| 3 3 3 3 3 3 3 3 90 75 67 8 75 10 5 5 10 10 1 9 6 73 6 72 4 19 2 21 5 84 84 83 2 5 11 51 25 6 6 6 85 59 70 32 6 52 68 20 14 45 34 2 2 2 2 2 1 1 35 35 94 147 17 65 36 16 2 14 2 2 37 38 17 17 21 38 38 36 29 7 5 2 34 34 4 38 1 1 1 1 1 86 1 3 7 78 3 3 3 3 75 76 72 62 61 1 62 4 63 3 3 76 3 77 1 67 5 5 1 71 72 72 86 86 5 79 1 81 76 7 68 12 63 76 46 29 27 10 4 4 3 2 2 3 1 25 38 32 1 1 1 30 25 3 2 2 2 25 10 1 1 1 2 13 9 3 10 13 3 297 27 27 9 78 6 67 73 73 73 73 66 7 67 61 6 62 1 52 9 18 43 17 44 59 2 58 2 60 1 59 2 56 5 54 8 58 3 57 57 52 5 7 49 45 7 10 4 1 1 5 5 2 1 2 4 1 3 114 175 2 3 1 2 1 1 2 169 7 293 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 tunneling device * Linux INET6 implementation * * Authors: * Ville Nuorvala <vnuorval@tcs.hut.fi> * Yasuyuki Kozakai <kozakai@linux-ipv6.org> * * Based on: * linux/net/ipv6/sit.c and linux/net/ipv4/ipip.c * * RFC 2473 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/sockios.h> #include <linux/icmp.h> #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/route.h> #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> #include <linux/slab.h> #include <linux/hash.h> #include <linux/etherdevice.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <net/icmp.h> #include <net/ip.h> #include <net/ip_tunnels.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/ip6_tunnel.h> #include <net/xfrm.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netdev_lock.h> #include <net/dst_metadata.h> #include <net/inet_dscp.h> MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("ip6tnl"); MODULE_ALIAS_NETDEV("ip6tnl0"); #define IP6_TUNNEL_MAX_DEST_TLVS 8 #define IP6_TUNNEL_HASH_SIZE_SHIFT 5 #define IP6_TUNNEL_HASH_SIZE (1 << IP6_TUNNEL_HASH_SIZE_SHIFT) static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) { u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); return hash_32(hash, IP6_TUNNEL_HASH_SIZE_SHIFT); } static int ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); static struct rtnl_link_ops ip6_link_ops __read_mostly; static unsigned int ip6_tnl_net_id __read_mostly; struct ip6_tnl_net { /* the IPv6 tunnel fallback device */ struct net_device *fb_tnl_dev; /* lists for storing tunnels in use */ struct ip6_tnl __rcu *tnls_r_l[IP6_TUNNEL_HASH_SIZE]; struct ip6_tnl __rcu *tnls_wc[1]; struct ip6_tnl __rcu **tnls[2]; struct ip6_tnl __rcu *collect_md_tun; }; static inline int ip6_tnl_mpls_supported(void) { return IS_ENABLED(CONFIG_MPLS); } /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses * @net: network namespace * @link: ifindex of underlying interface * @remote: the address of the tunnel exit-point * @local: the address of the tunnel entry-point * * Return: * tunnel matching given end-points if found, * else fallback tunnel if its device is up, * else %NULL **/ static struct ip6_tnl * ip6_tnl_lookup(struct net *net, int link, const struct in6_addr *remote, const struct in6_addr *local) { unsigned int hash = HASH(remote, local); struct ip6_tnl *t, *cand = NULL; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct in6_addr any; for_each_ip_tunnel_rcu(t, ip6n->tnls_r_l[hash]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || !ipv6_addr_equal(remote, &t->parms.raddr) || !(t->dev->flags & IFF_UP)) continue; if (link == t->parms.link) return t; else cand = t; } memset(&any, 0, sizeof(any)); hash = HASH(&any, local); for_each_ip_tunnel_rcu(t, ip6n->tnls_r_l[hash]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || !ipv6_addr_any(&t->parms.raddr) || !(t->dev->flags & IFF_UP)) continue; if (link == t->parms.link) return t; else if (!cand) cand = t; } hash = HASH(remote, &any); for_each_ip_tunnel_rcu(t, ip6n->tnls_r_l[hash]) { if (!ipv6_addr_equal(remote, &t->parms.raddr) || !ipv6_addr_any(&t->parms.laddr) || !(t->dev->flags & IFF_UP)) continue; if (link == t->parms.link) return t; else if (!cand) cand = t; } if (cand) return cand; t = rcu_dereference(ip6n->collect_md_tun); if (t && t->dev->flags & IFF_UP) return t; t = rcu_dereference(ip6n->tnls_wc[0]); if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } /** * ip6_tnl_bucket - get head of list matching given tunnel parameters * @ip6n: the private data for ip6_vti in the netns * @p: parameters containing tunnel end-points * * Description: * ip6_tnl_bucket() returns the head of the list matching the * &struct in6_addr entries laddr and raddr in @p. * * Return: head of IPv6 tunnel list **/ static struct ip6_tnl __rcu ** ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct __ip6_tnl_parm *p) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; unsigned int h = 0; int prio = 0; if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { prio = 1; h = HASH(remote, local); } return &ip6n->tnls[prio][h]; } /** * ip6_tnl_link - add tunnel to hash table * @ip6n: the private data for ip6_vti in the netns * @t: tunnel to be added **/ static void ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms); if (t->parms.collect_md) rcu_assign_pointer(ip6n->collect_md_tun, t); rcu_assign_pointer(t->next , rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } /** * ip6_tnl_unlink - remove tunnel from hash table * @ip6n: the private data for ip6_vti in the netns * @t: tunnel to be removed **/ static void ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp; struct ip6_tnl *iter; if (t->parms.collect_md) rcu_assign_pointer(ip6n->collect_md_tun, NULL); for (tp = ip6_tnl_bucket(ip6n, &t->parms); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { rcu_assign_pointer(*tp, t->next); break; } } } static void ip6_dev_free(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); gro_cells_destroy(&t->gro_cells); dst_cache_destroy(&t->dst_cache); } static int ip6_tnl_create2(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct ip6_tnl_net *ip6n = net_generic(t->net, ip6_tnl_net_id); int err; dev->rtnl_link_ops = &ip6_link_ops; err = register_netdevice(dev); if (err < 0) goto out; strcpy(t->parms.name, dev->name); ip6_tnl_link(ip6n, t); return 0; out: return err; } /** * ip6_tnl_create - create a new tunnel * @net: network namespace * @p: tunnel parameters * * Description: * Create tunnel matching given parameters. * * Return: * created tunnel or error pointer **/ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) { struct net_device *dev; struct ip6_tnl *t; char name[IFNAMSIZ]; int err = -E2BIG; if (p->name[0]) { if (!dev_valid_name(p->name)) goto failed; strscpy(name, p->name, IFNAMSIZ); } else { sprintf(name, "ip6tnl%%d"); } err = -ENOMEM; dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ip6_tnl_dev_setup); if (!dev) goto failed; dev_net_set(dev, net); t = netdev_priv(dev); t->parms = *p; t->net = dev_net(dev); err = ip6_tnl_create2(dev); if (err < 0) goto failed_free; return t; failed_free: free_netdev(dev); failed: return ERR_PTR(err); } /** * ip6_tnl_locate - find or create tunnel matching given parameters * @net: network namespace * @p: tunnel parameters * @create: != 0 if allowed to create new tunnel if no match found * * Description: * ip6_tnl_locate() first tries to locate an existing tunnel * based on @parms. If this is unsuccessful, but @create is set a new * tunnel device is created and registered for use. * * Return: * matching tunnel or error pointer **/ static struct ip6_tnl *ip6_tnl_locate(struct net *net, struct __ip6_tnl_parm *p, int create) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; struct ip6_tnl __rcu **tp; struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); for (tp = ip6_tnl_bucket(ip6n, p); (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && p->link == t->parms.link) { if (create) return ERR_PTR(-EEXIST); return t; } } if (!create) return ERR_PTR(-ENODEV); return ip6_tnl_create(net, p); } /** * ip6_tnl_dev_uninit - tunnel device uninitializer * @dev: the device to be destroyed * * Description: * ip6_tnl_dev_uninit() removes tunnel from its list **/ static void ip6_tnl_dev_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev == ip6n->fb_tnl_dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else ip6_tnl_unlink(ip6n, t); dst_cache_reset(&t->dst_cache); netdev_put(dev, &t->dev_tracker); } /** * ip6_tnl_parse_tlv_enc_lim - handle encapsulation limit option * @skb: received socket buffer * @raw: the ICMPv6 error message data * * Return: * 0 if none was found, * else index to encapsulation limit **/ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) { const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw; unsigned int nhoff = raw - skb->data; unsigned int off = nhoff + sizeof(*ipv6h); u8 nexthdr = ipv6h->nexthdr; while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) { struct ipv6_opt_hdr *hdr; u16 optlen; if (!pskb_may_pull(skb, off + sizeof(*hdr))) break; hdr = (struct ipv6_opt_hdr *)(skb->data + off); if (nexthdr == NEXTHDR_FRAGMENT) { optlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { optlen = ipv6_authlen(hdr); } else { optlen = ipv6_optlen(hdr); } if (!pskb_may_pull(skb, off + optlen)) break; hdr = (struct ipv6_opt_hdr *)(skb->data + off); if (nexthdr == NEXTHDR_FRAGMENT) { struct frag_hdr *frag_hdr = (struct frag_hdr *)hdr; if (frag_hdr->frag_off) break; } if (nexthdr == NEXTHDR_DEST) { int tlv_cnt = 0; u16 i = 2; while (1) { struct ipv6_tlv_tnl_enc_lim *tel; if (unlikely(tlv_cnt++ >= IP6_TUNNEL_MAX_DEST_TLVS)) break; /* No more room for encapsulation limit */ if (i + sizeof(*tel) > optlen) break; tel = (struct ipv6_tlv_tnl_enc_lim *)(skb->data + off + i); /* return index of option if found and valid */ if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT && tel->length == 1) return i + off - nhoff; /* else jump to next option */ if (tel->type) i += tel->length + 2; else i++; } } nexthdr = hdr->nexthdr; off += optlen; } return 0; } EXPORT_SYMBOL(ip6_tnl_parse_tlv_enc_lim); /* ip6_tnl_err() should handle errors in the tunnel according to the * specifications in RFC 2473. */ static int ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, u8 *type, u8 *code, int *msg, __u32 *info, int offset) { const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data; struct net *net = dev_net(skb->dev); u8 rel_type = ICMPV6_DEST_UNREACH; u8 rel_code = ICMPV6_ADDR_UNREACH; __u32 rel_info = 0; struct ip6_tnl *t; int err = -ENOENT; int rel_msg = 0; u8 tproto; __u16 len; /* If the packet doesn't contain the original IPv6 header we are in trouble since we might need the source address for further processing of the error. */ rcu_read_lock(); t = ip6_tnl_lookup(dev_net(skb->dev), skb->dev->ifindex, &ipv6h->daddr, &ipv6h->saddr); if (!t) goto out; tproto = READ_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto out; err = 0; switch (*type) { case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); rel_msg = 1; break; case ICMPV6_TIME_EXCEED: if ((*code) == ICMPV6_EXC_HOPLIMIT) { net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", t->parms.name); rel_msg = 1; } break; case ICMPV6_PARAMPROB: { struct ipv6_tlv_tnl_enc_lim *tel; __u32 teli; teli = 0; if ((*code) == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); if (teli && teli == *info - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; if (tel->encap_limit == 0) { net_dbg_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", t->parms.name); rel_msg = 1; } } else { net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n", t->parms.name); } break; } case ICMPV6_PKT_TOOBIG: { __u32 mtu; ip6_update_pmtu(skb, net, htonl(*info), 0, 0, sock_net_uid(net, NULL)); mtu = *info - offset; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; len = sizeof(*ipv6h) + ntohs(ipv6h->payload_len); if (len > mtu) { rel_type = ICMPV6_PKT_TOOBIG; rel_code = 0; rel_info = mtu; rel_msg = 1; } break; } case NDISC_REDIRECT: ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); break; } *type = rel_type; *code = rel_code; *info = rel_info; *msg = rel_msg; out: rcu_read_unlock(); return err; } static int ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __u32 rel_info = ntohl(info); const struct iphdr *eiph; struct sk_buff *skb2; int err, rel_msg = 0; u8 rel_type = type; u8 rel_code = code; struct rtable *rt; struct flowi4 fl4; err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); if (err < 0) return err; if (rel_msg == 0) return 0; switch (rel_type) { case ICMPV6_DEST_UNREACH: if (rel_code != ICMPV6_ADDR_UNREACH) return 0; rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_HOST_UNREACH; break; case ICMPV6_PKT_TOOBIG: if (rel_code != 0) return 0; rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_FRAG_NEEDED; break; default: return 0; } if (!pskb_may_pull(skb, offset + sizeof(struct iphdr))) return 0; skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) return 0; /* Remove debris left by IPv6 stack. */ memset(IPCB(skb2), 0, sizeof(*IPCB(skb2))); skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); eiph = ip_hdr(skb2); if (eiph->version != 4 || eiph->ihl < 5) goto out; /* Try to guess incoming interface */ rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr, 0, 0, 0, IPPROTO_IPIP, eiph->tos & INET_DSCP_MASK, 0); if (IS_ERR(rt)) goto out; skb2->dev = rt->dst.dev; ip_rt_put(rt); /* route "incoming" packet */ if (rt->rt_flags & RTCF_LOCAL) { rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->daddr, eiph->saddr, 0, 0, IPPROTO_IPIP, eiph->tos & INET_DSCP_MASK, 0); if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) { if (!IS_ERR(rt)) ip_rt_put(rt); goto out; } skb_dst_set(skb2, &rt->dst); } else { if (ip_route_input(skb2, eiph->daddr, eiph->saddr, ip4h_dscp(eiph), skb2->dev) || skb_dst_dev(skb2)->type != ARPHRD_TUNNEL6) goto out; } /* change mtu on this route */ if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) { if (rel_info > dst6_mtu(skb_dst(skb2))) goto out; skb_dst_update_pmtu_no_confirm(skb2, rel_info); } icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); out: kfree_skb(skb2); return 0; } static int ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __u32 rel_info = ntohl(info); int err, rel_msg = 0; u8 rel_type = type; u8 rel_code = code; err = ip6_tnl_err(skb, IPPROTO_IPV6, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); if (err < 0) return err; if (rel_msg && pskb_may_pull(skb, offset + sizeof(struct ipv6hdr))) { struct rt6_info *rt; struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) return 0; skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); /* Try to guess incoming interface */ rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, skb2, 0); if (rt && rt->dst.dev) skb2->dev = rt->dst.dev; icmpv6_send(skb2, rel_type, rel_code, rel_info); ip6_rt_put(rt); kfree_skb(skb2); } return 0; } static int mplsip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __u32 rel_info = ntohl(info); int err, rel_msg = 0; u8 rel_type = type; u8 rel_code = code; err = ip6_tnl_err(skb, IPPROTO_MPLS, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); return err; } static int ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb) { __u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK; if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield); return IP6_ECN_decapsulate(ipv6h, skb); } static int ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb) { if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb)); return IP6_ECN_decapsulate(ipv6h, skb); } static inline int mplsip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb) { /* ECN is not supported in AF_MPLS */ return 0; } __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { struct __ip6_tnl_parm *p = &t->parms; int ltype = ipv6_addr_type(laddr); int rtype = ipv6_addr_type(raddr); __u32 flags = 0; if (ltype == IPV6_ADDR_ANY || rtype == IPV6_ADDR_ANY) { flags = IP6_TNL_F_CAP_PER_PACKET; } else if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && !((ltype|rtype) & IPV6_ADDR_LOOPBACK) && (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) { if (ltype&IPV6_ADDR_UNICAST) flags |= IP6_TNL_F_CAP_XMIT; if (rtype&IPV6_ADDR_UNICAST) flags |= IP6_TNL_F_CAP_RCV; } return flags; } EXPORT_SYMBOL(ip6_tnl_get_cap); /* called with rcu_read_lock() */ int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { struct __ip6_tnl_parm *p = &t->parms; int ret = 0; struct net *net = t->net; if ((p->flags & IP6_TNL_F_CAP_RCV) || ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_RCV))) { struct net_device *ldev = NULL; if (p->link) ldev = dev_get_by_index_rcu(net, p->link); if ((ipv6_addr_is_multicast(laddr) || likely(ipv6_chk_addr_and_flags(net, laddr, ldev, false, 0, IFA_F_TENTATIVE))) && ((p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) || likely(!ipv6_chk_addr_and_flags(net, raddr, ldev, true, 0, IFA_F_TENTATIVE)))) ret = 1; } return ret; } EXPORT_SYMBOL_GPL(ip6_tnl_rcv_ctl); static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb), bool log_ecn_err) { const struct ipv6hdr *ipv6h; int nh, err; if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } tunnel->i_seqno = ntohl(tpi->seq) + 1; } skb->protocol = tpi->proto; /* Warning: All skb pointers will be invalidated! */ if (tunnel->dev->type == ARPHRD_ETHER) { if (!pskb_may_pull(skb, ETH_HLEN)) { DEV_STATS_INC(tunnel->dev, rx_length_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { skb->dev = tunnel->dev; skb_reset_mac_header(skb); } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); if (skb_vlan_inet_prepare(skb, true)) { DEV_STATS_INC(tunnel->dev, rx_length_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } /* Get the outer header. */ ipv6h = (struct ipv6hdr *)(skb->head + nh); memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); err = dscp_ecn_decapsulate(tunnel, ipv6h, skb); if (unlikely(err)) { if (log_ecn_err) net_info_ratelimited("non-ECT from %pI6 with DS=%#x\n", &ipv6h->saddr, ipv6_get_dsfield(ipv6h)); if (err > 1) { DEV_STATS_INC(tunnel->dev, rx_frame_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } } dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); if (tun_dst) skb_dst_set(skb, (struct dst_entry *)tun_dst); gro_cells_receive(&tunnel->gro_cells, skb); return 0; drop: if (tun_dst) dst_release((struct dst_entry *)tun_dst); kfree_skb(skb); return 0; } int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_err) { int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb); dscp_ecn_decapsulate = ip6ip6_dscp_ecn_decapsulate; if (tpi->proto == htons(ETH_P_IP)) dscp_ecn_decapsulate = ip4ip6_dscp_ecn_decapsulate; return __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate, log_ecn_err); } EXPORT_SYMBOL(ip6_tnl_rcv); static const struct tnl_ptk_info tpi_v6 = { /* no tunnel info required for ipxip6. */ .proto = htons(ETH_P_IPV6), }; static const struct tnl_ptk_info tpi_v4 = { /* no tunnel info required for ipxip6. */ .proto = htons(ETH_P_IP), }; static const struct tnl_ptk_info tpi_mpls = { /* no tunnel info required for mplsip6. */ .proto = htons(ETH_P_MPLS_UC), }; static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, const struct tnl_ptk_info *tpi, int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb)) { struct ip6_tnl *t; const struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct metadata_dst *tun_dst = NULL; int ret = -1; rcu_read_lock(); t = ip6_tnl_lookup(dev_net(skb->dev), skb->dev->ifindex, &ipv6h->saddr, &ipv6h->daddr); if (t) { u8 tproto = READ_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto drop; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; ipv6h = ipv6_hdr(skb); if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) goto drop; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; if (t->parms.collect_md) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; tun_dst = ipv6_tun_rx_dst(skb, flags, 0, 0); if (!tun_dst) goto drop; } ret = __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate, log_ecn_error); } rcu_read_unlock(); return ret; drop: rcu_read_unlock(); kfree_skb(skb); return 0; } static int ip4ip6_rcv(struct sk_buff *skb) { return ipxip6_rcv(skb, IPPROTO_IPIP, &tpi_v4, ip4ip6_dscp_ecn_decapsulate); } static int ip6ip6_rcv(struct sk_buff *skb) { return ipxip6_rcv(skb, IPPROTO_IPV6, &tpi_v6, ip6ip6_dscp_ecn_decapsulate); } static int mplsip6_rcv(struct sk_buff *skb) { return ipxip6_rcv(skb, IPPROTO_MPLS, &tpi_mpls, mplsip6_dscp_ecn_decapsulate); } struct ipv6_tel_txoption { struct ipv6_txoptions ops; __u8 dst_opt[8]; }; static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit) { memset(opt, 0, sizeof(struct ipv6_tel_txoption)); opt->dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT; opt->dst_opt[3] = 1; opt->dst_opt[4] = encap_limit; opt->dst_opt[5] = IPV6_TLV_PADN; opt->dst_opt[6] = 1; opt->ops.dst1opt = (struct ipv6_opt_hdr *) opt->dst_opt; opt->ops.opt_nflen = 8; } /** * ip6_tnl_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device * @hdr: IPv6 header from the incoming packet * * Description: * Avoid trivial tunneling loop by checking that tunnel exit-point * doesn't match source of incoming packet. * * Return: * 1 if conflict, * 0 else **/ static inline bool ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) { return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { struct __ip6_tnl_parm *p = &t->parms; int ret = 0; struct net *net = t->net; if (t->parms.collect_md) return 1; if ((p->flags & IP6_TNL_F_CAP_XMIT) || ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_XMIT))) { struct net_device *ldev = NULL; rcu_read_lock(); if (p->link) ldev = dev_get_by_index_rcu(net, p->link); if (unlikely(!ipv6_chk_addr_and_flags(net, laddr, ldev, false, 0, IFA_F_TENTATIVE))) pr_warn_ratelimited("%s xmit: Local address not yet configured!\n", p->name); else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) && !ipv6_addr_is_multicast(raddr) && unlikely(ipv6_chk_addr_and_flags(net, raddr, ldev, true, 0, IFA_F_TENTATIVE))) pr_warn_ratelimited("%s xmit: Routing loop! Remote address found on this node!\n", p->name); else ret = 1; rcu_read_unlock(); } return ret; } EXPORT_SYMBOL_GPL(ip6_tnl_xmit_ctl); /** * ip6_tnl_xmit - encapsulate packet and send * @skb: the outgoing socket buffer * @dev: the outgoing tunnel device * @dsfield: dscp code for outer header * @fl6: flow of tunneled packet * @encap_limit: encapsulation limit * @pmtu: Path MTU is stored if packet is too big * @proto: next header value * * Description: * Build new header and do some sanity checks on the packet before sending * it. * * Return: * 0 on success * -1 fail * %-EMSGSIZE message too big. return mtu in this case. **/ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, struct flowi6 *fl6, int encap_limit, __u32 *pmtu, __u8 proto) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct ipv6hdr *ipv6h; struct ipv6_tel_txoption opt; struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; int mtu; unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0; unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen; unsigned int max_headroom = psh_hlen; __be16 payload_protocol; bool use_cache = false; u8 hop_limit; int err = -1; payload_protocol = skb_protocol(skb, true); if (t->parms.collect_md) { hop_limit = skb_tunnel_info(skb)->key.ttl; goto route_lookup; } else { hop_limit = t->parms.hop_limit; } /* NBMA tunnel */ if (ipv6_addr_any(&t->parms.raddr)) { if (payload_protocol == htons(ETH_P_IPV6)) { struct in6_addr *addr6; struct neighbour *neigh; int addr_type; if (!skb_dst(skb)) goto tx_err_link_failure; neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (!neigh) goto tx_err_link_failure; addr6 = (struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) addr6 = &ipv6_hdr(skb)->daddr; memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); } else if (payload_protocol == htons(ETH_P_IP)) { const struct rtable *rt = skb_rtable(skb); if (!rt) goto tx_err_link_failure; if (rt->rt_gw_family == AF_INET6) memcpy(&fl6->daddr, &rt->rt_gw6, sizeof(fl6->daddr)); } } else if (t->parms.proto != 0 && !(t->parms.flags & (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { /* enable the cache only if neither the outer protocol nor the * routing decision depends on the current inner header value */ use_cache = true; } if (use_cache) dst = dst_cache_get(&t->dst_cache); if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr)) goto tx_err_link_failure; if (!dst) { route_lookup: /* add dsfield to flowlabel for route lookup */ fl6->flowlabel = ip6_make_flowinfo(dsfield, fl6->flowlabel); dst = ip6_route_output(net, NULL, fl6); if (dst->error) goto tx_err_link_failure; dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto tx_err_link_failure; } if (t->parms.collect_md && ipv6_addr_any(&fl6->saddr) && ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev, &fl6->daddr, 0, &fl6->saddr)) goto tx_err_link_failure; ndst = dst; } tdev = dst_dev(dst); if (tdev == dev) { DEV_STATS_INC(dev, collisions); net_warn_ratelimited("%s: Local routing loop detected!\n", t->parms.name); goto tx_err_dst_release; } mtu = dst6_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen; if (encap_limit >= 0) { max_headroom += 8; mtu -= 8; } mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ? IPV6_MIN_MTU : IPV4_MIN_MTU); skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { *pmtu = mtu; err = -EMSGSIZE; goto tx_err_dst_release; } if (t->err_count > 0) { if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO)) { t->err_count--; dst_link_failure(skb); } else { t->err_count = 0; } } skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom += LL_RESERVED_SPACE(tdev); if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb; new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) goto tx_err_dst_release; if (skb->sk) skb_set_owner_w(new_skb, skb->sk); consume_skb(skb); skb = new_skb; } if (t->parms.collect_md) { if (t->encap.type != TUNNEL_ENCAP_NONE) goto tx_err_dst_release; } else { if (use_cache && ndst) dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr); } skb_dst_set(skb, dst); if (hop_limit == 0) { if (payload_protocol == htons(ETH_P_IP)) hop_limit = ip_hdr(skb)->ttl; else if (payload_protocol == htons(ETH_P_IPV6)) hop_limit = ipv6_hdr(skb)->hop_limit; else hop_limit = ip6_dst_hoplimit(dst); } /* Calculate max headroom for all the headers and adjust * needed_headroom if necessary. */ max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr) + dst->header_len + t->hlen; ip_tunnel_adj_headroom(dev, max_headroom); err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) return err; if (encap_limit >= 0) { init_tel_txopt(&opt, encap_limit); proto = ipv6_push_frag_opts(skb, &opt.ops, proto); } skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); ip6_flow_hdr(ipv6h, dsfield, ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6)); ipv6h->hop_limit = hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; ipv6h->daddr = fl6->daddr; ip6tunnel_xmit(NULL, skb, dev, 0); return 0; tx_err_link_failure: DEV_STATS_INC(dev, tx_carrier_errors); dst_link_failure(skb); tx_err_dst_release: dst_release(dst); return err; } EXPORT_SYMBOL(ip6_tnl_xmit); static inline int ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, u8 protocol) { struct ip6_tnl *t = netdev_priv(dev); struct ipv6hdr *ipv6h; const struct iphdr *iph; int encap_limit = -1; __u16 offset; struct flowi6 fl6; __u8 dsfield, orig_dsfield; __u32 mtu; u8 tproto; int err; tproto = READ_ONCE(t->parms.proto); if (tproto != protocol && tproto != 0) return -1; if (t->parms.collect_md) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET6)) return -1; key = &tun_info->key; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = protocol; fl6.saddr = key->u.ipv6.src; fl6.daddr = key->u.ipv6.dst; fl6.flowlabel = key->label; dsfield = key->tos; switch (protocol) { case IPPROTO_IPIP: iph = ip_hdr(skb); orig_dsfield = ipv4_get_dsfield(iph); break; case IPPROTO_IPV6: ipv6h = ipv6_hdr(skb); orig_dsfield = ipv6_get_dsfield(ipv6h); break; default: orig_dsfield = dsfield; break; } } else { if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; if (protocol == IPPROTO_IPV6) { offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); /* ip6_tnl_parse_tlv_enc_lim() might have * reallocated skb->head */ if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; tel = (void *)&skb_network_header(skb)[offset]; if (tel->encap_limit == 0) { icmpv6_ndo_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, offset + 2); return -1; } encap_limit = tel->encap_limit - 1; } } memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); fl6.flowi6_proto = protocol; if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) fl6.flowi6_mark = skb->mark; else fl6.flowi6_mark = t->parms.fwmark; switch (protocol) { case IPPROTO_IPIP: iph = ip_hdr(skb); orig_dsfield = ipv4_get_dsfield(iph); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) dsfield = orig_dsfield; else dsfield = ip6_tclass(t->parms.flowinfo); break; case IPPROTO_IPV6: ipv6h = ipv6_hdr(skb); orig_dsfield = ipv6_get_dsfield(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) dsfield = orig_dsfield; else dsfield = ip6_tclass(t->parms.flowinfo); if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL) fl6.flowlabel |= ip6_flowlabel(ipv6h); break; default: orig_dsfield = dsfield = ip6_tclass(t->parms.flowinfo); break; } } fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); dsfield = INET_ECN_encapsulate(dsfield, orig_dsfield); if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; skb_set_inner_ipproto(skb, protocol); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, protocol); if (err != 0) { /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) switch (protocol) { case IPPROTO_IPIP: icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); break; case IPPROTO_IPV6: icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); break; default: break; } return -1; } return 0; } static netdev_tx_t ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); u8 ipproto; int ret; if (!pskb_inet_may_pull(skb)) goto tx_err; switch (skb->protocol) { case htons(ETH_P_IP): ipproto = IPPROTO_IPIP; break; case htons(ETH_P_IPV6): if (ip6_tnl_addr_conflict(t, ipv6_hdr(skb))) goto tx_err; ipproto = IPPROTO_IPV6; break; case htons(ETH_P_MPLS_UC): ipproto = IPPROTO_MPLS; break; default: goto tx_err; } ret = ipxip6_tnl_xmit(skb, dev, ipproto); if (ret < 0) goto tx_err; return NETDEV_TX_OK; tx_err: DEV_STATS_INC(dev, tx_errors); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } static void ip6_tnl_link_config(struct ip6_tnl *t) { struct net_device *dev = t->dev; struct net_device *tdev = NULL; struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; int t_hlen; int mtu; __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); /* Set up flowi template */ fl6->saddr = p->laddr; fl6->daddr = p->raddr; fl6->flowi6_oif = p->link; fl6->flowlabel = 0; if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS)) fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL)) fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV|IP6_TNL_F_CAP_PER_PACKET); p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); if (p->flags&IP6_TNL_F_CAP_XMIT && p->flags&IP6_TNL_F_CAP_RCV) dev->flags |= IFF_POINTOPOINT; else dev->flags &= ~IFF_POINTOPOINT; t->tun_hlen = 0; t->hlen = t->encap_hlen + t->tun_hlen; t_hlen = t->hlen + sizeof(struct ipv6hdr); if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)); struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, p->link, NULL, strict); if (rt) { tdev = rt->dst.dev; ip6_rt_put(rt); } if (!tdev && p->link) tdev = __dev_get_by_index(t->net, p->link); if (tdev) { dev->needed_headroom = tdev->hard_header_len + tdev->needed_headroom + t_hlen; mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); mtu = mtu - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) mtu -= 8; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; WRITE_ONCE(dev->mtu, mtu); } } } /** * ip6_tnl_change - update the tunnel parameters * @t: tunnel to be changed * @p: tunnel configuration parameters * * Description: * ip6_tnl_change() updates the tunnel parameters **/ static void ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) { t->parms.laddr = p->laddr; t->parms.raddr = p->raddr; t->parms.flags = p->flags; t->parms.hop_limit = p->hop_limit; t->parms.encap_limit = p->encap_limit; t->parms.flowinfo = p->flowinfo; t->parms.link = p->link; t->parms.proto = p->proto; t->parms.fwmark = p->fwmark; dst_cache_reset(&t->dst_cache); ip6_tnl_link_config(t); } static void ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) { struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); ip6_tnl_unlink(ip6n, t); synchronize_net(); ip6_tnl_change(t, p); ip6_tnl_link(ip6n, t); netdev_state_change(t->dev); } static int ip6_tnl0_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p, bool strict) { /* For the default ip6tnl0 device, allow changing only the protocol * (the IP6_TNL_F_CAP_PER_PACKET flag is set on ip6tnl0, and all other * parameters are 0). */ if (strict && (!ipv6_addr_any(&p->laddr) || !ipv6_addr_any(&p->raddr) || p->flags != t->parms.flags || p->hop_limit || p->encap_limit || p->flowinfo || p->link || p->fwmark || p->collect_md)) return -EINVAL; t->parms.proto = p->proto; netdev_state_change(t->dev); return 0; } static void ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u) { p->laddr = u->laddr; p->raddr = u->raddr; p->flags = u->flags; p->hop_limit = u->hop_limit; p->encap_limit = u->encap_limit; p->flowinfo = u->flowinfo; p->link = u->link; p->proto = u->proto; memcpy(p->name, u->name, sizeof(u->name)); } static void ip6_tnl_parm_to_user(struct ip6_tnl_parm *u, const struct __ip6_tnl_parm *p) { u->laddr = p->laddr; u->raddr = p->raddr; u->flags = p->flags; u->hop_limit = p->hop_limit; u->encap_limit = p->encap_limit; u->flowinfo = p->flowinfo; u->link = p->link; u->proto = p->proto; memcpy(u->name, p->name, sizeof(u->name)); } /** * ip6_tnl_siocdevprivate - configure ipv6 tunnels from userspace * @dev: virtual device associated with tunnel * @ifr: unused * @data: parameters passed from userspace * @cmd: command to be performed * * Description: * ip6_tnl_ioctl() is used for managing IPv6 tunnels * from userspace. * * The possible commands are the following: * %SIOCGETTUNNEL: get tunnel parameters for device * %SIOCADDTUNNEL: add tunnel matching given tunnel parameters * %SIOCCHGTUNNEL: change tunnel parameters to those given * %SIOCDELTUNNEL: delete tunnel * * The fallback device "ip6tnl0", created during module * initialization, can be used for creating other tunnel devices. * * Return: * 0 on success, * %-EFAULT if unable to copy data to or from userspace, * %-EPERM if current process hasn't %CAP_NET_ADMIN set * %-EINVAL if passed tunnel parameters are invalid, * %-EEXIST if changing a tunnel's parameters would cause a conflict * %-ENODEV if attempting to change or delete a nonexisting device **/ static int ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { int err = 0; struct ip6_tnl_parm p; struct __ip6_tnl_parm p1; struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); memset(&p1, 0, sizeof(p1)); switch (cmd) { case SIOCGETTUNNEL: if (dev == ip6n->fb_tnl_dev) { if (copy_from_user(&p, data, sizeof(p))) { err = -EFAULT; break; } ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); if (IS_ERR(t)) t = netdev_priv(dev); } else { memset(&p, 0, sizeof(p)); } ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = -EFAULT; if (copy_from_user(&p, data, sizeof(p))) break; err = -EINVAL; if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP && p.proto != 0) break; ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, cmd == SIOCADDTUNNEL); if (cmd == SIOCCHGTUNNEL) { if (!IS_ERR(t)) { if (t->dev != dev) { err = -EEXIST; break; } } else t = netdev_priv(dev); if (dev == ip6n->fb_tnl_dev) ip6_tnl0_update(t, &p1, false); else ip6_tnl_update(t, &p1); } if (!IS_ERR(t)) { err = 0; ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; } else { err = PTR_ERR(t); } break; case SIOCDELTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (dev == ip6n->fb_tnl_dev) { err = -EFAULT; if (copy_from_user(&p, data, sizeof(p))) break; err = -ENOENT; ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); if (IS_ERR(t)) break; err = -EPERM; if (t->dev == ip6n->fb_tnl_dev) break; dev = t->dev; } err = 0; unregister_netdevice(dev); break; default: err = -EINVAL; } return err; } /** * ip6_tnl_change_mtu - change mtu manually for tunnel device * @dev: virtual device associated with tunnel * @new_mtu: the new mtu * * Return: * 0 on success, * %-EINVAL if mtu too small **/ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { struct ip6_tnl *tnl = netdev_priv(dev); int t_hlen; t_hlen = tnl->hlen + sizeof(struct ipv6hdr); if (tnl->parms.proto == IPPROTO_IPV6) { if (new_mtu < IPV6_MIN_MTU) return -EINVAL; } else { if (new_mtu < ETH_MIN_MTU) return -EINVAL; } if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) { if (new_mtu > IP6_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } else { if (new_mtu > IP_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(ip6_tnl_change_mtu); int ip6_tnl_get_iflink(const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); return READ_ONCE(t->parms.link); } EXPORT_SYMBOL(ip6_tnl_get_iflink); int ip6_tnl_encap_add_ops(const struct ip6_tnl_encap_ops *ops, unsigned int num) { if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; return !cmpxchg((const struct ip6_tnl_encap_ops **) &ip6tun_encaps[num], NULL, ops) ? 0 : -1; } EXPORT_SYMBOL(ip6_tnl_encap_add_ops); int ip6_tnl_encap_del_ops(const struct ip6_tnl_encap_ops *ops, unsigned int num) { int ret; if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; ret = (cmpxchg((const struct ip6_tnl_encap_ops **) &ip6tun_encaps[num], ops, NULL) == ops) ? 0 : -1; synchronize_net(); return ret; } EXPORT_SYMBOL(ip6_tnl_encap_del_ops); int ip6_tnl_encap_setup(struct ip6_tnl *t, struct ip_tunnel_encap *ipencap) { int hlen; memset(&t->encap, 0, sizeof(t->encap)); hlen = ip6_encap_hlen(ipencap); if (hlen < 0) return hlen; t->encap.type = ipencap->type; t->encap.sport = ipencap->sport; t->encap.dport = ipencap->dport; t->encap.flags = ipencap->flags; t->encap_hlen = hlen; t->hlen = t->encap_hlen + t->tun_hlen; return 0; } EXPORT_SYMBOL_GPL(ip6_tnl_encap_setup); static int ip6_tnl_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct ip6_tnl *t = netdev_priv(ctx->dev); struct flowi6 fl6 = { .daddr = t->parms.raddr, }; struct dst_entry *dst; int err; dst = ip6_route_output(dev_net(ctx->dev), NULL, &fl6); if (!dst->error) { path->type = DEV_PATH_TUN; path->tun.src_v6 = t->parms.laddr; path->tun.dst_v6 = t->parms.raddr; path->tun.l3_proto = IPPROTO_IPV6; path->dev = ctx->dev; ctx->dev = dst->dev; } err = dst->error; dst_release(dst); return err; } static const struct net_device_ops ip6_tnl_netdev_ops = { .ndo_init = ip6_tnl_dev_init, .ndo_uninit = ip6_tnl_dev_uninit, .ndo_start_xmit = ip6_tnl_start_xmit, .ndo_siocdevprivate = ip6_tnl_siocdevprivate, .ndo_change_mtu = ip6_tnl_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, .ndo_fill_forward_path = ip6_tnl_fill_forward_path, }; #define IPXIPX_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_GSO_SOFTWARE | \ NETIF_F_HW_CSUM) /** * ip6_tnl_dev_setup - setup virtual tunnel device * @dev: virtual device associated with tunnel * * Description: * Initialize function pointers and device parameters **/ static void ip6_tnl_dev_setup(struct net_device *dev) { dev->netdev_ops = &ip6_tnl_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); dev->lltx = true; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); dev->features |= IPXIPX_FEATURES; dev->hw_features |= IPXIPX_FEATURES; /* This perm addr will be used as interface identifier by IPv6 */ dev->addr_assign_type = NET_ADDR_RANDOM; eth_random_addr(dev->perm_addr); } /** * ip6_tnl_dev_init_gen - general initializer for all tunnel devices * @dev: virtual device associated with tunnel **/ static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int ret; int t_hlen; t->dev = dev; ret = dst_cache_init(&t->dst_cache, GFP_KERNEL); if (ret) return ret; ret = gro_cells_init(&t->gro_cells, dev); if (ret) goto destroy_dst; t->tun_hlen = 0; t->hlen = t->encap_hlen + t->tun_hlen; t_hlen = t->hlen + sizeof(struct ipv6hdr); dev->type = ARPHRD_TUNNEL6; dev->mtu = ETH_DATA_LEN - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len - t_hlen; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); return 0; destroy_dst: dst_cache_destroy(&t->dst_cache); return ret; } /** * ip6_tnl_dev_init - initializer for all non fallback tunnel devices * @dev: virtual device associated with tunnel **/ static int ip6_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int err = ip6_tnl_dev_init_gen(dev); if (err) return err; ip6_tnl_link_config(t); if (t->parms.collect_md) netif_keep_dst(dev); return 0; } /** * ip6_fb_tnl_dev_init - initializer for fallback tunnel device * @dev: fallback device * * Return: 0 **/ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); t->net = net; t->parms.proto = IPPROTO_IPV6; rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { u8 proto; if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (proto != IPPROTO_IPV6 && proto != IPPROTO_IPIP && proto != 0) return -EINVAL; return 0; } static void ip6_tnl_netlink_parms(struct nlattr *data[], struct __ip6_tnl_parm *parms) { memset(parms, 0, sizeof(*parms)); if (!data) return; if (data[IFLA_IPTUN_LINK]) parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); if (data[IFLA_IPTUN_LOCAL]) parms->laddr = nla_get_in6_addr(data[IFLA_IPTUN_LOCAL]); if (data[IFLA_IPTUN_REMOTE]) parms->raddr = nla_get_in6_addr(data[IFLA_IPTUN_REMOTE]); if (data[IFLA_IPTUN_TTL]) parms->hop_limit = nla_get_u8(data[IFLA_IPTUN_TTL]); if (data[IFLA_IPTUN_ENCAP_LIMIT]) parms->encap_limit = nla_get_u8(data[IFLA_IPTUN_ENCAP_LIMIT]); if (data[IFLA_IPTUN_FLOWINFO]) parms->flowinfo = nla_get_be32(data[IFLA_IPTUN_FLOWINFO]); if (data[IFLA_IPTUN_FLAGS]) parms->flags = nla_get_u32(data[IFLA_IPTUN_FLAGS]); if (data[IFLA_IPTUN_PROTO]) parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (data[IFLA_IPTUN_COLLECT_METADATA]) parms->collect_md = true; if (data[IFLA_IPTUN_FWMARK]) parms->fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } static int ip6_tnl_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct ip_tunnel_encap ipencap; struct ip6_tnl_net *ip6n; struct ip6_tnl *nt, *t; struct net *net; int err; net = params->link_net ? : dev_net(dev); ip6n = net_generic(net, ip6_tnl_net_id); nt = netdev_priv(dev); nt->net = net; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { err = ip6_tnl_encap_setup(nt, &ipencap); if (err < 0) return err; } ip6_tnl_netlink_parms(data, &nt->parms); if (nt->parms.collect_md) { if (rtnl_dereference(ip6n->collect_md_tun)) return -EEXIST; } else { t = ip6_tnl_locate(net, &nt->parms, 0); if (!IS_ERR(t)) return -EEXIST; } err = ip6_tnl_create2(dev); if (!err && tb[IFLA_MTU]) ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); return err; } static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm p; struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct ip_tunnel_encap ipencap; if (dev == ip6n->fb_tnl_dev) { if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { /* iproute2 always sets TUNNEL_ENCAP_FLAG_CSUM6, so * let's ignore this flag. */ ipencap.flags &= ~TUNNEL_ENCAP_FLAG_CSUM6; if (memchr_inv(&ipencap, 0, sizeof(ipencap))) { NL_SET_ERR_MSG(extack, "Only protocol can be changed for fallback tunnel, not encap params"); return -EINVAL; } } ip6_tnl_netlink_parms(data, &p); if (ip6_tnl0_update(t, &p, true) < 0) { NL_SET_ERR_MSG(extack, "Only protocol can be changed for fallback tunnel"); return -EINVAL; } return 0; } if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { int err = ip6_tnl_encap_setup(t, &ipencap); if (err < 0) return err; } ip6_tnl_netlink_parms(data, &p); if (p.collect_md) return -EINVAL; t = ip6_tnl_locate(net, &p, 0); if (!IS_ERR(t)) { if (t->dev != dev) return -EEXIST; } else t = netdev_priv(dev); ip6_tnl_update(t, &p); return 0; } static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head) { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev != ip6n->fb_tnl_dev) unregister_netdevice_queue(dev, head); } static size_t ip6_tnl_get_size(const struct net_device *dev) { return /* IFLA_IPTUN_LINK */ nla_total_size(4) + /* IFLA_IPTUN_LOCAL */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_REMOTE */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_TTL */ nla_total_size(1) + /* IFLA_IPTUN_ENCAP_LIMIT */ nla_total_size(1) + /* IFLA_IPTUN_FLOWINFO */ nla_total_size(4) + /* IFLA_IPTUN_FLAGS */ nla_total_size(4) + /* IFLA_IPTUN_PROTO */ nla_total_size(1) + /* IFLA_IPTUN_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_IPTUN_COLLECT_METADATA */ nla_total_size(0) + /* IFLA_IPTUN_FWMARK */ nla_total_size(4) + 0; } static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); struct __ip6_tnl_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in6_addr(skb, IFLA_IPTUN_LOCAL, &parm->laddr) || nla_put_in6_addr(skb, IFLA_IPTUN_REMOTE, &parm->raddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto) || nla_put_u32(skb, IFLA_IPTUN_FWMARK, parm->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, tunnel->encap.sport) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, tunnel->encap.dport) || nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, tunnel->encap.flags)) goto nla_put_failure; if (parm->collect_md) if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } struct net *ip6_tnl_get_link_net(const struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); return READ_ONCE(tunnel->net); } EXPORT_SYMBOL(ip6_tnl_get_link_net); static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, [IFLA_IPTUN_LOCAL] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_REMOTE] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, [IFLA_IPTUN_ENCAP_LIMIT] = { .type = NLA_U8 }, [IFLA_IPTUN_FLOWINFO] = { .type = NLA_U32 }, [IFLA_IPTUN_FLAGS] = { .type = NLA_U32 }, [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, [IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_IPTUN_FWMARK] = { .type = NLA_U32 }, }; static struct rtnl_link_ops ip6_link_ops __read_mostly = { .kind = "ip6tnl", .maxtype = IFLA_IPTUN_MAX, .policy = ip6_tnl_policy, .priv_size = sizeof(struct ip6_tnl), .setup = ip6_tnl_dev_setup, .validate = ip6_tnl_validate, .newlink = ip6_tnl_newlink, .changelink = ip6_tnl_changelink, .dellink = ip6_tnl_dellink, .get_size = ip6_tnl_get_size, .fill_info = ip6_tnl_fill_info, .get_link_net = ip6_tnl_get_link_net, }; static struct xfrm6_tunnel ip4ip6_handler __read_mostly = { .handler = ip4ip6_rcv, .err_handler = ip4ip6_err, .priority = 1, }; static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .handler = ip6ip6_rcv, .err_handler = ip6ip6_err, .priority = 1, }; static struct xfrm6_tunnel mplsip6_handler __read_mostly = { .handler = mplsip6_rcv, .err_handler = mplsip6_err, .priority = 1, }; static void __net_exit ip6_tnl_exit_rtnl_net(struct net *net, struct list_head *list) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct net_device *dev, *aux; int h; struct ip6_tnl *t; for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &ip6_link_ops) unregister_netdevice_queue(dev, list); for (h = 0; h < IP6_TUNNEL_HASH_SIZE; h++) { t = rtnl_net_dereference(net, ip6n->tnls_r_l[h]); while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, list); t = rtnl_net_dereference(net, t->next); } } t = rtnl_net_dereference(net, ip6n->tnls_wc[0]); while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, list); t = rtnl_net_dereference(net, t->next); } } static int __net_init ip6_tnl_init_net(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct ip6_tnl *t = NULL; int err; ip6n->tnls[0] = ip6n->tnls_wc; ip6n->tnls[1] = ip6n->tnls_r_l; if (!net_has_fallback_tunnels(net)) return 0; err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0", NET_NAME_UNKNOWN, ip6_tnl_dev_setup); if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ ip6n->fb_tnl_dev->netns_immutable = true; err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) goto err_register; err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; t = netdev_priv(ip6n->fb_tnl_dev); strcpy(t->parms.name, ip6n->fb_tnl_dev->name); return 0; err_register: free_netdev(ip6n->fb_tnl_dev); err_alloc_dev: return err; } static struct pernet_operations ip6_tnl_net_ops = { .init = ip6_tnl_init_net, .exit_rtnl = ip6_tnl_exit_rtnl_net, .id = &ip6_tnl_net_id, .size = sizeof(struct ip6_tnl_net), }; /** * ip6_tunnel_init - register protocol and reserve needed resources * * Return: 0 on success **/ static int __init ip6_tunnel_init(void) { int err; if (!ipv6_mod_enabled()) return -EOPNOTSUPP; err = register_pernet_device(&ip6_tnl_net_ops); if (err < 0) goto out_pernet; err = xfrm6_tunnel_register(&ip4ip6_handler, AF_INET); if (err < 0) { pr_err("%s: can't register ip4ip6\n", __func__); goto out_ip4ip6; } err = xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6); if (err < 0) { pr_err("%s: can't register ip6ip6\n", __func__); goto out_ip6ip6; } if (ip6_tnl_mpls_supported()) { err = xfrm6_tunnel_register(&mplsip6_handler, AF_MPLS); if (err < 0) { pr_err("%s: can't register mplsip6\n", __func__); goto out_mplsip6; } } err = rtnl_link_register(&ip6_link_ops); if (err < 0) goto rtnl_link_failed; return 0; rtnl_link_failed: if (ip6_tnl_mpls_supported()) xfrm6_tunnel_deregister(&mplsip6_handler, AF_MPLS); out_mplsip6: xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6); out_ip6ip6: xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET); out_ip4ip6: unregister_pernet_device(&ip6_tnl_net_ops); out_pernet: return err; } /** * ip6_tunnel_cleanup - free resources and unregister protocol **/ static void __exit ip6_tunnel_cleanup(void) { rtnl_link_unregister(&ip6_link_ops); if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET)) pr_info("%s: can't deregister ip4ip6\n", __func__); if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6)) pr_info("%s: can't deregister ip6ip6\n", __func__); if (ip6_tnl_mpls_supported() && xfrm6_tunnel_deregister(&mplsip6_handler, AF_MPLS)) pr_info("%s: can't deregister mplsip6\n", __func__); unregister_pernet_device(&ip6_tnl_net_ops); } module_init(ip6_tunnel_init); module_exit(ip6_tunnel_cleanup); |
| 132 48 109 102 70 70 70 70 111 111 132 4 132 70 111 111 109 109 46 46 46 109 109 109 109 109 109 87 105 106 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/page_io.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Swap reorganised 29.12.95, * Asynchronous swapping added 30.12.95. Stephen Tweedie * Removed race in async swapping. 14.4.1996. Bruno Haible * Add swap of shared pages through the page cache. 20.2.1998. Stephen Tweedie * Always use brw_page, life becomes simpler. 12 May 1998 Eric Biederman */ #include <linux/mm.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/bio.h> #include <linux/swapops.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/psi.h> #include <linux/uio.h> #include <linux/sched/task.h> #include <linux/delayacct.h> #include <linux/zswap.h> #include "swap.h" static void __end_swap_bio_write(struct bio *bio) { struct folio *folio = bio_first_folio_all(bio); if (bio->bi_status) { /* * We failed to write the page out to swap-space. * Re-dirty the page in order to avoid it being reclaimed. * Also print a dire warning that things will go BAD (tm) * very quickly. * * Also clear PG_reclaim to avoid folio_rotate_reclaimable() */ folio_mark_dirty(folio); pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n", MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)), (unsigned long long)bio->bi_iter.bi_sector); folio_clear_reclaim(folio); } folio_end_writeback(folio); } static void end_swap_bio_write(struct bio *bio) { __end_swap_bio_write(bio); bio_put(bio); } static void __end_swap_bio_read(struct bio *bio) { struct folio *folio = bio_first_folio_all(bio); if (bio->bi_status) { pr_alert_ratelimited("Read-error on swap-device (%u:%u:%llu)\n", MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)), (unsigned long long)bio->bi_iter.bi_sector); } else { folio_mark_uptodate(folio); } folio_unlock(folio); } static void end_swap_bio_read(struct bio *bio) { __end_swap_bio_read(bio); bio_put(bio); } int generic_swapfile_activate(struct swap_info_struct *sis, struct file *swap_file, sector_t *span) { struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; unsigned blocks_per_page; unsigned long page_no; unsigned blkbits; sector_t probe_block; sector_t last_block; sector_t lowest_block = -1; sector_t highest_block = 0; int nr_extents = 0; int ret; blkbits = inode->i_blkbits; blocks_per_page = PAGE_SIZE >> blkbits; /* * Map all the blocks into the extent tree. This code doesn't try * to be very smart. */ probe_block = 0; page_no = 0; last_block = i_size_read(inode) >> blkbits; while ((probe_block + blocks_per_page) <= last_block && page_no < sis->max) { unsigned block_in_page; sector_t first_block; cond_resched(); first_block = probe_block; ret = bmap(inode, &first_block); if (ret || !first_block) goto bad_bmap; /* * It must be PAGE_SIZE aligned on-disk */ if (first_block & (blocks_per_page - 1)) { probe_block++; goto reprobe; } for (block_in_page = 1; block_in_page < blocks_per_page; block_in_page++) { sector_t block; block = probe_block + block_in_page; ret = bmap(inode, &block); if (ret || !block) goto bad_bmap; if (block != first_block + block_in_page) { /* Discontiguity */ probe_block++; goto reprobe; } } first_block >>= (PAGE_SHIFT - blkbits); if (page_no) { /* exclude the header page */ if (first_block < lowest_block) lowest_block = first_block; if (first_block > highest_block) highest_block = first_block; } /* * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks */ ret = add_swap_extent(sis, page_no, 1, first_block); if (ret < 0) goto out; nr_extents += ret; page_no++; probe_block += blocks_per_page; reprobe: continue; } ret = nr_extents; *span = 1 + highest_block - lowest_block; if (page_no == 0) page_no = 1; /* force Empty message */ sis->max = page_no; sis->pages = page_no - 1; out: return ret; bad_bmap: pr_err("swapon: swapfile has holes\n"); ret = -EINVAL; goto out; } static bool is_folio_zero_filled(struct folio *folio) { unsigned int pos, last_pos; unsigned long *data; unsigned int i; last_pos = PAGE_SIZE / sizeof(*data) - 1; for (i = 0; i < folio_nr_pages(folio); i++) { data = kmap_local_folio(folio, i * PAGE_SIZE); /* * Check last word first, incase the page is zero-filled at * the start and has non-zero data at the end, which is common * in real-world workloads. */ if (data[last_pos]) { kunmap_local(data); return false; } for (pos = 0; pos < last_pos; pos++) { if (data[pos]) { kunmap_local(data); return false; } } kunmap_local(data); } return true; } static void swap_zeromap_folio_set(struct folio *folio) { struct obj_cgroup *objcg = get_obj_cgroup_from_folio(folio); struct swap_info_struct *sis = __swap_entry_to_info(folio->swap); int nr_pages = folio_nr_pages(folio); swp_entry_t entry; unsigned int i; for (i = 0; i < folio_nr_pages(folio); i++) { entry = page_swap_entry(folio_page(folio, i)); set_bit(swp_offset(entry), sis->zeromap); } count_vm_events(SWPOUT_ZERO, nr_pages); if (objcg) { count_objcg_events(objcg, SWPOUT_ZERO, nr_pages); obj_cgroup_put(objcg); } } static void swap_zeromap_folio_clear(struct folio *folio) { struct swap_info_struct *sis = __swap_entry_to_info(folio->swap); swp_entry_t entry; unsigned int i; for (i = 0; i < folio_nr_pages(folio); i++) { entry = page_swap_entry(folio_page(folio, i)); clear_bit(swp_offset(entry), sis->zeromap); } } /* * We may have stale swap cache pages in memory: notice * them here and get rid of the unnecessary final write. */ int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug) { int ret = 0; if (folio_free_swap(folio)) goto out_unlock; /* * Arch code may have to preserve more data than just the page * contents, e.g. memory tags. */ ret = arch_prepare_to_swap(folio); if (ret) { folio_mark_dirty(folio); goto out_unlock; } /* * Use a bitmap (zeromap) to avoid doing IO for zero-filled pages. * The bits in zeromap are protected by the locked swapcache folio * and atomic updates are used to protect against read-modify-write * corruption due to other zero swap entries seeing concurrent updates. */ if (is_folio_zero_filled(folio)) { swap_zeromap_folio_set(folio); goto out_unlock; } /* * Clear bits this folio occupies in the zeromap to prevent zero data * being read in from any previous zero writes that occupied the same * swap entries. */ swap_zeromap_folio_clear(folio); if (zswap_store(folio)) { count_mthp_stat(folio_order(folio), MTHP_STAT_ZSWPOUT); goto out_unlock; } rcu_read_lock(); if (!mem_cgroup_zswap_writeback_enabled(folio_memcg(folio))) { rcu_read_unlock(); folio_mark_dirty(folio); return AOP_WRITEPAGE_ACTIVATE; } rcu_read_unlock(); __swap_writepage(folio, swap_plug); return 0; out_unlock: folio_unlock(folio); return ret; } static inline void count_swpout_vm_event(struct folio *folio) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (unlikely(folio_test_pmd_mappable(folio))) { count_memcg_folio_events(folio, THP_SWPOUT, 1); count_vm_event(THP_SWPOUT); } #endif count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT); count_memcg_folio_events(folio, PSWPOUT, folio_nr_pages(folio)); count_vm_events(PSWPOUT, folio_nr_pages(folio)); } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) static void bio_associate_blkg_from_page(struct bio *bio, struct folio *folio) { struct cgroup_subsys_state *css; struct mem_cgroup *memcg; if (!folio_memcg_charged(folio)) return; rcu_read_lock(); memcg = folio_memcg(folio); css = cgroup_e_css(memcg->css.cgroup, &io_cgrp_subsys); bio_associate_blkg_from_css(bio, css); rcu_read_unlock(); } #else #define bio_associate_blkg_from_page(bio, folio) do { } while (0) #endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */ struct swap_iocb { struct kiocb iocb; struct bio_vec bvec[SWAP_CLUSTER_MAX]; int pages; int len; }; static mempool_t *sio_pool; int sio_pool_init(void) { if (!sio_pool) { mempool_t *pool = mempool_create_kmalloc_pool( SWAP_CLUSTER_MAX, sizeof(struct swap_iocb)); if (cmpxchg(&sio_pool, NULL, pool)) mempool_destroy(pool); } if (!sio_pool) return -ENOMEM; return 0; } static void sio_write_complete(struct kiocb *iocb, long ret) { struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb); struct page *page = sio->bvec[0].bv_page; int p; if (ret != sio->len) { /* * In the case of swap-over-nfs, this can be a * temporary failure if the system has limited * memory for allocating transmit buffers. * Mark the page dirty and avoid * folio_rotate_reclaimable but rate-limit the * messages. */ pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n", ret, swap_dev_pos(page_swap_entry(page))); for (p = 0; p < sio->pages; p++) { page = sio->bvec[p].bv_page; set_page_dirty(page); ClearPageReclaim(page); } } for (p = 0; p < sio->pages; p++) end_page_writeback(sio->bvec[p].bv_page); mempool_free(sio, sio_pool); } static void swap_writepage_fs(struct folio *folio, struct swap_iocb **swap_plug) { struct swap_iocb *sio = swap_plug ? *swap_plug : NULL; struct swap_info_struct *sis = __swap_entry_to_info(folio->swap); struct file *swap_file = sis->swap_file; loff_t pos = swap_dev_pos(folio->swap); count_swpout_vm_event(folio); folio_start_writeback(folio); folio_unlock(folio); if (sio) { if (sio->iocb.ki_filp != swap_file || sio->iocb.ki_pos + sio->len != pos) { swap_write_unplug(sio); sio = NULL; } } if (!sio) { sio = mempool_alloc(sio_pool, GFP_NOIO); init_sync_kiocb(&sio->iocb, swap_file); sio->iocb.ki_complete = sio_write_complete; sio->iocb.ki_pos = pos; sio->pages = 0; sio->len = 0; } bvec_set_folio(&sio->bvec[sio->pages], folio, folio_size(folio), 0); sio->len += folio_size(folio); sio->pages += 1; if (sio->pages == ARRAY_SIZE(sio->bvec) || !swap_plug) { swap_write_unplug(sio); sio = NULL; } if (swap_plug) *swap_plug = sio; } static void swap_writepage_bdev_sync(struct folio *folio, struct swap_info_struct *sis) { struct bio_vec bv; struct bio bio; bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_WRITE | REQ_SWAP); bio.bi_iter.bi_sector = swap_folio_sector(folio); bio_add_folio_nofail(&bio, folio, folio_size(folio), 0); bio_associate_blkg_from_page(&bio, folio); count_swpout_vm_event(folio); folio_start_writeback(folio); folio_unlock(folio); submit_bio_wait(&bio); __end_swap_bio_write(&bio); } static void swap_writepage_bdev_async(struct folio *folio, struct swap_info_struct *sis) { struct bio *bio; bio = bio_alloc(sis->bdev, 1, REQ_OP_WRITE | REQ_SWAP, GFP_NOIO); bio->bi_iter.bi_sector = swap_folio_sector(folio); bio->bi_end_io = end_swap_bio_write; bio_add_folio_nofail(bio, folio, folio_size(folio), 0); bio_associate_blkg_from_page(bio, folio); count_swpout_vm_event(folio); folio_start_writeback(folio); folio_unlock(folio); submit_bio(bio); } void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug) { struct swap_info_struct *sis = __swap_entry_to_info(folio->swap); VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio); /* * ->flags can be updated non-atomically, * but that will never affect SWP_FS_OPS, so the data_race * is safe. */ if (data_race(sis->flags & SWP_FS_OPS)) swap_writepage_fs(folio, swap_plug); /* * ->flags can be updated non-atomically, * but that will never affect SWP_SYNCHRONOUS_IO, so the data_race * is safe. */ else if (data_race(sis->flags & SWP_SYNCHRONOUS_IO)) swap_writepage_bdev_sync(folio, sis); else swap_writepage_bdev_async(folio, sis); } void swap_write_unplug(struct swap_iocb *sio) { struct iov_iter from; struct address_space *mapping = sio->iocb.ki_filp->f_mapping; int ret; iov_iter_bvec(&from, ITER_SOURCE, sio->bvec, sio->pages, sio->len); ret = mapping->a_ops->swap_rw(&sio->iocb, &from); if (ret != -EIOCBQUEUED) sio_write_complete(&sio->iocb, ret); } static void sio_read_complete(struct kiocb *iocb, long ret) { struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb); int p; if (ret == sio->len) { for (p = 0; p < sio->pages; p++) { struct folio *folio = page_folio(sio->bvec[p].bv_page); count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN); count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio)); folio_mark_uptodate(folio); folio_unlock(folio); } count_vm_events(PSWPIN, sio->len >> PAGE_SHIFT); } else { for (p = 0; p < sio->pages; p++) { struct folio *folio = page_folio(sio->bvec[p].bv_page); folio_unlock(folio); } pr_alert_ratelimited("Read-error on swap-device\n"); } mempool_free(sio, sio_pool); } static bool swap_read_folio_zeromap(struct folio *folio) { int nr_pages = folio_nr_pages(folio); struct obj_cgroup *objcg; bool is_zeromap; /* * Swapping in a large folio that is partially in the zeromap is not * currently handled. Return true without marking the folio uptodate so * that an IO error is emitted (e.g. do_swap_page() will sigbus). */ if (WARN_ON_ONCE(swap_zeromap_batch(folio->swap, nr_pages, &is_zeromap) != nr_pages)) return true; if (!is_zeromap) return false; objcg = get_obj_cgroup_from_folio(folio); count_vm_events(SWPIN_ZERO, nr_pages); if (objcg) { count_objcg_events(objcg, SWPIN_ZERO, nr_pages); obj_cgroup_put(objcg); } folio_zero_range(folio, 0, folio_size(folio)); folio_mark_uptodate(folio); return true; } static void swap_read_folio_fs(struct folio *folio, struct swap_iocb **plug) { struct swap_info_struct *sis = __swap_entry_to_info(folio->swap); struct swap_iocb *sio = NULL; loff_t pos = swap_dev_pos(folio->swap); if (plug) sio = *plug; if (sio) { if (sio->iocb.ki_filp != sis->swap_file || sio->iocb.ki_pos + sio->len != pos) { swap_read_unplug(sio); sio = NULL; } } if (!sio) { sio = mempool_alloc(sio_pool, GFP_KERNEL); init_sync_kiocb(&sio->iocb, sis->swap_file); sio->iocb.ki_pos = pos; sio->iocb.ki_complete = sio_read_complete; sio->pages = 0; sio->len = 0; } bvec_set_folio(&sio->bvec[sio->pages], folio, folio_size(folio), 0); sio->len += folio_size(folio); sio->pages += 1; if (sio->pages == ARRAY_SIZE(sio->bvec) || !plug) { swap_read_unplug(sio); sio = NULL; } if (plug) *plug = sio; } static void swap_read_folio_bdev_sync(struct folio *folio, struct swap_info_struct *sis) { struct bio_vec bv; struct bio bio; bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_READ); bio.bi_iter.bi_sector = swap_folio_sector(folio); bio_add_folio_nofail(&bio, folio, folio_size(folio), 0); /* * Keep this task valid during swap readpage because the oom killer may * attempt to access it in the page fault retry time check. */ get_task_struct(current); count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN); count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio)); count_vm_events(PSWPIN, folio_nr_pages(folio)); submit_bio_wait(&bio); __end_swap_bio_read(&bio); put_task_struct(current); } static void swap_read_folio_bdev_async(struct folio *folio, struct swap_info_struct *sis) { struct bio *bio; bio = bio_alloc(sis->bdev, 1, REQ_OP_READ, GFP_KERNEL); bio->bi_iter.bi_sector = swap_folio_sector(folio); bio->bi_end_io = end_swap_bio_read; bio_add_folio_nofail(bio, folio, folio_size(folio), 0); count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN); count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio)); count_vm_events(PSWPIN, folio_nr_pages(folio)); submit_bio(bio); } void swap_read_folio(struct folio *folio, struct swap_iocb **plug) { struct swap_info_struct *sis = __swap_entry_to_info(folio->swap); bool synchronous = sis->flags & SWP_SYNCHRONOUS_IO; bool workingset = folio_test_workingset(folio); unsigned long pflags; bool in_thrashing; VM_BUG_ON_FOLIO(!folio_test_swapcache(folio) && !synchronous, folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio); /* * Count submission time as memory stall and delay. When the device * is congested, or the submitting cgroup IO-throttled, submission * can be a significant part of overall IO time. */ if (workingset) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); } delayacct_swapin_start(); if (swap_read_folio_zeromap(folio)) { folio_unlock(folio); goto finish; } if (zswap_load(folio) != -ENOENT) goto finish; /* We have to read from slower devices. Increase zswap protection. */ zswap_folio_swapin(folio); if (data_race(sis->flags & SWP_FS_OPS)) { swap_read_folio_fs(folio, plug); } else if (synchronous) { swap_read_folio_bdev_sync(folio, sis); } else { swap_read_folio_bdev_async(folio, sis); } finish: if (workingset) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } delayacct_swapin_end(); } void __swap_read_unplug(struct swap_iocb *sio) { struct iov_iter from; struct address_space *mapping = sio->iocb.ki_filp->f_mapping; int ret; iov_iter_bvec(&from, ITER_DEST, sio->bvec, sio->pages, sio->len); ret = mapping->a_ops->swap_rw(&sio->iocb, &from); if (ret != -EIOCBQUEUED) sio_read_complete(&sio->iocb, ret); } |
| 3 3 3 3 3 3 3 2 3 3 3 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 | // SPDX-License-Identifier: GPL-2.0 /* * This file implement the Wireless Extensions proc API. * * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. */ /* * The /proc/net/wireless file is a human readable user-space interface * exporting various wireless specific statistics from the wireless devices. * This is the most popular part of the Wireless Extensions ;-) * * This interface is a pure clone of /proc/net/dev (in net/core/dev.c). * The content of the file is basically the content of "struct iw_statistics". */ #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/wireless.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <net/iw_handler.h> #include <net/wext.h> static void wireless_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { /* Get stats from the driver */ struct iw_statistics *stats = get_wireless_stats(dev); static struct iw_statistics nullstats = {}; /* show device if it's wireless regardless of current stats */ if (!stats) { #ifdef CONFIG_WIRELESS_EXT if (dev->wireless_handlers) stats = &nullstats; #endif #ifdef CONFIG_CFG80211 if (dev->ieee80211_ptr) stats = &nullstats; #endif } if (stats) { seq_printf(seq, "%6s: %04x %3d%c %3d%c %3d%c %6d %6d %6d " "%6d %6d %6d\n", dev->name, stats->status, stats->qual.qual, stats->qual.updated & IW_QUAL_QUAL_UPDATED ? '.' : ' ', ((__s32) stats->qual.level) - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), stats->qual.updated & IW_QUAL_LEVEL_UPDATED ? '.' : ' ', ((__s32) stats->qual.noise) - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), stats->qual.updated & IW_QUAL_NOISE_UPDATED ? '.' : ' ', stats->discard.nwid, stats->discard.code, stats->discard.fragment, stats->discard.retries, stats->discard.misc, stats->miss.beacon); if (stats != &nullstats) stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; } } /* ---------------------------------------------------------------- */ /* * Print info for /proc/net/wireless (print all entries) */ static int wireless_dev_seq_show(struct seq_file *seq, void *v) { might_sleep(); if (v == SEQ_START_TOKEN) seq_printf(seq, "Inter-| sta-| Quality | Discarded " "packets | Missed | WE\n" " face | tus | link level noise | nwid " "crypt frag retry misc | beacon | %d\n", WIRELESS_EXT); else wireless_seq_printf_stats(seq, v); return 0; } static void *wireless_dev_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); loff_t off; struct net_device *dev; rtnl_lock(); if (!*pos) return SEQ_START_TOKEN; off = 1; for_each_netdev(net, dev) if (off++ == *pos) return dev; return NULL; } static void *wireless_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); ++*pos; return v == SEQ_START_TOKEN ? first_net_device(net) : next_net_device(v); } static void wireless_dev_seq_stop(struct seq_file *seq, void *v) { rtnl_unlock(); } static const struct seq_operations wireless_seq_ops = { .start = wireless_dev_seq_start, .next = wireless_dev_seq_next, .stop = wireless_dev_seq_stop, .show = wireless_dev_seq_show, }; int __net_init wext_proc_init(struct net *net) { /* Create /proc/net/wireless entry */ if (!proc_create_net("wireless", 0444, net->proc_net, &wireless_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } void __net_exit wext_proc_exit(struct net *net) { remove_proc_entry("wireless", net->proc_net); } |
| 1198 22 37933 28642 152 33398 36 47377 54 20216 1 1 45389 3295 3292 85 5581 5580 218 4012 672 75 5 23 93 738 422 92 31 3238 696 2621 70 40 1 13053 8238 3149 5 1057 7581 5 31 21659 16707 12 8 5277 2799 168 2 1 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_H #define _LINUX_LIST_H #include <linux/container_of.h> #include <linux/types.h> #include <linux/stddef.h> #include <linux/poison.h> #include <linux/const.h> #include <asm/barrier.h> /* * Circular doubly linked list implementation. * * Some of the internal functions ("__xxx") are useful when * manipulating whole lists rather than single entries, as * sometimes we already know the next/prev entries and we can * generate better code by using them directly rather than * using the generic single-entry routines. */ /** * LIST_HEAD_INIT - initialize a &struct list_head's links to point to itself * @name: name of the list_head */ #define LIST_HEAD_INIT(name) { &(name), &(name) } /** * LIST_HEAD - definition of a &struct list_head with initialization values * @name: name of the list_head */ #define LIST_HEAD(name) \ struct list_head name = LIST_HEAD_INIT(name) /** * INIT_LIST_HEAD - Initialize a list_head structure * @list: list_head structure to be initialized. * * Initializes the list_head to point to itself. If it is a list header, * the result is an empty list. */ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } #ifdef CONFIG_LIST_HARDENED #ifdef CONFIG_DEBUG_LIST # define __list_valid_slowpath #else # define __list_valid_slowpath __cold __preserve_most #endif /* * Performs the full set of list corruption checks before __list_add(). * On list corruption reports a warning, and returns false. */ bool __list_valid_slowpath __list_add_valid_or_report(struct list_head *new, struct list_head *prev, struct list_head *next); /* * Performs list corruption checks before __list_add(). Returns false if a * corruption is detected, true otherwise. * * With CONFIG_LIST_HARDENED only, performs minimal list integrity checking * inline to catch non-faulting corruptions, and only if a corruption is * detected calls the reporting function __list_add_valid_or_report(). */ static __always_inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { bool ret = true; if (!IS_ENABLED(CONFIG_DEBUG_LIST)) { /* * With the hardening version, elide checking if next and prev * are NULL, since the immediate dereference of them below would * result in a fault if NULL. * * With the reduced set of checks, we can afford to inline the * checks, which also gives the compiler a chance to elide some * of them completely if they can be proven at compile-time. If * one of the pre-conditions does not hold, the slow-path will * show a report which pre-condition failed. */ if (likely(next->prev == prev && prev->next == next && new != prev && new != next)) return true; ret = false; } ret &= __list_add_valid_or_report(new, prev, next); return ret; } /* * Performs the full set of list corruption checks before __list_del_entry(). * On list corruption reports a warning, and returns false. */ bool __list_valid_slowpath __list_del_entry_valid_or_report(struct list_head *entry); /* * Performs list corruption checks before __list_del_entry(). Returns false if a * corruption is detected, true otherwise. * * With CONFIG_LIST_HARDENED only, performs minimal list integrity checking * inline to catch non-faulting corruptions, and only if a corruption is * detected calls the reporting function __list_del_entry_valid_or_report(). */ static __always_inline bool __list_del_entry_valid(struct list_head *entry) { bool ret = true; if (!IS_ENABLED(CONFIG_DEBUG_LIST)) { struct list_head *prev = entry->prev; struct list_head *next = entry->next; /* * With the hardening version, elide checking if next and prev * are NULL, LIST_POISON1 or LIST_POISON2, since the immediate * dereference of them below would result in a fault. */ if (likely(prev->next == entry && next->prev == entry)) return true; ret = false; } ret &= __list_del_entry_valid_or_report(entry); return ret; } #else static inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { return true; } static inline bool __list_del_entry_valid(struct list_head *entry) { return true; } #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; next->prev = new; new->next = next; new->prev = prev; WRITE_ONCE(prev->next, new); } /** * list_add - add a new entry * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void list_add(struct list_head *new, struct list_head *head) { __list_add(new, head, head->next); } /** * list_add_tail - add a new entry * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. */ static inline void list_add_tail(struct list_head *new, struct list_head *head) { __list_add(new, head->prev, head); } /* * Delete a list entry by making the prev/next entries * point to each other. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_del(struct list_head * prev, struct list_head * next) { next->prev = prev; WRITE_ONCE(prev->next, next); } /* * Delete a list entry and clear the 'prev' pointer. * * This is a special-purpose list clearing method used in the networking code * for lists allocated as per-cpu, where we don't want to incur the extra * WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this * needs to check the node 'prev' pointer instead of calling list_empty(). */ static inline void __list_del_clearprev(struct list_head *entry) { __list_del(entry->prev, entry->next); entry->prev = NULL; } static inline void __list_del_entry(struct list_head *entry) { if (!__list_del_entry_valid(entry)) return; __list_del(entry->prev, entry->next); } /** * list_del - deletes entry from list. * @entry: the element to delete from the list. * Note: list_empty() on entry does not return true after this, the entry is * in an undefined state. */ static inline void list_del(struct list_head *entry) { __list_del_entry(entry); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; } /** * list_replace - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace(struct list_head *old, struct list_head *new) { new->next = old->next; new->next->prev = new; new->prev = old->prev; new->prev->next = new; } /** * list_replace_init - replace old entry by new one and initialize the old one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace_init(struct list_head *old, struct list_head *new) { list_replace(old, new); INIT_LIST_HEAD(old); } /** * list_swap - replace entry1 with entry2 and re-add entry1 at entry2's position * @entry1: the location to place entry2 * @entry2: the location to place entry1 */ static inline void list_swap(struct list_head *entry1, struct list_head *entry2) { struct list_head *pos = entry2->prev; list_del(entry2); list_replace(entry1, entry2); if (pos == entry1) pos = entry2; list_add(entry1, pos); } /** * list_del_init - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. */ static inline void list_del_init(struct list_head *entry) { __list_del_entry(entry); INIT_LIST_HEAD(entry); } /** * list_move - delete from one list and add as another's head * @list: the entry to move * @head: the head that will precede our entry */ static inline void list_move(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add(list, head); } /** * list_move_tail - delete from one list and add as another's tail * @list: the entry to move * @head: the head that will follow our entry */ static inline void list_move_tail(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add_tail(list, head); } /** * list_bulk_move_tail - move a subsection of a list to its tail * @head: the head that will follow our entry * @first: first entry to move * @last: last entry to move, can be the same as first * * Move all entries between @first and including @last before @head. * All three entries must belong to the same linked list. */ static inline void list_bulk_move_tail(struct list_head *head, struct list_head *first, struct list_head *last) { first->prev->next = last->next; last->next->prev = first->prev; head->prev->next = first; first->prev = head->prev; last->next = head; head->prev = last; } /** * list_is_first -- tests whether @list is the first entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } /** * list_is_head - tests whether @list is the list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_head(const struct list_head *list, const struct list_head *head) { return list == head; } /** * list_empty - tests whether a list is empty * @head: the list to test. */ static inline int list_empty(const struct list_head *head) { return READ_ONCE(head->next) == head; } /** * list_del_init_careful - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. * * This is the same as list_del_init(), except designed to be used * together with list_empty_careful() in a way to guarantee ordering * of other memory operations. * * Any memory operations done before a list_del_init_careful() are * guaranteed to be visible after a list_empty_careful() test. */ static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); WRITE_ONCE(entry->prev, entry); smp_store_release(&entry->next, entry); } /** * list_empty_careful - tests whether a list is empty and not being modified * @head: the list to test * * Description: * tests whether a list is empty _and_ checks that no other CPU might be * in the process of modifying either member (next or prev) * * NOTE: using list_empty_careful() without synchronization * can only be safe if the only activity that can happen * to the list entry is list_del_init(). Eg. it cannot be used * if another CPU could re-list_add() it. */ static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); return list_is_head(next, head) && (next == READ_ONCE(head->prev)); } /** * list_rotate_left - rotate the list to the left * @head: the head of the list */ static inline void list_rotate_left(struct list_head *head) { struct list_head *first; if (!list_empty(head)) { first = head->next; list_move_tail(first, head); } } /** * list_rotate_to_front() - Rotate list to specific item. * @list: The desired new front of the list. * @head: The head of the list. * * Rotates list so that @list becomes the new front of the list. */ static inline void list_rotate_to_front(struct list_head *list, struct list_head *head) { /* * Deletes the list head from the list denoted by @head and * places it as the tail of @list, this effectively rotates the * list so that @list is at the front. */ list_move_tail(head, list); } /** * list_is_singular - tests whether a list has just one entry. * @head: the list to test. */ static inline int list_is_singular(const struct list_head *head) { return !list_empty(head) && (head->next == head->prev); } static inline void __list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { struct list_head *new_first = entry->next; list->next = head->next; list->next->prev = list; list->prev = entry; entry->next = list; head->next = new_first; new_first->prev = head; } /** * list_cut_position - cut a list into two * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * and if so we won't cut the list * * This helper moves the initial part of @head, up to and * including @entry, from @head to @list. You should * pass on @entry an element you know is on @head. @list * should be an empty list or a list you do not care about * losing its data. * */ static inline void list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { if (list_empty(head)) return; if (list_is_singular(head) && !list_is_head(entry, head) && (entry != head->next)) return; if (list_is_head(entry, head)) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); } /** * list_cut_before - cut a list into two, before given entry * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * * This helper moves the initial part of @head, up to but * excluding @entry, from @head to @list. You should pass * in @entry an element you know is on @head. @list should * be an empty list or a list you do not care about losing * its data. * If @entry == @head, all entries on @head are moved to * @list. */ static inline void list_cut_before(struct list_head *list, struct list_head *head, struct list_head *entry) { if (head->next == entry) { INIT_LIST_HEAD(list); return; } list->next = head->next; list->next->prev = list; list->prev = entry->prev; list->prev->next = list; head->next = entry; entry->prev = head; } static inline void __list_splice(const struct list_head *list, struct list_head *prev, struct list_head *next) { struct list_head *first = list->next; struct list_head *last = list->prev; first->prev = prev; prev->next = first; last->next = next; next->prev = last; } /** * list_splice - join two lists, this is designed for stacks * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice(const struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head, head->next); } /** * list_splice_tail - join two lists, each list being a queue * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice_tail(struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head->prev, head); } /** * list_splice_init - join two lists and reinitialise the emptied list. * @list: the new list to add. * @head: the place to add it in the first list. * * The list at @list is reinitialised */ static inline void list_splice_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head, head->next); INIT_LIST_HEAD(list); } } /** * list_splice_tail_init - join two lists and reinitialise the emptied list * @list: the new list to add. * @head: the place to add it in the first list. * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void list_splice_tail_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head->prev, head); INIT_LIST_HEAD(list); } } /** * list_entry - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. */ #define list_entry(ptr, type, member) \ container_of(ptr, type, member) /** * list_first_entry - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_first_entry(ptr, type, member) \ list_entry((ptr)->next, type, member) /** * list_last_entry - get the last element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_last_entry(ptr, type, member) \ list_entry((ptr)->prev, type, member) /** * list_first_entry_or_null - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. */ #define list_first_entry_or_null(ptr, type, member) ({ \ struct list_head *head__ = (ptr); \ struct list_head *pos__ = READ_ONCE(head__->next); \ pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) /** * list_last_entry_or_null - get the last element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. */ #define list_last_entry_or_null(ptr, type, member) ({ \ struct list_head *head__ = (ptr); \ struct list_head *pos__ = READ_ONCE(head__->prev); \ pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) /** * list_next_entry - get the next element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_next_entry(pos, member) \ list_entry((pos)->member.next, typeof(*(pos)), member) /** * list_next_entry_circular - get the next element in list * @pos: the type * to cursor. * @head: the list head to take the element from. * @member: the name of the list_head within the struct. * * Wraparound if pos is the last element (return the first element). * Note, that list is expected to be not empty. */ #define list_next_entry_circular(pos, head, member) \ (list_is_last(&(pos)->member, head) ? \ list_first_entry(head, typeof(*(pos)), member) : list_next_entry(pos, member)) /** * list_prev_entry - get the prev element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_prev_entry(pos, member) \ list_entry((pos)->member.prev, typeof(*(pos)), member) /** * list_prev_entry_circular - get the prev element in list * @pos: the type * to cursor. * @head: the list head to take the element from. * @member: the name of the list_head within the struct. * * Wraparound if pos is the first element (return the last element). * Note, that list is expected to be not empty. */ #define list_prev_entry_circular(pos, head, member) \ (list_is_first(&(pos)->member, head) ? \ list_last_entry(head, typeof(*(pos)), member) : list_prev_entry(pos, member)) /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each(pos, head) \ for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_continue - continue iteration over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. * * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ for (pos = pos->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ for (pos = (head)->prev; !list_is_head(pos, (head)); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ for (pos = (head)->next, n = pos->next; \ !list_is_head(pos, (head)); \ pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ !list_is_head(pos, (head)); \ pos = n, n = pos->prev) /** * list_count_nodes - count nodes in the list * @head: the head for your list. */ static inline size_t list_count_nodes(struct list_head *head) { struct list_head *pos; size_t count = 0; list_for_each(pos, head) count++; return count; } /** * list_entry_is_head - test if the entry points to the head of the list * @pos: the type * to cursor * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_entry_is_head(pos, head, member) \ list_is_head(&pos->member, (head)) /** * list_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry(pos, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_reverse - iterate backwards over list of given type. * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_reverse(pos, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue() * @pos: the type * to use as a start point * @head: the head of the list * @member: the name of the list_head within the struct. * * Prepares a pos entry for use as a start point in list_for_each_entry_continue(). */ #define list_prepare_entry(pos, head, member) \ ((pos) ? : list_entry(head, typeof(*pos), member)) /** * list_for_each_entry_continue - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position. */ #define list_for_each_entry_continue(pos, head, member) \ for (pos = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_continue_reverse - iterate backwards from the given point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Start to iterate over list of given type backwards, continuing after * the current position. */ #define list_for_each_entry_continue_reverse(pos, head, member) \ for (pos = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_from - iterate over list of given type from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing from current position. */ #define list_for_each_entry_from(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_from_reverse - iterate backwards over list of given type * from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, continuing from current position. */ #define list_for_each_entry_from_reverse(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_safe(pos, n, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_continue - continue list iteration safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing after current point, * safe against removal of list entry. */ #define list_for_each_entry_safe_continue(pos, n, head, member) \ for (pos = list_next_entry(pos, member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_from - iterate over list from current point safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type from current point, safe against * removal of list entry. */ #define list_for_each_entry_safe_from(pos, n, head, member) \ for (n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, safe against removal * of list entry. */ #define list_for_each_entry_safe_reverse(pos, n, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member), \ n = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_prev_entry(n, member)) /** * list_safe_reset_next - reset a stale list_for_each_entry_safe loop * @pos: the loop cursor used in the list_for_each_entry_safe loop * @n: temporary storage used in list_for_each_entry_safe * @member: the name of the list_head within the struct. * * list_safe_reset_next is not safe to use in general if the list may be * modified concurrently (eg. the lock is dropped in the loop body). An * exception to this is if the cursor element (pos) is pinned in the list, * and list_safe_reset_next is called after re-taking the lock and before * completing the current iteration of the loop body. */ #define list_safe_reset_next(pos, n, member) \ n = list_next_entry(pos, member) /* * Double linked lists with a single pointer list head. * Mostly useful for hash tables where the two pointer list head is * too wasteful. * You lose the ability to access the tail in O(1). */ #define HLIST_HEAD_INIT { .first = NULL } #define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } #define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) static inline void INIT_HLIST_NODE(struct hlist_node *h) { h->next = NULL; h->pprev = NULL; } /** * hlist_unhashed - Has node been removed from list and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed * state. For example, hlist_nulls_del_init_rcu() does leave the * node in unhashed state, but hlist_nulls_del() does not. */ static inline int hlist_unhashed(const struct hlist_node *h) { return !h->pprev; } /** * hlist_unhashed_lockless - Version of hlist_unhashed for lockless use * @h: Node to be checked * * This variant of hlist_unhashed() must be used in lockless contexts * to avoid potential load-tearing. The READ_ONCE() is paired with the * various WRITE_ONCE() in hlist helpers that are defined below. */ static inline int hlist_unhashed_lockless(const struct hlist_node *h) { return !READ_ONCE(h->pprev); } /** * hlist_empty - Is the specified hlist_head structure an empty hlist? * @h: Structure to check. */ static inline int hlist_empty(const struct hlist_head *h) { return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) { struct hlist_node *next = n->next; struct hlist_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (next) WRITE_ONCE(next->pprev, pprev); } /** * hlist_del - Delete the specified hlist_node from its list * @n: Node to delete. * * Note that this function leaves the node in hashed state. Use * hlist_del_init() or similar instead to unhash @n. */ static inline void hlist_del(struct hlist_node *n) { __hlist_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } /** * hlist_del_init - Delete the specified hlist_node from its list and initialize * @n: Node to delete. * * Note that this function leaves the node in unhashed state. */ static inline void hlist_del_init(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); INIT_HLIST_NODE(n); } } /** * hlist_add_head - add a new entry at the beginning of the hlist * @n: new entry to be added * @h: hlist head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; WRITE_ONCE(n->next, first); if (first) WRITE_ONCE(first->pprev, &n->next); WRITE_ONCE(h->first, n); WRITE_ONCE(n->pprev, &h->first); } /** * hlist_add_before - add a new entry before the one specified * @n: new entry to be added * @next: hlist node to add it before, which must be non-NULL */ static inline void hlist_add_before(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); WRITE_ONCE(n->next, next); WRITE_ONCE(next->pprev, &n->next); WRITE_ONCE(*(n->pprev), n); } /** * hlist_add_behind - add a new entry after the one specified * @n: new entry to be added * @prev: hlist node to add it after, which must be non-NULL */ static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { WRITE_ONCE(n->next, prev->next); WRITE_ONCE(prev->next, n); WRITE_ONCE(n->pprev, &prev->next); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } /** * hlist_add_fake - create a fake hlist consisting of a single headless node * @n: Node to make a fake list out of * * This makes @n appear to be its own predecessor on a headless hlist. * The point of this is to allow things like hlist_del() to work correctly * in cases where there is no list. */ static inline void hlist_add_fake(struct hlist_node *n) { n->pprev = &n->next; } /** * hlist_fake: Is this node a fake hlist? * @h: Node to check for being a self-referential fake hlist. */ static inline bool hlist_fake(struct hlist_node *h) { return h->pprev == &h->next; } /** * hlist_is_singular_node - is node the only element of the specified hlist? * @n: Node to check for singularity. * @h: Header for potentially singular list. * * Check whether the node is the only node of the head without * accessing head, thus avoiding unnecessary cache misses. */ static inline bool hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h) { return !n->next && n->pprev == &h->first; } /** * hlist_move_list - Move an hlist * @old: hlist_head for old list. * @new: hlist_head for new list. * * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. */ static inline void hlist_move_list(struct hlist_head *old, struct hlist_head *new) { new->first = old->first; if (new->first) new->first->pprev = &new->first; old->first = NULL; } /** * hlist_splice_init() - move all entries from one list to another * @from: hlist_head from which entries will be moved * @last: last entry on the @from list * @to: hlist_head to which entries will be moved * * @to can be empty, @from must contain at least @last. */ static inline void hlist_splice_init(struct hlist_head *from, struct hlist_node *last, struct hlist_head *to) { if (to->first) to->first->pprev = &last->next; last->next = to->first; to->first = from->first; from->first->pprev = &to->first; from->first = NULL; } #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ for (pos = (head)->first; pos ; pos = pos->next) #define hlist_for_each_safe(pos, n, head) \ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ pos = n) #define hlist_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \ }) /** * hlist_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry(pos, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_continue - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue(pos, member) \ for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_from - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from(pos, member) \ for (; pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: a &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_safe(pos, n, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\ pos && ({ n = pos->member.next; 1; }); \ pos = hlist_entry_safe(n, typeof(*pos), member)) /** * hlist_count_nodes - count nodes in the hlist * @head: the head for your hlist. */ static inline size_t hlist_count_nodes(struct hlist_head *head) { struct hlist_node *pos; size_t count = 0; hlist_for_each(pos, head) count++; return count; } #endif |
| 7521 | 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 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM kmem #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KMEM_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(kmem_cache_alloc, TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, s, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __string( name, s->name ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) __field( bool, accounted ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __assign_str(name); __entry->bytes_req = s->object_size; __entry->bytes_alloc = s->size; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; __entry->accounted = IS_ENABLED(CONFIG_MEMCG) ? ((gfp_flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)) : false; ), TP_printk("call_site=%pS ptr=%p name=%s bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __get_str(name), __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, __entry->accounted ? "true" : "false") ); TRACE_EVENT(kmalloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, (IS_ENABLED(CONFIG_MEMCG) && (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false") ); TRACE_EVENT(kfree, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; ), TP_printk("call_site=%pS ptr=%p", (void *)__entry->call_site, __entry->ptr) ); TRACE_EVENT(kmem_cache_free, TP_PROTO(unsigned long call_site, const void *ptr, const struct kmem_cache *s), TP_ARGS(call_site, ptr, s), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __string( name, s->name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __assign_str(name); ), TP_printk("call_site=%pS ptr=%p name=%s", (void *)__entry->call_site, __entry->ptr, __get_str(name)) ); TRACE_EVENT(mm_page_free, TP_PROTO(struct page *page, unsigned int order), TP_ARGS(page, order), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->order = order; ), TP_printk("page=%p pfn=0x%lx order=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order) ); TRACE_EVENT(mm_page_free_batched, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field( unsigned long, pfn ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); ), TP_printk("page=%p pfn=0x%lx order=0", pfn_to_page(__entry->pfn), __entry->pfn) ); TRACE_EVENT(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype), TP_ARGS(page, order, gfp_flags, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_page, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) ); TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( int, alloc_order ) __field( int, fallback_order ) __field( int, alloc_migratetype ) __field( int, fallback_migratetype ) __field( int, change_ownership ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->alloc_order = alloc_order; __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; __entry->change_ownership = (alloc_migratetype == get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=0x%lx alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->alloc_order, __entry->fallback_order, pageblock_order, __entry->alloc_migratetype, __entry->fallback_migratetype, __entry->fallback_order < pageblock_order, __entry->change_ownership) ); TRACE_EVENT(mm_setup_per_zone_wmarks, TP_PROTO(struct zone *zone), TP_ARGS(zone), TP_STRUCT__entry( __field(int, node_id) __string(name, zone->name) __field(unsigned long, watermark_min) __field(unsigned long, watermark_low) __field(unsigned long, watermark_high) __field(unsigned long, watermark_promo) ), TP_fast_assign( __entry->node_id = zone->zone_pgdat->node_id; __assign_str(name); __entry->watermark_min = zone->_watermark[WMARK_MIN]; __entry->watermark_low = zone->_watermark[WMARK_LOW]; __entry->watermark_high = zone->_watermark[WMARK_HIGH]; __entry->watermark_promo = zone->_watermark[WMARK_PROMO]; ), TP_printk("node_id=%d zone name=%s watermark min=%lu low=%lu high=%lu promo=%lu", __entry->node_id, __get_str(name), __entry->watermark_min, __entry->watermark_low, __entry->watermark_high, __entry->watermark_promo) ); TRACE_EVENT(mm_setup_per_zone_lowmem_reserve, TP_PROTO(struct zone *zone, struct zone *upper_zone, long lowmem_reserve), TP_ARGS(zone, upper_zone, lowmem_reserve), TP_STRUCT__entry( __field(int, node_id) __string(name, zone->name) __string(upper_name, upper_zone->name) __field(long, lowmem_reserve) ), TP_fast_assign( __entry->node_id = zone->zone_pgdat->node_id; __assign_str(name); __assign_str(upper_name); __entry->lowmem_reserve = lowmem_reserve; ), TP_printk("node_id=%d zone name=%s upper_zone name=%s lowmem_reserve_pages=%ld", __entry->node_id, __get_str(name), __get_str(upper_name), __entry->lowmem_reserve) ); TRACE_EVENT(mm_calculate_totalreserve_pages, TP_PROTO(unsigned long totalreserve_pages), TP_ARGS(totalreserve_pages), TP_STRUCT__entry( __field(unsigned long, totalreserve_pages) ), TP_fast_assign( __entry->totalreserve_pages = totalreserve_pages; ), TP_printk("totalreserve_pages=%lu", __entry->totalreserve_pages) ); /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ #ifndef __PTR_TO_HASHVAL static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr) { int ret; unsigned long hashval; ret = ptr_to_hashval(ptr, &hashval); if (ret) return 0; /* The hashed value is only 32-bit */ return (unsigned int)hashval; } #define __PTR_TO_HASHVAL #endif #define TRACE_MM_PAGES \ EM(MM_FILEPAGES) \ EM(MM_ANONPAGES) \ EM(MM_SWAPENTS) \ EMe(MM_SHMEMPAGES) #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); TRACE_MM_PAGES #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } TRACE_EVENT(rss_stat, TP_PROTO(struct mm_struct *mm, int member), TP_ARGS(mm, member), TP_STRUCT__entry( __field(unsigned int, mm_id) __field(unsigned int, curr) __field(int, member) __field(long, size) ), TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); /* * curr is true if the mm matches the current task's mm_struct. * Since kthreads (PF_KTHREAD) have no mm_struct of their own * but can borrow one via kthread_use_mm(), we must filter them * out to avoid incorrectly attributing the RSS update to them. */ __entry->curr = current->mm == mm && !(current->flags & PF_KTHREAD); __entry->member = member; __entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member]) << PAGE_SHIFT); ), TP_printk("mm_id=%u curr=%d type=%s size=%ldB", __entry->mm_id, __entry->curr, __print_symbolic(__entry->member, TRACE_MM_PAGES), __entry->size) ); #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2009 Oracle. All rights reserved. */ #ifndef BTRFS_FREE_SPACE_CACHE_H #define BTRFS_FREE_SPACE_CACHE_H #include <linux/rbtree.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/mutex.h> #include <linux/freezer.h> #include "fs.h" struct inode; struct page; struct btrfs_fs_info; struct btrfs_path; struct btrfs_trans_handle; struct btrfs_trim_block_group; /* * This is the trim state of an extent or bitmap. * * BTRFS_TRIM_STATE_TRIMMING is special and used to maintain the state of a * bitmap as we may need several trims to fully trim a single bitmap entry. * This is reset should any free space other than trimmed space be added to the * bitmap. */ enum btrfs_trim_state { BTRFS_TRIM_STATE_UNTRIMMED, BTRFS_TRIM_STATE_TRIMMED, BTRFS_TRIM_STATE_TRIMMING, }; struct btrfs_free_space { struct rb_node offset_index; struct rb_node bytes_index; u64 offset; u64 bytes; u64 max_extent_size; unsigned long *bitmap; struct list_head list; enum btrfs_trim_state trim_state; s32 bitmap_extents; }; static inline bool btrfs_free_space_trimmed(struct btrfs_free_space *info) { return (info->trim_state == BTRFS_TRIM_STATE_TRIMMED); } static inline bool btrfs_free_space_trimming_bitmap( struct btrfs_free_space *info) { return (info->trim_state == BTRFS_TRIM_STATE_TRIMMING); } static inline bool btrfs_trim_interrupted(void) { return fatal_signal_pending(current) || freezing(current); } /* * Deltas are an effective way to populate global statistics. Give macro names * to make it clear what we're doing. An example is discard_extents in * btrfs_free_space_ctl. */ enum { BTRFS_STAT_CURR, BTRFS_STAT_PREV, BTRFS_STAT_NR_ENTRIES, }; struct btrfs_free_space_ctl { spinlock_t tree_lock; struct rb_root free_space_offset; struct rb_root_cached free_space_bytes; u64 free_space; int extents_thresh; int free_extents; int total_bitmaps; int unit; u64 start; s32 discardable_extents[BTRFS_STAT_NR_ENTRIES]; s64 discardable_bytes[BTRFS_STAT_NR_ENTRIES]; const struct btrfs_free_space_op *op; struct btrfs_block_group *block_group; struct mutex cache_writeout_mutex; struct list_head trimming_ranges; }; struct btrfs_free_space_op { bool (*use_bitmap)(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info); }; struct btrfs_io_ctl { void *cur, *orig; struct page *page; struct page **pages; struct btrfs_fs_info *fs_info; struct inode *inode; unsigned long size; int index; int num_pages; int entries; int bitmaps; }; int __init btrfs_free_space_init(void); void __cold btrfs_free_space_exit(void); struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group, struct btrfs_path *path); int create_free_space_inode(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path); int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans, struct inode *inode, struct btrfs_block_group *block_group); int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct inode *inode); int load_free_space_cache(struct btrfs_block_group *block_group); int btrfs_wait_cache_io(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path); int btrfs_write_out_cache(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path); void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group, struct btrfs_free_space_ctl *ctl); int btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size); int btrfs_add_free_space_unused(struct btrfs_block_group *block_group, u64 bytenr, u64 size); int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group, u64 bytenr, u64 size); int btrfs_remove_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size); void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group); bool btrfs_is_free_space_trimmed(struct btrfs_block_group *block_group); u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group, u64 offset, u64 bytes, u64 empty_size, u64 *max_extent_size); void btrfs_dump_free_space(struct btrfs_block_group *block_group, u64 bytes); int btrfs_find_space_cluster(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, u64 offset, u64 bytes, u64 empty_size); void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster); u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, u64 bytes, u64 min_start, u64 *max_extent_size); void btrfs_return_cluster_to_free_space( struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster); int btrfs_trim_block_group(struct btrfs_block_group *block_group, u64 *trimmed, u64 start, u64 end, u64 minlen); int btrfs_trim_block_group_extents(struct btrfs_block_group *block_group, u64 *trimmed, u64 start, u64 end, u64 minlen, bool async); int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group, u64 *trimmed, u64 start, u64 end, u64 minlen, u64 maxlen, bool async); void btrfs_trim_fully_remapped_block_group(struct btrfs_block_group *bg); bool btrfs_free_space_cache_v1_active(struct btrfs_fs_info *fs_info); int btrfs_set_free_space_cache_v1_active(struct btrfs_fs_info *fs_info, bool active); /* Support functions for running our sanity tests */ #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS int test_add_free_space_entry(struct btrfs_block_group *cache, u64 offset, u64 bytes, bool bitmap); int test_check_exists(struct btrfs_block_group *cache, u64 offset, u64 bytes); #endif #endif |
