make it appear in the log * before any other messages emitted during workqueue handling. */ ec_dbg_evt("Query(0x%02x) scheduled", value); spin_lock_irq(&ec->lock); ec->queries_in_progress++; queue_work(ec_query_wq, &q->work); spin_unlock_irq(&ec->lock); return 0; err_exit: kfree(q); return result; } static void acpi_ec_event_handler(struct work_struct *work) { struct acpi_ec *ec = container_of(work, struct acpi_ec, work); ec_dbg_evt("Event started"); spin_lock_irq(&ec->lock); while (ec->events_to_process) { spin_unlock_irq(&ec->lock); acpi_ec_submit_query(ec); spin_lock_irq(&ec->lock); ec->events_to_process--; } /* * Before exit, make sure that the it will be possible to queue up the * event handling work again regardless of whether or not the query * queued up above is processed successfully. */ if (ec_event_clearing == ACPI_EC_EVT_TIMING_EVENT) { bool guard_timeout; acpi_ec_complete_event(ec); ec_dbg_evt("Event stopped"); spin_unlock_irq(&ec->lock); guard_timeout = !!ec_guard(ec); spin_lock_irq(&ec->lock); /* Take care of SCI_EVT unless someone else is doing that. */ if (guard_timeout && !ec->curr) advance_transaction(ec, false); } else { acpi_ec_close_event(ec); ec_dbg_evt("Event stopped"); } ec->events_in_progress--; spin_unlock_irq(&ec->lock); } static void clear_gpe_and_advance_transaction(struct acpi_ec *ec, bool interrupt) { /* * Clear GPE_STS upfront to allow subsequent hardware GPE_STS 0->1 * changes to always trigger a GPE interrupt. * * GPE STS is a W1C register, which means: * * 1. Software can clear it without worrying about clearing the other * GPEs' STS bits when the hardware sets them in parallel. * * 2. As long as software can ensure only clearing it when it is set, * hardware won't set it in parallel. */ if (ec->gpe >= 0 && acpi_ec_gpe_status_set(ec)) acpi_clear_gpe(NULL, ec->gpe); advance_transaction(ec, true); } static void acpi_ec_handle_interrupt(struct acpi_ec *ec) { unsigned long flags; spin_lock_irqsave(&ec->lock, flags); clear_gpe_and_advance_transaction(ec, true); spin_unlock_irqrestore(&ec->lock, flags); } static u32 acpi_ec_gpe_handler(acpi_handle gpe_device, u32 gpe_number, void *data) { acpi_ec_handle_interrupt(data); return ACPI_INTERRUPT_HANDLED; } static irqreturn_t acpi_ec_irq_handler(int irq, void *data) { acpi_ec_handle_interrupt(data); return IRQ_HANDLED; } /* -------------------------------------------------------------------------- * Address Space Management * -------------------------------------------------------------------------- */ static acpi_status acpi_ec_space_handler(u32 function, acpi_physical_address address, u32 bits, u64 *value64, void *handler_context, void *region_context) { struct acpi_ec *ec = handler_context; int result = 0, i, bytes = bits / 8; u8 *value = (u8 *)value64; u32 glk; if ((address > 0xFF) || !value || !handler_context) return AE_BAD_PARAMETER; if (function != ACPI_READ && function != ACPI_WRITE) return AE_BAD_PARAMETER; mutex_lock(&ec->mutex); if (ec->global_lock) { acpi_status status; status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk); if (ACPI_FAILURE(status)) { result = -ENODEV; goto unlock; } } if (ec->busy_polling || bits > 8) acpi_ec_burst_enable(ec); for (i = 0; i < bytes; ++i, ++address, ++value) { result = (function == ACPI_READ) ? acpi_ec_read_unlocked(ec, address, value) : acpi_ec_write_unlocked(ec, address, *value); if (result < 0) break; } if (ec->busy_polling || bits > 8) acpi_ec_burst_disable(ec); if (ec->global_lock) acpi_release_global_lock(glk); unlock: mutex_unlock(&ec->mutex); switch (result) { case -EINVAL: return AE_BAD_PARAMETER; case -ENODEV: return AE_NOT_FOUND; case -ETIME: return AE_TIME; case 0: return AE_OK; default: return AE_ERROR; } } /* -------------------------------------------------------------------------- * Driver Interface * -------------------------------------------------------------------------- */ static acpi_status ec_parse_io_ports(struct acpi_resource *resource, void *context); static void acpi_ec_free(struct acpi_ec *ec) { if (first_ec == ec) first_ec = NULL; if (boot_ec == ec) boot_ec = NULL; kfree(ec); } static struct acpi_ec *acpi_ec_alloc(void) { struct acpi_ec *ec = kzalloc_obj(struct acpi_ec); if (!ec) return NULL; mutex_init(&ec->mutex); init_waitqueue_head(&ec->wait); INIT_LIST_HEAD(&ec->list); spin_lock_init(&ec->lock); INIT_WORK(&ec->work, acpi_ec_event_handler); ec->timestamp = jiffies; ec->busy_polling = true; ec->polling_guard = 0; ec->gpe = -1; ec->irq = -1; return ec; } static acpi_status acpi_ec_register_query_methods(acpi_handle handle, u32 level, void *context, void **return_value) { char node_name[5]; struct acpi_buffer buffer = { sizeof(node_name), node_name }; struct acpi_ec *ec = context; int value = 0; acpi_status status; status = acpi_get_name(handle, ACPI_SINGLE_NAME, &buffer); if (ACPI_SUCCESS(status) && sscanf(node_name, "_Q%x", &value) == 1) acpi_ec_add_query_handler(ec, value, handle, NULL, NULL); return AE_OK; } static acpi_status ec_parse_device(acpi_handle handle, u32 Level, void *context, void **retval) { acpi_status status; unsigned long long tmp = 0; struct acpi_ec *ec = context; /* clear addr values, ec_parse_io_ports depend on it */ ec->command_addr = ec->data_addr = 0; status = acpi_walk_resources(handle, METHOD_NAME__CRS, ec_parse_io_ports, ec); if (ACPI_FAILURE(status)) return status; if (ec->data_addr == 0 || ec->command_addr == 0) return AE_OK; /* Get GPE bit assignment (EC events). */ /* TODO: Add support for _GPE returning a package */ status = acpi_evaluate_integer(handle, "_GPE", NULL, &tmp); if (ACPI_SUCCESS(status)) ec->gpe = tmp; /* * Errors are non-fatal, allowing for ACPI Reduced Hardware * platforms which use GpioInt instead of GPE. */ /* Use the global lock for all EC transactions? */ tmp = 0; acpi_evaluate_integer(handle, "_GLK", NULL, &tmp); ec->global_lock = tmp; ec->handle = handle; return AE_CTRL_TERMINATE; } static bool install_gpe_event_handler(struct acpi_ec *ec) { acpi_status status; status = acpi_install_gpe_raw_handler(NULL, ec->gpe, ACPI_GPE_EDGE_TRIGGERED, &acpi_ec_gpe_handler, ec); if (ACPI_FAILURE(status)) return false; if (test_bit(EC_FLAGS_STARTED, &ec->flags) && ec->reference_count >= 1) acpi_ec_enable_gpe(ec, true); return true; } static bool install_gpio_irq_event_handler(struct acpi_ec *ec) { return request_threaded_irq(ec->irq, NULL, acpi_ec_irq_handler, IRQF_SHARED | IRQF_ONESHOT, "ACPI EC", ec) >= 0; } /** * ec_install_handlers - Install service callbacks and register query methods. * @ec: Target EC. * @device: ACPI device object corresponding to @ec. * @call_reg: If _REG should be called to notify OpRegion availability * * Install a handler for the EC address space type unless it has been installed * already. If @device is not NULL, also look for EC query methods in the * namespace and register them, and install an event (either GPE or GPIO IRQ) * handler for the EC, if possible. * * Return: * -ENODEV if the address space handler cannot be installed, which means * "unable to handle transactions", * -EPROBE_DEFER if GPIO IRQ acquisition needs to be deferred, * or 0 (success) otherwise. */ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, bool call_reg) { acpi_status status; acpi_ec_start(ec, false); if (!test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle; acpi_ec_enter_noirq(ec); status = acpi_install_address_space_handler_no_reg(scope_handle, ACPI_ADR_SPACE_EC, &acpi_ec_space_handler, NULL, ec); if (ACPI_FAILURE(status)) { acpi_ec_stop(ec, false); return -ENODEV; } set_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags); } if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { acpi_execute_reg_methods(ec->handle, ACPI_UINT32_MAX, ACPI_ADR_SPACE_EC); set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); } if (!device) return 0; if (ec->gpe < 0) { /* ACPI reduced hardware platforms use a GpioInt from _CRS. */ int irq = acpi_dev_gpio_irq_get(device, 0); /* * Bail out right away for deferred probing or complete the * initialization regardless of any other errors. */ if (irq == -EPROBE_DEFER) return -EPROBE_DEFER; else if (irq >= 0) ec->irq = irq; } if (!test_bit(EC_FLAGS_QUERY_METHODS_INSTALLED, &ec->flags)) { /* Find and register all query methods */ acpi_walk_namespace(ACPI_TYPE_METHOD, ec->handle, 1, acpi_ec_register_query_methods, NULL, ec, NULL); set_bit(EC_FLAGS_QUERY_METHODS_INSTALLED, &ec->flags); } if (!test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags)) { bool ready = false; if (ec->gpe >= 0) ready = install_gpe_event_handler(ec); else if (ec->irq >= 0) ready = install_gpio_irq_event_handler(ec); if (ready) { set_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags); acpi_ec_leave_noirq(ec); } /* * Failures to install an event handler are not fatal, because * the EC can be polled for events. */ } /* EC is fully operational, allow queries */ acpi_ec_enable_event(ec); return 0; } static void ec_remove_handlers(struct acpi_ec *ec) { acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle; if (test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { if (ACPI_FAILURE(acpi_remove_address_space_handler( scope_handle, ACPI_ADR_SPACE_EC, &acpi_ec_space_handler))) pr_err("failed to remove space handler\n"); clear_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags); } /* * Stops handling the EC transactions after removing the operation * region handler. This is required because _REG(DISCONNECT) * invoked during the removal can result in new EC transactions. * * Flushes the EC requests and thus disables the GPE before * removing the GPE handler. This is required by the current ACPICA * GPE core. ACPICA GPE core will automatically disable a GPE when * it is indicated but there is no way to handle it. So the drivers * must disable the GPEs prior to removing the GPE handlers. */ acpi_ec_stop(ec, false); if (test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags)) { if (ec->gpe >= 0 && ACPI_FAILURE(acpi_remove_gpe_handler(NULL, ec->gpe, &acpi_ec_gpe_handler))) pr_err("failed to remove gpe handler\n"); if (ec->irq >= 0) free_irq(ec->irq, ec); clear_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags); } if (test_bit(EC_FLAGS_QUERY_METHODS_INSTALLED, &ec->flags)) { acpi_ec_remove_query_handlers(ec, true, 0); clear_bit(EC_FLAGS_QUERY_METHODS_INSTALLED, &ec->flags); } } static int acpi_ec_setup(struct acpi_ec *ec, struct acpi_device *device, bool call_reg) { int ret; /* First EC capable of handling transactions */ if (!first_ec) first_ec = ec; ret = ec_install_handlers(ec, device, call_reg); if (ret) { ec_remove_handlers(ec); if (ec == first_ec) first_ec = NULL; return ret; } pr_info("EC_CMD/EC_SC=0x%lx, EC_DATA=0x%lx\n", ec->command_addr, ec->data_addr); if (test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags)) { if (ec->gpe >= 0) pr_info("GPE=0x%x\n", ec->gpe); else pr_info("IRQ=%d\n", ec->irq); } return ret; } static int acpi_ec_probe(struct platform_device *pdev) { struct acpi_device *device; struct acpi_ec *ec; int ret; device = ACPI_COMPANION(&pdev->dev); if (!device) return -ENODEV; if (boot_ec && (boot_ec->handle == device->handle || !strcmp(acpi_device_hid(device), ACPI_ECDT_HID))) { /* Fast path: this device corresponds to the boot EC. */ ec = boot_ec; } else { acpi_status status; ec = acpi_ec_alloc(); if (!ec) return -ENOMEM; status = ec_parse_device(device->handle, 0, ec, NULL); if (status != AE_CTRL_TERMINATE) { ret = -EINVAL; goto err; } if (boot_ec && ec->command_addr == boot_ec->command_addr && ec->data_addr == boot_ec->data_addr) { /* * Trust PNP0C09 namespace location rather than ECDT ID. * But trust ECDT GPE rather than _GPE because of ASUS * quirks. So do not change boot_ec->gpe to ec->gpe, * except when the TRUST_DSDT_GPE quirk is set. */ boot_ec->handle = ec->handle; if (EC_FLAGS_TRUST_DSDT_GPE) boot_ec->gpe = ec->gpe; acpi_handle_debug(ec->handle, "duplicated.\n"); acpi_ec_free(ec); ec = boot_ec; } } ret = acpi_ec_setup(ec, device, true); if (ret) goto err; if (ec == boot_ec) acpi_handle_info(boot_ec->handle, "Boot %s EC initialization complete\n", boot_ec_is_ecdt ? "ECDT" : "DSDT"); acpi_handle_info(ec->handle, "EC: Used to handle transactions and events\n"); platform_set_drvdata(pdev, ec); ret = !!request_region(ec->data_addr, 1, "EC data"); WARN(!ret, "Could not request EC data io port 0x%lx", ec->data_addr); ret = !!request_region(ec->command_addr, 1, "EC cmd"); WARN(!ret, "Could not request EC cmd io port 0x%lx", ec->command_addr); /* Reprobe devices depending on the EC */ acpi_dev_clear_dependencies(device); acpi_handle_debug(ec->handle, "enumerated.\n"); return 0; err: if (ec != boot_ec) acpi_ec_free(ec); return ret; } static void acpi_ec_remove(struct platform_device *pdev) { struct acpi_ec *ec = platform_get_drvdata(pdev); release_region(ec->data_addr, 1); release_region(ec->command_addr, 1); if (ec != boot_ec) { ec_remove_handlers(ec); acpi_ec_free(ec); } } void acpi_ec_register_opregions(struct acpi_device *adev) { if (first_ec && first_ec->handle != adev->handle) acpi_execute_reg_methods(adev->handle, 1, ACPI_ADR_SPACE_EC); } static acpi_status ec_parse_io_ports(struct acpi_resource *resource, void *context) { struct acpi_ec *ec = context; if (resource->type != ACPI_RESOURCE_TYPE_IO) return AE_OK; /* * The first address region returned is the data port, and * the second address region returned is the status/command * port. */ if (ec->data_addr == 0) ec->data_addr = resource->data.io.minimum; else if (ec->command_addr == 0) ec->command_addr = resource->data.io.minimum; else return AE_CTRL_TERMINATE; return AE_OK; } static const struct acpi_device_id ec_device_ids[] = { {"PNP0C09", 0}, {ACPI_ECDT_HID, 0}, {"", 0}, }; /* * This function is not Windows-compatible as Windows never enumerates the * namespace EC before the main ACPI device enumeration process. It is * retained for historical reason and will be deprecated in the future. */ void __init acpi_ec_dsdt_probe(void) { struct acpi_ec *ec; acpi_status status; int ret; /* * If a platform has ECDT, there is no need to proceed as the * following probe is not a part of the ACPI device enumeration, * executing _STA is not safe, and thus this probe may risk of * picking up an invalid EC device. */ if (boot_ec) return; ec = acpi_ec_alloc(); if (!ec) return; /* * At this point, the namespace is initialized, so start to find * the namespace objects. */ status = acpi_get_devices(ec_device_ids[0].id, ec_parse_device, ec, NULL); if (ACPI_FAILURE(status) || !ec->handle) { acpi_ec_free(ec); return; } /* * When the DSDT EC is available, always re-configure boot EC to * have _REG evaluated. _REG can only be evaluated after the * namespace initialization. * At this point, the GPE is not fully initialized, so do not to * handle the events. */ ret = acpi_ec_setup(ec, NULL, true); if (ret) { acpi_ec_free(ec); return; } boot_ec = ec; acpi_handle_info(ec->handle, "Boot DSDT EC used to handle transactions\n"); } /* * acpi_ec_ecdt_start - Finalize the boot ECDT EC initialization. * * First, look for an ACPI handle for the boot ECDT EC if acpi_ec_add() has not * found a matching object in the namespace. * * Next, in case the DSDT EC is not functioning, it is still necessary to * provide a functional ECDT EC to handle events, so add an extra device object * to represent it (see https://bugzilla.kernel.org/show_bug.cgi?id=115021). * * This is useful on platforms with valid ECDT and invalid DSDT EC settings, * like ASUS X550ZE (see https://bugzilla.kernel.org/show_bug.cgi?id=196847). */ static void __init acpi_ec_ecdt_start(void) { struct acpi_table_ecdt *ecdt_ptr; acpi_handle handle; acpi_status status; /* Bail out if a matching EC has been found in the namespace. */ if (!boot_ec || boot_ec->handle != ACPI_ROOT_OBJECT) return; /* Look up the object pointed to from the ECDT in the namespace. */ status = acpi_get_table(ACPI_SIG_ECDT, 1, (struct acpi_table_header **)&ecdt_ptr); if (ACPI_FAILURE(status)) return; status = acpi_get_handle(NULL, ecdt_ptr->id, &handle); if (ACPI_SUCCESS(status)) { boot_ec->handle = handle; /* Add a special ACPI device object to represent the boot EC. */ acpi_bus_register_early_device(ACPI_BUS_TYPE_ECDT_EC); } acpi_put_table((struct acpi_table_header *)ecdt_ptr); } /* * On some hardware it is necessary to clear events accumulated by the EC during * sleep. These ECs stop reporting GPEs until they are manually polled, if too * many events are accumulated. (e.g. Samsung Series 5/9 notebooks) * * https://bugzilla.kernel.org/show_bug.cgi?id=44161 * * Ideally, the EC should also be instructed NOT to accumulate events during * sleep (which Windows seems to do somehow), but the interface to control this * behaviour is not known at this time. * * Models known to be affected are Samsung 530Uxx/535Uxx/540Uxx/550Pxx/900Xxx, * however it is very likely that other Samsung models are affected. * * On systems which don't accumulate _Q events during sleep, this extra check * should be harmless. */ static int ec_clear_on_resume(const struct dmi_system_id *id) { pr_debug("Detected system needing EC poll on resume.\n"); EC_FLAGS_CLEAR_ON_RESUME = 1; ec_event_clearing = ACPI_EC_EVT_TIMING_STATUS; return 0; } /* * Some ECDTs contain wrong register addresses. * MSI MS-171F * https://bugzilla.kernel.org/show_bug.cgi?id=12461 */ static int ec_correct_ecdt(const struct dmi_system_id *id) { pr_debug("Detected system needing ECDT address correction.\n"); EC_FLAGS_CORRECT_ECDT = 1; return 0; } /* * Some ECDTs contain wrong GPE setting, but they share the same port addresses * with DSDT EC, don't duplicate the DSDT EC with ECDT EC in this case. * https://bugzilla.kernel.org/show_bug.cgi?id=209989 */ static int ec_honor_dsdt_gpe(const struct dmi_system_id *id) { pr_debug("Detected system needing DSDT GPE setting.\n"); EC_FLAGS_TRUST_DSDT_GPE = 1; return 0; } static const struct dmi_system_id ec_dmi_table[] __initconst = { { /* * MSI MS-171F * https://bugzilla.kernel.org/show_bug.cgi?id=12461 */ .callback = ec_correct_ecdt, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Micro-Star"), DMI_MATCH(DMI_PRODUCT_NAME, "MS-171F"), }, }, { /* * HP Pavilion Gaming Laptop 15-cx0xxx * https://bugzilla.kernel.org/show_bug.cgi?id=209989 */ .callback = ec_honor_dsdt_gpe, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Gaming Laptop 15-cx0xxx"), }, }, { /* * HP Pavilion Gaming Laptop 15-cx0041ur */ .callback = ec_honor_dsdt_gpe, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "HP 15-cx0041ur"), }, }, { /* * HP Pavilion Gaming Laptop 15-dk1xxx * https://github.com/systemd/systemd/issues/28942 */ .callback = ec_honor_dsdt_gpe, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Gaming Laptop 15-dk1xxx"), }, }, { /* * HP 250 G7 Notebook PC */ .callback = ec_honor_dsdt_gpe, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "HP 250 G7 Notebook PC"), }, }, { /* * Samsung hardware * https://bugzilla.kernel.org/show_bug.cgi?id=44161 */ .callback = ec_clear_on_resume, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), }, }, {} }; void __init acpi_ec_ecdt_probe(void) { struct acpi_table_ecdt *ecdt_ptr; struct acpi_ec *ec; acpi_status status; int ret; /* Generate a boot ec context. */ dmi_check_system(ec_dmi_table); status = acpi_get_table(ACPI_SIG_ECDT, 1, (struct acpi_table_header **)&ecdt_ptr); if (ACPI_FAILURE(status)) return; if (!ecdt_ptr->control.address || !ecdt_ptr->data.address) { /* * Asus X50GL: * https://bugzilla.kernel.org/show_bug.cgi?id=11880 */ goto out; } if (!strlen(ecdt_ptr->id)) { /* * The ECDT table on some MSI notebooks contains invalid data, together * with an empty ID string (""). * * Section 5.2.15 of the ACPI specification requires the ID string to be * a "fully qualified reference to the (...) embedded controller device", * so this string always has to start with a backslash. * * However some ThinkBook machines have a ECDT table with a valid EC * description but an invalid ID string ("_SB.PC00.LPCB.EC0"). * * Because of this we only check if the ID string is empty in order to * avoid the obvious cases. */ pr_err(FW_BUG "Ignoring ECDT due to empty ID string\n"); goto out; } ec = acpi_ec_alloc(); if (!ec) goto out; if (EC_FLAGS_CORRECT_ECDT) { ec->command_addr = ecdt_ptr->data.address; ec->data_addr = ecdt_ptr->control.address; } else { ec->command_addr = ecdt_ptr->control.address; ec->data_addr = ecdt_ptr->data.address; } /* * Ignore the GPE value on Reduced Hardware platforms. * Some products have this set to an erroneous value. */ if (!acpi_gbl_reduced_hardware) ec->gpe = ecdt_ptr->gpe; ec->handle = ACPI_ROOT_OBJECT; /* * At this point, the namespace is not initialized, so do not find * the namespace objects, or handle the events. */ ret = acpi_ec_setup(ec, NULL, false); if (ret) { acpi_ec_free(ec); goto out; } boot_ec = ec; boot_ec_is_ecdt = true; pr_info("Boot ECDT EC used to handle transactions\n"); out: acpi_put_table((struct acpi_table_header *)ecdt_ptr); } #ifdef CONFIG_PM_SLEEP static int acpi_ec_suspend(struct device *dev) { struct acpi_ec *ec = dev_get_drvdata(dev); if (!pm_suspend_no_platform() && ec_freeze_events) acpi_ec_disable_event(ec); return 0; } static int acpi_ec_suspend_noirq(struct device *dev) { struct acpi_ec *ec = dev_get_drvdata(dev); /* * The SCI handler doesn't run at this point, so the GPE can be * masked at the low level without side effects. */ if (ec_no_wakeup && test_bit(EC_FLAGS_STARTED, &ec->flags) && ec->gpe >= 0 && ec->reference_count >= 1) acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_DISABLE); acpi_ec_enter_noirq(ec); return 0; } static int acpi_ec_resume_noirq(struct device *dev) { struct acpi_ec *ec = dev_get_drvdata(dev); acpi_ec_leave_noirq(ec); if (ec_no_wakeup && test_bit(EC_FLAGS_STARTED, &ec->flags) && ec->gpe >= 0 && ec->reference_count >= 1) acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_ENABLE); return 0; } static int acpi_ec_resume(struct device *dev) { struct acpi_ec *ec = dev_get_drvdata(dev); acpi_ec_enable_event(ec); return 0; } void acpi_ec_mark_gpe_for_wake(void) { if (first_ec && !ec_no_wakeup) acpi_mark_gpe_for_wake(NULL, first_ec->gpe); } EXPORT_SYMBOL_GPL(acpi_ec_mark_gpe_for_wake); void acpi_ec_set_gpe_wake_mask(u8 action) { if (pm_suspend_no_platform() && first_ec && !ec_no_wakeup) acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action); } static bool acpi_ec_work_in_progress(struct acpi_ec *ec) { return ec->events_in_progress + ec->queries_in_progress > 0; } bool acpi_ec_dispatch_gpe(void) { bool work_in_progress = false; if (!first_ec) return acpi_any_gpe_status_set(U32_MAX); /* * Report wakeup if the status bit is set for any enabled GPE other * than the EC one. */ if (acpi_any_gpe_status_set(first_ec->gpe)) return true; /* * Cancel the SCI wakeup and process all pending events in case there * are any wakeup ones in there. * * Note that if any non-EC GPEs are active at this point, the SCI will * retrigger after the rearming in acpi_s2idle_wake(), so no events * should be missed by canceling the wakeup here. */ pm_system_cancel_wakeup(); /* * Dispatch the EC GPE in-band, but do not report wakeup in any case * to allow the caller to process events properly after that. */ spin_lock_irq(&first_ec->lock); if (acpi_ec_gpe_status_set(first_ec)) { pm_pr_dbg("ACPI EC GPE status set\n"); clear_gpe_and_advance_transaction(first_ec, false); work_in_progress = acpi_ec_work_in_progress(first_ec); } spin_unlock_irq(&first_ec->lock); if (!work_in_progress) return false; pm_pr_dbg("ACPI EC GPE dispatched\n"); /* Drain EC work. */ do { acpi_ec_flush_work(); pm_pr_dbg("ACPI EC work flushed\n"); spin_lock_irq(&first_ec->lock); work_in_progress = acpi_ec_work_in_progress(first_ec); spin_unlock_irq(&first_ec->lock); } while (work_in_progress && !pm_wakeup_pending()); return false; } #endif /* CONFIG_PM_SLEEP */ static const struct dev_pm_ops acpi_ec_pm = { SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(acpi_ec_suspend_noirq, acpi_ec_resume_noirq) SET_SYSTEM_SLEEP_PM_OPS(acpi_ec_suspend, acpi_ec_resume) }; static int param_set_event_clearing(const char *val, const struct kernel_param *kp) { int result = 0; if (!strncmp(val, "status", sizeof("status") - 1)) { ec_event_clearing = ACPI_EC_EVT_TIMING_STATUS; pr_info("Assuming SCI_EVT clearing on EC_SC accesses\n"); } else if (!strncmp(val, "query", sizeof("query") - 1)) { ec_event_clearing = ACPI_EC_EVT_TIMING_QUERY; pr_info("Assuming SCI_EVT clearing on QR_EC writes\n"); } else if (!strncmp(val, "event", sizeof("event") - 1)) { ec_event_clearing = ACPI_EC_EVT_TIMING_EVENT; pr_info("Assuming SCI_EVT clearing on event reads\n"); } else result = -EINVAL; return result; } static int param_get_event_clearing(char *buffer, const struct kernel_param *kp) { switch (ec_event_clearing) { case ACPI_EC_EVT_TIMING_STATUS: return sprintf(buffer, "status\n"); case ACPI_EC_EVT_TIMING_QUERY: return sprintf(buffer, "query\n"); case ACPI_EC_EVT_TIMING_EVENT: return sprintf(buffer, "event\n"); default: return sprintf(buffer, "invalid\n"); } return 0; } module_param_call(ec_event_clearing, param_set_event_clearing, param_get_event_clearing, NULL, 0644); MODULE_PARM_DESC(ec_event_clearing, "Assumed SCI_EVT clearing timing"); static struct platform_driver acpi_ec_driver = { .probe = acpi_ec_probe, .remove = acpi_ec_remove, .driver = { .name = "acpi-ec", .acpi_match_table = ec_device_ids, .pm = &acpi_ec_pm, }, }; static void acpi_ec_destroy_workqueues(void) { if (ec_wq) { destroy_workqueue(ec_wq); ec_wq = NULL; } if (ec_query_wq) { destroy_workqueue(ec_query_wq); ec_query_wq = NULL; } } static int acpi_ec_init_workqueues(void) { if (!ec_wq) ec_wq = alloc_ordered_workqueue("kec", 0); if (!ec_query_wq) ec_query_wq = alloc_workqueue("kec_query", WQ_PERCPU, ec_max_queries); if (!ec_wq || !ec_query_wq) { acpi_ec_destroy_workqueues(); return -ENODEV; } return 0; } static const struct dmi_system_id acpi_ec_no_wakeup[] = { { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_FAMILY, "Thinkpad X1 Carbon 6th"), }, }, { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Yoga 3rd"), }, }, { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_FAMILY, "103C_5336AN HP ZHAN 66 Pro"), }, }, /* * Lenovo Legion Go S; touchscreen blocks HW sleep when woken up from EC * https://gitlab.freedesktop.org/drm/amd/-/issues/3929 */ { .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "83L3"), } }, { .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "83N6"), } }, { .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "83Q2"), } }, { .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "83Q3"), } }, { // TUXEDO InfinityBook Pro AMD Gen9 .matches = { DMI_MATCH(DMI_BOARD_NAME, "GXxHRXx"), }, }, { }, }; void __init acpi_ec_init(void) { int result; result = acpi_ec_init_workqueues(); if (result) return; /* * Disable EC wakeup on following systems to prevent periodic * wakeup from EC GPE. */ if (dmi_check_system(acpi_ec_no_wakeup)) { ec_no_wakeup = true; pr_debug("Disabling EC wakeup on suspend-to-idle\n"); } /* Driver must be registered after acpi_ec_init_workqueues(). */ platform_driver_register(&acpi_ec_driver); acpi_ec_ecdt_start(); } |
| 3 6 6 2 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/netlink.h> #include <linux/rtnetlink.h> #include <linux/types.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <linux/in6.h> #include <net/ip.h> int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack) { *ip_proto = nla_get_u8(attr); switch (*ip_proto) { case IPPROTO_TCP: case IPPROTO_UDP: return 0; case IPPROTO_ICMP: if (family != AF_INET) break; return 0; #if IS_ENABLED(CONFIG_IPV6) case IPPROTO_ICMPV6: if (family != AF_INET6) break; return 0; #endif } NL_SET_ERR_MSG(extack, "Unsupported ip proto"); return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(rtm_getroute_parse_ip_proto); |
| 100 100 100 2 2 2 5 5 5 5 11 11 1554 1555 100 100 37 1 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 | // SPDX-License-Identifier: GPL-2.0-or-later /* * "LAPB via ethernet" driver release 001 * * This code REQUIRES 2.1.15 or higher/ NET3.038 * * This is a "pseudo" network driver to allow LAPB over Ethernet. * * This driver can use any ethernet destination address, and can be * limited to accept frames from one dedicated ethernet card only. * * History * LAPBETH 001 Jonathan Naylor Cloned from bpqether.c * 2000-10-29 Henner Eisen lapb_data_indication() return status. * 2000-11-14 Henner Eisen dev_hold/put, NETDEV_GOING_DOWN support */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/uaccess.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/notifier.h> #include <linux/stat.h> #include <linux/module.h> #include <linux/lapb.h> #include <linux/init.h> #include <net/netdev_lock.h> #include <net/x25device.h> static const u8 bcast_addr[6] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; /* If this number is made larger, check that the temporary string buffer * in lapbeth_new_device is large enough to store the probe device name. */ #define MAXLAPBDEV 100 struct lapbethdev { struct list_head node; struct net_device *ethdev; /* link to ethernet device */ struct net_device *axdev; /* lapbeth device (lapb#) */ bool up; spinlock_t up_lock; /* Protects "up" */ struct sk_buff_head rx_queue; struct napi_struct napi; }; static LIST_HEAD(lapbeth_devices); static void lapbeth_connected(struct net_device *dev, int reason); static void lapbeth_disconnected(struct net_device *dev, int reason); /* ------------------------------------------------------------------------ */ /* Get the LAPB device for the ethernet device */ static struct lapbethdev *lapbeth_get_x25_dev(struct net_device *dev) { struct lapbethdev *lapbeth; list_for_each_entry_rcu(lapbeth, &lapbeth_devices, node, lockdep_rtnl_is_held()) { if (lapbeth->ethdev == dev) return lapbeth; } return NULL; } static __inline__ int dev_is_ethdev(struct net_device *dev) { return dev->type == ARPHRD_ETHER && !netdev_need_ops_lock(dev); } /* ------------------------------------------------------------------------ */ static int lapbeth_napi_poll(struct napi_struct *napi, int budget) { struct lapbethdev *lapbeth = container_of(napi, struct lapbethdev, napi); struct sk_buff *skb; int processed = 0; for (; processed < budget; ++processed) { skb = skb_dequeue(&lapbeth->rx_queue); if (!skb) break; netif_receive_skb_core(skb); } if (processed < budget) napi_complete(napi); return processed; } /* Receive a LAPB frame via an ethernet interface. */ static int lapbeth_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) { int len, err; struct lapbethdev *lapbeth; if (dev_net(dev) != &init_net) goto drop; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) return NET_RX_DROP; if (!pskb_may_pull(skb, 2)) goto drop; rcu_read_lock(); lapbeth = lapbeth_get_x25_dev(dev); if (!lapbeth) goto drop_unlock_rcu; spin_lock_bh(&lapbeth->up_lock); if (!lapbeth->up) goto drop_unlock; len = skb->data[0] + skb->data[1] * 256; dev->stats.rx_packets++; dev->stats.rx_bytes += len; skb_pull(skb, 2); /* Remove the length bytes */ skb_trim(skb, len); /* Set the length of the data */ err = lapb_data_received(lapbeth->axdev, skb); if (err != LAPB_OK) { printk(KERN_DEBUG "lapbether: lapb_data_received err - %d\n", err); goto drop_unlock; } out: spin_unlock_bh(&lapbeth->up_lock); rcu_read_unlock(); return 0; drop_unlock: kfree_skb(skb); goto out; drop_unlock_rcu: rcu_read_unlock(); drop: kfree_skb(skb); return 0; } static int lapbeth_data_indication(struct net_device *dev, struct sk_buff *skb) { struct lapbethdev *lapbeth = netdev_priv(dev); unsigned char *ptr; if (skb_cow(skb, 1)) { kfree_skb(skb); return NET_RX_DROP; } skb_push(skb, 1); ptr = skb->data; *ptr = X25_IFACE_DATA; skb->protocol = x25_type_trans(skb, dev); skb_queue_tail(&lapbeth->rx_queue, skb); napi_schedule(&lapbeth->napi); return NET_RX_SUCCESS; } /* Send a LAPB frame via an ethernet interface */ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb, struct net_device *dev) { struct lapbethdev *lapbeth = netdev_priv(dev); int err; spin_lock_bh(&lapbeth->up_lock); if (!lapbeth->up) goto drop; /* There should be a pseudo header of 1 byte added by upper layers. * Check to make sure it is there before reading it. */ if (skb->len < 1) goto drop; switch (skb->data[0]) { case X25_IFACE_DATA: break; case X25_IFACE_CONNECT: err = lapb_connect_request(dev); if (err == LAPB_CONNECTED) lapbeth_connected(dev, LAPB_OK); else if (err != LAPB_OK) pr_err("lapb_connect_request error: %d\n", err); goto drop; case X25_IFACE_DISCONNECT: err = lapb_disconnect_request(dev); if (err == LAPB_NOTCONNECTED) lapbeth_disconnected(dev, LAPB_OK); else if (err != LAPB_OK) pr_err("lapb_disconnect_request err: %d\n", err); fallthrough; default: goto drop; } skb_pull(skb, 1); err = lapb_data_request(dev, skb); if (err != LAPB_OK) { pr_err("lapb_data_request error - %d\n", err); goto drop; } out: spin_unlock_bh(&lapbeth->up_lock); return NETDEV_TX_OK; drop: kfree_skb(skb); goto out; } static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb) { struct lapbethdev *lapbeth = netdev_priv(ndev); unsigned char *ptr; struct net_device *dev; int size = skb->len; ptr = skb_push(skb, 2); *ptr++ = size % 256; *ptr++ = size / 256; ndev->stats.tx_packets++; ndev->stats.tx_bytes += size; skb->dev = dev = lapbeth->ethdev; skb->protocol = htons(ETH_P_DEC); skb_reset_network_header(skb); dev_hard_header(skb, dev, ETH_P_DEC, bcast_addr, NULL, 0); dev_queue_xmit(skb); } static void lapbeth_connected(struct net_device *dev, int reason) { struct lapbethdev *lapbeth = netdev_priv(dev); unsigned char *ptr; struct sk_buff *skb = __dev_alloc_skb(1, GFP_ATOMIC | __GFP_NOMEMALLOC); if (!skb) return; ptr = skb_put(skb, 1); *ptr = X25_IFACE_CONNECT; skb->protocol = x25_type_trans(skb, dev); skb_queue_tail(&lapbeth->rx_queue, skb); napi_schedule(&lapbeth->napi); } static void lapbeth_disconnected(struct net_device *dev, int reason) { struct lapbethdev *lapbeth = netdev_priv(dev); unsigned char *ptr; struct sk_buff *skb = __dev_alloc_skb(1, GFP_ATOMIC | __GFP_NOMEMALLOC); if (!skb) return; ptr = skb_put(skb, 1); *ptr = X25_IFACE_DISCONNECT; skb->protocol = x25_type_trans(skb, dev); skb_queue_tail(&lapbeth->rx_queue, skb); napi_schedule(&lapbeth->napi); } /* Set AX.25 callsign */ static int lapbeth_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = addr; dev_addr_set(dev, sa->sa_data); return 0; } static const struct lapb_register_struct lapbeth_callbacks = { .connect_confirmation = lapbeth_connected, .connect_indication = lapbeth_connected, .disconnect_confirmation = lapbeth_disconnected, .disconnect_indication = lapbeth_disconnected, .data_indication = lapbeth_data_indication, .data_transmit = lapbeth_data_transmit, }; /* open/close a device */ static int lapbeth_open(struct net_device *dev) { struct lapbethdev *lapbeth = netdev_priv(dev); int err; napi_enable(&lapbeth->napi); err = lapb_register(dev, &lapbeth_callbacks); if (err != LAPB_OK) { napi_disable(&lapbeth->napi); pr_err("lapb_register error: %d\n", err); return -ENODEV; } spin_lock_bh(&lapbeth->up_lock); lapbeth->up = true; spin_unlock_bh(&lapbeth->up_lock); return 0; } static int lapbeth_close(struct net_device *dev) { struct lapbethdev *lapbeth = netdev_priv(dev); int err; spin_lock_bh(&lapbeth->up_lock); lapbeth->up = false; spin_unlock_bh(&lapbeth->up_lock); err = lapb_unregister(dev); if (err != LAPB_OK) pr_err("lapb_unregister error: %d\n", err); napi_disable(&lapbeth->napi); return 0; } /* ------------------------------------------------------------------------ */ static const struct net_device_ops lapbeth_netdev_ops = { .ndo_open = lapbeth_open, .ndo_stop = lapbeth_close, .ndo_start_xmit = lapbeth_xmit, .ndo_set_mac_address = lapbeth_set_mac_address, }; static void lapbeth_setup(struct net_device *dev) { netdev_lockdep_set_classes(dev); dev->netdev_ops = &lapbeth_netdev_ops; dev->needs_free_netdev = true; dev->type = ARPHRD_X25; dev->hard_header_len = 0; dev->mtu = 1000; dev->addr_len = 0; } /* Setup a new device. */ static int lapbeth_new_device(struct net_device *dev) { struct net_device *ndev; struct lapbethdev *lapbeth; int rc = -ENOMEM; ASSERT_RTNL(); if (dev->type != ARPHRD_ETHER) return -EINVAL; ndev = alloc_netdev(sizeof(*lapbeth), "lapb%d", NET_NAME_UNKNOWN, lapbeth_setup); if (!ndev) goto out; /* When transmitting data: * first this driver removes a pseudo header of 1 byte, * then the lapb module prepends an LAPB header of at most 3 bytes, * then this driver prepends a length field of 2 bytes, * then the underlying Ethernet device prepends its own header. */ ndev->needed_headroom = -1 + 3 + 2 + dev->hard_header_len + dev->needed_headroom; ndev->needed_tailroom = dev->needed_tailroom; lapbeth = netdev_priv(ndev); lapbeth->axdev = ndev; dev_hold(dev); lapbeth->ethdev = dev; lapbeth->up = false; spin_lock_init(&lapbeth->up_lock); skb_queue_head_init(&lapbeth->rx_queue); netif_napi_add_weight(ndev, &lapbeth->napi, lapbeth_napi_poll, 16); rc = -EIO; if (register_netdevice(ndev)) goto fail; list_add_rcu(&lapbeth->node, &lapbeth_devices); rc = 0; out: return rc; fail: dev_put(dev); free_netdev(ndev); goto out; } /* Free a lapb network device. */ static void lapbeth_free_device(struct lapbethdev *lapbeth) { dev_put(lapbeth->ethdev); list_del_rcu(&lapbeth->node); unregister_netdevice(lapbeth->axdev); } /* Handle device status changes. * * Called from notifier with RTNL held. */ static int lapbeth_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct lapbethdev *lapbeth; if (dev_net(dev) != &init_net) return NOTIFY_DONE; lapbeth = lapbeth_get_x25_dev(dev); if (!dev_is_ethdev(dev) && !lapbeth) return NOTIFY_DONE; switch (event) { case NETDEV_UP: /* New ethernet device -> new LAPB interface */ if (!lapbeth) lapbeth_new_device(dev); break; case NETDEV_GOING_DOWN: /* ethernet device closes -> close LAPB interface */ if (lapbeth) dev_close(lapbeth->axdev); break; case NETDEV_UNREGISTER: /* ethernet device disappears -> remove LAPB interface */ if (lapbeth) lapbeth_free_device(lapbeth); break; case NETDEV_PRE_TYPE_CHANGE: /* Our underlying device type must not change. */ if (lapbeth) return NOTIFY_BAD; } return NOTIFY_DONE; } /* ------------------------------------------------------------------------ */ static struct packet_type lapbeth_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_DEC), .func = lapbeth_rcv, }; static struct notifier_block lapbeth_dev_notifier = { .notifier_call = lapbeth_device_event, }; static const char banner[] __initconst = KERN_INFO "LAPB Ethernet driver version 0.02\n"; static int __init lapbeth_init_driver(void) { dev_add_pack(&lapbeth_packet_type); register_netdevice_notifier(&lapbeth_dev_notifier); printk(banner); return 0; } module_init(lapbeth_init_driver); static void __exit lapbeth_cleanup_driver(void) { struct lapbethdev *lapbeth; struct list_head *entry, *tmp; dev_remove_pack(&lapbeth_packet_type); unregister_netdevice_notifier(&lapbeth_dev_notifier); rtnl_lock(); list_for_each_safe(entry, tmp, &lapbeth_devices) { lapbeth = list_entry(entry, struct lapbethdev, node); dev_put(lapbeth->ethdev); unregister_netdevice(lapbeth->axdev); } rtnl_unlock(); } module_exit(lapbeth_cleanup_driver); MODULE_AUTHOR("Jonathan Naylor <g4klx@g4klx.demon.co.uk>"); MODULE_DESCRIPTION("The unofficial LAPB over Ethernet driver"); MODULE_LICENSE("GPL"); |
| 1 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 | /* * JFFS2 -- Journalling Flash File System, Version 2. * * Copyright © 2001-2007 Red Hat, Inc. * * Created by David Woodhouse <dwmw2@infradead.org> * * For licensing information, see the file 'LICENCE' in this directory. * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/list.h> #include <linux/fs.h> #include <linux/err.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/jffs2.h> #include <linux/pagemap.h> #include <linux/mtd/super.h> #include <linux/ctype.h> #include <linux/namei.h> #include <linux/seq_file.h> #include <linux/exportfs.h> #include "compr.h" #include "nodelist.h" static void jffs2_put_super(struct super_block *); static struct kmem_cache *jffs2_inode_cachep; static struct inode *jffs2_alloc_inode(struct super_block *sb) { struct jffs2_inode_info *f; f = alloc_inode_sb(sb, jffs2_inode_cachep, GFP_KERNEL); if (!f) return NULL; return &f->vfs_inode; } static void jffs2_free_inode(struct inode *inode) { struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); kfree(f->target); kmem_cache_free(jffs2_inode_cachep, f); } static void jffs2_i_init_once(void *foo) { struct jffs2_inode_info *f = foo; mutex_init(&f->sem); f->target = NULL; inode_init_once(&f->vfs_inode); } static const char *jffs2_compr_name(unsigned int compr) { switch (compr) { case JFFS2_COMPR_MODE_NONE: return "none"; #ifdef CONFIG_JFFS2_LZO case JFFS2_COMPR_MODE_FORCELZO: return "lzo"; #endif #ifdef CONFIG_JFFS2_ZLIB case JFFS2_COMPR_MODE_FORCEZLIB: return "zlib"; #endif default: /* should never happen; programmer error */ WARN_ON(1); return ""; } } static int jffs2_show_options(struct seq_file *s, struct dentry *root) { struct jffs2_sb_info *c = JFFS2_SB_INFO(root->d_sb); struct jffs2_mount_opts *opts = &c->mount_opts; if (opts->override_compr) seq_printf(s, ",compr=%s", jffs2_compr_name(opts->compr)); if (opts->set_rp_size) seq_printf(s, ",rp_size=%u", opts->rp_size / 1024); return 0; } static int jffs2_sync_fs(struct super_block *sb, int wait) { struct jffs2_sb_info *c = JFFS2_SB_INFO(sb); #ifdef CONFIG_JFFS2_FS_WRITEBUFFER if (jffs2_is_writebuffered(c)) cancel_delayed_work_sync(&c->wbuf_dwork); #endif mutex_lock(&c->alloc_sem); jffs2_flush_wbuf_pad(c); mutex_unlock(&c->alloc_sem); return 0; } static struct inode *jffs2_nfs_get_inode(struct super_block *sb, uint64_t ino, uint32_t generation) { /* We don't care about i_generation. We'll destroy the flash before we start re-using inode numbers anyway. And even if that wasn't true, we'd have other problems...*/ return jffs2_iget(sb, ino); } static struct dentry *jffs2_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_dentry(sb, fid, fh_len, fh_type, jffs2_nfs_get_inode); } static struct dentry *jffs2_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_parent(sb, fid, fh_len, fh_type, jffs2_nfs_get_inode); } static struct dentry *jffs2_get_parent(struct dentry *child) { struct jffs2_inode_info *f; uint32_t pino; BUG_ON(!d_is_dir(child)); f = JFFS2_INODE_INFO(d_inode(child)); pino = f->inocache->pino_nlink; JFFS2_DEBUG("Parent of directory ino #%u is #%u\n", f->inocache->ino, pino); return d_obtain_alias(jffs2_iget(child->d_sb, pino)); } static const struct export_operations jffs2_export_ops = { .encode_fh = generic_encode_ino32_fh, .get_parent = jffs2_get_parent, .fh_to_dentry = jffs2_fh_to_dentry, .fh_to_parent = jffs2_fh_to_parent, }; /* * JFFS2 mount options. * * Opt_source: The source device * Opt_override_compr: override default compressor * Opt_rp_size: size of reserved pool in KiB */ enum { Opt_override_compr, Opt_rp_size, }; static const struct constant_table jffs2_param_compr[] = { {"none", JFFS2_COMPR_MODE_NONE }, #ifdef CONFIG_JFFS2_LZO {"lzo", JFFS2_COMPR_MODE_FORCELZO }, #endif #ifdef CONFIG_JFFS2_ZLIB {"zlib", JFFS2_COMPR_MODE_FORCEZLIB }, #endif {} }; static const struct fs_parameter_spec jffs2_fs_parameters[] = { fsparam_enum ("compr", Opt_override_compr, jffs2_param_compr), fsparam_u32 ("rp_size", Opt_rp_size), {} }; static int jffs2_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; struct jffs2_sb_info *c = fc->s_fs_info; int opt; opt = fs_parse(fc, jffs2_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_override_compr: c->mount_opts.compr = result.uint_32; c->mount_opts.override_compr = true; break; case Opt_rp_size: if (result.uint_32 > UINT_MAX / 1024) return invalf(fc, "jffs2: rp_size unrepresentable"); c->mount_opts.rp_size = result.uint_32 * 1024; c->mount_opts.set_rp_size = true; break; default: return -EINVAL; } return 0; } static inline void jffs2_update_mount_opts(struct fs_context *fc) { struct jffs2_sb_info *new_c = fc->s_fs_info; struct jffs2_sb_info *c = JFFS2_SB_INFO(fc->root->d_sb); mutex_lock(&c->alloc_sem); if (new_c->mount_opts.override_compr) { c->mount_opts.override_compr = new_c->mount_opts.override_compr; c->mount_opts.compr = new_c->mount_opts.compr; } if (new_c->mount_opts.set_rp_size) { c->mount_opts.set_rp_size = new_c->mount_opts.set_rp_size; c->mount_opts.rp_size = new_c->mount_opts.rp_size; } mutex_unlock(&c->alloc_sem); } static int jffs2_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; sync_filesystem(sb); jffs2_update_mount_opts(fc); return jffs2_do_remount_fs(sb, fc); } static const struct super_operations jffs2_super_operations = { .alloc_inode = jffs2_alloc_inode, .free_inode = jffs2_free_inode, .put_super = jffs2_put_super, .statfs = jffs2_statfs, .evict_inode = jffs2_evict_inode, .dirty_inode = jffs2_dirty_inode, .show_options = jffs2_show_options, .sync_fs = jffs2_sync_fs, }; /* * fill in the superblock */ static int jffs2_fill_super(struct super_block *sb, struct fs_context *fc) { struct jffs2_sb_info *c = sb->s_fs_info; jffs2_dbg(1, "jffs2_get_sb_mtd():" " New superblock for device %d (\"%s\")\n", sb->s_mtd->index, sb->s_mtd->name); c->mtd = sb->s_mtd; c->os_priv = sb; if (c->mount_opts.rp_size > c->mtd->size) return invalf(fc, "jffs2: Too large reserve pool specified, max is %llu KB", c->mtd->size / 1024); /* Initialize JFFS2 superblock locks, the further initialization will * be done later */ mutex_init(&c->alloc_sem); mutex_init(&c->erase_free_sem); init_waitqueue_head(&c->erase_wait); init_waitqueue_head(&c->inocache_wq); spin_lock_init(&c->erase_completion_lock); spin_lock_init(&c->inocache_lock); sb->s_op = &jffs2_super_operations; sb->s_export_op = &jffs2_export_ops; sb->s_flags = sb->s_flags | SB_NOATIME; sb->s_xattr = jffs2_xattr_handlers; #ifdef CONFIG_JFFS2_FS_POSIX_ACL sb->s_flags |= SB_POSIXACL; #endif return jffs2_do_fill_super(sb, fc); } static int jffs2_get_tree(struct fs_context *fc) { return get_tree_mtd(fc, jffs2_fill_super); } static void jffs2_free_fc(struct fs_context *fc) { kfree(fc->s_fs_info); } static const struct fs_context_operations jffs2_context_ops = { .free = jffs2_free_fc, .parse_param = jffs2_parse_param, .get_tree = jffs2_get_tree, .reconfigure = jffs2_reconfigure, }; static int jffs2_init_fs_context(struct fs_context *fc) { struct jffs2_sb_info *ctx; ctx = kzalloc_obj(struct jffs2_sb_info); if (!ctx) return -ENOMEM; fc->s_fs_info = ctx; fc->ops = &jffs2_context_ops; return 0; } static void jffs2_put_super (struct super_block *sb) { struct jffs2_sb_info *c = JFFS2_SB_INFO(sb); jffs2_dbg(2, "%s()\n", __func__); mutex_lock(&c->alloc_sem); jffs2_flush_wbuf_pad(c); mutex_unlock(&c->alloc_sem); jffs2_sum_exit(c); jffs2_free_ino_caches(c); jffs2_free_raw_node_refs(c); kvfree(c->blocks); jffs2_flash_cleanup(c); kfree(c->inocache_list); jffs2_clear_xattr_subsystem(c); mtd_sync(c->mtd); jffs2_dbg(1, "%s(): returning\n", __func__); } static void jffs2_kill_sb(struct super_block *sb) { struct jffs2_sb_info *c = JFFS2_SB_INFO(sb); if (c && !sb_rdonly(sb)) jffs2_stop_garbage_collect_thread(c); kill_mtd_super(sb); kfree(c); } static struct file_system_type jffs2_fs_type = { .owner = THIS_MODULE, .name = "jffs2", .init_fs_context = jffs2_init_fs_context, .parameters = jffs2_fs_parameters, .kill_sb = jffs2_kill_sb, }; MODULE_ALIAS_FS("jffs2"); static int __init init_jffs2_fs(void) { int ret; /* Paranoia checks for on-medium structures. If we ask GCC to pack them with __attribute__((packed)) then it _also_ assumes that they're not aligned -- so it emits crappy code on some architectures. Ideally we want an attribute which means just 'no padding', without the alignment thing. But GCC doesn't have that -- we have to just hope the structs are the right sizes, instead. */ BUILD_BUG_ON(sizeof(struct jffs2_unknown_node) != 12); BUILD_BUG_ON(sizeof(struct jffs2_raw_dirent) != 40); BUILD_BUG_ON(sizeof(struct jffs2_raw_inode) != 68); BUILD_BUG_ON(sizeof(struct jffs2_raw_summary) != 32); pr_info("version 2.2." #ifdef CONFIG_JFFS2_FS_WRITEBUFFER " (NAND)" #endif #ifdef CONFIG_JFFS2_SUMMARY " (SUMMARY) " #endif " © 2001-2006 Red Hat, Inc.\n"); jffs2_inode_cachep = kmem_cache_create("jffs2_i", sizeof(struct jffs2_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), jffs2_i_init_once); if (!jffs2_inode_cachep) { pr_err("error: Failed to initialise inode cache\n"); return -ENOMEM; } ret = jffs2_compressors_init(); if (ret) { pr_err("error: Failed to initialise compressors\n"); goto out; } ret = jffs2_create_slab_caches(); if (ret) { pr_err("error: Failed to initialise slab caches\n"); goto out_compressors; } ret = register_filesystem(&jffs2_fs_type); if (ret) { pr_err("error: Failed to register filesystem\n"); goto out_slab; } return 0; out_slab: jffs2_destroy_slab_caches(); out_compressors: jffs2_compressors_exit(); out: kmem_cache_destroy(jffs2_inode_cachep); return ret; } static void __exit exit_jffs2_fs(void) { unregister_filesystem(&jffs2_fs_type); jffs2_destroy_slab_caches(); jffs2_compressors_exit(); /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(jffs2_inode_cachep); } module_init(init_jffs2_fs); module_exit(exit_jffs2_fs); MODULE_DESCRIPTION("The Journalling Flash File System, v2"); MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); // Actually dual-licensed, but it doesn't matter for // the sake of this tag. It's Free Software. |
| 14 14 13 14 13 3 11 13 13 11 11 9 9 9 3 3 1 10 12 12 12 10 10 12 12 12 6 4 4 2 3 2 3 1 1 1 1 1 4 2 2 2 2 2 2 2 2 2 2 406 406 406 10 21 43 43 21 61 61 21 21 21 21 61 61 61 61 21 21 1 12 11 21 21 21 21 21 11 21 43 43 43 43 3 43 34 43 43 43 43 43 3 3 3 165 167 1 1 167 16 15 16 1 1 91 90 16 75 1 1 1 1 91 91 91 2 2 2 2 2 1 1 1 1 1 1 1 2 2 1 2 2 2 1 2 1 1066 1066 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Anycast support for IPv6 * Linux INET6 implementation * * Authors: * David L Stevens (dlstevens@us.ibm.com) * * based heavily on net/ipv6/mcast.c */ #include <linux/capability.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/random.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/route.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/if_inet6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/checksum.h> #define IN6_ADDR_HSIZE_SHIFT 8 #define IN6_ADDR_HSIZE BIT(IN6_ADDR_HSIZE_SHIFT) /* anycast address hash table */ static struct hlist_head inet6_acaddr_lst[IN6_ADDR_HSIZE]; static DEFINE_SPINLOCK(acaddr_hash_lock); #define ac_dereference(a, idev) \ rcu_dereference_protected(a, lockdep_is_held(&(idev)->lock)) static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr); static u32 inet6_acaddr_hash(const struct net *net, const struct in6_addr *addr) { u32 val = __ipv6_addr_jhash(addr, net_hash_mix(net)); return hash_32(val, IN6_ADDR_HSIZE_SHIFT); } /* * socket join an anycast group */ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_ac_socklist *pac = NULL; struct net *net = sock_net(sk); netdevice_tracker dev_tracker; struct net_device *dev = NULL; struct inet6_dev *idev; int err = 0, ishost; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (ipv6_addr_is_multicast(addr)) return -EINVAL; if (ifindex) dev = netdev_get_by_index(net, ifindex, &dev_tracker, GFP_KERNEL); if (ipv6_chk_addr_and_flags(net, addr, dev, true, 0, IFA_F_TENTATIVE)) { err = -EINVAL; goto error; } pac = sock_kmalloc(sk, sizeof(struct ipv6_ac_socklist), GFP_KERNEL); if (!pac) { err = -ENOMEM; goto error; } pac->acl_next = NULL; pac->acl_addr = *addr; ishost = !READ_ONCE(net->ipv6.devconf_all->forwarding); if (ifindex == 0) { struct rt6_info *rt; rcu_read_lock(); rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); if (rt) { dev = dst_dev_rcu(&rt->dst); netdev_hold(dev, &dev_tracker, GFP_ATOMIC); ip6_rt_put(rt); } else if (ishost) { rcu_read_unlock(); err = -EADDRNOTAVAIL; goto error; } else { /* router, no matching interface: just pick one */ dev = netdev_get_by_flags_rcu(net, &dev_tracker, IFF_UP, IFF_UP | IFF_LOOPBACK); } rcu_read_unlock(); } if (!dev) { err = -ENODEV; goto error; } idev = in6_dev_get(dev); if (!idev) { if (ifindex) err = -ENODEV; else err = -EADDRNOTAVAIL; goto error; } /* reset ishost, now that we have a specific device */ ishost = !READ_ONCE(idev->cnf.forwarding); pac->acl_ifindex = dev->ifindex; /* XXX * For hosts, allow link-local or matching prefix anycasts. * This obviates the need for propagating anycast routes while * still allowing some non-router anycast participation. */ if (!ipv6_chk_prefix(addr, dev)) { if (ishost) err = -EADDRNOTAVAIL; if (err) goto error_idev; } err = __ipv6_dev_ac_inc(idev, addr); if (!err) { pac->acl_next = np->ipv6_ac_list; np->ipv6_ac_list = pac; pac = NULL; } error_idev: in6_dev_put(idev); error: netdev_put(dev, &dev_tracker); if (pac) sock_kfree_s(sk, pac, sizeof(*pac)); return err; } /* * socket leave an anycast group */ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_ac_socklist *pac, *prev_pac; struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct net_device *dev; prev_pac = NULL; for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) { if ((ifindex == 0 || pac->acl_ifindex == ifindex) && ipv6_addr_equal(&pac->acl_addr, addr)) break; prev_pac = pac; } if (!pac) return -ENOENT; if (prev_pac) prev_pac->acl_next = pac->acl_next; else np->ipv6_ac_list = pac->acl_next; dev = dev_get_by_index(net, pac->acl_ifindex); if (dev) { ipv6_dev_ac_dec(dev, &pac->acl_addr); dev_put(dev); } sock_kfree_s(sk, pac, sizeof(*pac)); return 0; } void __ipv6_sock_ac_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct net_device *dev = NULL; struct ipv6_ac_socklist *pac; int prev_index = 0; pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; while (pac) { struct ipv6_ac_socklist *next = pac->acl_next; if (pac->acl_ifindex != prev_index) { dev_put(dev); dev = dev_get_by_index(net, pac->acl_ifindex); prev_index = pac->acl_ifindex; } if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); sock_kfree_s(sk, pac, sizeof(*pac)); pac = next; } dev_put(dev); } void ipv6_sock_ac_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); if (!np->ipv6_ac_list) return; __ipv6_sock_ac_close(sk); } static void ipv6_add_acaddr_hash(struct net *net, struct ifacaddr6 *aca) { unsigned int hash = inet6_acaddr_hash(net, &aca->aca_addr); spin_lock_bh(&acaddr_hash_lock); hlist_add_head_rcu(&aca->aca_addr_lst, &inet6_acaddr_lst[hash]); spin_unlock_bh(&acaddr_hash_lock); } static void ipv6_del_acaddr_hash(struct ifacaddr6 *aca) { spin_lock_bh(&acaddr_hash_lock); hlist_del_init_rcu(&aca->aca_addr_lst); spin_unlock_bh(&acaddr_hash_lock); } static void aca_get(struct ifacaddr6 *aca) { refcount_inc(&aca->aca_refcnt); } static void aca_free_rcu(struct rcu_head *h) { struct ifacaddr6 *aca = container_of(h, struct ifacaddr6, rcu); fib6_info_release(aca->aca_rt); kfree(aca); } static void aca_put(struct ifacaddr6 *ac) { if (refcount_dec_and_test(&ac->aca_refcnt)) call_rcu_hurry(&ac->rcu, aca_free_rcu); } static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i, const struct in6_addr *addr) { struct ifacaddr6 *aca; aca = kzalloc_obj(*aca, GFP_ATOMIC); if (!aca) return NULL; aca->aca_addr = *addr; fib6_info_hold(f6i); aca->aca_rt = f6i; INIT_HLIST_NODE(&aca->aca_addr_lst); aca->aca_users = 1; /* aca_tstamp should be updated upon changes */ aca->aca_cstamp = aca->aca_tstamp = jiffies; refcount_set(&aca->aca_refcnt, 1); return aca; } static void inet6_ifacaddr_notify(struct net_device *dev, const struct ifacaddr6 *ifaca, int event) { struct inet6_fill_args fillargs = { .event = event, .netnsid = -1, }; struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOMEM; skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(sizeof(struct in6_addr)) + nla_total_size(sizeof(struct ifa_cacheinfo)), GFP_KERNEL); if (!skb) goto error; err = inet6_fill_ifacaddr(skb, ifaca, &fillargs); if (err < 0) { pr_err("Failed to fill in anycast addresses (err %d)\n", err); nlmsg_free(skb); goto error; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_ACADDR, NULL, GFP_KERNEL); return; error: rtnl_set_sk_err(net, RTNLGRP_IPV6_ACADDR, err); } /* * device anycast group inc (add if not found) */ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca; struct fib6_info *f6i; struct net *net; int err; write_lock_bh(&idev->lock); if (idev->dead) { err = -ENODEV; goto out; } for (aca = ac_dereference(idev->ac_list, idev); aca; aca = ac_dereference(aca->aca_next, idev)) { if (ipv6_addr_equal(&aca->aca_addr, addr)) { aca->aca_users++; err = 0; goto out; } } net = dev_net(idev->dev); f6i = addrconf_f6i_alloc(net, idev, addr, true, GFP_ATOMIC, NULL); if (IS_ERR(f6i)) { err = PTR_ERR(f6i); goto out; } aca = aca_alloc(f6i, addr); if (!aca) { fib6_info_release(f6i); err = -ENOMEM; goto out; } /* Hold this for addrconf_join_solict() below before we unlock, * it is already exposed via idev->ac_list. */ aca_get(aca); aca->aca_next = idev->ac_list; rcu_assign_pointer(idev->ac_list, aca); ipv6_add_acaddr_hash(net, aca); write_unlock_bh(&idev->lock); ip6_ins_rt(net, f6i); addrconf_join_solict(idev->dev, &aca->aca_addr); inet6_ifacaddr_notify(idev->dev, aca, RTM_NEWANYCAST); aca_put(aca); return 0; out: write_unlock_bh(&idev->lock); return err; } /* * device anycast group decrement */ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca, *prev_aca; write_lock_bh(&idev->lock); prev_aca = NULL; for (aca = ac_dereference(idev->ac_list, idev); aca; aca = ac_dereference(aca->aca_next, idev)) { if (ipv6_addr_equal(&aca->aca_addr, addr)) break; prev_aca = aca; } if (!aca) { write_unlock_bh(&idev->lock); return -ENOENT; } if (--aca->aca_users > 0) { write_unlock_bh(&idev->lock); return 0; } if (prev_aca) rcu_assign_pointer(prev_aca->aca_next, aca->aca_next); else rcu_assign_pointer(idev->ac_list, aca->aca_next); write_unlock_bh(&idev->lock); ipv6_del_acaddr_hash(aca); addrconf_leave_solict(idev, &aca->aca_addr); ip6_del_rt(dev_net(idev->dev), aca->aca_rt, false); inet6_ifacaddr_notify(idev->dev, aca, RTM_DELANYCAST); aca_put(aca); return 0; } static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev = in6_dev_get(dev); int err; if (!idev) return -ENODEV; err = __ipv6_dev_ac_dec(idev, addr); in6_dev_put(idev); return err; } void ipv6_ac_destroy_dev(struct inet6_dev *idev) { struct ifacaddr6 *aca; write_lock_bh(&idev->lock); while ((aca = ac_dereference(idev->ac_list, idev)) != NULL) { rcu_assign_pointer(idev->ac_list, aca->aca_next); write_unlock_bh(&idev->lock); ipv6_del_acaddr_hash(aca); addrconf_leave_solict(idev, &aca->aca_addr); ip6_del_rt(dev_net(idev->dev), aca->aca_rt, false); aca_put(aca); write_lock_bh(&idev->lock); } write_unlock_bh(&idev->lock); } /* * check if the interface has this anycast address * called with rcu_read_lock() */ static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev; struct ifacaddr6 *aca; idev = __in6_dev_get(dev); if (idev) { for (aca = rcu_dereference(idev->ac_list); aca; aca = rcu_dereference(aca->aca_next)) if (ipv6_addr_equal(&aca->aca_addr, addr)) break; return aca != NULL; } return false; } /* * check if given interface (or any, if dev==0) has this anycast address */ bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr) { struct net_device *nh_dev; struct ifacaddr6 *aca; bool found = false; rcu_read_lock(); if (dev) found = ipv6_chk_acast_dev(dev, addr); else { unsigned int hash = inet6_acaddr_hash(net, addr); hlist_for_each_entry_rcu(aca, &inet6_acaddr_lst[hash], aca_addr_lst) { nh_dev = fib6_info_nh_dev(aca->aca_rt); if (!nh_dev || !net_eq(dev_net(nh_dev), net)) continue; if (ipv6_addr_equal(&aca->aca_addr, addr)) { found = true; break; } } } rcu_read_unlock(); return found; } /* check if this anycast address is link-local on given interface or * is global */ bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev, const struct in6_addr *addr) { return ipv6_chk_acast_addr(net, (ipv6_addr_type(addr) & IPV6_ADDR_LINKLOCAL ? dev : NULL), addr); } #ifdef CONFIG_PROC_FS struct ac6_iter_state { struct seq_net_private p; struct net_device *dev; }; #define ac6_seq_private(seq) ((struct ac6_iter_state *)(seq)->private) static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq) { struct ac6_iter_state *state = ac6_seq_private(seq); struct net *net = seq_file_net(seq); struct ifacaddr6 *im = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; idev = __in6_dev_get(state->dev); if (!idev) continue; im = rcu_dereference(idev->ac_list); if (im) break; } return im; } static struct ifacaddr6 *ac6_get_next(struct seq_file *seq, struct ifacaddr6 *im) { struct ac6_iter_state *state = ac6_seq_private(seq); struct inet6_dev *idev; im = rcu_dereference(im->aca_next); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) break; idev = __in6_dev_get(state->dev); if (!idev) continue; im = rcu_dereference(idev->ac_list); } return im; } static struct ifacaddr6 *ac6_get_idx(struct seq_file *seq, loff_t pos) { struct ifacaddr6 *im = ac6_get_first(seq); if (im) while (pos && (im = ac6_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *ac6_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return ac6_get_idx(seq, *pos); } static void *ac6_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ifacaddr6 *im = ac6_get_next(seq, v); ++*pos; return im; } static void ac6_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ac6_seq_show(struct seq_file *seq, void *v) { struct ifacaddr6 *im = (struct ifacaddr6 *)v; struct ac6_iter_state *state = ac6_seq_private(seq); seq_printf(seq, "%-4d %-15s %pi6 %5d\n", state->dev->ifindex, state->dev->name, &im->aca_addr, im->aca_users); return 0; } static const struct seq_operations ac6_seq_ops = { .start = ac6_seq_start, .next = ac6_seq_next, .stop = ac6_seq_stop, .show = ac6_seq_show, }; int __net_init ac6_proc_init(struct net *net) { if (!proc_create_net("anycast6", 0444, net->proc_net, &ac6_seq_ops, sizeof(struct ac6_iter_state))) return -ENOMEM; return 0; } void ac6_proc_exit(struct net *net) { remove_proc_entry("anycast6", net->proc_net); } #endif /* Init / cleanup code */ int __init ipv6_anycast_init(void) { int i; for (i = 0; i < IN6_ADDR_HSIZE; i++) INIT_HLIST_HEAD(&inet6_acaddr_lst[i]); return 0; } void ipv6_anycast_cleanup(void) { int i; spin_lock_bh(&acaddr_hash_lock); for (i = 0; i < IN6_ADDR_HSIZE; i++) WARN_ON(!hlist_empty(&inet6_acaddr_lst[i])); spin_unlock_bh(&acaddr_hash_lock); } |
| 5775 5666 9733 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_WORD_AT_A_TIME_H #define _ASM_WORD_AT_A_TIME_H #include <linux/bitops.h> #include <linux/wordpart.h> struct word_at_a_time { const unsigned long one_bits, high_bits; }; #define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } /* Return nonzero if it has a zero */ static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) { unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; *bits = mask; return mask; } static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c) { return bits; } #ifdef CONFIG_64BIT /* Keep the initial has_zero() value for both bitmask and size calc */ #define create_zero_mask(bits) (bits) static inline unsigned long zero_bytemask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } #define find_zero(bits) (__ffs(bits) >> 3) #else /* Create the final mask for both bytemask and size */ static inline unsigned long create_zero_mask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } /* The mask we created is directly usable as a bytemask */ #define zero_bytemask(mask) (mask) /* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ static inline unsigned long find_zero(unsigned long mask) { /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ long a = (0x0ff0001+mask) >> 23; /* Fix the 1 for 00 case */ return a & mask; } #endif /* * Load an unaligned word from kernel space. * * In the (very unlikely) case of the word being a page-crosser * and the next page not being mapped, take the exception and * return zeroes in the non-existing part. */ static inline unsigned long load_unaligned_zeropad(const void *addr) { unsigned long ret; asm volatile( "1: mov %[mem], %[ret]\n" "2:\n" _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_ZEROPAD) : [ret] "=r" (ret) : [mem] "m" (*(unsigned long *)addr)); return ret; } #endif /* _ASM_WORD_AT_A_TIME_H */ |
| 10 10 10 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 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> * (C) 2011 Patrick McHardy <kaber@trash.net> */ #include <linux/module.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/ip.h> #include <net/ip.h> #include <net/netfilter/nf_nat.h> struct iptable_nat_pernet { struct nf_hook_ops *nf_nat_ops; }; static unsigned int iptable_nat_net_id __read_mostly; static const struct xt_table nf_nat_ipv4_table = { .name = "nat", .valid_hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, .af = NFPROTO_IPV4, }; static const struct nf_hook_ops nf_nat_ipv4_ops[] = { { .hook = ipt_do_table, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, }, { .hook = ipt_do_table, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_NAT_SRC, }, { .hook = ipt_do_table, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST, }, { .hook = ipt_do_table, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, }, }; static int ipt_nat_register_lookups(struct net *net) { struct iptable_nat_pernet *xt_nat_net; struct nf_hook_ops *ops; struct xt_table *table; int i, ret; xt_nat_net = net_generic(net, iptable_nat_net_id); table = xt_find_table(net, NFPROTO_IPV4, "nat"); if (WARN_ON_ONCE(!table)) return -ENOENT; ops = kmemdup(nf_nat_ipv4_ops, sizeof(nf_nat_ipv4_ops), GFP_KERNEL); if (!ops) return -ENOMEM; for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++) { ops[i].priv = table; ret = nf_nat_ipv4_register_fn(net, &ops[i]); if (ret) { while (i) nf_nat_ipv4_unregister_fn(net, &ops[--i]); kfree_rcu(ops, rcu); return ret; } } xt_nat_net->nf_nat_ops = ops; return 0; } static void ipt_nat_unregister_lookups(struct net *net) { struct iptable_nat_pernet *xt_nat_net = net_generic(net, iptable_nat_net_id); struct nf_hook_ops *ops = xt_nat_net->nf_nat_ops; int i; if (!ops) return; for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++) nf_nat_ipv4_unregister_fn(net, &ops[i]); kfree_rcu(ops, rcu); } static int iptable_nat_table_init(struct net *net) { struct ipt_replace *repl; int ret; repl = ipt_alloc_initial_table(&nf_nat_ipv4_table); if (repl == NULL) return -ENOMEM; ret = ipt_register_table(net, &nf_nat_ipv4_table, repl, NULL); if (ret < 0) { kfree(repl); return ret; } ret = ipt_nat_register_lookups(net); if (ret < 0) { xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "nat"); synchronize_rcu(); ipt_unregister_table_exit(net, "nat"); } kfree(repl); return ret; } static void __net_exit iptable_nat_net_pre_exit(struct net *net) { ipt_nat_unregister_lookups(net); xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "nat"); } static void __net_exit iptable_nat_net_exit(struct net *net) { ipt_unregister_table_exit(net, "nat"); } static struct pernet_operations iptable_nat_net_ops = { .pre_exit = iptable_nat_net_pre_exit, .exit = iptable_nat_net_exit, .id = &iptable_nat_net_id, .size = sizeof(struct iptable_nat_pernet), }; static int __init iptable_nat_init(void) { int ret; /* net->gen->ptr[iptable_nat_net_id] must be allocated * before calling iptable_nat_table_init(). */ ret = register_pernet_subsys(&iptable_nat_net_ops); if (ret < 0) return ret; ret = xt_register_template(&nf_nat_ipv4_table, iptable_nat_table_init); if (ret < 0) unregister_pernet_subsys(&iptable_nat_net_ops); return ret; } static void __exit iptable_nat_exit(void) { xt_unregister_template(&nf_nat_ipv4_table); unregister_pernet_subsys(&iptable_nat_net_ops); } module_init(iptable_nat_init); module_exit(iptable_nat_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("iptables legacy nat table"); |
| 7 7 7 7 6 6 7 7 2 2 2 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 6 6 6 6 6 2 2 6 2 2 5 6 6 5 6 6 6 6 6 6 3 2 3 6 6 6 6 6 6 6 6 6 6 6 2 6 6 1070 1070 1070 1070 1070 1 1 1 18 5 5 5 5 5 5 1070 1070 18 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <net/wext.h> #include <net/hotdata.h> #include "dev.h" static void *dev_seq_from_index(struct seq_file *seq, loff_t *pos) { unsigned long ifindex = *pos; struct net_device *dev; for_each_netdev_dump(seq_file_net(seq), dev, ifindex) { *pos = dev->ifindex; return dev; } return NULL; } static void *dev_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; return dev_seq_from_index(seq, pos); } static void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return dev_seq_from_index(seq, pos); } static void dev_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, stats->rx_dropped + stats->rx_missed_errors, stats->rx_fifo_errors, stats->rx_length_errors + stats->rx_over_errors + stats->rx_crc_errors + stats->rx_frame_errors, stats->rx_compressed, stats->multicast, stats->tx_bytes, stats->tx_packets, stats->tx_errors, stats->tx_dropped, stats->tx_fifo_errors, stats->collisions, stats->tx_carrier_errors + stats->tx_aborted_errors + stats->tx_window_errors + stats->tx_heartbeat_errors, stats->tx_compressed); } /* * Called from the PROCfs module. This now uses the new arbitrary sized * /proc/net interface to create /proc/net/dev */ static int dev_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Inter-| Receive " " | Transmit\n" " face |bytes packets errs drop fifo frame " "compressed multicast|bytes packets errs " "drop fifo colls carrier compressed\n"); else dev_seq_printf_stats(seq, v); return 0; } static u32 softnet_input_pkt_queue_len(struct softnet_data *sd) { return skb_queue_len_lockless(&sd->input_pkt_queue); } static u32 softnet_process_queue_len(struct softnet_data *sd) { return skb_queue_len_lockless(&sd->process_queue); } static struct softnet_data *softnet_get_online(loff_t *pos) { struct softnet_data *sd = NULL; while (*pos < nr_cpu_ids) if (cpu_online(*pos)) { sd = &per_cpu(softnet_data, *pos); break; } else ++*pos; return sd; } static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) { return softnet_get_online(pos); } static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return softnet_get_online(pos); } static void softnet_seq_stop(struct seq_file *seq, void *v) { } static int softnet_seq_show(struct seq_file *seq, void *v) { struct softnet_data *sd = v; u32 input_qlen = softnet_input_pkt_queue_len(sd); u32 process_qlen = softnet_process_queue_len(sd); unsigned int flow_limit_count = 0; #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit *fl; rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); /* Pairs with WRITE_ONCE() in skb_flow_limit() */ if (fl) flow_limit_count = READ_ONCE(fl->count); rcu_read_unlock(); #endif /* the index is the CPU id owing this sd. Since offline CPUs are not * displayed, it would be othrwise not trivial for the user-space * mapping the data a specific CPU */ seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x " "%08x %08x\n", READ_ONCE(sd->processed), numa_drop_read(&sd->drop_counters), READ_ONCE(sd->time_squeeze), 0, 0, 0, 0, 0, /* was fastroute */ 0, /* was cpu_collision */ READ_ONCE(sd->received_rps), flow_limit_count, input_qlen + process_qlen, (int)seq->index, input_qlen, process_qlen); return 0; } static const struct seq_operations dev_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = dev_seq_show, }; static const struct seq_operations softnet_seq_ops = { .start = softnet_seq_start, .next = softnet_seq_next, .stop = softnet_seq_stop, .show = softnet_seq_show, }; struct ptype_iter_state { struct seq_net_private p; struct net_device *dev; }; static void *ptype_get_idx(struct seq_file *seq, loff_t pos) { struct ptype_iter_state *iter = seq->private; struct list_head *ptype_list = NULL; struct packet_type *pt = NULL; struct net_device *dev; loff_t i = 0; int t; for_each_netdev_rcu(seq_file_net(seq), dev) { ptype_list = &dev->ptype_all; list_for_each_entry_rcu(pt, ptype_list, list) { if (i == pos) { iter->dev = dev; return pt; } ++i; } } iter->dev = NULL; list_for_each_entry_rcu(pt, &seq_file_net(seq)->ptype_all, list) { if (i == pos) return pt; ++i; } list_for_each_entry_rcu(pt, &seq_file_net(seq)->ptype_specific, list) { if (i == pos) return pt; ++i; } for (t = 0; t < PTYPE_HASH_SIZE; t++) { list_for_each_entry_rcu(pt, &ptype_base[t], list) { if (i == pos) return pt; ++i; } } return NULL; } static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return *pos ? ptype_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ptype_iter_state *iter = seq->private; struct net *net = seq_file_net(seq); struct net_device *dev; struct packet_type *pt; struct list_head *nxt; int hash; ++*pos; if (v == SEQ_START_TOKEN) return ptype_get_idx(seq, 0); pt = v; nxt = READ_ONCE(pt->list.next); dev = iter->dev; if (dev) { if (nxt != &dev->ptype_all) goto found; for_each_netdev_continue_rcu(seq_file_net(seq), dev) { nxt = READ_ONCE(dev->ptype_all.next); if (nxt != &dev->ptype_all) { iter->dev = dev; goto found; } } iter->dev = NULL; nxt = READ_ONCE(net->ptype_all.next); goto net_ptype_all; } if (pt->af_packet_net) { net_ptype_all: if (nxt != &net->ptype_all && nxt != &net->ptype_specific) goto found; if (nxt == &net->ptype_all) { /* continue with ->ptype_specific if it's not empty */ nxt = READ_ONCE(net->ptype_specific.next); if (nxt != &net->ptype_specific) goto found; } hash = 0; nxt = READ_ONCE(ptype_base[0].next); } else hash = ntohs(pt->type) & PTYPE_HASH_MASK; while (nxt == &ptype_base[hash]) { if (++hash >= PTYPE_HASH_SIZE) return NULL; nxt = READ_ONCE(ptype_base[hash].next); } found: return list_entry(nxt, struct packet_type, list); } static void ptype_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ptype_seq_show(struct seq_file *seq, void *v) { struct ptype_iter_state *iter = seq->private; struct packet_type *pt = v; struct net_device *dev; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Type Device Function\n"); return 0; } dev = iter->dev; if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && (!dev || net_eq(dev_net(dev), seq_file_net(seq)))) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else seq_printf(seq, "%04x", ntohs(pt->type)); seq_printf(seq, " %-8s %ps\n", dev ? dev->name : "", pt->func); } return 0; } static const struct seq_operations ptype_seq_ops = { .start = ptype_seq_start, .next = ptype_seq_next, .stop = ptype_seq_stop, .show = ptype_seq_show, }; static int __net_init dev_proc_net_init(struct net *net) { int rc = -ENOMEM; if (!proc_create_net("dev", 0444, net->proc_net, &dev_seq_ops, sizeof(struct seq_net_private))) goto out; if (!proc_create_seq("softnet_stat", 0444, net->proc_net, &softnet_seq_ops)) goto out_dev; if (!proc_create_net("ptype", 0444, net->proc_net, &ptype_seq_ops, sizeof(struct ptype_iter_state))) goto out_softnet; if (wext_proc_init(net)) goto out_ptype; rc = 0; out: return rc; out_ptype: remove_proc_entry("ptype", net->proc_net); out_softnet: remove_proc_entry("softnet_stat", net->proc_net); out_dev: remove_proc_entry("dev", net->proc_net); goto out; } static void __net_exit dev_proc_net_exit(struct net *net) { wext_proc_exit(net); remove_proc_entry("ptype", net->proc_net); remove_proc_entry("softnet_stat", net->proc_net); remove_proc_entry("dev", net->proc_net); } static struct pernet_operations __net_initdata dev_proc_ops = { .init = dev_proc_net_init, .exit = dev_proc_net_exit, }; static int dev_mc_seq_show(struct seq_file *seq, void *v) { struct netdev_hw_addr *ha; struct net_device *dev = v; if (v == SEQ_START_TOKEN) return 0; netif_addr_lock_bh(dev); netdev_for_each_mc_addr(ha, dev) { seq_printf(seq, "%-4d %-15s %-5d %-5d %*phN\n", dev->ifindex, dev->name, ha->refcount, ha->global_use, (int)dev->addr_len, ha->addr); } netif_addr_unlock_bh(dev); return 0; } static const struct seq_operations dev_mc_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = dev_mc_seq_show, }; static int __net_init dev_mc_net_init(struct net *net) { if (!proc_create_net("dev_mcast", 0, net->proc_net, &dev_mc_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } static void __net_exit dev_mc_net_exit(struct net *net) { remove_proc_entry("dev_mcast", net->proc_net); } static struct pernet_operations __net_initdata dev_mc_net_ops = { .init = dev_mc_net_init, .exit = dev_mc_net_exit, }; int __init dev_proc_init(void) { int ret = register_pernet_subsys(&dev_proc_ops); if (!ret) return register_pernet_subsys(&dev_mc_net_ops); return ret; } |
| 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ALSA sequencer device management * Copyright (c) 1999 by Takashi Iwai <tiwai@suse.de> * *---------------------------------------------------------------- * * This device handler separates the card driver module from sequencer * stuff (sequencer core, synth drivers, etc), so that user can avoid * to spend unnecessary resources e.g. if he needs only listening to * MP3s. * * The card (or lowlevel) driver creates a sequencer device entry * via snd_seq_device_new(). This is an entry pointer to communicate * with the sequencer device "driver", which is involved with the * actual part to communicate with the sequencer core. * Each sequencer device entry has an id string and the corresponding * driver with the same id is loaded when required. For example, * lowlevel codes to access emu8000 chip on sbawe card are included in * emu8000-synth module. To activate this module, the hardware * resources like i/o port are passed via snd_seq_device argument. */ #include <linux/device.h> #include <linux/init.h> #include <linux/module.h> #include <sound/core.h> #include <sound/info.h> #include <sound/seq_device.h> #include <sound/seq_kernel.h> #include <sound/initval.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/mutex.h> MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>"); MODULE_DESCRIPTION("ALSA sequencer device management"); MODULE_LICENSE("GPL"); /* * bus definition */ static int snd_seq_bus_match(struct device *dev, const struct device_driver *drv) { struct snd_seq_device *sdev = to_seq_dev(dev); const struct snd_seq_driver *sdrv = to_seq_drv(drv); return strcmp(sdrv->id, sdev->id) == 0 && sdrv->argsize == sdev->argsize; } static int snd_seq_bus_probe(struct device *dev) { struct snd_seq_device *sdev = to_seq_dev(dev); const struct snd_seq_driver *sdrv = to_seq_drv(dev->driver); if (sdrv->probe) return sdrv->probe(sdev); else return 0; } static void snd_seq_bus_remove(struct device *dev) { struct snd_seq_device *sdev = to_seq_dev(dev); const struct snd_seq_driver *sdrv = to_seq_drv(dev->driver); if (sdrv->remove) sdrv->remove(sdev); } static const struct bus_type snd_seq_bus_type = { .name = "snd_seq", .match = snd_seq_bus_match, .probe = snd_seq_bus_probe, .remove = snd_seq_bus_remove, }; /* * proc interface -- just for compatibility */ #ifdef CONFIG_SND_PROC_FS static struct snd_info_entry *info_entry; static int print_dev_info(struct device *dev, void *data) { struct snd_seq_device *sdev = to_seq_dev(dev); struct snd_info_buffer *buffer = data; snd_iprintf(buffer, "snd-%s,%s,%d\n", sdev->id, dev->driver ? "loaded" : "empty", dev->driver ? 1 : 0); return 0; } static void snd_seq_device_info(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { bus_for_each_dev(&snd_seq_bus_type, NULL, buffer, print_dev_info); } #endif /* * load all registered drivers (called from seq_clientmgr.c) */ #ifdef CONFIG_MODULES /* flag to block auto-loading */ static atomic_t snd_seq_in_init = ATOMIC_INIT(1); /* blocked as default */ static int request_seq_drv(struct device *dev, void *data) { struct snd_seq_device *sdev = to_seq_dev(dev); if (!dev->driver) request_module("snd-%s", sdev->id); return 0; } static void autoload_drivers(struct work_struct *work) { /* avoid reentrance */ if (atomic_inc_return(&snd_seq_in_init) == 1) bus_for_each_dev(&snd_seq_bus_type, NULL, NULL, request_seq_drv); atomic_dec(&snd_seq_in_init); } static DECLARE_WORK(autoload_work, autoload_drivers); static void queue_autoload_drivers(void) { schedule_work(&autoload_work); } void snd_seq_autoload_init(void) { atomic_dec(&snd_seq_in_init); #ifdef CONFIG_SND_SEQUENCER_MODULE /* initial autoload only when snd-seq is a module */ queue_autoload_drivers(); #endif } EXPORT_SYMBOL(snd_seq_autoload_init); void snd_seq_autoload_exit(void) { atomic_inc(&snd_seq_in_init); } EXPORT_SYMBOL(snd_seq_autoload_exit); void snd_seq_device_load_drivers(void) { queue_autoload_drivers(); flush_work(&autoload_work); } EXPORT_SYMBOL(snd_seq_device_load_drivers); static inline void cancel_autoload_drivers(void) { cancel_work_sync(&autoload_work); } #else static inline void queue_autoload_drivers(void) { } static inline void cancel_autoload_drivers(void) { } #endif /* * device management */ static int snd_seq_device_dev_free(struct snd_device *device) { struct snd_seq_device *dev = device->device_data; cancel_autoload_drivers(); if (dev->private_free) dev->private_free(dev); put_device(&dev->dev); return 0; } static int snd_seq_device_dev_register(struct snd_device *device) { struct snd_seq_device *dev = device->device_data; int err; err = device_add(&dev->dev); if (err < 0) return err; if (!dev->dev.driver) queue_autoload_drivers(); return 0; } static int snd_seq_device_dev_disconnect(struct snd_device *device) { struct snd_seq_device *dev = device->device_data; device_del(&dev->dev); return 0; } static void snd_seq_dev_release(struct device *dev) { kfree(to_seq_dev(dev)); } /* * register a sequencer device * card = card info * device = device number (if any) * id = id of driver * result = return pointer (NULL allowed if unnecessary) */ int snd_seq_device_new(struct snd_card *card, int device, const char *id, int argsize, struct snd_seq_device **result) { struct snd_seq_device *dev; int err; static const struct snd_device_ops dops = { .dev_free = snd_seq_device_dev_free, .dev_register = snd_seq_device_dev_register, .dev_disconnect = snd_seq_device_dev_disconnect, }; if (result) *result = NULL; if (snd_BUG_ON(!id)) return -EINVAL; if (argsize < 0) return -EINVAL; dev = kzalloc_flex(*dev, args, argsize); if (!dev) return -ENOMEM; /* set up device info */ dev->card = card; dev->device = device; dev->id = id; dev->argsize = argsize; device_initialize(&dev->dev); dev->dev.parent = &card->card_dev; dev->dev.bus = &snd_seq_bus_type; dev->dev.release = snd_seq_dev_release; dev_set_name(&dev->dev, "%s-%d-%d", dev->id, card->number, device); /* add this device to the list */ err = snd_device_new(card, SNDRV_DEV_SEQUENCER, dev, &dops); if (err < 0) { put_device(&dev->dev); return err; } if (result) *result = dev; return 0; } EXPORT_SYMBOL(snd_seq_device_new); /* * driver registration */ int __snd_seq_driver_register(struct snd_seq_driver *drv, struct module *mod) { if (WARN_ON(!drv->driver.name || !drv->id || drv->driver.probe || drv->driver.remove)) return -EINVAL; drv->driver.bus = &snd_seq_bus_type; drv->driver.owner = mod; return driver_register(&drv->driver); } EXPORT_SYMBOL_GPL(__snd_seq_driver_register); void snd_seq_driver_unregister(struct snd_seq_driver *drv) { driver_unregister(&drv->driver); } EXPORT_SYMBOL_GPL(snd_seq_driver_unregister); /* * module part */ static int __init seq_dev_proc_init(void) { #ifdef CONFIG_SND_PROC_FS info_entry = snd_info_create_module_entry(THIS_MODULE, "drivers", snd_seq_root); if (info_entry == NULL) return -ENOMEM; info_entry->content = SNDRV_INFO_CONTENT_TEXT; info_entry->c.text.read = snd_seq_device_info; if (snd_info_register(info_entry) < 0) { snd_info_free_entry(info_entry); return -ENOMEM; } #endif return 0; } static int __init alsa_seq_device_init(void) { int err; err = bus_register(&snd_seq_bus_type); if (err < 0) return err; err = seq_dev_proc_init(); if (err < 0) bus_unregister(&snd_seq_bus_type); return err; } static void __exit alsa_seq_device_exit(void) { #ifdef CONFIG_MODULES cancel_work_sync(&autoload_work); #endif #ifdef CONFIG_SND_PROC_FS snd_info_free_entry(info_entry); #endif bus_unregister(&snd_seq_bus_type); } subsys_initcall(alsa_seq_device_init) module_exit(alsa_seq_device_exit) |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/moduleparam.h> #include "x86_ops.h" #include "vmx.h" #include "mmu.h" #include "nested.h" #include "pmu.h" #include "posted_intr.h" #include "tdx.h" #include "tdx_arch.h" #ifdef CONFIG_KVM_INTEL_TDX static_assert(offsetof(struct vcpu_vmx, vt) == offsetof(struct vcpu_tdx, vt)); static void vt_disable_virtualization_cpu(void) { /* Note, TDX *and* VMX need to be disabled if TDX is enabled. */ if (enable_tdx) tdx_disable_virtualization_cpu(); vmx_disable_virtualization_cpu(); } static __init int vt_hardware_setup(void) { int ret; ret = vmx_hardware_setup(); if (ret) return ret; return enable_tdx ? tdx_hardware_setup() : 0; } static void vt_hardware_unsetup(void) { if (enable_tdx) tdx_hardware_unsetup(); vmx_hardware_unsetup(); } static int vt_vm_init(struct kvm *kvm) { if (is_td(kvm)) return tdx_vm_init(kvm); return vmx_vm_init(kvm); } static void vt_vm_pre_destroy(struct kvm *kvm) { if (is_td(kvm)) return tdx_mmu_release_hkid(kvm); } static void vt_vm_destroy(struct kvm *kvm) { if (is_td(kvm)) return tdx_vm_destroy(kvm); vmx_vm_destroy(kvm); } static int vt_vcpu_precreate(struct kvm *kvm) { if (is_td(kvm)) return 0; return vmx_vcpu_precreate(kvm); } static int vt_vcpu_create(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return tdx_vcpu_create(vcpu); return vmx_vcpu_create(vcpu); } static void vt_vcpu_free(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) { tdx_vcpu_free(vcpu); return; } vmx_vcpu_free(vcpu); } static void vt_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { if (is_td_vcpu(vcpu)) { tdx_vcpu_reset(vcpu, init_event); return; } vmx_vcpu_reset(vcpu, init_event); } static void vt_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { if (is_td_vcpu(vcpu)) { tdx_vcpu_load(vcpu, cpu); return; } vmx_vcpu_load(vcpu, cpu); } static void vt_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) { /* * Basic TDX does not support feature PML. KVM does not enable PML in * TD's VMCS, nor does it allocate or flush PML buffer for TDX. */ if (WARN_ON_ONCE(is_td_vcpu(vcpu))) return; vmx_update_cpu_dirty_logging(vcpu); } static void vt_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) { tdx_prepare_switch_to_guest(vcpu); return; } vmx_prepare_switch_to_guest(vcpu); } static void vt_vcpu_put(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) { tdx_vcpu_put(vcpu); return; } vmx_vcpu_put(vcpu); } static int vt_vcpu_pre_run(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return tdx_vcpu_pre_run(vcpu); return vmx_vcpu_pre_run(vcpu); } static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) { if (is_td_vcpu(vcpu)) return tdx_vcpu_run(vcpu, run_flags); return vmx_vcpu_run(vcpu, run_flags); } static int vt_handle_exit(struct kvm_vcpu *vcpu, enum exit_fastpath_completion fastpath) { if (is_td_vcpu(vcpu)) return tdx_handle_exit(vcpu, fastpath); return vmx_handle_exit(vcpu, fastpath); } static int vt_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { if (unlikely(is_td_vcpu(vcpu))) return tdx_set_msr(vcpu, msr_info); return vmx_set_msr(vcpu, msr_info); } /* * The kvm parameter can be NULL (module initialization, or invocation before * VM creation). Be sure to check the kvm parameter before using it. */ static bool vt_has_emulated_msr(struct kvm *kvm, u32 index) { if (kvm && is_td(kvm)) return tdx_has_emulated_msr(index); return vmx_has_emulated_msr(kvm, index); } static int vt_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { if (unlikely(is_td_vcpu(vcpu))) return tdx_get_msr(vcpu, msr_info); return vmx_get_msr(vcpu, msr_info); } static void vt_recalc_intercepts(struct kvm_vcpu *vcpu) { /* * TDX doesn't allow VMM to configure interception of instructions or * MSR accesses. TDX guest requests MSR accesses by calling TDVMCALL. * The MSR filters will be applied when handling the TDVMCALL for * RDMSR/WRMSR if the userspace has set any. */ if (is_td_vcpu(vcpu)) return; vmx_recalc_intercepts(vcpu); } static int vt_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) { if (is_td_vcpu(vcpu)) return tdx_complete_emulated_msr(vcpu, err); return vmx_complete_emulated_msr(vcpu, err); } #ifdef CONFIG_KVM_SMM static int vt_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (KVM_BUG_ON(is_td_vcpu(vcpu), vcpu->kvm)) return 0; return vmx_smi_allowed(vcpu, for_injection); } static int vt_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) { if (KVM_BUG_ON(is_td_vcpu(vcpu), vcpu->kvm)) return 0; return vmx_enter_smm(vcpu, smram); } static int vt_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) { if (KVM_BUG_ON(is_td_vcpu(vcpu), vcpu->kvm)) return 0; return vmx_leave_smm(vcpu, smram); } static void vt_enable_smi_window(struct kvm_vcpu *vcpu) { if (KVM_BUG_ON(is_td_vcpu(vcpu), vcpu->kvm)) return; /* RSM will cause a vmexit anyway. */ vmx_enable_smi_window(vcpu); } #endif static int vt_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len) { /* * For TDX, this can only be triggered for MMIO emulation. Let the * guest retry after installing the SPTE with suppress #VE bit cleared, * so that the guest will receive #VE when retry. The guest is expected * to call TDG.VP.VMCALL<MMIO> to request VMM to do MMIO emulation on * #VE. */ if (is_td_vcpu(vcpu)) return X86EMUL_RETRY_INSTR; return vmx_check_emulate_instruction(vcpu, emul_type, insn, insn_len); } static bool vt_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { /* * INIT and SIPI are always blocked for TDX, i.e., INIT handling and * the OP vcpu_deliver_sipi_vector() won't be called. */ if (is_td_vcpu(vcpu)) return true; return vmx_apic_init_signal_blocked(vcpu); } static void vt_set_virtual_apic_mode(struct kvm_vcpu *vcpu) { /* Only x2APIC mode is supported for TD. */ if (is_td_vcpu(vcpu)) return; return vmx_set_virtual_apic_mode(vcpu); } static void vt_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) { if (is_td_vcpu(vcpu)) return; return vmx_hwapic_isr_update(vcpu, max_isr); } static int vt_sync_pir_to_irr(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return -1; return vmx_sync_pir_to_irr(vcpu); } static void vt_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, int trig_mode, int vector) { if (is_td_vcpu(apic->vcpu)) { tdx_deliver_interrupt(apic, delivery_mode, trig_mode, vector); return; } vmx_deliver_interrupt(apic, delivery_mode, trig_mode, vector); } static void vt_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return; vmx_vcpu_after_set_cpuid(vcpu); } static void vt_update_exception_bitmap(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return; vmx_update_exception_bitmap(vcpu); } static u64 vt_get_segment_base(struct kvm_vcpu *vcpu, int seg) { if (is_td_vcpu(vcpu)) return 0; return vmx_get_segment_base(vcpu, seg); } static void vt_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { if (is_td_vcpu(vcpu)) { memset(var, 0, sizeof(*var)); return; } vmx_get_segment(vcpu, var, seg); } static void vt_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { if (is_td_vcpu(vcpu)) return; vmx_set_segment(vcpu, var, seg); } static int vt_get_cpl(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return 0; return vmx_get_cpl(vcpu); } static int vt_get_cpl_no_cache(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return 0; return vmx_get_cpl_no_cache(vcpu); } static void vt_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { if (is_td_vcpu(vcpu)) { *db = 0; *l = 0; return; } vmx_get_cs_db_l_bits(vcpu, db, l); } static bool vt_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { if (is_td_vcpu(vcpu)) return true; return vmx_is_valid_cr0(vcpu, cr0); } static void vt_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { if (is_td_vcpu(vcpu)) return; vmx_set_cr0(vcpu, cr0); } static bool vt_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { if (is_td_vcpu(vcpu)) return true; return vmx_is_valid_cr4(vcpu, cr4); } static void vt_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { if (is_td_vcpu(vcpu)) return; vmx_set_cr4(vcpu, cr4); } static int vt_set_efer(struct kvm_vcpu *vcpu, u64 efer) { if (is_td_vcpu(vcpu)) return 0; return vmx_set_efer(vcpu, efer); } static void vt_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { if (is_td_vcpu(vcpu)) { memset(dt, 0, sizeof(*dt)); return; } vmx_get_idt(vcpu, dt); } static void vt_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { if (is_td_vcpu(vcpu)) return; vmx_set_idt(vcpu, dt); } static void vt_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { if (is_td_vcpu(vcpu)) { memset(dt, 0, sizeof(*dt)); return; } vmx_get_gdt(vcpu, dt); } static void vt_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { if (is_td_vcpu(vcpu)) return; vmx_set_gdt(vcpu, dt); } static void vt_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { if (is_td_vcpu(vcpu)) return; vmx_set_dr7(vcpu, val); } static void vt_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { /* * MOV-DR exiting is always cleared for TD guest, even in debug mode. * Thus KVM_DEBUGREG_WONT_EXIT can never be set and it should never * reach here for TD vcpu. */ if (is_td_vcpu(vcpu)) return; vmx_sync_dirty_debug_regs(vcpu); } static void vt_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { if (WARN_ON_ONCE(is_td_vcpu(vcpu))) return; vmx_cache_reg(vcpu, reg); } static unsigned long vt_get_rflags(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return 0; return vmx_get_rflags(vcpu); } static void vt_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { if (is_td_vcpu(vcpu)) return; vmx_set_rflags(vcpu, rflags); } static bool vt_get_if_flag(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return false; return vmx_get_if_flag(vcpu); } static void vt_flush_tlb_all(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) { tdx_flush_tlb_all(vcpu); return; } vmx_flush_tlb_all(vcpu); } static void vt_flush_tlb_current(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) { tdx_flush_tlb_current(vcpu); return; } vmx_flush_tlb_current(vcpu); } static void vt_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) { if (is_td_vcpu(vcpu)) return; vmx_flush_tlb_gva(vcpu, addr); } static void vt_flush_tlb_guest(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return; vmx_flush_tlb_guest(vcpu); } static void vt_inject_nmi(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) { tdx_inject_nmi(vcpu); return; } vmx_inject_nmi(vcpu); } static int vt_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { /* * The TDX module manages NMI windows and NMI reinjection, and hides NMI * blocking, all KVM can do is throw an NMI over the wall. */ if (is_td_vcpu(vcpu)) return true; return vmx_nmi_allowed(vcpu, for_injection); } static bool vt_get_nmi_mask(struct kvm_vcpu *vcpu) { /* * KVM can't get NMI blocking status for TDX guest, assume NMIs are * always unmasked. */ if (is_td_vcpu(vcpu)) return false; return vmx_get_nmi_mask(vcpu); } static void vt_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) { if (is_td_vcpu(vcpu)) return; vmx_set_nmi_mask(vcpu, masked); } static void vt_enable_nmi_window(struct kvm_vcpu *vcpu) { /* Refer to the comments in tdx_inject_nmi(). */ if (is_td_vcpu(vcpu)) return; vmx_enable_nmi_window(vcpu); } static void vt_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level) { if (is_td_vcpu(vcpu)) { tdx_load_mmu_pgd(vcpu, root_hpa, pgd_level); return; } vmx_load_mmu_pgd(vcpu, root_hpa, pgd_level); } static void vt_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) { if (is_td_vcpu(vcpu)) return; vmx_set_interrupt_shadow(vcpu, mask); } static u32 vt_get_interrupt_shadow(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return 0; return vmx_get_interrupt_shadow(vcpu); } static void vt_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) { /* * Because guest memory is protected, guest can't be patched. TD kernel * is modified to use TDG.VP.VMCALL for hypercall. */ if (is_td_vcpu(vcpu)) return; vmx_patch_hypercall(vcpu, hypercall); } static void vt_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { if (is_td_vcpu(vcpu)) return; vmx_inject_irq(vcpu, reinjected); } static void vt_inject_exception(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return; vmx_inject_exception(vcpu); } static void vt_cancel_injection(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return; vmx_cancel_injection(vcpu); } static int vt_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (is_td_vcpu(vcpu)) return tdx_interrupt_allowed(vcpu); return vmx_interrupt_allowed(vcpu, for_injection); } static void vt_enable_irq_window(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return; vmx_enable_irq_window(vcpu); } static void vt_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code) { *intr_info = 0; *error_code = 0; if (is_td_vcpu(vcpu)) return; vmx_get_entry_info(vcpu, intr_info, error_code); } static void vt_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code) { if (is_td_vcpu(vcpu)) { tdx_get_exit_info(vcpu, reason, info1, info2, intr_info, error_code); return; } vmx_get_exit_info(vcpu, reason, info1, info2, intr_info, error_code); } static void vt_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { if (is_td_vcpu(vcpu)) return; vmx_update_cr8_intercept(vcpu, tpr, irr); } static void vt_set_apic_access_page_addr(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return; vmx_set_apic_access_page_addr(vcpu); } static void vt_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) { KVM_BUG_ON(!kvm_vcpu_apicv_active(vcpu), vcpu->kvm); return; } vmx_refresh_apicv_exec_ctrl(vcpu); } static void vt_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (is_td_vcpu(vcpu)) return; vmx_load_eoi_exitmap(vcpu, eoi_exit_bitmap); } static int vt_set_tss_addr(struct kvm *kvm, unsigned int addr) { if (is_td(kvm)) return 0; return vmx_set_tss_addr(kvm, addr); } static int vt_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { if (is_td(kvm)) return 0; return vmx_set_identity_map_addr(kvm, ident_addr); } static bool vt_tdp_has_smep(struct kvm *kvm) { if (is_td(kvm)) return false; return vmx_tdp_has_smep(kvm); } static u64 vt_get_l2_tsc_offset(struct kvm_vcpu *vcpu) { /* TDX doesn't support L2 guest at the moment. */ if (is_td_vcpu(vcpu)) return 0; return vmx_get_l2_tsc_offset(vcpu); } static u64 vt_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) { /* TDX doesn't support L2 guest at the moment. */ if (is_td_vcpu(vcpu)) return 0; return vmx_get_l2_tsc_multiplier(vcpu); } static void vt_write_tsc_offset(struct kvm_vcpu *vcpu) { /* In TDX, tsc offset can't be changed. */ if (is_td_vcpu(vcpu)) return; vmx_write_tsc_offset(vcpu); } static void vt_write_tsc_multiplier(struct kvm_vcpu *vcpu) { /* In TDX, tsc multiplier can't be changed. */ if (is_td_vcpu(vcpu)) return; vmx_write_tsc_multiplier(vcpu); } #ifdef CONFIG_X86_64 static int vt_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, bool *expired) { /* VMX-preemption timer isn't available for TDX. */ if (is_td_vcpu(vcpu)) return -EINVAL; return vmx_set_hv_timer(vcpu, guest_deadline_tsc, expired); } static void vt_cancel_hv_timer(struct kvm_vcpu *vcpu) { /* VMX-preemption timer can't be set. See vt_set_hv_timer(). */ if (is_td_vcpu(vcpu)) return; vmx_cancel_hv_timer(vcpu); } #endif static void vt_setup_mce(struct kvm_vcpu *vcpu) { if (is_td_vcpu(vcpu)) return; vmx_setup_mce(vcpu); } static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp) { if (!is_td(kvm)) return -ENOTTY; return tdx_vm_ioctl(kvm, argp); } static int vt_vcpu_mem_enc_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { if (!is_td_vcpu(vcpu)) return -EINVAL; return tdx_vcpu_ioctl(vcpu, argp); } static int vt_vcpu_mem_enc_unlocked_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { if (!is_td_vcpu(vcpu)) return -EINVAL; return tdx_vcpu_unlocked_ioctl(vcpu, argp); } static int vt_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private) { if (is_td(kvm)) return tdx_gmem_max_mapping_level(kvm, pfn, is_private); return 0; } #define vt_op(name) vt_##name #define vt_op_tdx_only(name) vt_##name #else /* CONFIG_KVM_INTEL_TDX */ #define vt_op(name) vmx_##name #define vt_op_tdx_only(name) NULL #endif /* CONFIG_KVM_INTEL_TDX */ #define VMX_REQUIRED_APICV_INHIBITS \ (BIT(APICV_INHIBIT_REASON_DISABLED) | \ BIT(APICV_INHIBIT_REASON_ABSENT) | \ BIT(APICV_INHIBIT_REASON_HYPERV) | \ BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED)) struct kvm_x86_ops vt_x86_ops __initdata = { .name = KBUILD_MODNAME, .check_processor_compatibility = vmx_check_processor_compat, .hardware_unsetup = vt_op(hardware_unsetup), .enable_virtualization_cpu = vmx_enable_virtualization_cpu, .disable_virtualization_cpu = vt_op(disable_virtualization_cpu), .emergency_disable_virtualization_cpu = vmx_emergency_disable_virtualization_cpu, .has_emulated_msr = vt_op(has_emulated_msr), .vm_size = sizeof(struct kvm_vmx), .vm_init = vt_op(vm_init), .vm_destroy = vt_op(vm_destroy), .vm_pre_destroy = vt_op_tdx_only(vm_pre_destroy), .vcpu_precreate = vt_op(vcpu_precreate), .vcpu_create = vt_op(vcpu_create), .vcpu_free = vt_op(vcpu_free), .vcpu_reset = vt_op(vcpu_reset), .prepare_switch_to_guest = vt_op(prepare_switch_to_guest), .vcpu_load = vt_op(vcpu_load), .vcpu_put = vt_op(vcpu_put), .HOST_OWNED_DEBUGCTL = VMX_HOST_OWNED_DEBUGCTL_BITS, .update_exception_bitmap = vt_op(update_exception_bitmap), .get_feature_msr = vmx_get_feature_msr, .get_msr = vt_op(get_msr), .set_msr = vt_op(set_msr), .get_segment_base = vt_op(get_segment_base), .get_segment = vt_op(get_segment), .set_segment = vt_op(set_segment), .get_cpl = vt_op(get_cpl), .get_cpl_no_cache = vt_op(get_cpl_no_cache), .get_cs_db_l_bits = vt_op(get_cs_db_l_bits), .is_valid_cr0 = vt_op(is_valid_cr0), .set_cr0 = vt_op(set_cr0), .is_valid_cr4 = vt_op(is_valid_cr4), .set_cr4 = vt_op(set_cr4), .set_efer = vt_op(set_efer), .get_idt = vt_op(get_idt), .set_idt = vt_op(set_idt), .get_gdt = vt_op(get_gdt), .set_gdt = vt_op(set_gdt), .set_dr7 = vt_op(set_dr7), .sync_dirty_debug_regs = vt_op(sync_dirty_debug_regs), .cache_reg = vt_op(cache_reg), .get_rflags = vt_op(get_rflags), .set_rflags = vt_op(set_rflags), .get_if_flag = vt_op(get_if_flag), .flush_tlb_all = vt_op(flush_tlb_all), .flush_tlb_current = vt_op(flush_tlb_current), .flush_tlb_gva = vt_op(flush_tlb_gva), .flush_tlb_guest = vt_op(flush_tlb_guest), .vcpu_pre_run = vt_op(vcpu_pre_run), .vcpu_run = vt_op(vcpu_run), .handle_exit = vt_op(handle_exit), .skip_emulated_instruction = vmx_skip_emulated_instruction, .update_emulated_instruction = vmx_update_emulated_instruction, .set_interrupt_shadow = vt_op(set_interrupt_shadow), .get_interrupt_shadow = vt_op(get_interrupt_shadow), .patch_hypercall = vt_op(patch_hypercall), .inject_irq = vt_op(inject_irq), .inject_nmi = vt_op(inject_nmi), .inject_exception = vt_op(inject_exception), .cancel_injection = vt_op(cancel_injection), .interrupt_allowed = vt_op(interrupt_allowed), .nmi_allowed = vt_op(nmi_allowed), .get_nmi_mask = vt_op(get_nmi_mask), .set_nmi_mask = vt_op(set_nmi_mask), .enable_nmi_window = vt_op(enable_nmi_window), .enable_irq_window = vt_op(enable_irq_window), .update_cr8_intercept = vt_op(update_cr8_intercept), .x2apic_icr_is_split = false, .set_virtual_apic_mode = vt_op(set_virtual_apic_mode), .set_apic_access_page_addr = vt_op(set_apic_access_page_addr), .refresh_apicv_exec_ctrl = vt_op(refresh_apicv_exec_ctrl), .load_eoi_exitmap = vt_op(load_eoi_exitmap), .apicv_pre_state_restore = pi_apicv_pre_state_restore, .