| 4 1 3 3 3 2 4 3 1 4 2 2 4 4 3 3 2 1 3 1 3 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 | // SPDX-License-Identifier: GPL-2.0 /* USB Driver for Sierra Wireless Copyright (C) 2006, 2007, 2008 Kevin Lloyd <klloyd@sierrawireless.com>, Copyright (C) 2008, 2009 Elina Pasheva, Matthew Safar, Rory Filer <linux@sierrawireless.com> IMPORTANT DISCLAIMER: This driver is not commercially supported by Sierra Wireless. Use at your own risk. Portions based on the option driver by Matthias Urlichs <smurf@smurf.noris.de> Whom based his on the Keyspan driver by Hugh Blemings <hugh@blemings.org> */ /* Uncomment to log function calls */ /* #define DEBUG */ #define DRIVER_AUTHOR "Kevin Lloyd, Elina Pasheva, Matthew Safar, Rory Filer" #define DRIVER_DESC "USB Driver for Sierra Wireless USB modems" #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/errno.h> #include <linux/tty.h> #include <linux/slab.h> #include <linux/tty_flip.h> #include <linux/module.h> #include <linux/usb.h> #include <linux/usb/serial.h> #define SWIMS_USB_REQUEST_SetPower 0x00 #define SWIMS_USB_REQUEST_SetNmea 0x07 #define N_IN_URB_HM 8 #define N_OUT_URB_HM 64 #define N_IN_URB 4 #define N_OUT_URB 4 #define IN_BUFLEN 4096 #define MAX_TRANSFER (PAGE_SIZE - 512) /* MAX_TRANSFER is chosen so that the VM is not stressed by allocations > PAGE_SIZE and the number of packets in a page is an integer 512 is the largest possible packet on EHCI */ static bool nmea; struct sierra_iface_list { const u8 *nums; /* array of interface numbers */ size_t count; /* number of elements in array */ }; struct sierra_intf_private { spinlock_t susp_lock; unsigned int suspended:1; int in_flight; unsigned int open_ports; }; static int sierra_set_power_state(struct usb_device *udev, __u16 swiState) { return usb_control_msg(udev, usb_sndctrlpipe(udev, 0), SWIMS_USB_REQUEST_SetPower, /* __u8 request */ USB_TYPE_VENDOR, /* __u8 request type */ swiState, /* __u16 value */ 0, /* __u16 index */ NULL, /* void *data */ 0, /* __u16 size */ USB_CTRL_SET_TIMEOUT); /* int timeout */ } static int sierra_vsc_set_nmea(struct usb_device *udev, __u16 enable) { return usb_control_msg(udev, usb_sndctrlpipe(udev, 0), SWIMS_USB_REQUEST_SetNmea, /* __u8 request */ USB_TYPE_VENDOR, /* __u8 request type */ enable, /* __u16 value */ 0x0000, /* __u16 index */ NULL, /* void *data */ 0, /* __u16 size */ USB_CTRL_SET_TIMEOUT); /* int timeout */ } static int sierra_calc_num_ports(struct usb_serial *serial, struct usb_serial_endpoints *epds) { int num_ports = 0; u8 ifnum, numendpoints; ifnum = serial->interface->cur_altsetting->desc.bInterfaceNumber; numendpoints = serial->interface->cur_altsetting->desc.bNumEndpoints; /* Dummy interface present on some SKUs should be ignored */ if (ifnum == 0x99) num_ports = 0; else if (numendpoints <= 3) num_ports = 1; else num_ports = (numendpoints-1)/2; return num_ports; } static bool is_listed(const u8 ifnum, const struct sierra_iface_list *list) { int i; if (!list) return false; for (i = 0; i < list->count; i++) { if (list->nums[i] == ifnum) return true; } return false; } static u8 sierra_interface_num(struct usb_serial *serial) { return serial->interface->cur_altsetting->desc.bInterfaceNumber; } static int sierra_probe(struct usb_serial *serial, const struct usb_device_id *id) { const struct sierra_iface_list *ignore_list; int result = 0; struct usb_device *udev; u8 ifnum; udev = serial->dev; ifnum = sierra_interface_num(serial); /* * If this interface supports more than 1 alternate * select the 2nd one */ if (serial->interface->num_altsetting == 2) { dev_dbg(&udev->dev, "Selecting alt setting for interface %d\n", ifnum); /* We know the alternate setting is 1 for the MC8785 */ usb_set_interface(udev, ifnum, 1); } ignore_list = (const struct sierra_iface_list *)id->driver_info; if (is_listed(ifnum, ignore_list)) { dev_dbg(&serial->dev->dev, "Ignoring interface #%d\n", ifnum); return -ENODEV; } return result; } /* interfaces with higher memory requirements */ static const u8 hi_memory_typeA_ifaces[] = { 0, 2 }; static const struct sierra_iface_list typeA_interface_list = { .nums = hi_memory_typeA_ifaces, .count = ARRAY_SIZE(hi_memory_typeA_ifaces), }; static const u8 hi_memory_typeB_ifaces[] = { 3, 4, 5, 6 }; static const struct sierra_iface_list typeB_interface_list = { .nums = hi_memory_typeB_ifaces, .count = ARRAY_SIZE(hi_memory_typeB_ifaces), }; /* 'ignorelist' of interfaces not served by this driver */ static const u8 direct_ip_non_serial_ifaces[] = { 7, 8, 9, 10, 11, 19, 20 }; static const struct sierra_iface_list direct_ip_interface_ignore = { .nums = direct_ip_non_serial_ifaces, .count = ARRAY_SIZE(direct_ip_non_serial_ifaces), }; static const struct usb_device_id id_table[] = { { USB_DEVICE(0x0F3D, 0x0112) }, /* Airprime/Sierra PC 5220 */ { USB_DEVICE(0x03F0, 0x1B1D) }, /* HP ev2200 a.k.a MC5720 */ { USB_DEVICE(0x03F0, 0x211D) }, /* HP ev2210 a.k.a MC5725 */ { USB_DEVICE(0x03F0, 0x1E1D) }, /* HP hs2300 a.k.a MC8775 */ { USB_DEVICE(0x1199, 0x0017) }, /* Sierra Wireless EM5625 */ { USB_DEVICE(0x1199, 0x0018) }, /* Sierra Wireless MC5720 */ { USB_DEVICE(0x1199, 0x0218) }, /* Sierra Wireless MC5720 */ { USB_DEVICE(0x1199, 0x0020) }, /* Sierra Wireless MC5725 */ { USB_DEVICE(0x1199, 0x0220) }, /* Sierra Wireless MC5725 */ { USB_DEVICE(0x1199, 0x0022) }, /* Sierra Wireless EM5725 */ { USB_DEVICE(0x1199, 0x0024) }, /* Sierra Wireless MC5727 */ { USB_DEVICE(0x1199, 0x0224) }, /* Sierra Wireless MC5727 */ { USB_DEVICE(0x1199, 0x0019) }, /* Sierra Wireless AirCard 595 */ { USB_DEVICE(0x1199, 0x0021) }, /* Sierra Wireless AirCard 597E */ { USB_DEVICE(0x1199, 0x0112) }, /* Sierra Wireless AirCard 580 */ { USB_DEVICE(0x1199, 0x0120) }, /* Sierra Wireless USB Dongle 595U */ { USB_DEVICE(0x1199, 0x0301) }, /* Sierra Wireless USB Dongle 250U */ /* Sierra Wireless C597 */ { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x0023, 0xFF, 0xFF, 0xFF) }, /* Sierra Wireless T598 */ { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x0025, 0xFF, 0xFF, 0xFF) }, { USB_DEVICE(0x1199, 0x0026) }, /* Sierra Wireless T11 */ { USB_DEVICE(0x1199, 0x0027) }, /* Sierra Wireless AC402 */ { USB_DEVICE(0x1199, 0x0028) }, /* Sierra Wireless MC5728 */ { USB_DEVICE(0x1199, 0x0029) }, /* Sierra Wireless Device */ { USB_DEVICE(0x1199, 0x6802) }, /* Sierra Wireless MC8755 */ { USB_DEVICE(0x1199, 0x6803) }, /* Sierra Wireless MC8765 */ { USB_DEVICE(0x1199, 0x6804) }, /* Sierra Wireless MC8755 */ { USB_DEVICE(0x1199, 0x6805) }, /* Sierra Wireless MC8765 */ { USB_DEVICE(0x1199, 0x6808) }, /* Sierra Wireless MC8755 */ { USB_DEVICE(0x1199, 0x6809) }, /* Sierra Wireless MC8765 */ { USB_DEVICE(0x1199, 0x6812) }, /* Sierra Wireless MC8775 & AC 875U */ { USB_DEVICE(0x1199, 0x6813) }, /* Sierra Wireless MC8775 */ { USB_DEVICE(0x1199, 0x6815) }, /* Sierra Wireless MC8775 */ { USB_DEVICE(0x1199, 0x6816) }, /* Sierra Wireless MC8775 */ { USB_DEVICE(0x1199, 0x6820) }, /* Sierra Wireless AirCard 875 */ { USB_DEVICE(0x1199, 0x6821) }, /* Sierra Wireless AirCard 875U */ { USB_DEVICE(0x1199, 0x6822) }, /* Sierra Wireless AirCard 875E */ { USB_DEVICE(0x1199, 0x6832) }, /* Sierra Wireless MC8780 */ { USB_DEVICE(0x1199, 0x6833) }, /* Sierra Wireless MC8781 */ { USB_DEVICE(0x1199, 0x6834) }, /* Sierra Wireless MC8780 */ { USB_DEVICE(0x1199, 0x6835) }, /* Sierra Wireless MC8781 */ { USB_DEVICE(0x1199, 0x6838) }, /* Sierra Wireless MC8780 */ { USB_DEVICE(0x1199, 0x6839) }, /* Sierra Wireless MC8781 */ { USB_DEVICE(0x1199, 0x683A) }, /* Sierra Wireless MC8785 */ { USB_DEVICE(0x1199, 0x683B) }, /* Sierra Wireless MC8785 Composite */ /* Sierra Wireless MC8790, MC8791, MC8792 Composite */ { USB_DEVICE(0x1199, 0x683C) }, { USB_DEVICE(0x1199, 0x683D) }, /* Sierra Wireless MC8791 Composite */ /* Sierra Wireless MC8790, MC8791, MC8792 */ { USB_DEVICE(0x1199, 0x683E) }, { USB_DEVICE(0x1199, 0x6850) }, /* Sierra Wireless AirCard 880 */ { USB_DEVICE(0x1199, 0x6851) }, /* Sierra Wireless AirCard 881 */ { USB_DEVICE(0x1199, 0x6852) }, /* Sierra Wireless AirCard 880 E */ { USB_DEVICE(0x1199, 0x6853) }, /* Sierra Wireless AirCard 881 E */ { USB_DEVICE(0x1199, 0x6855) }, /* Sierra Wireless AirCard 880 U */ { USB_DEVICE(0x1199, 0x6856) }, /* Sierra Wireless AirCard 881 U */ { USB_DEVICE(0x1199, 0x6859) }, /* Sierra Wireless AirCard 885 E */ { USB_DEVICE(0x1199, 0x685A) }, /* Sierra Wireless AirCard 885 E */ /* Sierra Wireless C885 */ { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x6880, 0xFF, 0xFF, 0xFF)}, /* Sierra Wireless C888, Air Card 501, USB 303, USB 304 */ { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x6890, 0xFF, 0xFF, 0xFF)}, /* Sierra Wireless C22/C33 */ { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x6891, 0xFF, 0xFF, 0xFF)}, /* Sierra Wireless HSPA Non-Composite Device */ { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x6892, 0xFF, 0xFF, 0xFF)}, { USB_DEVICE(0x1199, 0x6893) }, /* Sierra Wireless Device */ /* Sierra Wireless Direct IP modems */ { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68A3, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_ignore }, { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68AA, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_ignore }, { USB_DEVICE(0x1199, 0x68AB) }, /* Sierra Wireless AR8550 */ /* AT&T Direct IP LTE modems */ { USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68AA, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_ignore }, /* Airprime/Sierra Wireless Direct IP modems */ { USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68A3, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_ignore }, { } }; MODULE_DEVICE_TABLE(usb, id_table); struct sierra_port_private { spinlock_t lock; /* lock the structure */ int outstanding_urbs; /* number of out urbs in flight */ struct usb_anchor active; struct usb_anchor delayed; int num_out_urbs; int num_in_urbs; /* Input endpoints and buffers for this port */ struct urb *in_urbs[N_IN_URB_HM]; /* Settings for the port */ int rts_state; /* Handshaking pins (outputs) */ int dtr_state; int cts_state; /* Handshaking pins (inputs) */ int dsr_state; int dcd_state; int ri_state; }; static int sierra_send_setup(struct usb_serial_port *port) { struct usb_serial *serial = port->serial; struct sierra_port_private *portdata; __u16 interface = 0; int val = 0; int do_send = 0; int retval; portdata = usb_get_serial_port_data(port); if (portdata->dtr_state) val |= 0x01; if (portdata->rts_state) val |= 0x02; /* If composite device then properly report interface */ if (serial->num_ports == 1) { interface = sierra_interface_num(serial); /* Control message is sent only to interfaces with * interrupt_in endpoints */ if (port->interrupt_in_urb) { /* send control message */ do_send = 1; } } /* Otherwise the need to do non-composite mapping */ else { if (port->bulk_out_endpointAddress == 2) interface = 0; else if (port->bulk_out_endpointAddress == 4) interface = 1; else if (port->bulk_out_endpointAddress == 5) interface = 2; do_send = 1; } if (!do_send) return 0; retval = usb_autopm_get_interface(serial->interface); if (retval < 0) return retval; retval = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0), 0x22, 0x21, val, interface, NULL, 0, USB_CTRL_SET_TIMEOUT); usb_autopm_put_interface(serial->interface); return retval; } static int sierra_tiocmget(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; unsigned int value; struct sierra_port_private *portdata; portdata = usb_get_serial_port_data(port); value = ((portdata->rts_state) ? TIOCM_RTS : 0) | ((portdata->dtr_state) ? TIOCM_DTR : 0) | ((portdata->cts_state) ? TIOCM_CTS : 0) | ((portdata->dsr_state) ? TIOCM_DSR : 0) | ((portdata->dcd_state) ? TIOCM_CAR : 0) | ((portdata->ri_state) ? TIOCM_RNG : 0); return value; } static int sierra_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) { struct usb_serial_port *port = tty->driver_data; struct sierra_port_private *portdata; portdata = usb_get_serial_port_data(port); if (set & TIOCM_RTS) portdata->rts_state = 1; if (set & TIOCM_DTR) portdata->dtr_state = 1; if (clear & TIOCM_RTS) portdata->rts_state = 0; if (clear & TIOCM_DTR) portdata->dtr_state = 0; return sierra_send_setup(port); } static void sierra_release_urb(struct urb *urb) { if (urb) { kfree(urb->transfer_buffer); usb_free_urb(urb); } } static void sierra_outdat_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; struct sierra_port_private *portdata = usb_get_serial_port_data(port); struct sierra_intf_private *intfdata; int status = urb->status; unsigned long flags; intfdata = usb_get_serial_data(port->serial); /* free up the transfer buffer, as usb_free_urb() does not do this */ kfree(urb->transfer_buffer); usb_autopm_put_interface_async(port->serial->interface); if (status) dev_dbg(&port->dev, "%s - nonzero write bulk status " "received: %d\n", __func__, status); spin_lock_irqsave(&portdata->lock, flags); --portdata->outstanding_urbs; spin_unlock_irqrestore(&portdata->lock, flags); spin_lock_irqsave(&intfdata->susp_lock, flags); --intfdata->in_flight; spin_unlock_irqrestore(&intfdata->susp_lock, flags); usb_serial_port_softint(port); } /* Write */ static int sierra_write(struct tty_struct *tty, struct usb_serial_port *port, const unsigned char *buf, int count) { struct sierra_port_private *portdata; struct sierra_intf_private *intfdata; struct usb_serial *serial = port->serial; unsigned long flags; unsigned char *buffer; struct urb *urb; size_t writesize = min_t(size_t, count, MAX_TRANSFER); int retval = 0; /* verify that we actually have some data to write */ if (count == 0) return 0; portdata = usb_get_serial_port_data(port); intfdata = usb_get_serial_data(serial); dev_dbg(&port->dev, "%s: write (%zd bytes)\n", __func__, writesize); spin_lock_irqsave(&portdata->lock, flags); dev_dbg(&port->dev, "%s - outstanding_urbs: %d\n", __func__, portdata->outstanding_urbs); if (portdata->outstanding_urbs > portdata->num_out_urbs) { spin_unlock_irqrestore(&portdata->lock, flags); dev_dbg(&port->dev, "%s - write limit hit\n", __func__); return 0; } portdata->outstanding_urbs++; dev_dbg(&port->dev, "%s - 1, outstanding_urbs: %d\n", __func__, portdata->outstanding_urbs); spin_unlock_irqrestore(&portdata->lock, flags); retval = usb_autopm_get_interface_async(serial->interface); if (retval < 0) { spin_lock_irqsave(&portdata->lock, flags); portdata->outstanding_urbs--; spin_unlock_irqrestore(&portdata->lock, flags); goto error_simple; } buffer = kmemdup(buf, writesize, GFP_ATOMIC); if (!buffer) { retval = -ENOMEM; goto error_no_buffer; } urb = usb_alloc_urb(0, GFP_ATOMIC); if (!urb) { retval = -ENOMEM; goto error_no_urb; } usb_serial_debug_data(&port->dev, __func__, writesize, buffer); usb_fill_bulk_urb(urb, serial->dev, usb_sndbulkpipe(serial->dev, port->bulk_out_endpointAddress), buffer, writesize, sierra_outdat_callback, port); /* Handle the need to send a zero length packet */ urb->transfer_flags |= URB_ZERO_PACKET; spin_lock_irqsave(&intfdata->susp_lock, flags); if (intfdata->suspended) { usb_anchor_urb(urb, &portdata->delayed); spin_unlock_irqrestore(&intfdata->susp_lock, flags); goto skip_power; } else { usb_anchor_urb(urb, &portdata->active); } /* send it down the pipe */ retval = usb_submit_urb(urb, GFP_ATOMIC); if (retval) { usb_unanchor_urb(urb); spin_unlock_irqrestore(&intfdata->susp_lock, flags); dev_err(&port->dev, "%s - usb_submit_urb(write bulk) failed " "with status = %d\n", __func__, retval); goto error; } else { intfdata->in_flight++; spin_unlock_irqrestore(&intfdata->susp_lock, flags); } skip_power: /* we are done with this urb, so let the host driver * really free it when it is finished with it */ usb_free_urb(urb); return writesize; error: usb_free_urb(urb); error_no_urb: kfree(buffer); error_no_buffer: spin_lock_irqsave(&portdata->lock, flags); --portdata->outstanding_urbs; dev_dbg(&port->dev, "%s - 2. outstanding_urbs: %d\n", __func__, portdata->outstanding_urbs); spin_unlock_irqrestore(&portdata->lock, flags); usb_autopm_put_interface_async(serial->interface); error_simple: return retval; } static void sierra_indat_callback(struct urb *urb) { int err; int endpoint; struct usb_serial_port *port; unsigned char *data = urb->transfer_buffer; int status = urb->status; endpoint = usb_pipeendpoint(urb->pipe); port = urb->context; if (status) { dev_dbg(&port->dev, "%s: nonzero status: %d on" " endpoint %02x\n", __func__, status, endpoint); } else { if (urb->actual_length) { tty_insert_flip_string(&port->port, data, urb->actual_length); tty_flip_buffer_push(&port->port); usb_serial_debug_data(&port->dev, __func__, urb->actual_length, data); } else { dev_dbg(&port->dev, "%s: empty read urb" " received\n", __func__); } } /* Resubmit urb so we continue receiving */ if (status != -ESHUTDOWN && status != -EPERM) { usb_mark_last_busy(port->serial->dev); err = usb_submit_urb(urb, GFP_ATOMIC); if (err && err != -EPERM) dev_err(&port->dev, "resubmit read urb failed." "(%d)\n", err); } } static void sierra_instat_callback(struct urb *urb) { int err; int status = urb->status; struct usb_serial_port *port = urb->context; struct sierra_port_private *portdata = usb_get_serial_port_data(port); struct usb_serial *serial = port->serial; dev_dbg(&port->dev, "%s: urb %p port %p has data %p\n", __func__, urb, port, portdata); if (status == 0) { struct usb_ctrlrequest *req_pkt = urb->transfer_buffer; if (!req_pkt) { dev_dbg(&port->dev, "%s: NULL req_pkt\n", __func__); return; } if ((req_pkt->bRequestType == 0xA1) && (req_pkt->bRequest == 0x20)) { int old_dcd_state; unsigned char signals = *((unsigned char *) urb->transfer_buffer + sizeof(struct usb_ctrlrequest)); dev_dbg(&port->dev, "%s: signal x%x\n", __func__, signals); old_dcd_state = portdata->dcd_state; portdata->cts_state = 1; portdata->dcd_state = ((signals & 0x01) ? 1 : 0); portdata->dsr_state = ((signals & 0x02) ? 1 : 0); portdata->ri_state = ((signals & 0x08) ? 1 : 0); if (old_dcd_state && !portdata->dcd_state) tty_port_tty_hangup(&port->port, true); } else { dev_dbg(&port->dev, "%s: type %x req %x\n", __func__, req_pkt->bRequestType, req_pkt->bRequest); } } else dev_dbg(&port->dev, "%s: error %d\n", __func__, status); /* Resubmit urb so we continue receiving IRQ data */ if (status != -ESHUTDOWN && status != -ENOENT) { usb_mark_last_busy(serial->dev); err = usb_submit_urb(urb, GFP_ATOMIC); if (err && err != -EPERM) dev_err(&port->dev, "%s: resubmit intr urb " "failed. (%d)\n", __func__, err); } } static unsigned int sierra_write_room(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; struct sierra_port_private *portdata = usb_get_serial_port_data(port); unsigned long flags; /* try to give a good number back based on if we have any free urbs at * this point in time */ spin_lock_irqsave(&portdata->lock, flags); if (portdata->outstanding_urbs > (portdata->num_out_urbs * 2) / 3) { spin_unlock_irqrestore(&portdata->lock, flags); dev_dbg(&port->dev, "%s - write limit hit\n", __func__); return 0; } spin_unlock_irqrestore(&portdata->lock, flags); return 2048; } static unsigned int sierra_chars_in_buffer(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; struct sierra_port_private *portdata = usb_get_serial_port_data(port); unsigned long flags; unsigned int chars; /* NOTE: This overcounts somewhat. */ spin_lock_irqsave(&portdata->lock, flags); chars = portdata->outstanding_urbs * MAX_TRANSFER; spin_unlock_irqrestore(&portdata->lock, flags); dev_dbg(&port->dev, "%s - %u\n", __func__, chars); return chars; } static void sierra_stop_rx_urbs(struct usb_serial_port *port) { int i; struct sierra_port_private *portdata = usb_get_serial_port_data(port); for (i = 0; i < portdata->num_in_urbs; i++) usb_kill_urb(portdata->in_urbs[i]); usb_kill_urb(port->interrupt_in_urb); } static int sierra_submit_rx_urbs(struct usb_serial_port *port, gfp_t mem_flags) { int ok_cnt; int err = -EINVAL; int i; struct urb *urb; struct sierra_port_private *portdata = usb_get_serial_port_data(port); ok_cnt = 0; for (i = 0; i < portdata->num_in_urbs; i++) { urb = portdata->in_urbs[i]; if (!urb) continue; err = usb_submit_urb(urb, mem_flags); if (err) { dev_err(&port->dev, "%s: submit urb failed: %d\n", __func__, err); } else { ok_cnt++; } } if (ok_cnt && port->interrupt_in_urb) { err = usb_submit_urb(port->interrupt_in_urb, mem_flags); if (err) { dev_err(&port->dev, "%s: submit intr urb failed: %d\n", __func__, err); } } if (ok_cnt > 0) /* at least one rx urb submitted */ return 0; else return err; } static struct urb *sierra_setup_urb(struct usb_serial *serial, int endpoint, int dir, void *ctx, int len, gfp_t mem_flags, usb_complete_t callback) { struct urb *urb; u8 *buf; urb = usb_alloc_urb(0, mem_flags); if (!urb) return NULL; buf = kmalloc(len, mem_flags); if (buf) { /* Fill URB using supplied data */ usb_fill_bulk_urb(urb, serial->dev, usb_sndbulkpipe(serial->dev, endpoint) | dir, buf, len, callback, ctx); dev_dbg(&serial->dev->dev, "%s %c u : %p d:%p\n", __func__, dir == USB_DIR_IN ? 'i' : 'o', urb, buf); } else { sierra_release_urb(urb); urb = NULL; } return urb; } static void sierra_close(struct usb_serial_port *port) { int i; struct usb_serial *serial = port->serial; struct sierra_port_private *portdata; struct sierra_intf_private *intfdata = usb_get_serial_data(serial); struct urb *urb; portdata = usb_get_serial_port_data(port); /* * Need to take susp_lock to make sure port is not already being * resumed, but no need to hold it due to the tty-port initialized * flag. */ spin_lock_irq(&intfdata->susp_lock); if (--intfdata->open_ports == 0) serial->interface->needs_remote_wakeup = 0; spin_unlock_irq(&intfdata->susp_lock); for (;;) { urb = usb_get_from_anchor(&portdata->delayed); if (!urb) break; kfree(urb->transfer_buffer); usb_free_urb(urb); usb_autopm_put_interface_async(serial->interface); spin_lock_irq(&portdata->lock); portdata->outstanding_urbs--; spin_unlock_irq(&portdata->lock); } sierra_stop_rx_urbs(port); usb_kill_anchored_urbs(&portdata->active); for (i = 0; i < portdata->num_in_urbs; i++) { sierra_release_urb(portdata->in_urbs[i]); portdata->in_urbs[i] = NULL; } usb_autopm_get_interface_no_resume(serial->interface); } static int sierra_open(struct tty_struct *tty, struct usb_serial_port *port) { struct sierra_port_private *portdata; struct usb_serial *serial = port->serial; struct sierra_intf_private *intfdata = usb_get_serial_data(serial); int i; int err; int endpoint; struct urb *urb; portdata = usb_get_serial_port_data(port); endpoint = port->bulk_in_endpointAddress; for (i = 0; i < portdata->num_in_urbs; i++) { urb = sierra_setup_urb(serial, endpoint, USB_DIR_IN, port, IN_BUFLEN, GFP_KERNEL, sierra_indat_callback); portdata->in_urbs[i] = urb; } /* clear halt condition */ usb_clear_halt(serial->dev, usb_sndbulkpipe(serial->dev, endpoint) | USB_DIR_IN); err = sierra_submit_rx_urbs(port, GFP_KERNEL); if (err) goto err_submit; spin_lock_irq(&intfdata->susp_lock); if (++intfdata->open_ports == 1) serial->interface->needs_remote_wakeup = 1; spin_unlock_irq(&intfdata->susp_lock); usb_autopm_put_interface(serial->interface); return 0; err_submit: sierra_stop_rx_urbs(port); for (i = 0; i < portdata->num_in_urbs; i++) { sierra_release_urb(portdata->in_urbs[i]); portdata->in_urbs[i] = NULL; } return err; } static void sierra_dtr_rts(struct usb_serial_port *port, int on) { struct sierra_port_private *portdata; portdata = usb_get_serial_port_data(port); portdata->rts_state = on; portdata->dtr_state = on; sierra_send_setup(port); } static int sierra_startup(struct usb_serial *serial) { struct sierra_intf_private *intfdata; intfdata = kzalloc_obj(*intfdata); if (!intfdata) return -ENOMEM; spin_lock_init(&intfdata->susp_lock); usb_set_serial_data(serial, intfdata); /* Set Device mode to D0 */ sierra_set_power_state(serial->dev, 0x0000); /* Check NMEA and set */ if (nmea) sierra_vsc_set_nmea(serial->dev, 1); return 0; } static void sierra_release(struct usb_serial *serial) { struct sierra_intf_private *intfdata; intfdata = usb_get_serial_data(serial); kfree(intfdata); } static int sierra_port_probe(struct usb_serial_port *port) { struct usb_serial *serial = port->serial; struct sierra_port_private *portdata; const struct sierra_iface_list *himemory_list; u8 ifnum; portdata = kzalloc_obj(*portdata); if (!portdata) return -ENOMEM; spin_lock_init(&portdata->lock); init_usb_anchor(&portdata->active); init_usb_anchor(&portdata->delayed); /* Assume low memory requirements */ portdata->num_out_urbs = N_OUT_URB; portdata->num_in_urbs = N_IN_URB; /* Determine actual memory requirements */ if (serial->num_ports == 1) { /* Get interface number for composite device */ ifnum = sierra_interface_num(serial); himemory_list = &typeB_interface_list; } else { /* This is really the usb-serial port number of the interface * rather than the interface number. */ ifnum = port->port_number; himemory_list = &typeA_interface_list; } if (is_listed(ifnum, himemory_list)) { portdata->num_out_urbs = N_OUT_URB_HM; portdata->num_in_urbs = N_IN_URB_HM; } dev_dbg(&port->dev, "Memory usage (urbs) interface #%d, in=%d, out=%d\n", ifnum, portdata->num_in_urbs, portdata->num_out_urbs); usb_set_serial_port_data(port, portdata); return 0; } static void sierra_port_remove(struct usb_serial_port *port) { struct sierra_port_private *portdata; portdata = usb_get_serial_port_data(port); usb_set_serial_port_data(port, NULL); kfree(portdata); } #ifdef CONFIG_PM static void stop_read_write_urbs(struct usb_serial *serial) { int i; struct usb_serial_port *port; struct sierra_port_private *portdata; /* Stop reading/writing urbs */ for (i = 0; i < serial->num_ports; ++i) { port = serial->port[i]; portdata = usb_get_serial_port_data(port); if (!portdata) continue; sierra_stop_rx_urbs(port); usb_kill_anchored_urbs(&portdata->active); } } static int sierra_suspend(struct usb_serial *serial, pm_message_t message) { struct sierra_intf_private *intfdata = usb_get_serial_data(serial); spin_lock_irq(&intfdata->susp_lock); if (PMSG_IS_AUTO(message)) { if (intfdata->in_flight) { spin_unlock_irq(&intfdata->susp_lock); return -EBUSY; } } intfdata->suspended = 1; spin_unlock_irq(&intfdata->susp_lock); stop_read_write_urbs(serial); return 0; } /* Caller must hold susp_lock. */ static int sierra_submit_delayed_urbs(struct usb_serial_port *port) { struct sierra_port_private *portdata = usb_get_serial_port_data(port); struct sierra_intf_private *intfdata; struct urb *urb; int ec = 0; int err; intfdata = usb_get_serial_data(port->serial); for (;;) { urb = usb_get_from_anchor(&portdata->delayed); if (!urb) break; usb_anchor_urb(urb, &portdata->active); intfdata->in_flight++; err = usb_submit_urb(urb, GFP_ATOMIC); if (err) { dev_err(&port->dev, "%s - submit urb failed: %d", __func__, err); ec++; intfdata->in_flight--; usb_unanchor_urb(urb); kfree(urb->transfer_buffer); usb_free_urb(urb); spin_lock(&portdata->lock); portdata->outstanding_urbs--; spin_unlock(&portdata->lock); } } if (ec) return -EIO; return 0; } static int sierra_resume(struct usb_serial *serial) { struct usb_serial_port *port; struct sierra_intf_private *intfdata = usb_get_serial_data(serial); int ec = 0; int i, err; spin_lock_irq(&intfdata->susp_lock); for (i = 0; i < serial->num_ports; i++) { port = serial->port[i]; if (!tty_port_initialized(&port->port)) continue; err = sierra_submit_delayed_urbs(port); if (err) ec++; err = sierra_submit_rx_urbs(port, GFP_ATOMIC); if (err) ec++; } intfdata->suspended = 0; spin_unlock_irq(&intfdata->susp_lock); return ec ? -EIO : 0; } #else #define sierra_suspend NULL #define sierra_resume NULL #endif static struct usb_serial_driver sierra_device = { .driver = { .name = "sierra", }, .description = "Sierra USB modem", .id_table = id_table, .calc_num_ports = sierra_calc_num_ports, .probe = sierra_probe, .open = sierra_open, .close = sierra_close, .dtr_rts = sierra_dtr_rts, .write = sierra_write, .write_room = sierra_write_room, .chars_in_buffer = sierra_chars_in_buffer, .tiocmget = sierra_tiocmget, .tiocmset = sierra_tiocmset, .attach = sierra_startup, .release = sierra_release, .port_probe = sierra_port_probe, .port_remove = sierra_port_remove, .suspend = sierra_suspend, .resume = sierra_resume, .read_int_callback = sierra_instat_callback, }; static struct usb_serial_driver * const serial_drivers[] = { &sierra_device, NULL }; module_usb_serial_driver(serial_drivers, id_table); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL v2"); module_param(nmea, bool, 0644); MODULE_PARM_DESC(nmea, "NMEA streaming"); |
| 2 2 14 2 8 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/slab.h> #include <linux/regset.h> static int __regset_get(struct task_struct *target, const struct user_regset *regset, unsigned int size, void **data) { void *p = *data, *to_free = NULL; int res; if (!regset->regset_get) return -EOPNOTSUPP; if (size > regset->n * regset->size) size = regset->n * regset->size; if (!p) { to_free = p = kvzalloc(size, GFP_KERNEL); if (!p) return -ENOMEM; } res = regset->regset_get(target, regset, (struct membuf){.p = p, .left = size}); if (res < 0) { kvfree(to_free); return res; } *data = p; return size - res; } int regset_get(struct task_struct *target, const struct user_regset *regset, unsigned int size, void *data) { return __regset_get(target, regset, size, &data); } EXPORT_SYMBOL(regset_get); int regset_get_alloc(struct task_struct *target, const struct user_regset *regset, unsigned int size, void **data) { *data = NULL; return __regset_get(target, regset, size, data); } EXPORT_SYMBOL(regset_get_alloc); /** * copy_regset_to_user - fetch a thread's user_regset data into user memory * @target: thread to be examined * @view: &struct user_regset_view describing user thread machine state * @setno: index in @view->regsets * @offset: offset into the regset data, in bytes * @size: amount of data to copy, in bytes * @data: user-mode pointer to copy into */ int copy_regset_to_user(struct task_struct *target, const struct user_regset_view *view, unsigned int setno, unsigned int offset, unsigned int size, void __user *data) { const struct user_regset *regset = &view->regsets[setno]; void *buf; int ret; ret = regset_get_alloc(target, regset, size, &buf); if (ret > 0) ret = copy_to_user(data, buf, ret) ? -EFAULT : 0; kvfree(buf); return ret; } |
| 20 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 | /* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */ /* * Copyright (c) Meta Platforms, Inc. and affiliates. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the * LICENSE file in the root directory of this source tree) and the GPLv2 (found * in the COPYING file in the root directory of this source tree). * You may select, at your option, one of the above-listed licenses. */ #ifndef ZSTD_COMMON_CPU_H #define ZSTD_COMMON_CPU_H /* * Implementation taken from folly/CpuId.h * https://github.com/facebook/folly/blob/master/folly/CpuId.h */ #include "mem.h" typedef struct { U32 f1c; U32 f1d; U32 f7b; U32 f7c; } ZSTD_cpuid_t; MEM_STATIC ZSTD_cpuid_t ZSTD_cpuid(void) { U32 f1c = 0; U32 f1d = 0; U32 f7b = 0; U32 f7c = 0; #if defined(__i386__) && defined(__PIC__) && !defined(__clang__) && defined(__GNUC__) /* The following block like the normal cpuid branch below, but gcc * reserves ebx for use of its pic register so we must specially * handle the save and restore to avoid clobbering the register */ U32 n; __asm__( "pushl %%ebx\n\t" "cpuid\n\t" "popl %%ebx\n\t" : "=a"(n) : "a"(0) : "ecx", "edx"); if (n >= 1) { U32 f1a; __asm__( "pushl %%ebx\n\t" "cpuid\n\t" "popl %%ebx\n\t" : "=a"(f1a), "=c"(f1c), "=d"(f1d) : "a"(1)); } if (n >= 7) { __asm__( "pushl %%ebx\n\t" "cpuid\n\t" "movl %%ebx, %%eax\n\t" "popl %%ebx" : "=a"(f7b), "=c"(f7c) : "a"(7), "c"(0) : "edx"); } #elif defined(__x86_64__) || defined(_M_X64) || defined(__i386__) U32 n; __asm__("cpuid" : "=a"(n) : "a"(0) : "ebx", "ecx", "edx"); if (n >= 1) { U32 f1a; __asm__("cpuid" : "=a"(f1a), "=c"(f1c), "=d"(f1d) : "a"(1) : "ebx"); } if (n >= 7) { U32 f7a; __asm__("cpuid" : "=a"(f7a), "=b"(f7b), "=c"(f7c) : "a"(7), "c"(0) : "edx"); } #endif { ZSTD_cpuid_t cpuid; cpuid.f1c = f1c; cpuid.f1d = f1d; cpuid.f7b = f7b; cpuid.f7c = f7c; return cpuid; } } #define X(name, r, bit) \ MEM_STATIC int ZSTD_cpuid_##name(ZSTD_cpuid_t const cpuid) { \ return ((cpuid.r) & (1U << bit)) != 0; \ } /* cpuid(1): Processor Info and Feature Bits. */ #define C(name, bit) X(name, f1c, bit) C(sse3, 0) C(pclmuldq, 1) C(dtes64, 2) C(monitor, 3) C(dscpl, 4) C(vmx, 5) C(smx, 6) C(eist, 7) C(tm2, 8) C(ssse3, 9) C(cnxtid, 10) C(fma, 12) C(cx16, 13) C(xtpr, 14) C(pdcm, 15) C(pcid, 17) C(dca, 18) C(sse41, 19) C(sse42, 20) C(x2apic, 21) C(movbe, 22) C(popcnt, 23) C(tscdeadline, 24) C(aes, 25) C(xsave, 26) C(osxsave, 27) C(avx, 28) C(f16c, 29) C(rdrand, 30) #undef C #define D(name, bit) X(name, f1d, bit) D(fpu, 0) D(vme, 1) D(de, 2) D(pse, 3) D(tsc, 4) D(msr, 5) D(pae, 6) D(mce, 7) D(cx8, 8) D(apic, 9) D(sep, 11) D(mtrr, 12) D(pge, 13) D(mca, 14) D(cmov, 15) D(pat, 16) D(pse36, 17) D(psn, 18) D(clfsh, 19) D(ds, 21) D(acpi, 22) D(mmx, 23) D(fxsr, 24) D(sse, 25) D(sse2, 26) D(ss, 27) D(htt, 28) D(tm, 29) D(pbe, 31) #undef D /* cpuid(7): Extended Features. */ #define B(name, bit) X(name, f7b, bit) B(bmi1, 3) B(hle, 4) B(avx2, 5) B(smep, 7) B(bmi2, 8) B(erms, 9) B(invpcid, 10) B(rtm, 11) B(mpx, 14) B(avx512f, 16) B(avx512dq, 17) B(rdseed, 18) B(adx, 19) B(smap, 20) B(avx512ifma, 21) B(pcommit, 22) B(clflushopt, 23) B(clwb, 24) B(avx512pf, 26) B(avx512er, 27) B(avx512cd, 28) B(sha, 29) B(avx512bw, 30) B(avx512vl, 31) #undef B #define C(name, bit) X(name, f7c, bit) C(prefetchwt1, 0) C(avx512vbmi, 1) #undef C #undef X #endif /* ZSTD_COMMON_CPU_H */ |
| 6 6 6 6 17 1 4 12 6 6 11 1 12 6 6 11 1 535 530 4 4 280 278 279 274 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/gen_estimator.c Simple rate estimator. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Eric Dumazet <edumazet@google.com> * * Changes: * Jamal Hadi Salim - moved it to net/core and reshulfed * names to make it usable in general net subsystem. */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/seqlock.h> #include <net/sock.h> #include <net/gen_stats.h> /* This code is NOT intended to be used for statistics collection, * its purpose is to provide a base for statistical multiplexing * for controlled load service. * If you need only statistics, run a user level daemon which * periodically reads byte counters. */ struct net_rate_estimator { struct gnet_stats_basic_sync *bstats; spinlock_t *stats_lock; bool running; struct gnet_stats_basic_sync __percpu *cpu_bstats; u8 ewma_log; u8 intvl_log; /* period : (250ms << intvl_log) */ seqcount_t seq; u64 last_packets; u64 last_bytes; u64 avpps; u64 avbps; unsigned long next_jiffies; struct timer_list timer; struct rcu_head rcu; }; static void est_fetch_counters(struct net_rate_estimator *e, struct gnet_stats_basic_sync *b) { gnet_stats_basic_sync_init(b); if (e->stats_lock) spin_lock(e->stats_lock); gnet_stats_add_basic(b, e->cpu_bstats, e->bstats, e->running); if (e->stats_lock) spin_unlock(e->stats_lock); } static void est_timer(struct timer_list *t) { struct net_rate_estimator *est = timer_container_of(est, t, timer); struct gnet_stats_basic_sync b; u64 b_bytes, b_packets; u64 rate, brate; est_fetch_counters(est, &b); b_bytes = u64_stats_read(&b.bytes); b_packets = u64_stats_read(&b.packets); brate = (b_bytes - est->last_bytes) << (10 - est->intvl_log); brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log); rate = (b_packets - est->last_packets) << (10 - est->intvl_log); rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log); preempt_disable_nested(); write_seqcount_begin(&est->seq); est->avbps += brate; est->avpps += rate; write_seqcount_end(&est->seq); preempt_enable_nested(); est->last_bytes = b_bytes; est->last_packets = b_packets; est->next_jiffies += ((HZ/4) << est->intvl_log); if (unlikely(time_after_eq(jiffies, est->next_jiffies))) { /* Ouch... timer was delayed. */ est->next_jiffies = jiffies + 1; } mod_timer(&est->timer, est->next_jiffies); } /** * gen_new_estimator - create a new rate estimator * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path * @running: true if @bstats represents a running qdisc, thus @bstats' * internal values might change during basic reads. Only used * if @bstats_cpu is NULL * @opt: rate estimator configuration TLV * * Creates a new rate estimator with &bstats as source and &rate_est * as destination. A new timer with the interval specified in the * configuration TLV is created. Upon each interval, the latest statistics * will be read from &bstats and the estimated rate will be stored in * &rate_est with the statistics lock grabbed during this period. * * Returns 0 on success or a negative error code. * */ int gen_new_estimator(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, bool running, struct nlattr *opt) { struct gnet_estimator *parm = nla_data(opt); struct net_rate_estimator *old, *est; struct gnet_stats_basic_sync b; int intvl_log; if (nla_len(opt) < sizeof(*parm)) return -EINVAL; /* allowed timer periods are : * -2 : 250ms, -1 : 500ms, 0 : 1 sec * 1 : 2 sec, 2 : 4 sec, 3 : 8 sec */ if (parm->interval < -2 || parm->interval > 3) return -EINVAL; if (parm->ewma_log == 0 || parm->ewma_log >= 31) return -EINVAL; est = kzalloc_obj(*est); if (!est) return -ENOBUFS; seqcount_init(&est->seq); intvl_log = parm->interval + 2; est->bstats = bstats; est->stats_lock = lock; est->running = running; est->ewma_log = parm->ewma_log; est->intvl_log = intvl_log; est->cpu_bstats = cpu_bstats; if (lock) local_bh_disable(); est_fetch_counters(est, &b); if (lock) local_bh_enable(); est->last_bytes = u64_stats_read(&b.bytes); est->last_packets = u64_stats_read(&b.packets); if (lock) spin_lock_bh(lock); old = rcu_dereference_protected(*rate_est, 1); if (old) { timer_delete_sync(&old->timer); est->avbps = old->avbps; est->avpps = old->avpps; } est->next_jiffies = jiffies + ((HZ/4) << intvl_log); timer_setup(&est->timer, est_timer, 0); mod_timer(&est->timer, est->next_jiffies); rcu_assign_pointer(*rate_est, est); if (lock) spin_unlock_bh(lock); if (old) kfree_rcu(old, rcu); return 0; } EXPORT_SYMBOL(gen_new_estimator); /** * gen_kill_estimator - remove a rate estimator * @rate_est: rate estimator * * Removes the rate estimator. * */ void gen_kill_estimator(struct net_rate_estimator __rcu **rate_est) { struct net_rate_estimator *est; est = unrcu_pointer(xchg(rate_est, NULL)); if (est) { timer_shutdown_sync(&est->timer); kfree_rcu(est, rcu); } } EXPORT_SYMBOL(gen_kill_estimator); /** * gen_replace_estimator - replace rate estimator configuration * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path * @running: true if @bstats represents a running qdisc, thus @bstats' * internal values might change during basic reads. Only used * if @cpu_bstats is NULL * @opt: rate estimator configuration TLV * * Replaces the configuration of a rate estimator by calling * gen_kill_estimator() and gen_new_estimator(). * * Returns 0 on success or a negative error code. */ int gen_replace_estimator(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, bool running, struct nlattr *opt) { return gen_new_estimator(bstats, cpu_bstats, rate_est, lock, running, opt); } EXPORT_SYMBOL(gen_replace_estimator); /** * gen_estimator_active - test if estimator is currently in use * @rate_est: rate estimator * * Returns true if estimator is active, and false if not. */ bool gen_estimator_active(struct net_rate_estimator __rcu **rate_est) { return !!rcu_access_pointer(*rate_est); } EXPORT_SYMBOL(gen_estimator_active); bool gen_estimator_read(struct net_rate_estimator __rcu **rate_est, struct gnet_stats_rate_est64 *sample) { struct net_rate_estimator *est; unsigned seq; rcu_read_lock(); est = rcu_dereference(*rate_est); if (!est) { rcu_read_unlock(); return false; } do { seq = read_seqcount_begin(&est->seq); sample->bps = est->avbps >> 8; sample->pps = est->avpps >> 8; } while (read_seqcount_retry(&est->seq, seq)); rcu_read_unlock(); return true; } EXPORT_SYMBOL(gen_estimator_read); |
| 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KVM_X86_VMX_HYPERV_H #define __KVM_X86_VMX_HYPERV_H #include <linux/kvm_host.h> #include "vmcs12.h" #include "vmx.h" #define EVMPTR_INVALID (-1ULL) #define EVMPTR_MAP_PENDING (-2ULL) enum nested_evmptrld_status { EVMPTRLD_DISABLED, EVMPTRLD_SUCCEEDED, EVMPTRLD_VMFAIL, EVMPTRLD_ERROR, }; #ifdef CONFIG_KVM_HYPERV static inline bool evmptr_is_valid(u64 evmptr) { return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING; } static inline bool nested_vmx_is_evmptr12_valid(struct vcpu_vmx *vmx) { return evmptr_is_valid(vmx->nested.hv_evmcs_vmptr); } static inline bool evmptr_is_set(u64 evmptr) { return evmptr != EVMPTR_INVALID; } static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx) { return evmptr_is_set(vmx->nested.hv_evmcs_vmptr); } static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx) { return vmx->nested.hv_evmcs; } static inline bool guest_cpu_cap_has_evmcs(struct kvm_vcpu *vcpu) { /* * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and * eVMCS has been explicitly enabled by userspace. */ return vcpu->arch.hyperv_enabled && to_vmx(vcpu)->nested.enlightened_vmcs_enabled; } u64 nested_get_evmptr(struct kvm_vcpu *vcpu); uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); int nested_evmcs_check_controls(struct vmcs12 *vmcs12); bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu); void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); #else static inline bool evmptr_is_valid(u64 evmptr) { return false; } static inline bool nested_vmx_is_evmptr12_valid(struct vcpu_vmx *vmx) { return false; } static inline bool evmptr_is_set(u64 evmptr) { return false; } static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx) { return false; } static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx) { return NULL; } #endif #endif /* __KVM_X86_VMX_HYPERV_H */ |
| 213 11 224 224 4 213 211 210 211 2 2 208 208 1 206 206 77 77 63 13 73 73 98 99 71 40 73 73 1 73 165 165 141 94 78 139 94 78 51 51 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 | // SPDX-License-Identifier: GPL-2.0-only /* * vfsv0 quota IO operations on file */ #include <linux/errno.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/dqblk_v2.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/quotaops.h> #include <asm/byteorder.h> #include "quota_tree.h" #include "quotaio_v2.h" MODULE_AUTHOR("Jan Kara"); MODULE_DESCRIPTION("Quota format v2 support"); MODULE_LICENSE("GPL"); static void v2r0_mem2diskdqb(void *dp, struct dquot *dquot); static void v2r0_disk2memdqb(struct dquot *dquot, void *dp); static int v2r0_is_id(void *dp, struct dquot *dquot); static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot); static void v2r1_disk2memdqb(struct dquot *dquot, void *dp); static int v2r1_is_id(void *dp, struct dquot *dquot); static const struct qtree_fmt_operations v2r0_qtree_ops = { .mem2disk_dqblk = v2r0_mem2diskdqb, .disk2mem_dqblk = v2r0_disk2memdqb, .is_id = v2r0_is_id, }; static const struct qtree_fmt_operations v2r1_qtree_ops = { .mem2disk_dqblk = v2r1_mem2diskdqb, .disk2mem_dqblk = v2r1_disk2memdqb, .is_id = v2r1_is_id, }; #define QUOTABLOCK_BITS 10 #define QUOTABLOCK_SIZE (1 << QUOTABLOCK_BITS) static inline qsize_t v2_stoqb(qsize_t space) { return (space + QUOTABLOCK_SIZE - 1) >> QUOTABLOCK_BITS; } static inline qsize_t v2_qbtos(qsize_t blocks) { return blocks << QUOTABLOCK_BITS; } static int v2_read_header(struct super_block *sb, int type, struct v2_disk_dqheader *dqhead) { ssize_t size; size = sb->s_op->quota_read(sb, type, (char *)dqhead, sizeof(struct v2_disk_dqheader), 0); if (size != sizeof(struct v2_disk_dqheader)) { quota_error(sb, "Failed header read: expected=%zd got=%zd", sizeof(struct v2_disk_dqheader), size); if (size < 0) return size; return -EIO; } return 0; } /* Check whether given file is really vfsv0 quotafile */ static int v2_check_quota_file(struct super_block *sb, int type) { struct v2_disk_dqheader dqhead; static const uint quota_magics[] = V2_INITQMAGICS; static const uint quota_versions[] = V2_INITQVERSIONS; if (v2_read_header(sb, type, &dqhead)) return 0; if (le32_to_cpu(dqhead.dqh_magic) != quota_magics[type] || le32_to_cpu(dqhead.dqh_version) > quota_versions[type]) return 0; return 1; } /* Read information header from quota file */ static int v2_read_file_info(struct super_block *sb, int type) { struct v2_disk_dqinfo dinfo; struct v2_disk_dqheader dqhead; struct quota_info *dqopt = sb_dqopt(sb); struct mem_dqinfo *info = &dqopt->info[type]; struct qtree_mem_dqinfo *qinfo; ssize_t size; unsigned int version; unsigned int memalloc; int ret; down_read(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = v2_read_header(sb, type, &dqhead); if (ret < 0) goto out; version = le32_to_cpu(dqhead.dqh_version); if ((info->dqi_fmt_id == QFMT_VFS_V0 && version != 0) || (info->dqi_fmt_id == QFMT_VFS_V1 && version != 1)) { ret = -EINVAL; goto out; } size = sb->s_op->quota_read(sb, type, (char *)&dinfo, sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF); if (size != sizeof(struct v2_disk_dqinfo)) { quota_error(sb, "Can't read info structure"); if (size < 0) ret = size; else ret = -EIO; goto out; } info->dqi_priv = kmalloc_obj(struct qtree_mem_dqinfo); if (!info->dqi_priv) { ret = -ENOMEM; goto out; } qinfo = info->dqi_priv; if (version == 0) { /* limits are stored as unsigned 32-bit data */ info->dqi_max_spc_limit = 0xffffffffLL << QUOTABLOCK_BITS; info->dqi_max_ino_limit = 0xffffffff; } else { /* * Used space is stored as unsigned 64-bit value in bytes but * quota core supports only signed 64-bit values so use that * as a limit */ info->dqi_max_spc_limit = 0x7fffffffffffffffLL; /* 2^63-1 */ info->dqi_max_ino_limit = 0x7fffffffffffffffLL; } info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace); info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace); /* No flags currently supported */ info->dqi_flags = 0; qinfo->dqi_sb = sb; qinfo->dqi_type = type; qinfo->dqi_blocks = le32_to_cpu(dinfo.dqi_blocks); qinfo->dqi_free_blk = le32_to_cpu(dinfo.dqi_free_blk); qinfo->dqi_free_entry = le32_to_cpu(dinfo.dqi_free_entry); qinfo->dqi_blocksize_bits = V2_DQBLKSIZE_BITS; qinfo->dqi_usable_bs = 1 << V2_DQBLKSIZE_BITS; qinfo->dqi_qtree_depth = qtree_depth(qinfo); if (version == 0) { qinfo->dqi_entry_size = sizeof(struct v2r0_disk_dqblk); qinfo->dqi_ops = &v2r0_qtree_ops; } else { qinfo->dqi_entry_size = sizeof(struct v2r1_disk_dqblk); qinfo->dqi_ops = &v2r1_qtree_ops; } ret = -EUCLEAN; /* Some sanity checks of the read headers... */ if ((loff_t)qinfo->dqi_blocks << qinfo->dqi_blocksize_bits > i_size_read(sb_dqopt(sb)->files[type])) { quota_error(sb, "Number of blocks too big for quota file size (%llu > %llu).", (loff_t)qinfo->dqi_blocks << qinfo->dqi_blocksize_bits, i_size_read(sb_dqopt(sb)->files[type])); goto out_free; } if (qinfo->dqi_free_blk && (qinfo->dqi_free_blk <= QT_TREEOFF || qinfo->dqi_free_blk >= qinfo->dqi_blocks)) { quota_error(sb, "Free block number %u out of range (%u, %u).", qinfo->dqi_free_blk, QT_TREEOFF, qinfo->dqi_blocks); goto out_free; } if (qinfo->dqi_free_entry && (qinfo->dqi_free_entry <= QT_TREEOFF || qinfo->dqi_free_entry >= qinfo->dqi_blocks)) { quota_error(sb, "Block with free entry %u out of range (%u, %u).", qinfo->dqi_free_entry, QT_TREEOFF, qinfo->dqi_blocks); goto out_free; } ret = 0; out_free: if (ret) { kfree(info->dqi_priv); info->dqi_priv = NULL; } out: memalloc_nofs_restore(memalloc); up_read(&dqopt->dqio_sem); return ret; } /* Write information header to quota file */ static int v2_write_file_info(struct super_block *sb, int type) { struct v2_disk_dqinfo dinfo; struct quota_info *dqopt = sb_dqopt(sb); struct mem_dqinfo *info = &dqopt->info[type]; struct qtree_mem_dqinfo *qinfo = info->dqi_priv; ssize_t size; unsigned int memalloc; down_write(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); spin_lock(&dq_data_lock); info->dqi_flags &= ~DQF_INFO_DIRTY; dinfo.dqi_bgrace = cpu_to_le32(info->dqi_bgrace); dinfo.dqi_igrace = cpu_to_le32(info->dqi_igrace); /* No flags currently supported */ dinfo.dqi_flags = cpu_to_le32(0); spin_unlock(&dq_data_lock); dinfo.dqi_blocks = cpu_to_le32(qinfo->dqi_blocks); dinfo.dqi_free_blk = cpu_to_le32(qinfo->dqi_free_blk); dinfo.dqi_free_entry = cpu_to_le32(qinfo->dqi_free_entry); size = sb->s_op->quota_write(sb, type, (char *)&dinfo, sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF); memalloc_nofs_restore(memalloc); up_write(&dqopt->dqio_sem); if (size != sizeof(struct v2_disk_dqinfo)) { quota_error(sb, "Can't write info structure"); return size < 0 ? size : -EIO; } return 0; } static void v2r0_disk2memdqb(struct dquot *dquot, void *dp) { struct v2r0_disk_dqblk *d = dp, empty; struct mem_dqblk *m = &dquot->dq_dqb; m->dqb_ihardlimit = le32_to_cpu(d->dqb_ihardlimit); m->dqb_isoftlimit = le32_to_cpu(d->dqb_isoftlimit); m->dqb_curinodes = le32_to_cpu(d->dqb_curinodes); m->dqb_itime = le64_to_cpu(d->dqb_itime); m->dqb_bhardlimit = v2_qbtos(le32_to_cpu(d->dqb_bhardlimit)); m->dqb_bsoftlimit = v2_qbtos(le32_to_cpu(d->dqb_bsoftlimit)); m->dqb_curspace = le64_to_cpu(d->dqb_curspace); m->dqb_btime = le64_to_cpu(d->dqb_btime); /* We need to escape back all-zero structure */ memset(&empty, 0, sizeof(struct v2r0_disk_dqblk)); empty.dqb_itime = cpu_to_le64(1); if (!memcmp(&empty, dp, sizeof(struct v2r0_disk_dqblk))) m->dqb_itime = 0; } static void v2r0_mem2diskdqb(void *dp, struct dquot *dquot) { struct v2r0_disk_dqblk *d = dp; struct mem_dqblk *m = &dquot->dq_dqb; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; d->dqb_ihardlimit = cpu_to_le32(m->dqb_ihardlimit); d->dqb_isoftlimit = cpu_to_le32(m->dqb_isoftlimit); d->dqb_curinodes = cpu_to_le32(m->dqb_curinodes); d->dqb_itime = cpu_to_le64(m->dqb_itime); d->dqb_bhardlimit = cpu_to_le32(v2_stoqb(m->dqb_bhardlimit)); d->dqb_bsoftlimit = cpu_to_le32(v2_stoqb(m->dqb_bsoftlimit)); d->dqb_curspace = cpu_to_le64(m->dqb_curspace); d->dqb_btime = cpu_to_le64(m->dqb_btime); d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id)); if (qtree_entry_unused(info, dp)) d->dqb_itime = cpu_to_le64(1); } static int v2r0_is_id(void *dp, struct dquot *dquot) { struct v2r0_disk_dqblk *d = dp; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; if (qtree_entry_unused(info, dp)) return 0; return qid_eq(make_kqid(&init_user_ns, dquot->dq_id.type, le32_to_cpu(d->dqb_id)), dquot->dq_id); } static void v2r1_disk2memdqb(struct dquot *dquot, void *dp) { struct v2r1_disk_dqblk *d = dp, empty; struct mem_dqblk *m = &dquot->dq_dqb; m->dqb_ihardlimit = le64_to_cpu(d->dqb_ihardlimit); m->dqb_isoftlimit = le64_to_cpu(d->dqb_isoftlimit); m->dqb_curinodes = le64_to_cpu(d->dqb_curinodes); m->dqb_itime = le64_to_cpu(d->dqb_itime); m->dqb_bhardlimit = v2_qbtos(le64_to_cpu(d->dqb_bhardlimit)); m->dqb_bsoftlimit = v2_qbtos(le64_to_cpu(d->dqb_bsoftlimit)); m->dqb_curspace = le64_to_cpu(d->dqb_curspace); m->dqb_btime = le64_to_cpu(d->dqb_btime); /* We need to escape back all-zero structure */ memset(&empty, 0, sizeof(struct v2r1_disk_dqblk)); empty.dqb_itime = cpu_to_le64(1); if (!memcmp(&empty, dp, sizeof(struct v2r1_disk_dqblk))) m->dqb_itime = 0; } static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot) { struct v2r1_disk_dqblk *d = dp; struct mem_dqblk *m = &dquot->dq_dqb; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; d->dqb_ihardlimit = cpu_to_le64(m->dqb_ihardlimit); d->dqb_isoftlimit = cpu_to_le64(m->dqb_isoftlimit); d->dqb_curinodes = cpu_to_le64(m->dqb_curinodes); d->dqb_itime = cpu_to_le64(m->dqb_itime); d->dqb_bhardlimit = cpu_to_le64(v2_stoqb(m->dqb_bhardlimit)); d->dqb_bsoftlimit = cpu_to_le64(v2_stoqb(m->dqb_bsoftlimit)); d->dqb_curspace = cpu_to_le64(m->dqb_curspace); d->dqb_btime = cpu_to_le64(m->dqb_btime); d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id)); d->dqb_pad = 0; if (qtree_entry_unused(info, dp)) d->dqb_itime = cpu_to_le64(1); } static int v2r1_is_id(void *dp, struct dquot *dquot) { struct v2r1_disk_dqblk *d = dp; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; if (qtree_entry_unused(info, dp)) return 0; return qid_eq(make_kqid(&init_user_ns, dquot->dq_id.type, le32_to_cpu(d->dqb_id)), dquot->dq_id); } static int v2_read_dquot(struct dquot *dquot) { struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); int ret; unsigned int memalloc; down_read(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = qtree_read_dquot( sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); memalloc_nofs_restore(memalloc); up_read(&dqopt->dqio_sem); return ret; } static int v2_write_dquot(struct dquot *dquot) { struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); int ret; bool alloc = false; unsigned int memalloc; /* * If space for dquot is already allocated, we don't need any * protection as we'll only overwrite the place of dquot. We are * still protected by concurrent writes of the same dquot by * dquot->dq_lock. */ if (!dquot->dq_off) { alloc = true; down_write(&dqopt->dqio_sem); } else { down_read(&dqopt->dqio_sem); } memalloc = memalloc_nofs_save(); ret = qtree_write_dquot( sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); memalloc_nofs_restore(memalloc); if (alloc) up_write(&dqopt->dqio_sem); else up_read(&dqopt->dqio_sem); return ret; } static int v2_release_dquot(struct dquot *dquot) { struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); unsigned int memalloc; int ret; down_write(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = qtree_release_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); memalloc_nofs_restore(memalloc); up_write(&dqopt->dqio_sem); return ret; } static int v2_free_file_info(struct super_block *sb, int type) { kfree(sb_dqinfo(sb, type)->dqi_priv); return 0; } static int v2_get_next_id(struct super_block *sb, struct kqid *qid) { struct quota_info *dqopt = sb_dqopt(sb); unsigned int memalloc; int ret; down_read(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = qtree_get_next_id(sb_dqinfo(sb, qid->type)->dqi_priv, qid); memalloc_nofs_restore(memalloc); up_read(&dqopt->dqio_sem); return ret; } static const struct quota_format_ops v2_format_ops = { .check_quota_file = v2_check_quota_file, .read_file_info = v2_read_file_info, .write_file_info = v2_write_file_info, .free_file_info = v2_free_file_info, .read_dqblk = v2_read_dquot, .commit_dqblk = v2_write_dquot, .release_dqblk = v2_release_dquot, .get_next_id = v2_get_next_id, }; static struct quota_format_type v2r0_quota_format = { .qf_fmt_id = QFMT_VFS_V0, .qf_ops = &v2_format_ops, .qf_owner = THIS_MODULE }; static struct quota_format_type v2r1_quota_format = { .qf_fmt_id = QFMT_VFS_V1, .qf_ops = &v2_format_ops, .qf_owner = THIS_MODULE }; static int __init init_v2_quota_format(void) { register_quota_format(&v2r0_quota_format); register_quota_format(&v2r1_quota_format); return 0; } static void __exit exit_v2_quota_format(void) { unregister_quota_format(&v2r0_quota_format); unregister_quota_format(&v2r1_quota_format); } module_init(init_v2_quota_format); module_exit(exit_v2_quota_format); |
| 13 553 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 | // SPDX-License-Identifier: GPL-2.0 #ifndef IOU_KBUF_H #define IOU_KBUF_H #include <uapi/linux/io_uring.h> #include <linux/io_uring_types.h> enum { /* ring mapped provided buffers */ IOBL_BUF_RING = 1, /* buffers are consumed incrementally rather than always fully */ IOBL_INC = 2, }; struct io_buffer_list { /* * If the IOBL_BUF_RING flag is set, then buf_ring is used. If not, then * these are classic provided buffers and ->buf_list is used. */ union { struct list_head buf_list; struct io_uring_buf_ring *buf_ring; }; /* count of classic/legacy buffers in buffer list */ int nbufs; __u16 bgid; /* below is for ring provided buffers */ __u16 head; __u16 mask; __u16 flags; /* * minimum required amount to be left to reuse an incrementally * consumed buffer. If less than this is left at consumption time, * buffer is done and head is incremented to the next buffer. */ __u32 min_left_sub_one; struct io_mapped_region region; }; struct io_buffer { struct list_head list; __u64 addr; __u32 len; __u16 bid; __u16 bgid; }; enum { /* can alloc a bigger vec */ KBUF_MODE_EXPAND = 1, /* if bigger vec allocated, free old one */ KBUF_MODE_FREE = 2, }; struct buf_sel_arg { struct iovec *iovs; size_t out_len; size_t max_len; unsigned short nr_iovs; unsigned short mode; unsigned short buf_group; unsigned short partial_map; }; struct io_br_sel io_buffer_select(struct io_kiocb *req, size_t *len, unsigned buf_group, unsigned int issue_flags); int io_buffers_select(struct io_kiocb *req, struct buf_sel_arg *arg, struct io_br_sel *sel, unsigned int issue_flags); int io_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, struct io_br_sel *sel); void io_destroy_buffers(struct io_ring_ctx *ctx); int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_manage_buffers_legacy(struct io_kiocb *req, unsigned int issue_flags); int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg); int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg); int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg); bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags); void io_kbuf_drop_legacy(struct io_kiocb *req); unsigned int __io_put_kbufs(struct io_kiocb *req, struct io_buffer_list *bl, int len, int nbufs); bool io_kbuf_commit(struct io_kiocb *req, struct io_buffer_list *bl, int len, int nr); struct io_mapped_region *io_pbuf_get_region(struct io_ring_ctx *ctx, unsigned int bgid); static inline bool io_kbuf_recycle_ring(struct io_kiocb *req, struct io_buffer_list *bl) { if (bl) { req->flags &= ~(REQ_F_BUFFER_RING|REQ_F_BUFFERS_COMMIT); return true; } return false; } static inline bool io_do_buffer_select(struct io_kiocb *req) { if (!(req->flags & REQ_F_BUFFER_SELECT)) return false; return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)); } static inline bool io_kbuf_recycle(struct io_kiocb *req, struct io_buffer_list *bl, unsigned issue_flags) { if (req->flags & REQ_F_BL_NO_RECYCLE) return false; if (req->flags & REQ_F_BUFFER_RING) return io_kbuf_recycle_ring(req, bl); if (req->flags & REQ_F_BUFFER_SELECTED) return io_kbuf_recycle_legacy(req, issue_flags); return false; } static inline unsigned int io_put_kbuf(struct io_kiocb *req, int len, struct io_buffer_list *bl) { if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED))) return 0; return __io_put_kbufs(req, bl, len, 1); } static inline unsigned int io_put_kbufs(struct io_kiocb *req, int len, struct io_buffer_list *bl, int nbufs) { if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED))) return 0; return __io_put_kbufs(req, bl, len, nbufs); } #endif |
| 9 9 9 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/mrp_bridge.h> #include "br_private_mrp.h" static const u8 mrp_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x1 }; static const u8 mrp_in_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x3 }; static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb); static struct br_frame_type mrp_frame_type __read_mostly = { .type = cpu_to_be16(ETH_P_MRP), .frame_handler = br_mrp_process, }; static bool br_mrp_is_ring_port(struct net_bridge_port *p_port, struct net_bridge_port *s_port, struct net_bridge_port *port) { if (port == p_port || port == s_port) return true; return false; } static bool br_mrp_is_in_port(struct net_bridge_port *i_port, struct net_bridge_port *port) { if (port == i_port) return true; return false; } static struct net_bridge_port *br_mrp_get_port(struct net_bridge *br, u32 ifindex) { struct net_bridge_port *res = NULL; struct net_bridge_port *port; list_for_each_entry(port, &br->port_list, list) { if (port->dev->ifindex == ifindex) { res = port; break; } } return res; } static struct br_mrp *br_mrp_find_id(struct net_bridge *br, u32 ring_id) { struct br_mrp *res = NULL; struct br_mrp *mrp; hlist_for_each_entry_rcu(mrp, &br->mrp_list, list, lockdep_rtnl_is_held()) { if (mrp->ring_id == ring_id) { res = mrp; break; } } return res; } static struct br_mrp *br_mrp_find_in_id(struct net_bridge *br, u32 in_id) { struct br_mrp *res = NULL; struct br_mrp *mrp; hlist_for_each_entry_rcu(mrp, &br->mrp_list, list, lockdep_rtnl_is_held()) { if (mrp->in_id == in_id) { res = mrp; break; } } return res; } static bool br_mrp_unique_ifindex(struct net_bridge *br, u32 ifindex) { struct br_mrp *mrp; hlist_for_each_entry_rcu(mrp, &br->mrp_list, list, lockdep_rtnl_is_held()) { struct net_bridge_port *p; p = rtnl_dereference(mrp->p_port); if (p && p->dev->ifindex == ifindex) return false; p = rtnl_dereference(mrp->s_port); if (p && p->dev->ifindex == ifindex) return false; p = rtnl_dereference(mrp->i_port); if (p && p->dev->ifindex == ifindex) return false; } return true; } static struct br_mrp *br_mrp_find_port(struct net_bridge *br, struct net_bridge_port *p) { struct br_mrp *res = NULL; struct br_mrp *mrp; hlist_for_each_entry_rcu(mrp, &br->mrp_list, list, lockdep_rtnl_is_held()) { if (rcu_access_pointer(mrp->p_port) == p || rcu_access_pointer(mrp->s_port) == p || rcu_access_pointer(mrp->i_port) == p) { res = mrp; break; } } return res; } static int br_mrp_next_seq(struct br_mrp *mrp) { mrp->seq_id++; return mrp->seq_id; } static struct sk_buff *br_mrp_skb_alloc(struct net_bridge_port *p, const u8 *src, const u8 *dst) { struct ethhdr *eth_hdr; struct sk_buff *skb; __be16 *version; skb = dev_alloc_skb(MRP_MAX_FRAME_LENGTH); if (!skb) return NULL; skb->dev = p->dev; skb->protocol = htons(ETH_P_MRP); skb->priority = MRP_FRAME_PRIO; skb_reserve(skb, sizeof(*eth_hdr)); eth_hdr = skb_push(skb, sizeof(*eth_hdr)); ether_addr_copy(eth_hdr->h_dest, dst); ether_addr_copy(eth_hdr->h_source, src); eth_hdr->h_proto = htons(ETH_P_MRP); version = skb_put(skb, sizeof(*version)); *version = cpu_to_be16(MRP_VERSION); return skb; } static void br_mrp_skb_tlv(struct sk_buff *skb, enum br_mrp_tlv_header_type type, u8 length) { struct br_mrp_tlv_hdr *hdr; hdr = skb_put(skb, sizeof(*hdr)); hdr->type = type; hdr->length = length; } static void br_mrp_skb_common(struct sk_buff *skb, struct br_mrp *mrp) { struct br_mrp_common_hdr *hdr; br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_COMMON, sizeof(*hdr)); hdr = skb_put(skb, sizeof(*hdr)); hdr->seq_id = cpu_to_be16(br_mrp_next_seq(mrp)); memset(hdr->domain, 0xff, MRP_DOMAIN_UUID_LENGTH); } static struct sk_buff *br_mrp_alloc_test_skb(struct br_mrp *mrp, struct net_bridge_port *p, enum br_mrp_port_role_type port_role) { struct br_mrp_ring_test_hdr *hdr = NULL; struct sk_buff *skb = NULL; if (!p) return NULL; skb = br_mrp_skb_alloc(p, p->dev->dev_addr, mrp_test_dmac); if (!skb) return NULL; br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_RING_TEST, sizeof(*hdr)); hdr = skb_put(skb, sizeof(*hdr)); hdr->prio = cpu_to_be16(mrp->prio); ether_addr_copy(hdr->sa, p->br->dev->dev_addr); hdr->port_role = cpu_to_be16(port_role); hdr->state = cpu_to_be16(mrp->ring_state); hdr->transitions = cpu_to_be16(mrp->ring_transitions); hdr->timestamp = cpu_to_be32(jiffies_to_msecs(jiffies)); br_mrp_skb_common(skb, mrp); /* In case the node behaves as MRA then the Test frame needs to have * an Option TLV which includes eventually a sub-option TLV that has * the type AUTO_MGR */ if (mrp->ring_role == BR_MRP_RING_ROLE_MRA) { struct br_mrp_sub_option1_hdr *sub_opt = NULL; struct br_mrp_tlv_hdr *sub_tlv = NULL; struct br_mrp_oui_hdr *oui = NULL; u8 length; length = sizeof(*sub_opt) + sizeof(*sub_tlv) + sizeof(oui) + MRP_OPT_PADDING; br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_OPTION, length); oui = skb_put(skb, sizeof(*oui)); memset(oui, 0x0, sizeof(*oui)); sub_opt = skb_put(skb, sizeof(*sub_opt)); memset(sub_opt, 0x0, sizeof(*sub_opt)); sub_tlv = skb_put(skb, sizeof(*sub_tlv)); sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR; /* 32 bit alligment shall be ensured therefore add 2 bytes */ skb_put(skb, MRP_OPT_PADDING); } br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_END, 0x0); return skb; } static struct sk_buff *br_mrp_alloc_in_test_skb(struct br_mrp *mrp, struct net_bridge_port *p, enum br_mrp_port_role_type port_role) { struct br_mrp_in_test_hdr *hdr = NULL; struct sk_buff *skb = NULL; if (!p) return NULL; skb = br_mrp_skb_alloc(p, p->dev->dev_addr, mrp_in_test_dmac); if (!skb) return NULL; br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_IN_TEST, sizeof(*hdr)); hdr = skb_put(skb, sizeof(*hdr)); hdr->id = cpu_to_be16(mrp->in_id); ether_addr_copy(hdr->sa, p->br->dev->dev_addr); hdr->port_role = cpu_to_be16(port_role); hdr->state = cpu_to_be16(mrp->in_state); hdr->transitions = cpu_to_be16(mrp->in_transitions); hdr->timestamp = cpu_to_be32(jiffies_to_msecs(jiffies)); br_mrp_skb_common(skb, mrp); br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_END, 0x0); return skb; } /* This function is continuously called in the following cases: * - when node role is MRM, in this case test_monitor is always set to false * because it needs to notify the userspace that the ring is open and needs to * send MRP_Test frames * - when node role is MRA, there are 2 subcases: * - when MRA behaves as MRM, in this case is similar with MRM role * - when MRA behaves as MRC, in this case test_monitor is set to true, * because it needs to detect when it stops seeing MRP_Test frames * from MRM node but it doesn't need to send MRP_Test frames. */ static void br_mrp_test_work_expired(struct work_struct *work) { struct delayed_work *del_work = to_delayed_work(work); struct br_mrp *mrp = container_of(del_work, struct br_mrp, test_work); struct net_bridge_port *p; bool notify_open = false; struct sk_buff *skb; if (time_before_eq(mrp->test_end, jiffies)) return; if (mrp->test_count_miss < mrp->test_max_miss) { mrp->test_count_miss++; } else { /* Notify that the ring is open only if the ring state is * closed, otherwise it would continue to notify at every * interval. * Also notify that the ring is open when the node has the * role MRA and behaves as MRC. The reason is that the * userspace needs to know when the MRM stopped sending * MRP_Test frames so that the current node to try to take * the role of a MRM. */ if (mrp->ring_state == BR_MRP_RING_STATE_CLOSED || mrp->test_monitor) notify_open = true; } rcu_read_lock(); p = rcu_dereference(mrp->p_port); if (p) { if (!mrp->test_monitor) { skb = br_mrp_alloc_test_skb(mrp, p, BR_MRP_PORT_ROLE_PRIMARY); if (!skb) goto out; skb_reset_network_header(skb); dev_queue_xmit(skb); } if (notify_open && !mrp->ring_role_offloaded) br_mrp_ring_port_open(p->dev, true); } p = rcu_dereference(mrp->s_port); if (p) { if (!mrp->test_monitor) { skb = br_mrp_alloc_test_skb(mrp, p, BR_MRP_PORT_ROLE_SECONDARY); if (!skb) goto out; skb_reset_network_header(skb); dev_queue_xmit(skb); } if (notify_open && !mrp->ring_role_offloaded) br_mrp_ring_port_open(p->dev, true); } out: rcu_read_unlock(); queue_delayed_work(system_percpu_wq, &mrp->test_work, usecs_to_jiffies(mrp->test_interval)); } /* This function is continuously called when the node has the interconnect role * MIM. It would generate interconnect test frames and will send them on all 3 * ports. But will also check if it stop receiving interconnect test frames. */ static void br_mrp_in_test_work_expired(struct work_struct *work) { struct delayed_work *del_work = to_delayed_work(work); struct br_mrp *mrp = container_of(del_work, struct br_mrp, in_test_work); struct net_bridge_port *p; bool notify_open = false; struct sk_buff *skb; if (time_before_eq(mrp->in_test_end, jiffies)) return; if (mrp->in_test_count_miss < mrp->in_test_max_miss) { mrp->in_test_count_miss++; } else { /* Notify that the interconnect ring is open only if the * interconnect ring state is closed, otherwise it would * continue to notify at every interval. */ if (mrp->in_state == BR_MRP_IN_STATE_CLOSED) notify_open = true; } rcu_read_lock(); p = rcu_dereference(mrp->p_port); if (p) { skb = br_mrp_alloc_in_test_skb(mrp, p, BR_MRP_PORT_ROLE_PRIMARY); if (!skb) goto out; skb_reset_network_header(skb); dev_queue_xmit(skb); if (notify_open && !mrp->in_role_offloaded) br_mrp_in_port_open(p->dev, true); } p = rcu_dereference(mrp->s_port); if (p) { skb = br_mrp_alloc_in_test_skb(mrp, p, BR_MRP_PORT_ROLE_SECONDARY); if (!skb) goto out; skb_reset_network_header(skb); dev_queue_xmit(skb); if (notify_open && !mrp->in_role_offloaded) br_mrp_in_port_open(p->dev, true); } p = rcu_dereference(mrp->i_port); if (p) { skb = br_mrp_alloc_in_test_skb(mrp, p, BR_MRP_PORT_ROLE_INTER); if (!skb) goto out; skb_reset_network_header(skb); dev_queue_xmit(skb); if (notify_open && !mrp->in_role_offloaded) br_mrp_in_port_open(p->dev, true); } out: rcu_read_unlock(); queue_delayed_work(system_percpu_wq, &mrp->in_test_work, usecs_to_jiffies(mrp->in_test_interval)); } /* Deletes the MRP instance. * note: called under rtnl_lock */ static void br_mrp_del_impl(struct net_bridge *br, struct br_mrp *mrp) { struct net_bridge_port *p; u8 state; /* Stop sending MRP_Test frames */ cancel_delayed_work_sync(&mrp->test_work); br_mrp_switchdev_send_ring_test(br, mrp, 0, 0, 0, 0); /* Stop sending MRP_InTest frames if has an interconnect role */ cancel_delayed_work_sync(&mrp->in_test_work); br_mrp_switchdev_send_in_test(br, mrp, 0, 0, 0); /* Disable the roles */ br_mrp_switchdev_set_ring_role(br, mrp, BR_MRP_RING_ROLE_DISABLED); p = rtnl_dereference(mrp->i_port); if (p) br_mrp_switchdev_set_in_role(br, mrp, mrp->in_id, mrp->ring_id, BR_MRP_IN_ROLE_DISABLED); br_mrp_switchdev_del(br, mrp); /* Reset the ports */ p = rtnl_dereference(mrp->p_port); if (p) { spin_lock_bh(&br->lock); state = netif_running(br->dev) ? BR_STATE_FORWARDING : BR_STATE_DISABLED; p->state = state; p->flags &= ~BR_MRP_AWARE; spin_unlock_bh(&br->lock); br_mrp_port_switchdev_set_state(p, state); rcu_assign_pointer(mrp->p_port, NULL); } p = rtnl_dereference(mrp->s_port); if (p) { spin_lock_bh(&br->lock); state = netif_running(br->dev) ? BR_STATE_FORWARDING : BR_STATE_DISABLED; p->state = state; p->flags &= ~BR_MRP_AWARE; spin_unlock_bh(&br->lock); br_mrp_port_switchdev_set_state(p, state); rcu_assign_pointer(mrp->s_port, NULL); } p = rtnl_dereference(mrp->i_port); if (p) { spin_lock_bh(&br->lock); state = netif_running(br->dev) ? BR_STATE_FORWARDING : BR_STATE_DISABLED; p->state = state; p->flags &= ~BR_MRP_AWARE; spin_unlock_bh(&br->lock); br_mrp_port_switchdev_set_state(p, state); rcu_assign_pointer(mrp->i_port, NULL); } hlist_del_rcu(&mrp->list); kfree_rcu(mrp, rcu); if (hlist_empty(&br->mrp_list)) br_del_frame(br, &mrp_frame_type); } /* Adds a new MRP instance. * note: called under rtnl_lock */ int br_mrp_add(struct net_bridge *br, struct br_mrp_instance *instance) { struct net_bridge_port *p; struct br_mrp *mrp; int err; /* If the ring exists, it is not possible to create another one with the * same ring_id */ mrp = br_mrp_find_id(br, instance->ring_id); if (mrp) return -EINVAL; if (!br_mrp_get_port(br, instance->p_ifindex) || !br_mrp_get_port(br, instance->s_ifindex)) return -EINVAL; /* It is not possible to have the same port part of multiple rings */ if (!br_mrp_unique_ifindex(br, instance->p_ifindex) || !br_mrp_unique_ifindex(br, instance->s_ifindex)) return -EINVAL; mrp = kzalloc_obj(*mrp); if (!mrp) return -ENOMEM; mrp->ring_id = instance->ring_id; mrp->prio = instance->prio; p = br_mrp_get_port(br, instance->p_ifindex); spin_lock_bh(&br->lock); p->state = BR_STATE_FORWARDING; p->flags |= BR_MRP_AWARE; spin_unlock_bh(&br->lock); rcu_assign_pointer(mrp->p_port, p); p = br_mrp_get_port(br, instance->s_ifindex); spin_lock_bh(&br->lock); p->state = BR_STATE_FORWARDING; p->flags |= BR_MRP_AWARE; spin_unlock_bh(&br->lock); rcu_assign_pointer(mrp->s_port, p); if (hlist_empty(&br->mrp_list)) br_add_frame(br, &mrp_frame_type); INIT_DELAYED_WORK(&mrp->test_work, br_mrp_test_work_expired); INIT_DELAYED_WORK(&mrp->in_test_work, br_mrp_in_test_work_expired); hlist_add_tail_rcu(&mrp->list, &br->mrp_list); err = br_mrp_switchdev_add(br, mrp); if (err) goto delete_mrp; return 0; delete_mrp: br_mrp_del_impl(br, mrp); return err; } /* Deletes the MRP instance from which the port is part of * note: called under rtnl_lock */ void br_mrp_port_del(struct net_bridge *br, struct net_bridge_port *p) { struct br_mrp *mrp = br_mrp_find_port(br, p); /* If the port is not part of a MRP instance just bail out */ if (!mrp) return; br_mrp_del_impl(br, mrp); } /* Deletes existing MRP instance based on ring_id * note: called under rtnl_lock */ int br_mrp_del(struct net_bridge *br, struct br_mrp_instance *instance) { struct br_mrp *mrp = br_mrp_find_id(br, instance->ring_id); if (!mrp) return -EINVAL; br_mrp_del_impl(br, mrp); return 0; } /* Set port state, port state can be forwarding, blocked or disabled * note: already called with rtnl_lock */ int br_mrp_set_port_state(struct net_bridge_port *p, enum br_mrp_port_state_type state) { u32 port_state; if (!p || !(p->flags & BR_MRP_AWARE)) return -EINVAL; spin_lock_bh(&p->br->lock); if (state == BR_MRP_PORT_STATE_FORWARDING) port_state = BR_STATE_FORWARDING; else port_state = BR_STATE_BLOCKING; p->state = port_state; spin_unlock_bh(&p->br->lock); br_mrp_port_switchdev_set_state(p, port_state); return 0; } /* Set port role, port role can be primary or secondary * note: already called with rtnl_lock */ int br_mrp_set_port_role(struct net_bridge_port *p, enum br_mrp_port_role_type role) { struct br_mrp *mrp; if (!p || !(p->flags & BR_MRP_AWARE)) return -EINVAL; mrp = br_mrp_find_port(p->br, p); if (!mrp) return -EINVAL; switch (role) { case BR_MRP_PORT_ROLE_PRIMARY: rcu_assign_pointer(mrp->p_port, p); break; case BR_MRP_PORT_ROLE_SECONDARY: rcu_assign_pointer(mrp->s_port, p); break; default: return -EINVAL; } br_mrp_port_switchdev_set_role(p, role); return 0; } /* Set ring state, ring state can be only Open or Closed * note: already called with rtnl_lock */ int br_mrp_set_ring_state(struct net_bridge *br, struct br_mrp_ring_state *state) { struct br_mrp *mrp = br_mrp_find_id(br, state->ring_id); if (!mrp) return -EINVAL; if (mrp->ring_state != state->ring_state) mrp->ring_transitions++; mrp->ring_state = state->ring_state; br_mrp_switchdev_set_ring_state(br, mrp, state->ring_state); return 0; } /* Set ring role, ring role can be only MRM(Media Redundancy Manager) or * MRC(Media Redundancy Client). * note: already called with rtnl_lock */ int br_mrp_set_ring_role(struct net_bridge *br, struct br_mrp_ring_role *role) { struct br_mrp *mrp = br_mrp_find_id(br, role->ring_id); enum br_mrp_hw_support support; if (!mrp) return -EINVAL; mrp->ring_role = role->ring_role; /* If there is an error just bailed out */ support = br_mrp_switchdev_set_ring_role(br, mrp, role->ring_role); if (support == BR_MRP_NONE) return -EOPNOTSUPP; /* Now detect if the HW actually applied the role or not. If the HW * applied the role it means that the SW will not to do those operations * anymore. For example if the role ir MRM then the HW will notify the * SW when ring is open, but if the is not pushed to the HW the SW will * need to detect when the ring is open */ mrp->ring_role_offloaded = support == BR_MRP_SW ? 0 : 1; return 0; } /* Start to generate or monitor MRP test frames, the frames are generated by * HW and if it fails, they are generated by the SW. * note: already called with rtnl_lock */ int br_mrp_start_test(struct net_bridge *br, struct br_mrp_start_test *test) { struct br_mrp *mrp = br_mrp_find_id(br, test->ring_id); enum br_mrp_hw_support support; if (!mrp) return -EINVAL; /* Try to push it to the HW and if it fails then continue with SW * implementation and if that also fails then return error. */ support = br_mrp_switchdev_send_ring_test(br, mrp, test->interval, test->max_miss, test->period, test->monitor); if (support == BR_MRP_NONE) return -EOPNOTSUPP; if (support == BR_MRP_HW) return 0; mrp->test_interval = test->interval; mrp->test_end = jiffies + usecs_to_jiffies(test->period); mrp->test_max_miss = test->max_miss; mrp->test_monitor = test->monitor; mrp->test_count_miss = 0; queue_delayed_work(system_percpu_wq, &mrp->test_work, usecs_to_jiffies(test->interval)); return 0; } /* Set in state, int state can be only Open or Closed * note: already called with rtnl_lock */ int br_mrp_set_in_state(struct net_bridge *br, struct br_mrp_in_state *state) { struct br_mrp *mrp = br_mrp_find_in_id(br, state->in_id); if (!mrp) return -EINVAL; if (mrp->in_state != state->in_state) mrp->in_transitions++; mrp->in_state = state->in_state; br_mrp_switchdev_set_in_state(br, mrp, state->in_state); return 0; } /* Set in role, in role can be only MIM(Media Interconnection Manager) or * MIC(Media Interconnection Client). * note: already called with rtnl_lock */ int br_mrp_set_in_role(struct net_bridge *br, struct br_mrp_in_role *role) { struct br_mrp *mrp = br_mrp_find_id(br, role->ring_id); enum br_mrp_hw_support support; struct net_bridge_port *p; if (!mrp) return -EINVAL; if (!br_mrp_get_port(br, role->i_ifindex)) return -EINVAL; if (role->in_role == BR_MRP_IN_ROLE_DISABLED) { u8 state; /* It is not allowed to disable a port that doesn't exist */ p = rtnl_dereference(mrp->i_port); if (!p) return -EINVAL; /* Stop the generating MRP_InTest frames */ cancel_delayed_work_sync(&mrp->in_test_work); br_mrp_switchdev_send_in_test(br, mrp, 0, 0, 0); /* Remove the port */ spin_lock_bh(&br->lock); state = netif_running(br->dev) ? BR_STATE_FORWARDING : BR_STATE_DISABLED; p->state = state; p->flags &= ~BR_MRP_AWARE; spin_unlock_bh(&br->lock); br_mrp_port_switchdev_set_state(p, state); rcu_assign_pointer(mrp->i_port, NULL); mrp->in_role = role->in_role; mrp->in_id = 0; return 0; } /* It is not possible to have the same port part of multiple rings */ if (!br_mrp_unique_ifindex(br, role->i_ifindex)) return -EINVAL; /* It is not allowed to set a different interconnect port if the mrp * instance has already one. First it needs to be disabled and after * that set the new port */ if (rcu_access_pointer(mrp->i_port)) return -EINVAL; p = br_mrp_get_port(br, role->i_ifindex); spin_lock_bh(&br->lock); p->state = BR_STATE_FORWARDING; p->flags |= BR_MRP_AWARE; spin_unlock_bh(&br->lock); rcu_assign_pointer(mrp->i_port, p); mrp->in_role = role->in_role; mrp->in_id = role->in_id; /* If there is an error just bailed out */ support = br_mrp_switchdev_set_in_role(br, mrp, role->in_id, role->ring_id, role->in_role); if (support == BR_MRP_NONE) return -EOPNOTSUPP; /* Now detect if the HW actually applied the role or not. If the HW * applied the role it means that the SW will not to do those operations * anymore. For example if the role is MIM then the HW will notify the * SW when interconnect ring is open, but if the is not pushed to the HW * the SW will need to detect when the interconnect ring is open. */ mrp->in_role_offloaded = support == BR_MRP_SW ? 0 : 1; return 0; } /* Start to generate MRP_InTest frames, the frames are generated by * HW and if it fails, they are generated by the SW. * note: already called with rtnl_lock */ int br_mrp_start_in_test(struct net_bridge *br, struct br_mrp_start_in_test *in_test) { struct br_mrp *mrp = br_mrp_find_in_id(br, in_test->in_id); enum br_mrp_hw_support support; if (!mrp) return -EINVAL; if (mrp->in_role != BR_MRP_IN_ROLE_MIM) return -EINVAL; /* Try to push it to the HW and if it fails then continue with SW * implementation and if that also fails then return error. */ support = br_mrp_switchdev_send_in_test(br, mrp, in_test->interval, in_test->max_miss, in_test->period); if (support == BR_MRP_NONE) return -EOPNOTSUPP; if (support == BR_MRP_HW) return 0; mrp->in_test_interval = in_test->interval; mrp->in_test_end = jiffies + usecs_to_jiffies(in_test->period); mrp->in_test_max_miss = in_test->max_miss; mrp->in_test_count_miss = 0; queue_delayed_work(system_percpu_wq, &mrp->in_test_work, usecs_to_jiffies(in_test->interval)); return 0; } /* Determine if the frame type is a ring frame */ static bool br_mrp_ring_frame(struct sk_buff *skb) { const struct br_mrp_tlv_hdr *hdr; struct br_mrp_tlv_hdr _hdr; hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); if (!hdr) return false; if (hdr->type == BR_MRP_TLV_HEADER_RING_TEST || hdr->type == BR_MRP_TLV_HEADER_RING_TOPO || hdr->type == BR_MRP_TLV_HEADER_RING_LINK_DOWN || hdr->type == BR_MRP_TLV_HEADER_RING_LINK_UP || hdr->type == BR_MRP_TLV_HEADER_OPTION) return true; return false; } /* Determine if the frame type is an interconnect frame */ static bool br_mrp_in_frame(struct sk_buff *skb) { const struct br_mrp_tlv_hdr *hdr; struct br_mrp_tlv_hdr _hdr; hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); if (!hdr) return false; if (hdr->type == BR_MRP_TLV_HEADER_IN_TEST || hdr->type == BR_MRP_TLV_HEADER_IN_TOPO || hdr->type == BR_MRP_TLV_HEADER_IN_LINK_DOWN || hdr->type == BR_MRP_TLV_HEADER_IN_LINK_UP || hdr->type == BR_MRP_TLV_HEADER_IN_LINK_STATUS) return true; return false; } /* Process only MRP Test frame. All the other MRP frames are processed by * userspace application * note: already called with rcu_read_lock */ static void br_mrp_mrm_process(struct br_mrp *mrp, struct net_bridge_port *port, struct sk_buff *skb) { const struct br_mrp_tlv_hdr *hdr; struct br_mrp_tlv_hdr _hdr; /* Each MRP header starts with a version field which is 16 bits. * Therefore skip the version and get directly the TLV header. */ hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); if (!hdr) return; if (hdr->type != BR_MRP_TLV_HEADER_RING_TEST) return; mrp->test_count_miss = 0; /* Notify the userspace that the ring is closed only when the ring is * not closed */ if (mrp->ring_state != BR_MRP_RING_STATE_CLOSED) br_mrp_ring_port_open(port->dev, false); } /* Determine if the test hdr has a better priority than the node */ static bool br_mrp_test_better_than_own(struct br_mrp *mrp, struct net_bridge *br, const struct br_mrp_ring_test_hdr *hdr) { u16 prio = be16_to_cpu(hdr->prio); if (prio < mrp->prio || (prio == mrp->prio && ether_addr_to_u64(hdr->sa) < ether_addr_to_u64(br->dev->dev_addr))) return true; return false; } /* Process only MRP Test frame. All the other MRP frames are processed by * userspace application * note: already called with rcu_read_lock */ static void br_mrp_mra_process(struct br_mrp *mrp, struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb) { const struct br_mrp_ring_test_hdr *test_hdr; struct br_mrp_ring_test_hdr _test_hdr; const struct br_mrp_tlv_hdr *hdr; struct br_mrp_tlv_hdr _hdr; /* Each MRP header starts with a version field which is 16 bits. * Therefore skip the version and get directly the TLV header. */ hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); if (!hdr) return; if (hdr->type != BR_MRP_TLV_HEADER_RING_TEST) return; test_hdr = skb_header_pointer(skb, sizeof(uint16_t) + sizeof(_hdr), sizeof(_test_hdr), &_test_hdr); if (!test_hdr) return; /* Only frames that have a better priority than the node will * clear the miss counter because otherwise the node will need to behave * as MRM. */ if (br_mrp_test_better_than_own(mrp, br, test_hdr)) mrp->test_count_miss = 0; } /* Process only MRP InTest frame. All the other MRP frames are processed by * userspace application * note: already called with rcu_read_lock */ static bool br_mrp_mim_process(struct br_mrp *mrp, struct net_bridge_port *port, struct sk_buff *skb) { const struct br_mrp_in_test_hdr *in_hdr; struct br_mrp_in_test_hdr _in_hdr; const struct br_mrp_tlv_hdr *hdr; struct br_mrp_tlv_hdr _hdr; /* Each MRP header starts with a version field which is 16 bits. * Therefore skip the version and get directly the TLV header. */ hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); if (!hdr) return false; /* The check for InTest frame type was already done */ in_hdr = skb_header_pointer(skb, sizeof(uint16_t) + sizeof(_hdr), sizeof(_in_hdr), &_in_hdr); if (!in_hdr) return false; /* It needs to process only it's own InTest frames. */ if (mrp->in_id != ntohs(in_hdr->id)) return false; mrp->in_test_count_miss = 0; /* Notify the userspace that the ring is closed only when the ring is * not closed */ if (mrp->in_state != BR_MRP_IN_STATE_CLOSED) br_mrp_in_port_open(port->dev, false); return true; } /* Get the MRP frame type * note: already called with rcu_read_lock */ static u8 br_mrp_get_frame_type(struct sk_buff *skb) { const struct br_mrp_tlv_hdr *hdr; struct br_mrp_tlv_hdr _hdr; /* Each MRP header starts with a version field which is 16 bits. * Therefore skip the version and get directly the TLV header. */ hdr = skb_header_pointer(skb, sizeof(uint16_t), sizeof(_hdr), &_hdr); if (!hdr) return 0xff; return hdr->type; } static bool br_mrp_mrm_behaviour(struct br_mrp *mrp) { if (mrp->ring_role == BR_MRP_RING_ROLE_MRM || (mrp->ring_role == BR_MRP_RING_ROLE_MRA && !mrp->test_monitor)) return true; return false; } static bool br_mrp_mrc_behaviour(struct br_mrp *mrp) { if (mrp->ring_role == BR_MRP_RING_ROLE_MRC || (mrp->ring_role == BR_MRP_RING_ROLE_MRA && mrp->test_monitor)) return true; return false; } /* This will just forward the frame to the other mrp ring ports, depending on * the frame type, ring role and interconnect role * note: already called with rcu_read_lock */ static int br_mrp_rcv(struct net_bridge_port *p, struct sk_buff *skb, struct net_device *dev) { struct net_bridge_port *p_port, *s_port, *i_port = NULL; struct net_bridge_port *p_dst, *s_dst, *i_dst = NULL; struct net_bridge *br; struct br_mrp *mrp; /* If port is disabled don't accept any frames */ if (p->state == BR_STATE_DISABLED) return 0; br = p->br; mrp = br_mrp_find_port(br, p); if (unlikely(!mrp)) return 0; p_port = rcu_dereference(mrp->p_port); if (!p_port) return 0; p_dst = p_port; s_port = rcu_dereference(mrp->s_port); if (!s_port) return 0; s_dst = s_port; /* If the frame is a ring frame then it is not required to check the * interconnect role and ports to process or forward the frame */ if (br_mrp_ring_frame(skb)) { /* If the role is MRM then don't forward the frames */ if (mrp->ring_role == BR_MRP_RING_ROLE_MRM) { br_mrp_mrm_process(mrp, p, skb); goto no_forward; } /* If the role is MRA then don't forward the frames if it * behaves as MRM node */ if (mrp->ring_role == BR_MRP_RING_ROLE_MRA) { if (!mrp->test_monitor) { br_mrp_mrm_process(mrp, p, skb); goto no_forward; } br_mrp_mra_process(mrp, br, p, skb); } goto forward; } if (br_mrp_in_frame(skb)) { u8 in_type = br_mrp_get_frame_type(skb); i_port = rcu_dereference(mrp->i_port); i_dst = i_port; /* If the ring port is in block state it should not forward * In_Test frames */ if (br_mrp_is_ring_port(p_port, s_port, p) && p->state == BR_STATE_BLOCKING && in_type == BR_MRP_TLV_HEADER_IN_TEST) goto no_forward; /* Nodes that behaves as MRM needs to stop forwarding the * frames in case the ring is closed, otherwise will be a loop. * In this case the frame is no forward between the ring ports. */ if (br_mrp_mrm_behaviour(mrp) && br_mrp_is_ring_port(p_port, s_port, p) && (s_port->state != BR_STATE_FORWARDING || p_port->state != BR_STATE_FORWARDING)) { p_dst = NULL; s_dst = NULL; } /* A node that behaves as MRC and doesn't have a interconnect * role then it should forward all frames between the ring ports * because it doesn't have an interconnect port */ if (br_mrp_mrc_behaviour(mrp) && mrp->in_role == BR_MRP_IN_ROLE_DISABLED) goto forward; if (mrp->in_role == BR_MRP_IN_ROLE_MIM) { if (in_type == BR_MRP_TLV_HEADER_IN_TEST) { /* MIM should not forward it's own InTest * frames */ if (br_mrp_mim_process(mrp, p, skb)) { goto no_forward; } else { if (br_mrp_is_ring_port(p_port, s_port, p)) i_dst = NULL; if (br_mrp_is_in_port(i_port, p)) goto no_forward; } } else { /* MIM should forward IntLinkChange/Status and * IntTopoChange between ring ports but MIM * should not forward IntLinkChange/Status and * IntTopoChange if the frame was received at * the interconnect port */ if (br_mrp_is_ring_port(p_port, s_port, p)) i_dst = NULL; if (br_mrp_is_in_port(i_port, p)) goto no_forward; } } if (mrp->in_role == BR_MRP_IN_ROLE_MIC) { /* MIC should forward InTest frames on all ports * regardless of the received port */ if (in_type == BR_MRP_TLV_HEADER_IN_TEST) goto forward; /* MIC should forward IntLinkChange frames only if they * are received on ring ports to all the ports */ if (br_mrp_is_ring_port(p_port, s_port, p) && (in_type == BR_MRP_TLV_HEADER_IN_LINK_UP || in_type == BR_MRP_TLV_HEADER_IN_LINK_DOWN)) goto forward; /* MIC should forward IntLinkStatus frames only to * interconnect port if it was received on a ring port. * If it is received on interconnect port then, it * should be forward on both ring ports */ if (br_mrp_is_ring_port(p_port, s_port, p) && in_type == BR_MRP_TLV_HEADER_IN_LINK_STATUS) { p_dst = NULL; s_dst = NULL; } /* Should forward the InTopo frames only between the * ring ports */ if (in_type == BR_MRP_TLV_HEADER_IN_TOPO) { i_dst = NULL; goto forward; } /* In all the other cases don't forward the frames */ goto no_forward; } } forward: if (p_dst) br_forward(p_dst, skb, true, false); if (s_dst) br_forward(s_dst, skb, true, false); if (i_dst) br_forward(i_dst, skb, true, false); no_forward: return 1; } /* Check if the frame was received on a port that is part of MRP ring * and if the frame has MRP eth. In that case process the frame otherwise do * normal forwarding. * note: already called with rcu_read_lock */ static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb) { /* If there is no MRP instance do normal forwarding */ if (likely(!(p->flags & BR_MRP_AWARE))) goto out; return br_mrp_rcv(p, skb, p->dev); out: return 0; } bool br_mrp_enabled(struct net_bridge *br) { return !hlist_empty(&br->mrp_list); } |
| 2306 2338 2339 2336 2313 25 25 2312 2301 25 2277 2277 25 2301 2299 2301 2304 2305 2300 2305 2083 1389 2245 459 2303 27 2019 876 65 2013 395 1995 788 1041 1041 966 82 1038 504 736 738 785 6 1 270 964 82 306 755 28 1013 86 18 67 5 55 18 66 3 26 37 2343 2350 2313 2309 2304 2311 2308 2310 121 2242 64 2306 2300 2303 2301 2304 2306 2306 359 2303 2306 2306 355 2337 2342 2338 2336 25 2257 58 2340 2315 2336 2344 2340 2336 2284 2306 2303 2299 2629 2617 2593 2630 2336 75 75 1 74 1 56 56 56 42 35 2 10 52 75 75 74 75 75 74 1 118 62 56 56 56 56 56 56 100 2341 2353 1013 2390 2640 2640 3 2641 2636 2642 2639 5 5 2401 121 46 77 42 2 36 1 64 1 13 101 28 75 1 118 46 46 1 1 2301 2305 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/usb/core/driver.c - most of the driver model stuff for usb * * (C) Copyright 2005 Greg Kroah-Hartman <gregkh@suse.de> * * based on drivers/usb/usb.c which had the following copyrights: * (C) Copyright Linus Torvalds 1999 * (C) Copyright Johannes Erdfelt 1999-2001 * (C) Copyright Andreas Gal 1999 * (C) Copyright Gregory P. Smith 1999 * (C) Copyright Deti Fliegl 1999 (new USB architecture) * (C) Copyright Randy Dunlap 2000 * (C) Copyright David Brownell 2000-2004 * (C) Copyright Yggdrasil Computing, Inc. 2000 * (usb_device_id matching changes by Adam J. Richter) * (C) Copyright Greg Kroah-Hartman 2002-2003 * * Released under the GPLv2 only. * * NOTE! This is not actually a driver at all, rather this is * just a collection of helper routines that implement the * matching, probing, releasing, suspending and resuming for * real drivers. * */ #include <linux/device.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/usb.h> #include <linux/usb/quirks.h> #include <linux/usb/hcd.h> #include "usb.h" /* * Adds a new dynamic USBdevice ID to this driver, * and cause the driver to probe for all devices again. */ ssize_t usb_store_new_id(struct usb_dynids *dynids, const struct usb_device_id *id_table, struct device_driver *driver, const char *buf, size_t count) { struct usb_dynid *dynid; u32 idVendor = 0; u32 idProduct = 0; unsigned int bInterfaceClass = 0; u32 refVendor, refProduct; int fields = 0; int retval = 0; fields = sscanf(buf, "%x %x %x %x %x", &idVendor, &idProduct, &bInterfaceClass, &refVendor, &refProduct); if (fields < 2) return -EINVAL; dynid = kzalloc_obj(*dynid); if (!dynid) return -ENOMEM; INIT_LIST_HEAD(&dynid->node); dynid->id.idVendor = idVendor; dynid->id.idProduct = idProduct; dynid->id.match_flags = USB_DEVICE_ID_MATCH_DEVICE; if (fields > 2 && bInterfaceClass) { if (bInterfaceClass > 255) { retval = -EINVAL; goto fail; } dynid->id.bInterfaceClass = (u8)bInterfaceClass; dynid->id.match_flags |= USB_DEVICE_ID_MATCH_INT_CLASS; } if (fields > 4) { const struct usb_device_id *id = id_table; if (!id) { retval = -ENODEV; goto fail; } for (; id->match_flags; id++) if (id->idVendor == refVendor && id->idProduct == refProduct) break; if (id->match_flags) { dynid->id.driver_info = id->driver_info; } else { retval = -ENODEV; goto fail; } } mutex_lock(&usb_dynids_lock); list_add_tail(&dynid->node, &dynids->list); mutex_unlock(&usb_dynids_lock); retval = driver_attach(driver); if (retval) return retval; return count; fail: kfree(dynid); return retval; } EXPORT_SYMBOL_GPL(usb_store_new_id); ssize_t usb_show_dynids(struct usb_dynids *dynids, char *buf) { struct usb_dynid *dynid; size_t count = 0; guard(mutex)(&usb_dynids_lock); list_for_each_entry(dynid, &dynids->list, node) if (dynid->id.bInterfaceClass != 0) count += sysfs_emit_at(buf, count, "%04x %04x %02x\n", dynid->id.idVendor, dynid->id.idProduct, dynid->id.bInterfaceClass); else count += sysfs_emit_at(buf, count, "%04x %04x\n", dynid->id.idVendor, dynid->id.idProduct); return count; } EXPORT_SYMBOL_GPL(usb_show_dynids); static ssize_t new_id_show(struct device_driver *driver, char *buf) { struct usb_driver *usb_drv = to_usb_driver(driver); return usb_show_dynids(&usb_drv->dynids, buf); } static ssize_t new_id_store(struct device_driver *driver, const char *buf, size_t count) { struct usb_driver *usb_drv = to_usb_driver(driver); return usb_store_new_id(&usb_drv->dynids, usb_drv->id_table, driver, buf, count); } static DRIVER_ATTR_RW(new_id); /* * Remove a USB device ID from this driver */ static ssize_t remove_id_store(struct device_driver *driver, const char *buf, size_t count) { struct usb_dynid *dynid, *n; struct usb_driver *usb_driver = to_usb_driver(driver); u32 idVendor; u32 idProduct; int fields; fields = sscanf(buf, "%x %x", &idVendor, &idProduct); if (fields < 2) return -EINVAL; guard(mutex)(&usb_dynids_lock); list_for_each_entry_safe(dynid, n, &usb_driver->dynids.list, node) { struct usb_device_id *id = &dynid->id; if ((id->idVendor == idVendor) && (id->idProduct == idProduct)) { list_del(&dynid->node); kfree(dynid); break; } } return count; } static ssize_t remove_id_show(struct device_driver *driver, char *buf) { return new_id_show(driver, buf); } static DRIVER_ATTR_RW(remove_id); static int usb_create_newid_files(struct usb_driver *usb_drv) { int error = 0; if (usb_drv->no_dynamic_id) goto exit; if (usb_drv->probe != NULL) { error = driver_create_file(&usb_drv->driver, &driver_attr_new_id); if (error == 0) { error = driver_create_file(&usb_drv->driver, &driver_attr_remove_id); if (error) driver_remove_file(&usb_drv->driver, &driver_attr_new_id); } } exit: return error; } static void usb_remove_newid_files(struct usb_driver *usb_drv) { if (usb_drv->no_dynamic_id) return; if (usb_drv->probe != NULL) { driver_remove_file(&usb_drv->driver, &driver_attr_remove_id); driver_remove_file(&usb_drv->driver, &driver_attr_new_id); } } static void usb_free_dynids(struct usb_driver *usb_drv) { struct usb_dynid *dynid, *n; guard(mutex)(&usb_dynids_lock); list_for_each_entry_safe(dynid, n, &usb_drv->dynids.list, node) { list_del(&dynid->node); kfree(dynid); } } static const struct usb_device_id *usb_match_dynamic_id(struct usb_interface *intf, const struct usb_driver *drv) { struct usb_dynid *dynid; guard(mutex)(&usb_dynids_lock); list_for_each_entry(dynid, &drv->dynids.list, node) { if (usb_match_one_id(intf, &dynid->id)) { return &dynid->id; } } return NULL; } /* called from driver core with dev locked */ static int usb_probe_device(struct device *dev) { struct usb_device_driver *udriver = to_usb_device_driver(dev->driver); struct usb_device *udev = to_usb_device(dev); int error = 0; dev_dbg(dev, "%s\n", __func__); /* TODO: Add real matching code */ /* The device should always appear to be in use * unless the driver supports autosuspend. */ if (!udriver->supports_autosuspend) error = usb_autoresume_device(udev); if (error) return error; if (udriver->generic_subclass) error = usb_generic_driver_probe(udev); if (error) return error; /* Probe the USB device with the driver in hand, but only * defer to a generic driver in case the current USB * device driver has an id_table or a match function; i.e., * when the device driver was explicitly matched against * a device. * * If the device driver does not have either of these, * then we assume that it can bind to any device and is * not truly a more specialized/non-generic driver, so a * return value of -ENODEV should not force the device * to be handled by the generic USB driver, as there * can still be another, more specialized, device driver. * * This accommodates the usbip driver. * * TODO: What if, in the future, there are multiple * specialized USB device drivers for a particular device? * In such cases, there is a need to try all matching * specialised device drivers prior to setting the * use_generic_driver bit. */ if (udriver->probe) error = udriver->probe(udev); else if (!udriver->generic_subclass) error = -EINVAL; if (error == -ENODEV && udriver != &usb_generic_driver && (udriver->id_table || udriver->match)) { udev->use_generic_driver = 1; return -EPROBE_DEFER; } return error; } /* called from driver core with dev locked */ static int usb_unbind_device(struct device *dev) { struct usb_device *udev = to_usb_device(dev); struct usb_device_driver *udriver = to_usb_device_driver(dev->driver); if (udriver->disconnect) udriver->disconnect(udev); if (udriver->generic_subclass) usb_generic_driver_disconnect(udev); if (!udriver->supports_autosuspend) usb_autosuspend_device(udev); return 0; } /* called from driver core with dev locked */ static int usb_probe_interface(struct device *dev) { struct usb_driver *driver = to_usb_driver(dev->driver); struct usb_interface *intf = to_usb_interface(dev); struct usb_device *udev = interface_to_usbdev(intf); const struct usb_device_id *id; int error = -ENODEV; int lpm_disable_error = -ENODEV; dev_dbg(dev, "%s\n", __func__); intf->needs_binding = 0; if (usb_device_is_owned(udev)) return error; if (udev->authorized == 0) { dev_info(&intf->dev, "Device is not authorized for usage\n"); return error; } else if (intf->authorized == 0) { dev_info(&intf->dev, "Interface %d is not authorized for usage\n", intf->altsetting->desc.bInterfaceNumber); return error; } id = usb_match_dynamic_id(intf, driver); if (!id) id = usb_match_id(intf, driver->id_table); if (!id) return error; dev_dbg(dev, "%s - got id\n", __func__); error = usb_autoresume_device(udev); if (error) return error; intf->condition = USB_INTERFACE_BINDING; /* Probed interfaces are initially active. They are * runtime-PM-enabled only if the driver has autosuspend support. * They are sensitive to their children's power states. */ pm_runtime_set_active(dev); pm_suspend_ignore_children(dev, false); if (driver->supports_autosuspend) pm_runtime_enable(dev); /* If the new driver doesn't allow hub-initiated LPM, and we can't * disable hub-initiated LPM, then fail the probe. * * Otherwise, leaving LPM enabled should be harmless, because the * endpoint intervals should remain the same, and the U1/U2 timeouts * should remain the same. * * If we need to install alt setting 0 before probe, or another alt * setting during probe, that should also be fine. usb_set_interface() * will attempt to disable LPM, and fail if it can't disable it. */ if (driver->disable_hub_initiated_lpm) { lpm_disable_error = usb_unlocked_disable_lpm(udev); if (lpm_disable_error) { dev_err(&intf->dev, "%s Failed to disable LPM for driver %s\n", __func__, driver->name); error = lpm_disable_error; goto err; } } /* Carry out a deferred switch to altsetting 0 */ if (intf->needs_altsetting0) { error = usb_set_interface(udev, intf->altsetting[0]. desc.bInterfaceNumber, 0); if (error < 0) goto err; intf->needs_altsetting0 = 0; } error = driver->probe(intf, id); if (error) goto err; intf->condition = USB_INTERFACE_BOUND; /* If the LPM disable succeeded, balance the ref counts. */ if (!lpm_disable_error) usb_unlocked_enable_lpm(udev); usb_autosuspend_device(udev); return error; err: usb_set_intfdata(intf, NULL); intf->needs_remote_wakeup = 0; intf->condition = USB_INTERFACE_UNBOUND; /* If the LPM disable succeeded, balance the ref counts. */ if (!lpm_disable_error) usb_unlocked_enable_lpm(udev); /* Unbound interfaces are always runtime-PM-disabled and -suspended */ if (driver->supports_autosuspend) pm_runtime_disable(dev); pm_runtime_set_suspended(dev); usb_autosuspend_device(udev); return error; } /* called from driver core with dev locked */ static int usb_unbind_interface(struct device *dev) { struct usb_driver *driver = to_usb_driver(dev->driver); struct usb_interface *intf = to_usb_interface(dev); struct usb_host_endpoint *ep, **eps = NULL; struct usb_device *udev; int i, j, error, r; int lpm_disable_error = -ENODEV; intf->condition = USB_INTERFACE_UNBINDING; /* Autoresume for set_interface call below */ udev = interface_to_usbdev(intf); error = usb_autoresume_device(udev); /* If hub-initiated LPM policy may change, attempt to disable LPM until * the driver is unbound. If LPM isn't disabled, that's fine because it * wouldn't be enabled unless all the bound interfaces supported * hub-initiated LPM. */ if (driver->disable_hub_initiated_lpm) lpm_disable_error = usb_unlocked_disable_lpm(udev); /* * Terminate all URBs for this interface unless the driver * supports "soft" unbinding and the device is still present. */ if (!driver->soft_unbind || udev->state == USB_STATE_NOTATTACHED) usb_disable_interface(udev, intf, false); driver->disconnect(intf); /* Free streams */ for (i = 0, j = 0; i < intf->cur_altsetting->desc.bNumEndpoints; i++) { ep = &intf->cur_altsetting->endpoint[i]; if (ep->streams == 0) continue; if (j == 0) { eps = kmalloc_array(USB_MAXENDPOINTS, sizeof(void *), GFP_KERNEL); if (!eps) break; } eps[j++] = ep; } if (j) { usb_free_streams(intf, eps, j, GFP_KERNEL); kfree(eps); } /* Reset other interface state. * We cannot do a Set-Interface if the device is suspended or * if it is prepared for a system sleep (since installing a new * altsetting means creating new endpoint device entries). * When either of these happens, defer the Set-Interface. */ if (intf->cur_altsetting->desc.bAlternateSetting == 0) { /* Already in altsetting 0 so skip Set-Interface. * Just re-enable it without affecting the endpoint toggles. */ usb_enable_interface(udev, intf, false); } else if (!error && !intf->dev.power.is_prepared) { r = usb_set_interface(udev, intf->altsetting[0]. desc.bInterfaceNumber, 0); if (r < 0) intf->needs_altsetting0 = 1; } else { intf->needs_altsetting0 = 1; } usb_set_intfdata(intf, NULL); intf->condition = USB_INTERFACE_UNBOUND; intf->needs_remote_wakeup = 0; /* Attempt to re-enable USB3 LPM, if the disable succeeded. */ if (!lpm_disable_error) usb_unlocked_enable_lpm(udev); /* Unbound interfaces are always runtime-PM-disabled and -suspended */ if (driver->supports_autosuspend) pm_runtime_disable(dev); pm_runtime_set_suspended(dev); if (!error) usb_autosuspend_device(udev); return 0; } static void usb_shutdown_interface(struct device *dev) { struct usb_interface *intf = to_usb_interface(dev); struct usb_driver *driver; if (!dev->driver) return; driver = to_usb_driver(dev->driver); if (driver->shutdown) driver->shutdown(intf); } /** * usb_driver_claim_interface - bind a driver to an interface * @driver: the driver to be bound * @iface: the interface to which it will be bound; must be in the * usb device's active configuration * @data: driver data associated with that interface * * This is used by usb device drivers that need to claim more than one * interface on a device when probing (audio and acm are current examples). * No device driver should directly modify internal usb_interface or * usb_device structure members. * * Callers must own the device lock, so driver probe() entries don't need * extra locking, but other call contexts may need to explicitly claim that * lock. * * Return: 0 on success. */ int usb_driver_claim_interface(struct usb_driver *driver, struct usb_interface *iface, void *data) { struct device *dev; int retval = 0; if (!iface) return -ENODEV; dev = &iface->dev; if (dev->driver) return -EBUSY; /* reject claim if interface is not authorized */ if (!iface->authorized) return -ENODEV; dev->driver = &driver->driver; usb_set_intfdata(iface, data); iface->needs_binding = 0; iface->condition = USB_INTERFACE_BOUND; /* Claimed interfaces are initially inactive (suspended) and * runtime-PM-enabled, but only if the driver has autosuspend * support. Otherwise they are marked active, to prevent the * device from being autosuspended, but left disabled. In either * case they are sensitive to their children's power states. */ pm_suspend_ignore_children(dev, false); if (driver->supports_autosuspend) pm_runtime_enable(dev); else pm_runtime_set_active(dev); /* if interface was already added, bind now; else let * the future device_add() bind it, bypassing probe() */ if (device_is_registered(dev)) retval = device_bind_driver(dev); if (retval) { dev->driver = NULL; usb_set_intfdata(iface, NULL); iface->needs_remote_wakeup = 0; iface->condition = USB_INTERFACE_UNBOUND; /* * Unbound interfaces are always runtime-PM-disabled * and runtime-PM-suspended */ if (driver->supports_autosuspend) pm_runtime_disable(dev); pm_runtime_set_suspended(dev); } return retval; } EXPORT_SYMBOL_GPL(usb_driver_claim_interface); /** * usb_driver_release_interface - unbind a driver from an interface * @driver: the driver to be unbound * @iface: the interface from which it will be unbound * * This can be used by drivers to release an interface without waiting * for their disconnect() methods to be called. In typical cases this * also causes the driver disconnect() method to be called. * * This call is synchronous, and may not be used in an interrupt context. * Callers must own the device lock, so driver disconnect() entries don't * need extra locking, but other call contexts may need to explicitly claim * that lock. */ void usb_driver_release_interface(struct usb_driver *driver, struct usb_interface *iface) { struct device *dev = &iface->dev; /* this should never happen, don't release something that's not ours */ if (!dev->driver || dev->driver != &driver->driver) return; /* don't release from within disconnect() */ if (iface->condition != USB_INTERFACE_BOUND) return; iface->condition = USB_INTERFACE_UNBINDING; /* Release via the driver core only if the interface * has already been registered */ if (device_is_registered(dev)) { device_release_driver(dev); } else { device_lock(dev); usb_unbind_interface(dev); dev->driver = NULL; device_unlock(dev); } } EXPORT_SYMBOL_GPL(usb_driver_release_interface); /* returns 0 if no match, 1 if match */ int usb_match_device(struct usb_device *dev, const struct usb_device_id *id) { if ((id->match_flags & USB_DEVICE_ID_MATCH_VENDOR) && id->idVendor != le16_to_cpu(dev->descriptor.idVendor)) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_PRODUCT) && id->idProduct != le16_to_cpu(dev->descriptor.idProduct)) return 0; /* No need to test id->bcdDevice_lo != 0, since 0 is never greater than any unsigned number. */ if ((id->match_flags & USB_DEVICE_ID_MATCH_DEV_LO) && (id->bcdDevice_lo > le16_to_cpu(dev->descriptor.bcdDevice))) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_DEV_HI) && (id->bcdDevice_hi < le16_to_cpu(dev->descriptor.bcdDevice))) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_DEV_CLASS) && (id->bDeviceClass != dev->descriptor.bDeviceClass)) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_DEV_SUBCLASS) && (id->bDeviceSubClass != dev->descriptor.bDeviceSubClass)) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_DEV_PROTOCOL) && (id->bDeviceProtocol != dev->descriptor.bDeviceProtocol)) return 0; return 1; } /* returns 0 if no match, 1 if match */ int usb_match_one_id_intf(struct usb_device *dev, struct usb_host_interface *intf, const struct usb_device_id *id) { /* The interface class, subclass, protocol and number should never be * checked for a match if the device class is Vendor Specific, * unless the match record specifies the Vendor ID. */ if (dev->descriptor.bDeviceClass == USB_CLASS_VENDOR_SPEC && !(id->match_flags & USB_DEVICE_ID_MATCH_VENDOR) && (id->match_flags & (USB_DEVICE_ID_MATCH_INT_CLASS | USB_DEVICE_ID_MATCH_INT_SUBCLASS | USB_DEVICE_ID_MATCH_INT_PROTOCOL | USB_DEVICE_ID_MATCH_INT_NUMBER))) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_INT_CLASS) && (id->bInterfaceClass != intf->desc.bInterfaceClass)) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_INT_SUBCLASS) && (id->bInterfaceSubClass != intf->desc.bInterfaceSubClass)) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_INT_PROTOCOL) && (id->bInterfaceProtocol != intf->desc.bInterfaceProtocol)) return 0; if ((id->match_flags & USB_DEVICE_ID_MATCH_INT_NUMBER) && (id->bInterfaceNumber != intf->desc.bInterfaceNumber)) return 0; return 1; } /* returns 0 if no match, 1 if match */ int usb_match_one_id(struct usb_interface *interface, const struct usb_device_id *id) { struct usb_host_interface *intf; struct usb_device *dev; /* proc_connectinfo in devio.c may call us with id == NULL. */ if (id == NULL) return 0; intf = interface->cur_altsetting; dev = interface_to_usbdev(interface); if (!usb_match_device(dev, id)) return 0; return usb_match_one_id_intf(dev, intf, id); } EXPORT_SYMBOL_GPL(usb_match_one_id); /** * usb_match_id - find first usb_device_id matching device or interface * @interface: the interface of interest * @id: array of usb_device_id structures, terminated by zero entry * * usb_match_id searches an array of usb_device_id's and returns * the first one matching the device or interface, or null. * This is used when binding (or rebinding) a driver to an interface. * Most USB device drivers will use this indirectly, through the usb core, * but some layered driver frameworks use it directly. * These device tables are exported with MODULE_DEVICE_TABLE, through * modutils, to support the driver loading functionality of USB hotplugging. * * Return: The first matching usb_device_id, or %NULL. * * What Matches: * * The "match_flags" element in a usb_device_id controls which * members are used. If the corresponding bit is set, the * value in the device_id must match its corresponding member * in the device or interface descriptor, or else the device_id * does not match. * * "driver_info" is normally used only by device drivers, * but you can create a wildcard "matches anything" usb_device_id * as a driver's "modules.usbmap" entry if you provide an id with * only a nonzero "driver_info" field. If you do this, the USB device * driver's probe() routine should use additional intelligence to * decide whether to bind to the specified interface. * * What Makes Good usb_device_id Tables: * * The match algorithm is very simple, so that intelligence in * driver selection must come from smart driver id records. * Unless you have good reasons to use another selection policy, * provide match elements only in related groups, and order match * specifiers from specific to general. Use the macros provided * for that purpose if you can. * * The most specific match specifiers use device descriptor * data. These are commonly used with product-specific matches; * the USB_DEVICE macro lets you provide vendor and product IDs, * and you can also match against ranges of product revisions. * These are widely used for devices with application or vendor * specific bDeviceClass values. * * Matches based on device class/subclass/protocol specifications * are slightly more general; use the USB_DEVICE_INFO macro, or * its siblings. These are used with single-function devices * where bDeviceClass doesn't specify that each interface has * its own class. * * Matches based on interface class/subclass/protocol are the * most general; they let drivers bind to any interface on a * multiple-function device. Use the USB_INTERFACE_INFO * macro, or its siblings, to match class-per-interface style * devices (as recorded in bInterfaceClass). * * Note that an entry created by USB_INTERFACE_INFO won't match * any interface if the device class is set to Vendor-Specific. * This is deliberate; according to the USB spec the meanings of * the interface class/subclass/protocol for these devices are also * vendor-specific, and hence matching against a standard product * class wouldn't work anyway. If you really want to use an * interface-based match for such a device, create a match record * that also specifies the vendor ID. (Unforunately there isn't a * standard macro for creating records like this.) * * Within those groups, remember that not all combinations are * meaningful. For example, don't give a product version range * without vendor and product IDs; or specify a protocol without * its associated class and subclass. */ const struct usb_device_id *usb_match_id(struct usb_interface *interface, const struct usb_device_id *id) { /* proc_connectinfo in devio.c may call us with id == NULL. */ if (id == NULL) return NULL; /* It is important to check that id->driver_info is nonzero, since an entry that is all zeroes except for a nonzero id->driver_info is the way to create an entry that indicates that the driver want to examine every device and interface. */ for (; id->idVendor || id->idProduct || id->bDeviceClass || id->bInterfaceClass || id->driver_info; id++) { if (usb_match_one_id(interface, id)) return id; } return NULL; } EXPORT_SYMBOL_GPL(usb_match_id); const struct usb_device_id *usb_device_match_id(struct usb_device *udev, const struct usb_device_id *id) { if (!id) return NULL; for (; id->idVendor || id->idProduct ; id++) { if (usb_match_device(udev, id)) return id; } return NULL; } EXPORT_SYMBOL_GPL(usb_device_match_id); bool usb_driver_applicable(struct usb_device *udev, const struct usb_device_driver *udrv) { if (udrv->id_table && udrv->match) return usb_device_match_id(udev, udrv->id_table) != NULL && udrv->match(udev); if (udrv->id_table) return usb_device_match_id(udev, udrv->id_table) != NULL; if (udrv->match) return udrv->match(udev); return false; } static int usb_device_match(struct device *dev, const struct device_driver *drv) { /* devices and interfaces are handled separately */ if (is_usb_device(dev)) { struct usb_device *udev; const struct usb_device_driver *udrv; /* interface drivers never match devices */ if (!is_usb_device_driver(drv)) return 0; udev = to_usb_device(dev); udrv = to_usb_device_driver(drv); /* If the device driver under consideration does not have a * id_table or a match function, then let the driver's probe * function decide. */ if (!udrv->id_table && !udrv->match) return 1; return usb_driver_applicable(udev, udrv); } else if (is_usb_interface(dev)) { struct usb_interface *intf; const struct usb_driver *usb_drv; const struct usb_device_id *id; /* device drivers never match interfaces */ if (is_usb_device_driver(drv)) return 0; intf = to_usb_interface(dev); usb_drv = to_usb_driver(drv); id = usb_match_id(intf, usb_drv->id_table); if (id) return 1; id = usb_match_dynamic_id(intf, usb_drv); if (id) return 1; } return 0; } static int usb_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct usb_device *usb_dev; if (is_usb_device(dev)) { usb_dev = to_usb_device(dev); } else if (is_usb_interface(dev)) { const struct usb_interface *intf = to_usb_interface(dev); usb_dev = interface_to_usbdev(intf); } else { return 0; } if (usb_dev->devnum < 0) { /* driver is often null here; dev_dbg() would oops */ pr_debug("usb %s: already deleted?\n", dev_name(dev)); return -ENODEV; } if (!usb_dev->bus) { pr_debug("usb %s: bus removed?\n", dev_name(dev)); return -ENODEV; } /* per-device configurations are common */ if (add_uevent_var(env, "PRODUCT=%x/%x/%x", le16_to_cpu(usb_dev->descriptor.idVendor), le16_to_cpu(usb_dev->descriptor.idProduct), le16_to_cpu(usb_dev->descriptor.bcdDevice))) return -ENOMEM; /* class-based driver binding models */ if (add_uevent_var(env, "TYPE=%d/%d/%d", usb_dev->descriptor.bDeviceClass, usb_dev->descriptor.bDeviceSubClass, usb_dev->descriptor.bDeviceProtocol)) return -ENOMEM; return 0; } static int __usb_bus_reprobe_drivers(struct device *dev, void *data) { struct usb_device_driver *new_udriver = data; struct usb_device *udev; int ret; /* Don't reprobe if current driver isn't usb_generic_driver */ if (dev->driver != &usb_generic_driver.driver) return 0; udev = to_usb_device(dev); if (!usb_driver_applicable(udev, new_udriver)) return 0; ret = device_reprobe(dev); if (ret && ret != -EPROBE_DEFER) dev_err(dev, "Failed to reprobe device (error %d)\n", ret); return 0; } bool is_usb_device_driver(const struct device_driver *drv) { return drv->probe == usb_probe_device; } /** * usb_register_device_driver - register a USB device (not interface) driver * @new_udriver: USB operations for the device driver * @owner: module owner of this driver. * * Registers a USB device driver with the USB core. The list of * unattached devices will be rescanned whenever a new driver is * added, allowing the new driver to attach to any recognized devices. * * Return: A negative error code on failure and 0 on success. */ int usb_register_device_driver(struct usb_device_driver *new_udriver, struct module *owner) { int retval = 0; if (usb_disabled()) return -ENODEV; new_udriver->driver.name = new_udriver->name; new_udriver->driver.bus = &usb_bus_type; new_udriver->driver.probe = usb_probe_device; new_udriver->driver.remove = usb_unbind_device; new_udriver->driver.owner = owner; new_udriver->driver.dev_groups = new_udriver->dev_groups; retval = driver_register(&new_udriver->driver); if (!retval) { pr_info("%s: registered new device driver %s\n", usbcore_name, new_udriver->name); /* * Check whether any device could be better served with * this new driver */ bus_for_each_dev(&usb_bus_type, NULL, new_udriver, __usb_bus_reprobe_drivers); } else { pr_err("%s: error %d registering device driver %s\n", usbcore_name, retval, new_udriver->name); } return retval; } EXPORT_SYMBOL_GPL(usb_register_device_driver); /** * usb_deregister_device_driver - unregister a USB device (not interface) driver * @udriver: USB operations of the device driver to unregister * Context: must be able to sleep * * Unlinks the specified driver from the internal USB driver list. */ void usb_deregister_device_driver(struct usb_device_driver *udriver) { pr_info("%s: deregistering device driver %s\n", usbcore_name, udriver->name); driver_unregister(&udriver->driver); } EXPORT_SYMBOL_GPL(usb_deregister_device_driver); /** * usb_register_driver - register a USB interface driver * @new_driver: USB operations for the interface driver * @owner: module owner of this driver. * @mod_name: module name string * * Registers a USB interface driver with the USB core. The list of * unattached interfaces will be rescanned whenever a new driver is * added, allowing the new driver to attach to any recognized interfaces. * * Return: A negative error code on failure and 0 on success. * * NOTE: if you want your driver to use the USB major number, you must call * usb_register_dev() to enable that functionality. This function no longer * takes care of that. */ int usb_register_driver(struct usb_driver *new_driver, struct module *owner, const char *mod_name) { int retval = 0; if (usb_disabled()) return -ENODEV; new_driver->driver.name = new_driver->name; new_driver->driver.bus = &usb_bus_type; new_driver->driver.probe = usb_probe_interface; new_driver->driver.remove = usb_unbind_interface; new_driver->driver.shutdown = usb_shutdown_interface; new_driver->driver.owner = owner; new_driver->driver.mod_name = mod_name; new_driver->driver.dev_groups = new_driver->dev_groups; INIT_LIST_HEAD(&new_driver->dynids.list); retval = driver_register(&new_driver->driver); if (retval) goto out; retval = usb_create_newid_files(new_driver); if (retval) goto out_newid; pr_info("%s: registered new interface driver %s\n", usbcore_name, new_driver->name); return 0; out_newid: driver_unregister(&new_driver->driver); out: pr_err("%s: error %d registering interface driver %s\n", usbcore_name, retval, new_driver->name); return retval; } EXPORT_SYMBOL_GPL(usb_register_driver); /** * usb_deregister - unregister a USB interface driver * @driver: USB operations of the interface driver to unregister * Context: must be able to sleep * * Unlinks the specified driver from the internal USB driver list. * * NOTE: If you called usb_register_dev(), you still need to call * usb_deregister_dev() to clean up your driver's allocated minor numbers, * this * call will no longer do it for you. */ void usb_deregister(struct usb_driver *driver) { pr_info("%s: deregistering interface driver %s\n", usbcore_name, driver->name); usb_remove_newid_files(driver); driver_unregister(&driver->driver); usb_free_dynids(driver); } EXPORT_SYMBOL_GPL(usb_deregister); /* Forced unbinding of a USB interface driver, either because * it doesn't support pre_reset/post_reset/reset_resume or * because it doesn't support suspend/resume. * * The caller must hold @intf's device's lock, but not @intf's lock. */ void usb_forced_unbind_intf(struct usb_interface *intf) { struct usb_driver *driver = to_usb_driver(intf->dev.driver); dev_dbg(&intf->dev, "forced unbind\n"); usb_driver_release_interface(driver, intf); /* Mark the interface for later rebinding */ intf->needs_binding = 1; } /* * Unbind drivers for @udev's marked interfaces. These interfaces have * the needs_binding flag set, for example by usb_resume_interface(). * * The caller must hold @udev's device lock. */ static void unbind_marked_interfaces(struct usb_device *udev) { struct usb_host_config *config; int i; struct usb_interface *intf; config = udev->actconfig; if (config) { for (i = 0; i < config->desc.bNumInterfaces; ++i) { intf = config->interface[i]; if (intf->dev.driver && intf->needs_binding) usb_forced_unbind_intf(intf); } } } /* Delayed forced unbinding of a USB interface driver and scan * for rebinding. * * The caller must hold @intf's device's lock, but not @intf's lock. * * Note: Rebinds will be skipped if a system sleep transition is in * progress and the PM "complete" callback hasn't occurred yet. */ static void usb_rebind_intf(struct usb_interface *intf) { int rc; /* Delayed unbind of an existing driver */ if (intf->dev.driver) usb_forced_unbind_intf(intf); /* Try to rebind the interface */ if (!intf->dev.power.is_prepared) { intf->needs_binding = 0; rc = device_attach(&intf->dev); if (rc < 0 && rc != -EPROBE_DEFER) dev_warn(&intf->dev, "rebind failed: %d\n", rc); } } /* * Rebind drivers to @udev's marked interfaces. These interfaces have * the needs_binding flag set. * * The caller must hold @udev's device lock. */ static void rebind_marked_interfaces(struct usb_device *udev) { struct usb_host_config *config; int i; struct usb_interface *intf; config = udev->actconfig; if (config) { for (i = 0; i < config->desc.bNumInterfaces; ++i) { intf = config->interface[i]; if (intf->needs_binding) usb_rebind_intf(intf); } } } /* * Unbind all of @udev's marked interfaces and then rebind all of them. * This ordering is necessary because some drivers claim several interfaces * when they are first probed. * * The caller must hold @udev's device lock. */ void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev) { unbind_marked_interfaces(udev); rebind_marked_interfaces(udev); } #ifdef CONFIG_PM /* Unbind drivers for @udev's interfaces that don't support suspend/resume * There is no check for reset_resume here because it can be determined * only during resume whether reset_resume is needed. * * The caller must hold @udev's device lock. */ static void unbind_no_pm_drivers_interfaces(struct usb_device *udev) { struct usb_host_config *config; int i; struct usb_interface *intf; struct usb_driver *drv; config = udev->actconfig; if (config) { for (i = 0; i < config->desc.bNumInterfaces; ++i) { intf = config->interface[i]; if (intf->dev.driver) { drv = to_usb_driver(intf->dev.driver); if (!drv->suspend || !drv->resume) usb_forced_unbind_intf(intf); } } } } static int usb_suspend_device(struct usb_device *udev, pm_message_t msg) { struct usb_device_driver *udriver; int status = 0; if (udev->state == USB_STATE_NOTATTACHED || udev->state == USB_STATE_SUSPENDED) goto done; /* For devices that don't have a driver, we do a generic suspend. */ if (udev->dev.driver) udriver = to_usb_device_driver(udev->dev.driver); else { udev->do_remote_wakeup = 0; udriver = &usb_generic_driver; } if (udriver->suspend) status = udriver->suspend(udev, msg); if (status == 0 && udriver->generic_subclass) status = usb_generic_driver_suspend(udev, msg); done: dev_vdbg(&udev->dev, "%s: status %d\n", __func__, status); return status; } static int usb_resume_device(struct usb_device *udev, pm_message_t msg) { struct usb_device_driver *udriver; int status = 0; if (udev->state == USB_STATE_NOTATTACHED) goto done; /* Can't resume it if it doesn't have a driver. */ if (udev->dev.driver == NULL) { status = -ENOTCONN; goto done; } /* Non-root devices on a full/low-speed bus must wait for their * companion high-speed root hub, in case a handoff is needed. */ if (!PMSG_IS_AUTO(msg) && udev->parent && udev->bus->hs_companion) device_pm_wait_for_dev(&udev->dev, &udev->bus->hs_companion->root_hub->dev); if (udev->quirks & USB_QUIRK_RESET_RESUME) udev->reset_resume = 1; udriver = to_usb_device_driver(udev->dev.driver); if (udriver->generic_subclass) status = usb_generic_driver_resume(udev, msg); if (status == 0 && udriver->resume) status = udriver->resume(udev, msg); done: dev_vdbg(&udev->dev, "%s: status %d\n", __func__, status); return status; } static int usb_suspend_interface(struct usb_device *udev, struct usb_interface *intf, pm_message_t msg) { struct usb_driver *driver; int status = 0; if (udev->state == USB_STATE_NOTATTACHED || intf->condition == USB_INTERFACE_UNBOUND) goto done; driver = to_usb_driver(intf->dev.driver); /* at this time we know the driver supports suspend */ status = driver->suspend(intf, msg); if (status && !PMSG_IS_AUTO(msg)) dev_err(&intf->dev, "suspend error %d\n", status); done: dev_vdbg(&intf->dev, "%s: status %d\n", __func__, status); return status; } static int usb_resume_interface(struct usb_device *udev, struct usb_interface *intf, pm_message_t msg, int reset_resume) { struct usb_driver *driver; int status = 0; if (udev->state == USB_STATE_NOTATTACHED) goto done; /* Don't let autoresume interfere with unbinding */ if (intf->condition == USB_INTERFACE_UNBINDING) goto done; /* Can't resume it if it doesn't have a driver. */ if (intf->condition == USB_INTERFACE_UNBOUND) { /* Carry out a deferred switch to altsetting 0 */ if (intf->needs_altsetting0 && !intf->dev.power.is_prepared) { usb_set_interface(udev, intf->altsetting[0]. desc.bInterfaceNumber, 0); intf->needs_altsetting0 = 0; } goto done; } /* Don't resume if the interface is marked for rebinding */ if (intf->needs_binding) goto done; driver = to_usb_driver(intf->dev.driver); if (reset_resume) { if (driver->reset_resume) { status = driver->reset_resume(intf); if (status) dev_err(&intf->dev, "%s error %d\n", "reset_resume", status); } else { intf->needs_binding = 1; dev_dbg(&intf->dev, "no reset_resume for driver %s?\n", driver->name); } } else { status = driver->resume(intf); if (status) dev_err(&intf->dev, "resume error %d\n", status); } done: dev_vdbg(&intf->dev, "%s: status %d\n", __func__, status); /* Later we will unbind the driver and/or reprobe, if necessary */ return status; } /** * usb_suspend_both - suspend a USB device and its interfaces * @udev: the usb_device to suspend * @msg: Power Management message describing this state transition * * This is the central routine for suspending USB devices. It calls the * suspend methods for all the interface drivers in @udev and then calls * the suspend method for @udev itself. When the routine is called in * autosuspend, if an error occurs at any stage, all the interfaces * which were suspended are resumed so that they remain in the same * state as the device, but when called from system sleep, all error * from suspend methods of interfaces and the non-root-hub device itself * are simply ignored, so all suspended interfaces are only resumed * to the device's state when @udev is root-hub and its suspend method * returns failure. * * Autosuspend requests originating from a child device or an interface * driver may be made without the protection of @udev's device lock, but * all other suspend calls will hold the lock. Usbcore will insure that * method calls do not arrive during bind, unbind, or reset operations. * However drivers must be prepared to handle suspend calls arriving at * unpredictable times. * * This routine can run only in process context. * * Return: 0 if the suspend succeeded. */ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg) { int status = 0; int i = 0, n = 0; struct usb_interface *intf; bool offload_active = false; if (udev->state == USB_STATE_NOTATTACHED || udev->state == USB_STATE_SUSPENDED) goto done; usb_offload_set_pm_locked(udev, true); if (msg.event == PM_EVENT_SUSPEND && usb_offload_check(udev)) { dev_dbg(&udev->dev, "device offloaded, skip suspend.\n"); offload_active = true; } /* Suspend all the interfaces and then udev itself */ if (udev->actconfig) { n = udev->actconfig->desc.bNumInterfaces; for (i = n - 1; i >= 0; --i) { intf = udev->actconfig->interface[i]; /* * Don't suspend interfaces with remote wakeup while * the controller is active. This preserves pending * interrupt urbs, allowing interrupt events to be * handled during system suspend. */ if (offload_active && intf->needs_remote_wakeup) { dev_dbg(&intf->dev, "device offloaded, skip suspend.\n"); continue; } status = usb_suspend_interface(udev, intf, msg); /* Ignore errors during system sleep transitions */ if (!PMSG_IS_AUTO(msg)) status = 0; if (status != 0) break; } } if (status == 0) { if (!offload_active) status = usb_suspend_device(udev, msg); /* * Ignore errors from non-root-hub devices during * system sleep transitions. For the most part, * these devices should go to low power anyway when * the entire bus is suspended. */ if (udev->parent && !PMSG_IS_AUTO(msg)) status = 0; /* * If the device is inaccessible, don't try to resume * suspended interfaces and just return the error. */ if (status && status != -EBUSY) { int err; u16 devstat; err = usb_get_std_status(udev, USB_RECIP_DEVICE, 0, &devstat); if (err) { dev_err(&udev->dev, "Failed to suspend device, error %d\n", status); goto done; } } } /* If the suspend failed, resume interfaces that did get suspended */ if (status != 0) { if (udev->actconfig) { msg.event ^= (PM_EVENT_SUSPEND | PM_EVENT_RESUME); while (++i < n) { intf = udev->actconfig->interface[i]; usb_resume_interface(udev, intf, msg, 0); } } /* If the suspend succeeded then prevent any more URB submissions * and flush any outstanding URBs. */ } else { udev->can_submit = 0; if (!offload_active) { for (i = 0; i < 16; ++i) { usb_hcd_flush_endpoint(udev, udev->ep_out[i]); usb_hcd_flush_endpoint(udev, udev->ep_in[i]); } } } done: if (status != 0) usb_offload_set_pm_locked(udev, false); dev_vdbg(&udev->dev, "%s: status %d\n", __func__, status); return status; } /** * usb_resume_both - resume a USB device and its interfaces * @udev: the usb_device to resume * @msg: Power Management message describing this state transition * * This is the central routine for resuming USB devices. It calls the * resume method for @udev and then calls the resume methods for all * the interface drivers in @udev. * * Autoresume requests originating from a child device or an interface * driver may be made without the protection of @udev's device lock, but * all other resume calls will hold the lock. Usbcore will insure that * method calls do not arrive during bind, unbind, or reset operations. * However drivers must be prepared to handle resume calls arriving at * unpredictable times. * * This routine can run only in process context. * * Return: 0 on success. */ static int usb_resume_both(struct usb_device *udev, pm_message_t msg) { int status = 0; int i; struct usb_interface *intf; bool offload_active = false; if (udev->state == USB_STATE_NOTATTACHED) { status = -ENODEV; goto done; } udev->can_submit = 1; if (msg.event == PM_EVENT_RESUME) offload_active = usb_offload_check(udev); /* Resume the device */ if (udev->state == USB_STATE_SUSPENDED || udev->reset_resume) { if (!offload_active) status = usb_resume_device(udev, msg); else dev_dbg(&udev->dev, "device offloaded, skip resume.\n"); } /* Resume the interfaces */ if (status == 0 && udev->actconfig) { for (i = 0; i < udev->actconfig->desc.bNumInterfaces; i++) { intf = udev->actconfig->interface[i]; /* * Interfaces with remote wakeup aren't suspended * while the controller is active. This preserves * pending interrupt urbs, allowing interrupt events * to be handled during system suspend. */ if (offload_active && intf->needs_remote_wakeup) { dev_dbg(&intf->dev, "device offloaded, skip resume.\n"); continue; } usb_resume_interface(udev, intf, msg, udev->reset_resume); } } usb_mark_last_busy(udev); done: dev_vdbg(&udev->dev, "%s: status %d\n", __func__, status); usb_offload_set_pm_locked(udev, false); if (!status) udev->reset_resume = 0; return status; } static void choose_wakeup(struct usb_device *udev, pm_message_t msg) { int w; /* * For FREEZE/QUIESCE, disable remote wakeups so no interrupts get * generated. */ if (msg.event == PM_EVENT_FREEZE || msg.event == PM_EVENT_QUIESCE) { w = 0; } else { /* * Enable remote wakeup if it is allowed, even if no interface * drivers actually want it. */ w = device_may_wakeup(&udev->dev); } /* * If the device is autosuspended with the wrong wakeup setting, * autoresume now so the setting can be changed. */ if (udev->state == USB_STATE_SUSPENDED && w != udev->do_remote_wakeup) pm_runtime_resume(&udev->dev); udev->do_remote_wakeup = w; } /* The device lock is held by the PM core */ int usb_suspend(struct device *dev, pm_message_t msg) { struct usb_device *udev = to_usb_device(dev); int r; unbind_no_pm_drivers_interfaces(udev); /* From now on we are sure all drivers support suspend/resume * but not necessarily reset_resume() * so we may still need to unbind and rebind upon resume */ choose_wakeup(udev, msg); r = usb_suspend_both(udev, msg); if (r) return r; if (udev->quirks & USB_QUIRK_DISCONNECT_SUSPEND) usb_port_disable(udev); return 0; } /* The device lock is held by the PM core */ int usb_resume_complete(struct device *dev) { struct usb_device *udev = to_usb_device(dev); /* For PM complete calls, all we do is rebind interfaces * whose needs_binding flag is set */ if (udev->state != USB_STATE_NOTATTACHED) rebind_marked_interfaces(udev); return 0; } /* The device lock is held by the PM core */ int usb_resume(struct device *dev, pm_message_t msg) { struct usb_device *udev = to_usb_device(dev); int status; /* For all calls, take the device back to full power and * tell the PM core in case it was autosuspended previously. * Unbind the interfaces that will need rebinding later, * because they fail to support reset_resume. * (This can't be done in usb_resume_interface() * above because it doesn't own the right set of locks.) */ status = usb_resume_both(udev, msg); if (status == 0) { pm_runtime_disable(dev); pm_runtime_set_active(dev); pm_runtime_enable(dev); unbind_marked_interfaces(udev); } /* Avoid PM error messages for devices disconnected while suspended * as we'll display regular disconnect messages just a bit later. */ if (status == -ENODEV || status == -ESHUTDOWN) status = 0; return status; } /** * usb_enable_autosuspend - allow a USB device to be autosuspended * @udev: the USB device which may be autosuspended * * This routine allows @udev to be autosuspended. An autosuspend won't * take place until the autosuspend_delay has elapsed and all the other * necessary conditions are satisfied. * * The caller must hold @udev's device lock. */ void usb_enable_autosuspend(struct usb_device *udev) { pm_runtime_allow(&udev->dev); } EXPORT_SYMBOL_GPL(usb_enable_autosuspend); /** * usb_disable_autosuspend - prevent a USB device from being autosuspended * @udev: the USB device which may not be autosuspended * * This routine prevents @udev from being autosuspended and wakes it up * if it is already autosuspended. * * The caller must hold @udev's device lock. */ void usb_disable_autosuspend(struct usb_device *udev) { pm_runtime_forbid(&udev->dev); } EXPORT_SYMBOL_GPL(usb_disable_autosuspend); /** * usb_autosuspend_device - delayed autosuspend of a USB device and its interfaces * @udev: the usb_device to autosuspend * * This routine should be called when a core subsystem is finished using * @udev and wants to allow it to autosuspend. Examples would be when * @udev's device file in usbfs is closed or after a configuration change. * * @udev's usage counter is decremented; if it drops to 0 and all the * interfaces are inactive then a delayed autosuspend will be attempted. * The attempt may fail (see autosuspend_check()). * * The caller must hold @udev's device lock. * * This routine can run only in process context. */ void usb_autosuspend_device(struct usb_device *udev) { int status; usb_mark_last_busy(udev); status = pm_runtime_put_sync_autosuspend(&udev->dev); dev_vdbg(&udev->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&udev->dev.power.usage_count), status); } /** * usb_autoresume_device - immediately autoresume a USB device and its interfaces * @udev: the usb_device to autoresume * * This routine should be called when a core subsystem wants to use @udev * and needs to guarantee that it is not suspended. No autosuspend will * occur until usb_autosuspend_device() is called. (Note that this will * not prevent suspend events originating in the PM core.) Examples would * be when @udev's device file in usbfs is opened or when a remote-wakeup * request is received. * * @udev's usage counter is incremented to prevent subsequent autosuspends. * However if the autoresume fails then the usage counter is re-decremented. * * The caller must hold @udev's device lock. * * This routine can run only in process context. * * Return: 0 on success. A negative error code otherwise. */ int usb_autoresume_device(struct usb_device *udev) { int status; status = pm_runtime_resume_and_get(&udev->dev); dev_vdbg(&udev->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&udev->dev.power.usage_count), status); return status; } /** * usb_autopm_put_interface - decrement a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be decremented * * This routine should be called by an interface driver when it is * finished using @intf and wants to allow it to autosuspend. A typical * example would be a character-device driver when its device file is * closed. * * The routine decrements @intf's usage counter. When the counter reaches * 0, a delayed autosuspend request for @intf's device is attempted. The * attempt may fail (see autosuspend_check()). * * This routine can run only in process context. */ void usb_autopm_put_interface(struct usb_interface *intf) { struct usb_device *udev = interface_to_usbdev(intf); int status; usb_mark_last_busy(udev); status = pm_runtime_put_sync(&intf->dev); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), status); } EXPORT_SYMBOL_GPL(usb_autopm_put_interface); /** * usb_autopm_put_interface_async - decrement a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be decremented * * This routine does much the same thing as usb_autopm_put_interface(): * It decrements @intf's usage counter and schedules a delayed * autosuspend request if the counter is <= 0. The difference is that it * does not perform any synchronization; callers should hold a private * lock and handle all synchronization issues themselves. * * Typically a driver would call this routine during an URB's completion * handler, if no more URBs were pending. * * This routine can run in atomic context. */ void usb_autopm_put_interface_async(struct usb_interface *intf) { struct usb_device *udev = interface_to_usbdev(intf); usb_mark_last_busy(udev); pm_runtime_put(&intf->dev); dev_vdbg(&intf->dev, "%s: cnt %d\n", __func__, atomic_read(&intf->dev.power.usage_count)); } EXPORT_SYMBOL_GPL(usb_autopm_put_interface_async); /** * usb_autopm_put_interface_no_suspend - decrement a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be decremented * * This routine decrements @intf's usage counter but does not carry out an * autosuspend. * * This routine can run in atomic context. */ void usb_autopm_put_interface_no_suspend(struct usb_interface *intf) { struct usb_device *udev = interface_to_usbdev(intf); usb_mark_last_busy(udev); pm_runtime_put_noidle(&intf->dev); } EXPORT_SYMBOL_GPL(usb_autopm_put_interface_no_suspend); /** * usb_autopm_get_interface - increment a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be incremented * * This routine should be called by an interface driver when it wants to * use @intf and needs to guarantee that it is not suspended. In addition, * the routine prevents @intf from being autosuspended subsequently. (Note * that this will not prevent suspend events originating in the PM core.) * This prevention will persist until usb_autopm_put_interface() is called * or @intf is unbound. A typical example would be a character-device * driver when its device file is opened. * * @intf's usage counter is incremented to prevent subsequent autosuspends. * However if the autoresume fails then the counter is re-decremented. * * This routine can run only in process context. * * Return: 0 on success. */ int usb_autopm_get_interface(struct usb_interface *intf) { int status; status = pm_runtime_resume_and_get(&intf->dev); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), status); return status; } EXPORT_SYMBOL_GPL(usb_autopm_get_interface); /** * usb_autopm_get_interface_async - increment a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be incremented * * This routine does much the same thing as * usb_autopm_get_interface(): It increments @intf's usage counter and * queues an autoresume request if the device is suspended. The * differences are that it does not perform any synchronization (callers * should hold a private lock and handle all synchronization issues * themselves), and it does not autoresume the device directly (it only * queues a request). After a successful call, the device may not yet be * resumed. * * This routine can run in atomic context. * * Return: 0 on success. A negative error code otherwise. */ int usb_autopm_get_interface_async(struct usb_interface *intf) { int status; status = pm_runtime_get(&intf->dev); if (status < 0 && status != -EINPROGRESS) pm_runtime_put_noidle(&intf->dev); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), status); if (status > 0 || status == -EINPROGRESS) status = 0; return status; } EXPORT_SYMBOL_GPL(usb_autopm_get_interface_async); /** * usb_autopm_get_interface_no_resume - increment a USB interface's PM-usage counter * @intf: the usb_interface whose counter should be incremented * * This routine increments @intf's usage counter but does not carry out an * autoresume. * * This routine can run in atomic context. */ void usb_autopm_get_interface_no_resume(struct usb_interface *intf) { struct usb_device *udev = interface_to_usbdev(intf); usb_mark_last_busy(udev); pm_runtime_get_noresume(&intf->dev); } EXPORT_SYMBOL_GPL(usb_autopm_get_interface_no_resume); /* Internal routine to check whether we may autosuspend a device. */ static int autosuspend_check(struct usb_device *udev) { int w, i; struct usb_interface *intf; if (udev->state == USB_STATE_NOTATTACHED) return -ENODEV; /* Fail if autosuspend is disabled, or any interfaces are in use, or * any interface drivers require remote wakeup but it isn't available. */ w = 0; if (udev->actconfig) { for (i = 0; i < udev->actconfig->desc.bNumInterfaces; i++) { intf = udev->actconfig->interface[i]; /* We don't need to check interfaces that are * disabled for runtime PM. Either they are unbound * or else their drivers don't support autosuspend * and so they are permanently active. */ if (intf->dev.power.disable_depth) continue; if (atomic_read(&intf->dev.power.usage_count) > 0) return -EBUSY; w |= intf->needs_remote_wakeup; /* Don't allow autosuspend if the device will need * a reset-resume and any of its interface drivers * doesn't include support or needs remote wakeup. */ if (udev->quirks & USB_QUIRK_RESET_RESUME) { struct usb_driver *driver; driver = to_usb_driver(intf->dev.driver); if (!driver->reset_resume || intf->needs_remote_wakeup) return -EOPNOTSUPP; } } } if (w && !device_can_wakeup(&udev->dev)) { dev_dbg(&udev->dev, "remote wakeup needed for autosuspend\n"); return -EOPNOTSUPP; } /* * If the device is a direct child of the root hub and the HCD * doesn't handle wakeup requests, don't allow autosuspend when * wakeup is needed. */ if (w && udev->parent == udev->bus->root_hub && bus_to_hcd(udev->bus)->cant_recv_wakeups) { dev_dbg(&udev->dev, "HCD doesn't handle wakeup requests\n"); return -EOPNOTSUPP; } udev->do_remote_wakeup = w; return 0; } int usb_runtime_suspend(struct device *dev) { struct usb_device *udev = to_usb_device(dev); int status; /* A USB device can be suspended if it passes the various autosuspend * checks. Runtime suspend for a USB device means suspending all the * interfaces and then the device itself. */ if (autosuspend_check(udev) != 0) return -EAGAIN; status = usb_suspend_both(udev, PMSG_AUTO_SUSPEND); /* Allow a retry if autosuspend failed temporarily */ if (status == -EAGAIN || status == -EBUSY) usb_mark_last_busy(udev); /* * The PM core reacts badly unless the return code is 0, * -EAGAIN, or -EBUSY, so always return -EBUSY on an error * (except for root hubs, because they don't suspend through * an upstream port like other USB devices). */ if (status != 0 && udev->parent) return -EBUSY; return status; } int usb_runtime_resume(struct device *dev) { struct usb_device *udev = to_usb_device(dev); int status; /* Runtime resume for a USB device means resuming both the device * and all its interfaces. */ status = usb_resume_both(udev, PMSG_AUTO_RESUME); return status; } int usb_runtime_idle(struct device *dev) { struct usb_device *udev = to_usb_device(dev); /* An idle USB device can be suspended if it passes the various * autosuspend checks. */ if (autosuspend_check(udev) == 0) pm_runtime_autosuspend(dev); /* Tell the core not to suspend it, though. */ return -EBUSY; } static int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable) { struct usb_hcd *hcd = bus_to_hcd(udev->bus); int ret = -EPERM; if (hcd->driver->set_usb2_hw_lpm) { ret = hcd->driver->set_usb2_hw_lpm(hcd, udev, enable); if (!ret) udev->usb2_hw_lpm_enabled = enable; } return ret; } int usb_enable_usb2_hardware_lpm(struct usb_device *udev) { if (!udev->usb2_hw_lpm_capable || !udev->usb2_hw_lpm_allowed || udev->usb2_hw_lpm_enabled) return 0; return usb_set_usb2_hardware_lpm(udev, 1); } int usb_disable_usb2_hardware_lpm(struct usb_device *udev) { if (!udev->usb2_hw_lpm_enabled) return 0; return usb_set_usb2_hardware_lpm(udev, 0); } #endif /* CONFIG_PM */ const struct bus_type usb_bus_type = { .name = "usb", .match = usb_device_match, .uevent = usb_uevent, .need_parent_lock = true, }; |
| 9 7 9 16 2 2 2 2 2 2 2 1 1 2 1 1 2 2 2 2 2 2 2 2 2 2 2 3 2 2 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include "devl_internal.h" struct devlink_sb { struct list_head list; unsigned int index; u32 size; u16 ingress_pools_count; u16 egress_pools_count; u16 ingress_tc_count; u16 egress_tc_count; }; static u16 devlink_sb_pool_count(struct devlink_sb *devlink_sb) { return devlink_sb->ingress_pools_count + devlink_sb->egress_pools_count; } static struct devlink_sb *devlink_sb_get_by_index(struct devlink *devlink, unsigned int sb_index) { struct devlink_sb *devlink_sb; list_for_each_entry(devlink_sb, &devlink->sb_list, list) { if (devlink_sb->index == sb_index) return devlink_sb; } return NULL; } static bool devlink_sb_index_exists(struct devlink *devlink, unsigned int sb_index) { return devlink_sb_get_by_index(devlink, sb_index); } static struct devlink_sb *devlink_sb_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) { if (attrs[DEVLINK_ATTR_SB_INDEX]) { u32 sb_index = nla_get_u32(attrs[DEVLINK_ATTR_SB_INDEX]); struct devlink_sb *devlink_sb; devlink_sb = devlink_sb_get_by_index(devlink, sb_index); if (!devlink_sb) return ERR_PTR(-ENODEV); return devlink_sb; } return ERR_PTR(-EINVAL); } static struct devlink_sb *devlink_sb_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_sb_get_from_attrs(devlink, info->attrs); } static int devlink_sb_pool_index_get_from_attrs(struct devlink_sb *devlink_sb, struct nlattr **attrs, u16 *p_pool_index) { u16 val; if (!attrs[DEVLINK_ATTR_SB_POOL_INDEX]) return -EINVAL; val = nla_get_u16(attrs[DEVLINK_ATTR_SB_POOL_INDEX]); if (val >= devlink_sb_pool_count(devlink_sb)) return -EINVAL; *p_pool_index = val; return 0; } static int devlink_sb_pool_index_get_from_info(struct devlink_sb *devlink_sb, struct genl_info *info, u16 *p_pool_index) { return devlink_sb_pool_index_get_from_attrs(devlink_sb, info->attrs, p_pool_index); } static int devlink_sb_pool_type_get_from_attrs(struct nlattr **attrs, enum devlink_sb_pool_type *p_pool_type) { u8 val; if (!attrs[DEVLINK_ATTR_SB_POOL_TYPE]) return -EINVAL; val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_TYPE]); if (val != DEVLINK_SB_POOL_TYPE_INGRESS && val != DEVLINK_SB_POOL_TYPE_EGRESS) return -EINVAL; *p_pool_type = val; return 0; } static int devlink_sb_pool_type_get_from_info(struct genl_info *info, enum devlink_sb_pool_type *p_pool_type) { return devlink_sb_pool_type_get_from_attrs(info->attrs, p_pool_type); } static int devlink_sb_th_type_get_from_attrs(struct nlattr **attrs, enum devlink_sb_threshold_type *p_th_type) { u8 val; if (!attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]) return -EINVAL; val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]); if (val != DEVLINK_SB_THRESHOLD_TYPE_STATIC && val != DEVLINK_SB_THRESHOLD_TYPE_DYNAMIC) return -EINVAL; *p_th_type = val; return 0; } static int devlink_sb_th_type_get_from_info(struct genl_info *info, enum devlink_sb_threshold_type *p_th_type) { return devlink_sb_th_type_get_from_attrs(info->attrs, p_th_type); } static int devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb, struct nlattr **attrs, enum devlink_sb_pool_type pool_type, u16 *p_tc_index) { u16 val; if (!attrs[DEVLINK_ATTR_SB_TC_INDEX]) return -EINVAL; val = nla_get_u16(attrs[DEVLINK_ATTR_SB_TC_INDEX]); if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS && val >= devlink_sb->ingress_tc_count) return -EINVAL; if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS && val >= devlink_sb->egress_tc_count) return -EINVAL; *p_tc_index = val; return 0; } static int devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb, struct genl_info *info, enum devlink_sb_pool_type pool_type, u16 *p_tc_index) { return devlink_sb_tc_index_get_from_attrs(devlink_sb, info->attrs, pool_type, p_tc_index); } static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_sb *devlink_sb, enum devlink_command cmd, u32 portid, u32 seq, int flags) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_SIZE, devlink_sb->size)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_POOL_COUNT, devlink_sb->ingress_pools_count)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_POOL_COUNT, devlink_sb->egress_pools_count)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_TC_COUNT, devlink_sb->ingress_tc_count)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_TC_COUNT, devlink_sb->egress_tc_count)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_sb *devlink_sb; struct sk_buff *msg; int err; devlink_sb = devlink_sb_get_from_info(devlink, info); if (IS_ERR(devlink_sb)) return PTR_ERR(devlink_sb); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_sb_fill(msg, devlink, devlink_sb, DEVLINK_CMD_SB_NEW, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_sb_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_sb *devlink_sb; int idx = 0; int err = 0; list_for_each_entry(devlink_sb, &devlink->sb_list, list) { if (idx < state->idx) { idx++; continue; } err = devlink_nl_sb_fill(msg, devlink, devlink_sb, DEVLINK_CMD_SB_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) { state->idx = idx; break; } idx++; } return err; } int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_sb_get_dump_one); } static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_sb *devlink_sb, u16 pool_index, enum devlink_command cmd, u32 portid, u32 seq, int flags) { struct devlink_sb_pool_info pool_info; void *hdr; int err; err = devlink->ops->sb_pool_get(devlink, devlink_sb->index, pool_index, &pool_info); if (err) return err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index)) goto nla_put_failure; if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_info.pool_type)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_SIZE, pool_info.size)) goto nla_put_failure; if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, pool_info.threshold_type)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_CELL_SIZE, pool_info.cell_size)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_sb *devlink_sb; struct sk_buff *msg; u16 pool_index; int err; devlink_sb = devlink_sb_get_from_info(devlink, info); if (IS_ERR(devlink_sb)) return PTR_ERR(devlink_sb); err = devlink_sb_pool_index_get_from_info(devlink_sb, info, &pool_index); if (err) return err; if (!devlink->ops->sb_pool_get) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_sb_pool_fill(msg, devlink, devlink_sb, pool_index, DEVLINK_CMD_SB_POOL_NEW, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, struct devlink *devlink, struct devlink_sb *devlink_sb, u32 portid, u32 seq, int flags) { u16 pool_count = devlink_sb_pool_count(devlink_sb); u16 pool_index; int err; for (pool_index = 0; pool_index < pool_count; pool_index++) { if (*p_idx < start) { (*p_idx)++; continue; } err = devlink_nl_sb_pool_fill(msg, devlink, devlink_sb, pool_index, DEVLINK_CMD_SB_POOL_NEW, portid, seq, flags); if (err) return err; (*p_idx)++; } return 0; } static int devlink_nl_sb_pool_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_sb *devlink_sb; int err = 0; int idx = 0; if (!devlink->ops->sb_pool_get) return 0; list_for_each_entry(devlink_sb, &devlink->sb_list, list) { err = __sb_pool_get_dumpit(msg, state->idx, &idx, devlink, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err == -EOPNOTSUPP) { err = 0; } else if (err) { state->idx = idx; break; } } return err; } int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_sb_pool_get_dump_one); } static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type, struct netlink_ext_ack *extack) { const struct devlink_ops *ops = devlink->ops; if (ops->sb_pool_set) return ops->sb_pool_set(devlink, sb_index, pool_index, size, threshold_type, extack); return -EOPNOTSUPP; } int devlink_nl_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; enum devlink_sb_threshold_type threshold_type; struct devlink_sb *devlink_sb; u16 pool_index; u32 size; int err; devlink_sb = devlink_sb_get_from_info(devlink, info); if (IS_ERR(devlink_sb)) return PTR_ERR(devlink_sb); err = devlink_sb_pool_index_get_from_info(devlink_sb, info, &pool_index); if (err) return err; err = devlink_sb_th_type_get_from_info(info, &threshold_type); if (err) return err; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_POOL_SIZE)) return -EINVAL; size = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_POOL_SIZE]); return devlink_sb_pool_set(devlink, devlink_sb->index, pool_index, size, threshold_type, info->extack); } static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_port *devlink_port, struct devlink_sb *devlink_sb, u16 pool_index, enum devlink_command cmd, u32 portid, u32 seq, int flags) { const struct devlink_ops *ops = devlink->ops; u32 threshold; void *hdr; int err; err = ops->sb_port_pool_get(devlink_port, devlink_sb->index, pool_index, &threshold); if (err) return err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold)) goto nla_put_failure; if (ops->sb_occ_port_pool_get) { u32 cur; u32 max; err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index, pool_index, &cur, &max); if (err && err != -EOPNOTSUPP) goto sb_occ_get_failure; if (!err) { if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max)) goto nla_put_failure; } } genlmsg_end(msg, hdr); return 0; nla_put_failure: err = -EMSGSIZE; sb_occ_get_failure: genlmsg_cancel(msg, hdr); return err; } int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = devlink_port->devlink; struct devlink_sb *devlink_sb; struct sk_buff *msg; u16 pool_index; int err; devlink_sb = devlink_sb_get_from_info(devlink, info); if (IS_ERR(devlink_sb)) return PTR_ERR(devlink_sb); err = devlink_sb_pool_index_get_from_info(devlink_sb, info, &pool_index); if (err) return err; if (!devlink->ops->sb_port_pool_get) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_sb_port_pool_fill(msg, devlink, devlink_port, devlink_sb, pool_index, DEVLINK_CMD_SB_PORT_POOL_NEW, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, struct devlink *devlink, struct devlink_sb *devlink_sb, u32 portid, u32 seq, int flags) { struct devlink_port *devlink_port; u16 pool_count = devlink_sb_pool_count(devlink_sb); unsigned long port_index; u16 pool_index; int err; xa_for_each(&devlink->ports, port_index, devlink_port) { for (pool_index = 0; pool_index < pool_count; pool_index++) { if (*p_idx < start) { (*p_idx)++; continue; } err = devlink_nl_sb_port_pool_fill(msg, devlink, devlink_port, devlink_sb, pool_index, DEVLINK_CMD_SB_PORT_POOL_NEW, portid, seq, flags); if (err) return err; (*p_idx)++; } } return 0; } static int devlink_nl_sb_port_pool_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_sb *devlink_sb; int idx = 0; int err = 0; if (!devlink->ops->sb_port_pool_get) return 0; list_for_each_entry(devlink_sb, &devlink->sb_list, list) { err = __sb_port_pool_get_dumpit(msg, state->idx, &idx, devlink, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err == -EOPNOTSUPP) { err = 0; } else if (err) { state->idx = idx; break; } } return err; } int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_sb_port_pool_get_dump_one); } static int devlink_sb_port_pool_set(struct devlink_port *devlink_port, unsigned int sb_index, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack) { const struct devlink_ops *ops = devlink_port->devlink->ops; if (ops->sb_port_pool_set) return ops->sb_port_pool_set(devlink_port, sb_index, pool_index, threshold, extack); return -EOPNOTSUPP; } int devlink_nl_sb_port_pool_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; struct devlink_sb *devlink_sb; u16 pool_index; u32 threshold; int err; devlink_sb = devlink_sb_get_from_info(devlink, info); if (IS_ERR(devlink_sb)) return PTR_ERR(devlink_sb); err = devlink_sb_pool_index_get_from_info(devlink_sb, info, &pool_index); if (err) return err; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_THRESHOLD)) return -EINVAL; threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]); return devlink_sb_port_pool_set(devlink_port, devlink_sb->index, pool_index, threshold, info->extack); } static int devlink_nl_sb_tc_pool_bind_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_port *devlink_port, struct devlink_sb *devlink_sb, u16 tc_index, enum devlink_sb_pool_type pool_type, enum devlink_command cmd, u32 portid, u32 seq, int flags) { const struct devlink_ops *ops = devlink->ops; u16 pool_index; u32 threshold; void *hdr; int err; err = ops->sb_tc_pool_bind_get(devlink_port, devlink_sb->index, tc_index, pool_type, &pool_index, &threshold); if (err) return err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_TC_INDEX, tc_index)) goto nla_put_failure; if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_type)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold)) goto nla_put_failure; if (ops->sb_occ_tc_port_bind_get) { u32 cur; u32 max; err = ops->sb_occ_tc_port_bind_get(devlink_port, devlink_sb->index, tc_index, pool_type, &cur, &max); if (err && err != -EOPNOTSUPP) return err; if (!err) { if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max)) goto nla_put_failure; } } genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = devlink_port->devlink; struct devlink_sb *devlink_sb; struct sk_buff *msg; enum devlink_sb_pool_type pool_type; u16 tc_index; int err; devlink_sb = devlink_sb_get_from_info(devlink, info); if (IS_ERR(devlink_sb)) return PTR_ERR(devlink_sb); err = devlink_sb_pool_type_get_from_info(info, &pool_type); if (err) return err; err = devlink_sb_tc_index_get_from_info(devlink_sb, info, pool_type, &tc_index); if (err) return err; if (!devlink->ops->sb_tc_pool_bind_get) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, devlink_port, devlink_sb, tc_index, pool_type, DEVLINK_CMD_SB_TC_POOL_BIND_NEW, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, int start, int *p_idx, struct devlink *devlink, struct devlink_sb *devlink_sb, u32 portid, u32 seq, int flags) { struct devlink_port *devlink_port; unsigned long port_index; u16 tc_index; int err; xa_for_each(&devlink->ports, port_index, devlink_port) { for (tc_index = 0; tc_index < devlink_sb->ingress_tc_count; tc_index++) { if (*p_idx < start) { (*p_idx)++; continue; } err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, devlink_port, devlink_sb, tc_index, DEVLINK_SB_POOL_TYPE_INGRESS, DEVLINK_CMD_SB_TC_POOL_BIND_NEW, portid, seq, flags); if (err) return err; (*p_idx)++; } for (tc_index = 0; tc_index < devlink_sb->egress_tc_count; tc_index++) { if (*p_idx < start) { (*p_idx)++; continue; } err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, devlink_port, devlink_sb, tc_index, DEVLINK_SB_POOL_TYPE_EGRESS, DEVLINK_CMD_SB_TC_POOL_BIND_NEW, portid, seq, flags); if (err) return err; (*p_idx)++; } } return 0; } static int devlink_nl_sb_tc_pool_bind_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_sb *devlink_sb; int idx = 0; int err = 0; if (!devlink->ops->sb_tc_pool_bind_get) return 0; list_for_each_entry(devlink_sb, &devlink->sb_list, list) { err = __sb_tc_pool_bind_get_dumpit(msg, state->idx, &idx, devlink, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err == -EOPNOTSUPP) { err = 0; } else if (err) { state->idx = idx; break; } } return err; } int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_sb_tc_pool_bind_get_dump_one); } static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack) { const struct devlink_ops *ops = devlink_port->devlink->ops; if (ops->sb_tc_pool_bind_set) return ops->sb_tc_pool_bind_set(devlink_port, sb_index, tc_index, pool_type, pool_index, threshold, extack); return -EOPNOTSUPP; } int devlink_nl_sb_tc_pool_bind_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; enum devlink_sb_pool_type pool_type; struct devlink_sb *devlink_sb; u16 tc_index; u16 pool_index; u32 threshold; int err; devlink_sb = devlink_sb_get_from_info(devlink, info); if (IS_ERR(devlink_sb)) return PTR_ERR(devlink_sb); err = devlink_sb_pool_type_get_from_info(info, &pool_type); if (err) return err; err = devlink_sb_tc_index_get_from_info(devlink_sb, info, pool_type, &tc_index); if (err) return err; err = devlink_sb_pool_index_get_from_info(devlink_sb, info, &pool_index); if (err) return err; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SB_THRESHOLD)) return -EINVAL; threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]); return devlink_sb_tc_pool_bind_set(devlink_port, devlink_sb->index, tc_index, pool_type, pool_index, threshold, info->extack); } int devlink_nl_sb_occ_snapshot_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; struct devlink_sb *devlink_sb; devlink_sb = devlink_sb_get_from_info(devlink, info); if (IS_ERR(devlink_sb)) return PTR_ERR(devlink_sb); if (ops->sb_occ_snapshot) return ops->sb_occ_snapshot(devlink, devlink_sb->index); return -EOPNOTSUPP; } int devlink_nl_sb_occ_max_clear_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; struct devlink_sb *devlink_sb; devlink_sb = devlink_sb_get_from_info(devlink, info); if (IS_ERR(devlink_sb)) return PTR_ERR(devlink_sb); if (ops->sb_occ_max_clear) return ops->sb_occ_max_clear(devlink, devlink_sb->index); return -EOPNOTSUPP; } int devl_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, u16 egress_tc_count) { struct devlink_sb *devlink_sb; lockdep_assert_held(&devlink->lock); if (devlink_sb_index_exists(devlink, sb_index)) return -EEXIST; devlink_sb = kzalloc_obj(*devlink_sb); if (!devlink_sb) return -ENOMEM; devlink_sb->index = sb_index; devlink_sb->size = size; devlink_sb->ingress_pools_count = ingress_pools_count; devlink_sb->egress_pools_count = egress_pools_count; devlink_sb->ingress_tc_count = ingress_tc_count; devlink_sb->egress_tc_count = egress_tc_count; list_add_tail(&devlink_sb->list, &devlink->sb_list); return 0; } EXPORT_SYMBOL_GPL(devl_sb_register); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, u16 egress_tc_count) { int err; devl_lock(devlink); err = devl_sb_register(devlink, sb_index, size, ingress_pools_count, egress_pools_count, ingress_tc_count, egress_tc_count); devl_unlock(devlink); return err; } EXPORT_SYMBOL_GPL(devlink_sb_register); void devl_sb_unregister(struct devlink *devlink, unsigned int sb_index) { struct devlink_sb *devlink_sb; lockdep_assert_held(&devlink->lock); devlink_sb = devlink_sb_get_by_index(devlink, sb_index); WARN_ON(!devlink_sb); list_del(&devlink_sb->list); kfree(devlink_sb); } EXPORT_SYMBOL_GPL(devl_sb_unregister); void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index) { devl_lock(devlink); devl_sb_unregister(devlink, sb_index); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_sb_unregister); |
| 30 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TTY_BUFFER_H #define _LINUX_TTY_BUFFER_H #include <linux/atomic.h> #include <linux/llist.h> #include <linux/mutex.h> #include <linux/workqueue.h> struct tty_buffer { union { struct tty_buffer *next; struct llist_node free; }; unsigned int used; unsigned int size; unsigned int commit; unsigned int lookahead; /* Lazy update on recv, can become less than "read" */ unsigned int read; bool flags; /* Data points here */ u8 data[] __aligned(sizeof(unsigned long)); }; static inline u8 *char_buf_ptr(struct tty_buffer *b, unsigned int ofs) { return b->data + ofs; } static inline u8 *flag_buf_ptr(struct tty_buffer *b, unsigned int ofs) { return char_buf_ptr(b, ofs) + b->size; } struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct workqueue_struct *flip_wq; struct work_struct work; struct mutex lock; atomic_t priority; struct tty_buffer sentinel; struct llist_head free; /* Free queue head */ atomic_t mem_used; /* In-use buffers excluding free list */ int mem_limit; struct tty_buffer *tail; /* Active buffer */ }; /* * When a break, frame error, or parity error happens, these codes are * stuffed into the flags buffer. */ #define TTY_NORMAL 0 #define TTY_BREAK 1 #define TTY_FRAME 2 #define TTY_PARITY 3 #define TTY_OVERRUN 4 #endif |
| 6 10 5 34 56 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * ocfs2_fs.h * * On-disk structures for OCFS2. * * Copyright (C) 2002, 2004 Oracle. All rights reserved. */ #ifndef _OCFS2_FS_H #define _OCFS2_FS_H #include <linux/magic.h> /* Version */ #define OCFS2_MAJOR_REV_LEVEL 0 #define OCFS2_MINOR_REV_LEVEL 90 /* * An OCFS2 volume starts this way: * Sector 0: Valid ocfs1_vol_disk_hdr that cleanly fails to mount OCFS. * Sector 1: Valid ocfs1_vol_label that cleanly fails to mount OCFS. * Block OCFS2_SUPER_BLOCK_BLKNO: OCFS2 superblock. * * All other structures are found from the superblock information. * * OCFS2_SUPER_BLOCK_BLKNO is in blocks, not sectors. eg, for a * blocksize of 2K, it is 4096 bytes into disk. */ #define OCFS2_SUPER_BLOCK_BLKNO 2 /* * Cluster size limits. The maximum is kept arbitrarily at 1 MB, and could * grow if needed. */ #define OCFS2_MIN_CLUSTERSIZE 4096 #define OCFS2_MAX_CLUSTERSIZE 1048576 /* * Blocks cannot be bigger than clusters, so the maximum blocksize is the * minimum cluster size. */ #define OCFS2_MIN_BLOCKSIZE 512 #define OCFS2_MAX_BLOCKSIZE OCFS2_MIN_CLUSTERSIZE /* Object signatures */ #define OCFS2_SUPER_BLOCK_SIGNATURE "OCFSV2" #define OCFS2_INODE_SIGNATURE "INODE01" #define OCFS2_EXTENT_BLOCK_SIGNATURE "EXBLK01" #define OCFS2_GROUP_DESC_SIGNATURE "GROUP01" #define OCFS2_XATTR_BLOCK_SIGNATURE "XATTR01" #define OCFS2_DIR_TRAILER_SIGNATURE "DIRTRL1" #define OCFS2_DX_ROOT_SIGNATURE "DXDIR01" #define OCFS2_DX_LEAF_SIGNATURE "DXLEAF1" #define OCFS2_REFCOUNT_BLOCK_SIGNATURE "REFCNT1" /* Compatibility flags */ #define OCFS2_HAS_COMPAT_FEATURE(sb,mask) \ ( OCFS2_SB(sb)->s_feature_compat & (mask) ) #define OCFS2_HAS_RO_COMPAT_FEATURE(sb,mask) \ ( OCFS2_SB(sb)->s_feature_ro_compat & (mask) ) #define OCFS2_HAS_INCOMPAT_FEATURE(sb,mask) \ ( OCFS2_SB(sb)->s_feature_incompat & (mask) ) #define OCFS2_SET_COMPAT_FEATURE(sb,mask) \ OCFS2_SB(sb)->s_feature_compat |= (mask) #define OCFS2_SET_RO_COMPAT_FEATURE(sb,mask) \ OCFS2_SB(sb)->s_feature_ro_compat |= (mask) #define OCFS2_SET_INCOMPAT_FEATURE(sb,mask) \ OCFS2_SB(sb)->s_feature_incompat |= (mask) #define OCFS2_CLEAR_COMPAT_FEATURE(sb,mask) \ OCFS2_SB(sb)->s_feature_compat &= ~(mask) #define OCFS2_CLEAR_RO_COMPAT_FEATURE(sb,mask) \ OCFS2_SB(sb)->s_feature_ro_compat &= ~(mask) #define OCFS2_CLEAR_INCOMPAT_FEATURE(sb,mask) \ OCFS2_SB(sb)->s_feature_incompat &= ~(mask) #define OCFS2_FEATURE_COMPAT_SUPP (OCFS2_FEATURE_COMPAT_BACKUP_SB \ | OCFS2_FEATURE_COMPAT_JBD2_SB) #define OCFS2_FEATURE_INCOMPAT_SUPP (OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT \ | OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC \ | OCFS2_FEATURE_INCOMPAT_INLINE_DATA \ | OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP \ | OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK \ | OCFS2_FEATURE_INCOMPAT_XATTR \ | OCFS2_FEATURE_INCOMPAT_META_ECC \ | OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS \ | OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE \ | OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG \ | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO \ | OCFS2_FEATURE_INCOMPAT_APPEND_DIO) #define OCFS2_FEATURE_RO_COMPAT_SUPP (OCFS2_FEATURE_RO_COMPAT_UNWRITTEN \ | OCFS2_FEATURE_RO_COMPAT_USRQUOTA \ | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA) /* * Heartbeat-only devices are missing journals and other files. The * filesystem driver can't load them, but the library can. Never put * this in OCFS2_FEATURE_INCOMPAT_SUPP, *ever*. */ #define OCFS2_FEATURE_INCOMPAT_HEARTBEAT_DEV 0x0002 /* * tunefs sets this incompat flag before starting the resize and clears it * at the end. This flag protects users from inadvertently mounting the fs * after an aborted run without fsck-ing. */ #define OCFS2_FEATURE_INCOMPAT_RESIZE_INPROG 0x0004 /* Used to denote a non-clustered volume */ #define OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT 0x0008 /* Support for sparse allocation in b-trees */ #define OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC 0x0010 /* * Tunefs sets this incompat flag before starting an operation which * would require cleanup on abort. This is done to protect users from * inadvertently mounting the fs after an aborted run without * fsck-ing. * * s_tunefs_flags on the super block describes precisely which * operations were in progress. */ #define OCFS2_FEATURE_INCOMPAT_TUNEFS_INPROG 0x0020 /* Support for data packed into inode blocks */ #define OCFS2_FEATURE_INCOMPAT_INLINE_DATA 0x0040 /* * Support for alternate, userspace cluster stacks. If set, the superblock * field s_cluster_info contains a tag for the alternate stack in use as * well as the name of the cluster being joined. * mount.ocfs2 must pass in a matching stack name. * * If not set, the classic stack will be used. This is compatible with * all older versions. */ #define OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK 0x0080 /* Support for the extended slot map */ #define OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP 0x100 /* Support for extended attributes */ #define OCFS2_FEATURE_INCOMPAT_XATTR 0x0200 /* Support for indexed directories */ #define OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS 0x0400 /* Metadata checksum and error correction */ #define OCFS2_FEATURE_INCOMPAT_META_ECC 0x0800 /* Refcount tree support */ #define OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE 0x1000 /* Discontiguous block groups */ #define OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG 0x2000 /* * Incompat bit to indicate usable clusterinfo with stackflags for all * cluster stacks (userspace adnd o2cb). If this bit is set, * INCOMPAT_USERSPACE_STACK becomes superfluous and thus should not be set. */ #define OCFS2_FEATURE_INCOMPAT_CLUSTERINFO 0x4000 /* * Append Direct IO support */ #define OCFS2_FEATURE_INCOMPAT_APPEND_DIO 0x8000 /* * backup superblock flag is used to indicate that this volume * has backup superblocks. */ #define OCFS2_FEATURE_COMPAT_BACKUP_SB 0x0001 /* * The filesystem will correctly handle journal feature bits. */ #define OCFS2_FEATURE_COMPAT_JBD2_SB 0x0002 /* * Unwritten extents support. */ #define OCFS2_FEATURE_RO_COMPAT_UNWRITTEN 0x0001 /* * Maintain quota information for this filesystem */ #define OCFS2_FEATURE_RO_COMPAT_USRQUOTA 0x0002 #define OCFS2_FEATURE_RO_COMPAT_GRPQUOTA 0x0004 /* The byte offset of the first backup block will be 1G. * The following will be 4G, 16G, 64G, 256G and 1T. */ #define OCFS2_BACKUP_SB_START 1 << 30 /* the max backup superblock nums */ #define OCFS2_MAX_BACKUP_SUPERBLOCKS 6 /* * Flags on ocfs2_super_block.s_tunefs_flags */ #define OCFS2_TUNEFS_INPROG_REMOVE_SLOT 0x0001 /* Removing slots */ /* * Flags on ocfs2_dinode.i_flags */ #define OCFS2_VALID_FL (0x00000001) /* Inode is valid */ #define OCFS2_UNUSED2_FL (0x00000002) #define OCFS2_ORPHANED_FL (0x00000004) /* On the orphan list */ #define OCFS2_UNUSED3_FL (0x00000008) /* System inode flags */ #define OCFS2_SYSTEM_FL (0x00000010) /* System inode */ #define OCFS2_SUPER_BLOCK_FL (0x00000020) /* Super block */ #define OCFS2_LOCAL_ALLOC_FL (0x00000040) /* Slot local alloc bitmap */ #define OCFS2_BITMAP_FL (0x00000080) /* Allocation bitmap */ #define OCFS2_JOURNAL_FL (0x00000100) /* Slot local journal */ #define OCFS2_HEARTBEAT_FL (0x00000200) /* Heartbeat area */ #define OCFS2_CHAIN_FL (0x00000400) /* Chain allocator */ #define OCFS2_DEALLOC_FL (0x00000800) /* Truncate log */ #define OCFS2_QUOTA_FL (0x00001000) /* Quota file */ #define OCFS2_DIO_ORPHANED_FL (0X00002000) /* On the orphan list especially * for dio */ /* * Flags on ocfs2_dinode.i_dyn_features * * These can change much more often than i_flags. When adding flags, * keep in mind that i_dyn_features is only 16 bits wide. */ #define OCFS2_INLINE_DATA_FL (0x0001) /* Data stored in inode block */ #define OCFS2_HAS_XATTR_FL (0x0002) #define OCFS2_INLINE_XATTR_FL (0x0004) #define OCFS2_INDEXED_DIR_FL (0x0008) #define OCFS2_HAS_REFCOUNT_FL (0x0010) /* Inode attributes, keep in sync with EXT2 */ #define OCFS2_SECRM_FL FS_SECRM_FL /* Secure deletion */ #define OCFS2_UNRM_FL FS_UNRM_FL /* Undelete */ #define OCFS2_COMPR_FL FS_COMPR_FL /* Compress file */ #define OCFS2_SYNC_FL FS_SYNC_FL /* Synchronous updates */ #define OCFS2_IMMUTABLE_FL FS_IMMUTABLE_FL /* Immutable file */ #define OCFS2_APPEND_FL FS_APPEND_FL /* writes to file may only append */ #define OCFS2_NODUMP_FL FS_NODUMP_FL /* do not dump file */ #define OCFS2_NOATIME_FL FS_NOATIME_FL /* do not update atime */ /* Reserved for compression usage... */ #define OCFS2_DIRTY_FL FS_DIRTY_FL #define OCFS2_COMPRBLK_FL FS_COMPRBLK_FL /* One or more compressed clusters */ #define OCFS2_NOCOMP_FL FS_NOCOMP_FL /* Don't compress */ #define OCFS2_ECOMPR_FL FS_ECOMPR_FL /* Compression error */ /* End compression flags --- maybe not all used */ #define OCFS2_BTREE_FL FS_BTREE_FL /* btree format dir */ #define OCFS2_INDEX_FL FS_INDEX_FL /* hash-indexed directory */ #define OCFS2_IMAGIC_FL FS_IMAGIC_FL /* AFS directory */ #define OCFS2_JOURNAL_DATA_FL FS_JOURNAL_DATA_FL /* Reserved for ext3 */ #define OCFS2_NOTAIL_FL FS_NOTAIL_FL /* file tail should not be merged */ #define OCFS2_DIRSYNC_FL FS_DIRSYNC_FL /* dirsync behaviour (directories only) */ #define OCFS2_TOPDIR_FL FS_TOPDIR_FL /* Top of directory hierarchies*/ #define OCFS2_RESERVED_FL FS_RESERVED_FL /* reserved for ext2 lib */ #define OCFS2_FL_VISIBLE FS_FL_USER_VISIBLE /* User visible flags */ #define OCFS2_FL_MODIFIABLE FS_FL_USER_MODIFIABLE /* User modifiable flags */ /* * Extent record flags (e_node.leaf.flags) */ #define OCFS2_EXT_UNWRITTEN (0x01) /* Extent is allocated but * unwritten */ #define OCFS2_EXT_REFCOUNTED (0x02) /* Extent is reference * counted in an associated * refcount tree */ /* * Journal Flags (ocfs2_dinode.id1.journal1.i_flags) */ #define OCFS2_JOURNAL_DIRTY_FL (0x00000001) /* Journal needs recovery */ /* * superblock s_state flags */ #define OCFS2_ERROR_FS (0x00000001) /* FS saw errors */ /* Limit of space in ocfs2_dir_entry */ #define OCFS2_MAX_FILENAME_LEN 255 /* Maximum slots on an ocfs2 file system */ #define OCFS2_MAX_SLOTS 255 /* Slot map indicator for an empty slot */ #define OCFS2_INVALID_SLOT ((u16)-1) #define OCFS2_VOL_UUID_LEN 16 #define OCFS2_MAX_VOL_LABEL_LEN 64 /* The cluster stack fields */ #define OCFS2_STACK_LABEL_LEN 4 #define OCFS2_CLUSTER_NAME_LEN 16 /* Classic (historically speaking) cluster stack */ #define OCFS2_CLASSIC_CLUSTER_STACK "o2cb" /* Journal limits (in bytes) */ #define OCFS2_MIN_JOURNAL_SIZE (4 * 1024 * 1024) /* * Inline extended attribute size (in bytes) * The value chosen should be aligned to 16 byte boundaries. */ #define OCFS2_MIN_XATTR_INLINE_SIZE 256 /* * Cluster info flags (ocfs2_cluster_info.ci_stackflags) */ #define OCFS2_CLUSTER_O2CB_GLOBAL_HEARTBEAT (0x01) struct ocfs2_system_inode_info { char *si_name; int si_iflags; int si_mode; }; /* System file index */ enum { BAD_BLOCK_SYSTEM_INODE = 0, GLOBAL_INODE_ALLOC_SYSTEM_INODE, #define OCFS2_FIRST_ONLINE_SYSTEM_INODE GLOBAL_INODE_ALLOC_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE, HEARTBEAT_SYSTEM_INODE, GLOBAL_BITMAP_SYSTEM_INODE, USER_QUOTA_SYSTEM_INODE, GROUP_QUOTA_SYSTEM_INODE, #define OCFS2_LAST_GLOBAL_SYSTEM_INODE GROUP_QUOTA_SYSTEM_INODE #define OCFS2_FIRST_LOCAL_SYSTEM_INODE ORPHAN_DIR_SYSTEM_INODE ORPHAN_DIR_SYSTEM_INODE, EXTENT_ALLOC_SYSTEM_INODE, INODE_ALLOC_SYSTEM_INODE, JOURNAL_SYSTEM_INODE, LOCAL_ALLOC_SYSTEM_INODE, TRUNCATE_LOG_SYSTEM_INODE, LOCAL_USER_QUOTA_SYSTEM_INODE, LOCAL_GROUP_QUOTA_SYSTEM_INODE, #define OCFS2_LAST_LOCAL_SYSTEM_INODE LOCAL_GROUP_QUOTA_SYSTEM_INODE NUM_SYSTEM_INODES }; #define NUM_GLOBAL_SYSTEM_INODES OCFS2_FIRST_LOCAL_SYSTEM_INODE #define NUM_LOCAL_SYSTEM_INODES \ (NUM_SYSTEM_INODES - OCFS2_FIRST_LOCAL_SYSTEM_INODE) static struct ocfs2_system_inode_info ocfs2_system_inodes[NUM_SYSTEM_INODES] = { /* Global system inodes (single copy) */ /* The first two are only used from userspace mfks/tunefs */ [BAD_BLOCK_SYSTEM_INODE] = { "bad_blocks", 0, S_IFREG | 0644 }, [GLOBAL_INODE_ALLOC_SYSTEM_INODE] = { "global_inode_alloc", OCFS2_BITMAP_FL | OCFS2_CHAIN_FL, S_IFREG | 0644 }, /* These are used by the running filesystem */ [SLOT_MAP_SYSTEM_INODE] = { "slot_map", 0, S_IFREG | 0644 }, [HEARTBEAT_SYSTEM_INODE] = { "heartbeat", OCFS2_HEARTBEAT_FL, S_IFREG | 0644 }, [GLOBAL_BITMAP_SYSTEM_INODE] = { "global_bitmap", 0, S_IFREG | 0644 }, [USER_QUOTA_SYSTEM_INODE] = { "aquota.user", OCFS2_QUOTA_FL, S_IFREG | 0644 }, [GROUP_QUOTA_SYSTEM_INODE] = { "aquota.group", OCFS2_QUOTA_FL, S_IFREG | 0644 }, /* Slot-specific system inodes (one copy per slot) */ [ORPHAN_DIR_SYSTEM_INODE] = { "orphan_dir:%04d", 0, S_IFDIR | 0755 }, [EXTENT_ALLOC_SYSTEM_INODE] = { "extent_alloc:%04d", OCFS2_BITMAP_FL | OCFS2_CHAIN_FL, S_IFREG | 0644 }, [INODE_ALLOC_SYSTEM_INODE] = { "inode_alloc:%04d", OCFS2_BITMAP_FL | OCFS2_CHAIN_FL, S_IFREG | 0644 }, [JOURNAL_SYSTEM_INODE] = { "journal:%04d", OCFS2_JOURNAL_FL, S_IFREG | 0644 }, [LOCAL_ALLOC_SYSTEM_INODE] = { "local_alloc:%04d", OCFS2_BITMAP_FL | OCFS2_LOCAL_ALLOC_FL, S_IFREG | 0644 }, [TRUNCATE_LOG_SYSTEM_INODE] = { "truncate_log:%04d", OCFS2_DEALLOC_FL, S_IFREG | 0644 }, [LOCAL_USER_QUOTA_SYSTEM_INODE] = { "aquota.user:%04d", OCFS2_QUOTA_FL, S_IFREG | 0644 }, [LOCAL_GROUP_QUOTA_SYSTEM_INODE] = { "aquota.group:%04d", OCFS2_QUOTA_FL, S_IFREG | 0644 }, }; /* Parameter passed from mount.ocfs2 to module */ #define OCFS2_HB_NONE "heartbeat=none" #define OCFS2_HB_LOCAL "heartbeat=local" #define OCFS2_HB_GLOBAL "heartbeat=global" /* * OCFS2_DIR_PAD defines the directory entries boundaries * * NOTE: It must be a multiple of 4 */ #define OCFS2_DIR_PAD 4 #define OCFS2_DIR_ROUND (OCFS2_DIR_PAD - 1) #define OCFS2_DIR_MEMBER_LEN offsetof(struct ocfs2_dir_entry, name) #define OCFS2_DIR_REC_LEN(name_len) (((name_len) + OCFS2_DIR_MEMBER_LEN + \ OCFS2_DIR_ROUND) & \ ~OCFS2_DIR_ROUND) #define OCFS2_DIR_MIN_REC_LEN OCFS2_DIR_REC_LEN(1) #define OCFS2_LINK_MAX 32000 #define OCFS2_DX_LINK_MAX ((1U << 31) - 1U) #define OCFS2_LINKS_HI_SHIFT 16 #define OCFS2_DX_ENTRIES_MAX (0xffffffffU) /* * Convenience casts */ #define OCFS2_RAW_SB(dinode) (&((dinode)->id2.i_super)) /* * Block checking structure. This is used in metadata to validate the * contents. If OCFS2_FEATURE_INCOMPAT_META_ECC is not set, it is all * zeros. */ struct ocfs2_block_check { /*00*/ __le32 bc_crc32e; /* 802.3 Ethernet II CRC32 */ __le16 bc_ecc; /* Single-error-correction parity vector. This is a simple Hamming code dependent on the blocksize. OCFS2's maximum blocksize, 4K, requires 16 parity bits, so we fit in __le16. */ __le16 bc_reserved1; /*08*/ }; /* * On disk extent record for OCFS2 * It describes a range of clusters on disk. * * Length fields are divided into interior and leaf node versions. * This leaves room for a flags field (OCFS2_EXT_*) in the leaf nodes. */ struct ocfs2_extent_rec { /*00*/ __le32 e_cpos; /* Offset into the file, in clusters */ union { __le32 e_int_clusters; /* Clusters covered by all children */ struct { __le16 e_leaf_clusters; /* Clusters covered by this extent */ __u8 e_reserved1; __u8 e_flags; /* Extent flags */ }; }; __le64 e_blkno; /* Physical disk offset, in blocks */ /*10*/ }; struct ocfs2_chain_rec { __le32 c_free; /* Number of free bits in this chain. */ __le32 c_total; /* Number of total bits in this chain */ __le64 c_blkno; /* Physical disk offset (blocks) of 1st group */ }; struct ocfs2_truncate_rec { __le32 t_start; /* 1st cluster in this log */ __le32 t_clusters; /* Number of total clusters covered */ }; /* * On disk extent list for OCFS2 (node in the tree). Note that this * is contained inside ocfs2_dinode or ocfs2_extent_block, so the * offsets are relative to ocfs2_dinode.id2.i_list or * ocfs2_extent_block.h_list, respectively. */ struct ocfs2_extent_list { /*00*/ __le16 l_tree_depth; /* Extent tree depth from this point. 0 means data extents hang directly off this header (a leaf) NOTE: The high 8 bits cannot be used - tree_depth is never that big. */ __le16 l_count; /* Number of extent records */ __le16 l_next_free_rec; /* Next unused extent slot */ __le16 l_reserved1; __le64 l_reserved2; /* Pad to sizeof(ocfs2_extent_rec) */ /* Extent records */ /*10*/ struct ocfs2_extent_rec l_recs[] __counted_by_le(l_count); }; /* * On disk allocation chain list for OCFS2. Note that this is * contained inside ocfs2_dinode, so the offsets are relative to * ocfs2_dinode.id2.i_chain. */ struct ocfs2_chain_list { /*00*/ __le16 cl_cpg; /* Clusters per Block Group */ __le16 cl_bpc; /* Bits per cluster */ __le16 cl_count; /* Total chains in this list */ __le16 cl_next_free_rec; /* Next unused chain slot */ __le64 cl_reserved1; /* Chain records */ /*10*/ struct ocfs2_chain_rec cl_recs[] __counted_by_le(cl_count); }; /* * On disk deallocation log for OCFS2. Note that this is * contained inside ocfs2_dinode, so the offsets are relative to * ocfs2_dinode.id2.i_dealloc. */ struct ocfs2_truncate_log { /*00*/ __le16 tl_count; /* Total records in this log */ __le16 tl_used; /* Number of records in use */ __le32 tl_reserved1; /* Truncate records */ /*08*/ struct ocfs2_truncate_rec tl_recs[] __counted_by_le(tl_count); }; /* * On disk extent block (indirect block) for OCFS2 */ struct ocfs2_extent_block { /*00*/ __u8 h_signature[8]; /* Signature for verification */ struct ocfs2_block_check h_check; /* Error checking */ /*10*/ __le16 h_suballoc_slot; /* Slot suballocator this extent_header belongs to */ __le16 h_suballoc_bit; /* Bit offset in suballocator block group */ __le32 h_fs_generation; /* Must match super block */ __le64 h_blkno; /* Offset on disk, in blocks */ /*20*/ __le64 h_suballoc_loc; /* Suballocator block group this eb belongs to. Only valid if allocated from a discontiguous block group */ __le64 h_next_leaf_blk; /* Offset on disk, in blocks, of next leaf header pointing to data */ /*30*/ struct ocfs2_extent_list h_list; /* Extent record list */ /* Actual on-disk size is one block */ }; /* * On disk slot map for OCFS2. This defines the contents of the "slot_map" * system file. A slot is valid if it contains a node number >= 0. The * value -1 (0xFFFF) is OCFS2_INVALID_SLOT. This marks a slot empty. */ struct ocfs2_slot_map { /*00*/ DECLARE_FLEX_ARRAY(__le16, sm_slots); /* * Actual on-disk size is one block. OCFS2_MAX_SLOTS is 255, * 255 * sizeof(__le16) == 512B, within the 512B block minimum blocksize. */ }; struct ocfs2_extended_slot { /*00*/ __u8 es_valid; __u8 es_reserved1[3]; __le32 es_node_num; /*08*/ }; /* * The extended slot map, used when OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP * is set. It separates out the valid marker from the node number, and * has room to grow. Unlike the old slot map, this format is defined by * i_size. */ struct ocfs2_slot_map_extended { /*00*/ DECLARE_FLEX_ARRAY(struct ocfs2_extended_slot, se_slots); /* * Actual size is i_size of the slot_map system file. It should * match s_max_slots * sizeof(struct ocfs2_extended_slot) */ }; /* * ci_stackflags is only valid if the incompat bit * OCFS2_FEATURE_INCOMPAT_CLUSTERINFO is set. */ struct ocfs2_cluster_info { /*00*/ __u8 ci_stack[OCFS2_STACK_LABEL_LEN]; union { __le32 ci_reserved; struct { __u8 ci_stackflags; __u8 ci_reserved1; __u8 ci_reserved2; __u8 ci_reserved3; }; }; /*08*/ __u8 ci_cluster[OCFS2_CLUSTER_NAME_LEN]; /*18*/ }; /* * On disk superblock for OCFS2 * Note that it is contained inside an ocfs2_dinode, so all offsets * are relative to the start of ocfs2_dinode.id2. */ struct ocfs2_super_block { /*00*/ __le16 s_major_rev_level; __le16 s_minor_rev_level; __le16 s_mnt_count; __le16 s_max_mnt_count; __le16 s_state; /* File system state */ __le16 s_errors; /* Behaviour when detecting errors */ __le32 s_checkinterval; /* Max time between checks */ /*10*/ __le64 s_lastcheck; /* Time of last check */ __le32 s_creator_os; /* OS */ __le32 s_feature_compat; /* Compatible feature set */ /*20*/ __le32 s_feature_incompat; /* Incompatible feature set */ __le32 s_feature_ro_compat; /* Readonly-compatible feature set */ __le64 s_root_blkno; /* Offset, in blocks, of root directory dinode */ /*30*/ __le64 s_system_dir_blkno; /* Offset, in blocks, of system directory dinode */ __le32 s_blocksize_bits; /* Blocksize for this fs */ __le32 s_clustersize_bits; /* Clustersize for this fs */ /*40*/ __le16 s_max_slots; /* Max number of simultaneous mounts before tunefs required */ __le16 s_tunefs_flag; __le32 s_uuid_hash; /* hash value of uuid */ __le64 s_first_cluster_group; /* Block offset of 1st cluster * group header */ /*50*/ __u8 s_label[OCFS2_MAX_VOL_LABEL_LEN]; /* Label for mounting, etc. */ /*90*/ __u8 s_uuid[OCFS2_VOL_UUID_LEN]; /* 128-bit uuid */ /*A0*/ struct ocfs2_cluster_info s_cluster_info; /* Only valid if either userspace or clusterinfo INCOMPAT flag set. */ /*B8*/ __le16 s_xattr_inline_size; /* extended attribute inline size for this fs*/ __le16 s_reserved0; __le32 s_dx_seed[3]; /* seed[0-2] for dx dir hash. * s_uuid_hash serves as seed[3]. */ /*C8*/ __le64 s_reserved2[15]; /* Fill out superblock */ /*140*/ /* * NOTE: As stated above, all offsets are relative to * ocfs2_dinode.id2, which is at 0xC0 in the inode. * 0xC0 + 0x140 = 0x200 or 512 bytes. A superblock must fit within * our smallest blocksize, which is 512 bytes. To ensure this, * we reserve the space in s_reserved2. Anything past s_reserved2 * will not be available on the smallest blocksize. */ }; /* * Local allocation bitmap for OCFS2 slots * Note that it exists inside an ocfs2_dinode, so all offsets are * relative to the start of ocfs2_dinode.id2. */ struct ocfs2_local_alloc { /*00*/ __le32 la_bm_off; /* Starting bit offset in main bitmap */ __le16 la_size; /* Size of included bitmap, in bytes */ __le16 la_reserved1; __le64 la_reserved2; /*10*/ __u8 la_bitmap[] __counted_by_le(la_size); }; /* * Data-in-inode header. This is only used if i_dyn_features has * OCFS2_INLINE_DATA_FL set. */ struct ocfs2_inline_data { /*00*/ __le16 id_count; /* Number of bytes that can be used * for data, starting at id_data */ __le16 id_reserved0; __le32 id_reserved1; __u8 id_data[] __counted_by_le(id_count); /* Start of user data */ }; /* * On disk inode for OCFS2 */ struct ocfs2_dinode { /*00*/ __u8 i_signature[8]; /* Signature for validation */ __le32 i_generation; /* Generation number */ __le16 i_suballoc_slot; /* Slot suballocator this inode belongs to */ __le16 i_suballoc_bit; /* Bit offset in suballocator block group */ /*10*/ __le16 i_links_count_hi; /* High 16 bits of links count */ __le16 i_xattr_inline_size; __le32 i_clusters; /* Cluster count */ __le32 i_uid; /* Owner UID */ __le32 i_gid; /* Owning GID */ /*20*/ __le64 i_size; /* Size in bytes */ __le16 i_mode; /* File mode */ __le16 i_links_count; /* Links count */ __le32 i_flags; /* File flags */ /*30*/ __le64 i_atime; /* Access time */ __le64 i_ctime; /* Creation time */ /*40*/ __le64 i_mtime; /* Modification time */ __le64 i_dtime; /* Deletion time */ /*50*/ __le64 i_blkno; /* Offset on disk, in blocks */ __le64 i_last_eb_blk; /* Pointer to last extent block */ /*60*/ __le32 i_fs_generation; /* Generation per fs-instance */ __le32 i_atime_nsec; __le32 i_ctime_nsec; __le32 i_mtime_nsec; /*70*/ __le32 i_attr; __le16 i_orphaned_slot; /* Only valid when OCFS2_ORPHANED_FL was set in i_flags */ __le16 i_dyn_features; __le64 i_xattr_loc; /*80*/ struct ocfs2_block_check i_check; /* Error checking */ /*88*/ __le64 i_dx_root; /* Pointer to dir index root block */ /*90*/ __le64 i_refcount_loc; __le64 i_suballoc_loc; /* Suballocator block group this inode belongs to. Only valid if allocated from a discontiguous block group */ /*A0*/ __le16 i_dio_orphaned_slot; /* only used for append dio write */ __le16 i_reserved1[3]; __le64 i_reserved2[2]; /*B8*/ union { __le64 i_pad1; /* Generic way to refer to this 64bit union */ struct { __le64 i_rdev; /* Device number */ } dev1; struct { /* Info for bitmap system inodes */ __le32 i_used; /* Bits (ie, clusters) used */ __le32 i_total; /* Total bits (clusters) available */ } bitmap1; struct { /* Info for journal system inodes */ __le32 ij_flags; /* Mounted, version, etc. */ __le32 ij_recovery_generation; /* Incremented when the journal is recovered after an unclean shutdown */ } journal1; } id1; /* Inode type dependent 1 */ /*C0*/ union { struct ocfs2_super_block i_super; struct ocfs2_local_alloc i_lab; struct ocfs2_chain_list i_chain; struct ocfs2_extent_list i_list; struct ocfs2_truncate_log i_dealloc; struct ocfs2_inline_data i_data; DECLARE_FLEX_ARRAY(__u8, i_symlink); } id2; /* Actual on-disk size is one block */ }; /* * On-disk directory entry structure for OCFS2 * * Packed as this structure could be accessed unaligned on 64-bit platforms */ struct ocfs2_dir_entry { /*00*/ __le64 inode; /* Inode number */ __le16 rec_len; /* Directory entry length */ __u8 name_len; /* Name length */ __u8 file_type; /*0C*/ char name[OCFS2_MAX_FILENAME_LEN]; /* File name */ /* Actual on-disk length specified by rec_len */ } __attribute__ ((packed)); /* * Per-block record for the unindexed directory btree. This is carefully * crafted so that the rec_len and name_len records of an ocfs2_dir_entry are * mirrored. That way, the directory manipulation code needs a minimal amount * of update. * * NOTE: Keep this structure aligned to a multiple of 4 bytes. */ struct ocfs2_dir_block_trailer { /*00*/ __le64 db_compat_inode; /* Always zero. Was inode */ __le16 db_compat_rec_len; /* Backwards compatible with * ocfs2_dir_entry. */ __u8 db_compat_name_len; /* Always zero. Was name_len */ __u8 db_reserved0; __le16 db_reserved1; __le16 db_free_rec_len; /* Size of largest empty hole * in this block. (unused) */ /*10*/ __u8 db_signature[8]; /* Signature for verification */ __le64 db_reserved2; /*20*/ __le64 db_free_next; /* Next block in list (unused) */ __le64 db_blkno; /* Offset on disk, in blocks */ /*30*/ __le64 db_parent_dinode; /* dinode which owns me, in blocks */ struct ocfs2_block_check db_check; /* Error checking */ /*40*/ }; /* * A directory entry in the indexed tree. We don't store the full name here, * but instead provide a pointer to the full dirent in the unindexed tree. * * We also store name_len here so as to reduce the number of leaf blocks we * need to search in case of collisions. */ struct ocfs2_dx_entry { __le32 dx_major_hash; /* Used to find logical * cluster in index */ __le32 dx_minor_hash; /* Lower bits used to find * block in cluster */ __le64 dx_dirent_blk; /* Physical block in unindexed * tree holding this dirent. */ }; struct ocfs2_dx_entry_list { __le32 de_reserved; __le16 de_count; /* Maximum number of entries * possible in de_entries */ __le16 de_num_used; /* Current number of * de_entries entries */ /* Indexed dir entries in a packed * array of length de_num_used. */ struct ocfs2_dx_entry de_entries[] __counted_by_le(de_count); }; #define OCFS2_DX_FLAG_INLINE 0x01 /* * A directory indexing block. Each indexed directory has one of these, * pointed to by ocfs2_dinode. * * This block stores an indexed btree root, and a set of free space * start-of-list pointers. */ struct ocfs2_dx_root_block { __u8 dr_signature[8]; /* Signature for verification */ struct ocfs2_block_check dr_check; /* Error checking */ __le16 dr_suballoc_slot; /* Slot suballocator this * block belongs to. */ __le16 dr_suballoc_bit; /* Bit offset in suballocator * block group */ __le32 dr_fs_generation; /* Must match super block */ __le64 dr_blkno; /* Offset on disk, in blocks */ __le64 dr_last_eb_blk; /* Pointer to last * extent block */ __le32 dr_clusters; /* Clusters allocated * to the indexed tree. */ __u8 dr_flags; /* OCFS2_DX_FLAG_* flags */ __u8 dr_reserved0; __le16 dr_reserved1; __le64 dr_dir_blkno; /* Pointer to parent inode */ __le32 dr_num_entries; /* Total number of * names stored in * this directory.*/ __le32 dr_reserved2; __le64 dr_free_blk; /* Pointer to head of free * unindexed block list. */ __le64 dr_suballoc_loc; /* Suballocator block group this root belongs to. Only valid if allocated from a discontiguous block group */ __le64 dr_reserved3[14]; union { struct ocfs2_extent_list dr_list; /* Keep this aligned to 128 * bits for maximum space * efficiency. */ struct ocfs2_dx_entry_list dr_entries; /* In-root-block list of * entries. We grow out * to extents if this * gets too big. */ }; }; /* * The header of a leaf block in the indexed tree. */ struct ocfs2_dx_leaf { __u8 dl_signature[8];/* Signature for verification */ struct ocfs2_block_check dl_check; /* Error checking */ __le64 dl_blkno; /* Offset on disk, in blocks */ __le32 dl_fs_generation;/* Must match super block */ __le32 dl_reserved0; __le64 dl_reserved1; struct ocfs2_dx_entry_list dl_list; }; /* * Largest bitmap for a block (suballocator) group in bytes. This limit * does not affect cluster groups (global allocator). Cluster group * bitmaps run to the end of the block. */ #define OCFS2_MAX_BG_BITMAP_SIZE 256 /* * On disk allocator group structure for OCFS2 */ struct ocfs2_group_desc { /*00*/ __u8 bg_signature[8]; /* Signature for validation */ __le16 bg_size; /* Size of included bitmap in bytes. */ __le16 bg_bits; /* Bits represented by this group. */ __le16 bg_free_bits_count; /* Free bits count */ __le16 bg_chain; /* What chain I am in. */ /*10*/ __le32 bg_generation; __le16 bg_contig_free_bits; /* max contig free bits length */ __le16 bg_reserved1; __le64 bg_next_group; /* Next group in my list, in blocks */ /*20*/ __le64 bg_parent_dinode; /* dinode which owns me, in blocks */ __le64 bg_blkno; /* Offset on disk, in blocks */ /*30*/ struct ocfs2_block_check bg_check; /* Error checking */ __le64 bg_reserved2; /*40*/ union { DECLARE_FLEX_ARRAY(__u8, bg_bitmap); struct { /* * Block groups may be discontiguous when * OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG is set. * The extents of a discontiguous block group are * stored in bg_list. It is a flat list. * l_tree_depth must always be zero. A * discontiguous group is signified by a non-zero * bg_list->l_next_free_rec. Only block groups * can be discontiguous; Cluster groups cannot. * We've never made a block group with more than * 2048 blocks (256 bytes of bg_bitmap). This * codifies that limit so that we can fit bg_list. * bg_size of a discontiguous block group will * be 256 to match bg_bitmap_filler. */ __u8 bg_bitmap_filler[OCFS2_MAX_BG_BITMAP_SIZE]; /*140*/ struct ocfs2_extent_list bg_list; }; }; /* Actual on-disk size is one block */ }; struct ocfs2_refcount_rec { /*00*/ __le64 r_cpos; /* Physical offset, in clusters */ __le32 r_clusters; /* Clusters covered by this extent */ __le32 r_refcount; /* Reference count of this extent */ /*10*/ }; #define OCFS2_32BIT_POS_MASK (0xffffffffULL) #define OCFS2_REFCOUNT_LEAF_FL (0x00000001) #define OCFS2_REFCOUNT_TREE_FL (0x00000002) struct ocfs2_refcount_list { /*00*/ __le16 rl_count; /* Maximum number of entries possible in rl_records */ __le16 rl_used; /* Current number of used records */ __le32 rl_reserved2; __le64 rl_reserved1; /* Pad to sizeof(ocfs2_refcount_record) */ /* Refcount records */ /*10*/ struct ocfs2_refcount_rec rl_recs[] __counted_by_le(rl_count); }; struct ocfs2_refcount_block { /*00*/ __u8 rf_signature[8]; /* Signature for verification */ __le16 rf_suballoc_slot; /* Slot suballocator this block belongs to */ __le16 rf_suballoc_bit; /* Bit offset in suballocator block group */ __le32 rf_fs_generation; /* Must match superblock */ /*10*/ __le64 rf_blkno; /* Offset on disk, in blocks */ __le64 rf_parent; /* Parent block, only valid if OCFS2_REFCOUNT_LEAF_FL is set in rf_flags */ /*20*/ struct ocfs2_block_check rf_check; /* Error checking */ __le64 rf_last_eb_blk; /* Pointer to last extent block */ /*30*/ __le32 rf_count; /* Number of inodes sharing this refcount tree */ __le32 rf_flags; /* See the flags above */ __le32 rf_clusters; /* clusters covered by refcount tree. */ __le32 rf_cpos; /* cluster offset in refcount tree.*/ /*40*/ __le32 rf_generation; /* generation number. all be the same * for the same refcount tree. */ __le32 rf_reserved0; __le64 rf_suballoc_loc; /* Suballocator block group this refcount block belongs to. Only valid if allocated from a discontiguous block group */ /*50*/ __le64 rf_reserved1[6]; /*80*/ union { struct ocfs2_refcount_list rf_records; /* List of refcount records */ struct ocfs2_extent_list rf_list; /* Extent record list, only valid if OCFS2_REFCOUNT_TREE_FL is set in rf_flags */ }; /* Actual on-disk size is one block */ }; /* * On disk extended attribute structure for OCFS2. */ /* * ocfs2_xattr_entry indicates one extend attribute. * * Note that it can be stored in inode, one block or one xattr bucket. */ struct ocfs2_xattr_entry { __le32 xe_name_hash; /* hash value of xattr prefix+suffix. */ __le16 xe_name_offset; /* byte offset from the 1st entry in the local xattr storage(inode, xattr block or xattr bucket). */ __u8 xe_name_len; /* xattr name len, doesn't include prefix. */ __u8 xe_type; /* the low 7 bits indicate the name prefix * type and the highest bit indicates whether * the EA is stored in the local storage. */ __le64 xe_value_size; /* real xattr value length. */ }; /* * On disk structure for xattr header. * * One ocfs2_xattr_header describes how many ocfs2_xattr_entry records in * the local xattr storage. */ struct ocfs2_xattr_header { __le16 xh_count; /* contains the count of how many records are in the local xattr storage. */ __le16 xh_free_start; /* current offset for storing xattr. */ __le16 xh_name_value_len; /* total length of name/value length in this bucket. */ __le16 xh_num_buckets; /* Number of xattr buckets in this extent record, only valid in the first bucket. */ struct ocfs2_block_check xh_check; /* Error checking (Note, this is only used for xattr buckets. A block uses xb_check and sets this field to zero.) */ /* xattr entry list. */ struct ocfs2_xattr_entry xh_entries[] __counted_by_le(xh_count); }; /* * On disk structure for xattr value root. * * When an xattr's value is large enough, it is stored in an external * b-tree like file data. The xattr value root points to this structure. */ struct ocfs2_xattr_value_root { /*00*/ __le32 xr_clusters; /* clusters covered by xattr value. */ __le32 xr_reserved0; __le64 xr_last_eb_blk; /* Pointer to last extent block */ /*10*/ struct ocfs2_extent_list xr_list; /* Extent record list */ }; /* * On disk structure for xattr tree root. * * It is used when there are too many extended attributes for one file. These * attributes will be organized and stored in an indexed-btree. */ struct ocfs2_xattr_tree_root { /*00*/ __le32 xt_clusters; /* clusters covered by xattr. */ __le32 xt_reserved0; __le64 xt_last_eb_blk; /* Pointer to last extent block */ /*10*/ struct ocfs2_extent_list xt_list; /* Extent record list */ }; #define OCFS2_XATTR_INDEXED 0x1 #define OCFS2_HASH_SHIFT 5 #define OCFS2_XATTR_ROUND 3 #define OCFS2_XATTR_SIZE(size) (((size) + OCFS2_XATTR_ROUND) & \ ~(OCFS2_XATTR_ROUND)) #define OCFS2_XATTR_BUCKET_SIZE 4096 #define OCFS2_XATTR_MAX_BLOCKS_PER_BUCKET (OCFS2_XATTR_BUCKET_SIZE \ / OCFS2_MIN_BLOCKSIZE) /* * On disk structure for xattr block. */ struct ocfs2_xattr_block { /*00*/ __u8 xb_signature[8]; /* Signature for verification */ __le16 xb_suballoc_slot; /* Slot suballocator this block belongs to. */ __le16 xb_suballoc_bit; /* Bit offset in suballocator block group */ __le32 xb_fs_generation; /* Must match super block */ /*10*/ __le64 xb_blkno; /* Offset on disk, in blocks */ struct ocfs2_block_check xb_check; /* Error checking */ /*20*/ __le16 xb_flags; /* Indicates whether this block contains real xattr or a xattr tree. */ __le16 xb_reserved0; __le32 xb_reserved1; __le64 xb_suballoc_loc; /* Suballocator block group this xattr block belongs to. Only valid if allocated from a discontiguous block group */ /*30*/ union { struct ocfs2_xattr_header xb_header; /* xattr header if this block contains xattr */ struct ocfs2_xattr_tree_root xb_root;/* xattr tree root if this block contains xattr tree. */ } xb_attrs; }; #define OCFS2_XATTR_ENTRY_LOCAL 0x80 #define OCFS2_XATTR_TYPE_MASK 0x7F static inline void ocfs2_xattr_set_local(struct ocfs2_xattr_entry *xe, int local) { if (local) xe->xe_type |= OCFS2_XATTR_ENTRY_LOCAL; else xe->xe_type &= ~OCFS2_XATTR_ENTRY_LOCAL; } static inline int ocfs2_xattr_is_local(struct ocfs2_xattr_entry *xe) { return xe->xe_type & OCFS2_XATTR_ENTRY_LOCAL; } static inline void ocfs2_xattr_set_type(struct ocfs2_xattr_entry *xe, int type) { xe->xe_type |= type & OCFS2_XATTR_TYPE_MASK; } static inline int ocfs2_xattr_get_type(struct ocfs2_xattr_entry *xe) { return xe->xe_type & OCFS2_XATTR_TYPE_MASK; } /* * On disk structures for global quota file */ /* Magic numbers and known versions for global quota files */ #define OCFS2_GLOBAL_QMAGICS {\ 0x0cf52470, /* USRQUOTA */ \ 0x0cf52471 /* GRPQUOTA */ \ } #define OCFS2_GLOBAL_QVERSIONS {\ 0, \ 0, \ } /* Each block of each quota file has a certain fixed number of bytes reserved * for OCFS2 internal use at its end. OCFS2 can use it for things like * checksums, etc. */ #define OCFS2_QBLK_RESERVED_SPACE 8 /* Generic header of all quota files */ struct ocfs2_disk_dqheader { __le32 dqh_magic; /* Magic number identifying file */ __le32 dqh_version; /* Quota format version */ }; #define OCFS2_GLOBAL_INFO_OFF (sizeof(struct ocfs2_disk_dqheader)) /* Information header of global quota file (immediately follows the generic * header) */ struct ocfs2_global_disk_dqinfo { /*00*/ __le32 dqi_bgrace; /* Grace time for space softlimit excess */ __le32 dqi_igrace; /* Grace time for inode softlimit excess */ __le32 dqi_syncms; /* Time after which we sync local changes to * global quota file */ __le32 dqi_blocks; /* Number of blocks in quota file */ /*10*/ __le32 dqi_free_blk; /* First free block in quota file */ __le32 dqi_free_entry; /* First block with free dquot entry in quota * file */ }; /* Structure with global user / group information. We reserve some space * for future use. */ struct ocfs2_global_disk_dqblk { /*00*/ __le32 dqb_id; /* ID the structure belongs to */ __le32 dqb_use_count; /* Number of nodes having reference to this structure */ __le64 dqb_ihardlimit; /* absolute limit on allocated inodes */ /*10*/ __le64 dqb_isoftlimit; /* preferred inode limit */ __le64 dqb_curinodes; /* current # allocated inodes */ /*20*/ __le64 dqb_bhardlimit; /* absolute limit on disk space */ __le64 dqb_bsoftlimit; /* preferred limit on disk space */ /*30*/ __le64 dqb_curspace; /* current space occupied */ __le64 dqb_btime; /* time limit for excessive disk use */ /*40*/ __le64 dqb_itime; /* time limit for excessive inode use */ __le64 dqb_pad1; /*50*/ __le64 dqb_pad2; }; /* * On-disk structures for local quota file */ /* Magic numbers and known versions for local quota files */ #define OCFS2_LOCAL_QMAGICS {\ 0x0cf524c0, /* USRQUOTA */ \ 0x0cf524c1 /* GRPQUOTA */ \ } #define OCFS2_LOCAL_QVERSIONS {\ 0, \ 0, \ } /* Quota flags in dqinfo header */ #define OLQF_CLEAN 0x0001 /* Quota file is empty (this should be after\ * quota has been cleanly turned off) */ #define OCFS2_LOCAL_INFO_OFF (sizeof(struct ocfs2_disk_dqheader)) /* Information header of local quota file (immediately follows the generic * header) */ struct ocfs2_local_disk_dqinfo { __le32 dqi_flags; /* Flags for quota file */ __le32 dqi_chunks; /* Number of chunks of quota structures * with a bitmap */ __le32 dqi_blocks; /* Number of blocks allocated for quota file */ }; /* Header of one chunk of a quota file */ struct ocfs2_local_disk_chunk { __le32 dqc_free; /* Number of free entries in the bitmap */ __u8 dqc_bitmap[]; /* Bitmap of entries in the corresponding * chunk of quota file */ }; /* One entry in local quota file */ struct ocfs2_local_disk_dqblk { /*00*/ __le64 dqb_id; /* id this quota applies to */ __le64 dqb_spacemod; /* Change in the amount of used space */ /*10*/ __le64 dqb_inodemod; /* Change in the amount of used inodes */ }; /* * The quota trailer lives at the end of each quota block. */ struct ocfs2_disk_dqtrailer { /*00*/ struct ocfs2_block_check dq_check; /* Error checking */ /*08*/ /* Cannot be larger than OCFS2_QBLK_RESERVED_SPACE */ }; static inline struct ocfs2_disk_dqtrailer *ocfs2_block_dqtrailer(int blocksize, void *buf) { char *ptr = buf; ptr += blocksize - OCFS2_QBLK_RESERVED_SPACE; return (struct ocfs2_disk_dqtrailer *)ptr; } #ifdef __KERNEL__ static inline int ocfs2_fast_symlink_chars(struct super_block *sb) { return sb->s_blocksize - offsetof(struct ocfs2_dinode, id2.i_symlink); } static inline int ocfs2_max_inline_data_with_xattr(struct super_block *sb, struct ocfs2_dinode *di) { unsigned int xattrsize = le16_to_cpu(di->i_xattr_inline_size); if (le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_XATTR_FL) return sb->s_blocksize - offsetof(struct ocfs2_dinode, id2.i_data.id_data) - xattrsize; else return sb->s_blocksize - offsetof(struct ocfs2_dinode, id2.i_data.id_data); } static inline int ocfs2_extent_recs_per_inode(struct super_block *sb) { int size; size = sb->s_blocksize - offsetof(struct ocfs2_dinode, id2.i_list.l_recs); return size / sizeof(struct ocfs2_extent_rec); } static inline int ocfs2_extent_recs_per_inode_with_xattr( struct super_block *sb, struct ocfs2_dinode *di) { int size; unsigned int xattrsize = le16_to_cpu(di->i_xattr_inline_size); if (le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_XATTR_FL) size = sb->s_blocksize - offsetof(struct ocfs2_dinode, id2.i_list.l_recs) - xattrsize; else size = sb->s_blocksize - offsetof(struct ocfs2_dinode, id2.i_list.l_recs); return size / sizeof(struct ocfs2_extent_rec); } static inline int ocfs2_extent_recs_per_dx_root(struct super_block *sb) { int size; size = sb->s_blocksize - offsetof(struct ocfs2_dx_root_block, dr_list.l_recs); return size / sizeof(struct ocfs2_extent_rec); } static inline int ocfs2_chain_recs_per_inode(struct super_block *sb) { int size; size = sb->s_blocksize - offsetof(struct ocfs2_dinode, id2.i_chain.cl_recs); return size / sizeof(struct ocfs2_chain_rec); } static inline u16 ocfs2_extent_recs_per_eb(struct super_block *sb) { int size; size = sb->s_blocksize - offsetof(struct ocfs2_extent_block, h_list.l_recs); return size / sizeof(struct ocfs2_extent_rec); } static inline u16 ocfs2_extent_recs_per_gd(struct super_block *sb) { int size; size = sb->s_blocksize - offsetof(struct ocfs2_group_desc, bg_list.l_recs); return size / sizeof(struct ocfs2_extent_rec); } static inline int ocfs2_dx_entries_per_leaf(struct super_block *sb) { int size; size = sb->s_blocksize - offsetof(struct ocfs2_dx_leaf, dl_list.de_entries); return size / sizeof(struct ocfs2_dx_entry); } static inline int ocfs2_dx_entries_per_root(struct super_block *sb) { int size; size = sb->s_blocksize - offsetof(struct ocfs2_dx_root_block, dr_entries.de_entries); return size / sizeof(struct ocfs2_dx_entry); } static inline u16 ocfs2_local_alloc_size(struct super_block *sb) { u16 size; size = sb->s_blocksize - offsetof(struct ocfs2_dinode, id2.i_lab.la_bitmap); return size; } static inline int ocfs2_group_bitmap_size(struct super_block *sb, int suballocator, u32 feature_incompat) { int size = sb->s_blocksize - offsetof(struct ocfs2_group_desc, bg_bitmap); /* * The cluster allocator uses the entire block. Suballocators have * never used more than OCFS2_MAX_BG_BITMAP_SIZE. Unfortunately, older * code expects bg_size set to the maximum. Thus we must keep * bg_size as-is unless discontig_bg is enabled. */ if (suballocator && (feature_incompat & OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG)) size = OCFS2_MAX_BG_BITMAP_SIZE; return size; } static inline int ocfs2_truncate_recs_per_inode(struct super_block *sb) { int size; size = sb->s_blocksize - offsetof(struct ocfs2_dinode, id2.i_dealloc.tl_recs); return size / sizeof(struct ocfs2_truncate_rec); } static inline u64 ocfs2_backup_super_blkno(struct super_block *sb, int index) { u64 offset = OCFS2_BACKUP_SB_START; if (index >= 0 && index < OCFS2_MAX_BACKUP_SUPERBLOCKS) { offset <<= (2 * index); offset >>= sb->s_blocksize_bits; return offset; } return 0; } static inline u16 ocfs2_xattr_recs_per_xb(struct super_block *sb) { int size; size = sb->s_blocksize - offsetof(struct ocfs2_xattr_block, xb_attrs.xb_root.xt_list.l_recs); return size / sizeof(struct ocfs2_extent_rec); } static inline u16 ocfs2_extent_recs_per_rb(struct super_block *sb) { int size; size = sb->s_blocksize - offsetof(struct ocfs2_refcount_block, rf_list.l_recs); return size / sizeof(struct ocfs2_extent_rec); } static inline u16 ocfs2_refcount_recs_per_rb(struct super_block *sb) { int size; size = sb->s_blocksize - offsetof(struct ocfs2_refcount_block, rf_records.rl_recs); return size / sizeof(struct ocfs2_refcount_rec); } static inline u32 ocfs2_get_ref_rec_low_cpos(const struct ocfs2_refcount_rec *rec) { return le64_to_cpu(rec->r_cpos) & OCFS2_32BIT_POS_MASK; } #else static inline int ocfs2_fast_symlink_chars(int blocksize) { return blocksize - offsetof(struct ocfs2_dinode, id2.i_symlink); } static inline int ocfs2_max_inline_data_with_xattr(int blocksize, struct ocfs2_dinode *di) { if (di && (di->i_dyn_features & OCFS2_INLINE_XATTR_FL)) return blocksize - offsetof(struct ocfs2_dinode, id2.i_data.id_data) - di->i_xattr_inline_size; else return blocksize - offsetof(struct ocfs2_dinode, id2.i_data.id_data); } static inline int ocfs2_extent_recs_per_inode(int blocksize) { int size; size = blocksize - offsetof(struct ocfs2_dinode, id2.i_list.l_recs); return size / sizeof(struct ocfs2_extent_rec); } static inline int ocfs2_chain_recs_per_inode(int blocksize) { int size; size = blocksize - offsetof(struct ocfs2_dinode, id2.i_chain.cl_recs); return size / sizeof(struct ocfs2_chain_rec); } static inline int ocfs2_extent_recs_per_eb(int blocksize) { int size; size = blocksize - offsetof(struct ocfs2_extent_block, h_list.l_recs); return size / sizeof(struct ocfs2_extent_rec); } static inline int ocfs2_extent_recs_per_gd(int blocksize) { int size; size = blocksize - offsetof(struct ocfs2_group_desc, bg_list.l_recs); return size / sizeof(struct ocfs2_extent_rec); } static inline int ocfs2_local_alloc_size(int blocksize) { int size; size = blocksize - offsetof(struct ocfs2_dinode, id2.i_lab.la_bitmap); return size; } static inline int ocfs2_group_bitmap_size(int blocksize, int suballocator, uint32_t feature_incompat) { int size = sb->s_blocksize - offsetof(struct ocfs2_group_desc, bg_bitmap); /* * The cluster allocator uses the entire block. Suballocators have * never used more than OCFS2_MAX_BG_BITMAP_SIZE. Unfortunately, older * code expects bg_size set to the maximum. Thus we must keep * bg_size as-is unless discontig_bg is enabled. */ if (suballocator && (feature_incompat & OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG)) size = OCFS2_MAX_BG_BITMAP_SIZE; return size; } static inline int ocfs2_truncate_recs_per_inode(int blocksize) { int size; size = blocksize - offsetof(struct ocfs2_dinode, id2.i_dealloc.tl_recs); return size / sizeof(struct ocfs2_truncate_rec); } static inline uint64_t ocfs2_backup_super_blkno(int blocksize, int index) { uint64_t offset = OCFS2_BACKUP_SB_START; if (index >= 0 && index < OCFS2_MAX_BACKUP_SUPERBLOCKS) { offset <<= (2 * index); offset /= blocksize; return offset; } return 0; } static inline int ocfs2_xattr_recs_per_xb(int blocksize) { int size; size = blocksize - offsetof(struct ocfs2_xattr_block, xb_attrs.xb_root.xt_list.l_recs); return size / sizeof(struct ocfs2_extent_rec); } #endif /* __KERNEL__ */ static inline int ocfs2_system_inode_is_global(int type) { return ((type >= 0) && (type <= OCFS2_LAST_GLOBAL_SYSTEM_INODE)); } static inline int ocfs2_sprintf_system_inode_name(char *buf, int len, int type, int slot) { int chars; /* * Global system inodes can only have one copy. Everything * after OCFS2_LAST_GLOBAL_SYSTEM_INODE in the system inode * list has a copy per slot. */ if (type <= OCFS2_LAST_GLOBAL_SYSTEM_INODE) chars = snprintf(buf, len, "%s", ocfs2_system_inodes[type].si_name); else chars = snprintf(buf, len, ocfs2_system_inodes[type].si_name, slot); return chars; } static inline void ocfs2_set_de_type(struct ocfs2_dir_entry *de, umode_t mode) { de->file_type = fs_umode_to_ftype(mode); } static inline int ocfs2_gd_is_discontig(struct ocfs2_group_desc *gd) { if ((offsetof(struct ocfs2_group_desc, bg_bitmap) + le16_to_cpu(gd->bg_size)) != offsetof(struct ocfs2_group_desc, bg_list)) return 0; /* * Only valid to check l_next_free_rec if * bg_bitmap + bg_size == bg_list. */ if (!gd->bg_list.l_next_free_rec) return 0; return 1; } #endif /* _OCFS2_FS_H */ |
| 14901 1206 7941 7728 264 7947 1023 1845 7903 7906 7905 111 7923 5226 5224 4 11 1160 1162 1160 314 7231 7077 311 256 8 7237 1751 7195 449 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Percpu refcounts: * (C) 2012 Google, Inc. * Author: Kent Overstreet <koverstreet@google.com> * * This implements a refcount with similar semantics to atomic_t - atomic_inc(), * atomic_dec_and_test() - but percpu. * * There's one important difference between percpu refs and normal atomic_t * refcounts; you have to keep track of your initial refcount, and then when you * start shutting down you call percpu_ref_kill() _before_ dropping the initial * refcount. * * The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less * than an atomic_t - this is because of the way shutdown works, see * percpu_ref_kill()/PERCPU_COUNT_BIAS. * * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill() * puts the ref back in single atomic_t mode, collecting the per cpu refs and * issuing the appropriate barriers, and then marks the ref as shutting down so * that percpu_ref_put() will check for the ref hitting 0. After it returns, * it's safe to drop the initial ref. * * USAGE: * * See fs/aio.c for some example usage; it's used there for struct kioctx, which * is created when userspaces calls io_setup(), and destroyed when userspace * calls io_destroy() or the process exits. * * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref. * After that, there can't be any new users of the kioctx (from lookup_ioctx()) * and it's then safe to drop the initial ref with percpu_ref_put(). * * Note that the free path, free_ioctx(), needs to go through explicit call_rcu() * to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't * imply RCU grace periods of any kind and if a user wants to combine percpu_ref * with RCU protection, it must be done explicitly. * * Code that does a two stage shutdown like this often needs some kind of * explicit synchronization to ensure the initial refcount can only be dropped * once - percpu_ref_kill() does this for you, it returns true once and false if * someone else already called it. The aio code uses it this way, but it's not * necessary if the code has some other mechanism to synchronize teardown. * around. */ #ifndef _LINUX_PERCPU_REFCOUNT_H #define _LINUX_PERCPU_REFCOUNT_H #include <linux/atomic.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/types.h> #include <linux/gfp.h> struct percpu_ref; typedef void (percpu_ref_func_t)(struct percpu_ref *); /* flags set in the lower bits of percpu_ref->percpu_count_ptr */ enum { __PERCPU_REF_ATOMIC = 1LU << 0, /* operating in atomic mode */ __PERCPU_REF_DEAD = 1LU << 1, /* (being) killed */ __PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD, __PERCPU_REF_FLAG_BITS = 2, }; /* @flags for percpu_ref_init() */ enum { /* * Start w/ ref == 1 in atomic mode. Can be switched to percpu * operation using percpu_ref_switch_to_percpu(). If initialized * with this flag, the ref will stay in atomic mode until * percpu_ref_switch_to_percpu() is invoked on it. * Implies ALLOW_REINIT. */ PERCPU_REF_INIT_ATOMIC = 1 << 0, /* * Start dead w/ ref == 0 in atomic mode. Must be revived with * percpu_ref_reinit() before used. Implies INIT_ATOMIC and * ALLOW_REINIT. */ PERCPU_REF_INIT_DEAD = 1 << 1, /* * Allow switching from atomic mode to percpu mode. */ PERCPU_REF_ALLOW_REINIT = 1 << 2, }; struct percpu_ref_data { atomic_long_t count; percpu_ref_func_t *release; percpu_ref_func_t *confirm_switch; bool force_atomic:1; bool allow_reinit:1; struct rcu_head rcu; struct percpu_ref *ref; }; struct percpu_ref { /* * The low bit of the pointer indicates whether the ref is in percpu * mode; if set, then get/put will manipulate the atomic_t. */ unsigned long percpu_count_ptr; /* * 'percpu_ref' is often embedded into user structure, and only * 'percpu_count_ptr' is required in fast path, move other fields * into 'percpu_ref_data', so we can reduce memory footprint in * fast path. */ struct percpu_ref_data *data; }; int __must_check percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp); void percpu_ref_exit(struct percpu_ref *ref); void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch); void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref); void percpu_ref_switch_to_percpu(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); bool percpu_ref_is_zero(struct percpu_ref *ref); /** * percpu_ref_kill - drop the initial ref * @ref: percpu_ref to kill * * Must be used to drop the initial ref on a percpu refcount; must be called * precisely once before shutdown. * * Switches @ref into atomic mode before gathering up the percpu counters * and dropping the initial ref. * * There are no implied RCU grace periods between kill and release. */ static inline void percpu_ref_kill(struct percpu_ref *ref) { percpu_ref_kill_and_confirm(ref, NULL); } /* * Internal helper. Don't use outside percpu-refcount proper. The * function doesn't return the pointer and let the caller test it for NULL * because doing so forces the compiler to generate two conditional * branches as it can't assume that @ref->percpu_count is not NULL. */ static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { unsigned long percpu_ptr; /* * The value of @ref->percpu_count_ptr is tested for * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then * used as a pointer. If the compiler generates a separate fetch * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in * between contaminating the pointer value, meaning that * READ_ONCE() is required when fetching it. * * The dependency ordering from the READ_ONCE() pairs * with smp_store_release() in __percpu_ref_switch_to_percpu(). */ percpu_ptr = READ_ONCE(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, * then we'd have to mask off DEAD separately as DEAD may be * visible without ATOMIC if we race with percpu_ref_kill(). DEAD * implies ATOMIC anyway. Test them together. */ if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD)) return false; *percpu_countp = (unsigned long __percpu *)percpu_ptr; return true; } /** * percpu_ref_get_many - increment a percpu refcount * @ref: percpu_ref to get * @nr: number of references to get * * Analogous to atomic_long_add(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else atomic_long_add(nr, &ref->data->count); rcu_read_unlock(); } /** * percpu_ref_get - increment a percpu refcount * @ref: percpu_ref to get * * Analogous to atomic_long_inc(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get(struct percpu_ref *ref) { percpu_ref_get_many(ref, 1); } /** * percpu_ref_tryget_many - try to increment a percpu refcount * @ref: percpu_ref to try-get * @nr: number of references to get * * Increment a percpu refcount by @nr unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; bool ret; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_add(*percpu_count, nr); ret = true; } else { ret = atomic_long_add_unless(&ref->data->count, nr, 0); } rcu_read_unlock(); return ret; } /** * percpu_ref_tryget - try to increment a percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget(struct percpu_ref *ref) { return percpu_ref_tryget_many(ref, 1); } /** * percpu_ref_tryget_live_rcu - same as percpu_ref_tryget_live() but the * caller is responsible for taking RCU. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live_rcu(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; bool ret = false; WARN_ON_ONCE(!rcu_read_lock_held()); if (likely(__ref_is_percpu(ref, &percpu_count))) { this_cpu_inc(*percpu_count); ret = true; } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->data->count); } return ret; } /** * percpu_ref_tryget_live - try to increment a live percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless it has already been killed. Returns * %true on success; %false on failure. * * Completion of percpu_ref_kill() in itself doesn't guarantee that this * function will fail. For such guarantee, percpu_ref_kill_and_confirm() * should be used. After the confirm_kill callback is invoked, it's * guaranteed that no new reference will be given out by * percpu_ref_tryget_live(). * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) { bool ret = false; rcu_read_lock(); ret = percpu_ref_tryget_live_rcu(ref); rcu_read_unlock(); return ret; } /** * percpu_ref_put_many - decrement a percpu refcount * @ref: percpu_ref to put * @nr: number of references to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count))) ref->data->release(ref); rcu_read_unlock(); } /** * percpu_ref_put - decrement a percpu refcount * @ref: percpu_ref to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put(struct percpu_ref *ref) { percpu_ref_put_many(ref, 1); } /** * percpu_ref_is_dying - test whether a percpu refcount is dying or dead * @ref: percpu_ref to test * * Returns %true if @ref is dying or dead. * * This function is safe to call as long as @ref is between init and exit * and the caller is responsible for synchronizing against state changes. */ static inline bool percpu_ref_is_dying(struct percpu_ref *ref) { return ref->percpu_count_ptr & __PERCPU_REF_DEAD; } #endif |