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, .hwapic_isr_update = vt_op(hwapic_isr_update), .sync_pir_to_irr = vt_op(sync_pir_to_irr), .deliver_interrupt = vt_op(deliver_interrupt), .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt, .set_tss_addr = vt_op(set_tss_addr), .set_identity_map_addr = vt_op(set_identity_map_addr), .get_mt_mask = vmx_get_mt_mask, .tdp_has_smep = vt_op(tdp_has_smep), .get_exit_info = vt_op(get_exit_info), .get_entry_info = vt_op(get_entry_info), .vcpu_after_set_cpuid = vt_op(vcpu_after_set_cpuid), .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, .get_l2_tsc_offset = vt_op(get_l2_tsc_offset), .get_l2_tsc_multiplier = vt_op(get_l2_tsc_multiplier), .write_tsc_offset = vt_op(write_tsc_offset), .write_tsc_multiplier = vt_op(write_tsc_multiplier), .load_mmu_pgd = vt_op(load_mmu_pgd), .check_intercept = vmx_check_intercept, .handle_exit_irqoff = vmx_handle_exit_irqoff, .update_cpu_dirty_logging = vt_op(update_cpu_dirty_logging), .nested_ops = &vmx_nested_ops, .pi_update_irte = vmx_pi_update_irte, .pi_start_bypass = vmx_pi_start_bypass, #ifdef CONFIG_X86_64 .set_hv_timer = vt_op(set_hv_timer), .cancel_hv_timer = vt_op(cancel_hv_timer), #endif .setup_mce = vt_op(setup_mce), #ifdef CONFIG_KVM_SMM .smi_allowed = vt_op(smi_allowed), .enter_smm = vt_op(enter_smm), .leave_smm = vt_op(leave_smm), .enable_smi_window = vt_op(enable_smi_window), #endif .check_emulate_instruction = vt_op(check_emulate_instruction), .apic_init_signal_blocked = vt_op(apic_init_signal_blocked), .migrate_timers = vmx_migrate_timers, .recalc_intercepts = vt_op(recalc_intercepts), .complete_emulated_msr = vt_op(complete_emulated_msr), .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, .get_untagged_addr = vmx_get_untagged_addr, .mem_enc_ioctl = vt_op_tdx_only(mem_enc_ioctl), .vcpu_mem_enc_ioctl = vt_op_tdx_only(vcpu_mem_enc_ioctl), .vcpu_mem_enc_unlocked_ioctl = vt_op_tdx_only(vcpu_mem_enc_unlocked_ioctl), .gmem_max_mapping_level = vt_op_tdx_only(gmem_max_mapping_level) }; struct kvm_x86_init_ops vt_init_ops __initdata = { .hardware_setup = vt_op(hardware_setup), .handle_intel_pt_intr = NULL, .runtime_ops = &vt_x86_ops, .pmu_ops = &intel_pmu_ops, }; static void __exit vt_exit(void) { kvm_exit(); vmx_exit(); } module_exit(vt_exit); static int __init vt_init(void) { unsigned vcpu_size, vcpu_align; int r; r = vmx_init(); if (r) return r; /* * TDX and VMX have different vCPU structures. Calculate the * maximum size/align so that kvm_init() can use the larger * values to create the kmem_vcpu_cache. */ vcpu_size = sizeof(struct vcpu_vmx); vcpu_align = __alignof__(struct vcpu_vmx); if (enable_tdx) { vcpu_size = max_t(unsigned, vcpu_size, sizeof(struct vcpu_tdx)); vcpu_align = max_t(unsigned, vcpu_align, __alignof__(struct vcpu_tdx)); kvm_caps.supported_vm_types |= BIT(KVM_X86_TDX_VM); } /* * Common KVM initialization _must_ come last, after this, /dev/kvm is * exposed to userspace! */ r = kvm_init(vcpu_size, vcpu_align, THIS_MODULE); if (r) goto err_kvm_init; return 0; err_kvm_init: vmx_exit(); return r; } module_init(vt_init); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Framework and drivers for configuring and reading different PHYs * Based on code in sungem_phy.c and (long-removed) gianfar_phy.c * * Author: Andy Fleming * * Copyright (c) 2004 Freescale Semiconductor, Inc. */ #ifndef __PHY_H #define __PHY_H #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/ethtool.h> #include <linux/leds.h> #include <linux/linkmode.h> #include <linux/netlink.h> #include <linux/mdio.h> #include <linux/mii.h> #include <linux/mii_timestamper.h> #include <linux/module.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/device-id/mdio.h> #include <linux/u64_stats_sync.h> #include <linux/irqreturn.h> #include <linux/iopoll.h> #include <linux/refcount.h> #include <linux/atomic.h> #include <net/eee.h> extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1s_p2mp_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init; #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) #define PHY_BASIC_T1_FEATURES ((unsigned long *)&phy_basic_t1_features) #define PHY_BASIC_T1S_P2MP_FEATURES ((unsigned long *)&phy_basic_t1s_p2mp_features) #define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) #define PHY_EEE_CAP1_FEATURES ((unsigned long *)&phy_eee_cap1_features) #define PHY_EEE_CAP2_FEATURES ((unsigned long *)&phy_eee_cap2_features) extern const int phy_basic_ports_array[3]; /* * Set phydev->irq to PHY_POLL if interrupts are not supported, * or not desired for this PHY. Set to PHY_MAC_INTERRUPT if * the attached MAC driver handles the interrupt */ #define PHY_POLL -1 #define PHY_MAC_INTERRUPT -2 #define PHY_IS_INTERNAL 0x00000001 #define PHY_RST_AFTER_CLK_EN 0x00000002 #define PHY_POLL_CABLE_TEST 0x00000004 #define PHY_ALWAYS_CALL_SUSPEND 0x00000008 #define MDIO_DEVICE_IS_PHY 0x80000000 /** * enum phy_interface_t - Interface Mode definitions * * @PHY_INTERFACE_MODE_NA: Not Applicable - don't touch * @PHY_INTERFACE_MODE_INTERNAL: No interface, MAC and PHY combined * @PHY_INTERFACE_MODE_MII: Media-independent interface * @PHY_INTERFACE_MODE_GMII: Gigabit media-independent interface * @PHY_INTERFACE_MODE_SGMII: Serial gigabit media-independent interface * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface * @PHY_INTERFACE_MODE_REVRMII: Reduced Media Independent Interface in PHY role * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal TX delay * @PHY_INTERFACE_MODE_RTBI: Reduced TBI * @PHY_INTERFACE_MODE_SMII: Serial MII * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax * @PHY_INTERFACE_MODE_PSGMII: Penta SGMII * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII * @PHY_INTERFACE_MODE_100BASEX: 100 BaseX * @PHY_INTERFACE_MODE_1000BASEX: 1000 BaseX * @PHY_INTERFACE_MODE_2500BASEX: 2500 BaseX * @PHY_INTERFACE_MODE_5GBASER: 5G BaseR * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR * @PHY_INTERFACE_MODE_25GBASER: 25G BaseR * @PHY_INTERFACE_MODE_USXGMII: Universal Serial 10GE MII * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN * @PHY_INTERFACE_MODE_QUSGMII: Quad Universal SGMII * @PHY_INTERFACE_MODE_1000BASEKX: 1000Base-KX - with Clause 73 AN * @PHY_INTERFACE_MODE_10G_QXGMII: 10G-QXGMII - 4 ports over 10G USXGMII * @PHY_INTERFACE_MODE_50GBASER: 50GBase-R - with Clause 134 FEC * @PHY_INTERFACE_MODE_LAUI: 50 Gigabit Attachment Unit Interface * @PHY_INTERFACE_MODE_100GBASEP: 100GBase-P - with Clause 134 FEC * @PHY_INTERFACE_MODE_MIILITE: MII-Lite - MII without RXER TXER CRS COL * @PHY_INTERFACE_MODE_MAX: Book keeping * * Describes the interface between the MAC and PHY. */ typedef enum { PHY_INTERFACE_MODE_NA, PHY_INTERFACE_MODE_INTERNAL, PHY_INTERFACE_MODE_MII, PHY_INTERFACE_MODE_GMII, PHY_INTERFACE_MODE_SGMII, PHY_INTERFACE_MODE_TBI, PHY_INTERFACE_MODE_REVMII, PHY_INTERFACE_MODE_RMII, PHY_INTERFACE_MODE_REVRMII, PHY_INTERFACE_MODE_RGMII, PHY_INTERFACE_MODE_RGMII_ID, PHY_INTERFACE_MODE_RGMII_RXID, PHY_INTERFACE_MODE_RGMII_TXID, PHY_INTERFACE_MODE_RTBI, PHY_INTERFACE_MODE_SMII, PHY_INTERFACE_MODE_XGMII, PHY_INTERFACE_MODE_XLGMII, PHY_INTERFACE_MODE_MOCA, PHY_INTERFACE_MODE_PSGMII, PHY_INTERFACE_MODE_QSGMII, PHY_INTERFACE_MODE_TRGMII, PHY_INTERFACE_MODE_100BASEX, PHY_INTERFACE_MODE_1000BASEX, PHY_INTERFACE_MODE_2500BASEX, PHY_INTERFACE_MODE_5GBASER, PHY_INTERFACE_MODE_RXAUI, PHY_INTERFACE_MODE_XAUI, /* 10GBASE-R, XFI, SFI - single lane 10G Serdes */ PHY_INTERFACE_MODE_10GBASER, PHY_INTERFACE_MODE_25GBASER, PHY_INTERFACE_MODE_USXGMII, /* 10GBASE-KR - with Clause 73 AN */ PHY_INTERFACE_MODE_10GKR, PHY_INTERFACE_MODE_QUSGMII, PHY_INTERFACE_MODE_1000BASEKX, PHY_INTERFACE_MODE_10G_QXGMII, PHY_INTERFACE_MODE_50GBASER, PHY_INTERFACE_MODE_LAUI, PHY_INTERFACE_MODE_100GBASEP, PHY_INTERFACE_MODE_MIILITE, PHY_INTERFACE_MODE_MAX, } phy_interface_t; /* PHY interface mode bitmap handling */ #define DECLARE_PHY_INTERFACE_MASK(name) \ DECLARE_BITMAP(name, PHY_INTERFACE_MODE_MAX) static inline void phy_interface_zero(unsigned long *intf) { bitmap_zero(intf, PHY_INTERFACE_MODE_MAX); } static inline bool phy_interface_empty(const unsigned long *intf) { return bitmap_empty(intf, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_copy(unsigned long *d, const unsigned long *s) { bitmap_copy(d, s, PHY_INTERFACE_MODE_MAX); } static inline unsigned int phy_interface_weight(const unsigned long *intf) { return bitmap_weight(intf, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_and(unsigned long *dst, const unsigned long *a, const unsigned long *b) { bitmap_and(dst, a, b, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_or(unsigned long *dst, const unsigned long *a, const unsigned long *b) { bitmap_or(dst, a, b, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_set_rgmii(unsigned long *intf) { __set_bit(PHY_INTERFACE_MODE_RGMII, intf); __set_bit(PHY_INTERFACE_MODE_RGMII_ID, intf); __set_bit(PHY_INTERFACE_MODE_RGMII_RXID, intf); __set_bit(PHY_INTERFACE_MODE_RGMII_TXID, intf); } /** * phy_modes - map phy_interface_t enum to device tree binding of phy-mode * @interface: enum phy_interface_t value * * Description: maps enum &phy_interface_t defined in this file * into the device tree binding of 'phy-mode', so that Ethernet * device driver can get PHY interface from device tree. */ static inline const char *phy_modes(phy_interface_t interface) { switch (interface) { case PHY_INTERFACE_MODE_NA: return ""; case PHY_INTERFACE_MODE_INTERNAL: return "internal"; case PHY_INTERFACE_MODE_MII: return "mii"; case PHY_INTERFACE_MODE_GMII: return "gmii"; case PHY_INTERFACE_MODE_SGMII: return "sgmii"; case PHY_INTERFACE_MODE_TBI: return "tbi"; case PHY_INTERFACE_MODE_REVMII: return "rev-mii"; case PHY_INTERFACE_MODE_RMII: return "rmii"; case PHY_INTERFACE_MODE_REVRMII: return "rev-rmii"; case PHY_INTERFACE_MODE_RGMII: return "rgmii"; case PHY_INTERFACE_MODE_RGMII_ID: return "rgmii-id"; case PHY_INTERFACE_MODE_RGMII_RXID: return "rgmii-rxid"; case PHY_INTERFACE_MODE_RGMII_TXID: return "rgmii-txid"; case PHY_INTERFACE_MODE_RTBI: return "rtbi"; case PHY_INTERFACE_MODE_SMII: return "smii"; case PHY_INTERFACE_MODE_XGMII: return "xgmii"; case PHY_INTERFACE_MODE_XLGMII: return "xlgmii"; case PHY_INTERFACE_MODE_MOCA: return "moca"; case PHY_INTERFACE_MODE_PSGMII: return "psgmii"; case PHY_INTERFACE_MODE_QSGMII: return "qsgmii"; case PHY_INTERFACE_MODE_TRGMII: return "trgmii"; case PHY_INTERFACE_MODE_1000BASEX: return "1000base-x"; case PHY_INTERFACE_MODE_1000BASEKX: return "1000base-kx"; case PHY_INTERFACE_MODE_2500BASEX: return "2500base-x"; case PHY_INTERFACE_MODE_5GBASER: return "5gbase-r"; case PHY_INTERFACE_MODE_RXAUI: return "rxaui"; case PHY_INTERFACE_MODE_XAUI: return "xaui"; case PHY_INTERFACE_MODE_10GBASER: return "10gbase-r"; case PHY_INTERFACE_MODE_25GBASER: return "25gbase-r"; case PHY_INTERFACE_MODE_USXGMII: return "usxgmii"; case PHY_INTERFACE_MODE_10GKR: return "10gbase-kr"; case PHY_INTERFACE_MODE_100BASEX: return "100base-x"; case PHY_INTERFACE_MODE_QUSGMII: return "qusgmii"; case PHY_INTERFACE_MODE_10G_QXGMII: return "10g-qxgmii"; case PHY_INTERFACE_MODE_50GBASER: return "50gbase-r"; case PHY_INTERFACE_MODE_LAUI: return "laui"; case PHY_INTERFACE_MODE_100GBASEP: return "100gbase-p"; case PHY_INTERFACE_MODE_MIILITE: return "mii-lite"; default: return "unknown"; } } /** * rgmii_clock - map link speed to the clock rate * @speed: link speed value * * Description: maps RGMII supported link speeds into the clock rates. * This can also be used for MII, GMII, and RMII interface modes as the * clock rates are identical, but the caller must be aware that errors * for unsupported clock rates will not be signalled. * * Returns: clock rate or negative errno */ static inline long rgmii_clock(int speed) { switch (speed) { case SPEED_10: return 2500000; case SPEED_100: return 25000000; case SPEED_1000: return 125000000; default: return -EINVAL; } } #define PHY_MAX_ADDR 32 /* Used when trying to connect to a specific phy (mii bus id:phy device id) */ #define PHY_ID_FMT "%s:%02x" #define PHY_ID_SIZE (MII_BUS_ID_SIZE + 3) #define MII_BUS_ID_SIZE 61 struct device; struct kernel_hwtstamp_config; struct phylink; struct phy_port; struct sfp_bus; struct sfp_upstream_ops; struct sk_buff; /** * struct mdio_bus_stats - Statistics counters for MDIO busses * @transfers: Total number of transfers, i.e. @writes + @reads * @errors: Number of MDIO transfers that returned an error * @writes: Number of write transfers * @reads: Number of read transfers * @syncp: Synchronisation for incrementing statistics */ struct mdio_bus_stats { u64_stats_t transfers; u64_stats_t errors; u64_stats_t writes; u64_stats_t reads; /* Must be last, add new statistics above */ struct u64_stats_sync syncp; }; /** * struct mii_bus - Represents an MDIO bus * * @owner: Who owns this device * @name: User friendly name for this MDIO device, or driver name * @id: Unique identifier for this bus, typical from bus hierarchy * @priv: Driver private data * * The Bus class for PHYs. Devices which provide access to * PHYs should register using this structure */ struct mii_bus { struct module *owner; const char *name; char id[MII_BUS_ID_SIZE]; void *priv; /** @read: Perform a read transfer on the bus */ int (*read)(struct mii_bus *bus, int addr, int regnum); /** @write: Perform a write transfer on the bus */ int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val); /** @read_c45: Perform a C45 read transfer on the bus */ int (*read_c45)(struct mii_bus *bus, int addr, int devnum, int regnum); /** @write_c45: Perform a C45 write transfer on the bus */ int (*write_c45)(struct mii_bus *bus, int addr, int devnum, int regnum, u16 val); /** @reset: Perform a reset of the bus */ int (*reset)(struct mii_bus *bus); /** @stats: Statistic counters per device on the bus */ struct mdio_bus_stats stats[PHY_MAX_ADDR]; /** * @mdio_lock: A lock to ensure that only one thing can read/write * the MDIO bus at a time */ struct mutex mdio_lock; /** @parent: Parent device of this bus */ struct device *parent; /** @state: State of bus structure */ enum { MDIOBUS_ALLOCATED = 1, MDIOBUS_REGISTERED, MDIOBUS_UNREGISTERED, MDIOBUS_RELEASED, } state; /** @dev: Kernel device representation */ struct device dev; /** @mdio_map: list of all MDIO devices on bus */ struct mdio_device *mdio_map[PHY_MAX_ADDR]; /** @phy_mask: PHY addresses to be ignored when probing */ u32 phy_mask; /** @phy_ignore_ta_mask: PHY addresses to ignore the TA/read failure */ u32 phy_ignore_ta_mask; /** * @irq: An array of interrupts, each PHY's interrupt at the index * matching its address */ int irq[PHY_MAX_ADDR]; /** @reset_delay_us: GPIO reset pulse width in microseconds */ int reset_delay_us; /** @reset_post_delay_us: GPIO reset deassert delay in microseconds */ int reset_post_delay_us; /** @reset_gpiod: Reset GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; /** @shared_lock: protect access to the shared element */ struct mutex shared_lock; #if IS_ENABLED(CONFIG_PHY_PACKAGE) /** @shared: shared state across different PHYs */ struct phy_package_shared *shared[PHY_MAX_ADDR]; #endif }; #define to_mii_bus(d) container_of(d, struct mii_bus, dev) struct mii_bus *mdiobus_alloc_size(size_t size); /** * mdiobus_alloc - Allocate an MDIO bus structure * * The internal state of the MDIO bus will be set of MDIOBUS_ALLOCATED ready * for the driver to register the bus. */ static inline struct mii_bus *mdiobus_alloc(void) { return mdiobus_alloc_size(0); } int __mdiobus_register(struct mii_bus *bus, struct module *owner); int __devm_mdiobus_register(struct device *dev, struct mii_bus *bus, struct module *owner); #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) #define devm_mdiobus_register(dev, bus) \ __devm_mdiobus_register(dev, bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) { return devm_mdiobus_alloc_size(dev, 0); } struct mii_bus *mdio_find_bus(const char *mdio_name); struct phy_device *mdiobus_scan_c22(struct mii_bus *bus, int addr); #define PHY_INTERRUPT_DISABLED false #define PHY_INTERRUPT_ENABLED true /** * enum phy_state - PHY state machine states: * * @PHY_DOWN: PHY device and driver are not ready for anything. probe * should be called if and only if the PHY is in this state, * given that the PHY device exists. * - PHY driver probe function will set the state to @PHY_READY * * @PHY_READY: PHY is ready to send and receive packets, but the * controller is not. By default, PHYs which do not implement * probe will be set to this state by phy_probe(). * - start will set the state to UP * * @PHY_UP: The PHY and attached device are ready to do work. * Interrupts should be started here. * - timer moves to @PHY_NOLINK or @PHY_RUNNING * * @PHY_NOLINK: PHY is up, but not currently plugged in. * - irq or timer will set @PHY_RUNNING if link comes back * - phy_stop moves to @PHY_HALTED * * @PHY_RUNNING: PHY is currently up, running, and possibly sending * and/or receiving packets * - irq or timer will set @PHY_NOLINK if link goes down * - phy_stop moves to @PHY_HALTED * * @PHY_CABLETEST: PHY is performing a cable test. Packet reception/sending * is not expected to work, carrier will be indicated as down. PHY will be * poll once per second, or on interrupt for it current state. * Once complete, move to UP to restart the PHY. * - phy_stop aborts the running test and moves to @PHY_HALTED * * @PHY_HALTED: PHY is up, but no polling or interrupts are done. * - phy_start moves to @PHY_UP * * @PHY_ERROR: PHY is up, but is in an error state. * - phy_stop moves to @PHY_HALTED */ enum phy_state { PHY_DOWN = 0, PHY_READY, PHY_HALTED, PHY_ERROR, PHY_UP, PHY_RUNNING, PHY_NOLINK, PHY_CABLETEST, }; #define MDIO_MMD_NUM 32 /** * struct phy_c45_device_ids - 802.3-c45 Device Identifiers * @devices_in_package: IEEE 802.3 devices in package register value. * @mmds_present: bit vector of MMDs present. * @device_ids: The device identifier for each present device. */ struct phy_c45_device_ids { u32 devices_in_package; u32 mmds_present; u32 device_ids[MDIO_MMD_NUM]; }; struct macsec_context; struct macsec_ops; /** * struct phy_oatc14_sqi_capability - SQI capability information for OATC14 * 10Base-T1S PHY * @updated: Indicates whether the SQI capability fields have been updated. * @sqi_max: Maximum supported Signal Quality Indicator (SQI) level reported by * the PHY. * @sqiplus_bits: Bits for SQI+ levels supported by the PHY. * 0 - SQI+ is not supported * 3 - SQI+ is supported, using 3 bits (8 levels) * 4 - SQI+ is supported, using 4 bits (16 levels) * 5 - SQI+ is supported, using 5 bits (32 levels) * 6 - SQI+ is supported, using 6 bits (64 levels) * 7 - SQI+ is supported, using 7 bits (128 levels) * 8 - SQI+ is supported, using 8 bits (256 levels) * * This structure is used by the OATC14 10Base-T1S PHY driver to store the SQI * and SQI+ capability information retrieved from the PHY. */ struct phy_oatc14_sqi_capability { bool updated; int sqi_max; u8 sqiplus_bits; }; /** * struct phy_device - An instance of a PHY * * @mdio: MDIO bus this PHY is on * @drv: Pointer to the driver for this PHY instance * @devlink: Create a link between phy dev and mac dev, if the external phy * used by current mac interface is managed by another mac interface. * @phyindex: Unique id across the phy's parent tree of phys to address the PHY * from userspace, similar to ifindex. A zero index means the PHY * wasn't assigned an id yet. * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. * @is_internal: Set to true if this PHY is internal to a MAC. * @is_pseudo_fixed_link: Set to true if this PHY is an Ethernet switch, etc. * @is_gigabit_capable: Set to true if PHY supports 1000Mbps * @has_fixups: Set to true if this PHY has fixups/quirks. * @suspended: Set to true if this PHY has been suspended successfully. * @suspended_by_mdio_bus: Set to true if this PHY was suspended by MDIO bus. * @sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. * @loopback_enabled: Set true if this PHY has been loopbacked successfully. * @downshifted_rate: Set true if link speed has been downshifted. * @is_on_sfp_module: Set true if PHY is located on an SFP module. * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @wol_enabled: Set to true if the PHY or the attached MAC have Wake-on-LAN * enabled. * @is_genphy_driven: PHY is driven by one of the generic PHY drivers * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. * * - Bits [15:0] are free to use by the PHY driver to communicate * driver specific behavior. * - Bits [23:16] are currently reserved for future use. * - Bits [31:24] are reserved for defining generic * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) * @phylink: Pointer to phylink instance for this PHY * @sfp_bus_attached: Flag indicating whether the SFP bus has been attached * @sfp_bus: SFP bus attached to this PHY's fiber port * @attached_dev: The attached enet driver's device instance ptr * @adjust_link: Callback for the enet controller to respond to changes: in the * link state. * @phy_link_change: Callback for phylink for notification of link change * @macsec_ops: MACsec offloading ops. * * @speed: Current link speed * @duplex: Current duplex * @port: Current port * @pause: Current pause * @asym_pause: Current asymmetric pause * @supported: Combined MAC/PHY supported linkmodes * @advertising: Currently advertised linkmodes * @adv_old: Saved advertised while power saving for WoL * @supported_eee: supported PHY EEE linkmodes * @advertising_eee: Currently advertised EEE linkmodes * @enable_tx_lpi: When True, MAC should transmit LPI to PHY * @eee_active: phylib private state, indicating that EEE has been negotiated * @autonomous_eee_disabled: Set when autonomous EEE has been disabled, * used to re-apply after PHY soft reset * @eee_cfg: User configuration of EEE * @lp_advertising: Current link partner advertised linkmodes * @host_interfaces: PHY interface modes supported by host * @eee_disabled_modes: Energy efficient ethernet modes not to be advertised * @autoneg: Flag autoneg being used * @rate_matching: Current rate matching mode * @link: Current link state * @autoneg_complete: Flag auto negotiation of the link has completed * @mdix: Current crossover * @mdix_ctrl: User setting of crossover * @pma_extable: Cached value of PMA/PMD Extended Abilities Register * @interrupts: Flag interrupts have been enabled * @irq_suspended: Flag indicating PHY is suspended and therefore interrupt * handling shall be postponed until PHY has resumed * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended, * requiring a rerun of the interrupt handler after resume * @default_timestamp: Flag indicating whether we are using the phy * timestamp as the default one * @interface: enum phy_interface_t value * @possible_interfaces: bitmap if interface modes that the attached PHY * will switch between depending on media speed. * @skb: Netlink message for cable diagnostics * @nest: Netlink nest used for cable diagnostics * @ehdr: nNtlink header for cable diagnostics * @phy_led_triggers: Array of LED triggers * @phy_num_led_triggers: Number of triggers in @phy_led_triggers * @led_link_trigger: LED trigger for link up/down * @last_triggered: last LED trigger for link speed * @leds: list of PHY LED structures * @master_slave_set: User requested master/slave configuration * @master_slave_get: Current master/slave advertisement * @master_slave_state: Current master/slave configuration * @mii_ts: Pointer to time stamper callbacks * @psec: Pointer to Power Sourcing Equipment control struct * @ports: List of PHY ports structures * @n_ports: Number of ports currently attached to the PHY * @max_n_ports: Max number of ports this PHY can expose * @lock: Mutex for serialization access to PHY * @state_queue: Work queue for state machine * @link_down_events: Number of times link was lost * @shared: Pointer to private data shared by phys in one package * @priv: Pointer to driver private data * @oatc14_sqi_capability: SQI capability information for OATC14 10Base-T1S PHY * * interrupts currently only supports enabled or disabled, * but could be changed in the future to support enabling * and disabling specific interrupts * * Contains some infrastructure for polling and interrupt * handling, as well as handling shifts in PHY hardware state */ struct phy_device { struct mdio_device mdio; /* Information about the PHY type */ /* And management functions */ const struct phy_driver *drv; struct device_link *devlink; u32 phyindex; u32 phy_id; struct phy_c45_device_ids c45_ids; unsigned is_c45:1; unsigned is_internal:1; unsigned is_pseudo_fixed_link:1; unsigned is_gigabit_capable:1; unsigned has_fixups:1; unsigned suspended:1; unsigned suspended_by_mdio_bus:1; unsigned sysfs_links:1; unsigned loopback_enabled:1; unsigned downshifted_rate:1; unsigned is_on_sfp_module:1; unsigned mac_managed_pm:1; unsigned wol_enabled:1; unsigned is_genphy_driven:1; unsigned autoneg:1; /* The most recently read link state */ unsigned link:1; unsigned autoneg_complete:1; bool pause:1; bool asym_pause:1; /* Interrupts are enabled */ unsigned interrupts:1; unsigned irq_suspended:1; unsigned irq_rerun:1; unsigned default_timestamp:1; int rate_matching; enum phy_state state; u32 dev_flags; phy_interface_t interface; DECLARE_PHY_INTERFACE_MASK(possible_interfaces); /* * forced speed & duplex (no autoneg) * partner speed & duplex & pause (autoneg) */ int speed; int duplex; int port; u8 master_slave_get; u8 master_slave_set; u8 master_slave_state; /* Union of PHY and Attached devices' supported link modes */ /* See ethtool.h for more info */ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); /* used with phy_speed_down */ __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); /* used for eee validation and configuration*/ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_eee); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising_eee); /* Energy efficient ethernet modes which should be prohibited */ __ETHTOOL_DECLARE_LINK_MODE_MASK(eee_disabled_modes); bool enable_tx_lpi; bool eee_active; bool autonomous_eee_disabled; struct eee_config eee_cfg; /* Host supported PHY interface types. Should be ignored if empty. */ DECLARE_PHY_INTERFACE_MASK(host_interfaces); #ifdef CONFIG_LED_TRIGGER_PHY struct phy_led_trigger *phy_led_triggers; unsigned int phy_num_led_triggers; struct phy_led_trigger *last_triggered; struct phy_led_trigger *led_link_trigger; #endif struct list_head leds; /* * Interrupt number for this PHY * -1 means no interrupt */ int irq; /* private data pointer */ /* For use by PHYs to maintain extra state */ void *priv; #if IS_ENABLED(CONFIG_PHY_PACKAGE) /* shared data pointer */ /* For use by PHYs inside the same package that need a shared state. */ struct phy_package_shared *shared; #endif /* Reporting cable test results */ struct sk_buff *skb; void *ehdr; struct nlattr *nest; /* Interrupt and Polling infrastructure */ struct delayed_work state_queue; struct mutex lock; /* This may be modified under the rtnl lock */ bool sfp_bus_attached; struct sfp_bus *sfp_bus; struct phylink *phylink; struct net_device *attached_dev; struct mii_timestamper *mii_ts; struct pse_control *psec; struct list_head ports; int n_ports; int max_n_ports; u8 mdix; u8 mdix_ctrl; int pma_extable; unsigned int link_down_events; void (*phy_link_change)(struct phy_device *phydev, bool up); void (*adjust_link)(struct net_device *dev); #if IS_ENABLED(CONFIG_MACSEC) /* MACsec management functions */ const struct macsec_ops *macsec_ops; #endif struct phy_oatc14_sqi_capability oatc14_sqi_capability; }; /* Generic phy_device::dev_flags */ #define PHY_F_NO_IRQ 0x80000000 #define PHY_F_RXC_ALWAYS_ON 0x40000000 #define PHY_F_KEEP_PREAMBLE_BEFORE_SFD 0x20000000 #define to_phy_device(__dev) container_of_const(to_mdio_device(__dev), struct phy_device, mdio) #define phy_for_each_port(phydev, port) \ list_for_each_entry(port, &(phydev)->ports, head) /** * struct phy_tdr_config - Configuration of a TDR raw test * * @first: Distance for first data collection point * @last: Distance for last data collection point * @step: Step between data collection points * @pair: Bitmap of cable pairs to collect data for * * A structure containing possible configuration parameters * for a TDR cable test. The driver does not need to implement * all the parameters, but should report what is actually used. * All distances are in centimeters. */ struct phy_tdr_config { u32 first; u32 last; u32 step; s8 pair; }; #define PHY_PAIR_ALL -1 /** * enum link_inband_signalling - in-band signalling modes that are supported * * @LINK_INBAND_DISABLE: in-band signalling can be disabled * @LINK_INBAND_ENABLE: in-band signalling can be enabled without bypass * @LINK_INBAND_BYPASS: in-band signalling can be enabled with bypass * * The possible and required bits can only be used if the valid bit is set. * If possible is clear, that means inband signalling can not be used. * Required is only valid when possible is set, and means that inband * signalling must be used. */ enum link_inband_signalling { LINK_INBAND_DISABLE = BIT(0), LINK_INBAND_ENABLE = BIT(1), LINK_INBAND_BYPASS = BIT(2), }; /** * struct phy_plca_cfg - Configuration of the PLCA (Physical Layer Collision * Avoidance) Reconciliation Sublayer. * * @version: read-only PLCA register map version. -1 = not available. Ignored * when setting the configuration. Format is the same as reported by the PLCA * IDVER register (31.CA00). -1 = not available. * @enabled: PLCA configured mode (enabled/disabled). -1 = not available / don't * set. 0 = disabled, anything else = enabled. * @node_id: the PLCA local node identifier. -1 = not available / don't set. * Allowed values [0 .. 254]. 255 = node disabled. * @node_cnt: the PLCA node count (maximum number of nodes having a TO). Only * meaningful for the coordinator (node_id = 0). -1 = not available / don't * set. Allowed values [1 .. 255]. * @to_tmr: The value of the PLCA to_timer in bit-times, which determines the * PLCA transmit opportunity window opening. See IEEE802.3 Clause 148 for * more details. The to_timer shall be set equal over all nodes. * -1 = not available / don't set. Allowed values [0 .. 255]. * @burst_cnt: controls how many additional frames a node is allowed to send in * single transmit opportunity (TO). The default value of 0 means that the * node is allowed exactly one frame per TO. A value of 1 allows two frames * per TO, and so on. -1 = not available / don't set. * Allowed values [0 .. 255]. * @burst_tmr: controls how many bit times to wait for the MAC to send a new * frame before interrupting the burst. This value should be set to a value * greater than the MAC inter-packet gap (which is typically 96 bits). * -1 = not available / don't set. Allowed values [0 .. 255]. * * A structure containing configuration parameters for setting/getting the PLCA * RS configuration. The driver does not need to implement all the parameters, * but should report what is actually used. */ struct phy_plca_cfg { int version; int enabled; int node_id; int node_cnt; int to_tmr; int burst_cnt; int burst_tmr; }; /** * struct phy_plca_status - Status of the PLCA (Physical Layer Collision * Avoidance) Reconciliation Sublayer. * * @pst: The PLCA status as reported by the PST bit in the PLCA STATUS * register(31.CA03), indicating BEACON activity. * * A structure containing status information of the PLCA RS configuration. * The driver does not need to implement all the parameters, but should report * what is actually used. */ struct phy_plca_status { bool pst; }; /* Modes for PHY LED configuration */ enum phy_led_modes { PHY_LED_ACTIVE_HIGH = 0, PHY_LED_ACTIVE_LOW = 1, PHY_LED_INACTIVE_HIGH_IMPEDANCE = 2, /* keep it last */ __PHY_LED_MODES_NUM, }; /** * struct phy_led: An LED driven by the PHY * * @list: List of LEDs * @phydev: PHY this LED is attached to * @led_cdev: Standard LED class structure * @index: Number of the LED */ struct phy_led { struct list_head list; struct phy_device *phydev; struct led_classdev led_cdev; u8 index; }; #define to_phy_led(d) container_of(d, struct phy_led, led_cdev) /* * PHY_MSE_CAP_* - Bitmask flags for Mean Square Error (MSE) capabilities * * These flags describe which MSE metrics and selectors are implemented * by the PHY for the current link mode. They are used in * struct phy_mse_capability.supported_caps. * * Standardization: * The OPEN Alliance (OA) defines the presence of MSE/SQI/pMSE but not their * numeric scaling, update intervals, or aggregation windows. See: * OA 100BASE-T1 TC1 v1.0, sections 6.1.1-6.1.3 * OA 1000BASE-T1 TC12 v2.2, sections 6.1.1-6.1.2 * * Description of flags: * * PHY_MSE_CAP_CHANNEL_A * Per-pair diagnostics for Channel A are supported. Mapping to the * physical wire pair may depend on MDI/MDI-X polarity. * * PHY_MSE_CAP_CHANNEL_B, _C, _D * Same as above for channels B-D. * * PHY_MSE_CAP_WORST_CHANNEL * The PHY or driver can identify and report the single worst-performing * channel without querying each one individually. * * PHY_MSE_CAP_LINK * The PHY provides only a link-wide aggregate measurement or cannot map * results to a specific pair (for example 100BASE-TX with unknown * MDI/MDI-X). * * PHY_MSE_CAP_AVG * Average MSE (mean DCQ metric) is supported. For 100/1000BASE-T1 the OA * recommends 2^16 symbols, scaled 0..511, but the exact scaling is * vendor-specific. * * PHY_MSE_CAP_PEAK * Peak MSE (current peak within the measurement window) is supported. * Defined as pMSE for 100BASE-T1; vendor-specific for others. * * PHY_MSE_CAP_WORST_PEAK * Latched worst-case peak MSE since the last read (read-to-clear if * implemented). Optional in OA 100BASE-T1 TC1 6.1.3. */ #define PHY_MSE_CAP_CHANNEL_A BIT(0) #define PHY_MSE_CAP_CHANNEL_B BIT(1) #define PHY_MSE_CAP_CHANNEL_C BIT(2) #define PHY_MSE_CAP_CHANNEL_D BIT(3) #define PHY_MSE_CAP_WORST_CHANNEL BIT(4) #define PHY_MSE_CAP_LINK BIT(5) #define PHY_MSE_CAP_AVG BIT(6) #define PHY_MSE_CAP_PEAK BIT(7) #define PHY_MSE_CAP_WORST_PEAK BIT(8) /* * enum phy_mse_channel - Identifiers for selecting MSE measurement channels * * PHY_MSE_CHANNEL_A - PHY_MSE_CHANNEL_D * Select per-pair measurement for the corresponding channel. * * PHY_MSE_CHANNEL_WORST * Select the single worst-performing channel reported by hardware. * * PHY_MSE_CHANNEL_LINK * Select link-wide aggregate data (used when per-pair results are * unavailable). */ enum phy_mse_channel { PHY_MSE_CHANNEL_A, PHY_MSE_CHANNEL_B, PHY_MSE_CHANNEL_C, PHY_MSE_CHANNEL_D, PHY_MSE_CHANNEL_WORST, PHY_MSE_CHANNEL_LINK, }; /** * struct phy_mse_capability - Capabilities of Mean Square Error (MSE) * measurement interface * * Standardization notes: * * - Presence of MSE/SQI/pMSE is defined by OPEN Alliance specs, but numeric * scaling, refresh/update rate and aggregation windows are not fixed and * are vendor-/product-specific. (OA 100BASE-T1 TC1 v1.0 6.1.*; * OA 1000BASE-T1 TC12 v2.2 6.1.*) * * - Typical recommendations: 2^16 symbols and 0..511 scaling for MSE; pMSE only * defined for 100BASE-T1 (sliding window example), others are vendor * extensions. Drivers must report actual scale/limits here. * * Describes the MSE measurement capabilities for the current link mode. These * properties are dynamic and may change when link settings are modified. * Callers should re-query this capability after any link state change to * ensure they have the most up-to-date information. * * Callers should only request measurements for channels and types that are * indicated as supported by the @supported_caps bitmask. If @supported_caps * is 0, the device provides no MSE diagnostics, and driver operations should * typically return -EOPNOTSUPP. * * Snapshot values for average and peak MSE can be normalized to a 0..1 ratio * by dividing the raw snapshot by the corresponding @max_average_mse or * @max_peak_mse value. * * @max_average_mse: The maximum value for an average MSE snapshot. This * defines the scale for the measurement. If the PHY_MSE_CAP_AVG capability is * supported, this value MUST be greater than 0. (vendor-specific units). * @max_peak_mse: The maximum value for a peak MSE snapshot. If either * PHY_MSE_CAP_PEAK or PHY_MSE_CAP_WORST_PEAK is supported, this value MUST * be greater than 0. (vendor-specific units). * @refresh_rate_ps: The typical interval, in picoseconds, between hardware * updates of the MSE values. This is an estimate, and callers should not * assume synchronous sampling. (vendor-specific units). * @num_symbols: The number of symbols aggregated per hardware sample to * calculate the MSE. (vendor-specific units). * @supported_caps: A bitmask of PHY_MSE_CAP_* values indicating which * measurement types (e.g., average, peak) and channels * (e.g., per-pair or link-wide) are supported. */ struct phy_mse_capability { u64 max_average_mse; u64 max_peak_mse; u64 refresh_rate_ps; u64 num_symbols; u32 supported_caps; }; /** * struct phy_mse_snapshot - A snapshot of Mean Square Error (MSE) diagnostics * * Holds a set of MSE diagnostic values that were all captured from a single * measurement window. * * Values are raw, device-scaled and not normalized. Use struct * phy_mse_capability to interpret the scale and sampling window. * * @average_mse: The average MSE value over the measurement window. * OPEN Alliance references MSE as a DCQ metric; recommends 2^16 symbols and * 0..511 scaling. Exact scale and refresh are vendor-specific. * (100BASE-T1 TC1 v1.0 6.1.1; 1000BASE-T1 TC12 v2.2 6.1.1). * * @peak_mse: The peak MSE value observed within the measurement window. * For 100BASE-T1, "pMSE" is optional and may be implemented via a sliding * 128-symbol window with periodic capture; not standardized for 1000BASE-T1. * (100BASE-T1 TC1 v1.0 6.1.3, Table "DCQ.peakMSE"). * * @worst_peak_mse: A latched high-water mark of the peak MSE since last read * (read-to-clear if implemented). OPEN Alliance shows a latched "worst case * peak MSE" for 100BASE-T1 pMSE; availability/semantics outside that are * vendor-specific. (100BASE-T1 TC1 v1.0 6.1.3, DCQ.peakMSE high byte; * 1000BASE-T1 TC12 v2.2 treats DCQ details as vendor-specific.) */ struct phy_mse_snapshot { u64 average_mse; u64 peak_mse; u64 worst_peak_mse; }; /** * struct phy_driver - Driver structure for a particular PHY type * * @mdiodrv: Data common to all MDIO devices * @phy_id: The result of reading the UID registers of this PHY * type, and ANDing them with the phy_id_mask. This driver * only works for PHYs with IDs which match this field * @name: The friendly name of this PHY type * @phy_id_mask: Defines the important bits of the phy_id * @features: A mandatory list of features (speed, duplex, etc) * supported by this PHY * @flags: A bitfield defining certain other features this PHY * supports (like interrupts) * @driver_data: Static driver data * * All functions are optional. If config_aneg or read_status * are not implemented, the phy core uses the genphy versions. * Note that none of these functions should be called from * interrupt time. The goal is for the bus read/write functions * to be able to block when the bus transaction is happening, * and be freed up by an interrupt (The MPC85xx has this ability, * though it is not currently supported in the driver). */ struct phy_driver { struct mdio_driver_common mdiodrv; u32 phy_id; char *name; u32 phy_id_mask; const unsigned long * const features; u32 flags; const void *driver_data; /** * @soft_reset: Called to issue a PHY software reset */ int (*soft_reset)(struct phy_device *phydev); /** * @config_init: Called to initialize the PHY, * including after a reset */ int (*config_init)(struct phy_device *phydev); /** * @probe: Called during discovery. Used to set * up device-specific structures, if any */ int (*probe)(struct phy_device *phydev); /** * @get_features: Probe the hardware to determine what * abilities it has. Should only set phydev->supported. */ int (*get_features)(struct phy_device *phydev); /** * @inband_caps: query whether in-band is supported for the given PHY * interface mode. Returns a bitmask of bits defined by enum * link_inband_signalling. */ unsigned int (*inband_caps)(struct phy_device *phydev, phy_interface_t interface); /** * @config_inband: configure in-band mode for the PHY */ int (*config_inband)(struct phy_device *phydev, unsigned int modes); /** * @get_rate_matching: Get the supported type of rate matching for a * particular phy interface. This is used by phy consumers to determine * whether to advertise lower-speed modes for that interface. It is * assumed that if a rate matching mode is supported on an interface, * then that interface's rate can be adapted to all slower link speeds * supported by the phy. If the interface is not supported, this should * return %RATE_MATCH_NONE. */ int (*get_rate_matching)(struct phy_device *phydev, phy_interface_t iface); /* PHY Power Management */ /** @suspend: Suspend the hardware, saving state if needed */ int (*suspend)(struct phy_device *phydev); /** @resume: Resume the hardware, restoring state if needed */ int (*resume)(struct phy_device *phydev); /** * @config_aneg: Configures the advertisement and resets * autonegotiation if phydev->autoneg is on, * forces the speed to the current settings in phydev * if phydev->autoneg is off */ int (*config_aneg)(struct phy_device *phydev); /** @aneg_done: Determines the auto negotiation result */ int (*aneg_done)(struct phy_device *phydev); /** @read_status: Determines the negotiated speed and duplex */ int (*read_status)(struct phy_device *phydev); /** * @config_intr: Enables or disables interrupts. * It should also clear any pending interrupts prior to enabling the * IRQs and after disabling them. */ int (*config_intr)(struct phy_device *phydev); /** @handle_interrupt: Override default interrupt handling */ irqreturn_t (*handle_interrupt)(struct phy_device *phydev); /** @remove: Clears up any memory if needed */ void (*remove)(struct phy_device *phydev); /** * @match_phy_device: Returns true if this is a suitable * driver for the given phydev. If NULL, matching is based on * phy_id and phy_id_mask. */ int (*match_phy_device)(struct phy_device *phydev, const struct phy_driver *phydrv); /** * @set_wol: Some devices (e.g. qnap TS-119P II) require PHY * register changes to enable Wake on LAN, so set_wol is * provided to be called in the ethernet driver's set_wol * function. */ int (*set_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); /** * @get_wol: See set_wol, but for checking whether Wake on LAN * is enabled. */ void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); /** * @link_change_notify: Called to inform a PHY device driver * when the core is about to change the link state. This * callback is supposed to be used as fixup hook for drivers * that need to take action when the link state * changes. Drivers are by no means allowed to mess with the * PHY device structure in their implementations. */ void (*link_change_notify)(struct phy_device *dev); /** * @read_mmd: PHY specific driver override for reading a MMD * register. This function is optional for PHY specific * drivers. When not provided, the default MMD read function * will be used by phy_read_mmd(), which will use either a * direct read for Clause 45 PHYs or an indirect read for * Clause 22 PHYs. devnum is the MMD device number within the * PHY device, regnum is the register within the selected MMD * device. */ int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum); /** * @write_mmd: PHY specific driver override for writing a MMD * register. This function is optional for PHY specific * drivers. When not provided, the default MMD write function * will be used by phy_write_mmd(), which will use either a * direct write for Clause 45 PHYs, or an indirect write for * Clause 22 PHYs. devnum is the MMD device number within the * PHY device, regnum is the register within the selected MMD * device. val is the value to be written. */ int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum, u16 val); /** @read_page: Return the current PHY register page number */ int (*read_page)(struct phy_device *dev); /** @write_page: Set the current PHY register page number */ int (*write_page)(struct phy_device *dev, int page); /** * @module_info: Get the size and type of the eeprom contained * within a plug-in module */ int (*module_info)(struct phy_device *dev, struct ethtool_modinfo *modinfo); /** * @module_eeprom: Get the eeprom information from the plug-in * module */ int (*module_eeprom)(struct phy_device *dev, struct ethtool_eeprom *ee, u8 *data); /** @cable_test_start: Start a cable test */ int (*cable_test_start)(struct phy_device *dev); /** @cable_test_tdr_start: Start a raw TDR cable test */ int (*cable_test_tdr_start)(struct phy_device *dev, const struct phy_tdr_config *config); /** * @cable_test_get_status: Once per second, or on interrupt, * request the status of the test. */ int (*cable_test_get_status)(struct phy_device *dev, bool *finished); /* Get statistics from the PHY using ethtool */ /** * @get_phy_stats: Retrieve PHY statistics. * @dev: The PHY device for which the statistics are retrieved. * @eth_stats: structure where Ethernet PHY stats will be stored. * @stats: structure where additional PHY-specific stats will be stored. * * Retrieves the supported PHY statistics and populates the provided * structures. The input structures are pre-initialized with * `ETHTOOL_STAT_NOT_SET`, and the driver must only modify members * corresponding to supported statistics. Unmodified members will remain * set to `ETHTOOL_STAT_NOT_SET` and will not be returned to userspace. */ void (*get_phy_stats)(struct phy_device *dev, struct ethtool_eth_phy_stats *eth_stats, struct ethtool_phy_stats *stats); /** * @get_link_stats: Retrieve link statistics. * @dev: The PHY device for which the statistics are retrieved. * @link_stats: structure where link-specific stats will be stored. * * Retrieves link-related statistics for the given PHY device. The input * structure is pre-initialized with `ETHTOOL_STAT_NOT_SET`, and the * driver must only modify members corresponding to supported * statistics. Unmodified members will remain set to * `ETHTOOL_STAT_NOT_SET` and will not be returned to userspace. */ void (*get_link_stats)(struct phy_device *dev, struct ethtool_link_ext_stats *link_stats); /** * @update_stats: Trigger periodic statistics updates. * @dev: The PHY device for which statistics updates are triggered. * * Periodically gathers statistics from the PHY device to update locally * maintained 64-bit counters. This is necessary for PHYs that implement * reduced-width counters (e.g., 16-bit or 32-bit) which can overflow * more frequently compared to 64-bit counters. By invoking this * callback, drivers can fetch the current counter values, handle * overflow detection, and accumulate the results into local 64-bit * counters for accurate reporting through the `get_phy_stats` and * `get_link_stats` interfaces. * * Return: 0 on success or a negative error code on failure. */ int (*update_stats)(struct phy_device *dev); /** @get_sset_count: Number of statistic counters */ int (*get_sset_count)(struct phy_device *dev); /** @get_strings: Names of the statistic counters */ void (*get_strings)(struct phy_device *dev, u8 *data); /** @get_stats: Return the statistic counter values */ void (*get_stats)(struct phy_device *dev, struct ethtool_stats *stats, u64 *data); /** * @disable_autonomous_eee: Disable PHY-autonomous EEE * * Some PHYs manage EEE autonomously, preventing the MAC from * controlling LPI signaling. This callback disables autonomous * EEE at the PHY. * * Return: 0 on success, negative errno on failure. */ int (*disable_autonomous_eee)(struct phy_device *dev); /* Get and Set PHY tunables */ /** @get_tunable: Return the value of a tunable */ int (*get_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, void *data); /** @set_tunable: Set the value of a tunable */ int (*set_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, const void *data); /** * @set_loopback: Set the loopback mode of the PHY * enable selects if the loopback mode is enabled or disabled. If the * loopback mode is enabled, then the speed of the loopback mode can be * requested with the speed argument. If the speed argument is zero, * then any speed can be selected. If the speed argument is > 0, then * this speed shall be selected for the loopback mode or EOPNOTSUPP * shall be returned if speed selection is not supported. */ int (*set_loopback)(struct phy_device *dev, bool enable, int speed); /** @get_sqi: Get the signal quality indication */ int (*get_sqi)(struct phy_device *dev); /** @get_sqi_max: Get the maximum signal quality indication */ int (*get_sqi_max)(struct phy_device *dev); /** * @get_mse_capability: Get capabilities and scale of MSE measurement * @dev: PHY device * @cap: Output (filled on success) * * Fill @cap with the PHY's MSE capability for the current * link mode: scale limits (max_average_mse, max_peak_mse), update * interval (refresh_rate_ps), sample length (num_symbols) and the * capability bitmask (supported_caps). * * Implementations may defer capability report until hardware has * converged; in that case they should return -EAGAIN and allow the * caller to retry later. * * Return: 0 on success. On failure, returns a negative errno code, such * as -EOPNOTSUPP if MSE measurement is not supported by the PHY or in * the current link mode, or -EAGAIN if the capability information is * not yet available. */ int (*get_mse_capability)(struct phy_device *dev, struct phy_mse_capability *cap); /** * @get_mse_snapshot: Retrieve a snapshot of MSE diagnostic values * @dev: PHY device * @channel: Channel identifier (PHY_MSE_CHANNEL_*) * @snapshot: Output (filled on success) * * Fill @snapshot with a correlated set of MSE values from the most * recent measurement window. * * Callers must validate @channel against supported_caps returned by * get_mse_capability(). Drivers must not coerce @channel; if the * requested selector is not implemented by the device or current link * mode, the operation must fail. * * worst_peak_mse is latched and must be treated as read-to-clear. * * Return: 0 on success. On failure, returns a negative errno code, such * as -EOPNOTSUPP if MSE measurement is not supported by the PHY or in * the current link mode, or -EAGAIN if measurements are not yet * available. */ int (*get_mse_snapshot)(struct phy_device *dev, enum phy_mse_channel channel, struct phy_mse_snapshot *snapshot); /* PLCA RS interface */ /** @get_plca_cfg: Return the current PLCA configuration */ int (*get_plca_cfg)(struct phy_device *dev, struct phy_plca_cfg *plca_cfg); /** @set_plca_cfg: Set the PLCA configuration */ int (*set_plca_cfg)(struct phy_device *dev, const struct phy_plca_cfg *plca_cfg); /** @get_plca_status: Return the current PLCA status info */ int (*get_plca_status)(struct phy_device *dev, struct phy_plca_status *plca_st); /** * @led_brightness_set: Set a PHY LED brightness. Index * indicates which of the PHYs led should be set. Value * follows the standard LED class meaning, e.g. LED_OFF, * LED_HALF, LED_FULL. */ int (*led_brightness_set)(struct phy_device *dev, u8 index, enum led_brightness value); /** * @led_blink_set: Set a PHY LED blinking. Index indicates * which of the PHYs led should be configured to blink. Delays * are in milliseconds and if both are zero then a sensible * default should be chosen. The call should adjust the * timings in that case and if it can't match the values * specified exactly. */ int (*led_blink_set)(struct phy_device *dev, u8 index, unsigned long *delay_on, unsigned long *delay_off); /** * @led_hw_is_supported: Can the HW support the given rules. * @dev: PHY device which has the LED * @index: Which LED of the PHY device * @rules The core is interested in these rules * * Return 0 if yes, -EOPNOTSUPP if not, or an error code. */ int (*led_hw_is_supported)(struct phy_device *dev, u8 index, unsigned long rules); /** * @led_hw_control_set: Set the HW to control the LED * @dev: PHY device which has the LED * @index: Which LED of the PHY device * @rules The rules used to control the LED * * Returns 0, or a an error code. */ int (*led_hw_control_set)(struct phy_device *dev, u8 index, unsigned long rules); /** * @led_hw_control_get: Get how the HW is controlling the LED * @dev: PHY device which has the LED * @index: Which LED of the PHY device * @rules Pointer to the rules used to control the LED * * Set *@rules to how the HW is currently blinking. Returns 0 * on success, or a error code if the current blinking cannot * be represented in rules, or some other error happens. */ int (*led_hw_control_get)(struct phy_device *dev, u8 index, unsigned long *rules); /** * @led_polarity_set: Set the LED polarity modes * @dev: PHY device which has the LED * @index: Which LED of the PHY device * @modes: bitmap of LED polarity modes * * Configure LED with all the required polarity modes in @modes * to make it correctly turn ON or OFF. * * Returns 0, or an error code. */ int (*led_polarity_set)(struct phy_device *dev, int index, unsigned long modes); /** * @get_next_update_time: Get the time until the next update event * @dev: PHY device * * Callback to determine the time (in jiffies) until the next * update event for the PHY state machine. Allows PHY drivers to * dynamically adjust polling intervals based on link state or other * conditions. * * Returns the time in jiffies until the next update event. */ unsigned int (*get_next_update_time)(struct phy_device *dev); /** * @attach_mii_port: Attach the given MII port to the PHY device * @dev: PHY device to notify * @port: The port being added * * Called when an MII port that needs to be driven by the PHY is found. * * The port that is being passed may or may not be initialized. If it is * already initialized, it is by the generic port representation from * devicetree, which superseeds any strapping or vendor-specific * properties. * * If the port isn't initialized, the port->mediums and port->lanes * fields must be set, possibly according to strapping information. * * The PHY driver must set the port->interfaces field to indicate the * possible MII modes that this PHY can output on the port. * * Returns 0, or an error code. */ int (*attach_mii_port)(struct phy_device *dev, struct phy_port *port); /** * @attach_mdi_port: Attach the given MII port to the PHY device * @dev: PHY device to notify * @port: The port being added * * Called when a port that needs to be driven by the PHY is found. The * number of time this will be called depends on phydev->max_n_ports, * which the driver can change in .probe(). * * The port that is being passed may or may not be initialized. If it is * already initialized, it is by the generic port representation from * devicetree, which superseeds any strapping or vendor-specific * properties. * * If the port isn't initialized, the port->mediums and port->lanes * fields must be set, possibly according to strapping information. * * Returns 0, or an error code. */ int (*attach_mdi_port)(struct phy_device *dev, struct phy_port *port); }; #define to_phy_driver(d) container_of_const(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) #define PHY_ID_MATCH_EXTACT_MASK GENMASK(31, 0) #define PHY_ID_MATCH_MODEL_MASK GENMASK(31, 4) #define PHY_ID_MATCH_VENDOR_MASK GENMASK(31, 10) #define PHY_ID_MATCH_EXACT(id) .phy_id = (id), .phy_id_mask = PHY_ID_MATCH_EXTACT_MASK #define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = PHY_ID_MATCH_MODEL_MASK #define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = PHY_ID_MATCH_VENDOR_MASK /** * phy_id_compare - compare @id1 with @id2 taking account of @mask * @id1: first PHY ID * @id2: second PHY ID * @mask: the PHY ID mask, set bits are significant in matching * * Return true if the bits from @id1 and @id2 specified by @mask match. * This uses an equivalent test to (@id & @mask) == (@phy_id & @mask). */ static inline bool phy_id_compare(u32 id1, u32 id2, u32 mask) { return !((id1 ^ id2) & mask); } /** * phy_id_compare_vendor - compare @id with @vendor mask * @id: PHY ID * @vendor_mask: PHY Vendor mask * * Return: true if the bits from @id match @vendor using the * generic PHY Vendor mask. */ static inline bool phy_id_compare_vendor(u32 id, u32 vendor_mask) { return phy_id_compare(id, vendor_mask, PHY_ID_MATCH_VENDOR_MASK); } /** * phy_id_compare_model - compare @id with @model mask * @id: PHY ID * @model_mask: PHY Model mask * * Return: true if the bits from @id match @model using the * generic PHY Model mask. */ static inline bool phy_id_compare_model(u32 id, u32 model_mask) { return phy_id_compare(id, model_mask, PHY_ID_MATCH_MODEL_MASK); } /** * phydev_id_compare - compare @id with the PHY's Clause 22 ID * @phydev: the PHY device * @id: the PHY ID to be matched * * Compare the @phydev clause 22 ID with the provided @id and return true or * false depending whether it matches, using the bound driver mask. The * @phydev must be bound to a driver. */ static inline bool phydev_id_compare(struct phy_device *phydev, u32 id) { return phy_id_compare(id, phydev->phy_id, phydev->drv->phy_id_mask); } const char *phy_speed_to_str(int speed); const char *phy_duplex_to_str(unsigned int duplex); const char *phy_rate_matching_to_str(int rate_matching); int phy_interface_num_ports(phy_interface_t interface); /** * phy_is_started - Convenience function to check whether PHY is started * @phydev: The phy_device struct */ static inline bool phy_is_started(struct phy_device *phydev) { return phydev->state >= PHY_UP; } /** * phy_driver_is_genphy - Convenience function to check whether PHY is driven * by one of the generic PHY drivers * @phydev: The phy_device struct * Return: true if PHY is driven by one of the genphy drivers */ static inline bool phy_driver_is_genphy(struct phy_device *phydev) { return phydev->is_genphy_driven; } /** * phy_disable_eee_mode - Don't advertise an EEE mode. * @phydev: The phy_device struct * @link_mode: The EEE mode to be disabled */ static inline void phy_disable_eee_mode(struct phy_device *phydev, u32 link_mode) { WARN_ON(phy_is_started(phydev)); linkmode_set_bit(link_mode, phydev->eee_disabled_modes); linkmode_clear_bit(link_mode, phydev->advertising_eee); } /** * phy_can_wakeup() - indicate whether PHY has driver model wakeup capabilities * @phydev: The phy_device struct * * Returns: true/false depending on the PHY driver's device_set_wakeup_capable() * setting. */ static inline bool phy_can_wakeup(struct phy_device *phydev) { return device_can_wakeup(&phydev->mdio.dev); } /** * phy_may_wakeup() - indicate whether PHY has wakeup enabled * @phydev: The phy_device struct * * Returns: true/false depending on the PHY driver's device_set_wakeup_enabled() * setting if using the driver model, otherwise the legacy determination. */ bool phy_may_wakeup(struct phy_device *phydev); void phy_resolve_aneg_pause(struct phy_device *phydev); void phy_resolve_aneg_linkmode(struct phy_device *phydev); /** * phy_read - Convenience function for reading a given PHY register * @phydev: the phy_device struct * @regnum: register number to read * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. */ static inline int phy_read(struct phy_device *phydev, u32 regnum) { return mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, regnum); } #define phy_read_poll_timeout(phydev, regnum, val, cond, sleep_us, \ timeout_us, sleep_before_read) \ ({ \ int __ret, __val; \ __ret = read_poll_timeout(__val = phy_read, val, \ __val < 0 || (cond), \ sleep_us, timeout_us, sleep_before_read, phydev, regnum); \ if (__val < 0) \ __ret = __val; \ if (__ret) \ phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ __ret; \ }) /** * __phy_read - convenience function for reading a given PHY register * @phydev: the phy_device struct * @regnum: register number to read * * The caller must have taken the MDIO bus lock. */ static inline int __phy_read(struct phy_device *phydev, u32 regnum) { return __mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, regnum); } /** * phy_write - Convenience function for writing a given PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: value to write to @regnum * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. */ static inline int phy_write(struct phy_device *phydev, u32 regnum, u16 val) { return mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); } /** * __phy_write - Convenience function for writing a given PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: value to write to @regnum * * The caller must have taken the MDIO bus lock. */ static inline int __phy_write(struct phy_device *phydev, u32 regnum, u16 val) { return __mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); } /** * __phy_modify_changed() - Convenience function for modifying a PHY register * @phydev: a pointer to a &struct phy_device * @regnum: register number * @mask: bit mask of bits to clear * @set: bit mask of bits to set * * Unlocked helper function which allows a PHY register to be modified as * new register value = (old register value & ~mask) | set * * Returns negative errno, 0 if there was no change, and 1 in case of change */ static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) { return __mdiobus_modify_changed(phydev->mdio.bus, phydev->mdio.addr, regnum, mask, set); } /* * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. */ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); /** * phy_read_mmd_poll_timeout - Periodically poll a PHY register until a * condition is met or a timeout occurs * * @phydev: The phy_device struct * @devaddr: The MMD to read from * @regnum: The register on the MMD to read * @val: Variable to read the register into * @cond: Break condition (usually involving @val) * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please * read usleep_range() function description for details and * limitations. * @timeout_us: Timeout in us, 0 means never timeout * @sleep_before_read: if it is true, sleep @sleep_us before read. * * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either * case, the last read value at @args is stored in @val. Must not * be called from atomic context if sleep_us or timeout_us are used. */ #define phy_read_mmd_poll_timeout(phydev, devaddr, regnum, val, cond, \ sleep_us, timeout_us, sleep_before_read) \ ({ \ int __ret, __val; \ __ret = read_poll_timeout(__val = phy_read_mmd, val, \ __val < 0 || (cond), \ sleep_us, timeout_us, sleep_before_read, \ phydev, devaddr, regnum); \ if (__val < 0) \ __ret = __val; \ if (__ret) \ phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ __ret; \ }) /* * __phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. */ int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); /* * phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. */ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); /* * __phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. */ int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int __phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int __phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); /** * __phy_set_bits - Convenience function for setting bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to set * * The caller must have taken the MDIO bus lock. */ static inline int __phy_set_bits(struct phy_device *phydev, u32 regnum, u16 val) { return __phy_modify(phydev, regnum, 0, val); } /** * __phy_clear_bits - Convenience function for clearing bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to clear * * The caller must have taken the MDIO bus lock. */ static inline int __phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) { return __phy_modify(phydev, regnum, val, 0); } /** * phy_set_bits - Convenience function for setting bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to set */ static inline int phy_set_bits(struct phy_device *phydev, u32 regnum, u16 val) { return phy_modify(phydev, regnum, 0, val); } /** * phy_clear_bits - Convenience function for clearing bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to clear */ static inline int phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) { return phy_modify(phydev, regnum, val, 0); } /** * __phy_set_bits_mmd - Convenience function for setting bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to set * * The caller must have taken the MDIO bus lock. */ static inline int __phy_set_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return __phy_modify_mmd(phydev, devad, regnum, 0, val); } /** * __phy_clear_bits_mmd - Convenience function for clearing bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to clear * * The caller must have taken the MDIO bus lock. */ static inline int __phy_clear_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return __phy_modify_mmd(phydev, devad, regnum, val, 0); } /** * phy_set_bits_mmd - Convenience function for setting bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to set */ static inline int phy_set_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return phy_modify_mmd(phydev, devad, regnum, 0, val); } /** * phy_clear_bits_mmd - Convenience function for clearing bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to clear */ static inline int phy_clear_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return phy_modify_mmd(phydev, devad, regnum, val, 0); } /** * phy_interrupt_is_valid - Convenience function for testing a given PHY irq * @phydev: the phy_device struct * * NOTE: must be kept in sync with addition/removal of PHY_POLL and * PHY_MAC_INTERRUPT */ static inline bool phy_interrupt_is_valid(struct phy_device *phydev) { return phydev->irq != PHY_POLL && phydev->irq != PHY_MAC_INTERRUPT; } /** * phy_polling_mode - Convenience function for testing whether polling is * used to detect PHY status changes * @phydev: the phy_device struct */ static inline bool phy_polling_mode(struct phy_device *phydev) { if (phydev->state == PHY_CABLETEST) if (phydev->drv->flags & PHY_POLL_CABLE_TEST) return true; if (phydev->drv->update_stats) return true; return phydev->irq == PHY_POLL; } /** * phy_has_hwtstamp - Tests whether a PHY time stamp configuration. * @phydev: the phy_device struct */ static inline bool phy_has_hwtstamp(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->hwtstamp_set; } /** * phy_has_rxtstamp - Tests whether a PHY supports receive time stamping. * @phydev: the phy_device struct */ static inline bool phy_has_rxtstamp(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->rxtstamp; } /** * phy_has_tsinfo - Tests whether a PHY reports time stamping and/or * PTP hardware clock capabilities. * @phydev: the phy_device struct */ static inline bool phy_has_tsinfo(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->ts_info; } /** * phy_has_txtstamp - Tests whether a PHY supports transmit time stamping. * @phydev: the phy_device struct */ static inline bool phy_has_txtstamp(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->txtstamp; } static inline int phy_hwtstamp(struct phy_device *phydev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { return phydev->mii_ts->hwtstamp_set(phydev->mii_ts, cfg, extack); } static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { return phydev->mii_ts->rxtstamp(phydev->mii_ts, skb, type); } static inline int phy_ts_info(struct phy_device *phydev, struct kernel_ethtool_ts_info *tsinfo) { return phydev->mii_ts->ts_info(phydev->mii_ts, tsinfo); } static inline void phy_txtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { phydev->mii_ts->txtstamp(phydev->mii_ts, skb, type); } /** * phy_is_default_hwtstamp - Is the PHY hwtstamp the default timestamp * @phydev: Pointer to phy_device * * This is used to get default timestamping device taking into account * the new API choice, which is selecting the timestamping from MAC by * default if the phydev does not have default_timestamp flag enabled. * * Return: True if phy is the default hw timestamp, false otherwise. */ static inline bool phy_is_default_hwtstamp(struct phy_device *phydev) { return phy_has_hwtstamp(phydev) && phydev->default_timestamp; } /** * phy_on_sfp - Convenience function for testing if a PHY is on an SFP module * @phydev: the phy_device struct */ static inline bool phy_on_sfp(struct phy_device *phydev) { return phydev->is_on_sfp_module; } /** * phy_interface_mode_is_rgmii - Convenience function for testing if a * PHY interface mode is RGMII (all variants) * @mode: the &phy_interface_t enum */ static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode) { return mode >= PHY_INTERFACE_MODE_RGMII && mode <= PHY_INTERFACE_MODE_RGMII_TXID; }; /** * phy_interface_mode_is_8023z() - does the PHY interface mode use 802.3z * negotiation * @mode: one of &enum phy_interface_t * * Returns true if the PHY interface mode uses the 16-bit negotiation * word as defined in 802.3z. (See 802.3-2015 37.2.1 Config_Reg encoding) */ static inline bool phy_interface_mode_is_8023z(phy_interface_t mode) { return mode == PHY_INTERFACE_MODE_1000BASEX || mode == PHY_INTERFACE_MODE_2500BASEX; } /** * phy_interface_is_rgmii - Convenience function for testing if a PHY interface * is RGMII (all variants) * @phydev: the phy_device struct */ static inline bool phy_interface_is_rgmii(struct phy_device *phydev) { return phy_interface_mode_is_rgmii(phydev->interface); }; /** * phy_is_pseudo_fixed_link - Convenience function for testing if this * PHY is the CPU port facing side of an Ethernet switch, or similar. * @phydev: the phy_device struct */ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) { return phydev->is_pseudo_fixed_link; } phy_interface_t phy_fix_phy_mode_for_mac_delays(phy_interface_t interface, bool mac_txid, bool mac_rxid); int phy_save_page(struct phy_device *phydev); int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); int phy_read_paged(struct phy_device *phydev, int page, u32 regnum); int phy_write_paged(struct phy_device *phydev, int page, u32 regnum, u16 val); int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); void phy_device_remove(struct phy_device *phydev); int phy_get_c45_ids(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable, int speed); struct phy_device *phy_find_next(struct mii_bus *bus, struct phy_device *pos); int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, u32 flags, phy_interface_t interface); int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, void (*handler)(struct net_device *), phy_interface_t interface); struct phy_device *phy_connect(struct net_device *dev, const char *bus_id, void (*handler)(struct net_device *), phy_interface_t interface); void phy_disconnect(struct phy_device *phydev); void phy_detach(struct phy_device *phydev); void phy_start(struct phy_device *phydev); void phy_stop(struct phy_device *phydev); int phy_config_aneg(struct phy_device *phydev); int _phy_start_aneg(struct phy_device *phydev); int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); unsigned int phy_inband_caps(struct phy_device *phydev, phy_interface_t interface); int phy_config_inband(struct phy_device *phydev, unsigned int modes); int phy_speed_down(struct phy_device *phydev, bool sync); int phy_speed_up(struct phy_device *phydev); bool phy_check_valid(int speed, int duplex, unsigned long *features); int phy_restart_aneg(struct phy_device *phydev); int phy_reset_after_clk_enable(struct phy_device *phydev); static inline struct phy_device *phy_find_first(struct mii_bus *bus) { return phy_find_next(bus, NULL); } #define mdiobus_for_each_phy(_bus, _phydev) \ for (_phydev = phy_find_first(_bus); _phydev; \ _phydev = phy_find_next(_bus, _phydev)) #if IS_ENABLED(CONFIG_PHYLIB) int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack); int phy_start_cable_test_tdr(struct phy_device *phydev, struct netlink_ext_ack *extack, const struct phy_tdr_config *config); #else static inline int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; } static inline int phy_start_cable_test_tdr(struct phy_device *phydev, struct netlink_ext_ack *extack, const struct phy_tdr_config *config) { NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; } #endif static inline void phy_device_reset(struct phy_device *phydev, int value) { mdio_device_reset(&phydev->mdio, value); } #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) #define phydev_err_probe(_phydev, err, format, args...) \ dev_err_probe(&_phydev->mdio.dev, err, format, ##args) #define phydev_info(_phydev, format, args...) \ dev_info(&_phydev->mdio.dev, format, ##args) #define phydev_warn(_phydev, format, args...) \ dev_warn(&_phydev->mdio.dev, format, ##args) #define phydev_dbg(_phydev, format, args...) \ dev_dbg(&_phydev->mdio.dev, format, ##args) static inline const char *phydev_name(const struct phy_device *phydev) { return dev_name(&phydev->mdio.dev); } static inline void phy_lock_mdio_bus(struct phy_device *phydev) { mutex_lock(&phydev->mdio.bus->mdio_lock); } static inline void phy_unlock_mdio_bus(struct phy_device *phydev) { mutex_unlock(&phydev->mdio.bus->mdio_lock); } void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) __printf(2, 3); char *phy_attached_info_irq(struct phy_device *phydev) __malloc; void phy_attached_info(struct phy_device *phydev); int genphy_match_phy_device(struct phy_device *phydev, const struct phy_driver *phydrv); /* Clause 22 PHY */ int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart); int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); int genphy_read_lpa(struct phy_device *phydev); int genphy_read_status_fixed(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_read_master_slave(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_loopback(struct phy_device *phydev, bool enable, int speed); int genphy_soft_reset(struct phy_device *phydev); irqreturn_t genphy_handle_interrupt_no_ack(struct phy_device *phydev); static inline int genphy_config_aneg(struct phy_device *phydev) { return __genphy_config_aneg(phydev, false); } static inline int genphy_no_config_intr(struct phy_device *phydev) { return 0; } int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, u16 regnum); int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, u16 regnum, u16 val); /* Clause 37 */ int genphy_c37_config_aneg(struct phy_device *phydev); int genphy_c37_read_status(struct phy_device *phydev, bool *changed); /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart); int genphy_c45_aneg_done(struct phy_device *phydev); int genphy_c45_read_link(struct phy_device *phydev); int genphy_c45_read_lpa(struct phy_device *phydev); int genphy_c45_read_pma(struct phy_device *phydev); int genphy_c45_pma_setup_forced(struct phy_device *phydev); int genphy_c45_pma_baset1_setup_master_slave(struct phy_device *phydev); int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); int genphy_c45_pma_read_ext_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev); int genphy_c45_read_eee_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); int genphy_c45_baset1_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); int genphy_c45_loopback(struct phy_device *phydev, bool enable, int speed); int genphy_c45_pma_resume(struct phy_device *phydev); int genphy_c45_pma_suspend(struct phy_device *phydev); int genphy_c45_fast_retrain(struct phy_device *phydev, bool enable); int genphy_c45_plca_get_cfg(struct phy_device *phydev, struct phy_plca_cfg *plca_cfg); int genphy_c45_plca_set_cfg(struct phy_device *phydev, const struct phy_plca_cfg *plca_cfg); int genphy_c45_plca_get_status(struct phy_device *phydev, struct phy_plca_status *plca_st); int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *lp); int genphy_c45_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data); int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data); int genphy_c45_an_config_eee_aneg(struct phy_device *phydev); int genphy_c45_oatc14_cable_test_start(struct phy_device *phydev); int genphy_c45_oatc14_cable_test_get_status(struct phy_device *phydev, bool *finished); int genphy_c45_oatc14_get_sqi_max(struct phy_device *phydev); int genphy_c45_oatc14_get_sqi(struct phy_device *phydev); /* The gen10g_* functions are the old Clause 45 stub */ int gen10g_config_aneg(struct phy_device *phydev); static inline int phy_read_status(struct phy_device *phydev) { if (!phydev->drv) return -EIO; if (phydev->drv->read_status) return phydev->drv->read_status(phydev); else return genphy_read_status(phydev); } void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_error(struct phy_device *phydev); void phy_state_machine(struct work_struct *work); void phy_trigger_machine(struct phy_device *phydev); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd); int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_get_rate_matching(struct phy_device *phydev, phy_interface_t iface); void phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); void phy_advertise_eee_all(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); void phy_support_eee(struct phy_device *phydev); void phy_disable_eee(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); bool phy_validate_pause(struct phy_device *phydev, struct ethtool_pauseparam *pp); void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause); s32 phy_get_internal_delay(struct phy_device *phydev, const int *delay_values, int size, bool is_rx); int phy_get_tx_amplitude_gain(struct phy_device *phydev, struct device *dev, enum ethtool_link_mode_bit_indices linkmode, u32 *val); int phy_get_mac_termination(struct phy_device *phydev, struct device *dev, u32 *val); void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv, bool *tx_pause, bool *rx_pause); int phy_register_fixup_for_id(const char *bus_id, int (*run)(struct phy_device *)); int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); int phy_eee_tx_clock_stop_capable(struct phy_device *phydev); int phy_eee_rx_clock_stop(struct phy_device *phydev, bool clk_stop_enable); int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data); int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data); int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); void phy_ethtool_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); int phy_ethtool_get_link_ksettings(struct net_device *ndev, struct ethtool_link_ksettings *cmd); int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); int phy_ethtool_get_stats(struct phy_device *phydev, struct ethtool_stats *stats, u64 *data); void __phy_ethtool_get_phy_stats(struct phy_device *phydev, struct ethtool_eth_phy_stats *phy_stats, struct ethtool_phy_stats *phydev_stats); void __phy_ethtool_get_link_ext_stats(struct phy_device *phydev, struct ethtool_link_ext_stats *link_stats); int phy_ethtool_get_plca_cfg(struct phy_device *phydev, struct phy_plca_cfg *plca_cfg); int phy_ethtool_set_plca_cfg(struct phy_device *phydev, const struct phy_plca_cfg *plca_cfg, struct netlink_ext_ack *extack); int phy_ethtool_get_plca_status(struct phy_device *phydev, struct phy_plca_status *plca_st); int __phy_hwtstamp_get(struct phy_device *phydev, struct kernel_hwtstamp_config *config); int __phy_hwtstamp_set(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); struct phy_port *phy_get_sfp_port(struct phy_device *phydev); /** * phy_module_driver() - Helper macro for registering PHY drivers * @__phy_drivers: array of PHY drivers to register * @__count: Numbers of members in array * * Helper macro for PHY drivers which do not do anything special in module * init/exit. Each module may only use this macro once, and calling it * replaces module_init() and module_exit(). */ #define phy_module_driver(__phy_drivers, __count) \ static int __init phy_module_init(void) \ { \ return phy_drivers_register(__phy_drivers, __count, THIS_MODULE); \ } \ module_init(phy_module_init); \ static void __exit phy_module_exit(void) \ { \ phy_drivers_unregister(__phy_drivers, __count); \ } \ module_exit(phy_module_exit) #define module_phy_driver(__phy_drivers) \ phy_module_driver(__phy_drivers, ARRAY_SIZE(__phy_drivers)) #endif /* __PHY_H */ |