| 1 122 120 1 1 1 39 3 16 20 82 18 100 2 52 1 52 4 76 7 6 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 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * IEEE 802.11 defines * * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen * <jkmaline@cc.hut.fi> * Copyright (c) 2002-2003, Jouni Malinen <jkmaline@cc.hut.fi> * Copyright (c) 2005, Devicescape Software, Inc. * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net> * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH * Copyright (c) 2018 - 2026 Intel Corporation */ #ifndef LINUX_IEEE80211_H #define LINUX_IEEE80211_H #include <linux/types.h> #include <linux/if_ether.h> #include <linux/etherdevice.h> #include <linux/bitfield.h> #include <asm/byteorder.h> #include <linux/unaligned.h> /* * DS bit usage * * TA = transmitter address * RA = receiver address * DA = destination address * SA = source address * * ToDS FromDS A1(RA) A2(TA) A3 A4 Use * ----------------------------------------------------------------- * 0 0 DA SA BSSID - IBSS/DLS * 0 1 DA BSSID SA - AP -> STA * 1 0 BSSID SA DA - AP <- STA * 1 1 RA TA DA SA unspecified (WDS) */ #define FCS_LEN 4 #define IEEE80211_FCTL_VERS 0x0003 #define IEEE80211_FCTL_FTYPE 0x000c #define IEEE80211_FCTL_STYPE 0x00f0 #define IEEE80211_FCTL_TYPE (IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE) #define IEEE80211_FCTL_TODS 0x0100 #define IEEE80211_FCTL_FROMDS 0x0200 #define IEEE80211_FCTL_MOREFRAGS 0x0400 #define IEEE80211_FCTL_RETRY 0x0800 #define IEEE80211_FCTL_PM 0x1000 #define IEEE80211_FCTL_MOREDATA 0x2000 #define IEEE80211_FCTL_PROTECTED 0x4000 #define IEEE80211_FCTL_ORDER 0x8000 #define IEEE80211_FCTL_CTL_EXT 0x0f00 #define IEEE80211_SCTL_FRAG 0x000F #define IEEE80211_SCTL_SEQ 0xFFF0 #define IEEE80211_FTYPE_MGMT 0x0000 #define IEEE80211_FTYPE_CTL 0x0004 #define IEEE80211_FTYPE_DATA 0x0008 #define IEEE80211_FTYPE_EXT 0x000c /* management */ #define IEEE80211_STYPE_ASSOC_REQ 0x0000 #define IEEE80211_STYPE_ASSOC_RESP 0x0010 #define IEEE80211_STYPE_REASSOC_REQ 0x0020 #define IEEE80211_STYPE_REASSOC_RESP 0x0030 #define IEEE80211_STYPE_PROBE_REQ 0x0040 #define IEEE80211_STYPE_PROBE_RESP 0x0050 #define IEEE80211_STYPE_BEACON 0x0080 #define IEEE80211_STYPE_ATIM 0x0090 #define IEEE80211_STYPE_DISASSOC 0x00A0 #define IEEE80211_STYPE_AUTH 0x00B0 #define IEEE80211_STYPE_DEAUTH 0x00C0 #define IEEE80211_STYPE_ACTION 0x00D0 /* control */ #define IEEE80211_STYPE_TRIGGER 0x0020 #define IEEE80211_STYPE_CTL_EXT 0x0060 #define IEEE80211_STYPE_BACK_REQ 0x0080 #define IEEE80211_STYPE_BACK 0x0090 #define IEEE80211_STYPE_PSPOLL 0x00A0 #define IEEE80211_STYPE_RTS 0x00B0 #define IEEE80211_STYPE_CTS 0x00C0 #define IEEE80211_STYPE_ACK 0x00D0 #define IEEE80211_STYPE_CFEND 0x00E0 #define IEEE80211_STYPE_CFENDACK 0x00F0 /* data */ #define IEEE80211_STYPE_DATA 0x0000 #define IEEE80211_STYPE_DATA_CFACK 0x0010 #define IEEE80211_STYPE_DATA_CFPOLL 0x0020 #define IEEE80211_STYPE_DATA_CFACKPOLL 0x0030 #define IEEE80211_STYPE_NULLFUNC 0x0040 #define IEEE80211_STYPE_CFACK 0x0050 #define IEEE80211_STYPE_CFPOLL 0x0060 #define IEEE80211_STYPE_CFACKPOLL 0x0070 #define IEEE80211_STYPE_QOS_DATA 0x0080 #define IEEE80211_STYPE_QOS_DATA_CFACK 0x0090 #define IEEE80211_STYPE_QOS_DATA_CFPOLL 0x00A0 #define IEEE80211_STYPE_QOS_DATA_CFACKPOLL 0x00B0 #define IEEE80211_STYPE_QOS_NULLFUNC 0x00C0 #define IEEE80211_STYPE_QOS_CFACK 0x00D0 #define IEEE80211_STYPE_QOS_CFPOLL 0x00E0 #define IEEE80211_STYPE_QOS_CFACKPOLL 0x00F0 /* extension, added by 802.11ad */ #define IEEE80211_STYPE_DMG_BEACON 0x0000 #define IEEE80211_STYPE_S1G_BEACON 0x0010 #define IEEE80211_NDP_FTYPE_CTS 0 #define IEEE80211_NDP_FTYPE_CF_END 0 #define IEEE80211_NDP_FTYPE_PS_POLL 1 #define IEEE80211_NDP_FTYPE_ACK 2 #define IEEE80211_NDP_FTYPE_PS_POLL_ACK 3 #define IEEE80211_NDP_FTYPE_BA 4 #define IEEE80211_NDP_FTYPE_BF_REPORT_POLL 5 #define IEEE80211_NDP_FTYPE_PAGING 6 #define IEEE80211_NDP_FTYPE_PREQ 7 #define SM64(f, v) ((((u64)v) << f##_S) & f) /* NDP CMAC frame fields */ #define IEEE80211_NDP_FTYPE 0x0000000000000007 #define IEEE80211_NDP_FTYPE_S 0x0000000000000000 /* 1M Probe Request 11ah 9.9.3.1.1 */ #define IEEE80211_NDP_1M_PREQ_ANO 0x0000000000000008 #define IEEE80211_NDP_1M_PREQ_ANO_S 3 #define IEEE80211_NDP_1M_PREQ_CSSID 0x00000000000FFFF0 #define IEEE80211_NDP_1M_PREQ_CSSID_S 4 #define IEEE80211_NDP_1M_PREQ_RTYPE 0x0000000000100000 #define IEEE80211_NDP_1M_PREQ_RTYPE_S 20 #define IEEE80211_NDP_1M_PREQ_RSV 0x0000000001E00000 #define IEEE80211_NDP_1M_PREQ_RSV 0x0000000001E00000 /* 2M Probe Request 11ah 9.9.3.1.2 */ #define IEEE80211_NDP_2M_PREQ_ANO 0x0000000000000008 #define IEEE80211_NDP_2M_PREQ_ANO_S 3 #define IEEE80211_NDP_2M_PREQ_CSSID 0x0000000FFFFFFFF0 #define IEEE80211_NDP_2M_PREQ_CSSID_S 4 #define IEEE80211_NDP_2M_PREQ_RTYPE 0x0000001000000000 #define IEEE80211_NDP_2M_PREQ_RTYPE_S 36 #define IEEE80211_ANO_NETTYPE_WILD 15 /* control extension - for IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTL_EXT */ #define IEEE80211_CTL_EXT_POLL 0x2000 #define IEEE80211_CTL_EXT_SPR 0x3000 #define IEEE80211_CTL_EXT_GRANT 0x4000 #define IEEE80211_CTL_EXT_DMG_CTS 0x5000 #define IEEE80211_CTL_EXT_DMG_DTS 0x6000 #define IEEE80211_CTL_EXT_SSW 0x8000 #define IEEE80211_CTL_EXT_SSW_FBACK 0x9000 #define IEEE80211_CTL_EXT_SSW_ACK 0xa000 #define IEEE80211_SN_MASK ((IEEE80211_SCTL_SEQ) >> 4) #define IEEE80211_MAX_SN IEEE80211_SN_MASK #define IEEE80211_SN_MODULO (IEEE80211_MAX_SN + 1) /* PV1 Layout IEEE 802.11-2020 9.8.3.1 */ #define IEEE80211_PV1_FCTL_VERS 0x0003 #define IEEE80211_PV1_FCTL_FTYPE 0x001c #define IEEE80211_PV1_FCTL_STYPE 0x00e0 #define IEEE80211_PV1_FCTL_FROMDS 0x0100 #define IEEE80211_PV1_FCTL_MOREFRAGS 0x0200 #define IEEE80211_PV1_FCTL_PM 0x0400 #define IEEE80211_PV1_FCTL_MOREDATA 0x0800 #define IEEE80211_PV1_FCTL_PROTECTED 0x1000 #define IEEE80211_PV1_FCTL_END_SP 0x2000 #define IEEE80211_PV1_FCTL_RELAYED 0x4000 #define IEEE80211_PV1_FCTL_ACK_POLICY 0x8000 #define IEEE80211_PV1_FCTL_CTL_EXT 0x0f00 static inline bool ieee80211_sn_less(u16 sn1, u16 sn2) { return ((sn1 - sn2) & IEEE80211_SN_MASK) > (IEEE80211_SN_MODULO >> 1); } static inline bool ieee80211_sn_less_eq(u16 sn1, u16 sn2) { return ((sn2 - sn1) & IEEE80211_SN_MASK) <= (IEEE80211_SN_MODULO >> 1); } static inline u16 ieee80211_sn_add(u16 sn1, u16 sn2) { return (sn1 + sn2) & IEEE80211_SN_MASK; } static inline u16 ieee80211_sn_inc(u16 sn) { return ieee80211_sn_add(sn, 1); } static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) { return (sn1 - sn2) & IEEE80211_SN_MASK; } #define IEEE80211_SEQ_TO_SN(seq) (((seq) & IEEE80211_SCTL_SEQ) >> 4) #define IEEE80211_SN_TO_SEQ(ssn) (((ssn) << 4) & IEEE80211_SCTL_SEQ) /* miscellaneous IEEE 802.11 constants */ #define IEEE80211_MAX_FRAG_THRESHOLD 2352 #define IEEE80211_MAX_RTS_THRESHOLD 2353 #define IEEE80211_MAX_AID 2007 #define IEEE80211_MAX_AID_S1G 8191 #define IEEE80211_MAX_TIM_LEN 251 #define IEEE80211_MAX_MESH_PEERINGS 63 /* Maximum size for the MA-UNITDATA primitive, 802.11 standard section 6.2.1.1.2. 802.11e clarifies the figure in section 7.1.2. The frame body is up to 2304 octets long (maximum MSDU size) plus any crypt overhead. */ #define IEEE80211_MAX_DATA_LEN 2304 /* 802.11ad extends maximum MSDU size for DMG (freq > 40Ghz) networks * to 7920 bytes, see 8.2.3 General frame format */ #define IEEE80211_MAX_DATA_LEN_DMG 7920 /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */ #define IEEE80211_MAX_FRAME_LEN 2352 #define IEEE80211_MAX_SSID_LEN 32 #define IEEE80211_FIRST_TSPEC_TSID 8 #define IEEE80211_NUM_TIDS 16 /* number of user priorities 802.11 uses */ #define IEEE80211_NUM_UPS 8 /* number of ACs */ #define IEEE80211_NUM_ACS 4 #define IEEE80211_QOS_CTL_LEN 2 /* 1d tag mask */ #define IEEE80211_QOS_CTL_TAG1D_MASK 0x0007 /* TID mask */ #define IEEE80211_QOS_CTL_TID_MASK 0x000f /* EOSP */ #define IEEE80211_QOS_CTL_EOSP 0x0010 /* ACK policy */ #define IEEE80211_QOS_CTL_ACK_POLICY_NORMAL 0x0000 #define IEEE80211_QOS_CTL_ACK_POLICY_NOACK 0x0020 #define IEEE80211_QOS_CTL_ACK_POLICY_NO_EXPL 0x0040 #define IEEE80211_QOS_CTL_ACK_POLICY_BLOCKACK 0x0060 #define IEEE80211_QOS_CTL_ACK_POLICY_MASK 0x0060 /* A-MSDU 802.11n */ #define IEEE80211_QOS_CTL_A_MSDU_PRESENT 0x0080 /* Mesh Control 802.11s */ #define IEEE80211_QOS_CTL_MESH_CONTROL_PRESENT 0x0100 /* Mesh Power Save Level */ #define IEEE80211_QOS_CTL_MESH_PS_LEVEL 0x0200 /* Mesh Receiver Service Period Initiated */ #define IEEE80211_QOS_CTL_RSPI 0x0400 /* U-APSD queue for WMM IEs sent by AP */ #define IEEE80211_WMM_IE_AP_QOSINFO_UAPSD (1<<7) #define IEEE80211_WMM_IE_AP_QOSINFO_PARAM_SET_CNT_MASK 0x0f /* U-APSD queues for WMM IEs sent by STA */ #define IEEE80211_WMM_IE_STA_QOSINFO_AC_VO (1<<0) #define IEEE80211_WMM_IE_STA_QOSINFO_AC_VI (1<<1) #define IEEE80211_WMM_IE_STA_QOSINFO_AC_BK (1<<2) #define IEEE80211_WMM_IE_STA_QOSINFO_AC_BE (1<<3) #define IEEE80211_WMM_IE_STA_QOSINFO_AC_MASK 0x0f /* U-APSD max SP length for WMM IEs sent by STA */ #define IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL 0x00 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_2 0x01 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_4 0x02 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_6 0x03 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_MASK 0x03 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_SHIFT 5 /* trigger type within common_info of trigger frame */ #define IEEE80211_TRIGGER_TYPE_MASK 0xf #define IEEE80211_TRIGGER_TYPE_BASIC 0x0 #define IEEE80211_TRIGGER_TYPE_BFRP 0x1 #define IEEE80211_TRIGGER_TYPE_MU_BAR 0x2 #define IEEE80211_TRIGGER_TYPE_MU_RTS 0x3 #define IEEE80211_TRIGGER_TYPE_BSRP 0x4 #define IEEE80211_TRIGGER_TYPE_GCR_MU_BAR 0x5 #define IEEE80211_TRIGGER_TYPE_BQRP 0x6 #define IEEE80211_TRIGGER_TYPE_NFRP 0x7 /* UL-bandwidth within common_info of trigger frame */ #define IEEE80211_TRIGGER_ULBW_MASK 0xc0000 #define IEEE80211_TRIGGER_ULBW_20MHZ 0x0 #define IEEE80211_TRIGGER_ULBW_40MHZ 0x1 #define IEEE80211_TRIGGER_ULBW_80MHZ 0x2 #define IEEE80211_TRIGGER_ULBW_160_80P80MHZ 0x3 struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; struct_group(addrs, u8 addr1[ETH_ALEN]; u8 addr2[ETH_ALEN]; u8 addr3[ETH_ALEN]; ); __le16 seq_ctrl; u8 addr4[ETH_ALEN]; } __packed __aligned(2); struct ieee80211_hdr_3addr { __le16 frame_control; __le16 duration_id; u8 addr1[ETH_ALEN]; u8 addr2[ETH_ALEN]; u8 addr3[ETH_ALEN]; __le16 seq_ctrl; } __packed __aligned(2); struct ieee80211_qos_hdr { __le16 frame_control; __le16 duration_id; u8 addr1[ETH_ALEN]; u8 addr2[ETH_ALEN]; u8 addr3[ETH_ALEN]; __le16 seq_ctrl; __le16 qos_ctrl; } __packed __aligned(2); struct ieee80211_qos_hdr_4addr { __le16 frame_control; __le16 duration_id; u8 addr1[ETH_ALEN]; u8 addr2[ETH_ALEN]; u8 addr3[ETH_ALEN]; __le16 seq_ctrl; u8 addr4[ETH_ALEN]; __le16 qos_ctrl; } __packed __aligned(2); struct ieee80211_trigger { __le16 frame_control; __le16 duration; u8 ra[ETH_ALEN]; u8 ta[ETH_ALEN]; __le64 common_info; u8 variable[]; } __packed __aligned(2); /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame has to-DS set */ static inline bool ieee80211_has_tods(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_TODS)) != 0; } /** * ieee80211_has_fromds - check if IEEE80211_FCTL_FROMDS is set * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame has from-DS set */ static inline bool ieee80211_has_fromds(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FROMDS)) != 0; } /** * ieee80211_has_a4 - check if IEEE80211_FCTL_TODS and IEEE80211_FCTL_FROMDS are set * @fc: frame control bytes in little-endian byteorder * Return: whether or not it's a 4-address frame (from-DS and to-DS set) */ static inline bool ieee80211_has_a4(__le16 fc) { __le16 tmp = cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS); return (fc & tmp) == tmp; } /** * ieee80211_has_morefrags - check if IEEE80211_FCTL_MOREFRAGS is set * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame has more fragments (more frags bit set) */ static inline bool ieee80211_has_morefrags(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_MOREFRAGS)) != 0; } /** * ieee80211_has_retry - check if IEEE80211_FCTL_RETRY is set * @fc: frame control bytes in little-endian byteorder * Return: whether or not the retry flag is set */ static inline bool ieee80211_has_retry(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_RETRY)) != 0; } /** * ieee80211_has_pm - check if IEEE80211_FCTL_PM is set * @fc: frame control bytes in little-endian byteorder * Return: whether or not the power management flag is set */ static inline bool ieee80211_has_pm(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_PM)) != 0; } /** * ieee80211_has_moredata - check if IEEE80211_FCTL_MOREDATA is set * @fc: frame control bytes in little-endian byteorder * Return: whether or not the more data flag is set */ static inline bool ieee80211_has_moredata(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_MOREDATA)) != 0; } /** * ieee80211_has_protected - check if IEEE80211_FCTL_PROTECTED is set * @fc: frame control bytes in little-endian byteorder * Return: whether or not the protected flag is set */ static inline bool ieee80211_has_protected(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_PROTECTED)) != 0; } /** * ieee80211_has_order - check if IEEE80211_FCTL_ORDER is set * @fc: frame control bytes in little-endian byteorder * Return: whether or not the order flag is set */ static inline bool ieee80211_has_order(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_ORDER)) != 0; } /** * ieee80211_is_mgmt - check if type is IEEE80211_FTYPE_MGMT * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame type is management */ static inline bool ieee80211_is_mgmt(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT); } /** * ieee80211_is_ctl - check if type is IEEE80211_FTYPE_CTL * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame type is control */ static inline bool ieee80211_is_ctl(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL); } /** * ieee80211_is_data - check if type is IEEE80211_FTYPE_DATA * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a data frame */ static inline bool ieee80211_is_data(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA); } /** * ieee80211_is_ext - check if type is IEEE80211_FTYPE_EXT * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame type is extended */ static inline bool ieee80211_is_ext(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_EXT); } /** * ieee80211_is_data_qos - check if type is IEEE80211_FTYPE_DATA and IEEE80211_STYPE_QOS_DATA is set * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a QoS data frame */ static inline bool ieee80211_is_data_qos(__le16 fc) { /* * mask with QOS_DATA rather than IEEE80211_FCTL_STYPE as we just need * to check the one bit */ return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_STYPE_QOS_DATA)) == cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_DATA); } /** * ieee80211_is_data_present - check if type is IEEE80211_FTYPE_DATA and has data * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a QoS data frame that has data * (i.e. is not null data) */ static inline bool ieee80211_is_data_present(__le16 fc) { /* * mask with 0x40 and test that that bit is clear to only return true * for the data-containing substypes. */ return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | 0x40)) == cpu_to_le16(IEEE80211_FTYPE_DATA); } /** * ieee80211_is_assoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_REQ * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is an association request */ static inline bool ieee80211_is_assoc_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_REQ); } /** * ieee80211_is_assoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_RESP * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is an association response */ static inline bool ieee80211_is_assoc_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_RESP); } /** * ieee80211_is_reassoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_REQ * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a reassociation request */ static inline bool ieee80211_is_reassoc_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_REQ); } /** * ieee80211_is_reassoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_RESP * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a reassociation response */ static inline bool ieee80211_is_reassoc_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_RESP); } /** * ieee80211_is_probe_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_REQ * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a probe request */ static inline bool ieee80211_is_probe_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ); } /** * ieee80211_is_probe_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_RESP * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a probe response */ static inline bool ieee80211_is_probe_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP); } /** * ieee80211_is_beacon - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_BEACON * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a (regular, not S1G) beacon */ static inline bool ieee80211_is_beacon(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON); } /** * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is an ATIM frame */ static inline bool ieee80211_is_atim(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ATIM); } /** * ieee80211_is_disassoc - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DISASSOC * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a disassociation frame */ static inline bool ieee80211_is_disassoc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_DISASSOC); } /** * ieee80211_is_auth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_AUTH * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is an authentication frame */ static inline bool ieee80211_is_auth(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH); } /** * ieee80211_is_deauth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DEAUTH * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a deauthentication frame */ static inline bool ieee80211_is_deauth(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_DEAUTH); } /** * ieee80211_is_action - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ACTION * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is an action frame */ static inline bool ieee80211_is_action(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); } /** * ieee80211_is_back_req - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK_REQ * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a block-ACK request frame */ static inline bool ieee80211_is_back_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK_REQ); } /** * ieee80211_is_back - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a block-ACK frame */ static inline bool ieee80211_is_back(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK); } /** * ieee80211_is_pspoll - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_PSPOLL * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a PS-poll frame */ static inline bool ieee80211_is_pspoll(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_PSPOLL); } /** * ieee80211_is_rts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_RTS * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is an RTS frame */ static inline bool ieee80211_is_rts(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_RTS); } /** * ieee80211_is_cts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CTS * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a CTS frame */ static inline bool ieee80211_is_cts(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTS); } /** * ieee80211_is_ack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_ACK * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is an ACK frame */ static inline bool ieee80211_is_ack(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_ACK); } /** * ieee80211_is_cfend - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFEND * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a CF-end frame */ static inline bool ieee80211_is_cfend(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CFEND); } /** * ieee80211_is_cfendack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFENDACK * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a CF-end-ack frame */ static inline bool ieee80211_is_cfendack(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CFENDACK); } /** * ieee80211_is_nullfunc - check if frame is a regular (non-QoS) nullfunc frame * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a nullfunc frame */ static inline bool ieee80211_is_nullfunc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC); } /** * ieee80211_is_qos_nullfunc - check if frame is a QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a QoS nullfunc frame */ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC); } /** * ieee80211_is_trigger - check if frame is trigger frame * @fc: frame control field in little-endian byteorder * Return: whether or not the frame is a trigger frame */ static inline bool ieee80211_is_trigger(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_TRIGGER); } /** * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is a nullfunc or QoS nullfunc frame */ static inline bool ieee80211_is_any_nullfunc(__le16 fc) { return (ieee80211_is_nullfunc(fc) || ieee80211_is_qos_nullfunc(fc)); } /** * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set * @seq_ctrl: frame sequence control bytes in little-endian byteorder * Return: whether or not the frame is the first fragment (also true if * it's not fragmented at all) */ static inline bool ieee80211_is_first_frag(__le16 seq_ctrl) { return (seq_ctrl & cpu_to_le16(IEEE80211_SCTL_FRAG)) == 0; } /** * ieee80211_is_frag - check if a frame is a fragment * @hdr: 802.11 header of the frame * Return: whether or not the frame is a fragment */ static inline bool ieee80211_is_frag(struct ieee80211_hdr *hdr) { return ieee80211_has_morefrags(hdr->frame_control) || hdr->seq_ctrl & cpu_to_le16(IEEE80211_SCTL_FRAG); } static inline u16 ieee80211_get_sn(struct ieee80211_hdr *hdr) { return le16_get_bits(hdr->seq_ctrl, IEEE80211_SCTL_SEQ); } /** * struct ieee80211_quiet_ie - Quiet element * @count: Quiet Count * @period: Quiet Period * @duration: Quiet Duration * @offset: Quiet Offset * * This structure represents the payload of the "Quiet element" as * described in IEEE Std 802.11-2020 section 9.4.2.22. */ struct ieee80211_quiet_ie { u8 count; u8 period; __le16 duration; __le16 offset; } __packed; /** * struct ieee80211_msrment_ie - Measurement element * @token: Measurement Token * @mode: Measurement Report Mode * @type: Measurement Type * @request: Measurement Request or Measurement Report * * This structure represents the payload of both the "Measurement * Request element" and the "Measurement Report element" as described * in IEEE Std 802.11-2020 sections 9.4.2.20 and 9.4.2.21. */ struct ieee80211_msrment_ie { u8 token; u8 mode; u8 type; u8 request[]; } __packed; /** * struct ieee80211_channel_sw_ie - Channel Switch Announcement element * @mode: Channel Switch Mode * @new_ch_num: New Channel Number * @count: Channel Switch Count * * This structure represents the payload of the "Channel Switch * Announcement element" as described in IEEE Std 802.11-2020 section * 9.4.2.18. */ struct ieee80211_channel_sw_ie { u8 mode; u8 new_ch_num; u8 count; } __packed; /** * struct ieee80211_ext_chansw_ie - Extended Channel Switch Announcement element * @mode: Channel Switch Mode * @new_operating_class: New Operating Class * @new_ch_num: New Channel Number * @count: Channel Switch Count * * This structure represents the "Extended Channel Switch Announcement * element" as described in IEEE Std 802.11-2020 section 9.4.2.52. */ struct ieee80211_ext_chansw_ie { u8 mode; u8 new_operating_class; u8 new_ch_num; u8 count; } __packed; /** * struct ieee80211_sec_chan_offs_ie - secondary channel offset IE * @sec_chan_offs: secondary channel offset, uses IEEE80211_HT_PARAM_CHA_SEC_* * values here * This structure represents the "Secondary Channel Offset element" */ struct ieee80211_sec_chan_offs_ie { u8 sec_chan_offs; } __packed; /** * struct ieee80211_wide_bw_chansw_ie - wide bandwidth channel switch IE * @new_channel_width: New Channel Width * @new_center_freq_seg0: New Channel Center Frequency Segment 0 * @new_center_freq_seg1: New Channel Center Frequency Segment 1 * * This structure represents the payload of the "Wide Bandwidth * Channel Switch element" as described in IEEE Std 802.11-2020 * section 9.4.2.160. */ struct ieee80211_wide_bw_chansw_ie { u8 new_channel_width; u8 new_center_freq_seg0, new_center_freq_seg1; } __packed; /** * struct ieee80211_tim_ie - Traffic Indication Map information element * @dtim_count: DTIM Count * @dtim_period: DTIM Period * @bitmap_ctrl: Bitmap Control * @required_octet: "Syntatic sugar" to force the struct size to the * minimum valid size when carried in a non-S1G PPDU * @virtual_map: Partial Virtual Bitmap * * This structure represents the payload of the "TIM element" as * described in IEEE Std 802.11-2020 section 9.4.2.5. Note that this * definition is only applicable when the element is carried in a * non-S1G PPDU. When the TIM is carried in an S1G PPDU, the Bitmap * Control and Partial Virtual Bitmap may not be present. */ struct ieee80211_tim_ie { u8 dtim_count; u8 dtim_period; u8 bitmap_ctrl; union { u8 required_octet; DECLARE_FLEX_ARRAY(u8, virtual_map); }; } __packed; #define WLAN_SA_QUERY_TR_ID_LEN 2 #define WLAN_MEMBERSHIP_LEN 8 #define WLAN_USER_POSITION_LEN 16 /** * struct ieee80211_tpc_report_ie - TPC Report element * @tx_power: Transmit Power * @link_margin: Link Margin * * This structure represents the payload of the "TPC Report element" as * described in IEEE Std 802.11-2020 section 9.4.2.16. */ struct ieee80211_tpc_report_ie { u8 tx_power; u8 link_margin; } __packed; #define IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK GENMASK(2, 1) #define IEEE80211_ADDBA_EXT_FRAG_LEVEL_SHIFT 1 #define IEEE80211_ADDBA_EXT_NO_FRAG BIT(0) #define IEEE80211_ADDBA_EXT_BUF_SIZE_MASK GENMASK(7, 5) #define IEEE80211_ADDBA_EXT_BUF_SIZE_SHIFT 10 struct ieee80211_addba_ext_ie { u8 data; } __packed; struct ieee80211_ext { __le16 frame_control; __le16 duration; union { struct { u8 sa[ETH_ALEN]; __le32 timestamp; u8 change_seq; u8 variable[]; } __packed s1g_beacon; } u; } __packed __aligned(2); /** * struct ieee80211_bss_load_elem - BSS Load elemen * * Defined in section 9.4.2.26 in IEEE 802.11-REVme D4.1 * * @sta_count: total number of STAs currently associated with the AP. * @channel_util: Percentage of time that the access point sensed the channel * was busy. This value is in range [0, 255], the highest value means * 100% busy. * @avail_admission_capa: remaining amount of medium time used for admission * control. */ struct ieee80211_bss_load_elem { __le16 sta_count; u8 channel_util; __le16 avail_admission_capa; } __packed; struct ieee80211_mgmt { __le16 frame_control; __le16 duration; u8 da[ETH_ALEN]; u8 sa[ETH_ALEN]; u8 bssid[ETH_ALEN]; __le16 seq_ctrl; union { struct { __le16 auth_alg; __le16 auth_transaction; __le16 status_code; /* possibly followed by Challenge text */ u8 variable[]; } __packed auth; struct { __le16 reason_code; } __packed deauth; struct { __le16 capab_info; __le16 listen_interval; /* followed by SSID and Supported rates */ u8 variable[]; } __packed assoc_req; struct { __le16 capab_info; __le16 status_code; __le16 aid; /* followed by Supported rates */ u8 variable[]; } __packed assoc_resp, reassoc_resp; struct { __le16 capab_info; __le16 status_code; u8 variable[]; } __packed s1g_assoc_resp, s1g_reassoc_resp; struct { __le16 capab_info; __le16 listen_interval; u8 current_ap[ETH_ALEN]; /* followed by SSID and Supported rates */ u8 variable[]; } __packed reassoc_req; struct { __le16 reason_code; } __packed disassoc; struct { __le64 timestamp; __le16 beacon_int; __le16 capab_info; /* followed by some of SSID, Supported rates, * FH Params, DS Params, CF Params, IBSS Params, TIM */ u8 variable[]; } __packed beacon; struct { /* only variable items: SSID, Supported rates */ DECLARE_FLEX_ARRAY(u8, variable); } __packed probe_req; struct { __le64 timestamp; __le16 beacon_int; __le16 capab_info; /* followed by some of SSID, Supported rates, * FH Params, DS Params, CF Params, IBSS Params */ u8 variable[]; } __packed probe_resp; struct { u8 category; u8 action_code; union { struct { u8 dialog_token; u8 status_code; u8 variable[]; } __packed wme_action; struct{ u8 no_fixed_fields[0]; u8 variable[]; } __packed chan_switch; struct{ struct ieee80211_ext_chansw_ie data; u8 variable[]; } __packed ext_chan_switch; struct{ u8 dialog_token; u8 element_id; u8 length; struct ieee80211_msrment_ie msr_elem; } __packed measurement; struct{ u8 dialog_token; __le16 capab; __le16 timeout; __le16 start_seq_num; /* followed by BA Extension */ u8 variable[]; } __packed addba_req; struct{ u8 dialog_token; __le16 status; __le16 capab; __le16 timeout; /* followed by BA Extension */ u8 variable[]; } __packed addba_resp; struct{ __le16 params; __le16 reason_code; } __packed delba; struct { u8 no_fixed_fields[0]; u8 variable[]; } __packed self_prot; struct{ u8 no_fixed_fields[0]; u8 variable[]; } __packed mesh_action; struct { u8 trans_id[WLAN_SA_QUERY_TR_ID_LEN]; } __packed sa_query; struct { u8 smps_control; } __packed ht_smps; struct { u8 chanwidth; } __packed ht_notify_cw; struct { u8 dialog_token; __le16 capability; u8 variable[]; } __packed tdls_discover_resp; struct { u8 operating_mode; } __packed vht_opmode_notif; struct { u8 membership[WLAN_MEMBERSHIP_LEN]; u8 position[WLAN_USER_POSITION_LEN]; } __packed vht_group_notif; struct { u8 dialog_token; u8 tpc_elem_id; u8 tpc_elem_length; struct ieee80211_tpc_report_ie tpc; } __packed tpc_report; struct { u8 dialog_token; u8 follow_up; u8 tod[6]; u8 toa[6]; __le16 tod_error; __le16 toa_error; u8 variable[]; } __packed ftm; struct { u8 no_fixed_fields[0]; u8 variable[]; } __packed s1g; struct { u8 dialog_token; u8 follow_up; u32 tod; u32 toa; u8 max_tod_error; u8 max_toa_error; } __packed wnm_timing_msr; struct { u8 dialog_token; u8 variable[]; } __packed ttlm_req; struct { u8 dialog_token; __le16 status_code; u8 variable[]; } __packed ttlm_res; struct { u8 no_fixed_fields[0]; /* no variable fields either */ } __packed ttlm_tear_down; struct { u8 dialog_token; u8 variable[]; } __packed ml_reconf_req; struct { u8 dialog_token; u8 count; u8 variable[]; } __packed ml_reconf_resp; struct { u8 no_fixed_fields[0]; u8 variable[]; } __packed epcs; struct { u8 dialog_token; u8 control; u8 variable[]; } __packed eml_omn; }; } __packed action; DECLARE_FLEX_ARRAY(u8, body); /* Generic frame body */ } u; } __packed __aligned(2); /* Supported rates membership selectors */ #define BSS_MEMBERSHIP_SELECTOR_HT_PHY 127 #define BSS_MEMBERSHIP_SELECTOR_VHT_PHY 126 #define BSS_MEMBERSHIP_SELECTOR_GLK 125 #define BSS_MEMBERSHIP_SELECTOR_EPD 124 #define BSS_MEMBERSHIP_SELECTOR_SAE_H2E 123 #define BSS_MEMBERSHIP_SELECTOR_HE_PHY 122 #define BSS_MEMBERSHIP_SELECTOR_EHT_PHY 121 #define BSS_MEMBERSHIP_SELECTOR_UHR_PHY 120 #define BSS_MEMBERSHIP_SELECTOR_MIN BSS_MEMBERSHIP_SELECTOR_UHR_PHY #define IEEE80211_MIN_ACTION_SIZE(type) offsetofend(struct ieee80211_mgmt, u.action.type) /* Link Reconfiguration Status Duple field */ struct ieee80211_ml_reconf_status { u8 info; __le16 status; } __packed; #define IEEE80211_ML_RECONF_LINK_ID_MASK 0xf /* Management MIC information element (IEEE 802.11w) for CMAC */ struct ieee80211_mmie { u8 element_id; u8 length; __le16 key_id; u8 sequence_number[6]; u8 mic[8]; } __packed; /* Management MIC information element (IEEE 802.11w) for GMAC and CMAC-256 */ struct ieee80211_mmie_16 { u8 element_id; u8 length; __le16 key_id; u8 sequence_number[6]; u8 mic[16]; } __packed; /* Management MIC information element (IEEE 802.11w) for all variants */ struct ieee80211_mmie_var { u8 element_id; u8 length; __le16 key_id; u8 sequence_number[6]; u8 mic[]; /* 8 or 16 bytes */ } __packed; struct ieee80211_vendor_ie { u8 element_id; u8 len; u8 oui[3]; u8 oui_type; } __packed; struct ieee80211_wmm_ac_param { u8 aci_aifsn; /* AIFSN, ACM, ACI */ u8 cw; /* ECWmin, ECWmax (CW = 2^ECW - 1) */ __le16 txop_limit; } __packed; struct ieee80211_wmm_param_ie { u8 element_id; /* Element ID: 221 (0xdd); */ u8 len; /* Length: 24 */ /* required fields for WMM version 1 */ u8 oui[3]; /* 00:50:f2 */ u8 oui_type; /* 2 */ u8 oui_subtype; /* 1 */ u8 version; /* 1 for WMM version 1.0 */ u8 qos_info; /* AP/STA specific QoS info */ u8 reserved; /* 0 */ /* AC_BE, AC_BK, AC_VI, AC_VO */ struct ieee80211_wmm_ac_param ac[4]; } __packed; /* Control frames */ struct ieee80211_rts { __le16 frame_control; __le16 duration; u8 ra[ETH_ALEN]; u8 ta[ETH_ALEN]; } __packed __aligned(2); struct ieee80211_cts { __le16 frame_control; __le16 duration; u8 ra[ETH_ALEN]; } __packed __aligned(2); struct ieee80211_pspoll { __le16 frame_control; __le16 aid; u8 bssid[ETH_ALEN]; u8 ta[ETH_ALEN]; } __packed __aligned(2); /* TDLS */ /* Channel switch timing */ struct ieee80211_ch_switch_timing { __le16 switch_time; __le16 switch_timeout; } __packed; /* Link-id information element */ struct ieee80211_tdls_lnkie { u8 ie_type; /* Link Identifier IE */ u8 ie_len; u8 bssid[ETH_ALEN]; u8 init_sta[ETH_ALEN]; u8 resp_sta[ETH_ALEN]; } __packed; struct ieee80211_tdls_data { u8 da[ETH_ALEN]; u8 sa[ETH_ALEN]; __be16 ether_type; u8 payload_type; u8 category; u8 action_code; union { struct { u8 dialog_token; __le16 capability; u8 variable[]; } __packed setup_req; struct { __le16 status_code; u8 dialog_token; __le16 capability; u8 variable[]; } __packed setup_resp; struct { __le16 status_code; u8 dialog_token; u8 variable[]; } __packed setup_cfm; struct { __le16 reason_code; u8 variable[]; } __packed teardown; struct { u8 dialog_token; u8 variable[]; } __packed discover_req; struct { u8 target_channel; u8 oper_class; u8 variable[]; } __packed chan_switch_req; struct { __le16 status_code; u8 variable[]; } __packed chan_switch_resp; } u; } __packed; /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 #define WLAN_AUTH_FT 2 #define WLAN_AUTH_SAE 3 #define WLAN_AUTH_FILS_SK 4 #define WLAN_AUTH_FILS_SK_PFS 5 #define WLAN_AUTH_FILS_PK 6 #define WLAN_AUTH_IEEE8021X 8 #define WLAN_AUTH_EPPKE 9 #define WLAN_AUTH_LEAP 128 #define WLAN_AUTH_CHALLENGE_LEN 128 #define WLAN_CAPABILITY_ESS (1<<0) #define WLAN_CAPABILITY_IBSS (1<<1) /* * A mesh STA sets the ESS and IBSS capability bits to zero. * however, this holds true for p2p probe responses (in the p2p_find * phase) as well. */ #define WLAN_CAPABILITY_IS_STA_BSS(cap) \ (!((cap) & (WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS))) #define WLAN_CAPABILITY_CF_POLLABLE (1<<2) #define WLAN_CAPABILITY_CF_POLL_REQUEST (1<<3) #define WLAN_CAPABILITY_PRIVACY (1<<4) #define WLAN_CAPABILITY_SHORT_PREAMBLE (1<<5) #define WLAN_CAPABILITY_PBCC (1<<6) #define WLAN_CAPABILITY_CHANNEL_AGILITY (1<<7) /* 802.11h */ #define WLAN_CAPABILITY_SPECTRUM_MGMT (1<<8) #define WLAN_CAPABILITY_QOS (1<<9) #define WLAN_CAPABILITY_SHORT_SLOT_TIME (1<<10) #define WLAN_CAPABILITY_APSD (1<<11) #define WLAN_CAPABILITY_RADIO_MEASURE (1<<12) #define WLAN_CAPABILITY_DSSS_OFDM (1<<13) #define WLAN_CAPABILITY_DEL_BACK (1<<14) #define WLAN_CAPABILITY_IMM_BACK (1<<15) /* DMG (60gHz) 802.11ad */ /* type - bits 0..1 */ #define WLAN_CAPABILITY_DMG_TYPE_MASK (3<<0) #define WLAN_CAPABILITY_DMG_TYPE_IBSS (1<<0) /* Tx by: STA */ #define WLAN_CAPABILITY_DMG_TYPE_PBSS (2<<0) /* Tx by: PCP */ #define WLAN_CAPABILITY_DMG_TYPE_AP (3<<0) /* Tx by: AP */ #define WLAN_CAPABILITY_DMG_CBAP_ONLY (1<<2) #define WLAN_CAPABILITY_DMG_CBAP_SOURCE (1<<3) #define WLAN_CAPABILITY_DMG_PRIVACY (1<<4) #define WLAN_CAPABILITY_DMG_ECPAC (1<<5) #define WLAN_CAPABILITY_DMG_SPECTRUM_MGMT (1<<8) #define WLAN_CAPABILITY_DMG_RADIO_MEASURE (1<<12) /* measurement */ #define IEEE80211_SPCT_MSR_RPRT_MODE_LATE (1<<0) #define IEEE80211_SPCT_MSR_RPRT_MODE_INCAPABLE (1<<1) #define IEEE80211_SPCT_MSR_RPRT_MODE_REFUSED (1<<2) #define IEEE80211_SPCT_MSR_RPRT_TYPE_BASIC 0 #define IEEE80211_SPCT_MSR_RPRT_TYPE_CCA 1 #define IEEE80211_SPCT_MSR_RPRT_TYPE_RPI 2 #define IEEE80211_SPCT_MSR_RPRT_TYPE_LCI 8 #define IEEE80211_SPCT_MSR_RPRT_TYPE_CIVIC 11 /* 802.11g ERP information element */ #define WLAN_ERP_NON_ERP_PRESENT (1<<0) #define WLAN_ERP_USE_PROTECTION (1<<1) #define WLAN_ERP_BARKER_PREAMBLE (1<<2) /* WLAN_ERP_BARKER_PREAMBLE values */ enum { WLAN_ERP_PREAMBLE_SHORT = 0, WLAN_ERP_PREAMBLE_LONG = 1, }; /* Band ID, 802.11ad #8.4.1.45 */ enum { IEEE80211_BANDID_TV_WS = 0, /* TV white spaces */ IEEE80211_BANDID_SUB1 = 1, /* Sub-1 GHz (excluding TV white spaces) */ IEEE80211_BANDID_2G = 2, /* 2.4 GHz */ IEEE80211_BANDID_3G = 3, /* 3.6 GHz */ IEEE80211_BANDID_5G = 4, /* 4.9 and 5 GHz */ IEEE80211_BANDID_60G = 5, /* 60 GHz */ }; /* Status codes */ enum ieee80211_statuscode { WLAN_STATUS_SUCCESS = 0, WLAN_STATUS_UNSPECIFIED_FAILURE = 1, WLAN_STATUS_CAPS_UNSUPPORTED = 10, WLAN_STATUS_REASSOC_NO_ASSOC = 11, WLAN_STATUS_ASSOC_DENIED_UNSPEC = 12, WLAN_STATUS_NOT_SUPPORTED_AUTH_ALG = 13, WLAN_STATUS_UNKNOWN_AUTH_TRANSACTION = 14, WLAN_STATUS_CHALLENGE_FAIL = 15, WLAN_STATUS_AUTH_TIMEOUT = 16, WLAN_STATUS_AP_UNABLE_TO_HANDLE_NEW_STA = 17, WLAN_STATUS_ASSOC_DENIED_RATES = 18, /* 802.11b */ WLAN_STATUS_ASSOC_DENIED_NOSHORTPREAMBLE = 19, WLAN_STATUS_ASSOC_DENIED_NOPBCC = 20, WLAN_STATUS_ASSOC_DENIED_NOAGILITY = 21, /* 802.11h */ WLAN_STATUS_ASSOC_DENIED_NOSPECTRUM = 22, WLAN_STATUS_ASSOC_REJECTED_BAD_POWER = 23, WLAN_STATUS_ASSOC_REJECTED_BAD_SUPP_CHAN = 24, /* 802.11g */ WLAN_STATUS_ASSOC_DENIED_NOSHORTTIME = 25, WLAN_STATUS_ASSOC_DENIED_NODSSSOFDM = 26, /* 802.11w */ WLAN_STATUS_ASSOC_REJECTED_TEMPORARILY = 30, WLAN_STATUS_ROBUST_MGMT_FRAME_POLICY_VIOLATION = 31, /* 802.11i */ WLAN_STATUS_INVALID_IE = 40, WLAN_STATUS_INVALID_GROUP_CIPHER = 41, WLAN_STATUS_INVALID_PAIRWISE_CIPHER = 42, WLAN_STATUS_INVALID_AKMP = 43, WLAN_STATUS_UNSUPP_RSN_VERSION = 44, WLAN_STATUS_INVALID_RSN_IE_CAP = 45, WLAN_STATUS_CIPHER_SUITE_REJECTED = 46, /* 802.11e */ WLAN_STATUS_UNSPECIFIED_QOS = 32, WLAN_STATUS_ASSOC_DENIED_NOBANDWIDTH = 33, WLAN_STATUS_ASSOC_DENIED_LOWACK = 34, WLAN_STATUS_ASSOC_DENIED_UNSUPP_QOS = 35, WLAN_STATUS_REQUEST_DECLINED = 37, WLAN_STATUS_INVALID_QOS_PARAM = 38, WLAN_STATUS_CHANGE_TSPEC = 39, WLAN_STATUS_WAIT_TS_DELAY = 47, WLAN_STATUS_NO_DIRECT_LINK = 48, WLAN_STATUS_STA_NOT_PRESENT = 49, WLAN_STATUS_STA_NOT_QSTA = 50, /* 802.11s */ WLAN_STATUS_ANTI_CLOG_REQUIRED = 76, WLAN_STATUS_FCG_NOT_SUPP = 78, WLAN_STATUS_STA_NO_TBTT = 78, /* 802.11ad */ WLAN_STATUS_REJECTED_WITH_SUGGESTED_CHANGES = 39, WLAN_STATUS_REJECTED_FOR_DELAY_PERIOD = 47, WLAN_STATUS_REJECT_WITH_SCHEDULE = 83, WLAN_STATUS_PENDING_ADMITTING_FST_SESSION = 86, WLAN_STATUS_PERFORMING_FST_NOW = 87, WLAN_STATUS_PENDING_GAP_IN_BA_WINDOW = 88, WLAN_STATUS_REJECT_U_PID_SETTING = 89, WLAN_STATUS_REJECT_DSE_BAND = 96, WLAN_STATUS_DENIED_WITH_SUGGESTED_BAND_AND_CHANNEL = 99, WLAN_STATUS_DENIED_DUE_TO_SPECTRUM_MANAGEMENT = 103, /* 802.11ah */ WLAN_STATUS_REJECTED_NDP_BLOCK_ACK_SUGGESTED = 109, /* 802.11ai */ WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 112, WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 113, WLAN_STATUS_SAE_HASH_TO_ELEMENT = 126, WLAN_STATUS_SAE_PK = 127, WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING = 133, WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED = 134, WLAN_STATUS_8021X_AUTH_SUCCESS = 153, }; /* Reason codes */ enum ieee80211_reasoncode { WLAN_REASON_UNSPECIFIED = 1, WLAN_REASON_PREV_AUTH_NOT_VALID = 2, WLAN_REASON_DEAUTH_LEAVING = 3, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY = 4, WLAN_REASON_DISASSOC_AP_BUSY = 5, WLAN_REASON_CLASS2_FRAME_FROM_NONAUTH_STA = 6, WLAN_REASON_CLASS3_FRAME_FROM_NONASSOC_STA = 7, WLAN_REASON_DISASSOC_STA_HAS_LEFT = 8, WLAN_REASON_STA_REQ_ASSOC_WITHOUT_AUTH = 9, /* 802.11h */ WLAN_REASON_DISASSOC_BAD_POWER = 10, WLAN_REASON_DISASSOC_BAD_SUPP_CHAN = 11, /* 802.11i */ WLAN_REASON_INVALID_IE = 13, WLAN_REASON_MIC_FAILURE = 14, WLAN_REASON_4WAY_HANDSHAKE_TIMEOUT = 15, WLAN_REASON_GROUP_KEY_HANDSHAKE_TIMEOUT = 16, WLAN_REASON_IE_DIFFERENT = 17, WLAN_REASON_INVALID_GROUP_CIPHER = 18, WLAN_REASON_INVALID_PAIRWISE_CIPHER = 19, WLAN_REASON_INVALID_AKMP = 20, WLAN_REASON_UNSUPP_RSN_VERSION = 21, WLAN_REASON_INVALID_RSN_IE_CAP = 22, WLAN_REASON_IEEE8021X_FAILED = 23, WLAN_REASON_CIPHER_SUITE_REJECTED = 24, /* TDLS (802.11z) */ WLAN_REASON_TDLS_TEARDOWN_UNREACHABLE = 25, WLAN_REASON_TDLS_TEARDOWN_UNSPECIFIED = 26, /* 802.11e */ WLAN_REASON_DISASSOC_UNSPECIFIED_QOS = 32, WLAN_REASON_DISASSOC_QAP_NO_BANDWIDTH = 33, WLAN_REASON_DISASSOC_LOW_ACK = 34, WLAN_REASON_DISASSOC_QAP_EXCEED_TXOP = 35, WLAN_REASON_QSTA_LEAVE_QBSS = 36, WLAN_REASON_QSTA_NOT_USE = 37, WLAN_REASON_QSTA_REQUIRE_SETUP = 38, WLAN_REASON_QSTA_TIMEOUT = 39, WLAN_REASON_QSTA_CIPHER_NOT_SUPP = 45, /* 802.11s */ WLAN_REASON_MESH_PEER_CANCELED = 52, WLAN_REASON_MESH_MAX_PEERS = 53, WLAN_REASON_MESH_CONFIG = 54, WLAN_REASON_MESH_CLOSE = 55, WLAN_REASON_MESH_MAX_RETRIES = 56, WLAN_REASON_MESH_CONFIRM_TIMEOUT = 57, WLAN_REASON_MESH_INVALID_GTK = 58, WLAN_REASON_MESH_INCONSISTENT_PARAM = 59, WLAN_REASON_MESH_INVALID_SECURITY = 60, WLAN_REASON_MESH_PATH_ERROR = 61, WLAN_REASON_MESH_PATH_NOFORWARD = 62, WLAN_REASON_MESH_PATH_DEST_UNREACHABLE = 63, WLAN_REASON_MAC_EXISTS_IN_MBSS = 64, WLAN_REASON_MESH_CHAN_REGULATORY = 65, WLAN_REASON_MESH_CHAN = 66, }; /* Information Element IDs */ enum ieee80211_eid { WLAN_EID_SSID = 0, WLAN_EID_SUPP_RATES = 1, WLAN_EID_FH_PARAMS = 2, /* reserved now */ WLAN_EID_DS_PARAMS = 3, WLAN_EID_CF_PARAMS = 4, WLAN_EID_TIM = 5, WLAN_EID_IBSS_PARAMS = 6, WLAN_EID_COUNTRY = 7, /* 8, 9 reserved */ WLAN_EID_REQUEST = 10, WLAN_EID_QBSS_LOAD = 11, WLAN_EID_EDCA_PARAM_SET = 12, WLAN_EID_TSPEC = 13, WLAN_EID_TCLAS = 14, WLAN_EID_SCHEDULE = 15, WLAN_EID_CHALLENGE = 16, /* 17-31 reserved for challenge text extension */ WLAN_EID_PWR_CONSTRAINT = 32, WLAN_EID_PWR_CAPABILITY = 33, WLAN_EID_TPC_REQUEST = 34, WLAN_EID_TPC_REPORT = 35, WLAN_EID_SUPPORTED_CHANNELS = 36, WLAN_EID_CHANNEL_SWITCH = 37, WLAN_EID_MEASURE_REQUEST = 38, WLAN_EID_MEASURE_REPORT = 39, WLAN_EID_QUIET = 40, WLAN_EID_IBSS_DFS = 41, WLAN_EID_ERP_INFO = 42, WLAN_EID_TS_DELAY = 43, WLAN_EID_TCLAS_PROCESSING = 44, WLAN_EID_HT_CAPABILITY = 45, WLAN_EID_QOS_CAPA = 46, /* 47 reserved for Broadcom */ WLAN_EID_RSN = 48, WLAN_EID_802_15_COEX = 49, WLAN_EID_EXT_SUPP_RATES = 50, WLAN_EID_AP_CHAN_REPORT = 51, WLAN_EID_NEIGHBOR_REPORT = 52, WLAN_EID_RCPI = 53, WLAN_EID_MOBILITY_DOMAIN = 54, WLAN_EID_FAST_BSS_TRANSITION = 55, WLAN_EID_TIMEOUT_INTERVAL = 56, WLAN_EID_RIC_DATA = 57, WLAN_EID_DSE_REGISTERED_LOCATION = 58, WLAN_EID_SUPPORTED_REGULATORY_CLASSES = 59, WLAN_EID_EXT_CHANSWITCH_ANN = 60, WLAN_EID_HT_OPERATION = 61, WLAN_EID_SECONDARY_CHANNEL_OFFSET = 62, WLAN_EID_BSS_AVG_ACCESS_DELAY = 63, WLAN_EID_ANTENNA_INFO = 64, WLAN_EID_RSNI = 65, WLAN_EID_MEASUREMENT_PILOT_TX_INFO = 66, WLAN_EID_BSS_AVAILABLE_CAPACITY = 67, WLAN_EID_BSS_AC_ACCESS_DELAY = 68, WLAN_EID_TIME_ADVERTISEMENT = 69, WLAN_EID_RRM_ENABLED_CAPABILITIES = 70, WLAN_EID_MULTIPLE_BSSID = 71, WLAN_EID_BSS_COEX_2040 = 72, WLAN_EID_BSS_INTOLERANT_CHL_REPORT = 73, WLAN_EID_OVERLAP_BSS_SCAN_PARAM = 74, WLAN_EID_RIC_DESCRIPTOR = 75, WLAN_EID_MMIE = 76, WLAN_EID_ASSOC_COMEBACK_TIME = 77, WLAN_EID_EVENT_REQUEST = 78, WLAN_EID_EVENT_REPORT = 79, WLAN_EID_DIAGNOSTIC_REQUEST = 80, WLAN_EID_DIAGNOSTIC_REPORT = 81, WLAN_EID_LOCATION_PARAMS = 82, WLAN_EID_NON_TX_BSSID_CAP = 83, WLAN_EID_SSID_LIST = 84, WLAN_EID_MULTI_BSSID_IDX = 85, WLAN_EID_FMS_DESCRIPTOR = 86, WLAN_EID_FMS_REQUEST = 87, WLAN_EID_FMS_RESPONSE = 88, WLAN_EID_QOS_TRAFFIC_CAPA = 89, WLAN_EID_BSS_MAX_IDLE_PERIOD = 90, WLAN_EID_TSF_REQUEST = 91, WLAN_EID_TSF_RESPOSNE = 92, WLAN_EID_WNM_SLEEP_MODE = 93, WLAN_EID_TIM_BCAST_REQ = 94, WLAN_EID_TIM_BCAST_RESP = 95, WLAN_EID_COLL_IF_REPORT = 96, WLAN_EID_CHANNEL_USAGE = 97, WLAN_EID_TIME_ZONE = 98, WLAN_EID_DMS_REQUEST = 99, WLAN_EID_DMS_RESPONSE = 100, WLAN_EID_LINK_ID = 101, WLAN_EID_WAKEUP_SCHEDUL = 102, /* 103 reserved */ WLAN_EID_CHAN_SWITCH_TIMING = 104, WLAN_EID_PTI_CONTROL = 105, WLAN_EID_PU_BUFFER_STATUS = 106, WLAN_EID_INTERWORKING = 107, WLAN_EID_ADVERTISEMENT_PROTOCOL = 108, WLAN_EID_EXPEDITED_BW_REQ = 109, WLAN_EID_QOS_MAP_SET = 110, WLAN_EID_ROAMING_CONSORTIUM = 111, WLAN_EID_EMERGENCY_ALERT = 112, WLAN_EID_MESH_CONFIG = 113, WLAN_EID_MESH_ID = 114, WLAN_EID_LINK_METRIC_REPORT = 115, WLAN_EID_CONGESTION_NOTIFICATION = 116, WLAN_EID_PEER_MGMT = 117, WLAN_EID_CHAN_SWITCH_PARAM = 118, WLAN_EID_MESH_AWAKE_WINDOW = 119, WLAN_EID_BEACON_TIMING = 120, WLAN_EID_MCCAOP_SETUP_REQ = 121, WLAN_EID_MCCAOP_SETUP_RESP = 122, WLAN_EID_MCCAOP_ADVERT = 123, WLAN_EID_MCCAOP_TEARDOWN = 124, WLAN_EID_GANN = 125, WLAN_EID_RANN = 126, WLAN_EID_EXT_CAPABILITY = 127, /* 128, 129 reserved for Agere */ WLAN_EID_PREQ = 130, WLAN_EID_PREP = 131, WLAN_EID_PERR = 132, /* 133-136 reserved for Cisco */ WLAN_EID_PXU = 137, WLAN_EID_PXUC = 138, WLAN_EID_AUTH_MESH_PEER_EXCH = 139, WLAN_EID_MIC = 140, WLAN_EID_DESTINATION_URI = 141, WLAN_EID_UAPSD_COEX = 142, WLAN_EID_WAKEUP_SCHEDULE = 143, WLAN_EID_EXT_SCHEDULE = 144, WLAN_EID_STA_AVAILABILITY = 145, WLAN_EID_DMG_TSPEC = 146, WLAN_EID_DMG_AT = 147, WLAN_EID_DMG_CAP = 148, /* 149 reserved for Cisco */ WLAN_EID_CISCO_VENDOR_SPECIFIC = 150, WLAN_EID_DMG_OPERATION = 151, WLAN_EID_DMG_BSS_PARAM_CHANGE = 152, WLAN_EID_DMG_BEAM_REFINEMENT = 153, WLAN_EID_CHANNEL_MEASURE_FEEDBACK = 154, /* 155-156 reserved for Cisco */ WLAN_EID_AWAKE_WINDOW = 157, WLAN_EID_MULTI_BAND = 158, WLAN_EID_ADDBA_EXT = 159, WLAN_EID_NEXT_PCP_LIST = 160, WLAN_EID_PCP_HANDOVER = 161, WLAN_EID_DMG_LINK_MARGIN = 162, WLAN_EID_SWITCHING_STREAM = 163, WLAN_EID_SESSION_TRANSITION = 164, WLAN_EID_DYN_TONE_PAIRING_REPORT = 165, WLAN_EID_CLUSTER_REPORT = 166, WLAN_EID_RELAY_CAP = 167, WLAN_EID_RELAY_XFER_PARAM_SET = 168, WLAN_EID_BEAM_LINK_MAINT = 169, WLAN_EID_MULTIPLE_MAC_ADDR = 170, WLAN_EID_U_PID = 171, WLAN_EID_DMG_LINK_ADAPT_ACK = 172, /* 173 reserved for Symbol */ WLAN_EID_MCCAOP_ADV_OVERVIEW = 174, WLAN_EID_QUIET_PERIOD_REQ = 175, /* 176 reserved for Symbol */ WLAN_EID_QUIET_PERIOD_RESP = 177, /* 178-179 reserved for Symbol */ /* 180 reserved for ISO/IEC 20011 */ WLAN_EID_EPAC_POLICY = 182, WLAN_EID_CLISTER_TIME_OFF = 183, WLAN_EID_INTER_AC_PRIO = 184, WLAN_EID_SCS_DESCRIPTOR = 185, WLAN_EID_QLOAD_REPORT = 186, WLAN_EID_HCCA_TXOP_UPDATE_COUNT = 187, WLAN_EID_HL_STREAM_ID = 188, WLAN_EID_GCR_GROUP_ADDR = 189, WLAN_EID_ANTENNA_SECTOR_ID_PATTERN = 190, WLAN_EID_VHT_CAPABILITY = 191, WLAN_EID_VHT_OPERATION = 192, WLAN_EID_EXTENDED_BSS_LOAD = 193, WLAN_EID_WIDE_BW_CHANNEL_SWITCH = 194, WLAN_EID_TX_POWER_ENVELOPE = 195, WLAN_EID_CHANNEL_SWITCH_WRAPPER = 196, WLAN_EID_AID = 197, WLAN_EID_QUIET_CHANNEL = 198, WLAN_EID_OPMODE_NOTIF = 199, WLAN_EID_REDUCED_NEIGHBOR_REPORT = 201, WLAN_EID_AID_REQUEST = 210, WLAN_EID_AID_RESPONSE = 211, WLAN_EID_S1G_BCN_COMPAT = 213, WLAN_EID_S1G_SHORT_BCN_INTERVAL = 214, WLAN_EID_S1G_TWT = 216, WLAN_EID_S1G_CAPABILITIES = 217, WLAN_EID_VENDOR_SPECIFIC = 221, WLAN_EID_QOS_PARAMETER = 222, WLAN_EID_S1G_OPERATION = 232, WLAN_EID_CAG_NUMBER = 237, WLAN_EID_AP_CSN = 239, WLAN_EID_FILS_INDICATION = 240, WLAN_EID_DILS = 241, WLAN_EID_FRAGMENT = 242, WLAN_EID_RSNX = 244, WLAN_EID_EXTENSION = 255 }; /* Element ID Extensions for Element ID 255 */ enum ieee80211_eid_ext { WLAN_EID_EXT_ASSOC_DELAY_INFO = 1, WLAN_EID_EXT_FILS_REQ_PARAMS = 2, WLAN_EID_EXT_FILS_KEY_CONFIRM = 3, WLAN_EID_EXT_FILS_SESSION = 4, WLAN_EID_EXT_FILS_HLP_CONTAINER = 5, WLAN_EID_EXT_FILS_IP_ADDR_ASSIGN = 6, WLAN_EID_EXT_KEY_DELIVERY = 7, WLAN_EID_EXT_FILS_WRAPPED_DATA = 8, WLAN_EID_EXT_FILS_PUBLIC_KEY = 12, WLAN_EID_EXT_FILS_NONCE = 13, WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE = 14, WLAN_EID_EXT_DH_PARAMETER = 32, WLAN_EID_EXT_HE_CAPABILITY = 35, WLAN_EID_EXT_HE_OPERATION = 36, WLAN_EID_EXT_UORA = 37, WLAN_EID_EXT_HE_MU_EDCA = 38, WLAN_EID_EXT_HE_SPR = 39, WLAN_EID_EXT_NDP_FEEDBACK_REPORT_PARAMSET = 41, WLAN_EID_EXT_BSS_COLOR_CHG_ANN = 42, WLAN_EID_EXT_QUIET_TIME_PERIOD_SETUP = 43, WLAN_EID_EXT_ESS_REPORT = 45, WLAN_EID_EXT_OPS = 46, WLAN_EID_EXT_HE_BSS_LOAD = 47, WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME = 52, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION = 55, WLAN_EID_EXT_NON_INHERITANCE = 56, WLAN_EID_EXT_KNOWN_BSSID = 57, WLAN_EID_EXT_SHORT_SSID_LIST = 58, WLAN_EID_EXT_HE_6GHZ_CAPA = 59, WLAN_EID_EXT_UL_MU_POWER_CAPA = 60, WLAN_EID_EXT_EHT_OPERATION = 106, WLAN_EID_EXT_EHT_MULTI_LINK = 107, WLAN_EID_EXT_EHT_CAPABILITY = 108, WLAN_EID_EXT_TID_TO_LINK_MAPPING = 109, WLAN_EID_EXT_BANDWIDTH_INDICATION = 135, WLAN_EID_EXT_KNOWN_STA_IDENTIFCATION = 136, WLAN_EID_EXT_NON_AP_STA_REG_CON = 137, WLAN_EID_EXT_UHR_OPER = 151, WLAN_EID_EXT_UHR_CAPA = 152, WLAN_EID_EXT_MACP = 153, WLAN_EID_EXT_SMD = 154, WLAN_EID_EXT_BSS_SMD_TRANS_PARAMS = 155, WLAN_EID_EXT_CHAN_USAGE = 156, WLAN_EID_EXT_UHR_MODE_CHG = 157, WLAN_EID_EXT_UHR_PARAM_UPD = 158, WLAN_EID_EXT_TXPI = 159, }; /* Action category code */ enum ieee80211_category { WLAN_CATEGORY_SPECTRUM_MGMT = 0, WLAN_CATEGORY_QOS = 1, WLAN_CATEGORY_DLS = 2, WLAN_CATEGORY_BACK = 3, WLAN_CATEGORY_PUBLIC = 4, WLAN_CATEGORY_RADIO_MEASUREMENT = 5, WLAN_CATEGORY_FAST_BBS_TRANSITION = 6, WLAN_CATEGORY_HT = 7, WLAN_CATEGORY_SA_QUERY = 8, WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION = 9, WLAN_CATEGORY_WNM = 10, WLAN_CATEGORY_WNM_UNPROTECTED = 11, WLAN_CATEGORY_TDLS = 12, WLAN_CATEGORY_MESH_ACTION = 13, WLAN_CATEGORY_MULTIHOP_ACTION = 14, WLAN_CATEGORY_SELF_PROTECTED = 15, WLAN_CATEGORY_DMG = 16, WLAN_CATEGORY_WMM = 17, WLAN_CATEGORY_FST = 18, WLAN_CATEGORY_UNPROT_DMG = 20, WLAN_CATEGORY_VHT = 21, WLAN_CATEGORY_S1G = 22, WLAN_CATEGORY_PROTECTED_EHT = 37, WLAN_CATEGORY_VENDOR_SPECIFIC_PROTECTED = 126, WLAN_CATEGORY_VENDOR_SPECIFIC = 127, }; /* SPECTRUM_MGMT action code */ enum ieee80211_spectrum_mgmt_actioncode { WLAN_ACTION_SPCT_MSR_REQ = 0, WLAN_ACTION_SPCT_MSR_RPRT = 1, WLAN_ACTION_SPCT_TPC_REQ = 2, WLAN_ACTION_SPCT_TPC_RPRT = 3, WLAN_ACTION_SPCT_CHL_SWITCH = 4, }; /* Self Protected Action codes */ enum ieee80211_self_protected_actioncode { WLAN_SP_RESERVED = 0, WLAN_SP_MESH_PEERING_OPEN = 1, WLAN_SP_MESH_PEERING_CONFIRM = 2, WLAN_SP_MESH_PEERING_CLOSE = 3, WLAN_SP_MGK_INFORM = 4, WLAN_SP_MGK_ACK = 5, }; /* Unprotected WNM action codes */ enum ieee80211_unprotected_wnm_actioncode { WLAN_UNPROTECTED_WNM_ACTION_TIM = 0, WLAN_UNPROTECTED_WNM_ACTION_TIMING_MEASUREMENT_RESPONSE = 1, }; /* Security key length */ enum ieee80211_key_len { WLAN_KEY_LEN_WEP40 = 5, WLAN_KEY_LEN_WEP104 = 13, WLAN_KEY_LEN_CCMP = 16, WLAN_KEY_LEN_CCMP_256 = 32, WLAN_KEY_LEN_TKIP = 32, WLAN_KEY_LEN_AES_CMAC = 16, WLAN_KEY_LEN_SMS4 = 32, WLAN_KEY_LEN_GCMP = 16, WLAN_KEY_LEN_GCMP_256 = 32, WLAN_KEY_LEN_BIP_CMAC_256 = 32, WLAN_KEY_LEN_BIP_GMAC_128 = 16, WLAN_KEY_LEN_BIP_GMAC_256 = 32, }; /* Radio measurement action codes as defined in IEEE 802.11-2024 - Table 9-470 */ enum ieee80211_radio_measurement_actioncode { WLAN_RM_ACTION_RADIO_MEASUREMENT_REQUEST = 0, WLAN_RM_ACTION_RADIO_MEASUREMENT_REPORT = 1, WLAN_RM_ACTION_LINK_MEASUREMENT_REQUEST = 2, WLAN_RM_ACTION_LINK_MEASUREMENT_REPORT = 3, WLAN_RM_ACTION_NEIGHBOR_REPORT_REQUEST = 4, WLAN_RM_ACTION_NEIGHBOR_REPORT_RESPONSE = 5, }; #define IEEE80211_WEP_IV_LEN 4 #define IEEE80211_WEP_ICV_LEN 4 #define IEEE80211_CCMP_HDR_LEN 8 #define IEEE80211_CCMP_MIC_LEN 8 #define IEEE80211_CCMP_PN_LEN 6 #define IEEE80211_CCMP_256_HDR_LEN 8 #define IEEE80211_CCMP_256_MIC_LEN 16 #define IEEE80211_CCMP_256_PN_LEN 6 #define IEEE80211_TKIP_IV_LEN 8 #define IEEE80211_TKIP_ICV_LEN 4 #define IEEE80211_CMAC_PN_LEN 6 #define IEEE80211_GMAC_PN_LEN 6 #define IEEE80211_GCMP_HDR_LEN 8 #define IEEE80211_GCMP_MIC_LEN 16 #define IEEE80211_GCMP_PN_LEN 6 #define IEEE80211_CMAC_128_MIC_LEN 8 #define IEEE80211_CMAC_256_MIC_LEN 16 #define IEEE80211_GMAC_MIC_LEN 16 #define FILS_NONCE_LEN 16 #define FILS_MAX_KEK_LEN 64 #define FILS_ERP_MAX_USERNAME_LEN 16 #define FILS_ERP_MAX_REALM_LEN 253 #define FILS_ERP_MAX_RRK_LEN 64 #define PMK_MAX_LEN 64 #define SAE_PASSWORD_MAX_LEN 128 #define MICHAEL_MIC_LEN 8 void michael_mic(const u8 *key, struct ieee80211_hdr *hdr, const u8 *data, size_t data_len, u8 *mic); /* Public action codes (IEEE Std 802.11-2016, 9.6.8.1, Table 9-307) */ enum ieee80211_pub_actioncode { WLAN_PUB_ACTION_20_40_BSS_COEX = 0, WLAN_PUB_ACTION_DSE_ENABLEMENT = 1, WLAN_PUB_ACTION_DSE_DEENABLEMENT = 2, WLAN_PUB_ACTION_DSE_REG_LOC_ANN = 3, WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4, WLAN_PUB_ACTION_DSE_MSMT_REQ = 5, WLAN_PUB_ACTION_DSE_MSMT_RESP = 6, WLAN_PUB_ACTION_MSMT_PILOT = 7, WLAN_PUB_ACTION_DSE_PC = 8, WLAN_PUB_ACTION_VENDOR_SPECIFIC = 9, WLAN_PUB_ACTION_GAS_INITIAL_REQ = 10, WLAN_PUB_ACTION_GAS_INITIAL_RESP = 11, WLAN_PUB_ACTION_GAS_COMEBACK_REQ = 12, WLAN_PUB_ACTION_GAS_COMEBACK_RESP = 13, WLAN_PUB_ACTION_TDLS_DISCOVER_RES = 14, WLAN_PUB_ACTION_LOC_TRACK_NOTI = 15, WLAN_PUB_ACTION_QAB_REQUEST_FRAME = 16, WLAN_PUB_ACTION_QAB_RESPONSE_FRAME = 17, WLAN_PUB_ACTION_QMF_POLICY = 18, WLAN_PUB_ACTION_QMF_POLICY_CHANGE = 19, WLAN_PUB_ACTION_QLOAD_REQUEST = 20, WLAN_PUB_ACTION_QLOAD_REPORT = 21, WLAN_PUB_ACTION_HCCA_TXOP_ADVERT = 22, WLAN_PUB_ACTION_HCCA_TXOP_RESPONSE = 23, WLAN_PUB_ACTION_PUBLIC_KEY = 24, WLAN_PUB_ACTION_CHANNEL_AVAIL_QUERY = 25, WLAN_PUB_ACTION_CHANNEL_SCHEDULE_MGMT = 26, WLAN_PUB_ACTION_CONTACT_VERI_SIGNAL = 27, WLAN_PUB_ACTION_GDD_ENABLEMENT_REQ = 28, WLAN_PUB_ACTION_GDD_ENABLEMENT_RESP = 29, WLAN_PUB_ACTION_NETWORK_CHANNEL_CONTROL = 30, WLAN_PUB_ACTION_WHITE_SPACE_MAP_ANN = 31, WLAN_PUB_ACTION_FTM_REQUEST = 32, WLAN_PUB_ACTION_FTM_RESPONSE = 33, WLAN_PUB_ACTION_FILS_DISCOVERY = 34, }; /* TDLS action codes */ enum ieee80211_tdls_actioncode { WLAN_TDLS_SETUP_REQUEST = 0, WLAN_TDLS_SETUP_RESPONSE = 1, WLAN_TDLS_SETUP_CONFIRM = 2, WLAN_TDLS_TEARDOWN = 3, WLAN_TDLS_PEER_TRAFFIC_INDICATION = 4, WLAN_TDLS_CHANNEL_SWITCH_REQUEST = 5, WLAN_TDLS_CHANNEL_SWITCH_RESPONSE = 6, WLAN_TDLS_PEER_PSM_REQUEST = 7, WLAN_TDLS_PEER_PSM_RESPONSE = 8, WLAN_TDLS_PEER_TRAFFIC_RESPONSE = 9, WLAN_TDLS_DISCOVERY_REQUEST = 10, }; /* Extended Channel Switching capability to be set in the 1st byte of * the @WLAN_EID_EXT_CAPABILITY information element */ #define WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING BIT(2) /* Multiple BSSID capability is set in the 6th bit of 3rd byte of the * @WLAN_EID_EXT_CAPABILITY information element */ #define WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT BIT(6) /* Timing Measurement protocol for time sync is set in the 7th bit of 3rd byte * of the @WLAN_EID_EXT_CAPABILITY information element */ #define WLAN_EXT_CAPA3_TIMING_MEASUREMENT_SUPPORT BIT(7) /* TDLS capabilities in the 4th byte of @WLAN_EID_EXT_CAPABILITY */ #define WLAN_EXT_CAPA4_TDLS_BUFFER_STA BIT(4) #define WLAN_EXT_CAPA4_TDLS_PEER_PSM BIT(5) #define WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH BIT(6) /* Interworking capabilities are set in 7th bit of 4th byte of the * @WLAN_EID_EXT_CAPABILITY information element */ #define WLAN_EXT_CAPA4_INTERWORKING_ENABLED BIT(7) /* * TDLS capabililites to be enabled in the 5th byte of the * @WLAN_EID_EXT_CAPABILITY information element */ #define WLAN_EXT_CAPA5_TDLS_ENABLED BIT(5) #define WLAN_EXT_CAPA5_TDLS_PROHIBITED BIT(6) #define WLAN_EXT_CAPA5_TDLS_CH_SW_PROHIBITED BIT(7) #define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(5) #define WLAN_EXT_CAPA8_OPMODE_NOTIF BIT(6) /* Defines the maximal number of MSDUs in an A-MSDU. */ #define WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB BIT(7) #define WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB BIT(0) /* * Fine Timing Measurement Initiator - bit 71 of @WLAN_EID_EXT_CAPABILITY * information element */ #define WLAN_EXT_CAPA9_FTM_INITIATOR BIT(7) /* Defines support for TWT Requester and TWT Responder */ #define WLAN_EXT_CAPA10_TWT_REQUESTER_SUPPORT BIT(5) #define WLAN_EXT_CAPA10_TWT_RESPONDER_SUPPORT BIT(6) /* * When set, indicates that the AP is able to tolerate 26-tone RU UL * OFDMA transmissions using HE TB PPDU from OBSS (not falsely classify the * 26-tone RU UL OFDMA transmissions as radar pulses). */ #define WLAN_EXT_CAPA10_OBSS_NARROW_BW_RU_TOLERANCE_SUPPORT BIT(7) /* Defines support for enhanced multi-bssid advertisement*/ #define WLAN_EXT_CAPA11_EMA_SUPPORT BIT(3) /* Enable Beacon Protection */ #define WLAN_EXT_CAPA11_BCN_PROTECT BIT(4) /* TDLS specific payload type in the LLC/SNAP header */ #define WLAN_TDLS_SNAP_RFTYPE 0x2 /* BSS Coex IE information field bits */ #define WLAN_BSS_COEX_INFORMATION_REQUEST BIT(0) /* * IEEE 802.11-2007 7.3.2.9 Country information element * * Minimum length is 8 octets, ie len must be evenly * divisible by 2 */ /* Although the spec says 8 I'm seeing 6 in practice */ #define IEEE80211_COUNTRY_IE_MIN_LEN 6 /* The Country String field of the element shall be 3 octets in length */ #define IEEE80211_COUNTRY_STRING_LEN 3 /* * For regulatory extension stuff see IEEE 802.11-2007 * Annex I (page 1141) and Annex J (page 1147). Also * review 7.3.2.9. * * When dot11RegulatoryClassesRequired is true and the * first_channel/reg_extension_id is >= 201 then the IE * compromises of the 'ext' struct represented below: * * - Regulatory extension ID - when generating IE this just needs * to be monotonically increasing for each triplet passed in * the IE * - Regulatory class - index into set of rules * - Coverage class - index into air propagation time (Table 7-27), * in microseconds, you can compute the air propagation time from * the index by multiplying by 3, so index 10 yields a propagation * of 10 us. Valid values are 0-31, values 32-255 are not defined * yet. A value of 0 inicates air propagation of <= 1 us. * * See also Table I.2 for Emission limit sets and table * I.3 for Behavior limit sets. Table J.1 indicates how to map * a reg_class to an emission limit set and behavior limit set. */ #define IEEE80211_COUNTRY_EXTENSION_ID 201 /* * Channels numbers in the IE must be monotonically increasing * if dot11RegulatoryClassesRequired is not true. * * If dot11RegulatoryClassesRequired is true consecutive * subband triplets following a regulatory triplet shall * have monotonically increasing first_channel number fields. * * Channel numbers shall not overlap. * * Note that max_power is signed. */ struct ieee80211_country_ie_triplet { union { struct { u8 first_channel; u8 num_channels; s8 max_power; } __packed chans; struct { u8 reg_extension_id; u8 reg_class; u8 coverage_class; } __packed ext; }; } __packed; enum ieee80211_timeout_interval_type { WLAN_TIMEOUT_REASSOC_DEADLINE = 1 /* 802.11r */, WLAN_TIMEOUT_KEY_LIFETIME = 2 /* 802.11r */, WLAN_TIMEOUT_ASSOC_COMEBACK = 3 /* 802.11w */, }; /** * struct ieee80211_timeout_interval_ie - Timeout Interval element * @type: type, see &enum ieee80211_timeout_interval_type * @value: timeout interval value */ struct ieee80211_timeout_interval_ie { u8 type; __le32 value; } __packed; /** * enum ieee80211_idle_options - BSS idle options * @WLAN_IDLE_OPTIONS_PROTECTED_KEEP_ALIVE: the station should send an RSN * protected frame to the AP to reset the idle timer at the AP for * the station. */ enum ieee80211_idle_options { WLAN_IDLE_OPTIONS_PROTECTED_KEEP_ALIVE = BIT(0), }; /** * struct ieee80211_bss_max_idle_period_ie - BSS max idle period element struct * * This structure refers to "BSS Max idle period element" * * @max_idle_period: indicates the time period during which a station can * refrain from transmitting frames to its associated AP without being * disassociated. In units of 1000 TUs. * @idle_options: indicates the options associated with the BSS idle capability * as specified in &enum ieee80211_idle_options. */ struct ieee80211_bss_max_idle_period_ie { __le16 max_idle_period; u8 idle_options; } __packed; /* SA Query action */ enum ieee80211_sa_query_action { WLAN_ACTION_SA_QUERY_REQUEST = 0, WLAN_ACTION_SA_QUERY_RESPONSE = 1, }; /** * struct ieee80211_bssid_index - multiple BSSID index element structure * * This structure refers to "Multiple BSSID-index element" * * @bssid_index: BSSID index * @dtim_period: optional, overrides transmitted BSS dtim period * @dtim_count: optional, overrides transmitted BSS dtim count */ struct ieee80211_bssid_index { u8 bssid_index; u8 dtim_period; u8 dtim_count; }; /** * struct ieee80211_multiple_bssid_configuration - multiple BSSID configuration * element structure * * This structure refers to "Multiple BSSID Configuration element" * * @bssid_count: total number of active BSSIDs in the set * @profile_periodicity: the least number of beacon frames need to be received * in order to discover all the nontransmitted BSSIDs in the set. */ struct ieee80211_multiple_bssid_configuration { u8 bssid_count; u8 profile_periodicity; }; #define SUITE(oui, id) (((oui) << 8) | (id)) /* cipher suite selectors */ #define WLAN_CIPHER_SUITE_USE_GROUP SUITE(0x000FAC, 0) #define WLAN_CIPHER_SUITE_WEP40 SUITE(0x000FAC, 1) #define WLAN_CIPHER_SUITE_TKIP SUITE(0x000FAC, 2) /* reserved: SUITE(0x000FAC, 3) */ #define WLAN_CIPHER_SUITE_CCMP SUITE(0x000FAC, 4) #define WLAN_CIPHER_SUITE_WEP104 SUITE(0x000FAC, 5) #define WLAN_CIPHER_SUITE_AES_CMAC SUITE(0x000FAC, 6) #define WLAN_CIPHER_SUITE_GCMP SUITE(0x000FAC, 8) #define WLAN_CIPHER_SUITE_GCMP_256 SUITE(0x000FAC, 9) #define WLAN_CIPHER_SUITE_CCMP_256 SUITE(0x000FAC, 10) #define WLAN_CIPHER_SUITE_BIP_GMAC_128 SUITE(0x000FAC, 11) #define WLAN_CIPHER_SUITE_BIP_GMAC_256 SUITE(0x000FAC, 12) #define WLAN_CIPHER_SUITE_BIP_CMAC_256 SUITE(0x000FAC, 13) #define WLAN_CIPHER_SUITE_SMS4 SUITE(0x001472, 1) /* AKM suite selectors */ #define WLAN_AKM_SUITE_8021X SUITE(0x000FAC, 1) #define WLAN_AKM_SUITE_PSK SUITE(0x000FAC, 2) #define WLAN_AKM_SUITE_FT_8021X SUITE(0x000FAC, 3) #define WLAN_AKM_SUITE_FT_PSK SUITE(0x000FAC, 4) #define WLAN_AKM_SUITE_8021X_SHA256 SUITE(0x000FAC, 5) #define WLAN_AKM_SUITE_PSK_SHA256 SUITE(0x000FAC, 6) #define WLAN_AKM_SUITE_TDLS SUITE(0x000FAC, 7) #define WLAN_AKM_SUITE_SAE SUITE(0x000FAC, 8) #define WLAN_AKM_SUITE_FT_OVER_SAE SUITE(0x000FAC, 9) #define WLAN_AKM_SUITE_AP_PEER_KEY SUITE(0x000FAC, 10) #define WLAN_AKM_SUITE_8021X_SUITE_B SUITE(0x000FAC, 11) #define WLAN_AKM_SUITE_8021X_SUITE_B_192 SUITE(0x000FAC, 12) #define WLAN_AKM_SUITE_FT_8021X_SHA384 SUITE(0x000FAC, 13) #define WLAN_AKM_SUITE_FILS_SHA256 SUITE(0x000FAC, 14) #define WLAN_AKM_SUITE_FILS_SHA384 SUITE(0x000FAC, 15) #define WLAN_AKM_SUITE_FT_FILS_SHA256 SUITE(0x000FAC, 16) #define WLAN_AKM_SUITE_FT_FILS_SHA384 SUITE(0x000FAC, 17) #define WLAN_AKM_SUITE_OWE SUITE(0x000FAC, 18) #define WLAN_AKM_SUITE_FT_PSK_SHA384 SUITE(0x000FAC, 19) #define WLAN_AKM_SUITE_PSK_SHA384 SUITE(0x000FAC, 20) #define WLAN_AKM_SUITE_WFA_DPP SUITE(WLAN_OUI_WFA, 2) #define WLAN_MAX_KEY_LEN 32 #define WLAN_PMK_NAME_LEN 16 #define WLAN_PMKID_LEN 16 #define WLAN_PMK_LEN_EAP_LEAP 16 #define WLAN_PMK_LEN 32 #define WLAN_PMK_LEN_SUITE_B_192 48 #define WLAN_OUI_WFA 0x506f9a #define WLAN_OUI_TYPE_WFA_P2P 9 #define WLAN_OUI_TYPE_WFA_NAN 0x13 #define WLAN_OUI_TYPE_WFA_DPP 0x1A #define WLAN_OUI_MICROSOFT 0x0050f2 #define WLAN_OUI_TYPE_MICROSOFT_WPA 1 #define WLAN_OUI_TYPE_MICROSOFT_WMM 2 #define WLAN_OUI_TYPE_MICROSOFT_WPS 4 #define WLAN_OUI_TYPE_MICROSOFT_TPC 8 /* * WMM/802.11e Tspec Element */ #define IEEE80211_WMM_IE_TSPEC_TID_MASK 0x0F #define IEEE80211_WMM_IE_TSPEC_TID_SHIFT 1 enum ieee80211_tspec_status_code { IEEE80211_TSPEC_STATUS_ADMISS_ACCEPTED = 0, IEEE80211_TSPEC_STATUS_ADDTS_INVAL_PARAMS = 0x1, }; struct ieee80211_tspec_ie { u8 element_id; u8 len; u8 oui[3]; u8 oui_type; u8 oui_subtype; u8 version; __le16 tsinfo; u8 tsinfo_resvd; __le16 nominal_msdu; __le16 max_msdu; __le32 min_service_int; __le32 max_service_int; __le32 inactivity_int; __le32 suspension_int; __le32 service_start_time; __le32 min_data_rate; __le32 mean_data_rate; __le32 peak_data_rate; __le32 max_burst_size; __le32 delay_bound; __le32 min_phy_rate; __le16 sba; __le16 medium_time; } __packed; /** * ieee80211_get_qos_ctl - get pointer to qos control bytes * @hdr: the frame * Return: a pointer to the QoS control field in the frame header * * The qos ctrl bytes come after the frame_control, duration, seq_num * and 3 or 4 addresses of length ETH_ALEN. Checks frame_control to choose * between struct ieee80211_qos_hdr_4addr and struct ieee80211_qos_hdr. */ static inline u8 *ieee80211_get_qos_ctl(struct ieee80211_hdr *hdr) { union { struct ieee80211_qos_hdr addr3; struct ieee80211_qos_hdr_4addr addr4; } *qos; qos = (void *)hdr; if (ieee80211_has_a4(qos->addr3.frame_control)) return (u8 *)&qos->addr4.qos_ctrl; else return (u8 *)&qos->addr3.qos_ctrl; } /** * ieee80211_get_tid - get qos TID * @hdr: the frame * Return: the TID from the QoS control field */ static inline u8 ieee80211_get_tid(struct ieee80211_hdr *hdr) { u8 *qc = ieee80211_get_qos_ctl(hdr); return qc[0] & IEEE80211_QOS_CTL_TID_MASK; } /** * ieee80211_get_SA - get pointer to SA * @hdr: the frame * Return: a pointer to the source address (SA) * * Given an 802.11 frame, this function returns the offset * to the source address (SA). It does not verify that the * header is long enough to contain the address, and the * header must be long enough to contain the frame control * field. */ static inline u8 *ieee80211_get_SA(struct ieee80211_hdr *hdr) { if (ieee80211_has_a4(hdr->frame_control)) return hdr->addr4; if (ieee80211_has_fromds(hdr->frame_control)) return hdr->addr3; return hdr->addr2; } /** * ieee80211_get_DA - get pointer to DA * @hdr: the frame * Return: a pointer to the destination address (DA) * * Given an 802.11 frame, this function returns the offset * to the destination address (DA). It does not verify that * the header is long enough to contain the address, and the * header must be long enough to contain the frame control * field. */ static inline u8 *ieee80211_get_DA(struct ieee80211_hdr *hdr) { if (ieee80211_has_tods(hdr->frame_control)) return hdr->addr3; else return hdr->addr1; } /** * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU * @skb: the skb to check, starting with the 802.11 header * Return: whether or not the MMPDU is bufferable */ static inline bool ieee80211_is_bufferable_mmpdu(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; __le16 fc = mgmt->frame_control; /* * IEEE 802.11 REVme D2.0 definition of bufferable MMPDU; * note that this ignores the IBSS special case. */ if (!ieee80211_is_mgmt(fc)) return false; if (ieee80211_is_disassoc(fc) || ieee80211_is_deauth(fc)) return true; if (!ieee80211_is_action(fc)) return false; if (skb->len < IEEE80211_MIN_ACTION_SIZE(action_code)) return true; /* action frame - additionally check for non-bufferable FTM */ if (mgmt->u.action.category != WLAN_CATEGORY_PUBLIC && mgmt->u.action.category != WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION) return true; if (mgmt->u.action.action_code == WLAN_PUB_ACTION_FTM_REQUEST || mgmt->u.action.action_code == WLAN_PUB_ACTION_FTM_RESPONSE) return false; return true; } /** * _ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame * @hdr: the frame (buffer must include at least the first octet of payload) * Return: whether or not the frame is a robust management frame */ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) { if (ieee80211_is_disassoc(hdr->frame_control) || ieee80211_is_deauth(hdr->frame_control)) return true; if (ieee80211_is_action(hdr->frame_control)) { u8 *category; /* * Action frames, excluding Public Action frames, are Robust * Management Frames. However, if we are looking at a Protected * frame, skip the check since the data may be encrypted and * the frame has already been found to be a Robust Management * Frame (by the other end). */ if (ieee80211_has_protected(hdr->frame_control)) return true; category = ((u8 *) hdr) + 24; return *category != WLAN_CATEGORY_PUBLIC && *category != WLAN_CATEGORY_HT && *category != WLAN_CATEGORY_WNM_UNPROTECTED && *category != WLAN_CATEGORY_SELF_PROTECTED && *category != WLAN_CATEGORY_UNPROT_DMG && *category != WLAN_CATEGORY_VHT && *category != WLAN_CATEGORY_S1G && *category != WLAN_CATEGORY_VENDOR_SPECIFIC; } return false; } /** * ieee80211_is_robust_mgmt_frame - check if skb contains a robust mgmt frame * @skb: the skb containing the frame, length will be checked * Return: whether or not the frame is a robust management frame */ static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb) { if (skb->len < IEEE80211_MIN_ACTION_SIZE(category)) return false; return _ieee80211_is_robust_mgmt_frame((void *)skb->data); } /** * ieee80211_is_public_action - check if frame is a public action frame * @hdr: the frame * @len: length of the frame * Return: whether or not the frame is a public action frame */ static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr, size_t len) { struct ieee80211_mgmt *mgmt = (void *)hdr; if (len < IEEE80211_MIN_ACTION_SIZE(category)) return false; if (!ieee80211_is_action(hdr->frame_control)) return false; return mgmt->u.action.category == WLAN_CATEGORY_PUBLIC; } /** * ieee80211_is_protected_dual_of_public_action - check if skb contains a * protected dual of public action management frame * @skb: the skb containing the frame, length will be checked * * Return: true if the skb contains a protected dual of public action * management frame, false otherwise. */ static inline bool ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; u8 action; if (!ieee80211_is_public_action((void *)skb->data, skb->len) || skb->len < IEEE80211_MIN_ACTION_SIZE(action_code)) return false; action = mgmt->u.action.action_code; return action != WLAN_PUB_ACTION_20_40_BSS_COEX && action != WLAN_PUB_ACTION_DSE_REG_LOC_ANN && action != WLAN_PUB_ACTION_MSMT_PILOT && action != WLAN_PUB_ACTION_TDLS_DISCOVER_RES && action != WLAN_PUB_ACTION_LOC_TRACK_NOTI && action != WLAN_PUB_ACTION_FTM_REQUEST && action != WLAN_PUB_ACTION_FTM_RESPONSE && action != WLAN_PUB_ACTION_FILS_DISCOVERY && action != WLAN_PUB_ACTION_VENDOR_SPECIFIC; } /** * _ieee80211_is_group_privacy_action - check if frame is a group addressed * privacy action frame * @hdr: the frame * Return: whether or not the frame is a group addressed privacy action frame */ static inline bool _ieee80211_is_group_privacy_action(struct ieee80211_hdr *hdr) { struct ieee80211_mgmt *mgmt = (void *)hdr; if (!ieee80211_is_action(hdr->frame_control) || !is_multicast_ether_addr(hdr->addr1)) return false; return mgmt->u.action.category == WLAN_CATEGORY_MESH_ACTION || mgmt->u.action.category == WLAN_CATEGORY_MULTIHOP_ACTION; } /** * ieee80211_is_group_privacy_action - check if frame is a group addressed * privacy action frame * @skb: the skb containing the frame, length will be checked * Return: whether or not the frame is a group addressed privacy action frame */ static inline bool ieee80211_is_group_privacy_action(struct sk_buff *skb) { if (skb->len < IEEE80211_MIN_ACTION_SIZE(category)) return false; return _ieee80211_is_group_privacy_action((void *)skb->data); } /** * ieee80211_tu_to_usec - convert time units (TU) to microseconds * @tu: the TUs * Return: the time value converted to microseconds */ static inline unsigned long ieee80211_tu_to_usec(unsigned long tu) { return 1024 * tu; } static inline bool __ieee80211_check_tim(const struct ieee80211_tim_ie *tim, u8 tim_len, u16 aid) { u8 mask; u8 index, indexn1, indexn2; if (unlikely(!tim || tim_len < sizeof(*tim))) return false; aid &= 0x3fff; index = aid / 8; mask = 1 << (aid & 7); indexn1 = tim->bitmap_ctrl & 0xfe; indexn2 = tim_len + indexn1 - 4; if (index < indexn1 || index > indexn2) return false; index -= indexn1; return !!(tim->virtual_map[index] & mask); } /** * ieee80211_get_tdls_action - get TDLS action code * @skb: the skb containing the frame, length will not be checked * Return: the TDLS action code, or -1 if it's not an encapsulated TDLS action * frame * * This function assumes the frame is a data frame, and that the network header * is in the correct place. */ static inline int ieee80211_get_tdls_action(struct sk_buff *skb) { if (!skb_is_nonlinear(skb) && skb->len > (skb_network_offset(skb) + 2)) { /* Point to where the indication of TDLS should start */ const u8 *tdls_data = skb_network_header(skb) - 2; if (get_unaligned_be16(tdls_data) == ETH_P_TDLS && tdls_data[2] == WLAN_TDLS_SNAP_RFTYPE && tdls_data[3] == WLAN_CATEGORY_TDLS) return tdls_data[4]; } return -1; } /* convert time units */ #define TU_TO_JIFFIES(x) (usecs_to_jiffies((x) * 1024)) #define TU_TO_EXP_TIME(x) (jiffies + TU_TO_JIFFIES(x)) /* convert frequencies */ #define MHZ_TO_KHZ(freq) ((freq) * 1000) #define KHZ_TO_MHZ(freq) ((freq) / 1000) #define PR_KHZ(f) KHZ_TO_MHZ(f), f % 1000 #define KHZ_F "%d.%03d" /* convert powers */ #define DBI_TO_MBI(gain) ((gain) * 100) #define MBI_TO_DBI(gain) ((gain) / 100) #define DBM_TO_MBM(gain) ((gain) * 100) #define MBM_TO_DBM(gain) ((gain) / 100) /** * ieee80211_action_contains_tpc - checks if the frame contains TPC element * @skb: the skb containing the frame, length will be checked * Return: %true if the frame contains a TPC element, %false otherwise * * This function checks if it's either TPC report action frame or Link * Measurement report action frame as defined in IEEE Std. 802.11-2012 8.5.2.5 * and 8.5.7.5 accordingly. */ static inline bool ieee80211_action_contains_tpc(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; if (!ieee80211_is_action(mgmt->frame_control)) return false; if (skb->len < IEEE80211_MIN_ACTION_SIZE(tpc_report)) return false; /* * TPC report - check that: * category = 0 (Spectrum Management) or 5 (Radio Measurement) * spectrum management action = 3 (TPC/Link Measurement report) * TPC report EID = 35 * TPC report element length = 2 * * The spectrum management's tpc_report struct is used here both for * parsing tpc_report and radio measurement's link measurement report * frame, since the relevant part is identical in both frames. */ if (mgmt->u.action.category != WLAN_CATEGORY_SPECTRUM_MGMT && mgmt->u.action.category != WLAN_CATEGORY_RADIO_MEASUREMENT) return false; /* both spectrum mgmt and link measurement have same action code */ if (mgmt->u.action.action_code != WLAN_ACTION_SPCT_TPC_RPRT) return false; if (mgmt->u.action.tpc_report.tpc_elem_id != WLAN_EID_TPC_REPORT || mgmt->u.action.tpc_report.tpc_elem_length != sizeof(struct ieee80211_tpc_report_ie)) return false; return true; } /** * ieee80211_is_timing_measurement - check if frame is timing measurement response * @skb: the SKB to check * Return: whether or not the frame is a valid timing measurement response */ static inline bool ieee80211_is_timing_measurement(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; if (skb->len < IEEE80211_MIN_ACTION_SIZE(wnm_timing_msr)) return false; if (!ieee80211_is_action(mgmt->frame_control)) return false; if (mgmt->u.action.category == WLAN_CATEGORY_WNM_UNPROTECTED && mgmt->u.action.action_code == WLAN_UNPROTECTED_WNM_ACTION_TIMING_MEASUREMENT_RESPONSE) return true; return false; } /** * ieee80211_is_ftm - check if frame is FTM response * @skb: the SKB to check * Return: whether or not the frame is a valid FTM response action frame */ static inline bool ieee80211_is_ftm(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; if (skb->len < IEEE80211_MIN_ACTION_SIZE(ftm)) return false; if (!ieee80211_is_public_action((void *)mgmt, skb->len)) return false; return mgmt->u.action.action_code == WLAN_PUB_ACTION_FTM_RESPONSE; } struct element { u8 id; u8 datalen; u8 data[]; } __packed; /* element iteration helpers */ #define for_each_element(_elem, _data, _datalen) \ for (_elem = (const struct element *)(_data); \ (const u8 *)(_data) + (_datalen) - (const u8 *)_elem >= \ (int)sizeof(*_elem) && \ (const u8 *)(_data) + (_datalen) - (const u8 *)_elem >= \ (int)sizeof(*_elem) + _elem->datalen; \ _elem = (const struct element *)(_elem->data + _elem->datalen)) #define for_each_element_id(element, _id, data, datalen) \ for_each_element(element, data, datalen) \ if (element->id == (_id)) #define for_each_element_extid(element, extid, _data, _datalen) \ for_each_element(element, _data, _datalen) \ if (element->id == WLAN_EID_EXTENSION && \ element->datalen > 0 && \ element->data[0] == (extid)) #define for_each_subelement(sub, element) \ for_each_element(sub, (element)->data, (element)->datalen) #define for_each_subelement_id(sub, id, element) \ for_each_element_id(sub, id, (element)->data, (element)->datalen) #define for_each_subelement_extid(sub, extid, element) \ for_each_element_extid(sub, extid, (element)->data, (element)->datalen) /** * for_each_element_completed - determine if element parsing consumed all data * @element: element pointer after for_each_element() or friends * @data: same data pointer as passed to for_each_element() or friends * @datalen: same data length as passed to for_each_element() or friends * Return: %true if all elements were iterated, %false otherwise; see notes * * This function returns %true if all the data was parsed or considered * while walking the elements. Only use this if your for_each_element() * loop cannot be broken out of, otherwise it always returns %false. * * If some data was malformed, this returns %false since the last parsed * element will not fill the whole remaining data. */ static inline bool for_each_element_completed(const struct element *element, const void *data, size_t datalen) { return (const u8 *)element == (const u8 *)data + datalen; } /* * RSNX Capabilities: * bits 0-3: Field length (n-1) */ #define WLAN_RSNX_CAPA_PROTECTED_TWT BIT(4) #define WLAN_RSNX_CAPA_SAE_H2E BIT(5) /* EBPCC = Enhanced BSS Parameter Change Count */ #define IEEE80211_ENH_CRIT_UPD_EBPCC 0x0F #define IEEE80211_ENH_CRIT_UPD_TYPE 0x70 #define IEEE80211_ENH_CRIT_UPD_TYPE_NO_UHR 0 #define IEEE80211_ENH_CRIT_UPD_TYPE_UHR 1 #define IEEE80211_ENH_CRIT_UPD_ALL 0x80 /** * struct ieee80211_enh_crit_upd - enhanced critical update (UHR) * @v: value of the enhanced critical update data, * see %IEEE80211_ENH_CRIT_UPD_* to parse the bits */ struct ieee80211_enh_crit_upd { u8 v; } __packed; /* * reduced neighbor report, based on Draft P802.11ax_D6.1, * section 9.4.2.170 and accepted contributions. */ #define IEEE80211_AP_INFO_TBTT_HDR_TYPE 0x03 #define IEEE80211_AP_INFO_TBTT_HDR_FILTERED 0x04 #define IEEE80211_AP_INFO_TBTT_HDR_COLOC 0x08 #define IEEE80211_AP_INFO_TBTT_HDR_COUNT 0xF0 #define IEEE80211_TBTT_INFO_TYPE_TBTT 0 #define IEEE80211_TBTT_INFO_TYPE_MLD 1 #define IEEE80211_RNR_TBTT_PARAMS_OCT_RECOMMENDED 0x01 #define IEEE80211_RNR_TBTT_PARAMS_SAME_SSID 0x02 #define IEEE80211_RNR_TBTT_PARAMS_MULTI_BSSID 0x04 #define IEEE80211_RNR_TBTT_PARAMS_TRANSMITTED_BSSID 0x08 #define IEEE80211_RNR_TBTT_PARAMS_COLOC_ESS 0x10 #define IEEE80211_RNR_TBTT_PARAMS_PROBE_ACTIVE 0x20 #define IEEE80211_RNR_TBTT_PARAMS_COLOC_AP 0x40 #define IEEE80211_RNR_TBTT_PARAMS_SAME_SMD 0x80 #define IEEE80211_RNR_TBTT_PARAMS_PSD_NO_LIMIT 127 #define IEEE80211_RNR_TBTT_PARAMS_PSD_RESERVED -128 struct ieee80211_neighbor_ap_info { u8 tbtt_info_hdr; u8 tbtt_info_len; u8 op_class; u8 channel; } __packed; enum ieee80211_range_params_max_total_ltf { IEEE80211_RANGE_PARAMS_MAX_TOTAL_LTF_4 = 0, IEEE80211_RANGE_PARAMS_MAX_TOTAL_LTF_8, IEEE80211_RANGE_PARAMS_MAX_TOTAL_LTF_16, IEEE80211_RANGE_PARAMS_MAX_TOTAL_LTF_UNSPECIFIED, }; /* * reduced neighbor report, based on Draft P802.11be_D3.0, * section 9.4.2.170.2. */ struct ieee80211_rnr_mld_params { u8 mld_id; __le16 params; } __packed; #define IEEE80211_RNR_MLD_PARAMS_LINK_ID 0x000F #define IEEE80211_RNR_MLD_PARAMS_BSS_CHANGE_COUNT 0x0FF0 #define IEEE80211_RNR_MLD_PARAMS_UPDATES_INCLUDED 0x1000 #define IEEE80211_RNR_MLD_PARAMS_DISABLED_LINK 0x2000 /* Format of the TBTT information element if it has 7, 8 or 9 bytes */ struct ieee80211_tbtt_info_7_8_9 { u8 tbtt_offset; u8 bssid[ETH_ALEN]; /* The following element is optional, structure may not grow */ u8 bss_params; s8 psd_20; } __packed; /* Format of the TBTT information element if it has >= 11 bytes */ struct ieee80211_tbtt_info_ge_11 { u8 tbtt_offset; u8 bssid[ETH_ALEN]; __le32 short_ssid; /* The following elements are optional, structure may grow */ u8 bss_params; s8 psd_20; struct ieee80211_rnr_mld_params mld_params; struct ieee80211_enh_crit_upd enh_crit_upd; } __packed; #include "ieee80211-ht.h" #include "ieee80211-vht.h" #include "ieee80211-he.h" #include "ieee80211-eht.h" #include "ieee80211-uhr.h" #include "ieee80211-mesh.h" #include "ieee80211-s1g.h" #include "ieee80211-p2p.h" #include "ieee80211-nan.h" /** * ieee80211_check_tim - check if AID bit is set in TIM * @tim: the TIM IE * @tim_len: length of the TIM IE * @aid: the AID to look for * @s1g: whether the TIM is from an S1G PPDU * Return: whether or not traffic is indicated in the TIM for the given AID */ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, u8 tim_len, u16 aid, bool s1g) { return s1g ? ieee80211_s1g_check_tim(tim, tim_len, aid) : __ieee80211_check_tim(tim, tim_len, aid); } #endif /* LINUX_IEEE80211_H */ |
| 18 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2009 IBM Corporation * Author: Mimi Zohar <zohar@us.ibm.com> */ #ifndef _LINUX_INTEGRITY_H #define _LINUX_INTEGRITY_H #include <linux/fs.h> #include <linux/iversion.h> enum integrity_status { INTEGRITY_PASS = 0, INTEGRITY_PASS_IMMUTABLE, INTEGRITY_FAIL, INTEGRITY_FAIL_IMMUTABLE, INTEGRITY_NOLABEL, INTEGRITY_NOXATTRS, INTEGRITY_UNKNOWN, }; #ifdef CONFIG_INTEGRITY extern void __init integrity_load_keys(void); #else static inline void integrity_load_keys(void) { } #endif /* CONFIG_INTEGRITY */ /* An inode's attributes for detection of changes */ struct integrity_inode_attributes { u64 version; /* track inode changes */ unsigned long ino; dev_t dev; }; /* * On stacked filesystems the i_version alone is not enough to detect file data * or metadata change. Additional metadata is required. */ static inline void integrity_inode_attrs_store(struct integrity_inode_attributes *attrs, u64 i_version, const struct inode *inode) { attrs->version = i_version; attrs->dev = inode->i_sb->s_dev; attrs->ino = inode->i_ino; } /* * On stacked filesystems detect whether the inode or its content has changed. */ static inline bool integrity_inode_attrs_changed(const struct integrity_inode_attributes *attrs, const struct inode *inode) { return (inode->i_sb->s_dev != attrs->dev || inode->i_ino != attrs->ino || !inode_eq_iversion(inode, attrs->version)); } #endif /* _LINUX_INTEGRITY_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause /* * Copyright (c) Meta Platforms, Inc. and affiliates. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the * LICENSE file in the root directory of this source tree) and the GPLv2 (found * in the COPYING file in the root directory of this source tree). * You may select, at your option, one of the above-listed licenses. */ /* zstd_ddict.c : * concentrates all logic that needs to know the internals of ZSTD_DDict object */ /*-******************************************************* * Dependencies *********************************************************/ #include "../common/allocations.h" /* ZSTD_customMalloc, ZSTD_customFree */ #include "../common/zstd_deps.h" /* ZSTD_memcpy, ZSTD_memmove, ZSTD_memset */ #include "../common/cpu.h" /* bmi2 */ #include "../common/mem.h" /* low level memory routines */ #define FSE_STATIC_LINKING_ONLY #include "../common/fse.h" #include "../common/huf.h" #include "zstd_decompress_internal.h" #include "zstd_ddict.h" /*-******************************************************* * Types *********************************************************/ struct ZSTD_DDict_s { void* dictBuffer; const void* dictContent; size_t dictSize; ZSTD_entropyDTables_t entropy; U32 dictID; U32 entropyPresent; ZSTD_customMem cMem; }; /* typedef'd to ZSTD_DDict within "zstd.h" */ const void* ZSTD_DDict_dictContent(const ZSTD_DDict* ddict) { assert(ddict != NULL); return ddict->dictContent; } size_t ZSTD_DDict_dictSize(const ZSTD_DDict* ddict) { assert(ddict != NULL); return ddict->dictSize; } void ZSTD_copyDDictParameters(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict) { DEBUGLOG(4, "ZSTD_copyDDictParameters"); assert(dctx != NULL); assert(ddict != NULL); dctx->dictID = ddict->dictID; dctx->prefixStart = ddict->dictContent; dctx->virtualStart = ddict->dictContent; dctx->dictEnd = (const BYTE*)ddict->dictContent + ddict->dictSize; dctx->previousDstEnd = dctx->dictEnd; #ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION dctx->dictContentBeginForFuzzing = dctx->prefixStart; dctx->dictContentEndForFuzzing = dctx->previousDstEnd; #endif if (ddict->entropyPresent) { dctx->litEntropy = 1; dctx->fseEntropy = 1; dctx->LLTptr = ddict->entropy.LLTable; dctx->MLTptr = ddict->entropy.MLTable; dctx->OFTptr = ddict->entropy.OFTable; dctx->HUFptr = ddict->entropy.hufTable; dctx->entropy.rep[0] = ddict->entropy.rep[0]; dctx->entropy.rep[1] = ddict->entropy.rep[1]; dctx->entropy.rep[2] = ddict->entropy.rep[2]; } else { dctx->litEntropy = 0; dctx->fseEntropy = 0; } } static size_t ZSTD_loadEntropy_intoDDict(ZSTD_DDict* ddict, ZSTD_dictContentType_e dictContentType) { ddict->dictID = 0; ddict->entropyPresent = 0; if (dictContentType == ZSTD_dct_rawContent) return 0; if (ddict->dictSize < 8) { if (dictContentType == ZSTD_dct_fullDict) return ERROR(dictionary_corrupted); /* only accept specified dictionaries */ return 0; /* pure content mode */ } { U32 const magic = MEM_readLE32(ddict->dictContent); if (magic != ZSTD_MAGIC_DICTIONARY) { if (dictContentType == ZSTD_dct_fullDict) return ERROR(dictionary_corrupted); /* only accept specified dictionaries */ return 0; /* pure content mode */ } } ddict->dictID = MEM_readLE32((const char*)ddict->dictContent + ZSTD_FRAMEIDSIZE); /* load entropy tables */ RETURN_ERROR_IF(ZSTD_isError(ZSTD_loadDEntropy( &ddict->entropy, ddict->dictContent, ddict->dictSize)), dictionary_corrupted, ""); ddict->entropyPresent = 1; return 0; } static size_t ZSTD_initDDict_internal(ZSTD_DDict* ddict, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType) { if ((dictLoadMethod == ZSTD_dlm_byRef) || (!dict) || (!dictSize)) { ddict->dictBuffer = NULL; ddict->dictContent = dict; if (!dict) dictSize = 0; } else { void* const internalBuffer = ZSTD_customMalloc(dictSize, ddict->cMem); ddict->dictBuffer = internalBuffer; ddict->dictContent = internalBuffer; if (!internalBuffer) return ERROR(memory_allocation); ZSTD_memcpy(internalBuffer, dict, dictSize); } ddict->dictSize = dictSize; ddict->entropy.hufTable[0] = (HUF_DTable)((ZSTD_HUFFDTABLE_CAPACITY_LOG)*0x1000001); /* cover both little and big endian */ /* parse dictionary content */ FORWARD_IF_ERROR( ZSTD_loadEntropy_intoDDict(ddict, dictContentType) , ""); return 0; } ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType, ZSTD_customMem customMem) { if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL; { ZSTD_DDict* const ddict = (ZSTD_DDict*) ZSTD_customMalloc(sizeof(ZSTD_DDict), customMem); if (ddict == NULL) return NULL; ddict->cMem = customMem; { size_t const initResult = ZSTD_initDDict_internal(ddict, dict, dictSize, dictLoadMethod, dictContentType); if (ZSTD_isError(initResult)) { ZSTD_freeDDict(ddict); return NULL; } } return ddict; } } /*! ZSTD_createDDict() : * Create a digested dictionary, to start decompression without startup delay. * `dict` content is copied inside DDict. * Consequently, `dict` can be released after `ZSTD_DDict` creation */ ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize) { ZSTD_customMem const allocator = { NULL, NULL, NULL }; return ZSTD_createDDict_advanced(dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto, allocator); } /*! ZSTD_createDDict_byReference() : * Create a digested dictionary, to start decompression without startup delay. * Dictionary content is simply referenced, it will be accessed during decompression. * Warning : dictBuffer must outlive DDict (DDict must be freed before dictBuffer) */ ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize) { ZSTD_customMem const allocator = { NULL, NULL, NULL }; return ZSTD_createDDict_advanced(dictBuffer, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto, allocator); } const ZSTD_DDict* ZSTD_initStaticDDict( void* sBuffer, size_t sBufferSize, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType) { size_t const neededSpace = sizeof(ZSTD_DDict) + (dictLoadMethod == ZSTD_dlm_byRef ? 0 : dictSize); ZSTD_DDict* const ddict = (ZSTD_DDict*)sBuffer; assert(sBuffer != NULL); assert(dict != NULL); if ((size_t)sBuffer & 7) return NULL; /* 8-aligned */ if (sBufferSize < neededSpace) return NULL; if (dictLoadMethod == ZSTD_dlm_byCopy) { ZSTD_memcpy(ddict+1, dict, dictSize); /* local copy */ dict = ddict+1; } if (ZSTD_isError( ZSTD_initDDict_internal(ddict, dict, dictSize, ZSTD_dlm_byRef, dictContentType) )) return NULL; return ddict; } size_t ZSTD_freeDDict(ZSTD_DDict* ddict) { if (ddict==NULL) return 0; /* support free on NULL */ { ZSTD_customMem const cMem = ddict->cMem; ZSTD_customFree(ddict->dictBuffer, cMem); ZSTD_customFree(ddict, cMem); return 0; } } /*! ZSTD_estimateDDictSize() : * Estimate amount of memory that will be needed to create a dictionary for decompression. * Note : dictionary created by reference using ZSTD_dlm_byRef are smaller */ size_t ZSTD_estimateDDictSize(size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod) { return sizeof(ZSTD_DDict) + (dictLoadMethod == ZSTD_dlm_byRef ? 0 : dictSize); } size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict) { if (ddict==NULL) return 0; /* support sizeof on NULL */ return sizeof(*ddict) + (ddict->dictBuffer ? ddict->dictSize : 0) ; } /*! ZSTD_getDictID_fromDDict() : * Provides the dictID of the dictionary loaded into `ddict`. * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */ unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict) { if (ddict==NULL) return 0; return ddict->dictID; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Definitions of structures and functions for quota formats using trie */ #ifndef _LINUX_DQBLK_QTREE_H #define _LINUX_DQBLK_QTREE_H #include <linux/types.h> /* Numbers of blocks needed for updates - we count with the smallest * possible block size (1024) */ #define QTREE_INIT_ALLOC 4 #define QTREE_INIT_REWRITE 2 #define QTREE_DEL_ALLOC 0 #define QTREE_DEL_REWRITE 6 struct dquot; struct kqid; /* Operations */ struct qtree_fmt_operations { void (*mem2disk_dqblk)(void *disk, struct dquot *dquot); /* Convert given entry from in memory format to disk one */ void (*disk2mem_dqblk)(struct dquot *dquot, void *disk); /* Convert given entry from disk format to in memory one */ int (*is_id)(void *disk, struct dquot *dquot); /* Is this structure for given id? */ }; /* Inmemory copy of version specific information */ struct qtree_mem_dqinfo { struct super_block *dqi_sb; /* Sb quota is on */ int dqi_type; /* Quota type */ unsigned int dqi_blocks; /* # of blocks in quota file */ unsigned int dqi_free_blk; /* First block in list of free blocks */ unsigned int dqi_free_entry; /* First block with free entry */ unsigned int dqi_blocksize_bits; /* Block size of quota file */ unsigned int dqi_entry_size; /* Size of quota entry in quota file */ unsigned int dqi_usable_bs; /* Space usable in block for quota data */ unsigned int dqi_qtree_depth; /* Precomputed depth of quota tree */ const struct qtree_fmt_operations *dqi_ops; /* Operations for entry manipulation */ }; int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot); int qtree_read_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot); int qtree_delete_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot); int qtree_release_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot); int qtree_entry_unused(struct qtree_mem_dqinfo *info, char *disk); static inline int qtree_depth(struct qtree_mem_dqinfo *info) { unsigned int epb = info->dqi_usable_bs >> 2; unsigned long long entries = epb; int i; for (i = 1; entries < (1ULL << 32); i++) entries *= epb; return i; } int qtree_get_next_id(struct qtree_mem_dqinfo *info, struct kqid *qid); #endif /* _LINUX_DQBLK_QTREE_H */ |
| 26 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 | /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_IOPRIO_H #define _UAPI_LINUX_IOPRIO_H #include <linux/stddef.h> #include <linux/types.h> /* * Gives us 8 prio classes with 13-bits of data for each class */ #define IOPRIO_CLASS_SHIFT 13 #define IOPRIO_NR_CLASSES 8 #define IOPRIO_CLASS_MASK (IOPRIO_NR_CLASSES - 1) #define IOPRIO_PRIO_MASK ((1UL << IOPRIO_CLASS_SHIFT) - 1) #define IOPRIO_PRIO_CLASS(ioprio) \ (((ioprio) >> IOPRIO_CLASS_SHIFT) & IOPRIO_CLASS_MASK) #define IOPRIO_PRIO_DATA(ioprio) ((ioprio) & IOPRIO_PRIO_MASK) /* * These are the io priority classes as implemented by the BFQ and mq-deadline * schedulers. RT is the realtime class, it always gets premium service. For * ATA disks supporting NCQ IO priority, RT class IOs will be processed using * high priority NCQ commands. BE is the best-effort scheduling class, the * default for any process. IDLE is the idle scheduling class, it is only * served when no one else is using the disk. */ enum { IOPRIO_CLASS_NONE = 0, IOPRIO_CLASS_RT = 1, IOPRIO_CLASS_BE = 2, IOPRIO_CLASS_IDLE = 3, /* Special class to indicate an invalid ioprio value */ IOPRIO_CLASS_INVALID = 7, }; /* * The RT and BE priority classes both support up to 8 priority levels that * can be specified using the lower 3-bits of the priority data. */ #define IOPRIO_LEVEL_NR_BITS 3 #define IOPRIO_NR_LEVELS (1 << IOPRIO_LEVEL_NR_BITS) #define IOPRIO_LEVEL_MASK (IOPRIO_NR_LEVELS - 1) #define IOPRIO_PRIO_LEVEL(ioprio) ((ioprio) & IOPRIO_LEVEL_MASK) #define IOPRIO_BE_NR IOPRIO_NR_LEVELS /* * Possible values for the "which" argument of the ioprio_get() and * ioprio_set() system calls (see "man ioprio_set"). */ enum { IOPRIO_WHO_PROCESS = 1, IOPRIO_WHO_PGRP, IOPRIO_WHO_USER, }; /* * Fallback BE class priority level. */ #define IOPRIO_NORM 4 #define IOPRIO_BE_NORM IOPRIO_NORM /* * The 10 bits between the priority class and the priority level are used to * optionally define I/O hints for any combination of I/O priority class and * level. Depending on the kernel configuration, I/O scheduler being used and * the target I/O device being used, hints can influence how I/Os are processed * without affecting the I/O scheduling ordering defined by the I/O priority * class and level. */ #define IOPRIO_HINT_SHIFT IOPRIO_LEVEL_NR_BITS #define IOPRIO_HINT_NR_BITS 10 #define IOPRIO_NR_HINTS (1 << IOPRIO_HINT_NR_BITS) #define IOPRIO_HINT_MASK (IOPRIO_NR_HINTS - 1) #define IOPRIO_PRIO_HINT(ioprio) \ (((ioprio) >> IOPRIO_HINT_SHIFT) & IOPRIO_HINT_MASK) /* * I/O hints. */ enum { /* No hint */ IOPRIO_HINT_NONE = 0, /* * Device command duration limits: indicate to the device a desired * duration limit for the commands that will be used to process an I/O. * These will currently only be effective for SCSI and ATA devices that * support the command duration limits feature. If this feature is * enabled, then the commands issued to the device to process an I/O with * one of these hints set will have the duration limit index (dld field) * set to the value of the hint. */ IOPRIO_HINT_DEV_DURATION_LIMIT_1 = 1, IOPRIO_HINT_DEV_DURATION_LIMIT_2 = 2, IOPRIO_HINT_DEV_DURATION_LIMIT_3 = 3, IOPRIO_HINT_DEV_DURATION_LIMIT_4 = 4, IOPRIO_HINT_DEV_DURATION_LIMIT_5 = 5, IOPRIO_HINT_DEV_DURATION_LIMIT_6 = 6, IOPRIO_HINT_DEV_DURATION_LIMIT_7 = 7, }; #define IOPRIO_BAD_VALUE(val, max) ((val) < 0 || (val) >= (max)) /* * Return an I/O priority value based on a class, a level and a hint. */ static __always_inline __u16 ioprio_value(int prioclass, int priolevel, int priohint) { if (IOPRIO_BAD_VALUE(prioclass, IOPRIO_NR_CLASSES) || IOPRIO_BAD_VALUE(priolevel, IOPRIO_NR_LEVELS) || IOPRIO_BAD_VALUE(priohint, IOPRIO_NR_HINTS)) return IOPRIO_CLASS_INVALID << IOPRIO_CLASS_SHIFT; return (prioclass << IOPRIO_CLASS_SHIFT) | (priohint << IOPRIO_HINT_SHIFT) | priolevel; } #define IOPRIO_PRIO_VALUE(prioclass, priolevel) \ ioprio_value(prioclass, priolevel, IOPRIO_HINT_NONE) #define IOPRIO_PRIO_VALUE_HINT(prioclass, priolevel, priohint) \ ioprio_value(prioclass, priolevel, priohint) #endif /* _UAPI_LINUX_IOPRIO_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Special Initializers for certain USB Mass Storage devices * * Current development and maintenance by: * (c) 1999, 2000 Matthew Dharm (mdharm-usb@one-eyed-alien.net) * * This driver is based on the 'USB Mass Storage Class' document. This * describes in detail the protocol used to communicate with such * devices. Clearly, the designers had SCSI and ATAPI commands in * mind when they created this document. The commands are all very * similar to commands in the SCSI-II and ATAPI specifications. * * It is important to note that in a number of cases this class * exhibits class-specific exemptions from the USB specification. * Notably the usage of NAK, STALL and ACK differs from the norm, in * that they are used to communicate wait, failed and OK on commands. * * Also, for certain devices, the interrupt endpoint is used to convey * status of a command. */ #include <linux/errno.h> #include "usb.h" #include "initializers.h" #include "debug.h" #include "transport.h" /* * This places the Shuttle/SCM USB<->SCSI bridge devices in multi-target * mode */ int usb_stor_euscsi_init(struct us_data *us) { int result; usb_stor_dbg(us, "Attempting to init eUSCSI bridge...\n"); result = usb_stor_control_msg(us, us->send_ctrl_pipe, 0x0C, USB_RECIP_INTERFACE | USB_TYPE_VENDOR, 0x01, 0x0, NULL, 0x0, 5 * HZ); usb_stor_dbg(us, "-- result is %d\n", result); return 0; } /* * This function is required to activate all four slots on the UCR-61S2B * flash reader */ int usb_stor_ucr61s2b_init(struct us_data *us) { struct bulk_cb_wrap *bcb = (struct bulk_cb_wrap*) us->iobuf; struct bulk_cs_wrap *bcs = (struct bulk_cs_wrap*) us->iobuf; int res; unsigned int partial; static const char init_string[] = "\xec\x0a\x06\x00$PCCHIPS"; usb_stor_dbg(us, "Sending UCR-61S2B initialization packet...\n"); bcb->Signature = cpu_to_le32(US_BULK_CB_SIGN); bcb->Tag = 0; bcb->DataTransferLength = cpu_to_le32(0); bcb->Flags = bcb->Lun = 0; bcb->Length = sizeof(init_string) - 1; memset(bcb->CDB, 0, sizeof(bcb->CDB)); memcpy(bcb->CDB, init_string, sizeof(init_string) - 1); res = usb_stor_bulk_transfer_buf(us, us->send_bulk_pipe, bcb, US_BULK_CB_WRAP_LEN, &partial); if (res) return -EIO; usb_stor_dbg(us, "Getting status packet...\n"); res = usb_stor_bulk_transfer_buf(us, us->recv_bulk_pipe, bcs, US_BULK_CS_WRAP_LEN, &partial); if (res) return -EIO; return 0; } /* This places the HUAWEI E220 devices in multi-port mode */ int usb_stor_huawei_e220_init(struct us_data *us) { int result; result = usb_stor_control_msg(us, us->send_ctrl_pipe, USB_REQ_SET_FEATURE, USB_TYPE_STANDARD | USB_RECIP_DEVICE, 0x01, 0x0, NULL, 0x0, 1 * HZ); usb_stor_dbg(us, "Huawei mode set result is %d\n", result); return 0; } |
| 14764 584 | 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 */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 32 32 32 32 32 1 31 1 1 3 3 1 2 1 2 2 3 3 1 3 3 1 1 3 1 3 1 3 3 4 4 4 4 4 4 4 1 1 1 3 3 1 2 3 3 3 3 3 3 1 3 2 3 3 3 3 3 3 3 1 3 3 3 3 3 3 3 3 3 1 3 3 3 3 3 3 3 1 1 4 2 4 4 1 2 2 4 4 4 3 2 3 3 3 3 1 3 1 3 1 3 3 1 3 3 4 4 4 1 1 1 4 4 1 3 1 1 3 3 3 2 1 3 1 4 4 4 4 4 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2002, 2004 Oracle. All rights reserved. */ #include <linux/fs.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <asm/byteorder.h> #include <linux/swap.h> #include <linux/mpage.h> #include <linux/quotaops.h> #include <linux/blkdev.h> #include <linux/uio.h> #include <linux/mm.h> #include <cluster/masklog.h> #include "ocfs2.h" #include "alloc.h" #include "aops.h" #include "dlmglue.h" #include "extent_map.h" #include "file.h" #include "inode.h" #include "journal.h" #include "suballoc.h" #include "super.h" #include "symlink.h" #include "refcounttree.h" #include "ocfs2_trace.h" #include "buffer_head_io.h" #include "dir.h" #include "namei.h" #include "sysfile.h" #define OCFS2_DIO_MARK_EXTENT_BATCH 200 static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int err = -EIO; int status; struct ocfs2_dinode *fe = NULL; struct buffer_head *bh = NULL; struct buffer_head *buffer_cache_bh = NULL; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); trace_ocfs2_symlink_get_block( (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)iblock, bh_result, create); BUG_ON(ocfs2_inode_is_fast_symlink(inode)); if ((iblock << inode->i_sb->s_blocksize_bits) > PATH_MAX + 1) { mlog(ML_ERROR, "block offset > PATH_MAX: %llu", (unsigned long long)iblock); goto bail; } status = ocfs2_read_inode_block(inode, &bh); if (status < 0) { mlog_errno(status); goto bail; } fe = (struct ocfs2_dinode *) bh->b_data; if ((u64)iblock >= ocfs2_clusters_to_blocks(inode->i_sb, le32_to_cpu(fe->i_clusters))) { err = -ENOMEM; mlog(ML_ERROR, "block offset is outside the allocated size: " "%llu\n", (unsigned long long)iblock); goto bail; } /* We don't use the page cache to create symlink data, so if * need be, copy it over from the buffer cache. */ if (!buffer_uptodate(bh_result) && ocfs2_inode_is_new(inode)) { u64 blkno = le64_to_cpu(fe->id2.i_list.l_recs[0].e_blkno) + iblock; buffer_cache_bh = sb_getblk(osb->sb, blkno); if (!buffer_cache_bh) { err = -ENOMEM; mlog(ML_ERROR, "couldn't getblock for symlink!\n"); goto bail; } /* we haven't locked out transactions, so a commit * could've happened. Since we've got a reference on * the bh, even if it commits while we're doing the * copy, the data is still good. */ if (buffer_jbd(buffer_cache_bh) && ocfs2_inode_is_new(inode)) { memcpy_to_folio(bh_result->b_folio, bh_result->b_size * iblock, buffer_cache_bh->b_data, bh_result->b_size); set_buffer_uptodate(bh_result); } brelse(buffer_cache_bh); } map_bh(bh_result, inode->i_sb, le64_to_cpu(fe->id2.i_list.l_recs[0].e_blkno) + iblock); err = 0; bail: brelse(bh); return err; } static int ocfs2_lock_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int ret = 0; struct ocfs2_inode_info *oi = OCFS2_I(inode); down_read(&oi->ip_alloc_sem); ret = ocfs2_get_block(inode, iblock, bh_result, create); up_read(&oi->ip_alloc_sem); return ret; } int ocfs2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int err = 0; unsigned int ext_flags; u64 max_blocks = bh_result->b_size >> inode->i_blkbits; u64 p_blkno, count, past_eof; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); trace_ocfs2_get_block((unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)iblock, bh_result, create); if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE) mlog(ML_NOTICE, "get_block on system inode 0x%p (%llu)\n", inode, inode->i_ino); if (S_ISLNK(inode->i_mode)) { /* this always does I/O for some reason. */ err = ocfs2_symlink_get_block(inode, iblock, bh_result, create); goto bail; } err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, &count, &ext_flags); if (err) { mlog(ML_ERROR, "get_blocks() failed, inode: 0x%p, " "block: %llu\n", inode, (unsigned long long)iblock); goto bail; } if (max_blocks < count) count = max_blocks; /* * ocfs2 never allocates in this function - the only time we * need to use BH_New is when we're extending i_size on a file * system which doesn't support holes, in which case BH_New * allows __block_write_begin() to zero. * * If we see this on a sparse file system, then a truncate has * raced us and removed the cluster. In this case, we clear * the buffers dirty and uptodate bits and let the buffer code * ignore it as a hole. */ if (create && p_blkno == 0 && ocfs2_sparse_alloc(osb)) { clear_buffer_dirty(bh_result); clear_buffer_uptodate(bh_result); goto bail; } /* Treat the unwritten extent as a hole for zeroing purposes. */ if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN)) map_bh(bh_result, inode->i_sb, p_blkno); bh_result->b_size = count << inode->i_blkbits; if (!ocfs2_sparse_alloc(osb)) { if (p_blkno == 0) { err = -EIO; mlog(ML_ERROR, "iblock = %llu p_blkno = %llu blkno=(%llu)\n", (unsigned long long)iblock, (unsigned long long)p_blkno, (unsigned long long)OCFS2_I(inode)->ip_blkno); mlog(ML_ERROR, "Size %llu, clusters %u\n", (unsigned long long)i_size_read(inode), OCFS2_I(inode)->ip_clusters); dump_stack(); goto bail; } } past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode)); trace_ocfs2_get_block_end((unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)past_eof); if (create && (iblock >= past_eof)) set_buffer_new(bh_result); bail: if (err < 0) err = -EIO; return err; } int ocfs2_read_inline_data(struct inode *inode, struct folio *folio, struct buffer_head *di_bh) { loff_t size; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; if (!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL)) { ocfs2_error(inode->i_sb, "Inode %llu lost inline data flag\n", (unsigned long long)OCFS2_I(inode)->ip_blkno); return -EROFS; } size = i_size_read(inode); if (size > folio_size(folio) || size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) { ocfs2_error(inode->i_sb, "Inode %llu has with inline data has bad size: %Lu\n", (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)size); return -EROFS; } folio_fill_tail(folio, 0, di->id2.i_data.id_data, size); folio_mark_uptodate(folio); return 0; } static int ocfs2_readpage_inline(struct inode *inode, struct folio *folio) { int ret; struct buffer_head *di_bh = NULL; BUG_ON(!folio_test_locked(folio)); BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)); ret = ocfs2_read_inode_block(inode, &di_bh); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_read_inline_data(inode, folio, di_bh); out: folio_unlock(folio); brelse(di_bh); return ret; } static int ocfs2_read_folio(struct file *file, struct folio *folio) { struct inode *inode = folio->mapping->host; struct ocfs2_inode_info *oi = OCFS2_I(inode); loff_t start = folio_pos(folio); int ret, unlock = 1; trace_ocfs2_readpage((unsigned long long)oi->ip_blkno, folio->index); ret = ocfs2_inode_lock_with_folio(inode, NULL, 0, folio); if (ret != 0) { if (ret == AOP_TRUNCATED_PAGE) unlock = 0; mlog_errno(ret); goto out; } if (down_read_trylock(&oi->ip_alloc_sem) == 0) { /* * Unlock the folio and cycle ip_alloc_sem so that we don't * busyloop waiting for ip_alloc_sem to unlock */ ret = AOP_TRUNCATED_PAGE; folio_unlock(folio); unlock = 0; down_read(&oi->ip_alloc_sem); up_read(&oi->ip_alloc_sem); goto out_inode_unlock; } /* * i_size might have just been updated as we grabbed the meta lock. We * might now be discovering a truncate that hit on another node. * block_read_full_folio->get_block freaks out if it is asked to read * beyond the end of a file, so we check here. Callers * (generic_file_read, vm_ops->fault) are clever enough to check i_size * and notice that the folio they just read isn't needed. * * XXX sys_readahead() seems to get that wrong? */ if (start >= i_size_read(inode)) { folio_zero_segment(folio, 0, folio_size(folio)); folio_mark_uptodate(folio); ret = 0; goto out_alloc; } if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) ret = ocfs2_readpage_inline(inode, folio); else ret = block_read_full_folio(folio, ocfs2_get_block); unlock = 0; out_alloc: up_read(&oi->ip_alloc_sem); out_inode_unlock: ocfs2_inode_unlock(inode, 0); out: if (unlock) folio_unlock(folio); return ret; } /* * This is used only for read-ahead. Failures or difficult to handle * situations are safe to ignore. * * Right now, we don't bother with BH_Boundary - in-inode extent lists * are quite large (243 extents on 4k blocks), so most inodes don't * grow out to a tree. If need be, detecting boundary extents could * trivially be added in a future version of ocfs2_get_block(). */ static void ocfs2_readahead(struct readahead_control *rac) { int ret; struct inode *inode = rac->mapping->host; struct ocfs2_inode_info *oi = OCFS2_I(inode); /* * Use the nonblocking flag for the dlm code to avoid page * lock inversion, but don't bother with retrying. */ ret = ocfs2_inode_lock_full(inode, NULL, 0, OCFS2_LOCK_NONBLOCK); if (ret) return; if (down_read_trylock(&oi->ip_alloc_sem) == 0) goto out_unlock; /* * Don't bother with inline-data. There isn't anything * to read-ahead in that case anyway... */ if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) goto out_up; /* * Check whether a remote node truncated this file - we just * drop out in that case as it's not worth handling here. */ if (readahead_pos(rac) >= i_size_read(inode)) goto out_up; mpage_readahead(rac, ocfs2_get_block); out_up: up_read(&oi->ip_alloc_sem); out_unlock: ocfs2_inode_unlock(inode, 0); } /* Note: Because we don't support holes, our allocation has * already happened (allocation writes zeros to the file data) * so we don't have to worry about ordered writes in * ocfs2_writepages. * * ->writepages is called during the process of invalidating the page cache * during blocked lock processing. It can't block on any cluster locks * to during block mapping. It's relying on the fact that the block * mapping can't have disappeared under the dirty pages that it is * being asked to write back. */ static int ocfs2_writepages(struct address_space *mapping, struct writeback_control *wbc) { return mpage_writepages(mapping, wbc, ocfs2_get_block); } /* Taken from ext3. We don't necessarily need the full blown * functionality yet, but IMHO it's better to cut and paste the whole * thing so we can avoid introducing our own bugs (and easily pick up * their fixes when they happen) --Mark */ int walk_page_buffers( handle_t *handle, struct buffer_head *head, unsigned from, unsigned to, int *partial, int (*fn)( handle_t *handle, struct buffer_head *bh)) { struct buffer_head *bh; unsigned block_start, block_end; unsigned blocksize = head->b_size; int err, ret = 0; struct buffer_head *next; for ( bh = head, block_start = 0; ret == 0 && (bh != head || !block_start); block_start = block_end, bh = next) { next = bh->b_this_page; block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (partial && !buffer_uptodate(bh)) *partial = 1; continue; } err = (*fn)(handle, bh); if (!ret) ret = err; } return ret; } static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block) { sector_t status; u64 p_blkno = 0; int err = 0; struct inode *inode = mapping->host; trace_ocfs2_bmap((unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)block); /* * The swap code (ab-)uses ->bmap to get a block mapping and then * bypasseѕ the file system for actual I/O. We really can't allow * that on refcounted inodes, so we have to skip out here. And yes, * 0 is the magic code for a bmap error.. */ if (ocfs2_is_refcount_inode(inode)) return 0; /* We don't need to lock journal system files, since they aren't * accessed concurrently from multiple nodes. */ if (!INODE_JOURNAL(inode)) { err = ocfs2_inode_lock(inode, NULL, 0); if (err) { if (err != -ENOENT) mlog_errno(err); goto bail; } down_read(&OCFS2_I(inode)->ip_alloc_sem); } if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)) err = ocfs2_extent_map_get_blocks(inode, block, &p_blkno, NULL, NULL); if (!INODE_JOURNAL(inode)) { up_read(&OCFS2_I(inode)->ip_alloc_sem); ocfs2_inode_unlock(inode, 0); } if (err) { mlog(ML_ERROR, "get_blocks() failed, block = %llu\n", (unsigned long long)block); mlog_errno(err); goto bail; } bail: status = err ? 0 : p_blkno; return status; } static bool ocfs2_release_folio(struct folio *folio, gfp_t wait) { if (!folio_buffers(folio)) return false; return try_to_free_buffers(folio); } static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb, u32 cpos, unsigned int *start, unsigned int *end) { unsigned int cluster_start = 0, cluster_end = PAGE_SIZE; if (unlikely(PAGE_SHIFT > osb->s_clustersize_bits)) { unsigned int cpp; cpp = 1 << (PAGE_SHIFT - osb->s_clustersize_bits); cluster_start = cpos % cpp; cluster_start = cluster_start << osb->s_clustersize_bits; cluster_end = cluster_start + osb->s_clustersize; } BUG_ON(cluster_start > PAGE_SIZE); BUG_ON(cluster_end > PAGE_SIZE); if (start) *start = cluster_start; if (end) *end = cluster_end; } /* * 'from' and 'to' are the region in the page to avoid zeroing. * * If pagesize > clustersize, this function will avoid zeroing outside * of the cluster boundary. * * from == to == 0 is code for "zero the entire cluster region" */ static void ocfs2_clear_folio_regions(struct folio *folio, struct ocfs2_super *osb, u32 cpos, unsigned from, unsigned to) { void *kaddr; unsigned int cluster_start, cluster_end; ocfs2_figure_cluster_boundaries(osb, cpos, &cluster_start, &cluster_end); kaddr = kmap_local_folio(folio, 0); if (from || to) { if (from > cluster_start) memset(kaddr + cluster_start, 0, from - cluster_start); if (to < cluster_end) memset(kaddr + to, 0, cluster_end - to); } else { memset(kaddr + cluster_start, 0, cluster_end - cluster_start); } kunmap_local(kaddr); } /* * Nonsparse file systems fully allocate before we get to the write * code. This prevents ocfs2_write() from tagging the write as an * allocating one, which means ocfs2_map_folio_blocks() might try to * read-in the blocks at the tail of our file. Avoid reading them by * testing i_size against each block offset. */ static int ocfs2_should_read_blk(struct inode *inode, struct folio *folio, unsigned int block_start) { u64 offset = folio_pos(folio) + block_start; if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) return 1; if (i_size_read(inode) > offset) return 1; return 0; } /* * Some of this taken from __block_write_begin(). We already have our * mapping by now though, and the entire write will be allocating or * it won't, so not much need to use BH_New. * * This will also skip zeroing, which is handled externally. */ int ocfs2_map_folio_blocks(struct folio *folio, u64 *p_blkno, struct inode *inode, unsigned int from, unsigned int to, int new) { int ret = 0; struct buffer_head *head, *bh, *wait[2], **wait_bh = wait; unsigned int block_end, block_start; unsigned int bsize = i_blocksize(inode); head = folio_buffers(folio); if (!head) head = create_empty_buffers(folio, bsize, 0); for (bh = head, block_start = 0; bh != head || !block_start; bh = bh->b_this_page, block_start += bsize) { block_end = block_start + bsize; clear_buffer_new(bh); /* * Ignore blocks outside of our i/o range - * they may belong to unallocated clusters. */ if (block_start >= to || block_end <= from) { if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); continue; } /* * For an allocating write with cluster size >= page * size, we always write the entire page. */ if (new) set_buffer_new(bh); if (!buffer_mapped(bh)) { map_bh(bh, inode->i_sb, *p_blkno); clean_bdev_bh_alias(bh); } if (folio_test_uptodate(folio)) { set_buffer_uptodate(bh); } else if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_new(bh) && ocfs2_should_read_blk(inode, folio, block_start) && (block_start < from || block_end > to)) { bh_read_nowait(bh, 0); *wait_bh++=bh; } *p_blkno = *p_blkno + 1; } /* * If we issued read requests - let them complete. */ while(wait_bh > wait) { wait_on_buffer(*--wait_bh); if (!buffer_uptodate(*wait_bh)) ret = -EIO; } if (ret == 0 || !new) return ret; /* * If we get -EIO above, zero out any newly allocated blocks * to avoid exposing stale data. */ bh = head; block_start = 0; do { block_end = block_start + bsize; if (block_end <= from) goto next_bh; if (block_start >= to) break; folio_zero_range(folio, block_start, bh->b_size); set_buffer_uptodate(bh); mark_buffer_dirty(bh); next_bh: block_start = block_end; bh = bh->b_this_page; } while (bh != head); return ret; } #if (PAGE_SIZE >= OCFS2_MAX_CLUSTERSIZE) #define OCFS2_MAX_CTXT_PAGES 1 #else #define OCFS2_MAX_CTXT_PAGES (OCFS2_MAX_CLUSTERSIZE / PAGE_SIZE) #endif #define OCFS2_MAX_CLUSTERS_PER_PAGE (PAGE_SIZE / OCFS2_MIN_CLUSTERSIZE) struct ocfs2_unwritten_extent { struct list_head ue_node; struct list_head ue_ip_node; u32 ue_cpos; u32 ue_phys; }; /* * Describe the state of a single cluster to be written to. */ struct ocfs2_write_cluster_desc { u32 c_cpos; u32 c_phys; /* * Give this a unique field because c_phys eventually gets * filled. */ unsigned c_new; unsigned c_clear_unwritten; unsigned c_needs_zero; }; struct ocfs2_write_ctxt { /* Logical cluster position / len of write */ u32 w_cpos; u32 w_clen; /* First cluster allocated in a nonsparse extend */ u32 w_first_new_cpos; /* Type of caller. Must be one of buffer, mmap, direct. */ ocfs2_write_type_t w_type; struct ocfs2_write_cluster_desc w_desc[OCFS2_MAX_CLUSTERS_PER_PAGE]; /* * This is true if page_size > cluster_size. * * It triggers a set of special cases during write which might * have to deal with allocating writes to partial pages. */ unsigned int w_large_pages; /* * Folios involved in this write. * * w_target_folio is the folio being written to by the user. * * w_folios is an array of folios which always contains * w_target_folio, and in the case of an allocating write with * page_size < cluster size, it will contain zero'd and mapped * pages adjacent to w_target_folio which need to be written * out in so that future reads from that region will get * zero's. */ unsigned int w_num_folios; struct folio *w_folios[OCFS2_MAX_CTXT_PAGES]; struct folio *w_target_folio; /* * w_target_locked is used for page_mkwrite path indicating no unlocking * against w_target_folio in ocfs2_write_end_nolock. */ unsigned int w_target_locked:1; /* * ocfs2_write_end() uses this to know what the real range to * write in the target should be. */ unsigned int w_target_from; unsigned int w_target_to; /* * We could use journal_current_handle() but this is cleaner, * IMHO -Mark */ handle_t *w_handle; struct buffer_head *w_di_bh; struct ocfs2_cached_dealloc_ctxt w_dealloc; struct list_head w_unwritten_list; unsigned int w_unwritten_count; }; void ocfs2_unlock_and_free_folios(struct folio **folios, int num_folios) { int i; for(i = 0; i < num_folios; i++) { if (!folios[i]) continue; folio_unlock(folios[i]); folio_mark_accessed(folios[i]); folio_put(folios[i]); } } static void ocfs2_unlock_folios(struct ocfs2_write_ctxt *wc) { int i; /* * w_target_locked is only set to true in the page_mkwrite() case. * The intent is to allow us to lock the target page from write_begin() * to write_end(). The caller must hold a ref on w_target_folio. */ if (wc->w_target_locked) { BUG_ON(!wc->w_target_folio); for (i = 0; i < wc->w_num_folios; i++) { if (wc->w_target_folio == wc->w_folios[i]) { wc->w_folios[i] = NULL; break; } } folio_mark_accessed(wc->w_target_folio); folio_put(wc->w_target_folio); } ocfs2_unlock_and_free_folios(wc->w_folios, wc->w_num_folios); } static void ocfs2_free_unwritten_list(struct inode *inode, struct list_head *head) { struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_unwritten_extent *ue = NULL, *tmp = NULL; list_for_each_entry_safe(ue, tmp, head, ue_node) { list_del(&ue->ue_node); spin_lock(&oi->ip_lock); list_del(&ue->ue_ip_node); spin_unlock(&oi->ip_lock); kfree(ue); } } static void ocfs2_free_write_ctxt(struct inode *inode, struct ocfs2_write_ctxt *wc) { ocfs2_free_unwritten_list(inode, &wc->w_unwritten_list); ocfs2_unlock_folios(wc); brelse(wc->w_di_bh); kfree(wc); } static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp, struct ocfs2_super *osb, loff_t pos, unsigned len, ocfs2_write_type_t type, struct buffer_head *di_bh) { u32 cend; struct ocfs2_write_ctxt *wc; wc = kzalloc_obj(struct ocfs2_write_ctxt, GFP_NOFS); if (!wc) return -ENOMEM; wc->w_cpos = pos >> osb->s_clustersize_bits; wc->w_first_new_cpos = UINT_MAX; cend = (pos + len - 1) >> osb->s_clustersize_bits; wc->w_clen = cend - wc->w_cpos + 1; get_bh(di_bh); wc->w_di_bh = di_bh; wc->w_type = type; if (unlikely(PAGE_SHIFT > osb->s_clustersize_bits)) wc->w_large_pages = 1; else wc->w_large_pages = 0; ocfs2_init_dealloc_ctxt(&wc->w_dealloc); INIT_LIST_HEAD(&wc->w_unwritten_list); *wcp = wc; return 0; } /* * If a page has any new buffers, zero them out here, and mark them uptodate * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ static void ocfs2_zero_new_buffers(struct folio *folio, size_t from, size_t to) { unsigned int block_start, block_end; struct buffer_head *head, *bh; BUG_ON(!folio_test_locked(folio)); head = folio_buffers(folio); if (!head) return; bh = head; block_start = 0; do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { if (!folio_test_uptodate(folio)) { unsigned start, end; start = max(from, block_start); end = min(to, block_end); folio_zero_segment(folio, start, end); set_buffer_uptodate(bh); } clear_buffer_new(bh); mark_buffer_dirty(bh); } } block_start = block_end; bh = bh->b_this_page; } while (bh != head); } /* * Only called when we have a failure during allocating write to write * zero's to the newly allocated region. */ static void ocfs2_write_failure(struct inode *inode, struct ocfs2_write_ctxt *wc, loff_t user_pos, unsigned user_len) { int i; unsigned from = user_pos & (PAGE_SIZE - 1), to = user_pos + user_len; if (wc->w_target_folio) ocfs2_zero_new_buffers(wc->w_target_folio, from, to); for (i = 0; i < wc->w_num_folios; i++) { struct folio *folio = wc->w_folios[i]; if (folio && folio_buffers(folio)) { if (ocfs2_should_order_data(inode)) ocfs2_jbd2_inode_add_write(wc->w_handle, inode, user_pos, user_len); block_commit_write(folio, from, to); } } } static int ocfs2_prepare_folio_for_write(struct inode *inode, u64 *p_blkno, struct ocfs2_write_ctxt *wc, struct folio *folio, u32 cpos, loff_t user_pos, unsigned user_len, int new) { int ret; unsigned int map_from = 0, map_to = 0; unsigned int cluster_start, cluster_end; unsigned int user_data_from = 0, user_data_to = 0; ocfs2_figure_cluster_boundaries(OCFS2_SB(inode->i_sb), cpos, &cluster_start, &cluster_end); /* treat the write as new if the a hole/lseek spanned across * the page boundary. */ new = new | ((i_size_read(inode) <= folio_pos(folio)) && (folio_pos(folio) <= user_pos)); if (folio == wc->w_target_folio) { map_from = user_pos & (PAGE_SIZE - 1); map_to = map_from + user_len; if (new) ret = ocfs2_map_folio_blocks(folio, p_blkno, inode, cluster_start, cluster_end, new); else ret = ocfs2_map_folio_blocks(folio, p_blkno, inode, map_from, map_to, new); if (ret) { mlog_errno(ret); goto out; } user_data_from = map_from; user_data_to = map_to; if (new) { map_from = cluster_start; map_to = cluster_end; } } else { /* * If we haven't allocated the new folio yet, we * shouldn't be writing it out without copying user * data. This is likely a math error from the caller. */ BUG_ON(!new); map_from = cluster_start; map_to = cluster_end; ret = ocfs2_map_folio_blocks(folio, p_blkno, inode, cluster_start, cluster_end, new); if (ret) { mlog_errno(ret); goto out; } } /* * Parts of newly allocated folios need to be zero'd. * * Above, we have also rewritten 'to' and 'from' - as far as * the rest of the function is concerned, the entire cluster * range inside of a folio needs to be written. * * We can skip this if the folio is uptodate - it's already * been zero'd from being read in as a hole. */ if (new && !folio_test_uptodate(folio)) ocfs2_clear_folio_regions(folio, OCFS2_SB(inode->i_sb), cpos, user_data_from, user_data_to); flush_dcache_folio(folio); out: return ret; } /* * This function will only grab one clusters worth of pages. */ static int ocfs2_grab_folios_for_write(struct address_space *mapping, struct ocfs2_write_ctxt *wc, u32 cpos, loff_t user_pos, unsigned user_len, int new, struct folio *mmap_folio) { int ret = 0, i; unsigned long start, target_index, end_index, index; struct inode *inode = mapping->host; loff_t last_byte; target_index = user_pos >> PAGE_SHIFT; /* * Figure out how many pages we'll be manipulating here. For * non allocating write, we just change the one * page. Otherwise, we'll need a whole clusters worth. If we're * writing past i_size, we only need enough pages to cover the * last page of the write. */ if (new) { wc->w_num_folios = ocfs2_pages_per_cluster(inode->i_sb); start = ocfs2_align_clusters_to_page_index(inode->i_sb, cpos); /* * We need the index *past* the last page we could possibly * touch. This is the page past the end of the write or * i_size, whichever is greater. */ last_byte = max(user_pos + user_len, i_size_read(inode)); BUG_ON(last_byte < 1); end_index = ((last_byte - 1) >> PAGE_SHIFT) + 1; if ((start + wc->w_num_folios) > end_index) wc->w_num_folios = end_index - start; } else { wc->w_num_folios = 1; start = target_index; } end_index = (user_pos + user_len - 1) >> PAGE_SHIFT; for(i = 0; i < wc->w_num_folios; i++) { index = start + i; if (index >= target_index && index <= end_index && wc->w_type == OCFS2_WRITE_MMAP) { /* * ocfs2_pagemkwrite() is a little different * and wants us to directly use the page * passed in. */ folio_lock(mmap_folio); /* Exit and let the caller retry */ if (mmap_folio->mapping != mapping) { WARN_ON(mmap_folio->mapping); folio_unlock(mmap_folio); ret = -EAGAIN; goto out; } folio_get(mmap_folio); wc->w_folios[i] = mmap_folio; wc->w_target_locked = true; } else if (index >= target_index && index <= end_index && wc->w_type == OCFS2_WRITE_DIRECT) { /* Direct write has no mapping page. */ wc->w_folios[i] = NULL; continue; } else { wc->w_folios[i] = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS); if (IS_ERR(wc->w_folios[i])) { ret = PTR_ERR(wc->w_folios[i]); mlog_errno(ret); wc->w_folios[i] = NULL; goto out; } } folio_wait_stable(wc->w_folios[i]); if (index == target_index) wc->w_target_folio = wc->w_folios[i]; } out: if (ret) wc->w_target_locked = false; return ret; } /* * Prepare a single cluster for write one cluster into the file. */ static int ocfs2_write_cluster(struct address_space *mapping, u32 *phys, unsigned int new, unsigned int clear_unwritten, unsigned int should_zero, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac, struct ocfs2_write_ctxt *wc, u32 cpos, loff_t user_pos, unsigned user_len) { int ret, i; u64 p_blkno; struct inode *inode = mapping->host; struct ocfs2_extent_tree et; int bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1); if (new) { u32 tmp_pos; /* * This is safe to call with the page locks - it won't take * any additional semaphores or cluster locks. */ tmp_pos = cpos; ret = ocfs2_add_inode_data(OCFS2_SB(inode->i_sb), inode, &tmp_pos, 1, !clear_unwritten, wc->w_di_bh, wc->w_handle, data_ac, meta_ac, NULL); /* * This shouldn't happen because we must have already * calculated the correct meta data allocation required. The * internal tree allocation code should know how to increase * transaction credits itself. * * If need be, we could handle -EAGAIN for a * RESTART_TRANS here. */ mlog_bug_on_msg(ret == -EAGAIN, "Inode %llu: EAGAIN return during allocation.\n", (unsigned long long)OCFS2_I(inode)->ip_blkno); if (ret < 0) { mlog_errno(ret); goto out; } } else if (clear_unwritten) { ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), wc->w_di_bh); ret = ocfs2_mark_extent_written(inode, &et, wc->w_handle, cpos, 1, *phys, meta_ac, &wc->w_dealloc); if (ret < 0) { mlog_errno(ret); goto out; } } /* * The only reason this should fail is due to an inability to * find the extent added. */ ret = ocfs2_get_clusters(inode, cpos, phys, NULL, NULL); if (ret < 0) { mlog(ML_ERROR, "Get physical blkno failed for inode %llu, " "at logical cluster %u", (unsigned long long)OCFS2_I(inode)->ip_blkno, cpos); goto out; } BUG_ON(*phys == 0); p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *phys); if (!should_zero) p_blkno += (user_pos >> inode->i_sb->s_blocksize_bits) & (u64)(bpc - 1); for (i = 0; i < wc->w_num_folios; i++) { int tmpret; /* This is the direct io target page. */ if (wc->w_folios[i] == NULL) { p_blkno += (1 << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits)); continue; } tmpret = ocfs2_prepare_folio_for_write(inode, &p_blkno, wc, wc->w_folios[i], cpos, user_pos, user_len, should_zero); if (tmpret) { mlog_errno(tmpret); if (ret == 0) ret = tmpret; } } /* * We only have cleanup to do in case of allocating write. */ if (ret && new) ocfs2_write_failure(inode, wc, user_pos, user_len); out: return ret; } static int ocfs2_write_cluster_by_desc(struct address_space *mapping, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac, struct ocfs2_write_ctxt *wc, loff_t pos, unsigned len) { int ret, i; loff_t cluster_off; unsigned int local_len = len; struct ocfs2_write_cluster_desc *desc; struct ocfs2_super *osb = OCFS2_SB(mapping->host->i_sb); for (i = 0; i < wc->w_clen; i++) { desc = &wc->w_desc[i]; /* * We have to make sure that the total write passed in * doesn't extend past a single cluster. */ local_len = len; cluster_off = pos & (osb->s_clustersize - 1); if ((cluster_off + local_len) > osb->s_clustersize) local_len = osb->s_clustersize - cluster_off; ret = ocfs2_write_cluster(mapping, &desc->c_phys, desc->c_new, desc->c_clear_unwritten, desc->c_needs_zero, data_ac, meta_ac, wc, desc->c_cpos, pos, local_len); if (ret) { mlog_errno(ret); goto out; } len -= local_len; pos += local_len; } ret = 0; out: return ret; } /* * ocfs2_write_end() wants to know which parts of the target page it * should complete the write on. It's easiest to compute them ahead of * time when a more complete view of the write is available. */ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb, struct ocfs2_write_ctxt *wc, loff_t pos, unsigned len, int alloc) { struct ocfs2_write_cluster_desc *desc; wc->w_target_from = pos & (PAGE_SIZE - 1); wc->w_target_to = wc->w_target_from + len; if (alloc == 0) return; /* * Allocating write - we may have different boundaries based * on page size and cluster size. * * NOTE: We can no longer compute one value from the other as * the actual write length and user provided length may be * different. */ if (wc->w_large_pages) { /* * We only care about the 1st and last cluster within * our range and whether they should be zero'd or not. Either * value may be extended out to the start/end of a * newly allocated cluster. */ desc = &wc->w_desc[0]; if (desc->c_needs_zero) ocfs2_figure_cluster_boundaries(osb, desc->c_cpos, &wc->w_target_from, NULL); desc = &wc->w_desc[wc->w_clen - 1]; if (desc->c_needs_zero) ocfs2_figure_cluster_boundaries(osb, desc->c_cpos, NULL, &wc->w_target_to); } else { wc->w_target_from = 0; wc->w_target_to = PAGE_SIZE; } } /* * Check if this extent is marked UNWRITTEN by direct io. If so, we need not to * do the zero work. And should not to clear UNWRITTEN since it will be cleared * by the direct io procedure. * If this is a new extent that allocated by direct io, we should mark it in * the ip_unwritten_list. */ static int ocfs2_unwritten_check(struct inode *inode, struct ocfs2_write_ctxt *wc, struct ocfs2_write_cluster_desc *desc) { struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_unwritten_extent *ue = NULL, *new = NULL; int ret = 0; if (!desc->c_needs_zero) return 0; retry: spin_lock(&oi->ip_lock); /* Needs not to zero no metter buffer or direct. The one who is zero * the cluster is doing zero. And he will clear unwritten after all * cluster io finished. */ list_for_each_entry(ue, &oi->ip_unwritten_list, ue_ip_node) { if (desc->c_cpos == ue->ue_cpos) { BUG_ON(desc->c_new); desc->c_needs_zero = 0; desc->c_clear_unwritten = 0; goto unlock; } } if (wc->w_type != OCFS2_WRITE_DIRECT) goto unlock; if (new == NULL) { spin_unlock(&oi->ip_lock); new = kmalloc_obj(struct ocfs2_unwritten_extent, GFP_NOFS); if (new == NULL) { ret = -ENOMEM; goto out; } goto retry; } /* This direct write will doing zero. */ new->ue_cpos = desc->c_cpos; new->ue_phys = desc->c_phys; desc->c_clear_unwritten = 0; list_add_tail(&new->ue_ip_node, &oi->ip_unwritten_list); list_add_tail(&new->ue_node, &wc->w_unwritten_list); wc->w_unwritten_count++; new = NULL; unlock: spin_unlock(&oi->ip_lock); out: kfree(new); return ret; } /* * Populate each single-cluster write descriptor in the write context * with information about the i/o to be done. * * Returns the number of clusters that will have to be allocated, as * well as a worst case estimate of the number of extent records that * would have to be created during a write to an unwritten region. */ static int ocfs2_populate_write_desc(struct inode *inode, struct ocfs2_write_ctxt *wc, unsigned int *clusters_to_alloc, unsigned int *extents_to_split) { int ret; struct ocfs2_write_cluster_desc *desc; unsigned int num_clusters = 0; unsigned int ext_flags = 0; u32 phys = 0; int i; *clusters_to_alloc = 0; *extents_to_split = 0; for (i = 0; i < wc->w_clen; i++) { desc = &wc->w_desc[i]; desc->c_cpos = wc->w_cpos + i; if (num_clusters == 0) { /* * Need to look up the next extent record. */ ret = ocfs2_get_clusters(inode, desc->c_cpos, &phys, &num_clusters, &ext_flags); if (ret) { mlog_errno(ret); goto out; } /* We should already CoW the refcountd extent. */ BUG_ON(ext_flags & OCFS2_EXT_REFCOUNTED); /* * Assume worst case - that we're writing in * the middle of the extent. * * We can assume that the write proceeds from * left to right, in which case the extent * insert code is smart enough to coalesce the * next splits into the previous records created. */ if (ext_flags & OCFS2_EXT_UNWRITTEN) *extents_to_split = *extents_to_split + 2; } else if (phys) { /* * Only increment phys if it doesn't describe * a hole. */ phys++; } /* * If w_first_new_cpos is < UINT_MAX, we have a non-sparse * file that got extended. w_first_new_cpos tells us * where the newly allocated clusters are so we can * zero them. */ if (desc->c_cpos >= wc->w_first_new_cpos) { BUG_ON(phys == 0); desc->c_needs_zero = 1; } desc->c_phys = phys; if (phys == 0) { desc->c_new = 1; desc->c_needs_zero = 1; desc->c_clear_unwritten = 1; *clusters_to_alloc = *clusters_to_alloc + 1; } if (ext_flags & OCFS2_EXT_UNWRITTEN) { desc->c_clear_unwritten = 1; desc->c_needs_zero = 1; } ret = ocfs2_unwritten_check(inode, wc, desc); if (ret) { mlog_errno(ret); goto out; } num_clusters--; } ret = 0; out: return ret; } static int ocfs2_write_begin_inline(struct address_space *mapping, struct inode *inode, struct ocfs2_write_ctxt *wc) { int ret; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct folio *folio; handle_t *handle; struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } folio = __filemap_get_folio(mapping, 0, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS); if (IS_ERR(folio)) { ocfs2_commit_trans(osb, handle); ret = PTR_ERR(folio); mlog_errno(ret); goto out; } /* * If we don't set w_num_folios then this folio won't get unlocked * and freed on cleanup of the write context. */ wc->w_target_folio = folio; wc->w_folios[0] = folio; wc->w_num_folios = 1; ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { ocfs2_commit_trans(osb, handle); mlog_errno(ret); goto out; } if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)) ocfs2_set_inode_data_inline(inode, di); if (!folio_test_uptodate(folio)) { ret = ocfs2_read_inline_data(inode, folio, wc->w_di_bh); if (ret) { ocfs2_commit_trans(osb, handle); goto out; } } wc->w_handle = handle; out: return ret; } int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size) { struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; if (new_size <= le16_to_cpu(di->id2.i_data.id_count)) return 1; return 0; } static int ocfs2_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, size_t len, struct folio *mmap_folio, struct ocfs2_write_ctxt *wc) { int ret, written = 0; loff_t end = pos + len; struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_dinode *di = NULL; trace_ocfs2_try_to_write_inline_data((unsigned long long)oi->ip_blkno, len, (unsigned long long)pos, oi->ip_dyn_features); /* * Handle inodes which already have inline data 1st. */ if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) { if (mmap_folio == NULL && ocfs2_size_fits_inline_data(wc->w_di_bh, end)) goto do_inline_write; /* * The write won't fit - we have to give this inode an * inline extent list now. */ ret = ocfs2_convert_inline_data_to_extents(inode, wc->w_di_bh); if (ret) mlog_errno(ret); goto out; } /* * Check whether the inode can accept inline data. */ if (oi->ip_clusters != 0 || i_size_read(inode) != 0) return 0; /* * Check whether the write can fit. */ di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; if (mmap_folio || end > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) return 0; do_inline_write: ret = ocfs2_write_begin_inline(mapping, inode, wc); if (ret) { mlog_errno(ret); goto out; } /* * This signals to the caller that the data can be written * inline. */ written = 1; out: return written ? written : ret; } /* * This function only does anything for file systems which can't * handle sparse files. * * What we want to do here is fill in any hole between the current end * of allocation and the end of our write. That way the rest of the * write path can treat it as an non-allocating write, which has no * special case code for sparse/nonsparse files. */ static int ocfs2_expand_nonsparse_inode(struct inode *inode, struct buffer_head *di_bh, loff_t pos, unsigned len, struct ocfs2_write_ctxt *wc) { int ret; loff_t newsize = pos + len; BUG_ON(ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))); if (newsize <= i_size_read(inode)) return 0; ret = ocfs2_extend_no_holes(inode, di_bh, newsize, pos); if (ret) mlog_errno(ret); /* There is no wc if this is call from direct. */ if (wc) wc->w_first_new_cpos = ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)); return ret; } static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh, loff_t pos) { int ret = 0; BUG_ON(!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))); if (pos > i_size_read(inode)) ret = ocfs2_zero_extend(inode, di_bh, pos); return ret; } int ocfs2_write_begin_nolock(struct address_space *mapping, loff_t pos, unsigned len, ocfs2_write_type_t type, struct folio **foliop, void **fsdata, struct buffer_head *di_bh, struct folio *mmap_folio) { int ret, cluster_of_pages, credits = OCFS2_INODE_UPDATE_CREDITS; unsigned int clusters_to_alloc, extents_to_split, clusters_need = 0; struct ocfs2_write_ctxt *wc; struct inode *inode = mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_dinode *di; struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_alloc_context *meta_ac = NULL; handle_t *handle; struct ocfs2_extent_tree et; int try_free = 1, ret1; try_again: ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, type, di_bh); if (ret) { mlog_errno(ret); return ret; } if (ocfs2_supports_inline_data(osb)) { ret = ocfs2_try_to_write_inline_data(mapping, inode, pos, len, mmap_folio, wc); if (ret == 1) { ret = 0; goto success; } if (ret < 0) { mlog_errno(ret); goto out; } } /* Direct io change i_size late, should not zero tail here. */ if (type != OCFS2_WRITE_DIRECT) { if (ocfs2_sparse_alloc(osb)) ret = ocfs2_zero_tail(inode, di_bh, pos); else ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, len, wc); if (ret) { mlog_errno(ret); goto out; } } ret = ocfs2_check_range_for_refcount(inode, pos, len); if (ret < 0) { mlog_errno(ret); goto out; } else if (ret == 1) { clusters_need = wc->w_clen; ret = ocfs2_refcount_cow(inode, di_bh, wc->w_cpos, wc->w_clen, UINT_MAX); if (ret) { mlog_errno(ret); goto out; } } ret = ocfs2_populate_write_desc(inode, wc, &clusters_to_alloc, &extents_to_split); if (ret) { mlog_errno(ret); goto out; } clusters_need += clusters_to_alloc; di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; trace_ocfs2_write_begin_nolock( (unsigned long long)OCFS2_I(inode)->ip_blkno, (long long)i_size_read(inode), le32_to_cpu(di->i_clusters), pos, len, type, mmap_folio, clusters_to_alloc, extents_to_split); /* * We set w_target_from, w_target_to here so that * ocfs2_write_end() knows which range in the target page to * write out. An allocation requires that we write the entire * cluster range. */ if (clusters_to_alloc || extents_to_split) { /* * XXX: We are stretching the limits of * ocfs2_lock_allocators(). It greatly over-estimates * the work to be done. */ ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), wc->w_di_bh); ret = ocfs2_lock_allocators(inode, &et, clusters_to_alloc, extents_to_split, &data_ac, &meta_ac); if (ret) { mlog_errno(ret); goto out; } if (data_ac) data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv; credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list); } else if (type == OCFS2_WRITE_DIRECT) /* direct write needs not to start trans if no extents alloc. */ goto success; /* * We have to zero sparse allocated clusters, unwritten extent clusters, * and non-sparse clusters we just extended. For non-sparse writes, * we know zeros will only be needed in the first and/or last cluster. */ if (wc->w_clen && (wc->w_desc[0].c_needs_zero || wc->w_desc[wc->w_clen - 1].c_needs_zero)) cluster_of_pages = 1; else cluster_of_pages = 0; ocfs2_set_target_boundaries(osb, wc, pos, len, cluster_of_pages); handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } wc->w_handle = handle; if (clusters_to_alloc) { ret = dquot_alloc_space_nodirty(inode, ocfs2_clusters_to_bytes(osb->sb, clusters_to_alloc)); if (ret) goto out_commit; } ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_quota; } /* * Fill our folio array first. That way we've grabbed enough so * that we can zero and flush if we error after adding the * extent. */ ret = ocfs2_grab_folios_for_write(mapping, wc, wc->w_cpos, pos, len, cluster_of_pages, mmap_folio); if (ret) { /* * ocfs2_grab_folios_for_write() returns -EAGAIN if it * could not lock the target folio. In this case, we exit * with no error and no target folio. This will trigger * the caller, page_mkwrite(), to re-try the operation. */ if (type == OCFS2_WRITE_MMAP && ret == -EAGAIN) { BUG_ON(wc->w_target_folio); ret = 0; goto out_quota; } mlog_errno(ret); goto out_quota; } ret = ocfs2_write_cluster_by_desc(mapping, data_ac, meta_ac, wc, pos, len); if (ret) { mlog_errno(ret); goto out_quota; } if (data_ac) ocfs2_free_alloc_context(data_ac); if (meta_ac) ocfs2_free_alloc_context(meta_ac); success: if (foliop) *foliop = wc->w_target_folio; *fsdata = wc; return 0; out_quota: if (clusters_to_alloc) dquot_free_space(inode, ocfs2_clusters_to_bytes(osb->sb, clusters_to_alloc)); out_commit: ocfs2_commit_trans(osb, handle); out: /* * The mmapped page won't be unlocked in ocfs2_free_write_ctxt(), * even in case of error here like ENOSPC and ENOMEM. So, we need * to unlock the target page manually to prevent deadlocks when * retrying again on ENOSPC, or when returning non-VM_FAULT_LOCKED * to VM code. */ if (wc->w_target_locked) folio_unlock(mmap_folio); ocfs2_free_write_ctxt(inode, wc); if (data_ac) { ocfs2_free_alloc_context(data_ac); data_ac = NULL; } if (meta_ac) { ocfs2_free_alloc_context(meta_ac); meta_ac = NULL; } if (ret == -ENOSPC && try_free) { /* * Try to free some truncate log so that we can have enough * clusters to allocate. */ try_free = 0; ret1 = ocfs2_try_to_free_truncate_log(osb, clusters_need); if (ret1 == 1) goto try_again; if (ret1 < 0) mlog_errno(ret1); } return ret; } static int ocfs2_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { int ret; struct buffer_head *di_bh = NULL; struct inode *inode = mapping->host; ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret) { mlog_errno(ret); return ret; } /* * Take alloc sem here to prevent concurrent lookups. That way * the mapping, zeroing and tree manipulation within * ocfs2_write() will be safe against ->read_folio(). This * should also serve to lock out allocation from a shared * writeable region. */ down_write(&OCFS2_I(inode)->ip_alloc_sem); ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_BUFFER, foliop, fsdata, di_bh, NULL); if (ret) { mlog_errno(ret); goto out_fail; } brelse(di_bh); return 0; out_fail: up_write(&OCFS2_I(inode)->ip_alloc_sem); brelse(di_bh); ocfs2_inode_unlock(inode, 1); return ret; } static void ocfs2_write_end_inline(struct inode *inode, loff_t pos, unsigned len, unsigned *copied, struct ocfs2_dinode *di, struct ocfs2_write_ctxt *wc) { if (unlikely(*copied < len)) { if (!folio_test_uptodate(wc->w_target_folio)) { *copied = 0; return; } } memcpy_from_folio(di->id2.i_data.id_data + pos, wc->w_target_folio, pos, *copied); trace_ocfs2_write_end_inline( (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)pos, *copied, le16_to_cpu(di->id2.i_data.id_count), le16_to_cpu(di->i_dyn_features)); } int ocfs2_write_end_nolock(struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, void *fsdata) { int i, ret; size_t from, to, start = pos & (PAGE_SIZE - 1); struct inode *inode = mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_write_ctxt *wc = fsdata; struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data; handle_t *handle = wc->w_handle; BUG_ON(!list_empty(&wc->w_unwritten_list)); if (handle) { ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { copied = ret; mlog_errno(ret); goto out; } } if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { ocfs2_write_end_inline(inode, pos, len, &copied, di, wc); goto out_write_size; } if (unlikely(copied < len) && wc->w_target_folio) { loff_t new_isize; if (!folio_test_uptodate(wc->w_target_folio)) copied = 0; new_isize = max_t(loff_t, i_size_read(inode), pos + copied); if (new_isize > folio_pos(wc->w_target_folio)) ocfs2_zero_new_buffers(wc->w_target_folio, start+copied, start+len); else { /* * When folio is fully beyond new isize (data copy * failed), do not bother zeroing the folio. Invalidate * it instead so that writeback does not get confused * put page & buffer dirty bits into inconsistent * state. */ block_invalidate_folio(wc->w_target_folio, 0, folio_size(wc->w_target_folio)); } } if (wc->w_target_folio) flush_dcache_folio(wc->w_target_folio); for (i = 0; i < wc->w_num_folios; i++) { struct folio *folio = wc->w_folios[i]; /* This is the direct io target folio */ if (folio == NULL) continue; if (folio == wc->w_target_folio) { from = wc->w_target_from; to = wc->w_target_to; BUG_ON(from > folio_size(folio) || to > folio_size(folio) || to < from); } else { /* * Pages adjacent to the target (if any) imply * a hole-filling write in which case we want * to flush their entire range. */ from = 0; to = folio_size(folio); } if (folio_buffers(folio)) { if (handle && ocfs2_should_order_data(inode)) { loff_t start_byte = folio_pos(folio) + from; loff_t length = to - from; ocfs2_jbd2_inode_add_write(handle, inode, start_byte, length); } block_commit_write(folio, from, to); } } out_write_size: /* Direct io do not update i_size here. */ if (wc->w_type != OCFS2_WRITE_DIRECT) { pos += copied; if (pos > i_size_read(inode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } inode->i_blocks = ocfs2_inode_sector_count(inode); di->i_size = cpu_to_le64((u64)i_size_read(inode)); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); di->i_mtime = di->i_ctime = cpu_to_le64(inode_get_mtime_sec(inode)); di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode)); if (handle) ocfs2_update_inode_fsync_trans(handle, inode, 1); } if (handle) ocfs2_journal_dirty(handle, wc->w_di_bh); out: /* unlock pages before dealloc since it needs acquiring j_trans_barrier * lock, or it will cause a deadlock since journal commit threads holds * this lock and will ask for the page lock when flushing the data. * put it here to preserve the unlock order. */ ocfs2_unlock_folios(wc); if (handle) ocfs2_commit_trans(osb, handle); ocfs2_run_deallocs(osb, &wc->w_dealloc); brelse(wc->w_di_bh); kfree(wc); return copied; } static int ocfs2_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { int ret; struct inode *inode = mapping->host; ret = ocfs2_write_end_nolock(mapping, pos, len, copied, fsdata); up_write(&OCFS2_I(inode)->ip_alloc_sem); ocfs2_inode_unlock(inode, 1); return ret; } struct ocfs2_dio_write_ctxt { struct list_head dw_zero_list; unsigned dw_zero_count; int dw_orphaned; pid_t dw_writer_pid; }; static struct ocfs2_dio_write_ctxt * ocfs2_dio_alloc_write_ctx(struct buffer_head *bh, int *alloc) { struct ocfs2_dio_write_ctxt *dwc = NULL; if (bh->b_private) return bh->b_private; dwc = kmalloc_obj(struct ocfs2_dio_write_ctxt, GFP_NOFS); if (dwc == NULL) return NULL; INIT_LIST_HEAD(&dwc->dw_zero_list); dwc->dw_zero_count = 0; dwc->dw_orphaned = 0; dwc->dw_writer_pid = task_pid_nr(current); bh->b_private = dwc; *alloc = 1; return dwc; } static void ocfs2_dio_free_write_ctx(struct inode *inode, struct ocfs2_dio_write_ctxt *dwc) { ocfs2_free_unwritten_list(inode, &dwc->dw_zero_list); kfree(dwc); } /* * TODO: Make this into a generic get_blocks function. * * From do_direct_io in direct-io.c: * "So what we do is to permit the ->get_blocks function to populate * bh.b_size with the size of IO which is permitted at this offset and * this i_blkbits." * * This function is called directly from get_more_blocks in direct-io.c. * * called like this: dio->get_blocks(dio->inode, fs_startblk, * fs_count, map_bh, dio->rw == WRITE); */ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_write_ctxt *wc; struct ocfs2_write_cluster_desc *desc = NULL; struct ocfs2_dio_write_ctxt *dwc = NULL; struct buffer_head *di_bh = NULL; u64 p_blkno; unsigned int i_blkbits = inode->i_sb->s_blocksize_bits; loff_t pos = iblock << i_blkbits; sector_t endblk = (i_size_read(inode) - 1) >> i_blkbits; unsigned len, total_len = bh_result->b_size; int ret = 0, first_get_block = 0; len = osb->s_clustersize - (pos & (osb->s_clustersize - 1)); len = min(total_len, len); /* * bh_result->b_size is count in get_more_blocks according to write * "pos" and "end", we need map twice to return different buffer state: * 1. area in file size, not set NEW; * 2. area out file size, set NEW. * * iblock endblk * |--------|---------|---------|--------- * |<-------area in file------->| */ if ((iblock <= endblk) && ((iblock + ((len - 1) >> i_blkbits)) > endblk)) len = (endblk - iblock + 1) << i_blkbits; mlog(0, "get block of %llu at %llu:%u req %u\n", inode->i_ino, pos, len, total_len); /* * Because we need to change file size in ocfs2_dio_end_io_write(), or * we may need to add it to orphan dir. So can not fall to fast path * while file size will be changed. */ if (pos + total_len <= i_size_read(inode)) { /* This is the fast path for re-write. */ ret = ocfs2_lock_get_block(inode, iblock, bh_result, create); if (buffer_mapped(bh_result) && !buffer_new(bh_result) && ret == 0) goto out; /* Clear state set by ocfs2_get_block. */ bh_result->b_state = 0; } dwc = ocfs2_dio_alloc_write_ctx(bh_result, &first_get_block); if (unlikely(dwc == NULL)) { ret = -ENOMEM; mlog_errno(ret); goto out; } if (ocfs2_clusters_for_bytes(inode->i_sb, pos + total_len) > ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)) && !dwc->dw_orphaned) { /* * when we are going to alloc extents beyond file size, add the * inode to orphan dir, so we can recall those spaces when * system crashed during write. */ ret = ocfs2_add_inode_to_orphan(osb, inode); if (ret < 0) { mlog_errno(ret); goto out; } dwc->dw_orphaned = 1; } ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret) { mlog_errno(ret); goto out; } down_write(&oi->ip_alloc_sem); if (first_get_block) { if (ocfs2_sparse_alloc(osb)) ret = ocfs2_zero_tail(inode, di_bh, pos); else ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, total_len, NULL); if (ret < 0) { mlog_errno(ret); goto unlock; } } ret = ocfs2_write_begin_nolock(inode->i_mapping, pos, len, OCFS2_WRITE_DIRECT, NULL, (void **)&wc, di_bh, NULL); if (ret) { mlog_errno(ret); goto unlock; } desc = &wc->w_desc[0]; p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, desc->c_phys); BUG_ON(p_blkno == 0); p_blkno += iblock & (u64)(ocfs2_clusters_to_blocks(inode->i_sb, 1) - 1); map_bh(bh_result, inode->i_sb, p_blkno); bh_result->b_size = len; if (desc->c_needs_zero) set_buffer_new(bh_result); if (iblock > endblk) set_buffer_new(bh_result); /* May sleep in end_io. It should not happen in a irq context. So defer * it to dio work queue. */ set_buffer_defer_completion(bh_result); if (!list_empty(&wc->w_unwritten_list)) { struct ocfs2_unwritten_extent *ue = NULL; ue = list_first_entry(&wc->w_unwritten_list, struct ocfs2_unwritten_extent, ue_node); BUG_ON(ue->ue_cpos != desc->c_cpos); /* The physical address may be 0, fill it. */ ue->ue_phys = desc->c_phys; list_splice_tail_init(&wc->w_unwritten_list, &dwc->dw_zero_list); dwc->dw_zero_count += wc->w_unwritten_count; } ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, wc); BUG_ON(ret != len); ret = 0; unlock: up_write(&oi->ip_alloc_sem); ocfs2_inode_unlock(inode, 1); brelse(di_bh); out: return ret; } static int ocfs2_dio_end_io_write(struct inode *inode, struct ocfs2_dio_write_ctxt *dwc, loff_t offset, ssize_t bytes) { struct ocfs2_cached_dealloc_ctxt dealloc; struct ocfs2_extent_tree et; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_unwritten_extent *ue = NULL; struct buffer_head *di_bh = NULL; struct ocfs2_dinode *di; struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_alloc_context *meta_ac = NULL; handle_t *handle = NULL; loff_t end = offset + bytes; int ret = 0, credits = 0, batch = 0; ocfs2_init_dealloc_ctxt(&dealloc); /* We do clear unwritten, delete orphan, change i_size here. If neither * of these happen, we can skip all this. */ if (list_empty(&dwc->dw_zero_list) && end <= i_size_read(inode) && !dwc->dw_orphaned) goto out; ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret < 0) { mlog_errno(ret); goto out; } down_write(&oi->ip_alloc_sem); di = (struct ocfs2_dinode *)di_bh->b_data; ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh); /* Attach dealloc with extent tree in case that we may reuse extents * which are already unlinked from current extent tree due to extent * rotation and merging. */ et.et_dealloc = &dealloc; ret = ocfs2_lock_allocators(inode, &et, 0, dwc->dw_zero_count*2, &data_ac, &meta_ac); if (ret) { mlog_errno(ret); goto unlock; } credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list); list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) { if (!handle) { handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto unlock; } ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto commit; } } ret = ocfs2_assure_trans_credits(handle, credits); if (ret < 0) { mlog_errno(ret); goto commit; } ret = ocfs2_mark_extent_written(inode, &et, handle, ue->ue_cpos, 1, ue->ue_phys, meta_ac, &dealloc); if (ret < 0) { mlog_errno(ret); goto commit; } if (++batch == OCFS2_DIO_MARK_EXTENT_BATCH) { ocfs2_commit_trans(osb, handle); handle = NULL; batch = 0; } } if (end > i_size_read(inode)) { if (!handle) { handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto unlock; } } ret = ocfs2_set_inode_size(handle, inode, di_bh, end); if (ret < 0) mlog_errno(ret); } commit: if (handle) ocfs2_commit_trans(osb, handle); unlock: up_write(&oi->ip_alloc_sem); /* everything looks good, let's start the cleanup */ if (!ret && dwc->dw_orphaned) { BUG_ON(dwc->dw_writer_pid != task_pid_nr(current)); ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0); if (ret < 0) mlog_errno(ret); } ocfs2_inode_unlock(inode, 1); brelse(di_bh); out: if (data_ac) ocfs2_free_alloc_context(data_ac); if (meta_ac) ocfs2_free_alloc_context(meta_ac); ocfs2_run_deallocs(osb, &dealloc); ocfs2_dio_free_write_ctx(inode, dwc); return ret; } /* * ocfs2_dio_end_io is called by the dio core when a dio is finished. We're * particularly interested in the aio/dio case. We use the rw_lock DLM lock * to protect io on one node from truncation on another. */ static int ocfs2_dio_end_io(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private) { struct inode *inode = file_inode(iocb->ki_filp); int level; int ret = 0; /* this io's submitter should not have unlocked this before we could */ BUG_ON(!ocfs2_iocb_is_rw_locked(iocb)); if (bytes <= 0) mlog_ratelimited(ML_ERROR, "Direct IO failed, bytes = %lld", (long long)bytes); if (private) { if (bytes > 0) ret = ocfs2_dio_end_io_write(inode, private, offset, bytes); else ocfs2_dio_free_write_ctx(inode, private); } ocfs2_iocb_clear_rw_locked(iocb); level = ocfs2_iocb_rw_locked_level(iocb); ocfs2_rw_unlock(inode, level); return ret; } static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); get_block_t *get_block; /* * Fallback to buffered I/O if we see an inode without * extents. */ if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) return 0; /* Fallback to buffered I/O if we do not support append dio. */ if (iocb->ki_pos + iter->count > i_size_read(inode) && !ocfs2_supports_append_dio(osb)) return 0; if (iov_iter_rw(iter) == READ) get_block = ocfs2_lock_get_block; else get_block = ocfs2_dio_wr_get_block; return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, ocfs2_dio_end_io, 0); } const struct address_space_operations ocfs2_aops = { .dirty_folio = block_dirty_folio, .read_folio = ocfs2_read_folio, .readahead = ocfs2_readahead, .writepages = ocfs2_writepages, .write_begin = ocfs2_write_begin, .write_end = ocfs2_write_end, .bmap = ocfs2_bmap, .direct_IO = ocfs2_direct_IO, .invalidate_folio = block_invalidate_folio, .release_folio = ocfs2_release_folio, .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_folio = generic_error_remove_folio, }; |
| 6 1 3 1 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org> */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/ipv4/nf_dup_ipv4.h> struct nft_dup_ipv4 { u8 sreg_addr; u8 sreg_dev; }; static void nft_dup_ipv4_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_dup_ipv4 *priv = nft_expr_priv(expr); struct in_addr gw = { .s_addr = (__force __be32)regs->data[priv->sreg_addr], }; int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1; nf_dup_ipv4(nft_net(pkt), pkt->skb, nft_hook(pkt), &gw, oif); } static int nft_dup_ipv4_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_dup_ipv4 *priv = nft_expr_priv(expr); int err; if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, sizeof(struct in_addr)); if (err < 0) return err; if (tb[NFTA_DUP_SREG_DEV]) err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, sizeof(int)); return err; } static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_dup_ipv4 *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr)) goto nla_put_failure; if (priv->sreg_dev && nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static struct nft_expr_type nft_dup_ipv4_type; static const struct nft_expr_ops nft_dup_ipv4_ops = { .type = &nft_dup_ipv4_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_dup_ipv4)), .eval = nft_dup_ipv4_eval, .init = nft_dup_ipv4_init, .dump = nft_dup_ipv4_dump, }; static const struct nla_policy nft_dup_ipv4_policy[NFTA_DUP_MAX + 1] = { [NFTA_DUP_SREG_ADDR] = { .type = NLA_U32 }, [NFTA_DUP_SREG_DEV] = { .type = NLA_U32 }, }; static struct nft_expr_type nft_dup_ipv4_type __read_mostly = { .family = NFPROTO_IPV4, .name = "dup", .ops = &nft_dup_ipv4_ops, .policy = nft_dup_ipv4_policy, .maxattr = NFTA_DUP_MAX, .owner = THIS_MODULE, }; static int __init nft_dup_ipv4_module_init(void) { return nft_register_expr(&nft_dup_ipv4_type); } static void __exit nft_dup_ipv4_module_exit(void) { nft_unregister_expr(&nft_dup_ipv4_type); } module_init(nft_dup_ipv4_module_init); module_exit(nft_dup_ipv4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "dup"); MODULE_DESCRIPTION("IPv4 nftables packet duplication support"); |
| 5 3 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/phy.h> #include <linux/phylib_stubs.h> #include "bitset.h" #include "common.h" #include "netlink.h" struct stats_req_info { struct ethnl_req_info base; DECLARE_BITMAP(stat_mask, __ETHTOOL_STATS_CNT); enum ethtool_mac_stats_src src; }; #define STATS_REQINFO(__req_base) \ container_of(__req_base, struct stats_req_info, base) struct stats_reply_data { struct ethnl_reply_data base; struct_group(stats, struct ethtool_eth_phy_stats phy_stats; struct ethtool_eth_mac_stats mac_stats; struct ethtool_eth_ctrl_stats ctrl_stats; struct ethtool_rmon_stats rmon_stats; struct ethtool_phy_stats phydev_stats; ); const struct ethtool_rmon_hist_range *rmon_ranges; }; #define STATS_REPDATA(__reply_base) \ container_of(__reply_base, struct stats_reply_data, base) const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_STATS_ETH_PHY] = "eth-phy", [ETHTOOL_STATS_ETH_MAC] = "eth-mac", [ETHTOOL_STATS_ETH_CTRL] = "eth-ctrl", [ETHTOOL_STATS_RMON] = "rmon", [ETHTOOL_STATS_PHY] = "phydev", }; const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_ETH_PHY_5_SYM_ERR] = "SymbolErrorDuringCarrier", }; const char stats_eth_mac_names[__ETHTOOL_A_STATS_ETH_MAC_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_ETH_MAC_2_TX_PKT] = "FramesTransmittedOK", [ETHTOOL_A_STATS_ETH_MAC_3_SINGLE_COL] = "SingleCollisionFrames", [ETHTOOL_A_STATS_ETH_MAC_4_MULTI_COL] = "MultipleCollisionFrames", [ETHTOOL_A_STATS_ETH_MAC_5_RX_PKT] = "FramesReceivedOK", [ETHTOOL_A_STATS_ETH_MAC_6_FCS_ERR] = "FrameCheckSequenceErrors", [ETHTOOL_A_STATS_ETH_MAC_7_ALIGN_ERR] = "AlignmentErrors", [ETHTOOL_A_STATS_ETH_MAC_8_TX_BYTES] = "OctetsTransmittedOK", [ETHTOOL_A_STATS_ETH_MAC_9_TX_DEFER] = "FramesWithDeferredXmissions", [ETHTOOL_A_STATS_ETH_MAC_10_LATE_COL] = "LateCollisions", [ETHTOOL_A_STATS_ETH_MAC_11_XS_COL] = "FramesAbortedDueToXSColls", [ETHTOOL_A_STATS_ETH_MAC_12_TX_INT_ERR] = "FramesLostDueToIntMACXmitError", [ETHTOOL_A_STATS_ETH_MAC_13_CS_ERR] = "CarrierSenseErrors", [ETHTOOL_A_STATS_ETH_MAC_14_RX_BYTES] = "OctetsReceivedOK", [ETHTOOL_A_STATS_ETH_MAC_15_RX_INT_ERR] = "FramesLostDueToIntMACRcvError", [ETHTOOL_A_STATS_ETH_MAC_18_TX_MCAST] = "MulticastFramesXmittedOK", [ETHTOOL_A_STATS_ETH_MAC_19_TX_BCAST] = "BroadcastFramesXmittedOK", [ETHTOOL_A_STATS_ETH_MAC_20_XS_DEFER] = "FramesWithExcessiveDeferral", [ETHTOOL_A_STATS_ETH_MAC_21_RX_MCAST] = "MulticastFramesReceivedOK", [ETHTOOL_A_STATS_ETH_MAC_22_RX_BCAST] = "BroadcastFramesReceivedOK", [ETHTOOL_A_STATS_ETH_MAC_23_IR_LEN_ERR] = "InRangeLengthErrors", [ETHTOOL_A_STATS_ETH_MAC_24_OOR_LEN] = "OutOfRangeLengthField", [ETHTOOL_A_STATS_ETH_MAC_25_TOO_LONG_ERR] = "FrameTooLongErrors", }; const char stats_eth_ctrl_names[__ETHTOOL_A_STATS_ETH_CTRL_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_ETH_CTRL_3_TX] = "MACControlFramesTransmitted", [ETHTOOL_A_STATS_ETH_CTRL_4_RX] = "MACControlFramesReceived", [ETHTOOL_A_STATS_ETH_CTRL_5_RX_UNSUP] = "UnsupportedOpcodesReceived", }; const char stats_rmon_names[__ETHTOOL_A_STATS_RMON_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_RMON_UNDERSIZE] = "etherStatsUndersizePkts", [ETHTOOL_A_STATS_RMON_OVERSIZE] = "etherStatsOversizePkts", [ETHTOOL_A_STATS_RMON_FRAG] = "etherStatsFragments", [ETHTOOL_A_STATS_RMON_JABBER] = "etherStatsJabbers", }; const char stats_phy_names[__ETHTOOL_A_STATS_PHY_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_PHY_RX_PKTS] = "RxFrames", [ETHTOOL_A_STATS_PHY_RX_BYTES] = "RxOctets", [ETHTOOL_A_STATS_PHY_RX_ERRORS] = "RxErrors", [ETHTOOL_A_STATS_PHY_TX_PKTS] = "TxFrames", [ETHTOOL_A_STATS_PHY_TX_BYTES] = "TxOctets", [ETHTOOL_A_STATS_PHY_TX_ERRORS] = "TxErrors", }; const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_SRC + 1] = { [ETHTOOL_A_STATS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_STATS_GROUPS] = { .type = NLA_NESTED }, [ETHTOOL_A_STATS_SRC] = NLA_POLICY_MAX(NLA_U32, ETHTOOL_MAC_STATS_SRC_PMAC), }; static int stats_parse_request(struct ethnl_req_info *req_base, const struct genl_info *info, struct nlattr **tb, struct netlink_ext_ack *extack) { enum ethtool_mac_stats_src src = ETHTOOL_MAC_STATS_SRC_AGGREGATE; struct stats_req_info *req_info = STATS_REQINFO(req_base); bool mod = false; int err; err = ethnl_update_bitset(req_info->stat_mask, __ETHTOOL_STATS_CNT, tb[ETHTOOL_A_STATS_GROUPS], stats_std_names, extack, &mod); if (err) return err; if (!mod) { NL_SET_ERR_MSG(extack, "no stats requested"); return -EINVAL; } if (tb[ETHTOOL_A_STATS_SRC]) src = nla_get_u32(tb[ETHTOOL_A_STATS_SRC]); req_info->src = src; return 0; } static int stats_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { const struct stats_req_info *req_info = STATS_REQINFO(req_base); struct stats_reply_data *data = STATS_REPDATA(reply_base); enum ethtool_mac_stats_src src = req_info->src; struct net_device *dev = reply_base->dev; struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret; phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_STATS_HEADER, info->extack); if (IS_ERR(phydev)) return PTR_ERR(phydev); ret = ethnl_ops_begin(dev); if (ret < 0) return ret; if ((src == ETHTOOL_MAC_STATS_SRC_EMAC || src == ETHTOOL_MAC_STATS_SRC_PMAC) && !__ethtool_dev_mm_supported(dev)) { NL_SET_ERR_MSG_MOD(info->extack, "Device does not support MAC merge layer"); ethnl_ops_complete(dev); return -EOPNOTSUPP; } /* Mark all stats as unset (see ETHTOOL_STAT_NOT_SET) to prevent them * from being reported to user space in case driver did not set them. */ memset(&data->stats, 0xff, sizeof(data->stats)); data->phy_stats.src = src; data->mac_stats.src = src; data->ctrl_stats.src = src; data->rmon_stats.src = src; if ((test_bit(ETHTOOL_STATS_PHY, req_info->stat_mask) || test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask)) && src == ETHTOOL_MAC_STATS_SRC_AGGREGATE) { if (phydev) phy_ethtool_get_phy_stats(phydev, &data->phy_stats, &data->phydev_stats); } if (test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask) && dev->ethtool_ops->get_eth_phy_stats) dev->ethtool_ops->get_eth_phy_stats(dev, &data->phy_stats); if (test_bit(ETHTOOL_STATS_ETH_MAC, req_info->stat_mask) && dev->ethtool_ops->get_eth_mac_stats) dev->ethtool_ops->get_eth_mac_stats(dev, &data->mac_stats); if (test_bit(ETHTOOL_STATS_ETH_CTRL, req_info->stat_mask) && dev->ethtool_ops->get_eth_ctrl_stats) dev->ethtool_ops->get_eth_ctrl_stats(dev, &data->ctrl_stats); if (test_bit(ETHTOOL_STATS_RMON, req_info->stat_mask) && dev->ethtool_ops->get_rmon_stats) dev->ethtool_ops->get_rmon_stats(dev, &data->rmon_stats, &data->rmon_ranges); ethnl_ops_complete(dev); return 0; } static int stats_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct stats_req_info *req_info = STATS_REQINFO(req_base); unsigned int n_grps = 0, n_stats = 0; int len = 0; len += nla_total_size(sizeof(u32)); /* _STATS_SRC */ if (test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask)) { n_stats += sizeof(struct ethtool_eth_phy_stats) / sizeof(u64); n_grps++; } if (test_bit(ETHTOOL_STATS_ETH_MAC, req_info->stat_mask)) { n_stats += sizeof(struct ethtool_eth_mac_stats) / sizeof(u64); n_grps++; } if (test_bit(ETHTOOL_STATS_ETH_CTRL, req_info->stat_mask)) { n_stats += sizeof(struct ethtool_eth_ctrl_stats) / sizeof(u64); n_grps++; } if (test_bit(ETHTOOL_STATS_RMON, req_info->stat_mask)) { n_stats += sizeof(struct ethtool_rmon_stats) / sizeof(u64); n_grps++; /* Above includes the space for _A_STATS_GRP_HIST_VALs */ len += (nla_total_size(0) + /* _A_STATS_GRP_HIST */ nla_total_size(4) + /* _A_STATS_GRP_HIST_BKT_LOW */ nla_total_size(4)) * /* _A_STATS_GRP_HIST_BKT_HI */ ETHTOOL_RMON_HIST_MAX * 2; } if (test_bit(ETHTOOL_STATS_PHY, req_info->stat_mask)) { n_stats += sizeof(struct ethtool_phy_stats) / sizeof(u64); n_grps++; } len += n_grps * (nla_total_size(0) + /* _A_STATS_GRP */ nla_total_size(4) + /* _A_STATS_GRP_ID */ nla_total_size(4)); /* _A_STATS_GRP_SS_ID */ len += n_stats * (nla_total_size(0) + /* _A_STATS_GRP_STAT */ nla_total_size_64bit(sizeof(u64))); return len; } static int stat_put(struct sk_buff *skb, u16 attrtype, u64 val) { struct nlattr *nest; int ret; if (val == ETHTOOL_STAT_NOT_SET) return 0; /* We want to start stats attr types from 0, so we don't have a type * for pad inside ETHTOOL_A_STATS_GRP_STAT. Pad things on the outside * of ETHTOOL_A_STATS_GRP_STAT. Since we're one nest away from the * actual attr we're 4B off - nla_need_padding_for_64bit() & co. * can't be used. */ #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS if (!IS_ALIGNED((unsigned long)skb_tail_pointer(skb), 8)) if (!nla_reserve(skb, ETHTOOL_A_STATS_GRP_PAD, 0)) return -EMSGSIZE; #endif nest = nla_nest_start(skb, ETHTOOL_A_STATS_GRP_STAT); if (!nest) return -EMSGSIZE; ret = nla_put_u64_64bit(skb, attrtype, val, -1 /* not used */); if (ret) { nla_nest_cancel(skb, nest); return ret; } nla_nest_end(skb, nest); return 0; } static int stats_put_phy_stats(struct sk_buff *skb, const struct stats_reply_data *data) { if (stat_put(skb, ETHTOOL_A_STATS_ETH_PHY_5_SYM_ERR, data->phy_stats.SymbolErrorDuringCarrier)) return -EMSGSIZE; return 0; } static int stats_put_phydev_stats(struct sk_buff *skb, const struct stats_reply_data *data) { if (stat_put(skb, ETHTOOL_A_STATS_PHY_RX_PKTS, data->phydev_stats.rx_packets) || stat_put(skb, ETHTOOL_A_STATS_PHY_RX_BYTES, data->phydev_stats.rx_bytes) || stat_put(skb, ETHTOOL_A_STATS_PHY_RX_ERRORS, data->phydev_stats.rx_errors) || stat_put(skb, ETHTOOL_A_STATS_PHY_TX_PKTS, data->phydev_stats.tx_packets) || stat_put(skb, ETHTOOL_A_STATS_PHY_TX_BYTES, data->phydev_stats.tx_bytes) || stat_put(skb, ETHTOOL_A_STATS_PHY_TX_ERRORS, data->phydev_stats.tx_errors)) return -EMSGSIZE; return 0; } static int stats_put_mac_stats(struct sk_buff *skb, const struct stats_reply_data *data) { if (stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_2_TX_PKT, data->mac_stats.FramesTransmittedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_3_SINGLE_COL, data->mac_stats.SingleCollisionFrames) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_4_MULTI_COL, data->mac_stats.MultipleCollisionFrames) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_5_RX_PKT, data->mac_stats.FramesReceivedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_6_FCS_ERR, data->mac_stats.FrameCheckSequenceErrors) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_7_ALIGN_ERR, data->mac_stats.AlignmentErrors) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_8_TX_BYTES, data->mac_stats.OctetsTransmittedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_9_TX_DEFER, data->mac_stats.FramesWithDeferredXmissions) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_10_LATE_COL, data->mac_stats.LateCollisions) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_11_XS_COL, data->mac_stats.FramesAbortedDueToXSColls) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_12_TX_INT_ERR, data->mac_stats.FramesLostDueToIntMACXmitError) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_13_CS_ERR, data->mac_stats.CarrierSenseErrors) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_14_RX_BYTES, data->mac_stats.OctetsReceivedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_15_RX_INT_ERR, data->mac_stats.FramesLostDueToIntMACRcvError) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_18_TX_MCAST, data->mac_stats.MulticastFramesXmittedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_19_TX_BCAST, data->mac_stats.BroadcastFramesXmittedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_20_XS_DEFER, data->mac_stats.FramesWithExcessiveDeferral) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_21_RX_MCAST, data->mac_stats.MulticastFramesReceivedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_22_RX_BCAST, data->mac_stats.BroadcastFramesReceivedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_23_IR_LEN_ERR, data->mac_stats.InRangeLengthErrors) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_24_OOR_LEN, data->mac_stats.OutOfRangeLengthField) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_25_TOO_LONG_ERR, data->mac_stats.FrameTooLongErrors)) return -EMSGSIZE; return 0; } static int stats_put_ctrl_stats(struct sk_buff *skb, const struct stats_reply_data *data) { if (stat_put(skb, ETHTOOL_A_STATS_ETH_CTRL_3_TX, data->ctrl_stats.MACControlFramesTransmitted) || stat_put(skb, ETHTOOL_A_STATS_ETH_CTRL_4_RX, data->ctrl_stats.MACControlFramesReceived) || stat_put(skb, ETHTOOL_A_STATS_ETH_CTRL_5_RX_UNSUP, data->ctrl_stats.UnsupportedOpcodesReceived)) return -EMSGSIZE; return 0; } static int stats_put_rmon_hist(struct sk_buff *skb, u32 attr, const u64 *hist, const struct ethtool_rmon_hist_range *ranges) { struct nlattr *nest; int i; if (!ranges) return 0; for (i = 0; i < ETHTOOL_RMON_HIST_MAX; i++) { if (!ranges[i].low && !ranges[i].high) break; if (hist[i] == ETHTOOL_STAT_NOT_SET) continue; nest = nla_nest_start(skb, attr); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_STATS_GRP_HIST_BKT_LOW, ranges[i].low) || nla_put_u32(skb, ETHTOOL_A_STATS_GRP_HIST_BKT_HI, ranges[i].high) || nla_put_u64_64bit(skb, ETHTOOL_A_STATS_GRP_HIST_VAL, hist[i], ETHTOOL_A_STATS_GRP_PAD)) goto err_cancel_hist; nla_nest_end(skb, nest); } return 0; err_cancel_hist: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int stats_put_rmon_stats(struct sk_buff *skb, const struct stats_reply_data *data) { if (stats_put_rmon_hist(skb, ETHTOOL_A_STATS_GRP_HIST_RX, data->rmon_stats.hist, data->rmon_ranges) || stats_put_rmon_hist(skb, ETHTOOL_A_STATS_GRP_HIST_TX, data->rmon_stats.hist_tx, data->rmon_ranges)) return -EMSGSIZE; if (stat_put(skb, ETHTOOL_A_STATS_RMON_UNDERSIZE, data->rmon_stats.undersize_pkts) || stat_put(skb, ETHTOOL_A_STATS_RMON_OVERSIZE, data->rmon_stats.oversize_pkts) || stat_put(skb, ETHTOOL_A_STATS_RMON_FRAG, data->rmon_stats.fragments) || stat_put(skb, ETHTOOL_A_STATS_RMON_JABBER, data->rmon_stats.jabbers)) return -EMSGSIZE; return 0; } static int stats_put_stats(struct sk_buff *skb, const struct stats_reply_data *data, u32 id, u32 ss_id, int (*cb)(struct sk_buff *skb, const struct stats_reply_data *data)) { struct nlattr *nest; nest = nla_nest_start(skb, ETHTOOL_A_STATS_GRP); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_STATS_GRP_ID, id) || nla_put_u32(skb, ETHTOOL_A_STATS_GRP_SS_ID, ss_id)) goto err_cancel; if (cb(skb, data)) goto err_cancel; nla_nest_end(skb, nest); return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int stats_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct stats_req_info *req_info = STATS_REQINFO(req_base); const struct stats_reply_data *data = STATS_REPDATA(reply_base); int ret = 0; if (nla_put_u32(skb, ETHTOOL_A_STATS_SRC, req_info->src)) return -EMSGSIZE; if (!ret && test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_ETH_PHY, ETH_SS_STATS_ETH_PHY, stats_put_phy_stats); if (!ret && test_bit(ETHTOOL_STATS_ETH_MAC, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_ETH_MAC, ETH_SS_STATS_ETH_MAC, stats_put_mac_stats); if (!ret && test_bit(ETHTOOL_STATS_ETH_CTRL, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_ETH_CTRL, ETH_SS_STATS_ETH_CTRL, stats_put_ctrl_stats); if (!ret && test_bit(ETHTOOL_STATS_RMON, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_RMON, ETH_SS_STATS_RMON, stats_put_rmon_stats); if (!ret && test_bit(ETHTOOL_STATS_PHY, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_PHY, ETH_SS_STATS_PHY, stats_put_phydev_stats); return ret; } const struct ethnl_request_ops ethnl_stats_request_ops = { .request_cmd = ETHTOOL_MSG_STATS_GET, .reply_cmd = ETHTOOL_MSG_STATS_GET_REPLY, .hdr_attr = ETHTOOL_A_STATS_HEADER, .req_info_size = sizeof(struct stats_req_info), .reply_data_size = sizeof(struct stats_reply_data), .parse_request = stats_parse_request, .prepare_data = stats_prepare_data, .reply_size = stats_reply_size, .fill_reply = stats_fill_reply, }; static u64 ethtool_stats_sum(u64 a, u64 b) { if (a == ETHTOOL_STAT_NOT_SET) return b; if (b == ETHTOOL_STAT_NOT_SET) return a; return a + b; } /* Avoid modifying the aggregation procedure every time a new counter is added * by treating the structures as an array of u64 statistics. */ static void ethtool_aggregate_stats(void *aggr_stats, const void *emac_stats, const void *pmac_stats, size_t stats_size, size_t stats_offset) { size_t num_stats = stats_size / sizeof(u64); const u64 *s1 = emac_stats + stats_offset; const u64 *s2 = pmac_stats + stats_offset; u64 *s = aggr_stats + stats_offset; int i; for (i = 0; i < num_stats; i++) s[i] = ethtool_stats_sum(s1[i], s2[i]); } void ethtool_aggregate_mac_stats(struct net_device *dev, struct ethtool_eth_mac_stats *mac_stats) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_eth_mac_stats pmac, emac; memset(&emac, 0xff, sizeof(emac)); memset(&pmac, 0xff, sizeof(pmac)); emac.src = ETHTOOL_MAC_STATS_SRC_EMAC; pmac.src = ETHTOOL_MAC_STATS_SRC_PMAC; ops->get_eth_mac_stats(dev, &emac); ops->get_eth_mac_stats(dev, &pmac); ethtool_aggregate_stats(mac_stats, &emac, &pmac, sizeof(mac_stats->stats), offsetof(struct ethtool_eth_mac_stats, stats)); } EXPORT_SYMBOL(ethtool_aggregate_mac_stats); void ethtool_aggregate_phy_stats(struct net_device *dev, struct ethtool_eth_phy_stats *phy_stats) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_eth_phy_stats pmac, emac; memset(&emac, 0xff, sizeof(emac)); memset(&pmac, 0xff, sizeof(pmac)); emac.src = ETHTOOL_MAC_STATS_SRC_EMAC; pmac.src = ETHTOOL_MAC_STATS_SRC_PMAC; ops->get_eth_phy_stats(dev, &emac); ops->get_eth_phy_stats(dev, &pmac); ethtool_aggregate_stats(phy_stats, &emac, &pmac, sizeof(phy_stats->stats), offsetof(struct ethtool_eth_phy_stats, stats)); } EXPORT_SYMBOL(ethtool_aggregate_phy_stats); void ethtool_aggregate_ctrl_stats(struct net_device *dev, struct ethtool_eth_ctrl_stats *ctrl_stats) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_eth_ctrl_stats pmac, emac; memset(&emac, 0xff, sizeof(emac)); memset(&pmac, 0xff, sizeof(pmac)); emac.src = ETHTOOL_MAC_STATS_SRC_EMAC; pmac.src = ETHTOOL_MAC_STATS_SRC_PMAC; ops->get_eth_ctrl_stats(dev, &emac); ops->get_eth_ctrl_stats(dev, &pmac); ethtool_aggregate_stats(ctrl_stats, &emac, &pmac, sizeof(ctrl_stats->stats), offsetof(struct ethtool_eth_ctrl_stats, stats)); } EXPORT_SYMBOL(ethtool_aggregate_ctrl_stats); void ethtool_aggregate_pause_stats(struct net_device *dev, struct ethtool_pause_stats *pause_stats) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_pause_stats pmac, emac; memset(&emac, 0xff, sizeof(emac)); memset(&pmac, 0xff, sizeof(pmac)); emac.src = ETHTOOL_MAC_STATS_SRC_EMAC; pmac.src = ETHTOOL_MAC_STATS_SRC_PMAC; ops->get_pause_stats(dev, &emac); ops->get_pause_stats(dev, &pmac); ethtool_aggregate_stats(pause_stats, &emac, &pmac, sizeof(pause_stats->stats), offsetof(struct ethtool_pause_stats, stats)); } EXPORT_SYMBOL(ethtool_aggregate_pause_stats); void ethtool_aggregate_rmon_stats(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats) { const struct ethtool_ops *ops = dev->ethtool_ops; const struct ethtool_rmon_hist_range *dummy; struct ethtool_rmon_stats pmac, emac; memset(&emac, 0xff, sizeof(emac)); memset(&pmac, 0xff, sizeof(pmac)); emac.src = ETHTOOL_MAC_STATS_SRC_EMAC; pmac.src = ETHTOOL_MAC_STATS_SRC_PMAC; ops->get_rmon_stats(dev, &emac, &dummy); ops->get_rmon_stats(dev, &pmac, &dummy); ethtool_aggregate_stats(rmon_stats, &emac, &pmac, sizeof(rmon_stats->stats), offsetof(struct ethtool_rmon_stats, stats)); } EXPORT_SYMBOL(ethtool_aggregate_rmon_stats); |
| 30 30 30 30 30 30 35 21 21 6 6 6 20 5 20 3 16 2 18 5 34 34 34 1 10 8 21 2 2 2 16 16 16 14 2 7 2 2 31 32 24 1 5 2 2 31 31 32 36 36 9 26 32 31 14 6 2 3 3 8 4 25 25 18 7 20 7 4 4 4 3 20 6 17 7 16 36 28 1 2 1 1 25 22 2 3 19 10 1 1 1 1 2 28 24 24 24 24 6 6 1 3 2 4 1 4 1 3 2 4 1 4 1 6 6 4 2 1 1 66 138 3 2 2 136 4 4 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 virtual tunneling interface * * Copyright (C) 2013 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> * * Based on: * net/ipv6/ip6_tunnel.c */ #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/sockios.h> #include <linux/icmp.h> #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/route.h> #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> #include <linux/slab.h> #include <linux/hash.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <net/icmp.h> #include <net/ip.h> #include <net/ip_tunnels.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/ip6_tunnel.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netdev_lock.h> #include <linux/etherdevice.h> #define IP6_VTI_HASH_SIZE_SHIFT 5 #define IP6_VTI_HASH_SIZE (1 << IP6_VTI_HASH_SIZE_SHIFT) static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) { u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); return hash_32(hash, IP6_VTI_HASH_SIZE_SHIFT); } static int vti6_dev_init(struct net_device *dev); static void vti6_dev_setup(struct net_device *dev); static struct rtnl_link_ops vti6_link_ops __read_mostly; static unsigned int vti6_net_id __read_mostly; struct vti6_net { /* the vti6 tunnel fallback device */ struct net_device *fb_tnl_dev; /* lists for storing tunnels in use */ struct ip6_tnl __rcu *tnls_r_l[IP6_VTI_HASH_SIZE]; struct ip6_tnl __rcu *tnls_wc[1]; struct ip6_tnl __rcu **tnls[2]; }; #define for_each_vti6_tunnel_rcu(start) \ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) /** * vti6_tnl_lookup - fetch tunnel matching the end-point addresses * @net: network namespace * @remote: the address of the tunnel exit-point * @local: the address of the tunnel entry-point * * Return: * tunnel matching given end-points if found, * else fallback tunnel if its device is up, * else %NULL **/ static struct ip6_tnl * vti6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local) { unsigned int hash = HASH(remote, local); struct ip6_tnl *t; struct vti6_net *ip6n = net_generic(net, vti6_net_id); struct in6_addr any; for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) return t; } memset(&any, 0, sizeof(any)); hash = HASH(&any, local); for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(local, &t->parms.laddr) && (t->dev->flags & IFF_UP)) return t; } hash = HASH(remote, &any); for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) return t; } t = rcu_dereference(ip6n->tnls_wc[0]); if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } /** * vti6_tnl_bucket - get head of list matching given tunnel parameters * @ip6n: the private data for ip6_vti in the netns * @p: parameters containing tunnel end-points * * Description: * vti6_tnl_bucket() returns the head of the list matching the * &struct in6_addr entries laddr and raddr in @p. * * Return: head of IPv6 tunnel list **/ static struct ip6_tnl __rcu ** vti6_tnl_bucket(struct vti6_net *ip6n, const struct __ip6_tnl_parm *p) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; unsigned int h = 0; int prio = 0; if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { prio = 1; h = HASH(remote, local); } return &ip6n->tnls[prio][h]; } static void vti6_tnl_link(struct vti6_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp = vti6_tnl_bucket(ip6n, &t->parms); rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } static void vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp; struct ip6_tnl *iter; for (tp = vti6_tnl_bucket(ip6n, &t->parms); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { rcu_assign_pointer(*tp, t->next); break; } } } static int vti6_tnl_create2(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct vti6_net *ip6n = net_generic(t->net, vti6_net_id); int err; dev->rtnl_link_ops = &vti6_link_ops; err = register_netdevice(dev); if (err < 0) goto out; strcpy(t->parms.name, dev->name); vti6_tnl_link(ip6n, t); return 0; out: return err; } static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) { struct net_device *dev; struct ip6_tnl *t; char name[IFNAMSIZ]; int err; if (p->name[0]) { if (!dev_valid_name(p->name)) goto failed; strscpy(name, p->name, IFNAMSIZ); } else { sprintf(name, "ip6_vti%%d"); } dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup); if (!dev) goto failed; dev_net_set(dev, net); t = netdev_priv(dev); t->parms = *p; t->net = dev_net(dev); err = vti6_tnl_create2(dev); if (err < 0) goto failed_free; return t; failed_free: free_netdev(dev); failed: return NULL; } /** * vti6_locate - find or create tunnel matching given parameters * @net: network namespace * @p: tunnel parameters * @create: != 0 if allowed to create new tunnel if no match found * * Description: * vti6_locate() first tries to locate an existing tunnel * based on @parms. If this is unsuccessful, but @create is set a new * tunnel device is created and registered for use. * * Return: * matching tunnel or NULL **/ static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p, int create) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; struct ip6_tnl __rcu **tp; struct ip6_tnl *t; struct vti6_net *ip6n = net_generic(net, vti6_net_id); for (tp = vti6_tnl_bucket(ip6n, p); (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr)) { if (create) return NULL; return t; } } if (!create) return NULL; return vti6_tnl_create(net, p); } /** * vti6_dev_uninit - tunnel device uninitializer * @dev: the device to be destroyed * * Description: * vti6_dev_uninit() removes tunnel from its list **/ static void vti6_dev_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct vti6_net *ip6n = net_generic(t->net, vti6_net_id); if (dev == ip6n->fb_tnl_dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else vti6_tnl_unlink(ip6n, t); netdev_put(dev, &t->dev_tracker); } static int vti6_input_proto(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { struct ip6_tnl *t; const struct ipv6hdr *ipv6h = ipv6_hdr(skb); rcu_read_lock(); t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr); if (t) { if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) { rcu_read_unlock(); goto discard; } if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { rcu_read_unlock(); goto discard; } ipv6h = ipv6_hdr(skb); if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { DEV_STATS_INC(t->dev, rx_dropped); rcu_read_unlock(); goto discard; } rcu_read_unlock(); XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t; XFRM_SPI_SKB_CB(skb)->family = AF_INET6; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); return xfrm_input(skb, nexthdr, spi, encap_type); } rcu_read_unlock(); return -EINVAL; discard: kfree_skb(skb); return 0; } static int vti6_rcv(struct sk_buff *skb) { int nexthdr = skb_network_header(skb)[IP6CB(skb)->nhoff]; return vti6_input_proto(skb, nexthdr, 0, 0); } static int vti6_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; struct net_device *dev; struct xfrm_state *x; const struct xfrm_mode *inner_mode; struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6; u32 orig_mark = skb->mark; int ret; if (!t) return 1; dev = t->dev; if (err) { DEV_STATS_INC(dev, rx_errors); DEV_STATS_INC(dev, rx_dropped); return 0; } x = xfrm_input_state(skb); inner_mode = &x->inner_mode; if (x->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); if (inner_mode == NULL) { XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINSTATEMODEERROR); return -EINVAL; } } family = inner_mode->family; skb->mark = be32_to_cpu(t->parms.i_key); ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); skb->mark = orig_mark; if (!ret) return -EPERM; skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev))); skb->dev = dev; dev_sw_netstats_rx_add(dev, skb->len); return 0; } /** * vti6_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device * @hdr: IPv6 header from the incoming packet * * Description: * Avoid trivial tunneling loop by checking that tunnel exit-point * doesn't match source of incoming packet. * * Return: * 1 if conflict, * 0 else **/ static inline bool vti6_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) { return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } static bool vti6_state_check(const struct xfrm_state *x, const struct in6_addr *dst, const struct in6_addr *src) { xfrm_address_t *daddr = (xfrm_address_t *)dst; xfrm_address_t *saddr = (xfrm_address_t *)src; /* if there is no transform then this tunnel is not functional. * Or if the xfrm is not mode tunnel. */ if (!x || x->props.mode != XFRM_MODE_TUNNEL || x->props.family != AF_INET6) return false; if (ipv6_addr_any(dst)) return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET6); if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET6)) return false; return true; } /** * vti6_xmit - send a packet * @skb: the outgoing socket buffer * @dev: the outgoing tunnel device * @fl: the flow informations for the xfrm_lookup **/ static int vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct ip6_tnl *t = netdev_priv(dev); struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; struct xfrm_state *x; int pkt_len = skb->len; int err = -1; int mtu; if (!dst) { switch (skb->protocol) { case htons(ETH_P_IP): { struct rtable *rt; fl->u.ip4.flowi4_oif = dev->ifindex; fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); if (IS_ERR(rt)) goto tx_err_link_failure; dst = &rt->dst; skb_dst_set(skb, dst); break; } case htons(ETH_P_IPV6): fl->u.ip6.flowi6_oif = dev->ifindex; fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6); if (dst->error) { dst_release(dst); dst = NULL; goto tx_err_link_failure; } skb_dst_set(skb, dst); break; default: goto tx_err_link_failure; } } dst_hold(dst); dst = xfrm_lookup_route(t->net, dst, fl, NULL, 0); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto tx_err_link_failure; } if (dst->flags & DST_XFRM_QUEUE) goto xmit; x = dst->xfrm; if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr)) goto tx_err_link_failure; if (!ip6_tnl_xmit_ctl(t, (const struct in6_addr *)&x->props.saddr, (const struct in6_addr *)&x->id.daddr)) goto tx_err_link_failure; tdev = dst_dev(dst); if (tdev == dev) { DEV_STATS_INC(dev, collisions); net_warn_ratelimited("%s: Local routing loop detected!\n", t->parms.name); goto tx_err_dst_release; } mtu = dst_mtu(dst); if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } else { if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) goto xmit; icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } err = -EMSGSIZE; goto tx_err_dst_release; } xmit: skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = dst_dev(dst); err = dst_output(t->net, skb->sk, skb); if (net_xmit_eval(err) == 0) err = pkt_len; iptunnel_xmit_stats(dev, err); return 0; tx_err_link_failure: DEV_STATS_INC(dev, tx_carrier_errors); dst_link_failure(skb); tx_err_dst_release: dst_release(dst); return err; } static netdev_tx_t vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct flowi fl; int ret; if (!pskb_inet_may_pull(skb)) goto tx_err; memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { case htons(ETH_P_IPV6): if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) || vti6_addr_conflict(t, ipv6_hdr(skb))) goto tx_err; memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET6); break; case htons(ETH_P_IP): memset(IPCB(skb), 0, sizeof(*IPCB(skb))); xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET); break; default: goto tx_err; } /* override mark with tunnel output key */ fl.flowi_mark = be32_to_cpu(t->parms.o_key); ret = vti6_xmit(skb, dev, &fl); if (ret < 0) goto tx_err; return NETDEV_TX_OK; tx_err: DEV_STATS_INC(dev, tx_errors); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __be32 spi; __u32 mark; struct xfrm_state *x; struct ip6_tnl *t; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah; struct ip_comp_hdr *ipch; struct net *net = dev_net(skb->dev); const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; int protocol = iph->nexthdr; t = vti6_tnl_lookup(dev_net(skb->dev), &iph->daddr, &iph->saddr); if (!t) return -1; mark = be32_to_cpu(t->parms.o_key); switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data + offset); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data + offset); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data + offset); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return 0; x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET6); if (!x) return 0; if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); else ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); xfrm_state_put(x); return 0; } static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu) { struct net_device *dev = t->dev; struct __ip6_tnl_parm *p = &t->parms; struct net_device *tdev = NULL; int mtu; __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); p->flags &= ~(IP6_TNL_F_CAP_XMIT | IP6_TNL_F_CAP_RCV | IP6_TNL_F_CAP_PER_PACKET); p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); if (p->flags & IP6_TNL_F_CAP_XMIT && p->flags & IP6_TNL_F_CAP_RCV) dev->flags |= IFF_POINTOPOINT; else dev->flags &= ~IFF_POINTOPOINT; if (keep_mtu && dev->mtu) { WRITE_ONCE(dev->mtu, clamp(dev->mtu, dev->min_mtu, dev->max_mtu)); return; } if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, p->link, NULL, strict); if (rt) tdev = rt->dst.dev; ip6_rt_put(rt); } if (!tdev && p->link) tdev = __dev_get_by_index(t->net, p->link); if (tdev) mtu = tdev->mtu - sizeof(struct ipv6hdr); else mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr); dev->mtu = max_t(int, mtu, IPV4_MIN_MTU); } /** * vti6_tnl_change - update the tunnel parameters * @t: tunnel to be changed * @p: tunnel configuration parameters * @keep_mtu: MTU was set from userspace, don't re-compute it * * Description: * vti6_tnl_change() updates the tunnel parameters **/ static int vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p, bool keep_mtu) { t->parms.laddr = p->laddr; t->parms.raddr = p->raddr; t->parms.link = p->link; t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; t->parms.proto = p->proto; t->parms.fwmark = p->fwmark; dst_cache_reset(&t->dst_cache); vti6_link_config(t, keep_mtu); return 0; } static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p, bool keep_mtu) { struct net *net = dev_net(t->dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); int err; vti6_tnl_unlink(ip6n, t); synchronize_net(); err = vti6_tnl_change(t, p, keep_mtu); vti6_tnl_link(ip6n, t); netdev_state_change(t->dev); return err; } static void vti6_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm2 *u) { p->laddr = u->laddr; p->raddr = u->raddr; p->link = u->link; p->i_key = u->i_key; p->o_key = u->o_key; p->proto = u->proto; memcpy(p->name, u->name, sizeof(u->name)); } static void vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p) { u->laddr = p->laddr; u->raddr = p->raddr; u->link = p->link; u->i_key = p->i_key; u->o_key = p->o_key; if (u->i_key) u->i_flags |= GRE_KEY; if (u->o_key) u->o_flags |= GRE_KEY; u->proto = p->proto; memcpy(u->name, p->name, sizeof(u->name)); } /** * vti6_siocdevprivate - configure vti6 tunnels from userspace * @dev: virtual device associated with tunnel * @ifr: unused * @data: parameters passed from userspace * @cmd: command to be performed * * Description: * vti6_siocdevprivate() is used for managing vti6 tunnels * from userspace. * * The possible commands are the following: * %SIOCGETTUNNEL: get tunnel parameters for device * %SIOCADDTUNNEL: add tunnel matching given tunnel parameters * %SIOCCHGTUNNEL: change tunnel parameters to those given * %SIOCDELTUNNEL: delete tunnel * * The fallback device "ip6_vti0", created during module * initialization, can be used for creating other tunnel devices. * * Return: * 0 on success, * %-EFAULT if unable to copy data to or from userspace, * %-EPERM if current process hasn't %CAP_NET_ADMIN set * %-EINVAL if passed tunnel parameters are invalid, * %-EEXIST if changing a tunnel's parameters would cause a conflict * %-ENODEV if attempting to change or delete a nonexisting device **/ static int vti6_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { int err = 0; struct ip6_tnl_parm2 p; struct __ip6_tnl_parm p1; struct ip6_tnl *t = NULL; struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); memset(&p1, 0, sizeof(p1)); switch (cmd) { case SIOCGETTUNNEL: if (dev == ip6n->fb_tnl_dev) { if (copy_from_user(&p, data, sizeof(p))) { err = -EFAULT; break; } vti6_parm_from_user(&p1, &p); t = vti6_locate(net, &p1, 0); } else { memset(&p, 0, sizeof(p)); } if (!t) t = netdev_priv(dev); vti6_parm_to_user(&p, &t->parms); if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = -EFAULT; if (copy_from_user(&p, data, sizeof(p))) break; err = -EINVAL; if (p.proto != IPPROTO_IPV6 && p.proto != 0) break; vti6_parm_from_user(&p1, &p); t = vti6_locate(net, &p1, cmd == SIOCADDTUNNEL); if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) { if (t) { if (t->dev != dev) { err = -EEXIST; break; } } else t = netdev_priv(dev); err = vti6_update(t, &p1, false); } if (t) { err = 0; vti6_parm_to_user(&p, &t->parms); if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; } else err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); break; case SIOCDELTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (dev == ip6n->fb_tnl_dev) { err = -EFAULT; if (copy_from_user(&p, data, sizeof(p))) break; err = -ENOENT; vti6_parm_from_user(&p1, &p); t = vti6_locate(net, &p1, 0); if (!t) break; err = -EPERM; if (t->dev == ip6n->fb_tnl_dev) break; dev = t->dev; } err = 0; unregister_netdevice(dev); break; default: err = -EINVAL; } return err; } static const struct net_device_ops vti6_netdev_ops = { .ndo_init = vti6_dev_init, .ndo_uninit = vti6_dev_uninit, .ndo_start_xmit = vti6_tnl_xmit, .ndo_siocdevprivate = vti6_siocdevprivate, .ndo_get_iflink = ip6_tnl_get_iflink, }; /** * vti6_dev_setup - setup virtual tunnel device * @dev: virtual device associated with tunnel * * Description: * Initialize function pointers and device parameters **/ static void vti6_dev_setup(struct net_device *dev) { dev->netdev_ops = &vti6_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->type = ARPHRD_TUNNEL6; dev->min_mtu = IPV4_MIN_MTU; dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr); dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); netif_keep_dst(dev); /* This perm addr will be used as interface identifier by IPv6 */ dev->addr_assign_type = NET_ADDR_RANDOM; eth_random_addr(dev->perm_addr); } /** * vti6_dev_init_gen - general initializer for all tunnel devices * @dev: virtual device associated with tunnel **/ static inline int vti6_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); t->dev = dev; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); return 0; } /** * vti6_dev_init - initializer for all non fallback tunnel devices * @dev: virtual device associated with tunnel **/ static int vti6_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int err = vti6_dev_init_gen(dev); if (err) return err; vti6_link_config(t, true); return 0; } /** * vti6_fb_tnl_dev_init - initializer for fallback tunnel device * @dev: fallback device * * Return: 0 **/ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); t->net = net; t->parms.proto = IPPROTO_IPV6; rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } static int vti6_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { return 0; } static void vti6_netlink_parms(struct nlattr *data[], struct __ip6_tnl_parm *parms) { memset(parms, 0, sizeof(*parms)); if (!data) return; if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); if (data[IFLA_VTI_LOCAL]) parms->laddr = nla_get_in6_addr(data[IFLA_VTI_LOCAL]); if (data[IFLA_VTI_REMOTE]) parms->raddr = nla_get_in6_addr(data[IFLA_VTI_REMOTE]); if (data[IFLA_VTI_IKEY]) parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]); if (data[IFLA_VTI_OKEY]) parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]); if (data[IFLA_VTI_FWMARK]) parms->fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]); } static int vti6_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct nlattr **data = params->data; struct ip6_tnl *nt; struct net *net; net = params->link_net ? : dev_net(dev); nt = netdev_priv(dev); vti6_netlink_parms(data, &nt->parms); nt->parms.proto = IPPROTO_IPV6; nt->net = net; if (vti6_locate(net, &nt->parms, 0)) return -EEXIST; return vti6_tnl_create2(dev); } static void vti6_dellink(struct net_device *dev, struct list_head *head) { struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); if (dev != ip6n->fb_tnl_dev) unregister_netdevice_queue(dev, head); } static int vti6_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip6_tnl *t; struct __ip6_tnl_parm p; struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); if (dev == ip6n->fb_tnl_dev) return -EINVAL; vti6_netlink_parms(data, &p); t = vti6_locate(net, &p, 0); if (t) { if (t->dev != dev) return -EEXIST; } else t = netdev_priv(dev); return vti6_update(t, &p, tb && tb[IFLA_MTU]); } static size_t vti6_get_size(const struct net_device *dev) { return /* IFLA_VTI_LINK */ nla_total_size(4) + /* IFLA_VTI_LOCAL */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VTI_REMOTE */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VTI_IKEY */ nla_total_size(4) + /* IFLA_VTI_OKEY */ nla_total_size(4) + /* IFLA_VTI_FWMARK */ nla_total_size(4) + 0; } static int vti6_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); struct __ip6_tnl_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_VTI_LINK, parm->link) || nla_put_in6_addr(skb, IFLA_VTI_LOCAL, &parm->laddr) || nla_put_in6_addr(skb, IFLA_VTI_REMOTE, &parm->raddr) || nla_put_be32(skb, IFLA_VTI_IKEY, parm->i_key) || nla_put_be32(skb, IFLA_VTI_OKEY, parm->o_key) || nla_put_u32(skb, IFLA_VTI_FWMARK, parm->fwmark)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy vti6_policy[IFLA_VTI_MAX + 1] = { [IFLA_VTI_LINK] = { .type = NLA_U32 }, [IFLA_VTI_LOCAL] = { .len = sizeof(struct in6_addr) }, [IFLA_VTI_REMOTE] = { .len = sizeof(struct in6_addr) }, [IFLA_VTI_IKEY] = { .type = NLA_U32 }, [IFLA_VTI_OKEY] = { .type = NLA_U32 }, [IFLA_VTI_FWMARK] = { .type = NLA_U32 }, }; static struct rtnl_link_ops vti6_link_ops __read_mostly = { .kind = "vti6", .maxtype = IFLA_VTI_MAX, .policy = vti6_policy, .priv_size = sizeof(struct ip6_tnl), .setup = vti6_dev_setup, .validate = vti6_validate, .newlink = vti6_newlink, .dellink = vti6_dellink, .changelink = vti6_changelink, .get_size = vti6_get_size, .fill_info = vti6_fill_info, .get_link_net = ip6_tnl_get_link_net, }; static void __net_exit vti6_exit_rtnl_net(struct net *net, struct list_head *list) { struct vti6_net *ip6n = net_generic(net, vti6_net_id); struct ip6_tnl *t; int h; for (h = 0; h < IP6_VTI_HASH_SIZE; h++) { t = rtnl_net_dereference(net, ip6n->tnls_r_l[h]); while (t) { unregister_netdevice_queue(t->dev, list); t = rtnl_net_dereference(net, t->next); } } t = rtnl_net_dereference(net, ip6n->tnls_wc[0]); if (t) unregister_netdevice_queue(t->dev, list); } static int __net_init vti6_init_net(struct net *net) { struct vti6_net *ip6n = net_generic(net, vti6_net_id); struct ip6_tnl *t = NULL; int err; ip6n->tnls[0] = ip6n->tnls_wc; ip6n->tnls[1] = ip6n->tnls_r_l; if (!net_has_fallback_tunnels(net)) return 0; err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6_vti0", NET_NAME_UNKNOWN, vti6_dev_setup); if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); ip6n->fb_tnl_dev->rtnl_link_ops = &vti6_link_ops; err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) goto err_register; err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; t = netdev_priv(ip6n->fb_tnl_dev); strcpy(t->parms.name, ip6n->fb_tnl_dev->name); return 0; err_register: free_netdev(ip6n->fb_tnl_dev); err_alloc_dev: return err; } static struct pernet_operations vti6_net_ops = { .init = vti6_init_net, .exit_rtnl = vti6_exit_rtnl_net, .id = &vti6_net_id, .size = sizeof(struct vti6_net), }; static struct xfrm6_protocol vti_esp6_protocol __read_mostly = { .handler = vti6_rcv, .input_handler = vti6_input_proto, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 100, }; static struct xfrm6_protocol vti_ah6_protocol __read_mostly = { .handler = vti6_rcv, .input_handler = vti6_input_proto, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 100, }; static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = { .handler = vti6_rcv, .input_handler = vti6_input_proto, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 100, }; #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) static int vti6_rcv_tunnel(struct sk_buff *skb) { const xfrm_address_t *saddr; __be32 spi; saddr = (const xfrm_address_t *)&ipv6_hdr(skb)->saddr; spi = xfrm6_tunnel_spi_lookup(dev_net(skb->dev), saddr); return vti6_input_proto(skb, IPPROTO_IPV6, spi, 0); } static struct xfrm6_tunnel vti_ipv6_handler __read_mostly = { .handler = vti6_rcv_tunnel, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 0, }; static struct xfrm6_tunnel vti_ip6ip_handler __read_mostly = { .handler = vti6_rcv_tunnel, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 0, }; #endif /** * vti6_tunnel_init - register protocol and reserve needed resources * * Return: 0 on success **/ static int __init vti6_tunnel_init(void) { const char *msg; int err; msg = "tunnel device"; err = register_pernet_device(&vti6_net_ops); if (err < 0) goto pernet_dev_failed; msg = "tunnel protocols"; err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP); if (err < 0) goto xfrm_proto_esp_failed; err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH); if (err < 0) goto xfrm_proto_ah_failed; err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) msg = "ipv6 tunnel"; err = xfrm6_tunnel_register(&vti_ipv6_handler, AF_INET6); if (err < 0) goto vti_tunnel_ipv6_failed; err = xfrm6_tunnel_register(&vti_ip6ip_handler, AF_INET); if (err < 0) goto vti_tunnel_ip6ip_failed; #endif msg = "netlink interface"; err = rtnl_link_register(&vti6_link_ops); if (err < 0) goto rtnl_link_failed; return 0; rtnl_link_failed: #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) err = xfrm6_tunnel_deregister(&vti_ip6ip_handler, AF_INET); vti_tunnel_ip6ip_failed: err = xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET6); vti_tunnel_ipv6_failed: #endif xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); xfrm_proto_comp_failed: xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); xfrm_proto_ah_failed: xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); xfrm_proto_esp_failed: unregister_pernet_device(&vti6_net_ops); pernet_dev_failed: pr_err("vti6 init: failed to register %s\n", msg); return err; } /** * vti6_tunnel_cleanup - free resources and unregister protocol **/ static void __exit vti6_tunnel_cleanup(void) { rtnl_link_unregister(&vti6_link_ops); #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) xfrm6_tunnel_deregister(&vti_ip6ip_handler, AF_INET); xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET6); #endif xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); unregister_pernet_device(&vti6_net_ops); } module_init(vti6_tunnel_init); module_exit(vti6_tunnel_cleanup); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("vti6"); MODULE_ALIAS_NETDEV("ip6_vti0"); MODULE_AUTHOR("Steffen Klassert"); MODULE_DESCRIPTION("IPv6 virtual tunnel interface"); |
| 98 99 99 60 61 61 1 1 27193 27291 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic Timer-queue * * Manages a simple queue of timers, ordered by expiration time. * Uses rbtrees for quick list adds and expiration. * * NOTE: All of the following functions need to be serialized * to avoid races. No locking is done by this library code. */ #include <linux/bug.h> #include <linux/timerqueue.h> #include <linux/rbtree.h> #include <linux/export.h> #define __node_2_tq(_n) \ rb_entry((_n), struct timerqueue_node, node) static inline bool __timerqueue_less(struct rb_node *a, const struct rb_node *b) { return __node_2_tq(a)->expires < __node_2_tq(b)->expires; } /** * timerqueue_add - Adds timer to timerqueue. * * @head: head of timerqueue * @node: timer node to be added * * Adds the timer node to the timerqueue, sorted by the node's expires * value. Returns true if the newly added timer is the first expiring timer in * the queue. */ bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node) { /* Make sure we don't add nodes that are already added */ WARN_ON_ONCE(!RB_EMPTY_NODE(&node->node)); return rb_add_cached(&node->node, &head->rb_root, __timerqueue_less); } EXPORT_SYMBOL_GPL(timerqueue_add); /** * timerqueue_del - Removes a timer from the timerqueue. * * @head: head of timerqueue * @node: timer node to be removed * * Removes the timer node from the timerqueue. Returns true if the queue is * not empty after the remove. */ bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node) { WARN_ON_ONCE(RB_EMPTY_NODE(&node->node)); rb_erase_cached(&node->node, &head->rb_root); RB_CLEAR_NODE(&node->node); return !RB_EMPTY_ROOT(&head->rb_root.rb_root); } EXPORT_SYMBOL_GPL(timerqueue_del); /** * timerqueue_iterate_next - Returns the timer after the provided timer * * @node: Pointer to a timer. * * Provides the timer that is after the given node. This is used, when * necessary, to iterate through the list of timers in a timer list * without modifying the list. */ struct timerqueue_node *timerqueue_iterate_next(struct timerqueue_node *node) { struct rb_node *next; if (!node) return NULL; next = rb_next(&node->node); if (!next) return NULL; return container_of(next, struct timerqueue_node, node); } EXPORT_SYMBOL_GPL(timerqueue_iterate_next); #define __node_2_tq_linked(_n) \ container_of(rb_entry((_n), struct rb_node_linked, node), struct timerqueue_linked_node, node) static __always_inline bool __tq_linked_less(struct rb_node *a, const struct rb_node *b) { return __node_2_tq_linked(a)->expires < __node_2_tq_linked(b)->expires; } bool timerqueue_linked_add(struct timerqueue_linked_head *head, struct timerqueue_linked_node *node) { return rb_add_linked(&node->node, &head->rb_root, __tq_linked_less); } EXPORT_SYMBOL_GPL(timerqueue_linked_add); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * sysctl.h: General linux system control interface * * Begun 24 March 1995, Stephen Tweedie * **************************************************************** **************************************************************** ** ** WARNING: ** The values in this file are exported to user space via ** the sysctl() binary interface. Do *NOT* change the ** numbering of any existing values here, and do not change ** any numbers within any one set of values. If you have to ** redefine an existing interface, use a new number for it. ** The kernel will then return -ENOTDIR to any application using ** the old binary interface. ** **************************************************************** **************************************************************** */ #ifndef _LINUX_SYSCTL_H #define _LINUX_SYSCTL_H #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/wait.h> #include <linux/rbtree.h> #include <linux/uidgid.h> #include <uapi/linux/sysctl.h> /* For the /proc/sys support */ struct completion; struct ctl_table; struct nsproxy; struct ctl_table_root; struct ctl_table_header; struct ctl_dir; /* Keep the same order as in fs/proc/proc_sysctl.c */ #define SYSCTL_ZERO ((void *)&sysctl_vals[0]) #define SYSCTL_ONE ((void *)&sysctl_vals[1]) #define SYSCTL_TWO ((void *)&sysctl_vals[2]) #define SYSCTL_THREE ((void *)&sysctl_vals[3]) #define SYSCTL_FOUR ((void *)&sysctl_vals[4]) #define SYSCTL_ONE_HUNDRED ((void *)&sysctl_vals[5]) #define SYSCTL_TWO_HUNDRED ((void *)&sysctl_vals[6]) #define SYSCTL_ONE_THOUSAND ((void *)&sysctl_vals[7]) #define SYSCTL_THREE_THOUSAND ((void *)&sysctl_vals[8]) #define SYSCTL_INT_MAX ((void *)&sysctl_vals[9]) /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ #define SYSCTL_MAXOLDUID ((void *)&sysctl_vals[10]) #define SYSCTL_NEG_ONE ((void *)&sysctl_vals[11]) extern const int sysctl_vals[]; #define SYSCTL_LONG_ZERO ((void *)&sysctl_long_vals[0]) #define SYSCTL_LONG_ONE ((void *)&sysctl_long_vals[1]) #define SYSCTL_LONG_MAX ((void *)&sysctl_long_vals[2]) /** * * "dir" originates from read_iter (dir = 0) or write_iter (dir = 1) * in the file_operations struct at proc/proc_sysctl.c. Its value means * one of two things for sysctl: * 1. SYSCTL_USER_TO_KERN(dir) Writing to an internal kernel variable from user * space (dir > 0) * 2. SYSCTL_KERN_TO_USER(dir) Writing to a user space buffer from a kernel * variable (dir == 0). */ #define SYSCTL_USER_TO_KERN(dir) (!!(dir)) #define SYSCTL_KERN_TO_USER(dir) (!dir) extern const unsigned long sysctl_long_vals[]; typedef int proc_handler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_dostring(const struct ctl_table *, int, void *, size_t *, loff_t *); int proc_dobool(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_dointvec(const struct ctl_table *, int, void *, size_t *, loff_t *); int proc_dointvec_minmax(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos); int proc_dointvec_conv(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos, int (*conv)(bool *negp, unsigned long *u_ptr, int *k_ptr, int dir, const struct ctl_table *table)); int proc_int_k2u_conv_kop(ulong *u_ptr, const int *k_ptr, bool *negp, ulong (*k_ptr_op)(const ulong)); int proc_int_u2k_conv_uop(const ulong *u_ptr, int *k_ptr, const bool *negp, ulong (*u_ptr_op)(const ulong)); int proc_int_conv(bool *negp, ulong *u_ptr, int *k_ptr, int dir, const struct ctl_table *tbl, bool k_ptr_range_check, int (*user_to_kern)(const bool *negp, const ulong *u_ptr, int *k_ptr), int (*kern_to_user)(bool *negp, ulong *u_ptr, const int *k_ptr)); int proc_douintvec(const struct ctl_table *, int, void *, size_t *, loff_t *); int proc_douintvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_douintvec_conv(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos, int (*conv)(unsigned long *lvalp, unsigned int *valp, int write, const struct ctl_table *table)); int proc_uint_k2u_conv(ulong *u_ptr, const uint *k_ptr); int proc_uint_u2k_conv_uop(const ulong *u_ptr, uint *k_ptr, ulong (*u_ptr_op)(const ulong)); int proc_uint_conv(ulong *u_ptr, uint *k_ptr, int dir, const struct ctl_table *tbl, bool k_ptr_range_check, int (*user_to_kern)(const ulong *u_ptr, uint *k_ptr), int (*kern_to_user)(ulong *u_ptr, const uint *k_ptr)); int proc_dou8vec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_doulongvec_minmax(const struct ctl_table *, int, void *, size_t *, loff_t *); int proc_doulongvec_minmax_conv(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos, unsigned long convmul, unsigned long convdiv); int proc_do_large_bitmap(const struct ctl_table *, int, void *, size_t *, loff_t *); int proc_do_static_key(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* * Register a set of sysctl names by calling register_sysctl * with an initialised array of struct ctl_table's. * * sysctl names can be mirrored automatically under /proc/sys. The * procname supplied controls /proc naming. * * The table's mode will be honoured for proc-fs access. * * Leaf nodes in the sysctl tree will be represented by a single file * under /proc; non-leaf nodes will be represented by directories. A * null procname disables /proc mirroring at this node. * * The data and maxlen fields of the ctl_table * struct enable minimal validation of the values being written to be * performed, and the mode field allows minimal authentication. * * There must be a proc_handler routine for any terminal nodes * mirrored under /proc/sys (non-terminals are handled by a built-in * directory handler). Several default handlers are available to * cover common cases. */ /* Support for userspace poll() to watch for changes */ struct ctl_table_poll { atomic_t event; wait_queue_head_t wait; }; static inline void *proc_sys_poll_event(struct ctl_table_poll *poll) { return (void *)(unsigned long)atomic_read(&poll->event); } #define __CTL_TABLE_POLL_INITIALIZER(name) { \ .event = ATOMIC_INIT(0), \ .wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.wait) } #define DEFINE_CTL_TABLE_POLL(name) \ struct ctl_table_poll name = __CTL_TABLE_POLL_INITIALIZER(name) /* A sysctl table is an array of struct ctl_table: */ struct ctl_table { const char *procname; /* Text ID for /proc/sys */ void *data; int maxlen; umode_t mode; proc_handler *proc_handler; /* Callback for text formatting */ struct ctl_table_poll *poll; void *extra1; void *extra2; } __randomize_layout; struct ctl_node { struct rb_node node; struct ctl_table_header *header; }; /** * struct ctl_table_header - maintains dynamic lists of struct ctl_table trees * @ctl_table: pointer to the first element in ctl_table array * @ctl_table_size: number of elements pointed by @ctl_table * @used: The entry will never be touched when equal to 0. * @count: Upped every time something is added to @inodes and downed every time * something is removed from inodes * @nreg: When nreg drops to 0 the ctl_table_header will be unregistered. * @rcu: Delays the freeing of the inode. Introduced with "unfuck proc_sysctl ->d_compare()" * * @type: Enumeration to differentiate between ctl target types * @type.SYSCTL_TABLE_TYPE_DEFAULT: ctl target with no special considerations * @type.SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY: Identifies a permanently empty dir * target to serve as a mount point */ struct ctl_table_header { union { struct { const struct ctl_table *ctl_table; int ctl_table_size; int used; int count; int nreg; }; struct rcu_head rcu; }; struct completion *unregistering; const struct ctl_table *ctl_table_arg; struct ctl_table_root *root; struct ctl_table_set *set; struct ctl_dir *parent; struct ctl_node *node; struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */ enum { SYSCTL_TABLE_TYPE_DEFAULT, SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY, } type; }; struct ctl_dir { /* Header must be at the start of ctl_dir */ struct ctl_table_header header; struct rb_root root; }; struct ctl_table_set { int (*is_seen)(struct ctl_table_set *); struct ctl_dir dir; }; struct ctl_table_root { struct ctl_table_set default_set; struct ctl_table_set *(*lookup)(struct ctl_table_root *root); void (*set_ownership)(struct ctl_table_header *head, kuid_t *uid, kgid_t *gid); int (*permissions)(struct ctl_table_header *head, const struct ctl_table *table); }; #define register_sysctl(path, table) \ register_sysctl_sz(path, table, ARRAY_SIZE(table)) #ifdef CONFIG_SYSCTL void proc_sys_poll_notify(struct ctl_table_poll *poll); extern void setup_sysctl_set(struct ctl_table_set *p, struct ctl_table_root *root, int (*is_seen)(struct ctl_table_set *)); extern void retire_sysctl_set(struct ctl_table_set *set); struct ctl_table_header *__register_sysctl_table( struct ctl_table_set *set, const char *path, const struct ctl_table *table, size_t table_size); struct ctl_table_header *register_sysctl_sz(const char *path, const struct ctl_table *table, size_t table_size); void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init_bases(void); extern void __register_sysctl_init(const char *path, const struct ctl_table *table, const char *table_name, size_t table_size); #define register_sysctl_init(path, table) \ __register_sysctl_init(path, table, #table, ARRAY_SIZE(table)) extern struct ctl_table_header *register_sysctl_mount_point(const char *path); void do_sysctl_args(void); bool sysctl_is_alias(char *param); extern int unaligned_enabled; extern int no_unaligned_warning; #else /* CONFIG_SYSCTL */ static inline void register_sysctl_init(const char *path, const struct ctl_table *table) { } static inline struct ctl_table_header *register_sysctl_mount_point(const char *path) { return NULL; } static inline struct ctl_table_header *register_sysctl_sz(const char *path, const struct ctl_table *table, size_t table_size) { return NULL; } static inline void unregister_sysctl_table(struct ctl_table_header * table) { } static inline void setup_sysctl_set(struct ctl_table_set *p, struct ctl_table_root *root, int (*is_seen)(struct ctl_table_set *)) { } static inline void do_sysctl_args(void) { } static inline bool sysctl_is_alias(char *param) { return false; } #endif /* CONFIG_SYSCTL */ #endif /* _LINUX_SYSCTL_H */ |
| 878 879 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 | // SPDX-License-Identifier: GPL-2.0+ /* * IMA support for appraising module-style appended signatures. * * Copyright (C) 2019 IBM Corporation * * Author: * Thiago Jung Bauermann <bauerman@linux.ibm.com> */ #include <linux/types.h> #include <linux/module_signature.h> #include <keys/asymmetric-type.h> #include <crypto/pkcs7.h> #include "ima.h" struct modsig { struct pkcs7_message *pkcs7_msg; enum hash_algo hash_algo; /* This digest will go in the 'd-modsig' field of the IMA template. */ const u8 *digest; u32 digest_size; /* * This is what will go to the measurement list if the template requires * storing the signature. */ int raw_pkcs7_len; u8 raw_pkcs7[] __counted_by(raw_pkcs7_len); }; /* * ima_read_modsig - Read modsig from buf. * * Return: 0 on success, error code otherwise. */ int ima_read_modsig(enum ima_hooks func, const void *buf, loff_t buf_len, struct modsig **modsig) { const size_t marker_len = strlen(MODULE_SIGNATURE_MARKER); const struct module_signature *sig; struct modsig *hdr; size_t sig_len; const void *p; int rc; if (buf_len <= marker_len + sizeof(*sig)) return -ENOENT; p = buf + buf_len - marker_len; if (memcmp(p, MODULE_SIGNATURE_MARKER, marker_len)) return -ENOENT; buf_len -= marker_len; sig = (const struct module_signature *)(p - sizeof(*sig)); rc = mod_check_sig(sig, buf_len, func_tokens[func]); if (rc) return rc; sig_len = be32_to_cpu(sig->sig_len); buf_len -= sig_len + sizeof(*sig); /* Allocate sig_len additional bytes to hold the raw PKCS#7 data. */ hdr = kzalloc_flex(*hdr, raw_pkcs7, sig_len); if (!hdr) return -ENOMEM; hdr->raw_pkcs7_len = sig_len; hdr->pkcs7_msg = pkcs7_parse_message(buf + buf_len, sig_len); if (IS_ERR(hdr->pkcs7_msg)) { rc = PTR_ERR(hdr->pkcs7_msg); kfree(hdr); return rc; } memcpy(hdr->raw_pkcs7, buf + buf_len, sig_len); /* We don't know the hash algorithm yet. */ hdr->hash_algo = HASH_ALGO__LAST; *modsig = hdr; return 0; } /** * ima_collect_modsig - Calculate the file hash without the appended signature. * @modsig: parsed module signature * @buf: data to verify the signature on * @size: data size * * Since the modsig is part of the file contents, the hash used in its signature * isn't the same one ordinarily calculated by IMA. Therefore PKCS7 code * calculates a separate one for signature verification. */ void ima_collect_modsig(struct modsig *modsig, const void *buf, loff_t size) { int rc; /* * Provide the file contents (minus the appended sig) so that the PKCS7 * code can calculate the file hash. */ size -= modsig->raw_pkcs7_len + strlen(MODULE_SIGNATURE_MARKER) + sizeof(struct module_signature); rc = pkcs7_supply_detached_data(modsig->pkcs7_msg, buf, size); if (rc) return; /* Ask the PKCS7 code to calculate the file hash. */ rc = pkcs7_get_digest(modsig->pkcs7_msg, &modsig->digest, &modsig->digest_size, &modsig->hash_algo); } int ima_modsig_verify(struct key *keyring, const struct modsig *modsig) { return verify_pkcs7_message_sig(NULL, 0, modsig->pkcs7_msg, keyring, VERIFYING_MODULE_SIGNATURE, NULL, NULL); } int ima_get_modsig_digest(const struct modsig *modsig, enum hash_algo *algo, const u8 **digest, u32 *digest_size) { *algo = modsig->hash_algo; *digest = modsig->digest; *digest_size = modsig->digest_size; return 0; } int ima_get_raw_modsig(const struct modsig *modsig, const void **data, u32 *data_len) { *data = &modsig->raw_pkcs7; *data_len = modsig->raw_pkcs7_len; return 0; } void ima_free_modsig(struct modsig *modsig) { if (!modsig) return; pkcs7_free_message(modsig->pkcs7_msg); kfree(modsig); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_FPU_XCR_H #define _ASM_X86_FPU_XCR_H #define XCR_XFEATURE_ENABLED_MASK 0x00000000 #define XCR_XFEATURE_IN_USE_MASK 0x00000001 static __always_inline u64 xgetbv(u32 index) { u32 eax, edx; asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index)); return eax + ((u64)edx << 32); } static inline void xsetbv(u32 index, u64 value) { u32 eax = value; u32 edx = value >> 32; asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); } /* * Return a mask of xfeatures which are currently being tracked * by the processor as being not in the initial configuration. * * Callers should check X86_FEATURE_XGETBV1. */ static __always_inline u64 xfeatures_in_use(void) { return xgetbv(XCR_XFEATURE_IN_USE_MASK); } #endif /* _ASM_X86_FPU_XCR_H */ |
| 123 123 155 32 32 10 33 10 33 23 23 23 22 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 | // SPDX-License-Identifier: GPL-2.0-only /* * v4l2-fh.c * * V4L2 file handles. * * Copyright (C) 2009--2010 Nokia Corporation. * * Contact: Sakari Ailus <sakari.ailus@iki.fi> */ #include <linux/bitops.h> #include <linux/slab.h> #include <linux/export.h> #include <media/v4l2-dev.h> #include <media/v4l2-fh.h> #include <media/v4l2-event.h> #include <media/v4l2-ioctl.h> #include <media/v4l2-mc.h> void v4l2_fh_init(struct v4l2_fh *fh, struct video_device *vdev) { fh->vdev = vdev; /* Inherit from video_device. May be overridden by the driver. */ fh->ctrl_handler = vdev->ctrl_handler; INIT_LIST_HEAD(&fh->list); set_bit(V4L2_FL_USES_V4L2_FH, &fh->vdev->flags); /* * determine_valid_ioctls() does not know if struct v4l2_fh * is used by this driver, but here we do. So enable the * prio ioctls here. */ set_bit(_IOC_NR(VIDIOC_G_PRIORITY), vdev->valid_ioctls); set_bit(_IOC_NR(VIDIOC_S_PRIORITY), vdev->valid_ioctls); fh->prio = V4L2_PRIORITY_UNSET; init_waitqueue_head(&fh->wait); INIT_LIST_HEAD(&fh->available); INIT_LIST_HEAD(&fh->subscribed); fh->sequence = -1; mutex_init(&fh->subscribe_lock); } EXPORT_SYMBOL_GPL(v4l2_fh_init); void v4l2_fh_add(struct v4l2_fh *fh, struct file *filp) { unsigned long flags; filp->private_data = fh; v4l2_prio_open(fh->vdev->prio, &fh->prio); spin_lock_irqsave(&fh->vdev->fh_lock, flags); list_add(&fh->list, &fh->vdev->fh_list); spin_unlock_irqrestore(&fh->vdev->fh_lock, flags); } EXPORT_SYMBOL_GPL(v4l2_fh_add); int v4l2_fh_open(struct file *filp) { struct video_device *vdev = video_devdata(filp); struct v4l2_fh *fh = kzalloc_obj(*fh); if (fh == NULL) return -ENOMEM; v4l2_fh_init(fh, vdev); v4l2_fh_add(fh, filp); return 0; } EXPORT_SYMBOL_GPL(v4l2_fh_open); void v4l2_fh_del(struct v4l2_fh *fh, struct file *filp) { unsigned long flags; spin_lock_irqsave(&fh->vdev->fh_lock, flags); list_del_init(&fh->list); spin_unlock_irqrestore(&fh->vdev->fh_lock, flags); v4l2_prio_close(fh->vdev->prio, fh->prio); filp->private_data = NULL; } EXPORT_SYMBOL_GPL(v4l2_fh_del); void v4l2_fh_exit(struct v4l2_fh *fh) { if (fh->vdev == NULL) return; v4l_disable_media_source(fh->vdev); v4l2_event_unsubscribe_all(fh); mutex_destroy(&fh->subscribe_lock); fh->vdev = NULL; } EXPORT_SYMBOL_GPL(v4l2_fh_exit); int v4l2_fh_release(struct file *filp) { struct v4l2_fh *fh = file_to_v4l2_fh(filp); if (fh) { v4l2_fh_del(fh, filp); v4l2_fh_exit(fh); kfree(fh); } return 0; } EXPORT_SYMBOL_GPL(v4l2_fh_release); int v4l2_fh_is_singular(struct v4l2_fh *fh) { unsigned long flags; int is_singular; if (fh == NULL || fh->vdev == NULL) return 0; spin_lock_irqsave(&fh->vdev->fh_lock, flags); is_singular = list_is_singular(&fh->list); spin_unlock_irqrestore(&fh->vdev->fh_lock, flags); return is_singular; } EXPORT_SYMBOL_GPL(v4l2_fh_is_singular); |
| 12 12 1 2 2 1 1 2 1 1 1 1 1 15 17 1 15 12 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 | // SPDX-License-Identifier: GPL-2.0 /* * Key setup for v1 encryption policies * * Copyright 2015, 2019 Google LLC */ /* * This file implements compatibility functions for the original encryption * policy version ("v1"), including: * * - Deriving per-file encryption keys using the AES-128-ECB based KDF * (rather than the new method of using HKDF-SHA512) * * - Retrieving fscrypt master keys from process-subscribed keyrings * (rather than the new method of using a filesystem-level keyring) * * - Handling policies with the DIRECT_KEY flag set using a master key table * (rather than the new method of implementing DIRECT_KEY with per-mode keys * managed alongside the master keys in the filesystem-level keyring) */ #include <crypto/aes.h> #include <crypto/utils.h> #include <keys/user-type.h> #include <linux/hashtable.h> #include "fscrypt_private.h" /* Table of keys referenced by DIRECT_KEY policies */ static DEFINE_HASHTABLE(fscrypt_direct_keys, 6); /* 6 bits = 64 buckets */ static DEFINE_SPINLOCK(fscrypt_direct_keys_lock); /* * Search the current task's subscribed keyrings for a "logon" key with * description prefix:descriptor, and if found acquire a read lock on it and * return a pointer to its validated payload in *payload_ret. */ static struct key * find_and_lock_process_key(const char *prefix, const u8 descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE], unsigned int min_keysize, const struct fscrypt_key **payload_ret) { char *description; struct key *key; const struct user_key_payload *ukp; const struct fscrypt_key *payload; description = kasprintf(GFP_KERNEL, "%s%*phN", prefix, FSCRYPT_KEY_DESCRIPTOR_SIZE, descriptor); if (!description) return ERR_PTR(-ENOMEM); key = request_key(&key_type_logon, description, NULL); kfree(description); if (IS_ERR(key)) return key; down_read(&key->sem); ukp = user_key_payload_locked(key); if (!ukp) /* was the key revoked before we acquired its semaphore? */ goto invalid; payload = (const struct fscrypt_key *)ukp->data; if (ukp->datalen != sizeof(struct fscrypt_key) || payload->size < 1 || payload->size > sizeof(payload->raw)) { fscrypt_warn(NULL, "key with description '%s' has invalid payload", key->description); goto invalid; } if (payload->size < min_keysize) { fscrypt_warn(NULL, "key with description '%s' is too short (got %u bytes, need %u+ bytes)", key->description, payload->size, min_keysize); goto invalid; } *payload_ret = payload; return key; invalid: up_read(&key->sem); key_put(key); return ERR_PTR(-ENOKEY); } /* Master key referenced by DIRECT_KEY policy */ struct fscrypt_direct_key { struct super_block *dk_sb; struct hlist_node dk_node; refcount_t dk_refcount; const struct fscrypt_mode *dk_mode; struct fscrypt_prepared_key dk_key; u8 dk_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE]; u8 dk_raw[FSCRYPT_MAX_RAW_KEY_SIZE]; }; static void free_direct_key(struct fscrypt_direct_key *dk) { if (dk) { fscrypt_destroy_prepared_key(dk->dk_sb, &dk->dk_key); kfree_sensitive(dk); } } void fscrypt_put_direct_key(struct fscrypt_direct_key *dk) { if (!refcount_dec_and_lock(&dk->dk_refcount, &fscrypt_direct_keys_lock)) return; hash_del(&dk->dk_node); spin_unlock(&fscrypt_direct_keys_lock); free_direct_key(dk); } /* * Find/insert the given key into the fscrypt_direct_keys table. If found, it * is returned with elevated refcount, and 'to_insert' is freed if non-NULL. If * not found, 'to_insert' is inserted and returned if it's non-NULL; otherwise * NULL is returned. */ static struct fscrypt_direct_key * find_or_insert_direct_key(struct fscrypt_direct_key *to_insert, const u8 *raw_key, const struct fscrypt_inode_info *ci) { unsigned long hash_key; struct fscrypt_direct_key *dk; /* * Careful: to avoid potentially leaking secret key bytes via timing * information, we must key the hash table by descriptor rather than by * raw key, and use crypto_memneq() when comparing raw keys. */ BUILD_BUG_ON(sizeof(hash_key) > FSCRYPT_KEY_DESCRIPTOR_SIZE); memcpy(&hash_key, ci->ci_policy.v1.master_key_descriptor, sizeof(hash_key)); spin_lock(&fscrypt_direct_keys_lock); hash_for_each_possible(fscrypt_direct_keys, dk, dk_node, hash_key) { if (memcmp(ci->ci_policy.v1.master_key_descriptor, dk->dk_descriptor, FSCRYPT_KEY_DESCRIPTOR_SIZE) != 0) continue; if (ci->ci_mode != dk->dk_mode) continue; if (!fscrypt_is_key_prepared(&dk->dk_key, ci)) continue; if (crypto_memneq(raw_key, dk->dk_raw, ci->ci_mode->keysize)) continue; /* using existing tfm with same (descriptor, mode, raw_key) */ refcount_inc(&dk->dk_refcount); spin_unlock(&fscrypt_direct_keys_lock); free_direct_key(to_insert); return dk; } if (to_insert) hash_add(fscrypt_direct_keys, &to_insert->dk_node, hash_key); spin_unlock(&fscrypt_direct_keys_lock); return to_insert; } /* Prepare to encrypt directly using the master key in the given mode */ static struct fscrypt_direct_key * fscrypt_get_direct_key(const struct fscrypt_inode_info *ci, const u8 *raw_key) { struct fscrypt_direct_key *dk; int err; /* Is there already a tfm for this key? */ dk = find_or_insert_direct_key(NULL, raw_key, ci); if (dk) return dk; /* Nope, allocate one. */ dk = kzalloc_obj(*dk); if (!dk) return ERR_PTR(-ENOMEM); dk->dk_sb = ci->ci_inode->i_sb; refcount_set(&dk->dk_refcount, 1); dk->dk_mode = ci->ci_mode; err = fscrypt_prepare_key(&dk->dk_key, raw_key, ci); if (err) goto err_free_dk; memcpy(dk->dk_descriptor, ci->ci_policy.v1.master_key_descriptor, FSCRYPT_KEY_DESCRIPTOR_SIZE); memcpy(dk->dk_raw, raw_key, ci->ci_mode->keysize); return find_or_insert_direct_key(dk, raw_key, ci); err_free_dk: free_direct_key(dk); return ERR_PTR(err); } /* v1 policy, DIRECT_KEY: use the master key directly */ static int setup_v1_file_key_direct(struct fscrypt_inode_info *ci, const u8 *raw_master_key) { struct fscrypt_direct_key *dk; dk = fscrypt_get_direct_key(ci, raw_master_key); if (IS_ERR(dk)) return PTR_ERR(dk); ci->ci_direct_key = dk; ci->ci_enc_key = dk->dk_key; return 0; } /* * v1 policy, !DIRECT_KEY: derive the file's encryption key. * * The v1 key derivation function generates the derived key by encrypting the * master key with AES-128-ECB using the file's nonce as the AES key. This * provides a unique derived key with sufficient entropy for each inode. * However, it's nonstandard, non-extensible, doesn't evenly distribute the * entropy from the master key, and is trivially reversible: an attacker who * compromises a derived key can "decrypt" it to get back to the master key, * then derive any other key. For all new code, use HKDF instead. * * The master key must be at least as long as the derived key. If the master * key is longer, then only the first ci->ci_mode->keysize bytes are used. */ static int setup_v1_file_key_derived(struct fscrypt_inode_info *ci, const u8 *raw_master_key) { const unsigned int derived_keysize = ci->ci_mode->keysize; u8 derived_key[FSCRYPT_MAX_RAW_KEY_SIZE]; struct aes_enckey aes; int err; if (WARN_ON_ONCE(derived_keysize > FSCRYPT_MAX_RAW_KEY_SIZE || derived_keysize % AES_BLOCK_SIZE != 0)) return -EINVAL; static_assert(FSCRYPT_FILE_NONCE_SIZE == AES_KEYSIZE_128); aes_prepareenckey(&aes, ci->ci_nonce, FSCRYPT_FILE_NONCE_SIZE); for (unsigned int i = 0; i < derived_keysize; i += AES_BLOCK_SIZE) aes_encrypt(&aes, &derived_key[i], &raw_master_key[i]); err = fscrypt_set_per_file_enc_key(ci, derived_key); memzero_explicit(derived_key, derived_keysize); /* No need to zeroize 'aes', as its key is not secret. */ return err; } int fscrypt_setup_v1_file_key(struct fscrypt_inode_info *ci, const u8 *raw_master_key) { if (ci->ci_policy.v1.flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) return setup_v1_file_key_direct(ci, raw_master_key); else return setup_v1_file_key_derived(ci, raw_master_key); } int fscrypt_setup_v1_file_key_via_subscribed_keyrings(struct fscrypt_inode_info *ci) { const struct super_block *sb = ci->ci_inode->i_sb; struct key *key; const struct fscrypt_key *payload; int err; key = find_and_lock_process_key(FSCRYPT_KEY_DESC_PREFIX, ci->ci_policy.v1.master_key_descriptor, ci->ci_mode->keysize, &payload); if (key == ERR_PTR(-ENOKEY) && sb->s_cop->legacy_key_prefix) { key = find_and_lock_process_key(sb->s_cop->legacy_key_prefix, ci->ci_policy.v1.master_key_descriptor, ci->ci_mode->keysize, &payload); } if (IS_ERR(key)) return PTR_ERR(key); err = fscrypt_setup_v1_file_key(ci, payload->raw); up_read(&key->sem); key_put(key); return err; } |