| 30 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NFS internal definitions */ #include "nfs4_fs.h" #include <linux/fs_context.h> #include <linux/security.h> #include <linux/compiler_attributes.h> #include <linux/crc32.h> #include <linux/sunrpc/addr.h> #include <linux/nfs_page.h> #include <linux/nfslocalio.h> #include <linux/wait_bit.h> #define NFS_SB_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) extern const struct export_operations nfs_export_ops; struct nfs_string; struct nfs_pageio_descriptor; static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr) { if (!nfs_fsid_equal(&NFS_SB(parent)->fsid, &fattr->fsid)) fattr->valid |= NFS_ATTR_FATTR_MOUNTPOINT; } static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr) { if (((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) == 0) || (((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) && ((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0))) return 0; return 1; } static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) { if (!(NFS_SB(dentry->d_sb)->flags & NFS_MOUNT_SOFTREVAL)) return false; if (!d_is_positive(dentry) || !NFS_FH(d_inode(dentry))->size) return false; return true; } static inline fmode_t flags_to_mode(int flags) { fmode_t res = (__force fmode_t)flags & FMODE_EXEC; if ((flags & O_ACCMODE) != O_WRONLY) res |= FMODE_READ; if ((flags & O_ACCMODE) != O_RDONLY) res |= FMODE_WRITE; return res; } /* * Note: RFC 1813 doesn't limit the number of auth flavors that * a server can return, so make something up. */ #define NFS_MAX_SECFLAVORS (12) /* * Value used if the user did not specify a port value. */ #define NFS_UNSPEC_PORT (-1) #define NFS_UNSPEC_RETRANS (UINT_MAX) #define NFS_UNSPEC_TIMEO (UINT_MAX) struct nfs_client_initdata { unsigned long init_flags; const char *hostname; /* Hostname of the server */ const struct sockaddr_storage *addr; /* Address of the server */ const char *nodename; /* Hostname of the client */ const char *ip_addr; /* IP address of the client */ size_t addrlen; struct nfs_subversion *nfs_mod; int proto; u32 minorversion; unsigned int nconnect; unsigned int max_connect; struct net *net; const struct rpc_timeout *timeparms; const struct cred *cred; struct xprtsec_parms xprtsec; unsigned long connect_timeout; unsigned long reconnect_timeout; }; /* * In-kernel mount arguments */ struct nfs_fs_context { bool internal; bool skip_reconfig_option_check; bool need_mount; bool sloppy; unsigned int flags; /* NFS{,4}_MOUNT_* flags */ unsigned int rsize, wsize; unsigned int timeo, retrans; unsigned int acregmin, acregmax; unsigned int acdirmin, acdirmax; unsigned int namlen; unsigned int options; unsigned int bsize; struct nfs_auth_info auth_info; rpc_authflavor_t selected_flavor; struct xprtsec_parms xprtsec; char *client_address; unsigned int version; unsigned int minorversion; char *fscache_uniq; unsigned short protofamily; unsigned short mountfamily; bool has_sec_mnt_opts; int lock_status; struct { union { struct sockaddr address; struct sockaddr_storage _address; }; size_t addrlen; char *hostname; u32 version; int port; unsigned short protocol; } mount_server; struct { union { struct sockaddr address; struct sockaddr_storage _address; }; size_t addrlen; char *hostname; char *export_path; int port; unsigned short protocol; unsigned short nconnect; unsigned short max_connect; unsigned short export_path_len; } nfs_server; struct nfs_fh *mntfh; struct nfs_server *server; struct nfs_subversion *nfs_mod; /* Information for a cloned mount. */ struct nfs_clone_mount { struct super_block *sb; struct dentry *dentry; struct nfs_fattr *fattr; } clone_data; }; enum nfs_lock_status { NFS_LOCK_NOT_SET = 0, NFS_LOCK_LOCK = 1, NFS_LOCK_NOLOCK = 2, }; #define nfs_errorf(fc, fmt, ...) ((fc)->log.log ? \ errorf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); })) #define nfs_ferrorf(fc, fac, fmt, ...) ((fc)->log.log ? \ errorf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) #define nfs_invalf(fc, fmt, ...) ((fc)->log.log ? \ invalf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); -EINVAL; })) #define nfs_finvalf(fc, fac, fmt, ...) ((fc)->log.log ? \ invalf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); -EINVAL; })) #define nfs_warnf(fc, fmt, ...) ((fc)->log.log ? \ warnf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); })) #define nfs_fwarnf(fc, fac, fmt, ...) ((fc)->log.log ? \ warnf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc) { return fc->fs_private; } /* mount_clnt.c */ struct nfs_mount_request { struct sockaddr_storage *sap; size_t salen; char *hostname; char *dirpath; u32 version; unsigned short protocol; struct nfs_fh *fh; int noresvport; unsigned int *auth_flav_len; rpc_authflavor_t *auth_flavs; struct net *net; }; extern int nfs_mount(struct nfs_mount_request *info, int timeo, int retrans); /* client.c */ extern const struct rpc_program nfs_program; extern void nfs_clients_init(struct net *net); extern void nfs_clients_exit(struct net *net); extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *); int nfs_create_rpc_client(struct nfs_client *, const struct nfs_client_initdata *, rpc_authflavor_t); struct nfs_client *nfs_get_client(const struct nfs_client_initdata *); int nfs_probe_server(struct nfs_server *, struct nfs_fh *); void nfs_server_insert_lists(struct nfs_server *); void nfs_server_remove_lists(struct nfs_server *); void nfs_init_timeout_values(struct rpc_timeout *to, int proto, int timeo, int retrans); int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t, rpc_authflavor_t); struct nfs_server *nfs_alloc_server(void); void nfs_server_copy_userdata(struct nfs_server *, struct nfs_server *); extern void nfs_put_client(struct nfs_client *); extern void nfs_free_client(struct nfs_client *); extern struct nfs_client *nfs4_find_client_ident(struct net *, int); extern struct nfs_client * nfs4_find_client_sessionid(struct net *, const struct sockaddr *, struct nfs4_sessionid *, u32); extern struct nfs_server *nfs_create_server(struct fs_context *); extern void nfs_server_set_init_caps(struct nfs_server *); extern struct nfs_server *nfs4_create_server(struct fs_context *); extern struct nfs_server *nfs4_create_referral_server(struct fs_context *); extern int nfs4_update_server(struct nfs_server *server, const char *hostname, struct sockaddr_storage *sap, size_t salen, struct net *net); extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); extern bool nfs_client_init_is_complete(const struct nfs_client *clp); extern int nfs_client_init_status(const struct nfs_client *clp); extern int nfs_wait_client_init_complete(const struct nfs_client *clp); extern void nfs_mark_client_ready(struct nfs_client *clp, int state); extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, u32 minor_version); extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, struct inode *); extern void nfs4_session_limit_rwsize(struct nfs_server *server); extern void nfs4_session_limit_xasize(struct nfs_server *server); extern struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans); #ifdef CONFIG_PROC_FS extern int __init nfs_fs_proc_init(void); extern void nfs_fs_proc_exit(void); extern int nfs_fs_proc_net_init(struct net *net); extern void nfs_fs_proc_net_exit(struct net *net); #else static inline int nfs_fs_proc_net_init(struct net *net) { return 0; } static inline void nfs_fs_proc_net_exit(struct net *net) { } static inline int nfs_fs_proc_init(void) { return 0; } static inline void nfs_fs_proc_exit(void) { } #endif /* callback_xdr.c */ extern const struct svc_version nfs4_callback_version1; extern const struct svc_version nfs4_callback_version4; /* fs_context.c */ extern struct file_system_type nfs_fs_type; /* pagelist.c */ extern int __init nfs_init_nfspagecache(void); extern void nfs_destroy_nfspagecache(void); extern int __init nfs_init_readpagecache(void); extern void nfs_destroy_readpagecache(void); extern int __init nfs_init_writepagecache(void); extern void nfs_destroy_writepagecache(void); extern int __init nfs_init_directcache(void); extern void nfs_destroy_directcache(void); extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); int nfs_iocounter_wait(struct nfs_lock_context *l_ctx); extern const struct nfs_pageio_ops nfs_pgio_rw_ops; struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); void nfs_pgio_header_free(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, const struct cred *cred, const struct nfs_rpc_ops *rpc_ops, const struct rpc_call_ops *call_ops, int how, int flags, struct nfsd_file *localio); void nfs_free_request(struct nfs_page *req); struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1, const struct nfs_open_context *ctx2) { return cred_fscmp(ctx1->cred, ctx2->cred) == 0 && ctx1->state == ctx2->state; } /* nfs2xdr.c */ extern const struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); /* nfs3xdr.c */ extern const struct rpc_procinfo nfs3_procedures[]; extern int nfs3_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); /* nfs4xdr.c */ #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); extern const u32 nfs41_maxread_overhead; extern const u32 nfs41_maxwrite_overhead; extern const u32 nfs41_maxgetdevinfo_overhead; /* nfs4proc.c */ extern const struct rpc_procinfo nfs4_procedures[]; #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_V4_SECURITY_LABEL extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); static inline struct nfs4_label * nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) { if (!dst || !src) return NULL; if (src->len > NFS4_MAXLABELLEN) return NULL; dst->lfs = src->lfs; dst->pi = src->pi; dst->len = src->len; memcpy(dst->label, src->label, src->len); return dst; } static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL)) nfsi->cache_validity |= NFS_INO_INVALID_LABEL; } #else static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { } static inline struct nfs4_label * nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) { return NULL; } #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ /* proc.c */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync); extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); /* dir.c */ extern void nfs_readdir_record_entry_cache_hit(struct inode *dir); extern void nfs_readdir_record_entry_cache_miss(struct inode *dir); extern unsigned long nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc); extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc); struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); void nfs_d_prune_case_insensitive_aliases(struct inode *inode); int nfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); struct dentry *nfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int nfs_rmdir(struct inode *, struct dentry *); int nfs_unlink(struct inode *, struct dentry *); int nfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); int nfs_link(struct dentry *, struct inode *, struct dentry *); int nfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int nfs_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); #ifdef CONFIG_NFS_V4_2 static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) { if (!(server->caps & NFS_CAP_XATTR)) return 0; return NFS4_ACCESS_XAREAD | NFS4_ACCESS_XAWRITE | NFS4_ACCESS_XALIST; } #else static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) { return 0; } #endif /* file.c */ int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); loff_t nfs_file_llseek(struct file *, loff_t, int); ssize_t nfs_file_read(struct kiocb *, struct iov_iter *); ssize_t nfs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); int nfs_file_mmap_prepare(struct vm_area_desc *); ssize_t nfs_file_write(struct kiocb *, struct iov_iter *); int nfs_file_release(struct inode *, struct file *); int nfs_lock(struct file *, int, struct file_lock *); int nfs_flock(struct file *, int, struct file_lock *); int nfs_check_flags(int); void nfs_truncate_last_folio(struct address_space *mapping, loff_t from, loff_t to); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; extern struct workqueue_struct *nfslocaliod_workqueue; extern struct inode *nfs_alloc_inode(struct super_block *sb); extern void nfs_free_inode(struct inode *); extern int nfs_write_inode(struct inode *, struct writeback_control *); extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); extern void nfs_zap_acl_cache(struct inode *inode); extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags); extern bool nfs_check_cache_invalid(struct inode *, unsigned long); extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); struct file_kattr; int nfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa); #if IS_ENABLED(CONFIG_NFS_LOCALIO) /* localio.c */ struct nfs_local_dio { u32 mem_align; u32 offset_align; loff_t middle_offset; loff_t end_offset; ssize_t start_len; /* Length for misaligned first extent */ ssize_t middle_len; /* Length for DIO-aligned middle extent */ ssize_t end_len; /* Length for misaligned last extent */ }; extern void nfs_local_probe_async(struct nfs_client *); extern void nfs_local_probe_async_work(struct work_struct *); extern struct nfsd_file *nfs_local_open_fh(struct nfs_client *, const struct cred *, struct nfs_fh *, struct nfs_file_localio *, const fmode_t); extern int nfs_local_doio(struct nfs_client *, struct nfsd_file *, struct nfs_pgio_header *, const struct rpc_call_ops *); extern int nfs_local_commit(struct nfsd_file *, struct nfs_commit_data *, const struct rpc_call_ops *, int); extern bool nfs_server_is_local(const struct nfs_client *clp); #else /* CONFIG_NFS_LOCALIO */ static inline void nfs_local_probe(struct nfs_client *clp) {} static inline void nfs_local_probe_async(struct nfs_client *clp) {} static inline struct nfsd_file * nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, struct nfs_fh *fh, struct nfs_file_localio *nfl, const fmode_t mode) { return NULL; } static inline int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio, struct nfs_pgio_header *hdr, const struct rpc_call_ops *call_ops) { return -EINVAL; } static inline int nfs_local_commit(struct nfsd_file *localio, struct nfs_commit_data *data, const struct rpc_call_ops *call_ops, int how) { return -EINVAL; } static inline bool nfs_server_is_local(const struct nfs_client *clp) { return false; } #endif /* CONFIG_NFS_LOCALIO */ /* super.c */ extern const struct super_operations nfs_sops; bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); int nfs_try_get_tree(struct fs_context *); int nfs_get_tree_common(struct fs_context *); void nfs_kill_super(struct super_block *); extern int __init register_nfs_fs(void); extern void __exit unregister_nfs_fs(void); extern bool nfs_sb_active(struct super_block *sb); extern void nfs_sb_deactive(struct super_block *sb); extern int nfs_client_for_each_server(struct nfs_client *clp, int (*fn)(struct nfs_server *, void *), void *data); #ifdef CONFIG_NFS_FSCACHE extern const struct netfs_request_ops nfs_netfs_ops; #endif /* io.c */ extern __must_check int nfs_start_io_read(struct inode *inode); extern void nfs_end_io_read(struct inode *inode); extern __must_check int nfs_start_io_write(struct inode *inode); extern void nfs_end_io_write(struct inode *inode); extern __must_check int nfs_start_io_direct(struct inode *inode); extern __must_check int nfs_start_io_direct_nowait(struct inode *inode); extern void nfs_end_io_direct(struct inode *inode); static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi) { return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0; } /* Must be called with exclusively locked inode->i_rwsem */ static inline void nfs_file_block_o_direct(struct nfs_inode *nfsi) { if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) { clear_bit(NFS_INO_ODIRECT, &nfsi->flags); inode_dio_wait(&nfsi->vfs_inode); } } /* namespace.c */ #define NFS_PATH_CANONICAL 1 extern char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen, unsigned flags); extern struct vfsmount *nfs_d_automount(struct path *path); int nfs_submount(struct fs_context *, struct nfs_server *); int nfs_do_submount(struct fs_context *); /* getroot.c */ extern int nfs_get_root(struct super_block *s, struct fs_context *fc); #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool); #endif struct nfs_pgio_completion_ops; /* read.c */ extern const struct nfs_pgio_completion_ops nfs_async_read_completion_ops; extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); extern bool nfs_read_alloc_scratch(struct nfs_pgio_header *hdr, size_t size); extern int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, struct nfs_open_context *ctx, struct folio *folio); extern void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); /* super.c */ void nfs_umount_begin(struct super_block *); int nfs_statfs(struct dentry *, struct kstatfs *); int nfs_show_options(struct seq_file *, struct dentry *); int nfs_show_devname(struct seq_file *, struct dentry *); int nfs_show_path(struct seq_file *, struct dentry *); int nfs_show_stats(struct seq_file *, struct dentry *); int nfs_reconfigure(struct fs_context *); /* write.c */ extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_commit_free(struct nfs_commit_data *p); extern void nfs_commit_prepare(struct rpc_task *task, void *calldata); extern int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, const struct nfs_rpc_ops *nfs_ops, const struct rpc_call_ops *call_ops, int how, int flags, struct nfsd_file *localio); extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo); int nfs_scan_commit_list(struct list_head *src, struct list_head *dst, struct nfs_commit_info *cinfo, int max); unsigned long nfs_reqs_to_commit(struct nfs_commit_info *); int nfs_scan_commit(struct inode *inode, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo, u32 ds_commit_idx); int nfs_write_need_commit(struct nfs_pgio_header *); void nfs_writeback_update_inode(struct nfs_pgio_header *hdr); int nfs_generic_commit_list(struct inode *inode, struct list_head *head, int how, struct nfs_commit_info *cinfo); void nfs_retry_commit(struct list_head *page_list, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo, u32 ds_commit_idx); void nfs_commitdata_release(struct nfs_commit_data *data); void nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo); void nfs_request_add_commit_list_locked(struct nfs_page *req, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_request_remove_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo); void nfs_init_cinfo(struct nfs_commit_info *cinfo, struct inode *inode, struct nfs_direct_req *dreq); int nfs_key_timeout_notify(struct file *filp, struct inode *inode); bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode); void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio); int nfs_filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); #ifdef CONFIG_NFS_V4 static inline void pnfs_bucket_clear_pnfs_ds_commit_verifiers(struct pnfs_commit_bucket *buckets, unsigned int nbuckets) { unsigned int i; for (i = 0; i < nbuckets; i++) buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW; } static inline void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo) { struct pnfs_commit_array *array; rcu_read_lock(); list_for_each_entry_rcu(array, &cinfo->commits, cinfo_list) pnfs_bucket_clear_pnfs_ds_commit_verifiers(array->buckets, array->nbuckets); rcu_read_unlock(); } #else /* CONFIG_NFS_V4 */ static inline void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo) { } #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_MIGRATION int nfs_migrate_folio(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); #else #define nfs_migrate_folio NULL #endif static inline int nfs_write_verifier_cmp(const struct nfs_write_verifier *v1, const struct nfs_write_verifier *v2) { return memcmp(v1->data, v2->data, sizeof(v1->data)); } static inline bool nfs_write_match_verf(const struct nfs_writeverf *verf, struct nfs_page *req) { return verf->committed > NFS_UNSTABLE && !nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier); } static inline gfp_t nfs_io_gfp_mask(void) { gfp_t ret = current_gfp_context(GFP_KERNEL); /* For workers __GFP_NORETRY only with __GFP_IO or __GFP_FS */ if ((current->flags & PF_WQ_WORKER) && ret == GFP_KERNEL) ret |= __GFP_NORETRY | __GFP_NOWARN; return ret; } /* * Special version of should_remove_suid() that ignores capabilities. */ static inline int nfs_should_remove_suid(const struct inode *inode) { umode_t mode = inode->i_mode; int kill = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; /* * sgid without any exec bits is just a mandatory locking mark; leave * it alone. If some exec bits are set, it's a real sgid; kill it. */ if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) kill |= ATTR_KILL_SGID; if (unlikely(kill && S_ISREG(mode))) return kill; return 0; } /* unlink.c */ extern struct rpc_task * nfs_async_rename(struct inode *old_dir, struct inode *new_dir, struct dentry *old_dentry, struct dentry *new_dentry, void (*complete)(struct rpc_task *, struct nfs_renamedata *)); extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry); /* direct.c */ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, struct nfs_direct_req *dreq); extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq, loff_t offset); /* nfs4proc.c */ extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); extern int nfs41_walk_client_list(struct nfs_client *clp, struct nfs_client **result, const struct cred *cred); extern void nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *data); static inline struct inode *nfs_igrab_and_active(struct inode *inode) { struct super_block *sb = inode->i_sb; if (sb && nfs_sb_active(sb)) { if (igrab(inode)) return inode; nfs_sb_deactive(sb); } return NULL; } static inline void nfs_iput_and_deactive(struct inode *inode) { if (inode != NULL) { struct super_block *sb = inode->i_sb; iput(inode); nfs_sb_deactive(sb); } } /* * Determine the device name as a string */ static inline char *nfs_devname(struct dentry *dentry, char *buffer, ssize_t buflen) { char *dummy; return nfs_path(&dummy, dentry, buffer, buflen, NFS_PATH_CANONICAL); } /* * Determine the actual block size (and log2 thereof) */ static inline unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp) { /* make sure blocksize is a power of two */ if ((bsize & (bsize - 1)) || nrbitsp) { unsigned char nrbits; for (nrbits = 31; nrbits && !(bsize & (1UL << nrbits)); nrbits--) ; bsize = 1UL << nrbits; if (nrbitsp) *nrbitsp = nrbits; } return bsize; } /* * Calculate the number of 512byte blocks used. */ static inline blkcnt_t nfs_calc_block_size(u64 tsize) { blkcnt_t used = (tsize + 511) >> 9; return (used > ULONG_MAX) ? ULONG_MAX : used; } /* * Compute and set NFS server blocksize */ static inline unsigned long nfs_block_size(unsigned long bsize, unsigned char *nrbitsp) { if (bsize < NFS_MIN_FILE_IO_SIZE) bsize = NFS_DEF_FILE_IO_SIZE; else if (bsize >= NFS_MAX_FILE_IO_SIZE) bsize = NFS_MAX_FILE_IO_SIZE; return nfs_block_bits(bsize, nrbitsp); } /* * Compute and set NFS server rsize / wsize */ static inline unsigned long nfs_io_size(unsigned long iosize, enum xprt_transports proto) { if (iosize < NFS_MIN_FILE_IO_SIZE) iosize = NFS_DEF_FILE_IO_SIZE; else if (iosize >= NFS_MAX_FILE_IO_SIZE) iosize = NFS_MAX_FILE_IO_SIZE; if (proto == XPRT_TRANSPORT_UDP || iosize < PAGE_SIZE) return nfs_block_bits(iosize, NULL); return iosize & PAGE_MASK; } /* * Determine the maximum file size for a superblock */ static inline void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize) { sb->s_maxbytes = (loff_t)maxfilesize; if (sb->s_maxbytes > MAX_LFS_FILESIZE || sb->s_maxbytes <= 0) sb->s_maxbytes = MAX_LFS_FILESIZE; } /* * Record the page as unstable (an extra writeback period) and mark its * inode as dirty. */ static inline void nfs_folio_mark_unstable(struct folio *folio, struct nfs_commit_info *cinfo) { if (folio && !cinfo->dreq) { struct inode *inode = folio->mapping->host; long nr = folio_nr_pages(folio); /* This page is really still in write-back - just that the * writeback is happening on the server now. */ node_stat_mod_folio(folio, NR_WRITEBACK, nr); bdi_wb_stat_mod(inode, WB_WRITEBACK, nr); __mark_inode_dirty(inode, I_DIRTY_DATASYNC); } } /* * Determine the number of bytes of data the page contains */ static inline size_t nfs_folio_length(struct folio *folio) { loff_t i_size = i_size_read(folio->mapping->host); if (i_size > 0) { pgoff_t index = folio->index >> folio_order(folio); pgoff_t end_index = (i_size - 1) >> folio_shift(folio); if (index < end_index) return folio_size(folio); if (index == end_index) return offset_in_folio(folio, i_size - 1) + 1; } return 0; } /* * Convert a umode to a dirent->d_type */ static inline unsigned char nfs_umode_to_dtype(umode_t mode) { return (mode >> 12) & 15; } /* * Determine the number of pages in an array of length 'len' and * with a base offset of 'base' */ static inline unsigned int nfs_page_array_len(unsigned int base, size_t len) { return ((unsigned long)len + (unsigned long)base + PAGE_SIZE - 1) >> PAGE_SHIFT; } /* * Convert a struct timespec64 into a 64-bit change attribute * * This does approximately the same thing as timespec64_to_ns(), * but for calculation efficiency, we multiply the seconds by * 1024*1024*1024. */ static inline u64 nfs_timespec_to_change_attr(const struct timespec64 *ts) { return ((u64)ts->tv_sec << 30) + ts->tv_nsec; } static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid) { return ~crc32_le(0xFFFFFFFF, &stateid->other[0], NFS4_STATEID_OTHER_SIZE); } static inline bool nfs_current_task_exiting(void) { return (current->flags & PF_EXITING) != 0; } static inline bool nfs_error_is_fatal(int err) { switch (err) { case -ERESTARTSYS: case -EINTR: case -EACCES: case -EDQUOT: case -EFBIG: case -EIO: case -ENOSPC: case -EROFS: case -ESTALE: case -E2BIG: case -ENOMEM: case -ETIMEDOUT: return true; default: return false; } } static inline bool nfs_error_is_fatal_on_server(int err) { switch (err) { case 0: case -ERESTARTSYS: case -EINTR: case -ENOMEM: return false; } return nfs_error_is_fatal(err); } /* * Select between a default port value and a user-specified port value. * If a zero value is set, then autobind will be used. */ static inline void nfs_set_port(struct sockaddr_storage *sap, int *port, const unsigned short default_port) { if (*port == NFS_UNSPEC_PORT) *port = default_port; rpc_set_port((struct sockaddr *)sap, *port); } struct nfs_direct_req { struct kref kref; /* release manager */ /* I/O parameters */ struct nfs_open_context *ctx; /* file open context info */ struct nfs_lock_context *l_ctx; /* Lock context info */ struct kiocb * iocb; /* controlling i/o request */ struct inode * inode; /* target file of i/o */ /* completion state */ atomic_t io_count; /* i/os we're waiting for */ spinlock_t lock; /* protect completion state */ loff_t io_start; /* Start offset for I/O */ ssize_t count, /* bytes actually processed */ max_count, /* max expected count */ error; /* any reported error */ struct completion completion; /* wait for i/o completion */ /* commit state */ struct nfs_mds_commit_info mds_cinfo; /* Storage for cinfo */ struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */ struct work_struct work; int flags; /* for write */ #define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */ #define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */ /* for read */ #define NFS_ODIRECT_SHOULD_DIRTY (3) /* dirty user-space page after read */ #define NFS_ODIRECT_DONE INT_MAX /* write verification failed */ }; |
| 612 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Asynchronous Compression operations * * Copyright (c) 2016, Intel Corporation * Authors: Weigang Li <weigang.li@intel.com> * Giovanni Cabiddu <giovanni.cabiddu@intel.com> */ #ifndef _CRYPTO_ACOMP_H #define _CRYPTO_ACOMP_H #include <linux/atomic.h> #include <linux/args.h> #include <linux/compiler_types.h> #include <linux/container_of.h> #include <linux/crypto.h> #include <linux/err.h> #include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/spinlock_types.h> #include <linux/types.h> /* Set this bit if source is virtual address instead of SG list. */ #define CRYPTO_ACOMP_REQ_SRC_VIRT 0x00000002 /* Set this bit for if virtual address source cannot be used for DMA. */ #define CRYPTO_ACOMP_REQ_SRC_NONDMA 0x00000004 /* Set this bit if destination is virtual address instead of SG list. */ #define CRYPTO_ACOMP_REQ_DST_VIRT 0x00000008 /* Set this bit for if virtual address destination cannot be used for DMA. */ #define CRYPTO_ACOMP_REQ_DST_NONDMA 0x00000010 /* Private flags that should not be touched by the user. */ #define CRYPTO_ACOMP_REQ_PRIVATE \ (CRYPTO_ACOMP_REQ_SRC_VIRT | CRYPTO_ACOMP_REQ_SRC_NONDMA | \ CRYPTO_ACOMP_REQ_DST_VIRT | CRYPTO_ACOMP_REQ_DST_NONDMA) #define CRYPTO_ACOMP_DST_MAX 131072 #define MAX_SYNC_COMP_REQSIZE 0 #define ACOMP_REQUEST_ON_STACK(name, tfm) \ char __##name##_req[sizeof(struct acomp_req) + \ MAX_SYNC_COMP_REQSIZE] CRYPTO_MINALIGN_ATTR; \ struct acomp_req *name = acomp_request_on_stack_init( \ __##name##_req, (tfm)) #define ACOMP_REQUEST_CLONE(name, gfp) \ acomp_request_clone(name, sizeof(__##name##_req), gfp) struct acomp_req; struct folio; struct acomp_req_chain { crypto_completion_t compl; void *data; struct scatterlist ssg; struct scatterlist dsg; union { const u8 *src; struct folio *sfolio; }; union { u8 *dst; struct folio *dfolio; }; u32 flags; }; /** * struct acomp_req - asynchronous (de)compression request * * @base: Common attributes for asynchronous crypto requests * @src: Source scatterlist * @dst: Destination scatterlist * @svirt: Source virtual address * @dvirt: Destination virtual address * @slen: Size of the input buffer * @dlen: Size of the output buffer and number of bytes produced * @chain: Private API code data, do not use * @__ctx: Start of private context data */ struct acomp_req { struct crypto_async_request base; union { struct scatterlist *src; const u8 *svirt; }; union { struct scatterlist *dst; u8 *dvirt; }; unsigned int slen; unsigned int dlen; struct acomp_req_chain chain; void *__ctx[] CRYPTO_MINALIGN_ATTR; }; /** * struct crypto_acomp - user-instantiated objects which encapsulate * algorithms and core processing logic * * @compress: Function performs a compress operation * @decompress: Function performs a de-compress operation * @reqsize: Context size for (de)compression requests * @fb: Synchronous fallback tfm * @base: Common crypto API algorithm data structure */ struct crypto_acomp { int (*compress)(struct acomp_req *req); int (*decompress)(struct acomp_req *req); unsigned int reqsize; struct crypto_tfm base; }; #define COMP_ALG_COMMON { \ struct crypto_alg base; \ } struct comp_alg_common COMP_ALG_COMMON; /** * DOC: Asynchronous Compression API * * The Asynchronous Compression API is used with the algorithms of type * CRYPTO_ALG_TYPE_ACOMPRESS (listed as type "acomp" in /proc/crypto) */ /** * crypto_alloc_acomp() -- allocate ACOMPRESS tfm handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * compression algorithm e.g. "deflate" * @type: specifies the type of the algorithm * @mask: specifies the mask for the algorithm * * Allocate a handle for a compression algorithm. The returned struct * crypto_acomp is the handle that is required for any subsequent * API invocation for the compression operations. * * Return: allocated handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_acomp *crypto_alloc_acomp(const char *alg_name, u32 type, u32 mask); /** * crypto_alloc_acomp_node() -- allocate ACOMPRESS tfm handle with desired NUMA node * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * compression algorithm e.g. "deflate" * @type: specifies the type of the algorithm * @mask: specifies the mask for the algorithm * @node: specifies the NUMA node the ZIP hardware belongs to * * Allocate a handle for a compression algorithm. Drivers should try to use * (de)compressors on the specified NUMA node. * The returned struct crypto_acomp is the handle that is required for any * subsequent API invocation for the compression operations. * * Return: allocated handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_acomp *crypto_alloc_acomp_node(const char *alg_name, u32 type, u32 mask, int node); static inline struct crypto_tfm *crypto_acomp_tfm(struct crypto_acomp *tfm) { return &tfm->base; } static inline struct comp_alg_common *__crypto_comp_alg_common( struct crypto_alg *alg) { return container_of(alg, struct comp_alg_common, base); } static inline struct crypto_acomp *__crypto_acomp_tfm(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_acomp, base); } static inline struct comp_alg_common *crypto_comp_alg_common( struct crypto_acomp *tfm) { return __crypto_comp_alg_common(crypto_acomp_tfm(tfm)->__crt_alg); } static inline unsigned int crypto_acomp_reqsize(struct crypto_acomp *tfm) { return tfm->reqsize; } static inline void acomp_request_set_tfm(struct acomp_req *req, struct crypto_acomp *tfm) { crypto_request_set_tfm(&req->base, crypto_acomp_tfm(tfm)); } static inline bool acomp_is_async(struct crypto_acomp *tfm) { return crypto_comp_alg_common(tfm)->base.cra_flags & CRYPTO_ALG_ASYNC; } static inline struct crypto_acomp *crypto_acomp_reqtfm(struct acomp_req *req) { return __crypto_acomp_tfm(req->base.tfm); } /** * crypto_free_acomp() -- free ACOMPRESS tfm handle * * @tfm: ACOMPRESS tfm handle allocated with crypto_alloc_acomp() * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_acomp(struct crypto_acomp *tfm) { crypto_destroy_tfm(tfm, crypto_acomp_tfm(tfm)); } static inline int crypto_has_acomp(const char *alg_name, u32 type, u32 mask) { type &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_ACOMPRESS; mask |= CRYPTO_ALG_TYPE_ACOMPRESS_MASK; return crypto_has_alg(alg_name, type, mask); } static inline const char *crypto_acomp_alg_name(struct crypto_acomp *tfm) { return crypto_tfm_alg_name(crypto_acomp_tfm(tfm)); } static inline const char *crypto_acomp_driver_name(struct crypto_acomp *tfm) { return crypto_tfm_alg_driver_name(crypto_acomp_tfm(tfm)); } /** * acomp_request_alloc_extra() -- allocates asynchronous (de)compression request * * @tfm: ACOMPRESS tfm handle allocated with crypto_alloc_acomp() * @extra: amount of extra memory * @gfp: gfp to pass to kzalloc (defaults to GFP_KERNEL) * * Return: allocated handle in case of success or NULL in case of an error */ static inline struct acomp_req *acomp_request_alloc_extra_noprof( struct crypto_acomp *tfm, size_t extra, gfp_t gfp) { struct acomp_req *req; size_t len; len = ALIGN(sizeof(*req) + crypto_acomp_reqsize(tfm), CRYPTO_MINALIGN); if (check_add_overflow(len, extra, &len)) return NULL; req = kzalloc_noprof(len, gfp); if (likely(req)) acomp_request_set_tfm(req, tfm); return req; } #define acomp_request_alloc_noprof(tfm, ...) \ CONCATENATE(acomp_request_alloc_noprof_, COUNT_ARGS(__VA_ARGS__))( \ tfm, ##__VA_ARGS__) #define acomp_request_alloc_noprof_0(tfm) \ acomp_request_alloc_noprof_1(tfm, GFP_KERNEL) #define acomp_request_alloc_noprof_1(tfm, gfp) \ acomp_request_alloc_extra_noprof(tfm, 0, gfp) #define acomp_request_alloc(...) alloc_hooks(acomp_request_alloc_noprof(__VA_ARGS__)) /** * acomp_request_alloc_extra() -- allocate acomp request with extra memory * * @tfm: ACOMPRESS tfm handle allocated with crypto_alloc_acomp() * @extra: amount of extra memory * @gfp: gfp to pass to kzalloc * * Return: allocated handle in case of success or NULL in case of an error */ #define acomp_request_alloc_extra(...) alloc_hooks(acomp_request_alloc_extra_noprof(__VA_ARGS__)) static inline void *acomp_request_extra(struct acomp_req *req) { struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); size_t len; len = ALIGN(sizeof(*req) + crypto_acomp_reqsize(tfm), CRYPTO_MINALIGN); return (void *)((char *)req + len); } static inline bool acomp_req_on_stack(struct acomp_req *req) { return crypto_req_on_stack(&req->base); } /** * acomp_request_free() -- zeroize and free asynchronous (de)compression * request as well as the output buffer if allocated * inside the algorithm * * @req: request to free */ static inline void acomp_request_free(struct acomp_req *req) { if (!req || acomp_req_on_stack(req)) return; kfree_sensitive(req); } /** * acomp_request_set_callback() -- Sets an asynchronous callback * * Callback will be called when an asynchronous operation on a given * request is finished. * * @req: request that the callback will be set for * @flgs: specify for instance if the operation may backlog * @cmpl: callback which will be called * @data: private data used by the caller */ static inline void acomp_request_set_callback(struct acomp_req *req, u32 flgs, crypto_completion_t cmpl, void *data) { flgs &= ~CRYPTO_ACOMP_REQ_PRIVATE; flgs |= req->base.flags & CRYPTO_ACOMP_REQ_PRIVATE; crypto_request_set_callback(&req->base, flgs, cmpl, data); } /** * acomp_request_set_params() -- Sets request parameters * * Sets parameters required by an acomp operation * * @req: asynchronous compress request * @src: pointer to input buffer scatterlist * @dst: pointer to output buffer scatterlist. If this is NULL, the * acomp layer will allocate the output memory * @slen: size of the input buffer * @dlen: size of the output buffer. If dst is NULL, this can be used by * the user to specify the maximum amount of memory to allocate */ static inline void acomp_request_set_params(struct acomp_req *req, struct scatterlist *src, struct scatterlist *dst, unsigned int slen, unsigned int dlen) { req->src = src; req->dst = dst; req->slen = slen; req->dlen = dlen; req->base.flags &= ~(CRYPTO_ACOMP_REQ_SRC_VIRT | CRYPTO_ACOMP_REQ_SRC_NONDMA | CRYPTO_ACOMP_REQ_DST_VIRT | CRYPTO_ACOMP_REQ_DST_NONDMA); } /** * acomp_request_set_src_sg() -- Sets source scatterlist * * Sets source scatterlist required by an acomp operation. * * @req: asynchronous compress request * @src: pointer to input buffer scatterlist * @slen: size of the input buffer */ static inline void acomp_request_set_src_sg(struct acomp_req *req, struct scatterlist *src, unsigned int slen) { req->src = src; req->slen = slen; req->base.flags &= ~CRYPTO_ACOMP_REQ_SRC_NONDMA; req->base.flags &= ~CRYPTO_ACOMP_REQ_SRC_VIRT; } /** * acomp_request_set_src_dma() -- Sets DMA source virtual address * * Sets source virtual address required by an acomp operation. * The address must be usable for DMA. * * @req: asynchronous compress request * @src: virtual address pointer to input buffer * @slen: size of the input buffer */ static inline void acomp_request_set_src_dma(struct acomp_req *req, const u8 *src, unsigned int slen) { req->svirt = src; req->slen = slen; req->base.flags &= ~CRYPTO_ACOMP_REQ_SRC_NONDMA; req->base.flags |= CRYPTO_ACOMP_REQ_SRC_VIRT; } /** * acomp_request_set_src_nondma() -- Sets non-DMA source virtual address * * Sets source virtual address required by an acomp operation. * The address can not be used for DMA. * * @req: asynchronous compress request * @src: virtual address pointer to input buffer * @slen: size of the input buffer */ static inline void acomp_request_set_src_nondma(struct acomp_req *req, const u8 *src, unsigned int slen) { req->svirt = src; req->slen = slen; req->base.flags |= CRYPTO_ACOMP_REQ_SRC_NONDMA; req->base.flags |= CRYPTO_ACOMP_REQ_SRC_VIRT; } /** * acomp_request_set_src_folio() -- Sets source folio * * Sets source folio required by an acomp operation. * * @req: asynchronous compress request * @folio: pointer to input folio * @off: input folio offset * @len: size of the input buffer */ static inline void acomp_request_set_src_folio(struct acomp_req *req, struct folio *folio, size_t off, unsigned int len) { sg_init_table(&req->chain.ssg, 1); sg_set_folio(&req->chain.ssg, folio, len, off); acomp_request_set_src_sg(req, &req->chain.ssg, len); } /** * acomp_request_set_dst_sg() -- Sets destination scatterlist * * Sets destination scatterlist required by an acomp operation. * * @req: asynchronous compress request * @dst: pointer to output buffer scatterlist * @dlen: size of the output buffer */ static inline void acomp_request_set_dst_sg(struct acomp_req *req, struct scatterlist *dst, unsigned int dlen) { req->dst = dst; req->dlen = dlen; req->base.flags &= ~CRYPTO_ACOMP_REQ_DST_NONDMA; req->base.flags &= ~CRYPTO_ACOMP_REQ_DST_VIRT; } /** * acomp_request_set_dst_dma() -- Sets DMA destination virtual address * * Sets destination virtual address required by an acomp operation. * The address must be usable for DMA. * * @req: asynchronous compress request * @dst: virtual address pointer to output buffer * @dlen: size of the output buffer */ static inline void acomp_request_set_dst_dma(struct acomp_req *req, u8 *dst, unsigned int dlen) { req->dvirt = dst; req->dlen = dlen; req->base.flags &= ~CRYPTO_ACOMP_REQ_DST_NONDMA; req->base.flags |= CRYPTO_ACOMP_REQ_DST_VIRT; } /** * acomp_request_set_dst_nondma() -- Sets non-DMA destination virtual address * * Sets destination virtual address required by an acomp operation. * The address can not be used for DMA. * * @req: asynchronous compress request * @dst: virtual address pointer to output buffer * @dlen: size of the output buffer */ static inline void acomp_request_set_dst_nondma(struct acomp_req *req, u8 *dst, unsigned int dlen) { req->dvirt = dst; req->dlen = dlen; req->base.flags |= CRYPTO_ACOMP_REQ_DST_NONDMA; req->base.flags |= CRYPTO_ACOMP_REQ_DST_VIRT; } /** * acomp_request_set_dst_folio() -- Sets destination folio * * Sets destination folio required by an acomp operation. * * @req: asynchronous compress request * @folio: pointer to input folio * @off: input folio offset * @len: size of the input buffer */ static inline void acomp_request_set_dst_folio(struct acomp_req *req, struct folio *folio, size_t off, unsigned int len) { sg_init_table(&req->chain.dsg, 1); sg_set_folio(&req->chain.dsg, folio, len, off); acomp_request_set_dst_sg(req, &req->chain.dsg, len); } /** * crypto_acomp_compress() -- Invoke asynchronous compress operation * * Function invokes the asynchronous compress operation * * @req: asynchronous compress request * * Return: zero on success; error code in case of error */ int crypto_acomp_compress(struct acomp_req *req); /** * crypto_acomp_decompress() -- Invoke asynchronous decompress operation * * Function invokes the asynchronous decompress operation * * @req: asynchronous compress request * * Return: zero on success; error code in case of error */ int crypto_acomp_decompress(struct acomp_req *req); static inline struct acomp_req *acomp_request_on_stack_init( char *buf, struct crypto_acomp *tfm) { struct acomp_req *req = (void *)buf; crypto_stack_request_init(&req->base, crypto_acomp_tfm(tfm)); return req; } struct acomp_req *acomp_request_clone(struct acomp_req *req, size_t total, gfp_t gfp); #endif |
| 99 100 95 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 | /* * Copyright (C) 2011-2013 Intel Corporation * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice (including the next * paragraph) shall be included in all copies or substantial portions of the * Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #ifndef DRM_RECT_H #define DRM_RECT_H #include <linux/types.h> /** * DOC: rect utils * * Utility functions to help manage rectangular areas for * clipping, scaling, etc. calculations. */ /** * struct drm_rect - two dimensional rectangle * @x1: horizontal starting coordinate (inclusive) * @x2: horizontal ending coordinate (exclusive) * @y1: vertical starting coordinate (inclusive) * @y2: vertical ending coordinate (exclusive) * * Note that this must match the layout of struct drm_mode_rect or the damage * helpers like drm_atomic_helper_damage_iter_init() break. */ struct drm_rect { int x1, y1, x2, y2; }; /** * DRM_RECT_INIT - initialize a rectangle from x/y/w/h * @x: x coordinate * @y: y coordinate * @w: width * @h: height * * RETURNS: * A new rectangle of the specified size. */ #define DRM_RECT_INIT(x, y, w, h) ((struct drm_rect){ \ .x1 = (x), \ .y1 = (y), \ .x2 = (x) + (w), \ .y2 = (y) + (h) }) /** * DRM_RECT_FMT - printf string for &struct drm_rect */ #define DRM_RECT_FMT "%dx%d%+d%+d" /** * DRM_RECT_ARG - printf arguments for &struct drm_rect * @r: rectangle struct */ #define DRM_RECT_ARG(r) drm_rect_width(r), drm_rect_height(r), (r)->x1, (r)->y1 /** * DRM_RECT_FP_FMT - printf string for &struct drm_rect in 16.16 fixed point */ #define DRM_RECT_FP_FMT "%d.%06ux%d.%06u%+d.%06u%+d.%06u" /** * DRM_RECT_FP_ARG - printf arguments for &struct drm_rect in 16.16 fixed point * @r: rectangle struct * * This is useful for e.g. printing plane source rectangles, which are in 16.16 * fixed point. */ #define DRM_RECT_FP_ARG(r) \ drm_rect_width(r) >> 16, ((drm_rect_width(r) & 0xffff) * 15625) >> 10, \ drm_rect_height(r) >> 16, ((drm_rect_height(r) & 0xffff) * 15625) >> 10, \ (r)->x1 >> 16, (((r)->x1 & 0xffff) * 15625) >> 10, \ (r)->y1 >> 16, (((r)->y1 & 0xffff) * 15625) >> 10 /** * drm_rect_init - initialize the rectangle from x/y/w/h * @r: rectangle * @x: x coordinate * @y: y coordinate * @width: width * @height: height */ static inline void drm_rect_init(struct drm_rect *r, int x, int y, int width, int height) { r->x1 = x; r->y1 = y; r->x2 = x + width; r->y2 = y + height; } /** * drm_rect_adjust_size - adjust the size of the rectangle * @r: rectangle to be adjusted * @dw: horizontal adjustment * @dh: vertical adjustment * * Change the size of rectangle @r by @dw in the horizontal direction, * and by @dh in the vertical direction, while keeping the center * of @r stationary. * * Positive @dw and @dh increase the size, negative values decrease it. */ static inline void drm_rect_adjust_size(struct drm_rect *r, int dw, int dh) { r->x1 -= dw >> 1; r->y1 -= dh >> 1; r->x2 += (dw + 1) >> 1; r->y2 += (dh + 1) >> 1; } /** * drm_rect_translate - translate the rectangle * @r: rectangle to be translated * @dx: horizontal translation * @dy: vertical translation * * Move rectangle @r by @dx in the horizontal direction, * and by @dy in the vertical direction. */ static inline void drm_rect_translate(struct drm_rect *r, int dx, int dy) { r->x1 += dx; r->y1 += dy; r->x2 += dx; r->y2 += dy; } /** * drm_rect_translate_to - translate the rectangle to an absolute position * @r: rectangle to be translated * @x: horizontal position * @y: vertical position * * Move rectangle @r to @x in the horizontal direction, * and to @y in the vertical direction. */ static inline void drm_rect_translate_to(struct drm_rect *r, int x, int y) { drm_rect_translate(r, x - r->x1, y - r->y1); } /** * drm_rect_downscale - downscale a rectangle * @r: rectangle to be downscaled * @horz: horizontal downscale factor * @vert: vertical downscale factor * * Divide the coordinates of rectangle @r by @horz and @vert. */ static inline void drm_rect_downscale(struct drm_rect *r, int horz, int vert) { r->x1 /= horz; r->y1 /= vert; r->x2 /= horz; r->y2 /= vert; } /** * drm_rect_width - determine the rectangle width * @r: rectangle whose width is returned * * RETURNS: * The width of the rectangle. */ static inline int drm_rect_width(const struct drm_rect *r) { return r->x2 - r->x1; } /** * drm_rect_height - determine the rectangle height * @r: rectangle whose height is returned * * RETURNS: * The height of the rectangle. */ static inline int drm_rect_height(const struct drm_rect *r) { return r->y2 - r->y1; } /** * drm_rect_visible - determine if the rectangle is visible * @r: rectangle whose visibility is returned * * RETURNS: * %true if the rectangle is visible, %false otherwise. */ static inline bool drm_rect_visible(const struct drm_rect *r) { return drm_rect_width(r) > 0 && drm_rect_height(r) > 0; } /** * drm_rect_equals - determine if two rectangles are equal * @r1: first rectangle * @r2: second rectangle * * RETURNS: * %true if the rectangles are equal, %false otherwise. */ static inline bool drm_rect_equals(const struct drm_rect *r1, const struct drm_rect *r2) { return r1->x1 == r2->x1 && r1->x2 == r2->x2 && r1->y1 == r2->y1 && r1->y2 == r2->y2; } /** * drm_rect_fp_to_int - Convert a rect in 16.16 fixed point form to int form. * @dst: rect to be stored the converted value * @src: rect in 16.16 fixed point form */ static inline void drm_rect_fp_to_int(struct drm_rect *dst, const struct drm_rect *src) { drm_rect_init(dst, src->x1 >> 16, src->y1 >> 16, drm_rect_width(src) >> 16, drm_rect_height(src) >> 16); } /** * drm_rect_overlap - Check if two rectangles overlap * @a: first rectangle * @b: second rectangle * * RETURNS: * %true if the rectangles overlap, %false otherwise. */ static inline bool drm_rect_overlap(const struct drm_rect *a, const struct drm_rect *b) { return (a->x2 > b->x1 && b->x2 > a->x1 && a->y2 > b->y1 && b->y2 > a->y1); } bool drm_rect_intersect(struct drm_rect *r, const struct drm_rect *clip); bool drm_rect_clip_scaled(struct drm_rect *src, struct drm_rect *dst, const struct drm_rect *clip); int drm_rect_calc_hscale(const struct drm_rect *src, const struct drm_rect *dst, int min_hscale, int max_hscale); int drm_rect_calc_vscale(const struct drm_rect *src, const struct drm_rect *dst, int min_vscale, int max_vscale); void drm_rect_debug_print(const char *prefix, const struct drm_rect *r, bool fixed_point); void drm_rect_rotate(struct drm_rect *r, int width, int height, unsigned int rotation); void drm_rect_rotate_inv(struct drm_rect *r, int width, int height, unsigned int rotation); #endif |
| 11 7 10 2 165 184 21 183 20 1 20 184 13 2 4 12 11 9 9 170 8 7 7 6 8 6 5 4 4 2 4 2 173 9 1 1 7 3 1 9 9 8 183 3 3 1 3 1 163 162 1 163 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VIRTIO_NET_H #define _LINUX_VIRTIO_NET_H #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/udp.h> #include <uapi/linux/tcp.h> #include <uapi/linux/virtio_net.h> static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) { switch (gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: return protocol == cpu_to_be16(ETH_P_IP); case VIRTIO_NET_HDR_GSO_TCPV6: return protocol == cpu_to_be16(ETH_P_IPV6); case VIRTIO_NET_HDR_GSO_UDP: case VIRTIO_NET_HDR_GSO_UDP_L4: return protocol == cpu_to_be16(ETH_P_IP) || protocol == cpu_to_be16(ETH_P_IPV6); default: return false; } } static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, const struct virtio_net_hdr *hdr) { if (skb->protocol) return 0; switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: case VIRTIO_NET_HDR_GSO_UDP: case VIRTIO_NET_HDR_GSO_UDP_L4: skb->protocol = cpu_to_be16(ETH_P_IP); break; case VIRTIO_NET_HDR_GSO_TCPV6: skb->protocol = cpu_to_be16(ETH_P_IPV6); break; default: return -EINVAL; } return 0; } static inline int __virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian, u8 hdr_gso_type) { unsigned int nh_min_len = sizeof(struct iphdr); unsigned int gso_type = 0; unsigned int thlen = 0; unsigned int p_off = 0; unsigned int ip_proto; if (hdr_gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr_gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: gso_type = SKB_GSO_TCPV4; ip_proto = IPPROTO_TCP; thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; ip_proto = IPPROTO_TCP; thlen = sizeof(struct tcphdr); nh_min_len = sizeof(struct ipv6hdr); break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; ip_proto = IPPROTO_UDP; thlen = sizeof(struct udphdr); break; case VIRTIO_NET_HDR_GSO_UDP_L4: gso_type = SKB_GSO_UDP_L4; ip_proto = IPPROTO_UDP; thlen = sizeof(struct udphdr); break; default: return -EINVAL; } if (hdr_gso_type & VIRTIO_NET_HDR_GSO_ECN) gso_type |= SKB_GSO_TCP_ECN; if (hdr->gso_size == 0) return -EINVAL; } skb_reset_mac_header(skb); if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start); u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); if (!pskb_may_pull(skb, needed)) return -EINVAL; if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; if (skb_transport_offset(skb) < nh_min_len) return -EINVAL; nh_min_len = skb_transport_offset(skb); p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ if (gso_type && skb->network_header) { struct flow_keys_basic keys; if (!skb->protocol) { __be16 protocol = dev_parse_header_protocol(skb); if (!protocol) virtio_net_hdr_set_proto(skb, hdr); else if (!virtio_net_hdr_match_proto(protocol, hdr_gso_type)) return -EINVAL; else skb->protocol = protocol; } retry: if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) { /* UFO does not specify ipv4 or 6: try both */ if (gso_type & SKB_GSO_UDP && skb->protocol == htons(ETH_P_IP)) { skb->protocol = htons(ETH_P_IPV6); goto retry; } return -EINVAL; } p_off = keys.control.thoff + thlen; if (!pskb_may_pull(skb, p_off) || keys.basic.ip_proto != ip_proto) return -EINVAL; skb_set_transport_header(skb, keys.control.thoff); } else if (gso_type) { p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } } if (hdr_gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); unsigned int nh_off = p_off; struct skb_shared_info *shinfo = skb_shinfo(skb); switch (gso_type & ~SKB_GSO_TCP_ECN) { case SKB_GSO_UDP: /* UFO may not include transport header in gso_size. */ nh_off -= thlen; break; case SKB_GSO_UDP_L4: if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) return -EINVAL; if (skb->csum_offset != offsetof(struct udphdr, check)) return -EINVAL; if (skb->len - p_off > gso_size * UDP_MAX_SEGMENTS) return -EINVAL; if (gso_type != SKB_GSO_UDP_L4) return -EINVAL; break; case SKB_GSO_TCPV4: case SKB_GSO_TCPV6: if (skb->ip_summed == CHECKSUM_PARTIAL && skb->csum_offset != offsetof(struct tcphdr, check)) return -EINVAL; break; } /* Kernel has a special handling for GSO_BY_FRAGS. */ if (gso_size == GSO_BY_FRAGS) return -EINVAL; /* Too small packets are not really GSO ones. */ if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; shinfo->gso_type = gso_type; /* Header must be checked, and gso_segs computed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; } } return 0; } static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian) { return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type); } /* This function must be called after virtio_net_hdr_from_skb(). */ static inline void __virtio_net_set_hdrlen(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian) { u16 hdr_len; hdr_len = skb_transport_offset(skb); if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4) hdr_len += sizeof(struct udphdr); else hdr_len += tcp_hdrlen(skb); hdr->hdr_len = __cpu_to_virtio16(little_endian, hdr_len); } /* This function must be called after virtio_net_hdr_from_skb(). */ static inline void __virtio_net_set_tnl_hdrlen(const struct sk_buff *skb, struct virtio_net_hdr *hdr) { u16 hdr_len; hdr_len = skb_inner_transport_offset(skb); if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4) hdr_len += sizeof(struct udphdr); else hdr_len += inner_tcp_hdrlen(skb); hdr->hdr_len = __cpu_to_virtio16(true, hdr_len); } static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian, bool has_data_valid, int vlan_hlen) { memset(hdr, 0, sizeof(*hdr)); /* no info leak */ if (skb_is_gso(skb)) { struct skb_shared_info *sinfo = skb_shinfo(skb); /* This is a hint as to how much should be linear. */ hdr->hdr_len = __cpu_to_virtio16(little_endian, skb_headlen(skb)); hdr->gso_size = __cpu_to_virtio16(little_endian, sinfo->gso_size); if (sinfo->gso_type & SKB_GSO_TCPV4) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; else if (sinfo->gso_type & SKB_GSO_UDP_L4) hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP_L4; else return -EINVAL; if (sinfo->gso_type & SKB_GSO_TCP_ECN) hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN; } else hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE; if (skb->ip_summed == CHECKSUM_PARTIAL) { hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; hdr->csum_start = __cpu_to_virtio16(little_endian, skb_checksum_start_offset(skb) + vlan_hlen); hdr->csum_offset = __cpu_to_virtio16(little_endian, skb->csum_offset); } else if (has_data_valid && skb->ip_summed == CHECKSUM_UNNECESSARY) { hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ return 0; } static inline unsigned int virtio_l3min(bool is_ipv6) { return is_ipv6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr); } static inline int virtio_net_hdr_tnl_to_skb(struct sk_buff *skb, const struct virtio_net_hdr_v1_hash_tunnel *vhdr, bool tnl_hdr_negotiated, bool tnl_csum_negotiated, bool little_endian) { const struct virtio_net_hdr *hdr = (const struct virtio_net_hdr *)vhdr; unsigned int inner_nh, outer_th, inner_th; unsigned int inner_l3min, outer_l3min; u8 gso_inner_type, gso_tunnel_type; bool outer_isv6, inner_isv6; int ret; gso_tunnel_type = hdr->gso_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL; if (!gso_tunnel_type) return virtio_net_hdr_to_skb(skb, hdr, little_endian); /* Tunnel not supported/negotiated, but the hdr asks for it. */ if (!tnl_hdr_negotiated) return -EINVAL; /* Either ipv4 or ipv6. */ if (gso_tunnel_type == VIRTIO_NET_HDR_GSO_UDP_TUNNEL) return -EINVAL; /* The UDP tunnel must carry a GSO packet, but no UFO. */ gso_inner_type = hdr->gso_type & ~(VIRTIO_NET_HDR_GSO_ECN | VIRTIO_NET_HDR_GSO_UDP_TUNNEL); if (!gso_inner_type || gso_inner_type == VIRTIO_NET_HDR_GSO_UDP) return -EINVAL; /* Rely on csum being present. */ if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) return -EINVAL; /* Validate offsets. */ outer_isv6 = gso_tunnel_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6; inner_isv6 = gso_inner_type == VIRTIO_NET_HDR_GSO_TCPV6; inner_l3min = virtio_l3min(inner_isv6); outer_l3min = ETH_HLEN + virtio_l3min(outer_isv6); inner_th = __virtio16_to_cpu(little_endian, hdr->csum_start); inner_nh = le16_to_cpu(vhdr->inner_nh_offset); outer_th = le16_to_cpu(vhdr->outer_th_offset); if (outer_th < outer_l3min || inner_nh < outer_th + sizeof(struct udphdr) || inner_th < inner_nh + inner_l3min) return -EINVAL; /* Let the basic parsing deal with plain GSO features. */ ret = __virtio_net_hdr_to_skb(skb, hdr, true, hdr->gso_type & ~gso_tunnel_type); if (ret) return ret; /* In case of USO, the inner protocol is still unknown and * `inner_isv6` is just a guess, additional parsing is needed. * The previous validation ensures that accessing an ipv4 inner * network header is safe. */ if (gso_inner_type == VIRTIO_NET_HDR_GSO_UDP_L4) { struct iphdr *iphdr = (struct iphdr *)(skb->data + inner_nh); inner_isv6 = iphdr->version == 6; inner_l3min = virtio_l3min(inner_isv6); if (inner_th < inner_nh + inner_l3min) return -EINVAL; } skb_set_inner_protocol(skb, inner_isv6 ? htons(ETH_P_IPV6) : htons(ETH_P_IP)); if (hdr->flags & VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM) { if (!tnl_csum_negotiated) return -EINVAL; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; } else { skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; } skb->inner_transport_header = inner_th + skb_headroom(skb); skb->inner_network_header = inner_nh + skb_headroom(skb); skb->inner_mac_header = inner_nh + skb_headroom(skb); skb->transport_header = outer_th + skb_headroom(skb); skb->encapsulation = 1; return 0; } /* Checksum-related fields validation for the driver */ static inline int virtio_net_handle_csum_offload(struct sk_buff *skb, struct virtio_net_hdr *hdr, bool tnl_csum_negotiated) { if (!(hdr->gso_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL)) { if (!(hdr->flags & VIRTIO_NET_HDR_F_DATA_VALID)) return 0; skb->ip_summed = CHECKSUM_UNNECESSARY; if (!(hdr->flags & VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM)) return 0; /* tunnel csum packets are invalid when the related * feature has not been negotiated */ if (!tnl_csum_negotiated) return -EINVAL; skb->csum_level = 1; return 0; } /* DATA_VALID is mutually exclusive with NEEDS_CSUM, and GSO * over UDP tunnel requires the latter */ if (hdr->flags & VIRTIO_NET_HDR_F_DATA_VALID) return -EINVAL; return 0; } /* * vlan_hlen always refers to the outermost MAC header. That also * means it refers to the only MAC header, if the packet does not carry * any encapsulation. */ static inline int virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, struct virtio_net_hdr_v1_hash_tunnel *vhdr, bool tnl_hdr_negotiated, bool little_endian, int vlan_hlen, bool has_data_valid, bool feature_hdrlen) { struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr; unsigned int inner_nh, outer_th; int tnl_gso_type; int ret; tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM); if (!tnl_gso_type) { ret = virtio_net_hdr_from_skb(skb, hdr, little_endian, has_data_valid, vlan_hlen); if (ret) return ret; if (feature_hdrlen && hdr->hdr_len) __virtio_net_set_hdrlen(skb, hdr, little_endian); return ret; } /* Tunnel support not negotiated but skb ask for it. */ if (!tnl_hdr_negotiated) return -EINVAL; vhdr->hash_hdr.hash_value_lo = 0; vhdr->hash_hdr.hash_value_hi = 0; vhdr->hash_hdr.hash_report = 0; vhdr->hash_hdr.padding = 0; /* Let the basic parsing deal with plain GSO features. */ skb_shinfo(skb)->gso_type &= ~tnl_gso_type; ret = virtio_net_hdr_from_skb(skb, hdr, true, false, vlan_hlen); skb_shinfo(skb)->gso_type |= tnl_gso_type; if (ret) return ret; if (feature_hdrlen && hdr->hdr_len) __virtio_net_set_tnl_hdrlen(skb, hdr); if (skb->protocol == htons(ETH_P_IPV6)) hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6; else hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) hdr->flags |= VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM; inner_nh = skb->inner_network_header - skb_headroom(skb); outer_th = skb->transport_header - skb_headroom(skb); vhdr->inner_nh_offset = cpu_to_le16(inner_nh); vhdr->outer_th_offset = cpu_to_le16(outer_th); return 0; } #endif /* _LINUX_VIRTIO_NET_H */ |
| 176 160 222 222 224 174 239 160 118 1 239 160 160 160 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_IRQ_H #define _LINUX_IRQ_H /* * Please do not include this file in generic code. There is currently * no requirement for any architecture to implement anything held * within this file. * * Thanks. --rmk */ #include <linux/cache.h> #include <linux/spinlock.h> #include <linux/cpumask.h> #include <linux/irqhandler.h> #include <linux/irqreturn.h> #include <linux/irqnr.h> #include <linux/topology.h> #include <linux/io.h> #include <linux/slab.h> #include <asm/irq.h> #include <asm/ptrace.h> #include <asm/irq_regs.h> struct seq_file; struct module; struct msi_msg; struct irq_affinity_desc; enum irqchip_irq_state; /* * IRQ line status. * * Bits 0-7 are the same as the IRQF_* bits in linux/interrupt.h * * Note that the first 6 definitions are shadowed by C preprocessor definitions * in include/dt-bindings/interrupt-controller/irq.h. This is not an issue, as * the actual values must be the same, due to being part of the stable DT ABI. * * IRQ_TYPE_NONE - default, unspecified type * IRQ_TYPE_EDGE_RISING - rising edge triggered * IRQ_TYPE_EDGE_FALLING - falling edge triggered * IRQ_TYPE_EDGE_BOTH - rising and falling edge triggered * IRQ_TYPE_LEVEL_HIGH - high level triggered * IRQ_TYPE_LEVEL_LOW - low level triggered * IRQ_TYPE_LEVEL_MASK - Mask to filter out the level bits * IRQ_TYPE_SENSE_MASK - Mask for all the above bits * IRQ_TYPE_DEFAULT - For use by some PICs to ask irq_set_type * to setup the HW to a sane default (used * by irqdomain map() callbacks to synchronize * the HW state and SW flags for a newly * allocated descriptor). * * IRQ_TYPE_PROBE - Special flag for probing in progress * * Bits which can be modified via irq_set/clear/modify_status_flags() * IRQ_LEVEL - Interrupt is level type. Will be also * updated in the code when the above trigger * bits are modified via irq_set_irq_type() * IRQ_PER_CPU - Mark an interrupt PER_CPU. Will protect * it from affinity setting * IRQ_NOPROBE - Interrupt cannot be probed by autoprobing * IRQ_NOREQUEST - Interrupt cannot be requested via * request_irq() * IRQ_NOTHREAD - Interrupt cannot be threaded * IRQ_NOAUTOEN - Interrupt is not automatically enabled in * request/setup_irq() * IRQ_NO_BALANCING - Interrupt cannot be balanced (affinity set) * IRQ_NESTED_THREAD - Interrupt nests into another thread * IRQ_PER_CPU_DEVID - Dev_id is a per-cpu variable * IRQ_IS_POLLED - Always polled by another interrupt. Exclude * it from the spurious interrupt detection * mechanism and from core side polling. * IRQ_DISABLE_UNLAZY - Disable lazy irq disable * IRQ_HIDDEN - Don't show up in /proc/interrupts * IRQ_NO_DEBUG - Exclude from note_interrupt() debugging */ enum { IRQ_TYPE_NONE = 0x00000000, IRQ_TYPE_EDGE_RISING = 0x00000001, IRQ_TYPE_EDGE_FALLING = 0x00000002, IRQ_TYPE_EDGE_BOTH = (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING), IRQ_TYPE_LEVEL_HIGH = 0x00000004, IRQ_TYPE_LEVEL_LOW = 0x00000008, IRQ_TYPE_LEVEL_MASK = (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH), IRQ_TYPE_SENSE_MASK = 0x0000000f, IRQ_TYPE_DEFAULT = IRQ_TYPE_SENSE_MASK, IRQ_TYPE_PROBE = 0x00000010, IRQ_LEVEL = (1 << 8), IRQ_PER_CPU = (1 << 9), IRQ_NOPROBE = (1 << 10), IRQ_NOREQUEST = (1 << 11), IRQ_NOAUTOEN = (1 << 12), IRQ_NO_BALANCING = (1 << 13), IRQ_NESTED_THREAD = (1 << 15), IRQ_NOTHREAD = (1 << 16), IRQ_PER_CPU_DEVID = (1 << 17), IRQ_IS_POLLED = (1 << 18), IRQ_DISABLE_UNLAZY = (1 << 19), IRQ_HIDDEN = (1 << 20), IRQ_NO_DEBUG = (1 << 21), IRQ_RESERVED = (1 << 22), }; #define IRQF_MODIFY_MASK \ (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ IRQ_NOAUTOEN | IRQ_LEVEL | IRQ_NO_BALANCING | \ IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_HIDDEN) #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) /* * Return value for chip->irq_set_affinity() * * IRQ_SET_MASK_OK - OK, core updates irq_common_data.affinity * IRQ_SET_MASK_NOCOPY - OK, chip did update irq_common_data.affinity * IRQ_SET_MASK_OK_DONE - Same as IRQ_SET_MASK_OK for core. Special code to * support stacked irqchips, which indicates skipping * all descendant irqchips. */ enum { IRQ_SET_MASK_OK = 0, IRQ_SET_MASK_OK_NOCOPY, IRQ_SET_MASK_OK_DONE, }; struct msi_desc; struct irq_domain; /** * struct irq_common_data - per irq data shared by all irqchips * @state_use_accessors: status information for irq chip functions. * Use accessor functions to deal with it * @node: node index useful for balancing * @handler_data: per-IRQ data for the irq_chip methods * @affinity: IRQ affinity on SMP. If this is an IPI * related irq, then this is the mask of the * CPUs to which an IPI can be sent. * @effective_affinity: The effective IRQ affinity on SMP as some irq * chips do not allow multi CPU destinations. * A subset of @affinity. * @msi_desc: MSI descriptor * @ipi_offset: Offset of first IPI target cpu in @affinity. Optional. */ struct irq_common_data { unsigned int __private state_use_accessors; #ifdef CONFIG_NUMA unsigned int node; #endif void *handler_data; struct msi_desc *msi_desc; #ifdef CONFIG_SMP cpumask_var_t affinity; #endif #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK cpumask_var_t effective_affinity; #endif #ifdef CONFIG_GENERIC_IRQ_IPI unsigned int ipi_offset; #endif }; /** * struct irq_data - per irq chip data passed down to chip functions * @mask: precomputed bitmask for accessing the chip registers * @irq: interrupt number * @hwirq: hardware interrupt number, local to the interrupt domain * @common: point to data shared by all irqchips * @chip: low level interrupt hardware access * @domain: Interrupt translation domain; responsible for mapping * between hwirq number and linux irq number. * @parent_data: pointer to parent struct irq_data to support hierarchy * irq_domain * @chip_data: platform-specific per-chip private data for the chip * methods, to allow shared chip implementations */ struct irq_data { u32 mask; unsigned int irq; irq_hw_number_t hwirq; struct irq_common_data *common; struct irq_chip *chip; struct irq_domain *domain; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_data *parent_data; #endif void *chip_data; }; /* * Bit masks for irq_common_data.state_use_accessors * * IRQD_TRIGGER_MASK - Mask for the trigger type bits * IRQD_SETAFFINITY_PENDING - Affinity setting is pending * IRQD_ACTIVATED - Interrupt has already been activated * IRQD_NO_BALANCING - Balancing disabled for this IRQ * IRQD_PER_CPU - Interrupt is per cpu * IRQD_AFFINITY_SET - Interrupt affinity was set * IRQD_LEVEL - Interrupt is level triggered * IRQD_WAKEUP_STATE - Interrupt is configured for wakeup * from suspend * IRQD_IRQ_DISABLED - Disabled state of the interrupt * IRQD_IRQ_MASKED - Masked state of the interrupt * IRQD_IRQ_INPROGRESS - In progress state of the interrupt * IRQD_WAKEUP_ARMED - Wakeup mode armed * IRQD_FORWARDED_TO_VCPU - The interrupt is forwarded to a VCPU * IRQD_AFFINITY_MANAGED - Affinity is auto-managed by the kernel * IRQD_IRQ_STARTED - Startup state of the interrupt * IRQD_MANAGED_SHUTDOWN - Interrupt was shutdown due to empty affinity * mask. Applies only to affinity managed irqs. * IRQD_SINGLE_TARGET - IRQ allows only a single affinity target * IRQD_DEFAULT_TRIGGER_SET - Expected trigger already been set * IRQD_CAN_RESERVE - Can use reservation mode * IRQD_HANDLE_ENFORCE_IRQCTX - Enforce that handle_irq_*() is only invoked * from actual interrupt context. * IRQD_AFFINITY_ON_ACTIVATE - Affinity is set on activation. Don't call * irq_chip::irq_set_affinity() when deactivated. * IRQD_IRQ_ENABLED_ON_SUSPEND - Interrupt is enabled on suspend by irq pm if * irqchip have flag IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND set. * IRQD_RESEND_WHEN_IN_PROGRESS - Interrupt may fire when already in progress in which * case it must be resent at the next available opportunity. */ enum { IRQD_TRIGGER_MASK = 0xf, IRQD_SETAFFINITY_PENDING = BIT(8), IRQD_ACTIVATED = BIT(9), IRQD_NO_BALANCING = BIT(10), IRQD_PER_CPU = BIT(11), IRQD_AFFINITY_SET = BIT(12), IRQD_LEVEL = BIT(13), IRQD_WAKEUP_STATE = BIT(14), IRQD_IRQ_DISABLED = BIT(16), IRQD_IRQ_MASKED = BIT(17), IRQD_IRQ_INPROGRESS = BIT(18), IRQD_WAKEUP_ARMED = BIT(19), IRQD_FORWARDED_TO_VCPU = BIT(20), IRQD_AFFINITY_MANAGED = BIT(21), IRQD_IRQ_STARTED = BIT(22), IRQD_MANAGED_SHUTDOWN = BIT(23), IRQD_SINGLE_TARGET = BIT(24), IRQD_DEFAULT_TRIGGER_SET = BIT(25), IRQD_CAN_RESERVE = BIT(26), IRQD_HANDLE_ENFORCE_IRQCTX = BIT(27), IRQD_AFFINITY_ON_ACTIVATE = BIT(28), IRQD_IRQ_ENABLED_ON_SUSPEND = BIT(29), IRQD_RESEND_WHEN_IN_PROGRESS = BIT(30), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) static inline bool irqd_is_setaffinity_pending(struct irq_data *d) { return __irqd_to_state(d) & IRQD_SETAFFINITY_PENDING; } static inline bool irqd_is_per_cpu(struct irq_data *d) { return __irqd_to_state(d) & IRQD_PER_CPU; } static inline bool irqd_can_balance(struct irq_data *d) { return !(__irqd_to_state(d) & (IRQD_PER_CPU | IRQD_NO_BALANCING)); } static inline bool irqd_affinity_was_set(struct irq_data *d) { return __irqd_to_state(d) & IRQD_AFFINITY_SET; } static inline void irqd_mark_affinity_was_set(struct irq_data *d) { __irqd_to_state(d) |= IRQD_AFFINITY_SET; } static inline bool irqd_trigger_type_was_set(struct irq_data *d) { return __irqd_to_state(d) & IRQD_DEFAULT_TRIGGER_SET; } static inline u32 irqd_get_trigger_type(struct irq_data *d) { return __irqd_to_state(d) & IRQD_TRIGGER_MASK; } /* * Must only be called inside irq_chip.irq_set_type() functions or * from the DT/ACPI setup code. */ static inline void irqd_set_trigger_type(struct irq_data *d, u32 type) { __irqd_to_state(d) &= ~IRQD_TRIGGER_MASK; __irqd_to_state(d) |= type & IRQD_TRIGGER_MASK; __irqd_to_state(d) |= IRQD_DEFAULT_TRIGGER_SET; } static inline bool irqd_is_level_type(struct irq_data *d) { return __irqd_to_state(d) & IRQD_LEVEL; } /* * Must only be called of irqchip.irq_set_affinity() or low level * hierarchy domain allocation functions. */ static inline void irqd_set_single_target(struct irq_data *d) { __irqd_to_state(d) |= IRQD_SINGLE_TARGET; } static inline bool irqd_is_single_target(struct irq_data *d) { return __irqd_to_state(d) & IRQD_SINGLE_TARGET; } static inline void irqd_set_handle_enforce_irqctx(struct irq_data *d) { __irqd_to_state(d) |= IRQD_HANDLE_ENFORCE_IRQCTX; } static inline bool irqd_is_handle_enforce_irqctx(struct irq_data *d) { return __irqd_to_state(d) & IRQD_HANDLE_ENFORCE_IRQCTX; } static inline bool irqd_is_enabled_on_suspend(struct irq_data *d) { return __irqd_to_state(d) & IRQD_IRQ_ENABLED_ON_SUSPEND; } static inline bool irqd_is_wakeup_set(struct irq_data *d) { return __irqd_to_state(d) & IRQD_WAKEUP_STATE; } static inline bool irqd_irq_disabled(struct irq_data *d) { return __irqd_to_state(d) & IRQD_IRQ_DISABLED; } static inline bool irqd_irq_masked(struct irq_data *d) { return __irqd_to_state(d) & IRQD_IRQ_MASKED; } static inline bool irqd_irq_inprogress(struct irq_data *d) { return __irqd_to_state(d) & IRQD_IRQ_INPROGRESS; } static inline bool irqd_is_wakeup_armed(struct irq_data *d) { return __irqd_to_state(d) & IRQD_WAKEUP_ARMED; } static inline bool irqd_is_forwarded_to_vcpu(struct irq_data *d) { return __irqd_to_state(d) & IRQD_FORWARDED_TO_VCPU; } static inline void irqd_set_forwarded_to_vcpu(struct irq_data *d) { __irqd_to_state(d) |= IRQD_FORWARDED_TO_VCPU; } static inline void irqd_clr_forwarded_to_vcpu(struct irq_data *d) { __irqd_to_state(d) &= ~IRQD_FORWARDED_TO_VCPU; } static inline bool irqd_affinity_is_managed(struct irq_data *d) { return __irqd_to_state(d) & IRQD_AFFINITY_MANAGED; } static inline bool irqd_is_activated(struct irq_data *d) { return __irqd_to_state(d) & IRQD_ACTIVATED; } static inline void irqd_set_activated(struct irq_data *d) { __irqd_to_state(d) |= IRQD_ACTIVATED; } static inline void irqd_clr_activated(struct irq_data *d) { __irqd_to_state(d) &= ~IRQD_ACTIVATED; } static inline bool irqd_is_started(struct irq_data *d) { return __irqd_to_state(d) & IRQD_IRQ_STARTED; } static inline bool irqd_is_managed_and_shutdown(struct irq_data *d) { return __irqd_to_state(d) & IRQD_MANAGED_SHUTDOWN; } static inline void irqd_set_can_reserve(struct irq_data *d) { __irqd_to_state(d) |= IRQD_CAN_RESERVE; } static inline void irqd_clr_can_reserve(struct irq_data *d) { __irqd_to_state(d) &= ~IRQD_CAN_RESERVE; } static inline bool irqd_can_reserve(struct irq_data *d) { return __irqd_to_state(d) & IRQD_CAN_RESERVE; } static inline void irqd_set_affinity_on_activate(struct irq_data *d) { __irqd_to_state(d) |= IRQD_AFFINITY_ON_ACTIVATE; } static inline bool irqd_affinity_on_activate(struct irq_data *d) { return __irqd_to_state(d) & IRQD_AFFINITY_ON_ACTIVATE; } static inline void irqd_set_resend_when_in_progress(struct irq_data *d) { __irqd_to_state(d) |= IRQD_RESEND_WHEN_IN_PROGRESS; } static inline bool irqd_needs_resend_when_in_progress(struct irq_data *d) { return __irqd_to_state(d) & IRQD_RESEND_WHEN_IN_PROGRESS; } #undef __irqd_to_state static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) { return d->hwirq; } /** * struct irq_chip - hardware interrupt chip descriptor * * @name: name for /proc/interrupts * @irq_startup: start up the interrupt (defaults to ->enable if NULL) * @irq_shutdown: shut down the interrupt (defaults to ->disable if NULL) * @irq_enable: enable the interrupt (defaults to chip->unmask if NULL) * @irq_disable: disable the interrupt * @irq_ack: start of a new interrupt * @irq_mask: mask an interrupt source * @irq_mask_ack: ack and mask an interrupt source * @irq_unmask: unmask an interrupt source * @irq_eoi: end of interrupt * @irq_set_affinity: Set the CPU affinity on SMP machines. If the force * argument is true, it tells the driver to * unconditionally apply the affinity setting. Sanity * checks against the supplied affinity mask are not * required. This is used for CPU hotplug where the * target CPU is not yet set in the cpu_online_mask. * @irq_pre_redirect: Optional function to be invoked before redirecting * an interrupt via irq_work. Called only on CONFIG_SMP. * @irq_retrigger: resend an IRQ to the CPU * @irq_set_type: set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ * @irq_set_wake: enable/disable power-management wake-on of an IRQ * @irq_bus_lock: function to lock access to slow bus (i2c) chips * @irq_bus_sync_unlock:function to sync and unlock slow bus (i2c) chips * @irq_cpu_online: configure an interrupt source for a secondary CPU * @irq_cpu_offline: un-configure an interrupt source for a secondary CPU * @irq_suspend: function called from core code on suspend once per * chip, when one or more interrupts are installed * @irq_resume: function called from core code on resume once per chip, * when one ore more interrupts are installed * @irq_pm_shutdown: function called from core code on shutdown once per chip * @irq_calc_mask: Optional function to set irq_data.mask for special cases * @irq_print_chip: optional to print special chip info in show_interrupts * @irq_request_resources: optional to request resources before calling * any other callback related to this irq * @irq_release_resources: optional to release resources acquired with * irq_request_resources * @irq_compose_msi_msg: optional to compose message content for MSI * @irq_write_msi_msg: optional to write message content for MSI * @irq_get_irqchip_state: return the internal state of an interrupt * @irq_set_irqchip_state: set the internal state of a interrupt * @irq_set_vcpu_affinity: optional to target a vCPU in a virtual machine * @ipi_send_single: send a single IPI to destination cpus * @ipi_send_mask: send an IPI to destination cpus in cpumask * @irq_nmi_setup: function called from core code before enabling an NMI * @irq_nmi_teardown: function called from core code after disabling an NMI * @irq_force_complete_move: optional function to force complete pending irq move * @flags: chip specific flags */ struct irq_chip { const char *name; unsigned int (*irq_startup)(struct irq_data *data); void (*irq_shutdown)(struct irq_data *data); void (*irq_enable)(struct irq_data *data); void (*irq_disable)(struct irq_data *data); void (*irq_ack)(struct irq_data *data); void (*irq_mask)(struct irq_data *data); void (*irq_mask_ack)(struct irq_data *data); void (*irq_unmask)(struct irq_data *data); void (*irq_eoi)(struct irq_data *data); int (*irq_set_affinity)(struct irq_data *data, const struct cpumask *dest, bool force); void (*irq_pre_redirect)(struct irq_data *data); int (*irq_retrigger)(struct irq_data *data); int (*irq_set_type)(struct irq_data *data, unsigned int flow_type); int (*irq_set_wake)(struct irq_data *data, unsigned int on); void (*irq_bus_lock)(struct irq_data *data); void (*irq_bus_sync_unlock)(struct irq_data *data); #ifdef CONFIG_DEPRECATED_IRQ_CPU_ONOFFLINE void (*irq_cpu_online)(struct irq_data *data); void (*irq_cpu_offline)(struct irq_data *data); #endif void (*irq_suspend)(struct irq_data *data); void (*irq_resume)(struct irq_data *data); void (*irq_pm_shutdown)(struct irq_data *data); void (*irq_calc_mask)(struct irq_data *data); void (*irq_print_chip)(struct irq_data *data, struct seq_file *p); int (*irq_request_resources)(struct irq_data *data); void (*irq_release_resources)(struct irq_data *data); void (*irq_compose_msi_msg)(struct irq_data *data, struct msi_msg *msg); void (*irq_write_msi_msg)(struct irq_data *data, struct msi_msg *msg); int (*irq_get_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool *state); int (*irq_set_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool state); int (*irq_set_vcpu_affinity)(struct irq_data *data, void *vcpu_info); void (*ipi_send_single)(struct irq_data *data, unsigned int cpu); void (*ipi_send_mask)(struct irq_data *data, const struct cpumask *dest); int (*irq_nmi_setup)(struct irq_data *data); void (*irq_nmi_teardown)(struct irq_data *data); void (*irq_force_complete_move)(struct irq_data *data); unsigned long flags; }; /* * irq_chip specific flags * * IRQCHIP_SET_TYPE_MASKED: Mask before calling chip.irq_set_type() * IRQCHIP_EOI_IF_HANDLED: Only issue irq_eoi() when irq was handled * IRQCHIP_MASK_ON_SUSPEND: Mask non wake irqs in the suspend path * IRQCHIP_ONOFFLINE_ENABLED: Only call irq_on/off_line callbacks * when irq enabled * IRQCHIP_SKIP_SET_WAKE: Skip chip.irq_set_wake(), for this irq chip * IRQCHIP_ONESHOT_SAFE: One shot does not require mask/unmask * IRQCHIP_EOI_THREADED: Chip requires eoi() on unmask in threaded mode * IRQCHIP_SUPPORTS_LEVEL_MSI: Chip can provide two doorbells for Level MSIs * IRQCHIP_SUPPORTS_NMI: Chip can deliver NMIs, only for root irqchips * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup * IRQCHIP_IMMUTABLE: Don't ever change anything in this chip * IRQCHIP_MOVE_DEFERRED: Move the interrupt in actual interrupt context */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), IRQCHIP_EOI_IF_HANDLED = (1 << 1), IRQCHIP_MASK_ON_SUSPEND = (1 << 2), IRQCHIP_ONOFFLINE_ENABLED = (1 << 3), IRQCHIP_SKIP_SET_WAKE = (1 << 4), IRQCHIP_ONESHOT_SAFE = (1 << 5), IRQCHIP_EOI_THREADED = (1 << 6), IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7), IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), IRQCHIP_IMMUTABLE = (1 << 11), IRQCHIP_MOVE_DEFERRED = (1 << 12), }; #include <linux/irqdesc.h> /* * Pick up the arch-dependent methods: */ #include <asm/hw_irq.h> #ifndef NR_IRQS_LEGACY # define NR_IRQS_LEGACY 0 #endif #ifndef ARCH_IRQ_INIT_FLAGS # define ARCH_IRQ_INIT_FLAGS 0 #endif #define IRQ_DEFAULT_INIT_FLAGS ARCH_IRQ_INIT_FLAGS #ifdef CONFIG_DEPRECATED_IRQ_CPU_ONOFFLINE extern void irq_cpu_online(void); extern void irq_cpu_offline(void); #endif extern int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *cpumask, bool force); extern int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info); #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_IRQ_MIGRATION) extern void irq_migrate_all_off_this_cpu(void); extern int irq_affinity_online_cpu(unsigned int cpu); #else # define irq_affinity_online_cpu NULL #endif #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ) bool irq_can_move_in_process_context(struct irq_data *data); void __irq_move_irq(struct irq_data *data); static inline void irq_move_irq(struct irq_data *data) { if (unlikely(irqd_is_setaffinity_pending(data))) __irq_move_irq(data); } void irq_move_masked_irq(struct irq_data *data); #else static inline bool irq_can_move_in_process_context(struct irq_data *data) { return true; } static inline void irq_move_irq(struct irq_data *data) { } static inline void irq_move_masked_irq(struct irq_data *data) { } #endif extern int no_irq_affinity; #ifdef CONFIG_HARDIRQS_SW_RESEND int irq_set_parent(int irq, int parent_irq); #else static inline int irq_set_parent(int irq, int parent_irq) { return 0; } #endif /* * Built-in IRQ handlers for various IRQ types, * callable via desc->handle_irq() */ extern void handle_level_irq(struct irq_desc *desc); extern void handle_fasteoi_irq(struct irq_desc *desc); extern void handle_edge_irq(struct irq_desc *desc); extern void handle_edge_eoi_irq(struct irq_desc *desc); extern void handle_simple_irq(struct irq_desc *desc); extern void handle_untracked_irq(struct irq_desc *desc); extern void handle_percpu_irq(struct irq_desc *desc); extern void handle_percpu_devid_irq(struct irq_desc *desc); extern void handle_bad_irq(struct irq_desc *desc); extern void handle_nested_irq(unsigned int irq); extern void handle_fasteoi_nmi(struct irq_desc *desc); extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); extern int irq_chip_pm_get(struct irq_data *data); extern void irq_chip_pm_put(struct irq_data *data); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY extern void handle_fasteoi_ack_irq(struct irq_desc *desc); extern void handle_fasteoi_mask_irq(struct irq_desc *desc); extern int irq_chip_set_parent_state(struct irq_data *data, enum irqchip_irq_state which, bool val); extern int irq_chip_get_parent_state(struct irq_data *data, enum irqchip_irq_state which, bool *state); extern void irq_chip_shutdown_parent(struct irq_data *data); extern unsigned int irq_chip_startup_parent(struct irq_data *data); extern void irq_chip_enable_parent(struct irq_data *data); extern void irq_chip_disable_parent(struct irq_data *data); extern void irq_chip_ack_parent(struct irq_data *data); extern int irq_chip_retrigger_hierarchy(struct irq_data *data); extern void irq_chip_mask_parent(struct irq_data *data); extern void irq_chip_mask_ack_parent(struct irq_data *data); extern void irq_chip_unmask_parent(struct irq_data *data); extern void irq_chip_eoi_parent(struct irq_data *data); extern int irq_chip_set_affinity_parent(struct irq_data *data, const struct cpumask *dest, bool force); extern int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on); extern int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info); extern int irq_chip_set_type_parent(struct irq_data *data, unsigned int type); extern int irq_chip_request_resources_parent(struct irq_data *data); extern void irq_chip_release_resources_parent(struct irq_data *data); #ifdef CONFIG_SMP void irq_chip_pre_redirect_parent(struct irq_data *data); #endif #endif #ifdef CONFIG_SMP int irq_chip_redirect_set_affinity(struct irq_data *data, const struct cpumask *dest, bool force); #endif /* Disable or mask interrupts during a kernel kexec */ extern void machine_kexec_mask_interrupts(void); /* Handling of unhandled and spurious interrupts: */ extern void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret); /* Enable/disable irq debugging output: */ extern int noirqdebug_setup(char *str); /* Checks whether the interrupt can be requested by request_irq(): */ extern bool can_request_irq(unsigned int irq, unsigned long irqflags); /* Dummy irq-chip implementations: */ extern struct irq_chip no_irq_chip; extern struct irq_chip dummy_irq_chip; extern void irq_set_chip_and_handler_name(unsigned int irq, const struct irq_chip *chip, irq_flow_handler_t handle, const char *name); static inline void irq_set_chip_and_handler(unsigned int irq, const struct irq_chip *chip, irq_flow_handler_t handle) { irq_set_chip_and_handler_name(irq, chip, handle, NULL); } extern int irq_set_percpu_devid(unsigned int irq); extern void __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, const char *name); static inline void irq_set_handler(unsigned int irq, irq_flow_handler_t handle) { __irq_set_handler(irq, handle, 0, NULL); } /* * Set a highlevel chained flow handler for a given IRQ. * (a chained handler is automatically enabled and set to * IRQ_NOREQUEST, IRQ_NOPROBE, and IRQ_NOTHREAD) */ static inline void irq_set_chained_handler(unsigned int irq, irq_flow_handler_t handle) { __irq_set_handler(irq, handle, 1, NULL); } /* * Set a highlevel chained flow handler and its data for a given IRQ. * (a chained handler is automatically enabled and set to * IRQ_NOREQUEST, IRQ_NOPROBE, and IRQ_NOTHREAD) */ void irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle, void *data); void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set); static inline void irq_set_status_flags(unsigned int irq, unsigned long set) { irq_modify_status(irq, 0, set); } static inline void irq_clear_status_flags(unsigned int irq, unsigned long clr) { irq_modify_status(irq, clr, 0); } static inline void irq_set_noprobe(unsigned int irq) { irq_modify_status(irq, 0, IRQ_NOPROBE); } static inline void irq_set_probe(unsigned int irq) { irq_modify_status(irq, IRQ_NOPROBE, 0); } static inline void irq_set_nothread(unsigned int irq) { irq_modify_status(irq, 0, IRQ_NOTHREAD); } static inline void irq_set_thread(unsigned int irq) { irq_modify_status(irq, IRQ_NOTHREAD, 0); } static inline void irq_set_nested_thread(unsigned int irq, bool nest) { if (nest) irq_set_status_flags(irq, IRQ_NESTED_THREAD); else irq_clear_status_flags(irq, IRQ_NESTED_THREAD); } static inline void irq_set_percpu_devid_flags(unsigned int irq) { irq_set_status_flags(irq, IRQ_NOAUTOEN | IRQ_PER_CPU | IRQ_NOTHREAD | IRQ_NOPROBE | IRQ_PER_CPU_DEVID); } /* Set/get chip/data for an IRQ: */ extern int irq_set_chip(unsigned int irq, const struct irq_chip *chip); extern int irq_set_handler_data(unsigned int irq, void *data); extern int irq_set_chip_data(unsigned int irq, void *data); extern int irq_set_irq_type(unsigned int irq, unsigned int type); extern int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry); extern int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset, struct msi_desc *entry); extern struct irq_data *irq_get_irq_data(unsigned int irq); static inline struct irq_chip *irq_get_chip(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); return d ? d->chip : NULL; } static inline struct irq_chip *irq_data_get_irq_chip(struct irq_data *d) { return d->chip; } static inline void *irq_get_chip_data(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); return d ? d->chip_data : NULL; } static inline void *irq_data_get_irq_chip_data(struct irq_data *d) { return d->chip_data; } static inline void *irq_get_handler_data(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); return d ? d->common->handler_data : NULL; } static inline void *irq_data_get_irq_handler_data(struct irq_data *d) { return d->common->handler_data; } static inline struct msi_desc *irq_get_msi_desc(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); return d ? d->common->msi_desc : NULL; } static inline struct msi_desc *irq_data_get_msi_desc(struct irq_data *d) { return d->common->msi_desc; } static inline u32 irq_get_trigger_type(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); return d ? irqd_get_trigger_type(d) : 0; } static inline int irq_common_data_get_node(struct irq_common_data *d) { #ifdef CONFIG_NUMA return d->node; #else return 0; #endif } static inline int irq_data_get_node(struct irq_data *d) { return irq_common_data_get_node(d->common); } static inline const struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) { #ifdef CONFIG_SMP return d->common->affinity; #else return cpumask_of(0); #endif } static inline void irq_data_update_affinity(struct irq_data *d, const struct cpumask *m) { #ifdef CONFIG_SMP cpumask_copy(d->common->affinity, m); #endif } static inline const struct cpumask *irq_get_affinity_mask(int irq) { struct irq_data *d = irq_get_irq_data(irq); return d ? irq_data_get_affinity_mask(d) : NULL; } #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK static inline const struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) { return d->common->effective_affinity; } static inline void irq_data_update_effective_affinity(struct irq_data *d, const struct cpumask *m) { cpumask_copy(d->common->effective_affinity, m); } #else static inline void irq_data_update_effective_affinity(struct irq_data *d, const struct cpumask *m) { } static inline const struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) { return irq_data_get_affinity_mask(d); } #endif static inline const struct cpumask *irq_get_effective_affinity_mask(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); return d ? irq_data_get_effective_affinity_mask(d) : NULL; } unsigned int arch_dynirq_lower_bound(unsigned int from); int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, struct module *owner, const struct irq_affinity_desc *affinity); int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from, unsigned int cnt, int node, struct module *owner, const struct irq_affinity_desc *affinity); /* use macros to avoid needing export.h for THIS_MODULE */ #define irq_alloc_descs(irq, from, cnt, node) \ __irq_alloc_descs(irq, from, cnt, node, THIS_MODULE, NULL) #define irq_alloc_desc(node) \ irq_alloc_descs(-1, 1, 1, node) #define irq_alloc_desc_at(at, node) \ irq_alloc_descs(at, at, 1, node) #define irq_alloc_desc_from(from, node) \ irq_alloc_descs(-1, from, 1, node) #define irq_alloc_descs_from(from, cnt, node) \ irq_alloc_descs(-1, from, cnt, node) #define devm_irq_alloc_descs(dev, irq, from, cnt, node) \ __devm_irq_alloc_descs(dev, irq, from, cnt, node, THIS_MODULE, NULL) #define devm_irq_alloc_desc(dev, node) \ devm_irq_alloc_descs(dev, -1, 1, 1, node) #define devm_irq_alloc_desc_at(dev, at, node) \ devm_irq_alloc_descs(dev, at, at, 1, node) #define devm_irq_alloc_desc_from(dev, from, node) \ devm_irq_alloc_descs(dev, -1, from, 1, node) #define devm_irq_alloc_descs_from(dev, from, cnt, node) \ devm_irq_alloc_descs(dev, -1, from, cnt, node) void irq_free_descs(unsigned int irq, unsigned int cnt); static inline void irq_free_desc(unsigned int irq) { irq_free_descs(irq, 1); } /** * struct irq_chip_regs - register offsets for struct irq_gci * @enable: Enable register offset to reg_base * @disable: Disable register offset to reg_base * @mask: Mask register offset to reg_base * @ack: Ack register offset to reg_base * @eoi: Eoi register offset to reg_base * @type: Type configuration register offset to reg_base */ struct irq_chip_regs { unsigned long enable; unsigned long disable; unsigned long mask; unsigned long ack; unsigned long eoi; unsigned long type; }; /** * struct irq_chip_type - Generic interrupt chip instance for a flow type * @chip: The real interrupt chip which provides the callbacks * @regs: Register offsets for this chip * @handler: Flow handler associated with this chip * @type: Chip can handle these flow types * @mask_cache_priv: Cached mask register private to the chip type * @mask_cache: Pointer to cached mask register * * A irq_generic_chip can have several instances of irq_chip_type when * it requires different functions and register offsets for different * flow types. */ struct irq_chip_type { struct irq_chip chip; struct irq_chip_regs regs; irq_flow_handler_t handler; u32 type; u32 mask_cache_priv; u32 *mask_cache; }; /** * struct irq_chip_generic - Generic irq chip data structure * @lock: Lock to protect register and cache data access * @reg_base: Register base address (virtual) * @reg_readl: Alternate I/O accessor (defaults to readl if NULL) * @reg_writel: Alternate I/O accessor (defaults to writel if NULL) * @suspend: Function called from core code on suspend once per * chip; can be useful instead of irq_chip::suspend to * handle chip details even when no interrupts are in use * @resume: Function called from core code on resume once per chip; * can be useful instead of irq_chip::suspend to handle * chip details even when no interrupts are in use * @irq_base: Interrupt base nr for this chip * @irq_cnt: Number of interrupts handled by this chip * @mask_cache: Cached mask register shared between all chip types * @wake_enabled: Interrupt can wakeup from suspend * @wake_active: Interrupt is marked as an wakeup from suspend source * @num_ct: Number of available irq_chip_type instances (usually 1) * @private: Private data for non generic chip callbacks * @installed: bitfield to denote installed interrupts * @unused: bitfield to denote unused interrupts * @domain: irq domain pointer * @list: List head for keeping track of instances * @chip_types: Array of interrupt irq_chip_types * * Note, that irq_chip_generic can have multiple irq_chip_type * implementations which can be associated to a particular irq line of * an irq_chip_generic instance. That allows to share and protect * state in an irq_chip_generic instance when we need to implement * different flow mechanisms (level/edge) for it. */ struct irq_chip_generic { raw_spinlock_t lock; void __iomem *reg_base; u32 (*reg_readl)(void __iomem *addr); void (*reg_writel)(u32 val, void __iomem *addr); void (*suspend)(struct irq_chip_generic *gc); void (*resume)(struct irq_chip_generic *gc); unsigned int irq_base; unsigned int irq_cnt; u32 mask_cache; u32 wake_enabled; u32 wake_active; unsigned int num_ct; void *private; unsigned long installed; unsigned long unused; struct irq_domain *domain; struct list_head list; struct irq_chip_type chip_types[]; }; /** * enum irq_gc_flags - Initialization flags for generic irq chips * @IRQ_GC_INIT_MASK_CACHE: Initialize the mask_cache by reading mask reg * @IRQ_GC_INIT_NESTED_LOCK: Set the lock class of the irqs to nested for * irq chips which need to call irq_set_wake() on * the parent irq. Usually GPIO implementations * @IRQ_GC_MASK_CACHE_PER_TYPE: Mask cache is chip type private * @IRQ_GC_NO_MASK: Do not calculate irq_data->mask * @IRQ_GC_BE_IO: Use big-endian register accesses (default: LE) */ enum irq_gc_flags { IRQ_GC_INIT_MASK_CACHE = 1 << 0, IRQ_GC_INIT_NESTED_LOCK = 1 << 1, IRQ_GC_MASK_CACHE_PER_TYPE = 1 << 2, IRQ_GC_NO_MASK = 1 << 3, IRQ_GC_BE_IO = 1 << 4, }; /* * struct irq_domain_chip_generic - Generic irq chip data structure for irq domains * @irqs_per_chip: Number of interrupts per chip * @num_chips: Number of chips * @irq_flags_to_set: IRQ* flags to set on irq setup * @irq_flags_to_clear: IRQ* flags to clear on irq setup * @gc_flags: Generic chip specific setup flags * @exit: Function called on each chip when they are destroyed. * @gc: Array of pointers to generic interrupt chips */ struct irq_domain_chip_generic { unsigned int irqs_per_chip; unsigned int num_chips; unsigned int irq_flags_to_clear; unsigned int irq_flags_to_set; enum irq_gc_flags gc_flags; void (*exit)(struct irq_chip_generic *gc); struct irq_chip_generic *gc[]; }; /** * struct irq_domain_chip_generic_info - Generic chip information structure * @name: Name of the generic interrupt chip * @handler: Interrupt handler used by the generic interrupt chip * @irqs_per_chip: Number of interrupts each chip handles (max 32) * @num_ct: Number of irq_chip_type instances associated with each * chip * @irq_flags_to_clear: IRQ_* bits to clear in the mapping function * @irq_flags_to_set: IRQ_* bits to set in the mapping function * @gc_flags: Generic chip specific setup flags * @init: Function called on each chip when they are created. * Allow to do some additional chip initialisation. * @exit: Function called on each chip when they are destroyed. * Allow to do some chip cleanup operation. */ struct irq_domain_chip_generic_info { const char *name; irq_flow_handler_t handler; unsigned int irqs_per_chip; unsigned int num_ct; unsigned int irq_flags_to_clear; unsigned int irq_flags_to_set; enum irq_gc_flags gc_flags; int (*init)(struct irq_chip_generic *gc); void (*exit)(struct irq_chip_generic *gc); }; /* Generic chip callback functions */ void irq_gc_noop(struct irq_data *d); void irq_gc_mask_disable_reg(struct irq_data *d); void irq_gc_mask_set_bit(struct irq_data *d); void irq_gc_mask_clr_bit(struct irq_data *d); void irq_gc_unmask_enable_reg(struct irq_data *d); void irq_gc_ack_set_bit(struct irq_data *d); void irq_gc_ack_clr_bit(struct irq_data *d); void irq_gc_mask_disable_and_ack_set(struct irq_data *d); void irq_gc_eoi(struct irq_data *d); int irq_gc_set_wake(struct irq_data *d, unsigned int on); /* Setup functions for irq_chip_generic */ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq, irq_hw_number_t hw_irq); void irq_unmap_generic_chip(struct irq_domain *d, unsigned int virq); struct irq_chip_generic * irq_alloc_generic_chip(const char *name, int nr_ct, unsigned int irq_base, void __iomem *reg_base, irq_flow_handler_t handler); void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk, enum irq_gc_flags flags, unsigned int clr, unsigned int set); int irq_setup_alt_chip(struct irq_data *d, unsigned int type); void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk, unsigned int clr, unsigned int set); struct irq_chip_generic * devm_irq_alloc_generic_chip(struct device *dev, const char *name, int num_ct, unsigned int irq_base, void __iomem *reg_base, irq_flow_handler_t handler); int devm_irq_setup_generic_chip(struct device *dev, struct irq_chip_generic *gc, u32 msk, enum irq_gc_flags flags, unsigned int clr, unsigned int set); struct irq_chip_generic *irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq); #ifdef CONFIG_GENERIC_IRQ_CHIP int irq_domain_alloc_generic_chips(struct irq_domain *d, const struct irq_domain_chip_generic_info *info); void irq_domain_remove_generic_chips(struct irq_domain *d); #else static inline int irq_domain_alloc_generic_chips(struct irq_domain *d, const struct irq_domain_chip_generic_info *info) { return -EINVAL; } static inline void irq_domain_remove_generic_chips(struct irq_domain *d) { } #endif /* CONFIG_GENERIC_IRQ_CHIP */ int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, int num_ct, const char *name, irq_flow_handler_t handler, unsigned int clr, unsigned int set, enum irq_gc_flags flags); #define irq_alloc_domain_generic_chips(d, irqs_per_chip, num_ct, name, \ handler, clr, set, flags) \ ({ \ MAYBE_BUILD_BUG_ON(irqs_per_chip > 32); \ __irq_alloc_domain_generic_chips(d, irqs_per_chip, num_ct, name,\ handler, clr, set, flags); \ }) static inline void irq_free_generic_chip(struct irq_chip_generic *gc) { kfree(gc); } static inline void irq_destroy_generic_chip(struct irq_chip_generic *gc, u32 msk, unsigned int clr, unsigned int set) { irq_remove_generic_chip(gc, msk, clr, set); irq_free_generic_chip(gc); } static inline struct irq_chip_type *irq_data_get_chip_type(struct irq_data *d) { return container_of(d->chip, struct irq_chip_type, chip); } #define IRQ_MSK(n) (u32)((n) < 32 ? ((1 << (n)) - 1) : UINT_MAX) static inline void irq_reg_writel(struct irq_chip_generic *gc, u32 val, int reg_offset) { if (gc->reg_writel) gc->reg_writel(val, gc->reg_base + reg_offset); else writel(val, gc->reg_base + reg_offset); } static inline u32 irq_reg_readl(struct irq_chip_generic *gc, int reg_offset) { if (gc->reg_readl) return gc->reg_readl(gc->reg_base + reg_offset); else return readl(gc->reg_base + reg_offset); } struct irq_matrix; struct irq_matrix *irq_alloc_matrix(unsigned int matrix_bits, unsigned int alloc_start, unsigned int alloc_end); void irq_matrix_online(struct irq_matrix *m); void irq_matrix_offline(struct irq_matrix *m); void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit, bool replace); int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk); void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk); int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, unsigned int *mapped_cpu); void irq_matrix_reserve(struct irq_matrix *m); void irq_matrix_remove_reserved(struct irq_matrix *m); int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk, bool reserved, unsigned int *mapped_cpu); void irq_matrix_free(struct irq_matrix *m, unsigned int cpu, unsigned int bit, bool managed); void irq_matrix_assign(struct irq_matrix *m, unsigned int bit); unsigned int irq_matrix_available(struct irq_matrix *m, bool cpudown); unsigned int irq_matrix_allocated(struct irq_matrix *m); unsigned int irq_matrix_reserved(struct irq_matrix *m); void irq_matrix_debug_show(struct seq_file *sf, struct irq_matrix *m, int ind); /* Contrary to Linux irqs, for hardware irqs the irq number 0 is valid */ #define INVALID_HWIRQ (~0UL) irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu); int __ipi_send_single(struct irq_desc *desc, unsigned int cpu); int __ipi_send_mask(struct irq_desc *desc, const struct cpumask *dest); int ipi_send_single(unsigned int virq, unsigned int cpu); int ipi_send_mask(unsigned int virq, const struct cpumask *dest); void ipi_mux_process(void); int ipi_mux_create(unsigned int nr_ipi, void (*mux_send)(unsigned int cpu)); #ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER /* * Registers a generic IRQ handling function as the top-level IRQ handler in * the system, which is generally the first C code called from an assembly * architecture-specific interrupt handler. * * Returns 0 on success, or -EBUSY if an IRQ handler has already been * registered. */ int __init set_handle_irq(void (*handle_irq)(struct pt_regs *)); /* * Allows interrupt handlers to find the irqchip that's been registered as the * top-level IRQ handler. */ extern void (*handle_arch_irq)(struct pt_regs *) __ro_after_init; asmlinkage void generic_handle_arch_irq(struct pt_regs *regs); #else #ifndef set_handle_irq #define set_handle_irq(handle_irq) \ do { \ (void)handle_irq; \ WARN_ON(1); \ } while (0) #endif #endif #endif /* _LINUX_IRQ_H */ |