| 1 14 1 13 13 1 1 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 | // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2003-2008 Takahiro Hirofuchi * Copyright (C) 2015-2016 Nobuo Iwata */ #include <linux/kthread.h> #include <linux/file.h> #include <linux/net.h> #include <linux/platform_device.h> #include <linux/slab.h> /* Hardening for Spectre-v1 */ #include <linux/nospec.h> #include "usbip_common.h" #include "vhci.h" /* TODO: refine locking ?*/ /* * output example: * hub port sta spd dev sockfd local_busid * hs 0000 004 000 00000000 000003 1-2.3 * ................................................ * ss 0008 004 000 00000000 000004 2-3.4 * ................................................ * * Output includes socket fd instead of socket pointer address to avoid * leaking kernel memory address in: * /sys/devices/platform/vhci_hcd.0/status and in debug output. * The socket pointer address is not used at the moment and it was made * visible as a convenient way to find IP address from socket pointer * address by looking up /proc/net/{tcp,tcp6}. As this opens a security * hole, the change is made to use sockfd instead. * */ static void port_show_vhci(char **out, int hub, int port, struct vhci_device *vdev) { if (hub == HUB_SPEED_HIGH) *out += sprintf(*out, "hs %04u %03u ", port, vdev->ud.status); else /* hub == HUB_SPEED_SUPER */ *out += sprintf(*out, "ss %04u %03u ", port, vdev->ud.status); if (vdev->ud.status == VDEV_ST_USED) { *out += sprintf(*out, "%03u %08x ", vdev->speed, vdev->devid); *out += sprintf(*out, "%06u %s", vdev->ud.sockfd, dev_name(&vdev->udev->dev)); } else { *out += sprintf(*out, "000 00000000 "); *out += sprintf(*out, "000000 0-0"); } *out += sprintf(*out, "\n"); } /* Sysfs entry to show port status */ static ssize_t status_show_vhci(int pdev_nr, char *out) { struct platform_device *pdev = vhcis[pdev_nr].pdev; struct vhci *vhci; struct usb_hcd *hcd; struct vhci_hcd *vhci_hcd; char *s = out; int i; unsigned long flags; if (!pdev || !out) { usbip_dbg_vhci_sysfs("show status error\n"); return 0; } hcd = platform_get_drvdata(pdev); vhci_hcd = hcd_to_vhci_hcd(hcd); vhci = vhci_hcd->vhci; spin_lock_irqsave(&vhci->lock, flags); for (i = 0; i < VHCI_HC_PORTS; i++) { struct vhci_device *vdev = &vhci->vhci_hcd_hs->vdev[i]; spin_lock(&vdev->ud.lock); port_show_vhci(&out, HUB_SPEED_HIGH, pdev_nr * VHCI_PORTS + i, vdev); spin_unlock(&vdev->ud.lock); } for (i = 0; i < VHCI_HC_PORTS; i++) { struct vhci_device *vdev = &vhci->vhci_hcd_ss->vdev[i]; spin_lock(&vdev->ud.lock); port_show_vhci(&out, HUB_SPEED_SUPER, pdev_nr * VHCI_PORTS + VHCI_HC_PORTS + i, vdev); spin_unlock(&vdev->ud.lock); } spin_unlock_irqrestore(&vhci->lock, flags); return out - s; } static ssize_t status_show_not_ready(int pdev_nr, char *out) { char *s = out; int i = 0; for (i = 0; i < VHCI_HC_PORTS; i++) { out += sprintf(out, "hs %04u %03u ", (pdev_nr * VHCI_PORTS) + i, VDEV_ST_NOTASSIGNED); out += sprintf(out, "000 00000000 0000000000000000 0-0"); out += sprintf(out, "\n"); } for (i = 0; i < VHCI_HC_PORTS; i++) { out += sprintf(out, "ss %04u %03u ", (pdev_nr * VHCI_PORTS) + VHCI_HC_PORTS + i, VDEV_ST_NOTASSIGNED); out += sprintf(out, "000 00000000 0000000000000000 0-0"); out += sprintf(out, "\n"); } return out - s; } static int status_name_to_id(const char *name) { char *c; long val; int ret; c = strchr(name, '.'); if (c == NULL) return 0; ret = kstrtol(c+1, 10, &val); if (ret < 0) return ret; return val; } static ssize_t status_show(struct device *dev, struct device_attribute *attr, char *out) { char *s = out; int pdev_nr; out += sprintf(out, "hub port sta spd dev sockfd local_busid\n"); pdev_nr = status_name_to_id(attr->attr.name); if (pdev_nr < 0) out += status_show_not_ready(pdev_nr, out); else out += status_show_vhci(pdev_nr, out); return out - s; } static ssize_t nports_show(struct device *dev, struct device_attribute *attr, char *out) { char *s = out; /* * Half the ports are for SPEED_HIGH and half for SPEED_SUPER, * thus the * 2. */ out += sprintf(out, "%d\n", VHCI_PORTS * vhci_num_controllers); return out - s; } static DEVICE_ATTR_RO(nports); /* Sysfs entry to shutdown a virtual connection */ static int vhci_port_disconnect(struct vhci_hcd *vhci_hcd, __u32 rhport) { struct vhci_device *vdev = &vhci_hcd->vdev[rhport]; struct vhci *vhci = vhci_hcd->vhci; unsigned long flags; usbip_dbg_vhci_sysfs("enter\n"); mutex_lock(&vdev->ud.sysfs_lock); /* lock */ spin_lock_irqsave(&vhci->lock, flags); spin_lock(&vdev->ud.lock); if (vdev->ud.status == VDEV_ST_NULL) { pr_err("not connected %d\n", vdev->ud.status); /* unlock */ spin_unlock(&vdev->ud.lock); spin_unlock_irqrestore(&vhci->lock, flags); mutex_unlock(&vdev->ud.sysfs_lock); return -EINVAL; } /* unlock */ spin_unlock(&vdev->ud.lock); spin_unlock_irqrestore(&vhci->lock, flags); usbip_event_add(&vdev->ud, VDEV_EVENT_DOWN); mutex_unlock(&vdev->ud.sysfs_lock); return 0; } static int valid_port(__u32 *pdev_nr, __u32 *rhport) { if (*pdev_nr >= vhci_num_controllers) { pr_err("pdev %u\n", *pdev_nr); return 0; } *pdev_nr = array_index_nospec(*pdev_nr, vhci_num_controllers); if (*rhport >= VHCI_HC_PORTS) { pr_err("rhport %u\n", *rhport); return 0; } *rhport = array_index_nospec(*rhport, VHCI_HC_PORTS); return 1; } static ssize_t detach_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { __u32 port = 0, pdev_nr = 0, rhport = 0; struct usb_hcd *hcd; struct vhci_hcd *vhci_hcd; int ret; if (kstrtoint(buf, 10, &port) < 0) return -EINVAL; pdev_nr = port_to_pdev_nr(port); rhport = port_to_rhport(port); if (!valid_port(&pdev_nr, &rhport)) return -EINVAL; hcd = platform_get_drvdata(vhcis[pdev_nr].pdev); if (hcd == NULL) { dev_err(dev, "port is not ready %u\n", port); return -EAGAIN; } usbip_dbg_vhci_sysfs("rhport %d\n", rhport); if ((port / VHCI_HC_PORTS) % 2) vhci_hcd = hcd_to_vhci_hcd(hcd)->vhci->vhci_hcd_ss; else vhci_hcd = hcd_to_vhci_hcd(hcd)->vhci->vhci_hcd_hs; ret = vhci_port_disconnect(vhci_hcd, rhport); if (ret < 0) return -EINVAL; usbip_dbg_vhci_sysfs("Leave\n"); return count; } static DEVICE_ATTR_WO(detach); static int valid_args(__u32 *pdev_nr, __u32 *rhport, enum usb_device_speed speed) { if (!valid_port(pdev_nr, rhport)) { return 0; } switch (speed) { case USB_SPEED_LOW: case USB_SPEED_FULL: case USB_SPEED_HIGH: case USB_SPEED_WIRELESS: case USB_SPEED_SUPER: case USB_SPEED_SUPER_PLUS: break; default: pr_err("Failed attach request for unsupported USB speed: %s\n", usb_speed_string(speed)); return 0; } return 1; } /* Sysfs entry to establish a virtual connection */ /* * To start a new USB/IP attachment, a userland program needs to setup a TCP * connection and then write its socket descriptor with remote device * information into this sysfs file. * * A remote device is virtually attached to the root-hub port of @rhport with * @speed. @devid is embedded into a request to specify the remote device in a * server host. * * write() returns 0 on success, else negative errno. */ static ssize_t attach_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct socket *socket; int sockfd = 0; __u32 port = 0, pdev_nr = 0, rhport = 0, devid = 0, speed = 0; struct usb_hcd *hcd; struct vhci_hcd *vhci_hcd; struct vhci_device *vdev; struct vhci *vhci; int err; unsigned long flags; struct task_struct *tcp_rx = NULL; struct task_struct *tcp_tx = NULL; /* * @rhport: port number of vhci_hcd * @sockfd: socket descriptor of an established TCP connection * @devid: unique device identifier in a remote host * @speed: usb device speed in a remote host */ if (sscanf(buf, "%u %u %u %u", &port, &sockfd, &devid, &speed) != 4) return -EINVAL; pdev_nr = port_to_pdev_nr(port); rhport = port_to_rhport(port); usbip_dbg_vhci_sysfs("port(%u) pdev(%d) rhport(%u)\n", port, pdev_nr, rhport); usbip_dbg_vhci_sysfs("sockfd(%u) devid(%u) speed(%u)\n", sockfd, devid, speed); /* check received parameters */ if (!valid_args(&pdev_nr, &rhport, speed)) return -EINVAL; hcd = platform_get_drvdata(vhcis[pdev_nr].pdev); if (hcd == NULL) { dev_err(dev, "port %d is not ready\n", port); return -EAGAIN; } vhci_hcd = hcd_to_vhci_hcd(hcd); vhci = vhci_hcd->vhci; if (speed >= USB_SPEED_SUPER) vdev = &vhci->vhci_hcd_ss->vdev[rhport]; else vdev = &vhci->vhci_hcd_hs->vdev[rhport]; mutex_lock(&vdev->ud.sysfs_lock); /* Extract socket from fd. */ socket = sockfd_lookup(sockfd, &err); if (!socket) { dev_err(dev, "failed to lookup sock"); err = -EINVAL; goto unlock_mutex; } if (socket->type != SOCK_STREAM) { dev_err(dev, "Expecting SOCK_STREAM - found %d", socket->type); sockfd_put(socket); err = -EINVAL; goto unlock_mutex; } /* create threads before locking */ tcp_rx = kthread_create(vhci_rx_loop, &vdev->ud, "vhci_rx"); if (IS_ERR(tcp_rx)) { sockfd_put(socket); err = -EINVAL; goto unlock_mutex; } tcp_tx = kthread_create(vhci_tx_loop, &vdev->ud, "vhci_tx"); if (IS_ERR(tcp_tx)) { kthread_stop(tcp_rx); sockfd_put(socket); err = -EINVAL; goto unlock_mutex; } /* get task structs now */ get_task_struct(tcp_rx); get_task_struct(tcp_tx); /* now begin lock until setting vdev status set */ spin_lock_irqsave(&vhci->lock, flags); spin_lock(&vdev->ud.lock); if (vdev->ud.status != VDEV_ST_NULL) { /* end of the lock */ spin_unlock(&vdev->ud.lock); spin_unlock_irqrestore(&vhci->lock, flags); sockfd_put(socket); kthread_stop_put(tcp_rx); kthread_stop_put(tcp_tx); dev_err(dev, "port %d already used\n", rhport); /* * Will be retried from userspace * if there's another free port. */ err = -EBUSY; goto unlock_mutex; } dev_info(dev, "pdev(%u) rhport(%u) sockfd(%d)\n", pdev_nr, rhport, sockfd); dev_info(dev, "devid(%u) speed(%u) speed_str(%s)\n", devid, speed, usb_speed_string(speed)); vdev->devid = devid; vdev->speed = speed; vdev->ud.sockfd = sockfd; vdev->ud.tcp_socket = socket; vdev->ud.tcp_rx = tcp_rx; vdev->ud.tcp_tx = tcp_tx; vdev->ud.status = VDEV_ST_NOTASSIGNED; usbip_kcov_handle_init(&vdev->ud); spin_unlock(&vdev->ud.lock); spin_unlock_irqrestore(&vhci->lock, flags); /* end the lock */ wake_up_process(vdev->ud.tcp_rx); wake_up_process(vdev->ud.tcp_tx); rh_port_connect(vdev, speed); dev_info(dev, "Device attached\n"); mutex_unlock(&vdev->ud.sysfs_lock); return count; unlock_mutex: mutex_unlock(&vdev->ud.sysfs_lock); return err; } static DEVICE_ATTR_WO(attach); #define MAX_STATUS_NAME 16 struct status_attr { struct device_attribute attr; char name[MAX_STATUS_NAME+1]; }; static struct status_attr *status_attrs; static void set_status_attr(int id) { struct status_attr *status; status = status_attrs + id; if (id == 0) strscpy(status->name, "status"); else snprintf(status->name, MAX_STATUS_NAME+1, "status.%d", id); status->attr.attr.name = status->name; status->attr.attr.mode = S_IRUGO; status->attr.show = status_show; sysfs_attr_init(&status->attr.attr); } static int init_status_attrs(void) { int id; status_attrs = kzalloc_objs(struct status_attr, vhci_num_controllers); if (status_attrs == NULL) return -ENOMEM; for (id = 0; id < vhci_num_controllers; id++) set_status_attr(id); return 0; } static void finish_status_attrs(void) { kfree(status_attrs); } struct attribute_group vhci_attr_group = { .attrs = NULL, }; int vhci_init_attr_group(void) { struct attribute **attrs; int ret, i; attrs = kzalloc_objs(struct attribute *, (vhci_num_controllers + 5)); if (attrs == NULL) return -ENOMEM; ret = init_status_attrs(); if (ret) { kfree(attrs); return ret; } *attrs = &dev_attr_nports.attr; *(attrs + 1) = &dev_attr_detach.attr; *(attrs + 2) = &dev_attr_attach.attr; *(attrs + 3) = &dev_attr_usbip_debug.attr; for (i = 0; i < vhci_num_controllers; i++) *(attrs + i + 4) = &((status_attrs + i)->attr.attr); vhci_attr_group.attrs = attrs; return 0; } void vhci_finish_attr_group(void) { finish_status_attrs(); kfree(vhci_attr_group.attrs); } |
| 27 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * AEGIS common definitions * * Copyright (c) 2018 Ondrej Mosnacek <omosnacek@gmail.com> * Copyright (c) 2018 Red Hat, Inc. All rights reserved. */ #ifndef _CRYPTO_AEGIS_H #define _CRYPTO_AEGIS_H #include <crypto/aes.h> #include <linux/bitops.h> #include <linux/types.h> #define AEGIS_BLOCK_SIZE 16 union aegis_block { __le64 words64[AEGIS_BLOCK_SIZE / sizeof(__le64)]; __le32 words32[AEGIS_BLOCK_SIZE / sizeof(__le32)]; u8 bytes[AEGIS_BLOCK_SIZE]; }; struct aegis_state; extern int aegis128_have_aes_insn; #define AEGIS_BLOCK_ALIGN (__alignof__(union aegis_block)) #define AEGIS_ALIGNED(p) IS_ALIGNED((uintptr_t)p, AEGIS_BLOCK_ALIGN) bool crypto_aegis128_have_simd(void); void crypto_aegis128_update_simd(struct aegis_state *state, const void *msg); void crypto_aegis128_init_simd(struct aegis_state *state, const union aegis_block *key, const u8 *iv); void crypto_aegis128_encrypt_chunk_simd(struct aegis_state *state, u8 *dst, const u8 *src, unsigned int size); void crypto_aegis128_decrypt_chunk_simd(struct aegis_state *state, u8 *dst, const u8 *src, unsigned int size); int crypto_aegis128_final_simd(struct aegis_state *state, union aegis_block *tag_xor, unsigned int assoclen, unsigned int cryptlen, unsigned int authsize); static __always_inline void crypto_aegis_block_xor(union aegis_block *dst, const union aegis_block *src) { dst->words64[0] ^= src->words64[0]; dst->words64[1] ^= src->words64[1]; } static __always_inline void crypto_aegis_block_and(union aegis_block *dst, const union aegis_block *src) { dst->words64[0] &= src->words64[0]; dst->words64[1] &= src->words64[1]; } static __always_inline void crypto_aegis_aesenc(union aegis_block *dst, const union aegis_block *src, const union aegis_block *key) { const u8 *s = src->bytes; const u32 *t = aes_enc_tab; u32 d0, d1, d2, d3; d0 = t[s[ 0]] ^ rol32(t[s[ 5]], 8) ^ rol32(t[s[10]], 16) ^ rol32(t[s[15]], 24); d1 = t[s[ 4]] ^ rol32(t[s[ 9]], 8) ^ rol32(t[s[14]], 16) ^ rol32(t[s[ 3]], 24); d2 = t[s[ 8]] ^ rol32(t[s[13]], 8) ^ rol32(t[s[ 2]], 16) ^ rol32(t[s[ 7]], 24); d3 = t[s[12]] ^ rol32(t[s[ 1]], 8) ^ rol32(t[s[ 6]], 16) ^ rol32(t[s[11]], 24); dst->words32[0] = cpu_to_le32(d0) ^ key->words32[0]; dst->words32[1] = cpu_to_le32(d1) ^ key->words32[1]; dst->words32[2] = cpu_to_le32(d2) ^ key->words32[2]; dst->words32[3] = cpu_to_le32(d3) ^ key->words32[3]; } #endif /* _CRYPTO_AEGIS_H */ |
| 32 12 22 22 1 12 1 11 12 12 12 2 1 1 1 14 1 16 14 2 2 17 17 5 3 16 13 12 1 8 9 7 2 1 1 1 1 1 1 2 2 22 1 2 1 6 3 3 6 5 1 2 5 1 1 32 32 32 27 5 32 32 27 27 27 15 3 3 10 16 16 9 9 9 9 9 9 2 2 2 2 5 5 6 6 6 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 | // SPDX-License-Identifier: GPL-2.0-only /* * Framework for buffer objects that can be shared across devices/subsystems. * * Copyright(C) 2011 Linaro Limited. All rights reserved. * Author: Sumit Semwal <sumit.semwal@ti.com> * * Many thanks to linaro-mm-sig list, and specially * Arnd Bergmann <arnd@arndb.de>, Rob Clark <rob@ti.com> and * Daniel Vetter <daniel@ffwll.ch> for their support in creation and * refining of this idea. */ #include <linux/fs.h> #include <linux/slab.h> #include <linux/dma-buf.h> #include <linux/dma-fence.h> #include <linux/dma-fence-unwrap.h> #include <linux/anon_inodes.h> #include <linux/export.h> #include <linux/debugfs.h> #include <linux/list.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/seq_file.h> #include <linux/sync_file.h> #include <linux/poll.h> #include <linux/dma-resv.h> #include <linux/mm.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <uapi/linux/dma-buf.h> #include <uapi/linux/magic.h> #define CREATE_TRACE_POINTS #include <trace/events/dma_buf.h> /* * dmabuf->name must be accessed with holding dmabuf->name_lock. * we need to take the lock around the tracepoint call itself where * it is called in the code. * * Note: FUNC##_enabled() is a static branch that will only * be set when the trace event is enabled. */ #define DMA_BUF_TRACE(FUNC, ...) \ do { \ /* Always expose lock if lockdep is enabled */ \ if (IS_ENABLED(CONFIG_LOCKDEP) || FUNC##_enabled()) { \ guard(spinlock)(&dmabuf->name_lock); \ FUNC(__VA_ARGS__); \ } \ } while (0) /* Wrapper to hide the sg_table page link from the importer */ struct dma_buf_sg_table_wrapper { struct sg_table *original; struct sg_table wrapper; }; static inline int is_dma_buf_file(struct file *); static DEFINE_MUTEX(dmabuf_list_mutex); static LIST_HEAD(dmabuf_list); static void __dma_buf_list_add(struct dma_buf *dmabuf) { mutex_lock(&dmabuf_list_mutex); list_add(&dmabuf->list_node, &dmabuf_list); mutex_unlock(&dmabuf_list_mutex); } static void __dma_buf_list_del(struct dma_buf *dmabuf) { if (!dmabuf) return; mutex_lock(&dmabuf_list_mutex); list_del(&dmabuf->list_node); mutex_unlock(&dmabuf_list_mutex); } /** * dma_buf_iter_begin - begin iteration through global list of all DMA buffers * * Returns the first buffer in the global list of DMA-bufs that's not in the * process of being destroyed. Increments that buffer's reference count to * prevent buffer destruction. Callers must release the reference, either by * continuing iteration with dma_buf_iter_next(), or with dma_buf_put(). * * Return: * * First buffer from global list, with refcount elevated * * NULL if no active buffers are present */ struct dma_buf *dma_buf_iter_begin(void) { struct dma_buf *ret = NULL, *dmabuf; /* * The list mutex does not protect a dmabuf's refcount, so it can be * zeroed while we are iterating. We cannot call get_dma_buf() since the * caller may not already own a reference to the buffer. */ mutex_lock(&dmabuf_list_mutex); list_for_each_entry(dmabuf, &dmabuf_list, list_node) { if (file_ref_get(&dmabuf->file->f_ref)) { ret = dmabuf; break; } } mutex_unlock(&dmabuf_list_mutex); return ret; } /** * dma_buf_iter_next - continue iteration through global list of all DMA buffers * @dmabuf: [in] pointer to dma_buf * * Decrements the reference count on the provided buffer. Returns the next * buffer from the remainder of the global list of DMA-bufs with its reference * count incremented. Callers must release the reference, either by continuing * iteration with dma_buf_iter_next(), or with dma_buf_put(). * * Return: * * Next buffer from global list, with refcount elevated * * NULL if no additional active buffers are present */ struct dma_buf *dma_buf_iter_next(struct dma_buf *dmabuf) { struct dma_buf *ret = NULL; /* * The list mutex does not protect a dmabuf's refcount, so it can be * zeroed while we are iterating. We cannot call get_dma_buf() since the * caller may not already own a reference to the buffer. */ mutex_lock(&dmabuf_list_mutex); dma_buf_put(dmabuf); list_for_each_entry_continue(dmabuf, &dmabuf_list, list_node) { if (file_ref_get(&dmabuf->file->f_ref)) { ret = dmabuf; break; } } mutex_unlock(&dmabuf_list_mutex); return ret; } static char *dmabuffs_dname(struct dentry *dentry, char *buffer, int buflen) { struct dma_buf *dmabuf; char name[DMA_BUF_NAME_LEN]; ssize_t ret = 0; dmabuf = dentry->d_fsdata; spin_lock(&dmabuf->name_lock); if (dmabuf->name) ret = strscpy(name, dmabuf->name, sizeof(name)); spin_unlock(&dmabuf->name_lock); return dynamic_dname(buffer, buflen, "/%s:%s", dentry->d_name.name, ret > 0 ? name : ""); } static void dma_buf_release(struct dentry *dentry) { struct dma_buf *dmabuf; dmabuf = dentry->d_fsdata; if (unlikely(!dmabuf)) return; BUG_ON(dmabuf->vmapping_counter); /* * If you hit this BUG() it could mean: * * There's a file reference imbalance in dma_buf_poll / dma_buf_poll_cb or somewhere else * * dmabuf->cb_in/out.active are non-0 despite no pending fence callback */ BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active); dmabuf->ops->release(dmabuf); if (dmabuf->resv == (struct dma_resv *)&dmabuf[1]) dma_resv_fini(dmabuf->resv); WARN_ON(!list_empty(&dmabuf->attachments)); module_put(dmabuf->owner); kfree(dmabuf->name); kfree(dmabuf); } static int dma_buf_file_release(struct inode *inode, struct file *file) { if (!is_dma_buf_file(file)) return -EINVAL; __dma_buf_list_del(file->private_data); return 0; } static const struct dentry_operations dma_buf_dentry_ops = { .d_dname = dmabuffs_dname, .d_release = dma_buf_release, }; static struct vfsmount *dma_buf_mnt; static int dma_buf_fs_init_context(struct fs_context *fc) { struct pseudo_fs_context *ctx; ctx = init_pseudo(fc, DMA_BUF_MAGIC); if (!ctx) return -ENOMEM; ctx->dops = &dma_buf_dentry_ops; return 0; } static struct file_system_type dma_buf_fs_type = { .name = "dmabuf", .init_fs_context = dma_buf_fs_init_context, .kill_sb = kill_anon_super, }; static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma) { struct dma_buf *dmabuf; if (!is_dma_buf_file(file)) return -EINVAL; dmabuf = file->private_data; /* check if buffer supports mmap */ if (!dmabuf->ops->mmap) return -EINVAL; /* check for overflowing the buffer's size */ if (vma->vm_pgoff + vma_pages(vma) > dmabuf->size >> PAGE_SHIFT) return -EINVAL; DMA_BUF_TRACE(trace_dma_buf_mmap_internal, dmabuf); return dmabuf->ops->mmap(dmabuf, vma); } static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) { struct dma_buf *dmabuf; loff_t base; if (!is_dma_buf_file(file)) return -EBADF; dmabuf = file->private_data; /* only support discovering the end of the buffer, * but also allow SEEK_SET to maintain the idiomatic * SEEK_END(0), SEEK_CUR(0) pattern. */ if (whence == SEEK_END) base = dmabuf->size; else if (whence == SEEK_SET) base = 0; else return -EINVAL; if (offset != 0) return -EINVAL; return base + offset; } /** * DOC: implicit fence polling * * To support cross-device and cross-driver synchronization of buffer access * implicit fences (represented internally in the kernel with &struct dma_fence) * can be attached to a &dma_buf. The glue for that and a few related things are * provided in the &dma_resv structure. * * Userspace can query the state of these implicitly tracked fences using poll() * and related system calls: * * - Checking for EPOLLIN, i.e. read access, can be use to query the state of the * most recent write or exclusive fence. * * - Checking for EPOLLOUT, i.e. write access, can be used to query the state of * all attached fences, shared and exclusive ones. * * Note that this only signals the completion of the respective fences, i.e. the * DMA transfers are complete. Cache flushing and any other necessary * preparations before CPU access can begin still need to happen. * * As an alternative to poll(), the set of fences on DMA buffer can be * exported as a &sync_file using &dma_buf_sync_file_export. */ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) { struct dma_buf_poll_cb_t *dcb = (struct dma_buf_poll_cb_t *)cb; struct dma_buf *dmabuf = container_of(dcb->poll, struct dma_buf, poll); unsigned long flags; spin_lock_irqsave(&dcb->poll->lock, flags); wake_up_locked_poll(dcb->poll, dcb->active); dcb->active = 0; spin_unlock_irqrestore(&dcb->poll->lock, flags); dma_fence_put(fence); /* Paired with get_file in dma_buf_poll */ fput(dmabuf->file); } static bool dma_buf_poll_add_cb(struct dma_resv *resv, bool write, struct dma_buf_poll_cb_t *dcb) { struct dma_resv_iter cursor; struct dma_fence *fence; int r; dma_resv_for_each_fence(&cursor, resv, dma_resv_usage_rw(write), fence) { dma_fence_get(fence); r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb); if (!r) return true; dma_fence_put(fence); } return false; } static __poll_t dma_buf_poll(struct file *file, poll_table *poll) { struct dma_buf *dmabuf; struct dma_resv *resv; __poll_t events; dmabuf = file->private_data; if (!dmabuf || !dmabuf->resv) return EPOLLERR; resv = dmabuf->resv; poll_wait(file, &dmabuf->poll, poll); events = poll_requested_events(poll) & (EPOLLIN | EPOLLOUT); if (!events) return 0; dma_resv_lock(resv, NULL); if (events & EPOLLOUT) { struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_out; /* Check that callback isn't busy */ spin_lock_irq(&dmabuf->poll.lock); if (dcb->active) events &= ~EPOLLOUT; else dcb->active = EPOLLOUT; spin_unlock_irq(&dmabuf->poll.lock); if (events & EPOLLOUT) { /* Paired with fput in dma_buf_poll_cb */ get_file(dmabuf->file); if (!dma_buf_poll_add_cb(resv, true, dcb)) /* No callback queued, wake up any other waiters */ dma_buf_poll_cb(NULL, &dcb->cb); else events &= ~EPOLLOUT; } } if (events & EPOLLIN) { struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_in; /* Check that callback isn't busy */ spin_lock_irq(&dmabuf->poll.lock); if (dcb->active) events &= ~EPOLLIN; else dcb->active = EPOLLIN; spin_unlock_irq(&dmabuf->poll.lock); if (events & EPOLLIN) { /* Paired with fput in dma_buf_poll_cb */ get_file(dmabuf->file); if (!dma_buf_poll_add_cb(resv, false, dcb)) /* No callback queued, wake up any other waiters */ dma_buf_poll_cb(NULL, &dcb->cb); else events &= ~EPOLLIN; } } dma_resv_unlock(resv); return events; } /** * dma_buf_set_name - Set a name to a specific dma_buf to track the usage. * It could support changing the name of the dma-buf if the same * piece of memory is used for multiple purpose between different devices. * * @dmabuf: [in] dmabuf buffer that will be renamed. * @buf: [in] A piece of userspace memory that contains the name of * the dma-buf. * * Returns 0 on success. If the dma-buf buffer is already attached to * devices, return -EBUSY. * */ static long dma_buf_set_name(struct dma_buf *dmabuf, const char __user *buf) { char *name = strndup_user(buf, DMA_BUF_NAME_LEN); if (IS_ERR(name)) return PTR_ERR(name); spin_lock(&dmabuf->name_lock); kfree(dmabuf->name); dmabuf->name = name; spin_unlock(&dmabuf->name_lock); return 0; } #if IS_ENABLED(CONFIG_SYNC_FILE) static long dma_buf_export_sync_file(struct dma_buf *dmabuf, void __user *user_data) { struct dma_buf_export_sync_file arg; enum dma_resv_usage usage; struct dma_fence *fence = NULL; struct sync_file *sync_file; int fd, ret; if (copy_from_user(&arg, user_data, sizeof(arg))) return -EFAULT; if (arg.flags & ~DMA_BUF_SYNC_RW) return -EINVAL; if ((arg.flags & DMA_BUF_SYNC_RW) == 0) return -EINVAL; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; usage = dma_resv_usage_rw(arg.flags & DMA_BUF_SYNC_WRITE); ret = dma_resv_get_singleton(dmabuf->resv, usage, &fence); if (ret) goto err_put_fd; if (!fence) fence = dma_fence_get_stub(); sync_file = sync_file_create(fence); dma_fence_put(fence); if (!sync_file) { ret = -ENOMEM; goto err_put_fd; } arg.fd = fd; if (copy_to_user(user_data, &arg, sizeof(arg))) { ret = -EFAULT; goto err_put_file; } fd_install(fd, sync_file->file); return 0; err_put_file: fput(sync_file->file); err_put_fd: put_unused_fd(fd); return ret; } static long dma_buf_import_sync_file(struct dma_buf *dmabuf, const void __user *user_data) { struct dma_buf_import_sync_file arg; struct dma_fence *fence, *f; enum dma_resv_usage usage; struct dma_fence_unwrap iter; unsigned int num_fences; int ret = 0; if (copy_from_user(&arg, user_data, sizeof(arg))) return -EFAULT; if (arg.flags & ~DMA_BUF_SYNC_RW) return -EINVAL; if ((arg.flags & DMA_BUF_SYNC_RW) == 0) return -EINVAL; fence = sync_file_get_fence(arg.fd); if (!fence) return -EINVAL; usage = (arg.flags & DMA_BUF_SYNC_WRITE) ? DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ; num_fences = 0; dma_fence_unwrap_for_each(f, &iter, fence) ++num_fences; if (num_fences > 0) { dma_resv_lock(dmabuf->resv, NULL); ret = dma_resv_reserve_fences(dmabuf->resv, num_fences); if (!ret) { dma_fence_unwrap_for_each(f, &iter, fence) dma_resv_add_fence(dmabuf->resv, f, usage); } dma_resv_unlock(dmabuf->resv); } dma_fence_put(fence); return ret; } #endif static long dma_buf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct dma_buf *dmabuf; struct dma_buf_sync sync; enum dma_data_direction direction; int ret; dmabuf = file->private_data; switch (cmd) { case DMA_BUF_IOCTL_SYNC: if (copy_from_user(&sync, (void __user *) arg, sizeof(sync))) return -EFAULT; if (sync.flags & ~DMA_BUF_SYNC_VALID_FLAGS_MASK) return -EINVAL; switch (sync.flags & DMA_BUF_SYNC_RW) { case DMA_BUF_SYNC_READ: direction = DMA_FROM_DEVICE; break; case DMA_BUF_SYNC_WRITE: direction = DMA_TO_DEVICE; break; case DMA_BUF_SYNC_RW: direction = DMA_BIDIRECTIONAL; break; default: return -EINVAL; } if (sync.flags & DMA_BUF_SYNC_END) ret = dma_buf_end_cpu_access(dmabuf, direction); else ret = dma_buf_begin_cpu_access(dmabuf, direction); return ret; case DMA_BUF_SET_NAME_A: case DMA_BUF_SET_NAME_B: return dma_buf_set_name(dmabuf, (const char __user *)arg); #if IS_ENABLED(CONFIG_SYNC_FILE) case DMA_BUF_IOCTL_EXPORT_SYNC_FILE: return dma_buf_export_sync_file(dmabuf, (void __user *)arg); case DMA_BUF_IOCTL_IMPORT_SYNC_FILE: return dma_buf_import_sync_file(dmabuf, (const void __user *)arg); #endif default: return -ENOTTY; } } static void dma_buf_show_fdinfo(struct seq_file *m, struct file *file) { struct dma_buf *dmabuf = file->private_data; seq_printf(m, "size:\t%zu\n", dmabuf->size); /* Don't count the temporary reference taken inside procfs seq_show */ seq_printf(m, "count:\t%ld\n", file_count(dmabuf->file) - 1); seq_printf(m, "exp_name:\t%s\n", dmabuf->exp_name); spin_lock(&dmabuf->name_lock); if (dmabuf->name) seq_printf(m, "name:\t%s\n", dmabuf->name); spin_unlock(&dmabuf->name_lock); } static const struct file_operations dma_buf_fops = { .release = dma_buf_file_release, .mmap = dma_buf_mmap_internal, .llseek = dma_buf_llseek, .poll = dma_buf_poll, .unlocked_ioctl = dma_buf_ioctl, .compat_ioctl = compat_ptr_ioctl, .show_fdinfo = dma_buf_show_fdinfo, }; /* * is_dma_buf_file - Check if struct file* is associated with dma_buf */ static inline int is_dma_buf_file(struct file *file) { return file->f_op == &dma_buf_fops; } static struct file *dma_buf_getfile(size_t size, int flags) { static atomic64_t dmabuf_inode = ATOMIC64_INIT(0); struct inode *inode = alloc_anon_inode(dma_buf_mnt->mnt_sb); struct file *file; if (IS_ERR(inode)) return ERR_CAST(inode); inode->i_size = size; inode_set_bytes(inode, size); /* * The ->i_ino acquired from get_next_ino() is not unique thus * not suitable for using it as dentry name by dmabuf stats. * Override ->i_ino with the unique and dmabuffs specific * value. */ inode->i_ino = atomic64_inc_return(&dmabuf_inode); flags &= O_ACCMODE | O_NONBLOCK; file = alloc_file_pseudo(inode, dma_buf_mnt, "dmabuf", flags, &dma_buf_fops); if (IS_ERR(file)) goto err_alloc_file; return file; err_alloc_file: iput(inode); return file; } /** * DOC: dma buf device access * * For device DMA access to a shared DMA buffer the usual sequence of operations * is fairly simple: * * 1. The exporter defines his exporter instance using * DEFINE_DMA_BUF_EXPORT_INFO() and calls dma_buf_export() to wrap a private * buffer object into a &dma_buf. It then exports that &dma_buf to userspace * as a file descriptor by calling dma_buf_fd(). * * 2. Userspace passes this file-descriptors to all drivers it wants this buffer * to share with: First the file descriptor is converted to a &dma_buf using * dma_buf_get(). Then the buffer is attached to the device using * dma_buf_attach(). * * Up to this stage the exporter is still free to migrate or reallocate the * backing storage. * * 3. Once the buffer is attached to all devices userspace can initiate DMA * access to the shared buffer. In the kernel this is done by calling * dma_buf_map_attachment() and dma_buf_unmap_attachment(). * * 4. Once a driver is done with a shared buffer it needs to call * dma_buf_detach() (after cleaning up any mappings) and then release the * reference acquired with dma_buf_get() by calling dma_buf_put(). * * For the detailed semantics exporters are expected to implement see * &dma_buf_ops. */ /** * dma_buf_export - Creates a new dma_buf, and associates an anon file * with this buffer, so it can be exported. * Also connect the allocator specific data and ops to the buffer. * Additionally, provide a name string for exporter; useful in debugging. * * @exp_info: [in] holds all the export related information provided * by the exporter. see &struct dma_buf_export_info * for further details. * * Returns, on success, a newly created struct dma_buf object, which wraps the * supplied private data and operations for struct dma_buf_ops. On either * missing ops, or error in allocating struct dma_buf, will return negative * error. * * For most cases the easiest way to create @exp_info is through the * %DEFINE_DMA_BUF_EXPORT_INFO macro. */ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) { struct dma_buf *dmabuf; struct dma_resv *resv = exp_info->resv; struct file *file; size_t alloc_size = sizeof(struct dma_buf); int ret; if (WARN_ON(!exp_info->priv || !exp_info->ops || !exp_info->ops->map_dma_buf || !exp_info->ops->unmap_dma_buf || !exp_info->ops->release)) return ERR_PTR(-EINVAL); if (WARN_ON(!exp_info->ops->pin != !exp_info->ops->unpin)) return ERR_PTR(-EINVAL); if (!try_module_get(exp_info->owner)) return ERR_PTR(-ENOENT); file = dma_buf_getfile(exp_info->size, exp_info->flags); if (IS_ERR(file)) { ret = PTR_ERR(file); goto err_module; } if (!exp_info->resv) alloc_size += sizeof(struct dma_resv); else /* prevent &dma_buf[1] == dma_buf->resv */ alloc_size += 1; dmabuf = kzalloc(alloc_size, GFP_KERNEL); if (!dmabuf) { ret = -ENOMEM; goto err_file; } dmabuf->priv = exp_info->priv; dmabuf->ops = exp_info->ops; dmabuf->size = exp_info->size; dmabuf->exp_name = exp_info->exp_name; dmabuf->owner = exp_info->owner; spin_lock_init(&dmabuf->name_lock); init_waitqueue_head(&dmabuf->poll); dmabuf->cb_in.poll = dmabuf->cb_out.poll = &dmabuf->poll; dmabuf->cb_in.active = dmabuf->cb_out.active = 0; INIT_LIST_HEAD(&dmabuf->attachments); if (!resv) { dmabuf->resv = (struct dma_resv *)&dmabuf[1]; dma_resv_init(dmabuf->resv); } else { dmabuf->resv = resv; } file->private_data = dmabuf; file->f_path.dentry->d_fsdata = dmabuf; dmabuf->file = file; __dma_buf_list_add(dmabuf); DMA_BUF_TRACE(trace_dma_buf_export, dmabuf); return dmabuf; err_file: fput(file); err_module: module_put(exp_info->owner); return ERR_PTR(ret); } EXPORT_SYMBOL_NS_GPL(dma_buf_export, "DMA_BUF"); /** * dma_buf_fd - returns a file descriptor for the given struct dma_buf * @dmabuf: [in] pointer to dma_buf for which fd is required. * @flags: [in] flags to give to fd * * On success, returns an associated 'fd'. Else, returns error. */ int dma_buf_fd(struct dma_buf *dmabuf, int flags) { int fd; if (!dmabuf || !dmabuf->file) return -EINVAL; fd = FD_ADD(flags, dmabuf->file); DMA_BUF_TRACE(trace_dma_buf_fd, dmabuf, fd); return fd; } EXPORT_SYMBOL_NS_GPL(dma_buf_fd, "DMA_BUF"); /** * dma_buf_get - returns the struct dma_buf related to an fd * @fd: [in] fd associated with the struct dma_buf to be returned * * On success, returns the struct dma_buf associated with an fd; uses * file's refcounting done by fget to increase refcount. returns ERR_PTR * otherwise. */ struct dma_buf *dma_buf_get(int fd) { struct file *file; struct dma_buf *dmabuf; file = fget(fd); if (!file) return ERR_PTR(-EBADF); if (!is_dma_buf_file(file)) { fput(file); return ERR_PTR(-EINVAL); } dmabuf = file->private_data; DMA_BUF_TRACE(trace_dma_buf_get, dmabuf, fd); return dmabuf; } EXPORT_SYMBOL_NS_GPL(dma_buf_get, "DMA_BUF"); /** * dma_buf_put - decreases refcount of the buffer * @dmabuf: [in] buffer to reduce refcount of * * Uses file's refcounting done implicitly by fput(). * * If, as a result of this call, the refcount becomes 0, the 'release' file * operation related to this fd is called. It calls &dma_buf_ops.release vfunc * in turn, and frees the memory allocated for dmabuf when exported. */ void dma_buf_put(struct dma_buf *dmabuf) { if (WARN_ON(!dmabuf || !dmabuf->file)) return; DMA_BUF_TRACE(trace_dma_buf_put, dmabuf); fput(dmabuf->file); } EXPORT_SYMBOL_NS_GPL(dma_buf_put, "DMA_BUF"); static int dma_buf_wrap_sg_table(struct sg_table **sg_table) { struct scatterlist *to_sg, *from_sg; struct sg_table *from = *sg_table; struct dma_buf_sg_table_wrapper *to; int i, ret; if (!IS_ENABLED(CONFIG_DMABUF_DEBUG)) return 0; /* * To catch abuse of the underlying struct page by importers copy the * sg_table without copying the page_link and give only the copy back to * the importer. */ to = kzalloc_obj(*to); if (!to) return -ENOMEM; ret = sg_alloc_table(&to->wrapper, from->nents, GFP_KERNEL); if (ret) goto free_to; to_sg = to->wrapper.sgl; for_each_sgtable_dma_sg(from, from_sg, i) { to_sg->offset = 0; to_sg->length = 0; sg_assign_page(to_sg, NULL); sg_dma_address(to_sg) = sg_dma_address(from_sg); sg_dma_len(to_sg) = sg_dma_len(from_sg); to_sg = sg_next(to_sg); } to->original = from; *sg_table = &to->wrapper; return 0; free_to: kfree(to); return ret; } static void dma_buf_unwrap_sg_table(struct sg_table **sg_table) { struct dma_buf_sg_table_wrapper *copy; if (!IS_ENABLED(CONFIG_DMABUF_DEBUG)) return; copy = container_of(*sg_table, typeof(*copy), wrapper); *sg_table = copy->original; sg_free_table(©->wrapper); kfree(copy); } static inline bool dma_buf_attachment_is_dynamic(struct dma_buf_attachment *attach) { return !!attach->importer_ops; } static bool dma_buf_pin_on_map(struct dma_buf_attachment *attach) { return attach->dmabuf->ops->pin && !dma_buf_attachment_is_dynamic(attach); } /** * DOC: locking convention * * In order to avoid deadlock situations between dma-buf exports and importers, * all dma-buf API users must follow the common dma-buf locking convention. * * Convention for importers * * 1. Importers must hold the dma-buf reservation lock when calling these * functions: * * - dma_buf_pin() * - dma_buf_unpin() * - dma_buf_map_attachment() * - dma_buf_unmap_attachment() * - dma_buf_vmap() * - dma_buf_vunmap() * * 2. Importers must not hold the dma-buf reservation lock when calling these * functions: * * - dma_buf_attach() * - dma_buf_dynamic_attach() * - dma_buf_detach() * - dma_buf_export() * - dma_buf_fd() * - dma_buf_get() * - dma_buf_put() * - dma_buf_mmap() * - dma_buf_begin_cpu_access() * - dma_buf_end_cpu_access() * - dma_buf_map_attachment_unlocked() * - dma_buf_unmap_attachment_unlocked() * - dma_buf_vmap_unlocked() * - dma_buf_vunmap_unlocked() * * Convention for exporters * * 1. These &dma_buf_ops callbacks are invoked with unlocked dma-buf * reservation and exporter can take the lock: * * - &dma_buf_ops.attach() * - &dma_buf_ops.detach() * - &dma_buf_ops.release() * - &dma_buf_ops.begin_cpu_access() * - &dma_buf_ops.end_cpu_access() * - &dma_buf_ops.mmap() * * 2. These &dma_buf_ops callbacks are invoked with locked dma-buf * reservation and exporter can't take the lock: * * - &dma_buf_ops.pin() * - &dma_buf_ops.unpin() * - &dma_buf_ops.map_dma_buf() * - &dma_buf_ops.unmap_dma_buf() * - &dma_buf_ops.vmap() * - &dma_buf_ops.vunmap() * * 3. Exporters must hold the dma-buf reservation lock when calling these * functions: * * - dma_buf_invalidate_mappings() */ /** * dma_buf_dynamic_attach - Add the device to dma_buf's attachments list * @dmabuf: [in] buffer to attach device to. * @dev: [in] device to be attached. * @importer_ops: [in] importer operations for the attachment * @importer_priv: [in] importer private pointer for the attachment * * Returns struct dma_buf_attachment pointer for this attachment. Attachments * must be cleaned up by calling dma_buf_detach(). * * Optionally this calls &dma_buf_ops.attach to allow device-specific attach * functionality. * * Returns: * * A pointer to newly created &dma_buf_attachment on success, or a negative * error code wrapped into a pointer on failure. * * Note that this can fail if the backing storage of @dmabuf is in a place not * accessible to @dev, and cannot be moved to a more suitable place. This is * indicated with the error code -EBUSY. */ struct dma_buf_attachment * dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, const struct dma_buf_attach_ops *importer_ops, void *importer_priv) { struct dma_buf_attachment *attach; int ret; if (WARN_ON(!dmabuf || !dev)) return ERR_PTR(-EINVAL); attach = kzalloc_obj(*attach); if (!attach) return ERR_PTR(-ENOMEM); attach->dev = dev; attach->dmabuf = dmabuf; if (importer_ops) attach->peer2peer = importer_ops->allow_peer2peer; attach->importer_ops = importer_ops; attach->importer_priv = importer_priv; if (dmabuf->ops->attach) { ret = dmabuf->ops->attach(dmabuf, attach); if (ret) goto err_attach; } dma_resv_lock(dmabuf->resv, NULL); list_add(&attach->node, &dmabuf->attachments); dma_resv_unlock(dmabuf->resv); DMA_BUF_TRACE(trace_dma_buf_dynamic_attach, dmabuf, attach, dma_buf_attachment_is_dynamic(attach), dev); return attach; err_attach: kfree(attach); return ERR_PTR(ret); } EXPORT_SYMBOL_NS_GPL(dma_buf_dynamic_attach, "DMA_BUF"); /** * dma_buf_attach - Wrapper for dma_buf_dynamic_attach * @dmabuf: [in] buffer to attach device to. * @dev: [in] device to be attached. * * Wrapper to call dma_buf_dynamic_attach() for drivers which still use a static * mapping. */ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, struct device *dev) { return dma_buf_dynamic_attach(dmabuf, dev, NULL, NULL); } EXPORT_SYMBOL_NS_GPL(dma_buf_attach, "DMA_BUF"); /** * dma_buf_detach - Remove the given attachment from dmabuf's attachments list * @dmabuf: [in] buffer to detach from. * @attach: [in] attachment to be detached; is free'd after this call. * * Clean up a device attachment obtained by calling dma_buf_attach(). * * Optionally this calls &dma_buf_ops.detach for device-specific detach. */ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) { if (WARN_ON(!dmabuf || !attach || dmabuf != attach->dmabuf)) return; dma_resv_lock(dmabuf->resv, NULL); list_del(&attach->node); dma_resv_unlock(dmabuf->resv); if (dmabuf->ops->detach) dmabuf->ops->detach(dmabuf, attach); DMA_BUF_TRACE(trace_dma_buf_detach, dmabuf, attach, dma_buf_attachment_is_dynamic(attach), attach->dev); kfree(attach); } EXPORT_SYMBOL_NS_GPL(dma_buf_detach, "DMA_BUF"); /** * dma_buf_pin - Lock down the DMA-buf * @attach: [in] attachment which should be pinned * * Only dynamic importers (who set up @attach with dma_buf_dynamic_attach()) may * call this, and only for limited use cases like scanout and not for temporary * pin operations. It is not permitted to allow userspace to pin arbitrary * amounts of buffers through this interface. * * Buffers must be unpinned by calling dma_buf_unpin(). * * Returns: * 0 on success, negative error code on failure. */ int dma_buf_pin(struct dma_buf_attachment *attach) { struct dma_buf *dmabuf = attach->dmabuf; int ret = 0; WARN_ON(!attach->importer_ops); dma_resv_assert_held(dmabuf->resv); if (dmabuf->ops->pin) ret = dmabuf->ops->pin(attach); return ret; } EXPORT_SYMBOL_NS_GPL(dma_buf_pin, "DMA_BUF"); /** * dma_buf_unpin - Unpin a DMA-buf * @attach: [in] attachment which should be unpinned * * This unpins a buffer pinned by dma_buf_pin() and allows the exporter to move * any mapping of @attach again and inform the importer through * &dma_buf_attach_ops.invalidate_mappings. */ void dma_buf_unpin(struct dma_buf_attachment *attach) { struct dma_buf *dmabuf = attach->dmabuf; WARN_ON(!attach->importer_ops); dma_resv_assert_held(dmabuf->resv); if (dmabuf->ops->unpin) dmabuf->ops->unpin(attach); } EXPORT_SYMBOL_NS_GPL(dma_buf_unpin, "DMA_BUF"); /** * dma_buf_map_attachment - Returns the scatterlist table of the attachment; * mapped into _device_ address space. Is a wrapper for map_dma_buf() of the * dma_buf_ops. * @attach: [in] attachment whose scatterlist is to be returned * @direction: [in] direction of DMA transfer * * Returns sg_table containing the scatterlist to be returned; returns ERR_PTR * on error. May return -EINTR if it is interrupted by a signal. * * On success, the DMA addresses and lengths in the returned scatterlist are * PAGE_SIZE aligned. * * A mapping must be unmapped by using dma_buf_unmap_attachment(). Note that * the underlying backing storage is pinned for as long as a mapping exists, * therefore users/importers should not hold onto a mapping for undue amounts of * time. * * Important: Dynamic importers must wait for the exclusive fence of the struct * dma_resv attached to the DMA-BUF first. */ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, enum dma_data_direction direction) { struct sg_table *sg_table; signed long ret; might_sleep(); if (WARN_ON(!attach || !attach->dmabuf)) return ERR_PTR(-EINVAL); dma_resv_assert_held(attach->dmabuf->resv); if (dma_buf_pin_on_map(attach)) { ret = attach->dmabuf->ops->pin(attach); /* * Catch exporters making buffers inaccessible even when * attachments preventing that exist. */ WARN_ON_ONCE(ret == -EBUSY); if (ret) return ERR_PTR(ret); } sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); if (!sg_table) sg_table = ERR_PTR(-ENOMEM); if (IS_ERR(sg_table)) goto error_unpin; /* * Importers with static attachments don't wait for fences. */ if (!dma_buf_attachment_is_dynamic(attach)) { ret = dma_resv_wait_timeout(attach->dmabuf->resv, DMA_RESV_USAGE_KERNEL, true, MAX_SCHEDULE_TIMEOUT); if (ret < 0) goto error_unmap; } ret = dma_buf_wrap_sg_table(&sg_table); if (ret) goto error_unmap; if (IS_ENABLED(CONFIG_DMA_API_DEBUG)) { struct scatterlist *sg; u64 addr; int len; int i; for_each_sgtable_dma_sg(sg_table, sg, i) { addr = sg_dma_address(sg); len = sg_dma_len(sg); if (!PAGE_ALIGNED(addr) || !PAGE_ALIGNED(len)) { pr_debug("%s: addr %llx or len %x is not page aligned!\n", __func__, addr, len); break; } } } return sg_table; error_unmap: attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction); sg_table = ERR_PTR(ret); error_unpin: if (dma_buf_pin_on_map(attach)) attach->dmabuf->ops->unpin(attach); return sg_table; } EXPORT_SYMBOL_NS_GPL(dma_buf_map_attachment, "DMA_BUF"); /** * dma_buf_map_attachment_unlocked - Returns the scatterlist table of the attachment; * mapped into _device_ address space. Is a wrapper for map_dma_buf() of the * dma_buf_ops. * @attach: [in] attachment whose scatterlist is to be returned * @direction: [in] direction of DMA transfer * * Unlocked variant of dma_buf_map_attachment(). */ struct sg_table * dma_buf_map_attachment_unlocked(struct dma_buf_attachment *attach, enum dma_data_direction direction) { struct sg_table *sg_table; might_sleep(); if (WARN_ON(!attach || !attach->dmabuf)) return ERR_PTR(-EINVAL); dma_resv_lock(attach->dmabuf->resv, NULL); sg_table = dma_buf_map_attachment(attach, direction); dma_resv_unlock(attach->dmabuf->resv); return sg_table; } EXPORT_SYMBOL_NS_GPL(dma_buf_map_attachment_unlocked, "DMA_BUF"); /** * dma_buf_unmap_attachment - unmaps and decreases usecount of the buffer;might * deallocate the scatterlist associated. Is a wrapper for unmap_dma_buf() of * dma_buf_ops. * @attach: [in] attachment to unmap buffer from * @sg_table: [in] scatterlist info of the buffer to unmap * @direction: [in] direction of DMA transfer * * This unmaps a DMA mapping for @attached obtained by dma_buf_map_attachment(). */ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, struct sg_table *sg_table, enum dma_data_direction direction) { might_sleep(); if (WARN_ON(!attach || !attach->dmabuf || !sg_table)) return; dma_resv_assert_held(attach->dmabuf->resv); dma_buf_unwrap_sg_table(&sg_table); attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction); if (dma_buf_pin_on_map(attach)) attach->dmabuf->ops->unpin(attach); } EXPORT_SYMBOL_NS_GPL(dma_buf_unmap_attachment, "DMA_BUF"); /** * dma_buf_unmap_attachment_unlocked - unmaps and decreases usecount of the buffer;might * deallocate the scatterlist associated. Is a wrapper for unmap_dma_buf() of * dma_buf_ops. * @attach: [in] attachment to unmap buffer from * @sg_table: [in] scatterlist info of the buffer to unmap * @direction: [in] direction of DMA transfer * * Unlocked variant of dma_buf_unmap_attachment(). */ void dma_buf_unmap_attachment_unlocked(struct dma_buf_attachment *attach, struct sg_table *sg_table, enum dma_data_direction direction) { might_sleep(); if (WARN_ON(!attach || !attach->dmabuf || !sg_table)) return; dma_resv_lock(attach->dmabuf->resv, NULL); dma_buf_unmap_attachment(attach, sg_table, direction); dma_resv_unlock(attach->dmabuf->resv); } EXPORT_SYMBOL_NS_GPL(dma_buf_unmap_attachment_unlocked, "DMA_BUF"); /** * dma_buf_attach_revocable - check if a DMA-buf importer implements * revoke semantics. * @attach: the DMA-buf attachment to check * * Returns true if the DMA-buf importer can support the revoke sequence * explained in dma_buf_invalidate_mappings() within bounded time. Meaning the * importer implements invalidate_mappings() and ensures that unmap is called as * a result. */ bool dma_buf_attach_revocable(struct dma_buf_attachment *attach) { return attach->importer_ops && attach->importer_ops->invalidate_mappings; } EXPORT_SYMBOL_NS_GPL(dma_buf_attach_revocable, "DMA_BUF"); /** * dma_buf_invalidate_mappings - notify attachments that DMA-buf is moving * * @dmabuf: [in] buffer which is moving * * Informs all attachments that they need to destroy and recreate all their * mappings. If the attachment is dynamic then the dynamic importer is expected * to invalidate any caches it has of the mapping result and perform a new * mapping request before allowing HW to do any further DMA. * * If the attachment is pinned then this informs the pinned importer that the * underlying mapping is no longer available. Pinned importers may take this is * as a permanent revocation and never establish new mappings so exporters * should not trigger it lightly. * * Upon return importers may continue to access the DMA-buf memory. The caller * must do two additional waits to ensure that the memory is no longer being * accessed: * * 1) Until dma_resv_wait_timeout() retires fences the importer is allowed to * fully access the memory. * 2) Until the importer calls unmap it is allowed to speculatively * read-and-discard the memory. It must not write to the memory. * * A caller wishing to use dma_buf_invalidate_mappings() to fully stop access to * the DMA-buf must wait for both. Dynamic callers can often use just the first. * * All importers providing a invalidate_mappings() op must ensure that unmap is * called within bounded time after the op. * * Pinned importers that do not support a invalidate_mappings() op will * eventually perform unmap when they are done with the buffer, which may be an * ubounded time from calling this function. dma_buf_attach_revocable() can be * used to prevent such importers from attaching. * * Importers are free to request a new mapping in parallel as this function * returns. */ void dma_buf_invalidate_mappings(struct dma_buf *dmabuf) { struct dma_buf_attachment *attach; dma_resv_assert_held(dmabuf->resv); list_for_each_entry(attach, &dmabuf->attachments, node) if (attach->importer_ops && attach->importer_ops->invalidate_mappings) attach->importer_ops->invalidate_mappings(attach); } EXPORT_SYMBOL_NS_GPL(dma_buf_invalidate_mappings, "DMA_BUF"); /** * DOC: cpu access * * There are multiple reasons for supporting CPU access to a dma buffer object: * * - Fallback operations in the kernel, for example when a device is connected * over USB and the kernel needs to shuffle the data around first before * sending it away. Cache coherency is handled by bracketing any transactions * with calls to dma_buf_begin_cpu_access() and dma_buf_end_cpu_access() * access. * * Since for most kernel internal dma-buf accesses need the entire buffer, a * vmap interface is introduced. Note that on very old 32-bit architectures * vmalloc space might be limited and result in vmap calls failing. * * Interfaces: * * .. code-block:: c * * void *dma_buf_vmap(struct dma_buf *dmabuf, struct iosys_map *map) * void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map) * * The vmap call can fail if there is no vmap support in the exporter, or if * it runs out of vmalloc space. Note that the dma-buf layer keeps a reference * count for all vmap access and calls down into the exporter's vmap function * only when no vmapping exists, and only unmaps it once. Protection against * concurrent vmap/vunmap calls is provided by taking the &dma_buf.lock mutex. * * - For full compatibility on the importer side with existing userspace * interfaces, which might already support mmap'ing buffers. This is needed in * many processing pipelines (e.g. feeding a software rendered image into a * hardware pipeline, thumbnail creation, snapshots, ...). Also, Android's ION * framework already supported this and for DMA buffer file descriptors to * replace ION buffers mmap support was needed. * * There is no special interfaces, userspace simply calls mmap on the dma-buf * fd. But like for CPU access there's a need to bracket the actual access, * which is handled by the ioctl (DMA_BUF_IOCTL_SYNC). Note that * DMA_BUF_IOCTL_SYNC can fail with -EAGAIN or -EINTR, in which case it must * be restarted. * * Some systems might need some sort of cache coherency management e.g. when * CPU and GPU domains are being accessed through dma-buf at the same time. * To circumvent this problem there are begin/end coherency markers, that * forward directly to existing dma-buf device drivers vfunc hooks. Userspace * can make use of those markers through the DMA_BUF_IOCTL_SYNC ioctl. The * sequence would be used like following: * * - mmap dma-buf fd * - for each drawing/upload cycle in CPU 1. SYNC_START ioctl, 2. read/write * to mmap area 3. SYNC_END ioctl. This can be repeated as often as you * want (with the new data being consumed by say the GPU or the scanout * device) * - munmap once you don't need the buffer any more * * For correctness and optimal performance, it is always required to use * SYNC_START and SYNC_END before and after, respectively, when accessing the * mapped address. Userspace cannot rely on coherent access, even when there * are systems where it just works without calling these ioctls. * * - And as a CPU fallback in userspace processing pipelines. * * Similar to the motivation for kernel cpu access it is again important that * the userspace code of a given importing subsystem can use the same * interfaces with a imported dma-buf buffer object as with a native buffer * object. This is especially important for drm where the userspace part of * contemporary OpenGL, X, and other drivers is huge, and reworking them to * use a different way to mmap a buffer rather invasive. * * The assumption in the current dma-buf interfaces is that redirecting the * initial mmap is all that's needed. A survey of some of the existing * subsystems shows that no driver seems to do any nefarious thing like * syncing up with outstanding asynchronous processing on the device or * allocating special resources at fault time. So hopefully this is good * enough, since adding interfaces to intercept pagefaults and allow pte * shootdowns would increase the complexity quite a bit. * * Interface: * * .. code-block:: c * * int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, unsigned long); * * If the importing subsystem simply provides a special-purpose mmap call to * set up a mapping in userspace, calling do_mmap with &dma_buf.file will * equally achieve that for a dma-buf object. */ static int __dma_buf_begin_cpu_access(struct dma_buf *dmabuf, enum dma_data_direction direction) { bool write = (direction == DMA_BIDIRECTIONAL || direction == DMA_TO_DEVICE); struct dma_resv *resv = dmabuf->resv; long ret; /* Wait on any implicit rendering fences */ ret = dma_resv_wait_timeout(resv, dma_resv_usage_rw(write), true, MAX_SCHEDULE_TIMEOUT); if (ret < 0) return ret; return 0; } /** * dma_buf_begin_cpu_access - Must be called before accessing a dma_buf from the * cpu in the kernel context. Calls begin_cpu_access to allow exporter-specific * preparations. Coherency is only guaranteed in the specified range for the * specified access direction. * @dmabuf: [in] buffer to prepare cpu access for. * @direction: [in] direction of access. * * After the cpu access is complete the caller should call * dma_buf_end_cpu_access(). Only when cpu access is bracketed by both calls is * it guaranteed to be coherent with other DMA access. * * This function will also wait for any DMA transactions tracked through * implicit synchronization in &dma_buf.resv. For DMA transactions with explicit * synchronization this function will only ensure cache coherency, callers must * ensure synchronization with such DMA transactions on their own. * * Can return negative error values, returns 0 on success. */ int dma_buf_begin_cpu_access(struct dma_buf *dmabuf, enum dma_data_direction direction) { int ret = 0; if (WARN_ON(!dmabuf)) return -EINVAL; might_lock(&dmabuf->resv->lock.base); if (dmabuf->ops->begin_cpu_access) ret = dmabuf->ops->begin_cpu_access(dmabuf, direction); /* Ensure that all fences are waited upon - but we first allow * the native handler the chance to do so more efficiently if it * chooses. A double invocation here will be reasonably cheap no-op. */ if (ret == 0) ret = __dma_buf_begin_cpu_access(dmabuf, direction); return ret; } EXPORT_SYMBOL_NS_GPL(dma_buf_begin_cpu_access, "DMA_BUF"); /** * dma_buf_end_cpu_access - Must be called after accessing a dma_buf from the * cpu in the kernel context. Calls end_cpu_access to allow exporter-specific * actions. Coherency is only guaranteed in the specified range for the * specified access direction. * @dmabuf: [in] buffer to complete cpu access for. * @direction: [in] direction of access. * * This terminates CPU access started with dma_buf_begin_cpu_access(). * * Can return negative error values, returns 0 on success. */ int dma_buf_end_cpu_access(struct dma_buf *dmabuf, enum dma_data_direction direction) { int ret = 0; WARN_ON(!dmabuf); might_lock(&dmabuf->resv->lock.base); if (dmabuf->ops->end_cpu_access) ret = dmabuf->ops->end_cpu_access(dmabuf, direction); return ret; } EXPORT_SYMBOL_NS_GPL(dma_buf_end_cpu_access, "DMA_BUF"); /** * dma_buf_mmap - Setup up a userspace mmap with the given vma * @dmabuf: [in] buffer that should back the vma * @vma: [in] vma for the mmap * @pgoff: [in] offset in pages where this mmap should start within the * dma-buf buffer. * * This function adjusts the passed in vma so that it points at the file of the * dma_buf operation. It also adjusts the starting pgoff and does bounds * checking on the size of the vma. Then it calls the exporters mmap function to * set up the mapping. * * Can return negative error values, returns 0 on success. */ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma, unsigned long pgoff) { if (WARN_ON(!dmabuf || !vma)) return -EINVAL; /* check if buffer supports mmap */ if (!dmabuf->ops->mmap) return -EINVAL; /* check for offset overflow */ if (pgoff + vma_pages(vma) < pgoff) return -EOVERFLOW; /* check for overflowing the buffer's size */ if (pgoff + vma_pages(vma) > dmabuf->size >> PAGE_SHIFT) return -EINVAL; /* readjust the vma */ vma_set_file(vma, dmabuf->file); vma->vm_pgoff = pgoff; DMA_BUF_TRACE(trace_dma_buf_mmap, dmabuf); return dmabuf->ops->mmap(dmabuf, vma); } EXPORT_SYMBOL_NS_GPL(dma_buf_mmap, "DMA_BUF"); /** * dma_buf_vmap - Create virtual mapping for the buffer object into kernel * address space. Same restrictions as for vmap and friends apply. * @dmabuf: [in] buffer to vmap * @map: [out] returns the vmap pointer * * This call may fail due to lack of virtual mapping address space. * These calls are optional in drivers. The intended use for them * is for mapping objects linear in kernel space for high use objects. * * To ensure coherency users must call dma_buf_begin_cpu_access() and * dma_buf_end_cpu_access() around any cpu access performed through this * mapping. * * Returns 0 on success, or a negative errno code otherwise. */ int dma_buf_vmap(struct dma_buf *dmabuf, struct iosys_map *map) { struct iosys_map ptr; int ret; iosys_map_clear(map); if (WARN_ON(!dmabuf)) return -EINVAL; dma_resv_assert_held(dmabuf->resv); if (!dmabuf->ops->vmap) return -EINVAL; if (dmabuf->vmapping_counter) { dmabuf->vmapping_counter++; BUG_ON(iosys_map_is_null(&dmabuf->vmap_ptr)); *map = dmabuf->vmap_ptr; return 0; } BUG_ON(iosys_map_is_set(&dmabuf->vmap_ptr)); ret = dmabuf->ops->vmap(dmabuf, &ptr); if (WARN_ON_ONCE(ret)) return ret; dmabuf->vmap_ptr = ptr; dmabuf->vmapping_counter = 1; *map = dmabuf->vmap_ptr; return 0; } EXPORT_SYMBOL_NS_GPL(dma_buf_vmap, "DMA_BUF"); /** * dma_buf_vmap_unlocked - Create virtual mapping for the buffer object into kernel * address space. Same restrictions as for vmap and friends apply. * @dmabuf: [in] buffer to vmap * @map: [out] returns the vmap pointer * * Unlocked version of dma_buf_vmap() * * Returns 0 on success, or a negative errno code otherwise. */ int dma_buf_vmap_unlocked(struct dma_buf *dmabuf, struct iosys_map *map) { int ret; iosys_map_clear(map); if (WARN_ON(!dmabuf)) return -EINVAL; dma_resv_lock(dmabuf->resv, NULL); ret = dma_buf_vmap(dmabuf, map); dma_resv_unlock(dmabuf->resv); return ret; } EXPORT_SYMBOL_NS_GPL(dma_buf_vmap_unlocked, "DMA_BUF"); /** * dma_buf_vunmap - Unmap a vmap obtained by dma_buf_vmap. * @dmabuf: [in] buffer to vunmap * @map: [in] vmap pointer to vunmap */ void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map) { if (WARN_ON(!dmabuf)) return; dma_resv_assert_held(dmabuf->resv); BUG_ON(iosys_map_is_null(&dmabuf->vmap_ptr)); BUG_ON(dmabuf->vmapping_counter == 0); BUG_ON(!iosys_map_is_equal(&dmabuf->vmap_ptr, map)); if (--dmabuf->vmapping_counter == 0) { if (dmabuf->ops->vunmap) dmabuf->ops->vunmap(dmabuf, map); iosys_map_clear(&dmabuf->vmap_ptr); } } EXPORT_SYMBOL_NS_GPL(dma_buf_vunmap, "DMA_BUF"); /** * dma_buf_vunmap_unlocked - Unmap a vmap obtained by dma_buf_vmap. * @dmabuf: [in] buffer to vunmap * @map: [in] vmap pointer to vunmap */ void dma_buf_vunmap_unlocked(struct dma_buf *dmabuf, struct iosys_map *map) { if (WARN_ON(!dmabuf)) return; dma_resv_lock(dmabuf->resv, NULL); dma_buf_vunmap(dmabuf, map); dma_resv_unlock(dmabuf->resv); } EXPORT_SYMBOL_NS_GPL(dma_buf_vunmap_unlocked, "DMA_BUF"); #ifdef CONFIG_DEBUG_FS static int dma_buf_debug_show(struct seq_file *s, void *unused) { struct dma_buf *buf_obj; struct dma_buf_attachment *attach_obj; int count = 0, attach_count; size_t size = 0; int ret; ret = mutex_lock_interruptible(&dmabuf_list_mutex); if (ret) return ret; seq_puts(s, "\nDma-buf Objects:\n"); seq_printf(s, "%-8s\t%-8s\t%-8s\t%-8s\texp_name\t%-8s\tname\n", "size", "flags", "mode", "count", "ino"); list_for_each_entry(buf_obj, &dmabuf_list, list_node) { ret = dma_resv_lock_interruptible(buf_obj->resv, NULL); if (ret) goto error_unlock; spin_lock(&buf_obj->name_lock); seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\t%08llu\t%s\n", buf_obj->size, buf_obj->file->f_flags, buf_obj->file->f_mode, file_count(buf_obj->file), buf_obj->exp_name, file_inode(buf_obj->file)->i_ino, buf_obj->name ?: "<none>"); spin_unlock(&buf_obj->name_lock); dma_resv_describe(buf_obj->resv, s); seq_puts(s, "\tAttached Devices:\n"); attach_count = 0; list_for_each_entry(attach_obj, &buf_obj->attachments, node) { seq_printf(s, "\t%s\n", dev_name(attach_obj->dev)); attach_count++; } dma_resv_unlock(buf_obj->resv); seq_printf(s, "Total %d devices attached\n\n", attach_count); count++; size += buf_obj->size; } seq_printf(s, "\nTotal %d objects, %zu bytes\n", count, size); mutex_unlock(&dmabuf_list_mutex); return 0; error_unlock: mutex_unlock(&dmabuf_list_mutex); return ret; } DEFINE_SHOW_ATTRIBUTE(dma_buf_debug); static struct dentry *dma_buf_debugfs_dir; static int dma_buf_init_debugfs(void) { struct dentry *d; int err = 0; d = debugfs_create_dir("dma_buf", NULL); if (IS_ERR(d)) return PTR_ERR(d); dma_buf_debugfs_dir = d; d = debugfs_create_file("bufinfo", 0444, dma_buf_debugfs_dir, NULL, &dma_buf_debug_fops); if (IS_ERR(d)) { pr_debug("dma_buf: debugfs: failed to create node bufinfo\n"); debugfs_remove_recursive(dma_buf_debugfs_dir); dma_buf_debugfs_dir = NULL; err = PTR_ERR(d); } return err; } static void dma_buf_uninit_debugfs(void) { debugfs_remove_recursive(dma_buf_debugfs_dir); } #else static inline int dma_buf_init_debugfs(void) { return 0; } static inline void dma_buf_uninit_debugfs(void) { } #endif static int __init dma_buf_init(void) { dma_buf_mnt = kern_mount(&dma_buf_fs_type); if (IS_ERR(dma_buf_mnt)) return PTR_ERR(dma_buf_mnt); dma_buf_init_debugfs(); return 0; } subsys_initcall(dma_buf_init); static void __exit dma_buf_deinit(void) { dma_buf_uninit_debugfs(); kern_unmount(dma_buf_mnt); } __exitcall(dma_buf_deinit); |
| 78 2 59 77 7 5 3 63 2 61 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * VMware vSockets Driver * * Copyright (C) 2007-2012 VMware, Inc. All rights reserved. */ #include <linux/types.h> #include <linux/socket.h> #include <linux/stddef.h> #include <net/sock.h> #include <net/vsock_addr.h> void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port) { memset(addr, 0, sizeof(*addr)); addr->svm_family = AF_VSOCK; addr->svm_cid = cid; addr->svm_port = port; } EXPORT_SYMBOL_GPL(vsock_addr_init); int vsock_addr_validate(const struct sockaddr_vm *addr) { __u8 svm_valid_flags = VMADDR_FLAG_TO_HOST; if (!addr) return -EFAULT; if (addr->svm_family != AF_VSOCK) return -EAFNOSUPPORT; if (addr->svm_flags & ~svm_valid_flags) return -EINVAL; return 0; } EXPORT_SYMBOL_GPL(vsock_addr_validate); bool vsock_addr_bound(const struct sockaddr_vm *addr) { return addr->svm_port != VMADDR_PORT_ANY; } EXPORT_SYMBOL_GPL(vsock_addr_bound); void vsock_addr_unbind(struct sockaddr_vm *addr) { vsock_addr_init(addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); } EXPORT_SYMBOL_GPL(vsock_addr_unbind); bool vsock_addr_equals_addr(const struct sockaddr_vm *addr, const struct sockaddr_vm *other) { return addr->svm_cid == other->svm_cid && addr->svm_port == other->svm_port; } EXPORT_SYMBOL_GPL(vsock_addr_equals_addr); int vsock_addr_cast(const struct sockaddr_unsized *addr, size_t len, struct sockaddr_vm **out_addr) { if (len < sizeof(**out_addr)) return -EFAULT; *out_addr = (struct sockaddr_vm *)addr; return vsock_addr_validate(*out_addr); } EXPORT_SYMBOL_GPL(vsock_addr_cast); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* RTT/RTO calculation. * * Adapted from TCP for AF_RXRPC by David Howells (dhowells@redhat.com) * * https://tools.ietf.org/html/rfc6298 * https://tools.ietf.org/html/rfc1122#section-4.2.3.1 * http://ccr.sigcomm.org/archive/1995/jan95/ccr-9501-partridge87.pdf */ #include <linux/net.h> #include "ar-internal.h" #define RXRPC_RTO_MAX (120 * USEC_PER_SEC) #define RXRPC_TIMEOUT_INIT ((unsigned int)(1 * USEC_PER_SEC)) /* RFC6298 2.1 initial RTO value */ #define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */ static u32 rxrpc_rto_min_us(struct rxrpc_call *call) { return 200; } static u32 __rxrpc_set_rto(const struct rxrpc_call *call) { return (call->srtt_us >> 3) + call->rttvar_us; } static u32 rxrpc_bound_rto(u32 rto) { return clamp(200000, rto + 100000, RXRPC_RTO_MAX); } /* * Called to compute a smoothed rtt estimate. The data fed to this * routine either comes from timestamps, or from segments that were * known _not_ to have been retransmitted [see Karn/Partridge * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88 * piece by Van Jacobson. * NOTE: the next three routines used to be one big routine. * To save cycles in the RFC 1323 implementation it was better to break * it up into three procedures. -- erics */ static void rxrpc_rtt_estimator(struct rxrpc_call *call, long sample_rtt_us) { long m = sample_rtt_us; /* RTT */ u32 srtt = call->srtt_us; /* The following amusing code comes from Jacobson's * article in SIGCOMM '88. Note that rtt and mdev * are scaled versions of rtt and mean deviation. * This is designed to be as fast as possible * m stands for "measurement". * * On a 1990 paper the rto value is changed to: * RTO = rtt + 4 * mdev * * Funny. This algorithm seems to be very broken. * These formulae increase RTO, when it should be decreased, increase * too slowly, when it should be increased quickly, decrease too quickly * etc. I guess in BSD RTO takes ONE value, so that it is absolutely * does not matter how to _calculate_ it. Seems, it was trap * that VJ failed to avoid. 8) */ if (srtt != 0) { m -= (srtt >> 3); /* m is now error in rtt est */ srtt += m; /* rtt = 7/8 rtt + 1/8 new */ if (m < 0) { m = -m; /* m is now abs(error) */ m -= (call->mdev_us >> 2); /* similar update on mdev */ /* This is similar to one of Eifel findings. * Eifel blocks mdev updates when rtt decreases. * This solution is a bit different: we use finer gain * for mdev in this case (alpha*beta). * Like Eifel it also prevents growth of rto, * but also it limits too fast rto decreases, * happening in pure Eifel. */ if (m > 0) m >>= 3; } else { m -= (call->mdev_us >> 2); /* similar update on mdev */ } call->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ if (call->mdev_us > call->mdev_max_us) { call->mdev_max_us = call->mdev_us; if (call->mdev_max_us > call->rttvar_us) call->rttvar_us = call->mdev_max_us; } } else { /* no previous measure. */ srtt = m << 3; /* take the measured time to be rtt */ call->mdev_us = m << 1; /* make sure rto = 3*rtt */ call->rttvar_us = umax(call->mdev_us, rxrpc_rto_min_us(call)); call->mdev_max_us = call->rttvar_us; } call->srtt_us = umax(srtt, 1); } /* * Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ static void rxrpc_set_rto(struct rxrpc_call *call) { u32 rto; /* 1. If rtt variance happened to be less 50msec, it is hallucination. * It cannot be less due to utterly erratic ACK generation made * at least by solaris and freebsd. "Erratic ACKs" has _nothing_ * to do with delayed acks, because at cwnd>2 true delack timeout * is invisible. Actually, Linux-2.4 also generates erratic * ACKs in some circumstances. */ rto = __rxrpc_set_rto(call); /* 2. Fixups made earlier cannot be right. * If we do not estimate RTO correctly without them, * all the algo is pure shit and should be replaced * with correct one. It is exactly, which we pretend to do. */ /* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo * guarantees that rto is higher. */ call->rto_us = rxrpc_bound_rto(rto); } static void rxrpc_update_rtt_min(struct rxrpc_call *call, ktime_t resp_time, long rtt_us) { /* Window size 5mins in approx usec (ipv4.sysctl_tcp_min_rtt_wlen) */ u32 wlen_us = 5ULL * NSEC_PER_SEC / 1024; minmax_running_min(&call->min_rtt, wlen_us, resp_time / 1024, (u32)rtt_us ? : jiffies_to_usecs(1)); } static void rxrpc_ack_update_rtt(struct rxrpc_call *call, ktime_t resp_time, long rtt_us) { if (rtt_us < 0) return; /* Update RACK min RTT [RFC8985 6.1 Step 1]. */ rxrpc_update_rtt_min(call, resp_time, rtt_us); rxrpc_rtt_estimator(call, rtt_us); rxrpc_set_rto(call); /* Only reset backoff on valid RTT measurement [RFC6298]. */ call->backoff = 0; } /* * Add RTT information to cache. This is called in softirq mode and has * exclusive access to the call RTT data. */ void rxrpc_call_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, int rtt_slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, ktime_t send_time, ktime_t resp_time) { s64 rtt_us; rtt_us = ktime_to_us(ktime_sub(resp_time, send_time)); if (rtt_us < 0) return; rxrpc_ack_update_rtt(call, resp_time, rtt_us); if (call->rtt_count < 3) call->rtt_count++; call->rtt_taken++; WRITE_ONCE(call->peer->recent_srtt_us, call->srtt_us / 8); WRITE_ONCE(call->peer->recent_rto_us, call->rto_us); trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial, rtt_us, call->srtt_us, call->rto_us); } /* * Get the retransmission timeout to set in nanoseconds, backing it off each * time we retransmit. */ ktime_t rxrpc_get_rto_backoff(struct rxrpc_call *call, bool retrans) { u64 timo_us; u32 backoff = READ_ONCE(call->backoff); timo_us = call->rto_us; timo_us <<= backoff; if (retrans && timo_us * 2 <= RXRPC_RTO_MAX) WRITE_ONCE(call->backoff, backoff + 1); if (timo_us < 1) timo_us = 1; return ns_to_ktime(timo_us * NSEC_PER_USEC); } void rxrpc_call_init_rtt(struct rxrpc_call *call) { call->rtt_last_req = KTIME_MIN; call->rto_us = RXRPC_TIMEOUT_INIT; call->mdev_us = RXRPC_TIMEOUT_INIT; call->backoff = 0; //minmax_reset(&call->rtt_min, rxrpc_jiffies32, ~0U); } |
| 33 33 33 33 20 20 33 33 33 33 33 33 33 33 33 33 20 20 20 33 33 33 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 | // SPDX-License-Identifier: GPL-2.0 /* * Vidtv serves as a reference DVB driver and helps validate the existing APIs * in the media subsystem. It can also aid developers working on userspace * applications. * * This file contains the multiplexer logic for TS packets from different * elementary streams * * Loosely based on libavcodec/mpegtsenc.c * * Copyright (C) 2020 Daniel W. S. Almeida */ #include <linux/delay.h> #include <linux/dev_printk.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/math64.h> #include <linux/ratelimit.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/vmalloc.h> #include "vidtv_channel.h" #include "vidtv_common.h" #include "vidtv_encoder.h" #include "vidtv_mux.h" #include "vidtv_pes.h" #include "vidtv_psi.h" #include "vidtv_ts.h" static struct vidtv_mux_pid_ctx *vidtv_mux_get_pid_ctx(struct vidtv_mux *m, u16 pid) { struct vidtv_mux_pid_ctx *ctx; hash_for_each_possible(m->pid_ctx, ctx, h, pid) if (ctx->pid == pid) return ctx; return NULL; } static struct vidtv_mux_pid_ctx *vidtv_mux_create_pid_ctx_once(struct vidtv_mux *m, u16 pid) { struct vidtv_mux_pid_ctx *ctx; ctx = vidtv_mux_get_pid_ctx(m, pid); if (ctx) return ctx; ctx = kzalloc_obj(*ctx); if (!ctx) return NULL; ctx->pid = pid; ctx->cc = 0; hash_add(m->pid_ctx, &ctx->h, pid); return ctx; } static void vidtv_mux_pid_ctx_destroy(struct vidtv_mux *m) { struct vidtv_mux_pid_ctx *ctx; struct hlist_node *tmp; int bkt; hash_for_each_safe(m->pid_ctx, bkt, tmp, ctx, h) { hash_del(&ctx->h); kfree(ctx); } } static int vidtv_mux_pid_ctx_init(struct vidtv_mux *m) { struct vidtv_psi_table_pat_program *p = m->si.pat->program; u16 pid; hash_init(m->pid_ctx); /* push the pcr pid ctx */ if (!vidtv_mux_create_pid_ctx_once(m, m->pcr_pid)) return -ENOMEM; /* push the NULL packet pid ctx */ if (!vidtv_mux_create_pid_ctx_once(m, TS_NULL_PACKET_PID)) goto free; /* push the PAT pid ctx */ if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_PAT_PID)) goto free; /* push the SDT pid ctx */ if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_SDT_PID)) goto free; /* push the NIT pid ctx */ if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_NIT_PID)) goto free; /* push the EIT pid ctx */ if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_EIT_PID)) goto free; /* add a ctx for all PMT sections */ while (p) { pid = vidtv_psi_get_pat_program_pid(p); vidtv_mux_create_pid_ctx_once(m, pid); p = p->next; } return 0; free: vidtv_mux_pid_ctx_destroy(m); return -ENOMEM; } static void vidtv_mux_update_clk(struct vidtv_mux *m) { /* call this at every thread iteration */ u64 elapsed_time; m->timing.past_jiffies = m->timing.current_jiffies; m->timing.current_jiffies = get_jiffies_64(); elapsed_time = jiffies_to_usecs(m->timing.current_jiffies - m->timing.past_jiffies); /* update the 27Mhz clock proportionally to the elapsed time */ m->timing.clk += (CLOCK_UNIT_27MHZ / USEC_PER_SEC) * elapsed_time; } static u32 vidtv_mux_push_si(struct vidtv_mux *m) { struct vidtv_psi_pat_write_args pat_args = { .buf = m->mux_buf, .buf_sz = m->mux_buf_sz, .pat = m->si.pat, }; struct vidtv_psi_pmt_write_args pmt_args = { .buf = m->mux_buf, .buf_sz = m->mux_buf_sz, .pcr_pid = m->pcr_pid, }; struct vidtv_psi_sdt_write_args sdt_args = { .buf = m->mux_buf, .buf_sz = m->mux_buf_sz, .sdt = m->si.sdt, }; struct vidtv_psi_nit_write_args nit_args = { .buf = m->mux_buf, .buf_sz = m->mux_buf_sz, .nit = m->si.nit, }; struct vidtv_psi_eit_write_args eit_args = { .buf = m->mux_buf, .buf_sz = m->mux_buf_sz, .eit = m->si.eit, }; u32 initial_offset = m->mux_buf_offset; struct vidtv_mux_pid_ctx *pat_ctx; struct vidtv_mux_pid_ctx *pmt_ctx; struct vidtv_mux_pid_ctx *sdt_ctx; struct vidtv_mux_pid_ctx *nit_ctx; struct vidtv_mux_pid_ctx *eit_ctx; u32 nbytes; u16 pmt_pid; u32 i; pat_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_PAT_PID); sdt_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_SDT_PID); nit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_NIT_PID); eit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_EIT_PID); pat_args.offset = m->mux_buf_offset; pat_args.continuity_counter = &pat_ctx->cc; m->mux_buf_offset += vidtv_psi_pat_write_into(&pat_args); for (i = 0; i < m->si.pat->num_pmt; ++i) { pmt_pid = vidtv_psi_pmt_get_pid(m->si.pmt_secs[i], m->si.pat); if (pmt_pid > TS_LAST_VALID_PID) { dev_warn_ratelimited(m->dev, "PID: %d not found\n", pmt_pid); continue; } pmt_ctx = vidtv_mux_get_pid_ctx(m, pmt_pid); pmt_args.offset = m->mux_buf_offset; pmt_args.pmt = m->si.pmt_secs[i]; pmt_args.pid = pmt_pid; pmt_args.continuity_counter = &pmt_ctx->cc; /* write each section into buffer */ m->mux_buf_offset += vidtv_psi_pmt_write_into(&pmt_args); } sdt_args.offset = m->mux_buf_offset; sdt_args.continuity_counter = &sdt_ctx->cc; m->mux_buf_offset += vidtv_psi_sdt_write_into(&sdt_args); nit_args.offset = m->mux_buf_offset; nit_args.continuity_counter = &nit_ctx->cc; m->mux_buf_offset += vidtv_psi_nit_write_into(&nit_args); eit_args.offset = m->mux_buf_offset; eit_args.continuity_counter = &eit_ctx->cc; m->mux_buf_offset += vidtv_psi_eit_write_into(&eit_args); nbytes = m->mux_buf_offset - initial_offset; m->num_streamed_si++; return nbytes; } static u32 vidtv_mux_push_pcr(struct vidtv_mux *m) { struct pcr_write_args args = {}; struct vidtv_mux_pid_ctx *ctx; u32 nbytes = 0; ctx = vidtv_mux_get_pid_ctx(m, m->pcr_pid); args.dest_buf = m->mux_buf; args.pid = m->pcr_pid; args.buf_sz = m->mux_buf_sz; args.continuity_counter = &ctx->cc; /* the 27Mhz clock will feed both parts of the PCR bitfield */ args.pcr = m->timing.clk; nbytes += vidtv_ts_pcr_write_into(&args); m->mux_buf_offset += nbytes; m->num_streamed_pcr++; return nbytes; } static bool vidtv_mux_should_push_pcr(struct vidtv_mux *m) { u64 next_pcr_at; if (m->num_streamed_pcr == 0) return true; next_pcr_at = m->timing.start_jiffies + usecs_to_jiffies(m->num_streamed_pcr * m->timing.pcr_period_usecs); return time_after64(m->timing.current_jiffies, next_pcr_at); } static bool vidtv_mux_should_push_si(struct vidtv_mux *m) { u64 next_si_at; if (m->num_streamed_si == 0) return true; next_si_at = m->timing.start_jiffies + usecs_to_jiffies(m->num_streamed_si * m->timing.si_period_usecs); return time_after64(m->timing.current_jiffies, next_si_at); } static u32 vidtv_mux_packetize_access_units(struct vidtv_mux *m, struct vidtv_encoder *e) { struct pes_write_args args = { .dest_buf = m->mux_buf, .dest_buf_sz = m->mux_buf_sz, .pid = be16_to_cpu(e->es_pid), .encoder_id = e->id, .stream_id = be16_to_cpu(e->stream_id), .send_pts = true, /* forbidden value '01'... */ .send_dts = false, /* ...for PTS_DTS flags */ }; struct vidtv_access_unit *au = e->access_units; u32 initial_offset = m->mux_buf_offset; struct vidtv_mux_pid_ctx *pid_ctx; u32 nbytes = 0; u8 *buf = NULL; /* see SMPTE 302M clause 6.4 */ if (args.encoder_id == S302M) { args.send_dts = false; args.send_pts = true; } pid_ctx = vidtv_mux_create_pid_ctx_once(m, be16_to_cpu(e->es_pid)); args.continuity_counter = &pid_ctx->cc; while (au) { buf = e->encoder_buf + au->offset; args.from = buf; args.access_unit_len = au->nbytes; args.dest_offset = m->mux_buf_offset; args.pts = au->pts; args.pcr = m->timing.clk; m->mux_buf_offset += vidtv_pes_write_into(&args); au = au->next; } /* * clear the encoder state once the ES data has been written to the mux * buffer */ e->clear(e); nbytes = m->mux_buf_offset - initial_offset; return nbytes; } static u32 vidtv_mux_poll_encoders(struct vidtv_mux *m) { struct vidtv_channel *cur_chnl = m->channels; struct vidtv_encoder *e = NULL; u32 nbytes = 0; u32 au_nbytes; while (cur_chnl) { e = cur_chnl->encoders; while (e) { e->encode(e); /* get the TS packets into the mux buffer */ au_nbytes = vidtv_mux_packetize_access_units(m, e); nbytes += au_nbytes; m->mux_buf_offset += au_nbytes; /* grab next encoder */ e = e->next; } /* grab the next channel */ cur_chnl = cur_chnl->next; } return nbytes; } static u32 vidtv_mux_pad_with_nulls(struct vidtv_mux *m, u32 npkts) { struct null_packet_write_args args = { .dest_buf = m->mux_buf, .buf_sz = m->mux_buf_sz, .dest_offset = m->mux_buf_offset, }; u32 initial_offset = m->mux_buf_offset; struct vidtv_mux_pid_ctx *ctx; u32 nbytes; u32 i; ctx = vidtv_mux_get_pid_ctx(m, TS_NULL_PACKET_PID); args.continuity_counter = &ctx->cc; for (i = 0; i < npkts; ++i) { m->mux_buf_offset += vidtv_ts_null_write_into(&args); args.dest_offset = m->mux_buf_offset; } nbytes = m->mux_buf_offset - initial_offset; /* sanity check */ if (nbytes != npkts * TS_PACKET_LEN) dev_err_ratelimited(m->dev, "%d != %d\n", nbytes, npkts * TS_PACKET_LEN); return nbytes; } static void vidtv_mux_clear(struct vidtv_mux *m) { /* clear the packets currently in the mux */ memset(m->mux_buf, 0, m->mux_buf_sz * sizeof(*m->mux_buf)); /* point to the beginning of the buffer again */ m->mux_buf_offset = 0; } #define ERR_RATE 10000000 static void vidtv_mux_tick(struct work_struct *work) { struct vidtv_mux *m = container_of(work, struct vidtv_mux, mpeg_thread); struct dtv_frontend_properties *c = &m->fe->dtv_property_cache; u32 tot_bits = 0; u32 nbytes; u32 npkts; while (m->streaming) { nbytes = 0; vidtv_mux_update_clk(m); if (vidtv_mux_should_push_pcr(m)) nbytes += vidtv_mux_push_pcr(m); if (vidtv_mux_should_push_si(m)) nbytes += vidtv_mux_push_si(m); nbytes += vidtv_mux_poll_encoders(m); nbytes += vidtv_mux_pad_with_nulls(m, 256); npkts = nbytes / TS_PACKET_LEN; /* if the buffer is not aligned there is a bug somewhere */ if (nbytes % TS_PACKET_LEN) dev_err_ratelimited(m->dev, "Misaligned buffer\n"); if (m->on_new_packets_available_cb) m->on_new_packets_available_cb(m->priv, m->mux_buf, npkts); vidtv_mux_clear(m); /* * Update bytes and packet counts at DVBv5 stats * * For now, both pre and post bit counts are identical, * but post BER count can be lower than pre BER, if the error * correction logic discards packages. */ c->pre_bit_count.stat[0].uvalue = nbytes * 8; c->post_bit_count.stat[0].uvalue = nbytes * 8; c->block_count.stat[0].uvalue += npkts; /* * Even without any visible errors for the user, the pre-BER * stats usually have an error range up to 1E-6. So, * add some random error increment count to it. * * Please notice that this is a poor guy's implementation, * as it will produce one corrected bit error every time * ceil(total bytes / ERR_RATE) is incremented, without * any sort of (pseudo-)randomness. */ tot_bits += nbytes * 8; if (tot_bits > ERR_RATE) { c->pre_bit_error.stat[0].uvalue++; tot_bits -= ERR_RATE; } usleep_range(VIDTV_SLEEP_USECS, VIDTV_MAX_SLEEP_USECS); } } void vidtv_mux_start_thread(struct vidtv_mux *m) { if (m->streaming) { dev_warn_ratelimited(m->dev, "Already streaming. Skipping.\n"); return; } m->streaming = true; m->timing.start_jiffies = get_jiffies_64(); schedule_work(&m->mpeg_thread); } void vidtv_mux_stop_thread(struct vidtv_mux *m) { if (m->streaming) { m->streaming = false; /* thread will quit */ cancel_work_sync(&m->mpeg_thread); } } struct vidtv_mux *vidtv_mux_init(struct dvb_frontend *fe, struct device *dev, struct vidtv_mux_init_args *args) { struct vidtv_mux *m; m = kzalloc_obj(*m); if (!m) return NULL; m->dev = dev; m->fe = fe; m->timing.pcr_period_usecs = args->pcr_period_usecs; m->timing.si_period_usecs = args->si_period_usecs; m->mux_rate_kbytes_sec = args->mux_rate_kbytes_sec; m->on_new_packets_available_cb = args->on_new_packets_available_cb; m->mux_buf = vzalloc(args->mux_buf_sz); if (!m->mux_buf) goto free_mux; m->mux_buf_sz = args->mux_buf_sz; m->pcr_pid = args->pcr_pid; m->transport_stream_id = args->transport_stream_id; m->priv = args->priv; m->network_id = args->network_id; m->network_name = kstrdup(args->network_name, GFP_KERNEL); if (!m->network_name) goto free_mux_buf; m->timing.current_jiffies = get_jiffies_64(); if (args->channels) m->channels = args->channels; else if (vidtv_channels_init(m) < 0) goto free_mux_network_name; /* will alloc data for pmt_sections after initializing pat */ if (vidtv_channel_si_init(m) < 0) goto free_channels; INIT_WORK(&m->mpeg_thread, vidtv_mux_tick); if (vidtv_mux_pid_ctx_init(m) < 0) goto free_channel_si; return m; free_channel_si: vidtv_channel_si_destroy(m); free_channels: vidtv_channels_destroy(m); free_mux_network_name: kfree(m->network_name); free_mux_buf: vfree(m->mux_buf); free_mux: kfree(m); return NULL; } void vidtv_mux_destroy(struct vidtv_mux *m) { vidtv_mux_stop_thread(m); vidtv_mux_pid_ctx_destroy(m); vidtv_channel_si_destroy(m); vidtv_channels_destroy(m); kfree(m->network_name); vfree(m->mux_buf); kfree(m); } |
| 18 22 4 3 11 32 4 33 34 32 18 12 29 18 22 1 1 32 32 32 14 19 7 20 32 20 18 33 15 18 30 33 32 32 32 20 32 33 33 1 17 11 5 14 5 4 33 18 23 19 10 8 4 32 3 21 29 23 19 18 20 20 4 10 32 29 31 32 30 8 29 31 22 32 29 32 33 25 23 33 17 33 18 18 18 31 9 32 31 1 33 1 32 32 33 1 3 20 1 33 33 33 33 33 33 33 33 33 33 33 10 10 14 1 23 23 3 1 2 25 25 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 | // SPDX-License-Identifier: GPL-2.0 /* Bottleneck Bandwidth and RTT (BBR) congestion control * * BBR congestion control computes the sending rate based on the delivery * rate (throughput) estimated from ACKs. In a nutshell: * * On each ACK, update our model of the network path: * bottleneck_bandwidth = windowed_max(delivered / elapsed, 10 round trips) * min_rtt = windowed_min(rtt, 10 seconds) * pacing_rate = pacing_gain * bottleneck_bandwidth * cwnd = max(cwnd_gain * bottleneck_bandwidth * min_rtt, 4) * * The core algorithm does not react directly to packet losses or delays, * although BBR may adjust the size of next send per ACK when loss is * observed, or adjust the sending rate if it estimates there is a * traffic policer, in order to keep the drop rate reasonable. * * Here is a state transition diagram for BBR: * * | * V * +---> STARTUP ----+ * | | | * | V | * | DRAIN ----+ * | | | * | V | * +---> PROBE_BW ----+ * | ^ | | * | | | | * | +----+ | * | | * +---- PROBE_RTT <--+ * * A BBR flow starts in STARTUP, and ramps up its sending rate quickly. * When it estimates the pipe is full, it enters DRAIN to drain the queue. * In steady state a BBR flow only uses PROBE_BW and PROBE_RTT. * A long-lived BBR flow spends the vast majority of its time remaining * (repeatedly) in PROBE_BW, fully probing and utilizing the pipe's bandwidth * in a fair manner, with a small, bounded queue. *If* a flow has been * continuously sending for the entire min_rtt window, and hasn't seen an RTT * sample that matches or decreases its min_rtt estimate for 10 seconds, then * it briefly enters PROBE_RTT to cut inflight to a minimum value to re-probe * the path's two-way propagation delay (min_rtt). When exiting PROBE_RTT, if * we estimated that we reached the full bw of the pipe then we enter PROBE_BW; * otherwise we enter STARTUP to try to fill the pipe. * * BBR is described in detail in: * "BBR: Congestion-Based Congestion Control", * Neal Cardwell, Yuchung Cheng, C. Stephen Gunn, Soheil Hassas Yeganeh, * Van Jacobson. ACM Queue, Vol. 14 No. 5, September-October 2016. * * There is a public e-mail list for discussing BBR development and testing: * https://groups.google.com/forum/#!forum/bbr-dev * * NOTE: BBR might be used with the fq qdisc ("man tc-fq") with pacing enabled, * otherwise TCP stack falls back to an internal pacing using one high * resolution timer per TCP socket and may use more resources. */ #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/module.h> #include <net/tcp.h> #include <linux/inet_diag.h> #include <linux/inet.h> #include <linux/random.h> #include <linux/win_minmax.h> /* Scale factor for rate in pkt/uSec unit to avoid truncation in bandwidth * estimation. The rate unit ~= (1500 bytes / 1 usec / 2^24) ~= 715 bps. * This handles bandwidths from 0.06pps (715bps) to 256Mpps (3Tbps) in a u32. * Since the minimum window is >=4 packets, the lower bound isn't * an issue. The upper bound isn't an issue with existing technologies. */ #define BW_SCALE 24 #define BW_UNIT (1 << BW_SCALE) #define BBR_SCALE 8 /* scaling factor for fractions in BBR (e.g. gains) */ #define BBR_UNIT (1 << BBR_SCALE) /* BBR has the following modes for deciding how fast to send: */ enum bbr_mode { BBR_STARTUP, /* ramp up sending rate rapidly to fill pipe */ BBR_DRAIN, /* drain any queue created during startup */ BBR_PROBE_BW, /* discover, share bw: pace around estimated bw */ BBR_PROBE_RTT, /* cut inflight to min to probe min_rtt */ }; /* BBR congestion control block */ struct bbr { u32 min_rtt_us; /* min RTT in min_rtt_win_sec window */ u32 min_rtt_stamp; /* timestamp of min_rtt_us */ u32 probe_rtt_done_stamp; /* end time for BBR_PROBE_RTT mode */ struct minmax bw; /* Max recent delivery rate in pkts/uS << 24 */ u32 rtt_cnt; /* count of packet-timed rounds elapsed */ u32 next_rtt_delivered; /* scb->tx.delivered at end of round */ u64 cycle_mstamp; /* time of this cycle phase start */ u32 mode:3, /* current bbr_mode in state machine */ prev_ca_state:3, /* CA state on previous ACK */ packet_conservation:1, /* use packet conservation? */ round_start:1, /* start of packet-timed tx->ack round? */ idle_restart:1, /* restarting after idle? */ probe_rtt_round_done:1, /* a BBR_PROBE_RTT round at 4 pkts? */ unused:13, lt_is_sampling:1, /* taking long-term ("LT") samples now? */ lt_rtt_cnt:7, /* round trips in long-term interval */ lt_use_bw:1; /* use lt_bw as our bw estimate? */ u32 lt_bw; /* LT est delivery rate in pkts/uS << 24 */ u32 lt_last_delivered; /* LT intvl start: tp->delivered */ u32 lt_last_stamp; /* LT intvl start: tp->delivered_mstamp */ u32 lt_last_lost; /* LT intvl start: tp->lost */ u32 pacing_gain:10, /* current gain for setting pacing rate */ cwnd_gain:10, /* current gain for setting cwnd */ full_bw_reached:1, /* reached full bw in Startup? */ full_bw_cnt:2, /* number of rounds without large bw gains */ cycle_idx:3, /* current index in pacing_gain cycle array */ has_seen_rtt:1, /* have we seen an RTT sample yet? */ unused_b:5; u32 prior_cwnd; /* prior cwnd upon entering loss recovery */ u32 full_bw; /* recent bw, to estimate if pipe is full */ /* For tracking ACK aggregation: */ u64 ack_epoch_mstamp; /* start of ACK sampling epoch */ u16 extra_acked[2]; /* max excess data ACKed in epoch */ u32 ack_epoch_acked:20, /* packets (S)ACKed in sampling epoch */ extra_acked_win_rtts:5, /* age of extra_acked, in round trips */ extra_acked_win_idx:1, /* current index in extra_acked array */ unused_c:6; }; #define CYCLE_LEN 8 /* number of phases in a pacing gain cycle */ /* Window length of bw filter (in rounds): */ static const int bbr_bw_rtts = CYCLE_LEN + 2; /* Window length of min_rtt filter (in sec): */ static const u32 bbr_min_rtt_win_sec = 10; /* Minimum time (in ms) spent at bbr_cwnd_min_target in BBR_PROBE_RTT mode: */ static const u32 bbr_probe_rtt_mode_ms = 200; /* Skip TSO below the following bandwidth (bits/sec): */ static const int bbr_min_tso_rate = 1200000; /* Pace at ~1% below estimated bw, on average, to reduce queue at bottleneck. * In order to help drive the network toward lower queues and low latency while * maintaining high utilization, the average pacing rate aims to be slightly * lower than the estimated bandwidth. This is an important aspect of the * design. */ static const int bbr_pacing_margin_percent = 1; /* We use a high_gain value of 2/ln(2) because it's the smallest pacing gain * that will allow a smoothly increasing pacing rate that will double each RTT * and send the same number of packets per RTT that an un-paced, slow-starting * Reno or CUBIC flow would: */ static const int bbr_high_gain = BBR_UNIT * 2885 / 1000 + 1; /* The pacing gain of 1/high_gain in BBR_DRAIN is calculated to typically drain * the queue created in BBR_STARTUP in a single round: */ static const int bbr_drain_gain = BBR_UNIT * 1000 / 2885; /* The gain for deriving steady-state cwnd tolerates delayed/stretched ACKs: */ static const int bbr_cwnd_gain = BBR_UNIT * 2; /* The pacing_gain values for the PROBE_BW gain cycle, to discover/share bw: */ static const int bbr_pacing_gain[] = { BBR_UNIT * 5 / 4, /* probe for more available bw */ BBR_UNIT * 3 / 4, /* drain queue and/or yield bw to other flows */ BBR_UNIT, BBR_UNIT, BBR_UNIT, /* cruise at 1.0*bw to utilize pipe, */ BBR_UNIT, BBR_UNIT, BBR_UNIT /* without creating excess queue... */ }; /* Randomize the starting gain cycling phase over N phases: */ static const u32 bbr_cycle_rand = 7; /* Try to keep at least this many packets in flight, if things go smoothly. For * smooth functioning, a sliding window protocol ACKing every other packet * needs at least 4 packets in flight: */ static const u32 bbr_cwnd_min_target = 4; /* To estimate if BBR_STARTUP mode (i.e. high_gain) has filled pipe... */ /* If bw has increased significantly (1.25x), there may be more bw available: */ static const u32 bbr_full_bw_thresh = BBR_UNIT * 5 / 4; /* But after 3 rounds w/o significant bw growth, estimate pipe is full: */ static const u32 bbr_full_bw_cnt = 3; /* "long-term" ("LT") bandwidth estimator parameters... */ /* The minimum number of rounds in an LT bw sampling interval: */ static const u32 bbr_lt_intvl_min_rtts = 4; /* If lost/delivered ratio > 20%, interval is "lossy" and we may be policed: */ static const u32 bbr_lt_loss_thresh = 50; /* If 2 intervals have a bw ratio <= 1/8, their bw is "consistent": */ static const u32 bbr_lt_bw_ratio = BBR_UNIT / 8; /* If 2 intervals have a bw diff <= 4 Kbit/sec their bw is "consistent": */ static const u32 bbr_lt_bw_diff = 4000 / 8; /* If we estimate we're policed, use lt_bw for this many round trips: */ static const u32 bbr_lt_bw_max_rtts = 48; /* Gain factor for adding extra_acked to target cwnd: */ static const int bbr_extra_acked_gain = BBR_UNIT; /* Window length of extra_acked window. */ static const u32 bbr_extra_acked_win_rtts = 5; /* Max allowed val for ack_epoch_acked, after which sampling epoch is reset */ static const u32 bbr_ack_epoch_acked_reset_thresh = 1U << 20; /* Time period for clamping cwnd increment due to ack aggregation */ static const u32 bbr_extra_acked_max_us = 100 * 1000; static void bbr_check_probe_rtt_done(struct sock *sk); /* Do we estimate that STARTUP filled the pipe? */ static bool bbr_full_bw_reached(const struct sock *sk) { const struct bbr *bbr = inet_csk_ca(sk); return bbr->full_bw_reached; } /* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */ static u32 bbr_max_bw(const struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); return minmax_get(&bbr->bw); } /* Return the estimated bandwidth of the path, in pkts/uS << BW_SCALE. */ static u32 bbr_bw(const struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); return bbr->lt_use_bw ? bbr->lt_bw : bbr_max_bw(sk); } /* Return maximum extra acked in past k-2k round trips, * where k = bbr_extra_acked_win_rtts. */ static u16 bbr_extra_acked(const struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); return max(bbr->extra_acked[0], bbr->extra_acked[1]); } /* Return rate in bytes per second, optionally with a gain. * The order here is chosen carefully to avoid overflow of u64. This should * work for input rates of up to 2.9Tbit/sec and gain of 2.89x. */ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) { unsigned int mss = tcp_sk(sk)->mss_cache; rate *= mss; rate *= gain; rate >>= BBR_SCALE; rate *= USEC_PER_SEC / 100 * (100 - bbr_pacing_margin_percent); return rate >> BW_SCALE; } /* Convert a BBR bw and gain factor to a pacing rate in bytes per second. */ static unsigned long bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain) { u64 rate = bw; rate = bbr_rate_bytes_per_sec(sk, rate, gain); rate = min_t(u64, rate, READ_ONCE(sk->sk_max_pacing_rate)); return rate; } /* Initialize pacing rate to: high_gain * init_cwnd / RTT. */ static void bbr_init_pacing_rate_from_rtt(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u64 bw; u32 rtt_us; if (tp->srtt_us) { /* any RTT sample yet? */ rtt_us = max(tp->srtt_us >> 3, 1U); bbr->has_seen_rtt = 1; } else { /* no RTT sample yet */ rtt_us = USEC_PER_MSEC; /* use nominal default RTT */ } bw = (u64)tcp_snd_cwnd(tp) * BW_UNIT; do_div(bw, rtt_us); WRITE_ONCE(sk->sk_pacing_rate, bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain)); } /* Pace using current bw estimate and a gain factor. */ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); unsigned long rate = bbr_bw_to_pacing_rate(sk, bw, gain); if (unlikely(!bbr->has_seen_rtt && tp->srtt_us)) bbr_init_pacing_rate_from_rtt(sk); if (bbr_full_bw_reached(sk) || rate > READ_ONCE(sk->sk_pacing_rate)) WRITE_ONCE(sk->sk_pacing_rate, rate); } /* override sysctl_tcp_min_tso_segs */ __bpf_kfunc static u32 bbr_min_tso_segs(struct sock *sk) { return READ_ONCE(sk->sk_pacing_rate) < (bbr_min_tso_rate >> 3) ? 1 : 2; } static u32 bbr_tso_segs_goal(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 segs, bytes; /* Sort of tcp_tso_autosize() but ignoring * driver provided sk_gso_max_size. */ bytes = min_t(unsigned long, READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift), GSO_LEGACY_MAX_SIZE - 1 - MAX_TCP_HEADER); segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk)); return min(segs, 0x7FU); } /* Save "last known good" cwnd so we can restore it after losses or PROBE_RTT */ static void bbr_save_cwnd(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); if (bbr->prev_ca_state < TCP_CA_Recovery && bbr->mode != BBR_PROBE_RTT) bbr->prior_cwnd = tcp_snd_cwnd(tp); /* this cwnd is good enough */ else /* loss recovery or BBR_PROBE_RTT have temporarily cut cwnd */ bbr->prior_cwnd = max(bbr->prior_cwnd, tcp_snd_cwnd(tp)); } __bpf_kfunc static void bbr_cwnd_event_tx_start(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); if (tp->app_limited) { bbr->idle_restart = 1; bbr->ack_epoch_mstamp = tp->tcp_mstamp; bbr->ack_epoch_acked = 0; /* Avoid pointless buffer overflows: pace at est. bw if we don't * need more speed (we're restarting from idle and app-limited). */ if (bbr->mode == BBR_PROBE_BW) bbr_set_pacing_rate(sk, bbr_bw(sk), BBR_UNIT); else if (bbr->mode == BBR_PROBE_RTT) bbr_check_probe_rtt_done(sk); } } /* Calculate bdp based on min RTT and the estimated bottleneck bandwidth: * * bdp = ceil(bw * min_rtt * gain) * * The key factor, gain, controls the amount of queue. While a small gain * builds a smaller queue, it becomes more vulnerable to noise in RTT * measurements (e.g., delayed ACKs or other ACK compression effects). This * noise may cause BBR to under-estimate the rate. */ static u32 bbr_bdp(struct sock *sk, u32 bw, int gain) { struct bbr *bbr = inet_csk_ca(sk); u32 bdp; u64 w; /* If we've never had a valid RTT sample, cap cwnd at the initial * default. This should only happen when the connection is not using TCP * timestamps and has retransmitted all of the SYN/SYNACK/data packets * ACKed so far. In this case, an RTO can cut cwnd to 1, in which * case we need to slow-start up toward something safe: TCP_INIT_CWND. */ if (unlikely(bbr->min_rtt_us == ~0U)) /* no valid RTT samples yet? */ return TCP_INIT_CWND; /* be safe: cap at default initial cwnd*/ w = (u64)bw * bbr->min_rtt_us; /* Apply a gain to the given value, remove the BW_SCALE shift, and * round the value up to avoid a negative feedback loop. */ bdp = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; return bdp; } /* To achieve full performance in high-speed paths, we budget enough cwnd to * fit full-sized skbs in-flight on both end hosts to fully utilize the path: * - one skb in sending host Qdisc, * - one skb in sending host TSO/GSO engine * - one skb being received by receiver host LRO/GRO/delayed-ACK engine * Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because * in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets, * which allows 2 outstanding 2-packet sequences, to try to keep pipe * full even with ACK-every-other-packet delayed ACKs. */ static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd) { struct bbr *bbr = inet_csk_ca(sk); /* Allow enough full-sized skbs in flight to utilize end systems. */ cwnd += 3 * bbr_tso_segs_goal(sk); /* Reduce delayed ACKs by rounding up cwnd to the next even number. */ cwnd = (cwnd + 1) & ~1U; /* Ensure gain cycling gets inflight above BDP even for small BDPs. */ if (bbr->mode == BBR_PROBE_BW && bbr->cycle_idx == 0) cwnd += 2; return cwnd; } /* Find inflight based on min RTT and the estimated bottleneck bandwidth. */ static u32 bbr_inflight(struct sock *sk, u32 bw, int gain) { u32 inflight; inflight = bbr_bdp(sk, bw, gain); inflight = bbr_quantization_budget(sk, inflight); return inflight; } /* With pacing at lower layers, there's often less data "in the network" than * "in flight". With TSQ and departure time pacing at lower layers (e.g. fq), * we often have several skbs queued in the pacing layer with a pre-scheduled * earliest departure time (EDT). BBR adapts its pacing rate based on the * inflight level that it estimates has already been "baked in" by previous * departure time decisions. We calculate a rough estimate of the number of our * packets that might be in the network at the earliest departure time for the * next skb scheduled: * in_network_at_edt = inflight_at_edt - (EDT - now) * bw * If we're increasing inflight, then we want to know if the transmit of the * EDT skb will push inflight above the target, so inflight_at_edt includes * bbr_tso_segs_goal() from the skb departing at EDT. If decreasing inflight, * then estimate if inflight will sink too low just before the EDT transmit. */ static u32 bbr_packets_in_net_at_edt(struct sock *sk, u32 inflight_now) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u64 now_ns, edt_ns, interval_us; u32 interval_delivered, inflight_at_edt; now_ns = tp->tcp_clock_cache; edt_ns = max(tp->tcp_wstamp_ns, now_ns); interval_us = div_u64(edt_ns - now_ns, NSEC_PER_USEC); interval_delivered = (u64)bbr_bw(sk) * interval_us >> BW_SCALE; inflight_at_edt = inflight_now; if (bbr->pacing_gain > BBR_UNIT) /* increasing inflight */ inflight_at_edt += bbr_tso_segs_goal(sk); /* include EDT skb */ if (interval_delivered >= inflight_at_edt) return 0; return inflight_at_edt - interval_delivered; } /* Find the cwnd increment based on estimate of ack aggregation */ static u32 bbr_ack_aggregation_cwnd(struct sock *sk) { u32 max_aggr_cwnd, aggr_cwnd = 0; if (bbr_extra_acked_gain && bbr_full_bw_reached(sk)) { max_aggr_cwnd = ((u64)bbr_bw(sk) * bbr_extra_acked_max_us) / BW_UNIT; aggr_cwnd = (bbr_extra_acked_gain * bbr_extra_acked(sk)) >> BBR_SCALE; aggr_cwnd = min(aggr_cwnd, max_aggr_cwnd); } return aggr_cwnd; } /* An optimization in BBR to reduce losses: On the first round of recovery, we * follow the packet conservation principle: send P packets per P packets acked. * After that, we slow-start and send at most 2*P packets per P packets acked. * After recovery finishes, or upon undo, we restore the cwnd we had when * recovery started (capped by the target cwnd based on estimated BDP). * * TODO(ycheng/ncardwell): implement a rate-based approach. */ static bool bbr_set_cwnd_to_recover_or_restore( struct sock *sk, const struct rate_sample *rs, u32 acked, u32 *new_cwnd) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u8 prev_state = bbr->prev_ca_state, state = inet_csk(sk)->icsk_ca_state; u32 cwnd = tcp_snd_cwnd(tp); /* An ACK for P pkts should release at most 2*P packets. We do this * in two steps. First, here we deduct the number of lost packets. * Then, in bbr_set_cwnd() we slow start up toward the target cwnd. */ if (rs->losses > 0) cwnd = max_t(s32, cwnd - rs->losses, 1); if (state == TCP_CA_Recovery && prev_state != TCP_CA_Recovery) { /* Starting 1st round of Recovery, so do packet conservation. */ bbr->packet_conservation = 1; bbr->next_rtt_delivered = tp->delivered; /* start round now */ /* Cut unused cwnd from app behavior, TSQ, or TSO deferral: */ cwnd = tcp_packets_in_flight(tp) + acked; } else if (prev_state >= TCP_CA_Recovery && state < TCP_CA_Recovery) { /* Exiting loss recovery; restore cwnd saved before recovery. */ cwnd = max(cwnd, bbr->prior_cwnd); bbr->packet_conservation = 0; } bbr->prev_ca_state = state; if (bbr->packet_conservation) { *new_cwnd = max(cwnd, tcp_packets_in_flight(tp) + acked); return true; /* yes, using packet conservation */ } *new_cwnd = cwnd; return false; } /* Slow-start up toward target cwnd (if bw estimate is growing, or packet loss * has drawn us down below target), or snap down to target if we're above it. */ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs, u32 acked, u32 bw, int gain) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u32 cwnd = tcp_snd_cwnd(tp), target_cwnd = 0; if (!acked) goto done; /* no packet fully ACKed; just apply caps */ if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd)) goto done; target_cwnd = bbr_bdp(sk, bw, gain); /* Increment the cwnd to account for excess ACKed data that seems * due to aggregation (of data and/or ACKs) visible in the ACK stream. */ target_cwnd += bbr_ack_aggregation_cwnd(sk); target_cwnd = bbr_quantization_budget(sk, target_cwnd); /* If we're below target cwnd, slow start cwnd toward target cwnd. */ if (bbr_full_bw_reached(sk)) /* only cut cwnd if we filled the pipe */ cwnd = min(cwnd + acked, target_cwnd); else if (cwnd < target_cwnd || tp->delivered < TCP_INIT_CWND) cwnd = cwnd + acked; cwnd = max(cwnd, bbr_cwnd_min_target); done: tcp_snd_cwnd_set(tp, min(cwnd, tp->snd_cwnd_clamp)); /* apply global cap */ if (bbr->mode == BBR_PROBE_RTT) /* drain queue, refresh min_rtt */ tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp), bbr_cwnd_min_target)); } /* End cycle phase if it's time and/or we hit the phase's in-flight target. */ static bool bbr_is_next_cycle_phase(struct sock *sk, const struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bool is_full_length = tcp_stamp_us_delta(tp->delivered_mstamp, bbr->cycle_mstamp) > bbr->min_rtt_us; u32 inflight, bw; /* The pacing_gain of 1.0 paces at the estimated bw to try to fully * use the pipe without increasing the queue. */ if (bbr->pacing_gain == BBR_UNIT) return is_full_length; /* just use wall clock time */ inflight = bbr_packets_in_net_at_edt(sk, rs->prior_in_flight); bw = bbr_max_bw(sk); /* A pacing_gain > 1.0 probes for bw by trying to raise inflight to at * least pacing_gain*BDP; this may take more than min_rtt if min_rtt is * small (e.g. on a LAN). We do not persist if packets are lost, since * a path with small buffers may not hold that much. */ if (bbr->pacing_gain > BBR_UNIT) return is_full_length && (rs->losses || /* perhaps pacing_gain*BDP won't fit */ inflight >= bbr_inflight(sk, bw, bbr->pacing_gain)); /* A pacing_gain < 1.0 tries to drain extra queue we added if bw * probing didn't find more bw. If inflight falls to match BDP then we * estimate queue is drained; persisting would underutilize the pipe. */ return is_full_length || inflight <= bbr_inflight(sk, bw, BBR_UNIT); } static void bbr_advance_cycle_phase(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1); bbr->cycle_mstamp = tp->delivered_mstamp; } /* Gain cycling: cycle pacing gain to converge to fair share of available bw. */ static void bbr_update_cycle_phase(struct sock *sk, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); if (bbr->mode == BBR_PROBE_BW && bbr_is_next_cycle_phase(sk, rs)) bbr_advance_cycle_phase(sk); } static void bbr_reset_startup_mode(struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); bbr->mode = BBR_STARTUP; } static void bbr_reset_probe_bw_mode(struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); bbr->mode = BBR_PROBE_BW; bbr->cycle_idx = CYCLE_LEN - 1 - get_random_u32_below(bbr_cycle_rand); bbr_advance_cycle_phase(sk); /* flip to next phase of gain cycle */ } static void bbr_reset_mode(struct sock *sk) { if (!bbr_full_bw_reached(sk)) bbr_reset_startup_mode(sk); else bbr_reset_probe_bw_mode(sk); } /* Start a new long-term sampling interval. */ static void bbr_reset_lt_bw_sampling_interval(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bbr->lt_last_stamp = div_u64(tp->delivered_mstamp, USEC_PER_MSEC); bbr->lt_last_delivered = tp->delivered; bbr->lt_last_lost = tp->lost; bbr->lt_rtt_cnt = 0; } /* Completely reset long-term bandwidth sampling. */ static void bbr_reset_lt_bw_sampling(struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); bbr->lt_bw = 0; bbr->lt_use_bw = 0; bbr->lt_is_sampling = false; bbr_reset_lt_bw_sampling_interval(sk); } /* Long-term bw sampling interval is done. Estimate whether we're policed. */ static void bbr_lt_bw_interval_done(struct sock *sk, u32 bw) { struct bbr *bbr = inet_csk_ca(sk); u32 diff; if (bbr->lt_bw) { /* do we have bw from a previous interval? */ /* Is new bw close to the lt_bw from the previous interval? */ diff = abs(bw - bbr->lt_bw); if ((diff * BBR_UNIT <= bbr_lt_bw_ratio * bbr->lt_bw) || (bbr_rate_bytes_per_sec(sk, diff, BBR_UNIT) <= bbr_lt_bw_diff)) { /* All criteria are met; estimate we're policed. */ bbr->lt_bw = (bw + bbr->lt_bw) >> 1; /* avg 2 intvls */ bbr->lt_use_bw = 1; bbr->pacing_gain = BBR_UNIT; /* try to avoid drops */ bbr->lt_rtt_cnt = 0; return; } } bbr->lt_bw = bw; bbr_reset_lt_bw_sampling_interval(sk); } /* Token-bucket traffic policers are common (see "An Internet-Wide Analysis of * Traffic Policing", SIGCOMM 2016). BBR detects token-bucket policers and * explicitly models their policed rate, to reduce unnecessary losses. We * estimate that we're policed if we see 2 consecutive sampling intervals with * consistent throughput and high packet loss. If we think we're being policed, * set lt_bw to the "long-term" average delivery rate from those 2 intervals. */ static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u32 lost, delivered; u64 bw; u32 t; if (bbr->lt_use_bw) { /* already using long-term rate, lt_bw? */ if (bbr->mode == BBR_PROBE_BW && bbr->round_start && ++bbr->lt_rtt_cnt >= bbr_lt_bw_max_rtts) { bbr_reset_lt_bw_sampling(sk); /* stop using lt_bw */ bbr_reset_probe_bw_mode(sk); /* restart gain cycling */ } return; } /* Wait for the first loss before sampling, to let the policer exhaust * its tokens and estimate the steady-state rate allowed by the policer. * Starting samples earlier includes bursts that over-estimate the bw. */ if (!bbr->lt_is_sampling) { if (!rs->losses) return; bbr_reset_lt_bw_sampling_interval(sk); bbr->lt_is_sampling = true; } /* To avoid underestimates, reset sampling if we run out of data. */ if (rs->is_app_limited) { bbr_reset_lt_bw_sampling(sk); return; } if (bbr->round_start) bbr->lt_rtt_cnt++; /* count round trips in this interval */ if (bbr->lt_rtt_cnt < bbr_lt_intvl_min_rtts) return; /* sampling interval needs to be longer */ if (bbr->lt_rtt_cnt > 4 * bbr_lt_intvl_min_rtts) { bbr_reset_lt_bw_sampling(sk); /* interval is too long */ return; } /* End sampling interval when a packet is lost, so we estimate the * policer tokens were exhausted. Stopping the sampling before the * tokens are exhausted under-estimates the policed rate. */ if (!rs->losses) return; /* Calculate packets lost and delivered in sampling interval. */ lost = tp->lost - bbr->lt_last_lost; delivered = tp->delivered - bbr->lt_last_delivered; /* Is loss rate (lost/delivered) >= lt_loss_thresh? If not, wait. */ if (!delivered || (lost << BBR_SCALE) < bbr_lt_loss_thresh * delivered) return; /* Find average delivery rate in this sampling interval. */ t = div_u64(tp->delivered_mstamp, USEC_PER_MSEC) - bbr->lt_last_stamp; if ((s32)t < 1) return; /* interval is less than one ms, so wait */ /* Check if can multiply without overflow */ if (t >= ~0U / USEC_PER_MSEC) { bbr_reset_lt_bw_sampling(sk); /* interval too long; reset */ return; } t *= USEC_PER_MSEC; bw = (u64)delivered * BW_UNIT; do_div(bw, t); bbr_lt_bw_interval_done(sk, bw); } /* Estimate the bandwidth based on how fast packets are delivered */ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u64 bw; bbr->round_start = 0; if (rs->delivered < 0 || rs->interval_us <= 0) return; /* Not a valid observation */ /* See if we've reached the next RTT */ if (!before(rs->prior_delivered, bbr->next_rtt_delivered)) { bbr->next_rtt_delivered = tp->delivered; bbr->rtt_cnt++; bbr->round_start = 1; bbr->packet_conservation = 0; } bbr_lt_bw_sampling(sk, rs); /* Divide delivered by the interval to find a (lower bound) bottleneck * bandwidth sample. Delivered is in packets and interval_us in uS and * ratio will be <<1 for most connections. So delivered is first scaled. */ bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us); /* If this sample is application-limited, it is likely to have a very * low delivered count that represents application behavior rather than * the available network rate. Such a sample could drag down estimated * bw, causing needless slow-down. Thus, to continue to send at the * last measured network rate, we filter out app-limited samples unless * they describe the path bw at least as well as our bw model. * * So the goal during app-limited phase is to proceed with the best * network rate no matter how long. We automatically leave this * phase when app writes faster than the network can deliver :) */ if (!rs->is_app_limited || bw >= bbr_max_bw(sk)) { /* Incorporate new sample into our max bw filter. */ minmax_running_max(&bbr->bw, bbr_bw_rtts, bbr->rtt_cnt, bw); } } /* Estimates the windowed max degree of ack aggregation. * This is used to provision extra in-flight data to keep sending during * inter-ACK silences. * * Degree of ack aggregation is estimated as extra data acked beyond expected. * * max_extra_acked = "maximum recent excess data ACKed beyond max_bw * interval" * cwnd += max_extra_acked * * Max extra_acked is clamped by cwnd and bw * bbr_extra_acked_max_us (100 ms). * Max filter is an approximate sliding window of 5-10 (packet timed) round * trips. */ static void bbr_update_ack_aggregation(struct sock *sk, const struct rate_sample *rs) { u32 epoch_us, expected_acked, extra_acked; struct bbr *bbr = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); if (!bbr_extra_acked_gain || rs->acked_sacked <= 0 || rs->delivered < 0 || rs->interval_us <= 0) return; if (bbr->round_start) { bbr->extra_acked_win_rtts = min(0x1F, bbr->extra_acked_win_rtts + 1); if (bbr->extra_acked_win_rtts >= bbr_extra_acked_win_rtts) { bbr->extra_acked_win_rtts = 0; bbr->extra_acked_win_idx = bbr->extra_acked_win_idx ? 0 : 1; bbr->extra_acked[bbr->extra_acked_win_idx] = 0; } } /* Compute how many packets we expected to be delivered over epoch. */ epoch_us = tcp_stamp_us_delta(tp->delivered_mstamp, bbr->ack_epoch_mstamp); expected_acked = ((u64)bbr_bw(sk) * epoch_us) / BW_UNIT; /* Reset the aggregation epoch if ACK rate is below expected rate or * significantly large no. of ack received since epoch (potentially * quite old epoch). */ if (bbr->ack_epoch_acked <= expected_acked || (bbr->ack_epoch_acked + rs->acked_sacked >= bbr_ack_epoch_acked_reset_thresh)) { bbr->ack_epoch_acked = 0; bbr->ack_epoch_mstamp = tp->delivered_mstamp; expected_acked = 0; } /* Compute excess data delivered, beyond what was expected. */ bbr->ack_epoch_acked = min_t(u32, 0xFFFFF, bbr->ack_epoch_acked + rs->acked_sacked); extra_acked = bbr->ack_epoch_acked - expected_acked; extra_acked = min(extra_acked, tcp_snd_cwnd(tp)); if (extra_acked > bbr->extra_acked[bbr->extra_acked_win_idx]) bbr->extra_acked[bbr->extra_acked_win_idx] = extra_acked; } /* Estimate when the pipe is full, using the change in delivery rate: BBR * estimates that STARTUP filled the pipe if the estimated bw hasn't changed by * at least bbr_full_bw_thresh (25%) after bbr_full_bw_cnt (3) non-app-limited * rounds. Why 3 rounds: 1: rwin autotuning grows the rwin, 2: we fill the * higher rwin, 3: we get higher delivery rate samples. Or transient * cross-traffic or radio noise can go away. CUBIC Hystart shares a similar * design goal, but uses delay and inter-ACK spacing instead of bandwidth. */ static void bbr_check_full_bw_reached(struct sock *sk, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); u32 bw_thresh; if (bbr_full_bw_reached(sk) || !bbr->round_start || rs->is_app_limited) return; bw_thresh = (u64)bbr->full_bw * bbr_full_bw_thresh >> BBR_SCALE; if (bbr_max_bw(sk) >= bw_thresh) { bbr->full_bw = bbr_max_bw(sk); bbr->full_bw_cnt = 0; return; } ++bbr->full_bw_cnt; bbr->full_bw_reached = bbr->full_bw_cnt >= bbr_full_bw_cnt; } /* If pipe is probably full, drain the queue and then enter steady-state. */ static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); if (bbr->mode == BBR_STARTUP && bbr_full_bw_reached(sk)) { bbr->mode = BBR_DRAIN; /* drain queue we created */ WRITE_ONCE(tcp_sk(sk)->snd_ssthresh, bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT)); } /* fall through to check if in-flight is already small: */ if (bbr->mode == BBR_DRAIN && bbr_packets_in_net_at_edt(sk, tcp_packets_in_flight(tcp_sk(sk))) <= bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT)) bbr_reset_probe_bw_mode(sk); /* we estimate queue is drained */ } static void bbr_check_probe_rtt_done(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); if (!(bbr->probe_rtt_done_stamp && after(tcp_jiffies32, bbr->probe_rtt_done_stamp))) return; bbr->min_rtt_stamp = tcp_jiffies32; /* wait a while until PROBE_RTT */ tcp_snd_cwnd_set(tp, max(tcp_snd_cwnd(tp), bbr->prior_cwnd)); bbr_reset_mode(sk); } /* The goal of PROBE_RTT mode is to have BBR flows cooperatively and * periodically drain the bottleneck queue, to converge to measure the true * min_rtt (unloaded propagation delay). This allows the flows to keep queues * small (reducing queuing delay and packet loss) and achieve fairness among * BBR flows. * * The min_rtt filter window is 10 seconds. When the min_rtt estimate expires, * we enter PROBE_RTT mode and cap the cwnd at bbr_cwnd_min_target=4 packets. * After at least bbr_probe_rtt_mode_ms=200ms and at least one packet-timed * round trip elapsed with that flight size <= 4, we leave PROBE_RTT mode and * re-enter the previous mode. BBR uses 200ms to approximately bound the * performance penalty of PROBE_RTT's cwnd capping to roughly 2% (200ms/10s). * * Note that flows need only pay 2% if they are busy sending over the last 10 * seconds. Interactive applications (e.g., Web, RPCs, video chunks) often have * natural silences or low-rate periods within 10 seconds where the rate is low * enough for long enough to drain its queue in the bottleneck. We pick up * these min RTT measurements opportunistically with our min_rtt filter. :-) */ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bool filter_expired; /* Track min RTT seen in the min_rtt_win_sec filter window: */ filter_expired = after(tcp_jiffies32, bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ); if (rs->rtt_us >= 0 && (rs->rtt_us < bbr->min_rtt_us || (filter_expired && !rs->is_ack_delayed))) { bbr->min_rtt_us = rs->rtt_us; bbr->min_rtt_stamp = tcp_jiffies32; } if (bbr_probe_rtt_mode_ms > 0 && filter_expired && !bbr->idle_restart && bbr->mode != BBR_PROBE_RTT) { bbr->mode = BBR_PROBE_RTT; /* dip, drain queue */ bbr_save_cwnd(sk); /* note cwnd so we can restore it */ bbr->probe_rtt_done_stamp = 0; } if (bbr->mode == BBR_PROBE_RTT) { /* Ignore low rate samples during this mode. */ tp->app_limited = (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; /* Maintain min packets in flight for max(200 ms, 1 round). */ if (!bbr->probe_rtt_done_stamp && tcp_packets_in_flight(tp) <= bbr_cwnd_min_target) { bbr->probe_rtt_done_stamp = tcp_jiffies32 + msecs_to_jiffies(bbr_probe_rtt_mode_ms); bbr->probe_rtt_round_done = 0; bbr->next_rtt_delivered = tp->delivered; } else if (bbr->probe_rtt_done_stamp) { if (bbr->round_start) bbr->probe_rtt_round_done = 1; if (bbr->probe_rtt_round_done) bbr_check_probe_rtt_done(sk); } } /* Restart after idle ends only once we process a new S/ACK for data */ if (rs->delivered > 0) bbr->idle_restart = 0; } static void bbr_update_gains(struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); switch (bbr->mode) { case BBR_STARTUP: bbr->pacing_gain = bbr_high_gain; bbr->cwnd_gain = bbr_high_gain; break; case BBR_DRAIN: bbr->pacing_gain = bbr_drain_gain; /* slow, to drain */ bbr->cwnd_gain = bbr_high_gain; /* keep cwnd */ break; case BBR_PROBE_BW: bbr->pacing_gain = (bbr->lt_use_bw ? BBR_UNIT : bbr_pacing_gain[bbr->cycle_idx]); bbr->cwnd_gain = bbr_cwnd_gain; break; case BBR_PROBE_RTT: bbr->pacing_gain = BBR_UNIT; bbr->cwnd_gain = BBR_UNIT; break; default: WARN_ONCE(1, "BBR bad mode: %u\n", bbr->mode); break; } } static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) { bbr_update_bw(sk, rs); bbr_update_ack_aggregation(sk, rs); bbr_update_cycle_phase(sk, rs); bbr_check_full_bw_reached(sk, rs); bbr_check_drain(sk, rs); bbr_update_min_rtt(sk, rs); bbr_update_gains(sk); } __bpf_kfunc static void bbr_main(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); u32 bw; bbr_update_model(sk, rs); bw = bbr_bw(sk); bbr_set_pacing_rate(sk, bw, bbr->pacing_gain); bbr_set_cwnd(sk, rs, rs->acked_sacked, bw, bbr->cwnd_gain); } __bpf_kfunc static void bbr_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bbr->prior_cwnd = 0; WRITE_ONCE(tp->snd_ssthresh, TCP_INFINITE_SSTHRESH); bbr->rtt_cnt = 0; bbr->next_rtt_delivered = tp->delivered; bbr->prev_ca_state = TCP_CA_Open; bbr->packet_conservation = 0; bbr->probe_rtt_done_stamp = 0; bbr->probe_rtt_round_done = 0; bbr->min_rtt_us = tcp_min_rtt(tp); bbr->min_rtt_stamp = tcp_jiffies32; minmax_reset(&bbr->bw, bbr->rtt_cnt, 0); /* init max bw to 0 */ bbr->has_seen_rtt = 0; bbr_init_pacing_rate_from_rtt(sk); bbr->round_start = 0; bbr->idle_restart = 0; bbr->full_bw_reached = 0; bbr->full_bw = 0; bbr->full_bw_cnt = 0; bbr->cycle_mstamp = 0; bbr->cycle_idx = 0; bbr_reset_lt_bw_sampling(sk); bbr_reset_startup_mode(sk); bbr->ack_epoch_mstamp = tp->tcp_mstamp; bbr->ack_epoch_acked = 0; bbr->extra_acked_win_rtts = 0; bbr->extra_acked_win_idx = 0; bbr->extra_acked[0] = 0; bbr->extra_acked[1] = 0; cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); } __bpf_kfunc static u32 bbr_sndbuf_expand(struct sock *sk) { /* Provision 3 * cwnd since BBR may slow-start even during recovery. */ return 3; } /* In theory BBR does not need to undo the cwnd since it does not * always reduce cwnd on losses (see bbr_main()). Keep it for now. */ __bpf_kfunc static u32 bbr_undo_cwnd(struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); bbr->full_bw = 0; /* spurious slow-down; reset full pipe detection */ bbr->full_bw_cnt = 0; bbr_reset_lt_bw_sampling(sk); return tcp_snd_cwnd(tcp_sk(sk)); } /* Entering loss recovery, so save cwnd for when we exit or undo recovery. */ __bpf_kfunc static u32 bbr_ssthresh(struct sock *sk) { bbr_save_cwnd(sk); return tcp_sk(sk)->snd_ssthresh; } static size_t bbr_get_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { if (ext & (1 << (INET_DIAG_BBRINFO - 1)) || ext & (1 << (INET_DIAG_VEGASINFO - 1))) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u64 bw = bbr_bw(sk); bw = bw * tp->mss_cache * USEC_PER_SEC >> BW_SCALE; memset(&info->bbr, 0, sizeof(info->bbr)); info->bbr.bbr_bw_lo = (u32)bw; info->bbr.bbr_bw_hi = (u32)(bw >> 32); info->bbr.bbr_min_rtt = bbr->min_rtt_us; info->bbr.bbr_pacing_gain = bbr->pacing_gain; info->bbr.bbr_cwnd_gain = bbr->cwnd_gain; *attr = INET_DIAG_BBRINFO; return sizeof(info->bbr); } return 0; } __bpf_kfunc static void bbr_set_state(struct sock *sk, u8 new_state) { struct bbr *bbr = inet_csk_ca(sk); if (new_state == TCP_CA_Loss) { struct rate_sample rs = { .losses = 1 }; bbr->prev_ca_state = TCP_CA_Loss; bbr->full_bw = 0; bbr->round_start = 1; /* treat RTO like end of a round */ bbr_lt_bw_sampling(sk, &rs); } } static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { .flags = TCP_CONG_NON_RESTRICTED, .name = "bbr", .owner = THIS_MODULE, .init = bbr_init, .cong_control = bbr_main, .sndbuf_expand = bbr_sndbuf_expand, .undo_cwnd = bbr_undo_cwnd, .cwnd_event_tx_start = bbr_cwnd_event_tx_start, .ssthresh = bbr_ssthresh, .min_tso_segs = bbr_min_tso_segs, .get_info = bbr_get_info, .set_state = bbr_set_state, }; BTF_KFUNCS_START(tcp_bbr_check_kfunc_ids) BTF_ID_FLAGS(func, bbr_init) BTF_ID_FLAGS(func, bbr_main) BTF_ID_FLAGS(func, bbr_sndbuf_expand) BTF_ID_FLAGS(func, bbr_undo_cwnd) BTF_ID_FLAGS(func, bbr_cwnd_event_tx_start) BTF_ID_FLAGS(func, bbr_ssthresh) BTF_ID_FLAGS(func, bbr_min_tso_segs) BTF_ID_FLAGS(func, bbr_set_state) BTF_KFUNCS_END(tcp_bbr_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = { .owner = THIS_MODULE, .set = &tcp_bbr_check_kfunc_ids, }; static int __init bbr_register(void) { int ret; BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE); ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_bbr_kfunc_set); if (ret < 0) return ret; return tcp_register_congestion_control(&tcp_bbr_cong_ops); } static void __exit bbr_unregister(void) { tcp_unregister_congestion_control(&tcp_bbr_cong_ops); } module_init(bbr_register); module_exit(bbr_unregister); MODULE_AUTHOR("Van Jacobson <vanj@google.com>"); MODULE_AUTHOR("Neal Cardwell <ncardwell@google.com>"); MODULE_AUTHOR("Yuchung Cheng <ycheng@google.com>"); MODULE_AUTHOR("Soheil Hassas Yeganeh <soheil@google.com>"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("TCP BBR (Bottleneck Bandwidth and RTT)"); |