| 1554 1227 1227 1227 178 177 1553 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Monitoring code for network dropped packet alerts * * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> #include <linux/if_arp.h> #include <linux/inetdevice.h> #include <linux/inet.h> #include <linux/interrupt.h> #include <linux/netpoll.h> #include <linux/sched.h> #include <linux/delay.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/netlink.h> #include <linux/net_dropmon.h> #include <linux/bitfield.h> #include <linux/percpu.h> #include <linux/timer.h> #include <linux/bitops.h> #include <linux/slab.h> #include <linux/module.h> #include <net/genetlink.h> #include <net/netevent.h> #include <net/flow_offload.h> #include <net/dropreason.h> #include <net/devlink.h> #include <trace/events/skb.h> #include <trace/events/napi.h> #include <trace/events/devlink.h> #include <linux/unaligned.h> #define TRACE_ON 1 #define TRACE_OFF 0 /* * Globals, our netlink socket pointer * and the work handle that will send up * netlink alerts */ static int trace_state = TRACE_OFF; static bool monitor_hw; /* net_dm_mutex * * An overall lock guarding every operation coming from userspace. */ static DEFINE_MUTEX(net_dm_mutex); struct net_dm_stats { u64_stats_t dropped; struct u64_stats_sync syncp; }; #define NET_DM_MAX_HW_TRAP_NAME_LEN 40 struct net_dm_hw_entry { char trap_name[NET_DM_MAX_HW_TRAP_NAME_LEN]; u32 count; }; struct net_dm_hw_entries { u32 num_entries; struct net_dm_hw_entry entries[]; }; struct per_cpu_dm_data { raw_spinlock_t lock; /* Protects 'skb', 'hw_entries' and * 'send_timer' */ union { struct sk_buff *skb; struct net_dm_hw_entries *hw_entries; }; struct sk_buff_head drop_queue; struct work_struct dm_alert_work; struct timer_list send_timer; struct net_dm_stats stats; }; struct dm_hw_stat_delta { unsigned long last_rx; unsigned long last_drop_val; struct rcu_head rcu; }; static struct genl_family net_drop_monitor_family; static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_hw_cpu_data); static int dm_hit_limit = 64; static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static enum net_dm_alert_mode net_dm_alert_mode = NET_DM_ALERT_MODE_SUMMARY; static u32 net_dm_trunc_len; static u32 net_dm_queue_len = 1000; struct net_dm_alert_ops { void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb, void *location, enum skb_drop_reason reason, const struct sock *rx_sk); void (*napi_poll_probe)(void *ignore, struct napi_struct *napi, int work, int budget); void (*work_item_func)(struct work_struct *work); void (*hw_work_item_func)(struct work_struct *work); void (*hw_trap_probe)(void *ignore, const struct devlink *devlink, struct sk_buff *skb, const struct devlink_trap_metadata *metadata); }; struct net_dm_skb_cb { union { struct devlink_trap_metadata *hw_metadata; void *pc; }; enum skb_drop_reason reason; }; #define NET_DM_SKB_CB(__skb) ((struct net_dm_skb_cb *)&((__skb)->cb[0])) static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; struct net_dm_alert_msg *msg; struct nlattr *nla; struct sk_buff *skb; unsigned long flags; void *msg_header; al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); al += sizeof(struct nlattr); skb = genlmsg_new(al, GFP_KERNEL); if (!skb) goto err; msg_header = genlmsg_put(skb, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_ALERT); if (!msg_header) { nlmsg_free(skb); skb = NULL; goto err; } nla = nla_reserve(skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg)); if (!nla) { nlmsg_free(skb); skb = NULL; goto err; } msg = nla_data(nla); memset(msg, 0, al); goto out; err: mod_timer(&data->send_timer, jiffies + HZ / 10); out: raw_spin_lock_irqsave(&data->lock, flags); swap(data->skb, skb); raw_spin_unlock_irqrestore(&data->lock, flags); if (skb) { struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data; struct genlmsghdr *gnlh = (struct genlmsghdr *)nlmsg_data(nlh); genlmsg_end(skb, genlmsg_data(gnlh)); } return skb; } static const struct genl_multicast_group dropmon_mcgrps[] = { { .name = "events", .flags = GENL_MCAST_CAP_SYS_ADMIN, }, }; static void send_dm_alert(struct work_struct *work) { struct sk_buff *skb; struct per_cpu_dm_data *data; data = container_of(work, struct per_cpu_dm_data, dm_alert_work); skb = reset_per_cpu_data(data); if (skb) genlmsg_multicast(&net_drop_monitor_family, skb, 0, 0, GFP_KERNEL); } /* * This is the timer function to delay the sending of an alert * in the event that more drops will arrive during the * hysteresis period. */ static void sched_send_work(struct timer_list *t) { struct per_cpu_dm_data *data = timer_container_of(data, t, send_timer); schedule_work(&data->dm_alert_work); } static void trace_drop_common(struct sk_buff *skb, void *location) { struct net_dm_alert_msg *msg; struct net_dm_drop_point *point; struct nlmsghdr *nlh; struct nlattr *nla; int i; struct sk_buff *dskb; struct per_cpu_dm_data *data; unsigned long flags; local_irq_save(flags); data = this_cpu_ptr(&dm_cpu_data); raw_spin_lock(&data->lock); dskb = data->skb; if (!dskb) goto out; nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); point = msg->points; for (i = 0; i < msg->entries; i++) { if (!memcmp(&location, &point->pc, sizeof(void *))) { point->count++; goto out; } point++; } if (msg->entries == dm_hit_limit) goto out; /* * We need to create a new entry */ __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); memcpy(point->pc, &location, sizeof(void *)); point->count = 1; msg->entries++; if (!timer_pending(&data->send_timer)) { data->send_timer.expires = jiffies + dm_delay * HZ; add_timer(&data->send_timer); } out: raw_spin_unlock_irqrestore(&data->lock, flags); } static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location, enum skb_drop_reason reason, const struct sock *rx_sk) { trace_drop_common(skb, location); } static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi, int work, int budget) { struct net_device *dev = napi->dev; struct dm_hw_stat_delta *stat; /* * Don't check napi structures with no associated device */ if (!dev) return; rcu_read_lock(); stat = rcu_dereference(dev->dm_private); if (stat) { /* * only add a note to our monitor buffer if: * 1) its after the last_rx delta * 2) our rx_dropped count has gone up */ if (time_after(jiffies, stat->last_rx + dm_hw_check_delta) && (dev->stats.rx_dropped != stat->last_drop_val)) { trace_drop_common(NULL, NULL); stat->last_drop_val = dev->stats.rx_dropped; stat->last_rx = jiffies; } } rcu_read_unlock(); } static struct net_dm_hw_entries * net_dm_hw_reset_per_cpu_data(struct per_cpu_dm_data *hw_data) { struct net_dm_hw_entries *hw_entries; unsigned long flags; hw_entries = kzalloc_flex(*hw_entries, entries, dm_hit_limit); if (!hw_entries) { /* If the memory allocation failed, we try to perform another * allocation in 1/10 second. Otherwise, the probe function * will constantly bail out. */ mod_timer(&hw_data->send_timer, jiffies + HZ / 10); } raw_spin_lock_irqsave(&hw_data->lock, flags); swap(hw_data->hw_entries, hw_entries); raw_spin_unlock_irqrestore(&hw_data->lock, flags); return hw_entries; } static int net_dm_hw_entry_put(struct sk_buff *msg, const struct net_dm_hw_entry *hw_entry) { struct nlattr *attr; attr = nla_nest_start(msg, NET_DM_ATTR_HW_ENTRY); if (!attr) return -EMSGSIZE; if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_NAME, hw_entry->trap_name)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_HW_TRAP_COUNT, hw_entry->count)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_hw_entries_put(struct sk_buff *msg, const struct net_dm_hw_entries *hw_entries) { struct nlattr *attr; int i; attr = nla_nest_start(msg, NET_DM_ATTR_HW_ENTRIES); if (!attr) return -EMSGSIZE; for (i = 0; i < hw_entries->num_entries; i++) { int rc; rc = net_dm_hw_entry_put(msg, &hw_entries->entries[i]); if (rc) goto nla_put_failure; } nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_hw_summary_report_fill(struct sk_buff *msg, const struct net_dm_hw_entries *hw_entries) { struct net_dm_alert_msg anc_hdr = { 0 }; void *hdr; int rc; hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_ALERT); if (!hdr) return -EMSGSIZE; /* We need to put the ancillary header in order not to break user * space. */ if (nla_put(msg, NLA_UNSPEC, sizeof(anc_hdr), &anc_hdr)) goto nla_put_failure; rc = net_dm_hw_entries_put(msg, hw_entries); if (rc) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void net_dm_hw_summary_work(struct work_struct *work) { struct net_dm_hw_entries *hw_entries; struct per_cpu_dm_data *hw_data; struct sk_buff *msg; int rc; hw_data = container_of(work, struct per_cpu_dm_data, dm_alert_work); hw_entries = net_dm_hw_reset_per_cpu_data(hw_data); if (!hw_entries) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) goto out; rc = net_dm_hw_summary_report_fill(msg, hw_entries); if (rc) { nlmsg_free(msg); goto out; } genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); out: kfree(hw_entries); } static void net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink, struct sk_buff *skb, const struct devlink_trap_metadata *metadata) { struct net_dm_hw_entries *hw_entries; struct net_dm_hw_entry *hw_entry; struct per_cpu_dm_data *hw_data; unsigned long flags; int i; if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL) return; hw_data = this_cpu_ptr(&dm_hw_cpu_data); raw_spin_lock_irqsave(&hw_data->lock, flags); hw_entries = hw_data->hw_entries; if (!hw_entries) goto out; for (i = 0; i < hw_entries->num_entries; i++) { hw_entry = &hw_entries->entries[i]; if (!strncmp(hw_entry->trap_name, metadata->trap_name, NET_DM_MAX_HW_TRAP_NAME_LEN - 1)) { hw_entry->count++; goto out; } } if (WARN_ON_ONCE(hw_entries->num_entries == dm_hit_limit)) goto out; hw_entry = &hw_entries->entries[hw_entries->num_entries]; strscpy(hw_entry->trap_name, metadata->trap_name, NET_DM_MAX_HW_TRAP_NAME_LEN - 1); hw_entry->count = 1; hw_entries->num_entries++; if (!timer_pending(&hw_data->send_timer)) { hw_data->send_timer.expires = jiffies + dm_delay * HZ; add_timer(&hw_data->send_timer); } out: raw_spin_unlock_irqrestore(&hw_data->lock, flags); } static const struct net_dm_alert_ops net_dm_alert_summary_ops = { .kfree_skb_probe = trace_kfree_skb_hit, .napi_poll_probe = trace_napi_poll_hit, .work_item_func = send_dm_alert, .hw_work_item_func = net_dm_hw_summary_work, .hw_trap_probe = net_dm_hw_trap_summary_probe, }; static void net_dm_packet_trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location, enum skb_drop_reason reason, const struct sock *rx_sk) { ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *data; struct net_dm_skb_cb *cb; struct sk_buff *nskb; unsigned long flags; if (!skb_mac_header_was_set(skb)) return; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return; cb = NET_DM_SKB_CB(nskb); cb->reason = reason; cb->pc = location; /* Override the timestamp because we care about the time when the * packet was dropped. */ nskb->tstamp = tstamp; data = this_cpu_ptr(&dm_cpu_data); spin_lock_irqsave(&data->drop_queue.lock, flags); if (skb_queue_len(&data->drop_queue) < net_dm_queue_len) __skb_queue_tail(&data->drop_queue, nskb); else goto unlock_free; spin_unlock_irqrestore(&data->drop_queue.lock, flags); schedule_work(&data->dm_alert_work); return; unlock_free: spin_unlock_irqrestore(&data->drop_queue.lock, flags); u64_stats_update_begin(&data->stats.syncp); u64_stats_inc(&data->stats.dropped); u64_stats_update_end(&data->stats.syncp); consume_skb(nskb); } static void net_dm_packet_trace_napi_poll_hit(void *ignore, struct napi_struct *napi, int work, int budget) { } static size_t net_dm_in_port_size(void) { /* NET_DM_ATTR_IN_PORT nest */ return nla_total_size(0) + /* NET_DM_ATTR_PORT_NETDEV_IFINDEX */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PORT_NETDEV_NAME */ nla_total_size(IFNAMSIZ + 1); } #define NET_DM_MAX_SYMBOL_LEN 40 #define NET_DM_MAX_REASON_LEN 50 static size_t net_dm_packet_report_size(size_t payload_len) { size_t size; size = nlmsg_msg_size(GENL_HDRLEN + net_drop_monitor_family.hdrsize); return NLMSG_ALIGN(size) + /* NET_DM_ATTR_ORIGIN */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_PC */ nla_total_size(sizeof(u64)) + /* NET_DM_ATTR_SYMBOL */ nla_total_size(NET_DM_MAX_SYMBOL_LEN + 1) + /* NET_DM_ATTR_IN_PORT */ net_dm_in_port_size() + /* NET_DM_ATTR_TIMESTAMP */ nla_total_size(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PROTO */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_REASON */ nla_total_size(NET_DM_MAX_REASON_LEN + 1) + /* NET_DM_ATTR_PAYLOAD */ nla_total_size(payload_len); } static int net_dm_packet_report_in_port_put(struct sk_buff *msg, int ifindex, const char *name) { struct nlattr *attr; attr = nla_nest_start(msg, NET_DM_ATTR_IN_PORT); if (!attr) return -EMSGSIZE; if (ifindex && nla_put_u32(msg, NET_DM_ATTR_PORT_NETDEV_IFINDEX, ifindex)) goto nla_put_failure; if (name && nla_put_string(msg, NET_DM_ATTR_PORT_NETDEV_NAME, name)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, size_t payload_len) { struct net_dm_skb_cb *cb = NET_DM_SKB_CB(skb); const struct drop_reason_list *list = NULL; unsigned int subsys, subsys_reason; char buf[NET_DM_MAX_SYMBOL_LEN]; struct nlattr *attr; void *hdr; int rc; hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_PACKET_ALERT); if (!hdr) return -EMSGSIZE; if (nla_put_u16(msg, NET_DM_ATTR_ORIGIN, NET_DM_ORIGIN_SW)) goto nla_put_failure; if (nla_put_u64_64bit(msg, NET_DM_ATTR_PC, (u64)(uintptr_t)cb->pc, NET_DM_ATTR_PAD)) goto nla_put_failure; rcu_read_lock(); subsys = u32_get_bits(cb->reason, SKB_DROP_REASON_SUBSYS_MASK); if (subsys < SKB_DROP_REASON_SUBSYS_NUM) list = rcu_dereference(drop_reasons_by_subsys[subsys]); subsys_reason = cb->reason & ~SKB_DROP_REASON_SUBSYS_MASK; if (!list || subsys_reason >= list->n_reasons || !list->reasons[subsys_reason] || strlen(list->reasons[subsys_reason]) > NET_DM_MAX_REASON_LEN) { list = rcu_dereference(drop_reasons_by_subsys[SKB_DROP_REASON_SUBSYS_CORE]); subsys_reason = SKB_DROP_REASON_NOT_SPECIFIED; } if (nla_put_string(msg, NET_DM_ATTR_REASON, list->reasons[subsys_reason])) { rcu_read_unlock(); goto nla_put_failure; } rcu_read_unlock(); snprintf(buf, sizeof(buf), "%pS", cb->pc); if (nla_put_string(msg, NET_DM_ATTR_SYMBOL, buf)) goto nla_put_failure; rc = net_dm_packet_report_in_port_put(msg, skb->skb_iif, NULL); if (rc) goto nla_put_failure; if (nla_put_u64_64bit(msg, NET_DM_ATTR_TIMESTAMP, ktime_to_ns(skb->tstamp), NET_DM_ATTR_PAD)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_ORIG_LEN, skb->len)) goto nla_put_failure; if (!payload_len) goto out; if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) goto nla_put_failure; attr = skb_put(msg, nla_total_size(payload_len)); attr->nla_type = NET_DM_ATTR_PAYLOAD; attr->nla_len = nla_attr_size(payload_len); if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) goto nla_put_failure; out: genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } #define NET_DM_MAX_PACKET_SIZE (0xffff - NLA_HDRLEN - NLA_ALIGNTO) static void net_dm_packet_report(struct sk_buff *skb) { struct sk_buff *msg; size_t payload_len; int rc; /* Make sure we start copying the packet from the MAC header */ if (skb->data > skb_mac_header(skb)) skb_push(skb, skb->data - skb_mac_header(skb)); else skb_pull(skb, skb_mac_header(skb) - skb->data); /* Ensure packet fits inside a single netlink attribute */ payload_len = min_t(size_t, skb->len, NET_DM_MAX_PACKET_SIZE); if (net_dm_trunc_len) payload_len = min_t(size_t, net_dm_trunc_len, payload_len); msg = nlmsg_new(net_dm_packet_report_size(payload_len), GFP_KERNEL); if (!msg) goto out; rc = net_dm_packet_report_fill(msg, skb, payload_len); if (rc) { nlmsg_free(msg); goto out; } genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); out: consume_skb(skb); } static void net_dm_packet_work(struct work_struct *work) { struct per_cpu_dm_data *data; struct sk_buff_head list; struct sk_buff *skb; unsigned long flags; data = container_of(work, struct per_cpu_dm_data, dm_alert_work); __skb_queue_head_init(&list); spin_lock_irqsave(&data->drop_queue.lock, flags); skb_queue_splice_tail_init(&data->drop_queue, &list); spin_unlock_irqrestore(&data->drop_queue.lock, flags); while ((skb = __skb_dequeue(&list))) net_dm_packet_report(skb); } static size_t net_dm_flow_action_cookie_size(const struct devlink_trap_metadata *hw_metadata) { return hw_metadata->fa_cookie ? nla_total_size(hw_metadata->fa_cookie->cookie_len) : 0; } static size_t net_dm_hw_packet_report_size(size_t payload_len, const struct devlink_trap_metadata *hw_metadata) { size_t size; size = nlmsg_msg_size(GENL_HDRLEN + net_drop_monitor_family.hdrsize); return NLMSG_ALIGN(size) + /* NET_DM_ATTR_ORIGIN */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_HW_TRAP_GROUP_NAME */ nla_total_size(strlen(hw_metadata->trap_group_name) + 1) + /* NET_DM_ATTR_HW_TRAP_NAME */ nla_total_size(strlen(hw_metadata->trap_name) + 1) + /* NET_DM_ATTR_IN_PORT */ net_dm_in_port_size() + /* NET_DM_ATTR_FLOW_ACTION_COOKIE */ net_dm_flow_action_cookie_size(hw_metadata) + /* NET_DM_ATTR_TIMESTAMP */ nla_total_size(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PROTO */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_PAYLOAD */ nla_total_size(payload_len); } static int net_dm_hw_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, size_t payload_len) { struct devlink_trap_metadata *hw_metadata; struct nlattr *attr; void *hdr; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_PACKET_ALERT); if (!hdr) return -EMSGSIZE; if (nla_put_u16(msg, NET_DM_ATTR_ORIGIN, NET_DM_ORIGIN_HW)) goto nla_put_failure; if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_GROUP_NAME, hw_metadata->trap_group_name)) goto nla_put_failure; if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_NAME, hw_metadata->trap_name)) goto nla_put_failure; if (hw_metadata->input_dev) { struct net_device *dev = hw_metadata->input_dev; int rc; rc = net_dm_packet_report_in_port_put(msg, dev->ifindex, dev->name); if (rc) goto nla_put_failure; } if (hw_metadata->fa_cookie && nla_put(msg, NET_DM_ATTR_FLOW_ACTION_COOKIE, hw_metadata->fa_cookie->cookie_len, hw_metadata->fa_cookie->cookie)) goto nla_put_failure; if (nla_put_u64_64bit(msg, NET_DM_ATTR_TIMESTAMP, ktime_to_ns(skb->tstamp), NET_DM_ATTR_PAD)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_ORIG_LEN, skb->len)) goto nla_put_failure; if (!payload_len) goto out; if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) goto nla_put_failure; attr = skb_put(msg, nla_total_size(payload_len)); attr->nla_type = NET_DM_ATTR_PAYLOAD; attr->nla_len = nla_attr_size(payload_len); if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) goto nla_put_failure; out: genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static struct devlink_trap_metadata * net_dm_hw_metadata_copy(const struct devlink_trap_metadata *metadata) { const struct flow_action_cookie *fa_cookie; struct devlink_trap_metadata *hw_metadata; const char *trap_group_name; const char *trap_name; hw_metadata = kzalloc_obj(*hw_metadata, GFP_ATOMIC); if (!hw_metadata) return NULL; trap_group_name = kstrdup(metadata->trap_group_name, GFP_ATOMIC); if (!trap_group_name) goto free_hw_metadata; hw_metadata->trap_group_name = trap_group_name; trap_name = kstrdup(metadata->trap_name, GFP_ATOMIC); if (!trap_name) goto free_trap_group; hw_metadata->trap_name = trap_name; if (metadata->fa_cookie) { size_t cookie_size = sizeof(*fa_cookie) + metadata->fa_cookie->cookie_len; fa_cookie = kmemdup(metadata->fa_cookie, cookie_size, GFP_ATOMIC); if (!fa_cookie) goto free_trap_name; hw_metadata->fa_cookie = fa_cookie; } hw_metadata->input_dev = metadata->input_dev; netdev_hold(hw_metadata->input_dev, &hw_metadata->dev_tracker, GFP_ATOMIC); return hw_metadata; free_trap_name: kfree(trap_name); free_trap_group: kfree(trap_group_name); free_hw_metadata: kfree(hw_metadata); return NULL; } static void net_dm_hw_metadata_free(struct devlink_trap_metadata *hw_metadata) { netdev_put(hw_metadata->input_dev, &hw_metadata->dev_tracker); kfree(hw_metadata->fa_cookie); kfree(hw_metadata->trap_name); kfree(hw_metadata->trap_group_name); kfree(hw_metadata); } static void net_dm_hw_packet_report(struct sk_buff *skb) { struct devlink_trap_metadata *hw_metadata; struct sk_buff *msg; size_t payload_len; int rc; if (skb->data > skb_mac_header(skb)) skb_push(skb, skb->data - skb_mac_header(skb)); else skb_pull(skb, skb_mac_header(skb) - skb->data); payload_len = min_t(size_t, skb->len, NET_DM_MAX_PACKET_SIZE); if (net_dm_trunc_len) payload_len = min_t(size_t, net_dm_trunc_len, payload_len); hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; msg = nlmsg_new(net_dm_hw_packet_report_size(payload_len, hw_metadata), GFP_KERNEL); if (!msg) goto out; rc = net_dm_hw_packet_report_fill(msg, skb, payload_len); if (rc) { nlmsg_free(msg); goto out; } genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); out: net_dm_hw_metadata_free(NET_DM_SKB_CB(skb)->hw_metadata); consume_skb(skb); } static void net_dm_hw_packet_work(struct work_struct *work) { struct per_cpu_dm_data *hw_data; struct sk_buff_head list; struct sk_buff *skb; unsigned long flags; hw_data = container_of(work, struct per_cpu_dm_data, dm_alert_work); __skb_queue_head_init(&list); spin_lock_irqsave(&hw_data->drop_queue.lock, flags); skb_queue_splice_tail_init(&hw_data->drop_queue, &list); spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); while ((skb = __skb_dequeue(&list))) net_dm_hw_packet_report(skb); } static void net_dm_hw_trap_packet_probe(void *ignore, const struct devlink *devlink, struct sk_buff *skb, const struct devlink_trap_metadata *metadata) { struct devlink_trap_metadata *n_hw_metadata; ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *hw_data; struct sk_buff *nskb; unsigned long flags; if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL) return; if (!skb_mac_header_was_set(skb)) return; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return; n_hw_metadata = net_dm_hw_metadata_copy(metadata); if (!n_hw_metadata) goto free; NET_DM_SKB_CB(nskb)->hw_metadata = n_hw_metadata; nskb->tstamp = tstamp; hw_data = this_cpu_ptr(&dm_hw_cpu_data); spin_lock_irqsave(&hw_data->drop_queue.lock, flags); if (skb_queue_len(&hw_data->drop_queue) < net_dm_queue_len) __skb_queue_tail(&hw_data->drop_queue, nskb); else goto unlock_free; spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); schedule_work(&hw_data->dm_alert_work); return; unlock_free: spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); u64_stats_update_begin(&hw_data->stats.syncp); u64_stats_inc(&hw_data->stats.dropped); u64_stats_update_end(&hw_data->stats.syncp); net_dm_hw_metadata_free(n_hw_metadata); free: consume_skb(nskb); } static const struct net_dm_alert_ops net_dm_alert_packet_ops = { .kfree_skb_probe = net_dm_packet_trace_kfree_skb_hit, .napi_poll_probe = net_dm_packet_trace_napi_poll_hit, .work_item_func = net_dm_packet_work, .hw_work_item_func = net_dm_hw_packet_work, .hw_trap_probe = net_dm_hw_trap_packet_probe, }; static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = { [NET_DM_ALERT_MODE_SUMMARY] = &net_dm_alert_summary_ops, [NET_DM_ALERT_MODE_PACKET] = &net_dm_alert_packet_ops, }; #if IS_ENABLED(CONFIG_NET_DEVLINK) static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops) { return register_trace_devlink_trap_report(ops->hw_trap_probe, NULL); } static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops) { unregister_trace_devlink_trap_report(ops->hw_trap_probe, NULL); tracepoint_synchronize_unregister(); } #else static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops) { return -EOPNOTSUPP; } static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops) { } #endif static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; int cpu, rc; if (monitor_hw) { NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already enabled"); return -EAGAIN; } ops = net_dm_alert_ops_arr[net_dm_alert_mode]; if (!try_module_get(THIS_MODULE)) { NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); return -ENODEV; } for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct net_dm_hw_entries *hw_entries; INIT_WORK(&hw_data->dm_alert_work, ops->hw_work_item_func); timer_setup(&hw_data->send_timer, sched_send_work, 0); hw_entries = net_dm_hw_reset_per_cpu_data(hw_data); kfree(hw_entries); } rc = net_dm_hw_probe_register(ops); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to devlink_trap_probe() tracepoint"); goto err_module_put; } monitor_hw = true; return 0; err_module_put: for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct sk_buff *skb; timer_delete_sync(&hw_data->send_timer); cancel_work_sync(&hw_data->dm_alert_work); while ((skb = __skb_dequeue(&hw_data->drop_queue))) { struct devlink_trap_metadata *hw_metadata; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; net_dm_hw_metadata_free(hw_metadata); consume_skb(skb); } } module_put(THIS_MODULE); return rc; } static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; int cpu; if (!monitor_hw) { NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already disabled"); return; } ops = net_dm_alert_ops_arr[net_dm_alert_mode]; monitor_hw = false; net_dm_hw_probe_unregister(ops); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct sk_buff *skb; timer_delete_sync(&hw_data->send_timer); cancel_work_sync(&hw_data->dm_alert_work); while ((skb = __skb_dequeue(&hw_data->drop_queue))) { struct devlink_trap_metadata *hw_metadata; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; net_dm_hw_metadata_free(hw_metadata); consume_skb(skb); } } module_put(THIS_MODULE); } static int net_dm_trace_on_set(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; int cpu, rc; ops = net_dm_alert_ops_arr[net_dm_alert_mode]; if (!try_module_get(THIS_MODULE)) { NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); return -ENODEV; } for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; INIT_WORK(&data->dm_alert_work, ops->work_item_func); timer_setup(&data->send_timer, sched_send_work, 0); /* Allocate a new per-CPU skb for the summary alert message and * free the old one which might contain stale data from * previous tracing. */ skb = reset_per_cpu_data(data); consume_skb(skb); } rc = register_trace_kfree_skb(ops->kfree_skb_probe, NULL); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to kfree_skb() tracepoint"); goto err_module_put; } rc = register_trace_napi_poll(ops->napi_poll_probe, NULL); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to napi_poll() tracepoint"); goto err_unregister_trace; } return 0; err_unregister_trace: unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); err_module_put: for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; timer_delete_sync(&data->send_timer); cancel_work_sync(&data->dm_alert_work); while ((skb = __skb_dequeue(&data->drop_queue))) consume_skb(skb); } module_put(THIS_MODULE); return rc; } static void net_dm_trace_off_set(void) { const struct net_dm_alert_ops *ops; int cpu; ops = net_dm_alert_ops_arr[net_dm_alert_mode]; unregister_trace_napi_poll(ops->napi_poll_probe, NULL); unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); tracepoint_synchronize_unregister(); /* Make sure we do not send notifications to user space after request * to stop tracing returns. */ for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; timer_delete_sync(&data->send_timer); cancel_work_sync(&data->dm_alert_work); while ((skb = __skb_dequeue(&data->drop_queue))) consume_skb(skb); } module_put(THIS_MODULE); } static int set_all_monitor_traces(int state, struct netlink_ext_ack *extack) { int rc = 0; if (state == trace_state) { NL_SET_ERR_MSG_MOD(extack, "Trace state already set to requested state"); return -EAGAIN; } switch (state) { case TRACE_ON: rc = net_dm_trace_on_set(extack); break; case TRACE_OFF: net_dm_trace_off_set(); break; default: rc = 1; break; } if (!rc) trace_state = state; else rc = -EINPROGRESS; return rc; } static bool net_dm_is_monitoring(void) { return trace_state == TRACE_ON || monitor_hw; } static int net_dm_alert_mode_get_from_info(struct genl_info *info, enum net_dm_alert_mode *p_alert_mode) { u8 val; val = nla_get_u8(info->attrs[NET_DM_ATTR_ALERT_MODE]); switch (val) { case NET_DM_ALERT_MODE_SUMMARY: case NET_DM_ALERT_MODE_PACKET: *p_alert_mode = val; break; default: return -EINVAL; } return 0; } static int net_dm_alert_mode_set(struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; enum net_dm_alert_mode alert_mode; int rc; if (!info->attrs[NET_DM_ATTR_ALERT_MODE]) return 0; rc = net_dm_alert_mode_get_from_info(info, &alert_mode); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Invalid alert mode"); return -EINVAL; } net_dm_alert_mode = alert_mode; return 0; } static void net_dm_trunc_len_set(struct genl_info *info) { if (!info->attrs[NET_DM_ATTR_TRUNC_LEN]) return; net_dm_trunc_len = nla_get_u32(info->attrs[NET_DM_ATTR_TRUNC_LEN]); } static void net_dm_queue_len_set(struct genl_info *info) { if (!info->attrs[NET_DM_ATTR_QUEUE_LEN]) return; net_dm_queue_len = nla_get_u32(info->attrs[NET_DM_ATTR_QUEUE_LEN]); } static int net_dm_cmd_config(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; int rc; if (net_dm_is_monitoring()) { NL_SET_ERR_MSG_MOD(extack, "Cannot configure drop monitor during monitoring"); return -EBUSY; } rc = net_dm_alert_mode_set(info); if (rc) return rc; net_dm_trunc_len_set(info); net_dm_queue_len_set(info); return 0; } static int net_dm_monitor_start(bool set_sw, bool set_hw, struct netlink_ext_ack *extack) { bool sw_set = false; int rc; if (set_sw) { rc = set_all_monitor_traces(TRACE_ON, extack); if (rc) return rc; sw_set = true; } if (set_hw) { rc = net_dm_hw_monitor_start(extack); if (rc) goto err_monitor_hw; } return 0; err_monitor_hw: if (sw_set) set_all_monitor_traces(TRACE_OFF, extack); return rc; } static void net_dm_monitor_stop(bool set_sw, bool set_hw, struct netlink_ext_ack *extack) { if (set_hw) net_dm_hw_monitor_stop(extack); if (set_sw) set_all_monitor_traces(TRACE_OFF, extack); } static int net_dm_cmd_trace(struct sk_buff *skb, struct genl_info *info) { bool set_sw = !!info->attrs[NET_DM_ATTR_SW_DROPS]; bool set_hw = !!info->attrs[NET_DM_ATTR_HW_DROPS]; struct netlink_ext_ack *extack = info->extack; /* To maintain backward compatibility, we start / stop monitoring of * software drops if no flag is specified. */ if (!set_sw && !set_hw) set_sw = true; switch (info->genlhdr->cmd) { case NET_DM_CMD_START: return net_dm_monitor_start(set_sw, set_hw, extack); case NET_DM_CMD_STOP: net_dm_monitor_stop(set_sw, set_hw, extack); return 0; } return -EOPNOTSUPP; } static int net_dm_config_fill(struct sk_buff *msg, struct genl_info *info) { void *hdr; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &net_drop_monitor_family, 0, NET_DM_CMD_CONFIG_NEW); if (!hdr) return -EMSGSIZE; if (nla_put_u8(msg, NET_DM_ATTR_ALERT_MODE, net_dm_alert_mode)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_TRUNC_LEN, net_dm_trunc_len)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_QUEUE_LEN, net_dm_queue_len)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int net_dm_cmd_config_get(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; int rc; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; rc = net_dm_config_fill(msg, info); if (rc) goto free_msg; return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); return rc; } static void net_dm_stats_read(struct net_dm_stats *stats) { int cpu; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct net_dm_stats *cpu_stats = &data->stats; unsigned int start; u64 dropped; do { start = u64_stats_fetch_begin(&cpu_stats->syncp); dropped = u64_stats_read(&cpu_stats->dropped); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->dropped, dropped); } } static int net_dm_stats_put(struct sk_buff *msg) { struct net_dm_stats stats; struct nlattr *attr; net_dm_stats_read(&stats); attr = nla_nest_start(msg, NET_DM_ATTR_STATS); if (!attr) return -EMSGSIZE; if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, u64_stats_read(&stats.dropped), NET_DM_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static void net_dm_hw_stats_read(struct net_dm_stats *stats) { int cpu; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct net_dm_stats *cpu_stats = &hw_data->stats; unsigned int start; u64 dropped; do { start = u64_stats_fetch_begin(&cpu_stats->syncp); dropped = u64_stats_read(&cpu_stats->dropped); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->dropped, dropped); } } static int net_dm_hw_stats_put(struct sk_buff *msg) { struct net_dm_stats stats; struct nlattr *attr; net_dm_hw_stats_read(&stats); attr = nla_nest_start(msg, NET_DM_ATTR_HW_STATS); if (!attr) return -EMSGSIZE; if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, u64_stats_read(&stats.dropped), NET_DM_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_stats_fill(struct sk_buff *msg, struct genl_info *info) { void *hdr; int rc; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &net_drop_monitor_family, 0, NET_DM_CMD_STATS_NEW); if (!hdr) return -EMSGSIZE; rc = net_dm_stats_put(msg); if (rc) goto nla_put_failure; rc = net_dm_hw_stats_put(msg); if (rc) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int net_dm_cmd_stats_get(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; int rc; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; rc = net_dm_stats_fill(msg, info); if (rc) goto free_msg; return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); return rc; } static int dropmon_net_event(struct notifier_block *ev_block, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dm_hw_stat_delta *stat; switch (event) { case NETDEV_REGISTER: if (WARN_ON_ONCE(rtnl_dereference(dev->dm_private))) break; stat = kzalloc_obj(*stat); if (!stat) break; stat->last_rx = jiffies; rcu_assign_pointer(dev->dm_private, stat); break; case NETDEV_UNREGISTER: stat = rtnl_dereference(dev->dm_private); if (stat) { rcu_assign_pointer(dev->dm_private, NULL); kfree_rcu(stat, rcu); } break; } return NOTIFY_DONE; } static const struct nla_policy net_dm_nl_policy[NET_DM_ATTR_MAX + 1] = { [NET_DM_ATTR_UNSPEC] = { .strict_start_type = NET_DM_ATTR_UNSPEC + 1 }, [NET_DM_ATTR_ALERT_MODE] = { .type = NLA_U8 }, [NET_DM_ATTR_TRUNC_LEN] = { .type = NLA_U32 }, [NET_DM_ATTR_QUEUE_LEN] = { .type = NLA_U32 }, [NET_DM_ATTR_SW_DROPS] = {. type = NLA_FLAG }, [NET_DM_ATTR_HW_DROPS] = {. type = NLA_FLAG }, }; static const struct genl_small_ops dropmon_ops[] = { { .cmd = NET_DM_CMD_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_config, .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_START, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_STOP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_CONFIG_GET, .doit = net_dm_cmd_config_get, }, { .cmd = NET_DM_CMD_STATS_GET, .doit = net_dm_cmd_stats_get, }, }; static int net_dm_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_lock(&net_dm_mutex); return 0; } static void net_dm_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_unlock(&net_dm_mutex); } static struct genl_family net_drop_monitor_family __ro_after_init = { .hdrsize = 0, .name = "NET_DM", .version = 2, .maxattr = NET_DM_ATTR_MAX, .policy = net_dm_nl_policy, .pre_doit = net_dm_nl_pre_doit, .post_doit = net_dm_nl_post_doit, .module = THIS_MODULE, .small_ops = dropmon_ops, .n_small_ops = ARRAY_SIZE(dropmon_ops), .resv_start_op = NET_DM_CMD_STATS_GET + 1, .mcgrps = dropmon_mcgrps, .n_mcgrps = ARRAY_SIZE(dropmon_mcgrps), }; static struct notifier_block dropmon_net_notifier = { .notifier_call = dropmon_net_event }; static void __net_dm_cpu_data_init(struct per_cpu_dm_data *data) { raw_spin_lock_init(&data->lock); skb_queue_head_init(&data->drop_queue); u64_stats_init(&data->stats.syncp); } static void __net_dm_cpu_data_fini(struct per_cpu_dm_data *data) { WARN_ON(!skb_queue_empty(&data->drop_queue)); } static void net_dm_cpu_data_init(int cpu) { struct per_cpu_dm_data *data; data = &per_cpu(dm_cpu_data, cpu); __net_dm_cpu_data_init(data); } static void net_dm_cpu_data_fini(int cpu) { struct per_cpu_dm_data *data; data = &per_cpu(dm_cpu_data, cpu); /* At this point, we should have exclusive access * to this struct and can free the skb inside it. */ consume_skb(data->skb); __net_dm_cpu_data_fini(data); } static void net_dm_hw_cpu_data_init(int cpu) { struct per_cpu_dm_data *hw_data; hw_data = &per_cpu(dm_hw_cpu_data, cpu); __net_dm_cpu_data_init(hw_data); } static void net_dm_hw_cpu_data_fini(int cpu) { struct per_cpu_dm_data *hw_data; hw_data = &per_cpu(dm_hw_cpu_data, cpu); kfree(hw_data->hw_entries); __net_dm_cpu_data_fini(hw_data); } static int __init init_net_drop_monitor(void) { int cpu, rc; pr_info("Initializing network drop monitor service\n"); if (sizeof(void *) > 8) { pr_err("Unable to store program counters on this arch, Drop monitor failed\n"); return -ENOSPC; } for_each_possible_cpu(cpu) { net_dm_cpu_data_init(cpu); net_dm_hw_cpu_data_init(cpu); } rc = register_netdevice_notifier(&dropmon_net_notifier); if (rc < 0) { pr_crit("Failed to register netdevice notifier\n"); return rc; } rc = genl_register_family(&net_drop_monitor_family); if (rc) { pr_err("Could not create drop monitor netlink family\n"); goto out_unreg; } WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = 0; goto out; out_unreg: WARN_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); out: return rc; } static void exit_net_drop_monitor(void) { int cpu; /* * Because of the module_get/put we do in the trace state change path * we are guaranteed not to have any current users when we get here */ BUG_ON(genl_unregister_family(&net_drop_monitor_family)); BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); for_each_possible_cpu(cpu) { net_dm_hw_cpu_data_fini(cpu); net_dm_cpu_data_fini(cpu); } } module_init(init_net_drop_monitor); module_exit(exit_net_drop_monitor); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>"); MODULE_ALIAS_GENL_FAMILY("NET_DM"); MODULE_DESCRIPTION("Monitoring code for network dropped packet alerts"); |
| 3 6 6 1 1 1 45 45 44 | 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-only /* * KVM dirty ring implementation * * Copyright 2019 Red Hat, Inc. */ #include <linux/kvm_host.h> #include <linux/kvm.h> #include <linux/vmalloc.h> #include <linux/kvm_dirty_ring.h> #include <trace/events/kvm.h> #include "kvm_mm.h" int __weak kvm_cpu_dirty_log_size(struct kvm *kvm) { return 0; } u32 kvm_dirty_ring_get_rsvd_entries(struct kvm *kvm) { return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size(kvm); } bool kvm_use_dirty_bitmap(struct kvm *kvm) { lockdep_assert_held(&kvm->slots_lock); return !kvm->dirty_ring_size || kvm->dirty_ring_with_bitmap; } #ifndef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) { return false; } #endif static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring) { return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index); } static bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) { return kvm_dirty_ring_used(ring) >= ring->soft_limit; } static bool kvm_dirty_ring_full(struct kvm_dirty_ring *ring) { return kvm_dirty_ring_used(ring) >= ring->size; } static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask) { struct kvm_memory_slot *memslot; int as_id, id; as_id = slot >> 16; id = (u16)slot; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return; memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id); if (!memslot || offset >= memslot->npages || offset + __fls(mask) >= memslot->npages) return; KVM_MMU_LOCK(kvm); kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); KVM_MMU_UNLOCK(kvm); } int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring, int index, u32 size) { ring->dirty_gfns = vzalloc(size); if (!ring->dirty_gfns) return -ENOMEM; ring->size = size / sizeof(struct kvm_dirty_gfn); ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries(kvm); ring->dirty_index = 0; ring->reset_index = 0; ring->index = index; return 0; } static inline void kvm_dirty_gfn_set_invalid(struct kvm_dirty_gfn *gfn) { smp_store_release(&gfn->flags, 0); } static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn) { gfn->flags = KVM_DIRTY_GFN_F_DIRTY; } static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn) { return smp_load_acquire(&gfn->flags) & KVM_DIRTY_GFN_F_RESET; } int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring, int *nr_entries_reset) { /* * To minimize mmu_lock contention, batch resets for harvested entries * whose gfns are in the same slot, and are within N frame numbers of * each other, where N is the number of bits in an unsigned long. For * simplicity, process the current set of entries when the next entry * can't be included in the batch. * * Track the current batch slot, the gfn offset into the slot for the * batch, and the bitmask of gfns that need to be reset (relative to * offset). Note, the offset may be adjusted backwards, e.g. so that * a sequence of gfns X, X-1, ... X-N-1 can be batched. */ u32 cur_slot, next_slot; u64 cur_offset, next_offset; unsigned long mask = 0; struct kvm_dirty_gfn *entry; /* * Ensure concurrent calls to KVM_RESET_DIRTY_RINGS are serialized, * e.g. so that KVM fully resets all entries processed by a given call * before returning to userspace. Holding slots_lock also protects * the various memslot accesses. */ lockdep_assert_held(&kvm->slots_lock); while (likely((*nr_entries_reset) < INT_MAX)) { if (signal_pending(current)) return -EINTR; entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)]; if (!kvm_dirty_gfn_harvested(entry)) break; next_slot = READ_ONCE(entry->slot); next_offset = READ_ONCE(entry->offset); /* Update the flags to reflect that this GFN is reset */ kvm_dirty_gfn_set_invalid(entry); ring->reset_index++; (*nr_entries_reset)++; if (mask) { /* * While the size of each ring is fixed, it's possible * for the ring to be constantly re-dirtied/harvested * while the reset is in-progress (the hard limit exists * only to guard against the count becoming negative). */ cond_resched(); /* * Try to coalesce the reset operations when the guest * is scanning pages in the same slot. */ if (next_slot == cur_slot) { s64 delta = next_offset - cur_offset; if (delta >= 0 && delta < BITS_PER_LONG) { mask |= 1ull << delta; continue; } /* Backwards visit, careful about overflows! */ if (delta > -BITS_PER_LONG && delta < 0 && (mask << -delta >> -delta) == mask) { cur_offset = next_offset; mask = (mask << -delta) | 1; continue; } } /* * Reset the slot for all the harvested entries that * have been gathered, but not yet fully processed. */ kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); } /* * The current slot was reset or this is the first harvested * entry, (re)initialize the metadata. */ cur_slot = next_slot; cur_offset = next_offset; mask = 1; } /* * Perform a final reset if there are harvested entries that haven't * been processed, which is guaranteed if at least one harvested was * found. The loop only performs a reset when the "next" entry can't * be batched with the "current" entry(s), and that reset processes the * _current_ entry(s); i.e. the last harvested entry, a.k.a. next, will * always be left pending. */ if (mask) kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); /* * The request KVM_REQ_DIRTY_RING_SOFT_FULL will be cleared * by the VCPU thread next time when it enters the guest. */ trace_kvm_dirty_ring_reset(ring); return 0; } void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset) { struct kvm_dirty_ring *ring = &vcpu->dirty_ring; struct kvm_dirty_gfn *entry; /* It should never get full */ WARN_ON_ONCE(kvm_dirty_ring_full(ring)); entry = &ring->dirty_gfns[ring->dirty_index & (ring->size - 1)]; entry->slot = slot; entry->offset = offset; /* * Make sure the data is filled in before we publish this to * the userspace program. There's no paired kernel-side reader. */ smp_wmb(); kvm_dirty_gfn_set_dirtied(entry); ring->dirty_index++; trace_kvm_dirty_ring_push(ring, slot, offset); if (kvm_dirty_ring_soft_full(ring)) kvm_make_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu); } bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu) { /* * The VCPU isn't runnable when the dirty ring becomes soft full. * The KVM_REQ_DIRTY_RING_SOFT_FULL event is always set to prevent * the VCPU from running until the dirty pages are harvested and * the dirty ring is reset by userspace. */ if (kvm_check_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu) && kvm_dirty_ring_soft_full(&vcpu->dirty_ring)) { kvm_make_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu); vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL; trace_kvm_dirty_ring_exit(vcpu); return true; } return false; } struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset) { return vmalloc_to_page((void *)ring->dirty_gfns + offset * PAGE_SIZE); } void kvm_dirty_ring_free(struct kvm_dirty_ring *ring) { vfree(ring->dirty_gfns); ring->dirty_gfns = NULL; } |
| 854 854 670 831 831 831 831 801 831 829 831 831 831 831 638 638 638 638 634 633 634 634 634 591 501 460 501 85 63 85 460 280 280 280 854 854 854 854 854 854 831 100 100 100 100 853 100 88 4 4 4 88 84 84 84 84 84 84 84 84 84 84 84 84 84 666 666 666 634 84 84 84 73 15 666 199 168 168 168 199 1348 1349 1349 248 230 1349 145 1348 338 331 332 332 332 332 332 338 7 7 1 7 7 7 7 7 7 7 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 | // SPDX-License-Identifier: GPL-2.0 /* * Workingset detection * * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner */ #include <linux/memcontrol.h> #include <linux/mm_inline.h> #include <linux/writeback.h> #include <linux/shmem_fs.h> #include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/module.h> #include <linux/swap.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/mm.h> #include "swap_table.h" #include "internal.h" /* * Double CLOCK lists * * Per node, two clock lists are maintained for file pages: the * inactive and the active list. Freshly faulted pages start out at * the head of the inactive list and page reclaim scans pages from the * tail. Pages that are accessed multiple times on the inactive list * are promoted to the active list, to protect them from reclaim, * whereas active pages are demoted to the inactive list when the * active list grows too big. * * fault ------------------------+ * | * +--------------+ | +-------------+ * reclaim <- | inactive | <-+-- demotion | active | <--+ * +--------------+ +-------------+ | * | | * +-------------- promotion ------------------+ * * * Access frequency and refault distance * * A workload is thrashing when its pages are frequently used but they * are evicted from the inactive list every time before another access * would have promoted them to the active list. * * In cases where the average access distance between thrashing pages * is bigger than the size of memory there is nothing that can be * done - the thrashing set could never fit into memory under any * circumstance. * * However, the average access distance could be bigger than the * inactive list, yet smaller than the size of memory. In this case, * the set could fit into memory if it weren't for the currently * active pages - which may be used more, hopefully less frequently: * * +-memory available to cache-+ * | | * +-inactive------+-active----+ * a b | c d e f g h i | J K L M N | * +---------------+-----------+ * * It is prohibitively expensive to accurately track access frequency * of pages. But a reasonable approximation can be made to measure * thrashing on the inactive list, after which refaulting pages can be * activated optimistically to compete with the existing active pages. * * Approximating inactive page access frequency - Observations: * * 1. When a page is accessed for the first time, it is added to the * head of the inactive list, slides every existing inactive page * towards the tail by one slot, and pushes the current tail page * out of memory. * * 2. When a page is accessed for the second time, it is promoted to * the active list, shrinking the inactive list by one slot. This * also slides all inactive pages that were faulted into the cache * more recently than the activated page towards the tail of the * inactive list. * * Thus: * * 1. The sum of evictions and activations between any two points in * time indicate the minimum number of inactive pages accessed in * between. * * 2. Moving one inactive page N page slots towards the tail of the * list requires at least N inactive page accesses. * * Combining these: * * 1. When a page is finally evicted from memory, the number of * inactive pages accessed while the page was in cache is at least * the number of page slots on the inactive list. * * 2. In addition, measuring the sum of evictions and activations (E) * at the time of a page's eviction, and comparing it to another * reading (R) at the time the page faults back into memory tells * the minimum number of accesses while the page was not cached. * This is called the refault distance. * * Because the first access of the page was the fault and the second * access the refault, we combine the in-cache distance with the * out-of-cache distance to get the complete minimum access distance * of this page: * * NR_inactive + (R - E) * * And knowing the minimum access distance of a page, we can easily * tell if the page would be able to stay in cache assuming all page * slots in the cache were available: * * NR_inactive + (R - E) <= NR_inactive + NR_active * * If we have swap we should consider about NR_inactive_anon and * NR_active_anon, so for page cache and anonymous respectively: * * NR_inactive_file + (R - E) <= NR_inactive_file + NR_active_file * + NR_inactive_anon + NR_active_anon * * NR_inactive_anon + (R - E) <= NR_inactive_anon + NR_active_anon * + NR_inactive_file + NR_active_file * * Which can be further simplified to: * * (R - E) <= NR_active_file + NR_inactive_anon + NR_active_anon * * (R - E) <= NR_active_anon + NR_inactive_file + NR_active_file * * Put into words, the refault distance (out-of-cache) can be seen as * a deficit in inactive list space (in-cache). If the inactive list * had (R - E) more page slots, the page would not have been evicted * in between accesses, but activated instead. And on a full system, * the only thing eating into inactive list space is active pages. * * * Refaulting inactive pages * * All that is known about the active list is that the pages have been * accessed more than once in the past. This means that at any given * time there is actually a good chance that pages on the active list * are no longer in active use. * * So when a refault distance of (R - E) is observed and there are at * least (R - E) pages in the userspace workingset, the refaulting page * is activated optimistically in the hope that (R - E) pages are actually * used less frequently than the refaulting page - or even not used at * all anymore. * * That means if inactive cache is refaulting with a suitable refault * distance, we assume the cache workingset is transitioning and put * pressure on the current workingset. * * If this is wrong and demotion kicks in, the pages which are truly * used more frequently will be reactivated while the less frequently * used once will be evicted from memory. * * But if this is right, the stale pages will be pushed out of memory * and the used pages get to stay in cache. * * Refaulting active pages * * If on the other hand the refaulting pages have recently been * deactivated, it means that the active list is no longer protecting * actively used cache from reclaim. The cache is NOT transitioning to * a different workingset; the existing workingset is thrashing in the * space allocated to the page cache. * * * Implementation * * For each node's LRU lists, a counter for inactive evictions and * activations is maintained (node->nonresident_age). * * On eviction, a snapshot of this counter (along with some bits to * identify the node) is stored in the now empty page cache * slot of the evicted page. This is called a shadow entry. * * On cache misses for which there are shadow entries, an eligible * refault distance will immediately activate the refaulting page. */ #define WORKINGSET_SHIFT 1 #define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \ WORKINGSET_SHIFT + NODES_SHIFT + \ MEM_CGROUP_ID_SHIFT) #define EVICTION_SHIFT_ANON (EVICTION_SHIFT + SWAP_COUNT_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) #define EVICTION_MASK_ANON (~0UL >> EVICTION_SHIFT_ANON) /* * Eviction timestamps need to be able to cover the full range of * actionable refaults. However, bits are tight in the xarray * entry, and after storing the identifier for the lruvec there might * not be enough left to represent every single actionable refault. In * that case, we have to sacrifice granularity for distance, and group * evictions into coarser buckets by shaving off lower timestamp bits. */ static unsigned int bucket_order[ANON_AND_FILE] __read_mostly; static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, bool workingset, bool file) { eviction &= file ? EVICTION_MASK : EVICTION_MASK_ANON; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; eviction = (eviction << WORKINGSET_SHIFT) | workingset; return xa_mk_value(eviction); } static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, unsigned long *evictionp, bool *workingsetp) { unsigned long entry = xa_to_value(shadow); int memcgid, nid; bool workingset; workingset = entry & ((1UL << WORKINGSET_SHIFT) - 1); entry >>= WORKINGSET_SHIFT; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); entry >>= MEM_CGROUP_ID_SHIFT; *memcgidp = memcgid; *pgdat = NODE_DATA(nid); *evictionp = entry; *workingsetp = workingset; } #ifdef CONFIG_LRU_GEN static void *lru_gen_eviction(struct folio *folio) { int hist; unsigned long token; unsigned long min_seq; struct lruvec *lruvec; struct lru_gen_folio *lrugen; int type = folio_is_file_lru(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); bool workingset = folio_test_workingset(folio); int tier = lru_tier_from_refs(refs, workingset); struct mem_cgroup *memcg; struct pglist_data *pgdat = folio_pgdat(folio); unsigned short memcg_id; BUILD_BUG_ON(LRU_GEN_WIDTH + LRU_REFS_WIDTH > BITS_PER_LONG - max(EVICTION_SHIFT, EVICTION_SHIFT_ANON)); rcu_read_lock(); memcg = folio_memcg(folio); lruvec = mem_cgroup_lruvec(memcg, pgdat); lrugen = &lruvec->lrugen; min_seq = READ_ONCE(lrugen->min_seq[type]); token = (min_seq << LRU_REFS_WIDTH) | max(refs - 1, 0); hist = lru_hist_from_seq(min_seq); atomic_long_add(delta, &lrugen->evicted[hist][type][tier]); memcg_id = mem_cgroup_private_id(memcg); rcu_read_unlock(); return pack_shadow(memcg_id, pgdat, token, workingset, type); } /* * Tests if the shadow entry is for a folio that was recently evicted. * Fills in @lruvec, @token, @workingset with the values unpacked from shadow. */ static bool lru_gen_test_recent(void *shadow, struct lruvec **lruvec, unsigned long *token, bool *workingset, bool file) { int memcg_id; unsigned long max_seq; struct mem_cgroup *memcg; struct pglist_data *pgdat; unpack_shadow(shadow, &memcg_id, &pgdat, token, workingset); memcg = mem_cgroup_from_private_id(memcg_id); *lruvec = mem_cgroup_lruvec(memcg, pgdat); max_seq = READ_ONCE((*lruvec)->lrugen.max_seq); max_seq &= (file ? EVICTION_MASK : EVICTION_MASK_ANON) >> LRU_REFS_WIDTH; return abs_diff(max_seq, *token >> LRU_REFS_WIDTH) < MAX_NR_GENS; } static void lru_gen_refault(struct folio *folio, void *shadow) { bool recent; int hist, tier, refs; bool workingset; unsigned long token; struct lruvec *lruvec; struct lru_gen_folio *lrugen; int type = folio_is_file_lru(folio); int delta = folio_nr_pages(folio); rcu_read_lock(); recent = lru_gen_test_recent(shadow, &lruvec, &token, &workingset, type); if (lruvec != folio_lruvec(folio)) goto unlock; mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + type, delta); if (!recent) goto unlock; lrugen = &lruvec->lrugen; hist = lru_hist_from_seq(READ_ONCE(lrugen->min_seq[type])); refs = (token & (BIT(LRU_REFS_WIDTH) - 1)) + 1; tier = lru_tier_from_refs(refs, workingset); atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]); if (workingset) { /* * see folio_add_lru(), where folio_set_active() is * called for workingset folios */ if (lru_gen_in_fault()) mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta); folio_set_workingset(folio); mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta); } else set_mask_bits(&folio->flags.f, LRU_REFS_MASK, (refs - 1UL) << LRU_REFS_PGOFF); unlock: rcu_read_unlock(); } #else /* !CONFIG_LRU_GEN */ static void *lru_gen_eviction(struct folio *folio) { return NULL; } static bool lru_gen_test_recent(void *shadow, struct lruvec **lruvec, unsigned long *token, bool *workingset, bool file) { return false; } static void lru_gen_refault(struct folio *folio, void *shadow) { } #endif /* CONFIG_LRU_GEN */ /** * workingset_age_nonresident - age non-resident entries as LRU ages * @lruvec: the lruvec that was aged * @nr_pages: the number of pages to count * * As in-memory pages are aged, non-resident pages need to be aged as * well, in order for the refault distances later on to be comparable * to the in-memory dimensions. This function allows reclaim and LRU * operations to drive the non-resident aging along in parallel. */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages) { /* * Reclaiming a cgroup means reclaiming all its children in a * round-robin fashion. That means that each cgroup has an LRU * order that is composed of the LRU orders of its child * cgroups; and every page has an LRU position not just in the * cgroup that owns it, but in all of that group's ancestors. * * So when the physical inactive list of a leaf cgroup ages, * the virtual inactive lists of all its parents, including * the root cgroup's, age as well. */ do { atomic_long_add(nr_pages, &lruvec->nonresident_age); } while ((lruvec = parent_lruvec(lruvec))); } /** * workingset_eviction - note the eviction of a folio from memory * @target_memcg: the cgroup that is causing the reclaim * @folio: the folio being evicted * * Return: a shadow entry to be stored in @folio->mapping->i_pages in place * of the evicted @folio so that a later refault can be detected. */ void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg) { struct pglist_data *pgdat = folio_pgdat(folio); int file = folio_is_file_lru(folio); unsigned long eviction; struct lruvec *lruvec; int memcgid; /* Folio is fully exclusive and pins folio's memory cgroup pointer */ VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (lru_gen_enabled()) return lru_gen_eviction(folio); lruvec = mem_cgroup_lruvec(target_memcg, pgdat); /* XXX: target_memcg can be NULL, go through lruvec */ memcgid = mem_cgroup_private_id(lruvec_memcg(lruvec)); eviction = atomic_long_read(&lruvec->nonresident_age); eviction >>= bucket_order[file]; workingset_age_nonresident(lruvec, folio_nr_pages(folio)); return pack_shadow(memcgid, pgdat, eviction, folio_test_workingset(folio), file); } /** * workingset_test_recent - tests if the shadow entry is for a folio that was * recently evicted. Also fills in @workingset with the value unpacked from * shadow. * @shadow: the shadow entry to be tested. * @file: whether the corresponding folio is from the file lru. * @workingset: where the workingset value unpacked from shadow should * be stored. * @flush: whether to flush cgroup rstat. * * Return: true if the shadow is for a recently evicted folio; false otherwise. */ bool workingset_test_recent(void *shadow, bool file, bool *workingset, bool flush) { struct mem_cgroup *eviction_memcg; struct lruvec *eviction_lruvec; unsigned long refault_distance; unsigned long workingset_size; unsigned long refault; int memcgid; struct pglist_data *pgdat; unsigned long eviction; if (lru_gen_enabled()) { bool recent; rcu_read_lock(); recent = lru_gen_test_recent(shadow, &eviction_lruvec, &eviction, workingset, file); rcu_read_unlock(); return recent; } rcu_read_lock(); unpack_shadow(shadow, &memcgid, &pgdat, &eviction, workingset); eviction <<= bucket_order[file]; /* * Look up the memcg associated with the stored ID. It might * have been deleted since the folio's eviction. * * Note that in rare events the ID could have been recycled * for a new cgroup that refaults a shared folio. This is * impossible to tell from the available data. However, this * should be a rare and limited disturbance, and activations * are always speculative anyway. Ultimately, it's the aging * algorithm's job to shake out the minimum access frequency * for the active cache. * * XXX: On !CONFIG_MEMCG, this will always return NULL; it * would be better if the root_mem_cgroup existed in all * configurations instead. */ eviction_memcg = mem_cgroup_from_private_id(memcgid); if (!mem_cgroup_tryget(eviction_memcg)) eviction_memcg = NULL; rcu_read_unlock(); if (!mem_cgroup_disabled() && !eviction_memcg) return false; /* * Flush stats (and potentially sleep) outside the RCU read section. * * Note that workingset_test_recent() itself might be called in RCU read * section (for e.g, in cachestat) - these callers need to skip flushing * stats (via the flush argument). * * XXX: With per-memcg flushing and thresholding, is ratelimiting * still needed here? */ if (flush) mem_cgroup_flush_stats_ratelimited(eviction_memcg); eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat); refault = atomic_long_read(&eviction_lruvec->nonresident_age); /* * Calculate the refault distance * * The unsigned subtraction here gives an accurate distance * across nonresident_age overflows in most cases. There is a * special case: usually, shadow entries have a short lifetime * and are either refaulted or reclaimed along with the inode * before they get too old. But it is not impossible for the * nonresident_age to lap a shadow entry in the field, which * can then result in a false small refault distance, leading * to a false activation should this old entry actually * refault again. However, earlier kernels used to deactivate * unconditionally with *every* reclaim invocation for the * longest time, so the occasional inappropriate activation * leading to pressure on the active list is not a problem. */ refault_distance = ((refault - eviction) & (file ? EVICTION_MASK : EVICTION_MASK_ANON)); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if * all the memory was available to the workingset. Whether * workingset competition needs to consider anon or not depends * on having free swap space. */ workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE); if (!file) { workingset_size += lruvec_page_state(eviction_lruvec, NR_INACTIVE_FILE); } if (mem_cgroup_get_nr_swap_pages(eviction_memcg) > 0) { workingset_size += lruvec_page_state(eviction_lruvec, NR_ACTIVE_ANON); if (file) { workingset_size += lruvec_page_state(eviction_lruvec, NR_INACTIVE_ANON); } } mem_cgroup_put(eviction_memcg); return refault_distance <= workingset_size; } /** * workingset_refault - Evaluate the refault of a previously evicted folio. * @folio: The freshly allocated replacement folio. * @shadow: Shadow entry of the evicted folio. * * Calculates and evaluates the refault distance of the previously * evicted folio in the context of the node and the memcg whose memory * pressure caused the eviction. */ void workingset_refault(struct folio *folio, void *shadow) { bool file = folio_is_file_lru(folio); struct mem_cgroup *memcg; struct lruvec *lruvec; bool workingset; long nr; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (lru_gen_enabled()) { lru_gen_refault(folio, shadow); return; } /* * The activation decision for this folio is made at the level * where the eviction occurred, as that is where the LRU order * during folio reclaim is being determined. * * However, the cgroup that will own the folio is the one that * is actually experiencing the refault event. Make sure the folio is * locked to guarantee folio_memcg() stability throughout. */ nr = folio_nr_pages(folio); memcg = get_mem_cgroup_from_folio(folio); lruvec = mem_cgroup_lruvec(memcg, folio_pgdat(folio)); mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); if (!workingset_test_recent(shadow, file, &workingset, true)) goto out; folio_set_active(folio); workingset_age_nonresident(lruvec, nr); mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file, nr); /* Folio was active prior to eviction */ if (workingset) { folio_set_workingset(folio); /* * XXX: Move to folio_add_lru() when it supports new vs * putback */ lru_note_cost_refault(folio); mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr); } out: mem_cgroup_put(memcg); } /** * workingset_activation - note a page activation * @folio: Folio that is being activated. */ void workingset_activation(struct folio *folio) { /* * Filter non-memcg pages here, e.g. unmap can call * mark_page_accessed() on VDSO pages. */ if (mem_cgroup_disabled() || folio_memcg_charged(folio)) { rcu_read_lock(); workingset_age_nonresident(folio_lruvec(folio), folio_nr_pages(folio)); rcu_read_unlock(); } } /* * Shadow entries reflect the share of the working set that does not * fit into memory, so their number depends on the access pattern of * the workload. In most cases, they will refault or get reclaimed * along with the inode, but a (malicious) workload that streams * through files with a total size several times that of available * memory, while preventing the inodes from being reclaimed, can * create excessive amounts of shadow nodes. To keep a lid on this, * track shadow nodes and reclaim them when they grow way past the * point where they would still be useful. */ struct list_lru shadow_nodes; void workingset_update_node(struct xa_node *node) { struct page *page = virt_to_page(node); /* * Track non-empty nodes that contain only shadow entries; * unlink those that contain pages or are being freed. * * Avoid acquiring the list_lru lock when the nodes are * already where they should be. The list_empty() test is safe * as node->private_list is protected by the i_pages lock. */ lockdep_assert_held(&node->array->xa_lock); if (node->count && node->count == node->nr_values) { if (list_empty(&node->private_list)) { list_lru_add_obj(&shadow_nodes, &node->private_list); __inc_node_page_state(page, WORKINGSET_NODES); } } else { if (!list_empty(&node->private_list)) { list_lru_del_obj(&shadow_nodes, &node->private_list); __dec_node_page_state(page, WORKINGSET_NODES); } } } static unsigned long count_shadow_nodes(struct shrinker *shrinker, struct shrink_control *sc) { unsigned long max_nodes; unsigned long nodes; unsigned long pages; nodes = list_lru_shrink_count(&shadow_nodes, sc); if (!nodes) return SHRINK_EMPTY; /* * Approximate a reasonable limit for the nodes * containing shadow entries. We don't need to keep more * shadow entries than possible pages on the active list, * since refault distances bigger than that are dismissed. * * The size of the active list converges toward 100% of * overall page cache as memory grows, with only a tiny * inactive list. Assume the total cache size for that. * * Nodes might be sparsely populated, with only one shadow * entry in the extreme case. Obviously, we cannot keep one * node for every eligible shadow entry, so compromise on a * worst-case density of 1/8th. Below that, not all eligible * refaults can be detected anymore. * * On 64-bit with 7 xa_nodes per page and 64 slots * each, this will reclaim shadow entries when they consume * ~1.8% of available memory: * * PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE */ #ifdef CONFIG_MEMCG if (sc->memcg) { struct lruvec *lruvec; int i; mem_cgroup_flush_stats_ratelimited(sc->memcg); lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid)); for (pages = 0, i = 0; i < NR_LRU_LISTS; i++) pages += lruvec_lru_size(lruvec, i, MAX_NR_ZONES - 1); pages += lruvec_page_state_local( lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT; pages += lruvec_page_state_local( lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT; } else #endif pages = node_present_pages(sc->nid); max_nodes = pages >> (XA_CHUNK_SHIFT - 3); if (nodes <= max_nodes) return 0; return nodes - max_nodes; } static enum lru_status shadow_lru_isolate(struct list_head *item, struct list_lru_one *lru, void *arg) __must_hold(lru->lock) { struct xa_node *node = container_of(item, struct xa_node, private_list); struct address_space *mapping; int ret; /* * Page cache insertions and deletions synchronously maintain * the shadow node LRU under the i_pages lock and the * &lru->lock. Because the page cache tree is emptied before * the inode can be destroyed, holding the &lru->lock pins any * address_space that has nodes on the LRU. * * We can then safely transition to the i_pages lock to * pin only the address_space of the particular node we want * to reclaim, take the node off-LRU, and drop the &lru->lock. */ mapping = container_of(node->array, struct address_space, i_pages); /* Coming from the list, invert the lock order */ if (!xa_trylock(&mapping->i_pages)) { spin_unlock_irq(&lru->lock); ret = LRU_RETRY; goto out; } /* For page cache we need to hold i_lock */ if (mapping->host != NULL) { if (!spin_trylock(&mapping->host->i_lock)) { xa_unlock(&mapping->i_pages); spin_unlock_irq(&lru->lock); ret = LRU_RETRY; goto out; } } list_lru_isolate(lru, item); __dec_node_page_state(virt_to_page(node), WORKINGSET_NODES); spin_unlock(&lru->lock); /* * The nodes should only contain one or more shadow entries, * no pages, so we expect to be able to remove them all and * delete and free the empty node afterwards. */ if (WARN_ON_ONCE(!node->nr_values)) goto out_invalid; if (WARN_ON_ONCE(node->count != node->nr_values)) goto out_invalid; xa_delete_node(node, workingset_update_node); mod_lruvec_kmem_state(node, WORKINGSET_NODERECLAIM, 1); out_invalid: xa_unlock_irq(&mapping->i_pages); if (mapping->host != NULL) { if (mapping_shrinkable(mapping)) inode_lru_list_add(mapping->host); spin_unlock(&mapping->host->i_lock); } ret = LRU_REMOVED_RETRY; out: cond_resched(); return ret; } static unsigned long scan_shadow_nodes(struct shrinker *shrinker, struct shrink_control *sc) { /* list_lru lock nests inside the IRQ-safe i_pages lock */ return list_lru_shrink_walk_irq(&shadow_nodes, sc, shadow_lru_isolate, NULL); } /* * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe * i_pages lock. */ static struct lock_class_key shadow_nodes_key; static int __init workingset_init(void) { unsigned int timestamp_bits, timestamp_bits_anon; struct shrinker *workingset_shadow_shrinker; unsigned int max_order; int ret = -ENOMEM; BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT); /* * Calculate the eviction bucket size to cover the longest * actionable refault distance, which is currently half of * memory (totalram_pages/2). However, memory hotplug may add * some more pages at runtime, so keep working with up to * double the initial memory by using totalram_pages as-is. */ timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT; timestamp_bits_anon = BITS_PER_LONG - EVICTION_SHIFT_ANON; max_order = fls_long(totalram_pages() - 1); if (max_order > (BITS_PER_LONG - EVICTION_SHIFT)) bucket_order[WORKINGSET_FILE] = max_order - timestamp_bits; if (max_order > timestamp_bits_anon) bucket_order[WORKINGSET_ANON] = max_order - timestamp_bits_anon; pr_info("workingset: timestamp_bits=%d (anon: %d) max_order=%d bucket_order=%u (anon: %d)\n", timestamp_bits, timestamp_bits_anon, max_order, bucket_order[WORKINGSET_FILE], bucket_order[WORKINGSET_ANON]); workingset_shadow_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, "mm-shadow"); if (!workingset_shadow_shrinker) goto err; ret = list_lru_init_memcg_key(&shadow_nodes, workingset_shadow_shrinker, &shadow_nodes_key); if (ret) goto err_list_lru; workingset_shadow_shrinker->count_objects = count_shadow_nodes; workingset_shadow_shrinker->scan_objects = scan_shadow_nodes; /* ->count reports only fully expendable nodes */ workingset_shadow_shrinker->seeks = 0; shrinker_register(workingset_shadow_shrinker); return 0; err_list_lru: shrinker_free(workingset_shadow_shrinker); err: return ret; } module_init(workingset_init); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ELF_H #define _ASM_X86_ELF_H /* * ELF register definitions.. */ #include <linux/thread_info.h> #include <asm/ia32.h> #include <asm/ptrace.h> #include <asm/user.h> #include <asm/auxvec.h> #include <asm/fsgsbase.h> typedef unsigned long elf_greg_t; #define ELF_NGREG (sizeof(struct user_regs_struct) / sizeof(elf_greg_t)) typedef elf_greg_t elf_gregset_t[ELF_NGREG]; typedef struct user_i387_struct elf_fpregset_t; #ifdef __i386__ #define R_386_NONE 0 #define R_386_32 1 #define R_386_PC32 2 #define R_386_GOT32 3 #define R_386_PLT32 4 #define R_386_COPY 5 #define R_386_GLOB_DAT 6 #define R_386_JMP_SLOT 7 #define R_386_RELATIVE 8 #define R_386_GOTOFF 9 #define R_386_GOTPC 10 #define R_386_NUM 11 /* * These are used to set parameters in the core dumps. */ #define ELF_CLASS ELFCLASS32 #define ELF_DATA ELFDATA2LSB #define ELF_ARCH EM_386 #else /* x86-64 relocation types */ #define R_X86_64_NONE 0 /* No reloc */ #define R_X86_64_64 1 /* Direct 64 bit */ #define R_X86_64_PC32 2 /* PC relative 32 bit signed */ #define R_X86_64_GOT32 3 /* 32 bit GOT entry */ #define R_X86_64_PLT32 4 /* 32 bit PLT address */ #define R_X86_64_COPY 5 /* Copy symbol at runtime */ #define R_X86_64_GLOB_DAT 6 /* Create GOT entry */ #define R_X86_64_JUMP_SLOT 7 /* Create PLT entry */ #define R_X86_64_RELATIVE 8 /* Adjust by program base */ #define R_X86_64_GOTPCREL 9 /* 32 bit signed pc relative offset to GOT */ #define R_X86_64_32 10 /* Direct 32 bit zero extended */ #define R_X86_64_32S 11 /* Direct 32 bit sign extended */ #define R_X86_64_16 12 /* Direct 16 bit zero extended */ #define R_X86_64_PC16 13 /* 16 bit sign extended pc relative */ #define R_X86_64_8 14 /* Direct 8 bit sign extended */ #define R_X86_64_PC8 15 /* 8 bit sign extended pc relative */ #define R_X86_64_PC64 24 /* Place relative 64-bit signed */ /* * These are used to set parameters in the core dumps. */ #define ELF_CLASS ELFCLASS64 #define ELF_DATA ELFDATA2LSB #define ELF_ARCH EM_X86_64 #endif #include <asm/vdso.h> extern unsigned int vdso64_enabled; extern unsigned int vdso32_enabled; /* * This is used to ensure we don't load something for the wrong architecture. */ #define elf_check_arch_ia32(x) \ (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486)) #include <asm/processor.h> #ifdef CONFIG_X86_32 #include <asm/desc.h> #define elf_check_arch(x) elf_check_arch_ia32(x) /* SVR4/i386 ABI (pages 3-31, 3-32) says that when the program starts %edx contains a pointer to a function which might be registered using `atexit'. This provides a mean for the dynamic linker to call DT_FINI functions for shared libraries that have been loaded before the code runs. A value of 0 tells we have no such handler. We might as well make sure everything else is cleared too (except for %esp), just to make things more deterministic. */ #define ELF_PLAT_INIT(_r, load_addr) \ do { \ _r->bx = 0; _r->cx = 0; _r->dx = 0; \ _r->si = 0; _r->di = 0; _r->bp = 0; \ _r->ax = 0; \ } while (0) /* * regs is struct pt_regs, pr_reg is elf_gregset_t (which is * now struct_user_regs, they are different) */ #define ELF_CORE_COPY_REGS(pr_reg, regs) \ do { \ pr_reg[0] = regs->bx; \ pr_reg[1] = regs->cx; \ pr_reg[2] = regs->dx; \ pr_reg[3] = regs->si; \ pr_reg[4] = regs->di; \ pr_reg[5] = regs->bp; \ pr_reg[6] = regs->ax; \ pr_reg[7] = regs->ds; \ pr_reg[8] = regs->es; \ pr_reg[9] = regs->fs; \ savesegment(gs, pr_reg[10]); \ pr_reg[11] = regs->orig_ax; \ pr_reg[12] = regs->ip; \ pr_reg[13] = regs->cs; \ pr_reg[14] = regs->flags; \ pr_reg[15] = regs->sp; \ pr_reg[16] = regs->ss; \ } while (0); #define ELF_PLATFORM (utsname()->machine) #define set_personality_64bit() do { } while (0) #else /* CONFIG_X86_32 */ /* * This is used to ensure we don't load something for the wrong architecture. */ #define elf_check_arch(x) \ ((x)->e_machine == EM_X86_64) #define compat_elf_check_arch(x) \ ((elf_check_arch_ia32(x) && ia32_enabled_verbose()) || \ (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) static inline void elf_common_init(struct thread_struct *t, struct pt_regs *regs, const u16 ds) { /* ax gets execve's return value. */ /*regs->ax = */ regs->bx = regs->cx = regs->dx = 0; regs->si = regs->di = regs->bp = 0; regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0; regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; t->fsbase = t->gsbase = 0; t->fsindex = t->gsindex = 0; t->ds = t->es = ds; } #define ELF_PLAT_INIT(_r, load_addr) \ elf_common_init(¤t->thread, _r, 0) #define COMPAT_ELF_PLAT_INIT(regs, load_addr) \ elf_common_init(¤t->thread, regs, __USER_DS) void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32); #define COMPAT_START_THREAD(ex, regs, new_ip, new_sp) \ compat_start_thread(regs, new_ip, new_sp, ex->e_machine == EM_X86_64) void set_personality_ia32(bool); #define COMPAT_SET_PERSONALITY(ex) \ set_personality_ia32((ex).e_machine == EM_X86_64) #define COMPAT_ELF_PLATFORM ("i686") /* * regs is struct pt_regs, pr_reg is elf_gregset_t (which is * now struct_user_regs, they are different). Assumes current is the process * getting dumped. */ #define ELF_CORE_COPY_REGS(pr_reg, regs) \ do { \ (pr_reg)[0] = (regs)->r15; \ (pr_reg)[1] = (regs)->r14; \ (pr_reg)[2] = (regs)->r13; \ (pr_reg)[3] = (regs)->r12; \ (pr_reg)[4] = (regs)->bp; \ (pr_reg)[5] = (regs)->bx; \ (pr_reg)[6] = (regs)->r11; \ (pr_reg)[7] = (regs)->r10; \ (pr_reg)[8] = (regs)->r9; \ (pr_reg)[9] = (regs)->r8; \ (pr_reg)[10] = (regs)->ax; \ (pr_reg)[11] = (regs)->cx; \ (pr_reg)[12] = (regs)->dx; \ (pr_reg)[13] = (regs)->si; \ (pr_reg)[14] = (regs)->di; \ (pr_reg)[15] = (regs)->orig_ax; \ (pr_reg)[16] = (regs)->ip; \ (pr_reg)[17] = (regs)->cs; \ (pr_reg)[18] = (regs)->flags; \ (pr_reg)[19] = (regs)->sp; \ (pr_reg)[20] = (regs)->ss; \ (pr_reg)[21] = x86_fsbase_read_cpu(); \ (pr_reg)[22] = x86_gsbase_read_cpu_inactive(); \ savesegment(ds, (pr_reg)[23]); \ savesegment(es, (pr_reg)[24]); \ savesegment(fs, (pr_reg)[25]); \ savesegment(gs, (pr_reg)[26]); \ } while (0); /* I'm not sure if we can use '-' here */ #define ELF_PLATFORM ("x86_64") extern void set_personality_64bit(void); extern int force_personality32; #endif /* !CONFIG_X86_32 */ #define CORE_DUMP_USE_REGSET #define ELF_EXEC_PAGESIZE 4096 /* * This is the base location for PIE (ET_DYN with INTERP) loads. On * 64-bit, this is above 4GB to leave the entire 32-bit address * space open for things that want to use the area for 32-bit pointers. */ #define ELF_ET_DYN_BASE (mmap_is_ia32() ? 0x000400000UL : \ (DEFAULT_MAP_WINDOW / 3 * 2)) /* This yields a mask that user programs can use to figure out what instruction set this CPU supports. This could be done in user space, but it's not easy, and we've already done it here. */ #define ELF_HWCAP (boot_cpu_data.x86_capability[CPUID_1_EDX]) extern u32 elf_hwcap2; /* * HWCAP2 supplies mask with kernel enabled CPU features, so that * the application can discover that it can safely use them. * The bits are defined in uapi/asm/hwcap2.h. */ #define ELF_HWCAP2 (elf_hwcap2) /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in intent than poking at uname or /proc/cpuinfo. For the moment, we have only optimizations for the Intel generations, but that could change... */ #define SET_PERSONALITY(ex) set_personality_64bit() /* * An executable for which elf_read_implies_exec() returns TRUE will * have the READ_IMPLIES_EXEC personality flag set automatically. * * The decision process for determining the results are: * * CPU: | lacks NX* | has NX, ia32 | has NX, x86_64 | * ELF: | | | | * ---------------------|------------|------------------|----------------| * missing PT_GNU_STACK | exec-all | exec-all | exec-none | * PT_GNU_STACK == RWX | exec-stack | exec-stack | exec-stack | * PT_GNU_STACK == RW | exec-none | exec-none | exec-none | * * exec-all : all PROT_READ user mappings are executable, except when * backed by files on a noexec-filesystem. * exec-none : only PROT_EXEC user mappings are executable. * exec-stack: only the stack and PROT_EXEC user mappings are executable. * * *this column has no architectural effect: NX markings are ignored by * hardware, but may have behavioral effects when "wants X" collides with * "cannot be X" constraints in memory permission flags, as in * https://lkml.kernel.org/r/20190418055759.GA3155@mellanox.com * */ #define elf_read_implies_exec(ex, executable_stack) \ (mmap_is_ia32() && executable_stack == EXSTACK_DEFAULT) struct task_struct; #define ARCH_DLINFO_IA32 \ do { \ if (VDSO_CURRENT_BASE) { \ NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \ NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \ } \ NEW_AUX_ENT(AT_MINSIGSTKSZ, get_sigframe_size()); \ } while (0) /* * True on X86_32 or when emulating IA32 on X86_64 */ static inline int mmap_is_ia32(void) { return IS_ENABLED(CONFIG_X86_32) || (IS_ENABLED(CONFIG_COMPAT) && test_thread_flag(TIF_ADDR32)); } extern unsigned long task_size_32bit(void); extern unsigned long task_size_64bit(int full_addr_space); extern unsigned long get_mmap_base(int is_legacy); extern bool mmap_address_hint_valid(unsigned long addr, unsigned long len); extern unsigned long get_sigframe_size(void); #ifdef CONFIG_X86_32 #define __STACK_RND_MASK(is32bit) (0x7ff) #define STACK_RND_MASK (0x7ff) #define ARCH_DLINFO ARCH_DLINFO_IA32 /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ #else /* CONFIG_X86_32 */ /* 1GB for 64bit, 8MB for 32bit */ #define __STACK_RND_MASK(is32bit) ((is32bit) ? 0x7ff : 0x3fffff) #define STACK_RND_MASK __STACK_RND_MASK(mmap_is_ia32()) #define ARCH_DLINFO \ do { \ if (vdso64_enabled) \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ (unsigned long __force)current->mm->context.vdso); \ NEW_AUX_ENT(AT_MINSIGSTKSZ, get_sigframe_size()); \ } while (0) /* As a historical oddity, the x32 and x86_64 vDSOs are controlled together. */ #define ARCH_DLINFO_X32 \ do { \ if (vdso64_enabled) \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ (unsigned long __force)current->mm->context.vdso); \ NEW_AUX_ENT(AT_MINSIGSTKSZ, get_sigframe_size()); \ } while (0) #define AT_SYSINFO 32 #define COMPAT_ARCH_DLINFO \ if (exec->e_machine == EM_X86_64) \ ARCH_DLINFO_X32; \ else if (IS_ENABLED(CONFIG_IA32_EMULATION)) \ ARCH_DLINFO_IA32 #define COMPAT_ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000) #endif /* !CONFIG_X86_32 */ #define VDSO_CURRENT_BASE ((unsigned long)current->mm->context.vdso) #define VDSO_ENTRY \ ((unsigned long)current->mm->context.vdso + \ vdso32_image.sym___kernel_vsyscall) struct linux_binprm; #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 extern int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp); extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp, bool x32); #define COMPAT_ARCH_SETUP_ADDITIONAL_PAGES(bprm, ex, interpreter) \ compat_arch_setup_additional_pages(bprm, interpreter, \ (ex->e_machine == EM_X86_64)) extern bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs); /* Do not change the values. See get_align_mask() */ enum align_flags { ALIGN_VA_32 = BIT(0), ALIGN_VA_64 = BIT(1), }; struct va_alignment { int flags; unsigned long mask; unsigned long bits; } ____cacheline_aligned; extern struct va_alignment va_align; #endif /* _ASM_X86_ELF_H */ |
| 5 5 5 5 5 5 5 5 5 5 5 5 5 5 1 5 5 8 8 8 8 8 8 8 8 5 5 8 8 8 8 8 8 8 8 8 8 1 1 7 8 8 8 8 8 8 11 11 5 5 5 11 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 | // SPDX-License-Identifier: GPL-2.0-only /* * Scanning implementation * * Copyright 2003, Jouni Malinen <jkmaline@cc.hut.fi> * Copyright 2004, Instant802 Networks, Inc. * Copyright 2005, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2015 Intel Mobile Communications GmbH * Copyright 2016-2017 Intel Deutschland GmbH * Copyright (C) 2018-2025 Intel Corporation */ #include <linux/if_arp.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <net/sch_generic.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/random.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "mesh.h" #define IEEE80211_PROBE_DELAY (HZ / 33) #define IEEE80211_CHANNEL_TIME (HZ / 33) #define IEEE80211_PASSIVE_CHANNEL_TIME (HZ / 9) void ieee80211_rx_bss_put(struct ieee80211_local *local, struct ieee80211_bss *bss) { if (!bss) return; cfg80211_put_bss(local->hw.wiphy, container_of((void *)bss, struct cfg80211_bss, priv)); } static bool is_uapsd_supported(struct ieee802_11_elems *elems) { u8 qos_info; if (elems->wmm_info && elems->wmm_info_len == 7 && elems->wmm_info[5] == 1) qos_info = elems->wmm_info[6]; else if (elems->wmm_param && elems->wmm_param_len == 24 && elems->wmm_param[5] == 1) qos_info = elems->wmm_param[6]; else /* no valid wmm information or parameter element found */ return false; return qos_info & IEEE80211_WMM_IE_AP_QOSINFO_UAPSD; } struct inform_bss_update_data { struct ieee80211_rx_status *rx_status; bool beacon; }; void ieee80211_inform_bss(struct wiphy *wiphy, struct cfg80211_bss *cbss, const struct cfg80211_bss_ies *ies, void *data) { struct ieee80211_local *local = wiphy_priv(wiphy); struct inform_bss_update_data *update_data = data; struct ieee80211_bss *bss = (void *)cbss->priv; struct ieee80211_rx_status *rx_status; struct ieee802_11_elems *elems; int clen, srlen; /* This happens while joining an IBSS */ if (!update_data) return; elems = ieee802_11_parse_elems(ies->data, ies->len, update_data->beacon ? IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON : IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP, NULL); if (!elems) return; rx_status = update_data->rx_status; if (update_data->beacon) bss->device_ts_beacon = rx_status->device_timestamp; else bss->device_ts_presp = rx_status->device_timestamp; if (elems->parse_error) { if (update_data->beacon) bss->corrupt_data |= IEEE80211_BSS_CORRUPT_BEACON; else bss->corrupt_data |= IEEE80211_BSS_CORRUPT_PROBE_RESP; } else { if (update_data->beacon) bss->corrupt_data &= ~IEEE80211_BSS_CORRUPT_BEACON; else bss->corrupt_data &= ~IEEE80211_BSS_CORRUPT_PROBE_RESP; } /* save the ERP value so that it is available at association time */ if (elems->erp_info && (!elems->parse_error || !(bss->valid_data & IEEE80211_BSS_VALID_ERP))) { bss->erp_value = elems->erp_info[0]; bss->has_erp_value = true; if (!elems->parse_error) bss->valid_data |= IEEE80211_BSS_VALID_ERP; } /* replace old supported rates if we get new values */ if (!elems->parse_error || !(bss->valid_data & IEEE80211_BSS_VALID_RATES)) { srlen = 0; if (elems->supp_rates) { clen = IEEE80211_MAX_SUPP_RATES; if (clen > elems->supp_rates_len) clen = elems->supp_rates_len; memcpy(bss->supp_rates, elems->supp_rates, clen); srlen += clen; } if (elems->ext_supp_rates) { clen = IEEE80211_MAX_SUPP_RATES - srlen; if (clen > elems->ext_supp_rates_len) clen = elems->ext_supp_rates_len; memcpy(bss->supp_rates + srlen, elems->ext_supp_rates, clen); srlen += clen; } if (srlen) { bss->supp_rates_len = srlen; if (!elems->parse_error) bss->valid_data |= IEEE80211_BSS_VALID_RATES; } } if (!elems->parse_error || !(bss->valid_data & IEEE80211_BSS_VALID_WMM)) { bss->wmm_used = elems->wmm_param || elems->wmm_info; bss->uapsd_supported = is_uapsd_supported(elems); if (!elems->parse_error) bss->valid_data |= IEEE80211_BSS_VALID_WMM; } if (update_data->beacon) { struct ieee80211_supported_band *sband = local->hw.wiphy->bands[rx_status->band]; if (!(rx_status->encoding == RX_ENC_HT) && !(rx_status->encoding == RX_ENC_VHT)) bss->beacon_rate = &sband->bitrates[rx_status->rate_idx]; } if (elems->vht_cap_elem) bss->vht_cap_info = le32_to_cpu(elems->vht_cap_elem->vht_cap_info); else bss->vht_cap_info = 0; kfree(elems); } struct ieee80211_bss * ieee80211_bss_info_update(struct ieee80211_local *local, struct ieee80211_rx_status *rx_status, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_channel *channel) { bool beacon = ieee80211_is_beacon(mgmt->frame_control) || ieee80211_is_s1g_beacon(mgmt->frame_control); struct cfg80211_bss *cbss; struct inform_bss_update_data update_data = { .rx_status = rx_status, .beacon = beacon, }; struct cfg80211_inform_bss bss_meta = { .boottime_ns = rx_status->boottime_ns, .drv_data = (void *)&update_data, }; bool signal_valid; struct ieee80211_sub_if_data *scan_sdata; if (rx_status->flag & RX_FLAG_NO_SIGNAL_VAL) bss_meta.signal = 0; /* invalid signal indication */ else if (ieee80211_hw_check(&local->hw, SIGNAL_DBM)) bss_meta.signal = rx_status->signal * 100; else if (ieee80211_hw_check(&local->hw, SIGNAL_UNSPEC)) bss_meta.signal = (rx_status->signal * 100) / local->hw.max_signal; bss_meta.chan = channel; rcu_read_lock(); scan_sdata = rcu_dereference(local->scan_sdata); if (scan_sdata && scan_sdata->vif.type == NL80211_IFTYPE_STATION && scan_sdata->vif.cfg.assoc && ieee80211_have_rx_timestamp(rx_status)) { struct ieee80211_bss_conf *link_conf = NULL; /* for an MLO connection, set the TSF data only in case we have * an indication on which of the links the frame was received */ if (ieee80211_vif_is_mld(&scan_sdata->vif)) { if (rx_status->link_valid) { s8 link_id = rx_status->link_id; link_conf = rcu_dereference(scan_sdata->vif.link_conf[link_id]); } } else { link_conf = &scan_sdata->vif.bss_conf; } if (link_conf) { bss_meta.parent_tsf = ieee80211_calculate_rx_timestamp(&local->hw, rx_status, len + FCS_LEN, 24); ether_addr_copy(bss_meta.parent_bssid, link_conf->bssid); } } rcu_read_unlock(); cbss = cfg80211_inform_bss_frame_data(local->hw.wiphy, &bss_meta, mgmt, len, GFP_ATOMIC); if (!cbss) return NULL; /* In case the signal is invalid update the status */ signal_valid = channel == cbss->channel; if (!signal_valid) rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL; return (void *)cbss->priv; } static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *channel, u32 scan_flags, const u8 *da) { struct ieee80211_link_data *link_sdata; u8 link_id; if (!sdata) return false; /* accept broadcast on 6 GHz and for OCE */ if (is_broadcast_ether_addr(da) && (channel->band == NL80211_BAND_6GHZ || scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP)) return true; if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR) return true; if (ether_addr_equal(da, sdata->vif.addr)) return true; for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { link_sdata = rcu_dereference(sdata->link[link_id]); if (!link_sdata) continue; if (ether_addr_equal(da, link_sdata->conf->addr)) return true; } return false; } void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); struct ieee80211_mgmt *mgmt = (void *)skb->data; struct ieee80211_bss *bss; struct ieee80211_channel *channel; struct ieee80211_ext *ext; size_t min_hdr_len = offsetof(struct ieee80211_mgmt, u.probe_resp.variable); if (!ieee80211_is_probe_resp(mgmt->frame_control) && !ieee80211_is_beacon(mgmt->frame_control) && !ieee80211_is_s1g_beacon(mgmt->frame_control)) return; if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { ext = (struct ieee80211_ext *)mgmt; min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon.variable) + ieee80211_s1g_optional_len(ext->frame_control); } if (skb->len < min_hdr_len) return; if (test_and_clear_bit(SCAN_BEACON_WAIT, &local->scanning)) { /* * we were passive scanning because of radar/no-IR, but * the beacon/proberesp rx gives us an opportunity to upgrade * to active scan */ set_bit(SCAN_BEACON_DONE, &local->scanning); wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, 0); } channel = ieee80211_get_channel_khz(local->hw.wiphy, ieee80211_rx_status_to_khz(rx_status)); if (!channel || channel->flags & IEEE80211_CHAN_DISABLED) return; if (ieee80211_is_probe_resp(mgmt->frame_control)) { struct ieee80211_sub_if_data *sdata1, *sdata2; struct cfg80211_scan_request *scan_req; struct cfg80211_sched_scan_request *sched_scan_req; u32 scan_req_flags = 0, sched_scan_req_flags = 0; sdata1 = rcu_dereference(local->scan_sdata); sdata2 = rcu_dereference(local->sched_scan_sdata); if (likely(!sdata1 && !sdata2)) return; scan_req = rcu_dereference(local->scan_req); sched_scan_req = rcu_dereference(local->sched_scan_req); if (scan_req) scan_req_flags = scan_req->flags; if (sched_scan_req) sched_scan_req_flags = sched_scan_req->flags; /* ignore ProbeResp to foreign address or non-bcast (OCE) * unless scanning with randomised address */ if (!ieee80211_scan_accept_presp(sdata1, channel, scan_req_flags, mgmt->da) && !ieee80211_scan_accept_presp(sdata2, channel, sched_scan_req_flags, mgmt->da)) return; } else { /* * Non-S1G beacons are expected only with broadcast address. * S1G beacons only carry the SA so no DA check is required * nor possible. */ if (!ieee80211_is_s1g_beacon(mgmt->frame_control) && !is_broadcast_ether_addr(mgmt->da)) return; } /* Do not update the BSS table in case of only monitor interfaces */ if (local->open_count == local->monitors) return; bss = ieee80211_bss_info_update(local, rx_status, mgmt, skb->len, channel); if (bss) ieee80211_rx_bss_put(local, bss); } static void ieee80211_prepare_scan_chandef(struct cfg80211_chan_def *chandef) { memset(chandef, 0, sizeof(*chandef)); chandef->width = NL80211_CHAN_WIDTH_20_NOHT; } /* return false if no more work */ static bool ieee80211_prep_hw_scan(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct cfg80211_scan_request *req; struct cfg80211_chan_def chandef; u8 bands_used = 0; int i, ielen; u32 *n_chans; u32 flags = 0; req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->hw.wiphy->mtx)); if (test_bit(SCAN_HW_CANCELLED, &local->scanning)) return false; if (ieee80211_hw_check(&local->hw, SINGLE_SCAN_ON_ALL_BANDS)) { local->hw_scan_req->req.n_channels = req->n_channels; for (i = 0; i < req->n_channels; i++) { local->hw_scan_req->req.channels[i] = req->channels[i]; bands_used |= BIT(req->channels[i]->band); } } else { do { if (local->hw_scan_band == NUM_NL80211_BANDS) return false; n_chans = &local->hw_scan_req->req.n_channels; *n_chans = 0; for (i = 0; i < req->n_channels; i++) { if (req->channels[i]->band != local->hw_scan_band) continue; local->hw_scan_req->req.channels[(*n_chans)++] = req->channels[i]; bands_used |= BIT(req->channels[i]->band); } local->hw_scan_band++; } while (!*n_chans); } ieee80211_prepare_scan_chandef(&chandef); if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; ielen = ieee80211_build_preq_ies(sdata, (u8 *)local->hw_scan_req->req.ie, local->hw_scan_ies_bufsize, &local->hw_scan_req->ies, req->ie, req->ie_len, bands_used, req->rates, &chandef, flags); if (ielen < 0) return false; local->hw_scan_req->req.ie_len = ielen; local->hw_scan_req->req.no_cck = req->no_cck; ether_addr_copy(local->hw_scan_req->req.mac_addr, req->mac_addr); ether_addr_copy(local->hw_scan_req->req.mac_addr_mask, req->mac_addr_mask); ether_addr_copy(local->hw_scan_req->req.bssid, req->bssid); return true; } static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) { struct ieee80211_local *local = hw_to_local(hw); bool hw_scan = test_bit(SCAN_HW_SCANNING, &local->scanning); bool was_scanning = local->scanning; struct cfg80211_scan_request *scan_req; struct ieee80211_sub_if_data *scan_sdata; struct ieee80211_sub_if_data *sdata; lockdep_assert_wiphy(local->hw.wiphy); /* * It's ok to abort a not-yet-running scan (that * we have one at all will be verified by checking * local->scan_req next), but not to complete it * successfully. */ if (WARN_ON(!local->scanning && !aborted)) aborted = true; if (WARN_ON(!local->scan_req)) return; scan_sdata = rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)); if (hw_scan && !aborted && !ieee80211_hw_check(&local->hw, SINGLE_SCAN_ON_ALL_BANDS) && ieee80211_prep_hw_scan(scan_sdata)) { int rc; rc = drv_hw_scan(local, rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)), local->hw_scan_req); if (rc == 0) return; /* HW scan failed and is going to be reported as aborted, * so clear old scan info. */ memset(&local->scan_info, 0, sizeof(local->scan_info)); aborted = true; } kfree(local->hw_scan_req); local->hw_scan_req = NULL; scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->hw.wiphy->mtx)); RCU_INIT_POINTER(local->scan_req, NULL); RCU_INIT_POINTER(local->scan_sdata, NULL); local->scanning = 0; local->scan_chandef.chan = NULL; synchronize_rcu(); if (scan_req != local->int_scan_req) { local->scan_info.aborted = aborted; cfg80211_scan_done(scan_req, &local->scan_info); } /* Set power back to normal operating levels. */ ieee80211_hw_conf_chan(local); if (!hw_scan && was_scanning) { ieee80211_configure_filter(local); drv_sw_scan_complete(local, scan_sdata); ieee80211_offchannel_return(local); } ieee80211_recalc_idle(local); ieee80211_mlme_notify_scan_completed(local); ieee80211_ibss_notify_scan_completed(local); /* Requeue all the work that might have been ignored while * the scan was in progress; if there was none this will * just be a no-op for the particular interface. */ list_for_each_entry(sdata, &local->interfaces, list) { if (ieee80211_sdata_running(sdata)) wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work); } if (was_scanning) ieee80211_start_next_roc(local); } void ieee80211_scan_completed(struct ieee80211_hw *hw, struct cfg80211_scan_info *info) { struct ieee80211_local *local = hw_to_local(hw); trace_api_scan_completed(local, info->aborted); set_bit(SCAN_COMPLETED, &local->scanning); if (info->aborted) set_bit(SCAN_ABORTED, &local->scanning); memcpy(&local->scan_info, info, sizeof(*info)); wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, 0); } EXPORT_SYMBOL(ieee80211_scan_completed); static int ieee80211_start_sw_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { /* Software scan is not supported in multi-channel cases */ if (!local->emulate_chanctx) return -EOPNOTSUPP; /* * Hardware/driver doesn't support hw_scan, so use software * scanning instead. First send a nullfunc frame with power save * bit on so that AP will buffer the frames for us while we are not * listening, then send probe requests to each channel and wait for * the responses. After all channels are scanned, tune back to the * original channel and send a nullfunc frame with power save bit * off to trigger the AP to send us all the buffered frames. * * Note that while local->sw_scanning is true everything else but * nullfunc frames and probe requests will be dropped in * ieee80211_tx_h_check_assoc(). */ drv_sw_scan_start(local, sdata, local->scan_addr); local->leave_oper_channel_time = jiffies; local->next_scan_state = SCAN_DECISION; local->scan_channel_idx = 0; ieee80211_offchannel_stop_vifs(local); /* ensure nullfunc is transmitted before leaving operating channel */ ieee80211_flush_queues(local, NULL, false); ieee80211_configure_filter(local); /* We need to set power level at maximum rate for scanning. */ ieee80211_hw_conf_chan(local); wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, 0); return 0; } static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *sdata_iter; unsigned int link_id; lockdep_assert_wiphy(local->hw.wiphy); if (!ieee80211_is_radar_required(local, req)) return true; if (!regulatory_pre_cac_allowed(local->hw.wiphy)) return false; list_for_each_entry(sdata_iter, &local->interfaces, list) { for_each_valid_link(&sdata_iter->wdev, link_id) if (sdata_iter->wdev.links[link_id].cac_started) return false; } return true; } static bool ieee80211_can_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req) { if (!__ieee80211_can_leave_ch(sdata, req)) return false; if (!list_empty(&local->roc_list)) return false; if (sdata->vif.type == NL80211_IFTYPE_STATION && sdata->u.mgd.flags & IEEE80211_STA_CONNECTION_POLL) return false; return true; } void ieee80211_run_deferred_scan(struct ieee80211_local *local) { struct cfg80211_scan_request *req; lockdep_assert_wiphy(local->hw.wiphy); if (!local->scan_req || local->scanning) return; req = wiphy_dereference(local->hw.wiphy, local->scan_req); if (!ieee80211_can_scan(local, rcu_dereference_protected( local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)), req)) return; wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, round_jiffies_relative(0)); } static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata, const u8 *src, const u8 *dst, const u8 *ssid, size_t ssid_len, const u8 *ie, size_t ie_len, u32 ratemask, u32 flags, u32 tx_flags, struct ieee80211_channel *channel) { struct sk_buff *skb; skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel, ssid, ssid_len, ie, ie_len, flags); if (skb) { if (flags & IEEE80211_PROBE_FLAG_RANDOM_SN) { struct ieee80211_hdr *hdr = (void *)skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); u16 sn = get_random_u16(); info->control.flags |= IEEE80211_TX_CTRL_NO_SEQNO; hdr->seq_ctrl = cpu_to_le16(IEEE80211_SN_TO_SEQ(sn)); } IEEE80211_SKB_CB(skb)->flags |= tx_flags; IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_DONT_USE_RATE_MASK; ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band); } } static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, unsigned long *next_delay) { int i; struct ieee80211_sub_if_data *sdata; struct cfg80211_scan_request *scan_req; enum nl80211_band band = local->hw.conf.chandef.chan->band; u32 flags = 0, tx_flags; scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->hw.wiphy->mtx)); tx_flags = IEEE80211_TX_INTFL_OFFCHAN_TX_OK; if (scan_req->no_cck) tx_flags |= IEEE80211_TX_CTL_NO_CCK_RATE; if (scan_req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; if (scan_req->flags & NL80211_SCAN_FLAG_RANDOM_SN) flags |= IEEE80211_PROBE_FLAG_RANDOM_SN; sdata = rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)); for (i = 0; i < scan_req->n_ssids; i++) ieee80211_send_scan_probe_req( sdata, local->scan_addr, scan_req->bssid, scan_req->ssids[i].ssid, scan_req->ssids[i].ssid_len, scan_req->ie, scan_req->ie_len, scan_req->rates[band], flags, tx_flags, local->hw.conf.chandef.chan); /* * After sending probe requests, wait for probe responses * on the channel. */ *next_delay = msecs_to_jiffies(scan_req->duration) > IEEE80211_PROBE_DELAY + IEEE80211_CHANNEL_TIME ? msecs_to_jiffies(scan_req->duration) - IEEE80211_PROBE_DELAY : IEEE80211_CHANNEL_TIME; local->next_scan_state = SCAN_DECISION; } static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req) { struct ieee80211_local *local = sdata->local; bool hw_scan = local->ops->hw_scan; int rc; lockdep_assert_wiphy(local->hw.wiphy); if (local->scan_req) return -EBUSY; /* For an MLO connection, if a link ID was specified, validate that it * is indeed active. */ if (ieee80211_vif_is_mld(&sdata->vif) && req->tsf_report_link_id >= 0 && !(sdata->vif.active_links & BIT(req->tsf_report_link_id))) return -EINVAL; if (!__ieee80211_can_leave_ch(sdata, req)) return -EBUSY; if (!ieee80211_can_scan(local, sdata, req)) { /* wait for the work to finish/time out */ rcu_assign_pointer(local->scan_req, req); rcu_assign_pointer(local->scan_sdata, sdata); return 0; } again: if (hw_scan) { u8 *ies; local->hw_scan_ies_bufsize = local->scan_ies_len + req->ie_len; if (ieee80211_hw_check(&local->hw, SINGLE_SCAN_ON_ALL_BANDS)) { int i, n_bands = 0; u8 bands_counted = 0; for (i = 0; i < req->n_channels; i++) { if (bands_counted & BIT(req->channels[i]->band)) continue; bands_counted |= BIT(req->channels[i]->band); n_bands++; } local->hw_scan_ies_bufsize *= n_bands; } local->hw_scan_req = kmalloc(struct_size(local->hw_scan_req, req.channels, req->n_channels) + local->hw_scan_ies_bufsize, GFP_KERNEL); if (!local->hw_scan_req) return -ENOMEM; local->hw_scan_req->req.ssids = req->ssids; local->hw_scan_req->req.n_ssids = req->n_ssids; /* None of the channels are actually set * up but let UBSAN know the boundaries. */ local->hw_scan_req->req.n_channels = req->n_channels; ies = (u8 *)local->hw_scan_req + sizeof(*local->hw_scan_req) + req->n_channels * sizeof(req->channels[0]); local->hw_scan_req->req.ie = ies; local->hw_scan_req->req.flags = req->flags; eth_broadcast_addr(local->hw_scan_req->req.bssid); local->hw_scan_req->req.duration = req->duration; local->hw_scan_req->req.duration_mandatory = req->duration_mandatory; local->hw_scan_req->req.tsf_report_link_id = req->tsf_report_link_id; local->hw_scan_band = 0; local->hw_scan_req->req.n_6ghz_params = req->n_6ghz_params; local->hw_scan_req->req.scan_6ghz_params = req->scan_6ghz_params; local->hw_scan_req->req.scan_6ghz = req->scan_6ghz; local->hw_scan_req->req.first_part = req->first_part; /* * After allocating local->hw_scan_req, we must * go through until ieee80211_prep_hw_scan(), so * anything that might be changed here and leave * this function early must not go after this * allocation. */ } rcu_assign_pointer(local->scan_req, req); rcu_assign_pointer(local->scan_sdata, sdata); if (req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) get_random_mask_addr(local->scan_addr, req->mac_addr, req->mac_addr_mask); else memcpy(local->scan_addr, sdata->vif.addr, ETH_ALEN); if (hw_scan) { __set_bit(SCAN_HW_SCANNING, &local->scanning); } else if ((req->n_channels == 1) && (req->channels[0] == local->hw.conf.chandef.chan)) { /* * If we are scanning only on the operating channel * then we do not need to stop normal activities */ unsigned long next_delay; __set_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning); ieee80211_recalc_idle(local); /* Notify driver scan is starting, keep order of operations * same as normal software scan, in case that matters. */ drv_sw_scan_start(local, sdata, local->scan_addr); ieee80211_configure_filter(local); /* accept probe-responses */ /* We need to ensure power level is at max for scanning. */ ieee80211_hw_conf_chan(local); if ((req->channels[0]->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) || !req->n_ssids) { next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; if (req->n_ssids) set_bit(SCAN_BEACON_WAIT, &local->scanning); } else { ieee80211_scan_state_send_probe(local, &next_delay); next_delay = IEEE80211_CHANNEL_TIME; } /* Now, just wait a bit and we are all done! */ wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, next_delay); return 0; } else { /* Do normal software scan */ __set_bit(SCAN_SW_SCANNING, &local->scanning); } ieee80211_recalc_idle(local); if (hw_scan) { WARN_ON(!ieee80211_prep_hw_scan(sdata)); rc = drv_hw_scan(local, sdata, local->hw_scan_req); } else { rc = ieee80211_start_sw_scan(local, sdata); } if (rc) { kfree(local->hw_scan_req); local->hw_scan_req = NULL; local->scanning = 0; ieee80211_recalc_idle(local); local->scan_req = NULL; RCU_INIT_POINTER(local->scan_sdata, NULL); } if (hw_scan && rc == 1) { /* * we can't fall back to software for P2P-GO * as it must update NoA etc. */ if (ieee80211_vif_type_p2p(&sdata->vif) == NL80211_IFTYPE_P2P_GO) return -EOPNOTSUPP; hw_scan = false; goto again; } return rc; } static unsigned long ieee80211_scan_get_channel_time(struct ieee80211_channel *chan) { /* * TODO: channel switching also consumes quite some time, * add that delay as well to get a better estimation */ if (chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) return IEEE80211_PASSIVE_CHANNEL_TIME; return IEEE80211_PROBE_DELAY + IEEE80211_CHANNEL_TIME; } static void ieee80211_scan_state_decision(struct ieee80211_local *local, unsigned long *next_delay) { bool associated = false; bool tx_empty = true; bool bad_latency; struct ieee80211_sub_if_data *sdata; struct ieee80211_channel *next_chan; enum mac80211_scan_state next_scan_state; struct cfg80211_scan_request *scan_req; lockdep_assert_wiphy(local->hw.wiphy); /* * check if at least one STA interface is associated, * check if at least one STA interface has pending tx frames * and grab the lowest used beacon interval */ list_for_each_entry(sdata, &local->interfaces, list) { if (!ieee80211_sdata_running(sdata)) continue; if (sdata->vif.type == NL80211_IFTYPE_STATION) { if (sdata->u.mgd.associated) { associated = true; if (!qdisc_all_tx_empty(sdata->dev)) { tx_empty = false; break; } } } } scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->hw.wiphy->mtx)); next_chan = scan_req->channels[local->scan_channel_idx]; /* * we're currently scanning a different channel, let's * see if we can scan another channel without interfering * with the current traffic situation. * * Keep good latency, do not stay off-channel more than 125 ms. */ bad_latency = time_after(jiffies + ieee80211_scan_get_channel_time(next_chan), local->leave_oper_channel_time + HZ / 8); if (associated && !tx_empty) { if (scan_req->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) next_scan_state = SCAN_ABORT; else next_scan_state = SCAN_SUSPEND; } else if (associated && bad_latency) { next_scan_state = SCAN_SUSPEND; } else { next_scan_state = SCAN_SET_CHANNEL; } local->next_scan_state = next_scan_state; *next_delay = 0; } static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, unsigned long *next_delay) { int skip; struct ieee80211_channel *chan; struct cfg80211_scan_request *scan_req; scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->hw.wiphy->mtx)); skip = 0; chan = scan_req->channels[local->scan_channel_idx]; local->scan_chandef.chan = chan; local->scan_chandef.center_freq1 = chan->center_freq; local->scan_chandef.freq1_offset = chan->freq_offset; local->scan_chandef.center_freq2 = 0; /* For S1G, only scan the 1MHz primaries. */ if (chan->band == NL80211_BAND_S1GHZ) { local->scan_chandef.width = NL80211_CHAN_WIDTH_1; local->scan_chandef.s1g_primary_2mhz = false; goto set_channel; } /* * If scanning on oper channel, use whatever channel-type * is currently in use. */ if (chan == local->hw.conf.chandef.chan) local->scan_chandef = local->hw.conf.chandef; else local->scan_chandef.width = NL80211_CHAN_WIDTH_20_NOHT; set_channel: if (ieee80211_hw_conf_chan(local)) skip = 1; /* advance state machine to next channel/band */ local->scan_channel_idx++; if (skip) { /* if we skip this channel return to the decision state */ local->next_scan_state = SCAN_DECISION; return; } /* * Probe delay is used to update the NAV, cf. 11.1.3.2.2 * (which unfortunately doesn't say _why_ step a) is done, * but it waits for the probe delay or until a frame is * received - and the received frame would update the NAV). * For now, we do not support waiting until a frame is * received. * * In any case, it is not necessary for a passive scan. */ if ((chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) || !scan_req->n_ssids) { *next_delay = max(msecs_to_jiffies(scan_req->duration), IEEE80211_PASSIVE_CHANNEL_TIME); local->next_scan_state = SCAN_DECISION; if (scan_req->n_ssids) set_bit(SCAN_BEACON_WAIT, &local->scanning); return; } /* active scan, send probes */ *next_delay = IEEE80211_PROBE_DELAY; local->next_scan_state = SCAN_SEND_PROBE; } static void ieee80211_scan_state_suspend(struct ieee80211_local *local, unsigned long *next_delay) { /* switch back to the operating channel */ local->scan_chandef.chan = NULL; ieee80211_hw_conf_chan(local); /* disable PS */ ieee80211_offchannel_return(local); *next_delay = HZ / 5; /* afterwards, resume scan & go to next channel */ local->next_scan_state = SCAN_RESUME; } static void ieee80211_scan_state_resume(struct ieee80211_local *local, unsigned long *next_delay) { ieee80211_offchannel_stop_vifs(local); if (local->ops->flush) { ieee80211_flush_queues(local, NULL, false); *next_delay = 0; } else *next_delay = HZ / 10; /* remember when we left the operating channel */ local->leave_oper_channel_time = jiffies; /* advance to the next channel to be scanned */ local->next_scan_state = SCAN_SET_CHANNEL; } void ieee80211_scan_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_local *local = container_of(work, struct ieee80211_local, scan_work.work); struct ieee80211_sub_if_data *sdata; struct cfg80211_scan_request *scan_req; unsigned long next_delay = 0; bool aborted; lockdep_assert_wiphy(local->hw.wiphy); if (!ieee80211_can_run_worker(local)) { aborted = true; goto out_complete; } sdata = rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)); scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->hw.wiphy->mtx)); /* When scanning on-channel, the first-callback means completed. */ if (test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning)) { aborted = test_and_clear_bit(SCAN_ABORTED, &local->scanning); goto out_complete; } if (test_and_clear_bit(SCAN_COMPLETED, &local->scanning)) { aborted = test_and_clear_bit(SCAN_ABORTED, &local->scanning); goto out_complete; } if (!sdata || !scan_req) return; if (!local->scanning) { int rc; RCU_INIT_POINTER(local->scan_req, NULL); RCU_INIT_POINTER(local->scan_sdata, NULL); rc = __ieee80211_start_scan(sdata, scan_req); if (!rc) return; /* need to complete scan in cfg80211 */ rcu_assign_pointer(local->scan_req, scan_req); aborted = true; goto out_complete; } clear_bit(SCAN_BEACON_WAIT, &local->scanning); /* * as long as no delay is required advance immediately * without scheduling a new work */ do { if (!ieee80211_sdata_running(sdata)) { aborted = true; goto out_complete; } if (test_and_clear_bit(SCAN_BEACON_DONE, &local->scanning) && local->next_scan_state == SCAN_DECISION) local->next_scan_state = SCAN_SEND_PROBE; switch (local->next_scan_state) { case SCAN_DECISION: /* if no more bands/channels left, complete scan */ if (local->scan_channel_idx >= scan_req->n_channels) { aborted = false; goto out_complete; } ieee80211_scan_state_decision(local, &next_delay); break; case SCAN_SET_CHANNEL: ieee80211_scan_state_set_channel(local, &next_delay); break; case SCAN_SEND_PROBE: ieee80211_scan_state_send_probe(local, &next_delay); break; case SCAN_SUSPEND: ieee80211_scan_state_suspend(local, &next_delay); break; case SCAN_RESUME: ieee80211_scan_state_resume(local, &next_delay); break; case SCAN_ABORT: aborted = true; goto out_complete; } } while (next_delay == 0); wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, next_delay); return; out_complete: __ieee80211_scan_completed(&local->hw, aborted); } int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req) { lockdep_assert_wiphy(sdata->local->hw.wiphy); return __ieee80211_start_scan(sdata, req); } int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, const u8 *ssid, u8 ssid_len, struct ieee80211_channel **channels, unsigned int n_channels) { struct ieee80211_local *local = sdata->local; int i, n_ch = 0; enum nl80211_band band; lockdep_assert_wiphy(local->hw.wiphy); /* busy scanning */ if (local->scan_req) return -EBUSY; /* fill internal scan request */ if (!channels) { int max_n; for (band = 0; band < NUM_NL80211_BANDS; band++) { if (!local->hw.wiphy->bands[band] || band == NL80211_BAND_6GHZ || band == NL80211_BAND_S1GHZ) continue; max_n = local->hw.wiphy->bands[band]->n_channels; for (i = 0; i < max_n; i++) { struct ieee80211_channel *tmp_ch = &local->hw.wiphy->bands[band]->channels[i]; if (tmp_ch->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_DISABLED) || !cfg80211_wdev_channel_allowed(&sdata->wdev, tmp_ch)) continue; local->int_scan_req->channels[n_ch] = tmp_ch; n_ch++; } } if (WARN_ON_ONCE(n_ch == 0)) return -EINVAL; local->int_scan_req->n_channels = n_ch; } else { for (i = 0; i < n_channels; i++) { if (channels[i]->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_DISABLED) || !cfg80211_wdev_channel_allowed(&sdata->wdev, channels[i])) continue; local->int_scan_req->channels[n_ch] = channels[i]; n_ch++; } if (n_ch == 0) return -EINVAL; local->int_scan_req->n_channels = n_ch; } local->int_scan_req->ssids = &local->scan_ssid; local->int_scan_req->n_ssids = 1; memcpy(local->int_scan_req->ssids[0].ssid, ssid, IEEE80211_MAX_SSID_LEN); local->int_scan_req->ssids[0].ssid_len = ssid_len; return __ieee80211_start_scan(sdata, sdata->local->int_scan_req); } void ieee80211_scan_cancel(struct ieee80211_local *local) { /* ensure a new scan cannot be queued */ lockdep_assert_wiphy(local->hw.wiphy); /* * We are canceling software scan, or deferred scan that was not * yet really started (see __ieee80211_start_scan ). * * Regarding hardware scan: * - we can not call __ieee80211_scan_completed() as when * SCAN_HW_SCANNING bit is set this function change * local->hw_scan_req to operate on 5G band, what race with * driver which can use local->hw_scan_req * * - we can not cancel scan_work since driver can schedule it * by ieee80211_scan_completed(..., true) to finish scan * * Hence we only call the cancel_hw_scan() callback, but the low-level * driver is still responsible for calling ieee80211_scan_completed() * after the scan was completed/aborted. */ if (!local->scan_req) return; /* * We have a scan running and the driver already reported completion, * but the worker hasn't run yet or is stuck on the mutex - mark it as * cancelled. */ if (test_bit(SCAN_HW_SCANNING, &local->scanning) && test_bit(SCAN_COMPLETED, &local->scanning)) { set_bit(SCAN_HW_CANCELLED, &local->scanning); return; } if (test_bit(SCAN_HW_SCANNING, &local->scanning)) { /* * Make sure that __ieee80211_scan_completed doesn't trigger a * scan on another band. */ set_bit(SCAN_HW_CANCELLED, &local->scanning); if (local->ops->cancel_hw_scan) drv_cancel_hw_scan(local, rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx))); return; } wiphy_delayed_work_cancel(local->hw.wiphy, &local->scan_work); /* and clean up */ memset(&local->scan_info, 0, sizeof(local->scan_info)); __ieee80211_scan_completed(&local->hw, true); } int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_sched_scan_request *req) { struct ieee80211_local *local = sdata->local; struct ieee80211_scan_ies sched_scan_ies = {}; struct cfg80211_chan_def chandef; int ret, i, iebufsz, num_bands = 0; u32 rate_masks[NUM_NL80211_BANDS] = {}; u8 bands_used = 0; u8 *ie; u32 flags = 0; lockdep_assert_wiphy(local->hw.wiphy); iebufsz = local->scan_ies_len + req->ie_len; if (!local->ops->sched_scan_start) return -EOPNOTSUPP; for (i = 0; i < NUM_NL80211_BANDS; i++) { if (local->hw.wiphy->bands[i]) { bands_used |= BIT(i); rate_masks[i] = (u32) -1; num_bands++; } } if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; ie = kcalloc(iebufsz, num_bands, GFP_KERNEL); if (!ie) { ret = -ENOMEM; goto out; } ieee80211_prepare_scan_chandef(&chandef); ret = ieee80211_build_preq_ies(sdata, ie, num_bands * iebufsz, &sched_scan_ies, req->ie, req->ie_len, bands_used, rate_masks, &chandef, flags); if (ret < 0) goto error; ret = drv_sched_scan_start(local, sdata, req, &sched_scan_ies); if (ret == 0) { rcu_assign_pointer(local->sched_scan_sdata, sdata); rcu_assign_pointer(local->sched_scan_req, req); } error: kfree(ie); out: if (ret) { /* Clean in case of failure after HW restart or upon resume. */ RCU_INIT_POINTER(local->sched_scan_sdata, NULL); RCU_INIT_POINTER(local->sched_scan_req, NULL); } return ret; } int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_sched_scan_request *req) { struct ieee80211_local *local = sdata->local; lockdep_assert_wiphy(local->hw.wiphy); if (rcu_access_pointer(local->sched_scan_sdata)) return -EBUSY; return __ieee80211_request_sched_scan_start(sdata, req); } int ieee80211_request_sched_scan_stop(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sched_scan_sdata; int ret = -ENOENT; lockdep_assert_wiphy(local->hw.wiphy); if (!local->ops->sched_scan_stop) return -EOPNOTSUPP; /* We don't want to restart sched scan anymore. */ RCU_INIT_POINTER(local->sched_scan_req, NULL); sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)); if (sched_scan_sdata) { ret = drv_sched_scan_stop(local, sched_scan_sdata); if (!ret) RCU_INIT_POINTER(local->sched_scan_sdata, NULL); } return ret; } void ieee80211_sched_scan_results(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); trace_api_sched_scan_results(local); cfg80211_sched_scan_results(hw->wiphy, 0); } EXPORT_SYMBOL(ieee80211_sched_scan_results); void ieee80211_sched_scan_end(struct ieee80211_local *local) { lockdep_assert_wiphy(local->hw.wiphy); if (!rcu_access_pointer(local->sched_scan_sdata)) return; RCU_INIT_POINTER(local->sched_scan_sdata, NULL); /* If sched scan was aborted by the driver. */ RCU_INIT_POINTER(local->sched_scan_req, NULL); cfg80211_sched_scan_stopped_locked(local->hw.wiphy, 0); } void ieee80211_sched_scan_stopped_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_local *local = container_of(work, struct ieee80211_local, sched_scan_stopped_work); ieee80211_sched_scan_end(local); } void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); trace_api_sched_scan_stopped(local); /* * this shouldn't really happen, so for simplicity * simply ignore it, and let mac80211 reconfigure * the sched scan later on. */ if (local->in_reconfig) return; wiphy_work_queue(hw->wiphy, &local->sched_scan_stopped_work); } EXPORT_SYMBOL(ieee80211_sched_scan_stopped); |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 | // SPDX-License-Identifier: GPL-2.0 /* * (C) 2001 Clemson University and The University of Chicago * * Changes by Acxiom Corporation to add protocol version to kernel * communication, Copyright Acxiom Corporation, 2005. * * See COPYING in top-level directory. */ #include "protocol.h" #include "orangefs-kernel.h" #include "orangefs-dev-proto.h" #include "orangefs-bufmap.h" #include "orangefs-debugfs.h" #include <linux/debugfs.h> #include <linux/slab.h> /* this file implements the /dev/pvfs2-req device node */ uint32_t orangefs_userspace_version; static int open_access_count; static DEFINE_MUTEX(devreq_mutex); #define DUMP_DEVICE_ERROR() \ do { \ gossip_err("*****************************************************\n");\ gossip_err("ORANGEFS Device Error: You cannot open the device file "); \ gossip_err("\n/dev/%s more than once. Please make sure that\nthere " \ "are no ", ORANGEFS_REQDEVICE_NAME); \ gossip_err("instances of a program using this device\ncurrently " \ "running. (You must verify this!)\n"); \ gossip_err("For example, you can use the lsof program as follows:\n");\ gossip_err("'lsof | grep %s' (run this as root)\n", \ ORANGEFS_REQDEVICE_NAME); \ gossip_err(" open_access_count = %d\n", open_access_count); \ gossip_err("*****************************************************\n");\ } while (0) static int hash_func(__u64 tag, int table_size) { return do_div(tag, (unsigned int)table_size); } static void orangefs_devreq_add_op(struct orangefs_kernel_op_s *op) { int index = hash_func(op->tag, hash_table_size); list_add_tail(&op->list, &orangefs_htable_ops_in_progress[index]); } /* * find the op with this tag and remove it from the in progress * hash table. */ static struct orangefs_kernel_op_s *orangefs_devreq_remove_op(__u64 tag) { struct orangefs_kernel_op_s *op, *next; int index; index = hash_func(tag, hash_table_size); spin_lock(&orangefs_htable_ops_in_progress_lock); list_for_each_entry_safe(op, next, &orangefs_htable_ops_in_progress[index], list) { if (op->tag == tag && !op_state_purged(op) && !op_state_given_up(op)) { list_del_init(&op->list); spin_unlock(&orangefs_htable_ops_in_progress_lock); return op; } } spin_unlock(&orangefs_htable_ops_in_progress_lock); return NULL; } /* Returns whether any FS are still pending remounted */ static int mark_all_pending_mounts(void) { int unmounted = 1; struct orangefs_sb_info_s *orangefs_sb = NULL; spin_lock(&orangefs_superblocks_lock); list_for_each_entry(orangefs_sb, &orangefs_superblocks, list) { /* All of these file system require a remount */ orangefs_sb->mount_pending = 1; unmounted = 0; } spin_unlock(&orangefs_superblocks_lock); return unmounted; } /* * Determine if a given file system needs to be remounted or not * Returns -1 on error * 0 if already mounted * 1 if needs remount */ static int fs_mount_pending(__s32 fsid) { int mount_pending = -1; struct orangefs_sb_info_s *orangefs_sb = NULL; spin_lock(&orangefs_superblocks_lock); list_for_each_entry(orangefs_sb, &orangefs_superblocks, list) { if (orangefs_sb->fs_id == fsid) { mount_pending = orangefs_sb->mount_pending; break; } } spin_unlock(&orangefs_superblocks_lock); return mount_pending; } static int orangefs_devreq_open(struct inode *inode, struct file *file) { int ret = -EINVAL; /* in order to ensure that the filesystem driver sees correct UIDs */ if (file->f_cred->user_ns != &init_user_ns) { gossip_err("%s: device cannot be opened outside init_user_ns\n", __func__); goto out; } if (!(file->f_flags & O_NONBLOCK)) { gossip_err("%s: device cannot be opened in blocking mode\n", __func__); goto out; } ret = -EACCES; gossip_debug(GOSSIP_DEV_DEBUG, "client-core: opening device\n"); mutex_lock(&devreq_mutex); if (open_access_count == 0) { open_access_count = 1; ret = 0; } else { DUMP_DEVICE_ERROR(); } mutex_unlock(&devreq_mutex); out: gossip_debug(GOSSIP_DEV_DEBUG, "pvfs2-client-core: open device complete (ret = %d)\n", ret); return ret; } /* Function for read() callers into the device */ static ssize_t orangefs_devreq_read(struct file *file, char __user *buf, size_t count, loff_t *offset) { struct orangefs_kernel_op_s *op, *temp; __s32 proto_ver = ORANGEFS_KERNEL_PROTO_VERSION; static __s32 magic = ORANGEFS_DEVREQ_MAGIC; struct orangefs_kernel_op_s *cur_op; unsigned long ret; /* We do not support blocking IO. */ if (!(file->f_flags & O_NONBLOCK)) { gossip_err("%s: blocking read from client-core.\n", __func__); return -EINVAL; } /* * The client will do an ioctl to find MAX_DEV_REQ_UPSIZE, then * always read with that size buffer. */ if (count != MAX_DEV_REQ_UPSIZE) { gossip_err("orangefs: client-core tried to read wrong size\n"); return -EINVAL; } /* Check for an empty list before locking. */ if (list_empty(&orangefs_request_list)) return -EAGAIN; restart: cur_op = NULL; /* Get next op (if any) from top of list. */ spin_lock(&orangefs_request_list_lock); list_for_each_entry_safe(op, temp, &orangefs_request_list, list) { __s32 fsid; /* This lock is held past the end of the loop when we break. */ spin_lock(&op->lock); if (unlikely(op_state_purged(op) || op_state_given_up(op))) { spin_unlock(&op->lock); continue; } fsid = fsid_of_op(op); if (fsid != ORANGEFS_FS_ID_NULL) { int ret; /* Skip ops whose filesystem needs to be mounted. */ ret = fs_mount_pending(fsid); if (ret == 1) { gossip_debug(GOSSIP_DEV_DEBUG, "%s: mount pending, skipping op tag " "%llu %s\n", __func__, llu(op->tag), get_opname_string(op)); spin_unlock(&op->lock); continue; /* * Skip ops whose filesystem we don't know about unless * it is being mounted or unmounted. It is possible for * a filesystem we don't know about to be unmounted if * it fails to mount in the kernel after userspace has * been sent the mount request. */ /* XXX: is there a better way to detect this? */ } else if (ret == -1 && !(op->upcall.type == ORANGEFS_VFS_OP_FS_MOUNT || op->upcall.type == ORANGEFS_VFS_OP_GETATTR || op->upcall.type == ORANGEFS_VFS_OP_FS_UMOUNT)) { gossip_debug(GOSSIP_DEV_DEBUG, "orangefs: skipping op tag %llu %s\n", llu(op->tag), get_opname_string(op)); gossip_err( "orangefs: ERROR: fs_mount_pending %d\n", fsid); spin_unlock(&op->lock); continue; } } /* * Either this op does not pertain to a filesystem, is mounting * a filesystem, or pertains to a mounted filesystem. Let it * through. */ cur_op = op; break; } /* * At this point we either have a valid op and can continue or have not * found an op and must ask the client to try again later. */ if (!cur_op) { spin_unlock(&orangefs_request_list_lock); return -EAGAIN; } gossip_debug(GOSSIP_DEV_DEBUG, "%s: reading op tag %llu %s\n", __func__, llu(cur_op->tag), get_opname_string(cur_op)); /* * Such an op should never be on the list in the first place. If so, we * will abort. */ if (op_state_in_progress(cur_op) || op_state_serviced(cur_op)) { gossip_err("orangefs: ERROR: Current op already queued.\n"); list_del_init(&cur_op->list); spin_unlock(&cur_op->lock); spin_unlock(&orangefs_request_list_lock); return -EAGAIN; } list_del_init(&cur_op->list); spin_unlock(&orangefs_request_list_lock); spin_unlock(&cur_op->lock); /* Push the upcall out. */ ret = copy_to_user(buf, &proto_ver, sizeof(__s32)); if (ret != 0) goto error; ret = copy_to_user(buf + sizeof(__s32), &magic, sizeof(__s32)); if (ret != 0) goto error; ret = copy_to_user(buf + 2 * sizeof(__s32), &cur_op->tag, sizeof(__u64)); if (ret != 0) goto error; ret = copy_to_user(buf + 2 * sizeof(__s32) + sizeof(__u64), &cur_op->upcall, sizeof(struct orangefs_upcall_s)); if (ret != 0) goto error; spin_lock(&orangefs_htable_ops_in_progress_lock); spin_lock(&cur_op->lock); if (unlikely(op_state_given_up(cur_op))) { spin_unlock(&cur_op->lock); spin_unlock(&orangefs_htable_ops_in_progress_lock); complete(&cur_op->waitq); goto restart; } /* * Set the operation to be in progress and move it between lists since * it has been sent to the client. */ set_op_state_inprogress(cur_op); gossip_debug(GOSSIP_DEV_DEBUG, "%s: 1 op:%s: op_state:%d: process:%s:\n", __func__, get_opname_string(cur_op), cur_op->op_state, current->comm); orangefs_devreq_add_op(cur_op); spin_unlock(&cur_op->lock); spin_unlock(&orangefs_htable_ops_in_progress_lock); /* The client only asks to read one size buffer. */ return MAX_DEV_REQ_UPSIZE; error: /* * We were unable to copy the op data to the client. Put the op back in * list. If client has crashed, the op will be purged later when the * device is released. */ gossip_err("orangefs: Failed to copy data to user space\n"); spin_lock(&orangefs_request_list_lock); spin_lock(&cur_op->lock); if (likely(!op_state_given_up(cur_op))) { set_op_state_waiting(cur_op); gossip_debug(GOSSIP_DEV_DEBUG, "%s: 2 op:%s: op_state:%d: process:%s:\n", __func__, get_opname_string(cur_op), cur_op->op_state, current->comm); list_add(&cur_op->list, &orangefs_request_list); spin_unlock(&cur_op->lock); } else { spin_unlock(&cur_op->lock); complete(&cur_op->waitq); } spin_unlock(&orangefs_request_list_lock); return -EFAULT; } /* * Function for writev() callers into the device. * * Userspace should have written: * - __u32 version * - __u32 magic * - __u64 tag * - struct orangefs_downcall_s * - trailer buffer (in the case of READDIR operations) */ static ssize_t orangefs_devreq_write_iter(struct kiocb *iocb, struct iov_iter *iter) { ssize_t ret; struct orangefs_kernel_op_s *op = NULL; struct { __u32 version; __u32 magic; __u64 tag; } head; int total = ret = iov_iter_count(iter); int downcall_size = sizeof(struct orangefs_downcall_s); int head_size = sizeof(head); gossip_debug(GOSSIP_DEV_DEBUG, "%s: total:%d: ret:%zd:\n", __func__, total, ret); if (total < MAX_DEV_REQ_DOWNSIZE) { gossip_err("%s: total:%d: must be at least:%u:\n", __func__, total, (unsigned int) MAX_DEV_REQ_DOWNSIZE); return -EFAULT; } if (!copy_from_iter_full(&head, head_size, iter)) { gossip_err("%s: failed to copy head.\n", __func__); return -EFAULT; } if (head.version < ORANGEFS_MINIMUM_USERSPACE_VERSION) { gossip_err("%s: userspace claims version" "%d, minimum version required: %d.\n", __func__, head.version, ORANGEFS_MINIMUM_USERSPACE_VERSION); return -EPROTO; } if (head.magic != ORANGEFS_DEVREQ_MAGIC) { gossip_err("Error: Device magic number does not match.\n"); return -EPROTO; } if (!orangefs_userspace_version) { orangefs_userspace_version = head.version; } else if (orangefs_userspace_version != head.version) { gossip_err("Error: userspace version changes\n"); return -EPROTO; } /* remove the op from the in progress hash table */ op = orangefs_devreq_remove_op(head.tag); if (!op) { gossip_debug(GOSSIP_DEV_DEBUG, "%s: No one's waiting for tag %llu\n", __func__, llu(head.tag)); return ret; } if (!copy_from_iter_full(&op->downcall, downcall_size, iter)) { gossip_err("%s: failed to copy downcall.\n", __func__); goto Efault; } if (op->downcall.status) goto wakeup; /* * We've successfully peeled off the head and the downcall. * Something has gone awry if total doesn't equal the * sum of head_size, downcall_size and trailer_size. */ if ((head_size + downcall_size + op->downcall.trailer_size) != total) { gossip_err("%s: funky write, head_size:%d" ": downcall_size:%d: trailer_size:%lld" ": total size:%d:\n", __func__, head_size, downcall_size, op->downcall.trailer_size, total); goto Efault; } /* Only READDIR operations should have trailers. */ if ((op->downcall.type != ORANGEFS_VFS_OP_READDIR) && (op->downcall.trailer_size != 0)) { gossip_err("%s: %x operation with trailer.", __func__, op->downcall.type); goto Efault; } /* READDIR operations should always have trailers. */ if ((op->downcall.type == ORANGEFS_VFS_OP_READDIR) && (op->downcall.trailer_size == 0)) { gossip_err("%s: %x operation with no trailer.", __func__, op->downcall.type); goto Efault; } if (op->downcall.type != ORANGEFS_VFS_OP_READDIR) goto wakeup; op->downcall.trailer_buf = vzalloc(op->downcall.trailer_size); if (!op->downcall.trailer_buf) goto Enomem; if (!copy_from_iter_full(op->downcall.trailer_buf, op->downcall.trailer_size, iter)) { gossip_err("%s: failed to copy trailer.\n", __func__); vfree(op->downcall.trailer_buf); goto Efault; } wakeup: /* * Return to vfs waitqueue, and back to service_operation * through wait_for_matching_downcall. */ spin_lock(&op->lock); if (unlikely(op_is_cancel(op))) { spin_unlock(&op->lock); put_cancel(op); } else if (unlikely(op_state_given_up(op))) { spin_unlock(&op->lock); complete(&op->waitq); } else { set_op_state_serviced(op); gossip_debug(GOSSIP_DEV_DEBUG, "%s: op:%s: op_state:%d: process:%s:\n", __func__, get_opname_string(op), op->op_state, current->comm); spin_unlock(&op->lock); } return ret; Efault: op->downcall.status = -(ORANGEFS_ERROR_BIT | 9); ret = -EFAULT; goto wakeup; Enomem: op->downcall.status = -(ORANGEFS_ERROR_BIT | 8); ret = -ENOMEM; goto wakeup; } /* * NOTE: gets called when the last reference to this device is dropped. * Using the open_access_count variable, we enforce a reference count * on this file so that it can be opened by only one process at a time. * the devreq_mutex is used to make sure all i/o has completed * before we call orangefs_bufmap_finalize, and similar such tricky * situations */ static int orangefs_devreq_release(struct inode *inode, struct file *file) { int unmounted = 0; gossip_debug(GOSSIP_DEV_DEBUG, "%s:pvfs2-client-core: exiting, closing device\n", __func__); mutex_lock(&devreq_mutex); orangefs_bufmap_finalize(); open_access_count = -1; unmounted = mark_all_pending_mounts(); gossip_debug(GOSSIP_DEV_DEBUG, "ORANGEFS Device Close: Filesystem(s) %s\n", (unmounted ? "UNMOUNTED" : "MOUNTED")); purge_waiting_ops(); purge_inprogress_ops(); orangefs_bufmap_run_down(); gossip_debug(GOSSIP_DEV_DEBUG, "pvfs2-client-core: device close complete\n"); open_access_count = 0; orangefs_userspace_version = 0; mutex_unlock(&devreq_mutex); return 0; } int is_daemon_in_service(void) { int in_service; /* * What this function does is checks if client-core is alive * based on the access count we maintain on the device. */ mutex_lock(&devreq_mutex); in_service = open_access_count == 1 ? 0 : -EIO; mutex_unlock(&devreq_mutex); return in_service; } bool __is_daemon_in_service(void) { return open_access_count == 1; } static inline long check_ioctl_command(unsigned int command) { /* Check for valid ioctl codes */ if (_IOC_TYPE(command) != ORANGEFS_DEV_MAGIC) { gossip_err("device ioctl magic numbers don't match! Did you rebuild pvfs2-client-core/libpvfs2? [cmd %x, magic %x != %x]\n", command, _IOC_TYPE(command), ORANGEFS_DEV_MAGIC); return -EINVAL; } /* and valid ioctl commands */ if (_IOC_NR(command) >= ORANGEFS_DEV_MAXNR || _IOC_NR(command) <= 0) { gossip_err("Invalid ioctl command number [%d >= %d]\n", _IOC_NR(command), ORANGEFS_DEV_MAXNR); return -ENOIOCTLCMD; } return 0; } static long dispatch_ioctl_command(unsigned int command, unsigned long arg) { static __s32 magic = ORANGEFS_DEVREQ_MAGIC; static __s32 max_up_size = MAX_DEV_REQ_UPSIZE; static __s32 max_down_size = MAX_DEV_REQ_DOWNSIZE; struct ORANGEFS_dev_map_desc user_desc; int ret = 0; int upstream_kmod = 1; struct orangefs_sb_info_s *orangefs_sb; /* mtmoore: add locking here */ switch (command) { case ORANGEFS_DEV_GET_MAGIC: return ((put_user(magic, (__s32 __user *) arg) == -EFAULT) ? -EIO : 0); case ORANGEFS_DEV_GET_MAX_UPSIZE: return ((put_user(max_up_size, (__s32 __user *) arg) == -EFAULT) ? -EIO : 0); case ORANGEFS_DEV_GET_MAX_DOWNSIZE: return ((put_user(max_down_size, (__s32 __user *) arg) == -EFAULT) ? -EIO : 0); case ORANGEFS_DEV_MAP: ret = copy_from_user(&user_desc, (struct ORANGEFS_dev_map_desc __user *) arg, sizeof(struct ORANGEFS_dev_map_desc)); /* WTF -EIO and not -EFAULT? */ return ret ? -EIO : orangefs_bufmap_initialize(&user_desc); case ORANGEFS_DEV_REMOUNT_ALL: gossip_debug(GOSSIP_DEV_DEBUG, "%s: got ORANGEFS_DEV_REMOUNT_ALL\n", __func__); /* * remount all mounted orangefs volumes to regain the lost * dynamic mount tables (if any) -- NOTE: this is done * without keeping the superblock list locked due to the * upcall/downcall waiting. also, the request mutex is * used to ensure that no operations will be serviced until * all of the remounts are serviced (to avoid ops between * mounts to fail) */ ret = mutex_lock_interruptible(&orangefs_request_mutex); if (ret < 0) return ret; gossip_debug(GOSSIP_DEV_DEBUG, "%s: priority remount in progress\n", __func__); spin_lock(&orangefs_superblocks_lock); list_for_each_entry(orangefs_sb, &orangefs_superblocks, list) { /* * We have to drop the spinlock, so entries can be * removed. They can't be freed, though, so we just * keep the forward pointers and zero the back ones - * that way we can get to the rest of the list. */ if (!orangefs_sb->list.prev) continue; gossip_debug(GOSSIP_DEV_DEBUG, "%s: Remounting SB %p\n", __func__, orangefs_sb); spin_unlock(&orangefs_superblocks_lock); ret = orangefs_remount(orangefs_sb); spin_lock(&orangefs_superblocks_lock); if (ret) { gossip_debug(GOSSIP_DEV_DEBUG, "SB %p remount failed\n", orangefs_sb); break; } } spin_unlock(&orangefs_superblocks_lock); gossip_debug(GOSSIP_DEV_DEBUG, "%s: priority remount complete\n", __func__); mutex_unlock(&orangefs_request_mutex); return ret; case ORANGEFS_DEV_UPSTREAM: ret = copy_to_user((void __user *)arg, &upstream_kmod, sizeof(upstream_kmod)); if (ret != 0) return -EIO; else return ret; case ORANGEFS_DEV_CLIENT_MASK: return orangefs_debugfs_new_client_mask((void __user *)arg); case ORANGEFS_DEV_CLIENT_STRING: return orangefs_debugfs_new_client_string((void __user *)arg); case ORANGEFS_DEV_DEBUG: return orangefs_debugfs_new_debug((void __user *)arg); default: return -ENOIOCTLCMD; } return -ENOIOCTLCMD; } static long orangefs_devreq_ioctl(struct file *file, unsigned int command, unsigned long arg) { long ret; /* Check for properly constructed commands */ ret = check_ioctl_command(command); if (ret < 0) return (int)ret; return (int)dispatch_ioctl_command(command, arg); } #ifdef CONFIG_COMPAT /* CONFIG_COMPAT is in .config */ /* Compat structure for the ORANGEFS_DEV_MAP ioctl */ struct ORANGEFS_dev_map_desc32 { compat_uptr_t ptr; __s32 total_size; __s32 size; __s32 count; }; /* * 32 bit user-space apps' ioctl handlers when kernel modules * is compiled as a 64 bit one */ static long orangefs_devreq_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long args) { long ret; /* Check for properly constructed commands */ ret = check_ioctl_command(cmd); if (ret < 0) return ret; if (cmd == ORANGEFS_DEV_MAP) { struct ORANGEFS_dev_map_desc desc; struct ORANGEFS_dev_map_desc32 d32; if (copy_from_user(&d32, (void __user *)args, sizeof(d32))) return -EFAULT; desc.ptr = compat_ptr(d32.ptr); desc.total_size = d32.total_size; desc.size = d32.size; desc.count = d32.count; return orangefs_bufmap_initialize(&desc); } /* no other ioctl requires translation */ return dispatch_ioctl_command(cmd, args); } #endif /* CONFIG_COMPAT is in .config */ static __poll_t orangefs_devreq_poll(struct file *file, struct poll_table_struct *poll_table) { __poll_t poll_revent_mask = 0; poll_wait(file, &orangefs_request_list_waitq, poll_table); if (!list_empty(&orangefs_request_list)) poll_revent_mask |= EPOLLIN; return poll_revent_mask; } /* the assigned character device major number */ static int orangefs_dev_major; static const struct file_operations orangefs_devreq_file_operations = { .owner = THIS_MODULE, .read = orangefs_devreq_read, .write_iter = orangefs_devreq_write_iter, .open = orangefs_devreq_open, .release = orangefs_devreq_release, .unlocked_ioctl = orangefs_devreq_ioctl, #ifdef CONFIG_COMPAT /* CONFIG_COMPAT is in .config */ .compat_ioctl = orangefs_devreq_compat_ioctl, #endif .poll = orangefs_devreq_poll }; /* * Initialize orangefs device specific state: * Must be called at module load time only */ int orangefs_dev_init(void) { /* register orangefs-req device */ orangefs_dev_major = register_chrdev(0, ORANGEFS_REQDEVICE_NAME, &orangefs_devreq_file_operations); if (orangefs_dev_major < 0) { gossip_debug(GOSSIP_DEV_DEBUG, "Failed to register /dev/%s (error %d)\n", ORANGEFS_REQDEVICE_NAME, orangefs_dev_major); return orangefs_dev_major; } gossip_debug(GOSSIP_DEV_DEBUG, "*** /dev/%s character device registered ***\n", ORANGEFS_REQDEVICE_NAME); gossip_debug(GOSSIP_DEV_DEBUG, "'mknod /dev/%s c %d 0'.\n", ORANGEFS_REQDEVICE_NAME, orangefs_dev_major); return 0; } void orangefs_dev_cleanup(void) { unregister_chrdev(orangefs_dev_major, ORANGEFS_REQDEVICE_NAME); gossip_debug(GOSSIP_DEV_DEBUG, "*** /dev/%s character device unregistered ***\n", ORANGEFS_REQDEVICE_NAME); } |
| 25 12 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Media device node * * Copyright (C) 2010 Nokia Corporation * * Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com> * Sakari Ailus <sakari.ailus@iki.fi> * * -- * * Common functions for media-related drivers to register and unregister media * device nodes. */ #ifndef _MEDIA_DEVNODE_H #define _MEDIA_DEVNODE_H #include <linux/poll.h> #include <linux/fs.h> #include <linux/device.h> #include <linux/cdev.h> #include <linux/debugfs.h> struct media_device; /* debugfs top-level media directory */ extern struct dentry *media_debugfs_root; /* * Flag to mark the media_devnode struct as registered. Drivers must not touch * this flag directly, it will be set and cleared by media_devnode_register and * media_devnode_unregister. */ #define MEDIA_FLAG_REGISTERED 0 /** * struct media_file_operations - Media device file operations * * @owner: should be filled with %THIS_MODULE * @read: pointer to the function that implements read() syscall * @write: pointer to the function that implements write() syscall * @poll: pointer to the function that implements poll() syscall * @ioctl: pointer to the function that implements ioctl() syscall * @compat_ioctl: pointer to the function that will handle 32 bits userspace * calls to the ioctl() syscall on a Kernel compiled with 64 bits. * @open: pointer to the function that implements open() syscall * @release: pointer to the function that will release the resources allocated * by the @open function. */ struct media_file_operations { struct module *owner; ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*open) (struct file *); int (*release) (struct file *); }; /** * struct media_devnode - Media device node * @media_dev: pointer to struct &media_device * @fops: pointer to struct &media_file_operations with media device ops * @dev: pointer to struct &device containing the media controller device * @cdev: struct cdev pointer character device * @parent: parent device * @minor: device node minor number * @flags: flags, combination of the ``MEDIA_FLAG_*`` constants * @release: release callback called at the end of ``media_devnode_release()`` * routine at media-device.c. * * This structure represents a media-related device node. * * The @parent is a physical device. It must be set by core or device drivers * before registering the node. */ struct media_devnode { struct media_device *media_dev; /* device ops */ const struct media_file_operations *fops; /* sysfs */ struct device dev; /* media device */ struct cdev cdev; /* character device */ struct device *parent; /* device parent */ /* device info */ int minor; unsigned long flags; /* Use bitops to access flags */ /* callbacks */ void (*release)(struct media_devnode *devnode); }; /* dev to media_devnode */ #define to_media_devnode(cd) container_of(cd, struct media_devnode, dev) /** * media_devnode_register - register a media device node * * @mdev: struct media_device we want to register a device node * @devnode: media device node structure we want to register * @owner: should be filled with %THIS_MODULE * * The registration code assigns minor numbers and registers the new device node * with the kernel. An error is returned if no free minor number can be found, * or if the registration of the device node fails. * * Zero is returned on success. * * Note that if the media_devnode_register call fails, the release() callback of * the media_devnode structure is *not* called, so the caller is responsible for * freeing any data. */ int __must_check media_devnode_register(struct media_device *mdev, struct media_devnode *devnode, struct module *owner); /** * media_devnode_unregister_prepare - clear the media device node register bit * @devnode: the device node to prepare for unregister * * This clears the passed device register bit. Future open calls will be met * with errors. Should be called before media_devnode_unregister() to avoid * races with unregister and device file open calls. * * This function can safely be called if the device node has never been * registered or has already been unregistered. */ void media_devnode_unregister_prepare(struct media_devnode *devnode); /** * media_devnode_unregister - unregister a media device node * @devnode: the device node to unregister * * This unregisters the passed device. Future open calls will be met with * errors. * * Should be called after media_devnode_unregister_prepare() */ void media_devnode_unregister(struct media_devnode *devnode); /** * media_devnode_data - returns a pointer to the &media_devnode * * @filp: pointer to struct &file */ static inline struct media_devnode *media_devnode_data(struct file *filp) { return filp->private_data; } /** * media_devnode_is_registered - returns true if &media_devnode is registered; * false otherwise. * * @devnode: pointer to struct &media_devnode. * * Note: If mdev is NULL, it also returns false. */ static inline int media_devnode_is_registered(struct media_devnode *devnode) { if (!devnode) return false; return test_bit(MEDIA_FLAG_REGISTERED, &devnode->flags); } #endif /* _MEDIA_DEVNODE_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Symmetric key ciphers. * * Copyright (c) 2007-2015 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_SKCIPHER_H #define _CRYPTO_SKCIPHER_H #include <linux/atomic.h> #include <linux/container_of.h> #include <linux/crypto.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/types.h> /* Set this bit if the lskcipher operation is a continuation. */ #define CRYPTO_LSKCIPHER_FLAG_CONT 0x00000001 /* Set this bit if the lskcipher operation is final. */ #define CRYPTO_LSKCIPHER_FLAG_FINAL 0x00000002 /* The bit CRYPTO_TFM_REQ_MAY_SLEEP can also be set if needed. */ /* Set this bit if the skcipher operation is a continuation. */ #define CRYPTO_SKCIPHER_REQ_CONT 0x00000001 /* Set this bit if the skcipher operation is not final. */ #define CRYPTO_SKCIPHER_REQ_NOTFINAL 0x00000002 struct scatterlist; /** * struct skcipher_request - Symmetric key cipher request * @cryptlen: Number of bytes to encrypt or decrypt * @iv: Initialisation Vector * @src: Source SG list * @dst: Destination SG list * @base: Underlying async request * @__ctx: Start of private context data */ struct skcipher_request { unsigned int cryptlen; u8 *iv; struct scatterlist *src; struct scatterlist *dst; struct crypto_async_request base; void *__ctx[] CRYPTO_MINALIGN_ATTR; }; struct crypto_skcipher { unsigned int reqsize; struct crypto_tfm base; }; struct crypto_sync_skcipher { struct crypto_skcipher base; }; struct crypto_lskcipher { struct crypto_tfm base; }; /* * struct skcipher_alg_common - common properties of skcipher_alg * @min_keysize: Minimum key size supported by the transformation. This is the * smallest key length supported by this transformation algorithm. * This must be set to one of the pre-defined values as this is * not hardware specific. Possible values for this field can be * found via git grep "_MIN_KEY_SIZE" include/crypto/ * @max_keysize: Maximum key size supported by the transformation. This is the * largest key length supported by this transformation algorithm. * This must be set to one of the pre-defined values as this is * not hardware specific. Possible values for this field can be * found via git grep "_MAX_KEY_SIZE" include/crypto/ * @ivsize: IV size applicable for transformation. The consumer must provide an * IV of exactly that size to perform the encrypt or decrypt operation. * @chunksize: Equal to the block size except for stream ciphers such as * CTR where it is set to the underlying block size. * @statesize: Size of the internal state for the algorithm. * @base: Definition of a generic crypto algorithm. */ #define SKCIPHER_ALG_COMMON { \ unsigned int min_keysize; \ unsigned int max_keysize; \ unsigned int ivsize; \ unsigned int chunksize; \ unsigned int statesize; \ \ struct crypto_alg base; \ } struct skcipher_alg_common SKCIPHER_ALG_COMMON; /** * struct skcipher_alg - symmetric key cipher definition * @setkey: Set key for the transformation. This function is used to either * program a supplied key into the hardware or store the key in the * transformation context for programming it later. Note that this * function does modify the transformation context. This function can * be called multiple times during the existence of the transformation * object, so one must make sure the key is properly reprogrammed into * the hardware. This function is also responsible for checking the key * length for validity. In case a software fallback was put in place in * the @cra_init call, this function might need to use the fallback if * the algorithm doesn't support all of the key sizes. * @encrypt: Encrypt a scatterlist of blocks. This function is used to encrypt * the supplied scatterlist containing the blocks of data. The crypto * API consumer is responsible for aligning the entries of the * scatterlist properly and making sure the chunks are correctly * sized. In case a software fallback was put in place in the * @cra_init call, this function might need to use the fallback if * the algorithm doesn't support all of the key sizes. In case the * key was stored in transformation context, the key might need to be * re-programmed into the hardware in this function. This function * shall not modify the transformation context, as this function may * be called in parallel with the same transformation object. * @decrypt: Decrypt a single block. This is a reverse counterpart to @encrypt * and the conditions are exactly the same. * @export: Export partial state of the transformation. This function dumps the * entire state of the ongoing transformation into a provided block of * data so it can be @import 'ed back later on. This is useful in case * you want to save partial result of the transformation after * processing certain amount of data and reload this partial result * multiple times later on for multiple re-use. No data processing * happens at this point. * @import: Import partial state of the transformation. This function loads the * entire state of the ongoing transformation from a provided block of * data so the transformation can continue from this point onward. No * data processing happens at this point. * @init: Initialize the cryptographic transformation object. This function * is used to initialize the cryptographic transformation object. * This function is called only once at the instantiation time, right * after the transformation context was allocated. In case the * cryptographic hardware has some special requirements which need to * be handled by software, this function shall check for the precise * requirement of the transformation and put any software fallbacks * in place. * @exit: Deinitialize the cryptographic transformation object. This is a * counterpart to @init, used to remove various changes set in * @init. * @walksize: Equal to the chunk size except in cases where the algorithm is * considerably more efficient if it can operate on multiple chunks * in parallel. Should be a multiple of chunksize. * @co: see struct skcipher_alg_common * @SKCIPHER_ALG_COMMON: see struct skcipher_alg_common * * All fields except @ivsize are mandatory and must be filled. */ struct skcipher_alg { int (*setkey)(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen); int (*encrypt)(struct skcipher_request *req); int (*decrypt)(struct skcipher_request *req); int (*export)(struct skcipher_request *req, void *out); int (*import)(struct skcipher_request *req, const void *in); int (*init)(struct crypto_skcipher *tfm); void (*exit)(struct crypto_skcipher *tfm); unsigned int walksize; union { struct SKCIPHER_ALG_COMMON; struct skcipher_alg_common co; }; }; /** * struct lskcipher_alg - linear symmetric key cipher definition * @setkey: Set key for the transformation. This function is used to either * program a supplied key into the hardware or store the key in the * transformation context for programming it later. Note that this * function does modify the transformation context. This function can * be called multiple times during the existence of the transformation * object, so one must make sure the key is properly reprogrammed into * the hardware. This function is also responsible for checking the key * length for validity. In case a software fallback was put in place in * the @cra_init call, this function might need to use the fallback if * the algorithm doesn't support all of the key sizes. * @encrypt: Encrypt a number of bytes. This function is used to encrypt * the supplied data. This function shall not modify * the transformation context, as this function may be called * in parallel with the same transformation object. Data * may be left over if length is not a multiple of blocks * and there is more to come (final == false). The number of * left-over bytes should be returned in case of success. * The siv field shall be as long as ivsize + statesize with * the IV placed at the front. The state will be used by the * algorithm internally. * @decrypt: Decrypt a number of bytes. This is a reverse counterpart to * @encrypt and the conditions are exactly the same. * @init: Initialize the cryptographic transformation object. This function * is used to initialize the cryptographic transformation object. * This function is called only once at the instantiation time, right * after the transformation context was allocated. * @exit: Deinitialize the cryptographic transformation object. This is a * counterpart to @init, used to remove various changes set in * @init. * @co: see struct skcipher_alg_common */ struct lskcipher_alg { int (*setkey)(struct crypto_lskcipher *tfm, const u8 *key, unsigned int keylen); int (*encrypt)(struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len, u8 *siv, u32 flags); int (*decrypt)(struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len, u8 *siv, u32 flags); int (*init)(struct crypto_lskcipher *tfm); void (*exit)(struct crypto_lskcipher *tfm); struct skcipher_alg_common co; }; #define MAX_SYNC_SKCIPHER_REQSIZE 384 /* * This performs a type-check against the "_tfm" argument to make sure * all users have the correct skcipher tfm for doing on-stack requests. */ #define SYNC_SKCIPHER_REQUEST_ON_STACK(name, _tfm) \ char __##name##_desc[sizeof(struct skcipher_request) + \ MAX_SYNC_SKCIPHER_REQSIZE \ ] CRYPTO_MINALIGN_ATTR; \ struct skcipher_request *name = \ (((struct skcipher_request *)__##name##_desc)->base.tfm = \ crypto_sync_skcipher_tfm((_tfm)), \ (void *)__##name##_desc) /** * DOC: Symmetric Key Cipher API * * Symmetric key cipher API is used with the ciphers of type * CRYPTO_ALG_TYPE_SKCIPHER (listed as type "skcipher" in /proc/crypto). * * Asynchronous cipher operations imply that the function invocation for a * cipher request returns immediately before the completion of the operation. * The cipher request is scheduled as a separate kernel thread and therefore * load-balanced on the different CPUs via the process scheduler. To allow * the kernel crypto API to inform the caller about the completion of a cipher * request, the caller must provide a callback function. That function is * invoked with the cipher handle when the request completes. * * To support the asynchronous operation, additional information than just the * cipher handle must be supplied to the kernel crypto API. That additional * information is given by filling in the skcipher_request data structure. * * For the symmetric key cipher API, the state is maintained with the tfm * cipher handle. A single tfm can be used across multiple calls and in * parallel. For asynchronous block cipher calls, context data supplied and * only used by the caller can be referenced the request data structure in * addition to the IV used for the cipher request. The maintenance of such * state information would be important for a crypto driver implementer to * have, because when calling the callback function upon completion of the * cipher operation, that callback function may need some information about * which operation just finished if it invoked multiple in parallel. This * state information is unused by the kernel crypto API. */ static inline struct crypto_skcipher *__crypto_skcipher_cast( struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_skcipher, base); } /** * crypto_alloc_skcipher() - allocate symmetric key cipher handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * skcipher cipher * @type: specifies the type of the cipher * @mask: specifies the mask for the cipher * * Allocate a cipher handle for an skcipher. The returned struct * crypto_skcipher is the cipher handle that is required for any subsequent * API invocation for that skcipher. * * Return: allocated cipher handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_skcipher *crypto_alloc_skcipher(const char *alg_name, u32 type, u32 mask); struct crypto_sync_skcipher *crypto_alloc_sync_skcipher(const char *alg_name, u32 type, u32 mask); /** * crypto_alloc_lskcipher() - allocate linear symmetric key cipher handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * lskcipher * @type: specifies the type of the cipher * @mask: specifies the mask for the cipher * * Allocate a cipher handle for an lskcipher. The returned struct * crypto_lskcipher is the cipher handle that is required for any subsequent * API invocation for that lskcipher. * * Return: allocated cipher handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_lskcipher *crypto_alloc_lskcipher(const char *alg_name, u32 type, u32 mask); static inline struct crypto_tfm *crypto_skcipher_tfm( struct crypto_skcipher *tfm) { return &tfm->base; } static inline struct crypto_tfm *crypto_lskcipher_tfm( struct crypto_lskcipher *tfm) { return &tfm->base; } static inline struct crypto_tfm *crypto_sync_skcipher_tfm( struct crypto_sync_skcipher *tfm) { return crypto_skcipher_tfm(&tfm->base); } /** * crypto_free_skcipher() - zeroize and free cipher handle * @tfm: cipher handle to be freed * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_skcipher(struct crypto_skcipher *tfm) { crypto_destroy_tfm(tfm, crypto_skcipher_tfm(tfm)); } static inline void crypto_free_sync_skcipher(struct crypto_sync_skcipher *tfm) { crypto_free_skcipher(&tfm->base); } /** * crypto_free_lskcipher() - zeroize and free cipher handle * @tfm: cipher handle to be freed * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_lskcipher(struct crypto_lskcipher *tfm) { crypto_destroy_tfm(tfm, crypto_lskcipher_tfm(tfm)); } /** * crypto_has_skcipher() - Search for the availability of an skcipher. * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * skcipher * @type: specifies the type of the skcipher * @mask: specifies the mask for the skcipher * * Return: true when the skcipher is known to the kernel crypto API; false * otherwise */ int crypto_has_skcipher(const char *alg_name, u32 type, u32 mask); static inline const char *crypto_skcipher_driver_name( struct crypto_skcipher *tfm) { return crypto_tfm_alg_driver_name(crypto_skcipher_tfm(tfm)); } static inline const char *crypto_lskcipher_driver_name( struct crypto_lskcipher *tfm) { return crypto_tfm_alg_driver_name(crypto_lskcipher_tfm(tfm)); } static inline struct skcipher_alg_common *crypto_skcipher_alg_common( struct crypto_skcipher *tfm) { return container_of(crypto_skcipher_tfm(tfm)->__crt_alg, struct skcipher_alg_common, base); } static inline struct skcipher_alg *crypto_skcipher_alg( struct crypto_skcipher *tfm) { return container_of(crypto_skcipher_tfm(tfm)->__crt_alg, struct skcipher_alg, base); } static inline struct lskcipher_alg *crypto_lskcipher_alg( struct crypto_lskcipher *tfm) { return container_of(crypto_lskcipher_tfm(tfm)->__crt_alg, struct lskcipher_alg, co.base); } /** * crypto_skcipher_ivsize() - obtain IV size * @tfm: cipher handle * * The size of the IV for the skcipher referenced by the cipher handle is * returned. This IV size may be zero if the cipher does not need an IV. * * Return: IV size in bytes */ static inline unsigned int crypto_skcipher_ivsize(struct crypto_skcipher *tfm) { return crypto_skcipher_alg_common(tfm)->ivsize; } static inline unsigned int crypto_sync_skcipher_ivsize( struct crypto_sync_skcipher *tfm) { return crypto_skcipher_ivsize(&tfm->base); } /** * crypto_lskcipher_ivsize() - obtain IV size * @tfm: cipher handle * * The size of the IV for the lskcipher referenced by the cipher handle is * returned. This IV size may be zero if the cipher does not need an IV. * * Return: IV size in bytes */ static inline unsigned int crypto_lskcipher_ivsize( struct crypto_lskcipher *tfm) { return crypto_lskcipher_alg(tfm)->co.ivsize; } /** * crypto_skcipher_blocksize() - obtain block size of cipher * @tfm: cipher handle * * The block size for the skcipher referenced with the cipher handle is * returned. The caller may use that information to allocate appropriate * memory for the data returned by the encryption or decryption operation * * Return: block size of cipher */ static inline unsigned int crypto_skcipher_blocksize( struct crypto_skcipher *tfm) { return crypto_tfm_alg_blocksize(crypto_skcipher_tfm(tfm)); } /** * crypto_lskcipher_blocksize() - obtain block size of cipher * @tfm: cipher handle * * The block size for the lskcipher referenced with the cipher handle is * returned. The caller may use that information to allocate appropriate * memory for the data returned by the encryption or decryption operation * * Return: block size of cipher */ static inline unsigned int crypto_lskcipher_blocksize( struct crypto_lskcipher *tfm) { return crypto_tfm_alg_blocksize(crypto_lskcipher_tfm(tfm)); } /** * crypto_skcipher_chunksize() - obtain chunk size * @tfm: cipher handle * * The block size is set to one for ciphers such as CTR. However, * you still need to provide incremental updates in multiples of * the underlying block size as the IV does not have sub-block * granularity. This is known in this API as the chunk size. * * Return: chunk size in bytes */ static inline unsigned int crypto_skcipher_chunksize( struct crypto_skcipher *tfm) { return crypto_skcipher_alg_common(tfm)->chunksize; } /** * crypto_lskcipher_chunksize() - obtain chunk size * @tfm: cipher handle * * The block size is set to one for ciphers such as CTR. However, * you still need to provide incremental updates in multiples of * the underlying block size as the IV does not have sub-block * granularity. This is known in this API as the chunk size. * * Return: chunk size in bytes */ static inline unsigned int crypto_lskcipher_chunksize( struct crypto_lskcipher *tfm) { return crypto_lskcipher_alg(tfm)->co.chunksize; } /** * crypto_skcipher_statesize() - obtain state size * @tfm: cipher handle * * Some algorithms cannot be chained with the IV alone. They carry * internal state which must be replicated if data is to be processed * incrementally. The size of that state can be obtained with this * function. * * Return: state size in bytes */ static inline unsigned int crypto_skcipher_statesize( struct crypto_skcipher *tfm) { return crypto_skcipher_alg_common(tfm)->statesize; } /** * crypto_lskcipher_statesize() - obtain state size * @tfm: cipher handle * * Some algorithms cannot be chained with the IV alone. They carry * internal state which must be replicated if data is to be processed * incrementally. The size of that state can be obtained with this * function. * * Return: state size in bytes */ static inline unsigned int crypto_lskcipher_statesize( struct crypto_lskcipher *tfm) { return crypto_lskcipher_alg(tfm)->co.statesize; } static inline unsigned int crypto_sync_skcipher_blocksize( struct crypto_sync_skcipher *tfm) { return crypto_skcipher_blocksize(&tfm->base); } static inline unsigned int crypto_skcipher_alignmask( struct crypto_skcipher *tfm) { return crypto_tfm_alg_alignmask(crypto_skcipher_tfm(tfm)); } static inline unsigned int crypto_lskcipher_alignmask( struct crypto_lskcipher *tfm) { return crypto_tfm_alg_alignmask(crypto_lskcipher_tfm(tfm)); } static inline u32 crypto_skcipher_get_flags(struct crypto_skcipher *tfm) { return crypto_tfm_get_flags(crypto_skcipher_tfm(tfm)); } static inline void crypto_skcipher_set_flags(struct crypto_skcipher *tfm, u32 flags) { crypto_tfm_set_flags(crypto_skcipher_tfm(tfm), flags); } static inline void crypto_skcipher_clear_flags(struct crypto_skcipher *tfm, u32 flags) { crypto_tfm_clear_flags(crypto_skcipher_tfm(tfm), flags); } static inline u32 crypto_sync_skcipher_get_flags( struct crypto_sync_skcipher *tfm) { return crypto_skcipher_get_flags(&tfm->base); } static inline void crypto_sync_skcipher_set_flags( struct crypto_sync_skcipher *tfm, u32 flags) { crypto_skcipher_set_flags(&tfm->base, flags); } static inline void crypto_sync_skcipher_clear_flags( struct crypto_sync_skcipher *tfm, u32 flags) { crypto_skcipher_clear_flags(&tfm->base, flags); } static inline u32 crypto_lskcipher_get_flags(struct crypto_lskcipher *tfm) { return crypto_tfm_get_flags(crypto_lskcipher_tfm(tfm)); } static inline void crypto_lskcipher_set_flags(struct crypto_lskcipher *tfm, u32 flags) { crypto_tfm_set_flags(crypto_lskcipher_tfm(tfm), flags); } static inline void crypto_lskcipher_clear_flags(struct crypto_lskcipher *tfm, u32 flags) { crypto_tfm_clear_flags(crypto_lskcipher_tfm(tfm), flags); } /** * crypto_skcipher_setkey() - set key for cipher * @tfm: cipher handle * @key: buffer holding the key * @keylen: length of the key in bytes * * The caller provided key is set for the skcipher referenced by the cipher * handle. * * Note, the key length determines the cipher type. Many block ciphers implement * different cipher modes depending on the key size, such as AES-128 vs AES-192 * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128 * is performed. * * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ int crypto_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen); static inline int crypto_sync_skcipher_setkey(struct crypto_sync_skcipher *tfm, const u8 *key, unsigned int keylen) { return crypto_skcipher_setkey(&tfm->base, key, keylen); } /** * crypto_lskcipher_setkey() - set key for cipher * @tfm: cipher handle * @key: buffer holding the key * @keylen: length of the key in bytes * * The caller provided key is set for the lskcipher referenced by the cipher * handle. * * Note, the key length determines the cipher type. Many block ciphers implement * different cipher modes depending on the key size, such as AES-128 vs AES-192 * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128 * is performed. * * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ int crypto_lskcipher_setkey(struct crypto_lskcipher *tfm, const u8 *key, unsigned int keylen); static inline unsigned int crypto_skcipher_min_keysize( struct crypto_skcipher *tfm) { return crypto_skcipher_alg_common(tfm)->min_keysize; } static inline unsigned int crypto_skcipher_max_keysize( struct crypto_skcipher *tfm) { return crypto_skcipher_alg_common(tfm)->max_keysize; } static inline unsigned int crypto_lskcipher_min_keysize( struct crypto_lskcipher *tfm) { return crypto_lskcipher_alg(tfm)->co.min_keysize; } static inline unsigned int crypto_lskcipher_max_keysize( struct crypto_lskcipher *tfm) { return crypto_lskcipher_alg(tfm)->co.max_keysize; } /** * crypto_skcipher_reqtfm() - obtain cipher handle from request * @req: skcipher_request out of which the cipher handle is to be obtained * * Return the crypto_skcipher handle when furnishing an skcipher_request * data structure. * * Return: crypto_skcipher handle */ static inline struct crypto_skcipher *crypto_skcipher_reqtfm( struct skcipher_request *req) { return __crypto_skcipher_cast(req->base.tfm); } static inline struct crypto_sync_skcipher *crypto_sync_skcipher_reqtfm( struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); return container_of(tfm, struct crypto_sync_skcipher, base); } /** * crypto_skcipher_encrypt() - encrypt plaintext * @req: reference to the skcipher_request handle that holds all information * needed to perform the cipher operation * * Encrypt plaintext data using the skcipher_request handle. That data * structure and how it is filled with data is discussed with the * skcipher_request_* functions. * * Return: 0 if the cipher operation was successful; < 0 if an error occurred */ int crypto_skcipher_encrypt(struct skcipher_request *req); /** * crypto_skcipher_decrypt() - decrypt ciphertext * @req: reference to the skcipher_request handle that holds all information * needed to perform the cipher operation * * Decrypt ciphertext data using the skcipher_request handle. That data * structure and how it is filled with data is discussed with the * skcipher_request_* functions. * * Return: 0 if the cipher operation was successful; < 0 if an error occurred */ int crypto_skcipher_decrypt(struct skcipher_request *req); /** * crypto_skcipher_export() - export partial state * @req: reference to the skcipher_request handle that holds all information * needed to perform the operation * @out: output buffer of sufficient size that can hold the state * * Export partial state of the transformation. This function dumps the * entire state of the ongoing transformation into a provided block of * data so it can be @import 'ed back later on. This is useful in case * you want to save partial result of the transformation after * processing certain amount of data and reload this partial result * multiple times later on for multiple re-use. No data processing * happens at this point. * * Return: 0 if the cipher operation was successful; < 0 if an error occurred */ int crypto_skcipher_export(struct skcipher_request *req, void *out); /** * crypto_skcipher_import() - import partial state * @req: reference to the skcipher_request handle that holds all information * needed to perform the operation * @in: buffer holding the state * * Import partial state of the transformation. This function loads the * entire state of the ongoing transformation from a provided block of * data so the transformation can continue from this point onward. No * data processing happens at this point. * * Return: 0 if the cipher operation was successful; < 0 if an error occurred */ int crypto_skcipher_import(struct skcipher_request *req, const void *in); /** * crypto_lskcipher_encrypt() - encrypt plaintext * @tfm: lskcipher handle * @src: source buffer * @dst: destination buffer * @len: number of bytes to process * @siv: IV + state for the cipher operation. The length of the IV must * comply with the IV size defined by crypto_lskcipher_ivsize. The * IV is then followed with a buffer with the length as specified by * crypto_lskcipher_statesize. * Encrypt plaintext data using the lskcipher handle. * * Return: >=0 if the cipher operation was successful, if positive * then this many bytes have been left unprocessed; * < 0 if an error occurred */ int crypto_lskcipher_encrypt(struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len, u8 *siv); /** * crypto_lskcipher_decrypt() - decrypt ciphertext * @tfm: lskcipher handle * @src: source buffer * @dst: destination buffer * @len: number of bytes to process * @siv: IV + state for the cipher operation. The length of the IV must * comply with the IV size defined by crypto_lskcipher_ivsize. The * IV is then followed with a buffer with the length as specified by * crypto_lskcipher_statesize. * * Decrypt ciphertext data using the lskcipher handle. * * Return: >=0 if the cipher operation was successful, if positive * then this many bytes have been left unprocessed; * < 0 if an error occurred */ int crypto_lskcipher_decrypt(struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len, u8 *siv); /** * DOC: Symmetric Key Cipher Request Handle * * The skcipher_request data structure contains all pointers to data * required for the symmetric key cipher operation. This includes the cipher * handle (which can be used by multiple skcipher_request instances), pointer * to plaintext and ciphertext, asynchronous callback function, etc. It acts * as a handle to the skcipher_request_* API calls in a similar way as * skcipher handle to the crypto_skcipher_* API calls. */ /** * crypto_skcipher_reqsize() - obtain size of the request data structure * @tfm: cipher handle * * Return: number of bytes */ static inline unsigned int crypto_skcipher_reqsize(struct crypto_skcipher *tfm) { return tfm->reqsize; } /** * skcipher_request_set_tfm() - update cipher handle reference in request * @req: request handle to be modified * @tfm: cipher handle that shall be added to the request handle * * Allow the caller to replace the existing skcipher handle in the request * data structure with a different one. */ static inline void skcipher_request_set_tfm(struct skcipher_request *req, struct crypto_skcipher *tfm) { req->base.tfm = crypto_skcipher_tfm(tfm); } static inline void skcipher_request_set_sync_tfm(struct skcipher_request *req, struct crypto_sync_skcipher *tfm) { skcipher_request_set_tfm(req, &tfm->base); } static inline struct skcipher_request *skcipher_request_cast( struct crypto_async_request *req) { return container_of(req, struct skcipher_request, base); } /** * skcipher_request_alloc() - allocate request data structure * @tfm: cipher handle to be registered with the request * @gfp: memory allocation flag that is handed to kmalloc by the API call. * * Allocate the request data structure that must be used with the skcipher * encrypt and decrypt API calls. During the allocation, the provided skcipher * handle is registered in the request data structure. * * Return: allocated request handle in case of success, or NULL if out of memory */ static inline struct skcipher_request *skcipher_request_alloc_noprof( struct crypto_skcipher *tfm, gfp_t gfp) { struct skcipher_request *req; req = kmalloc_noprof(sizeof(struct skcipher_request) + crypto_skcipher_reqsize(tfm), gfp); if (likely(req)) skcipher_request_set_tfm(req, tfm); return req; } #define skcipher_request_alloc(...) alloc_hooks(skcipher_request_alloc_noprof(__VA_ARGS__)) /** * skcipher_request_free() - zeroize and free request data structure * @req: request data structure cipher handle to be freed */ static inline void skcipher_request_free(struct skcipher_request *req) { kfree_sensitive(req); } static inline void skcipher_request_zero(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); memzero_explicit(req, sizeof(*req) + crypto_skcipher_reqsize(tfm)); } /** * skcipher_request_set_callback() - set asynchronous callback function * @req: request handle * @flags: specify zero or an ORing of the flags * CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and * increase the wait queue beyond the initial maximum size; * CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep * @compl: callback function pointer to be registered with the request handle * @data: The data pointer refers to memory that is not used by the kernel * crypto API, but provided to the callback function for it to use. Here, * the caller can provide a reference to memory the callback function can * operate on. As the callback function is invoked asynchronously to the * related functionality, it may need to access data structures of the * related functionality which can be referenced using this pointer. The * callback function can access the memory via the "data" field in the * crypto_async_request data structure provided to the callback function. * * This function allows setting the callback function that is triggered once the * cipher operation completes. * * The callback function is registered with the skcipher_request handle and * must comply with the following template:: * * void callback_function(struct crypto_async_request *req, int error) */ static inline void skcipher_request_set_callback(struct skcipher_request *req, u32 flags, crypto_completion_t compl, void *data) { req->base.complete = compl; req->base.data = data; req->base.flags = flags; } /** * skcipher_request_set_crypt() - set data buffers * @req: request handle * @src: source scatter / gather list * @dst: destination scatter / gather list * @cryptlen: number of bytes to process from @src * @iv: IV for the cipher operation which must comply with the IV size defined * by crypto_skcipher_ivsize * * This function allows setting of the source data and destination data * scatter / gather lists. * * For encryption, the source is treated as the plaintext and the * destination is the ciphertext. For a decryption operation, the use is * reversed - the source is the ciphertext and the destination is the plaintext. */ static inline void skcipher_request_set_crypt( struct skcipher_request *req, struct scatterlist *src, struct scatterlist *dst, unsigned int cryptlen, void *iv) { req->src = src; req->dst = dst; req->cryptlen = cryptlen; req->iv = iv; } #endif /* _CRYPTO_SKCIPHER_H */ |
| 1228 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MINMAX_H #define _LINUX_MINMAX_H #include <linux/build_bug.h> #include <linux/compiler.h> #include <linux/const.h> #include <linux/types.h> /* * min()/max()/clamp() macros must accomplish several things: * * - Avoid multiple evaluations of the arguments (so side-effects like * "x++" happen only once) when non-constant. * - Perform signed v unsigned type-checking (to generate compile * errors instead of nasty runtime surprises). * - Unsigned char/short are always promoted to signed int and can be * compared against signed or unsigned arguments. * - Unsigned arguments can be compared against non-negative signed constants. * - Comparison of a signed argument against an unsigned constant fails * even if the constant is below __INT_MAX__ and could be cast to int. */ #define __typecheck(x, y) \ (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) /* * __sign_use for integer expressions: * bit #0 set if ok for unsigned comparisons * bit #1 set if ok for signed comparisons * * In particular, statically non-negative signed integer expressions * are ok for both. * * NOTE! Unsigned types smaller than 'int' are implicitly converted to 'int' * in expressions, and are accepted for signed conversions for now. * This is debatable. * * Note that 'x' is the original expression, and 'ux' is the unique variable * that contains the value. * * We use 'ux' for pure type checking, and 'x' for when we need to look at the * value (but without evaluating it for side effects! * Careful to only ever evaluate it with sizeof() or __builtin_constant_p() etc). * * Pointers end up being checked by the normal C type rules at the actual * comparison, and these expressions only need to be careful to not cause * warnings for pointer use. */ #define __sign_use(ux) (is_signed_type(typeof(ux)) ? \ (2 + __is_nonneg(ux)) : (1 + 2 * (sizeof(ux) < 4))) /* * Check whether a signed value is always non-negative. * * A cast is needed to avoid any warnings from values that aren't signed * integer types (in which case the result doesn't matter). * * On 64-bit any integer or pointer type can safely be cast to 'long long'. * But on 32-bit we need to avoid warnings about casting pointers to integers * of different sizes without truncating 64-bit values so 'long' or 'long long' * must be used depending on the size of the value. * * This does not work for 128-bit signed integers since the cast would truncate * them, but we do not use s128 types in the kernel (we do use 'u128', * but they are handled by the !is_signed_type() case). */ #if __SIZEOF_POINTER__ == __SIZEOF_LONG_LONG__ #define __is_nonneg(ux) statically_true((long long)(ux) >= 0) #else #define __is_nonneg(ux) statically_true( \ (typeof(__builtin_choose_expr(sizeof(ux) > 4, 1LL, 1L)))(ux) >= 0) #endif #define __types_ok(ux, uy) \ (__sign_use(ux) & __sign_use(uy)) #define __types_ok3(ux, uy, uz) \ (__sign_use(ux) & __sign_use(uy) & __sign_use(uz)) #define __cmp_op_min < #define __cmp_op_max > #define __cmp(op, x, y) ((x) __cmp_op_##op (y) ? (x) : (y)) #define __cmp_once_unique(op, type, x, y, ux, uy) \ ({ type ux = (x); type uy = (y); __cmp(op, ux, uy); }) #define __cmp_once(op, type, x, y) \ __cmp_once_unique(op, type, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) #define __careful_cmp_once(op, x, y, ux, uy) ({ \ auto ux = (x); auto uy = (y); \ BUILD_BUG_ON_MSG(!__types_ok(ux, uy), \ #op"("#x", "#y") signedness error"); \ __cmp(op, ux, uy); }) #define __careful_cmp(op, x, y) \ __careful_cmp_once(op, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) /** * min - return minimum of two values of the same or compatible types * @x: first value * @y: second value */ #define min(x, y) __careful_cmp(min, x, y) /** * max - return maximum of two values of the same or compatible types * @x: first value * @y: second value */ #define max(x, y) __careful_cmp(max, x, y) /** * umin - return minimum of two non-negative values * Signed types are zero extended to match a larger unsigned type. * @x: first value * @y: second value */ #define umin(x, y) \ __careful_cmp(min, (x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull) /** * umax - return maximum of two non-negative values * @x: first value * @y: second value */ #define umax(x, y) \ __careful_cmp(max, (x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull) #define __careful_op3(op, x, y, z, ux, uy, uz) ({ \ auto ux = (x); auto uy = (y); auto uz = (z); \ BUILD_BUG_ON_MSG(!__types_ok3(ux, uy, uz), \ #op"3("#x", "#y", "#z") signedness error"); \ __cmp(op, ux, __cmp(op, uy, uz)); }) /** * min3 - return minimum of three values * @x: first value * @y: second value * @z: third value */ #define min3(x, y, z) \ __careful_op3(min, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) /** * max3 - return maximum of three values * @x: first value * @y: second value * @z: third value */ #define max3(x, y, z) \ __careful_op3(max, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) /** * min_t - return minimum of two values, using the specified type * @type: data type to use * @x: first value * @y: second value */ #define min_t(type, x, y) __cmp_once(min, type, x, y) /** * max_t - return maximum of two values, using the specified type * @type: data type to use * @x: first value * @y: second value */ #define max_t(type, x, y) __cmp_once(max, type, x, y) /** * min_not_zero - return the minimum that is _not_ zero, unless both are zero * @x: value1 * @y: value2 */ #define min_not_zero(x, y) ({ \ typeof(x) __x = (x); \ typeof(y) __y = (y); \ __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) #define __clamp(val, lo, hi) \ ((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val))) #define __clamp_once(type, val, lo, hi, uval, ulo, uhi) ({ \ type uval = (val); \ type ulo = (lo); \ type uhi = (hi); \ BUILD_BUG_ON_MSG(statically_true(ulo > uhi), \ "clamp() low limit " #lo " greater than high limit " #hi); \ BUILD_BUG_ON_MSG(!__types_ok3(uval, ulo, uhi), \ "clamp("#val", "#lo", "#hi") signedness error"); \ __clamp(uval, ulo, uhi); }) #define __careful_clamp(type, val, lo, hi) \ __clamp_once(type, val, lo, hi, __UNIQUE_ID(v_), __UNIQUE_ID(l_), __UNIQUE_ID(h_)) /** * clamp - return a value clamped to a given range with typechecking * @val: current value * @lo: lowest allowable value * @hi: highest allowable value * * This macro checks @val/@lo/@hi to make sure they have compatible * signedness. */ #define clamp(val, lo, hi) __careful_clamp(auto, val, lo, hi) /** * clamp_t - return a value clamped to a given range using a given type * @type: the type of variable to use * @val: current value * @lo: minimum allowable value * @hi: maximum allowable value * * This macro does no typechecking and uses temporary variables of type * @type to make all the comparisons. */ #define clamp_t(type, val, lo, hi) __careful_clamp(type, val, lo, hi) /** * clamp_val - return a value clamped to a given range using val's type * @val: current value * @lo: minimum allowable value * @hi: maximum allowable value * * This macro does no typechecking and uses temporary variables of whatever * type the input argument @val is. This is useful when @val is an unsigned * type and @lo and @hi are literals that will otherwise be assigned a signed * integer type. */ #define clamp_val(val, lo, hi) __careful_clamp(typeof(val), val, lo, hi) /* * Do not check the array parameter using __must_be_array(). * In the following legit use-case where the "array" passed is a simple pointer, * __must_be_array() will return a failure. * --- 8< --- * int *buff * ... * min = min_array(buff, nb_items); * --- 8< --- * * The first typeof(&(array)[0]) is needed in order to support arrays of both * 'int *buff' and 'int buff[N]' types. * * The array can be an array of const items. * typeof() keeps the const qualifier. Use __unqual_scalar_typeof() in order * to discard the const qualifier for the __element variable. */ #define __minmax_array(op, array, len) ({ \ typeof(&(array)[0]) __array = (array); \ typeof(len) __len = (len); \ __unqual_scalar_typeof(__array[0]) __element = __array[--__len];\ while (__len--) \ __element = op(__element, __array[__len]); \ __element; }) /** * min_array - return minimum of values present in an array * @array: array * @len: array length * * Note that @len must not be zero (empty array). */ #define min_array(array, len) __minmax_array(min, array, len) /** * max_array - return maximum of values present in an array * @array: array * @len: array length * * Note that @len must not be zero (empty array). */ #define max_array(array, len) __minmax_array(max, array, len) static inline bool in_range64(u64 val, u64 start, u64 len) { return (val - start) < len; } static inline bool in_range32(u32 val, u32 start, u32 len) { return (val - start) < len; } /** * in_range - Determine if a value lies within a range. * @val: Value to test. * @start: First value in range. * @len: Number of values in range. * * This is more efficient than "if (start <= val && val < (start + len))". * It also gives a different answer if @start + @len overflows the size of * the type by a sufficient amount to encompass @val. Decide for yourself * which behaviour you want, or prove that start + len never overflow. * Do not blindly replace one form with the other. */ #define in_range(val, start, len) \ ((sizeof(start) | sizeof(len) | sizeof(val)) <= sizeof(u32) ? \ in_range32(val, start, len) : in_range64(val, start, len)) /** * swap - swap values of @a and @b * @a: first value * @b: second value */ #define swap(a, b) \ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) /* * Use these carefully: no type checking, and uses the arguments * multiple times. Use for obvious constants only. */ #define MIN(a, b) __cmp(min, a, b) #define MAX(a, b) __cmp(max, a, b) #define MIN_T(type, a, b) __cmp(min, (type)(a), (type)(b)) #define MAX_T(type, a, b) __cmp(max, (type)(a), (type)(b)) #endif /* _LINUX_MINMAX_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef ARCH_X86_CPU_H #define ARCH_X86_CPU_H #include <asm/cpu.h> #include <asm/topology.h> #include "topology.h" /* attempt to consolidate cpu attributes */ struct cpu_dev { const char *c_vendor; /* some have two possibilities for cpuid string */ const char *c_ident[2]; void (*c_early_init)(struct cpuinfo_x86 *); void (*c_bsp_init)(struct cpuinfo_x86 *); void (*c_init)(struct cpuinfo_x86 *); void (*c_identify)(struct cpuinfo_x86 *); void (*c_detect_tlb)(struct cpuinfo_x86 *); int c_x86_vendor; #ifdef CONFIG_X86_32 /* Optional vendor specific routine to obtain the cache size. */ unsigned int (*legacy_cache_size)(struct cpuinfo_x86 *, unsigned int); /* Family/stepping-based lookup table for model names. */ struct legacy_cpu_model_info { int family; const char *model_names[16]; } legacy_models[5]; #endif }; #define cpu_dev_register(cpu_devX) \ static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \ __section(".x86_cpu_dev.init") = \ &cpu_devX; extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; #ifdef CONFIG_CPU_SUP_INTEL extern void __init tsx_init(void); void tsx_ap_init(void); void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c); #else static inline void tsx_init(void) { } static inline void tsx_ap_init(void) { } static inline void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c) { } #endif /* CONFIG_CPU_SUP_INTEL */ extern void init_spectral_chicken(struct cpuinfo_x86 *c); extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void get_cpu_address_sizes(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c); extern void init_intel_cacheinfo(struct cpuinfo_x86 *c); extern void init_amd_cacheinfo(struct cpuinfo_x86 *c); extern void init_hygon_cacheinfo(struct cpuinfo_x86 *c); extern void check_null_seg_clears_base(struct cpuinfo_x86 *c); void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id); void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c); #if defined(CONFIG_AMD_NB) && defined(CONFIG_SYSFS) struct amd_northbridge *amd_init_l3_cache(int index); #else static inline struct amd_northbridge *amd_init_l3_cache(int index) { return NULL; } #endif void cpu_select_mitigations(void); extern void x86_spec_ctrl_setup_ap(void); extern void update_srbds_msr(void); extern void update_gds_msr(void); extern enum spectre_v2_mitigation spectre_v2_enabled; static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) { return mode == SPECTRE_V2_EIBRS || mode == SPECTRE_V2_EIBRS_RETPOLINE || mode == SPECTRE_V2_EIBRS_LFENCE; } #endif /* ARCH_X86_CPU_H */ |