| 301 15 3 1 71 1 8 376 3 390 48 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2009-2021 Christoph Hellwig * * NOTE: none of these tracepoints shall be considered a stable kernel ABI * as they can change at any time. * * Current conventions for printing numbers measuring specific units: * * offset: byte offset into a subcomponent of a file operation * pos: file offset, in bytes * length: length of a file operation, in bytes * ino: inode number * * Numbers describing space allocations should be formatted in hexadecimal. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM iomap #if !defined(_IOMAP_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define _IOMAP_TRACE_H #include <linux/tracepoint.h> struct inode; DECLARE_EVENT_CLASS(iomap_readpage_class, TP_PROTO(struct inode *inode, int nr_pages), TP_ARGS(inode, nr_pages), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(int, nr_pages) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nr_pages = nr_pages; ), TP_printk("dev %d:%d ino 0x%llx nr_pages %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->nr_pages) ) #define DEFINE_READPAGE_EVENT(name) \ DEFINE_EVENT(iomap_readpage_class, name, \ TP_PROTO(struct inode *inode, int nr_pages), \ TP_ARGS(inode, nr_pages)) DEFINE_READPAGE_EVENT(iomap_readpage); DEFINE_READPAGE_EVENT(iomap_readahead); DECLARE_EVENT_CLASS(iomap_range_class, TP_PROTO(struct inode *inode, loff_t off, u64 len), TP_ARGS(inode, off, len), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, size) __field(loff_t, offset) __field(u64, length) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->size = i_size_read(inode); __entry->offset = off; __entry->length = len; ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx length 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, __entry->offset, __entry->length) ) #define DEFINE_RANGE_EVENT(name) \ DEFINE_EVENT(iomap_range_class, name, \ TP_PROTO(struct inode *inode, loff_t off, u64 len),\ TP_ARGS(inode, off, len)) DEFINE_RANGE_EVENT(iomap_writeback_folio); DEFINE_RANGE_EVENT(iomap_release_folio); DEFINE_RANGE_EVENT(iomap_invalidate_folio); DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); DEFINE_RANGE_EVENT(iomap_dio_rw_queued); DEFINE_RANGE_EVENT(iomap_zero_iter); #define IOMAP_TYPE_STRINGS \ { IOMAP_HOLE, "HOLE" }, \ { IOMAP_DELALLOC, "DELALLOC" }, \ { IOMAP_MAPPED, "MAPPED" }, \ { IOMAP_UNWRITTEN, "UNWRITTEN" }, \ { IOMAP_INLINE, "INLINE" } #define IOMAP_FLAGS_STRINGS \ { IOMAP_WRITE, "WRITE" }, \ { IOMAP_ZERO, "ZERO" }, \ { IOMAP_REPORT, "REPORT" }, \ { IOMAP_FAULT, "FAULT" }, \ { IOMAP_DIRECT, "DIRECT" }, \ { IOMAP_NOWAIT, "NOWAIT" }, \ { IOMAP_OVERWRITE_ONLY, "OVERWRITE_ONLY" }, \ { IOMAP_UNSHARE, "UNSHARE" }, \ { IOMAP_DAX, "DAX" }, \ { IOMAP_ATOMIC, "ATOMIC" }, \ { IOMAP_DONTCACHE, "DONTCACHE" } #define IOMAP_F_FLAGS_STRINGS \ { IOMAP_F_NEW, "NEW" }, \ { IOMAP_F_DIRTY, "DIRTY" }, \ { IOMAP_F_SHARED, "SHARED" }, \ { IOMAP_F_MERGED, "MERGED" }, \ { IOMAP_F_BUFFER_HEAD, "BH" }, \ { IOMAP_F_XATTR, "XATTR" }, \ { IOMAP_F_BOUNDARY, "BOUNDARY" }, \ { IOMAP_F_ANON_WRITE, "ANON_WRITE" }, \ { IOMAP_F_ATOMIC_BIO, "ATOMIC_BIO" }, \ { IOMAP_F_PRIVATE, "PRIVATE" }, \ { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" }, \ { IOMAP_F_STALE, "STALE" } #define IOMAP_DIO_STRINGS \ {IOMAP_DIO_FORCE_WAIT, "DIO_FORCE_WAIT" }, \ {IOMAP_DIO_OVERWRITE_ONLY, "DIO_OVERWRITE_ONLY" }, \ {IOMAP_DIO_PARTIAL, "DIO_PARTIAL" }, \ {IOMAP_DIO_FSBLOCK_ALIGNED, "DIO_FSBLOCK_ALIGNED" } DECLARE_EVENT_CLASS(iomap_class, TP_PROTO(struct inode *inode, struct iomap *iomap), TP_ARGS(inode, iomap), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(u64, addr) __field(loff_t, offset) __field(u64, length) __field(u16, type) __field(u16, flags) __field(dev_t, bdev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->addr = iomap->addr; __entry->offset = iomap->offset; __entry->length = iomap->length; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d addr 0x%llx offset 0x%llx " "length 0x%llx type %s (0x%x) flags %s (0x%x)", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, MAJOR(__entry->bdev), MINOR(__entry->bdev), __entry->addr, __entry->offset, __entry->length, __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), __entry->type, __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS), __entry->flags) ) #define DEFINE_IOMAP_EVENT(name) \ DEFINE_EVENT(iomap_class, name, \ TP_PROTO(struct inode *inode, struct iomap *iomap), \ TP_ARGS(inode, iomap)) DEFINE_IOMAP_EVENT(iomap_iter_dstmap); DEFINE_IOMAP_EVENT(iomap_iter_srcmap); TRACE_EVENT(iomap_add_to_ioend, TP_PROTO(struct inode *inode, u64 pos, unsigned int dirty_len, struct iomap *iomap), TP_ARGS(inode, pos, dirty_len, iomap), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(u64, pos) __field(u64, dirty_len) __field(u64, addr) __field(loff_t, offset) __field(u64, length) __field(u16, type) __field(u16, flags) __field(dev_t, bdev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->dirty_len = dirty_len; __entry->addr = iomap->addr; __entry->offset = iomap->offset; __entry->length = iomap->length; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d pos 0x%llx dirty len 0x%llx " "addr 0x%llx offset 0x%llx length 0x%llx type %s (0x%x) flags %s (0x%x)", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, MAJOR(__entry->bdev), MINOR(__entry->bdev), __entry->pos, __entry->dirty_len, __entry->addr, __entry->offset, __entry->length, __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), __entry->type, __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS), __entry->flags) ); TRACE_EVENT(iomap_iter, TP_PROTO(struct iomap_iter *iter, const void *ops, unsigned long caller), TP_ARGS(iter, ops, caller), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, pos) __field(u64, length) __field(int, status) __field(unsigned int, flags) __field(const void *, ops) __field(unsigned long, caller) ), TP_fast_assign( __entry->dev = iter->inode->i_sb->s_dev; __entry->ino = iter->inode->i_ino; __entry->pos = iter->pos; __entry->length = iomap_length(iter); __entry->status = iter->status; __entry->flags = iter->flags; __entry->ops = ops; __entry->caller = caller; ), TP_printk("dev %d:%d ino 0x%llx pos 0x%llx length 0x%llx status %d flags %s (0x%x) ops %ps caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->pos, __entry->length, __entry->status, __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS), __entry->flags, __entry->ops, (void *)__entry->caller) ); TRACE_EVENT(iomap_dio_rw_begin, TP_PROTO(struct kiocb *iocb, struct iov_iter *iter, unsigned int dio_flags, size_t done_before), TP_ARGS(iocb, iter, dio_flags, done_before), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, isize) __field(loff_t, pos) __field(size_t, count) __field(size_t, done_before) __field(int, ki_flags) __field(unsigned int, dio_flags) __field(bool, aio) ), TP_fast_assign( __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; __entry->ino = file_inode(iocb->ki_filp)->i_ino; __entry->isize = file_inode(iocb->ki_filp)->i_size; __entry->pos = iocb->ki_pos; __entry->count = iov_iter_count(iter); __entry->done_before = done_before; __entry->ki_flags = iocb->ki_flags; __entry->dio_flags = dio_flags; __entry->aio = !is_sync_kiocb(iocb); ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx length 0x%zx done_before 0x%zx flags %s dio_flags %s aio %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->isize, __entry->pos, __entry->count, __entry->done_before, __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), __print_flags(__entry->dio_flags, "|", IOMAP_DIO_STRINGS), __entry->aio) ); TRACE_EVENT(iomap_dio_complete, TP_PROTO(struct kiocb *iocb, int error, ssize_t ret), TP_ARGS(iocb, error, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, isize) __field(loff_t, pos) __field(int, ki_flags) __field(bool, aio) __field(int, error) __field(ssize_t, ret) ), TP_fast_assign( __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; __entry->ino = file_inode(iocb->ki_filp)->i_ino; __entry->isize = file_inode(iocb->ki_filp)->i_size; __entry->pos = iocb->ki_pos; __entry->ki_flags = iocb->ki_flags; __entry->aio = !is_sync_kiocb(iocb); __entry->error = error; __entry->ret = ret; ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx flags %s aio %d error %d ret %zd", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->isize, __entry->pos, __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), __entry->aio, __entry->error, __entry->ret) ); #endif /* _IOMAP_TRACE_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 2 2 2 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2014 Protonic Holland, * David Jander * Copyright (C) 2014-2021, 2023 Pengutronix, * Marc Kleine-Budde <kernel@pengutronix.de> */ #include <linux/can/dev.h> #include <linux/can/rx-offload.h> struct can_rx_offload_cb { u32 timestamp; }; static inline struct can_rx_offload_cb * can_rx_offload_get_cb(struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct can_rx_offload_cb) > sizeof(skb->cb)); return (struct can_rx_offload_cb *)skb->cb; } static inline bool can_rx_offload_le(struct can_rx_offload *offload, unsigned int a, unsigned int b) { if (offload->inc) return a <= b; else return a >= b; } static inline unsigned int can_rx_offload_inc(struct can_rx_offload *offload, unsigned int *val) { if (offload->inc) return (*val)++; else return (*val)--; } static int can_rx_offload_napi_poll(struct napi_struct *napi, int quota) { struct can_rx_offload *offload = container_of(napi, struct can_rx_offload, napi); struct net_device *dev = offload->dev; struct net_device_stats *stats = &dev->stats; struct sk_buff *skb; int work_done = 0; while ((work_done < quota) && (skb = skb_dequeue(&offload->skb_queue))) { struct can_frame *cf = (struct can_frame *)skb->data; work_done++; if (!(cf->can_id & CAN_ERR_FLAG)) { stats->rx_packets++; if (!(cf->can_id & CAN_RTR_FLAG)) stats->rx_bytes += cf->len; } netif_receive_skb(skb); } if (work_done < quota) { napi_complete_done(napi, work_done); /* Check if there was another interrupt */ if (!skb_queue_empty(&offload->skb_queue)) napi_schedule(&offload->napi); } return work_done; } static inline void __skb_queue_add_sort(struct sk_buff_head *head, struct sk_buff *new, int (*compare)(struct sk_buff *a, struct sk_buff *b)) { struct sk_buff *pos, *insert = NULL; skb_queue_reverse_walk(head, pos) { const struct can_rx_offload_cb *cb_pos, *cb_new; cb_pos = can_rx_offload_get_cb(pos); cb_new = can_rx_offload_get_cb(new); netdev_dbg(new->dev, "%s: pos=0x%08x, new=0x%08x, diff=%10d, queue_len=%d\n", __func__, cb_pos->timestamp, cb_new->timestamp, cb_new->timestamp - cb_pos->timestamp, skb_queue_len(head)); if (compare(pos, new) < 0) continue; insert = pos; break; } if (!insert) __skb_queue_head(head, new); else __skb_queue_after(head, insert, new); } static int can_rx_offload_compare(struct sk_buff *a, struct sk_buff *b) { const struct can_rx_offload_cb *cb_a, *cb_b; cb_a = can_rx_offload_get_cb(a); cb_b = can_rx_offload_get_cb(b); /* Subtract two u32 and return result as int, to keep * difference steady around the u32 overflow. */ return cb_b->timestamp - cb_a->timestamp; } /** * can_rx_offload_offload_one() - Read one CAN frame from HW * @offload: pointer to rx_offload context * @n: number of mailbox to read * * The task of this function is to read a CAN frame from mailbox @n * from the device and return the mailbox's content as a struct * sk_buff. * * If the struct can_rx_offload::skb_queue exceeds the maximal queue * length (struct can_rx_offload::skb_queue_len_max) or no skb can be * allocated, the mailbox contents is discarded by reading it into an * overflow buffer. This way the mailbox is marked as free by the * driver. * * Return: A pointer to skb containing the CAN frame on success. * * NULL if the mailbox @n is empty. * * ERR_PTR() in case of an error */ static struct sk_buff * can_rx_offload_offload_one(struct can_rx_offload *offload, unsigned int n) { struct sk_buff *skb; struct can_rx_offload_cb *cb; bool drop = false; u32 timestamp; /* If queue is full drop frame */ if (unlikely(skb_queue_len(&offload->skb_queue) > offload->skb_queue_len_max)) drop = true; skb = offload->mailbox_read(offload, n, ×tamp, drop); /* Mailbox was empty. */ if (unlikely(!skb)) return NULL; /* There was a problem reading the mailbox, propagate * error value. */ if (IS_ERR(skb)) { offload->dev->stats.rx_dropped++; offload->dev->stats.rx_fifo_errors++; return skb; } /* Mailbox was read. */ cb = can_rx_offload_get_cb(skb); cb->timestamp = timestamp; return skb; } int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 pending) { unsigned int i; int received = 0; for (i = offload->mb_first; can_rx_offload_le(offload, i, offload->mb_last); can_rx_offload_inc(offload, &i)) { struct sk_buff *skb; if (!(pending & BIT_ULL(i))) continue; skb = can_rx_offload_offload_one(offload, i); if (IS_ERR_OR_NULL(skb)) continue; __skb_queue_add_sort(&offload->skb_irq_queue, skb, can_rx_offload_compare); received++; } return received; } EXPORT_SYMBOL_GPL(can_rx_offload_irq_offload_timestamp); int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload) { struct sk_buff *skb; int received = 0; while (1) { skb = can_rx_offload_offload_one(offload, 0); if (IS_ERR(skb)) continue; if (!skb) break; __skb_queue_tail(&offload->skb_irq_queue, skb); received++; } return received; } EXPORT_SYMBOL_GPL(can_rx_offload_irq_offload_fifo); int can_rx_offload_queue_timestamp(struct can_rx_offload *offload, struct sk_buff *skb, u32 timestamp) { struct can_rx_offload_cb *cb; if (skb_queue_len(&offload->skb_queue) > offload->skb_queue_len_max) { dev_kfree_skb_any(skb); return -ENOBUFS; } cb = can_rx_offload_get_cb(skb); cb->timestamp = timestamp; __skb_queue_add_sort(&offload->skb_irq_queue, skb, can_rx_offload_compare); return 0; } EXPORT_SYMBOL_GPL(can_rx_offload_queue_timestamp); unsigned int can_rx_offload_get_echo_skb_queue_timestamp(struct can_rx_offload *offload, unsigned int idx, u32 timestamp, unsigned int *frame_len_ptr) { struct net_device *dev = offload->dev; struct net_device_stats *stats = &dev->stats; struct sk_buff *skb; unsigned int len; int err; skb = __can_get_echo_skb(dev, idx, &len, frame_len_ptr); if (!skb) return 0; err = can_rx_offload_queue_timestamp(offload, skb, timestamp); if (err) { stats->rx_errors++; stats->tx_fifo_errors++; } return len; } EXPORT_SYMBOL_GPL(can_rx_offload_get_echo_skb_queue_timestamp); int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb) { if (skb_queue_len(&offload->skb_queue) > offload->skb_queue_len_max) { dev_kfree_skb_any(skb); return -ENOBUFS; } __skb_queue_tail(&offload->skb_irq_queue, skb); return 0; } EXPORT_SYMBOL_GPL(can_rx_offload_queue_tail); unsigned int can_rx_offload_get_echo_skb_queue_tail(struct can_rx_offload *offload, unsigned int idx, unsigned int *frame_len_ptr) { struct net_device *dev = offload->dev; struct net_device_stats *stats = &dev->stats; struct sk_buff *skb; unsigned int len; int err; skb = __can_get_echo_skb(dev, idx, &len, frame_len_ptr); if (!skb) return 0; err = can_rx_offload_queue_tail(offload, skb); if (err) { stats->rx_errors++; stats->tx_fifo_errors++; } return len; } EXPORT_SYMBOL_GPL(can_rx_offload_get_echo_skb_queue_tail); void can_rx_offload_irq_finish(struct can_rx_offload *offload) { unsigned long flags; int queue_len; if (skb_queue_empty_lockless(&offload->skb_irq_queue)) return; spin_lock_irqsave(&offload->skb_queue.lock, flags); skb_queue_splice_tail_init(&offload->skb_irq_queue, &offload->skb_queue); spin_unlock_irqrestore(&offload->skb_queue.lock, flags); queue_len = skb_queue_len(&offload->skb_queue); if (queue_len > offload->skb_queue_len_max / 8) netdev_dbg(offload->dev, "%s: queue_len=%d\n", __func__, queue_len); napi_schedule(&offload->napi); } EXPORT_SYMBOL_GPL(can_rx_offload_irq_finish); void can_rx_offload_threaded_irq_finish(struct can_rx_offload *offload) { unsigned long flags; int queue_len; if (skb_queue_empty_lockless(&offload->skb_irq_queue)) return; spin_lock_irqsave(&offload->skb_queue.lock, flags); skb_queue_splice_tail_init(&offload->skb_irq_queue, &offload->skb_queue); spin_unlock_irqrestore(&offload->skb_queue.lock, flags); queue_len = skb_queue_len(&offload->skb_queue); if (queue_len > offload->skb_queue_len_max / 8) netdev_dbg(offload->dev, "%s: queue_len=%d\n", __func__, queue_len); local_bh_disable(); napi_schedule(&offload->napi); local_bh_enable(); } EXPORT_SYMBOL_GPL(can_rx_offload_threaded_irq_finish); static int can_rx_offload_init_queue(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight) { offload->dev = dev; /* Limit queue len to 4x the weight (rounded to next power of two) */ offload->skb_queue_len_max = 2 << fls(weight); offload->skb_queue_len_max *= 4; skb_queue_head_init(&offload->skb_queue); __skb_queue_head_init(&offload->skb_irq_queue); netif_napi_add_weight(dev, &offload->napi, can_rx_offload_napi_poll, weight); dev_dbg(dev->dev.parent, "%s: skb_queue_len_max=%d\n", __func__, offload->skb_queue_len_max); return 0; } int can_rx_offload_add_timestamp(struct net_device *dev, struct can_rx_offload *offload) { unsigned int weight; if (offload->mb_first > BITS_PER_LONG_LONG || offload->mb_last > BITS_PER_LONG_LONG || !offload->mailbox_read) return -EINVAL; if (offload->mb_first < offload->mb_last) { offload->inc = true; weight = offload->mb_last - offload->mb_first; } else { offload->inc = false; weight = offload->mb_first - offload->mb_last; } return can_rx_offload_init_queue(dev, offload, weight); } EXPORT_SYMBOL_GPL(can_rx_offload_add_timestamp); int can_rx_offload_add_fifo(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight) { if (!offload->mailbox_read) return -EINVAL; return can_rx_offload_init_queue(dev, offload, weight); } EXPORT_SYMBOL_GPL(can_rx_offload_add_fifo); int can_rx_offload_add_manual(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight) { if (offload->mailbox_read) return -EINVAL; return can_rx_offload_init_queue(dev, offload, weight); } EXPORT_SYMBOL_GPL(can_rx_offload_add_manual); void can_rx_offload_enable(struct can_rx_offload *offload) { napi_enable(&offload->napi); } EXPORT_SYMBOL_GPL(can_rx_offload_enable); void can_rx_offload_del(struct can_rx_offload *offload) { netif_napi_del(&offload->napi); skb_queue_purge(&offload->skb_queue); __skb_queue_purge(&offload->skb_irq_queue); } EXPORT_SYMBOL_GPL(can_rx_offload_del); |
| 1 1 1 1 1 1 5 5 5 1 1 1 1 1 1 1 5 5 5 5 5 5 5 5 5 5 5 5 5 1 1 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) International Business Machines Corp., 2006 * Copyright (c) Nokia Corporation, 2006, 2007 * * Author: Artem Bityutskiy (Битюцкий Артём) */ /* * This file includes volume table manipulation code. The volume table is an * on-flash table containing volume meta-data like name, number of reserved * physical eraseblocks, type, etc. The volume table is stored in the so-called * "layout volume". * * The layout volume is an internal volume which is organized as follows. It * consists of two logical eraseblocks - LEB 0 and LEB 1. Each logical * eraseblock stores one volume table copy, i.e. LEB 0 and LEB 1 duplicate each * other. This redundancy guarantees robustness to unclean reboots. The volume * table is basically an array of volume table records. Each record contains * full information about the volume and protected by a CRC checksum. Note, * nowadays we use the atomic LEB change operation when updating the volume * table, so we do not really need 2 LEBs anymore, but we preserve the older * design for the backward compatibility reasons. * * When the volume table is changed, it is first changed in RAM. Then LEB 0 is * erased, and the updated volume table is written back to LEB 0. Then same for * LEB 1. This scheme guarantees recoverability from unclean reboots. * * In this UBI implementation the on-flash volume table does not contain any * information about how much data static volumes contain. * * But it would still be beneficial to store this information in the volume * table. For example, suppose we have a static volume X, and all its physical * eraseblocks became bad for some reasons. Suppose we are attaching the * corresponding MTD device, for some reason we find no logical eraseblocks * corresponding to the volume X. According to the volume table volume X does * exist. So we don't know whether it is just empty or all its physical * eraseblocks went bad. So we cannot alarm the user properly. * * The volume table also stores so-called "update marker", which is used for * volume updates. Before updating the volume, the update marker is set, and * after the update operation is finished, the update marker is cleared. So if * the update operation was interrupted (e.g. by an unclean reboot) - the * update marker is still there and we know that the volume's contents is * damaged. */ #include <linux/crc32.h> #include <linux/err.h> #include <linux/slab.h> #include <asm/div64.h> #include "ubi.h" static void self_vtbl_check(const struct ubi_device *ubi); /* Empty volume table record */ static struct ubi_vtbl_record empty_vtbl_record; /** * ubi_update_layout_vol - helper for updatting layout volumes on flash * @ubi: UBI device description object */ static int ubi_update_layout_vol(struct ubi_device *ubi) { struct ubi_volume *layout_vol; int i, err; layout_vol = ubi->volumes[vol_id2idx(ubi, UBI_LAYOUT_VOLUME_ID)]; for (i = 0; i < UBI_LAYOUT_VOLUME_EBS; i++) { err = ubi_eba_atomic_leb_change(ubi, layout_vol, i, ubi->vtbl, ubi->vtbl_size); if (err) return err; } return 0; } /** * ubi_change_vtbl_record - change volume table record. * @ubi: UBI device description object * @idx: table index to change * @vtbl_rec: new volume table record * * This function changes volume table record @idx. If @vtbl_rec is %NULL, empty * volume table record is written. The caller does not have to calculate CRC of * the record as it is done by this function. Returns zero in case of success * and a negative error code in case of failure. */ int ubi_change_vtbl_record(struct ubi_device *ubi, int idx, struct ubi_vtbl_record *vtbl_rec) { int err; uint32_t crc; ubi_assert(idx >= 0 && idx < ubi->vtbl_slots); if (!vtbl_rec) vtbl_rec = &empty_vtbl_record; else { crc = crc32(UBI_CRC32_INIT, vtbl_rec, UBI_VTBL_RECORD_SIZE_CRC); vtbl_rec->crc = cpu_to_be32(crc); } memcpy(&ubi->vtbl[idx], vtbl_rec, sizeof(struct ubi_vtbl_record)); err = ubi_update_layout_vol(ubi); self_vtbl_check(ubi); return err ? err : 0; } /** * ubi_vtbl_rename_volumes - rename UBI volumes in the volume table. * @ubi: UBI device description object * @rename_list: list of &struct ubi_rename_entry objects * * This function re-names multiple volumes specified in @req in the volume * table. Returns zero in case of success and a negative error code in case of * failure. */ int ubi_vtbl_rename_volumes(struct ubi_device *ubi, struct list_head *rename_list) { struct ubi_rename_entry *re; list_for_each_entry(re, rename_list, list) { uint32_t crc; struct ubi_volume *vol = re->desc->vol; struct ubi_vtbl_record *vtbl_rec = &ubi->vtbl[vol->vol_id]; if (re->remove) { memcpy(vtbl_rec, &empty_vtbl_record, sizeof(struct ubi_vtbl_record)); continue; } vtbl_rec->name_len = cpu_to_be16(re->new_name_len); memcpy(vtbl_rec->name, re->new_name, re->new_name_len); memset(vtbl_rec->name + re->new_name_len, 0, UBI_VOL_NAME_MAX + 1 - re->new_name_len); crc = crc32(UBI_CRC32_INIT, vtbl_rec, UBI_VTBL_RECORD_SIZE_CRC); vtbl_rec->crc = cpu_to_be32(crc); } return ubi_update_layout_vol(ubi); } /** * vtbl_check - check if volume table is not corrupted and sensible. * @ubi: UBI device description object * @vtbl: volume table * * This function returns zero if @vtbl is all right, %1 if CRC is incorrect, * and %-EINVAL if it contains inconsistent data. */ static int vtbl_check(const struct ubi_device *ubi, const struct ubi_vtbl_record *vtbl) { int i, n, reserved_pebs, alignment, data_pad, vol_type, name_len; int upd_marker, err; uint32_t crc; const char *name; for (i = 0; i < ubi->vtbl_slots; i++) { cond_resched(); reserved_pebs = be32_to_cpu(vtbl[i].reserved_pebs); alignment = be32_to_cpu(vtbl[i].alignment); data_pad = be32_to_cpu(vtbl[i].data_pad); upd_marker = vtbl[i].upd_marker; vol_type = vtbl[i].vol_type; name_len = be16_to_cpu(vtbl[i].name_len); name = &vtbl[i].name[0]; crc = crc32(UBI_CRC32_INIT, &vtbl[i], UBI_VTBL_RECORD_SIZE_CRC); if (be32_to_cpu(vtbl[i].crc) != crc) { ubi_err(ubi, "bad CRC at record %u: %#08x, not %#08x", i, crc, be32_to_cpu(vtbl[i].crc)); ubi_dump_vtbl_record(&vtbl[i], i); return 1; } if (reserved_pebs == 0) { if (memcmp(&vtbl[i], &empty_vtbl_record, UBI_VTBL_RECORD_SIZE)) { err = 2; goto bad; } continue; } if (reserved_pebs < 0 || alignment < 0 || data_pad < 0 || name_len < 0) { err = 3; goto bad; } if (alignment > ubi->leb_size || alignment == 0) { err = 4; goto bad; } n = alignment & (ubi->min_io_size - 1); if (alignment != 1 && n) { err = 5; goto bad; } n = ubi->leb_size % alignment; if (data_pad != n) { ubi_err(ubi, "bad data_pad, has to be %d", n); err = 6; goto bad; } if (vol_type != UBI_VID_DYNAMIC && vol_type != UBI_VID_STATIC) { err = 7; goto bad; } if (upd_marker != 0 && upd_marker != 1) { err = 8; goto bad; } if (reserved_pebs > ubi->good_peb_count) { ubi_err(ubi, "too large reserved_pebs %d, good PEBs %d", reserved_pebs, ubi->good_peb_count); err = 9; goto bad; } if (name_len > UBI_VOL_NAME_MAX) { err = 10; goto bad; } if (name[0] == '\0') { err = 11; goto bad; } if (name_len != strnlen(name, name_len + 1)) { err = 12; goto bad; } } /* Checks that all names are unique */ for (i = 0; i < ubi->vtbl_slots - 1; i++) { for (n = i + 1; n < ubi->vtbl_slots; n++) { int len1 = be16_to_cpu(vtbl[i].name_len); int len2 = be16_to_cpu(vtbl[n].name_len); if (len1 > 0 && len1 == len2 && !strncmp(vtbl[i].name, vtbl[n].name, len1)) { ubi_err(ubi, "volumes %d and %d have the same name \"%s\"", i, n, vtbl[i].name); ubi_dump_vtbl_record(&vtbl[i], i); ubi_dump_vtbl_record(&vtbl[n], n); return -EINVAL; } } } return 0; bad: ubi_err(ubi, "volume table check failed: record %d, error %d", i, err); ubi_dump_vtbl_record(&vtbl[i], i); return -EINVAL; } /** * create_vtbl - create a copy of volume table. * @ubi: UBI device description object * @ai: attaching information * @copy: number of the volume table copy * @vtbl: contents of the volume table * * This function returns zero in case of success and a negative error code in * case of failure. */ static int create_vtbl(struct ubi_device *ubi, struct ubi_attach_info *ai, int copy, void *vtbl) { int err, tries = 0; struct ubi_vid_io_buf *vidb; struct ubi_vid_hdr *vid_hdr; struct ubi_ainf_peb *new_aeb; dbg_gen("create volume table (copy #%d)", copy + 1); vidb = ubi_alloc_vid_buf(ubi, GFP_KERNEL); if (!vidb) return -ENOMEM; vid_hdr = ubi_get_vid_hdr(vidb); retry: new_aeb = ubi_early_get_peb(ubi, ai); if (IS_ERR(new_aeb)) { err = PTR_ERR(new_aeb); goto out_free; } vid_hdr->vol_type = UBI_LAYOUT_VOLUME_TYPE; vid_hdr->vol_id = cpu_to_be32(UBI_LAYOUT_VOLUME_ID); vid_hdr->compat = UBI_LAYOUT_VOLUME_COMPAT; vid_hdr->data_size = vid_hdr->used_ebs = vid_hdr->data_pad = cpu_to_be32(0); vid_hdr->lnum = cpu_to_be32(copy); vid_hdr->sqnum = cpu_to_be64(++ai->max_sqnum); /* The EC header is already there, write the VID header */ err = ubi_io_write_vid_hdr(ubi, new_aeb->pnum, vidb); if (err) goto write_error; /* Write the layout volume contents */ err = ubi_io_write_data(ubi, vtbl, new_aeb->pnum, 0, ubi->vtbl_size); if (err) goto write_error; /* * And add it to the attaching information. Don't delete the old version * of this LEB as it will be deleted and freed in 'ubi_add_to_av()'. */ err = ubi_add_to_av(ubi, ai, new_aeb->pnum, new_aeb->ec, vid_hdr, 0); ubi_free_aeb(ai, new_aeb); ubi_free_vid_buf(vidb); return err; write_error: if (err == -EIO && ++tries <= 5) { /* * Probably this physical eraseblock went bad, try to pick * another one. */ list_add(&new_aeb->u.list, &ai->erase); goto retry; } ubi_free_aeb(ai, new_aeb); out_free: ubi_free_vid_buf(vidb); return err; } /** * process_lvol - process the layout volume. * @ubi: UBI device description object * @ai: attaching information * @av: layout volume attaching information * * This function is responsible for reading the layout volume, ensuring it is * not corrupted, and recovering from corruptions if needed. Returns volume * table in case of success and a negative error code in case of failure. */ static struct ubi_vtbl_record *process_lvol(struct ubi_device *ubi, struct ubi_attach_info *ai, struct ubi_ainf_volume *av) { int err; struct rb_node *rb; struct ubi_ainf_peb *aeb; struct ubi_vtbl_record *leb[UBI_LAYOUT_VOLUME_EBS] = { NULL, NULL }; int leb_corrupted[UBI_LAYOUT_VOLUME_EBS] = {1, 1}; /* * UBI goes through the following steps when it changes the layout * volume: * a. erase LEB 0; * b. write new data to LEB 0; * c. erase LEB 1; * d. write new data to LEB 1. * * Before the change, both LEBs contain the same data. * * Due to unclean reboots, the contents of LEB 0 may be lost, but there * should LEB 1. So it is OK if LEB 0 is corrupted while LEB 1 is not. * Similarly, LEB 1 may be lost, but there should be LEB 0. And * finally, unclean reboots may result in a situation when neither LEB * 0 nor LEB 1 are corrupted, but they are different. In this case, LEB * 0 contains more recent information. * * So the plan is to first check LEB 0. Then * a. if LEB 0 is OK, it must be containing the most recent data; then * we compare it with LEB 1, and if they are different, we copy LEB * 0 to LEB 1; * b. if LEB 0 is corrupted, but LEB 1 has to be OK, and we copy LEB 1 * to LEB 0. */ dbg_gen("check layout volume"); /* Read both LEB 0 and LEB 1 into memory */ ubi_rb_for_each_entry(rb, aeb, &av->root, u.rb) { leb[aeb->lnum] = vzalloc(ubi->vtbl_size); if (!leb[aeb->lnum]) { err = -ENOMEM; goto out_free; } err = ubi_io_read_data(ubi, leb[aeb->lnum], aeb->pnum, 0, ubi->vtbl_size); if (err == UBI_IO_BITFLIPS || mtd_is_eccerr(err)) /* * Scrub the PEB later. Note, -EBADMSG indicates an * uncorrectable ECC error, but we have our own CRC and * the data will be checked later. If the data is OK, * the PEB will be scrubbed (because we set * aeb->scrub). If the data is not OK, the contents of * the PEB will be recovered from the second copy, and * aeb->scrub will be cleared in * 'ubi_add_to_av()'. */ aeb->scrub = 1; else if (err) goto out_free; } err = -EINVAL; if (leb[0]) { leb_corrupted[0] = vtbl_check(ubi, leb[0]); if (leb_corrupted[0] < 0) goto out_free; } if (!leb_corrupted[0]) { /* LEB 0 is OK */ if (leb[1]) leb_corrupted[1] = memcmp(leb[0], leb[1], ubi->vtbl_size); if (leb_corrupted[1]) { ubi_warn(ubi, "volume table copy #2 is corrupted"); err = create_vtbl(ubi, ai, 1, leb[0]); if (err) goto out_free; ubi_msg(ubi, "volume table was restored"); } /* Both LEB 1 and LEB 2 are OK and consistent */ vfree(leb[1]); return leb[0]; } else { /* LEB 0 is corrupted or does not exist */ if (leb[1]) { leb_corrupted[1] = vtbl_check(ubi, leb[1]); if (leb_corrupted[1] < 0) goto out_free; } if (leb_corrupted[1]) { /* Both LEB 0 and LEB 1 are corrupted */ ubi_err(ubi, "both volume tables are corrupted"); goto out_free; } ubi_warn(ubi, "volume table copy #1 is corrupted"); err = create_vtbl(ubi, ai, 0, leb[1]); if (err) goto out_free; ubi_msg(ubi, "volume table was restored"); vfree(leb[0]); return leb[1]; } out_free: vfree(leb[0]); vfree(leb[1]); return ERR_PTR(err); } /** * create_empty_lvol - create empty layout volume. * @ubi: UBI device description object * @ai: attaching information * * This function returns volume table contents in case of success and a * negative error code in case of failure. */ static struct ubi_vtbl_record *create_empty_lvol(struct ubi_device *ubi, struct ubi_attach_info *ai) { int i; struct ubi_vtbl_record *vtbl; vtbl = vzalloc(ubi->vtbl_size); if (!vtbl) return ERR_PTR(-ENOMEM); for (i = 0; i < ubi->vtbl_slots; i++) memcpy(&vtbl[i], &empty_vtbl_record, UBI_VTBL_RECORD_SIZE); for (i = 0; i < UBI_LAYOUT_VOLUME_EBS; i++) { int err; err = create_vtbl(ubi, ai, i, vtbl); if (err) { vfree(vtbl); return ERR_PTR(err); } } return vtbl; } /** * init_volumes - initialize volume information for existing volumes. * @ubi: UBI device description object * @ai: scanning information * @vtbl: volume table * * This function allocates volume description objects for existing volumes. * Returns zero in case of success and a negative error code in case of * failure. */ static int init_volumes(struct ubi_device *ubi, const struct ubi_attach_info *ai, const struct ubi_vtbl_record *vtbl) { int i, err, reserved_pebs = 0; struct ubi_ainf_volume *av; struct ubi_volume *vol; for (i = 0; i < ubi->vtbl_slots; i++) { cond_resched(); if (be32_to_cpu(vtbl[i].reserved_pebs) == 0) continue; /* Empty record */ vol = kzalloc_obj(struct ubi_volume); if (!vol) return -ENOMEM; vol->reserved_pebs = be32_to_cpu(vtbl[i].reserved_pebs); vol->alignment = be32_to_cpu(vtbl[i].alignment); vol->data_pad = be32_to_cpu(vtbl[i].data_pad); vol->upd_marker = vtbl[i].upd_marker; vol->vol_type = vtbl[i].vol_type == UBI_VID_DYNAMIC ? UBI_DYNAMIC_VOLUME : UBI_STATIC_VOLUME; vol->name_len = be16_to_cpu(vtbl[i].name_len); vol->usable_leb_size = ubi->leb_size - vol->data_pad; memcpy(vol->name, vtbl[i].name, vol->name_len); vol->name[vol->name_len] = '\0'; vol->vol_id = i; if (vtbl[i].flags & UBI_VTBL_SKIP_CRC_CHECK_FLG) vol->skip_check = 1; if (vtbl[i].flags & UBI_VTBL_AUTORESIZE_FLG) { /* Auto re-size flag may be set only for one volume */ if (ubi->autoresize_vol_id != -1) { ubi_err(ubi, "more than one auto-resize volume (%d and %d)", ubi->autoresize_vol_id, i); kfree(vol); return -EINVAL; } ubi->autoresize_vol_id = i; } ubi_assert(!ubi->volumes[i]); ubi->volumes[i] = vol; ubi->vol_count += 1; vol->ubi = ubi; reserved_pebs += vol->reserved_pebs; /* * We use ubi->peb_count and not vol->reserved_pebs because * we want to keep the code simple. Otherwise we'd have to * resize/check the bitmap upon volume resize too. * Allocating a few bytes more does not hurt. */ err = ubi_fastmap_init_checkmap(vol, ubi->peb_count); if (err) return err; /* * In case of dynamic volume UBI knows nothing about how many * data is stored there. So assume the whole volume is used. */ if (vol->vol_type == UBI_DYNAMIC_VOLUME) { vol->used_ebs = vol->reserved_pebs; vol->last_eb_bytes = vol->usable_leb_size; vol->used_bytes = (long long)vol->used_ebs * vol->usable_leb_size; continue; } /* Static volumes only */ av = ubi_find_av(ai, i); if (!av || !av->leb_count) { /* * No eraseblocks belonging to this volume found. We * don't actually know whether this static volume is * completely corrupted or just contains no data. And * we cannot know this as long as data size is not * stored on flash. So we just assume the volume is * empty. FIXME: this should be handled. */ continue; } if (av->leb_count != av->used_ebs) { /* * We found a static volume which misses several * eraseblocks. Treat it as corrupted. */ ubi_warn(ubi, "static volume %d misses %d LEBs - corrupted", av->vol_id, av->used_ebs - av->leb_count); vol->corrupted = 1; continue; } vol->used_ebs = av->used_ebs; vol->used_bytes = (long long)(vol->used_ebs - 1) * vol->usable_leb_size; vol->used_bytes += av->last_data_size; vol->last_eb_bytes = av->last_data_size; } /* And add the layout volume */ vol = kzalloc_obj(struct ubi_volume); if (!vol) return -ENOMEM; vol->reserved_pebs = UBI_LAYOUT_VOLUME_EBS; vol->alignment = UBI_LAYOUT_VOLUME_ALIGN; vol->vol_type = UBI_DYNAMIC_VOLUME; vol->name_len = sizeof(UBI_LAYOUT_VOLUME_NAME) - 1; memcpy(vol->name, UBI_LAYOUT_VOLUME_NAME, vol->name_len + 1); vol->usable_leb_size = ubi->leb_size; vol->used_ebs = vol->reserved_pebs; vol->last_eb_bytes = vol->reserved_pebs; vol->used_bytes = (long long)vol->used_ebs * (ubi->leb_size - vol->data_pad); vol->vol_id = UBI_LAYOUT_VOLUME_ID; vol->ref_count = 1; ubi_assert(!ubi->volumes[i]); ubi->volumes[vol_id2idx(ubi, vol->vol_id)] = vol; reserved_pebs += vol->reserved_pebs; ubi->vol_count += 1; vol->ubi = ubi; err = ubi_fastmap_init_checkmap(vol, UBI_LAYOUT_VOLUME_EBS); if (err) return err; if (reserved_pebs > ubi->avail_pebs) { ubi_err(ubi, "not enough PEBs, required %d, available %d", reserved_pebs, ubi->avail_pebs); if (ubi->corr_peb_count) ubi_err(ubi, "%d PEBs are corrupted and not used", ubi->corr_peb_count); return -ENOSPC; } ubi->rsvd_pebs += reserved_pebs; ubi->avail_pebs -= reserved_pebs; return 0; } /** * check_av - check volume attaching information. * @vol: UBI volume description object * @av: volume attaching information * * This function returns zero if the volume attaching information is consistent * to the data read from the volume tabla, and %-EINVAL if not. */ static int check_av(const struct ubi_volume *vol, const struct ubi_ainf_volume *av) { int err; if (av->highest_lnum >= vol->reserved_pebs) { err = 1; goto bad; } if (av->leb_count > vol->reserved_pebs) { err = 2; goto bad; } if (av->vol_type != vol->vol_type) { err = 3; goto bad; } if (av->used_ebs > vol->reserved_pebs) { err = 4; goto bad; } if (av->data_pad != vol->data_pad) { err = 5; goto bad; } return 0; bad: ubi_err(vol->ubi, "bad attaching information, error %d", err); ubi_dump_av(av); ubi_dump_vol_info(vol); return -EINVAL; } /** * check_attaching_info - check that attaching information. * @ubi: UBI device description object * @ai: attaching information * * Even though we protect on-flash data by CRC checksums, we still don't trust * the media. This function ensures that attaching information is consistent to * the information read from the volume table. Returns zero if the attaching * information is OK and %-EINVAL if it is not. */ static int check_attaching_info(const struct ubi_device *ubi, struct ubi_attach_info *ai) { int err, i; struct ubi_ainf_volume *av; struct ubi_volume *vol; if (ai->vols_found > UBI_INT_VOL_COUNT + ubi->vtbl_slots) { ubi_err(ubi, "found %d volumes while attaching, maximum is %d + %d", ai->vols_found, UBI_INT_VOL_COUNT, ubi->vtbl_slots); return -EINVAL; } if (ai->highest_vol_id >= ubi->vtbl_slots + UBI_INT_VOL_COUNT && ai->highest_vol_id < UBI_INTERNAL_VOL_START) { ubi_err(ubi, "too large volume ID %d found", ai->highest_vol_id); return -EINVAL; } for (i = 0; i < ubi->vtbl_slots + UBI_INT_VOL_COUNT; i++) { cond_resched(); av = ubi_find_av(ai, i); vol = ubi->volumes[i]; if (!vol) { if (av) ubi_remove_av(ai, av); continue; } if (vol->reserved_pebs == 0) { ubi_assert(i < ubi->vtbl_slots); if (!av) continue; /* * During attaching we found a volume which does not * exist according to the information in the volume * table. This must have happened due to an unclean * reboot while the volume was being removed. Discard * these eraseblocks. */ ubi_msg(ubi, "finish volume %d removal", av->vol_id); ubi_remove_av(ai, av); } else if (av) { err = check_av(vol, av); if (err) return err; } } return 0; } /** * ubi_read_volume_table - read the volume table. * @ubi: UBI device description object * @ai: attaching information * * This function reads volume table, checks it, recover from errors if needed, * or creates it if needed. Returns zero in case of success and a negative * error code in case of failure. */ int ubi_read_volume_table(struct ubi_device *ubi, struct ubi_attach_info *ai) { int err; struct ubi_ainf_volume *av; empty_vtbl_record.crc = cpu_to_be32(0xf116c36b); /* * The number of supported volumes is limited by the eraseblock size * and by the UBI_MAX_VOLUMES constant. */ if (ubi->leb_size < UBI_VTBL_RECORD_SIZE) { ubi_err(ubi, "LEB size too small for a volume record"); return -EINVAL; } ubi->vtbl_slots = ubi->leb_size / UBI_VTBL_RECORD_SIZE; if (ubi->vtbl_slots > UBI_MAX_VOLUMES) ubi->vtbl_slots = UBI_MAX_VOLUMES; ubi->vtbl_size = ubi->vtbl_slots * UBI_VTBL_RECORD_SIZE; ubi->vtbl_size = ALIGN(ubi->vtbl_size, ubi->min_io_size); av = ubi_find_av(ai, UBI_LAYOUT_VOLUME_ID); if (!av) { /* * No logical eraseblocks belonging to the layout volume were * found. This could mean that the flash is just empty. In * this case we create empty layout volume. * * But if flash is not empty this must be a corruption or the * MTD device just contains garbage. */ if (ai->is_empty) { ubi->vtbl = create_empty_lvol(ubi, ai); if (IS_ERR(ubi->vtbl)) return PTR_ERR(ubi->vtbl); } else { ubi_err(ubi, "the layout volume was not found"); return -EINVAL; } } else { if (av->leb_count > UBI_LAYOUT_VOLUME_EBS) { /* This must not happen with proper UBI images */ ubi_err(ubi, "too many LEBs (%d) in layout volume", av->leb_count); return -EINVAL; } ubi->vtbl = process_lvol(ubi, ai, av); if (IS_ERR(ubi->vtbl)) return PTR_ERR(ubi->vtbl); } ubi->avail_pebs = ubi->good_peb_count - ubi->corr_peb_count; /* * The layout volume is OK, initialize the corresponding in-RAM data * structures. */ err = init_volumes(ubi, ai, ubi->vtbl); if (err) goto out_free; /* * Make sure that the attaching information is consistent to the * information stored in the volume table. */ err = check_attaching_info(ubi, ai); if (err) goto out_free; return 0; out_free: vfree(ubi->vtbl); ubi_free_all_volumes(ubi); return err; } /** * self_vtbl_check - check volume table. * @ubi: UBI device description object */ static void self_vtbl_check(const struct ubi_device *ubi) { if (!ubi_dbg_chk_gen(ubi)) return; if (vtbl_check(ubi, ubi->vtbl)) { ubi_err(ubi, "self-check failed"); BUG(); } } |
| 1454 1457 9 1463 1457 1458 1600 1555 7 5 5 23 22 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_DST_METADATA_H #define __NET_DST_METADATA_H 1 #include <linux/skbuff.h> #include <net/ip.h> #include <net/ip_tunnels.h> #include <net/macsec.h> #include <net/dst.h> enum metadata_type { METADATA_IP_TUNNEL, METADATA_HW_PORT_MUX, METADATA_MACSEC, METADATA_XFRM, }; struct hw_port_info { struct net_device *lower_dev; u32 port_id; }; struct macsec_info { sci_t sci; }; struct xfrm_md_info { u32 if_id; int link; struct dst_entry *dst_orig; }; struct metadata_dst { struct dst_entry dst; enum metadata_type type; union { struct ip_tunnel_info tun_info; struct hw_port_info port_info; struct macsec_info macsec_info; struct xfrm_md_info xfrm_info; } u; }; static inline struct metadata_dst *skb_metadata_dst(const struct sk_buff *skb) { struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb); if (md_dst && md_dst->dst.flags & DST_METADATA) return md_dst; return NULL; } static inline struct ip_tunnel_info * skb_tunnel_info(const struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dst_entry *dst; if (md_dst && md_dst->type == METADATA_IP_TUNNEL) return &md_dst->u.tun_info; dst = skb_dst(skb); if (dst && dst->lwtstate && (dst->lwtstate->type == LWTUNNEL_ENCAP_IP || dst->lwtstate->type == LWTUNNEL_ENCAP_IP6)) return lwt_tun_info(dst->lwtstate); return NULL; } static inline struct xfrm_md_info *lwt_xfrm_info(struct lwtunnel_state *lwt) { return (struct xfrm_md_info *)lwt->data; } static inline struct xfrm_md_info *skb_xfrm_md_info(const struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dst_entry *dst; if (md_dst && md_dst->type == METADATA_XFRM) return &md_dst->u.xfrm_info; dst = skb_dst(skb); if (dst && dst->lwtstate && dst->lwtstate->type == LWTUNNEL_ENCAP_XFRM) return lwt_xfrm_info(dst->lwtstate); return NULL; } static inline bool skb_valid_dst(const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); return dst && !(dst->flags & DST_METADATA); } static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { const struct metadata_dst *a, *b; if (!(skb_a->_skb_refdst | skb_b->_skb_refdst)) return 0; a = (const struct metadata_dst *) skb_dst(skb_a); b = (const struct metadata_dst *) skb_dst(skb_b); if (!a != !b || a->type != b->type) return 1; switch (a->type) { case METADATA_HW_PORT_MUX: return memcmp(&a->u.port_info, &b->u.port_info, sizeof(a->u.port_info)); case METADATA_IP_TUNNEL: return memcmp(&a->u.tun_info, &b->u.tun_info, sizeof(a->u.tun_info) + a->u.tun_info.options_len); case METADATA_MACSEC: return memcmp(&a->u.macsec_info, &b->u.macsec_info, sizeof(a->u.macsec_info)); case METADATA_XFRM: return memcmp(&a->u.xfrm_info, &b->u.xfrm_info, sizeof(a->u.xfrm_info)); default: return 1; } } void metadata_dst_free(struct metadata_dst *); struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, gfp_t flags); void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst); struct metadata_dst __percpu * metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags); static inline struct metadata_dst *tun_rx_dst(int md_size) { struct metadata_dst *tun_dst; tun_dst = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC); if (!tun_dst) return NULL; tun_dst->u.tun_info.options_len = 0; tun_dst->u.tun_info.mode = 0; return tun_dst; } static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); int md_size; struct metadata_dst *new_md; if (!md_dst || md_dst->type != METADATA_IP_TUNNEL) return ERR_PTR(-EINVAL); md_size = md_dst->u.tun_info.options_len; new_md = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC); if (!new_md) return ERR_PTR(-ENOMEM); memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, sizeof(struct ip_tunnel_info) + md_size); #ifdef CONFIG_DST_CACHE /* Unclone the dst cache if there is one */ if (new_md->u.tun_info.dst_cache.cache) { int ret; ret = dst_cache_init(&new_md->u.tun_info.dst_cache, GFP_ATOMIC); if (ret) { metadata_dst_free(new_md); return ERR_PTR(ret); } } #endif skb_dst_drop(skb); skb_dst_set(skb, &new_md->dst); return new_md; } static inline struct ip_tunnel_info *skb_tunnel_info_unclone(struct sk_buff *skb) { struct metadata_dst *dst; dst = tun_dst_unclone(skb); if (IS_ERR(dst)) return NULL; return &dst->u.tun_info; } static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, __be32 daddr, __u8 tos, __u8 ttl, __be16 tp_dst, const unsigned long *flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; tun_dst = tun_rx_dst(md_size); if (!tun_dst) return NULL; ip_tunnel_key_init(&tun_dst->u.tun_info.key, saddr, daddr, tos, ttl, 0, 0, tp_dst, tunnel_id, flags); return tun_dst; } static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, const unsigned long *flags, __be64 tunnel_id, int md_size) { const struct iphdr *iph = ip_hdr(skb); struct metadata_dst *tun_dst; tun_dst = __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl, 0, flags, tunnel_id, md_size); if (tun_dst && (iph->frag_off & htons(IP_DF))) __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, tun_dst->u.tun_info.key.tun_flags); return tun_dst; } static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *saddr, const struct in6_addr *daddr, __u8 tos, __u8 ttl, __be16 tp_dst, __be32 label, const unsigned long *flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; struct ip_tunnel_info *info; tun_dst = tun_rx_dst(md_size); if (!tun_dst) return NULL; info = &tun_dst->u.tun_info; info->mode = IP_TUNNEL_INFO_IPV6; ip_tunnel_flags_copy(info->key.tun_flags, flags); info->key.tun_id = tunnel_id; info->key.tp_src = 0; info->key.tp_dst = tp_dst; info->key.u.ipv6.src = *saddr; info->key.u.ipv6.dst = *daddr; info->key.tos = tos; info->key.ttl = ttl; info->key.label = label; return tun_dst; } static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, const unsigned long *flags, __be64 tunnel_id, int md_size) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); return __ipv6_tun_set_dst(&ip6h->saddr, &ip6h->daddr, ipv6_get_dsfield(ip6h), ip6h->hop_limit, 0, ip6_flowlabel(ip6h), flags, tunnel_id, md_size); } #endif /* __NET_DST_METADATA_H */ |
| 145 70 40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/iso_fs.h> #include <linux/unaligned.h> enum isofs_file_format { isofs_file_normal = 0, isofs_file_sparse = 1, isofs_file_compressed = 2, }; /* * iso fs inode data in memory */ struct iso_inode_info { unsigned long i_iget5_block; unsigned long i_iget5_offset; unsigned int i_first_extent; unsigned char i_file_format; unsigned char i_format_parm[3]; unsigned long i_next_section_block; unsigned long i_next_section_offset; off_t i_section_size; struct inode vfs_inode; }; /* * iso9660 super-block data in memory */ struct isofs_sb_info { unsigned long s_ninodes; unsigned long s_nzones; unsigned long s_firstdatazone; unsigned long s_log_zone_size; unsigned long s_max_size; int s_rock_offset; /* offset of SUSP fields within SU area */ s32 s_sbsector; unsigned char s_joliet_level; unsigned char s_mapping; unsigned char s_check; unsigned char s_session; unsigned int s_high_sierra:1; unsigned int s_rock:2; unsigned int s_cruft:1; /* Broken disks with high byte of length * containing junk */ unsigned int s_nocompress:1; unsigned int s_hide:1; unsigned int s_showassoc:1; unsigned int s_overriderockperm:1; unsigned int s_uid_set:1; unsigned int s_gid_set:1; umode_t s_fmode; umode_t s_dmode; kgid_t s_gid; kuid_t s_uid; struct nls_table *s_nls_iocharset; /* Native language support table */ }; #define ISOFS_INVALID_MODE ((umode_t) -1) static inline struct isofs_sb_info *ISOFS_SB(struct super_block *sb) { return sb->s_fs_info; } static inline struct iso_inode_info *ISOFS_I(struct inode *inode) { return container_of(inode, struct iso_inode_info, vfs_inode); } static inline int isonum_711(u8 *p) { return *p; } static inline int isonum_712(s8 *p) { return *p; } static inline unsigned int isonum_721(u8 *p) { return get_unaligned_le16(p); } static inline unsigned int isonum_722(u8 *p) { return get_unaligned_be16(p); } static inline unsigned int isonum_723(u8 *p) { /* Ignore bigendian datum due to broken mastering programs */ return get_unaligned_le16(p); } static inline unsigned int isonum_731(u8 *p) { return get_unaligned_le32(p); } static inline unsigned int isonum_732(u8 *p) { return get_unaligned_be32(p); } static inline unsigned int isonum_733(u8 *p) { /* Ignore bigendian datum due to broken mastering programs */ return get_unaligned_le32(p); } #define ISO_DATE_HIGH_SIERRA (1 << 0) #define ISO_DATE_LONG_FORM (1 << 1) struct timespec64 iso_date(u8 *p, int flags); struct inode; /* To make gcc happy */ extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *, int relocated); extern int get_rock_ridge_filename(struct iso_directory_record *, char *, struct inode *); extern int isofs_name_translate(struct iso_directory_record *, char *, struct inode *); int get_joliet_filename(struct iso_directory_record *, unsigned char *, struct inode *); int get_acorn_filename(struct iso_directory_record *, char *, struct inode *); extern struct dentry *isofs_lookup(struct inode *, struct dentry *, unsigned int flags); extern struct buffer_head *isofs_bread(struct inode *, sector_t); extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long); struct inode *__isofs_iget(struct super_block *sb, unsigned long block, unsigned long offset, int relocated); static inline struct inode *isofs_iget(struct super_block *sb, unsigned long block, unsigned long offset) { return __isofs_iget(sb, block, offset, 0); } static inline struct inode *isofs_iget_reloc(struct super_block *sb, unsigned long block, unsigned long offset) { return __isofs_iget(sb, block, offset, 1); } /* Because the inode number is no longer relevant to finding the * underlying meta-data for an inode, we are free to choose a more * convenient 32-bit number as the inode number. The inode numbering * scheme was recommended by Sergey Vlasov and Eric Lammerts. */ static inline unsigned long isofs_get_ino(unsigned long block, unsigned long offset, unsigned long bufbits) { return (block << (bufbits - 5)) | (offset >> 5); } /* Every directory can have many redundant directory entries scattered * throughout the directory tree. First there is the directory entry * with the name of the directory stored in the parent directory. * Then, there is the "." directory entry stored in the directory * itself. Finally, there are possibly many ".." directory entries * stored in all the subdirectories. * * In order for the NFS get_parent() method to work and for the * general consistency of the dcache, we need to make sure the * "i_iget5_block" and "i_iget5_offset" all point to exactly one of * the many redundant entries for each directory. We normalize the * block and offset by always making them point to the "." directory. * * Notice that we do not use the entry for the directory with the name * that is located in the parent directory. Even though choosing this * first directory is more natural, it is much easier to find the "." * entry in the NFS get_parent() method because it is implicitly * encoded in the "extent + ext_attr_length" fields of _all_ the * redundant entries for the directory. Thus, it can always be * reached regardless of which directory entry you have in hand. * * This works because the "." entry is simply the first directory * record when you start reading the file that holds all the directory * records, and this file starts at "extent + ext_attr_length" blocks. * Because the "." entry is always the first entry listed in the * directories file, the normalized "offset" value is always 0. * * You should pass the directory entry in "de". On return, "block" * and "offset" will hold normalized values. Only directories are * affected making it safe to call even for non-directory file * types. */ static inline void isofs_normalize_block_and_offset(struct iso_directory_record* de, unsigned long *block, unsigned long *offset) { /* Only directories are normalized. */ if (de->flags[0] & 2) { *offset = 0; *block = (unsigned long)isonum_733(de->extent) + (unsigned long)isonum_711(de->ext_attr_length); } } extern const struct inode_operations isofs_dir_inode_operations; extern const struct file_operations isofs_dir_operations; extern const struct address_space_operations isofs_symlink_aops; extern const struct export_operations isofs_export_ops; |
| 12 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 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef PAGE_ACTOR_H #define PAGE_ACTOR_H /* * Copyright (c) 2013 * Phillip Lougher <phillip@squashfs.org.uk> */ struct squashfs_page_actor { union { void **buffer; struct page **page; }; void *pageaddr; void *tmp_buffer; void *(*squashfs_first_page)(struct squashfs_page_actor *); void *(*squashfs_next_page)(struct squashfs_page_actor *); void (*squashfs_finish_page)(struct squashfs_page_actor *); struct page *last_page; int pages; int length; int next_page; int alloc_buffer; int returned_pages; pgoff_t next_index; }; extern struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, int pages, int length); extern struct squashfs_page_actor *squashfs_page_actor_init_special( struct squashfs_sb_info *msblk, struct page **page, int pages, int length, loff_t start_index); static inline struct page *squashfs_page_actor_free(struct squashfs_page_actor *actor) { struct page *last_page = actor->next_page == actor->pages ? actor->last_page : ERR_PTR(-EIO); kfree(actor->tmp_buffer); kfree(actor); return last_page; } static inline void *squashfs_first_page(struct squashfs_page_actor *actor) { return actor->squashfs_first_page(actor); } static inline void *squashfs_next_page(struct squashfs_page_actor *actor) { return actor->squashfs_next_page(actor); } static inline void squashfs_finish_page(struct squashfs_page_actor *actor) { actor->squashfs_finish_page(actor); } static inline void squashfs_actor_nobuff(struct squashfs_page_actor *actor) { actor->alloc_buffer = 0; } #endif |
| 4 114 111 4 111 1 2 111 2 2 110 2 3 114 7 2 113 116 117 117 116 3 3 3 117 117 116 1 114 113 114 | 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); |
| 4481 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BLK_INTEGRITY_H #define _LINUX_BLK_INTEGRITY_H #include <linux/blk-mq.h> #include <linux/bio-integrity.h> #include <linux/blk-mq-dma.h> struct request; enum blk_integrity_flags { BLK_INTEGRITY_NOVERIFY = 1 << 0, BLK_INTEGRITY_NOGENERATE = 1 << 1, BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, BLK_INTEGRITY_REF_TAG = 1 << 3, BLK_INTEGRITY_STACKED = 1 << 4, BLK_SPLIT_INTERVAL_CAPABLE = 1 << 5, }; const char *blk_integrity_profile_name(struct blk_integrity *bi); bool queue_limits_stack_integrity(struct queue_limits *t, struct queue_limits *b); static inline bool queue_limits_stack_integrity_bdev(struct queue_limits *t, struct block_device *bdev) { return queue_limits_stack_integrity(t, &bdev->bd_disk->queue->limits); } #ifdef CONFIG_BLK_DEV_INTEGRITY int blk_rq_map_integrity_sg(struct request *, struct scatterlist *); int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, ssize_t bytes); int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd, struct logical_block_metadata_cap __user *argp); bool blk_rq_integrity_dma_map_iter_start(struct request *req, struct device *dma_dev, struct dma_iova_state *state, struct blk_dma_iter *iter); bool blk_rq_integrity_dma_map_iter_next(struct request *req, struct device *dma_dev, struct blk_dma_iter *iter); static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) { return q->limits.integrity.metadata_size; } static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { if (!blk_integrity_queue_supports_integrity(disk->queue)) return NULL; return &disk->queue->limits.integrity; } static inline struct blk_integrity * bdev_get_integrity(struct block_device *bdev) { return blk_get_integrity(bdev->bd_disk); } static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { return q->limits.max_integrity_segments; } /** * bio_integrity_intervals - Return number of integrity intervals for a bio * @bi: blk_integrity profile for device * @sectors: Size of the bio in 512-byte sectors * * Description: The block layer calculates everything in 512 byte * sectors but integrity metadata is done in terms of the data integrity * interval size of the storage device. Convert the block layer sectors * to the appropriate number of integrity intervals. */ static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { return sectors >> (bi->interval_exp - 9); } static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, unsigned int sectors) { return bio_integrity_intervals(bi, sectors) * bi->metadata_size; } static inline bool blk_integrity_rq(const struct request *rq) { return rq->cmd_flags & REQ_INTEGRITY; } /* * Return the current bvec that contains the integrity data. bip_iter may be * advanced to iterate over the integrity data. */ static inline struct bio_vec rq_integrity_vec(struct request *rq) { return mp_bvec_iter_bvec(rq->bio->bi_integrity->bip_vec, rq->bio->bi_integrity->bip_iter); } #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd, struct logical_block_metadata_cap __user *argp) { return -ENOIOCTLCMD; } static inline int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *b) { return 0; } static inline int blk_rq_map_integrity_sg(struct request *q, struct scatterlist *s) { return 0; } static inline int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, ssize_t bytes) { return -EINVAL; } static inline bool blk_rq_integrity_dma_map_iter_start(struct request *req, struct device *dma_dev, struct dma_iova_state *state, struct blk_dma_iter *iter) { return false; } static inline bool blk_rq_integrity_dma_map_iter_next(struct request *req, struct device *dma_dev, struct blk_dma_iter *iter) { return false; } static inline struct blk_integrity *bdev_get_integrity(struct block_device *b) { return NULL; } static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { return NULL; } static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) { return false; } static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { return 0; } static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { return 0; } static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, unsigned int sectors) { return 0; } static inline bool blk_integrity_rq(const struct request *rq) { return false; } static inline struct bio_vec rq_integrity_vec(struct request *rq) { /* the optimizer will remove all calls to this function */ return (struct bio_vec){ }; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ enum bio_integrity_action { BI_ACT_BUFFER = (1u << 0), /* allocate buffer */ BI_ACT_CHECK = (1u << 1), /* generate / verify PI */ BI_ACT_ZERO = (1u << 2), /* zero buffer */ }; /** * bio_integrity_action - return the integrity action needed for a bio * @bio: bio to operate on * * Returns the mask of integrity actions (BI_ACT_*) that need to be performed * for @bio. */ unsigned int __bio_integrity_action(struct bio *bio); static inline unsigned int bio_integrity_action(struct bio *bio) { if (!blk_get_integrity(bio->bi_bdev->bd_disk)) return 0; if (bio_integrity(bio)) return 0; return __bio_integrity_action(bio); } #endif /* _LINUX_BLK_INTEGRITY_H */ |
| 38 242 62 5 4 2 40 40 40 40 258 291 256 216 217 1 1 1 1 1 1 1 4 1 1 1 44 44 44 43 44 1 128 1 272 19 19 82 82 211 83 129 85 85 85 85 85 85 1 217 215 215 217 135 85 85 272 272 1 163 10 215 2 2 39 32 1 6 163 163 163 163 4 274 273 275 35 35 34 35 35 35 35 35 75 75 70 245 245 245 244 245 70 69 70 70 70 255 257 257 253 207 4 206 207 30 5 5 5 5 5 5 30 30 5 5 1 1 4 274 1 1 1 1 1 1 1 1 1 273 273 1 1 1 226 4 1 1 274 163 229 229 228 39 227 273 272 163 227 275 275 66 1 271 275 275 1 2 14 14 14 13 14 14 13 9 19 19 9 1 1 19 19 1 19 19 15 15 24 8 38 69 234 234 234 234 234 69 69 234 186 69 69 69 242 194 38 58 58 58 242 242 44 44 242 242 241 186 45 24 234 240 242 242 185 186 241 242 258 257 255 255 5 244 242 15 15 272 259 1 29 261 3 202 214 1 1 1 1 1 6 148 148 148 148 4 4 4 4 4 4 4 4 153 153 18 18 1 1 1 1 1 1 1 1 1 15 15 15 15 1 1 1 5 1 4 1 84 84 84 6 6 6 6 6 243 301 302 15 14 1 3 3 1 2 3 1 3 2 3 3 3 3 3 1 2 3 3 2 83 79 4 4 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 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 | // 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. * * MMU support * * Copyright (C) 2006 Qumranet, Inc. * Copyright 2010 Red Hat, Inc. and/or its affiliates. * * Authors: * Yaniv Kamay <yaniv@qumranet.com> * Avi Kivity <avi@qumranet.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "irq.h" #include "ioapic.h" #include "mmu.h" #include "mmu_internal.h" #include "tdp_mmu.h" #include "x86.h" #include "kvm_cache_regs.h" #include "smm.h" #include "kvm_emulate.h" #include "page_track.h" #include "cpuid.h" #include "spte.h" #include <linux/kvm_host.h> #include <linux/types.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/moduleparam.h> #include <linux/export.h> #include <linux/swap.h> #include <linux/hugetlb.h> #include <linux/compiler.h> #include <linux/srcu.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/kern_levels.h> #include <linux/kstrtox.h> #include <linux/kthread.h> #include <linux/wordpart.h> #include <asm/page.h> #include <asm/memtype.h> #include <asm/cmpxchg.h> #include <asm/io.h> #include <asm/set_memory.h> #include <asm/spec-ctrl.h> #include <asm/vmx.h> #include "trace.h" static bool nx_hugepage_mitigation_hard_disabled; int __read_mostly nx_huge_pages = -1; static uint __read_mostly nx_huge_pages_recovery_period_ms; #ifdef CONFIG_PREEMPT_RT /* Recovery can cause latency spikes, disable it for PREEMPT_RT. */ static uint __read_mostly nx_huge_pages_recovery_ratio = 0; #else static uint __read_mostly nx_huge_pages_recovery_ratio = 60; #endif static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp); static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp); static const struct kernel_param_ops nx_huge_pages_ops = { .set = set_nx_huge_pages, .get = get_nx_huge_pages, }; static const struct kernel_param_ops nx_huge_pages_recovery_param_ops = { .set = set_nx_huge_pages_recovery_param, .get = param_get_uint, }; module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644); __MODULE_PARM_TYPE(nx_huge_pages, "bool"); module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_param_ops, &nx_huge_pages_recovery_ratio, 0644); __MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); module_param_cb(nx_huge_pages_recovery_period_ms, &nx_huge_pages_recovery_param_ops, &nx_huge_pages_recovery_period_ms, 0644); __MODULE_PARM_TYPE(nx_huge_pages_recovery_period_ms, "uint"); static bool __read_mostly force_flush_and_sync_on_reuse; module_param_named(flush_on_reuse, force_flush_and_sync_on_reuse, bool, 0644); /* * When setting this variable to true it enables Two-Dimensional-Paging * where the hardware walks 2 page tables: * 1. the guest-virtual to guest-physical * 2. while doing 1. it walks guest-physical to host-physical * If the hardware supports that we don't need to do shadow paging. */ bool tdp_enabled = false; static bool __ro_after_init tdp_mmu_allowed; #ifdef CONFIG_X86_64 bool __read_mostly tdp_mmu_enabled = true; module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0444); EXPORT_SYMBOL_FOR_KVM_INTERNAL(tdp_mmu_enabled); #endif static int max_huge_page_level __read_mostly; static int tdp_root_level __read_mostly; static int max_tdp_level __read_mostly; #define PTE_PREFETCH_NUM 8 #include <trace/events/kvm.h> /* make pte_list_desc fit well in cache lines */ #define PTE_LIST_EXT 14 /* * struct pte_list_desc is the core data structure used to implement a custom * list for tracking a set of related SPTEs, e.g. all the SPTEs that map a * given GFN when used in the context of rmaps. Using a custom list allows KVM * to optimize for the common case where many GFNs will have at most a handful * of SPTEs pointing at them, i.e. allows packing multiple SPTEs into a small * memory footprint, which in turn improves runtime performance by exploiting * cache locality. * * A list is comprised of one or more pte_list_desc objects (descriptors). * Each individual descriptor stores up to PTE_LIST_EXT SPTEs. If a descriptor * is full and a new SPTEs needs to be added, a new descriptor is allocated and * becomes the head of the list. This means that by definitions, all tail * descriptors are full. * * Note, the meta data fields are deliberately placed at the start of the * structure to optimize the cacheline layout; accessing the descriptor will * touch only a single cacheline so long as @spte_count<=6 (or if only the * descriptors metadata is accessed). */ struct pte_list_desc { struct pte_list_desc *more; /* The number of PTEs stored in _this_ descriptor. */ u32 spte_count; /* The number of PTEs stored in all tails of this descriptor. */ u32 tail_count; u64 *sptes[PTE_LIST_EXT]; }; struct kvm_shadow_walk_iterator { u64 addr; hpa_t shadow_addr; u64 *sptep; int level; unsigned index; }; #define for_each_shadow_entry_using_root(_vcpu, _root, _addr, _walker) \ for (shadow_walk_init_using_root(&(_walker), (_vcpu), \ (_root), (_addr)); \ shadow_walk_okay(&(_walker)); \ shadow_walk_next(&(_walker))) #define for_each_shadow_entry(_vcpu, _addr, _walker) \ for (shadow_walk_init(&(_walker), _vcpu, _addr); \ shadow_walk_okay(&(_walker)); \ shadow_walk_next(&(_walker))) #define for_each_shadow_entry_lockless(_vcpu, _addr, _walker, spte) \ for (shadow_walk_init(&(_walker), _vcpu, _addr); \ shadow_walk_okay(&(_walker)) && \ ({ spte = mmu_spte_get_lockless(_walker.sptep); 1; }); \ __shadow_walk_next(&(_walker), spte)) static struct kmem_cache *pte_list_desc_cache; struct kmem_cache *mmu_page_header_cache; static void mmu_spte_set(u64 *sptep, u64 spte); struct kvm_mmu_role_regs { const unsigned long cr0; const unsigned long cr4; const u64 efer; }; #define CREATE_TRACE_POINTS #include "mmutrace.h" /* * Yes, lot's of underscores. They're a hint that you probably shouldn't be * reading from the role_regs. Once the root_role is constructed, it becomes * the single source of truth for the MMU's state. */ #define BUILD_MMU_ROLE_REGS_ACCESSOR(reg, name, flag) \ static inline bool __maybe_unused \ ____is_##reg##_##name(const struct kvm_mmu_role_regs *regs) \ { \ return !!(regs->reg & flag); \ } BUILD_MMU_ROLE_REGS_ACCESSOR(cr0, pg, X86_CR0_PG); BUILD_MMU_ROLE_REGS_ACCESSOR(cr0, wp, X86_CR0_WP); BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, pse, X86_CR4_PSE); BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, pae, X86_CR4_PAE); BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, smep, X86_CR4_SMEP); BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, smap, X86_CR4_SMAP); BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, pke, X86_CR4_PKE); BUILD_MMU_ROLE_REGS_ACCESSOR(cr4, la57, X86_CR4_LA57); BUILD_MMU_ROLE_REGS_ACCESSOR(efer, nx, EFER_NX); BUILD_MMU_ROLE_REGS_ACCESSOR(efer, lma, EFER_LMA); /* * The MMU itself (with a valid role) is the single source of truth for the * MMU. Do not use the regs used to build the MMU/role, nor the vCPU. The * regs don't account for dependencies, e.g. clearing CR4 bits if CR0.PG=1, * and the vCPU may be incorrect/irrelevant. */ #define BUILD_MMU_ROLE_ACCESSOR(base_or_ext, reg, name) \ static inline bool __maybe_unused is_##reg##_##name(struct kvm_mmu *mmu) \ { \ return !!(mmu->cpu_role. base_or_ext . reg##_##name); \ } BUILD_MMU_ROLE_ACCESSOR(base, cr0, wp); BUILD_MMU_ROLE_ACCESSOR(ext, cr4, pse); BUILD_MMU_ROLE_ACCESSOR(ext, cr4, smep); BUILD_MMU_ROLE_ACCESSOR(ext, cr4, smap); BUILD_MMU_ROLE_ACCESSOR(ext, cr4, pke); BUILD_MMU_ROLE_ACCESSOR(ext, cr4, la57); BUILD_MMU_ROLE_ACCESSOR(base, efer, nx); BUILD_MMU_ROLE_ACCESSOR(ext, efer, lma); static inline bool is_cr0_pg(struct kvm_mmu *mmu) { return mmu->cpu_role.base.level > 0; } static inline bool is_cr4_pae(struct kvm_mmu *mmu) { return !mmu->cpu_role.base.has_4_byte_gpte; } static struct kvm_mmu_role_regs vcpu_to_role_regs(struct kvm_vcpu *vcpu) { struct kvm_mmu_role_regs regs = { .cr0 = kvm_read_cr0_bits(vcpu, KVM_MMU_CR0_ROLE_BITS), .cr4 = kvm_read_cr4_bits(vcpu, KVM_MMU_CR4_ROLE_BITS), .efer = vcpu->arch.efer, }; return regs; } static unsigned long get_guest_cr3(struct kvm_vcpu *vcpu) { return kvm_read_cr3(vcpu); } static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) { if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) return kvm_read_cr3(vcpu); return mmu->get_guest_pgd(vcpu); } static inline bool kvm_available_flush_remote_tlbs_range(void) { #if IS_ENABLED(CONFIG_HYPERV) return kvm_x86_ops.flush_remote_tlbs_range; #else return false; #endif } static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index); /* Flush the range of guest memory mapped by the given SPTE. */ static void kvm_flush_remote_tlbs_sptep(struct kvm *kvm, u64 *sptep) { struct kvm_mmu_page *sp = sptep_to_sp(sptep); gfn_t gfn = kvm_mmu_page_get_gfn(sp, spte_index(sptep)); kvm_flush_remote_tlbs_gfn(kvm, gfn, sp->role.level); } static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, unsigned int access) { u64 spte = make_mmio_spte(vcpu, gfn, access); trace_mark_mmio_spte(sptep, gfn, spte); mmu_spte_set(sptep, spte); } static gfn_t get_mmio_spte_gfn(u64 spte) { u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask; gpa |= (spte >> SHADOW_NONPRESENT_OR_RSVD_MASK_LEN) & shadow_nonpresent_or_rsvd_mask; return gpa >> PAGE_SHIFT; } static unsigned get_mmio_spte_access(u64 spte) { return spte & shadow_mmio_access_mask; } static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) { u64 kvm_gen, spte_gen, gen; gen = kvm_vcpu_memslots(vcpu)->generation; if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS)) return false; kvm_gen = gen & MMIO_SPTE_GEN_MASK; spte_gen = get_mmio_spte_generation(spte); trace_check_mmio_spte(spte, kvm_gen, spte_gen); return likely(kvm_gen == spte_gen); } static int is_cpuid_PSE36(void) { return 1; } #ifdef CONFIG_X86_64 static void __set_spte(u64 *sptep, u64 spte) { KVM_MMU_WARN_ON(is_ept_ve_possible(spte)); WRITE_ONCE(*sptep, spte); } static void __update_clear_spte_fast(u64 *sptep, u64 spte) { KVM_MMU_WARN_ON(is_ept_ve_possible(spte)); WRITE_ONCE(*sptep, spte); } static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) { KVM_MMU_WARN_ON(is_ept_ve_possible(spte)); return xchg(sptep, spte); } static u64 __get_spte_lockless(u64 *sptep) { return READ_ONCE(*sptep); } #else union split_spte { struct { u32 spte_low; u32 spte_high; }; u64 spte; }; static void count_spte_clear(u64 *sptep, u64 spte) { struct kvm_mmu_page *sp = sptep_to_sp(sptep); if (is_shadow_present_pte(spte)) return; /* Ensure the spte is completely set before we increase the count */ smp_wmb(); sp->clear_spte_count++; } static void __set_spte(u64 *sptep, u64 spte) { union split_spte *ssptep, sspte; ssptep = (union split_spte *)sptep; sspte = (union split_spte)spte; ssptep->spte_high = sspte.spte_high; /* * If we map the spte from nonpresent to present, We should store * the high bits firstly, then set present bit, so cpu can not * fetch this spte while we are setting the spte. */ smp_wmb(); WRITE_ONCE(ssptep->spte_low, sspte.spte_low); } static void __update_clear_spte_fast(u64 *sptep, u64 spte) { union split_spte *ssptep, sspte; ssptep = (union split_spte *)sptep; sspte = (union split_spte)spte; WRITE_ONCE(ssptep->spte_low, sspte.spte_low); /* * If we map the spte from present to nonpresent, we should clear * present bit firstly to avoid vcpu fetch the old high bits. */ smp_wmb(); ssptep->spte_high = sspte.spte_high; count_spte_clear(sptep, spte); } static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) { union split_spte *ssptep, sspte, orig; ssptep = (union split_spte *)sptep; sspte = (union split_spte)spte; /* xchg acts as a barrier before the setting of the high bits */ orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low); orig.spte_high = ssptep->spte_high; ssptep->spte_high = sspte.spte_high; count_spte_clear(sptep, spte); return orig.spte; } /* * The idea using the light way get the spte on x86_32 guest is from * gup_get_pte (mm/gup.c). * * An spte tlb flush may be pending, because they are coalesced and * we are running out of the MMU lock. Therefore * we need to protect against in-progress updates of the spte. * * Reading the spte while an update is in progress may get the old value * for the high part of the spte. The race is fine for a present->non-present * change (because the high part of the spte is ignored for non-present spte), * but for a present->present change we must reread the spte. * * All such changes are done in two steps (present->non-present and * non-present->present), hence it is enough to count the number of * present->non-present updates: if it changed while reading the spte, * we might have hit the race. This is done using clear_spte_count. */ static u64 __get_spte_lockless(u64 *sptep) { struct kvm_mmu_page *sp = sptep_to_sp(sptep); union split_spte spte, *orig = (union split_spte *)sptep; int count; retry: count = sp->clear_spte_count; smp_rmb(); spte.spte_low = orig->spte_low; smp_rmb(); spte.spte_high = orig->spte_high; smp_rmb(); if (unlikely(spte.spte_low != orig->spte_low || count != sp->clear_spte_count)) goto retry; return spte.spte; } #endif /* Rules for using mmu_spte_set: * Set the sptep from nonpresent to present. * Note: the sptep being assigned *must* be either not present * or in a state where the hardware will not attempt to update * the spte. */ static void mmu_spte_set(u64 *sptep, u64 new_spte) { WARN_ON_ONCE(is_shadow_present_pte(*sptep)); __set_spte(sptep, new_spte); } /* Rules for using mmu_spte_update: * Update the state bits, it means the mapped pfn is not changed. * * Returns true if the TLB needs to be flushed */ static bool mmu_spte_update(u64 *sptep, u64 new_spte) { u64 old_spte = *sptep; WARN_ON_ONCE(!is_shadow_present_pte(new_spte)); check_spte_writable_invariants(new_spte); if (!is_shadow_present_pte(old_spte)) { mmu_spte_set(sptep, new_spte); return false; } if (!spte_needs_atomic_update(old_spte)) __update_clear_spte_fast(sptep, new_spte); else old_spte = __update_clear_spte_slow(sptep, new_spte); WARN_ON_ONCE(!is_shadow_present_pte(old_spte) || spte_to_pfn(old_spte) != spte_to_pfn(new_spte)); return leaf_spte_change_needs_tlb_flush(old_spte, new_spte); } /* * Rules for using mmu_spte_clear_track_bits: * It sets the sptep from present to nonpresent, and track the * state bits, it is used to clear the last level sptep. * Returns the old PTE. */ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) { u64 old_spte = *sptep; int level = sptep_to_sp(sptep)->role.level; if (!is_shadow_present_pte(old_spte) || !spte_needs_atomic_update(old_spte)) __update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE); else old_spte = __update_clear_spte_slow(sptep, SHADOW_NONPRESENT_VALUE); if (!is_shadow_present_pte(old_spte)) return old_spte; kvm_update_page_stats(kvm, level, -1); return old_spte; } /* * Rules for using mmu_spte_clear_no_track: * Directly clear spte without caring the state bits of sptep, * it is used to set the upper level spte. */ static void mmu_spte_clear_no_track(u64 *sptep) { __update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE); } static u64 mmu_spte_get_lockless(u64 *sptep) { return __get_spte_lockless(sptep); } static inline bool is_tdp_mmu_active(struct kvm_vcpu *vcpu) { return tdp_mmu_enabled && vcpu->arch.mmu->root_role.direct; } static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) { if (is_tdp_mmu_active(vcpu)) { kvm_tdp_mmu_walk_lockless_begin(); } else { /* * Prevent page table teardown by making any free-er wait during * kvm_flush_remote_tlbs() IPI to all active vcpus. */ local_irq_disable(); /* * Make sure a following spte read is not reordered ahead of the write * to vcpu->mode. */ smp_store_mb(vcpu->mode, READING_SHADOW_PAGE_TABLES); } } static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu) { if (is_tdp_mmu_active(vcpu)) { kvm_tdp_mmu_walk_lockless_end(); } else { /* * Make sure the write to vcpu->mode is not reordered in front of * reads to sptes. If it does, kvm_mmu_commit_zap_page() can see us * OUTSIDE_GUEST_MODE and proceed to free the shadow page table. */ smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE); local_irq_enable(); } } static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect) { int r; /* 1 rmap, 1 parent PTE per level, and the prefetched rmaps. */ r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache, 1 + PT64_ROOT_MAX_LEVEL + PTE_PREFETCH_NUM); if (r) return r; if (kvm_has_mirrored_tdp(vcpu->kvm)) { r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_external_spt_cache, PT64_ROOT_MAX_LEVEL); if (r) return r; } r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadow_page_cache, PT64_ROOT_MAX_LEVEL); if (r) return r; if (maybe_indirect) { r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadowed_info_cache, PT64_ROOT_MAX_LEVEL); if (r) return r; } return kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_page_header_cache, PT64_ROOT_MAX_LEVEL); } static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) { kvm_mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadow_page_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadowed_info_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_external_spt_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache); } static void mmu_free_pte_list_desc(struct pte_list_desc *pte_list_desc) { kmem_cache_free(pte_list_desc_cache, pte_list_desc); } static bool sp_has_gptes(struct kvm_mmu_page *sp); static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index) { if (sp->role.passthrough) return sp->gfn; if (sp->shadowed_translation) return sp->shadowed_translation[index] >> PAGE_SHIFT; return sp->gfn + (index << ((sp->role.level - 1) * SPTE_LEVEL_BITS)); } /* * For leaf SPTEs, fetch the *guest* access permissions being shadowed. Note * that the SPTE itself may have a more constrained access permissions that * what the guest enforces. For example, a guest may create an executable * huge PTE but KVM may disallow execution to mitigate iTLB multihit. */ static u32 kvm_mmu_page_get_access(struct kvm_mmu_page *sp, int index) { if (sp->shadowed_translation) return sp->shadowed_translation[index] & ACC_ALL; /* * For direct MMUs (e.g. TDP or non-paging guests) or passthrough SPs, * KVM is not shadowing any guest page tables, so the "guest access * permissions" are just ACC_ALL. * * For direct SPs in indirect MMUs (shadow paging), i.e. when KVM * is shadowing a guest huge page with small pages, the guest access * permissions being shadowed are the access permissions of the huge * page. * * In both cases, sp->role.access contains the correct access bits. */ return sp->role.access; } static void kvm_mmu_page_set_translation(struct kvm_mmu_page *sp, int index, gfn_t gfn, unsigned int access) { if (sp->shadowed_translation) { sp->shadowed_translation[index] = (gfn << PAGE_SHIFT) | access; return; } WARN_ONCE(access != kvm_mmu_page_get_access(sp, index), "access mismatch under %s page %llx (expected %u, got %u)\n", sp->role.passthrough ? "passthrough" : "direct", sp->gfn, kvm_mmu_page_get_access(sp, index), access); WARN_ONCE(gfn != kvm_mmu_page_get_gfn(sp, index), "gfn mismatch under %s page %llx (expected %llx, got %llx)\n", sp->role.passthrough ? "passthrough" : "direct", sp->gfn, kvm_mmu_page_get_gfn(sp, index), gfn); } static void kvm_mmu_page_set_access(struct kvm_mmu_page *sp, int index, unsigned int access) { gfn_t gfn = kvm_mmu_page_get_gfn(sp, index); kvm_mmu_page_set_translation(sp, index, gfn, access); } /* * Return the pointer to the large page information for a given gfn, * handling slots that are not large page aligned. */ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, const struct kvm_memory_slot *slot, int level) { unsigned long idx; idx = gfn_to_index(gfn, slot->base_gfn, level); return &slot->arch.lpage_info[level - 2][idx]; } /* * The most significant bit in disallow_lpage tracks whether or not memory * attributes are mixed, i.e. not identical for all gfns at the current level. * The lower order bits are used to refcount other cases where a hugepage is * disallowed, e.g. if KVM has shadow a page table at the gfn. */ #define KVM_LPAGE_MIXED_FLAG BIT(31) static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot, gfn_t gfn, int count) { struct kvm_lpage_info *linfo; int old, i; for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); old = linfo->disallow_lpage; linfo->disallow_lpage += count; WARN_ON_ONCE((old ^ linfo->disallow_lpage) & KVM_LPAGE_MIXED_FLAG); } } void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn) { update_gfn_disallow_lpage_count(slot, gfn, 1); } void kvm_mmu_gfn_allow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn) { update_gfn_disallow_lpage_count(slot, gfn, -1); } static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; gfn_t gfn; kvm->arch.indirect_shadow_pages++; /* * Ensure indirect_shadow_pages is elevated prior to re-reading guest * child PTEs in FNAME(gpte_changed), i.e. guarantee either in-flight * emulated writes are visible before re-reading guest PTEs, or that * an emulated write will see the elevated count and acquire mmu_lock * to update SPTEs. Pairs with the smp_mb() in kvm_mmu_track_write(). */ smp_mb(); gfn = sp->gfn; slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); /* the non-leaf shadow pages are keeping readonly. */ if (sp->role.level > PG_LEVEL_4K) return __kvm_write_track_add_gfn(kvm, slot, gfn); kvm_mmu_gfn_disallow_lpage(slot, gfn); if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K)) kvm_flush_remote_tlbs_gfn(kvm, gfn, PG_LEVEL_4K); } void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp, enum kvm_mmu_type mmu_type) { /* * If it's possible to replace the shadow page with an NX huge page, * i.e. if the shadow page is the only thing currently preventing KVM * from using a huge page, add the shadow page to the list of "to be * zapped for NX recovery" pages. Note, the shadow page can already be * on the list if KVM is reusing an existing shadow page, i.e. if KVM * links a shadow page at multiple points. */ if (!list_empty(&sp->possible_nx_huge_page_link)) return; ++kvm->stat.nx_lpage_splits; ++kvm->arch.possible_nx_huge_pages[mmu_type].nr_pages; list_add_tail(&sp->possible_nx_huge_page_link, &kvm->arch.possible_nx_huge_pages[mmu_type].pages); } static void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp, bool nx_huge_page_possible) { sp->nx_huge_page_disallowed = true; if (nx_huge_page_possible) track_possible_nx_huge_page(kvm, sp, KVM_SHADOW_MMU); } static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; gfn_t gfn; kvm->arch.indirect_shadow_pages--; gfn = sp->gfn; slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); if (sp->role.level > PG_LEVEL_4K) return __kvm_write_track_remove_gfn(kvm, slot, gfn); kvm_mmu_gfn_allow_lpage(slot, gfn); } void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp, enum kvm_mmu_type mmu_type) { if (list_empty(&sp->possible_nx_huge_page_link)) return; --kvm->stat.nx_lpage_splits; --kvm->arch.possible_nx_huge_pages[mmu_type].nr_pages; list_del_init(&sp->possible_nx_huge_page_link); } static void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) { sp->nx_huge_page_disallowed = false; untrack_possible_nx_huge_page(kvm, sp, KVM_SHADOW_MMU); } static struct kvm_memory_slot *gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) { struct kvm_memory_slot *slot; slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return NULL; if (no_dirty_log && kvm_slot_dirty_track_enabled(slot)) return NULL; return slot; } /* * About rmap_head encoding: * * If the bit zero of rmap_head->val is clear, then it points to the only spte * in this rmap chain. Otherwise, (rmap_head->val & ~3) points to a struct * pte_list_desc containing more mappings. */ #define KVM_RMAP_MANY BIT(0) /* * rmaps and PTE lists are mostly protected by mmu_lock (the shadow MMU always * operates with mmu_lock held for write), but rmaps can be walked without * holding mmu_lock so long as the caller can tolerate SPTEs in the rmap chain * being zapped/dropped _while the rmap is locked_. * * Other than the KVM_RMAP_LOCKED flag, modifications to rmap entries must be * done while holding mmu_lock for write. This allows a task walking rmaps * without holding mmu_lock to concurrently walk the same entries as a task * that is holding mmu_lock but _not_ the rmap lock. Neither task will modify * the rmaps, thus the walks are stable. * * As alluded to above, SPTEs in rmaps are _not_ protected by KVM_RMAP_LOCKED, * only the rmap chains themselves are protected. E.g. holding an rmap's lock * ensures all "struct pte_list_desc" fields are stable. */ #define KVM_RMAP_LOCKED BIT(1) static unsigned long __kvm_rmap_lock(struct kvm_rmap_head *rmap_head) { unsigned long old_val, new_val; lockdep_assert_preemption_disabled(); /* * Elide the lock if the rmap is empty, as lockless walkers (read-only * mode) don't need to (and can't) walk an empty rmap, nor can they add * entries to the rmap. I.e. the only paths that process empty rmaps * do so while holding mmu_lock for write, and are mutually exclusive. */ old_val = atomic_long_read(&rmap_head->val); if (!old_val) return 0; do { /* * If the rmap is locked, wait for it to be unlocked before * trying acquire the lock, e.g. to avoid bouncing the cache * line. */ while (old_val & KVM_RMAP_LOCKED) { cpu_relax(); old_val = atomic_long_read(&rmap_head->val); } /* * Recheck for an empty rmap, it may have been purged by the * task that held the lock. */ if (!old_val) return 0; new_val = old_val | KVM_RMAP_LOCKED; /* * Use try_cmpxchg_acquire() to prevent reads and writes to the rmap * from being reordered outside of the critical section created by * __kvm_rmap_lock(). * * Pairs with the atomic_long_set_release() in kvm_rmap_unlock(). * * For the !old_val case, no ordering is needed, as there is no rmap * to walk. */ } while (!atomic_long_try_cmpxchg_acquire(&rmap_head->val, &old_val, new_val)); /* * Return the old value, i.e. _without_ the LOCKED bit set. It's * impossible for the return value to be 0 (see above), i.e. the read- * only unlock flow can't get a false positive and fail to unlock. */ return old_val; } static unsigned long kvm_rmap_lock(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { lockdep_assert_held_write(&kvm->mmu_lock); return __kvm_rmap_lock(rmap_head); } static void __kvm_rmap_unlock(struct kvm_rmap_head *rmap_head, unsigned long val) { KVM_MMU_WARN_ON(val & KVM_RMAP_LOCKED); /* * Ensure that all accesses to the rmap have completed before unlocking * the rmap. * * Pairs with the atomic_long_try_cmpxchg_acquire() in __kvm_rmap_lock(). */ atomic_long_set_release(&rmap_head->val, val); } static void kvm_rmap_unlock(struct kvm *kvm, struct kvm_rmap_head *rmap_head, unsigned long new_val) { lockdep_assert_held_write(&kvm->mmu_lock); __kvm_rmap_unlock(rmap_head, new_val); } static unsigned long kvm_rmap_get(struct kvm_rmap_head *rmap_head) { return atomic_long_read(&rmap_head->val) & ~KVM_RMAP_LOCKED; } /* * If mmu_lock isn't held, rmaps can only be locked in read-only mode. The * actual locking is the same, but the caller is disallowed from modifying the * rmap, and so the unlock flow is a nop if the rmap is/was empty. */ static unsigned long kvm_rmap_lock_readonly(struct kvm_rmap_head *rmap_head) { unsigned long rmap_val; preempt_disable(); rmap_val = __kvm_rmap_lock(rmap_head); if (!rmap_val) preempt_enable(); return rmap_val; } static void kvm_rmap_unlock_readonly(struct kvm_rmap_head *rmap_head, unsigned long old_val) { if (!old_val) return; KVM_MMU_WARN_ON(old_val != kvm_rmap_get(rmap_head)); __kvm_rmap_unlock(rmap_head, old_val); preempt_enable(); } /* * Returns the number of pointers in the rmap chain, not counting the new one. */ static int pte_list_add(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, u64 *spte, struct kvm_rmap_head *rmap_head) { unsigned long old_val, new_val; struct pte_list_desc *desc; int count = 0; old_val = kvm_rmap_lock(kvm, rmap_head); if (!old_val) { new_val = (unsigned long)spte; } else if (!(old_val & KVM_RMAP_MANY)) { desc = kvm_mmu_memory_cache_alloc(cache); desc->sptes[0] = (u64 *)old_val; desc->sptes[1] = spte; desc->spte_count = 2; desc->tail_count = 0; new_val = (unsigned long)desc | KVM_RMAP_MANY; ++count; } else { desc = (struct pte_list_desc *)(old_val & ~KVM_RMAP_MANY); count = desc->tail_count + desc->spte_count; /* * If the previous head is full, allocate a new head descriptor * as tail descriptors are always kept full. */ if (desc->spte_count == PTE_LIST_EXT) { desc = kvm_mmu_memory_cache_alloc(cache); desc->more = (struct pte_list_desc *)(old_val & ~KVM_RMAP_MANY); desc->spte_count = 0; desc->tail_count = count; new_val = (unsigned long)desc | KVM_RMAP_MANY; } else { new_val = old_val; } desc->sptes[desc->spte_count++] = spte; } kvm_rmap_unlock(kvm, rmap_head, new_val); return count; } static void pte_list_desc_remove_entry(struct kvm *kvm, unsigned long *rmap_val, struct pte_list_desc *desc, int i) { struct pte_list_desc *head_desc = (struct pte_list_desc *)(*rmap_val & ~KVM_RMAP_MANY); int j = head_desc->spte_count - 1; /* * The head descriptor should never be empty. A new head is added only * when adding an entry and the previous head is full, and heads are * removed (this flow) when they become empty. */ KVM_BUG_ON_DATA_CORRUPTION(j < 0, kvm); /* * Replace the to-be-freed SPTE with the last valid entry from the head * descriptor to ensure that tail descriptors are full at all times. * Note, this also means that tail_count is stable for each descriptor. */ desc->sptes[i] = head_desc->sptes[j]; head_desc->sptes[j] = NULL; head_desc->spte_count--; if (head_desc->spte_count) return; /* * The head descriptor is empty. If there are no tail descriptors, * nullify the rmap head to mark the list as empty, else point the rmap * head at the next descriptor, i.e. the new head. */ if (!head_desc->more) *rmap_val = 0; else *rmap_val = (unsigned long)head_desc->more | KVM_RMAP_MANY; mmu_free_pte_list_desc(head_desc); } static void pte_list_remove(struct kvm *kvm, u64 *spte, struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; unsigned long rmap_val; int i; rmap_val = kvm_rmap_lock(kvm, rmap_head); if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_val, kvm)) goto out; if (!(rmap_val & KVM_RMAP_MANY)) { if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_val != spte, kvm)) goto out; rmap_val = 0; } else { desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY); while (desc) { for (i = 0; i < desc->spte_count; ++i) { if (desc->sptes[i] == spte) { pte_list_desc_remove_entry(kvm, &rmap_val, desc, i); goto out; } } desc = desc->more; } KVM_BUG_ON_DATA_CORRUPTION(true, kvm); } out: kvm_rmap_unlock(kvm, rmap_head, rmap_val); } static void kvm_zap_one_rmap_spte(struct kvm *kvm, struct kvm_rmap_head *rmap_head, u64 *sptep) { mmu_spte_clear_track_bits(kvm, sptep); pte_list_remove(kvm, sptep, rmap_head); } /* Return true if at least one SPTE was zapped, false otherwise */ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc, *next; unsigned long rmap_val; int i; rmap_val = kvm_rmap_lock(kvm, rmap_head); if (!rmap_val) return false; if (!(rmap_val & KVM_RMAP_MANY)) { mmu_spte_clear_track_bits(kvm, (u64 *)rmap_val); goto out; } desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY); for (; desc; desc = next) { for (i = 0; i < desc->spte_count; i++) mmu_spte_clear_track_bits(kvm, desc->sptes[i]); next = desc->more; mmu_free_pte_list_desc(desc); } out: /* rmap_head is meaningless now, remember to reset it */ kvm_rmap_unlock(kvm, rmap_head, 0); return true; } unsigned int pte_list_count(struct kvm_rmap_head *rmap_head) { unsigned long rmap_val = kvm_rmap_get(rmap_head); struct pte_list_desc *desc; if (!rmap_val) return 0; else if (!(rmap_val & KVM_RMAP_MANY)) return 1; desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY); return desc->tail_count + desc->spte_count; } static struct kvm_rmap_head *gfn_to_rmap(gfn_t gfn, int level, const struct kvm_memory_slot *slot) { unsigned long idx; idx = gfn_to_index(gfn, slot->base_gfn, level); return &slot->arch.rmap[level - PG_LEVEL_4K][idx]; } static void rmap_remove(struct kvm *kvm, u64 *spte) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; struct kvm_mmu_page *sp; gfn_t gfn; struct kvm_rmap_head *rmap_head; sp = sptep_to_sp(spte); gfn = kvm_mmu_page_get_gfn(sp, spte_index(spte)); /* * Unlike rmap_add, rmap_remove does not run in the context of a vCPU * so we have to determine which memslots to use based on context * information in sp->role. */ slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); pte_list_remove(kvm, spte, rmap_head); } /* * Used by the following functions to iterate through the sptes linked by a * rmap. All fields are private and not assumed to be used outside. */ struct rmap_iterator { /* private fields */ struct rmap_head *head; struct pte_list_desc *desc; /* holds the sptep if not NULL */ int pos; /* index of the sptep */ }; /* * Iteration must be started by this function. This should also be used after * removing/dropping sptes from the rmap link because in such cases the * information in the iterator may not be valid. * * Returns sptep if found, NULL otherwise. */ static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head, struct rmap_iterator *iter) { unsigned long rmap_val = kvm_rmap_get(rmap_head); if (!rmap_val) return NULL; if (!(rmap_val & KVM_RMAP_MANY)) { iter->desc = NULL; return (u64 *)rmap_val; } iter->desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY); iter->pos = 0; return iter->desc->sptes[iter->pos]; } /* * Must be used with a valid iterator: e.g. after rmap_get_first(). * * Returns sptep if found, NULL otherwise. */ static u64 *rmap_get_next(struct rmap_iterator *iter) { if (iter->desc) { if (iter->pos < PTE_LIST_EXT - 1) { ++iter->pos; if (iter->desc->sptes[iter->pos]) return iter->desc->sptes[iter->pos]; } iter->desc = iter->desc->more; if (iter->desc) { iter->pos = 0; /* desc->sptes[0] cannot be NULL */ return iter->desc->sptes[iter->pos]; } } return NULL; } #define __for_each_rmap_spte(_rmap_head_, _iter_, _sptep_) \ for (_sptep_ = rmap_get_first(_rmap_head_, _iter_); \ _sptep_; _sptep_ = rmap_get_next(_iter_)) #define for_each_rmap_spte(_rmap_head_, _iter_, _sptep_) \ __for_each_rmap_spte(_rmap_head_, _iter_, _sptep_) \ if (!WARN_ON_ONCE(!is_shadow_present_pte(*(_sptep_)))) \ #define for_each_rmap_spte_lockless(_rmap_head_, _iter_, _sptep_, _spte_) \ __for_each_rmap_spte(_rmap_head_, _iter_, _sptep_) \ if (is_shadow_present_pte(_spte_ = mmu_spte_get_lockless(sptep))) static void drop_spte(struct kvm *kvm, u64 *sptep) { u64 old_spte = mmu_spte_clear_track_bits(kvm, sptep); if (is_shadow_present_pte(old_spte)) rmap_remove(kvm, sptep); } static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush) { struct kvm_mmu_page *sp; sp = sptep_to_sp(sptep); WARN_ON_ONCE(sp->role.level == PG_LEVEL_4K); drop_spte(kvm, sptep); if (flush) kvm_flush_remote_tlbs_sptep(kvm, sptep); } /* * Write-protect on the specified @sptep, @pt_protect indicates whether * spte write-protection is caused by protecting shadow page table. * * Note: write protection is difference between dirty logging and spte * protection: * - for dirty logging, the spte can be set to writable at anytime if * its dirty bitmap is properly set. * - for spte protection, the spte can be writable only after unsync-ing * shadow page. * * Return true if tlb need be flushed. */ static bool spte_write_protect(u64 *sptep, bool pt_protect) { u64 spte = *sptep; if (!is_writable_pte(spte) && !