| 39 39 39 39 39 38 39 38 39 39 39 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2003-2005 Devicescape Software, Inc. * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2015 Intel Deutschland GmbH * Copyright (C) 2021-2023 Intel Corporation */ #include <linux/kobject.h> #include <linux/slab.h> #include "ieee80211_i.h" #include "key.h" #include "debugfs.h" #include "debugfs_key.h" #define KEY_READ(name, prop, format_string) \ static ssize_t key_##name##_read(struct file *file, \ char __user *userbuf, \ size_t count, loff_t *ppos) \ { \ struct ieee80211_key *key = file->private_data; \ return mac80211_format_buffer(userbuf, count, ppos, \ format_string, key->prop); \ } #define KEY_READ_X(name) KEY_READ(name, name, "0x%x\n") #define KEY_OPS(name) \ static const struct debugfs_short_fops key_ ##name## _ops = { \ .read = key_##name##_read, \ .llseek = generic_file_llseek, \ } #define KEY_OPS_W(name) \ static const struct debugfs_short_fops key_ ##name## _ops = { \ .read = key_##name##_read, \ .write = key_##name##_write, \ .llseek = generic_file_llseek, \ } #define KEY_FILE(name, format) \ KEY_READ_##format(name) \ KEY_OPS(name) #define KEY_CONF_READ(name, format_string) \ KEY_READ(conf_##name, conf.name, format_string) #define KEY_CONF_READ_D(name) KEY_CONF_READ(name, "%d\n") #define KEY_CONF_OPS(name) \ static const struct debugfs_short_fops key_ ##name## _ops = { \ .read = key_conf_##name##_read, \ .llseek = generic_file_llseek, \ } #define KEY_CONF_FILE(name, format) \ KEY_CONF_READ_##format(name) \ KEY_CONF_OPS(name) KEY_CONF_FILE(keylen, D); KEY_CONF_FILE(keyidx, D); KEY_CONF_FILE(hw_key_idx, D); KEY_FILE(flags, X); KEY_READ(ifindex, sdata->name, "%s\n"); KEY_OPS(ifindex); static ssize_t key_algorithm_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { char buf[15]; struct ieee80211_key *key = file->private_data; u32 c = key->conf.cipher; sprintf(buf, "%.2x-%.2x-%.2x:%d\n", c >> 24, (c >> 16) & 0xff, (c >> 8) & 0xff, c & 0xff); return simple_read_from_buffer(userbuf, count, ppos, buf, strlen(buf)); } KEY_OPS(algorithm); static ssize_t key_tx_spec_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; u64 pn; int ret; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: return -EINVAL; case WLAN_CIPHER_SUITE_TKIP: /* not supported yet */ return -EOPNOTSUPP; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: ret = kstrtou64_from_user(userbuf, count, 16, &pn); if (ret) return ret; /* PN is a 48-bit counter */ if (pn >= (1ULL << 48)) return -ERANGE; atomic64_set(&key->conf.tx_pn, pn); return count; default: return 0; } } static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { u64 pn; char buf[20]; int len; struct ieee80211_key *key = file->private_data; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: len = scnprintf(buf, sizeof(buf), "\n"); break; case WLAN_CIPHER_SUITE_TKIP: pn = atomic64_read(&key->conf.tx_pn); len = scnprintf(buf, sizeof(buf), "%08x %04x\n", TKIP_PN_TO_IV32(pn), TKIP_PN_TO_IV16(pn)); break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: pn = atomic64_read(&key->conf.tx_pn); len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n", (u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24), (u8)(pn >> 16), (u8)(pn >> 8), (u8)pn); break; default: return 0; } return simple_read_from_buffer(userbuf, count, ppos, buf, len); } KEY_OPS_W(tx_spec); static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; char buf[14*IEEE80211_NUM_TIDS+1], *p = buf; int i, len; const u8 *rpn; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: len = scnprintf(buf, sizeof(buf), "\n"); break; case WLAN_CIPHER_SUITE_TKIP: for (i = 0; i < IEEE80211_NUM_TIDS; i++) p += scnprintf(p, sizeof(buf)+buf-p, "%08x %04x\n", key->u.tkip.rx[i].iv32, key->u.tkip.rx[i].iv16); len = p - buf; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) { rpn = key->u.ccmp.rx_pn[i]; p += scnprintf(p, sizeof(buf)+buf-p, "%02x%02x%02x%02x%02x%02x\n", rpn[0], rpn[1], rpn[2], rpn[3], rpn[4], rpn[5]); } len = p - buf; break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: rpn = key->u.aes_cmac.rx_pn; p += scnprintf(p, sizeof(buf)+buf-p, "%02x%02x%02x%02x%02x%02x\n", rpn[0], rpn[1], rpn[2], rpn[3], rpn[4], rpn[5]); len = p - buf; break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: rpn = key->u.aes_gmac.rx_pn; p += scnprintf(p, sizeof(buf)+buf-p, "%02x%02x%02x%02x%02x%02x\n", rpn[0], rpn[1], rpn[2], rpn[3], rpn[4], rpn[5]); len = p - buf; break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) { rpn = key->u.gcmp.rx_pn[i]; p += scnprintf(p, sizeof(buf)+buf-p, "%02x%02x%02x%02x%02x%02x\n", rpn[0], rpn[1], rpn[2], rpn[3], rpn[4], rpn[5]); } len = p - buf; break; default: return 0; } return simple_read_from_buffer(userbuf, count, ppos, buf, len); } KEY_OPS(rx_spec); static ssize_t key_replays_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; char buf[20]; int len; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.ccmp.replays); break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.aes_cmac.replays); break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.aes_gmac.replays); break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.gcmp.replays); break; default: return 0; } return simple_read_from_buffer(userbuf, count, ppos, buf, len); } KEY_OPS(replays); static ssize_t key_icverrors_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; char buf[20]; int len; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.aes_cmac.icverrors); break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.aes_gmac.icverrors); break; default: return 0; } return simple_read_from_buffer(userbuf, count, ppos, buf, len); } KEY_OPS(icverrors); static ssize_t key_mic_failures_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; char buf[20]; int len; if (key->conf.cipher != WLAN_CIPHER_SUITE_TKIP) return -EINVAL; len = scnprintf(buf, sizeof(buf), "%u\n", key->u.tkip.mic_failures); return simple_read_from_buffer(userbuf, count, ppos, buf, len); } KEY_OPS(mic_failures); static ssize_t key_key_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; int i, bufsize = 2 * key->conf.keylen + 2; char *buf = kmalloc(bufsize, GFP_KERNEL); char *p = buf; ssize_t res; if (!buf) return -ENOMEM; for (i = 0; i < key->conf.keylen; i++) p += scnprintf(p, bufsize + buf - p, "%02x", key->conf.key[i]); p += scnprintf(p, bufsize+buf-p, "\n"); res = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return res; } KEY_OPS(key); #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, key->debugfs.dir, \ key, &key_##name##_ops) #define DEBUGFS_ADD_W(name) \ debugfs_create_file(#name, 0600, key->debugfs.dir, \ key, &key_##name##_ops); void ieee80211_debugfs_key_add(struct ieee80211_key *key) { static int keycount; char buf[100]; struct sta_info *sta; if (!key->local->debugfs.keys) return; sprintf(buf, "%d", keycount); key->debugfs.cnt = keycount; keycount++; key->debugfs.dir = debugfs_create_dir(buf, key->local->debugfs.keys); sta = key->sta; if (sta) { sprintf(buf, "../../netdev:%s/stations/%pM", sta->sdata->name, sta->sta.addr); key->debugfs.stalink = debugfs_create_symlink("station", key->debugfs.dir, buf); } DEBUGFS_ADD(keylen); DEBUGFS_ADD(flags); DEBUGFS_ADD(keyidx); DEBUGFS_ADD(hw_key_idx); DEBUGFS_ADD(algorithm); DEBUGFS_ADD_W(tx_spec); DEBUGFS_ADD(rx_spec); DEBUGFS_ADD(replays); DEBUGFS_ADD(icverrors); DEBUGFS_ADD(mic_failures); DEBUGFS_ADD(key); DEBUGFS_ADD(ifindex); }; void ieee80211_debugfs_key_remove(struct ieee80211_key *key) { if (!key) return; debugfs_remove_recursive(key->debugfs.dir); key->debugfs.dir = NULL; } void ieee80211_debugfs_key_update_default(struct ieee80211_sub_if_data *sdata) { char buf[50]; struct ieee80211_key *key; if (!sdata->vif.debugfs_dir) return; lockdep_assert_wiphy(sdata->local->hw.wiphy); debugfs_remove(sdata->debugfs.default_unicast_key); sdata->debugfs.default_unicast_key = NULL; if (sdata->default_unicast_key) { key = wiphy_dereference(sdata->local->hw.wiphy, sdata->default_unicast_key); sprintf(buf, "../keys/%d", key->debugfs.cnt); sdata->debugfs.default_unicast_key = debugfs_create_symlink("default_unicast_key", sdata->vif.debugfs_dir, buf); } debugfs_remove(sdata->debugfs.default_multicast_key); sdata->debugfs.default_multicast_key = NULL; if (sdata->deflink.default_multicast_key) { key = wiphy_dereference(sdata->local->hw.wiphy, sdata->deflink.default_multicast_key); sprintf(buf, "../keys/%d", key->debugfs.cnt); sdata->debugfs.default_multicast_key = debugfs_create_symlink("default_multicast_key", sdata->vif.debugfs_dir, buf); } } void ieee80211_debugfs_key_remove_mgmt_default(struct ieee80211_sub_if_data *sdata) { if (!sdata) return; debugfs_remove(sdata->debugfs.default_mgmt_key); sdata->debugfs.default_mgmt_key = NULL; } void ieee80211_debugfs_key_remove_beacon_default(struct ieee80211_sub_if_data *sdata) { if (!sdata) return; debugfs_remove(sdata->debugfs.default_beacon_key); sdata->debugfs.default_beacon_key = NULL; } |
| 420 418 397 417 26 26 420 1475 1473 7 1554 1472 1469 1307 1470 1470 1471 1553 41 41 40 22 41 22 41 41 45 4 1550 1554 1552 1553 1475 7 1473 7 1472 1 1 1464 1553 1554 2 2 1553 1553 1472 1564 1567 1464 1463 4 1565 418 309 384 418 310 419 425 425 425 384 1464 1464 1464 1465 1465 3 3 1464 1465 298 298 298 297 297 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/group.c - Operations for adding/removing multiple files at once. * * Copyright (c) 2003 Patrick Mochel * Copyright (c) 2003 Open Source Development Lab * Copyright (c) 2013 Greg Kroah-Hartman * Copyright (c) 2013 The Linux Foundation */ #include <linux/kobject.h> #include <linux/module.h> #include <linux/dcache.h> #include <linux/namei.h> #include <linux/err.h> #include <linux/fs.h> #include "sysfs.h" static void remove_files(struct kernfs_node *parent, const struct attribute_group *grp) { struct attribute *const *attr; const struct bin_attribute *const *bin_attr; if (grp->attrs) for (attr = grp->attrs; *attr; attr++) kernfs_remove_by_name(parent, (*attr)->name); if (grp->bin_attrs) for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) kernfs_remove_by_name(parent, (*bin_attr)->attr.name); } static umode_t __first_visible(const struct attribute_group *grp, struct kobject *kobj) { if (grp->attrs && grp->attrs[0] && grp->is_visible) return grp->is_visible(kobj, grp->attrs[0], 0); if (grp->attrs && grp->attrs[0] && grp->is_visible_const) return grp->is_visible_const(kobj, grp->attrs[0], 0); if (grp->bin_attrs && grp->bin_attrs[0] && grp->is_bin_visible) return grp->is_bin_visible(kobj, grp->bin_attrs[0], 0); return 0; } static int create_files(struct kernfs_node *parent, struct kobject *kobj, kuid_t uid, kgid_t gid, const struct attribute_group *grp, int update) { struct attribute *const *attr; const struct bin_attribute *const *bin_attr; int error = 0, i; if (grp->attrs) { for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++) { umode_t mode = (*attr)->mode; /* * In update mode, we're changing the permissions or * visibility. Do this by first removing then * re-adding (if required) the file. */ if (update) kernfs_remove_by_name(parent, (*attr)->name); if (grp->is_visible || grp->is_visible_const) { if (grp->is_visible) mode = grp->is_visible(kobj, *attr, i); else mode = grp->is_visible_const(kobj, *attr, i); mode &= ~SYSFS_GROUP_INVISIBLE; if (!mode) continue; } WARN(mode & ~(SYSFS_PREALLOC | 0664), "Attribute %s: Invalid permissions 0%o\n", (*attr)->name, mode); mode &= SYSFS_PREALLOC | 0664; error = sysfs_add_file_mode_ns(parent, *attr, mode, uid, gid, NULL); if (unlikely(error)) break; } if (error) { remove_files(parent, grp); goto exit; } } if (grp->bin_attrs) { for (i = 0, bin_attr = grp->bin_attrs; *bin_attr; i++, bin_attr++) { umode_t mode = (*bin_attr)->attr.mode; size_t size = (*bin_attr)->size; if (update) kernfs_remove_by_name(parent, (*bin_attr)->attr.name); if (grp->is_bin_visible) { mode = grp->is_bin_visible(kobj, *bin_attr, i); mode &= ~SYSFS_GROUP_INVISIBLE; if (!mode) continue; } if (grp->bin_size) size = grp->bin_size(kobj, *bin_attr, i); WARN(mode & ~(SYSFS_PREALLOC | 0664), "Attribute %s: Invalid permissions 0%o\n", (*bin_attr)->attr.name, mode); mode &= SYSFS_PREALLOC | 0664; error = sysfs_add_bin_file_mode_ns(parent, *bin_attr, mode, size, uid, gid, NULL); if (error) break; } if (error) remove_files(parent, grp); } exit: return error; } static int internal_create_group(struct kobject *kobj, int update, const struct attribute_group *grp) { struct kernfs_node *kn; kuid_t uid; kgid_t gid; int error; if (WARN_ON(!kobj || (!update && !kobj->sd))) return -EINVAL; /* Updates may happen before the object has been instantiated */ if (unlikely(update && !kobj->sd)) return -EINVAL; if (!grp->attrs && !grp->bin_attrs) { pr_debug("sysfs: (bin_)attrs not set by subsystem for group: %s/%s, skipping\n", kobj->name, grp->name ?: ""); return 0; } kobject_get_ownership(kobj, &uid, &gid); if (grp->name) { umode_t mode = __first_visible(grp, kobj); if (mode & SYSFS_GROUP_INVISIBLE) mode = 0; else mode = S_IRWXU | S_IRUGO | S_IXUGO; if (update) { kn = kernfs_find_and_get(kobj->sd, grp->name); if (!kn) { pr_debug("attr grp %s/%s not created yet\n", kobj->name, grp->name); /* may have been invisible prior to this update */ update = 0; } else if (!mode) { sysfs_remove_group(kobj, grp); kernfs_put(kn); return 0; } } if (!update) { if (!mode) return 0; kn = kernfs_create_dir_ns(kobj->sd, grp->name, mode, uid, gid, kobj, NULL); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(kobj->sd, grp->name); return PTR_ERR(kn); } } } else { kn = kobj->sd; } kernfs_get(kn); error = create_files(kn, kobj, uid, gid, grp, update); if (error) { if (grp->name && !update) kernfs_remove(kn); } kernfs_put(kn); if (grp->name && update) kernfs_put(kn); return error; } /** * sysfs_create_group - given a directory kobject, create an attribute group * @kobj: The kobject to create the group on * @grp: The attribute group to create * * This function creates a group for the first time. It will explicitly * warn and error if any of the attribute files being created already exist. * * Returns 0 on success or error code on failure. */ int sysfs_create_group(struct kobject *kobj, const struct attribute_group *grp) { return internal_create_group(kobj, 0, grp); } EXPORT_SYMBOL_GPL(sysfs_create_group); static int internal_create_groups(struct kobject *kobj, int update, const struct attribute_group *const *groups) { int error = 0; int i; if (!groups) return 0; for (i = 0; groups[i]; i++) { error = internal_create_group(kobj, update, groups[i]); if (error) { while (--i >= 0) sysfs_remove_group(kobj, groups[i]); break; } } return error; } /** * sysfs_create_groups - given a directory kobject, create a bunch of attribute groups * @kobj: The kobject to create the group on * @groups: The attribute groups to create, NULL terminated * * This function creates a bunch of attribute groups. If an error occurs when * creating a group, all previously created groups will be removed, unwinding * everything back to the original state when this function was called. * It will explicitly warn and error if any of the attribute files being * created already exist. * * Returns 0 on success or error code from sysfs_create_group on failure. */ int sysfs_create_groups(struct kobject *kobj, const struct attribute_group *const *groups) { return internal_create_groups(kobj, 0, groups); } EXPORT_SYMBOL_GPL(sysfs_create_groups); /** * sysfs_update_groups - given a directory kobject, create a bunch of attribute groups * @kobj: The kobject to update the group on * @groups: The attribute groups to update, NULL terminated * * This function update a bunch of attribute groups. If an error occurs when * updating a group, all previously updated groups will be removed together * with already existing (not updated) attributes. * * Returns 0 on success or error code from sysfs_update_group on failure. */ int sysfs_update_groups(struct kobject *kobj, const struct attribute_group *const *groups) { return internal_create_groups(kobj, 1, groups); } EXPORT_SYMBOL_GPL(sysfs_update_groups); /** * sysfs_update_group - given a directory kobject, update an attribute group * @kobj: The kobject to update the group on * @grp: The attribute group to update * * This function updates an attribute group. Unlike * sysfs_create_group(), it will explicitly not warn or error if any * of the attribute files being created already exist. Furthermore, * if the visibility of the files has changed through the is_visible() * callback, it will update the permissions and add or remove the * relevant files. Changing a group's name (subdirectory name under * kobj's directory in sysfs) is not allowed. * * The primary use for this function is to call it after making a change * that affects group visibility. * * Returns 0 on success or error code on failure. */ int sysfs_update_group(struct kobject *kobj, const struct attribute_group *grp) { return internal_create_group(kobj, 1, grp); } EXPORT_SYMBOL_GPL(sysfs_update_group); /** * sysfs_remove_group: remove a group from a kobject * @kobj: kobject to remove the group from * @grp: group to remove * * This function removes a group of attributes from a kobject. The attributes * previously have to have been created for this group, otherwise it will fail. */ void sysfs_remove_group(struct kobject *kobj, const struct attribute_group *grp) { struct kernfs_node *parent = kobj->sd; struct kernfs_node *kn; if (grp->name) { kn = kernfs_find_and_get(parent, grp->name); if (!kn) { pr_debug("sysfs group '%s' not found for kobject '%s'\n", grp->name, kobject_name(kobj)); return; } } else { kn = parent; kernfs_get(kn); } remove_files(kn, grp); if (grp->name) kernfs_remove(kn); kernfs_put(kn); } EXPORT_SYMBOL_GPL(sysfs_remove_group); /** * sysfs_remove_groups - remove a list of groups * * @kobj: The kobject for the groups to be removed from * @groups: NULL terminated list of groups to be removed * * If groups is not NULL, remove the specified groups from the kobject. */ void sysfs_remove_groups(struct kobject *kobj, const struct attribute_group *const *groups) { int i; if (!groups) return; for (i = 0; groups[i]; i++) sysfs_remove_group(kobj, groups[i]); } EXPORT_SYMBOL_GPL(sysfs_remove_groups); /** * sysfs_merge_group - merge files into a pre-existing named attribute group. * @kobj: The kobject containing the group. * @grp: The files to create and the attribute group they belong to. * * This function returns an error if the group doesn't exist, the .name field is * NULL or any of the files already exist in that group, in which case none of * the new files are created. */ int sysfs_merge_group(struct kobject *kobj, const struct attribute_group *grp) { struct kernfs_node *parent; kuid_t uid; kgid_t gid; int error = 0; struct attribute *const *attr; int i; parent = kernfs_find_and_get(kobj->sd, grp->name); if (!parent) return -ENOENT; kobject_get_ownership(kobj, &uid, &gid); for ((i = 0, attr = grp->attrs); *attr && !error; (++i, ++attr)) error = sysfs_add_file_mode_ns(parent, *attr, (*attr)->mode, uid, gid, NULL); if (error) { while (--i >= 0) kernfs_remove_by_name(parent, (*--attr)->name); } kernfs_put(parent); return error; } EXPORT_SYMBOL_GPL(sysfs_merge_group); /** * sysfs_unmerge_group - remove files from a pre-existing named attribute group. * @kobj: The kobject containing the group. * @grp: The files to remove and the attribute group they belong to. */ void sysfs_unmerge_group(struct kobject *kobj, const struct attribute_group *grp) { struct kernfs_node *parent; struct attribute *const *attr; parent = kernfs_find_and_get(kobj->sd, grp->name); if (parent) { for (attr = grp->attrs; *attr; ++attr) kernfs_remove_by_name(parent, (*attr)->name); kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_unmerge_group); /** * sysfs_add_link_to_group - add a symlink to an attribute group. * @kobj: The kobject containing the group. * @group_name: The name of the group. * @target: The target kobject of the symlink to create. * @link_name: The name of the symlink to create. */ int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name, struct kobject *target, const char *link_name) { struct kernfs_node *parent; int error = 0; parent = kernfs_find_and_get(kobj->sd, group_name); if (!parent) return -ENOENT; error = sysfs_create_link_sd(parent, target, link_name); kernfs_put(parent); return error; } EXPORT_SYMBOL_GPL(sysfs_add_link_to_group); /** * sysfs_remove_link_from_group - remove a symlink from an attribute group. * @kobj: The kobject containing the group. * @group_name: The name of the group. * @link_name: The name of the symlink to remove. */ void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name, const char *link_name) { struct kernfs_node *parent; parent = kernfs_find_and_get(kobj->sd, group_name); if (parent) { kernfs_remove_by_name(parent, link_name); kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_remove_link_from_group); /** * compat_only_sysfs_link_entry_to_kobj - add a symlink to a kobject pointing * to a group or an attribute * @kobj: The kobject containing the group. * @target_kobj: The target kobject. * @target_name: The name of the target group or attribute. * @symlink_name: The name of the symlink file (target_name will be * considered if symlink_name is NULL). */ int compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, struct kobject *target_kobj, const char *target_name, const char *symlink_name) { struct kernfs_node *target; struct kernfs_node *entry; struct kernfs_node *link; /* * We don't own @target_kobj and it may be removed at any time. * Synchronize using sysfs_symlink_target_lock. See sysfs_remove_dir() * for details. */ spin_lock(&sysfs_symlink_target_lock); target = target_kobj->sd; if (target) kernfs_get(target); spin_unlock(&sysfs_symlink_target_lock); if (!target) return -ENOENT; entry = kernfs_find_and_get(target, target_name); if (!entry) { kernfs_put(target); return -ENOENT; } if (!symlink_name) symlink_name = target_name; link = kernfs_create_link(kobj->sd, symlink_name, entry); if (PTR_ERR(link) == -EEXIST) sysfs_warn_dup(kobj->sd, symlink_name); kernfs_put(entry); kernfs_put(target); return PTR_ERR_OR_ZERO(link); } EXPORT_SYMBOL_GPL(compat_only_sysfs_link_entry_to_kobj); static int sysfs_group_attrs_change_owner(struct kobject *kobj, struct kernfs_node *grp_kn, const struct attribute_group *grp, struct iattr *newattrs) { struct kernfs_node *kn; int error, i; umode_t mode; if (grp->attrs) { struct attribute *const *attr; for (i = 0, attr = grp->attrs; *attr; i++, attr++) { if (grp->is_visible || grp->is_visible_const) { if (grp->is_visible) mode = grp->is_visible(kobj, *attr, i); else mode = grp->is_visible_const(kobj, *attr, i); if (mode & SYSFS_GROUP_INVISIBLE) break; if (!mode) continue; } kn = kernfs_find_and_get(grp_kn, (*attr)->name); if (!kn) return -ENOENT; error = kernfs_setattr(kn, newattrs); kernfs_put(kn); if (error) return error; } } if (grp->bin_attrs) { const struct bin_attribute *const *bin_attr; for (i = 0, bin_attr = grp->bin_attrs; *bin_attr; i++, bin_attr++) { if (grp->is_bin_visible) { mode = grp->is_bin_visible(kobj, *bin_attr, i); if (mode & SYSFS_GROUP_INVISIBLE) break; if (!mode) continue; } kn = kernfs_find_and_get(grp_kn, (*bin_attr)->attr.name); if (!kn) return -ENOENT; error = kernfs_setattr(kn, newattrs); kernfs_put(kn); if (error) return error; } } return 0; } /** * sysfs_group_change_owner - change owner of an attribute group. * @kobj: The kobject containing the group. * @grp: The attribute group. * @kuid: new owner's kuid * @kgid: new owner's kgid * * Returns 0 on success or error code on failure. */ int sysfs_group_change_owner(struct kobject *kobj, const struct attribute_group *grp, kuid_t kuid, kgid_t kgid) { struct kernfs_node *grp_kn; int error; struct iattr newattrs = { .ia_valid = ATTR_UID | ATTR_GID, .ia_uid = kuid, .ia_gid = kgid, }; if (!kobj->state_in_sysfs) return -EINVAL; if (grp->name) { grp_kn = kernfs_find_and_get(kobj->sd, grp->name); } else { kernfs_get(kobj->sd); grp_kn = kobj->sd; } if (!grp_kn) return -ENOENT; error = kernfs_setattr(grp_kn, &newattrs); if (!error) error = sysfs_group_attrs_change_owner(kobj, grp_kn, grp, &newattrs); kernfs_put(grp_kn); return error; } EXPORT_SYMBOL_GPL(sysfs_group_change_owner); /** * sysfs_groups_change_owner - change owner of a set of attribute groups. * @kobj: The kobject containing the groups. * @groups: The attribute groups. * @kuid: new owner's kuid * @kgid: new owner's kgid * * Returns 0 on success or error code on failure. */ int sysfs_groups_change_owner(struct kobject *kobj, const struct attribute_group *const *groups, kuid_t kuid, kgid_t kgid) { int error = 0, i; if (!kobj->state_in_sysfs) return -EINVAL; if (!groups) return 0; for (i = 0; groups[i]; i++) { error = sysfs_group_change_owner(kobj, groups[i], kuid, kgid); if (error) break; } return error; } EXPORT_SYMBOL_GPL(sysfs_groups_change_owner); |
| 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-only #include "bitset.h" #include "common.h" #include "netlink.h" struct privflags_req_info { struct ethnl_req_info base; }; struct privflags_reply_data { struct ethnl_reply_data base; const char (*priv_flag_names)[ETH_GSTRING_LEN]; unsigned int n_priv_flags; u32 priv_flags; }; #define PRIVFLAGS_REPDATA(__reply_base) \ container_of(__reply_base, struct privflags_reply_data, base) const struct nla_policy ethnl_privflags_get_policy[] = { [ETHTOOL_A_PRIVFLAGS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int ethnl_get_priv_flags_info(struct net_device *dev, unsigned int *count, const char (**names)[ETH_GSTRING_LEN]) { const struct ethtool_ops *ops = dev->ethtool_ops; int nflags; nflags = ops->get_sset_count(dev, ETH_SS_PRIV_FLAGS); if (nflags < 0) return nflags; if (names) { *names = kcalloc(nflags, ETH_GSTRING_LEN, GFP_KERNEL); if (!*names) return -ENOMEM; ops->get_strings(dev, ETH_SS_PRIV_FLAGS, (u8 *)*names); } /* We can pass more than 32 private flags to userspace via netlink but * we cannot get more with ethtool_ops::get_priv_flags(). Note that we * must not adjust nflags before allocating the space for flag names * as the buffer must be large enough for all flags. */ if (WARN_ONCE(nflags > 32, "device %s reports more than 32 private flags (%d)\n", netdev_name(dev), nflags)) nflags = 32; *count = nflags; return 0; } static int privflags_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const char (*names)[ETH_GSTRING_LEN]; const struct ethtool_ops *ops; unsigned int nflags; int ret; ops = dev->ethtool_ops; if (!ops->get_priv_flags || !ops->get_sset_count || !ops->get_strings) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = ethnl_get_priv_flags_info(dev, &nflags, &names); if (ret < 0) goto out_ops; data->priv_flags = ops->get_priv_flags(dev); data->priv_flag_names = names; data->n_priv_flags = nflags; out_ops: ethnl_ops_complete(dev); return ret; } static int privflags_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const u32 all_flags = ~(u32)0 >> (32 - data->n_priv_flags); return ethnl_bitset32_size(&data->priv_flags, &all_flags, data->n_priv_flags, data->priv_flag_names, compact); } static int privflags_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const u32 all_flags = ~(u32)0 >> (32 - data->n_priv_flags); return ethnl_put_bitset32(skb, ETHTOOL_A_PRIVFLAGS_FLAGS, &data->priv_flags, &all_flags, data->n_priv_flags, data->priv_flag_names, compact); } static void privflags_cleanup_data(struct ethnl_reply_data *reply_data) { struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_data); kfree(data->priv_flag_names); } /* PRIVFLAGS_SET */ const struct nla_policy ethnl_privflags_set_policy[] = { [ETHTOOL_A_PRIVFLAGS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_PRIVFLAGS_FLAGS] = { .type = NLA_NESTED }, }; static int ethnl_set_privflags_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; if (!info->attrs[ETHTOOL_A_PRIVFLAGS_FLAGS]) return -EINVAL; if (!ops->get_priv_flags || !ops->set_priv_flags || !ops->get_sset_count || !ops->get_strings) return -EOPNOTSUPP; return 1; } static int ethnl_set_privflags(struct ethnl_req_info *req_info, struct genl_info *info) { const char (*names)[ETH_GSTRING_LEN] = NULL; struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; unsigned int nflags; bool mod = false; bool compact; u32 flags; int ret; ret = ethnl_bitset_is_compact(tb[ETHTOOL_A_PRIVFLAGS_FLAGS], &compact); if (ret < 0) return ret; ret = ethnl_get_priv_flags_info(dev, &nflags, compact ? NULL : &names); if (ret < 0) return ret; flags = dev->ethtool_ops->get_priv_flags(dev); ret = ethnl_update_bitset32(&flags, nflags, tb[ETHTOOL_A_PRIVFLAGS_FLAGS], names, info->extack, &mod); if (ret < 0 || !mod) goto out_free; ret = dev->ethtool_ops->set_priv_flags(dev, flags); if (ret < 0) goto out_free; ret = 1; out_free: kfree(names); return ret; } const struct ethnl_request_ops ethnl_privflags_request_ops = { .request_cmd = ETHTOOL_MSG_PRIVFLAGS_GET, .reply_cmd = ETHTOOL_MSG_PRIVFLAGS_GET_REPLY, .hdr_attr = ETHTOOL_A_PRIVFLAGS_HEADER, .req_info_size = sizeof(struct privflags_req_info), .reply_data_size = sizeof(struct privflags_reply_data), .prepare_data = privflags_prepare_data, .reply_size = privflags_reply_size, .fill_reply = privflags_fill_reply, .cleanup_data = privflags_cleanup_data, .set_validate = ethnl_set_privflags_validate, .set = ethnl_set_privflags, .set_ntf_cmd = ETHTOOL_MSG_PRIVFLAGS_NTF, }; |
| 3 3 2 1 3 4 3 3 3 2 1 1 2 1 13 12 11 11 10 9 9 8 302 2 2 38 38 5 9 6 5 4 3 3 2 7 6 5 4 4 3 4 4 3 2 2 1 5 4 5 4 3 2 1 6 5 5 4 4 3 9 8 7 6 6 6 6 6 7 6 5 4 97 97 12 12 85 94 2 2 2 2 1 1 4 3 2 1 11 11 10 8 1 7 5 11 306 97 2 3 2 13 1 2 2 1 1 2 1 1 1 1 2 1 2 1 1 1 21 21 20 19 1 6 7 4 1 4 6 9 302 91 353 4 4 2 1 2 1 11 1 352 307 213 90 88 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/capability.h> #include <linux/compat.h> #include <linux/blkdev.h> #include <linux/export.h> #include <linux/gfp.h> #include <linux/blkpg.h> #include <linux/hdreg.h> #include <linux/backing-dev.h> #include <linux/fs.h> #include <linux/blktrace_api.h> #include <linux/pr.h> #include <linux/uaccess.h> #include <linux/pagemap.h> #include <linux/io_uring/cmd.h> #include <linux/blk-integrity.h> #include <uapi/linux/blkdev.h> #include "blk.h" #include "blk-crypto-internal.h" static int blkpg_do_ioctl(struct block_device *bdev, struct blkpg_partition __user *upart, int op) { struct gendisk *disk = bdev->bd_disk; struct blkpg_partition p; sector_t start, length, capacity, end; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (copy_from_user(&p, upart, sizeof(struct blkpg_partition))) return -EFAULT; if (bdev_is_partition(bdev)) return -EINVAL; if (p.pno <= 0) return -EINVAL; if (op == BLKPG_DEL_PARTITION) return bdev_del_partition(disk, p.pno); if (p.start < 0 || p.length <= 0 || LLONG_MAX - p.length < p.start) return -EINVAL; /* Check that the partition is aligned to the block size */ if (!IS_ALIGNED(p.start | p.length, bdev_logical_block_size(bdev))) return -EINVAL; start = p.start >> SECTOR_SHIFT; length = p.length >> SECTOR_SHIFT; capacity = get_capacity(disk); if (check_add_overflow(start, length, &end)) return -EINVAL; if (start >= capacity || end > capacity) return -EINVAL; switch (op) { case BLKPG_ADD_PARTITION: return bdev_add_partition(disk, p.pno, start, length); case BLKPG_RESIZE_PARTITION: return bdev_resize_partition(disk, p.pno, start, length); default: return -EINVAL; } } static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg) { struct blkpg_partition __user *udata; int op; if (get_user(op, &arg->op) || get_user(udata, &arg->data)) return -EFAULT; return blkpg_do_ioctl(bdev, udata, op); } #ifdef CONFIG_COMPAT struct compat_blkpg_ioctl_arg { compat_int_t op; compat_int_t flags; compat_int_t datalen; compat_caddr_t data; }; static int compat_blkpg_ioctl(struct block_device *bdev, struct compat_blkpg_ioctl_arg __user *arg) { compat_caddr_t udata; int op; if (get_user(op, &arg->op) || get_user(udata, &arg->data)) return -EFAULT; return blkpg_do_ioctl(bdev, compat_ptr(udata), op); } #endif /* * Check that [start, start + len) is a valid range from the block device's * perspective, including verifying that it can be correctly translated into * logical block addresses. */ static int blk_validate_byte_range(struct block_device *bdev, uint64_t start, uint64_t len) { unsigned int bs_mask = bdev_logical_block_size(bdev) - 1; uint64_t end; if ((start | len) & bs_mask) return -EINVAL; if (!len) return -EINVAL; if (check_add_overflow(start, len, &end) || end > bdev_nr_bytes(bdev)) return -EINVAL; return 0; } static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, unsigned long arg) { uint64_t range[2], start, len; struct bio *prev = NULL, *bio; sector_t sector, nr_sects; struct blk_plug plug; int err; if (copy_from_user(range, (void __user *)arg, sizeof(range))) return -EFAULT; start = range[0]; len = range[1]; if (!bdev_max_discard_sectors(bdev)) return -EOPNOTSUPP; if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (bdev_read_only(bdev)) return -EPERM; err = blk_validate_byte_range(bdev, start, len); if (err) return err; inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, start + len - 1); if (err) goto fail; sector = start >> SECTOR_SHIFT; nr_sects = len >> SECTOR_SHIFT; blk_start_plug(&plug); while (!fatal_signal_pending(current)) { bio = blk_alloc_discard_bio(bdev, §or, &nr_sects, GFP_KERNEL); if (!bio) break; prev = bio_chain_and_submit(prev, bio); } if (prev) { err = bio_submit_or_kill(prev, BLKDEV_ZERO_KILLABLE); if (err == -EOPNOTSUPP) err = 0; bio_put(prev); } blk_finish_plug(&plug); fail: filemap_invalidate_unlock(bdev->bd_mapping); inode_unlock(bdev->bd_mapping->host); return err; } static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode, void __user *argp) { uint64_t start, len, end; uint64_t range[2]; int err; if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (!bdev_max_secure_erase_sectors(bdev)) return -EOPNOTSUPP; if (copy_from_user(range, argp, sizeof(range))) return -EFAULT; start = range[0]; len = range[1]; if ((start & 511) || (len & 511)) return -EINVAL; if (check_add_overflow(start, len, &end) || end > bdev_nr_bytes(bdev)) return -EINVAL; inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, end - 1); if (!err) err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9, GFP_KERNEL); filemap_invalidate_unlock(bdev->bd_mapping); inode_unlock(bdev->bd_mapping->host); return err; } static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode, unsigned long arg) { uint64_t range[2]; uint64_t start, end, len; int err; if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (copy_from_user(range, (void __user *)arg, sizeof(range))) return -EFAULT; start = range[0]; len = range[1]; end = start + len - 1; if (start & 511) return -EINVAL; if (len & 511) return -EINVAL; if (end >= (uint64_t)bdev_nr_bytes(bdev)) return -EINVAL; if (end < start) return -EINVAL; /* Invalidate the page cache, including dirty pages */ inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, end); if (err) goto fail; err = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, BLKDEV_ZERO_NOUNMAP | BLKDEV_ZERO_KILLABLE); fail: filemap_invalidate_unlock(bdev->bd_mapping); inode_unlock(bdev->bd_mapping->host); return err; } static int put_ushort(unsigned short __user *argp, unsigned short val) { return put_user(val, argp); } static int put_int(int __user *argp, int val) { return put_user(val, argp); } static int put_uint(unsigned int __user *argp, unsigned int val) { return put_user(val, argp); } static int put_long(long __user *argp, long val) { return put_user(val, argp); } static int put_ulong(unsigned long __user *argp, unsigned long val) { return put_user(val, argp); } static int put_u64(u64 __user *argp, u64 val) { return put_user(val, argp); } #ifdef CONFIG_COMPAT static int compat_put_long(compat_long_t __user *argp, long val) { return put_user(val, argp); } static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val) { return put_user(val, argp); } #endif #ifdef CONFIG_COMPAT /* * This is the equivalent of compat_ptr_ioctl(), to be used by block * drivers that implement only commands that are completely compatible * between 32-bit and 64-bit user space */ int blkdev_compat_ptr_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned cmd, unsigned long arg) { struct gendisk *disk = bdev->bd_disk; if (disk->fops->ioctl) return disk->fops->ioctl(bdev, mode, cmd, (unsigned long)compat_ptr(arg)); return -ENOIOCTLCMD; } EXPORT_SYMBOL(blkdev_compat_ptr_ioctl); #endif enum pr_direction { PR_IN, /* read from device */ PR_OUT, /* write to device */ }; static bool blkdev_pr_allowed(struct block_device *bdev, blk_mode_t mode, enum pr_direction dir) { /* no sense to make reservations for partitions */ if (bdev_is_partition(bdev)) return false; if (capable(CAP_SYS_ADMIN)) return true; /* * Only allow unprivileged reservation _out_ commands if the file * descriptor is open for writing. Allow reservation _in_ commands if * the file descriptor is open for reading since they do not modify the * device. */ if (dir == PR_IN) return mode & BLK_OPEN_READ; else return mode & BLK_OPEN_WRITE; } static int blkdev_pr_register(struct block_device *bdev, blk_mode_t mode, struct pr_registration __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_registration reg; if (!blkdev_pr_allowed(bdev, mode, PR_OUT)) return -EPERM; if (!ops || !ops->pr_register) return -EOPNOTSUPP; if (copy_from_user(®, arg, sizeof(reg))) return -EFAULT; if (reg.flags & ~PR_FL_IGNORE_KEY) return -EOPNOTSUPP; return ops->pr_register(bdev, reg.old_key, reg.new_key, reg.flags); } static int blkdev_pr_reserve(struct block_device *bdev, blk_mode_t mode, struct pr_reservation __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_reservation rsv; if (!blkdev_pr_allowed(bdev, mode, PR_OUT)) return -EPERM; if (!ops || !ops->pr_reserve) return -EOPNOTSUPP; if (copy_from_user(&rsv, arg, sizeof(rsv))) return -EFAULT; if (rsv.flags & ~PR_FL_IGNORE_KEY) return -EOPNOTSUPP; return ops->pr_reserve(bdev, rsv.key, rsv.type, rsv.flags); } static int blkdev_pr_release(struct block_device *bdev, blk_mode_t mode, struct pr_reservation __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_reservation rsv; if (!blkdev_pr_allowed(bdev, mode, PR_OUT)) return -EPERM; if (!ops || !ops->pr_release) return -EOPNOTSUPP; if (copy_from_user(&rsv, arg, sizeof(rsv))) return -EFAULT; if (rsv.flags) return -EOPNOTSUPP; return ops->pr_release(bdev, rsv.key, rsv.type); } static int blkdev_pr_preempt(struct block_device *bdev, blk_mode_t mode, struct pr_preempt __user *arg, bool abort) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_preempt p; if (!blkdev_pr_allowed(bdev, mode, PR_OUT)) return -EPERM; if (!ops || !ops->pr_preempt) return -EOPNOTSUPP; if (copy_from_user(&p, arg, sizeof(p))) return -EFAULT; if (p.flags) return -EOPNOTSUPP; return ops->pr_preempt(bdev, p.old_key, p.new_key, p.type, abort); } static int blkdev_pr_clear(struct block_device *bdev, blk_mode_t mode, struct pr_clear __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_clear c; if (!blkdev_pr_allowed(bdev, mode, PR_OUT)) return -EPERM; if (!ops || !ops->pr_clear) return -EOPNOTSUPP; if (copy_from_user(&c, arg, sizeof(c))) return -EFAULT; if (c.flags) return -EOPNOTSUPP; return ops->pr_clear(bdev, c.key); } static int blkdev_pr_read_keys(struct block_device *bdev, blk_mode_t mode, struct pr_read_keys __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_keys *keys_info; struct pr_read_keys read_keys; u64 __user *keys_ptr; size_t keys_info_len; size_t keys_copy_len; int ret; if (!blkdev_pr_allowed(bdev, mode, PR_IN)) return -EPERM; if (!ops || !ops->pr_read_keys) return -EOPNOTSUPP; if (copy_from_user(&read_keys, arg, sizeof(read_keys))) return -EFAULT; if (read_keys.num_keys > PR_KEYS_MAX) return -EINVAL; keys_info_len = struct_size(keys_info, keys, read_keys.num_keys); keys_info = kvzalloc(keys_info_len, GFP_KERNEL); if (!keys_info) return -ENOMEM; keys_info->num_keys = read_keys.num_keys; ret = ops->pr_read_keys(bdev, keys_info); if (ret) goto out; /* Copy out individual keys */ keys_ptr = u64_to_user_ptr(read_keys.keys_ptr); keys_copy_len = min(read_keys.num_keys, keys_info->num_keys) * sizeof(keys_info->keys[0]); if (copy_to_user(keys_ptr, keys_info->keys, keys_copy_len)) { ret = -EFAULT; goto out; } /* Copy out the arg struct */ read_keys.generation = keys_info->generation; read_keys.num_keys = keys_info->num_keys; if (copy_to_user(arg, &read_keys, sizeof(read_keys))) ret = -EFAULT; out: kvfree(keys_info); return ret; } static int blkdev_pr_read_reservation(struct block_device *bdev, blk_mode_t mode, struct pr_read_reservation __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_held_reservation rsv = {}; struct pr_read_reservation out = {}; int ret; if (!blkdev_pr_allowed(bdev, mode, PR_IN)) return -EPERM; if (!ops || !ops->pr_read_reservation) return -EOPNOTSUPP; ret = ops->pr_read_reservation(bdev, &rsv); if (ret) return ret; out.key = rsv.key; out.generation = rsv.generation; out.type = rsv.type; if (copy_to_user(arg, &out, sizeof(out))) return -EFAULT; return 0; } static int blkdev_flushbuf(struct block_device *bdev, unsigned cmd, unsigned long arg) { if (!capable(CAP_SYS_ADMIN)) return -EACCES; mutex_lock(&bdev->bd_holder_lock); if (bdev->bd_holder_ops && bdev->bd_holder_ops->sync) bdev->bd_holder_ops->sync(bdev); else { mutex_unlock(&bdev->bd_holder_lock); sync_blockdev(bdev); } invalidate_bdev(bdev); return 0; } static int blkdev_roset(struct block_device *bdev, unsigned cmd, unsigned long arg) { int ret, n; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (get_user(n, (int __user *)arg)) return -EFAULT; if (bdev->bd_disk->fops->set_read_only) { ret = bdev->bd_disk->fops->set_read_only(bdev, n); if (ret) return ret; } if (n) bdev_set_flag(bdev, BD_READ_ONLY); else bdev_clear_flag(bdev, BD_READ_ONLY); return 0; } static int blkdev_getgeo(struct block_device *bdev, struct hd_geometry __user *argp) { struct gendisk *disk = bdev->bd_disk; struct hd_geometry geo; int ret; if (!argp) return -EINVAL; if (!disk->fops->getgeo) return -ENOTTY; /* * We need to set the startsect first, the driver may * want to override it. */ memset(&geo, 0, sizeof(geo)); geo.start = get_start_sect(bdev); ret = disk->fops->getgeo(disk, &geo); if (ret) return ret; if (copy_to_user(argp, &geo, sizeof(geo))) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT struct compat_hd_geometry { unsigned char heads; unsigned char sectors; unsigned short cylinders; u32 start; }; static int compat_hdio_getgeo(struct block_device *bdev, struct compat_hd_geometry __user *ugeo) { struct gendisk *disk = bdev->bd_disk; struct hd_geometry geo; int ret; if (!ugeo) return -EINVAL; if (!disk->fops->getgeo) return -ENOTTY; memset(&geo, 0, sizeof(geo)); /* * We need to set the startsect first, the driver may * want to override it. */ geo.start = get_start_sect(bdev); ret = disk->fops->getgeo(disk, &geo); if (ret) return ret; ret = copy_to_user(ugeo, &geo, 4); ret |= put_user(geo.start, &ugeo->start); if (ret) ret = -EFAULT; return ret; } #endif /* set the logical block size */ static int blkdev_bszset(struct file *file, blk_mode_t mode, int __user *argp) { // this one might be file_inode(file)->i_rdev - a rare valid // use of file_inode() for those. dev_t dev = I_BDEV(file->f_mapping->host)->bd_dev; struct file *excl_file; int ret, n; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (!argp) return -EINVAL; if (get_user(n, argp)) return -EFAULT; if (mode & BLK_OPEN_EXCL) return set_blocksize(file, n); excl_file = bdev_file_open_by_dev(dev, mode, &dev, NULL); if (IS_ERR(excl_file)) return -EBUSY; ret = set_blocksize(excl_file, n); fput(excl_file); return ret; } /* * Common commands that are handled the same way on native and compat * user space. Note the separate arg/argp parameters that are needed * to deal with the compat_ptr() conversion. */ static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg, void __user *argp) { unsigned int max_sectors; switch (cmd) { case BLKFLSBUF: return blkdev_flushbuf(bdev, cmd, arg); case BLKROSET: return blkdev_roset(bdev, cmd, arg); case BLKDISCARD: return blk_ioctl_discard(bdev, mode, arg); case BLKSECDISCARD: return blk_ioctl_secure_erase(bdev, mode, argp); case BLKZEROOUT: return blk_ioctl_zeroout(bdev, mode, arg); case BLKGETDISKSEQ: return put_u64(argp, bdev->bd_disk->diskseq); case BLKREPORTZONE: case BLKREPORTZONEV2: return blkdev_report_zones_ioctl(bdev, cmd, arg); case BLKRESETZONE: case BLKOPENZONE: case BLKCLOSEZONE: case BLKFINISHZONE: return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg); case BLKGETZONESZ: return put_uint(argp, bdev_zone_sectors(bdev)); case BLKGETNRZONES: return put_uint(argp, bdev_nr_zones(bdev)); case BLKROGET: return put_int(argp, bdev_read_only(bdev) != 0); case BLKSSZGET: /* get block device logical block size */ return put_int(argp, bdev_logical_block_size(bdev)); case BLKPBSZGET: /* get block device physical block size */ return put_uint(argp, bdev_physical_block_size(bdev)); case BLKIOMIN: return put_uint(argp, bdev_io_min(bdev)); case BLKIOOPT: return put_uint(argp, bdev_io_opt(bdev)); case BLKALIGNOFF: return put_int(argp, bdev_alignment_offset(bdev)); case BLKDISCARDZEROES: return put_uint(argp, 0); case BLKSECTGET: max_sectors = min_t(unsigned int, USHRT_MAX, queue_max_sectors(bdev_get_queue(bdev))); return put_ushort(argp, max_sectors); case BLKROTATIONAL: return put_ushort(argp, bdev_rot(bdev)); case BLKRASET: case BLKFRASET: if(!capable(CAP_SYS_ADMIN)) return -EACCES; bdev->bd_disk->bdi->ra_pages = (arg * 512) / PAGE_SIZE; return 0; case BLKRRPART: if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (bdev_is_partition(bdev)) return -EINVAL; return disk_scan_partitions(bdev->bd_disk, mode | BLK_OPEN_STRICT_SCAN); case BLKTRACESTART: case BLKTRACESTOP: case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); case BLKCRYPTOIMPORTKEY: case BLKCRYPTOGENERATEKEY: case BLKCRYPTOPREPAREKEY: return blk_crypto_ioctl(bdev, cmd, argp); case IOC_PR_REGISTER: return blkdev_pr_register(bdev, mode, argp); case IOC_PR_RESERVE: return blkdev_pr_reserve(bdev, mode, argp); case IOC_PR_RELEASE: return blkdev_pr_release(bdev, mode, argp); case IOC_PR_PREEMPT: return blkdev_pr_preempt(bdev, mode, argp, false); case IOC_PR_PREEMPT_ABORT: return blkdev_pr_preempt(bdev, mode, argp, true); case IOC_PR_CLEAR: return blkdev_pr_clear(bdev, mode, argp); case IOC_PR_READ_KEYS: return blkdev_pr_read_keys(bdev, mode, argp); case IOC_PR_READ_RESERVATION: return blkdev_pr_read_reservation(bdev, mode, argp); default: return blk_get_meta_cap(bdev, cmd, argp); } } /* * Always keep this in sync with compat_blkdev_ioctl() * to handle all incompatible commands in both functions. * * New commands must be compatible and go into blkdev_common_ioctl */ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct block_device *bdev = I_BDEV(file->f_mapping->host); void __user *argp = (void __user *)arg; blk_mode_t mode = file_to_blk_mode(file); int ret; switch (cmd) { /* These need separate implementations for the data structure */ case HDIO_GETGEO: return blkdev_getgeo(bdev, argp); case BLKPG: return blkpg_ioctl(bdev, argp); /* Compat mode returns 32-bit data instead of 'long' */ case BLKRAGET: case BLKFRAGET: if (!argp) return -EINVAL; return put_long(argp, (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: if (bdev_nr_sectors(bdev) > ~0UL) return -EFBIG; return put_ulong(argp, bdev_nr_sectors(bdev)); /* The data is compatible, but the command number is different */ case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */ return put_int(argp, block_size(bdev)); case BLKBSZSET: return blkdev_bszset(file, mode, argp); case BLKGETSIZE64: return put_u64(argp, bdev_nr_bytes(bdev)); /* Incompatible alignment on i386 */ case BLKTRACESETUP: case BLKTRACESETUP2: return blk_trace_ioctl(bdev, cmd, argp); default: break; } ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp); if (ret != -ENOIOCTLCMD) return ret; if (!bdev->bd_disk->fops->ioctl) return -ENOTTY; return bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg); } #ifdef CONFIG_COMPAT #define BLKBSZGET_32 _IOR(0x12, 112, int) #define BLKBSZSET_32 _IOW(0x12, 113, int) #define BLKGETSIZE64_32 _IOR(0x12, 114, int) /* Most of the generic ioctls are handled in the normal fallback path. This assumes the blkdev's low level compat_ioctl always returns ENOIOCTLCMD for unknown ioctls. */ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) { int ret; void __user *argp = compat_ptr(arg); struct block_device *bdev = I_BDEV(file->f_mapping->host); struct gendisk *disk = bdev->bd_disk; blk_mode_t mode = file_to_blk_mode(file); switch (cmd) { /* These need separate implementations for the data structure */ case HDIO_GETGEO: return compat_hdio_getgeo(bdev, argp); case BLKPG: return compat_blkpg_ioctl(bdev, argp); /* Compat mode returns 32-bit data instead of 'long' */ case BLKRAGET: case BLKFRAGET: if (!argp) return -EINVAL; return compat_put_long(argp, (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: if (bdev_nr_sectors(bdev) > ~(compat_ulong_t)0) return -EFBIG; return compat_put_ulong(argp, bdev_nr_sectors(bdev)); /* The data is compatible, but the command number is different */ case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */ return put_int(argp, bdev_logical_block_size(bdev)); case BLKBSZSET_32: return blkdev_bszset(file, mode, argp); case BLKGETSIZE64_32: return put_u64(argp, bdev_nr_bytes(bdev)); /* Incompatible alignment on i386 */ case BLKTRACESETUP32: return blk_trace_ioctl(bdev, cmd, argp); default: break; } ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp); if (ret == -ENOIOCTLCMD && disk->fops->compat_ioctl) ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg); return ret; } #endif struct blk_iou_cmd { u64 start; u64 len; int res; bool nowait; }; static void blk_cmd_complete(struct io_tw_req tw_req, io_tw_token_t tw) { struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req); struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd); if (bic->res == -EAGAIN && bic->nowait) io_uring_cmd_issue_blocking(cmd); else io_uring_cmd_done(cmd, bic->res, IO_URING_CMD_TASK_WORK_ISSUE_FLAGS); } static void bio_cmd_bio_end_io(struct bio *bio) { struct io_uring_cmd *cmd = bio->bi_private; struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd); if (unlikely(bio->bi_status) && !bic->res) bic->res = blk_status_to_errno(bio->bi_status); io_uring_cmd_do_in_task_lazy(cmd, blk_cmd_complete); bio_put(bio); } static int blkdev_cmd_discard(struct io_uring_cmd *cmd, struct block_device *bdev, uint64_t start, uint64_t len, bool nowait) { struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd); gfp_t gfp = nowait ? GFP_NOWAIT : GFP_KERNEL; sector_t sector = start >> SECTOR_SHIFT; sector_t nr_sects = len >> SECTOR_SHIFT; struct bio *prev = NULL, *bio; int err; if (!bdev_max_discard_sectors(bdev)) return -EOPNOTSUPP; if (!(file_to_blk_mode(cmd->file) & BLK_OPEN_WRITE)) return -EBADF; if (bdev_read_only(bdev)) return -EPERM; err = blk_validate_byte_range(bdev, start, len); if (err) return err; err = filemap_invalidate_pages(bdev->bd_mapping, start, start + len - 1, nowait); if (err) return err; while (true) { bio = blk_alloc_discard_bio(bdev, §or, &nr_sects, gfp); if (!bio) break; if (nowait) { /* * Don't allow multi-bio non-blocking submissions as * subsequent bios may fail but we won't get a direct * indication of that. Normally, the caller should * retry from a blocking context. */ if (unlikely(nr_sects)) { bio_put(bio); return -EAGAIN; } bio->bi_opf |= REQ_NOWAIT; } prev = bio_chain_and_submit(prev, bio); } if (unlikely(!prev)) return -EAGAIN; if (unlikely(nr_sects)) bic->res = -EAGAIN; prev->bi_private = cmd; prev->bi_end_io = bio_cmd_bio_end_io; submit_bio(prev); return -EIOCBQUEUED; } int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { struct block_device *bdev = I_BDEV(cmd->file->f_mapping->host); struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd); u32 cmd_op = cmd->cmd_op; /* Read what we need from the SQE on the first issue */ if (!(cmd->flags & IORING_URING_CMD_REISSUE)) { const struct io_uring_sqe *sqe = cmd->sqe; if (unlikely(sqe->ioprio || sqe->__pad1 || sqe->len || sqe->rw_flags || sqe->file_index)) return -EINVAL; bic->start = READ_ONCE(sqe->addr); bic->len = READ_ONCE(sqe->addr3); } bic->res = 0; bic->nowait = issue_flags & IO_URING_F_NONBLOCK; switch (cmd_op) { case BLOCK_URING_CMD_DISCARD: return blkdev_cmd_discard(cmd, bdev, bic->start, bic->len, bic->nowait); } return -EINVAL; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _INPUT_COMPAT_H #define _INPUT_COMPAT_H /* * 32bit compatibility wrappers for the input subsystem. * * Very heavily based on evdev.c - Copyright (c) 1999-2002 Vojtech Pavlik */ #include <linux/compiler.h> #include <linux/compat.h> #include <linux/input.h> #ifdef CONFIG_COMPAT struct input_event_compat { compat_ulong_t sec; compat_ulong_t usec; __u16 type; __u16 code; __s32 value; }; struct ff_periodic_effect_compat { __u16 waveform; __u16 period; __s16 magnitude; __s16 offset; __u16 phase; struct ff_envelope envelope; __u32 custom_len; compat_uptr_t custom_data; }; struct ff_effect_compat { __u16 type; __s16 id; __u16 direction; struct ff_trigger trigger; struct ff_replay replay; union { struct ff_constant_effect constant; struct ff_ramp_effect ramp; struct ff_periodic_effect_compat periodic; struct ff_condition_effect condition[2]; /* One for each axis */ struct ff_rumble_effect rumble; } u; }; static inline size_t input_event_size(void) { return (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) ? sizeof(struct input_event_compat) : sizeof(struct input_event); } #else static inline size_t input_event_size(void) { return sizeof(struct input_event); } #endif /* CONFIG_COMPAT */ int input_event_from_user(const char __user *buffer, struct input_event *event); int input_event_to_user(char __user *buffer, const struct input_event *event); int input_ff_effect_from_user(const char __user *buffer, size_t size, struct ff_effect *effect); int input_bits_to_string(char *buf, int buf_size, unsigned long bits, bool skip_empty); #endif /* _INPUT_COMPAT_H */ |
| 83 30 1 92 99 100 13 13 13 13 13 13 1 2 2 1 1 1 1 1 1 1 1 1 7 7 6 6 6 6 6 5 6 6 11 14 14 14 14 14 14 14 13 14 13 1 1 13 4 13 13 13 1 2 1 1 2 1 2 1 2 1 2 1 2 3 2 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * kernel/power/hibernate.c - Hibernation (a.k.a suspend-to-disk) support. * * Copyright (c) 2003 Patrick Mochel * Copyright (c) 2003 Open Source Development Lab * Copyright (c) 2004 Pavel Machek <pavel@ucw.cz> * Copyright (c) 2009 Rafael J. Wysocki, Novell Inc. * Copyright (C) 2012 Bojan Smojver <bojan@rexursive.com> */ #define pr_fmt(fmt) "PM: hibernation: " fmt #include <crypto/acompress.h> #include <linux/blkdev.h> #include <linux/export.h> #include <linux/suspend.h> #include <linux/reboot.h> #include <linux/string.h> #include <linux/device.h> #include <linux/async.h> #include <linux/delay.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/pm.h> #include <linux/nmi.h> #include <linux/console.h> #include <linux/cpu.h> #include <linux/freezer.h> #include <linux/gfp.h> #include <linux/syscore_ops.h> #include <linux/ctype.h> #include <linux/ktime.h> #include <linux/security.h> #include <linux/secretmem.h> #include <trace/events/power.h> #include "power.h" static int nocompress; static int noresume; static int nohibernate; static int resume_wait; static unsigned int resume_delay; static char resume_file[256] = CONFIG_PM_STD_PARTITION; dev_t swsusp_resume_device; sector_t swsusp_resume_block; __visible int in_suspend __nosavedata; static char hibernate_compressor[CRYPTO_MAX_ALG_NAME] = CONFIG_HIBERNATION_DEF_COMP; /* * Compression/decompression algorithm to be used while saving/loading * image to/from disk. This would later be used in 'kernel/power/swap.c' * to allocate comp streams. */ char hib_comp_algo[CRYPTO_MAX_ALG_NAME]; enum { HIBERNATION_INVALID, HIBERNATION_PLATFORM, HIBERNATION_SHUTDOWN, HIBERNATION_REBOOT, #ifdef CONFIG_SUSPEND HIBERNATION_SUSPEND, #endif HIBERNATION_TEST_RESUME, /* keep last */ __HIBERNATION_AFTER_LAST }; #define HIBERNATION_MAX (__HIBERNATION_AFTER_LAST-1) #define HIBERNATION_FIRST (HIBERNATION_INVALID + 1) static int hibernation_mode = HIBERNATION_SHUTDOWN; bool freezer_test_done; static const struct platform_hibernation_ops *hibernation_ops; static atomic_t hibernate_atomic = ATOMIC_INIT(1); #ifdef CONFIG_SUSPEND /** * pm_hibernation_mode_is_suspend - Check if hibernation has been set to suspend */ bool pm_hibernation_mode_is_suspend(void) { return hibernation_mode == HIBERNATION_SUSPEND; } EXPORT_SYMBOL_GPL(pm_hibernation_mode_is_suspend); #endif bool hibernate_acquire(void) { return atomic_add_unless(&hibernate_atomic, -1, 0); } void hibernate_release(void) { atomic_inc(&hibernate_atomic); } bool hibernation_in_progress(void) { return !atomic_read(&hibernate_atomic); } bool hibernation_available(void) { return nohibernate == 0 && !security_locked_down(LOCKDOWN_HIBERNATION) && !secretmem_active() && !cxl_mem_active(); } /** * hibernation_set_ops - Set the global hibernate operations. * @ops: Hibernation operations to use in subsequent hibernation transitions. */ void hibernation_set_ops(const struct platform_hibernation_ops *ops) { unsigned int sleep_flags; if (ops && !(ops->begin && ops->end && ops->pre_snapshot && ops->prepare && ops->finish && ops->enter && ops->pre_restore && ops->restore_cleanup && ops->leave)) { WARN_ON(1); return; } sleep_flags = lock_system_sleep(); hibernation_ops = ops; if (ops) hibernation_mode = HIBERNATION_PLATFORM; else if (hibernation_mode == HIBERNATION_PLATFORM) hibernation_mode = HIBERNATION_SHUTDOWN; unlock_system_sleep(sleep_flags); } EXPORT_SYMBOL_GPL(hibernation_set_ops); static bool entering_platform_hibernation; bool system_entering_hibernation(void) { return entering_platform_hibernation; } EXPORT_SYMBOL(system_entering_hibernation); #ifdef CONFIG_PM_DEBUG static unsigned int pm_test_delay = 5; module_param(pm_test_delay, uint, 0644); MODULE_PARM_DESC(pm_test_delay, "Number of seconds to wait before resuming from hibernation test"); static void hibernation_debug_sleep(void) { pr_info("hibernation debug: Waiting for %d second(s).\n", pm_test_delay); mdelay(pm_test_delay * 1000); } static int hibernation_test(int level) { if (pm_test_level == level) { hibernation_debug_sleep(); return 1; } return 0; } #else /* !CONFIG_PM_DEBUG */ static int hibernation_test(int level) { return 0; } #endif /* !CONFIG_PM_DEBUG */ /** * platform_begin - Call platform to start hibernation. * @platform_mode: Whether or not to use the platform driver. */ static int platform_begin(int platform_mode) { return (platform_mode && hibernation_ops) ? hibernation_ops->begin(PMSG_FREEZE) : 0; } /** * platform_end - Call platform to finish transition to the working state. * @platform_mode: Whether or not to use the platform driver. */ static void platform_end(int platform_mode) { if (platform_mode && hibernation_ops) hibernation_ops->end(); } /** * platform_pre_snapshot - Call platform to prepare the machine for hibernation. * @platform_mode: Whether or not to use the platform driver. * * Use the platform driver to prepare the system for creating a hibernate image, * if so configured, and return an error code if that fails. */ static int platform_pre_snapshot(int platform_mode) { return (platform_mode && hibernation_ops) ? hibernation_ops->pre_snapshot() : 0; } /** * platform_leave - Call platform to prepare a transition to the working state. * @platform_mode: Whether or not to use the platform driver. * * Use the platform driver prepare to prepare the machine for switching to the * normal mode of operation. * * This routine is called on one CPU with interrupts disabled. */ static void platform_leave(int platform_mode) { if (platform_mode && hibernation_ops) hibernation_ops->leave(); } /** * platform_finish - Call platform to switch the system to the working state. * @platform_mode: Whether or not to use the platform driver. * * Use the platform driver to switch the machine to the normal mode of * operation. * * This routine must be called after platform_prepare(). */ static void platform_finish(int platform_mode) { if (platform_mode && hibernation_ops) hibernation_ops->finish(); } /** * platform_pre_restore - Prepare for hibernate image restoration. * @platform_mode: Whether or not to use the platform driver. * * Use the platform driver to prepare the system for resume from a hibernation * image. * * If the restore fails after this function has been called, * platform_restore_cleanup() must be called. */ static int platform_pre_restore(int platform_mode) { return (platform_mode && hibernation_ops) ? hibernation_ops->pre_restore() : 0; } /** * platform_restore_cleanup - Switch to the working state after failing restore. * @platform_mode: Whether or not to use the platform driver. * * Use the platform driver to switch the system to the normal mode of operation * after a failing restore. * * If platform_pre_restore() has been called before the failing restore, this * function must be called too, regardless of the result of * platform_pre_restore(). */ static void platform_restore_cleanup(int platform_mode) { if (platform_mode && hibernation_ops) hibernation_ops->restore_cleanup(); } /** * platform_recover - Recover from a failure to suspend devices. * @platform_mode: Whether or not to use the platform driver. */ static void platform_recover(int platform_mode) { if (platform_mode && hibernation_ops && hibernation_ops->recover) hibernation_ops->recover(); } /** * swsusp_show_speed - Print time elapsed between two events during hibernation. * @start: Starting event. * @stop: Final event. * @nr_pages: Number of memory pages processed between @start and @stop. * @msg: Additional diagnostic message to print. */ void swsusp_show_speed(ktime_t start, ktime_t stop, unsigned nr_pages, char *msg) { ktime_t diff; u64 elapsed_centisecs64; unsigned int centisecs; unsigned int k; unsigned int kps; diff = ktime_sub(stop, start); elapsed_centisecs64 = ktime_divns(diff, 10*NSEC_PER_MSEC); centisecs = elapsed_centisecs64; if (centisecs == 0) centisecs = 1; /* avoid div-by-zero */ k = nr_pages * (PAGE_SIZE / 1024); kps = (k * 100) / centisecs; pr_info("%s %u kbytes in %u.%02u seconds (%u.%02u MB/s)\n", msg, k, centisecs / 100, centisecs % 100, kps / 1000, (kps % 1000) / 10); } __weak int arch_resume_nosmt(void) { return 0; } /** * create_image - Create a hibernation image. * @platform_mode: Whether or not to use the platform driver. * * Execute device drivers' "late" and "noirq" freeze callbacks, create a * hibernation image and run the drivers' "noirq" and "early" thaw callbacks. * * Control reappears in this routine after the subsequent restore. */ static int create_image(int platform_mode) { int error; error = dpm_suspend_end(PMSG_FREEZE); if (error) { pr_err("Some devices failed to power down, aborting\n"); return error; } error = platform_pre_snapshot(platform_mode); if (error || hibernation_test(TEST_PLATFORM)) goto Platform_finish; error = pm_sleep_disable_secondary_cpus(); if (error || hibernation_test(TEST_CPUS)) goto Enable_cpus; local_irq_disable(); system_state = SYSTEM_SUSPEND; error = syscore_suspend(); if (error) { pr_err("Some system devices failed to power down, aborting\n"); goto Enable_irqs; } if (hibernation_test(TEST_CORE) || pm_wakeup_pending()) goto Power_up; in_suspend = 1; save_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true); error = swsusp_arch_suspend(); /* Restore control flow magically appears here */ restore_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false); if (error) pr_err("Error %d creating image\n", error); if (!in_suspend) { events_check_enabled = false; clear_or_poison_free_pages(); } platform_leave(platform_mode); Power_up: syscore_resume(); Enable_irqs: system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: pm_sleep_enable_secondary_cpus(); /* Allow architectures to do nosmt-specific post-resume dances */ if (!in_suspend) error = arch_resume_nosmt(); Platform_finish: platform_finish(platform_mode); dpm_resume_start(in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); return error; } /** * hibernation_snapshot - Quiesce devices and create a hibernation image. * @platform_mode: If set, use platform driver to prepare for the transition. * * This routine must be called with system_transition_mutex held. */ int hibernation_snapshot(int platform_mode) { pm_message_t msg; int error; pm_suspend_clear_flags(); error = platform_begin(platform_mode); if (error) goto Close; error = freeze_kernel_threads(); if (error) goto Close; if (hibernation_test(TEST_FREEZER)) { /* * Indicate to the caller that we are returning due to a * successful freezer test. */ freezer_test_done = true; goto Thaw; } error = dpm_prepare(PMSG_FREEZE); if (error) goto Complete; /* Preallocate image memory before shutting down devices. */ error = hibernate_preallocate_memory(); if (error) goto Complete; console_suspend_all(); pm_restrict_gfp_mask(); error = dpm_suspend(PMSG_FREEZE); if (error || hibernation_test(TEST_DEVICES)) platform_recover(platform_mode); else error = create_image(platform_mode); /* * In the case that we call create_image() above, the control * returns here (1) after the image has been created or the * image creation has failed and (2) after a successful restore. */ /* We may need to release the preallocated image pages here. */ if (error || !in_suspend) swsusp_free(); msg = in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE; dpm_resume(msg); if (error || !in_suspend) pm_restore_gfp_mask(); console_resume_all(); dpm_complete(msg); Close: platform_end(platform_mode); return error; Complete: dpm_complete(PMSG_RECOVER); Thaw: thaw_kernel_threads(); goto Close; } int __weak hibernate_resume_nonboot_cpu_disable(void) { return suspend_disable_secondary_cpus(); } /** * resume_target_kernel - Restore system state from a hibernation image. * @platform_mode: Whether or not to use the platform driver. * * Execute device drivers' "noirq" and "late" freeze callbacks, restore the * contents of highmem that have not been restored yet from the image and run * the low-level code that will restore the remaining contents of memory and * switch to the just restored target kernel. */ static int resume_target_kernel(bool platform_mode) { int error; error = dpm_suspend_end(PMSG_QUIESCE); if (error) { pr_err("Some devices failed to power down, aborting resume\n"); return error; } error = platform_pre_restore(platform_mode); if (error) goto Cleanup; cpuidle_pause(); error = hibernate_resume_nonboot_cpu_disable(); if (error) goto Enable_cpus; local_irq_disable(); system_state = SYSTEM_SUSPEND; error = syscore_suspend(); if (error) goto Enable_irqs; save_processor_state(); error = restore_highmem(); if (!error) { error = swsusp_arch_resume(); /* * The code below is only ever reached in case of a failure. * Otherwise, execution continues at the place where * swsusp_arch_suspend() was called. */ BUG_ON(!error); /* * This call to restore_highmem() reverts the changes made by * the previous one. */ restore_highmem(); } /* * The only reason why swsusp_arch_resume() can fail is memory being * very tight, so we have to free it as soon as we can to avoid * subsequent failures. */ swsusp_free(); restore_processor_state(); touch_softlockup_watchdog(); syscore_resume(); Enable_irqs: system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: pm_sleep_enable_secondary_cpus(); Cleanup: platform_restore_cleanup(platform_mode); dpm_resume_start(PMSG_RECOVER); return error; } /** * hibernation_restore - Quiesce devices and restore from a hibernation image. * @platform_mode: If set, use platform driver to prepare for the transition. * * This routine must be called with system_transition_mutex held. If it is * successful, control reappears in the restored target kernel in * hibernation_snapshot(). */ int hibernation_restore(int platform_mode) { int error; pm_prepare_console(); console_suspend_all(); error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { error = resume_target_kernel(platform_mode); /* * The above should either succeed and jump to the new kernel, * or return with an error. Otherwise things are just * undefined, so let's be paranoid. */ BUG_ON(!error); } dpm_resume_end(PMSG_RECOVER); console_resume_all(); pm_restore_console(); return error; } /** * hibernation_platform_enter - Power off the system using the platform driver. */ int hibernation_platform_enter(void) { int error; if (!hibernation_ops) return -ENOSYS; /* * We have cancelled the power transition by running * hibernation_ops->finish() before saving the image, so we should let * the firmware know that we're going to enter the sleep state after all */ error = hibernation_ops->begin(PMSG_HIBERNATE); if (error) goto Close; entering_platform_hibernation = true; console_suspend_all(); error = dpm_suspend_start(PMSG_HIBERNATE); if (error) { if (hibernation_ops->recover) hibernation_ops->recover(); goto Resume_devices; } error = dpm_suspend_end(PMSG_HIBERNATE); if (error) goto Resume_devices; error = hibernation_ops->prepare(); if (error) goto Platform_finish; error = pm_sleep_disable_secondary_cpus(); if (error) goto Enable_cpus; local_irq_disable(); system_state = SYSTEM_SUSPEND; error = syscore_suspend(); if (error) goto Enable_irqs; if (pm_wakeup_pending()) { error = -EAGAIN; goto Power_up; } hibernation_ops->enter(); /* We should never get here */ while (1); Power_up: syscore_resume(); Enable_irqs: system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: pm_sleep_enable_secondary_cpus(); Platform_finish: hibernation_ops->finish(); dpm_resume_start(PMSG_RESTORE); Resume_devices: entering_platform_hibernation = false; dpm_resume_end(PMSG_RESTORE); console_resume_all(); Close: hibernation_ops->end(); return error; } /** * power_down - Shut the machine down for hibernation. * * Use the platform driver, if configured, to put the system into the sleep * state corresponding to hibernation, or try to power it off or reboot, * depending on the value of hibernation_mode. */ static void power_down(void) { int error; #ifdef CONFIG_SUSPEND if (hibernation_mode == HIBERNATION_SUSPEND) { error = suspend_devices_and_enter(mem_sleep_current); if (!error) goto exit; hibernation_mode = hibernation_ops ? HIBERNATION_PLATFORM : HIBERNATION_SHUTDOWN; } #endif switch (hibernation_mode) { case HIBERNATION_REBOOT: kernel_restart(NULL); break; case HIBERNATION_PLATFORM: error = hibernation_platform_enter(); if (error == -EAGAIN || error == -EBUSY) { events_check_enabled = false; pr_info("Wakeup event detected during hibernation, rolling back.\n"); goto exit; } fallthrough; case HIBERNATION_SHUTDOWN: if (kernel_can_power_off()) { entering_platform_hibernation = true; kernel_power_off(); entering_platform_hibernation = false; } break; } kernel_halt(); /* * Valid image is on the disk, if we continue we risk serious data * corruption after resume. */ pr_crit("Power down manually\n"); while (1) cpu_relax(); exit: /* Restore swap signature. */ error = swsusp_unmark(); if (error) pr_err("Swap will be unusable! Try swapon -a.\n"); } static int load_image_and_restore(void) { int error; unsigned int flags; pm_pr_dbg("Loading hibernation image.\n"); lock_device_hotplug(); error = create_basic_memory_bitmaps(); if (error) { swsusp_close(); goto Unlock; } error = swsusp_read(&flags); swsusp_close(); if (!error) error = hibernation_restore(flags & SF_PLATFORM_MODE); pr_err("Failed to load image, recovering.\n"); swsusp_free(); free_basic_memory_bitmaps(); Unlock: unlock_device_hotplug(); return error; } #define COMPRESSION_ALGO_LZO "lzo" #define COMPRESSION_ALGO_LZ4 "lz4" /** * hibernate - Carry out system hibernation, including saving the image. */ int hibernate(void) { bool snapshot_test = false; unsigned int sleep_flags; int error; if (!hibernation_available()) { pm_pr_dbg("Hibernation not available.\n"); return -EPERM; } /* * Query for the compression algorithm support if compression is enabled. */ if (!nocompress) { strscpy(hib_comp_algo, hibernate_compressor); if (!crypto_has_acomp(hib_comp_algo, 0, CRYPTO_ALG_ASYNC)) { pr_err("%s compression is not available\n", hib_comp_algo); return -EOPNOTSUPP; } } sleep_flags = lock_system_sleep(); /* The snapshot device should not be opened while we're running */ if (!hibernate_acquire()) { error = -EBUSY; goto Unlock; } pr_info("hibernation entry\n"); pm_prepare_console(); error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION); if (error) goto Restore; error = pm_sleep_fs_sync(); if (error) goto Notify; filesystems_freeze(filesystem_freeze_enabled); error = freeze_processes(); if (error) goto Exit; lock_device_hotplug(); /* Allocate memory management structures */ error = create_basic_memory_bitmaps(); if (error) goto Thaw; error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM); if (error || freezer_test_done) goto Free_bitmaps; if (in_suspend) { unsigned int flags = 0; if (hibernation_mode == HIBERNATION_PLATFORM) flags |= SF_PLATFORM_MODE; if (nocompress) { flags |= SF_NOCOMPRESS_MODE; } else { flags |= SF_CRC32_MODE; /* * By default, LZO compression is enabled. Use SF_COMPRESSION_ALG_LZ4 * to override this behaviour and use LZ4. * * Refer kernel/power/power.h for more details */ if (!strcmp(hib_comp_algo, COMPRESSION_ALGO_LZ4)) flags |= SF_COMPRESSION_ALG_LZ4; else flags |= SF_COMPRESSION_ALG_LZO; } pm_pr_dbg("Writing hibernation image.\n"); error = swsusp_write(flags); swsusp_free(); if (!error) { if (hibernation_mode == HIBERNATION_TEST_RESUME) snapshot_test = true; else power_down(); } in_suspend = 0; pm_restore_gfp_mask(); } else { pm_pr_dbg("Hibernation image restored successfully.\n"); } Free_bitmaps: free_basic_memory_bitmaps(); Thaw: unlock_device_hotplug(); if (snapshot_test) { pm_pr_dbg("Checking hibernation image\n"); error = swsusp_check(false); if (!error) error = load_image_and_restore(); } thaw_processes(); /* Don't bother checking whether freezer_test_done is true */ freezer_test_done = false; Exit: filesystems_thaw(); Notify: pm_notifier_call_chain(PM_POST_HIBERNATION); Restore: pm_restore_console(); hibernate_release(); Unlock: unlock_system_sleep(sleep_flags); pr_info("hibernation exit\n"); return error; } /** * hibernate_quiet_exec - Execute a function with all devices frozen. * @func: Function to execute. * @data: Data pointer to pass to @func. * * Return the @func return value or an error code if it cannot be executed. */ int hibernate_quiet_exec(int (*func)(void *data), void *data) { unsigned int sleep_flags; int error; sleep_flags = lock_system_sleep(); if (!hibernate_acquire()) { error = -EBUSY; goto unlock; } pm_prepare_console(); error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION); if (error) goto restore; filesystems_freeze(filesystem_freeze_enabled); error = freeze_processes(); if (error) goto exit; lock_device_hotplug(); pm_suspend_clear_flags(); error = platform_begin(true); if (error) goto thaw; error = freeze_kernel_threads(); if (error) goto thaw; error = dpm_prepare(PMSG_FREEZE); if (error) goto dpm_complete; console_suspend_all(); error = dpm_suspend(PMSG_FREEZE); if (error) goto dpm_resume; error = dpm_suspend_end(PMSG_FREEZE); if (error) goto dpm_resume; error = platform_pre_snapshot(true); if (error) goto skip; error = func(data); skip: platform_finish(true); dpm_resume_start(PMSG_THAW); dpm_resume: dpm_resume(PMSG_THAW); console_resume_all(); dpm_complete: dpm_complete(PMSG_THAW); thaw_kernel_threads(); thaw: platform_end(true); unlock_device_hotplug(); thaw_processes(); exit: filesystems_thaw(); pm_notifier_call_chain(PM_POST_HIBERNATION); restore: pm_restore_console(); hibernate_release(); unlock: unlock_system_sleep(sleep_flags); return error; } EXPORT_SYMBOL_GPL(hibernate_quiet_exec); static int __init find_resume_device(void) { if (!strlen(resume_file)) return -ENOENT; pm_pr_dbg("Checking hibernation image partition %s\n", resume_file); if (resume_delay) { pr_info("Waiting %dsec before reading resume device ...\n", resume_delay); ssleep(resume_delay); } /* Check if the device is there */ if (!early_lookup_bdev(resume_file, &swsusp_resume_device)) return 0; /* * Some device discovery might still be in progress; we need to wait for * this to finish. */ wait_for_device_probe(); if (resume_wait) { while (early_lookup_bdev(resume_file, &swsusp_resume_device)) msleep(10); async_synchronize_full(); } return early_lookup_bdev(resume_file, &swsusp_resume_device); } static int software_resume(void) { int error; pm_pr_dbg("Hibernation image partition %d:%d present\n", MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device)); pm_pr_dbg("Looking for hibernation image.\n"); mutex_lock(&system_transition_mutex); error = swsusp_check(true); if (error) goto Unlock; /* * Check if the hibernation image is compressed. If so, query for * the algorithm support. */ if (!(swsusp_header_flags & SF_NOCOMPRESS_MODE)) { if (swsusp_header_flags & SF_COMPRESSION_ALG_LZ4) strscpy(hib_comp_algo, COMPRESSION_ALGO_LZ4); else strscpy(hib_comp_algo, COMPRESSION_ALGO_LZO); if (!crypto_has_acomp(hib_comp_algo, 0, CRYPTO_ALG_ASYNC)) { pr_err("%s compression is not available\n", hib_comp_algo); error = -EOPNOTSUPP; goto Unlock; } } /* The snapshot device should not be opened while we're running */ if (!hibernate_acquire()) { error = -EBUSY; swsusp_close(); goto Unlock; } pr_info("resume from hibernation\n"); pm_prepare_console(); error = pm_notifier_call_chain_robust(PM_RESTORE_PREPARE, PM_POST_RESTORE); if (error) goto Restore; filesystems_freeze(filesystem_freeze_enabled); pm_pr_dbg("Preparing processes for hibernation restore.\n"); error = freeze_processes(); if (error) { filesystems_thaw(); goto Close_Finish; } error = freeze_kernel_threads(); if (error) { thaw_processes(); filesystems_thaw(); goto Close_Finish; } error = load_image_and_restore(); thaw_processes(); filesystems_thaw(); Finish: pm_notifier_call_chain(PM_POST_RESTORE); Restore: pm_restore_console(); pr_info("resume failed (%d)\n", error); hibernate_release(); /* For success case, the suspend path will release the lock */ Unlock: mutex_unlock(&system_transition_mutex); pm_pr_dbg("Hibernation image not present or could not be loaded.\n"); return error; Close_Finish: swsusp_close(); goto Finish; } /** * software_resume_initcall - Resume from a saved hibernation image. * * This routine is called as a late initcall, when all devices have been * discovered and initialized already. * * The image reading code is called to see if there is a hibernation image * available for reading. If that is the case, devices are quiesced and the * contents of memory is restored from the saved image. * * If this is successful, control reappears in the restored target kernel in * hibernation_snapshot() which returns to hibernate(). Otherwise, the routine * attempts to recover gracefully and make the kernel return to the normal mode * of operation. */ static int __init software_resume_initcall(void) { /* * If the user said "noresume".. bail out early. */ if (noresume || !hibernation_available()) return 0; if (!swsusp_resume_device) { int error = find_resume_device(); if (error) return error; } return software_resume(); } late_initcall_sync(software_resume_initcall); static const char * const hibernation_modes[] = { [HIBERNATION_PLATFORM] = "platform", [HIBERNATION_SHUTDOWN] = "shutdown", [HIBERNATION_REBOOT] = "reboot", #ifdef CONFIG_SUSPEND [HIBERNATION_SUSPEND] = "suspend", #endif [HIBERNATION_TEST_RESUME] = "test_resume", }; /* * /sys/power/disk - Control hibernation mode. * * Hibernation can be handled in several ways. There are a few different ways * to put the system into the sleep state: using the platform driver (e.g. ACPI * or other hibernation_ops), powering it off or rebooting it (for testing * mostly). * * The sysfs file /sys/power/disk provides an interface for selecting the * hibernation mode to use. Reading from this file causes the available modes * to be printed. There are 3 modes that can be supported: * * 'platform' * 'shutdown' * 'reboot' * * If a platform hibernation driver is in use, 'platform' will be supported * and will be used by default. Otherwise, 'shutdown' will be used by default. * The selected option (i.e. the one corresponding to the current value of * hibernation_mode) is enclosed by a square bracket. * * To select a given hibernation mode it is necessary to write the mode's * string representation (as returned by reading from /sys/power/disk) back * into /sys/power/disk. */ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { ssize_t count = 0; int i; if (!hibernation_available()) return sysfs_emit(buf, "[disabled]\n"); for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) { if (!hibernation_modes[i]) continue; switch (i) { case HIBERNATION_SHUTDOWN: case HIBERNATION_REBOOT: #ifdef CONFIG_SUSPEND case HIBERNATION_SUSPEND: #endif case HIBERNATION_TEST_RESUME: break; case HIBERNATION_PLATFORM: if (hibernation_ops) break; /* not a valid mode, continue with loop */ continue; } if (i == hibernation_mode) count += sysfs_emit_at(buf, count, "[%s] ", hibernation_modes[i]); else count += sysfs_emit_at(buf, count, "%s ", hibernation_modes[i]); } /* Convert the last space to a newline if needed. */ if (count > 0) buf[count - 1] = '\n'; return count; } static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t n) { int mode = HIBERNATION_INVALID; unsigned int sleep_flags; int error = 0; int len; char *p; int i; if (!hibernation_available()) return -EPERM; p = memchr(buf, '\n', n); len = p ? p - buf : n; sleep_flags = lock_system_sleep(); for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) { if (len == strlen(hibernation_modes[i]) && !strncmp(buf, hibernation_modes[i], len)) { mode = i; break; } } if (mode != HIBERNATION_INVALID) { switch (mode) { case HIBERNATION_SHUTDOWN: case HIBERNATION_REBOOT: #ifdef CONFIG_SUSPEND case HIBERNATION_SUSPEND: #endif case HIBERNATION_TEST_RESUME: hibernation_mode = mode; break; case HIBERNATION_PLATFORM: if (hibernation_ops) hibernation_mode = mode; else error = -EINVAL; } } else error = -EINVAL; if (!error) pm_pr_dbg("Hibernation mode set to '%s'\n", hibernation_modes[mode]); unlock_system_sleep(sleep_flags); return error ? error : n; } power_attr(disk); static ssize_t resume_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%d:%d\n", MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device)); } static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t n) { unsigned int sleep_flags; int len = n; char *name; dev_t dev; int error; if (!hibernation_available()) return n; if (len && buf[len-1] == '\n') len--; name = kstrndup(buf, len, GFP_KERNEL); if (!name) return -ENOMEM; error = lookup_bdev(name, &dev); if (error) { unsigned maj, min, offset; char *p, dummy; error = 0; if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 || sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, &dummy) == 3) { dev = MKDEV(maj, min); if (maj != MAJOR(dev) || min != MINOR(dev)) error = -EINVAL; } else { dev = new_decode_dev(simple_strtoul(name, &p, 16)); if (*p) error = -EINVAL; } } kfree(name); if (error) return error; sleep_flags = lock_system_sleep(); swsusp_resume_device = dev; unlock_system_sleep(sleep_flags); pm_pr_dbg("Configured hibernation resume from disk to %u\n", swsusp_resume_device); noresume = 0; software_resume(); return n; } power_attr(resume); static ssize_t resume_offset_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)swsusp_resume_block); } static ssize_t resume_offset_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t n) { unsigned long long offset; int rc; rc = kstrtoull(buf, 0, &offset); if (rc) return rc; swsusp_resume_block = offset; return n; } power_attr(resume_offset); static ssize_t image_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", image_size); } static ssize_t image_size_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t n) { unsigned long size; if (sscanf(buf, "%lu", &size) == 1) { image_size = size; return n; } return -EINVAL; } power_attr(image_size); static ssize_t reserved_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", reserved_size); } static ssize_t reserved_size_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t n) { unsigned long size; if (sscanf(buf, "%lu", &size) == 1) { reserved_size = size; return n; } return -EINVAL; } power_attr(reserved_size); static struct attribute *g[] = { &disk_attr.attr, &resume_offset_attr.attr, &resume_attr.attr, &image_size_attr.attr, &reserved_size_attr.attr, NULL, }; static const struct attribute_group attr_group = { .attrs = g, }; static int __init pm_disk_init(void) { return sysfs_create_group(power_kobj, &attr_group); } core_initcall(pm_disk_init); static int __init resume_setup(char *str) { if (noresume) return 1; strscpy(resume_file, str); return 1; } static int __init resume_offset_setup(char *str) { unsigned long long offset; if (noresume) return 1; if (sscanf(str, "%llu", &offset) == 1) swsusp_resume_block = offset; return 1; } static int __init hibernate_setup(char *str) { if (!strncmp(str, "noresume", 8)) { noresume = 1; } else if (!strncmp(str, "nocompress", 10)) { nocompress = 1; } else if (!strncmp(str, "no", 2)) { noresume = 1; nohibernate = 1; } else if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) && !strncmp(str, "protect_image", 13)) { enable_restore_image_protection(); } return 1; } static int __init noresume_setup(char *str) { noresume = 1; return 1; } static int __init resumewait_setup(char *str) { resume_wait = 1; return 1; } static int __init resumedelay_setup(char *str) { int rc = kstrtouint(str, 0, &resume_delay); if (rc) pr_warn("resumedelay: bad option string '%s'\n", str); return 1; } static int __init nohibernate_setup(char *str) { noresume = 1; nohibernate = 1; return 1; } static const char * const comp_alg_enabled[] = { #if IS_ENABLED(CONFIG_CRYPTO_LZO) COMPRESSION_ALGO_LZO, #endif #if IS_ENABLED(CONFIG_CRYPTO_LZ4) COMPRESSION_ALGO_LZ4, #endif }; static int hibernate_compressor_param_set(const char *compressor, const struct kernel_param *kp) { int index, ret; if (!mutex_trylock(&system_transition_mutex)) return -EBUSY; index = sysfs_match_string(comp_alg_enabled, compressor); if (index >= 0) { ret = param_set_copystring(comp_alg_enabled[index], kp); if (!ret) strscpy(hib_comp_algo, comp_alg_enabled[index]); } else { ret = index; } mutex_unlock(&system_transition_mutex); if (ret) pr_debug("Cannot set specified compressor %s\n", compressor); return ret; } static const struct kernel_param_ops hibernate_compressor_param_ops = { .set = hibernate_compressor_param_set, .get = param_get_string, }; static struct kparam_string hibernate_compressor_param_string = { .maxlen = sizeof(hibernate_compressor), .string = hibernate_compressor, }; module_param_cb(compressor, &hibernate_compressor_param_ops, &hibernate_compressor_param_string, 0644); MODULE_PARM_DESC(compressor, "Compression algorithm to be used with hibernation"); __setup("noresume", noresume_setup); __setup("resume_offset=", resume_offset_setup); __setup("resume=", resume_setup); __setup("hibernate=", hibernate_setup); __setup("resumewait", resumewait_setup); __setup("resumedelay=", resumedelay_setup); __setup("nohibernate", nohibernate_setup); |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * vimc-capture.c Virtual Media Controller Driver * * Copyright (C) 2015-2017 Helen Koike <helen.fornazier@gmail.com> */ #include <media/v4l2-ioctl.h> #include <media/videobuf2-core.h> #include <media/videobuf2-dma-contig.h> #include <media/videobuf2-vmalloc.h> #include "vimc-common.h" #include "vimc-streamer.h" struct vimc_capture_device { struct vimc_ent_device ved; struct video_device vdev; struct v4l2_pix_format format; struct vb2_queue queue; struct list_head buf_list; /* * NOTE: in a real driver, a spin lock must be used to access the * queue because the frames are generated from a hardware interruption * and the isr is not allowed to sleep. * Even if it is not necessary a spinlock in the vimc driver, we * use it here as a code reference */ spinlock_t qlock; struct mutex lock; u32 sequence; struct vimc_stream stream; struct media_pad pad; }; static const struct v4l2_pix_format fmt_default = { .width = 640, .height = 480, .pixelformat = V4L2_PIX_FMT_RGB24, .field = V4L2_FIELD_NONE, .colorspace = V4L2_COLORSPACE_SRGB, }; struct vimc_capture_buffer { /* * struct vb2_v4l2_buffer must be the first element * the videobuf2 framework will allocate this struct based on * buf_struct_size and use the first sizeof(struct vb2_buffer) bytes of * memory as a vb2_buffer */ struct vb2_v4l2_buffer vb2; struct list_head list; }; static int vimc_capture_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { strscpy(cap->driver, VIMC_PDEV_NAME, sizeof(cap->driver)); strscpy(cap->card, KBUILD_MODNAME, sizeof(cap->card)); return 0; } static void vimc_capture_get_format(struct vimc_ent_device *ved, struct v4l2_pix_format *fmt) { struct vimc_capture_device *vcapture = container_of(ved, struct vimc_capture_device, ved); *fmt = vcapture->format; } static int vimc_capture_g_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { struct vimc_capture_device *vcapture = video_drvdata(file); f->fmt.pix = vcapture->format; return 0; } static int vimc_capture_try_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { struct v4l2_pix_format *format = &f->fmt.pix; const struct vimc_pix_map *vpix; format->width = clamp_t(u32, format->width, VIMC_FRAME_MIN_WIDTH, VIMC_FRAME_MAX_WIDTH) & ~1; format->height = clamp_t(u32, format->height, VIMC_FRAME_MIN_HEIGHT, VIMC_FRAME_MAX_HEIGHT) & ~1; /* Don't accept a pixelformat that is not on the table */ vpix = vimc_pix_map_by_pixelformat(format->pixelformat); if (!vpix) { format->pixelformat = fmt_default.pixelformat; vpix = vimc_pix_map_by_pixelformat(format->pixelformat); } /* TODO: Add support for custom bytesperline values */ format->bytesperline = format->width * vpix->bpp; format->sizeimage = format->bytesperline * format->height; if (format->field == V4L2_FIELD_ANY) format->field = fmt_default.field; vimc_colorimetry_clamp(format); if (format->colorspace == V4L2_COLORSPACE_DEFAULT) format->colorspace = fmt_default.colorspace; return 0; } static int vimc_capture_s_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { struct vimc_capture_device *vcapture = video_drvdata(file); int ret; /* Do not change the format while stream is on */ if (vb2_is_busy(&vcapture->queue)) return -EBUSY; ret = vimc_capture_try_fmt_vid_cap(file, priv, f); if (ret) return ret; dev_dbg(vcapture->ved.dev, "%s: format update: " "old:%dx%d (0x%x, %d, %d, %d, %d) " "new:%dx%d (0x%x, %d, %d, %d, %d)\n", vcapture->vdev.name, /* old */ vcapture->format.width, vcapture->format.height, vcapture->format.pixelformat, vcapture->format.colorspace, vcapture->format.quantization, vcapture->format.xfer_func, vcapture->format.ycbcr_enc, /* new */ f->fmt.pix.width, f->fmt.pix.height, f->fmt.pix.pixelformat, f->fmt.pix.colorspace, f->fmt.pix.quantization, f->fmt.pix.xfer_func, f->fmt.pix.ycbcr_enc); vcapture->format = f->fmt.pix; return 0; } static int vimc_capture_enum_fmt_vid_cap(struct file *file, void *priv, struct v4l2_fmtdesc *f) { const struct vimc_pix_map *vpix; if (f->mbus_code) { if (f->index > 0) return -EINVAL; vpix = vimc_pix_map_by_code(f->mbus_code); } else { vpix = vimc_pix_map_by_index(f->index); } if (!vpix) return -EINVAL; f->pixelformat = vpix->pixelformat; return 0; } static int vimc_capture_enum_framesizes(struct file *file, void *priv, struct v4l2_frmsizeenum *fsize) { const struct vimc_pix_map *vpix; if (fsize->index) return -EINVAL; /* Only accept code in the pix map table */ vpix = vimc_pix_map_by_code(fsize->pixel_format); if (!vpix) return -EINVAL; fsize->type = V4L2_FRMSIZE_TYPE_CONTINUOUS; fsize->stepwise.min_width = VIMC_FRAME_MIN_WIDTH; fsize->stepwise.max_width = VIMC_FRAME_MAX_WIDTH; fsize->stepwise.min_height = VIMC_FRAME_MIN_HEIGHT; fsize->stepwise.max_height = VIMC_FRAME_MAX_HEIGHT; fsize->stepwise.step_width = 1; fsize->stepwise.step_height = 1; return 0; } static const struct v4l2_file_operations vimc_capture_fops = { .owner = THIS_MODULE, .open = v4l2_fh_open, .release = vb2_fop_release, .read = vb2_fop_read, .poll = vb2_fop_poll, .unlocked_ioctl = video_ioctl2, .mmap = vb2_fop_mmap, }; static const struct v4l2_ioctl_ops vimc_capture_ioctl_ops = { .vidioc_querycap = vimc_capture_querycap, .vidioc_g_fmt_vid_cap = vimc_capture_g_fmt_vid_cap, .vidioc_s_fmt_vid_cap = vimc_capture_s_fmt_vid_cap, .vidioc_try_fmt_vid_cap = vimc_capture_try_fmt_vid_cap, .vidioc_enum_fmt_vid_cap = vimc_capture_enum_fmt_vid_cap, .vidioc_enum_framesizes = vimc_capture_enum_framesizes, .vidioc_reqbufs = vb2_ioctl_reqbufs, .vidioc_create_bufs = vb2_ioctl_create_bufs, .vidioc_prepare_buf = vb2_ioctl_prepare_buf, .vidioc_querybuf = vb2_ioctl_querybuf, .vidioc_qbuf = vb2_ioctl_qbuf, .vidioc_dqbuf = vb2_ioctl_dqbuf, .vidioc_expbuf = vb2_ioctl_expbuf, .vidioc_streamon = vb2_ioctl_streamon, .vidioc_streamoff = vb2_ioctl_streamoff, .vidioc_remove_bufs = vb2_ioctl_remove_bufs, }; static void vimc_capture_return_all_buffers(struct vimc_capture_device *vcapture, enum vb2_buffer_state state) { struct vimc_capture_buffer *vbuf, *node; spin_lock(&vcapture->qlock); list_for_each_entry_safe(vbuf, node, &vcapture->buf_list, list) { list_del(&vbuf->list); vb2_buffer_done(&vbuf->vb2.vb2_buf, state); } spin_unlock(&vcapture->qlock); } static int vimc_capture_start_streaming(struct vb2_queue *vq, unsigned int count) { struct vimc_capture_device *vcapture = vb2_get_drv_priv(vq); int ret; vcapture->sequence = 0; /* Start the media pipeline */ ret = video_device_pipeline_start(&vcapture->vdev, &vcapture->stream.pipe); if (ret) { vimc_capture_return_all_buffers(vcapture, VB2_BUF_STATE_QUEUED); return ret; } ret = vimc_streamer_s_stream(&vcapture->stream, &vcapture->ved, 1); if (ret) { video_device_pipeline_stop(&vcapture->vdev); vimc_capture_return_all_buffers(vcapture, VB2_BUF_STATE_QUEUED); return ret; } return 0; } /* * Stop the stream engine. Any remaining buffers in the stream queue are * dequeued and passed on to the vb2 framework marked as STATE_ERROR. */ static void vimc_capture_stop_streaming(struct vb2_queue *vq) { struct vimc_capture_device *vcapture = vb2_get_drv_priv(vq); vimc_streamer_s_stream(&vcapture->stream, &vcapture->ved, 0); /* Stop the media pipeline */ video_device_pipeline_stop(&vcapture->vdev); /* Release all active buffers */ vimc_capture_return_all_buffers(vcapture, VB2_BUF_STATE_ERROR); } static void vimc_capture_buf_queue(struct vb2_buffer *vb2_buf) { struct vimc_capture_device *vcapture = vb2_get_drv_priv(vb2_buf->vb2_queue); struct vimc_capture_buffer *buf = container_of(vb2_buf, struct vimc_capture_buffer, vb2.vb2_buf); spin_lock(&vcapture->qlock); list_add_tail(&buf->list, &vcapture->buf_list); spin_unlock(&vcapture->qlock); } static int vimc_capture_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers, unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[]) { struct vimc_capture_device *vcapture = vb2_get_drv_priv(vq); if (*nplanes) return sizes[0] < vcapture->format.sizeimage ? -EINVAL : 0; /* We don't support multiplanes for now */ *nplanes = 1; sizes[0] = vcapture->format.sizeimage; return 0; } static int vimc_capture_buffer_prepare(struct vb2_buffer *vb) { struct vimc_capture_device *vcapture = vb2_get_drv_priv(vb->vb2_queue); unsigned long size = vcapture->format.sizeimage; if (vb2_plane_size(vb, 0) < size) { dev_err(vcapture->ved.dev, "%s: buffer too small (%lu < %lu)\n", vcapture->vdev.name, vb2_plane_size(vb, 0), size); return -EINVAL; } return 0; } static const struct vb2_ops vimc_capture_qops = { .start_streaming = vimc_capture_start_streaming, .stop_streaming = vimc_capture_stop_streaming, .buf_queue = vimc_capture_buf_queue, .queue_setup = vimc_capture_queue_setup, .buf_prepare = vimc_capture_buffer_prepare, }; static const struct media_entity_operations vimc_capture_mops = { .link_validate = vimc_vdev_link_validate, }; static void vimc_capture_release(struct vimc_ent_device *ved) { struct vimc_capture_device *vcapture = container_of(ved, struct vimc_capture_device, ved); media_entity_cleanup(vcapture->ved.ent); kfree(vcapture); } static void vimc_capture_unregister(struct vimc_ent_device *ved) { struct vimc_capture_device *vcapture = container_of(ved, struct vimc_capture_device, ved); vb2_video_unregister_device(&vcapture->vdev); } static void *vimc_capture_process_frame(struct vimc_ent_device *ved, const void *frame) { struct vimc_capture_device *vcapture = container_of(ved, struct vimc_capture_device, ved); struct vimc_capture_buffer *vimc_buf; void *vbuf; spin_lock(&vcapture->qlock); /* Get the first entry of the list */ vimc_buf = list_first_entry_or_null(&vcapture->buf_list, typeof(*vimc_buf), list); if (!vimc_buf) { spin_unlock(&vcapture->qlock); return ERR_PTR(-EAGAIN); } /* Remove this entry from the list */ list_del(&vimc_buf->list); spin_unlock(&vcapture->qlock); /* Fill the buffer */ vimc_buf->vb2.vb2_buf.timestamp = ktime_get_ns(); vimc_buf->vb2.sequence = vcapture->sequence++; vimc_buf->vb2.field = vcapture->format.field; vbuf = vb2_plane_vaddr(&vimc_buf->vb2.vb2_buf, 0); memcpy(vbuf, frame, vcapture->format.sizeimage); /* Set it as ready */ vb2_set_plane_payload(&vimc_buf->vb2.vb2_buf, 0, vcapture->format.sizeimage); vb2_buffer_done(&vimc_buf->vb2.vb2_buf, VB2_BUF_STATE_DONE); return NULL; } static struct vimc_ent_device *vimc_capture_add(struct vimc_device *vimc, const char *vcfg_name) { struct v4l2_device *v4l2_dev = &vimc->v4l2_dev; const struct vimc_pix_map *vpix; struct vimc_capture_device *vcapture; struct video_device *vdev; struct vb2_queue *q; int ret; /* Allocate the vimc_capture_device struct */ vcapture = kzalloc_obj(*vcapture); if (!vcapture) return ERR_PTR(-ENOMEM); /* Initialize the media entity */ vcapture->vdev.entity.name = vcfg_name; vcapture->vdev.entity.function = MEDIA_ENT_F_IO_V4L; vcapture->pad.flags = MEDIA_PAD_FL_SINK; ret = media_entity_pads_init(&vcapture->vdev.entity, 1, &vcapture->pad); if (ret) goto err_free_vcapture; /* Initialize the lock */ mutex_init(&vcapture->lock); /* Initialize the vb2 queue */ q = &vcapture->queue; q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE; q->io_modes = VB2_MMAP | VB2_DMABUF; if (vimc_allocator == VIMC_ALLOCATOR_VMALLOC) q->io_modes |= VB2_USERPTR; q->drv_priv = vcapture; q->buf_struct_size = sizeof(struct vimc_capture_buffer); q->ops = &vimc_capture_qops; q->mem_ops = vimc_allocator == VIMC_ALLOCATOR_DMA_CONTIG ? &vb2_dma_contig_memops : &vb2_vmalloc_memops; q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; q->min_reqbufs_allocation = 2; q->lock = &vcapture->lock; q->dev = v4l2_dev->dev; ret = vb2_queue_init(q); if (ret) { dev_err(vimc->mdev.dev, "%s: vb2 queue init failed (err=%d)\n", vcfg_name, ret); goto err_clean_m_ent; } /* Initialize buffer list and its lock */ INIT_LIST_HEAD(&vcapture->buf_list); spin_lock_init(&vcapture->qlock); /* Set default frame format */ vcapture->format = fmt_default; vpix = vimc_pix_map_by_pixelformat(vcapture->format.pixelformat); vcapture->format.bytesperline = vcapture->format.width * vpix->bpp; vcapture->format.sizeimage = vcapture->format.bytesperline * vcapture->format.height; /* Fill the vimc_ent_device struct */ vcapture->ved.ent = &vcapture->vdev.entity; vcapture->ved.process_frame = vimc_capture_process_frame; vcapture->ved.vdev_get_format = vimc_capture_get_format; vcapture->ved.dev = vimc->mdev.dev; /* Initialize the video_device struct */ vdev = &vcapture->vdev; vdev->device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING | V4L2_CAP_IO_MC; vdev->entity.ops = &vimc_capture_mops; vdev->release = video_device_release_empty; vdev->fops = &vimc_capture_fops; vdev->ioctl_ops = &vimc_capture_ioctl_ops; vdev->lock = &vcapture->lock; vdev->queue = q; vdev->v4l2_dev = v4l2_dev; vdev->vfl_dir = VFL_DIR_RX; strscpy(vdev->name, vcfg_name, sizeof(vdev->name)); video_set_drvdata(vdev, &vcapture->ved); /* Register the video_device with the v4l2 and the media framework */ ret = video_register_device(vdev, VFL_TYPE_VIDEO, -1); if (ret) { dev_err(vimc->mdev.dev, "%s: video register failed (err=%d)\n", vcapture->vdev.name, ret); goto err_clean_m_ent; } return &vcapture->ved; err_clean_m_ent: media_entity_cleanup(&vcapture->vdev.entity); err_free_vcapture: kfree(vcapture); return ERR_PTR(ret); } const struct vimc_ent_type vimc_capture_type = { .add = vimc_capture_add, .unregister = vimc_capture_unregister, .release = vimc_capture_release }; |
| 37 37 37 1 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37 | 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 | /* mpiutil.ac - Utility functions for MPI * Copyright (C) 1998, 1999 Free Software Foundation, Inc. * * This file is part of GnuPG. * * GnuPG is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * GnuPG 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. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA */ #include <linux/export.h> #include "mpi-internal.h" /**************** * Note: It was a bad idea to use the number of limbs to allocate * because on a alpha the limbs are large but we normally need * integers of n bits - So we should change this to bits (or bytes). * * But mpi_alloc is used in a lot of places :-) */ MPI mpi_alloc(unsigned nlimbs) { MPI a; a = kmalloc_obj(*a); if (!a) return a; if (nlimbs) { a->d = mpi_alloc_limb_space(nlimbs); if (!a->d) { kfree(a); return NULL; } } else { a->d = NULL; } a->alloced = nlimbs; a->nlimbs = 0; a->sign = 0; a->flags = 0; a->nbits = 0; return a; } EXPORT_SYMBOL_GPL(mpi_alloc); mpi_ptr_t mpi_alloc_limb_space(unsigned nlimbs) { size_t len = nlimbs * sizeof(mpi_limb_t); if (!len) return NULL; return kmalloc(len, GFP_KERNEL); } void mpi_free_limb_space(mpi_ptr_t a) { if (!a) return; kfree_sensitive(a); } void mpi_assign_limb_space(MPI a, mpi_ptr_t ap, unsigned nlimbs) { mpi_free_limb_space(a->d); a->d = ap; a->alloced = nlimbs; } /**************** * Resize the array of A to NLIMBS. the additional space is cleared * (set to 0) [done by m_realloc()] */ int mpi_resize(MPI a, unsigned nlimbs) { void *p; if (nlimbs <= a->alloced) return 0; /* no need to do it */ if (a->d) { p = kzalloc_objs(mpi_limb_t, nlimbs); if (!p) return -ENOMEM; memcpy(p, a->d, a->alloced * sizeof(mpi_limb_t)); kfree_sensitive(a->d); a->d = p; } else { a->d = kzalloc_objs(mpi_limb_t, nlimbs); if (!a->d) return -ENOMEM; } a->alloced = nlimbs; return 0; } void mpi_free(MPI a) { if (!a) return; if (a->flags & 4) kfree_sensitive(a->d); else mpi_free_limb_space(a->d); if (a->flags & ~7) pr_info("invalid flag value in mpi\n"); kfree(a); } EXPORT_SYMBOL_GPL(mpi_free); /**************** * Note: This copy function should not interpret the MPI * but copy it transparently. */ MPI mpi_copy(MPI a) { int i; MPI b; if (a) { b = mpi_alloc(a->nlimbs); if (!b) return NULL; b->nlimbs = a->nlimbs; b->sign = a->sign; b->flags = a->flags; b->flags &= ~(16|32); /* Reset the immutable and constant flags. */ for (i = 0; i < b->nlimbs; i++) b->d[i] = a->d[i]; } else b = NULL; return b; } MODULE_DESCRIPTION("Multiprecision maths library"); MODULE_LICENSE("GPL"); |
| 11393 11435 3 3 3 3 430 432 430 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Common code for 32 and 64-bit NUMA */ #include <linux/acpi.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/of.h> #include <linux/string.h> #include <linux/init.h> #include <linux/memblock.h> #include <linux/mmzone.h> #include <linux/ctype.h> #include <linux/nodemask.h> #include <linux/sched.h> #include <linux/topology.h> #include <linux/sort.h> #include <linux/numa_memblks.h> #include <asm/e820/api.h> #include <asm/proto.h> #include <asm/dma.h> #include <asm/numa.h> #include <asm/amd/nb.h> #include "mm_internal.h" int numa_off; static __init int numa_setup(char *opt) { if (!opt) return -EINVAL; if (!strncmp(opt, "off", 3)) numa_off = 1; if (!strncmp(opt, "fake=", 5)) return numa_emu_cmdline(opt + 5); if (!strncmp(opt, "noacpi", 6)) disable_srat(); if (!strncmp(opt, "nohmat", 6)) disable_hmat(); return 0; } early_param("numa", numa_setup); /* * apicid, cpu, node mappings */ s16 __apicid_to_node[MAX_LOCAL_APIC] = { [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE }; nodemask_t numa_phys_nodes_parsed __initdata; int numa_cpu_node(int cpu) { u32 apicid = early_per_cpu(x86_cpu_to_apicid, cpu); if (apicid != BAD_APICID) return __apicid_to_node[apicid]; return NUMA_NO_NODE; } int __init num_phys_nodes(void) { return bitmap_weight(numa_phys_nodes_parsed.bits, MAX_NUMNODES); } cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; EXPORT_SYMBOL(node_to_cpumask_map); /* * Map cpu index to node index */ DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE); EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); void numa_set_node(int cpu, int node) { int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); /* early setting, no percpu area yet */ if (cpu_to_node_map) { cpu_to_node_map[cpu] = node; return; } #ifdef CONFIG_DEBUG_PER_CPU_MAPS if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) { printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu); dump_stack(); return; } #endif per_cpu(x86_cpu_to_node_map, cpu) = node; set_cpu_numa_node(cpu, node); } void numa_clear_node(int cpu) { numa_set_node(cpu, NUMA_NO_NODE); } /* * Allocate node_to_cpumask_map based on number of available nodes * Requires node_possible_map to be valid. * * Note: cpumask_of_node() is not valid until after this is done. * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) */ void __init setup_node_to_cpumask_map(void) { unsigned int node; /* setup nr_node_ids if not done yet */ if (nr_node_ids == MAX_NUMNODES) setup_nr_node_ids(); /* allocate the map */ for (node = 0; node < nr_node_ids; node++) alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); /* cpumask_of_node() will now work */ pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids); } static int __init numa_register_nodes(void) { int nid; if (!memblock_validate_numa_coverage(SZ_1M)) return -EINVAL; /* Finally register nodes. */ for_each_node_mask(nid, node_possible_map) { unsigned long start_pfn, end_pfn; /* * Note, get_pfn_range_for_nid() depends on * memblock_set_node() having already happened */ get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); if (start_pfn >= end_pfn) continue; alloc_node_data(nid); node_set_online(nid); } /* Dump memblock with node info and return. */ memblock_dump_all(); return 0; } /* * There are unfortunately some poorly designed mainboards around that * only connect memory to a single CPU. This breaks the 1:1 cpu->node * mapping. To avoid this fill in the mapping for all possible CPUs, * as the number of CPUs is not known yet. We round robin the existing * nodes. */ static void __init numa_init_array(void) { int rr, i; rr = first_node(node_online_map); for (i = 0; i < nr_cpu_ids; i++) { if (early_cpu_to_node(i) != NUMA_NO_NODE) continue; numa_set_node(i, rr); rr = next_node_in(rr, node_online_map); } } static int __init numa_init(int (*init_func)(void)) { int i; int ret; for (i = 0; i < MAX_LOCAL_APIC; i++) set_apicid_to_node(i, NUMA_NO_NODE); ret = numa_memblks_init(init_func, /* memblock_force_top_down */ true); if (ret < 0) return ret; ret = numa_register_nodes(); if (ret < 0) return ret; for (i = 0; i < nr_cpu_ids; i++) { int nid = early_cpu_to_node(i); if (nid == NUMA_NO_NODE) continue; if (!node_online(nid)) numa_clear_node(i); } numa_init_array(); return 0; } /** * dummy_numa_init - Fallback dummy NUMA init * * Used if there's no underlying NUMA architecture, NUMA initialization * fails, or NUMA is disabled on the command line. * * Must online at least one node and add memory blocks that cover all * allowed memory. This function must not fail. */ static int __init dummy_numa_init(void) { printk(KERN_INFO "%s\n", numa_off ? "NUMA turned off" : "No NUMA configuration found"); printk(KERN_INFO "Faking a node at [mem %#018Lx-%#018Lx]\n", 0LLU, PFN_PHYS(max_pfn) - 1); node_set(0, numa_nodes_parsed); node_set(0, numa_phys_nodes_parsed); numa_add_memblk(0, 0, PFN_PHYS(max_pfn)); return 0; } /** * x86_numa_init - Initialize NUMA * * Try each configured NUMA initialization method until one succeeds. The * last fallback is dummy single node config encompassing whole memory and * never fails. */ void __init x86_numa_init(void) { if (!numa_off) { #ifdef CONFIG_ACPI_NUMA if (!numa_init(x86_acpi_numa_init)) return; #endif #ifdef CONFIG_AMD_NUMA if (!numa_init(amd_numa_init)) return; #endif if (acpi_disabled && !numa_init(of_numa_init)) return; } numa_init(dummy_numa_init); } /* * A node may exist which has one or more Generic Initiators but no CPUs and no * memory. * * This function must be called after init_cpu_to_node(), to ensure that any * memoryless CPU nodes have already been brought online, and before the * node_data[nid] is needed for zone list setup in build_all_zonelists(). * * When this function is called, any nodes containing either memory and/or CPUs * will already be online and there is no need to do anything extra, even if * they also contain one or more Generic Initiators. */ void __init init_gi_nodes(void) { int nid; /* * Exclude this node from * bringup_nonboot_cpus * cpu_up * __try_online_node * register_node * because node_subsys is not initialized yet. * TODO remove dependency on node_online */ for_each_node_state(nid, N_GENERIC_INITIATOR) if (!node_online(nid)) node_set_online(nid); } /* * Setup early cpu_to_node. * * Populate cpu_to_node[] only if x86_cpu_to_apicid[], * and apicid_to_node[] tables have valid entries for a CPU. * This means we skip cpu_to_node[] initialisation for NUMA * emulation and faking node case (when running a kernel compiled * for NUMA on a non NUMA box), which is OK as cpu_to_node[] * is already initialized in a round robin manner at numa_init_array, * prior to this call, and this initialization is good enough * for the fake NUMA cases. * * Called before the per_cpu areas are setup. */ void __init init_cpu_to_node(void) { int cpu; u32 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid); BUG_ON(cpu_to_apicid == NULL); for_each_possible_cpu(cpu) { int node = numa_cpu_node(cpu); if (node == NUMA_NO_NODE) continue; /* * Exclude this node from * bringup_nonboot_cpus * cpu_up * __try_online_node * register_node * because node_subsys is not initialized yet. * TODO remove dependency on node_online */ if (!node_online(node)) node_set_online(node); numa_set_node(cpu, node); } } #ifndef CONFIG_DEBUG_PER_CPU_MAPS # ifndef CONFIG_NUMA_EMU void numa_add_cpu(unsigned int cpu) { cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); } void numa_remove_cpu(unsigned int cpu) { cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); } # endif /* !CONFIG_NUMA_EMU */ #else /* !CONFIG_DEBUG_PER_CPU_MAPS */ int __cpu_to_node(int cpu) { if (early_per_cpu_ptr(x86_cpu_to_node_map)) { printk(KERN_WARNING "cpu_to_node(%d): usage too early!\n", cpu); dump_stack(); return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; } return per_cpu(x86_cpu_to_node_map, cpu); } EXPORT_SYMBOL(__cpu_to_node); /* * Same function as cpu_to_node() but used if called before the * per_cpu areas are setup. */ int early_cpu_to_node(int cpu) { if (early_per_cpu_ptr(x86_cpu_to_node_map)) return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; if (!cpu_possible(cpu)) { printk(KERN_WARNING "early_cpu_to_node(%d): no per_cpu area!\n", cpu); dump_stack(); return NUMA_NO_NODE; } return per_cpu(x86_cpu_to_node_map, cpu); } void debug_cpumask_set_cpu(unsigned int cpu, int node, bool enable) { struct cpumask *mask; if (node == NUMA_NO_NODE) { /* early_cpu_to_node() already emits a warning and trace */ return; } mask = node_to_cpumask_map[node]; if (!cpumask_available(mask)) { pr_err("node_to_cpumask_map[%i] NULL\n", node); dump_stack(); return; } if (enable) cpumask_set_cpu(cpu, mask); else cpumask_clear_cpu(cpu, mask); printk(KERN_DEBUG "%s cpu %d node %d: mask now %*pbl\n", enable ? "numa_add_cpu" : "numa_remove_cpu", cpu, node, cpumask_pr_args(mask)); return; } # ifndef CONFIG_NUMA_EMU static void numa_set_cpumask(int cpu, bool enable) { debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable); } void numa_add_cpu(unsigned int cpu) { numa_set_cpumask(cpu, true); } void numa_remove_cpu(unsigned int cpu) { numa_set_cpumask(cpu, false); } # endif /* !CONFIG_NUMA_EMU */ /* * Returns a pointer to the bitmask of CPUs on Node 'node'. */ const struct cpumask *cpumask_of_node(int node) { if ((unsigned)node >= nr_node_ids) { printk(KERN_WARNING "cpumask_of_node(%d): (unsigned)node >= nr_node_ids(%u)\n", node, nr_node_ids); dump_stack(); return cpu_none_mask; } if (!cpumask_available(node_to_cpumask_map[node])) { printk(KERN_WARNING "cpumask_of_node(%d): no node_to_cpumask_map!\n", node); dump_stack(); return cpu_online_mask; } return node_to_cpumask_map[node]; } EXPORT_SYMBOL(cpumask_of_node); #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ #ifdef CONFIG_NUMA_EMU void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys, unsigned int nr_emu_nids) { int i, j; /* * Transform __apicid_to_node table to use emulated nids by * reverse-mapping phys_nid. The maps should always exist but fall * back to zero just in case. */ for (i = 0; i < ARRAY_SIZE(__apicid_to_node); i++) { if (__apicid_to_node[i] == NUMA_NO_NODE) continue; for (j = 0; j < nr_emu_nids; j++) if (__apicid_to_node[i] == emu_nid_to_phys[j]) break; __apicid_to_node[i] = j < nr_emu_nids ? j : 0; } } u64 __init numa_emu_dma_end(void) { return PFN_PHYS(MAX_DMA32_PFN); } #endif /* CONFIG_NUMA_EMU */ |
| 32 32 32 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 | /* * Copyright 2011 Red Hat, Inc. * Copyright © 2014 The Chromium OS Authors * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software") * to deal in the software without restriction, including without limitation * on the rights to use, copy, modify, merge, publish, distribute, sub * license, and/or sell copies of the Software, and to permit persons to whom * them Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice (including the next * paragraph) shall be included in all copies or substantial portions of the * Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTIBILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL * THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER LIABILITY, WHETHER * IN AN ACTION OF CONTRACT, TORT, OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. * * Authors: * Adam Jackson <ajax@redhat.com> * Ben Widawsky <ben@bwidawsk.net> */ /* * This is vgem, a (non-hardware-backed) GEM service. This is used by Mesa's * software renderer and the X server for efficient buffer sharing. */ #include <linux/dma-buf.h> #include <linux/module.h> #include <linux/device/faux.h> #include <linux/shmem_fs.h> #include <linux/vmalloc.h> #include <drm/drm_drv.h> #include <drm/drm_file.h> #include <drm/drm_gem_shmem_helper.h> #include <drm/drm_ioctl.h> #include <drm/drm_managed.h> #include <drm/drm_prime.h> #include "vgem_drv.h" #define DRIVER_NAME "vgem" #define DRIVER_DESC "Virtual GEM provider" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 static struct vgem_device { struct drm_device drm; struct faux_device *faux_dev; } *vgem_device; static int vgem_open(struct drm_device *dev, struct drm_file *file) { struct vgem_file *vfile; int ret; vfile = kzalloc_obj(*vfile); if (!vfile) return -ENOMEM; file->driver_priv = vfile; ret = vgem_fence_open(vfile); if (ret) { kfree(vfile); return ret; } return 0; } static void vgem_postclose(struct drm_device *dev, struct drm_file *file) { struct vgem_file *vfile = file->driver_priv; vgem_fence_close(vfile); kfree(vfile); } static struct drm_ioctl_desc vgem_ioctls[] = { DRM_IOCTL_DEF_DRV(VGEM_FENCE_ATTACH, vgem_fence_attach_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(VGEM_FENCE_SIGNAL, vgem_fence_signal_ioctl, DRM_RENDER_ALLOW), }; DEFINE_DRM_GEM_FOPS(vgem_driver_fops); static struct drm_gem_object *vgem_gem_create_object(struct drm_device *dev, size_t size) { struct drm_gem_shmem_object *obj; obj = kzalloc_obj(*obj); if (!obj) return ERR_PTR(-ENOMEM); /* * vgem doesn't have any begin/end cpu access ioctls, therefore must use * coherent memory or dma-buf sharing just wont work. */ obj->map_wc = true; return &obj->base; } static const struct drm_driver vgem_driver = { .driver_features = DRIVER_GEM | DRIVER_RENDER, .open = vgem_open, .postclose = vgem_postclose, .ioctls = vgem_ioctls, .num_ioctls = ARRAY_SIZE(vgem_ioctls), .fops = &vgem_driver_fops, DRM_GEM_SHMEM_DRIVER_OPS, .gem_create_object = vgem_gem_create_object, .name = DRIVER_NAME, .desc = DRIVER_DESC, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, }; static int __init vgem_init(void) { int ret; struct faux_device *fdev; fdev = faux_device_create("vgem", NULL, NULL); if (!fdev) return -ENODEV; if (!devres_open_group(&fdev->dev, NULL, GFP_KERNEL)) { ret = -ENOMEM; goto out_unregister; } dma_coerce_mask_and_coherent(&fdev->dev, DMA_BIT_MASK(64)); vgem_device = devm_drm_dev_alloc(&fdev->dev, &vgem_driver, struct vgem_device, drm); if (IS_ERR(vgem_device)) { ret = PTR_ERR(vgem_device); goto out_devres; } vgem_device->faux_dev = fdev; /* Final step: expose the device/driver to userspace */ ret = drm_dev_register(&vgem_device->drm, 0); if (ret) goto out_devres; return 0; out_devres: devres_release_group(&fdev->dev, NULL); out_unregister: faux_device_destroy(fdev); return ret; } static void __exit vgem_exit(void) { struct faux_device *fdev = vgem_device->faux_dev; drm_dev_unregister(&vgem_device->drm); devres_release_group(&fdev->dev, NULL); faux_device_destroy(fdev); } module_init(vgem_init); module_exit(vgem_exit); MODULE_AUTHOR("Red Hat, Inc."); MODULE_AUTHOR("Intel Corporation"); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL and additional rights"); |
| 96 96 95 96 96 96 95 96 96 96 96 96 95 96 96 96 95 96 96 95 96 | 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 | /* * Copyright (C) 2011-2013 Intel Corporation * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice (including the next * paragraph) shall be included in all copies or substantial portions of the * Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/errno.h> #include <linux/export.h> #include <linux/kernel.h> #include <drm/drm_mode.h> #include <drm/drm_print.h> #include <drm/drm_rect.h> /** * drm_rect_intersect - intersect two rectangles * @r1: first rectangle * @r2: second rectangle * * Calculate the intersection of rectangles @r1 and @r2. * @r1 will be overwritten with the intersection. * * RETURNS: * %true if rectangle @r1 is still visible after the operation, * %false otherwise. */ bool drm_rect_intersect(struct drm_rect *r1, const struct drm_rect *r2) { r1->x1 = max(r1->x1, r2->x1); r1->y1 = max(r1->y1, r2->y1); r1->x2 = min(r1->x2, r2->x2); r1->y2 = min(r1->y2, r2->y2); return drm_rect_visible(r1); } EXPORT_SYMBOL(drm_rect_intersect); static u32 clip_scaled(int src, int dst, int *clip) { u64 tmp; if (dst == 0) return 0; /* Only clip what we have. Keeps the result bounded. */ *clip = min(*clip, dst); tmp = mul_u32_u32(src, dst - *clip); /* * Round toward 1.0 when clipping so that we don't accidentally * change upscaling to downscaling or vice versa. */ if (src < (dst << 16)) return DIV_ROUND_UP_ULL(tmp, dst); else return DIV_ROUND_DOWN_ULL(tmp, dst); } /** * drm_rect_clip_scaled - perform a scaled clip operation * @src: source window rectangle * @dst: destination window rectangle * @clip: clip rectangle * * Clip rectangle @dst by rectangle @clip. Clip rectangle @src by * the corresponding amounts, retaining the vertical and horizontal scaling * factors from @src to @dst. * * RETURNS: * %true if rectangle @dst is still visible after being clipped, * %false otherwise. */ bool drm_rect_clip_scaled(struct drm_rect *src, struct drm_rect *dst, const struct drm_rect *clip) { int diff; diff = clip->x1 - dst->x1; if (diff > 0) { u32 new_src_w = clip_scaled(drm_rect_width(src), drm_rect_width(dst), &diff); src->x1 = src->x2 - new_src_w; dst->x1 += diff; } diff = clip->y1 - dst->y1; if (diff > 0) { u32 new_src_h = clip_scaled(drm_rect_height(src), drm_rect_height(dst), &diff); src->y1 = src->y2 - new_src_h; dst->y1 += diff; } diff = dst->x2 - clip->x2; if (diff > 0) { u32 new_src_w = clip_scaled(drm_rect_width(src), drm_rect_width(dst), &diff); src->x2 = src->x1 + new_src_w; dst->x2 -= diff; } diff = dst->y2 - clip->y2; if (diff > 0) { u32 new_src_h = clip_scaled(drm_rect_height(src), drm_rect_height(dst), &diff); src->y2 = src->y1 + new_src_h; dst->y2 -= diff; } return drm_rect_visible(dst); } EXPORT_SYMBOL(drm_rect_clip_scaled); static int drm_calc_scale(int src, int dst) { int scale = 0; if (WARN_ON(src < 0 || dst < 0)) return -EINVAL; if (dst == 0) return 0; if (src > (dst << 16)) return DIV_ROUND_UP(src, dst); else scale = src / dst; return scale; } /** * drm_rect_calc_hscale - calculate the horizontal scaling factor * @src: source window rectangle * @dst: destination window rectangle * @min_hscale: minimum allowed horizontal scaling factor * @max_hscale: maximum allowed horizontal scaling factor * * Calculate the horizontal scaling factor as * (@src width) / (@dst width). * * If the scale is below 1 << 16, round down. If the scale is above * 1 << 16, round up. This will calculate the scale with the most * pessimistic limit calculation. * * RETURNS: * The horizontal scaling factor, or errno of out of limits. */ int drm_rect_calc_hscale(const struct drm_rect *src, const struct drm_rect *dst, int min_hscale, int max_hscale) { int src_w = drm_rect_width(src); int dst_w = drm_rect_width(dst); int hscale = drm_calc_scale(src_w, dst_w); if (hscale < 0 || dst_w == 0) return hscale; if (hscale < min_hscale || hscale > max_hscale) return -ERANGE; return hscale; } EXPORT_SYMBOL(drm_rect_calc_hscale); /** * drm_rect_calc_vscale - calculate the vertical scaling factor * @src: source window rectangle * @dst: destination window rectangle * @min_vscale: minimum allowed vertical scaling factor * @max_vscale: maximum allowed vertical scaling factor * * Calculate the vertical scaling factor as * (@src height) / (@dst height). * * If the scale is below 1 << 16, round down. If the scale is above * 1 << 16, round up. This will calculate the scale with the most * pessimistic limit calculation. * * RETURNS: * The vertical scaling factor, or errno of out of limits. */ int drm_rect_calc_vscale(const struct drm_rect *src, const struct drm_rect *dst, int min_vscale, int max_vscale) { int src_h = drm_rect_height(src); int dst_h = drm_rect_height(dst); int vscale = drm_calc_scale(src_h, dst_h); if (vscale < 0 || dst_h == 0) return vscale; if (vscale < min_vscale || vscale > max_vscale) return -ERANGE; return vscale; } EXPORT_SYMBOL(drm_rect_calc_vscale); /** * drm_rect_debug_print - print the rectangle information * @prefix: prefix string * @r: rectangle to print * @fixed_point: rectangle is in 16.16 fixed point format */ void drm_rect_debug_print(const char *prefix, const struct drm_rect *r, bool fixed_point) { if (fixed_point) DRM_DEBUG_KMS("%s" DRM_RECT_FP_FMT "\n", prefix, DRM_RECT_FP_ARG(r)); else DRM_DEBUG_KMS("%s" DRM_RECT_FMT "\n", prefix, DRM_RECT_ARG(r)); } EXPORT_SYMBOL(drm_rect_debug_print); /** * drm_rect_rotate - Rotate the rectangle * @r: rectangle to be rotated * @width: Width of the coordinate space * @height: Height of the coordinate space * @rotation: Transformation to be applied * * Apply @rotation to the coordinates of rectangle @r. * * @width and @height combined with @rotation define * the location of the new origin. * * @width correcsponds to the horizontal and @height * to the vertical axis of the untransformed coordinate * space. */ void drm_rect_rotate(struct drm_rect *r, int width, int height, unsigned int rotation) { struct drm_rect tmp; if (rotation & (DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y)) { tmp = *r; if (rotation & DRM_MODE_REFLECT_X) { r->x1 = width - tmp.x2; r->x2 = width - tmp.x1; } if (rotation & DRM_MODE_REFLECT_Y) { r->y1 = height - tmp.y2; r->y2 = height - tmp.y1; } } switch (rotation & DRM_MODE_ROTATE_MASK) { case DRM_MODE_ROTATE_0: break; case DRM_MODE_ROTATE_90: tmp = *r; r->x1 = tmp.y1; r->x2 = tmp.y2; r->y1 = width - tmp.x2; r->y2 = width - tmp.x1; break; case DRM_MODE_ROTATE_180: tmp = *r; r->x1 = width - tmp.x2; r->x2 = width - tmp.x1; r->y1 = height - tmp.y2; r->y2 = height - tmp.y1; break; case DRM_MODE_ROTATE_270: tmp = *r; r->x1 = height - tmp.y2; r->x2 = height - tmp.y1; r->y1 = tmp.x1; r->y2 = tmp.x2; break; default: break; } } EXPORT_SYMBOL(drm_rect_rotate); /** * drm_rect_rotate_inv - Inverse rotate the rectangle * @r: rectangle to be rotated * @width: Width of the coordinate space * @height: Height of the coordinate space * @rotation: Transformation whose inverse is to be applied * * Apply the inverse of @rotation to the coordinates * of rectangle @r. * * @width and @height combined with @rotation define * the location of the new origin. * * @width correcsponds to the horizontal and @height * to the vertical axis of the original untransformed * coordinate space, so that you never have to flip * them when doing a rotatation and its inverse. * That is, if you do :: * * drm_rect_rotate(&r, width, height, rotation); * drm_rect_rotate_inv(&r, width, height, rotation); * * you will always get back the original rectangle. */ void drm_rect_rotate_inv(struct drm_rect *r, int width, int height, unsigned int rotation) { struct drm_rect tmp; switch (rotation & DRM_MODE_ROTATE_MASK) { case DRM_MODE_ROTATE_0: break; case DRM_MODE_ROTATE_90: tmp = *r; r->x1 = width - tmp.y2; r->x2 = width - tmp.y1; r->y1 = tmp.x1; r->y2 = tmp.x2; break; case DRM_MODE_ROTATE_180: tmp = *r; r->x1 = width - tmp.x2; r->x2 = width - tmp.x1; r->y1 = height - tmp.y2; r->y2 = height - tmp.y1; break; case DRM_MODE_ROTATE_270: tmp = *r; r->x1 = tmp.y1; r->x2 = tmp.y2; r->y1 = height - tmp.x2; r->y2 = height - tmp.x1; break; default: break; } if (rotation & (DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y)) { tmp = *r; if (rotation & DRM_MODE_REFLECT_X) { r->x1 = width - tmp.x2; r->x2 = width - tmp.x1; } if (rotation & DRM_MODE_REFLECT_Y) { r->y1 = height - tmp.y2; r->y2 = height - tmp.y1; } } } EXPORT_SYMBOL(drm_rect_rotate_inv); |
| 12 12 3 5 5 6 1 1 1 5 7 4 2 32 2 1 1 1 2 2 1 1 1 1 30 28 2 27 25 3 24 1 2 2 1 1 3 1 7 1 7 7 1 2 15 1 12 14 3 4 4 1 32 1 31 31 11 11 6 6 11 2 2 9 1 2 9 9 11 11 11 6 11 18 19 19 19 13 6 7 7 1 7 7 6 6 6 7 7 4 3 2 1 2 2 1 1 1 2 3 2 5 4 1 4 3 3 3 3 3 4 4 2 1 1 1 1 1 9 9 8 7 2 4 4 3 3 1 6 6 6 6 5 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2015 Nicira, Inc. */ #include <linux/module.h> #include <linux/openvswitch.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/sctp.h> #include <linux/static_key.h> #include <linux/string_helpers.h> #include <net/ip.h> #include <net/genetlink.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_count.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/ipv6_frag.h> #if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_nat.h> #endif #include <net/netfilter/nf_conntrack_act_ct.h> #include "datapath.h" #include "drop.h" #include "conntrack.h" #include "flow.h" #include "flow_netlink.h" struct ovs_ct_len_tbl { int maxlen; int minlen; }; /* Metadata mark for masked write to conntrack mark */ struct md_mark { u32 value; u32 mask; }; /* Metadata label for masked write to conntrack label. */ struct md_labels { struct ovs_key_ct_labels value; struct ovs_key_ct_labels mask; }; enum ovs_ct_nat { OVS_CT_NAT = 1 << 0, /* NAT for committed connections only. */ OVS_CT_SRC_NAT = 1 << 1, /* Source NAT for NEW connections. */ OVS_CT_DST_NAT = 1 << 2, /* Destination NAT for NEW connections. */ }; /* Conntrack action context for execution. */ struct ovs_conntrack_info { struct nf_conntrack_helper *helper; struct nf_conntrack_zone zone; struct nf_conn *ct; u8 commit : 1; u8 nat : 3; /* enum ovs_ct_nat */ u8 force : 1; u8 have_eventmask : 1; u16 family; u32 eventmask; /* Mask of 1 << IPCT_*. */ struct md_mark mark; struct md_labels labels; char timeout[CTNL_TIMEOUT_NAME_MAX]; struct nf_ct_timeout *nf_ct_timeout; #if IS_ENABLED(CONFIG_NF_NAT) struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */ #endif }; #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) #define OVS_CT_LIMIT_UNLIMITED 0 #define OVS_CT_LIMIT_DEFAULT OVS_CT_LIMIT_UNLIMITED #define CT_LIMIT_HASH_BUCKETS 512 static DEFINE_STATIC_KEY_FALSE(ovs_ct_limit_enabled); struct ovs_ct_limit { /* Elements in ovs_ct_limit_info->limits hash table */ struct hlist_node hlist_node; struct rcu_head rcu; u16 zone; u32 limit; }; struct ovs_ct_limit_info { u32 default_limit; struct hlist_head *limits; struct nf_conncount_data *data; }; static const struct nla_policy ct_limit_policy[OVS_CT_LIMIT_ATTR_MAX + 1] = { [OVS_CT_LIMIT_ATTR_ZONE_LIMIT] = { .type = NLA_NESTED, }, }; #endif static bool labels_nonzero(const struct ovs_key_ct_labels *labels); static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info); static u16 key_to_nfproto(const struct sw_flow_key *key) { switch (ntohs(key->eth.type)) { case ETH_P_IP: return NFPROTO_IPV4; case ETH_P_IPV6: return NFPROTO_IPV6; default: return NFPROTO_UNSPEC; } } /* Map SKB connection state into the values used by flow definition. */ static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo) { u8 ct_state = OVS_CS_F_TRACKED; switch (ctinfo) { case IP_CT_ESTABLISHED_REPLY: case IP_CT_RELATED_REPLY: ct_state |= OVS_CS_F_REPLY_DIR; break; default: break; } switch (ctinfo) { case IP_CT_ESTABLISHED: case IP_CT_ESTABLISHED_REPLY: ct_state |= OVS_CS_F_ESTABLISHED; break; case IP_CT_RELATED: case IP_CT_RELATED_REPLY: ct_state |= OVS_CS_F_RELATED; break; case IP_CT_NEW: ct_state |= OVS_CS_F_NEW; break; default: break; } return ct_state; } static u32 ovs_ct_get_mark(const struct nf_conn *ct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) return ct ? READ_ONCE(ct->mark) : 0; #else return 0; #endif } /* Guard against conntrack labels max size shrinking below 128 bits. */ #if NF_CT_LABELS_MAX_SIZE < 16 #error NF_CT_LABELS_MAX_SIZE must be at least 16 bytes #endif static void ovs_ct_get_labels(const struct nf_conn *ct, struct ovs_key_ct_labels *labels) { struct nf_conn_labels *cl = NULL; if (ct) { if (ct->master && !nf_ct_is_confirmed(ct)) ct = ct->master; cl = nf_ct_labels_find(ct); } if (cl) memcpy(labels, cl->bits, OVS_CT_LABELS_LEN); else memset(labels, 0, OVS_CT_LABELS_LEN); } static void __ovs_ct_update_key_orig_tp(struct sw_flow_key *key, const struct nf_conntrack_tuple *orig, u8 icmp_proto) { key->ct_orig_proto = orig->dst.protonum; if (orig->dst.protonum == icmp_proto) { key->ct.orig_tp.src = htons(orig->dst.u.icmp.type); key->ct.orig_tp.dst = htons(orig->dst.u.icmp.code); } else { key->ct.orig_tp.src = orig->src.u.all; key->ct.orig_tp.dst = orig->dst.u.all; } } static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, const struct nf_conntrack_zone *zone, const struct nf_conn *ct) { key->ct_state = state; key->ct_zone = zone->id; key->ct.mark = ovs_ct_get_mark(ct); ovs_ct_get_labels(ct, &key->ct.labels); if (ct) { const struct nf_conntrack_tuple *orig; /* Use the master if we have one. */ if (ct->master) ct = ct->master; orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* IP version must match with the master connection. */ if (key->eth.type == htons(ETH_P_IP) && nf_ct_l3num(ct) == NFPROTO_IPV4) { key->ipv4.ct_orig.src = orig->src.u3.ip; key->ipv4.ct_orig.dst = orig->dst.u3.ip; __ovs_ct_update_key_orig_tp(key, orig, IPPROTO_ICMP); return; } else if (key->eth.type == htons(ETH_P_IPV6) && !sw_flow_key_is_nd(key) && nf_ct_l3num(ct) == NFPROTO_IPV6) { key->ipv6.ct_orig.src = orig->src.u3.in6; key->ipv6.ct_orig.dst = orig->dst.u3.in6; __ovs_ct_update_key_orig_tp(key, orig, NEXTHDR_ICMP); return; } } /* Clear 'ct_orig_proto' to mark the non-existence of conntrack * original direction key fields. */ key->ct_orig_proto = 0; } /* Update 'key' based on skb->_nfct. If 'post_ct' is true, then OVS has * previously sent the packet to conntrack via the ct action. If * 'keep_nat_flags' is true, the existing NAT flags retained, else they are * initialized from the connection status. */ static void ovs_ct_update_key(const struct sk_buff *skb, const struct ovs_conntrack_info *info, struct sw_flow_key *key, bool post_ct, bool keep_nat_flags) { const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; enum ip_conntrack_info ctinfo; struct nf_conn *ct; u8 state = 0; ct = nf_ct_get(skb, &ctinfo); if (ct) { state = ovs_ct_get_state(ctinfo); /* All unconfirmed entries are NEW connections. */ if (!nf_ct_is_confirmed(ct)) state |= OVS_CS_F_NEW; /* OVS persists the related flag for the duration of the * connection. */ if (ct->master) state |= OVS_CS_F_RELATED; if (keep_nat_flags) { state |= key->ct_state & OVS_CS_F_NAT_MASK; } else { if (ct->status & IPS_SRC_NAT) state |= OVS_CS_F_SRC_NAT; if (ct->status & IPS_DST_NAT) state |= OVS_CS_F_DST_NAT; } zone = nf_ct_zone(ct); } else if (post_ct) { state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID; if (info) zone = &info->zone; } __ovs_ct_update_key(key, state, zone, ct); } /* This is called to initialize CT key fields possibly coming in from the local * stack. */ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key, bool post_ct) { ovs_ct_update_key(skb, NULL, key, post_ct, false); } int ovs_ct_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, struct sk_buff *skb) { if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, output->ct_state)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, output->ct_zone)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && nla_put_u32(skb, OVS_KEY_ATTR_CT_MARK, output->ct.mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(output->ct.labels), &output->ct.labels)) return -EMSGSIZE; if (swkey->ct_orig_proto) { if (swkey->eth.type == htons(ETH_P_IP)) { struct ovs_key_ct_tuple_ipv4 orig; memset(&orig, 0, sizeof(orig)); orig.ipv4_src = output->ipv4.ct_orig.src; orig.ipv4_dst = output->ipv4.ct_orig.dst; orig.src_port = output->ct.orig_tp.src; orig.dst_port = output->ct.orig_tp.dst; orig.ipv4_proto = output->ct_orig_proto; if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, sizeof(orig), &orig)) return -EMSGSIZE; } else if (swkey->eth.type == htons(ETH_P_IPV6)) { struct ovs_key_ct_tuple_ipv6 orig; memset(&orig, 0, sizeof(orig)); memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32, sizeof(orig.ipv6_src)); memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32, sizeof(orig.ipv6_dst)); orig.src_port = output->ct.orig_tp.src; orig.dst_port = output->ct.orig_tp.dst; orig.ipv6_proto = output->ct_orig_proto; if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, sizeof(orig), &orig)) return -EMSGSIZE; } } return 0; } static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key, u32 ct_mark, u32 mask) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) u32 new_mark; new_mark = ct_mark | (READ_ONCE(ct->mark) & ~(mask)); if (READ_ONCE(ct->mark) != new_mark) { WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); key->ct.mark = new_mark; } return 0; #else return -ENOTSUPP; #endif } static struct nf_conn_labels *ovs_ct_get_conn_labels(struct nf_conn *ct) { struct nf_conn_labels *cl; cl = nf_ct_labels_find(ct); if (!cl) { nf_ct_labels_ext_add(ct); cl = nf_ct_labels_find(ct); } return cl; } /* Initialize labels for a new, yet to be committed conntrack entry. Note that * since the new connection is not yet confirmed, and thus no-one else has * access to it's labels, we simply write them over. */ static int ovs_ct_init_labels(struct nf_conn *ct, struct sw_flow_key *key, const struct ovs_key_ct_labels *labels, const struct ovs_key_ct_labels *mask) { struct nf_conn_labels *cl, *master_cl; bool have_mask = labels_nonzero(mask); /* Inherit master's labels to the related connection? */ master_cl = ct->master ? nf_ct_labels_find(ct->master) : NULL; if (!master_cl && !have_mask) return 0; /* Nothing to do. */ cl = ovs_ct_get_conn_labels(ct); if (!cl) return -ENOSPC; /* Inherit the master's labels, if any. */ if (master_cl) *cl = *master_cl; if (have_mask) { u32 *dst = (u32 *)cl->bits; int i; for (i = 0; i < OVS_CT_LABELS_LEN_32; i++) dst[i] = (dst[i] & ~mask->ct_labels_32[i]) | (labels->ct_labels_32[i] & mask->ct_labels_32[i]); } /* Labels are included in the IPCTNL_MSG_CT_NEW event only if the * IPCT_LABEL bit is set in the event cache. */ nf_conntrack_event_cache(IPCT_LABEL, ct); memcpy(&key->ct.labels, cl->bits, OVS_CT_LABELS_LEN); return 0; } static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key, const struct ovs_key_ct_labels *labels, const struct ovs_key_ct_labels *mask) { struct nf_conn_labels *cl; int err; cl = ovs_ct_get_conn_labels(ct); if (!cl) return -ENOSPC; err = nf_connlabels_replace(ct, labels->ct_labels_32, mask->ct_labels_32, OVS_CT_LABELS_LEN_32); if (err) return err; memcpy(&key->ct.labels, cl->bits, OVS_CT_LABELS_LEN); return 0; } static int ovs_ct_handle_fragments(struct net *net, struct sw_flow_key *key, u16 zone, int family, struct sk_buff *skb) { struct ovs_skb_cb ovs_cb = *OVS_CB(skb); int err; err = nf_ct_handle_fragments(net, skb, zone, family, &key->ip.proto, &ovs_cb.mru); if (err) return err; /* The key extracted from the fragment that completed this datagram * likely didn't have an L4 header, so regenerate it. */ ovs_flow_key_update_l3l4(skb, key); key->ip.frag = OVS_FRAG_TYPE_NONE; *OVS_CB(skb) = ovs_cb; return 0; } /* This replicates logic from nf_conntrack_core.c that is not exported. */ static enum ip_conntrack_info ovs_ct_get_info(const struct nf_conntrack_tuple_hash *h) { const struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) return IP_CT_ESTABLISHED_REPLY; /* Once we've had two way comms, always ESTABLISHED. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) return IP_CT_ESTABLISHED; if (test_bit(IPS_EXPECTED_BIT, &ct->status)) return IP_CT_RELATED; return IP_CT_NEW; } /* Find an existing connection which this packet belongs to without * re-attributing statistics or modifying the connection state. This allows an * skb->_nfct lost due to an upcall to be recovered during actions execution. * * Must be called with rcu_read_lock. * * On success, populates skb->_nfct and returns the connection. Returns NULL * if there is no existing entry. */ static struct nf_conn * ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, u8 l3num, struct sk_buff *skb, bool natted) { struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), l3num, net, &tuple)) { pr_debug("ovs_ct_find_existing: Can't get tuple\n"); return NULL; } /* Must invert the tuple if skb has been transformed by NAT. */ if (natted) { struct nf_conntrack_tuple inverse; if (!nf_ct_invert_tuple(&inverse, &tuple)) { pr_debug("ovs_ct_find_existing: Inversion failed!\n"); return NULL; } tuple = inverse; } /* look for tuple match */ h = nf_conntrack_find_get(net, zone, &tuple); if (!h) return NULL; /* Not found. */ ct = nf_ct_tuplehash_to_ctrack(h); /* Inverted packet tuple matches the reverse direction conntrack tuple, * select the other tuplehash to get the right 'ctinfo' bits for this * packet. */ if (natted) h = &ct->tuplehash[!h->tuple.dst.dir]; nf_ct_set(skb, ct, ovs_ct_get_info(h)); return ct; } static struct nf_conn *ovs_ct_executed(struct net *net, const struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb, bool *ct_executed) { struct nf_conn *ct = NULL; /* If no ct, check if we have evidence that an existing conntrack entry * might be found for this skb. This happens when we lose a skb->_nfct * due to an upcall, or if the direction is being forced. If the * connection was not confirmed, it is not cached and needs to be run * through conntrack again. */ *ct_executed = (key->ct_state & OVS_CS_F_TRACKED) && !(key->ct_state & OVS_CS_F_INVALID) && (key->ct_zone == info->zone.id); if (*ct_executed || (!key->ct_state && info->force)) { ct = ovs_ct_find_existing(net, &info->zone, info->family, skb, !!(key->ct_state & OVS_CS_F_NAT_MASK)); } return ct; } /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ static bool skb_nfct_cached(struct net *net, const struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; bool ct_executed = true; ct = nf_ct_get(skb, &ctinfo); if (!ct) ct = ovs_ct_executed(net, key, info, skb, &ct_executed); if (ct) nf_ct_get(skb, &ctinfo); else return false; if (!net_eq(net, read_pnet(&ct->ct_net))) return false; if (!nf_ct_zone_equal_any(info->ct, nf_ct_zone(ct))) return false; if (info->helper) { struct nf_conn_help *help; help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER); if (help && rcu_access_pointer(help->helper) != info->helper) return false; } if (info->nf_ct_timeout) { struct nf_conn_timeout *timeout_ext; timeout_ext = nf_ct_timeout_find(ct); if (!timeout_ext || info->nf_ct_timeout != rcu_dereference(timeout_ext->timeout)) return false; } /* Force conntrack entry direction to the current packet? */ if (info->force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { /* Delete the conntrack entry if confirmed, else just release * the reference. */ if (nf_ct_is_confirmed(ct)) nf_ct_delete(ct, 0, 0); nf_ct_put(ct); nf_ct_set(skb, NULL, 0); return false; } return ct_executed; } #if IS_ENABLED(CONFIG_NF_NAT) static void ovs_nat_update_key(struct sw_flow_key *key, const struct sk_buff *skb, enum nf_nat_manip_type maniptype) { if (maniptype == NF_NAT_MANIP_SRC) { __be16 src; key->ct_state |= OVS_CS_F_SRC_NAT; if (key->eth.type == htons(ETH_P_IP)) key->ipv4.addr.src = ip_hdr(skb)->saddr; else if (key->eth.type == htons(ETH_P_IPV6)) memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr, sizeof(key->ipv6.addr.src)); else return; if (key->ip.proto == IPPROTO_UDP) src = udp_hdr(skb)->source; else if (key->ip.proto == IPPROTO_TCP) src = tcp_hdr(skb)->source; else if (key->ip.proto == IPPROTO_SCTP) src = sctp_hdr(skb)->source; else return; key->tp.src = src; } else { __be16 dst; key->ct_state |= OVS_CS_F_DST_NAT; if (key->eth.type == htons(ETH_P_IP)) key->ipv4.addr.dst = ip_hdr(skb)->daddr; else if (key->eth.type == htons(ETH_P_IPV6)) memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr, sizeof(key->ipv6.addr.dst)); else return; if (key->ip.proto == IPPROTO_UDP) dst = udp_hdr(skb)->dest; else if (key->ip.proto == IPPROTO_TCP) dst = tcp_hdr(skb)->dest; else if (key->ip.proto == IPPROTO_SCTP) dst = sctp_hdr(skb)->dest; else return; key->tp.dst = dst; } } /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { int err, action = 0; if (!(info->nat & OVS_CT_NAT)) return NF_ACCEPT; if (info->nat & OVS_CT_SRC_NAT) action |= BIT(NF_NAT_MANIP_SRC); if (info->nat & OVS_CT_DST_NAT) action |= BIT(NF_NAT_MANIP_DST); err = nf_ct_nat(skb, ct, ctinfo, &action, &info->range, info->commit); if (err != NF_ACCEPT) return err; if (action & BIT(NF_NAT_MANIP_SRC)) ovs_nat_update_key(key, skb, NF_NAT_MANIP_SRC); if (action & BIT(NF_NAT_MANIP_DST)) ovs_nat_update_key(key, skb, NF_NAT_MANIP_DST); return err; } #else /* !CONFIG_NF_NAT */ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { return NF_ACCEPT; } #endif static int verdict_to_errno(unsigned int verdict) { switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: return 0; case NF_DROP: return -EINVAL; case NF_STOLEN: return -EINPROGRESS; default: break; } return -EINVAL; } /* Pass 'skb' through conntrack in 'net', using zone configured in 'info', if * not done already. Update key with new CT state after passing the packet * through conntrack. * Note that if the packet is deemed invalid by conntrack, skb->_nfct will be * set to NULL and 0 will be returned. */ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb) { /* If we are recirculating packets to match on conntrack fields and * committing with a separate conntrack action, then we don't need to * actually run the packet through conntrack twice unless it's for a * different zone. */ bool cached = skb_nfct_cached(net, key, info, skb); enum ip_conntrack_info ctinfo; struct nf_conn *ct; if (!cached) { struct nf_hook_state state = { .hook = NF_INET_PRE_ROUTING, .pf = info->family, .net = net, }; struct nf_conn *tmpl = info->ct; int err; /* Associate skb with specified zone. */ if (tmpl) { ct = nf_ct_get(skb, &ctinfo); nf_ct_put(ct); nf_conntrack_get(&tmpl->ct_general); nf_ct_set(skb, tmpl, IP_CT_NEW); } err = nf_conntrack_in(skb, &state); if (err != NF_ACCEPT) return verdict_to_errno(err); /* Clear CT state NAT flags to mark that we have not yet done * NAT after the nf_conntrack_in() call. We can actually clear * the whole state, as it will be re-initialized below. */ key->ct_state = 0; /* Update the key, but keep the NAT flags. */ ovs_ct_update_key(skb, info, key, true, true); } ct = nf_ct_get(skb, &ctinfo); if (ct) { bool add_helper = false; /* Packets starting a new connection must be NATted before the * helper, so that the helper knows about the NAT. We enforce * this by delaying both NAT and helper calls for unconfirmed * connections until the committing CT action. For later * packets NAT and Helper may be called in either order. * * NAT will be done only if the CT action has NAT, and only * once per packet (per zone), as guarded by the NAT bits in * the key->ct_state. */ if (info->nat && !(key->ct_state & OVS_CS_F_NAT_MASK) && (nf_ct_is_confirmed(ct) || info->commit)) { int err = ovs_ct_nat(net, key, info, skb, ct, ctinfo); err = verdict_to_errno(err); if (err) return err; } /* Userspace may decide to perform a ct lookup without a helper * specified followed by a (recirculate and) commit with one, * or attach a helper in a later commit. Therefore, for * connections which we will commit, we may need to attach * the helper here. */ if (!nf_ct_is_confirmed(ct) && info->commit && info->helper && !nfct_help(ct)) { int err = __nf_ct_try_assign_helper(ct, info->ct, GFP_ATOMIC); if (err) return err; add_helper = true; /* helper installed, add seqadj if NAT is required */ if (info->nat && !nfct_seqadj(ct)) { if (!nfct_seqadj_ext_add(ct)) return -EINVAL; } } /* Call the helper only if: * - nf_conntrack_in() was executed above ("!cached") or a * helper was just attached ("add_helper") for a confirmed * connection, or * - When committing an unconfirmed connection. */ if ((nf_ct_is_confirmed(ct) ? !cached || add_helper : info->commit)) { int err = nf_ct_helper(skb, ct, ctinfo, info->family); err = verdict_to_errno(err); if (err) return err; } if (nf_ct_protonum(ct) == IPPROTO_TCP && nf_ct_is_confirmed(ct) && nf_conntrack_tcp_established(ct)) { /* Be liberal for tcp packets so that out-of-window * packets are not marked invalid. */ nf_ct_set_tcp_be_liberal(ct); } nf_conn_act_ct_ext_fill(skb, ct, ctinfo); } return 0; } /* Lookup connection and read fields into key. */ static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb) { struct nf_conn *ct; int err; err = __ovs_ct_lookup(net, key, info, skb); if (err) return err; ct = (struct nf_conn *)skb_nfct(skb); if (ct) nf_ct_deliver_cached_events(ct); return 0; } static bool labels_nonzero(const struct ovs_key_ct_labels *labels) { size_t i; for (i = 0; i < OVS_CT_LABELS_LEN_32; i++) if (labels->ct_labels_32[i]) return true; return false; } #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) static struct hlist_head *ct_limit_hash_bucket( const struct ovs_ct_limit_info *info, u16 zone) { return &info->limits[zone & (CT_LIMIT_HASH_BUCKETS - 1)]; } /* Call with ovs_mutex */ static void ct_limit_set(const struct ovs_ct_limit_info *info, struct ovs_ct_limit *new_ct_limit) { struct ovs_ct_limit *ct_limit; struct hlist_head *head; head = ct_limit_hash_bucket(info, new_ct_limit->zone); hlist_for_each_entry_rcu(ct_limit, head, hlist_node, lockdep_ovsl_is_held()) { if (ct_limit->zone == new_ct_limit->zone) { hlist_replace_rcu(&ct_limit->hlist_node, &new_ct_limit->hlist_node); kfree_rcu(ct_limit, rcu); return; } } hlist_add_head_rcu(&new_ct_limit->hlist_node, head); } /* Call with ovs_mutex */ static void ct_limit_del(const struct ovs_ct_limit_info *info, u16 zone) { struct ovs_ct_limit *ct_limit; struct hlist_head *head; struct hlist_node *n; head = ct_limit_hash_bucket(info, zone); hlist_for_each_entry_safe(ct_limit, n, head, hlist_node) { if (ct_limit->zone == zone) { hlist_del_rcu(&ct_limit->hlist_node); kfree_rcu(ct_limit, rcu); return; } } } /* Call with RCU read lock */ static u32 ct_limit_get(const struct ovs_ct_limit_info *info, u16 zone) { struct ovs_ct_limit *ct_limit; struct hlist_head *head; head = ct_limit_hash_bucket(info, zone); hlist_for_each_entry_rcu(ct_limit, head, hlist_node) { if (ct_limit->zone == zone) return ct_limit->limit; } return info->default_limit; } static int ovs_ct_check_limit(struct net *net, const struct sk_buff *skb, const struct ovs_conntrack_info *info) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); const struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; u32 per_zone_limit, connections; u32 conncount_key; conncount_key = info->zone.id; per_zone_limit = ct_limit_get(ct_limit_info, info->zone.id); if (per_zone_limit == OVS_CT_LIMIT_UNLIMITED) return 0; connections = nf_conncount_count_skb(net, skb, info->family, ct_limit_info->data, &conncount_key); if (connections > per_zone_limit) return -ENOMEM; return 0; } #endif /* Lookup connection and confirm if unconfirmed. */ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; int err; err = __ovs_ct_lookup(net, key, info, skb); if (err) return err; /* The connection could be invalid, in which case this is a no-op.*/ ct = nf_ct_get(skb, &ctinfo); if (!ct) return 0; #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) if (static_branch_unlikely(&ovs_ct_limit_enabled)) { if (!nf_ct_is_confirmed(ct)) { err = ovs_ct_check_limit(net, skb, info); if (err) { net_warn_ratelimited("openvswitch: zone: %u " "exceeds conntrack limit\n", info->zone.id); return err; } } } #endif /* Set the conntrack event mask if given. NEW and DELETE events have * their own groups, but the NFNLGRP_CONNTRACK_UPDATE group listener * typically would receive many kinds of updates. Setting the event * mask allows those events to be filtered. The set event mask will * remain in effect for the lifetime of the connection unless changed * by a further CT action with both the commit flag and the eventmask * option. */ if (info->have_eventmask) { struct nf_conntrack_ecache *cache = nf_ct_ecache_find(ct); if (cache) cache->ctmask = info->eventmask; } /* Apply changes before confirming the connection so that the initial * conntrack NEW netlink event carries the values given in the CT * action. */ if (info->mark.mask) { err = ovs_ct_set_mark(ct, key, info->mark.value, info->mark.mask); if (err) return err; } if (!nf_ct_is_confirmed(ct)) { err = ovs_ct_init_labels(ct, key, &info->labels.value, &info->labels.mask); if (err) return err; nf_conn_act_ct_ext_add(skb, ct, ctinfo); } else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && labels_nonzero(&info->labels.mask)) { err = ovs_ct_set_labels(ct, key, &info->labels.value, &info->labels.mask); if (err) return err; } /* This will take care of sending queued events even if the connection * is already confirmed. */ err = nf_conntrack_confirm(skb); return verdict_to_errno(err); } /* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero * value if 'skb' is freed. */ int ovs_ct_execute(struct net *net, struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_conntrack_info *info) { int nh_ofs; int err; /* The conntrack module expects to be working at L3. */ nh_ofs = skb_network_offset(skb); skb_pull_rcsum(skb, nh_ofs); err = nf_ct_skb_network_trim(skb, info->family); if (err) { kfree_skb(skb); return err; } if (key->ip.frag != OVS_FRAG_TYPE_NONE) { err = ovs_ct_handle_fragments(net, key, info->zone.id, info->family, skb); if (err) return err; } if (info->commit) err = ovs_ct_commit(net, key, info, skb); else err = ovs_ct_lookup(net, key, info, skb); /* conntrack core returned NF_STOLEN */ if (err == -EINPROGRESS) return err; skb_push_rcsum(skb, nh_ofs); if (err) ovs_kfree_skb_reason(skb, OVS_DROP_CONNTRACK); return err; } int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); nf_ct_put(ct); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); if (key) ovs_ct_fill_key(skb, key, false); return 0; } #if IS_ENABLED(CONFIG_NF_NAT) static int parse_nat(const struct nlattr *attr, struct ovs_conntrack_info *info, bool log) { struct nlattr *a; int rem; bool have_ip_max = false; bool have_proto_max = false; bool ip_vers = (info->family == NFPROTO_IPV6); nla_for_each_nested(a, attr, rem) { static const int ovs_nat_attr_lens[OVS_NAT_ATTR_MAX + 1][2] = { [OVS_NAT_ATTR_SRC] = {0, 0}, [OVS_NAT_ATTR_DST] = {0, 0}, [OVS_NAT_ATTR_IP_MIN] = {sizeof(struct in_addr), sizeof(struct in6_addr)}, [OVS_NAT_ATTR_IP_MAX] = {sizeof(struct in_addr), sizeof(struct in6_addr)}, [OVS_NAT_ATTR_PROTO_MIN] = {sizeof(u16), sizeof(u16)}, [OVS_NAT_ATTR_PROTO_MAX] = {sizeof(u16), sizeof(u16)}, [OVS_NAT_ATTR_PERSISTENT] = {0, 0}, [OVS_NAT_ATTR_PROTO_HASH] = {0, 0}, [OVS_NAT_ATTR_PROTO_RANDOM] = {0, 0}, }; int type = nla_type(a); if (type > OVS_NAT_ATTR_MAX) { OVS_NLERR(log, "Unknown NAT attribute (type=%d, max=%d)", type, OVS_NAT_ATTR_MAX); return -EINVAL; } if (nla_len(a) != ovs_nat_attr_lens[type][ip_vers]) { OVS_NLERR(log, "NAT attribute type %d has unexpected length (%d != %d)", type, nla_len(a), ovs_nat_attr_lens[type][ip_vers]); return -EINVAL; } switch (type) { case OVS_NAT_ATTR_SRC: case OVS_NAT_ATTR_DST: if (info->nat) { OVS_NLERR(log, "Only one type of NAT may be specified"); return -ERANGE; } info->nat |= OVS_CT_NAT; info->nat |= ((type == OVS_NAT_ATTR_SRC) ? OVS_CT_SRC_NAT : OVS_CT_DST_NAT); break; case OVS_NAT_ATTR_IP_MIN: nla_memcpy(&info->range.min_addr, a, sizeof(info->range.min_addr)); info->range.flags |= NF_NAT_RANGE_MAP_IPS; break; case OVS_NAT_ATTR_IP_MAX: have_ip_max = true; nla_memcpy(&info->range.max_addr, a, sizeof(info->range.max_addr)); info->range.flags |= NF_NAT_RANGE_MAP_IPS; break; case OVS_NAT_ATTR_PROTO_MIN: info->range.min_proto.all = htons(nla_get_u16(a)); info->range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; break; case OVS_NAT_ATTR_PROTO_MAX: have_proto_max = true; info->range.max_proto.all = htons(nla_get_u16(a)); info->range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; break; case OVS_NAT_ATTR_PERSISTENT: info->range.flags |= NF_NAT_RANGE_PERSISTENT; break; case OVS_NAT_ATTR_PROTO_HASH: info->range.flags |= NF_NAT_RANGE_PROTO_RANDOM; break; case OVS_NAT_ATTR_PROTO_RANDOM: info->range.flags |= NF_NAT_RANGE_PROTO_RANDOM_FULLY; break; default: OVS_NLERR(log, "Unknown nat attribute (%d)", type); return -EINVAL; } } if (rem > 0) { OVS_NLERR(log, "NAT attribute has %d unknown bytes", rem); return -EINVAL; } if (!info->nat) { /* Do not allow flags if no type is given. */ if (info->range.flags) { OVS_NLERR(log, "NAT flags may be given only when NAT range (SRC or DST) is also specified." ); return -EINVAL; } info->nat = OVS_CT_NAT; /* NAT existing connections. */ } else if (!info->commit) { OVS_NLERR(log, "NAT attributes may be specified only when CT COMMIT flag is also specified." ); return -EINVAL; } /* Allow missing IP_MAX. */ if (info->range.flags & NF_NAT_RANGE_MAP_IPS && !have_ip_max) { memcpy(&info->range.max_addr, &info->range.min_addr, sizeof(info->range.max_addr)); } /* Allow missing PROTO_MAX. */ if (info->range.flags & NF_NAT_RANGE_PROTO_SPECIFIED && !have_proto_max) { info->range.max_proto.all = info->range.min_proto.all; } return 0; } #endif static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { [OVS_CT_ATTR_COMMIT] = { .minlen = 0, .maxlen = 0 }, [OVS_CT_ATTR_FORCE_COMMIT] = { .minlen = 0, .maxlen = 0 }, [OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16), .maxlen = sizeof(u16) }, [OVS_CT_ATTR_MARK] = { .minlen = sizeof(struct md_mark), .maxlen = sizeof(struct md_mark) }, [OVS_CT_ATTR_LABELS] = { .minlen = sizeof(struct md_labels), .maxlen = sizeof(struct md_labels) }, [OVS_CT_ATTR_HELPER] = { .minlen = 1, .maxlen = NF_CT_HELPER_NAME_LEN }, #if IS_ENABLED(CONFIG_NF_NAT) /* NAT length is checked when parsing the nested attributes. */ [OVS_CT_ATTR_NAT] = { .minlen = 0, .maxlen = INT_MAX }, #endif [OVS_CT_ATTR_EVENTMASK] = { .minlen = sizeof(u32), .maxlen = sizeof(u32) }, [OVS_CT_ATTR_TIMEOUT] = { .minlen = 1, .maxlen = CTNL_TIMEOUT_NAME_MAX }, }; static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, const char **helper, bool log) { struct nlattr *a; int rem; nla_for_each_nested(a, attr, rem) { int type = nla_type(a); int maxlen; int minlen; if (type > OVS_CT_ATTR_MAX) { OVS_NLERR(log, "Unknown conntrack attr (type=%d, max=%d)", type, OVS_CT_ATTR_MAX); return -EINVAL; } maxlen = ovs_ct_attr_lens[type].maxlen; minlen = ovs_ct_attr_lens[type].minlen; if (nla_len(a) < minlen || nla_len(a) > maxlen) { OVS_NLERR(log, "Conntrack attr type has unexpected length (type=%d, length=%d, expected=%d)", type, nla_len(a), maxlen); return -EINVAL; } switch (type) { case OVS_CT_ATTR_FORCE_COMMIT: info->force = true; fallthrough; case OVS_CT_ATTR_COMMIT: info->commit = true; break; #ifdef CONFIG_NF_CONNTRACK_ZONES case OVS_CT_ATTR_ZONE: info->zone.id = nla_get_u16(a); break; #endif #ifdef CONFIG_NF_CONNTRACK_MARK case OVS_CT_ATTR_MARK: { struct md_mark *mark = nla_data(a); if (!mark->mask) { OVS_NLERR(log, "ct_mark mask cannot be 0"); return -EINVAL; } info->mark = *mark; break; } #endif #ifdef CONFIG_NF_CONNTRACK_LABELS case OVS_CT_ATTR_LABELS: { struct md_labels *labels = nla_data(a); if (!labels_nonzero(&labels->mask)) { OVS_NLERR(log, "ct_labels mask cannot be 0"); return -EINVAL; } info->labels = *labels; break; } #endif case OVS_CT_ATTR_HELPER: *helper = nla_data(a); if (!string_is_terminated(*helper, nla_len(a))) { OVS_NLERR(log, "Invalid conntrack helper"); return -EINVAL; } break; #if IS_ENABLED(CONFIG_NF_NAT) case OVS_CT_ATTR_NAT: { int err = parse_nat(a, info, log); if (err) return err; break; } #endif case OVS_CT_ATTR_EVENTMASK: info->have_eventmask = true; info->eventmask = nla_get_u32(a); break; #ifdef CONFIG_NF_CONNTRACK_TIMEOUT case OVS_CT_ATTR_TIMEOUT: memcpy(info->timeout, nla_data(a), nla_len(a)); if (!string_is_terminated(info->timeout, nla_len(a))) { OVS_NLERR(log, "Invalid conntrack timeout"); return -EINVAL; } break; #endif default: OVS_NLERR(log, "Unknown conntrack attr (%d)", type); return -EINVAL; } } #ifdef CONFIG_NF_CONNTRACK_MARK if (!info->commit && info->mark.mask) { OVS_NLERR(log, "Setting conntrack mark requires 'commit' flag."); return -EINVAL; } #endif #ifdef CONFIG_NF_CONNTRACK_LABELS if (!info->commit && labels_nonzero(&info->labels.mask)) { OVS_NLERR(log, "Setting conntrack labels requires 'commit' flag."); return -EINVAL; } #endif if (rem > 0) { OVS_NLERR(log, "Conntrack attr has %d unknown bytes", rem); return -EINVAL; } return 0; } bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr) { if (attr == OVS_KEY_ATTR_CT_STATE) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && attr == OVS_KEY_ATTR_CT_ZONE) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && attr == OVS_KEY_ATTR_CT_MARK) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && attr == OVS_KEY_ATTR_CT_LABELS) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); return ovs_net->xt_label; } return false; } int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, bool log) { struct ovs_conntrack_info ct_info; const char *helper = NULL; u16 family; int err; family = key_to_nfproto(key); if (family == NFPROTO_UNSPEC) { OVS_NLERR(log, "ct family unspecified"); return -EINVAL; } memset(&ct_info, 0, sizeof(ct_info)); ct_info.family = family; nf_ct_zone_init(&ct_info.zone, NF_CT_DEFAULT_ZONE_ID, NF_CT_DEFAULT_ZONE_DIR, 0); err = parse_ct(attr, &ct_info, &helper, log); if (err) return err; /* Set up template for tracking connections in specific zones. */ ct_info.ct = nf_ct_tmpl_alloc(net, &ct_info.zone, GFP_KERNEL); if (!ct_info.ct) { OVS_NLERR(log, "Failed to allocate conntrack template"); return -ENOMEM; } if (ct_info.timeout[0]) { if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto, ct_info.timeout)) OVS_NLERR(log, "Failed to associated timeout policy '%s'", ct_info.timeout); else ct_info.nf_ct_timeout = rcu_dereference( nf_ct_timeout_find(ct_info.ct)->timeout); } if (helper) { err = nf_ct_add_helper(ct_info.ct, helper, ct_info.family, key->ip.proto, ct_info.nat, &ct_info.helper); if (err) { OVS_NLERR(log, "Failed to add %s helper %d", helper, err); goto err_free_ct; } } err = ovs_nla_add_action(sfa, OVS_ACTION_ATTR_CT, &ct_info, sizeof(ct_info), log); if (err) goto err_free_ct; if (ct_info.commit) __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); return 0; err_free_ct: __ovs_ct_free_action(&ct_info); return err; } #if IS_ENABLED(CONFIG_NF_NAT) static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, struct sk_buff *skb) { struct nlattr *start; start = nla_nest_start_noflag(skb, OVS_CT_ATTR_NAT); if (!start) return false; if (info->nat & OVS_CT_SRC_NAT) { if (nla_put_flag(skb, OVS_NAT_ATTR_SRC)) return false; } else if (info->nat & OVS_CT_DST_NAT) { if (nla_put_flag(skb, OVS_NAT_ATTR_DST)) return false; } else { goto out; } if (info->range.flags & NF_NAT_RANGE_MAP_IPS) { if (IS_ENABLED(CONFIG_NF_NAT) && info->family == NFPROTO_IPV4) { if (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MIN, info->range.min_addr.ip) || (info->range.max_addr.ip != info->range.min_addr.ip && (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MAX, info->range.max_addr.ip)))) return false; } else if (IS_ENABLED(CONFIG_IPV6) && info->family == NFPROTO_IPV6) { if (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MIN, &info->range.min_addr.in6) || (memcmp(&info->range.max_addr.in6, &info->range.min_addr.in6, sizeof(info->range.max_addr.in6)) && (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MAX, &info->range.max_addr.in6)))) return false; } else { return false; } } if (info->range.flags & NF_NAT_RANGE_PROTO_SPECIFIED && (nla_put_u16(skb, OVS_NAT_ATTR_PROTO_MIN, ntohs(info->range.min_proto.all)) || (info->range.max_proto.all != info->range.min_proto.all && nla_put_u16(skb, OVS_NAT_ATTR_PROTO_MAX, ntohs(info->range.max_proto.all))))) return false; if (info->range.flags & NF_NAT_RANGE_PERSISTENT && nla_put_flag(skb, OVS_NAT_ATTR_PERSISTENT)) return false; if (info->range.flags & NF_NAT_RANGE_PROTO_RANDOM && nla_put_flag(skb, OVS_NAT_ATTR_PROTO_HASH)) return false; if (info->range.flags & NF_NAT_RANGE_PROTO_RANDOM_FULLY && nla_put_flag(skb, OVS_NAT_ATTR_PROTO_RANDOM)) return false; out: nla_nest_end(skb, start); return true; } #endif int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, struct sk_buff *skb) { struct nlattr *start; start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_CT); if (!start) return -EMSGSIZE; if (ct_info->commit && nla_put_flag(skb, ct_info->force ? OVS_CT_ATTR_FORCE_COMMIT : OVS_CT_ATTR_COMMIT)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && ct_info->mark.mask && nla_put(skb, OVS_CT_ATTR_MARK, sizeof(ct_info->mark), &ct_info->mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && labels_nonzero(&ct_info->labels.mask) && nla_put(skb, OVS_CT_ATTR_LABELS, sizeof(ct_info->labels), &ct_info->labels)) return -EMSGSIZE; if (ct_info->helper) { if (nla_put_string(skb, OVS_CT_ATTR_HELPER, ct_info->helper->name)) return -EMSGSIZE; } if (ct_info->have_eventmask && nla_put_u32(skb, OVS_CT_ATTR_EVENTMASK, ct_info->eventmask)) return -EMSGSIZE; if (ct_info->timeout[0]) { if (nla_put_string(skb, OVS_CT_ATTR_TIMEOUT, ct_info->timeout)) return -EMSGSIZE; } #if IS_ENABLED(CONFIG_NF_NAT) if (ct_info->nat && !ovs_ct_nat_to_attr(ct_info, skb)) return -EMSGSIZE; #endif nla_nest_end(skb, start); return 0; } void ovs_ct_free_action(const struct nlattr *a) { struct ovs_conntrack_info *ct_info = nla_data(a); __ovs_ct_free_action(ct_info); } static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info) { if (ct_info->helper) { #if IS_ENABLED(CONFIG_NF_NAT) if (ct_info->nat) nf_nat_helper_put(ct_info->helper); #endif nf_conntrack_helper_put(ct_info->helper); } if (ct_info->ct) { if (ct_info->timeout[0]) nf_ct_destroy_timeout(ct_info->ct); nf_ct_tmpl_free(ct_info->ct); } } #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) static int ovs_ct_limit_init(struct net *net, struct ovs_net *ovs_net) { int i, err; ovs_net->ct_limit_info = kmalloc_obj(*ovs_net->ct_limit_info); if (!ovs_net->ct_limit_info) return -ENOMEM; ovs_net->ct_limit_info->default_limit = OVS_CT_LIMIT_DEFAULT; ovs_net->ct_limit_info->limits = kmalloc_objs(struct hlist_head, CT_LIMIT_HASH_BUCKETS); if (!ovs_net->ct_limit_info->limits) { kfree(ovs_net->ct_limit_info); return -ENOMEM; } for (i = 0; i < CT_LIMIT_HASH_BUCKETS; i++) INIT_HLIST_HEAD(&ovs_net->ct_limit_info->limits[i]); ovs_net->ct_limit_info->data = nf_conncount_init(net, sizeof(u32)); if (IS_ERR(ovs_net->ct_limit_info->data)) { err = PTR_ERR(ovs_net->ct_limit_info->data); kfree(ovs_net->ct_limit_info->limits); kfree(ovs_net->ct_limit_info); pr_err("openvswitch: failed to init nf_conncount %d\n", err); return err; } return 0; } static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) { const struct ovs_ct_limit_info *info = ovs_net->ct_limit_info; int i; nf_conncount_destroy(net, info->data); for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; struct hlist_node *next; hlist_for_each_entry_safe(ct_limit, next, head, hlist_node) kfree_rcu(ct_limit, rcu); } kfree(info->limits); kfree(info); } static struct sk_buff * ovs_ct_limit_cmd_reply_start(struct genl_info *info, u8 cmd, struct ovs_header **ovs_reply_header) { struct ovs_header *ovs_header = genl_info_userhdr(info); struct sk_buff *skb; skb = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM); *ovs_reply_header = genlmsg_put(skb, info->snd_portid, info->snd_seq, &dp_ct_limit_genl_family, 0, cmd); if (!*ovs_reply_header) { nlmsg_free(skb); return ERR_PTR(-EMSGSIZE); } (*ovs_reply_header)->dp_ifindex = ovs_header->dp_ifindex; return skb; } static bool check_zone_id(int zone_id, u16 *pzone) { if (zone_id >= 0 && zone_id <= 65535) { *pzone = (u16)zone_id; return true; } return false; } static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit, struct ovs_ct_limit_info *info) { struct ovs_zone_limit *zone_limit; int rem; u16 zone; rem = NLA_ALIGN(nla_len(nla_zone_limit)); zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit); while (rem >= sizeof(*zone_limit)) { if (unlikely(zone_limit->zone_id == OVS_ZONE_LIMIT_DEFAULT_ZONE)) { ovs_lock(); info->default_limit = zone_limit->limit; ovs_unlock(); } else if (unlikely(!check_zone_id( zone_limit->zone_id, &zone))) { OVS_NLERR(true, "zone id is out of range"); } else { struct ovs_ct_limit *ct_limit; ct_limit = kmalloc_obj(*ct_limit, GFP_KERNEL_ACCOUNT); if (!ct_limit) return -ENOMEM; ct_limit->zone = zone; ct_limit->limit = zone_limit->limit; ovs_lock(); ct_limit_set(info, ct_limit); ovs_unlock(); } rem -= NLA_ALIGN(sizeof(*zone_limit)); zone_limit = (struct ovs_zone_limit *)((u8 *)zone_limit + NLA_ALIGN(sizeof(*zone_limit))); } if (rem) OVS_NLERR(true, "set zone limit has %d unknown bytes", rem); return 0; } static int ovs_ct_limit_del_zone_limit(struct nlattr *nla_zone_limit, struct ovs_ct_limit_info *info) { struct ovs_zone_limit *zone_limit; int rem; u16 zone; rem = NLA_ALIGN(nla_len(nla_zone_limit)); zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit); while (rem >= sizeof(*zone_limit)) { if (unlikely(zone_limit->zone_id == OVS_ZONE_LIMIT_DEFAULT_ZONE)) { ovs_lock(); info->default_limit = OVS_CT_LIMIT_DEFAULT; ovs_unlock(); } else if (unlikely(!check_zone_id( zone_limit->zone_id, &zone))) { OVS_NLERR(true, "zone id is out of range"); } else { ovs_lock(); ct_limit_del(info, zone); ovs_unlock(); } rem -= NLA_ALIGN(sizeof(*zone_limit)); zone_limit = (struct ovs_zone_limit *)((u8 *)zone_limit + NLA_ALIGN(sizeof(*zone_limit))); } if (rem) OVS_NLERR(true, "del zone limit has %d unknown bytes", rem); return 0; } static int ovs_ct_limit_get_default_limit(struct ovs_ct_limit_info *info, struct sk_buff *reply) { struct ovs_zone_limit zone_limit = { .zone_id = OVS_ZONE_LIMIT_DEFAULT_ZONE, .limit = info->default_limit, }; return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit); } static int __ovs_ct_limit_get_zone_limit(struct net *net, struct nf_conncount_data *data, u16 zone_id, u32 limit, struct sk_buff *reply) { struct nf_conntrack_zone ct_zone; struct ovs_zone_limit zone_limit; u32 conncount_key = zone_id; zone_limit.zone_id = zone_id; zone_limit.limit = limit; nf_ct_zone_init(&ct_zone, zone_id, NF_CT_DEFAULT_ZONE_DIR, 0); zone_limit.count = nf_conncount_count_skb(net, NULL, 0, data, &conncount_key); return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit); } static int ovs_ct_limit_get_zone_limit(struct net *net, struct nlattr *nla_zone_limit, struct ovs_ct_limit_info *info, struct sk_buff *reply) { struct ovs_zone_limit *zone_limit; int rem, err; u32 limit; u16 zone; rem = NLA_ALIGN(nla_len(nla_zone_limit)); zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit); while (rem >= sizeof(*zone_limit)) { if (unlikely(zone_limit->zone_id == OVS_ZONE_LIMIT_DEFAULT_ZONE)) { err = ovs_ct_limit_get_default_limit(info, reply); if (err) return err; } else if (unlikely(!check_zone_id(zone_limit->zone_id, &zone))) { OVS_NLERR(true, "zone id is out of range"); } else { rcu_read_lock(); limit = ct_limit_get(info, zone); err = __ovs_ct_limit_get_zone_limit( net, info->data, zone, limit, reply); rcu_read_unlock(); if (err) return err; } rem -= NLA_ALIGN(sizeof(*zone_limit)); zone_limit = (struct ovs_zone_limit *)((u8 *)zone_limit + NLA_ALIGN(sizeof(*zone_limit))); } if (rem) OVS_NLERR(true, "get zone limit has %d unknown bytes", rem); return 0; } static int ovs_ct_limit_get_all_zone_limit(struct net *net, struct ovs_ct_limit_info *info, struct sk_buff *reply) { struct ovs_ct_limit *ct_limit; struct hlist_head *head; int i, err = 0; err = ovs_ct_limit_get_default_limit(info, reply); if (err) return err; rcu_read_lock(); for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { head = &info->limits[i]; hlist_for_each_entry_rcu(ct_limit, head, hlist_node) { err = __ovs_ct_limit_get_zone_limit(net, info->data, ct_limit->zone, ct_limit->limit, reply); if (err) goto exit_err; } } exit_err: rcu_read_unlock(); return err; } static int ovs_ct_limit_cmd_set(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct ovs_net *ovs_net = net_generic(sock_net(skb->sk), ovs_net_id); struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; int err; reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_SET, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply); if (!a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) { err = -EINVAL; goto exit_err; } err = ovs_ct_limit_set_zone_limit(a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], ct_limit_info); if (err) goto exit_err; static_branch_enable(&ovs_ct_limit_enabled); genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); exit_err: nlmsg_free(reply); return err; } static int ovs_ct_limit_cmd_del(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct ovs_net *ovs_net = net_generic(sock_net(skb->sk), ovs_net_id); struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; int err; reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_DEL, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply); if (!a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) { err = -EINVAL; goto exit_err; } err = ovs_ct_limit_del_zone_limit(a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], ct_limit_info); if (err) goto exit_err; genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); exit_err: nlmsg_free(reply); return err; } static int ovs_ct_limit_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct nlattr *nla_reply; struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct net *net = sock_net(skb->sk); struct ovs_net *ovs_net = net_generic(net, ovs_net_id); struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; int err; reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_GET, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply); nla_reply = nla_nest_start_noflag(reply, OVS_CT_LIMIT_ATTR_ZONE_LIMIT); if (!nla_reply) { err = -EMSGSIZE; goto exit_err; } if (a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) { err = ovs_ct_limit_get_zone_limit( net, a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], ct_limit_info, reply); if (err) goto exit_err; } else { err = ovs_ct_limit_get_all_zone_limit(net, ct_limit_info, reply); if (err) goto exit_err; } nla_nest_end(reply, nla_reply); genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); exit_err: nlmsg_free(reply); return err; } static const struct genl_small_ops ct_limit_genl_ops[] = { { .cmd = OVS_CT_LIMIT_CMD_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN * privilege. */ .doit = ovs_ct_limit_cmd_set, }, { .cmd = OVS_CT_LIMIT_CMD_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN * privilege. */ .doit = ovs_ct_limit_cmd_del, }, { .cmd = OVS_CT_LIMIT_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, /* OK for unprivileged users. */ .doit = ovs_ct_limit_cmd_get, }, }; static const struct genl_multicast_group ovs_ct_limit_multicast_group = { .name = OVS_CT_LIMIT_MCGROUP, }; struct genl_family dp_ct_limit_genl_family __ro_after_init = { .hdrsize = sizeof(struct ovs_header), .name = OVS_CT_LIMIT_FAMILY, .version = OVS_CT_LIMIT_VERSION, .maxattr = OVS_CT_LIMIT_ATTR_MAX, .policy = ct_limit_policy, .netnsok = true, .parallel_ops = true, .small_ops = ct_limit_genl_ops, .n_small_ops = ARRAY_SIZE(ct_limit_genl_ops), .resv_start_op = OVS_CT_LIMIT_CMD_GET + 1, .mcgrps = &ovs_ct_limit_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, }; #endif int ovs_ct_init(struct net *net) { unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_net *ovs_net = net_generic(net, ovs_net_id); if (nf_connlabels_get(net, n_bits - 1)) { ovs_net->xt_label = false; OVS_NLERR(true, "Failed to set connlabel length"); } else { ovs_net->xt_label = true; } #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) return ovs_ct_limit_init(net, ovs_net); #else return 0; #endif } void ovs_ct_exit(struct net *net) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) ovs_ct_limit_exit(net, ovs_net); #endif if (ovs_net->xt_label) nf_connlabels_put(net); } |
| 12 138 3 13 8547 1 112 23 3512 116 100 81 1 158 203 70 4 15 10 135 22 96 152 12 6 293 10 23 79 25 620 29 8 30 36 82 32 42 3 63 7352 3820 420 505 594 15 35 24 28 77 21 24 74 4 822 5420 850 825 59 62 44 31 7 24 21 8 24 34 7 6 1 16 14 969 5 24 1624 7699 8547 4003 4798 5281 3812 693 83 237 39 68 2 4695 4482 743 740 57 7 7 1076 577 101 3 42 40 111 54 17 3 1 2 5201 21 21 16 4 17 11 9 101 79 395 617 16 79 30 33 16 1 39 16 8 26 2 26 11 27 1 34 25 3737 6169 5 1 5 97 6 13 81 3126 3026 171 513 803 120 78 5423 2010 24 28 882 1608 105 5213 1 3852 3052 855 19 808 32 32 17 18 18 3 210 124 19 3 168 4 1 4 162 95 186 3 2 3 859 146 146 3 64 59 740 94 485 41 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Linux Security Module Hook declarations. * * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> * Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2001 James Morris <jmorris@intercode.com.au> * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group) * Copyright (C) 2015 Intel Corporation. * Copyright (C) 2015 Casey Schaufler <casey@schaufler-ca.com> * Copyright (C) 2016 Mellanox Techonologies * Copyright (C) 2020 Google LLC. */ /* * The macro LSM_HOOK is used to define the data structures required by * the LSM framework using the pattern: * * LSM_HOOK(<return_type>, <default_value>, <hook_name>, args...) * * struct security_hook_heads { * #define LSM_HOOK(RET, DEFAULT, NAME, ...) struct hlist_head NAME; * #include <linux/lsm_hook_defs.h> * #undef LSM_HOOK * }; */ LSM_HOOK(int, 0, binder_set_context_mgr, const struct cred *mgr) LSM_HOOK(int, 0, binder_transaction, const struct cred *from, const struct cred *to) LSM_HOOK(int, 0, binder_transfer_binder, const struct cred *from, const struct cred *to) LSM_HOOK(int, 0, binder_transfer_file, const struct cred *from, const struct cred *to, const struct file *file) LSM_HOOK(int, 0, ptrace_access_check, struct task_struct *child, unsigned int mode) LSM_HOOK(int, 0, ptrace_traceme, struct task_struct *parent) LSM_HOOK(int, 0, capget, const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) LSM_HOOK(int, 0, capset, struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) LSM_HOOK(int, 0, capable, const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) LSM_HOOK(int, 0, quotactl, int cmds, int type, int id, const struct super_block *sb) LSM_HOOK(int, 0, quota_on, struct dentry *dentry) LSM_HOOK(int, 0, syslog, int type) LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, const struct file *file) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, const struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, const struct linux_binprm *bprm) LSM_HOOK(int, 0, fs_context_submount, struct fs_context *fc, struct super_block *reference) LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc, struct fs_context *src_sc) LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc, struct fs_parameter *param) LSM_HOOK(int, 0, sb_alloc_security, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_delete, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_security, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_mnt_opts, void *mnt_opts) LSM_HOOK(int, 0, sb_eat_lsm_opts, char *orig, void **mnt_opts) LSM_HOOK(int, 0, sb_mnt_opts_compat, struct super_block *sb, void *mnt_opts) LSM_HOOK(int, 0, sb_remount, struct super_block *sb, void *mnt_opts) LSM_HOOK(int, 0, sb_kern_mount, const struct super_block *sb) LSM_HOOK(int, 0, sb_show_options, struct seq_file *m, struct super_block *sb) LSM_HOOK(int, 0, sb_statfs, struct dentry *dentry) LSM_HOOK(int, 0, sb_mount, const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) LSM_HOOK(int, 0, sb_umount, struct vfsmount *mnt, int flags) LSM_HOOK(int, 0, sb_pivotroot, const struct path *old_path, const struct path *new_path) LSM_HOOK(int, 0, sb_set_mnt_opts, struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) LSM_HOOK(int, 0, sb_clone_mnt_opts, const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) LSM_HOOK(int, 0, move_mount, const struct path *from_path, const struct path *to_path) LSM_HOOK(int, -EOPNOTSUPP, dentry_init_security, struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, struct lsm_context *cp) LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode, const struct qstr *name, const struct cred *old, struct cred *new) #ifdef CONFIG_SECURITY_PATH LSM_HOOK(int, 0, path_unlink, const struct path *dir, struct dentry *dentry) LSM_HOOK(int, 0, path_mkdir, const struct path *dir, struct dentry *dentry, umode_t mode) LSM_HOOK(int, 0, path_rmdir, const struct path *dir, struct dentry *dentry) LSM_HOOK(int, 0, path_mknod, const struct path *dir, struct dentry *dentry, umode_t mode, unsigned int dev) LSM_HOOK(void, LSM_RET_VOID, path_post_mknod, struct mnt_idmap *idmap, struct dentry *dentry) LSM_HOOK(int, 0, path_truncate, const struct path *path) LSM_HOOK(int, 0, path_symlink, const struct path *dir, struct dentry *dentry, const char *old_name) LSM_HOOK(int, 0, path_link, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) LSM_HOOK(int, 0, path_rename, const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry, unsigned int flags) LSM_HOOK(int, 0, path_chmod, const struct path *path, umode_t mode) LSM_HOOK(int, 0, path_chown, const struct path *path, kuid_t uid, kgid_t gid) LSM_HOOK(int, 0, path_chroot, const struct path *path) #endif /* CONFIG_SECURITY_PATH */ /* Needed for inode based security check */ LSM_HOOK(int, 0, path_notify, const struct path *path, u64 mask, unsigned int obj_type) LSM_HOOK(int, 0, inode_alloc_security, struct inode *inode) LSM_HOOK(void, LSM_RET_VOID, inode_free_security, struct inode *inode) LSM_HOOK(void, LSM_RET_VOID, inode_free_security_rcu, void *inode_security) LSM_HOOK(int, -EOPNOTSUPP, inode_init_security, struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) LSM_HOOK(int, 0, inode_init_security_anon, struct inode *inode, const struct qstr *name, const struct inode *context_inode) LSM_HOOK(int, 0, inode_create, struct inode *dir, struct dentry *dentry, umode_t mode) LSM_HOOK(void, LSM_RET_VOID, inode_post_create_tmpfile, struct mnt_idmap *idmap, struct inode *inode) LSM_HOOK(int, 0, inode_link, struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) LSM_HOOK(int, 0, inode_unlink, struct inode *dir, struct dentry *dentry) LSM_HOOK(int, 0, inode_symlink, struct inode *dir, struct dentry *dentry, const char *old_name) LSM_HOOK(int, 0, inode_mkdir, struct inode *dir, struct dentry *dentry, umode_t mode) LSM_HOOK(int, 0, inode_rmdir, struct inode *dir, struct dentry *dentry) LSM_HOOK(int, 0, inode_mknod, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) LSM_HOOK(int, 0, inode_rename, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) LSM_HOOK(int, 0, inode_readlink, struct dentry *dentry) LSM_HOOK(int, 0, inode_follow_link, struct dentry *dentry, struct inode *inode, bool rcu) LSM_HOOK(int, 0, inode_permission, struct inode *inode, int mask) LSM_HOOK(int, 0, inode_setattr, struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) LSM_HOOK(void, LSM_RET_VOID, inode_post_setattr, struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) LSM_HOOK(int, 0, inode_getattr, const struct path *path) LSM_HOOK(int, 0, inode_xattr_skipcap, const char *name) LSM_HOOK(int, 0, inode_setxattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) LSM_HOOK(void, LSM_RET_VOID, inode_post_setxattr, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_getxattr, struct dentry *dentry, const char *name) LSM_HOOK(int, 0, inode_listxattr, struct dentry *dentry) LSM_HOOK(int, 0, inode_removexattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name) LSM_HOOK(void, LSM_RET_VOID, inode_post_removexattr, struct dentry *dentry, const char *name) LSM_HOOK(int, 0, inode_file_setattr, struct dentry *dentry, struct file_kattr *fa) LSM_HOOK(int, 0, inode_file_getattr, struct dentry *dentry, struct file_kattr *fa) LSM_HOOK(int, 0, inode_set_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) LSM_HOOK(void, LSM_RET_VOID, inode_post_set_acl, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) LSM_HOOK(int, 0, inode_get_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) LSM_HOOK(int, 0, inode_remove_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) LSM_HOOK(void, LSM_RET_VOID, inode_post_remove_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) LSM_HOOK(int, 0, inode_need_killpriv, struct dentry *dentry) LSM_HOOK(int, 0, inode_killpriv, struct mnt_idmap *idmap, struct dentry *dentry) LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char **buffer, ssize_t *remaining_size) LSM_HOOK(void, LSM_RET_VOID, inode_getlsmprop, struct inode *inode, struct lsm_prop *prop) LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new) LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, struct dentry *src, const char *name) LSM_HOOK(int, 0, inode_setintegrity, const struct inode *inode, enum lsm_integrity_type type, const void *value, size_t size) LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir, struct kernfs_node *kn) LSM_HOOK(int, 0, file_permission, struct file *file, int mask) LSM_HOOK(int, 0, file_alloc_security, struct file *file) LSM_HOOK(void, LSM_RET_VOID, file_release, struct file *file) LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file) LSM_HOOK(int, 0, backing_file_alloc, struct file *backing_file, const struct file *user_file) LSM_HOOK(void, LSM_RET_VOID, backing_file_free, struct file *backing_file) LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd, unsigned long arg) LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd, unsigned long arg) LSM_HOOK(int, 0, mmap_addr, unsigned long addr) LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) LSM_HOOK(int, 0, mmap_backing_file, struct vm_area_struct *vma, struct file *backing_file, struct file *user_file) LSM_HOOK(int, 0, file_mprotect, struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) LSM_HOOK(int, 0, file_lock, struct file *file, unsigned int cmd) LSM_HOOK(int, 0, file_fcntl, struct file *file, unsigned int cmd, unsigned long arg) LSM_HOOK(void, LSM_RET_VOID, file_set_fowner, struct file *file) LSM_HOOK(int, 0, file_send_sigiotask, struct task_struct *tsk, struct fown_struct *fown, int sig) LSM_HOOK(int, 0, file_receive, struct file *file) LSM_HOOK(int, 0, file_open, struct file *file) LSM_HOOK(int, 0, file_post_open, struct file *file, int mask) LSM_HOOK(int, 0, file_truncate, struct file *file) LSM_HOOK(int, 0, task_alloc, struct task_struct *task, u64 clone_flags) LSM_HOOK(void, LSM_RET_VOID, task_free, struct task_struct *task) LSM_HOOK(int, 0, cred_alloc_blank, struct cred *cred, gfp_t gfp) LSM_HOOK(void, LSM_RET_VOID, cred_free, struct cred *cred) LSM_HOOK(int, 0, cred_prepare, struct cred *new, const struct cred *old, gfp_t gfp) LSM_HOOK(void, LSM_RET_VOID, cred_transfer, struct cred *new, const struct cred *old) LSM_HOOK(void, LSM_RET_VOID, cred_getsecid, const struct cred *c, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, cred_getlsmprop, const struct cred *c, struct lsm_prop *prop) LSM_HOOK(int, 0, kernel_act_as, struct cred *new, u32 secid) LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode) LSM_HOOK(int, 0, kernel_module_request, char *kmod_name) LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id, bool contents) LSM_HOOK(int, 0, kernel_post_load_data, char *buf, loff_t size, enum kernel_load_data_id id, char *description) LSM_HOOK(int, 0, kernel_read_file, struct file *file, enum kernel_read_file_id id, bool contents) LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) LSM_HOOK(int, 0, task_fix_setuid, struct cred *new, const struct cred *old, int flags) LSM_HOOK(int, 0, task_fix_setgid, struct cred *new, const struct cred * old, int flags) LSM_HOOK(int, 0, task_fix_setgroups, struct cred *new, const struct cred * old) LSM_HOOK(int, 0, task_setpgid, struct task_struct *p, pid_t pgid) LSM_HOOK(int, 0, task_getpgid, struct task_struct *p) LSM_HOOK(int, 0, task_getsid, struct task_struct *p) LSM_HOOK(void, LSM_RET_VOID, current_getlsmprop_subj, struct lsm_prop *prop) LSM_HOOK(void, LSM_RET_VOID, task_getlsmprop_obj, struct task_struct *p, struct lsm_prop *prop) LSM_HOOK(int, 0, task_setnice, struct task_struct *p, int nice) LSM_HOOK(int, 0, task_setioprio, struct task_struct *p, int ioprio) LSM_HOOK(int, 0, task_getioprio, struct task_struct *p) LSM_HOOK(int, 0, task_prlimit, const struct cred *cred, const struct cred *tcred, unsigned int flags) LSM_HOOK(int, 0, task_setrlimit, struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) LSM_HOOK(int, 0, task_setscheduler, struct task_struct *p) LSM_HOOK(int, 0, task_getscheduler, struct task_struct *p) LSM_HOOK(int, 0, task_movememory, struct task_struct *p) LSM_HOOK(int, 0, task_kill, struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) LSM_HOOK(int, -ENOSYS, task_prctl, int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) LSM_HOOK(void, LSM_RET_VOID, task_to_inode, struct task_struct *p, struct inode *inode) LSM_HOOK(int, 0, userns_create, const struct cred *cred) LSM_HOOK(int, 0, ipc_permission, struct kern_ipc_perm *ipcp, short flag) LSM_HOOK(void, LSM_RET_VOID, ipc_getlsmprop, struct kern_ipc_perm *ipcp, struct lsm_prop *prop) LSM_HOOK(int, 0, msg_msg_alloc_security, struct msg_msg *msg) LSM_HOOK(void, LSM_RET_VOID, msg_msg_free_security, struct msg_msg *msg) LSM_HOOK(int, 0, msg_queue_alloc_security, struct kern_ipc_perm *perm) LSM_HOOK(void, LSM_RET_VOID, msg_queue_free_security, struct kern_ipc_perm *perm) LSM_HOOK(int, 0, msg_queue_associate, struct kern_ipc_perm *perm, int msqflg) LSM_HOOK(int, 0, msg_queue_msgctl, struct kern_ipc_perm *perm, int cmd) LSM_HOOK(int, 0, msg_queue_msgsnd, struct kern_ipc_perm *perm, struct msg_msg *msg, int msqflg) LSM_HOOK(int, 0, msg_queue_msgrcv, struct kern_ipc_perm *perm, struct msg_msg *msg, struct task_struct *target, long type, int mode) LSM_HOOK(int, 0, shm_alloc_security, struct kern_ipc_perm *perm) LSM_HOOK(void, LSM_RET_VOID, shm_free_security, struct kern_ipc_perm *perm) LSM_HOOK(int, 0, shm_associate, struct kern_ipc_perm *perm, int shmflg) LSM_HOOK(int, 0, shm_shmctl, struct kern_ipc_perm *perm, int cmd) LSM_HOOK(int, 0, shm_shmat, struct kern_ipc_perm *perm, char __user *shmaddr, int shmflg) LSM_HOOK(int, 0, sem_alloc_security, struct kern_ipc_perm *perm) LSM_HOOK(void, LSM_RET_VOID, sem_free_security, struct kern_ipc_perm *perm) LSM_HOOK(int, 0, sem_associate, struct kern_ipc_perm *perm, int semflg) LSM_HOOK(int, 0, sem_semctl, struct kern_ipc_perm *perm, int cmd) LSM_HOOK(int, 0, sem_semop, struct kern_ipc_perm *perm, struct sembuf *sops, unsigned nsops, int alter) LSM_HOOK(int, 0, netlink_send, struct sock *sk, struct sk_buff *skb) LSM_HOOK(void, LSM_RET_VOID, d_instantiate, struct dentry *dentry, struct inode *inode) LSM_HOOK(int, -EOPNOTSUPP, getselfattr, unsigned int attr, struct lsm_ctx __user *ctx, u32 *size, u32 flags) LSM_HOOK(int, -EOPNOTSUPP, setselfattr, unsigned int attr, struct lsm_ctx *ctx, u32 size, u32 flags) LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, const char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) LSM_HOOK(int, 0, ismaclabel, const char *name) LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, struct lsm_context *cp) LSM_HOOK(int, -EOPNOTSUPP, lsmprop_to_secctx, struct lsm_prop *prop, struct lsm_context *cp) LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, release_secctx, struct lsm_context *cp) LSM_HOOK(void, LSM_RET_VOID, inode_invalidate_secctx, struct inode *inode) LSM_HOOK(int, 0, inode_notifysecctx, struct inode *inode, void *ctx, u32 ctxlen) LSM_HOOK(int, 0, inode_setsecctx, struct dentry *dentry, void *ctx, u32 ctxlen) LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode, struct lsm_context *cp) #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) LSM_HOOK(int, 0, post_notification, const struct cred *w_cred, const struct cred *cred, struct watch_notification *n) #endif /* CONFIG_SECURITY && CONFIG_WATCH_QUEUE */ #if defined(CONFIG_SECURITY) && defined(CONFIG_KEY_NOTIFICATIONS) LSM_HOOK(int, 0, watch_key, struct key *key) #endif /* CONFIG_SECURITY && CONFIG_KEY_NOTIFICATIONS */ #if defined(CONFIG_SECURITY_NETWORK) && defined(CONFIG_SECURITY_PATH) LSM_HOOK(int, 0, unix_find, const struct path *path, struct sock *other, int flags) #endif /* CONFIG_SECURITY_NETWORK && CONFIG_SECURITY_PATH */ #ifdef CONFIG_SECURITY_NETWORK LSM_HOOK(int, 0, unix_stream_connect, struct sock *sock, struct sock *other, struct sock *newsk) LSM_HOOK(int, 0, unix_may_send, struct socket *sock, struct socket *other) LSM_HOOK(int, 0, socket_create, int family, int type, int protocol, int kern) LSM_HOOK(int, 0, socket_post_create, struct socket *sock, int family, int type, int protocol, int kern) LSM_HOOK(int, 0, socket_socketpair, struct socket *socka, struct socket *sockb) LSM_HOOK(int, 0, socket_bind, struct socket *sock, struct sockaddr *address, int addrlen) LSM_HOOK(int, 0, socket_connect, struct socket *sock, struct sockaddr *address, int addrlen) LSM_HOOK(int, 0, socket_listen, struct socket *sock, int backlog) LSM_HOOK(int, 0, socket_accept, struct socket *sock, struct socket *newsock) LSM_HOOK(int, 0, socket_sendmsg, struct socket *sock, struct msghdr *msg, int size) LSM_HOOK(int, 0, socket_recvmsg, struct socket *sock, struct msghdr *msg, int size, int flags) LSM_HOOK(int, 0, socket_getsockname, struct socket *sock) LSM_HOOK(int, 0, socket_getpeername, struct socket *sock) LSM_HOOK(int, 0, socket_getsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_setsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_shutdown, struct socket *sock, int how) LSM_HOOK(int, 0, socket_sock_rcv_skb, struct sock *sk, struct sk_buff *skb) LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_stream, struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_dgram, struct socket *sock, struct sk_buff *skb, u32 *secid) LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority) LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk) LSM_HOOK(void, LSM_RET_VOID, sk_clone_security, const struct sock *sk, struct sock *newsk) LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, const struct sock *sk, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, sock_graft, struct sock *sk, struct socket *parent) LSM_HOOK(int, 0, inet_conn_request, const struct sock *sk, struct sk_buff *skb, struct request_sock *req) LSM_HOOK(void, LSM_RET_VOID, inet_csk_clone, struct sock *newsk, const struct request_sock *req) LSM_HOOK(void, LSM_RET_VOID, inet_conn_established, struct sock *sk, struct sk_buff *skb) LSM_HOOK(int, 0, secmark_relabel_packet, u32 secid) LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_inc, void) LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_dec, void) LSM_HOOK(void, LSM_RET_VOID, req_classify_flow, const struct request_sock *req, struct flowi_common *flic) LSM_HOOK(int, 0, tun_dev_alloc_security, void *security) LSM_HOOK(int, 0, tun_dev_create, void) LSM_HOOK(int, 0, tun_dev_attach_queue, void *security) LSM_HOOK(int, 0, tun_dev_attach, struct sock *sk, void *security) LSM_HOOK(int, 0, tun_dev_open, void *security) LSM_HOOK(int, 0, sctp_assoc_request, struct sctp_association *asoc, struct sk_buff *skb) LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) LSM_HOOK(int, 0, sctp_assoc_established, struct sctp_association *asoc, struct sk_buff *skb) LSM_HOOK(int, 0, mptcp_add_subflow, struct sock *sk, struct sock *ssk) #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK(int, 0, ib_pkey_access, void *sec, u64 subnet_prefix, u16 pkey) LSM_HOOK(int, 0, ib_endport_manage_subnet, void *sec, const char *dev_name, u8 port_num) LSM_HOOK(int, 0, ib_alloc_security, void *sec) #endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK(int, 0, xfrm_policy_alloc_security, struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp) LSM_HOOK(int, 0, xfrm_policy_clone_security, struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctx) LSM_HOOK(void, LSM_RET_VOID, xfrm_policy_free_security, struct xfrm_sec_ctx *ctx) LSM_HOOK(int, 0, xfrm_policy_delete_security, struct xfrm_sec_ctx *ctx) LSM_HOOK(int, 0, xfrm_state_alloc, struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) LSM_HOOK(int, 0, xfrm_state_alloc_acquire, struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid) LSM_HOOK(void, LSM_RET_VOID, xfrm_state_free_security, struct xfrm_state *x) LSM_HOOK(int, 0, xfrm_state_delete_security, struct xfrm_state *x) LSM_HOOK(int, 0, xfrm_policy_lookup, struct xfrm_sec_ctx *ctx, u32 fl_secid) LSM_HOOK(int, 1, xfrm_state_pol_flow_match, struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) LSM_HOOK(int, 0, xfrm_decode_session, struct sk_buff *skb, u32 *secid, int ckall) #endif /* CONFIG_SECURITY_NETWORK_XFRM */ /* key management security hooks */ #ifdef CONFIG_KEYS LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred, unsigned long flags) LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **buffer) LSM_HOOK(void, LSM_RET_VOID, key_post_create_or_update, struct key *keyring, struct key *key, const void *payload, size_t payload_len, unsigned long flags, bool create) #endif /* CONFIG_KEYS */ #ifdef CONFIG_AUDIT LSM_HOOK(int, 0, audit_rule_init, u32 field, u32 op, char *rulestr, void **lsmrule, gfp_t gfp) LSM_HOOK(int, 0, audit_rule_known, struct audit_krule *krule) LSM_HOOK(int, 0, audit_rule_match, struct lsm_prop *prop, u32 field, u32 op, void *lsmrule) LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) #endif /* CONFIG_AUDIT */ #ifdef CONFIG_BPF_SYSCALL LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode) LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog) LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr, struct bpf_token *token, bool kernel) LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map) LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token, bool kernel) LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr, const struct path *path) LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token) LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd) LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap) #endif /* CONFIG_BPF_SYSCALL */ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) #ifdef CONFIG_PERF_EVENTS LSM_HOOK(int, 0, perf_event_open, int type) LSM_HOOK(int, 0, perf_event_alloc, struct perf_event *event) LSM_HOOK(int, 0, perf_event_read, struct perf_event *event) LSM_HOOK(int, 0, perf_event_write, struct perf_event *event) #endif /* CONFIG_PERF_EVENTS */ #ifdef CONFIG_IO_URING LSM_HOOK(int, 0, uring_override_creds, const struct cred *new) LSM_HOOK(int, 0, uring_sqpoll, void) LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd) LSM_HOOK(int, 0, uring_allowed, void) #endif /* CONFIG_IO_URING */ LSM_HOOK(void, LSM_RET_VOID, initramfs_populated, void) LSM_HOOK(int, 0, bdev_alloc_security, struct block_device *bdev) LSM_HOOK(void, LSM_RET_VOID, bdev_free_security, struct block_device *bdev) LSM_HOOK(int, 0, bdev_setintegrity, struct block_device *bdev, enum lsm_integrity_type type, const void *value, size_t size) |
| 27 2 1 20 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 | /* SPDX-License-Identifier: GPL-2.0-only */ #undef TRACE_SYSTEM #define TRACE_SYSTEM l2tp #if !defined(_TRACE_L2TP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_L2TP_H #include <linux/tracepoint.h> #include <linux/l2tp.h> #include "l2tp_core.h" #define encap_type_name(e) { L2TP_ENCAPTYPE_##e, #e } #define show_encap_type_name(val) \ __print_symbolic(val, \ encap_type_name(UDP), \ encap_type_name(IP)) #define pw_type_name(p) { L2TP_PWTYPE_##p, #p } #define show_pw_type_name(val) \ __print_symbolic(val, \ pw_type_name(ETH_VLAN), \ pw_type_name(ETH), \ pw_type_name(PPP), \ pw_type_name(PPP_AC), \ pw_type_name(IP)) DECLARE_EVENT_CLASS(tunnel_only_evt, TP_PROTO(struct l2tp_tunnel *tunnel), TP_ARGS(tunnel), TP_STRUCT__entry( __array(char, name, L2TP_TUNNEL_NAME_MAX) ), TP_fast_assign( memcpy(__entry->name, tunnel->name, L2TP_TUNNEL_NAME_MAX); ), TP_printk("%s", __entry->name) ); DECLARE_EVENT_CLASS(session_only_evt, TP_PROTO(struct l2tp_session *session), TP_ARGS(session), TP_STRUCT__entry( __array(char, name, L2TP_SESSION_NAME_MAX) ), TP_fast_assign( memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); ), TP_printk("%s", __entry->name) ); TRACE_EVENT(register_tunnel, TP_PROTO(struct l2tp_tunnel *tunnel), TP_ARGS(tunnel), TP_STRUCT__entry( __array(char, name, L2TP_TUNNEL_NAME_MAX) __field(int, fd) __field(u32, tid) __field(u32, ptid) __field(int, version) __field(enum l2tp_encap_type, encap) ), TP_fast_assign( memcpy(__entry->name, tunnel->name, L2TP_TUNNEL_NAME_MAX); __entry->fd = tunnel->fd; __entry->tid = tunnel->tunnel_id; __entry->ptid = tunnel->peer_tunnel_id; __entry->version = tunnel->version; __entry->encap = tunnel->encap; ), TP_printk("%s: type=%s encap=%s version=L2TPv%d tid=%u ptid=%u fd=%d", __entry->name, __entry->fd > 0 ? "managed" : "unmanaged", show_encap_type_name(__entry->encap), __entry->version, __entry->tid, __entry->ptid, __entry->fd) ); DEFINE_EVENT(tunnel_only_evt, delete_tunnel, TP_PROTO(struct l2tp_tunnel *tunnel), TP_ARGS(tunnel) ); DEFINE_EVENT(tunnel_only_evt, free_tunnel, TP_PROTO(struct l2tp_tunnel *tunnel), TP_ARGS(tunnel) ); TRACE_EVENT(register_session, TP_PROTO(struct l2tp_session *session), TP_ARGS(session), TP_STRUCT__entry( __array(char, name, L2TP_SESSION_NAME_MAX) __field(u32, tid) __field(u32, ptid) __field(u32, sid) __field(u32, psid) __field(enum l2tp_pwtype, pwtype) ), TP_fast_assign( memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); __entry->tid = session->tunnel ? session->tunnel->tunnel_id : 0; __entry->ptid = session->tunnel ? session->tunnel->peer_tunnel_id : 0; __entry->sid = session->session_id; __entry->psid = session->peer_session_id; __entry->pwtype = session->pwtype; ), TP_printk("%s: pseudowire=%s sid=%u psid=%u tid=%u ptid=%u", __entry->name, show_pw_type_name(__entry->pwtype), __entry->sid, __entry->psid, __entry->sid, __entry->psid) ); DEFINE_EVENT(session_only_evt, delete_session, TP_PROTO(struct l2tp_session *session), TP_ARGS(session) ); DEFINE_EVENT(session_only_evt, free_session, TP_PROTO(struct l2tp_session *session), TP_ARGS(session) ); DEFINE_EVENT(session_only_evt, session_seqnum_lns_enable, TP_PROTO(struct l2tp_session *session), TP_ARGS(session) ); DEFINE_EVENT(session_only_evt, session_seqnum_lns_disable, TP_PROTO(struct l2tp_session *session), TP_ARGS(session) ); DECLARE_EVENT_CLASS(session_seqnum_evt, TP_PROTO(struct l2tp_session *session), TP_ARGS(session), TP_STRUCT__entry( __array(char, name, L2TP_SESSION_NAME_MAX) __field(u32, ns) __field(u32, nr) ), TP_fast_assign( memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); __entry->ns = session->ns; __entry->nr = session->nr; ), TP_printk("%s: ns=%u nr=%u", __entry->name, __entry->ns, __entry->nr) ); DEFINE_EVENT(session_seqnum_evt, session_seqnum_update, TP_PROTO(struct l2tp_session *session), TP_ARGS(session) ); DEFINE_EVENT(session_seqnum_evt, session_seqnum_reset, TP_PROTO(struct l2tp_session *session), TP_ARGS(session) ); DECLARE_EVENT_CLASS(session_pkt_discard_evt, TP_PROTO(struct l2tp_session *session, u32 pkt_ns), TP_ARGS(session, pkt_ns), TP_STRUCT__entry( __array(char, name, L2TP_SESSION_NAME_MAX) __field(u32, pkt_ns) __field(u32, my_nr) __field(u32, reorder_q_len) ), TP_fast_assign( memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); __entry->pkt_ns = pkt_ns, __entry->my_nr = session->nr; __entry->reorder_q_len = skb_queue_len(&session->reorder_q); ), TP_printk("%s: pkt_ns=%u my_nr=%u reorder_q_len=%u", __entry->name, __entry->pkt_ns, __entry->my_nr, __entry->reorder_q_len) ); DEFINE_EVENT(session_pkt_discard_evt, session_pkt_expired, TP_PROTO(struct l2tp_session *session, u32 pkt_ns), TP_ARGS(session, pkt_ns) ); DEFINE_EVENT(session_pkt_discard_evt, session_pkt_outside_rx_window, TP_PROTO(struct l2tp_session *session, u32 pkt_ns), TP_ARGS(session, pkt_ns) ); DEFINE_EVENT(session_pkt_discard_evt, session_pkt_oos, TP_PROTO(struct l2tp_session *session, u32 pkt_ns), TP_ARGS(session, pkt_ns) ); #endif /* _TRACE_L2TP_H */ /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 15 15 15 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 | // SPDX-License-Identifier: GPL-2.0 /* * fs/partitions/sysv68.c * * Copyright (C) 2007 Philippe De Muyter <phdm@macqel.be> */ #include "check.h" /* * Volume ID structure: on first 256-bytes sector of disk */ struct volumeid { u8 vid_unused[248]; u8 vid_mac[8]; /* ASCII string "MOTOROLA" */ }; /* * config block: second 256-bytes sector on disk */ struct dkconfig { u8 ios_unused0[128]; __be32 ios_slcblk; /* Slice table block number */ __be16 ios_slccnt; /* Number of entries in slice table */ u8 ios_unused1[122]; }; /* * combined volumeid and dkconfig block */ struct dkblk0 { struct volumeid dk_vid; struct dkconfig dk_ios; }; /* * Slice Table Structure */ struct slice { __be32 nblocks; /* slice size (in blocks) */ __be32 blkoff; /* block offset of slice */ }; int sysv68_partition(struct parsed_partitions *state) { int i, slices; int slot = 1; Sector sect; unsigned char *data; struct dkblk0 *b; struct slice *slice; data = read_part_sector(state, 0, §); if (!data) return -1; b = (struct dkblk0 *)data; if (memcmp(b->dk_vid.vid_mac, "MOTOROLA", sizeof(b->dk_vid.vid_mac))) { put_dev_sector(sect); return 0; } slices = be16_to_cpu(b->dk_ios.ios_slccnt); i = be32_to_cpu(b->dk_ios.ios_slcblk); put_dev_sector(sect); data = read_part_sector(state, i, §); if (!data) return -1; slices -= 1; /* last slice is the whole disk */ seq_buf_printf(&state->pp_buf, "sysV68: %s(s%u)", state->name, slices); slice = (struct slice *)data; for (i = 0; i < slices; i++, slice++) { if (slot == state->limit) break; if (be32_to_cpu(slice->nblocks)) { put_partition(state, slot, be32_to_cpu(slice->blkoff), be32_to_cpu(slice->nblocks)); seq_buf_printf(&state->pp_buf, "(s%u)", i); } slot++; } seq_buf_puts(&state->pp_buf, "\n"); put_dev_sector(sect); return 1; } |
| 1159 155 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SMP_H #define __LINUX_SMP_H /* * Generic SMP support * Alan Cox. <alan@redhat.com> */ #include <linux/errno.h> #include <linux/types.h> #include <linux/list.h> #include <linux/cpumask.h> #include <linux/init.h> #include <linux/smp_types.h> typedef void (*smp_call_func_t)(void *info); typedef bool (*smp_cond_func_t)(int cpu, void *info); /* * structure shares (partial) layout with struct irq_work */ struct __call_single_data { struct __call_single_node node; smp_call_func_t func; void *info; }; #define CSD_INIT(_func, _info) \ (struct __call_single_data){ .func = (_func), .info = (_info), } /* Use __aligned() to avoid to use 2 cache lines for 1 csd */ typedef struct __call_single_data call_single_data_t __aligned(sizeof(struct __call_single_data)); #define INIT_CSD(_csd, _func, _info) \ do { \ *(_csd) = CSD_INIT((_func), (_info)); \ } while (0) /* * Enqueue a llist_node on the call_single_queue; be very careful, read * flush_smp_call_function_queue() in detail. */ extern void __smp_call_single_queue(int cpu, struct llist_node *node); /* total number of cpus in this system (may exceed NR_CPUS) */ extern unsigned int total_cpus; int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, int wait); void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask); int smp_call_function_single_async(int cpu, call_single_data_t *csd); /* * Cpus stopping functions in panic. All have default weak definitions. * Architecture-dependent code may override them. */ void __noreturn panic_smp_self_stop(void); void __noreturn nmi_panic_self_stop(struct pt_regs *regs); void crash_smp_send_stop(void); int panic_smp_redirect_cpu(int target_cpu, void *msg); /* * Call a function on all processors */ static inline void on_each_cpu(smp_call_func_t func, void *info, int wait) { on_each_cpu_cond_mask(NULL, func, info, wait, cpu_online_mask); } /** * on_each_cpu_mask() - Run a function on processors specified by * cpumask, which may include the local processor. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. The * exception is that it may be used during early boot while * early_boot_irqs_disabled is set. */ static inline void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { on_each_cpu_cond_mask(NULL, func, info, wait, mask); } /* * Call a function on each processor for which the supplied function * cond_func returns a positive value. This may include the local * processor. May be used during early boot while early_boot_irqs_disabled is * set. Use local_irq_save/restore() instead of local_irq_disable/enable(). */ static inline void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait) { on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask); } /* * Architecture specific boot CPU setup. Defined as empty weak function in * init/main.c. Architectures can override it. */ void __init smp_prepare_boot_cpu(void); #ifdef CONFIG_SMP #include <linux/preempt.h> #include <linux/compiler.h> #include <linux/thread_info.h> #include <asm/smp.h> /* * main cross-CPU interfaces, handles INIT, TLB flush, STOP, etc. * (defined in asm header): */ /* * stops all CPUs but the current one: */ extern void smp_send_stop(void); /* * sends a 'reschedule' event to another CPU: */ extern void arch_smp_send_reschedule(int cpu); /* * scheduler_ipi() is inline so can't be passed as callback reason, but the * callsite IP should be sufficient for root-causing IPIs sent from here. */ #define smp_send_reschedule(cpu) ({ \ trace_ipi_send_cpu(cpu, _RET_IP_, NULL); \ arch_smp_send_reschedule(cpu); \ }) /* * Prepare machine for booting other CPUs. */ extern void smp_prepare_cpus(unsigned int max_cpus); /* * Bring a CPU up */ extern int __cpu_up(unsigned int cpunum, struct task_struct *tidle); /* * Final polishing of CPUs */ extern void smp_cpus_done(unsigned int max_cpus); /* * Call a function on all other processors */ void smp_call_function(smp_call_func_t func, void *info, int wait); void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait); int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait); void kick_all_cpus_sync(void); void wake_up_all_idle_cpus(void); bool cpus_peek_for_pending_ipi(const struct cpumask *mask); /* * Generic and arch helpers */ void __init call_function_init(void); void generic_smp_call_function_single_interrupt(void); #define generic_smp_call_function_interrupt \ generic_smp_call_function_single_interrupt extern unsigned int setup_max_cpus; extern void __init setup_nr_cpu_ids(void); extern void __init smp_init(void); extern int __boot_cpu_id; static inline int get_boot_cpu_id(void) { return __boot_cpu_id; } #else /* !SMP */ static inline void smp_send_stop(void) { } /* * These macros fold the SMP functionality into a single CPU system */ #define raw_smp_processor_id() 0 static inline void up_smp_call_function(smp_call_func_t func, void *info) { } #define smp_call_function(func, info, wait) \ (up_smp_call_function(func, info)) static inline void smp_send_reschedule(int cpu) { } #define smp_call_function_many(mask, func, info, wait) \ (up_smp_call_function(func, info)) static inline void call_function_init(void) { } static inline int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait) { return smp_call_function_single(0, func, info, wait); } static inline void kick_all_cpus_sync(void) { } static inline void wake_up_all_idle_cpus(void) { } static inline bool cpus_peek_for_pending_ipi(const struct cpumask *mask) { return false; } #define setup_max_cpus 0 #ifdef CONFIG_UP_LATE_INIT extern void __init up_late_init(void); static __always_inline void smp_init(void) { up_late_init(); } #else static inline void smp_init(void) { } #endif static inline int get_boot_cpu_id(void) { return 0; } #endif /* !SMP */ /* * raw_smp_processor_id() - get the current (unstable) CPU id * * raw_smp_processor_id() is arch-specific/arch-defined and * may be a macro or a static inline function. * * For when you know what you are doing and need an unstable * CPU id. */ /* * Allow the architecture to differentiate between a stable and unstable read. * For example, x86 uses an IRQ-safe asm-volatile read for the unstable but a * regular asm read for the stable. */ #ifndef __smp_processor_id #define __smp_processor_id() raw_smp_processor_id() #endif #ifdef CONFIG_DEBUG_PREEMPT extern unsigned int debug_smp_processor_id(void); # define smp_processor_id() debug_smp_processor_id() #else /** * smp_processor_id() - get the current (stable) CPU id * * This is the normal accessor to the CPU id and should be used * whenever possible. * * The CPU id is stable when: * * - IRQs are disabled; * - preemption is disabled; * - the task is CPU affine. * * When CONFIG_DEBUG_PREEMPT=y, we verify these assumptions and WARN * when smp_processor_id() is used when the CPU id is not stable. */ # define smp_processor_id() __smp_processor_id() #endif #define get_cpu() ({ preempt_disable(); __smp_processor_id(); }) #define put_cpu() preempt_enable() /* * Callback to arch code if there's nosmp or maxcpus=0 on the * boot command line: */ extern void arch_disable_smp_support(void); extern void arch_thaw_secondary_cpus_begin(void); extern void arch_thaw_secondary_cpus_end(void); void smp_setup_processor_id(void); int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys); /* SMP core functions */ int smpcfd_prepare_cpu(unsigned int cpu); int smpcfd_dead_cpu(unsigned int cpu); int smpcfd_dying_cpu(unsigned int cpu); #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG bool csd_lock_is_stuck(void); #else static inline bool csd_lock_is_stuck(void) { return false; } #endif #endif /* __LINUX_SMP_H */ |
| 62 34 33 34 34 32 34 34 34 34 63 63 1 62 62 62 1538 1535 1537 40 40 40 1536 51 51 63 1538 38 40 1537 2 2 1535 32 94 92 94 94 93 94 92 94 94 94 94 94 94 93 93 94 93 92 94 93 91 92 93 94 94 92 94 94 92 93 91 93 94 94 94 94 94 94 93 94 93 94 94 94 94 34 33 34 32 34 34 33 34 34 33 34 37 38 37 2 38 38 38 38 38 38 38 38 37 36 21 38 38 38 38 38 34 33 34 32 34 2 34 34 34 34 34 34 2 32 32 33 34 37 38 32 32 32 32 32 31 31 33 6 6 6 1 84 35 51 101 101 102 102 102 102 102 100 102 102 102 101 102 102 101 102 102 102 102 102 101 101 102 102 102 102 102 102 102 102 102 102 101 101 102 102 102 102 102 99 102 101 102 102 100 102 102 102 1 1 1 1 1 1 14 10 10 7 7 7 14 14 14 14 14 14 14 1 14 14 14 14 14 14 14 7 7 14 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Bridge netlink control interface * * Authors: * Stephen Hemminger <shemminger@osdl.org> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/etherdevice.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #include <uapi/linux/if_bridge.h> #include "br_private.h" #include "br_private_stp.h" #include "br_private_cfm.h" #include "br_private_tunnel.h" #include "br_private_mcast_eht.h" static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) { struct net_bridge_vlan *v; u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; u16 flags, pvid; int num_vlans = 0; if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; pvid = br_get_pvid(vg); /* Count number of vlan infos */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; /* only a context, bridge vlan not activated */ if (!br_vlan_should_use(v)) continue; if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { vid_range_end = v->vid; continue; } else { if ((vid_range_end - vid_range_start) > 0) num_vlans += 2; else num_vlans += 1; } initvars: vid_range_start = v->vid; vid_range_end = v->vid; vid_range_flags = flags; } if (vid_range_start != 0) { if ((vid_range_end - vid_range_start) > 0) num_vlans += 2; else num_vlans += 1; } return num_vlans; } static int br_get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) { int num_vlans; if (!vg) return 0; if (filter_mask & RTEXT_FILTER_BRVLAN) return vg->num_vlans; rcu_read_lock(); num_vlans = __get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); return num_vlans; } static size_t br_get_link_af_size_filtered(const struct net_device *dev, u32 filter_mask) { struct net_bridge_vlan_group *vg = NULL; struct net_bridge_port *p = NULL; struct net_bridge *br = NULL; u32 num_cfm_peer_mep_infos; u32 num_cfm_mep_infos; size_t vinfo_sz = 0; int num_vlan_infos; rcu_read_lock(); if (netif_is_bridge_port(dev)) { p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); } else if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); } num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); if (p && test_bit(BR_VLAN_TUNNEL_BIT, &p->flags)) vinfo_sz += br_get_vlan_tunnel_info_size(vg); /* Each VLAN is returned in bridge_vlan_info along with flags */ vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); if (p && vg && (filter_mask & RTEXT_FILTER_MST)) vinfo_sz += br_mst_info_size(vg); if (!(filter_mask & RTEXT_FILTER_CFM_STATUS)) return vinfo_sz; if (!br) return vinfo_sz; /* CFM status info must be added */ br_cfm_mep_count(br, &num_cfm_mep_infos); br_cfm_peer_mep_count(br, &num_cfm_peer_mep_infos); vinfo_sz += nla_total_size(0); /* IFLA_BRIDGE_CFM */ /* For each status struct the MEP instance (u32) is added */ /* MEP instance (u32) + br_cfm_mep_status */ vinfo_sz += num_cfm_mep_infos * /*IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE */ (nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN */ + nla_total_size(sizeof(u32))); /* MEP instance (u32) + br_cfm_cc_peer_status */ vinfo_sz += num_cfm_peer_mep_infos * /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE */ (nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE */ + nla_total_size(sizeof(u8)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE */ + nla_total_size(sizeof(u8)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN */ + nla_total_size(sizeof(u32))); return vinfo_sz; } static inline size_t br_port_info_size(void) { return nla_total_size(1) /* IFLA_BRPORT_STATE */ + nla_total_size(2) /* IFLA_BRPORT_PRIORITY */ + nla_total_size(4) /* IFLA_BRPORT_COST */ + nla_total_size(1) /* IFLA_BRPORT_MODE */ + nla_total_size(1) /* IFLA_BRPORT_GUARD */ + nla_total_size(1) /* IFLA_BRPORT_PROTECT */ + nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */ + nla_total_size(1) /* IFLA_BRPORT_MCAST_TO_UCAST */ + nla_total_size(1) /* IFLA_BRPORT_LEARNING */ + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_MCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_BCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + nla_total_size(1) /* IFLA_BRPORT_LOCKED */ + nla_total_size(1) /* IFLA_BRPORT_MAB */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_VLAN_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_FORWARD_GRAT */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_TOPOLOGY_CHANGE_ACK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_CONFIG_PENDING */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_MESSAGE_AGE_TIMER */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_FORWARD_DELAY_TIMER */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_N_GROUPS */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_MAX_GROUPS */ #endif + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_IN_OPEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_CNT */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_BACKUP_NHID */ + 0; } static inline size_t br_nlmsg_size(struct net_device *dev, u32 filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(br_port_info_size()) /* IFLA_PROTINFO */ + nla_total_size(br_get_link_af_size_filtered(dev, filter_mask)) /* IFLA_AF_SPEC */ + nla_total_size(4); /* IFLA_BRPORT_BACKUP_PORT */ } static int br_port_fill_attrs(struct sk_buff *skb, const struct net_bridge_port *p) { unsigned long flags = READ_ONCE(p->flags); u8 mode = !!(flags & BR_HAIRPIN_MODE); struct net_bridge_port *backup_p; u64 timerval; if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) || nla_put_u16(skb, IFLA_BRPORT_PRIORITY, READ_ONCE(p->priority)) || nla_put_u32(skb, IFLA_BRPORT_COST, READ_ONCE(p->path_cost)) || nla_put_u8(skb, IFLA_BRPORT_MODE, mode) || nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(flags & BR_BPDU_GUARD)) || nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(flags & BR_ROOT_BLOCK)) || nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(flags & BR_MULTICAST_FAST_LEAVE)) || nla_put_u8(skb, IFLA_BRPORT_MCAST_TO_UCAST, !!(flags & BR_MULTICAST_TO_UNICAST)) || nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(flags & BR_LEARNING)) || nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(flags & BR_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_MCAST_FLOOD, !!(flags & BR_MCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_BCAST_FLOOD, !!(flags & BR_BCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(flags & BR_PROXYARP)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, !!(flags & BR_PROXYARP_WIFI)) || nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id), &p->designated_root) || nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id), &p->designated_bridge) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, READ_ONCE(p->designated_port)) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, READ_ONCE(p->designated_cost)) || nla_put_u16(skb, IFLA_BRPORT_ID, READ_ONCE(p->port_id)) || nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no) || nla_put_u8(skb, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, p->topology_change_ack) || nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, READ_ONCE(p->config_pending)) || nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(flags & BR_VLAN_TUNNEL)) || nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS, !!(flags & BR_NEIGH_SUPPRESS)) || nla_put_u8(skb, IFLA_BRPORT_MRP_RING_OPEN, !!(flags & BR_MRP_LOST_CONT)) || nla_put_u8(skb, IFLA_BRPORT_MRP_IN_OPEN, !!(flags & BR_MRP_LOST_IN_CONT)) || nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(flags & BR_ISOLATED)) || nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(flags & BR_PORT_LOCKED)) || nla_put_u8(skb, IFLA_BRPORT_MAB, !!(flags & BR_PORT_MAB)) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, !!(flags & BR_NEIGH_VLAN_SUPPRESS)) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_FORWARD_GRAT, !!(flags & BR_NEIGH_FORWARD_GRAT))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_MESSAGE_AGE_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; timerval = br_timer_value(&p->forward_delay_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_FORWARD_DELAY_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; timerval = br_timer_value(&p->hold_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_HOLD_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER, p->multicast_ctx.multicast_router) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, p->multicast_eht_hosts_limit) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, p->multicast_eht_hosts_cnt) || nla_put_u32(skb, IFLA_BRPORT_MCAST_N_GROUPS, br_multicast_ngroups_get(&p->multicast_ctx)) || nla_put_u32(skb, IFLA_BRPORT_MCAST_MAX_GROUPS, br_multicast_ngroups_get_max(&p->multicast_ctx))) return -EMSGSIZE; #endif /* we might be called only with br->lock */ rcu_read_lock(); backup_p = rcu_dereference(p->backup_port); if (backup_p) nla_put_u32(skb, IFLA_BRPORT_BACKUP_PORT, backup_p->dev->ifindex); rcu_read_unlock(); if (p->backup_nhid && nla_put_u32(skb, IFLA_BRPORT_BACKUP_NHID, p->backup_nhid)) return -EMSGSIZE; return 0; } static int br_fill_ifvlaninfo_range(struct sk_buff *skb, u16 vid_start, u16 vid_end, u16 flags) { struct bridge_vlan_info vinfo; if ((vid_end - vid_start) > 0) { /* add range to skb */ vinfo.vid = vid_start; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_BEGIN; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; vinfo.vid = vid_end; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_END; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } else { vinfo.vid = vid_start; vinfo.flags = flags; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *v; u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; u16 flags, pvid; int err = 0; /* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan * and mark vlan info with begin and end flags * if vlaninfo represents a range */ pvid = br_get_pvid(vg); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; if (!br_vlan_should_use(v)) continue; if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { vid_range_end = v->vid; continue; } else { err = br_fill_ifvlaninfo_range(skb, vid_range_start, vid_range_end, vid_range_flags); if (err) return err; } initvars: vid_range_start = v->vid; vid_range_end = v->vid; vid_range_flags = flags; } if (vid_range_start != 0) { /* Call it once more to send any left over vlans */ err = br_fill_ifvlaninfo_range(skb, vid_range_start, vid_range_end, vid_range_flags); if (err) return err; } return 0; } static int br_fill_ifvlaninfo(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct bridge_vlan_info vinfo; struct net_bridge_vlan *v; u16 pvid; pvid = br_get_pvid(vg); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; vinfo.vid = v->vid; vinfo.flags = 0; if (v->vid == pvid) vinfo.flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } /* * Create one netlink message for one interface * Contains port and master info as well as carrier and bridge state. */ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *port, u32 pid, u32 seq, int event, unsigned int flags, u32 filter_mask, const struct net_device *dev, bool getlink) { u8 operstate = netif_running(dev) ? READ_ONCE(dev->operstate) : IF_OPER_DOWN; struct nlattr *af = NULL; struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; if (port) br = port->br; else br = netdev_priv(dev); br_debug(br, "br_fill_ifinfo event %d port %s master %s\n", event, dev->name, br->dev->name); nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags); if (nlh == NULL) return -EMSGSIZE; hdr = nlmsg_data(nlh); hdr->ifi_family = AF_BRIDGE; hdr->__ifi_pad = 0; hdr->ifi_type = dev->type; hdr->ifi_index = dev->ifindex; hdr->ifi_flags = netif_get_flags(dev); hdr->ifi_change = 0; if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_MASTER, br->dev->ifindex) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || nla_put_u8(skb, IFLA_OPERSTATE, operstate) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || (dev->ifindex != dev_get_iflink(dev) && nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev)))) goto nla_put_failure; if (event == RTM_NEWLINK && port) { struct nlattr *nest; nest = nla_nest_start(skb, IFLA_PROTINFO); if (nest == NULL || br_port_fill_attrs(skb, port) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } if (filter_mask & (RTEXT_FILTER_BRVLAN | RTEXT_FILTER_BRVLAN_COMPRESSED | RTEXT_FILTER_MRP | RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS | RTEXT_FILTER_MST)) { af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) goto nla_put_failure; } /* Check if the VID information is requested */ if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { struct net_bridge_vlan_group *vg; int err; /* RCU needed because of the VLAN locking rules (rcu || rtnl) */ rcu_read_lock(); if (port) vg = nbp_vlan_group_rcu(port); else vg = br_vlan_group_rcu(br); if (!vg || !vg->num_vlans) { rcu_read_unlock(); goto done; } if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) err = br_fill_ifvlaninfo_compressed(skb, vg); else err = br_fill_ifvlaninfo(skb, vg); if (port && test_bit(BR_VLAN_TUNNEL_BIT, &port->flags)) err = br_fill_vlan_tunnel_info(skb, vg); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & RTEXT_FILTER_MRP) { int err; if (!br_mrp_enabled(br) || port) goto done; rcu_read_lock(); err = br_mrp_fill_info(skb, br); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & (RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS)) { struct nlattr *cfm_nest = NULL; int err; if (!br_cfm_created(br) || port) goto done; cfm_nest = nla_nest_start(skb, IFLA_BRIDGE_CFM); if (!cfm_nest) goto nla_put_failure; if (filter_mask & RTEXT_FILTER_CFM_CONFIG) { rcu_read_lock(); err = br_cfm_config_fill_info(skb, br); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & RTEXT_FILTER_CFM_STATUS) { rcu_read_lock(); err = br_cfm_status_fill_info(skb, br, getlink); rcu_read_unlock(); if (err) goto nla_put_failure; } nla_nest_end(skb, cfm_nest); } if ((filter_mask & RTEXT_FILTER_MST) && br_opt_get(br, BROPT_MST_ENABLED) && port) { const struct net_bridge_vlan_group *vg = nbp_vlan_group(port); struct nlattr *mst_nest; int err; if (!vg || !vg->num_vlans) goto done; mst_nest = nla_nest_start(skb, IFLA_BRIDGE_MST); if (!mst_nest) goto nla_put_failure; err = br_mst_fill_info(skb, vg); if (err) goto nla_put_failure; nla_nest_end(skb, mst_nest); } done: if (af) { if (nlmsg_get_pos(skb) - (void *)af > nla_attr_size(0)) nla_nest_end(skb, af); else nla_nest_cancel(skb, af); } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void br_info_notify(int event, const struct net_bridge *br, const struct net_bridge_port *port, u32 filter) { struct net_device *dev; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; u16 port_no = 0; if (WARN_ON(!port && !br)) return; if (port) { dev = port->dev; br = port->br; port_no = port->port_no; } else { dev = br->dev; } net = dev_net(dev); br_debug(br, "port %u(%s) event %d\n", port_no, dev->name, event); skb = nlmsg_new(br_nlmsg_size(dev, filter), GFP_ATOMIC); if (skb == NULL) goto errout; err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev, false); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_LINK, err); } /* Notify listeners of a change in bridge or port information */ void br_ifinfo_notify(int event, const struct net_bridge *br, const struct net_bridge_port *port) { u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; br_info_notify(event, br, port, filter); } /* * Dump information about all ports, in response to GETLINK */ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) { struct net_bridge_port *port = br_port_get_rtnl(dev); if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) && !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) && !(filter_mask & RTEXT_FILTER_MRP) && !(filter_mask & RTEXT_FILTER_CFM_CONFIG) && !(filter_mask & RTEXT_FILTER_CFM_STATUS)) return 0; return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags, filter_mask, dev, true); } static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo, bool *changed, struct netlink_ext_ack *extack) { bool curr_change; int err = 0; switch (cmd) { case RTM_SETLINK: if (p) { /* if the MASTER flag is set this will act on the global * per-VLAN entry as well */ err = nbp_vlan_add(p, vinfo->vid, vinfo->flags, &curr_change, extack); } else { vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY; err = br_vlan_add(br, vinfo->vid, vinfo->flags, &curr_change, extack); } if (curr_change) *changed = true; break; case RTM_DELLINK: if (p) { if (!nbp_vlan_delete(p, vinfo->vid)) *changed = true; if ((vinfo->flags & BRIDGE_VLAN_INFO_MASTER) && !br_vlan_delete(p->br, vinfo->vid)) *changed = true; } else if (!br_vlan_delete(br, vinfo->vid)) { *changed = true; } break; } return err; } int br_process_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo_curr, struct bridge_vlan_info **vinfo_last, bool *changed, struct netlink_ext_ack *extack) { int err, rtm_cmd; if (!br_vlan_valid_id(vinfo_curr->vid, extack)) return -EINVAL; /* needed for vlan-only NEWVLAN/DELVLAN notifications */ rtm_cmd = br_afspec_cmd_to_rtm(cmd); if (vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; *vinfo_last = vinfo_curr; return 0; } if (*vinfo_last) { struct bridge_vlan_info tmp_vinfo; int v, v_change_start = 0; if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; memcpy(&tmp_vinfo, *vinfo_last, sizeof(struct bridge_vlan_info)); for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) { bool curr_change = false; tmp_vinfo.vid = v; err = br_vlan_info(br, p, cmd, &tmp_vinfo, &curr_change, extack); if (err) break; if (curr_change) { *changed = curr_change; if (!v_change_start) v_change_start = v; } else { /* nothing to notify yet */ if (!v_change_start) continue; br_vlan_notify(br, p, v_change_start, v - 1, rtm_cmd); v_change_start = 0; } cond_resched(); } /* v_change_start is set only if the last/whole range changed */ if (v_change_start) br_vlan_notify(br, p, v_change_start, v - 1, rtm_cmd); *vinfo_last = NULL; return err; } err = br_vlan_info(br, p, cmd, vinfo_curr, changed, extack); if (*changed) br_vlan_notify(br, p, vinfo_curr->vid, 0, rtm_cmd); return err; } static int br_afspec(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *af_spec, int cmd, bool *changed, struct netlink_ext_ack *extack) { struct bridge_vlan_info *vinfo_curr = NULL; struct bridge_vlan_info *vinfo_last = NULL; struct nlattr *attr; struct vtunnel_info tinfo_last = {}; struct vtunnel_info tinfo_curr = {}; int err = 0, rem; nla_for_each_nested(attr, af_spec, rem) { err = 0; switch (nla_type(attr)) { case IFLA_BRIDGE_VLAN_TUNNEL_INFO: if (!p || !test_bit(BR_VLAN_TUNNEL_BIT, &p->flags)) return -EINVAL; err = br_parse_vlan_tunnel_info(attr, &tinfo_curr); if (err) return err; err = br_process_vlan_tunnel_info(br, p, cmd, &tinfo_curr, &tinfo_last, changed); if (err) return err; break; case IFLA_BRIDGE_VLAN_INFO: if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo_curr = nla_data(attr); err = br_process_vlan_info(br, p, cmd, vinfo_curr, &vinfo_last, changed, extack); if (err) return err; break; case IFLA_BRIDGE_MRP: err = br_mrp_parse(br, p, attr, cmd, extack); if (err) return err; break; case IFLA_BRIDGE_CFM: err = br_cfm_parse(br, p, attr, cmd, extack); if (err) return err; break; case IFLA_BRIDGE_MST: if (!p) { NL_SET_ERR_MSG(extack, "MST states can only be set on bridge ports"); return -EINVAL; } if (cmd != RTM_SETLINK) { NL_SET_ERR_MSG(extack, "MST states can only be set through RTM_SETLINK"); return -EINVAL; } err = br_mst_process(p, attr, extack); if (err) return err; break; } } return err; } static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_UNSPEC] = { .strict_start_type = IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT + 1 }, [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, [IFLA_BRPORT_COST] = { .type = NLA_U32 }, [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, [IFLA_BRPORT_MODE] = { .type = NLA_U8 }, [IFLA_BRPORT_GUARD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 }, [IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 }, [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, [IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_VLAN_TUNNEL] = { .type = NLA_U8 }, [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, [IFLA_BRPORT_LOCKED] = { .type = NLA_U8 }, [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_N_GROUPS] = { .type = NLA_REJECT }, [IFLA_BRPORT_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, [IFLA_BRPORT_NEIGH_VLAN_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_BRPORT_BACKUP_NHID] = { .type = NLA_U32 }, [IFLA_BRPORT_NEIGH_FORWARD_GRAT] = NLA_POLICY_MAX(NLA_U8, 1), }; /* Change the state of the port and notify spanning tree */ static int br_set_port_state(struct net_bridge_port *p, u8 state) { if (state > BR_STATE_BLOCKING) return -EINVAL; /* if kernel STP is running, don't allow changes */ if (p->br->stp_enabled == BR_KERNEL_STP) return -EBUSY; /* if device is not up, change is not allowed * if link is not present, only allowable state is disabled */ if (!netif_running(p->dev) || (!netif_oper_up(p->dev) && state != BR_STATE_DISABLED)) return -ENETDOWN; br_set_state(p, state); br_port_state_selection(p->br); return 0; } /* Set/clear or port flags based on attribute */ static void br_set_port_flag(unsigned long *set_flags, unsigned long *clear_flags, struct nlattr *tb[], int attrtype, unsigned long mask) { if (tb[attrtype]) { if (nla_get_u8(tb[attrtype])) *set_flags |= mask; else *clear_flags |= mask; } } /* Process bridge protocol info on port */ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], struct netlink_ext_ack *extack) { unsigned long old_flags, flags, changed_mask; unsigned long set = 0, clear = 0; bool br_vlan_tunnel_old; int err; old_flags = READ_ONCE(p->flags); br_vlan_tunnel_old = (old_flags & BR_VLAN_TUNNEL) ? true : false; br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_LOCKED, BR_PORT_LOCKED); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_MAB, BR_PORT_MAB); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, BR_NEIGH_VLAN_SUPPRESS); br_set_port_flag(&set, &clear, tb, IFLA_BRPORT_NEIGH_FORWARD_GRAT, BR_NEIGH_FORWARD_GRAT); flags = (old_flags | set) & ~clear; if ((flags & BR_PORT_MAB) && (!(flags & BR_PORT_LOCKED) || !(flags & BR_LEARNING))) { NL_SET_ERR_MSG(extack, "Bridge port must be locked and have learning enabled when MAB is enabled"); return -EINVAL; } if (!(flags & BR_PORT_MAB) && (old_flags & BR_PORT_MAB)) { struct net_bridge_fdb_flush_desc desc = { .flags = BIT(BR_FDB_LOCKED), .flags_mask = BIT(BR_FDB_LOCKED), .port_ifindex = p->dev->ifindex, }; br_fdb_flush(p->br, &desc); } changed_mask = old_flags ^ flags; err = br_switchdev_set_port_flag(p, flags, changed_mask, extack); if (err) return err; do { flags = (old_flags | set) & ~clear; } while (!try_cmpxchg(&p->flags, &old_flags, flags)); if (br_vlan_tunnel_old && !(flags & BR_VLAN_TUNNEL)) nbp_vlan_tunnel_info_flush(p); br_port_flags_change(p, changed_mask); if (tb[IFLA_BRPORT_COST]) { spin_lock_bh(&p->br->lock); err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); spin_unlock_bh(&p->br->lock); if (err) return err; } if (tb[IFLA_BRPORT_PRIORITY]) { spin_lock_bh(&p->br->lock); err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY])); spin_unlock_bh(&p->br->lock); if (err) return err; } if (tb[IFLA_BRPORT_STATE]) { spin_lock_bh(&p->br->lock); err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE])); spin_unlock_bh(&p->br->lock); if (err) return err; } if (tb[IFLA_BRPORT_FLUSH]) br_fdb_delete_by_port(p->br, p, 0, 0); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (tb[IFLA_BRPORT_MULTICAST_ROUTER]) { u8 mcast_router = nla_get_u8(tb[IFLA_BRPORT_MULTICAST_ROUTER]); err = br_multicast_set_port_router(&p->multicast_ctx, mcast_router); if (err) return err; } if (tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]) { u32 hlimit; hlimit = nla_get_u32(tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]); err = br_multicast_eht_set_hosts_limit(p, hlimit); if (err) return err; } if (tb[IFLA_BRPORT_MCAST_MAX_GROUPS]) { u32 max_groups; max_groups = nla_get_u32(tb[IFLA_BRPORT_MCAST_MAX_GROUPS]); br_multicast_ngroups_set_max(&p->multicast_ctx, max_groups); } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]); if (fwd_mask & BR_GROUPFWD_MACPAUSE) return -EINVAL; p->group_fwd_mask = fwd_mask; } if (tb[IFLA_BRPORT_BACKUP_PORT]) { struct net_device *backup_dev = NULL; u32 backup_ifindex; backup_ifindex = nla_get_u32(tb[IFLA_BRPORT_BACKUP_PORT]); if (backup_ifindex) { backup_dev = __dev_get_by_index(dev_net(p->dev), backup_ifindex); if (!backup_dev) return -ENOENT; } err = nbp_backup_change(p, backup_dev); if (err) return err; } if (tb[IFLA_BRPORT_BACKUP_NHID]) { u32 backup_nhid = nla_get_u32(tb[IFLA_BRPORT_BACKUP_NHID]); WRITE_ONCE(p->backup_nhid, backup_nhid); } return 0; } /* Change state and parameters on port. */ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, struct netlink_ext_ack *extack) { struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct nlattr *tb[IFLA_BRPORT_MAX + 1]; struct net_bridge_port *p; struct nlattr *protinfo; struct nlattr *afspec; bool changed = false; int err = 0; protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!protinfo && !afspec) return 0; p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself if the AF_SPEC * is set to see if someone is setting vlan info on the bridge */ if (!p && !afspec) return -EINVAL; if (p && protinfo) { if (protinfo->nla_type & NLA_F_NESTED) { err = nla_parse_nested_deprecated(tb, IFLA_BRPORT_MAX, protinfo, br_port_policy, NULL); if (err) return err; err = br_setport(p, tb, extack); } else { /* Binary compatibility with old RSTP */ if (nla_len(protinfo) < sizeof(u8)) return -EINVAL; spin_lock_bh(&p->br->lock); err = br_set_port_state(p, nla_get_u8(protinfo)); spin_unlock_bh(&p->br->lock); } if (err) goto out; changed = true; } if (afspec) err = br_afspec(br, p, afspec, RTM_SETLINK, &changed, extack); if (changed) br_ifinfo_notify(RTM_NEWLINK, br, p); out: return err; } /* Delete port information */ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct net_bridge_port *p; struct nlattr *afspec; bool changed = false; int err = 0; afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!afspec) return 0; p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself as well */ if (!p && !netif_is_bridge_master(dev)) return -EINVAL; err = br_afspec(br, p, afspec, RTM_DELLINK, &changed, NULL); if (changed) /* Send RTM_NEWLINK because userspace * expects RTM_NEWLINK for vlan dels */ br_ifinfo_notify(RTM_NEWLINK, br, p); return err; } static int br_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) return 0; #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (data[IFLA_BR_VLAN_PROTOCOL] && !eth_type_vlan(nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]))) return -EPROTONOSUPPORT; if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); if (defpvid >= VLAN_VID_MASK) return -EINVAL; } #endif return 0; } static int br_port_slave_changelink(struct net_device *brdev, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) return 0; return br_setport(br_port_get_rtnl(dev), data, extack); } static int br_port_fill_slave_info(struct sk_buff *skb, const struct net_device *brdev, const struct net_device *dev) { return br_port_fill_attrs(skb, br_port_get_rtnl(dev)); } static size_t br_port_get_slave_size(const struct net_device *brdev, const struct net_device *dev) { return br_port_info_size(); } static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_UNSPEC] = { .strict_start_type = IFLA_BR_FDB_N_LEARNED }, [IFLA_BR_FORWARD_DELAY] = { .type = NLA_U32 }, [IFLA_BR_HELLO_TIME] = { .type = NLA_U32 }, [IFLA_BR_MAX_AGE] = { .type = NLA_U32 }, [IFLA_BR_AGEING_TIME] = { .type = NLA_U32 }, [IFLA_BR_STP_STATE] = { .type = NLA_U32 }, [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, [IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 }, [IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 }, [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_MEMBERSHIP_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERIER_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_NF_CALL_IPTABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_IP6TABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 }, [IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 }, [IFLA_BR_VLAN_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 }, [IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 }, [IFLA_BR_VLAN_STATS_PER_PORT] = { .type = NLA_U8 }, [IFLA_BR_MULTI_BOOLOPT] = NLA_POLICY_EXACT_LEN(sizeof(struct br_boolopt_multi)), [IFLA_BR_FDB_N_LEARNED] = { .type = NLA_REJECT }, [IFLA_BR_FDB_MAX_LEARNED] = { .type = NLA_U32 }, [IFLA_BR_STP_MODE] = NLA_POLICY_RANGE(NLA_U32, BR_STP_MODE_AUTO, BR_STP_MODE_MAX), }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int err; if (!data) return 0; if (data[IFLA_BR_FORWARD_DELAY]) { err = br_set_forward_delay(br, nla_get_u32(data[IFLA_BR_FORWARD_DELAY])); if (err) return err; } if (data[IFLA_BR_HELLO_TIME]) { err = br_set_hello_time(br, nla_get_u32(data[IFLA_BR_HELLO_TIME])); if (err) return err; } if (data[IFLA_BR_MAX_AGE]) { err = br_set_max_age(br, nla_get_u32(data[IFLA_BR_MAX_AGE])); if (err) return err; } if (data[IFLA_BR_AGEING_TIME]) { err = br_set_ageing_time(br, nla_get_u32(data[IFLA_BR_AGEING_TIME])); if (err) return err; } if (data[IFLA_BR_STP_MODE]) { u32 mode = nla_get_u32(data[IFLA_BR_STP_MODE]); if (mode != br->stp_mode) { bool stp_off = br->stp_enabled == BR_NO_STP || (data[IFLA_BR_STP_STATE] && !nla_get_u32(data[IFLA_BR_STP_STATE])); if (!stp_off) { NL_SET_ERR_MSG_MOD(extack, "Can't change STP mode while STP is enabled"); return -EBUSY; } } br->stp_mode = mode; } if (data[IFLA_BR_STP_STATE]) { u32 stp_enabled = nla_get_u32(data[IFLA_BR_STP_STATE]); err = br_stp_set_enabled(br, stp_enabled, extack); if (err) return err; } if (data[IFLA_BR_PRIORITY]) { u32 priority = nla_get_u16(data[IFLA_BR_PRIORITY]); br_stp_set_bridge_priority(br, priority); } if (data[IFLA_BR_VLAN_FILTERING]) { u8 vlan_filter = nla_get_u8(data[IFLA_BR_VLAN_FILTERING]); err = br_vlan_filter_toggle(br, vlan_filter, extack); if (err) return err; } #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (data[IFLA_BR_VLAN_PROTOCOL]) { __be16 vlan_proto = nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]); err = __br_vlan_set_proto(br, vlan_proto, extack); if (err) return err; } if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); err = __br_vlan_set_default_pvid(br, defpvid, extack); if (err) return err; } if (data[IFLA_BR_VLAN_STATS_ENABLED]) { __u8 vlan_stats = nla_get_u8(data[IFLA_BR_VLAN_STATS_ENABLED]); err = br_vlan_set_stats(br, vlan_stats); if (err) return err; } if (data[IFLA_BR_VLAN_STATS_PER_PORT]) { __u8 per_port = nla_get_u8(data[IFLA_BR_VLAN_STATS_PER_PORT]); err = br_vlan_set_stats_per_port(br, per_port); if (err) return err; } #endif if (data[IFLA_BR_GROUP_FWD_MASK]) { u16 fwd_mask = nla_get_u16(data[IFLA_BR_GROUP_FWD_MASK]); if (fwd_mask & BR_GROUPFWD_RESTRICTED) return -EINVAL; br->group_fwd_mask = fwd_mask; } if (data[IFLA_BR_GROUP_ADDR]) { u8 new_addr[ETH_ALEN]; if (nla_len(data[IFLA_BR_GROUP_ADDR]) != ETH_ALEN) return -EINVAL; memcpy(new_addr, nla_data(data[IFLA_BR_GROUP_ADDR]), ETH_ALEN); if (!is_link_local_ether_addr(new_addr)) return -EINVAL; if (new_addr[5] == 1 || /* 802.3x Pause address */ new_addr[5] == 2 || /* 802.3ad Slow protocols */ new_addr[5] == 3) /* 802.1X PAE address */ return -EINVAL; spin_lock_bh(&br->lock); memcpy(br->group_addr, new_addr, sizeof(br->group_addr)); spin_unlock_bh(&br->lock); br_opt_toggle(br, BROPT_GROUP_ADDR_SET, true); br_recalculate_fwd_mask(br); } if (data[IFLA_BR_FDB_FLUSH]) { struct net_bridge_fdb_flush_desc desc = { .flags_mask = BIT(BR_FDB_STATIC) }; br_fdb_flush(br, &desc); } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (data[IFLA_BR_MCAST_ROUTER]) { u8 multicast_router = nla_get_u8(data[IFLA_BR_MCAST_ROUTER]); err = br_multicast_set_router(&br->multicast_ctx, multicast_router); if (err) return err; } if (data[IFLA_BR_MCAST_SNOOPING]) { u8 mcast_snooping = nla_get_u8(data[IFLA_BR_MCAST_SNOOPING]); err = br_multicast_toggle(br, mcast_snooping, extack); if (err) return err; } if (data[IFLA_BR_MCAST_QUERY_USE_IFADDR]) { u8 val; val = nla_get_u8(data[IFLA_BR_MCAST_QUERY_USE_IFADDR]); br_opt_toggle(br, BROPT_MULTICAST_QUERY_USE_IFADDR, !!val); } if (data[IFLA_BR_MCAST_QUERIER]) { u8 mcast_querier = nla_get_u8(data[IFLA_BR_MCAST_QUERIER]); err = br_multicast_set_querier(&br->multicast_ctx, mcast_querier); if (err) return err; } if (data[IFLA_BR_MCAST_HASH_ELASTICITY]) br_warn(br, "the hash_elasticity option has been deprecated and is always %u\n", RHT_ELASTICITY); if (data[IFLA_BR_MCAST_HASH_MAX]) br->hash_max = nla_get_u32(data[IFLA_BR_MCAST_HASH_MAX]); if (data[IFLA_BR_MCAST_LAST_MEMBER_CNT]) { u32 val = nla_get_u32(data[IFLA_BR_MCAST_LAST_MEMBER_CNT]); br->multicast_ctx.multicast_last_member_count = val; } if (data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]) { u32 val = nla_get_u32(data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]); br->multicast_ctx.multicast_startup_query_count = val; } if (data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]); br->multicast_ctx.multicast_last_member_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]); br->multicast_ctx.multicast_membership_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERIER_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERIER_INTVL]); br->multicast_ctx.multicast_querier_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_INTVL]); br_multicast_set_query_intvl(&br->multicast_ctx, val); } if (data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]); br->multicast_ctx.multicast_query_response_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]); br_multicast_set_startup_query_intvl(&br->multicast_ctx, val); } if (data[IFLA_BR_MCAST_STATS_ENABLED]) { __u8 mcast_stats; mcast_stats = nla_get_u8(data[IFLA_BR_MCAST_STATS_ENABLED]); br_opt_toggle(br, BROPT_MULTICAST_STATS_ENABLED, !!mcast_stats); } if (data[IFLA_BR_MCAST_IGMP_VERSION]) { __u8 igmp_version; igmp_version = nla_get_u8(data[IFLA_BR_MCAST_IGMP_VERSION]); err = br_multicast_set_igmp_version(&br->multicast_ctx, igmp_version); if (err) return err; } #if IS_ENABLED(CONFIG_IPV6) if (data[IFLA_BR_MCAST_MLD_VERSION]) { __u8 mld_version; mld_version = nla_get_u8(data[IFLA_BR_MCAST_MLD_VERSION]); err = br_multicast_set_mld_version(&br->multicast_ctx, mld_version); if (err) return err; } #endif #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (data[IFLA_BR_NF_CALL_IPTABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IPTABLES]); br_opt_toggle(br, BROPT_NF_CALL_IPTABLES, !!val); } if (data[IFLA_BR_NF_CALL_IP6TABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IP6TABLES]); br_opt_toggle(br, BROPT_NF_CALL_IP6TABLES, !!val); } if (data[IFLA_BR_NF_CALL_ARPTABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_ARPTABLES]); br_opt_toggle(br, BROPT_NF_CALL_ARPTABLES, !!val); } #endif if (data[IFLA_BR_MULTI_BOOLOPT]) { struct br_boolopt_multi *bm; bm = nla_data(data[IFLA_BR_MULTI_BOOLOPT]); err = br_boolopt_multi_toggle(br, bm, extack); if (err) return err; } if (data[IFLA_BR_FDB_MAX_LEARNED]) { u32 val = nla_get_u32(data[IFLA_BR_FDB_MAX_LEARNED]); WRITE_ONCE(br->fdb_max_learned, val); } return 0; } static int br_dev_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); struct nlattr **data = params->data; struct nlattr **tb = params->tb; int err; err = register_netdevice(dev); if (err) return err; if (tb[IFLA_ADDRESS]) { spin_lock_bh(&br->lock); br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); spin_unlock_bh(&br->lock); } err = br_changelink(dev, tb, data, extack); if (err) br_dev_delete(dev, NULL); return err; } static size_t br_get_size(const struct net_device *brdev) { return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_HELLO_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MAX_AGE */ nla_total_size(sizeof(u32)) + /* IFLA_BR_AGEING_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_STATE */ nla_total_size(sizeof(u16)) + /* IFLA_BR_PRIORITY */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_FILTERING */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */ nla_total_size(sizeof(u16)) + /* IFLA_BR_VLAN_DEFAULT_PVID */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_STATS_ENABLED */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_STATS_PER_PORT */ #endif nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_HELLO_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_GC_TIMER */ nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */ nla_total_size(sizeof(u32)) + /* IFLA_BR_FDB_N_LEARNED */ nla_total_size(sizeof(u32)) + /* IFLA_BR_FDB_MAX_LEARNED */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_STATS_ENABLED */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_STARTUP_QUERY_CNT */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_LAST_MEMBER_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_MEMBERSHIP_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERIER_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_IGMP_VERSION */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_MLD_VERSION */ br_multicast_querier_state_size() + /* IFLA_BR_MCAST_QUERIER_STATE */ #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IPTABLES */ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IP6TABLES */ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_ARPTABLES */ #endif nla_total_size(sizeof(struct br_boolopt_multi)) + /* IFLA_BR_MULTI_BOOLOPT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_MODE */ 0; } static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) { struct net_bridge *br = netdev_priv(brdev); u32 forward_delay = jiffies_to_clock_t(br->forward_delay); u32 hello_time = jiffies_to_clock_t(br->hello_time); u32 age_time = jiffies_to_clock_t(br->max_age); u32 ageing_time = jiffies_to_clock_t(br->ageing_time); u32 stp_enabled = br->stp_enabled; u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; u8 vlan_enabled = br_vlan_enabled(br->dev); struct br_boolopt_multi bm; u64 clockval; clockval = br_timer_value(&br->hello_timer); if (nla_put_u64_64bit(skb, IFLA_BR_HELLO_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->tcn_timer); if (nla_put_u64_64bit(skb, IFLA_BR_TCN_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->topology_change_timer); if (nla_put_u64_64bit(skb, IFLA_BR_TOPOLOGY_CHANGE_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->gc_work.timer); if (nla_put_u64_64bit(skb, IFLA_BR_GC_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; br_boolopt_multi_get(br, &bm); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) || nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) || nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, br->group_fwd_mask) || nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(struct ifla_bridge_id), &br->bridge_id) || nla_put(skb, IFLA_BR_ROOT_ID, sizeof(struct ifla_bridge_id), &br->designated_root) || nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port) || nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE, br->topology_change) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, br->topology_change_detected) || nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr) || nla_put(skb, IFLA_BR_MULTI_BOOLOPT, sizeof(bm), &bm) || nla_put_u32(skb, IFLA_BR_FDB_N_LEARNED, atomic_read(&br->fdb_n_learned)) || nla_put_u32(skb, IFLA_BR_FDB_MAX_LEARNED, br->fdb_max_learned) || nla_put_u32(skb, IFLA_BR_STP_MODE, br->stp_mode)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto) || nla_put_u16(skb, IFLA_BR_VLAN_DEFAULT_PVID, br->default_pvid) || nla_put_u8(skb, IFLA_BR_VLAN_STATS_ENABLED, br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) || nla_put_u8(skb, IFLA_BR_VLAN_STATS_PER_PORT, br_opt_get(br, BROPT_VLAN_STATS_PER_PORT))) return -EMSGSIZE; #endif #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_ctx.multicast_router) || nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, br_opt_get(br, BROPT_MULTICAST_ENABLED)) || nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR, br_opt_get(br, BROPT_MULTICAST_QUERY_USE_IFADDR)) || nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_ctx.multicast_querier) || nla_put_u8(skb, IFLA_BR_MCAST_STATS_ENABLED, br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, RHT_ELASTICITY) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) || nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT, br->multicast_ctx.multicast_last_member_count) || nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT, br->multicast_ctx.multicast_startup_query_count) || nla_put_u8(skb, IFLA_BR_MCAST_IGMP_VERSION, br->multicast_ctx.multicast_igmp_version) || br_multicast_dump_querier_state(skb, &br->multicast_ctx, IFLA_BR_MCAST_QUERIER_STATE)) return -EMSGSIZE; #if IS_ENABLED(CONFIG_IPV6) if (nla_put_u8(skb, IFLA_BR_MCAST_MLD_VERSION, br->multicast_ctx.multicast_mld_version)) return -EMSGSIZE; #endif clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_last_member_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_membership_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_MEMBERSHIP_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_querier_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERIER_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_query_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_query_response_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_startup_query_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_u8(skb, IFLA_BR_NF_CALL_IPTABLES, br_opt_get(br, BROPT_NF_CALL_IPTABLES) ? 1 : 0) || nla_put_u8(skb, IFLA_BR_NF_CALL_IP6TABLES, br_opt_get(br, BROPT_NF_CALL_IP6TABLES) ? 1 : 0) || nla_put_u8(skb, IFLA_BR_NF_CALL_ARPTABLES, br_opt_get(br, BROPT_NF_CALL_ARPTABLES) ? 1 : 0)) return -EMSGSIZE; #endif return 0; } static size_t br_get_linkxstats_size(const struct net_device *dev, int attr) { struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge *br; int numvls = 0; switch (attr) { case IFLA_STATS_LINK_XSTATS: br = netdev_priv(dev); vg = br_vlan_group(br); break; case IFLA_STATS_LINK_XSTATS_SLAVE: p = br_port_get_rtnl(dev); if (!p) return 0; vg = nbp_vlan_group(p); break; default: return 0; } if (vg) { /* we need to count all, even placeholder entries */ list_for_each_entry(v, &vg->vlan_list, vlist) numvls++; } return numvls * nla_total_size(sizeof(struct bridge_vlan_xstats)) + nla_total_size_64bit(sizeof(struct br_mcast_stats)) + (p ? nla_total_size_64bit(sizeof(p->stp_xstats)) : 0) + nla_total_size(0); } static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev, int *prividx, int attr) { unsigned int limit = U16_MAX - nla_total_size(0); struct nlattr *nla __maybe_unused; struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge *br; struct nlattr *nest; int vl_idx = 0; switch (attr) { case IFLA_STATS_LINK_XSTATS: br = netdev_priv(dev); vg = br_vlan_group(br); break; case IFLA_STATS_LINK_XSTATS_SLAVE: p = br_port_get_rtnl(dev); if (!p) return 0; limit -= nla_total_size_64bit(sizeof(p->stp_xstats)); br = p->br; vg = nbp_vlan_group(p); break; default: return -EINVAL; } nest = nla_nest_start_noflag(skb, LINK_XSTATS_TYPE_BRIDGE); if (!nest) return -EMSGSIZE; if (vg) { u16 pvid; #ifdef CONFIG_BRIDGE_IGMP_SNOOPING limit -= nla_total_size_64bit(sizeof(struct br_mcast_stats)); #endif pvid = br_get_pvid(vg); list_for_each_entry(v, &vg->vlan_list, vlist) { struct bridge_vlan_xstats vxi; struct pcpu_sw_netstats stats; if (++vl_idx < *prividx) continue; if (skb_tail_pointer(skb) - (unsigned char *)nest + nla_total_size(sizeof(vxi)) >= limit) goto nla_put_failure; memset(&vxi, 0, sizeof(vxi)); vxi.vid = v->vid; vxi.flags = v->flags; if (v->vid == pvid) vxi.flags |= BRIDGE_VLAN_INFO_PVID; br_vlan_get_stats(v, &stats); vxi.rx_bytes = u64_stats_read(&stats.rx_bytes); vxi.rx_packets = u64_stats_read(&stats.rx_packets); vxi.tx_bytes = u64_stats_read(&stats.tx_bytes); vxi.tx_packets = u64_stats_read(&stats.tx_packets); if (nla_put(skb, BRIDGE_XSTATS_VLAN, sizeof(vxi), &vxi)) goto nla_put_failure; } } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (++vl_idx >= *prividx) { nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_MCAST, sizeof(struct br_mcast_stats), BRIDGE_XSTATS_PAD); if (!nla) goto nla_put_failure; br_multicast_get_stats(br, p, nla_data(nla)); } #endif if (p) { nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_STP, sizeof(p->stp_xstats), BRIDGE_XSTATS_PAD); if (!nla) goto nla_put_failure; spin_lock_bh(&br->lock); memcpy(nla_data(nla), &p->stp_xstats, sizeof(p->stp_xstats)); spin_unlock_bh(&br->lock); } nla_nest_end(skb, nest); *prividx = 0; return 0; nla_put_failure: nla_nest_end(skb, nest); *prividx = vl_idx; return -EMSGSIZE; } static struct rtnl_af_ops br_af_ops __read_mostly = { .family = AF_BRIDGE, .get_link_af_size = br_get_link_af_size_filtered, }; struct rtnl_link_ops br_link_ops __read_mostly = { .kind = "bridge", .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, .maxtype = IFLA_BR_MAX, .policy = br_policy, .validate = br_validate, .newlink = br_dev_newlink, .changelink = br_changelink, .dellink = br_dev_delete, .get_size = br_get_size, .fill_info = br_fill_info, .fill_linkxstats = br_fill_linkxstats, .get_linkxstats_size = br_get_linkxstats_size, .slave_maxtype = IFLA_BRPORT_MAX, .slave_policy = br_port_policy, .slave_changelink = br_port_slave_changelink, .get_slave_size = br_port_get_slave_size, .fill_slave_info = br_port_fill_slave_info, }; int __init br_netlink_init(void) { int err; err = br_vlan_rtnl_init(); if (err) goto out; err = rtnl_af_register(&br_af_ops); if (err) goto out_vlan; err = rtnl_link_register(&br_link_ops); if (err) goto out_af; return 0; out_af: rtnl_af_unregister(&br_af_ops); out_vlan: br_vlan_rtnl_uninit(); out: return err; } void br_netlink_fini(void) { br_vlan_rtnl_uninit(); rtnl_af_unregister(&br_af_ops); rtnl_link_unregister(&br_link_ops); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 #ifndef IORING_CANCEL_H #define IORING_CANCEL_H #include <linux/io_uring_types.h> struct io_cancel_data { struct io_ring_ctx *ctx; u64 data; struct file *file; u8 opcode; u32 flags; int seq; }; int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags); int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, unsigned int issue_flags); int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg); bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd); bool io_match_task_safe(struct io_kiocb *head, struct io_uring_task *tctx, bool cancel_all); 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 *)); 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 *)); __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct io_uring_task *tctx, bool cancel_all, bool is_sqpoll_thread); __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); __cold bool io_cancel_ctx_cb(struct io_wq_work *work, void *data); static inline bool io_cancel_match_sequence(struct io_kiocb *req, int sequence) { if (req->cancel_seq_set && sequence == req->work.cancel_seq) return true; req->cancel_seq_set = true; req->work.cancel_seq = sequence; return false; } #endif |
| 100 100 100 100 100 100 100 100 49 49 49 49 100 49 103 103 103 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) by Jaroslav Kysela <perex@perex.cz> * Takashi Iwai <tiwai@suse.de> * * Generic memory allocators */ #include <linux/slab.h> #include <linux/mm.h> #include <linux/dma-mapping.h> #include <linux/dma-map-ops.h> #include <linux/genalloc.h> #include <linux/highmem.h> #include <linux/vmalloc.h> #ifdef CONFIG_X86 #include <asm/set_memory.h> #endif #include <sound/memalloc.h> struct snd_malloc_ops { void *(*alloc)(struct snd_dma_buffer *dmab, size_t size); void (*free)(struct snd_dma_buffer *dmab); dma_addr_t (*get_addr)(struct snd_dma_buffer *dmab, size_t offset); struct page *(*get_page)(struct snd_dma_buffer *dmab, size_t offset); unsigned int (*get_chunk_size)(struct snd_dma_buffer *dmab, unsigned int ofs, unsigned int size); int (*mmap)(struct snd_dma_buffer *dmab, struct vm_area_struct *area); void (*sync)(struct snd_dma_buffer *dmab, enum snd_dma_sync_mode mode); }; #define DEFAULT_GFP \ (GFP_KERNEL | \ __GFP_RETRY_MAYFAIL | /* don't trigger OOM-killer */ \ __GFP_NOWARN) /* no stack trace print - this call is non-critical */ static const struct snd_malloc_ops *snd_dma_get_ops(struct snd_dma_buffer *dmab); static void *__snd_dma_alloc_pages(struct snd_dma_buffer *dmab, size_t size) { const struct snd_malloc_ops *ops = snd_dma_get_ops(dmab); if (WARN_ON_ONCE(!ops || !ops->alloc)) return NULL; return ops->alloc(dmab, size); } /** * snd_dma_alloc_dir_pages - allocate the buffer area according to the given * type and direction * @type: the DMA buffer type * @device: the device pointer * @dir: DMA direction * @size: the buffer size to allocate * @dmab: buffer allocation record to store the allocated data * * Calls the memory-allocator function for the corresponding * buffer type. * * Return: Zero if the buffer with the given size is allocated successfully, * otherwise a negative value on error. */ int snd_dma_alloc_dir_pages(int type, struct device *device, enum dma_data_direction dir, size_t size, struct snd_dma_buffer *dmab) { if (WARN_ON(!size)) return -ENXIO; if (WARN_ON(!dmab)) return -ENXIO; size = PAGE_ALIGN(size); dmab->dev.type = type; dmab->dev.dev = device; dmab->dev.dir = dir; dmab->bytes = 0; dmab->addr = 0; dmab->private_data = NULL; dmab->area = __snd_dma_alloc_pages(dmab, size); if (!dmab->area) return -ENOMEM; dmab->bytes = size; return 0; } EXPORT_SYMBOL(snd_dma_alloc_dir_pages); /** * snd_dma_alloc_pages_fallback - allocate the buffer area according to the given type with fallback * @type: the DMA buffer type * @device: the device pointer * @size: the buffer size to allocate * @dmab: buffer allocation record to store the allocated data * * Calls the memory-allocator function for the corresponding * buffer type. When no space is left, this function reduces the size and * tries to allocate again. The size actually allocated is stored in * res_size argument. * * Return: Zero if the buffer with the given size is allocated successfully, * otherwise a negative value on error. */ int snd_dma_alloc_pages_fallback(int type, struct device *device, size_t size, struct snd_dma_buffer *dmab) { int err; while ((err = snd_dma_alloc_pages(type, device, size, dmab)) < 0) { if (err != -ENOMEM) return err; if (size <= PAGE_SIZE) return -ENOMEM; size >>= 1; size = PAGE_SIZE << get_order(size); } if (! dmab->area) return -ENOMEM; return 0; } EXPORT_SYMBOL(snd_dma_alloc_pages_fallback); /** * snd_dma_free_pages - release the allocated buffer * @dmab: the buffer allocation record to release * * Releases the allocated buffer via snd_dma_alloc_pages(). */ void snd_dma_free_pages(struct snd_dma_buffer *dmab) { const struct snd_malloc_ops *ops = snd_dma_get_ops(dmab); if (ops && ops->free) ops->free(dmab); } EXPORT_SYMBOL(snd_dma_free_pages); /* called by devres */ static void __snd_release_pages(struct device *dev, void *res) { snd_dma_free_pages(res); } /** * snd_devm_alloc_dir_pages - allocate the buffer and manage with devres * @dev: the device pointer * @type: the DMA buffer type * @dir: DMA direction * @size: the buffer size to allocate * * Allocate buffer pages depending on the given type and manage using devres. * The pages will be released automatically at the device removal. * * Unlike snd_dma_alloc_pages(), this function requires the real device pointer, * hence it can't work with SNDRV_DMA_TYPE_CONTINUOUS or * SNDRV_DMA_TYPE_VMALLOC type. * * Return: the snd_dma_buffer object at success, or NULL if failed */ struct snd_dma_buffer * snd_devm_alloc_dir_pages(struct device *dev, int type, enum dma_data_direction dir, size_t size) { struct snd_dma_buffer *dmab; int err; if (WARN_ON(type == SNDRV_DMA_TYPE_CONTINUOUS || type == SNDRV_DMA_TYPE_VMALLOC)) return NULL; dmab = devres_alloc(__snd_release_pages, sizeof(*dmab), GFP_KERNEL); if (!dmab) return NULL; err = snd_dma_alloc_dir_pages(type, dev, dir, size, dmab); if (err < 0) { devres_free(dmab); return NULL; } devres_add(dev, dmab); return dmab; } EXPORT_SYMBOL_GPL(snd_devm_alloc_dir_pages); /** * snd_dma_buffer_mmap - perform mmap of the given DMA buffer * @dmab: buffer allocation information * @area: VM area information * * Return: zero if successful, or a negative error code */ int snd_dma_buffer_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { const struct snd_malloc_ops *ops; if (!dmab) return -ENOENT; ops = snd_dma_get_ops(dmab); if (ops && ops->mmap) return ops->mmap(dmab, area); else return -ENOENT; } EXPORT_SYMBOL(snd_dma_buffer_mmap); #ifdef CONFIG_HAS_DMA /** * snd_dma_buffer_sync - sync DMA buffer between CPU and device * @dmab: buffer allocation information * @mode: sync mode */ void snd_dma_buffer_sync(struct snd_dma_buffer *dmab, enum snd_dma_sync_mode mode) { const struct snd_malloc_ops *ops; if (!dmab || !dmab->dev.need_sync) return; ops = snd_dma_get_ops(dmab); if (ops && ops->sync) ops->sync(dmab, mode); } EXPORT_SYMBOL_GPL(snd_dma_buffer_sync); #endif /* CONFIG_HAS_DMA */ /** * snd_sgbuf_get_addr - return the physical address at the corresponding offset * @dmab: buffer allocation information * @offset: offset in the ring buffer * * Return: the physical address */ dma_addr_t snd_sgbuf_get_addr(struct snd_dma_buffer *dmab, size_t offset) { const struct snd_malloc_ops *ops = snd_dma_get_ops(dmab); if (ops && ops->get_addr) return ops->get_addr(dmab, offset); else return dmab->addr + offset; } EXPORT_SYMBOL(snd_sgbuf_get_addr); /** * snd_sgbuf_get_page - return the physical page at the corresponding offset * @dmab: buffer allocation information * @offset: offset in the ring buffer * * Return: the page pointer */ struct page *snd_sgbuf_get_page(struct snd_dma_buffer *dmab, size_t offset) { const struct snd_malloc_ops *ops = snd_dma_get_ops(dmab); if (ops && ops->get_page) return ops->get_page(dmab, offset); else return virt_to_page(dmab->area + offset); } EXPORT_SYMBOL(snd_sgbuf_get_page); /** * snd_sgbuf_get_chunk_size - compute the max chunk size with continuous pages * on sg-buffer * @dmab: buffer allocation information * @ofs: offset in the ring buffer * @size: the requested size * * Return: the chunk size */ unsigned int snd_sgbuf_get_chunk_size(struct snd_dma_buffer *dmab, unsigned int ofs, unsigned int size) { const struct snd_malloc_ops *ops = snd_dma_get_ops(dmab); if (ops && ops->get_chunk_size) return ops->get_chunk_size(dmab, ofs, size); else return size; } EXPORT_SYMBOL(snd_sgbuf_get_chunk_size); /* * Continuous pages allocator */ static void *do_alloc_pages(struct device *dev, size_t size, dma_addr_t *addr, bool wc) { void *p; gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; again: p = alloc_pages_exact(size, gfp); if (!p) return NULL; *addr = page_to_phys(virt_to_page(p)); if (!dev) return p; if ((*addr + size - 1) & ~dev->coherent_dma_mask) { if (IS_ENABLED(CONFIG_ZONE_DMA32) && !(gfp & GFP_DMA32)) { gfp |= GFP_DMA32; goto again; } if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA)) { gfp = (gfp & ~GFP_DMA32) | GFP_DMA; goto again; } } #ifdef CONFIG_X86 if (wc) set_memory_wc((unsigned long)(p), size >> PAGE_SHIFT); #endif return p; } static void do_free_pages(void *p, size_t size, bool wc) { #ifdef CONFIG_X86 if (wc) set_memory_wb((unsigned long)(p), size >> PAGE_SHIFT); #endif free_pages_exact(p, size); } static void *snd_dma_continuous_alloc(struct snd_dma_buffer *dmab, size_t size) { return do_alloc_pages(dmab->dev.dev, size, &dmab->addr, false); } static void snd_dma_continuous_free(struct snd_dma_buffer *dmab) { do_free_pages(dmab->area, dmab->bytes, false); } static int snd_dma_continuous_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { return remap_pfn_range(area, area->vm_start, dmab->addr >> PAGE_SHIFT, area->vm_end - area->vm_start, area->vm_page_prot); } static const struct snd_malloc_ops snd_dma_continuous_ops = { .alloc = snd_dma_continuous_alloc, .free = snd_dma_continuous_free, .mmap = snd_dma_continuous_mmap, }; /* * VMALLOC allocator */ static void *snd_dma_vmalloc_alloc(struct snd_dma_buffer *dmab, size_t size) { return vmalloc(size); } static void snd_dma_vmalloc_free(struct snd_dma_buffer *dmab) { vfree(dmab->area); } static int snd_dma_vmalloc_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { return remap_vmalloc_range(area, dmab->area, 0); } #define get_vmalloc_page_addr(dmab, offset) \ page_to_phys(vmalloc_to_page((dmab)->area + (offset))) static dma_addr_t snd_dma_vmalloc_get_addr(struct snd_dma_buffer *dmab, size_t offset) { return get_vmalloc_page_addr(dmab, offset) + offset % PAGE_SIZE; } static struct page *snd_dma_vmalloc_get_page(struct snd_dma_buffer *dmab, size_t offset) { return vmalloc_to_page(dmab->area + offset); } static unsigned int snd_dma_vmalloc_get_chunk_size(struct snd_dma_buffer *dmab, unsigned int ofs, unsigned int size) { unsigned int start, end; unsigned long addr; start = ALIGN_DOWN(ofs, PAGE_SIZE); end = ofs + size - 1; /* the last byte address */ /* check page continuity */ addr = get_vmalloc_page_addr(dmab, start); for (;;) { start += PAGE_SIZE; if (start > end) break; addr += PAGE_SIZE; if (get_vmalloc_page_addr(dmab, start) != addr) return start - ofs; } /* ok, all on continuous pages */ return size; } static const struct snd_malloc_ops snd_dma_vmalloc_ops = { .alloc = snd_dma_vmalloc_alloc, .free = snd_dma_vmalloc_free, .mmap = snd_dma_vmalloc_mmap, .get_addr = snd_dma_vmalloc_get_addr, .get_page = snd_dma_vmalloc_get_page, .get_chunk_size = snd_dma_vmalloc_get_chunk_size, }; #ifdef CONFIG_HAS_DMA /* * IRAM allocator */ #ifdef CONFIG_GENERIC_ALLOCATOR static void *snd_dma_iram_alloc(struct snd_dma_buffer *dmab, size_t size) { struct device *dev = dmab->dev.dev; struct gen_pool *pool; void *p; if (dev->of_node) { pool = of_gen_pool_get(dev->of_node, "iram", 0); /* Assign the pool into private_data field */ dmab->private_data = pool; p = gen_pool_dma_alloc_align(pool, size, &dmab->addr, PAGE_SIZE); if (p) return p; } /* Internal memory might have limited size and no enough space, * so if we fail to malloc, try to fetch memory traditionally. */ dmab->dev.type = SNDRV_DMA_TYPE_DEV; return __snd_dma_alloc_pages(dmab, size); } static void snd_dma_iram_free(struct snd_dma_buffer *dmab) { struct gen_pool *pool = dmab->private_data; if (pool && dmab->area) gen_pool_free(pool, (unsigned long)dmab->area, dmab->bytes); } static int snd_dma_iram_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { area->vm_page_prot = pgprot_writecombine(area->vm_page_prot); return remap_pfn_range(area, area->vm_start, dmab->addr >> PAGE_SHIFT, area->vm_end - area->vm_start, area->vm_page_prot); } static const struct snd_malloc_ops snd_dma_iram_ops = { .alloc = snd_dma_iram_alloc, .free = snd_dma_iram_free, .mmap = snd_dma_iram_mmap, }; #endif /* CONFIG_GENERIC_ALLOCATOR */ /* * Coherent device pages allocator */ static void *snd_dma_dev_alloc(struct snd_dma_buffer *dmab, size_t size) { return dma_alloc_coherent(dmab->dev.dev, size, &dmab->addr, DEFAULT_GFP); } static void snd_dma_dev_free(struct snd_dma_buffer *dmab) { dma_free_coherent(dmab->dev.dev, dmab->bytes, dmab->area, dmab->addr); } static int snd_dma_dev_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { return dma_mmap_coherent(dmab->dev.dev, area, dmab->area, dmab->addr, dmab->bytes); } static const struct snd_malloc_ops snd_dma_dev_ops = { .alloc = snd_dma_dev_alloc, .free = snd_dma_dev_free, .mmap = snd_dma_dev_mmap, }; /* * Write-combined pages */ #ifdef CONFIG_SND_DMA_SGBUF /* x86-specific allocations */ static void *snd_dma_wc_alloc(struct snd_dma_buffer *dmab, size_t size) { void *p = do_alloc_pages(dmab->dev.dev, size, &dmab->addr, true); if (!p) return NULL; dmab->addr = dma_map_single(dmab->dev.dev, p, size, DMA_BIDIRECTIONAL); if (dma_mapping_error(dmab->dev.dev, dmab->addr)) { do_free_pages(dmab->area, size, true); return NULL; } return p; } static void snd_dma_wc_free(struct snd_dma_buffer *dmab) { dma_unmap_single(dmab->dev.dev, dmab->addr, dmab->bytes, DMA_BIDIRECTIONAL); do_free_pages(dmab->area, dmab->bytes, true); } static int snd_dma_wc_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { area->vm_page_prot = pgprot_writecombine(area->vm_page_prot); return dma_mmap_coherent(dmab->dev.dev, area, dmab->area, dmab->addr, dmab->bytes); } #else static void *snd_dma_wc_alloc(struct snd_dma_buffer *dmab, size_t size) { return dma_alloc_wc(dmab->dev.dev, size, &dmab->addr, DEFAULT_GFP); } static void snd_dma_wc_free(struct snd_dma_buffer *dmab) { dma_free_wc(dmab->dev.dev, dmab->bytes, dmab->area, dmab->addr); } static int snd_dma_wc_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { return dma_mmap_wc(dmab->dev.dev, area, dmab->area, dmab->addr, dmab->bytes); } #endif static const struct snd_malloc_ops snd_dma_wc_ops = { .alloc = snd_dma_wc_alloc, .free = snd_dma_wc_free, .mmap = snd_dma_wc_mmap, }; /* * Non-contiguous pages allocator */ static void *snd_dma_noncontig_alloc(struct snd_dma_buffer *dmab, size_t size) { struct sg_table *sgt; void *p; sgt = dma_alloc_noncontiguous(dmab->dev.dev, size, dmab->dev.dir, DEFAULT_GFP, 0); if (!sgt) return NULL; dmab->dev.need_sync = dma_need_sync(dmab->dev.dev, sg_dma_address(sgt->sgl)); p = dma_vmap_noncontiguous(dmab->dev.dev, size, sgt); if (p) { dmab->private_data = sgt; /* store the first page address for convenience */ dmab->addr = snd_sgbuf_get_addr(dmab, 0); } else { dma_free_noncontiguous(dmab->dev.dev, size, sgt, dmab->dev.dir); } return p; } static void snd_dma_noncontig_free(struct snd_dma_buffer *dmab) { dma_vunmap_noncontiguous(dmab->dev.dev, dmab->area); dma_free_noncontiguous(dmab->dev.dev, dmab->bytes, dmab->private_data, dmab->dev.dir); } static int snd_dma_noncontig_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { return dma_mmap_noncontiguous(dmab->dev.dev, area, dmab->bytes, dmab->private_data); } static void snd_dma_noncontig_sync(struct snd_dma_buffer *dmab, enum snd_dma_sync_mode mode) { if (mode == SNDRV_DMA_SYNC_CPU) { if (dmab->dev.dir == DMA_TO_DEVICE) return; invalidate_kernel_vmap_range(dmab->area, dmab->bytes); dma_sync_sgtable_for_cpu(dmab->dev.dev, dmab->private_data, dmab->dev.dir); } else { if (dmab->dev.dir == DMA_FROM_DEVICE) return; flush_kernel_vmap_range(dmab->area, dmab->bytes); dma_sync_sgtable_for_device(dmab->dev.dev, dmab->private_data, dmab->dev.dir); } } static inline void snd_dma_noncontig_iter_set(struct snd_dma_buffer *dmab, struct sg_page_iter *piter, size_t offset) { struct sg_table *sgt = dmab->private_data; __sg_page_iter_start(piter, sgt->sgl, sgt->orig_nents, offset >> PAGE_SHIFT); } static dma_addr_t snd_dma_noncontig_get_addr(struct snd_dma_buffer *dmab, size_t offset) { struct sg_dma_page_iter iter; snd_dma_noncontig_iter_set(dmab, &iter.base, offset); __sg_page_iter_dma_next(&iter); return sg_page_iter_dma_address(&iter) + offset % PAGE_SIZE; } static struct page *snd_dma_noncontig_get_page(struct snd_dma_buffer *dmab, size_t offset) { struct sg_page_iter iter; snd_dma_noncontig_iter_set(dmab, &iter, offset); __sg_page_iter_next(&iter); return sg_page_iter_page(&iter); } static unsigned int snd_dma_noncontig_get_chunk_size(struct snd_dma_buffer *dmab, unsigned int ofs, unsigned int size) { struct sg_dma_page_iter iter; unsigned int start, end; unsigned long addr; start = ALIGN_DOWN(ofs, PAGE_SIZE); end = ofs + size - 1; /* the last byte address */ snd_dma_noncontig_iter_set(dmab, &iter.base, start); if (!__sg_page_iter_dma_next(&iter)) return 0; /* check page continuity */ addr = sg_page_iter_dma_address(&iter); for (;;) { start += PAGE_SIZE; if (start > end) break; addr += PAGE_SIZE; if (!__sg_page_iter_dma_next(&iter) || sg_page_iter_dma_address(&iter) != addr) return start - ofs; } /* ok, all on continuous pages */ return size; } static const struct snd_malloc_ops snd_dma_noncontig_ops = { .alloc = snd_dma_noncontig_alloc, .free = snd_dma_noncontig_free, .mmap = snd_dma_noncontig_mmap, .sync = snd_dma_noncontig_sync, .get_addr = snd_dma_noncontig_get_addr, .get_page = snd_dma_noncontig_get_page, .get_chunk_size = snd_dma_noncontig_get_chunk_size, }; #ifdef CONFIG_SND_DMA_SGBUF /* Fallback SG-buffer allocations for x86 */ struct snd_dma_sg_fallback { struct sg_table sgt; /* used by get_addr - must be the first item */ size_t count; struct page **pages; unsigned int *npages; }; static void __snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab, struct snd_dma_sg_fallback *sgbuf) { bool wc = dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG; size_t i, size; if (sgbuf->pages && sgbuf->npages) { i = 0; while (i < sgbuf->count) { size = sgbuf->npages[i]; if (!size) break; do_free_pages(page_address(sgbuf->pages[i]), size << PAGE_SHIFT, wc); i += size; } } kvfree(sgbuf->pages); kvfree(sgbuf->npages); kfree(sgbuf); } /* fallback manual S/G buffer allocations */ static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size) { bool wc = dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG; struct snd_dma_sg_fallback *sgbuf; struct page **pagep, *curp; size_t chunk; dma_addr_t addr; unsigned int idx, npages; void *p; sgbuf = kzalloc_obj(*sgbuf); if (!sgbuf) return NULL; size = PAGE_ALIGN(size); sgbuf->count = size >> PAGE_SHIFT; sgbuf->pages = kvzalloc_objs(*sgbuf->pages, sgbuf->count); sgbuf->npages = kvcalloc(sgbuf->count, sizeof(*sgbuf->npages), GFP_KERNEL); if (!sgbuf->pages || !sgbuf->npages) goto error; pagep = sgbuf->pages; chunk = size; idx = 0; while (size > 0) { chunk = min(size, chunk); p = do_alloc_pages(dmab->dev.dev, chunk, &addr, wc); if (!p) { if (chunk <= PAGE_SIZE) goto error; chunk >>= 1; chunk = PAGE_SIZE << get_order(chunk); continue; } size -= chunk; /* fill pages */ npages = chunk >> PAGE_SHIFT; sgbuf->npages[idx] = npages; idx += npages; curp = virt_to_page(p); while (npages--) *pagep++ = curp++; } if (sg_alloc_table_from_pages(&sgbuf->sgt, sgbuf->pages, sgbuf->count, 0, sgbuf->count << PAGE_SHIFT, GFP_KERNEL)) goto error; if (dma_map_sgtable(dmab->dev.dev, &sgbuf->sgt, DMA_BIDIRECTIONAL, 0)) goto error_dma_map; p = vmap(sgbuf->pages, sgbuf->count, VM_MAP, PAGE_KERNEL); if (!p) goto error_vmap; dmab->private_data = sgbuf; /* store the first page address for convenience */ dmab->addr = snd_sgbuf_get_addr(dmab, 0); return p; error_vmap: dma_unmap_sgtable(dmab->dev.dev, &sgbuf->sgt, DMA_BIDIRECTIONAL, 0); error_dma_map: sg_free_table(&sgbuf->sgt); error: __snd_dma_sg_fallback_free(dmab, sgbuf); return NULL; } static void snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab) { struct snd_dma_sg_fallback *sgbuf = dmab->private_data; vunmap(dmab->area); dma_unmap_sgtable(dmab->dev.dev, &sgbuf->sgt, DMA_BIDIRECTIONAL, 0); sg_free_table(&sgbuf->sgt); __snd_dma_sg_fallback_free(dmab, dmab->private_data); } static int snd_dma_sg_fallback_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { struct snd_dma_sg_fallback *sgbuf = dmab->private_data; if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG) area->vm_page_prot = pgprot_writecombine(area->vm_page_prot); return vm_map_pages(area, sgbuf->pages, sgbuf->count); } static void *snd_dma_sg_alloc(struct snd_dma_buffer *dmab, size_t size) { int type = dmab->dev.type; void *p; /* try the standard DMA API allocation at first */ if (type == SNDRV_DMA_TYPE_DEV_WC_SG) dmab->dev.type = SNDRV_DMA_TYPE_DEV_WC; else dmab->dev.type = SNDRV_DMA_TYPE_DEV; p = __snd_dma_alloc_pages(dmab, size); if (p) return p; dmab->dev.type = type; /* restore the type */ return snd_dma_sg_fallback_alloc(dmab, size); } static const struct snd_malloc_ops snd_dma_sg_ops = { .alloc = snd_dma_sg_alloc, .free = snd_dma_sg_fallback_free, .mmap = snd_dma_sg_fallback_mmap, /* reuse noncontig helper */ .get_addr = snd_dma_noncontig_get_addr, /* reuse vmalloc helpers */ .get_page = snd_dma_vmalloc_get_page, .get_chunk_size = snd_dma_vmalloc_get_chunk_size, }; #endif /* CONFIG_SND_DMA_SGBUF */ /* * Non-coherent pages allocator */ static void *snd_dma_noncoherent_alloc(struct snd_dma_buffer *dmab, size_t size) { void *p; p = dma_alloc_noncoherent(dmab->dev.dev, size, &dmab->addr, dmab->dev.dir, DEFAULT_GFP); if (p) dmab->dev.need_sync = dma_need_sync(dmab->dev.dev, dmab->addr); return p; } static void snd_dma_noncoherent_free(struct snd_dma_buffer *dmab) { dma_free_noncoherent(dmab->dev.dev, dmab->bytes, dmab->area, dmab->addr, dmab->dev.dir); } static int snd_dma_noncoherent_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { area->vm_page_prot = vm_get_page_prot(area->vm_flags); return dma_mmap_pages(dmab->dev.dev, area, area->vm_end - area->vm_start, virt_to_page(dmab->area)); } static void snd_dma_noncoherent_sync(struct snd_dma_buffer *dmab, enum snd_dma_sync_mode mode) { if (mode == SNDRV_DMA_SYNC_CPU) { if (dmab->dev.dir != DMA_TO_DEVICE) dma_sync_single_for_cpu(dmab->dev.dev, dmab->addr, dmab->bytes, dmab->dev.dir); } else { if (dmab->dev.dir != DMA_FROM_DEVICE) dma_sync_single_for_device(dmab->dev.dev, dmab->addr, dmab->bytes, dmab->dev.dir); } } static const struct snd_malloc_ops snd_dma_noncoherent_ops = { .alloc = snd_dma_noncoherent_alloc, .free = snd_dma_noncoherent_free, .mmap = snd_dma_noncoherent_mmap, .sync = snd_dma_noncoherent_sync, }; #endif /* CONFIG_HAS_DMA */ /* * Entry points */ static const struct snd_malloc_ops *snd_dma_ops[] = { [SNDRV_DMA_TYPE_CONTINUOUS] = &snd_dma_continuous_ops, [SNDRV_DMA_TYPE_VMALLOC] = &snd_dma_vmalloc_ops, #ifdef CONFIG_HAS_DMA [SNDRV_DMA_TYPE_DEV] = &snd_dma_dev_ops, [SNDRV_DMA_TYPE_DEV_WC] = &snd_dma_wc_ops, [SNDRV_DMA_TYPE_NONCONTIG] = &snd_dma_noncontig_ops, [SNDRV_DMA_TYPE_NONCOHERENT] = &snd_dma_noncoherent_ops, #ifdef CONFIG_SND_DMA_SGBUF [SNDRV_DMA_TYPE_DEV_SG] = &snd_dma_sg_ops, [SNDRV_DMA_TYPE_DEV_WC_SG] = &snd_dma_sg_ops, #endif #ifdef CONFIG_GENERIC_ALLOCATOR [SNDRV_DMA_TYPE_DEV_IRAM] = &snd_dma_iram_ops, #endif /* CONFIG_GENERIC_ALLOCATOR */ #endif /* CONFIG_HAS_DMA */ }; static const struct snd_malloc_ops *snd_dma_get_ops(struct snd_dma_buffer *dmab) { if (WARN_ON_ONCE(!dmab)) return NULL; if (WARN_ON_ONCE(dmab->dev.type <= SNDRV_DMA_TYPE_UNKNOWN || dmab->dev.type >= ARRAY_SIZE(snd_dma_ops))) return NULL; return snd_dma_ops[dmab->dev.type]; } |
| 454 15 454 491 491 491 6 454 454 454 454 | 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 */ #ifndef _LINUX_SEQ_BUF_H #define _LINUX_SEQ_BUF_H #include <linux/bug.h> #include <linux/minmax.h> #include <linux/seq_file.h> #include <linux/types.h> /* * Trace sequences are used to allow a function to call several other functions * to create a string of data to use. */ /** * struct seq_buf - seq buffer structure * @buffer: pointer to the buffer * @size: size of the buffer * @len: the amount of data inside the buffer */ struct seq_buf { char *buffer; size_t size; size_t len; }; #define DECLARE_SEQ_BUF(NAME, SIZE) \ struct seq_buf NAME = { \ .buffer = (char[SIZE]) { 0 }, \ .size = SIZE, \ } static inline void seq_buf_clear(struct seq_buf *s) { s->len = 0; if (s->size) s->buffer[0] = '\0'; } static inline void seq_buf_init(struct seq_buf *s, char *buf, unsigned int size) { s->buffer = buf; s->size = size; seq_buf_clear(s); } /* * seq_buf have a buffer that might overflow. When this happens * len is set to be greater than size. */ static inline bool seq_buf_has_overflowed(struct seq_buf *s) { return s->len > s->size; } static inline void seq_buf_set_overflow(struct seq_buf *s) { s->len = s->size + 1; } /* * How much buffer is left on the seq_buf? */ static inline unsigned int seq_buf_buffer_left(struct seq_buf *s) { if (seq_buf_has_overflowed(s)) return 0; return s->size - s->len; } /* How much buffer was written? */ static inline unsigned int seq_buf_used(struct seq_buf *s) { return min(s->len, s->size); } /** * seq_buf_str - get NUL-terminated C string from seq_buf * @s: the seq_buf handle * * This makes sure that the buffer in @s is NUL-terminated and * safe to read as a string. * * Note, if this is called when the buffer has overflowed, then * the last byte of the buffer is zeroed, and the len will still * point passed it. * * After this function is called, s->buffer is safe to use * in string operations. * * Returns: @s->buf after making sure it is terminated. */ static inline const char *seq_buf_str(struct seq_buf * |