(pt_protect && is_mmu_writable_spte(spte))) return false; if (pt_protect) spte &= ~shadow_mmu_writable_mask; spte = spte & ~PT_WRITABLE_MASK; return mmu_spte_update(sptep, spte); } static bool rmap_write_protect(struct kvm_rmap_head *rmap_head, bool pt_protect) { u64 *sptep; struct rmap_iterator iter; bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) flush |= spte_write_protect(sptep, pt_protect); return flush; } static bool spte_clear_dirty(u64 *sptep) { u64 spte = *sptep; KVM_MMU_WARN_ON(!spte_ad_enabled(spte)); spte &= ~shadow_dirty_mask; return mmu_spte_update(sptep, spte); } /* * Gets the GFN ready for another round of dirty logging by clearing the * - D bit on ad-enabled SPTEs, and * - W bit on ad-disabled SPTEs. * Returns true iff any D or W bits were cleared. */ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head, const struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) { if (spte_ad_need_write_protect(*sptep)) flush |= test_and_clear_bit(PT_WRITABLE_SHIFT, (unsigned long *)sptep); else flush |= spte_clear_dirty(sptep); } return flush; } static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { struct kvm_rmap_head *rmap_head; if (tdp_mmu_enabled) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, true); if (!kvm_memslots_have_rmaps(kvm)) return; while (mask) { rmap_head = gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), PG_LEVEL_4K, slot); rmap_write_protect(rmap_head, false); /* clear the first set bit */ mask &= mask - 1; } } static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { struct kvm_rmap_head *rmap_head; if (tdp_mmu_enabled) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, false); if (!kvm_memslots_have_rmaps(kvm)) return; while (mask) { rmap_head = gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), PG_LEVEL_4K, slot); __rmap_clear_dirty(kvm, rmap_head, slot); /* clear the first set bit */ mask &= mask - 1; } } void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { /* * If the slot was assumed to be "initially all dirty", write-protect * huge pages to ensure they are split to 4KiB on the first write (KVM * dirty logs at 4KiB granularity). If eager page splitting is enabled, * immediately try to split huge pages, e.g. so that vCPUs don't get * saddled with the cost of splitting. * * The gfn_offset is guaranteed to be aligned to 64, but the base_gfn * of memslot has no such restriction, so the range can cross two large * pages. */ if (kvm_dirty_log_manual_protect_and_init_set(kvm)) { gfn_t start = slot->base_gfn + gfn_offset + __ffs(mask); gfn_t end = slot->base_gfn + gfn_offset + __fls(mask); if (READ_ONCE(eager_page_split)) kvm_mmu_try_split_huge_pages(kvm, slot, start, end + 1, PG_LEVEL_4K); kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M); /* Cross two large pages? */ if (ALIGN(start << PAGE_SHIFT, PMD_SIZE) != ALIGN(end << PAGE_SHIFT, PMD_SIZE)) kvm_mmu_slot_gfn_write_protect(kvm, slot, end, PG_LEVEL_2M); } /* * (Re)Enable dirty logging for all 4KiB SPTEs that map the GFNs in * mask. If PML is enabled and the GFN doesn't need to be write- * protected for other reasons, e.g. shadow paging, clear the Dirty bit. * Otherwise clear the Writable bit. * * Note that kvm_mmu_clear_dirty_pt_masked() is called whenever PML is * enabled but it chooses between clearing the Dirty bit and Writeable * bit based on the context. */ if (kvm->arch.cpu_dirty_log_size) kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask); else kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } int kvm_cpu_dirty_log_size(struct kvm *kvm) { return kvm->arch.cpu_dirty_log_size; } bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn, int min_level) { struct kvm_rmap_head *rmap_head; int i; bool write_protected = false; if (kvm_memslots_have_rmaps(kvm)) { for (i = min_level; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { rmap_head = gfn_to_rmap(gfn, i, slot); write_protected |= rmap_write_protect(rmap_head, true); } } if (tdp_mmu_enabled) write_protected |= kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn, min_level); return write_protected; } static bool kvm_vcpu_write_protect_gfn(struct kvm_vcpu *vcpu, u64 gfn) { struct kvm_memory_slot *slot; slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn, PG_LEVEL_4K); } static bool kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, const struct kvm_memory_slot *slot) { return kvm_zap_all_rmap_sptes(kvm, rmap_head); } struct slot_rmap_walk_iterator { /* input fields. */ const struct kvm_memory_slot *slot; gfn_t start_gfn; gfn_t end_gfn; int start_level; int end_level; /* output fields. */ gfn_t gfn; struct kvm_rmap_head *rmap; int level; /* private field. */ struct kvm_rmap_head *end_rmap; }; static void rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level) { iterator->level = level; iterator->gfn = iterator->start_gfn; iterator->rmap = gfn_to_rmap(iterator->gfn, level, iterator->slot); iterator->end_rmap = gfn_to_rmap(iterator->end_gfn, level, iterator->slot); } static void slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator, const struct kvm_memory_slot *slot, int start_level, int end_level, gfn_t start_gfn, gfn_t end_gfn) { iterator->slot = slot; iterator->start_level = start_level; iterator->end_level = end_level; iterator->start_gfn = start_gfn; iterator->end_gfn = end_gfn; rmap_walk_init_level(iterator, iterator->start_level); } static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator) { return !!iterator->rmap; } static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) { while (++iterator->rmap <= iterator->end_rmap) { iterator->gfn += KVM_PAGES_PER_HPAGE(iterator->level); if (atomic_long_read(&iterator->rmap->val)) return; } if (++iterator->level > iterator->end_level) { iterator->rmap = NULL; return; } rmap_walk_init_level(iterator, iterator->level); } #define for_each_slot_rmap_range(_slot_, _start_level_, _end_level_, \ _start_gfn, _end_gfn, _iter_) \ for (slot_rmap_walk_init(_iter_, _slot_, _start_level_, \ _end_level_, _start_gfn, _end_gfn); \ slot_rmap_walk_okay(_iter_); \ slot_rmap_walk_next(_iter_)) /* The return value indicates if tlb flush on all vcpus is needed. */ typedef bool (*slot_rmaps_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head, const struct kvm_memory_slot *slot); static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, const struct kvm_memory_slot *slot, slot_rmaps_handler fn, int start_level, int end_level, gfn_t start_gfn, gfn_t end_gfn, bool can_yield, bool flush_on_yield, bool flush) { struct slot_rmap_walk_iterator iterator; lockdep_assert_held_write(&kvm->mmu_lock); for_each_slot_rmap_range(slot, start_level, end_level, start_gfn, end_gfn, &iterator) { if (iterator.rmap) flush |= fn(kvm, iterator.rmap, slot); if (!can_yield) continue; if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { if (flush && flush_on_yield) { kvm_flush_remote_tlbs_range(kvm, start_gfn, iterator.gfn - start_gfn + 1); flush = false; } cond_resched_rwlock_write(&kvm->mmu_lock); } } return flush; } static __always_inline bool walk_slot_rmaps(struct kvm *kvm, const struct kvm_memory_slot *slot, slot_rmaps_handler fn, int start_level, int end_level, bool flush_on_yield) { return __walk_slot_rmaps(kvm, slot, fn, start_level, end_level, slot->base_gfn, slot->base_gfn + slot->npages - 1, true, flush_on_yield, false); } static __always_inline bool walk_slot_rmaps_4k(struct kvm *kvm, const struct kvm_memory_slot *slot, slot_rmaps_handler fn, bool flush_on_yield) { return walk_slot_rmaps(kvm, slot, fn, PG_LEVEL_4K, PG_LEVEL_4K, flush_on_yield); } static bool __kvm_rmap_zap_gfn_range(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t start, gfn_t end, bool can_yield, bool flush) { return __walk_slot_rmaps(kvm, slot, kvm_zap_rmap, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, start, end - 1, can_yield, true, flush); } bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { bool flush = false; /* * To prevent races with vCPUs faulting in a gfn using stale data, * zapping a gfn range must be protected by mmu_invalidate_in_progress * (and mmu_invalidate_seq). The only exception is memslot deletion; * in that case, SRCU synchronization ensures that SPTEs are zapped * after all vCPUs have unlocked SRCU, guaranteeing that vCPUs see the * invalid slot. */ lockdep_assert_once(kvm->mmu_invalidate_in_progress || lockdep_is_held(&kvm->slots_lock)); if (kvm_memslots_have_rmaps(kvm)) flush = __kvm_rmap_zap_gfn_range(kvm, range->slot, range->start, range->end, range->may_block, flush); if (tdp_mmu_enabled) flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); if (kvm_x86_ops.set_apic_access_page_addr && range->slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); return flush; } #define RMAP_RECYCLE_THRESHOLD 1000 static void __rmap_add(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, const struct kvm_memory_slot *slot, u64 *spte, gfn_t gfn, unsigned int access) { struct kvm_mmu_page *sp; struct kvm_rmap_head *rmap_head; int rmap_count; sp = sptep_to_sp(spte); kvm_mmu_page_set_translation(sp, spte_index(spte), gfn, access); kvm_update_page_stats(kvm, sp->role.level, 1); rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); rmap_count = pte_list_add(kvm, cache, spte, rmap_head); if (rmap_count > kvm->stat.max_mmu_rmap_size) kvm->stat.max_mmu_rmap_size = rmap_count; if (rmap_count > RMAP_RECYCLE_THRESHOLD) { kvm_zap_all_rmap_sptes(kvm, rmap_head); kvm_flush_remote_tlbs_gfn(kvm, gfn, sp->role.level); } } static void rmap_add(struct kvm_vcpu *vcpu, const struct kvm_memory_slot *slot, u64 *spte, gfn_t gfn, unsigned int access) { struct kvm_mmu_memory_cache *cache = &vcpu->arch.mmu_pte_list_desc_cache; __rmap_add(vcpu->kvm, cache, slot, spte, gfn, access); } static bool kvm_rmap_age_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool test_only) { struct kvm_rmap_head *rmap_head; struct rmap_iterator iter; unsigned long rmap_val; bool young = false; u64 *sptep; gfn_t gfn; int level; u64 spte; for (level = PG_LEVEL_4K; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { for (gfn = range->start; gfn < range->end; gfn += KVM_PAGES_PER_HPAGE(level)) { rmap_head = gfn_to_rmap(gfn, level, range->slot); rmap_val = kvm_rmap_lock_readonly(rmap_head); for_each_rmap_spte_lockless(rmap_head, &iter, sptep, spte) { if (!is_accessed_spte(spte)) continue; if (test_only) { kvm_rmap_unlock_readonly(rmap_head, rmap_val); return true; } if (spte_ad_enabled(spte)) clear_bit((ffs(shadow_accessed_mask) - 1), (unsigned long *)sptep); else /* * If the following cmpxchg fails, the * spte is being concurrently modified * and should most likely stay young. */ cmpxchg64(sptep, spte, mark_spte_for_access_track(spte)); young = true; } kvm_rmap_unlock_readonly(rmap_head, rmap_val); } } return young; } static bool kvm_may_have_shadow_mmu_sptes(struct kvm *kvm) { return !tdp_mmu_enabled || READ_ONCE(kvm->arch.indirect_shadow_pages); } bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { bool young = false; if (tdp_mmu_enabled) young = kvm_tdp_mmu_age_gfn_range(kvm, range); if (kvm_may_have_shadow_mmu_sptes(kvm)) young |= kvm_rmap_age_gfn_range(kvm, range, false); return young; } bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { bool young = false; if (tdp_mmu_enabled) young = kvm_tdp_mmu_test_age_gfn(kvm, range); if (young) return young; if (kvm_may_have_shadow_mmu_sptes(kvm)) young |= kvm_rmap_age_gfn_range(kvm, range, true); return young; } static void kvm_mmu_check_sptes_at_free(struct kvm_mmu_page *sp) { #ifdef CONFIG_KVM_PROVE_MMU int i; for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { if (KVM_MMU_WARN_ON(is_shadow_present_pte(sp->spt[i]))) pr_err_ratelimited("SPTE %llx (@ %p) for gfn %llx shadow-present at free", sp->spt[i], &sp->spt[i], kvm_mmu_page_get_gfn(sp, i)); } #endif } static void kvm_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { kvm->arch.n_used_mmu_pages++; kvm_account_pgtable_pages((void *)sp->spt, +1); } static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { kvm->arch.n_used_mmu_pages--; kvm_account_pgtable_pages((void *)sp->spt, -1); } static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp) { kvm_mmu_check_sptes_at_free(sp); hlist_del(&sp->hash_link); list_del(&sp->link); free_page((unsigned long)sp->spt); free_page((unsigned long)sp->shadowed_translation); kmem_cache_free(mmu_page_header_cache, sp); } static unsigned kvm_page_table_hashfn(gfn_t gfn) { return hash_64(gfn, KVM_MMU_HASH_SHIFT); } static void mmu_page_add_parent_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, struct kvm_mmu_page *sp, u64 *parent_pte) { if (!parent_pte) return; pte_list_add(kvm, cache, parent_pte, &sp->parent_ptes); } static void mmu_page_remove_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *parent_pte) { pte_list_remove(kvm, parent_pte, &sp->parent_ptes); } static void drop_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *parent_pte) { mmu_page_remove_parent_pte(kvm, sp, parent_pte); mmu_spte_clear_no_track(parent_pte); } static void mark_unsync(u64 *spte); static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp) { u64 *sptep; struct rmap_iterator iter; for_each_rmap_spte(&sp->parent_ptes, &iter, sptep) { mark_unsync(sptep); } } static void mark_unsync(u64 *spte) { struct kvm_mmu_page *sp; sp = sptep_to_sp(spte); if (__test_and_set_bit(spte_index(spte), sp->unsync_child_bitmap)) return; if (sp->unsync_children++) return; kvm_mmu_mark_parents_unsync(sp); } #define KVM_PAGE_ARRAY_NR 16 struct kvm_mmu_pages { struct mmu_page_and_offset { struct kvm_mmu_page *sp; unsigned int idx; } page[KVM_PAGE_ARRAY_NR]; unsigned int nr; }; static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, int idx) { int i; if (sp->unsync) for (i=0; i < pvec->nr; i++) if (pvec->page[i].sp == sp) return 0; pvec->page[pvec->nr].sp = sp; pvec->page[pvec->nr].idx = idx; pvec->nr++; return (pvec->nr == KVM_PAGE_ARRAY_NR); } static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx) { --sp->unsync_children; WARN_ON_ONCE((int)sp->unsync_children < 0); __clear_bit(idx, sp->unsync_child_bitmap); } static int __mmu_unsync_walk(struct kvm_mmu_page *sp, struct kvm_mmu_pages *pvec) { int i, ret, nr_unsync_leaf = 0; for_each_set_bit(i, sp->unsync_child_bitmap, 512) { struct kvm_mmu_page *child; u64 ent = sp->spt[i]; if (!is_shadow_present_pte(ent) || is_large_pte(ent)) { clear_unsync_child_bit(sp, i); continue; } child = spte_to_child_sp(ent); if (child->unsync_children) { if (mmu_pages_add(pvec, child, i)) return -ENOSPC; ret = __mmu_unsync_walk(child, pvec); if (!ret) { clear_unsync_child_bit(sp, i); continue; } else if (ret > 0) { nr_unsync_leaf += ret; } else return ret; } else if (child->unsync) { nr_unsync_leaf++; if (mmu_pages_add(pvec, child, i)) return -ENOSPC; } else clear_unsync_child_bit(sp, i); } return nr_unsync_leaf; } #define INVALID_INDEX (-1) static int mmu_unsync_walk(struct kvm_mmu_page *sp, struct kvm_mmu_pages *pvec) { pvec->nr = 0; if (!sp->unsync_children) return 0; mmu_pages_add(pvec, sp, INVALID_INDEX); return __mmu_unsync_walk(sp, pvec); } static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) { WARN_ON_ONCE(!sp->unsync); trace_kvm_mmu_sync_page(sp); sp->unsync = 0; --kvm->stat.mmu_unsync; } static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, struct list_head *invalid_list); static void kvm_mmu_commit_zap_page(struct kvm *kvm, struct list_head *invalid_list); static bool sp_has_gptes(struct kvm_mmu_page *sp) { if (sp->role.direct) return false; if (sp->role.passthrough) return false; return true; } static __ro_after_init HLIST_HEAD(empty_page_hash); static struct hlist_head *kvm_get_mmu_page_hash(struct kvm *kvm, gfn_t gfn) { /* * Ensure the load of the hash table pointer itself is ordered before * loads to walk the table. The pointer is set at runtime outside of * mmu_lock when the TDP MMU is enabled, i.e. when the hash table of * shadow pages becomes necessary only when KVM needs to shadow L1's * TDP for an L2 guest. Pairs with the smp_store_release() in * kvm_mmu_alloc_page_hash(). */ struct hlist_head *page_hash = smp_load_acquire(&kvm->arch.mmu_page_hash); lockdep_assert_held(&kvm->mmu_lock); if (!page_hash) return &empty_page_hash; return &page_hash[kvm_page_table_hashfn(gfn)]; } #define for_each_valid_sp(_kvm, _sp, _list) \ hlist_for_each_entry(_sp, _list, hash_link) \ if (is_obsolete_sp((_kvm), (_sp))) { \ } else #define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn) \ for_each_valid_sp(_kvm, _sp, kvm_get_mmu_page_hash(_kvm, _gfn)) \ if ((_sp)->gfn != (_gfn) || !sp_has_gptes(_sp)) {} else static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { union kvm_mmu_page_role root_role = vcpu->arch.mmu->root_role; /* * Ignore various flags when verifying that it's safe to sync a shadow * page using the current MMU context. * * - level: not part of the overall MMU role and will never match as the MMU's * level tracks the root level * - access: updated based on the new guest PTE * - quadrant: not part of the overall MMU role (similar to level) */ const union kvm_mmu_page_role sync_role_ign = { .level = 0xf, .access = 0x7, .quadrant = 0x3, .passthrough = 0x1, }; /* * Direct pages can never be unsync, and KVM should never attempt to * sync a shadow page for a different MMU context, e.g. if the role * differs then the memslot lookup (SMM vs. non-SMM) will be bogus, the * reserved bits checks will be wrong, etc... */ if (WARN_ON_ONCE(sp->role.direct || !vcpu->arch.mmu->sync_spte || (sp->role.word ^ root_role.word) & ~sync_role_ign.word)) return false; return true; } static int kvm_sync_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i) { /* sp->spt[i] has initial value of shadow page table allocation */ if (sp->spt[i] == SHADOW_NONPRESENT_VALUE) return 0; return vcpu->arch.mmu->sync_spte(vcpu, sp, i); } static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { int flush = 0; int i; if (!kvm_sync_page_check(vcpu, sp)) return -1; for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { int ret = kvm_sync_spte(vcpu, sp, i); if (ret < -1) return -1; flush |= ret; } /* * Note, any flush is purely for KVM's correctness, e.g. when dropping * an existing SPTE or clearing W/A/D bits to ensure an mmu_notifier * unmap or dirty logging event doesn't fail to flush. The guest is * responsible for flushing the TLB to ensure any changes in protection * bits are recognized, i.e. until the guest flushes or page faults on * a relevant address, KVM is architecturally allowed to let vCPUs use * cached translations with the old protection bits. */ return flush; } static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { int ret = __kvm_sync_page(vcpu, sp); if (ret < 0) kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); return ret; } static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm, struct list_head *invalid_list, bool remote_flush) { if (!remote_flush && list_empty(invalid_list)) return false; if (!list_empty(invalid_list)) kvm_mmu_commit_zap_page(kvm, invalid_list); else kvm_flush_remote_tlbs(kvm); return true; } static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { if (sp->role.invalid) return true; /* TDP MMU pages do not use the MMU generation. */ return !is_tdp_mmu_page(sp) && unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); } struct mmu_page_path { struct kvm_mmu_page *parent[PT64_ROOT_MAX_LEVEL]; unsigned int idx[PT64_ROOT_MAX_LEVEL]; }; #define for_each_sp(pvec, sp, parents, i) \ for (i = mmu_pages_first(&pvec, &parents); \ i < pvec.nr && ({ sp = pvec.page[i].sp; 1;}); \ i = mmu_pages_next(&pvec, &parents, i)) static int mmu_pages_next(struct kvm_mmu_pages *pvec, struct mmu_page_path *parents, int i) { int n; for (n = i+1; n < pvec->nr; n++) { struct kvm_mmu_page *sp = pvec->page[n].sp; unsigned idx = pvec->page[n].idx; int level = sp->role.level; parents->idx[level-1] = idx; if (level == PG_LEVEL_4K) break; parents->parent[level-2] = sp; } return n; } static int mmu_pages_first(struct kvm_mmu_pages *pvec, struct mmu_page_path *parents) { struct kvm_mmu_page *sp; int level; if (pvec->nr == 0) return 0; WARN_ON_ONCE(pvec->page[0].idx != INVALID_INDEX); sp = pvec->page[0].sp; level = sp->role.level; WARN_ON_ONCE(level == PG_LEVEL_4K); parents->parent[level-2] = sp; /* Also set up a sentinel. Further entries in pvec are all * children of sp, so this element is never overwritten. */ parents->parent[level-1] = NULL; return mmu_pages_next(pvec, parents, 0); } static void mmu_pages_clear_parents(struct mmu_page_path *parents) { struct kvm_mmu_page *sp; unsigned int level = 0; do { unsigned int idx = parents->idx[level]; sp = parents->parent[level]; if (!sp) return; WARN_ON_ONCE(idx == INVALID_INDEX); clear_unsync_child_bit(sp, idx); level++; } while (!sp->unsync_children); } static int mmu_sync_children(struct kvm_vcpu *vcpu, struct kvm_mmu_page *parent, bool can_yield) { int i; struct kvm_mmu_page *sp; struct mmu_page_path parents; struct kvm_mmu_pages pages; LIST_HEAD(invalid_list); bool flush = false; while (mmu_unsync_walk(parent, &pages)) { bool protected = false; for_each_sp(pages, sp, parents, i) protected |= kvm_vcpu_write_protect_gfn(vcpu, sp->gfn); if (protected) { kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, true); flush = false; } for_each_sp(pages, sp, parents, i) { kvm_unlink_unsync_page(vcpu->kvm, sp); flush |= kvm_sync_page(vcpu, sp, &invalid_list) > 0; mmu_pages_clear_parents(&parents); } if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) { kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, flush); if (!can_yield) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); return -EINTR; } cond_resched_rwlock_write(&vcpu->kvm->mmu_lock); flush = false; } } kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, flush); return 0; } static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp) { atomic_set(&sp->write_flooding_count, 0); } static void clear_sp_write_flooding_count(u64 *spte) { __clear_sp_write_flooding_count(sptep_to_sp(spte)); } /* * The vCPU is required when finding indirect shadow pages; the shadow * page may already exist and syncing it needs the vCPU pointer in * order to read guest page tables. Direct shadow pages are never * unsync, thus @vcpu can be NULL if @role.direct is true. */ static struct kvm_mmu_page *kvm_mmu_find_shadow_page(struct kvm *kvm, struct kvm_vcpu *vcpu, gfn_t gfn, struct hlist_head *sp_list, union kvm_mmu_page_role role) { struct kvm_mmu_page *sp; int ret; int collisions = 0; LIST_HEAD(invalid_list); for_each_valid_sp(kvm, sp, sp_list) { if (sp->gfn != gfn) { collisions++; continue; } if (sp->role.word != role.word) { /* * If the guest is creating an upper-level page, zap * unsync pages for the same gfn. While it's possible * the guest is using recursive page tables, in all * likelihood the guest has stopped using the unsync * page and is installing a completely unrelated page. * Unsync pages must not be left as is, because the new * upper-level page will be write-protected. */ if (role.level > PG_LEVEL_4K && sp->unsync) kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); continue; } /* unsync and write-flooding only apply to indirect SPs. */ if (sp->role.direct) goto out; if (sp->unsync) { if (KVM_BUG_ON(!vcpu, kvm)) break; /* * The page is good, but is stale. kvm_sync_page does * get the latest guest state, but (unlike mmu_unsync_children) * it doesn't write-protect the page or mark it synchronized! * This way the validity of the mapping is ensured, but the * overhead of write protection is not incurred until the * guest invalidates the TLB mapping. This allows multiple * SPs for a single gfn to be unsync. * * If the sync fails, the page is zapped. If so, break * in order to rebuild it. */ ret = kvm_sync_page(vcpu, sp, &invalid_list); if (ret < 0) break; WARN_ON_ONCE(!list_empty(&invalid_list)); if (ret > 0) kvm_flush_remote_tlbs(kvm); } __clear_sp_write_flooding_count(sp); goto out; } sp = NULL; ++kvm->stat.mmu_cache_miss; out: kvm_mmu_commit_zap_page(kvm, &invalid_list); if (collisions > kvm->stat.max_mmu_page_hash_collisions) kvm->stat.max_mmu_page_hash_collisions = collisions; return sp; } /* Caches used when allocating a new shadow page. */ struct shadow_page_caches { struct kvm_mmu_memory_cache *page_header_cache; struct kvm_mmu_memory_cache *shadow_page_cache; struct kvm_mmu_memory_cache *shadowed_info_cache; }; static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm, struct shadow_page_caches *caches, gfn_t gfn, struct hlist_head *sp_list, union kvm_mmu_page_role role) { struct kvm_mmu_page *sp; sp = kvm_mmu_memory_cache_alloc(caches->page_header_cache); sp->spt = kvm_mmu_memory_cache_alloc(caches->shadow_page_cache); if (!role.direct && role.level <= KVM_MAX_HUGEPAGE_LEVEL) sp->shadowed_translation = kvm_mmu_memory_cache_alloc(caches->shadowed_info_cache); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); INIT_LIST_HEAD(&sp->possible_nx_huge_page_link); /* * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages() * depends on valid pages being added to the head of the list. See * comments in kvm_zap_obsolete_pages(). */ sp->mmu_valid_gen = kvm->arch.mmu_valid_gen; list_add(&sp->link, &kvm->arch.active_mmu_pages); kvm_account_mmu_page(kvm, sp); sp->gfn = gfn; sp->role = role; hlist_add_head(&sp->hash_link, sp_list); if (sp_has_gptes(sp)) account_shadowed(kvm, sp); return sp; } /* Note, @vcpu may be NULL if @role.direct is true; see kvm_mmu_find_shadow_page. */ static struct kvm_mmu_page *__kvm_mmu_get_shadow_page(struct kvm *kvm, struct kvm_vcpu *vcpu, struct shadow_page_caches *caches, gfn_t gfn, union kvm_mmu_page_role role) { struct hlist_head *sp_list; struct kvm_mmu_page *sp; bool created = false; /* * No need for memory barriers, unlike in kvm_get_mmu_page_hash(), as * mmu_page_hash must be set prior to creating the first shadow root, * i.e. reaching this point is fully serialized by slots_arch_lock. */ BUG_ON(!kvm->arch.mmu_page_hash); sp_list = &kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]; sp = kvm_mmu_find_shadow_page(kvm, vcpu, gfn, sp_list, role); if (!sp) { created = true; sp = kvm_mmu_alloc_shadow_page(kvm, caches, gfn, sp_list, role); } trace_kvm_mmu_get_page(sp, created); return sp; } static struct kvm_mmu_page *kvm_mmu_get_shadow_page(struct kvm_vcpu *vcpu, gfn_t gfn, union kvm_mmu_page_role role) { struct shadow_page_caches caches = { .page_header_cache = &vcpu->arch.mmu_page_header_cache, .shadow_page_cache = &vcpu->arch.mmu_shadow_page_cache, .shadowed_info_cache = &vcpu->arch.mmu_shadowed_info_cache, }; return __kvm_mmu_get_shadow_page(vcpu->kvm, vcpu, &caches, gfn, role); } static union kvm_mmu_page_role kvm_mmu_child_role(u64 *sptep, bool direct, unsigned int access) { struct kvm_mmu_page *parent_sp = sptep_to_sp(sptep); union kvm_mmu_page_role role; role = parent_sp->role; role.level--; role.access = access; role.direct = direct; role.passthrough = 0; /* * If the guest has 4-byte PTEs then that means it's using 32-bit, * 2-level, non-PAE paging. KVM shadows such guests with PAE paging * (i.e. 8-byte PTEs). The difference in PTE size means that KVM must * shadow each guest page table with multiple shadow page tables, which * requires extra bookkeeping in the role. * * Specifically, to shadow the guest's page directory (which covers a * 4GiB address space), KVM uses 4 PAE page directories, each mapping * 1GiB of the address space. @role.quadrant encodes which quarter of * the address space each maps. * * To shadow the guest's page tables (which each map a 4MiB region), KVM * uses 2 PAE page tables, each mapping a 2MiB region. For these, * @role.quadrant encodes which half of the region they map. * * Concretely, a 4-byte PDE consumes bits 31:22, while an 8-byte PDE * consumes bits 29:21. To consume bits 31:30, KVM's uses 4 shadow * PDPTEs; those 4 PAE page directories are pre-allocated and their * quadrant is assigned in mmu_alloc_root(). A 4-byte PTE consumes * bits 21:12, while an 8-byte PTE consumes bits 20:12. To consume * bit 21 in the PTE (the child here), KVM propagates that bit to the * quadrant, i.e. sets quadrant to '0' or '1'. The parent 8-byte PDE * covers bit 21 (see above), thus the quadrant is calculated from the * _least_ significant bit of the PDE index. */ if (role.has_4_byte_gpte) { WARN_ON_ONCE(role.level != PG_LEVEL_4K); role.quadrant = spte_index(sptep) & 1; } return role; } static struct kvm_mmu_page *kvm_mmu_get_child_sp(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, bool direct, unsigned int access) { union kvm_mmu_page_role role; if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) return ERR_PTR(-EEXIST); role = kvm_mmu_child_role(sptep, direct, access); return kvm_mmu_get_shadow_page(vcpu, gfn, role); } static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterator, struct kvm_vcpu *vcpu, hpa_t root, u64 addr) { iterator->addr = addr; iterator->shadow_addr = root; iterator->level = vcpu->arch.mmu->root_role.level; if (iterator->level >= PT64_ROOT_4LEVEL && vcpu->arch.mmu->cpu_role.base.level < PT64_ROOT_4LEVEL && !vcpu->arch.mmu->root_role.direct) iterator->level = PT32E_ROOT_LEVEL; if (iterator->level == PT32E_ROOT_LEVEL) { /* * prev_root is currently only used for 64-bit hosts. So only * the active root_hpa is valid here. */ BUG_ON(root != vcpu->arch.mmu->root.hpa); iterator->shadow_addr = vcpu->arch.mmu->pae_root[(addr >> 30) & 3]; iterator->shadow_addr &= SPTE_BASE_ADDR_MASK; --iterator->level; if (!iterator->shadow_addr) iterator->level = 0; } } static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator, struct kvm_vcpu *vcpu, u64 addr) { shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu->root.hpa, addr); } static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator) { if (iterator->level < PG_LEVEL_4K) return false; iterator->index = SPTE_INDEX(iterator->addr, iterator->level); iterator->sptep = ((u64 *)__va(iterator->shadow_addr)) + iterator->index; return true; } static void __shadow_walk_next(struct kvm_shadow_walk_iterator *iterator, u64 spte) { if (!is_shadow_present_pte(spte) || is_last_spte(spte, iterator->level)) { iterator->level = 0; return; } iterator->shadow_addr = spte & SPTE_BASE_ADDR_MASK; --iterator->level; } static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator) { __shadow_walk_next(iterator, *iterator->sptep); } static void __link_shadow_page(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, u64 *sptep, struct kvm_mmu_page *sp, bool flush) { u64 spte; BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); /* * If an SPTE is present already, it must be a leaf and therefore * a large one. Drop it, and flush the TLB if needed, before * installing sp. */ if (is_shadow_present_pte(*sptep)) drop_large_spte(kvm, sptep, flush); spte = make_nonleaf_spte(sp->spt, sp_ad_disabled(sp)); mmu_spte_set(sptep, spte); mmu_page_add_parent_pte(kvm, cache, sp, sptep); /* * The non-direct sub-pagetable must be updated before linking. For * L1 sp, the pagetable is updated via kvm_sync_page() in * kvm_mmu_find_shadow_page() without write-protecting the gfn, * so sp->unsync can be true or false. For higher level non-direct * sp, the pagetable is updated/synced via mmu_sync_children() in * FNAME(fetch)(), so sp->unsync_children can only be false. * WARN_ON_ONCE() if anything happens unexpectedly. */ if (WARN_ON_ONCE(sp->unsync_children) || sp->unsync) mark_unsync(sptep); } static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, struct kvm_mmu_page *sp) { __link_shadow_page(vcpu->kvm, &vcpu->arch.mmu_pte_list_desc_cache, sptep, sp, true); } static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned direct_access) { if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) { struct kvm_mmu_page *child; /* * For the direct sp, if the guest pte's dirty bit * changed form clean to dirty, it will corrupt the * sp's access: allow writable in the read-only sp, * so we should update the spte at this point to get * a new sp with the correct access. */ child = spte_to_child_sp(*sptep); if (child->role.access == direct_access) return; drop_parent_pte(vcpu->kvm, child, sptep); kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep); } } /* Returns the number of zapped non-leaf child shadow pages. */ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *spte, struct list_head *invalid_list) { u64 pte; struct kvm_mmu_page *child; pte = *spte; if (is_shadow_present_pte(pte)) { if (is_last_spte(pte, sp->role.level)) { drop_spte(kvm, spte); } else { child = spte_to_child_sp(pte); drop_parent_pte(kvm, child, spte); /* * Recursively zap nested TDP SPs, parentless SPs are * unlikely to be used again in the near future. This * avoids retaining a large number of stale nested SPs. */ if (tdp_enabled && invalid_list && child->role.guest_mode && !atomic_long_read(&child->parent_ptes.val)) return kvm_mmu_prepare_zap_page(kvm, child, invalid_list); } } else if (is_mmio_spte(kvm, pte)) { mmu_spte_clear_no_track(spte); } return 0; } static int kvm_mmu_page_unlink_children(struct kvm *kvm, struct kvm_mmu_page *sp, struct list_head *invalid_list) { int zapped = 0; unsigned i; for (i = 0; i < SPTE_ENT_PER_PAGE; ++i) zapped += mmu_page_zap_pte(kvm, sp, sp->spt + i, invalid_list); return zapped; } static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) { u64 *sptep; struct rmap_iterator iter; while ((sptep = rmap_get_first(&sp->parent_ptes, &iter))) drop_parent_pte(kvm, sp, sptep); } static int mmu_zap_unsync_children(struct kvm *kvm, struct kvm_mmu_page *parent, struct list_head *invalid_list) { int i, zapped = 0; struct mmu_page_path parents; struct kvm_mmu_pages pages; if (parent->role.level == PG_LEVEL_4K) return 0; while (mmu_unsync_walk(parent, &pages)) { struct kvm_mmu_page *sp; for_each_sp(pages, sp, parents, i) { kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); mmu_pages_clear_parents(&parents); zapped++; } } return zapped; } static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, struct list_head *invalid_list, int *nr_zapped) { bool list_unstable, zapped_root = false; lockdep_assert_held_write(&kvm->mmu_lock); trace_kvm_mmu_prepare_zap_page(sp); ++kvm->stat.mmu_shadow_zapped; *nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list); *nr_zapped += kvm_mmu_page_unlink_children(kvm, sp, invalid_list); kvm_mmu_unlink_parents(kvm, sp); /* Zapping children means active_mmu_pages has become unstable. */ list_unstable = *nr_zapped; if (!sp->role.invalid && sp_has_gptes(sp)) unaccount_shadowed(kvm, sp); if (sp->unsync) kvm_unlink_unsync_page(kvm, sp); if (!sp->root_count) { /* Count self */ (*nr_zapped)++; /* * Already invalid pages (previously active roots) are not on * the active page list. See list_del() in the "else" case of * !sp->root_count. */ if (sp->role.invalid) list_add(&sp->link, invalid_list); else list_move(&sp->link, invalid_list); kvm_unaccount_mmu_page(kvm, sp); } else { /* * Remove the active root from the active page list, the root * will be explicitly freed when the root_count hits zero. */ list_del(&sp->link); /* * Obsolete pages cannot be used on any vCPUs, see the comment * in kvm_mmu_zap_all_fast(). Note, is_obsolete_sp() also * treats invalid shadow pages as being obsolete. */ zapped_root = !is_obsolete_sp(kvm, sp); } if (sp->nx_huge_page_disallowed) unaccount_nx_huge_page(kvm, sp); sp->role.invalid = 1; /* * Make the request to free obsolete roots after marking the root * invalid, otherwise other vCPUs may not see it as invalid. */ if (zapped_root) kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_FREE_OBSOLETE_ROOTS); return list_unstable; } static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, struct list_head *invalid_list) { int nr_zapped; __kvm_mmu_prepare_zap_page(kvm, sp, invalid_list, &nr_zapped); return nr_zapped; } static void kvm_mmu_commit_zap_page(struct kvm *kvm, struct list_head *invalid_list) { struct kvm_mmu_page *sp, *nsp; if (list_empty(invalid_list)) return; /* * We need to make sure everyone sees our modifications to * the page tables and see changes to vcpu->mode here. The barrier * in the kvm_flush_remote_tlbs() achieves this. This pairs * with vcpu_enter_guest and walk_shadow_page_lockless_begin/end. * * In addition, kvm_flush_remote_tlbs waits for all vcpus to exit * guest mode and/or lockless shadow page table walks. */ kvm_flush_remote_tlbs(kvm); list_for_each_entry_safe(sp, nsp, invalid_list, link) { WARN_ON_ONCE(!sp->role.invalid || sp->root_count); kvm_mmu_free_shadow_page(sp); } } static unsigned long kvm_mmu_zap_oldest_mmu_pages(struct kvm *kvm, unsigned long nr_to_zap) { unsigned long total_zapped = 0; struct kvm_mmu_page *sp, *tmp; LIST_HEAD(invalid_list); bool unstable; int nr_zapped; if (list_empty(&kvm->arch.active_mmu_pages)) return 0; restart: list_for_each_entry_safe_reverse(sp, tmp, &kvm->arch.active_mmu_pages, link) { /* * Don't zap active root pages, the page itself can't be freed * and zapping it will just force vCPUs to realloc and reload. */ if (sp->root_count) continue; unstable = __kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &nr_zapped); total_zapped += nr_zapped; if (total_zapped >= nr_to_zap) break; if (unstable) goto restart; } kvm_mmu_commit_zap_page(kvm, &invalid_list); kvm->stat.mmu_recycled += total_zapped; return total_zapped; } static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm) { if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages) return kvm->arch.n_max_mmu_pages - kvm->arch.n_used_mmu_pages; return 0; } static int make_mmu_pages_available(struct kvm_vcpu *vcpu) { unsigned long avail = kvm_mmu_available_pages(vcpu->kvm); if (likely(avail >= KVM_MIN_FREE_MMU_PAGES)) return 0; kvm_mmu_zap_oldest_mmu_pages(vcpu->kvm, KVM_REFILL_PAGES - avail); /* * Note, this check is intentionally soft, it only guarantees that one * page is available, while the caller may end up allocating as many as * four pages, e.g. for PAE roots or for 5-level paging. Temporarily * exceeding the (arbitrary by default) limit will not harm the host, * being too aggressive may unnecessarily kill the guest, and getting an * exact count is far more trouble than it's worth, especially in the * page fault paths. */ if (!kvm_mmu_available_pages(vcpu->kvm)) return -ENOSPC; return 0; } /* * Changing the number of mmu pages allocated to the vm * Note: if goal_nr_mmu_pages is too small, you will get dead lock */ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) { write_lock(&kvm->mmu_lock); if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) { kvm_mmu_zap_oldest_mmu_pages(kvm, kvm->arch.n_used_mmu_pages - goal_nr_mmu_pages); goal_nr_mmu_pages = kvm->arch.n_used_mmu_pages; } kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages; write_unlock(&kvm->mmu_lock); } bool __kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool always_retry) { struct kvm *kvm = vcpu->kvm; LIST_HEAD(invalid_list); struct kvm_mmu_page *sp; gpa_t gpa = cr2_or_gpa; bool r = false; /* * Bail early if there aren't any write-protected shadow pages to avoid * unnecessarily taking mmu_lock lock, e.g. if the gfn is write-tracked * by a third party. Reading indirect_shadow_pages without holding * mmu_lock is safe, as this is purely an optimization, i.e. a false * positive is benign, and a false negative will simply result in KVM * skipping the unprotect+retry path, which is also an optimization. */ if (!READ_ONCE(kvm->arch.indirect_shadow_pages)) goto out; if (!vcpu->arch.mmu->root_role.direct) { gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); if (gpa == INVALID_GPA) goto out; } write_lock(&kvm->mmu_lock); for_each_gfn_valid_sp_with_gptes(kvm, sp, gpa_to_gfn(gpa)) kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); /* * Snapshot the result before zapping, as zapping will remove all list * entries, i.e. checking the list later would yield a false negative. */ r = !list_empty(&invalid_list); kvm_mmu_commit_zap_page(kvm, &invalid_list); write_unlock(&kvm->mmu_lock); out: if (r || always_retry) { vcpu->arch.last_retry_eip = kvm_rip_read(vcpu); vcpu->arch.last_retry_addr = cr2_or_gpa; } return r; } static void kvm_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) { trace_kvm_mmu_unsync_page(sp); ++kvm->stat.mmu_unsync; sp->unsync = 1; kvm_mmu_mark_parents_unsync(sp); } /* * Attempt to unsync any shadow pages that can be reached by the specified gfn, * KVM is creating a writable mapping for said gfn. Returns 0 if all pages * were marked unsync (or if there is no shadow page), -EPERM if the SPTE must * be write-protected. */ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool synchronizing, bool prefetch) { struct kvm_mmu_page *sp; bool locked = false; /* * Force write-protection if the page is being tracked. Note, the page * track machinery is used to write-protect upper-level shadow pages, * i.e. this guards the role.level == 4K assertion below! */ if (kvm_gfn_is_write_tracked(kvm, slot, gfn)) return -EPERM; /* * Only 4KiB mappings can become unsync, and KVM disallows hugepages * when accounting 4KiB shadow pages. Upper-level gPTEs are always * write-protected (see above), thus if the gfn can be mapped with a * hugepage and isn't write-tracked, it can't have a shadow page. */ if (!lpage_info_slot(gfn, slot, PG_LEVEL_2M)->disallow_lpage) return 0; /* * The page is not write-tracked, mark existing shadow pages unsync * unless KVM is synchronizing an unsync SP. In that case, KVM must * complete emulation of the guest TLB flush before allowing shadow * pages to become unsync (writable by the guest). */ for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) { if (synchronizing) return -EPERM; if (sp->unsync) continue; if (prefetch) return -EEXIST; /* * TDP MMU page faults require an additional spinlock as they * run with mmu_lock held for read, not write, and the unsync * logic is not thread safe. Take the spinklock regardless of * the MMU type to avoid extra conditionals/parameters, there's * no meaningful penalty if mmu_lock is held for write. */ if (!locked) { locked = true; spin_lock(&kvm->arch.mmu_unsync_pages_lock); /* * Recheck after taking the spinlock, a different vCPU * may have since marked the page unsync. A false * negative on the unprotected check above is not * possible as clearing sp->unsync _must_ hold mmu_lock * for write, i.e. unsync cannot transition from 1->0 * while this CPU holds mmu_lock for read (or write). */ if (READ_ONCE(sp->unsync)) continue; } WARN_ON_ONCE(sp->role.level != PG_LEVEL_4K); kvm_unsync_page(kvm, sp); } if (locked) spin_unlock(&kvm->arch.mmu_unsync_pages_lock); /* * We need to ensure that the marking of unsync pages is visible * before the SPTE is updated to allow writes because * kvm_mmu_sync_roots() checks the unsync flags without holding * the MMU lock and so can race with this. If the SPTE was updated * before the page had been marked as unsync-ed, something like the * following could happen: * * CPU 1 CPU 2 * --------------------------------------------------------------------- * 1.2 Host updates SPTE * to be writable * 2.1 Guest writes a GPTE for GVA X. * (GPTE being in the guest page table shadowed * by the SP from CPU 1.) * This reads SPTE during the page table walk. * Since SPTE.W is read as 1, there is no * fault. * * 2.2 Guest issues TLB flush. * That causes a VM Exit. * * 2.3 Walking of unsync pages sees sp->unsync is * false and skips the page. * * 2.4 Guest accesses GVA X. * Since the mapping in the SP was not updated, * so the old mapping for GVA X incorrectly * gets used. * 1.1 Host marks SP * as unsync * (sp->unsync = true) * * The write barrier below ensures that 1.1 happens before 1.2 and thus * the situation in 2.4 does not arise. It pairs with the read barrier * in is_unsync_root(), placed between 2.1's load of SPTE.W and 2.3. */ smp_wmb(); return 0; } static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, u64 *sptep, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, struct kvm_page_fault *fault) { struct kvm_mmu_page *sp = sptep_to_sp(sptep); int level = sp->role.level; int was_rmapped = 0; int ret = RET_PF_FIXED; bool flush = false; bool wrprot; u64 spte; /* Prefetching always gets a writable pfn. */ bool host_writable = !fault || fault->map_writable; bool prefetch = !fault || fault->prefetch; bool write_fault = fault && fault->write; if (is_shadow_present_pte(*sptep)) { if (prefetch && is_last_spte(*sptep, level) && pfn == spte_to_pfn(*sptep)) return RET_PF_SPURIOUS; /* * If we overwrite a PTE page pointer with a 2MB PMD, unlink * the parent of the now unreachable PTE. */ if (level > PG_LEVEL_4K && !is_large_pte(*sptep)) { struct kvm_mmu_page *child; u64 pte = *sptep; child = spte_to_child_sp(pte); drop_parent_pte(vcpu->kvm, child, sptep); flush = true; } else if (pfn != spte_to_pfn(*sptep)) { WARN_ON_ONCE(vcpu->arch.mmu->root_role.direct); drop_spte(vcpu->kvm, sptep); flush = true; } else was_rmapped = 1; } if (unlikely(is_noslot_pfn(pfn))) { vcpu->stat.pf_mmio_spte_created++; mark_mmio_spte(vcpu, sptep, gfn, pte_access); if (flush) kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level); return RET_PF_EMULATE; } wrprot = make_spte(vcpu, sp, slot, pte_access, gfn, pfn, *sptep, prefetch, false, host_writable, &spte); if (*sptep == spte) { ret = RET_PF_SPURIOUS; } else { flush |= mmu_spte_update(sptep, spte); trace_kvm_mmu_set_spte(level, gfn, sptep); } if (wrprot && write_fault) ret = RET_PF_WRITE_PROTECTED; if (flush) kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level); if (!was_rmapped) { WARN_ON_ONCE(ret == RET_PF_SPURIOUS); rmap_add(vcpu, slot, sptep, gfn, pte_access); } else { /* Already rmapped but the pte_access bits may have changed. */ kvm_mmu_page_set_access(sp, spte_index(sptep), pte_access); } return ret; } static bool kvm_mmu_prefetch_sptes(struct kvm_vcpu *vcpu, gfn_t gfn, u64 *sptep, int nr_pages, unsigned int access) { struct page *pages[PTE_PREFETCH_NUM]; struct kvm_memory_slot *slot; int i; if (WARN_ON_ONCE(nr_pages > PTE_PREFETCH_NUM)) return false; slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK); if (!slot) return false; nr_pages = kvm_prefetch_pages(slot, gfn, pages, nr_pages); if (nr_pages <= 0) return false; for (i = 0; i < nr_pages; i++, gfn++, sptep++) { mmu_set_spte(vcpu, slot, sptep, access, gfn, page_to_pfn(pages[i]), NULL); /* * KVM always prefetches writable pages from the primary MMU, * and KVM can make its SPTE writable in the fast page handler, * without notifying the primary MMU. Mark pages/folios dirty * now to ensure file data is written back if it ends up being * written by the guest. Because KVM's prefetching GUPs * writable PTEs, the probability of unnecessary writeback is * extremely low. */ kvm_release_page_dirty(pages[i]); } return true; } static bool direct_pte_prefetch_many(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *start, u64 *end) { gfn_t gfn = kvm_mmu_page_get_gfn(sp, spte_index(start)); unsigned int access = sp->role.access; return kvm_mmu_prefetch_sptes(vcpu, gfn, start, end - start, access); } static void __direct_pte_prefetch(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *sptep) { u64 *spte, *start = NULL; int i; WARN_ON_ONCE(!sp->role.direct); i = spte_index(sptep) & ~(PTE_PREFETCH_NUM - 1); spte = sp->spt + i; for (i = 0; i < PTE_PREFETCH_NUM; i++, spte++) { if (is_shadow_present_pte(*spte) || spte == sptep) { if (!start) continue; if (!direct_pte_prefetch_many(vcpu, sp, start, spte)) return; start = NULL; } else if (!start) start = spte; } if (start) direct_pte_prefetch_many(vcpu, sp, start, spte); } static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) { struct kvm_mmu_page *sp; sp = sptep_to_sp(sptep); /* * Without accessed bits, there's no way to distinguish between * actually accessed translations and prefetched, so disable pte * prefetch if accessed bits aren't available. */ if (sp_ad_disabled(sp)) return; if (sp->role.level > PG_LEVEL_4K) return; /* * If addresses are being invalidated, skip prefetching to avoid * accidentally prefetching those addresses. */ if (unlikely(vcpu->kvm->mmu_invalidate_in_progress)) return; __direct_pte_prefetch(vcpu, sp, sptep); } /* * Lookup the mapping level for @gfn in the current mm. * * WARNING! Use of host_pfn_mapping_level() requires the caller and the end * consumer to be tied into KVM's handlers for MMU notifier events! * * There are several ways to safely use this helper: * * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before * consuming it. In this case, mmu_lock doesn't need to be held during the * lookup, but it does need to be held while checking the MMU notifier. * * - Hold mmu_lock AND ensure there is no in-progress MMU notifier invalidation * event for the hva. This can be done by explicit checking the MMU notifier * or by ensuring that KVM already has a valid mapping that covers the hva. * * - Do not use the result to install new mappings, e.g. use the host mapping * level only to decide whether or not to zap an entry. In this case, it's * not required to hold mmu_lock (though it's highly likely the caller will * want to hold mmu_lock anyways, e.g. to modify SPTEs). * * Note! The lookup can still race with modifications to host page tables, but * the above "rules" ensure KVM will not _consume_ the result of the walk if a * race with the primary MMU occurs. */ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, const struct kvm_memory_slot *slot) { int level = PG_LEVEL_4K; unsigned long hva; unsigned long flags; pgd_t pgd; p4d_t p4d; pud_t pud; pmd_t pmd; /* * Note, using the already-retrieved memslot and __gfn_to_hva_memslot() * is not solely for performance, it's also necessary to avoid the * "writable" check in __gfn_to_hva_many(), which will always fail on * read-only memslots due to gfn_to_hva() assuming writes. Earlier * page fault steps have already verified the guest isn't writing a * read-only memslot. */ hva = __gfn_to_hva_memslot(slot, gfn); /* * Disable IRQs to prevent concurrent tear down of host page tables, * e.g. if the primary MMU promotes a P*D to a huge page and then frees * the original page table. */ local_irq_save(flags); /* * Read each entry once. As above, a non-leaf entry can be promoted to * a huge page _during_ this walk. Re-reading the entry could send the * walk into the weeks, e.g. p*d_leaf() returns false (sees the old * value) and then p*d_offset() walks into the target huge page instead * of the old page table (sees the new value). */ pgd = READ_ONCE(*pgd_offset(kvm->mm, hva)); if (pgd_none(pgd)) goto out; p4d = READ_ONCE(*p4d_offset(&pgd, hva)); if (p4d_none(p4d) || !p4d_present(p4d)) goto out; pud = READ_ONCE(*pud_offset(&p4d, hva)); if (pud_none(pud) || !pud_present(pud)) goto out; if (pud_leaf(pud)) { level = PG_LEVEL_1G; goto out; } pmd = READ_ONCE(*pmd_offset(&pud, hva)); if (pmd_none(pmd) || !pmd_present(pmd)) goto out; if (pmd_leaf(pmd)) level = PG_LEVEL_2M; out: local_irq_restore(flags); return level; } static u8 kvm_max_level_for_order(int order) { BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G); KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) && order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) && order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K)); if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G)) return PG_LEVEL_1G; if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M)) return PG_LEVEL_2M; return PG_LEVEL_4K; } static u8 kvm_gmem_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault, const struct kvm_memory_slot *slot, gfn_t gfn, bool is_private) { u8 max_level, coco_level; kvm_pfn_t pfn; /* For faults, use the gmem information that was resolved earlier. */ if (fault) { pfn = fault->pfn; max_level = fault->max_level; } else { /* TODO: Call into guest_memfd once hugepages are supported. */ WARN_ONCE(1, "Get pfn+order from guest_memfd"); pfn = KVM_PFN_ERR_FAULT; max_level = PG_LEVEL_4K; } if (max_level == PG_LEVEL_4K) return max_level; /* * CoCo may influence the max mapping level, e.g. due to RMP or S-EPT * restrictions. A return of '0' means "no additional restrictions", to * allow for using an optional "ret0" static call. */ coco_level = kvm_x86_call(gmem_max_mapping_level)(kvm, pfn, is_private); if (coco_level) max_level = min(max_level, coco_level); return max_level; } int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault, const struct kvm_memory_slot *slot, gfn_t gfn) { struct kvm_lpage_info *linfo; int host_level, max_level; bool is_private; lockdep_assert_held(&kvm->mmu_lock); if (fault) { max_level = fault->max_level; is_private = fault->is_private; } else { max_level = PG_LEVEL_NUM; is_private = kvm_mem_is_private(kvm, gfn); } max_level = min(max_level, max_huge_page_level); for ( ; max_level > PG_LEVEL_4K; max_level--) { linfo = lpage_info_slot(gfn, slot, max_level); if (!linfo->disallow_lpage) break; } if (max_level == PG_LEVEL_4K) return PG_LEVEL_4K; if (is_private || kvm_memslot_is_gmem_only(slot)) host_level = kvm_gmem_max_mapping_level(kvm, fault, slot, gfn, is_private); else host_level = host_pfn_mapping_level(kvm, gfn, slot); return min(host_level, max_level); } void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; kvm_pfn_t mask; fault->huge_page_disallowed = fault->exec && fault->nx_huge_page_workaround_enabled; if (unlikely(fault->max_level == PG_LEVEL_4K)) return; if (is_error_noslot_pfn(fault->pfn)) return; if (kvm_slot_dirty_track_enabled(slot)) return; /* * Enforce the iTLB multihit workaround after capturing the requested * level, which will be used to do precise, accurate accounting. */ fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, fault, fault->slot, fault->gfn); if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed) return; /* * mmu_invalidate_retry() was successful and mmu_lock is held, so * the pmd can't be split from under us. */ fault->goal_level = fault->req_level; mask = KVM_PAGES_PER_HPAGE(fault->goal_level) - 1; VM_BUG_ON((fault->gfn & mask) != (fault->pfn & mask)); fault->pfn &= ~mask; } void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level) { if (cur_level > PG_LEVEL_4K && cur_level == fault->goal_level && is_shadow_present_pte(spte) && !is_large_pte(spte) && spte_to_child_sp(spte)->nx_huge_page_disallowed) { /* * A small SPTE exists for this pfn, but FNAME(fetch), * direct_map(), or kvm_tdp_mmu_map() would like to create a * large PTE instead: just force them to go down another level, * patching back for them into pfn the next 9 bits of the * address. */ u64 page_mask = KVM_PAGES_PER_HPAGE(cur_level) - KVM_PAGES_PER_HPAGE(cur_level - 1); fault->pfn |= fault->gfn & page_mask; fault->goal_level--; } } static int direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; int ret; gfn_t base_gfn = fault->gfn; kvm_mmu_hugepage_adjust(vcpu, fault); trace_kvm_mmu_spte_requested(fault); for_each_shadow_entry(vcpu, fault->addr, it) { /* * We cannot overwrite existing page tables with an NX * large page, as the leaf could be executable. */ if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, *it.sptep, it.level); base_gfn = gfn_round_for_level(fault->gfn, it.level); if (it.level == fault->goal_level) break; sp = kvm_mmu_get_child_sp(vcpu, it.sptep, base_gfn, true, ACC_ALL); if (sp == ERR_PTR(-EEXIST)) continue; link_shadow_page(vcpu, it.sptep, sp); if (fault->huge_page_disallowed) account_nx_huge_page(vcpu->kvm, sp, fault->req_level >= it.level); } if (WARN_ON_ONCE(it.level != fault->goal_level)) return -EFAULT; ret = mmu_set_spte(vcpu, fault->slot, it.sptep, ACC_ALL, base_gfn, fault->pfn, fault); if (ret == RET_PF_SPURIOUS) return ret; direct_pte_prefetch(vcpu, it.sptep); return ret; } static void kvm_send_hwpoison_signal(struct kvm_memory_slot *slot, gfn_t gfn) { unsigned long hva = gfn_to_hva_memslot(slot, gfn); send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva, PAGE_SHIFT, current); } static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { if (is_sigpending_pfn(fault->pfn)) { kvm_handle_signal_exit(vcpu); return -EINTR; } /* * Do not cache the mmio info caused by writing the readonly gfn * into the spte otherwise read access on readonly gfn also can * caused mmio page fault and treat it as mmio access. */ if (fault->pfn == KVM_PFN_ERR_RO_FAULT) return RET_PF_EMULATE; if (fault->pfn == KVM_PFN_ERR_HWPOISON) { kvm_send_hwpoison_signal(fault->slot, fault->gfn); return RET_PF_RETRY; } return -EFAULT; } static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, unsigned int access) { gva_t gva = fault->is_tdp ? 0 : fault->addr; if (fault->is_private) { kvm_mmu_prepare_memory_fault_exit(vcpu, fault); return -EFAULT; } vcpu_cache_mmio_info(vcpu, gva, fault->gfn, access & shadow_mmio_access_mask); fault->slot = NULL; fault->pfn = KVM_PFN_NOSLOT; fault->map_writable = false; /* * If MMIO caching is disabled, emulate immediately without * touching the shadow page tables as attempting to install an * MMIO SPTE will just be an expensive nop. */ if (unlikely(!enable_mmio_caching)) return RET_PF_EMULATE; /* * Do not create an MMIO SPTE for a gfn greater than host.MAXPHYADDR, * any guest that generates such gfns is running nested and is being * tricked by L0 userspace (you can observe gfn > L1.MAXPHYADDR if and * only if L1's MAXPHYADDR is inaccurate with respect to the * hardware's). */ if (unlikely(fault->gfn > kvm_mmu_max_gfn())) return RET_PF_EMULATE; return RET_PF_CONTINUE; } static bool page_fault_can_be_fast(struct kvm *kvm, struct kvm_page_fault *fault) { /* * Page faults with reserved bits set, i.e. faults on MMIO SPTEs, only * reach the common page fault handler if the SPTE has an invalid MMIO * generation number. Refreshing the MMIO generation needs to go down * the slow path. Note, EPT Misconfigs do NOT set the PRESENT flag! */ if (fault->rsvd) return false; /* * For hardware-protected VMs, certain conditions like attempting to * perform a write to a page which is not in the state that the guest * expects it to be in can result in a nested/extended #PF. In this * case, the below code might misconstrue this situation as being the * result of a write-protected access, and treat it as a spurious case * rather than taking any action to satisfy the real source of the #PF * such as generating a KVM_EXIT_MEMORY_FAULT. This can lead to the * guest spinning on a #PF indefinitely, so don't attempt the fast path * in this case. * * Note that the kvm_mem_is_private() check might race with an * attribute update, but this will either result in the guest spinning * on RET_PF_SPURIOUS until the update completes, or an actual spurious * case might go down the slow path. Either case will resolve itself. */ if (kvm->arch.has_private_mem && fault->is_private != kvm_mem_is_private(kvm, fault->gfn)) return false; /* * #PF can be fast if: * * 1. The shadow page table entry is not present and A/D bits are * disabled _by KVM_, which could mean that the fault is potentially * caused by access tracking (if enabled). If A/D bits are enabled * by KVM, but disabled by L1 for L2, KVM is forced to disable A/D * bits for L2 and employ access tracking, but the fast page fault * mechanism only supports direct MMUs. * 2. The shadow page table entry is present, the access is a write, * and no reserved bits are set (MMIO SPTEs cannot be "fixed"), i.e. * the fault was caused by a write-protection violation. If the * SPTE is MMU-writable (determined later), the fault can be fixed * by setting the Writable bit, which can be done out of mmu_lock. */ if (!fault->present) return !kvm_ad_enabled; /* * Note, instruction fetches and writes are mutually exclusive, ignore * the "exec" flag. */ return fault->write; } /* * Returns true if the SPTE was fixed successfully. Otherwise, * someone else modified the SPTE from its original value. */ static bool fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, u64 *sptep, u64 old_spte, u64 new_spte) { /* * Theoretically we could also set dirty bit (and flush TLB) here in * order to eliminate unnecessary PML logging. See comments in * set_spte. But fast_page_fault is very unlikely to happen with PML * enabled, so we do not do this. This might result in the same GPA * to be logged in PML buffer again when the write really happens, and * eventually to be called by mark_page_dirty twice. But it's also no * harm. This also avoids the TLB flush needed after setting dirty bit * so non-PML cases won't be impacted. * * Compare with make_spte() where instead shadow_dirty_mask is set. */ if (!try_cmpxchg64(sptep, &old_spte, new_spte)) return false; if (is_writable_pte(new_spte) && !is_writable_pte(old_spte)) mark_page_dirty_in_slot(vcpu->kvm, fault->slot, fault->gfn); return true; } /* * Returns the last level spte pointer of the shadow page walk for the given * gpa, and sets *spte to the spte value. This spte may be non-preset. If no * walk could be performed, returns NULL and *spte does not contain valid data. * * Contract: * - Must be called between walk_shadow_page_lockless_{begin,end}. * - The returned sptep must not be used after walk_shadow_page_lockless_end. */ static u64 *fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gpa_t gpa, u64 *spte) { struct kvm_shadow_walk_iterator iterator; u64 old_spte; u64 *sptep = NULL; for_each_shadow_entry_lockless(vcpu, gpa, iterator, old_spte) { sptep = iterator.sptep; *spte = old_spte; } return sptep; } /* * Returns one of RET_PF_INVALID, RET_PF_FIXED or RET_PF_SPURIOUS. */ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_mmu_page *sp; int ret = RET_PF_INVALID; u64 spte; u64 *sptep; uint retry_count = 0; if (!page_fault_can_be_fast(vcpu->kvm, fault)) return ret; walk_shadow_page_lockless_begin(vcpu); do { u64 new_spte; if (tdp_mmu_enabled) sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->gfn, &spte); else sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte); /* * It's entirely possible for the mapping to have been zapped * by a different task, but the root page should always be * available as the vCPU holds a reference to its root(s). */ if (WARN_ON_ONCE(!sptep)) spte = FROZEN_SPTE; if (!is_shadow_present_pte(spte)) break; sp = sptep_to_sp(sptep); if (!is_last_spte(spte, sp->role.level)) break; /* * Check whether the memory access that caused the fault would * still cause it if it were to be performed right now. If not, * then this is a spurious fault caused by TLB lazily flushed, * or some other CPU has already fixed the PTE after the * current CPU took the fault. * * Need not check the access of upper level table entries since * they are always ACC_ALL. */ if (is_access_allowed(fault, spte)) { ret = RET_PF_SPURIOUS; break; } new_spte = spte; /* * KVM only supports fixing page faults outside of MMU lock for * direct MMUs, nested MMUs are always indirect, and KVM always * uses A/D bits for non-nested MMUs. Thus, if A/D bits are * enabled, the SPTE can't be an access-tracked SPTE. */ if (unlikely(!kvm_ad_enabled) && is_access_track_spte(spte)) new_spte = restore_acc_track_spte(new_spte) | shadow_accessed_mask; /* * To keep things simple, only SPTEs that are MMU-writable can * be made fully writable outside of mmu_lock, e.g. only SPTEs * that were write-protected for dirty-logging or access * tracking are handled here. Don't bother checking if the * SPTE is writable to prioritize running with A/D bits enabled. * The is_access_allowed() check above handles the common case * of the fault being spurious, and the SPTE is known to be * shadow-present, i.e. except for access tracking restoration * making the new SPTE writable, the check is wasteful. */ if (fault->write && is_mmu_writable_spte(spte)) { new_spte |= PT_WRITABLE_MASK; /* * Do not fix write-permission on the large spte when * dirty logging is enabled. Since we only dirty the * first page into the dirty-bitmap in * fast_pf_fix_direct_spte(), other pages are missed * if its slot has dirty logging enabled. * * Instead, we let the slow page fault path create a * normal spte to fix the access. */ if (sp->role.level > PG_LEVEL_4K && kvm_slot_dirty_track_enabled(fault->slot)) break; } /* Verify that the fault can be handled in the fast path */ if (new_spte == spte || !is_access_allowed(fault, new_spte)) break; /* * Currently, fast page fault only works for direct mapping * since the gfn is not stable for indirect shadow page. See * Documentation/virt/kvm/locking.rst to get more detail. */ if (fast_pf_fix_direct_spte(vcpu, fault, sptep, spte, new_spte)) { ret = RET_PF_FIXED; break; } if (++retry_count > 4) { pr_warn_once("Fast #PF retrying more than 4 times.\n"); break; } } while (true); trace_fast_page_fault(vcpu, fault, sptep, spte, ret); walk_shadow_page_lockless_end(vcpu); if (ret != RET_PF_INVALID) vcpu->stat.pf_fast++; return ret; } static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, struct list_head *invalid_list) { struct kvm_mmu_page *sp; if (!VALID_PAGE(*root_hpa)) return; sp = root_to_sp(*root_hpa); if (WARN_ON_ONCE(!sp)) return; if (is_tdp_mmu_page(sp)) { lockdep_assert_held_read(&kvm->mmu_lock); kvm_tdp_mmu_put_root(kvm, sp); } else { lockdep_assert_held_write(&kvm->mmu_lock); if (!--sp->root_count && sp->role.invalid) kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); } *root_hpa = INVALID_PAGE; } /* roots_to_free must be some combination of the KVM_MMU_ROOT_* flags */ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, ulong roots_to_free) { bool is_tdp_mmu = tdp_mmu_enabled && mmu->root_role.direct; int i; LIST_HEAD(invalid_list); bool free_active_root; WARN_ON_ONCE(roots_to_free & ~KVM_MMU_ROOTS_ALL); BUILD_BUG_ON(KVM_MMU_NUM_PREV_ROOTS >= BITS_PER_LONG); /* Before acquiring the MMU lock, see if we need to do any real work. */ free_active_root = (roots_to_free & KVM_MMU_ROOT_CURRENT) && VALID_PAGE(mmu->root.hpa); if (!free_active_root) { for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if ((roots_to_free & KVM_MMU_ROOT_PREVIOUS(i)) && VALID_PAGE(mmu->prev_roots[i].hpa)) break; if (i == KVM_MMU_NUM_PREV_ROOTS) return; } if (is_tdp_mmu) read_lock(&kvm->mmu_lock); else write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if (roots_to_free & KVM_MMU_ROOT_PREVIOUS(i)) mmu_free_root_page(kvm, &mmu->prev_roots[i].hpa, &invalid_list); if (free_active_root) { if (kvm_mmu_is_dummy_root(mmu->root.hpa)) { /* Nothing to cleanup for dummy roots. */ } else if (root_to_sp(mmu->root.hpa)) { mmu_free_root_page(kvm, &mmu->root.hpa, &invalid_list); } else if (mmu->pae_root) { for (i = 0; i < 4; ++i) { if (!IS_VALID_PAE_ROOT(mmu->pae_root[i])) continue; mmu_free_root_page(kvm, &mmu->pae_root[i], &invalid_list); mmu->pae_root[i] = INVALID_PAE_ROOT; } } mmu->root.hpa = INVALID_PAGE; mmu->root.pgd = 0; } if (is_tdp_mmu) { read_unlock(&kvm->mmu_lock); WARN_ON_ONCE(!list_empty(&invalid_list)); } else { kvm_mmu_commit_zap_page(kvm, &invalid_list); write_unlock(&kvm->mmu_lock); } } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_free_roots); void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu) { unsigned long roots_to_free = 0; struct kvm_mmu_page *sp; hpa_t root_hpa; int i; /* * This should not be called while L2 is active, L2 can't invalidate * _only_ its own roots, e.g. INVVPID unconditionally exits. */ WARN_ON_ONCE(mmu->root_role.guest_mode); for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { root_hpa = mmu->prev_roots[i].hpa; if (!VALID_PAGE(root_hpa)) continue; sp = root_to_sp(root_hpa); if (!sp || sp->role.guest_mode) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); } kvm_mmu_free_roots(kvm, mmu, roots_to_free); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_free_guest_mode_roots); static hpa_t mmu_alloc_root(struct kvm_vcpu *vcpu, gfn_t gfn, int quadrant, u8 level) { union kvm_mmu_page_role role = vcpu->arch.mmu->root_role; struct kvm_mmu_page *sp; role.level = level; role.quadrant = quadrant; WARN_ON_ONCE(quadrant && !role.has_4_byte_gpte); WARN_ON_ONCE(role.direct && role.has_4_byte_gpte); sp = kvm_mmu_get_shadow_page(vcpu, gfn, role); ++sp->root_count; return __pa(sp->spt); } static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; u8 shadow_root_level = mmu->root_role.level; hpa_t root; unsigned i; int r; if (tdp_mmu_enabled) { if (kvm_has_mirrored_tdp(vcpu->kvm) && !VALID_PAGE(mmu->mirror_root_hpa)) kvm_tdp_mmu_alloc_root(vcpu, true); kvm_tdp_mmu_alloc_root(vcpu, false); return 0; } write_lock(&vcpu->kvm->mmu_lock); r = make_mmu_pages_available(vcpu); if (r < 0) goto out_unlock; if (shadow_root_level >= PT64_ROOT_4LEVEL) { root = mmu_alloc_root(vcpu, 0, 0, shadow_root_level); mmu->root.hpa = root; } else if (shadow_root_level == PT32E_ROOT_LEVEL) { if (WARN_ON_ONCE(!mmu->pae_root)) { r = -EIO; goto out_unlock; } for (i = 0; i < 4; ++i) { WARN_ON_ONCE(IS_VALID_PAE_ROOT(mmu->pae_root[i])); root = mmu_alloc_root(vcpu, i << (30 - PAGE_SHIFT), 0, PT32_ROOT_LEVEL); mmu->pae_root[i] = root | PT_PRESENT_MASK | shadow_me_value; } mmu->root.hpa = __pa(mmu->pae_root); } else { WARN_ONCE(1, "Bad TDP root level = %d\n", shadow_root_level); r = -EIO; goto out_unlock; } /* root.pgd is ignored for direct MMUs. */ mmu->root.pgd = 0; out_unlock: write_unlock(&vcpu->kvm->mmu_lock); return r; } static int kvm_mmu_alloc_page_hash(struct kvm *kvm) { struct hlist_head *h; if (kvm->arch.mmu_page_hash) return 0; h = kvzalloc_objs(*h, KVM_NUM_MMU_PAGES, GFP_KERNEL_ACCOUNT); if (!h) return -ENOMEM; /* * Ensure the hash table pointer is set only after all stores to zero * the memory are retired. Pairs with the smp_load_acquire() in * kvm_get_mmu_page_hash(). Note, mmu_lock must be held for write to * add (or remove) shadow pages, and so readers are guaranteed to see * an empty list for their current mmu_lock critical section. */ smp_store_release(&kvm->arch.mmu_page_hash, h); return 0; } static int mmu_first_shadow_root_alloc(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; int r = 0, i, bkt; /* * Check if this is the first shadow root being allocated before * taking the lock. */ if (kvm_shadow_root_allocated(kvm)) return 0; mutex_lock(&kvm->slots_arch_lock); /* Recheck, under the lock, whether this is the first shadow root. */ if (kvm_shadow_root_allocated(kvm)) goto out_unlock; r = kvm_mmu_alloc_page_hash(kvm); if (r) goto out_unlock; /* * Check if memslot metadata actually needs to be allocated, e.g. all * metadata will be allocated upfront if TDP is disabled. */ if (kvm_memslots_have_rmaps(kvm) && kvm_page_track_write_tracking_enabled(kvm)) goto out_success; for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot(slot, bkt, slots) { /* * Both of these functions are no-ops if the target is * already allocated, so unconditionally calling both * is safe. Intentionally do NOT free allocations on * failure to avoid having to track which allocations * were made now versus when the memslot was created. * The metadata is guaranteed to be freed when the slot * is freed, and will be kept/used if userspace retries * KVM_RUN instead of killing the VM. */ r = memslot_rmap_alloc(slot, slot->npages); if (r) goto out_unlock; r = kvm_page_track_write_tracking_alloc(slot); if (r) goto out_unlock; } } /* * Ensure that shadow_root_allocated becomes true strictly after * all the related pointers are set. */ out_success: smp_store_release(&kvm->arch.shadow_root_allocated, true); out_unlock: mutex_unlock(&kvm->slots_arch_lock); return r; } static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; u64 pdptrs[4], pm_mask; gfn_t root_gfn, root_pgd; int quadrant, i, r; hpa_t root; root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu); root_gfn = (root_pgd & __PT_BASE_ADDR_MASK) >> PAGE_SHIFT; if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) { mmu->root.hpa = kvm_mmu_get_dummy_root(); return 0; } /* * On SVM, reading PDPTRs might access guest memory, which might fault * and thus might sleep. Grab the PDPTRs before acquiring mmu_lock. */ if (mmu->cpu_role.base.level == PT32E_ROOT_LEVEL) { for (i = 0; i < 4; ++i) { pdptrs[i] = mmu->get_pdptr(vcpu, i); if (!(pdptrs[i] & PT_PRESENT_MASK)) continue; if (!kvm_vcpu_is_visible_gfn(vcpu, pdptrs[i] >> PAGE_SHIFT)) pdptrs[i] = 0; } } r = mmu_first_shadow_root_alloc(vcpu->kvm); if (r) return r; write_lock(&vcpu->kvm->mmu_lock); r = make_mmu_pages_available(vcpu); if (r < 0) goto out_unlock; /* * Do we shadow a long mode page table? If so we need to * write-protect the guests page table root. */ if (mmu->cpu_role.base.level >= PT64_ROOT_4LEVEL) { root = mmu_alloc_root(vcpu, root_gfn, 0, mmu->root_role.level); mmu->root.hpa = root; goto set_root_pgd; } if (WARN_ON_ONCE(!mmu->pae_root)) { r = -EIO; goto out_unlock; } /* * We shadow a 32 bit page table. This may be a legacy 2-level * or a PAE 3-level page table. In either case we need to be aware that * the shadow page table may be a PAE or a long mode page table. */ pm_mask = PT_PRESENT_MASK | shadow_me_value; if (mmu->root_role.level >= PT64_ROOT_4LEVEL) { pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK; if (WARN_ON_ONCE(!mmu->pml4_root)) { r = -EIO; goto out_unlock; } mmu->pml4_root[0] = __pa(mmu->pae_root) | pm_mask; if (mmu->root_role.level == PT64_ROOT_5LEVEL) { if (WARN_ON_ONCE(!mmu->pml5_root)) { r = -EIO; goto out_unlock; } mmu->pml5_root[0] = __pa(mmu->pml4_root) | pm_mask; } } for (i = 0; i < 4; ++i) { WARN_ON_ONCE(IS_VALID_PAE_ROOT(mmu->pae_root[i])); if (mmu->cpu_role.base.level == PT32E_ROOT_LEVEL) { if (!(pdptrs[i] & PT_PRESENT_MASK)) { mmu->pae_root[i] = INVALID_PAE_ROOT; continue; } root_gfn = pdptrs[i] >> PAGE_SHIFT; } /* * If shadowing 32-bit non-PAE page tables, each PAE page * directory maps one quarter of the guest's non-PAE page * directory. Othwerise each PAE page direct shadows one guest * PAE page directory so that quadrant should be 0. */ quadrant = (mmu->cpu_role.base.level == PT32_ROOT_LEVEL) ? i : 0; root = mmu_alloc_root(vcpu, root_gfn, quadrant, PT32_ROOT_LEVEL); mmu->pae_root[i] = root | pm_mask; } if (mmu->root_role.level == PT64_ROOT_5LEVEL) mmu->root.hpa = __pa(mmu->pml5_root); else if (mmu->root_role.level == PT64_ROOT_4LEVEL) mmu->root.hpa = __pa(mmu->pml4_root); else mmu->root.hpa = __pa(mmu->pae_root); set_root_pgd: mmu->root.pgd = root_pgd; out_unlock: write_unlock(&vcpu->kvm->mmu_lock); return r; } static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; bool need_pml5 = mmu->root_role.level > PT64_ROOT_4LEVEL; u64 *pml5_root = NULL; u64 *pml4_root = NULL; u64 *pae_root; /* * When shadowing 32-bit or PAE NPT with 64-bit NPT, the PML4 and PDP * tables are allocated and initialized at root creation as there is no * equivalent level in the guest's NPT to shadow. Allocate the tables * on demand, as running a 32-bit L1 VMM on 64-bit KVM is very rare. */ if (mmu->root_role.direct || mmu->cpu_role.base.level >= PT64_ROOT_4LEVEL || mmu->root_role.level < PT64_ROOT_4LEVEL) return 0; /* * NPT, the only paging mode that uses this horror, uses a fixed number * of levels for the shadow page tables, e.g. all MMUs are 4-level or * all MMus are 5-level. Thus, this can safely require that pml5_root * is allocated if the other roots are valid and pml5 is needed, as any * prior MMU would also have required pml5. */ if (mmu->pae_root && mmu->pml4_root && (!need_pml5 || mmu->pml5_root)) return 0; /* * The special roots should always be allocated in concert. Yell and * bail if KVM ends up in a state where only one of the roots is valid. */ if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->pml4_root || (need_pml5 && mmu->pml5_root))) return -EIO; /* * Unlike 32-bit NPT, the PDP table doesn't need to be in low mem, and * doesn't need to be decrypted. */ pae_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!pae_root) return -ENOMEM; #ifdef CONFIG_X86_64 pml4_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!pml4_root) goto err_pml4; if (need_pml5) { pml5_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!pml5_root) goto err_pml5; } #endif mmu->pae_root = pae_root; mmu->pml4_root = pml4_root; mmu->pml5_root = pml5_root; return 0; #ifdef CONFIG_X86_64 err_pml5: free_page((unsigned long)pml4_root); err_pml4: free_page((unsigned long)pae_root); return -ENOMEM; #endif } static bool is_unsync_root(hpa_t root) { struct kvm_mmu_page *sp; if (!VALID_PAGE(root) || kvm_mmu_is_dummy_root(root)) return false; /* * The read barrier orders the CPU's read of SPTE.W during the page table * walk before the reads of sp->unsync/sp->unsync_children here. * * Even if another CPU was marking the SP as unsync-ed simultaneously, * any guest page table changes are not guaranteed to be visible anyway * until this VCPU issues a TLB flush strictly after those changes are * made. We only need to ensure that the other CPU sets these flags * before any actual changes to the page tables are made. The comments * in mmu_try_to_unsync_pages() describe what could go wrong if this * requirement isn't satisfied. */ smp_rmb(); sp = root_to_sp(root); /* * PAE roots (somewhat arbitrarily) aren't backed by shadow pages, the * PDPTEs for a given PAE root need to be synchronized individually. */ if (WARN_ON_ONCE(!sp)) return false; if (sp->unsync || sp->unsync_children) return true; return false; } void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) { int i; struct kvm_mmu_page *sp; if (vcpu->arch.mmu->root_role.direct) return; if (!VALID_PAGE(vcpu->arch.mmu->root.hpa)) return; vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); if (vcpu->arch.mmu->cpu_role.base.level >= PT64_ROOT_4LEVEL) { hpa_t root = vcpu->arch.mmu->root.hpa; if (!is_unsync_root(root)) return; sp = root_to_sp(root); write_lock(&vcpu->kvm->mmu_lock); mmu_sync_children(vcpu, sp, true); write_unlock(&vcpu->kvm->mmu_lock); return; } write_lock(&vcpu->kvm->mmu_lock); for (i = 0; i < 4; ++i) { hpa_t root = vcpu->arch.mmu->pae_root[i]; if (IS_VALID_PAE_ROOT(root)) { sp = spte_to_child_sp(root); mmu_sync_children(vcpu, sp, true); } } write_unlock(&vcpu->kvm->mmu_lock); } void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu) { unsigned long roots_to_free = 0; int i; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if (is_unsync_root(vcpu->arch.mmu->prev_roots[i].hpa)) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); /* sync prev_roots by simply freeing them */ kvm_mmu_free_roots(vcpu->kvm, vcpu->arch.mmu, roots_to_free); } static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, gpa_t vaddr, u64 access, struct x86_exception *exception) { if (exception) exception->error_code = 0; return kvm_translate_gpa(vcpu, mmu, vaddr, access, exception); } static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) { /* * A nested guest cannot use the MMIO cache if it is using nested * page tables, because cr2 is a nGPA while the cache stores GPAs. */ if (mmu_is_nested(vcpu)) return false; if (direct) return vcpu_match_mmio_gpa(vcpu, addr); return vcpu_match_mmio_gva(vcpu, addr); } /* * Return the level of the lowest level SPTE added to sptes. * That SPTE may be non-present. * * Must be called between walk_shadow_page_lockless_{begin,end}. */ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level) { struct kvm_shadow_walk_iterator iterator; int leaf = -1; u64 spte; for (shadow_walk_init(&iterator, vcpu, addr), *root_level = iterator.level; shadow_walk_okay(&iterator); __shadow_walk_next(&iterator, spte)) { leaf = iterator.level; spte = mmu_spte_get_lockless(iterator.sptep); sptes[leaf] = spte; } return leaf; } static int get_sptes_lockless(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level) { int leaf; walk_shadow_page_lockless_begin(vcpu); if (is_tdp_mmu_active(vcpu)) leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, root_level); else leaf = get_walk(vcpu, addr, sptes, root_level); walk_shadow_page_lockless_end(vcpu); return leaf; } /* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; struct rsvd_bits_validate *rsvd_check; int root, leaf, level; bool reserved = false; leaf = get_sptes_lockless(vcpu, addr, sptes, &root); if (unlikely(leaf < 0)) { *sptep = 0ull; return reserved; } *sptep = sptes[leaf]; /* * Skip reserved bits checks on the terminal leaf if it's not a valid * SPTE. Note, this also (intentionally) skips MMIO SPTEs, which, by * design, always have reserved bits set. The purpose of the checks is * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs. */ if (!is_shadow_present_pte(sptes[leaf])) leaf++; rsvd_check = &vcpu->arch.mmu->shadow_zero_check; for (level = root; level >= leaf; level--) reserved |= is_rsvd_spte(rsvd_check, sptes[level], level); if (reserved) { pr_err("%s: reserved bits set on MMU-present spte, addr 0x%llx, hierarchy:\n", __func__, addr); for (level = root; level >= leaf; level--) pr_err("------ spte = 0x%llx level = %d, rsvd bits = 0x%llx", sptes[level], level, get_rsvd_bits(rsvd_check, sptes[level], level)); } return reserved; } static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) { u64 spte; bool reserved; if (mmio_info_in_cache(vcpu, addr, direct)) return RET_PF_EMULATE; reserved = get_mmio_spte(vcpu, addr, &spte); if (WARN_ON_ONCE(reserved)) return -EINVAL; if (is_mmio_spte(vcpu->kvm, spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); unsigned int access = get_mmio_spte_access(spte); if (!check_mmio_spte(vcpu, spte)) return RET_PF_INVALID; if (direct) addr = 0; trace_handle_mmio_page_fault(addr, gfn, access); vcpu_cache_mmio_info(vcpu, addr, gfn, access); return RET_PF_EMULATE; } /* * If the page table is zapped by other cpus, let CPU fault again on * the address. */ return RET_PF_RETRY; } static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { if (unlikely(fault->rsvd)) return false; if (!fault->present || !fault->write) return false; /* * guest is writing the page which is write tracked which can * not be fixed by page fault handler. */ if (kvm_gfn_is_write_tracked(vcpu->kvm, fault->slot, fault->gfn)) return true; return false; } static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) { struct kvm_shadow_walk_iterator iterator; u64 spte; walk_shadow_page_lockless_begin(vcpu); for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) clear_sp_write_flooding_count(iterator.sptep); walk_shadow_page_lockless_end(vcpu); } static u32 alloc_apf_token(struct kvm_vcpu *vcpu) { /* make sure the token value is not 0 */ u32 id = vcpu->arch.apf.id; if (id << 12 == 0) vcpu->arch.apf.id = 1; return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; } static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_arch_async_pf arch; arch.token = alloc_apf_token(vcpu); arch.gfn = fault->gfn; arch.error_code = fault->error_code; arch.direct_map = vcpu->arch.mmu->root_role.direct; if (arch.direct_map) arch.cr3 = (unsigned long)INVALID_GPA; else arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu); return kvm_setup_async_pf(vcpu, fault->addr, kvm_vcpu_gfn_to_hva(vcpu, fault->gfn), &arch); } void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { int r; if (WARN_ON_ONCE(work->arch.error_code & PFERR_PRIVATE_ACCESS)) return; if ((vcpu->arch.mmu->root_role.direct != work->arch.direct_map) || work->wakeup_all) return; r = kvm_mmu_reload(vcpu); if (unlikely(r)) return; if (!vcpu->arch.mmu->root_role.direct && work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu)) return; r = kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, work->arch.error_code, true, NULL, NULL); /* * Account fixed page faults, otherwise they'll never be counted, but * ignore stats for all other return times. Page-ready "faults" aren't * truly spurious and never trigger emulation */ if (r == RET_PF_FIXED) vcpu->stat.pf_fixed++; } static void kvm_mmu_finish_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, int r) { kvm_release_faultin_page(vcpu->kvm, fault->refcounted_page, r == RET_PF_RETRY, fault->map_writable); } static int kvm_mmu_faultin_pfn_gmem(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { int max_order, r; if (!kvm_slot_has_gmem(fault->slot)) { kvm_mmu_prepare_memory_fault_exit(vcpu, fault); return -EFAULT; } r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, &fault->refcounted_page, &max_order); if (r) { kvm_mmu_prepare_memory_fault_exit(vcpu, fault); return r; } fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY); fault->max_level = kvm_max_level_for_order(max_order); return RET_PF_CONTINUE; } static int __kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { unsigned int foll = fault->write ? FOLL_WRITE : 0; if (fault->is_private || kvm_memslot_is_gmem_only(fault->slot)) return kvm_mmu_faultin_pfn_gmem(vcpu, fault); foll |= FOLL_NOWAIT; fault->pfn = __kvm_faultin_pfn(fault->slot, fault->gfn, foll, &fault->map_writable, &fault->refcounted_page); /* * If resolving the page failed because I/O is needed to fault-in the * page, then either set up an asynchronous #PF to do the I/O, or if * doing an async #PF isn't possible, retry with I/O allowed. All * other failures are terminal, i.e. retrying won't help. */ if (fault->pfn != KVM_PFN_ERR_NEEDS_IO) return RET_PF_CONTINUE; if (!fault->prefetch && kvm_can_do_async_pf(vcpu)) { trace_kvm_try_async_get_page(fault->addr, fault->gfn); if (kvm_find_async_pf_gfn(vcpu, fault->gfn)) { trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); return RET_PF_RETRY; } else if (kvm_arch_setup_async_pf(vcpu, fault)) { return RET_PF_RETRY; } } /* * Allow gup to bail on pending non-fatal signals when it's also allowed * to wait for IO. Note, gup always bails if it is unable to quickly * get a page and a fatal signal, i.e. SIGKILL, is pending. */ foll |= FOLL_INTERRUPTIBLE; foll &= ~FOLL_NOWAIT; fault->pfn = __kvm_faultin_pfn(fault->slot, fault->gfn, foll, &fault->map_writable, &fault->refcounted_page); return RET_PF_CONTINUE; } static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, unsigned int access) { struct kvm_memory_slot *slot = fault->slot; struct kvm *kvm = vcpu->kvm; int ret; if (KVM_BUG_ON(kvm_is_gfn_alias(kvm, fault->gfn), kvm)) return -EFAULT; /* * Note that the mmu_invalidate_seq also serves to detect a concurrent * change in attributes. is_page_fault_stale() will detect an * invalidation relate to fault->fn and resume the guest without * installing a mapping in the page tables. */ fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); /* * Now that we have a snapshot of mmu_invalidate_seq we can check for a * private vs. shared mismatch. */ if (fault->is_private != kvm_mem_is_private(kvm, fault->gfn)) { kvm_mmu_prepare_memory_fault_exit(vcpu, fault); return -EFAULT; } if (unlikely(!slot)) return kvm_handle_noslot_fault(vcpu, fault, access); /* * Retry the page fault if the gfn hit a memslot that is being deleted * or moved. This ensures any existing SPTEs for the old memslot will * be zapped before KVM inserts a new MMIO SPTE for the gfn. Punt the * error to userspace if this is a prefault, as KVM's prefaulting ABI * doesn't provide the same forward progress guarantees as KVM_RUN. */ if (slot->flags & KVM_MEMSLOT_INVALID) { if (fault->prefetch) return -EAGAIN; return RET_PF_RETRY; } if (slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) { /* * Don't map L1's APIC access page into L2, KVM doesn't support * using APICv/AVIC to accelerate L2 accesses to L1's APIC, * i.e. the access needs to be emulated. Emulating access to * L1's APIC is also correct if L1 is accelerating L2's own * virtual APIC, but for some reason L1 also maps _L1's_ APIC * into L2. Note, vcpu_is_mmio_gpa() always treats access to * the APIC as MMIO. Allow an MMIO SPTE to be created, as KVM * uses different roots for L1 vs. L2, i.e. there is no danger * of breaking APICv/AVIC for L1. */ if (is_guest_mode(vcpu)) return kvm_handle_noslot_fault(vcpu, fault, access); /* * If the APIC access page exists but is disabled, go directly * to emulation without caching the MMIO access or creating a * MMIO SPTE. That way the cache doesn't need to be purged * when the AVIC is re-enabled. */ if (!kvm_apicv_activated(vcpu->kvm)) return RET_PF_EMULATE; } /* * Check for a relevant mmu_notifier invalidation event before getting * the pfn from the primary MMU, and before acquiring mmu_lock. * * For mmu_lock, if there is an in-progress invalidation and the kernel * allows preemption, the invalidation task may drop mmu_lock and yield * in response to mmu_lock being contended, which is *very* counter- * productive as this vCPU can't actually make forward progress until * the invalidation completes. * * Retrying now can also avoid unnessary lock contention in the primary * MMU, as the primary MMU doesn't necessarily hold a single lock for * the duration of the invalidation, i.e. faulting in a conflicting pfn * can cause the invalidation to take longer by holding locks that are * needed to complete the invalidation. * * Do the pre-check even for non-preemtible kernels, i.e. even if KVM * will never yield mmu_lock in response to contention, as this vCPU is * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held * to detect retry guarantees the worst case latency for the vCPU. */ if (mmu_invalidate_retry_gfn_unsafe(kvm, fault->mmu_seq, fault->gfn)) return RET_PF_RETRY; ret = __kvm_mmu_faultin_pfn(vcpu, fault); if (ret != RET_PF_CONTINUE) return ret; if (unlikely(is_error_pfn(fault->pfn))) return kvm_handle_error_pfn(vcpu, fault); if (WARN_ON_ONCE(!fault->slot || is_noslot_pfn(fault->pfn))) return kvm_handle_noslot_fault(vcpu, fault, access); /* * Check again for a relevant mmu_notifier invalidation event purely to * avoid contending mmu_lock. Most invalidations will be detected by * the previous check, but checking is extremely cheap relative to the * overall cost of failing to detect the invalidation until after * mmu_lock is acquired. */ if (mmu_invalidate_retry_gfn_unsafe(kvm, fault->mmu_seq, fault->gfn)) { kvm_mmu_finish_page_fault(vcpu, fault, RET_PF_RETRY); return RET_PF_RETRY; } return RET_PF_CONTINUE; } /* * Returns true if the page fault is stale and needs to be retried, i.e. if the * root was invalidated by a memslot update or a relevant mmu_notifier fired. */ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_mmu_page *sp = root_to_sp(vcpu->arch.mmu->root.hpa); /* Special roots, e.g. pae_root, are not backed by shadow pages. */ if (sp && is_obsolete_sp(vcpu->kvm, sp)) return true; /* * Roots without an associated shadow page are considered invalid if * there is a pending request to free obsolete roots. The request is * only a hint that the current root _may_ be obsolete and needs to be * reloaded, e.g. if the guest frees a PGD that KVM is tracking as a * previous root, then __kvm_mmu_prepare_zap_page() signals all vCPUs * to reload even if no vCPU is actively using the root. */ if (!sp && kvm_test_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu)) return true; /* * Check for a relevant mmu_notifier invalidation event one last time * now that mmu_lock is held, as the "unsafe" checks performed without * holding mmu_lock can get false negatives. */ return fault->slot && mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn); } static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { int r; /* Dummy roots are used only for shadowing bad guest roots. */ if (WARN_ON_ONCE(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa))) return RET_PF_RETRY; if (page_fault_handle_page_track(vcpu, fault)) return RET_PF_WRITE_PROTECTED; r = fast_page_fault(vcpu, fault); if (r != RET_PF_INVALID) return r; r = mmu_topup_memory_caches(vcpu, false); if (r) return r; r = kvm_mmu_faultin_pfn(vcpu, fault, ACC_ALL); if (r != RET_PF_CONTINUE) return r; r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); if (is_page_fault_stale(vcpu, fault)) goto out_unlock; r = make_mmu_pages_available(vcpu); if (r) goto out_unlock; r = direct_map(vcpu, fault); out_unlock: kvm_mmu_finish_page_fault(vcpu, fault, r); write_unlock(&vcpu->kvm->mmu_lock); return r; } static int nonpaging_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { /* This path builds a PAE pagetable, we can map 2mb pages at maximum. */ fault->max_level = PG_LEVEL_2M; return direct_page_fault(vcpu, fault); } int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len) { int r = 1; u32 flags = vcpu->arch.apf.host_apf_flags; #ifndef CONFIG_X86_64 /* A 64-bit CR2 should be impossible on 32-bit KVM. */ if (WARN_ON_ONCE(fault_address >> 32)) return -EFAULT; #endif /* * Legacy #PF exception only have a 32-bit error code. Simply drop the * upper bits as KVM doesn't use them for #PF (because they are never * set), and to ensure there are no collisions with KVM-defined bits. */ if (WARN_ON_ONCE(error_code >> 32)) error_code = lower_32_bits(error_code); /* * Restrict KVM-defined flags to bits 63:32 so that it's impossible for * them to conflict with #PF error codes, which are limited to 32 bits. */ BUILD_BUG_ON(lower_32_bits(PFERR_SYNTHETIC_MASK)); kvm_request_l1tf_flush_l1d(); if (!flags) { trace_kvm_page_fault(vcpu, fault_address, error_code); r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn, insn_len); } else if (flags & KVM_PV_REASON_PAGE_NOT_PRESENT) { vcpu->arch.apf.host_apf_flags = 0; local_irq_disable(); kvm_async_pf_task_wait_schedule(fault_address); local_irq_enable(); } else { WARN_ONCE(1, "Unexpected host async PF flags: %x\n", flags); } return r; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_handle_page_fault); #ifdef CONFIG_X86_64 static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { int r; if (page_fault_handle_page_track(vcpu, fault)) return RET_PF_WRITE_PROTECTED; r = fast_page_fault(vcpu, fault); if (r != RET_PF_INVALID) return r; r = mmu_topup_memory_caches(vcpu, false); if (r) return r; r = kvm_mmu_faultin_pfn(vcpu, fault, ACC_ALL); if (r != RET_PF_CONTINUE) return r; r = RET_PF_RETRY; read_lock(&vcpu->kvm->mmu_lock); if (is_page_fault_stale(vcpu, fault)) goto out_unlock; r = kvm_tdp_mmu_map(vcpu, fault); out_unlock: kvm_mmu_finish_page_fault(vcpu, fault, r); read_unlock(&vcpu->kvm->mmu_lock); return r; } #endif int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { #ifdef CONFIG_X86_64 if (tdp_mmu_enabled) return kvm_tdp_mmu_page_fault(vcpu, fault); #endif return direct_page_fault(vcpu, fault); } static int kvm_tdp_page_prefault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, u8 *level) { int r; /* * Restrict to TDP page fault, since that's the only case where the MMU * is indexed by GPA. */ if (vcpu->arch.mmu->page_fault != kvm_tdp_page_fault) return -EOPNOTSUPP; do { if (signal_pending(current)) return -EINTR; if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) return -EIO; cond_resched(); r = kvm_mmu_do_page_fault(vcpu, gpa, error_code, true, NULL, level); } while (r == RET_PF_RETRY); if (r < 0) return r; switch (r) { case RET_PF_FIXED: case RET_PF_SPURIOUS: case RET_PF_WRITE_PROTECTED: return 0; case RET_PF_EMULATE: return -ENOENT; case RET_PF_RETRY: case RET_PF_CONTINUE: case RET_PF_INVALID: default: WARN_ONCE(1, "could not fix page fault during prefault"); return -EIO; } } long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, struct kvm_pre_fault_memory *range) { u64 error_code = PFERR_GUEST_FINAL_MASK; u8 level = PG_LEVEL_4K; u64 direct_bits; u64 end; int r; if (!vcpu->kvm->arch.pre_fault_allowed) return -EOPNOTSUPP; if (kvm_is_gfn_alias(vcpu->kvm, gpa_to_gfn(range->gpa))) return -EINVAL; /* * reload is efficient when called repeatedly, so we can do it on * every iteration. */ r = kvm_mmu_reload(vcpu); if (r) return r; direct_bits = 0; if (kvm_arch_has_private_mem(vcpu->kvm) && kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa))) error_code |= PFERR_PRIVATE_ACCESS; else direct_bits = gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm)); /* * Shadow paging uses GVA for kvm page fault, so restrict to * two-dimensional paging. */ r = kvm_tdp_page_prefault(vcpu, range->gpa | direct_bits, error_code, &level); if (r < 0) return r; /* * If the mapping that covers range->gpa can use a huge page, it * may start below it or end after range->gpa + range->size. */ end = (range->gpa & KVM_HPAGE_MASK(level)) + KVM_HPAGE_SIZE(level); return min(range->size, end - range->gpa); } #ifdef CONFIG_KVM_GUEST_MEMFD static void kvm_assert_gmem_invalidate_lock_held(struct kvm_memory_slot *slot) { #ifdef CONFIG_PROVE_LOCKING if (WARN_ON_ONCE(!kvm_slot_has_gmem(slot)) || WARN_ON_ONCE(!slot->gmem.file) || WARN_ON_ONCE(!file_count(slot->gmem.file))) return; lockdep_assert_held(&file_inode(slot->gmem.file)->i_mapping->invalidate_lock); #endif } int kvm_tdp_mmu_map_private_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) { struct kvm_page_fault fault = { .addr = gfn_to_gpa(gfn), .error_code = PFERR_GUEST_FINAL_MASK | PFERR_PRIVATE_ACCESS, .prefetch = true, .is_tdp = true, .nx_huge_page_workaround_enabled = is_nx_huge_page_enabled(vcpu->kvm), .max_level = PG_LEVEL_4K, .req_level = PG_LEVEL_4K, .goal_level = PG_LEVEL_4K, .is_private = true, .gfn = gfn, .slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn), .pfn = pfn, .map_writable = true, }; struct kvm *kvm = vcpu->kvm; int r; lockdep_assert_held(&kvm->slots_lock); /* * Mapping a pre-determined private pfn is intended only for use when * populating a guest_memfd instance. Assert that the slot is backed * by guest_memfd and that the gmem instance's invalidate_lock is held. */ kvm_assert_gmem_invalidate_lock_held(fault.slot); if (KVM_BUG_ON(!tdp_mmu_enabled, kvm)) return -EIO; if (kvm_gfn_is_write_tracked(kvm, fault.slot, fault.gfn)) return -EPERM; r = kvm_mmu_reload(vcpu); if (r) return r; r = mmu_topup_memory_caches(vcpu, false); if (r) return r; do { if (signal_pending(current)) return -EINTR; if (kvm_test_request(KVM_REQ_VM_DEAD, vcpu)) return -EIO; cond_resched(); guard(read_lock)(&kvm->mmu_lock); r = kvm_tdp_mmu_map(vcpu, &fault); } while (r == RET_PF_RETRY); if (r != RET_PF_FIXED) return -EIO; return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_tdp_mmu_map_private_pfn); #endif static void nonpaging_init_context(struct kvm_mmu *context) { context->page_fault = nonpaging_page_fault; context->gva_to_gpa = nonpaging_gva_to_gpa; context->sync_spte = NULL; } static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd, union kvm_mmu_page_role role) { struct kvm_mmu_page *sp; if (!VALID_PAGE(root->hpa)) return false; if (!role.direct && pgd != root->pgd) return false; sp = root_to_sp(root->hpa); if (WARN_ON_ONCE(!sp)) return false; return role.word == sp->role.word; } /* * Find out if a previously cached root matching the new pgd/role is available, * and insert the current root as the MRU in the cache. * If a matching root is found, it is assigned to kvm_mmu->root and * true is returned. * If no match is found, kvm_mmu->root is left invalid, the LRU root is * evicted to make room for the current root, and false is returned. */ static bool cached_root_find_and_keep_current(struct kvm *kvm, struct kvm_mmu *mmu, gpa_t new_pgd, union kvm_mmu_page_role new_role) { uint i; if (is_root_usable(&mmu->root, new_pgd, new_role)) return true; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { /* * The swaps end up rotating the cache like this: * C 0 1 2 3 (on entry to the function) * 0 C 1 2 3 * 1 C 0 2 3 * 2 C 0 1 3 * 3 C 0 1 2 (on exit from the loop) */ swap(mmu->root, mmu->prev_roots[i]); if (is_root_usable(&mmu->root, new_pgd, new_role)) return true; } kvm_mmu_free_roots(kvm, mmu, KVM_MMU_ROOT_CURRENT); return false; } /* * Find out if a previously cached root matching the new pgd/role is available. * On entry, mmu->root is invalid. * If a matching root is found, it is assigned to kvm_mmu->root, the LRU entry * of the cache becomes invalid, and true is returned. * If no match is found, kvm_mmu->root is left invalid and false is returned. */ static bool cached_root_find_without_current(struct kvm *kvm, struct kvm_mmu *mmu, gpa_t new_pgd, union kvm_mmu_page_role new_role) { uint i; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if (is_root_usable(&mmu->prev_roots[i], new_pgd, new_role)) goto hit; return false; hit: swap(mmu->root, mmu->prev_roots[i]); /* Bubble up the remaining roots. */ for (; i < KVM_MMU_NUM_PREV_ROOTS - 1; i++) mmu->prev_roots[i] = mmu->prev_roots[i + 1]; mmu->prev_roots[i].hpa = INVALID_PAGE; return true; } static bool fast_pgd_switch(struct kvm *kvm, struct kvm_mmu *mmu, gpa_t new_pgd, union kvm_mmu_page_role new_role) { /* * Limit reuse to 64-bit hosts+VMs without "special" roots in order to * avoid having to deal with PDPTEs and other complexities. */ if (VALID_PAGE(mmu->root.hpa) && !root_to_sp(mmu->root.hpa)) kvm_mmu_free_roots(kvm, mmu, KVM_MMU_ROOT_CURRENT); if (VALID_PAGE(mmu->root.hpa)) return cached_root_find_and_keep_current(kvm, mmu, new_pgd, new_role); else return cached_root_find_without_current(kvm, mmu, new_pgd, new_role); } void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd) { struct kvm_mmu *mmu = vcpu->arch.mmu; union kvm_mmu_page_role new_role = mmu->root_role; /* * Return immediately if no usable root was found, kvm_mmu_reload() * will establish a valid root prior to the next VM-Enter. */ if (!fast_pgd_switch(vcpu->kvm, mmu, new_pgd, new_role)) return; /* * It's possible that the cached previous root page is obsolete because * of a change in the MMU generation number. However, changing the * generation number is accompanied by KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, * which will free the root set here and allocate a new one. */ kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); if (force_flush_and_sync_on_reuse) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } /* * The last MMIO access's GVA and GPA are cached in the VCPU. When * switching to a new CR3, that GVA->GPA mapping may no longer be * valid. So clear any cached MMIO info even when we don't need to sync * the shadow page tables. */ vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); /* * If this is a direct root page, it doesn't have a write flooding * count. Otherwise, clear the write flooding count. */ if (!new_role.direct) { struct kvm_mmu_page *sp = root_to_sp(vcpu->arch.mmu->root.hpa); if (!WARN_ON_ONCE(!sp)) __clear_sp_write_flooding_count(sp); } } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_new_pgd); static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, unsigned int access) { if (unlikely(is_mmio_spte(vcpu->kvm, *sptep))) { if (gfn != get_mmio_spte_gfn(*sptep)) { mmu_spte_clear_no_track(sptep); return true; } mark_mmio_spte(vcpu, sptep, gfn, access); return true; } return false; } #define PTTYPE_EPT 18 /* arbitrary */ #define PTTYPE PTTYPE_EPT #include "paging_tmpl.h" #undef PTTYPE #define PTTYPE 64 #include "paging_tmpl.h" #undef PTTYPE #define PTTYPE 32 #include "paging_tmpl.h" #undef PTTYPE static void __reset_rsvds_bits_mask(struct rsvd_bits_validate *rsvd_check, u64 pa_bits_rsvd, int level, bool nx, bool gbpages, bool pse, bool amd) { u64 gbpages_bit_rsvd = 0; u64 nonleaf_bit8_rsvd = 0; u64 high_bits_rsvd; rsvd_check->bad_mt_xwr = 0; if (!gbpages) gbpages_bit_rsvd = rsvd_bits(7, 7); if (level == PT32E_ROOT_LEVEL) high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 62); else high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51); /* Note, NX doesn't exist in PDPTEs, this is handled below. */ if (!nx) high_bits_rsvd |= rsvd_bits(63, 63); /* * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for * leaf entries) on AMD CPUs only. */ if (amd) nonleaf_bit8_rsvd = rsvd_bits(8, 8); switch (level) { case PT32_ROOT_LEVEL: /* no rsvd bits for 2 level 4K page table entries */ rsvd_check->rsvd_bits_mask[0][1] = 0; rsvd_check->rsvd_bits_mask[0][0] = 0; rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; if (!pse) { rsvd_check->rsvd_bits_mask[1][1] = 0; break; } if (is_cpuid_PSE36()) /* 36bits PSE 4MB page */ rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(17, 21); else /* 32 bits PSE 4MB page */ rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(13, 21); break; case PT32E_ROOT_LEVEL: rsvd_check->rsvd_bits_mask[0][2] = rsvd_bits(63, 63) | high_bits_rsvd | rsvd_bits(5, 8) | rsvd_bits(1, 2); /* PDPTE */ rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd; /* PDE */ rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; /* PTE */ rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(13, 20); /* large page */ rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; break; case PT64_ROOT_5LEVEL: rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | nonleaf_bit8_rsvd | rsvd_bits(7, 7); rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; fallthrough; case PT64_ROOT_4LEVEL: rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | nonleaf_bit8_rsvd | rsvd_bits(7, 7); rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | gbpages_bit_rsvd; rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd; rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | gbpages_bit_rsvd | rsvd_bits(13, 29); rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(13, 20); /* large page */ rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; break; } } static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { __reset_rsvds_bits_mask(&context->guest_rsvd_check, vcpu->arch.reserved_gpa_bits, context->cpu_role.base.level, is_efer_nx(context), guest_cpu_cap_has(vcpu, X86_FEATURE_GBPAGES), is_cr4_pse(context), guest_cpuid_is_amd_compatible(vcpu)); } static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, u64 pa_bits_rsvd, bool execonly, int huge_page_level) { u64 high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51); u64 large_1g_rsvd = 0, large_2m_rsvd = 0; u64 bad_mt_xwr; if (huge_page_level < PG_LEVEL_1G) large_1g_rsvd = rsvd_bits(7, 7); if (huge_page_level < PG_LEVEL_2M) large_2m_rsvd = rsvd_bits(7, 7); rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | rsvd_bits(3, 7); rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | rsvd_bits(3, 7); rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6) | large_1g_rsvd; rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6) | large_2m_rsvd; rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; /* large page */ rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29) | large_1g_rsvd; rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20) | large_2m_rsvd; rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; bad_mt_xwr = 0xFFull << (2 * 8); /* bits 3..5 must not be 2 */ bad_mt_xwr |= 0xFFull << (3 * 8); /* bits 3..5 must not be 3 */ bad_mt_xwr |= 0xFFull << (7 * 8); /* bits 3..5 must not be 7 */ bad_mt_xwr |= REPEAT_BYTE(1ull << 2); /* bits 0..2 must not be 010 */ bad_mt_xwr |= REPEAT_BYTE(1ull << 6); /* bits 0..2 must not be 110 */ if (!execonly) { /* bits 0..2 must not be 100 unless VMX capabilities allow it */ bad_mt_xwr |= REPEAT_BYTE(1ull << 4); } rsvd_check->bad_mt_xwr = bad_mt_xwr; } static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly, int huge_page_level) { __reset_rsvds_bits_mask_ept(&context->guest_rsvd_check, vcpu->arch.reserved_gpa_bits, execonly, huge_page_level); } static inline u64 reserved_hpa_bits(void) { return rsvd_bits(kvm_host.maxphyaddr, 63); } /* * the page table on host is the shadow page table for the page * table in guest or amd nested guest, its mmu features completely * follow the features in guest. */ static void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { /* @amd adds a check on bit of SPTEs, which KVM shouldn't use anyways. */ bool is_amd = true; /* KVM doesn't use 2-level page tables for the shadow MMU. */ bool is_pse = false; struct rsvd_bits_validate *shadow_zero_check; int i; WARN_ON_ONCE(context->root_role.level < PT32E_ROOT_LEVEL); shadow_zero_check = &context->shadow_zero_check; __reset_rsvds_bits_mask(shadow_zero_check, reserved_hpa_bits(), context->root_role.level, context->root_role.efer_nx, guest_cpu_cap_has(vcpu, X86_FEATURE_GBPAGES), is_pse, is_amd); if (!shadow_me_mask) return; for (i = context->root_role.level; --i >= 0;) { /* * So far shadow_me_value is a constant during KVM's life * time. Bits in shadow_me_value are allowed to be set. * Bits in shadow_me_mask but not in shadow_me_value are * not allowed to be set. */ shadow_zero_check->rsvd_bits_mask[0][i] |= shadow_me_mask; shadow_zero_check->rsvd_bits_mask[1][i] |= shadow_me_mask; shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_value; shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_value; } } static inline bool boot_cpu_is_amd(void) { WARN_ON_ONCE(!tdp_enabled); return shadow_x_mask == 0; } /* * the direct page table on host, use as much mmu features as * possible, however, kvm currently does not do execution-protection. */ static void reset_tdp_shadow_zero_bits_mask(struct kvm_mmu *context) { struct rsvd_bits_validate *shadow_zero_check; int i; shadow_zero_check = &context->shadow_zero_check; if (boot_cpu_is_amd()) __reset_rsvds_bits_mask(shadow_zero_check, reserved_hpa_bits(), context->root_role.level, true, boot_cpu_has(X86_FEATURE_GBPAGES), false, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, reserved_hpa_bits(), false, max_huge_page_level); if (!shadow_me_mask) return; for (i = context->root_role.level; --i >= 0;) { shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask; shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask; } } /* * as the comments in reset_shadow_zero_bits_mask() except it * is the shadow page table for intel nested guest. */ static void reset_ept_shadow_zero_bits_mask(struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, reserved_hpa_bits(), execonly, max_huge_page_level); } #define BYTE_MASK(access) \ ((1 & (access) ? 2 : 0) | \ (2 & (access) ? 4 : 0) | \ (3 & (access) ? 8 : 0) | \ (4 & (access) ? 16 : 0) | \ (5 & (access) ? 32 : 0) | \ (6 & (access) ? 64 : 0) | \ (7 & (access) ? 128 : 0)) static void update_permission_bitmask(struct kvm_mmu *mmu, bool ept) { unsigned byte; const u8 x = BYTE_MASK(ACC_EXEC_MASK); const u8 w = BYTE_MASK(ACC_WRITE_MASK); const u8 u = BYTE_MASK(ACC_USER_MASK); bool cr4_smep = is_cr4_smep(mmu); bool cr4_smap = is_cr4_smap(mmu); bool cr0_wp = is_cr0_wp(mmu); bool efer_nx = is_efer_nx(mmu); for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) { unsigned pfec = byte << 1; /* * Each "*f" variable has a 1 bit for each UWX value * that causes a fault with the given PFEC. */ /* Faults from writes to non-writable pages */ u8 wf = (pfec & PFERR_WRITE_MASK) ? (u8)~w : 0; /* Faults from user mode accesses to supervisor pages */ u8 uf = (pfec & PFERR_USER_MASK) ? (u8)~u : 0; /* Faults from fetches of non-executable pages*/ u8 ff = (pfec & PFERR_FETCH_MASK) ? (u8)~x : 0; /* Faults from kernel mode fetches of user pages */ u8 smepf = 0; /* Faults from kernel mode accesses of user pages */ u8 smapf = 0; if (!ept) { /* Faults from kernel mode accesses to user pages */ u8 kf = (pfec & PFERR_USER_MASK) ? 0 : u; /* Not really needed: !nx will cause pte.nx to fault */ if (!efer_nx) ff = 0; /* Allow supervisor writes if !cr0.wp */ if (!cr0_wp) wf = (pfec & PFERR_USER_MASK) ? wf : 0; /* Disallow supervisor fetches of user code if cr4.smep */ if (cr4_smep) smepf = (pfec & PFERR_FETCH_MASK) ? kf : 0; /* * SMAP:kernel-mode data accesses from user-mode * mappings should fault. A fault is considered * as a SMAP violation if all of the following * conditions are true: * - X86_CR4_SMAP is set in CR4 * - A user page is accessed * - The access is not a fetch * - The access is supervisor mode * - If implicit supervisor access or X86_EFLAGS_AC is clear * * Here, we cover the first four conditions. * The fifth is computed dynamically in permission_fault(); * PFERR_RSVD_MASK bit will be set in PFEC if the access is * *not* subject to SMAP restrictions. */ if (cr4_smap) smapf = (pfec & (PFERR_RSVD_MASK|PFERR_FETCH_MASK)) ? 0 : kf; } mmu->permissions[byte] = ff | uf | wf | smepf | smapf; } } /* * PKU is an additional mechanism by which the paging controls access to * user-mode addresses based on the value in the PKRU register. Protection * key violations are reported through a bit in the page fault error code. * Unlike other bits of the error code, the PK bit is not known at the * call site of e.g. gva_to_gpa; it must be computed directly in * permission_fault based on two bits of PKRU, on some machine state (CR4, * CR0, EFER, CPL), and on other bits of the error code and the page tables. * * In particular the following conditions come from the error code, the * page tables and the machine state: * - PK is always zero unless CR4.PKE=1 and EFER.LMA=1 * - PK is always zero if RSVD=1 (reserved bit set) or F=1 (instruction fetch) * - PK is always zero if U=0 in the page tables * - PKRU.WD is ignored if CR0.WP=0 and the access is a supervisor access. * * The PKRU bitmask caches the result of these four conditions. The error * code (minus the P bit) and the page table's U bit form an index into the * PKRU bitmask. Two bits of the PKRU bitmask are then extracted and ANDed * with the two bits of the PKRU register corresponding to the protection key. * For the first three conditions above the bits will be 00, thus masking * away both AD and WD. For all reads or if the last condition holds, WD * only will be masked away. */ static void update_pkru_bitmask(struct kvm_mmu *mmu) { unsigned bit; bool wp; mmu->pkru_mask = 0; if (!is_cr4_pke(mmu)) return; wp = is_cr0_wp(mmu); for (bit = 0; bit < ARRAY_SIZE(mmu->permissions); ++bit) { unsigned pfec, pkey_bits; bool check_pkey, check_write, ff, uf, wf, pte_user; pfec = bit << 1; ff = pfec & PFERR_FETCH_MASK; uf = pfec & PFERR_USER_MASK; wf = pfec & PFERR_WRITE_MASK; /* PFEC.RSVD is replaced by ACC_USER_MASK. */ pte_user = pfec & PFERR_RSVD_MASK; /* * Only need to check the access which is not an * instruction fetch and is to a user page. */ check_pkey = (!ff && pte_user); /* * write access is controlled by PKRU if it is a * user access or CR0.WP = 1. */ check_write = check_pkey && wf && (uf || wp); /* PKRU.AD stops both read and write access. */ pkey_bits = !!check_pkey; /* PKRU.WD stops write access. */ pkey_bits |= (!!check_write) << 1; mmu->pkru_mask |= (pkey_bits & 3) << pfec; } } static void reset_guest_paging_metadata(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) { if (!is_cr0_pg(mmu)) return; reset_guest_rsvds_bits_mask(vcpu, mmu); update_permission_bitmask(mmu, false); update_pkru_bitmask(mmu); } static void paging64_init_context(struct kvm_mmu *context) { context->page_fault = paging64_page_fault; context->gva_to_gpa = paging64_gva_to_gpa; context->sync_spte = paging64_sync_spte; } static void paging32_init_context(struct kvm_mmu *context) { context->page_fault = paging32_page_fault; context->gva_to_gpa = paging32_gva_to_gpa; context->sync_spte = paging32_sync_spte; } static union kvm_cpu_role kvm_calc_cpu_role(struct kvm_vcpu *vcpu, const struct kvm_mmu_role_regs *regs) { union kvm_cpu_role role = {0}; role.base.access = ACC_ALL; role.base.smm = is_smm(vcpu); role.base.guest_mode = is_guest_mode(vcpu); role.ext.valid = 1; if (!____is_cr0_pg(regs)) { role.base.direct = 1; return role; } role.base.efer_nx = ____is_efer_nx(regs); role.base.cr0_wp = ____is_cr0_wp(regs); role.base.smep_andnot_wp = ____is_cr4_smep(regs) && !____is_cr0_wp(regs); role.base.smap_andnot_wp = ____is_cr4_smap(regs) && !____is_cr0_wp(regs); role.base.has_4_byte_gpte = !____is_cr4_pae(regs); if (____is_efer_lma(regs)) role.base.level = ____is_cr4_la57(regs) ? PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL; else if (____is_cr4_pae(regs)) role.base.level = PT32E_ROOT_LEVEL; else role.base.level = PT32_ROOT_LEVEL; role.ext.cr4_smep = ____is_cr4_smep(regs); role.ext.cr4_smap = ____is_cr4_smap(regs); role.ext.cr4_pse = ____is_cr4_pse(regs); /* PKEY and LA57 are active iff long mode is active. */ role.ext.cr4_pke = ____is_efer_lma(regs) && ____is_cr4_pke(regs); role.ext.cr4_la57 = ____is_efer_lma(regs) && ____is_cr4_la57(regs); role.ext.efer_lma = ____is_efer_lma(regs); return role; } void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) { const bool cr0_wp = kvm_is_cr0_bit_set(vcpu, X86_CR0_WP); BUILD_BUG_ON((KVM_MMU_CR0_ROLE_BITS & KVM_POSSIBLE_CR0_GUEST_BITS) != X86_CR0_WP); BUILD_BUG_ON((KVM_MMU_CR4_ROLE_BITS & KVM_POSSIBLE_CR4_GUEST_BITS)); if (is_cr0_wp(mmu) == cr0_wp) return; mmu->cpu_role.base.cr0_wp = cr0_wp; reset_guest_paging_metadata(vcpu, mmu); } static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu) { int maxpa; if (vcpu->kvm->arch.vm_type == KVM_X86_TDX_VM) maxpa = cpuid_query_maxguestphyaddr(vcpu); else maxpa = cpuid_maxphyaddr(vcpu); /* tdp_root_level is architecture forced level, use it if nonzero */ if (tdp_root_level) return tdp_root_level; /* Use 5-level TDP if and only if it's useful/necessary. */ if (max_tdp_level == 5 && maxpa <= 48) return 4; return max_tdp_level; } u8 kvm_mmu_get_max_tdp_level(void) { return tdp_root_level ? tdp_root_level : max_tdp_level; } static union kvm_mmu_page_role kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, union kvm_cpu_role cpu_role) { union kvm_mmu_page_role role = {0}; role.access = ACC_ALL; role.cr0_wp = true; role.efer_nx = true; role.smm = cpu_role.base.smm; role.guest_mode = cpu_role.base.guest_mode; role.ad_disabled = !kvm_ad_enabled; role.level = kvm_mmu_get_tdp_level(vcpu); role.direct = true; role.has_4_byte_gpte = false; return role; } static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu, union kvm_cpu_role cpu_role) { struct kvm_mmu *context = &vcpu->arch.root_mmu; union kvm_mmu_page_role root_role = kvm_calc_tdp_mmu_root_page_role(vcpu, cpu_role); if (cpu_role.as_u64 == context->cpu_role.as_u64 && root_role.word == context->root_role.word) return; context->cpu_role.as_u64 = cpu_role.as_u64; context->root_role.word = root_role.word; context->page_fault = kvm_tdp_page_fault; context->sync_spte = NULL; context->get_guest_pgd = get_guest_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; if (!is_cr0_pg(context)) context->gva_to_gpa = nonpaging_gva_to_gpa; else if (is_cr4_pae(context)) context->gva_to_gpa = paging64_gva_to_gpa; else context->gva_to_gpa = paging32_gva_to_gpa; reset_guest_paging_metadata(vcpu, context); reset_tdp_shadow_zero_bits_mask(context); } static void shadow_mmu_init_context(struct kvm_vcpu *vcpu, struct kvm_mmu *context, union kvm_cpu_role cpu_role, union kvm_mmu_page_role root_role) { if (cpu_role.as_u64 == context->cpu_role.as_u64 && root_role.word == context->root_role.word) return; context->cpu_role.as_u64 = cpu_role.as_u64; context->root_role.word = root_role.word; if (!is_cr0_pg(context)) nonpaging_init_context(context); else if (is_cr4_pae(context)) paging64_init_context(context); else paging32_init_context(context); reset_guest_paging_metadata(vcpu, context); reset_shadow_zero_bits_mask(vcpu, context); } static void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, union kvm_cpu_role cpu_role) { struct kvm_mmu *context = &vcpu->arch.root_mmu; union kvm_mmu_page_role root_role; root_role = cpu_role.base; /* KVM uses PAE paging whenever the guest isn't using 64-bit paging. */ root_role.level = max_t(u32, root_role.level, PT32E_ROOT_LEVEL); /* * KVM forces EFER.NX=1 when TDP is disabled, reflect it in the MMU role. * KVM uses NX when TDP is disabled to handle a variety of scenarios, * notably for huge SPTEs if iTLB multi-hit mitigation is enabled and * to generate correct permissions for CR0.WP=0/CR4.SMEP=1/EFER.NX=0. * The iTLB multi-hit workaround can be toggled at any time, so assume * NX can be used by any non-nested shadow MMU to avoid having to reset * MMU contexts. */ root_role.efer_nx = true; shadow_mmu_init_context(vcpu, context, cpu_role, root_role); } void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, unsigned long cr4, u64 efer, gpa_t nested_cr3) { struct kvm_mmu *context = &vcpu->arch.guest_mmu; struct kvm_mmu_role_regs regs = { .cr0 = cr0, .cr4 = cr4 & ~X86_CR4_PKE, .efer = efer, }; union kvm_cpu_role cpu_role = kvm_calc_cpu_role(vcpu, ®s); union kvm_mmu_page_role root_role; /* NPT requires CR0.PG=1. */ WARN_ON_ONCE(cpu_role.base.direct || !cpu_role.base.guest_mode); root_role = cpu_role.base; root_role.level = kvm_mmu_get_tdp_level(vcpu); if (root_role.level == PT64_ROOT_5LEVEL && cpu_role.base.level == PT64_ROOT_4LEVEL) root_role.passthrough = 1; shadow_mmu_init_context(vcpu, context, cpu_role, root_role); kvm_mmu_new_pgd(vcpu, nested_cr3); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_init_shadow_npt_mmu); static union kvm_cpu_role kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, bool execonly, u8 level) { union kvm_cpu_role role = {0}; /* * KVM does not support SMM transfer monitors, and consequently does not * support the "entry to SMM" control either. role.base.smm is always 0. */ WARN_ON_ONCE(is_smm(vcpu)); role.base.level = level; role.base.has_4_byte_gpte = false; role.base.direct = false; role.base.ad_disabled = !accessed_dirty; role.base.guest_mode = true; role.base.access = ACC_ALL; role.ext.word = 0; role.ext.execonly = execonly; role.ext.valid = 1; return role; } void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, int huge_page_level, bool accessed_dirty, gpa_t new_eptp) { struct kvm_mmu *context = &vcpu->arch.guest_mmu; u8 level = vmx_eptp_page_walk_level(new_eptp); union kvm_cpu_role new_mode = kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty, execonly, level); if (new_mode.as_u64 != context->cpu_role.as_u64) { /* EPT, and thus nested EPT, does not consume CR0, CR4, nor EFER. */ context->cpu_role.as_u64 = new_mode.as_u64; context->root_role.word = new_mode.base.word; context->page_fault = ept_page_fault; context->gva_to_gpa = ept_gva_to_gpa; context->sync_spte = ept_sync_spte; update_permission_bitmask(context, true); context->pkru_mask = 0; reset_rsvds_bits_mask_ept(vcpu, context, execonly, huge_page_level); reset_ept_shadow_zero_bits_mask(context, execonly); } kvm_mmu_new_pgd(vcpu, new_eptp); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_init_shadow_ept_mmu); static void init_kvm_softmmu(struct kvm_vcpu *vcpu, union kvm_cpu_role cpu_role) { struct kvm_mmu *context = &vcpu->arch.root_mmu; kvm_init_shadow_mmu(vcpu, cpu_role); context->get_guest_pgd = get_guest_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; } static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu, union kvm_cpu_role new_mode) { struct kvm_mmu *g_context = &vcpu->arch.nested_mmu; if (new_mode.as_u64 == g_context->cpu_role.as_u64) return; g_context->cpu_role.as_u64 = new_mode.as_u64; g_context->get_guest_pgd = get_guest_cr3; g_context->get_pdptr = kvm_pdptr_read; g_context->inject_page_fault = kvm_inject_page_fault; /* * L2 page tables are never shadowed, so there is no need to sync * SPTEs. */ g_context->sync_spte = NULL; /* * Note that arch.mmu->gva_to_gpa translates l2_gpa to l1_gpa using * L1's nested page tables (e.g. EPT12). The nested translation * of l2_gva to l1_gpa is done by arch.nested_mmu.gva_to_gpa using * L2's page tables as the first level of translation and L1's * nested page tables as the second level of translation. Basically * the gva_to_gpa functions between mmu and nested_mmu are swapped. */ if (!is_paging(vcpu)) g_context->gva_to_gpa = nonpaging_gva_to_gpa; else if (is_long_mode(vcpu)) g_context->gva_to_gpa = paging64_gva_to_gpa; else if (is_pae(vcpu)) g_context->gva_to_gpa = paging64_gva_to_gpa; else g_context->gva_to_gpa = paging32_gva_to_gpa; reset_guest_paging_metadata(vcpu, g_context); } void kvm_init_mmu(struct kvm_vcpu *vcpu) { struct kvm_mmu_role_regs regs = vcpu_to_role_regs(vcpu); union kvm_cpu_role cpu_role = kvm_calc_cpu_role(vcpu, ®s); if (mmu_is_nested(vcpu)) init_kvm_nested_mmu(vcpu, cpu_role); else if (tdp_enabled) init_kvm_tdp_mmu(vcpu, cpu_role); else init_kvm_softmmu(vcpu, cpu_role); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_init_mmu); void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) { /* * Invalidate all MMU roles to force them to reinitialize as CPUID * information is factored into reserved bit calculations. * * Correctly handling multiple vCPU models with respect to paging and * physical address properties) in a single VM would require tracking * all relevant CPUID information in kvm_mmu_page_role. That is very * undesirable as it would increase the memory requirements for * gfn_write_track (see struct kvm_mmu_page_role comments). For now * that problem is swept under the rug; KVM's CPUID API is horrific and * it's all but impossible to solve it without introducing a new API. */ vcpu->arch.root_mmu.root_role.invalid = 1; vcpu->arch.guest_mmu.root_role.invalid = 1; vcpu->arch.nested_mmu.root_role.invalid = 1; vcpu->arch.root_mmu.cpu_role.ext.valid = 0; vcpu->arch.guest_mmu.cpu_role.ext.valid = 0; vcpu->arch.nested_mmu.cpu_role.ext.valid = 0; kvm_mmu_reset_context(vcpu); KVM_BUG_ON(!kvm_can_set_cpuid_and_feature_msrs(vcpu), vcpu->kvm); } void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); kvm_init_mmu(vcpu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_reset_context); int kvm_mmu_load(struct kvm_vcpu *vcpu) { int r; r = mmu_topup_memory_caches(vcpu, !vcpu->arch.mmu->root_role.direct); if (r) goto out; r = mmu_alloc_special_roots(vcpu); if (r) goto out; if (vcpu->arch.mmu->root_role.direct) r = mmu_alloc_direct_roots(vcpu); else r = mmu_alloc_shadow_roots(vcpu); if (r) goto out; kvm_mmu_sync_roots(vcpu); kvm_mmu_load_pgd(vcpu); /* * Flush any TLB entries for the new root, the provenance of the root * is unknown. Even if KVM ensures there are no stale TLB entries * for a freed root, in theory another hypervisor could have left * stale entries. Flushing on alloc also allows KVM to skip the TLB * flush when freeing a root (see kvm_tdp_mmu_put_root()). */ kvm_x86_call(flush_tlb_current)(vcpu); out: return r; } void kvm_mmu_unload(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; kvm_mmu_free_roots(kvm, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL); WARN_ON_ONCE(VALID_PAGE(vcpu->arch.root_mmu.root.hpa)); kvm_mmu_free_roots(kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL); WARN_ON_ONCE(VALID_PAGE(vcpu->arch.guest_mmu.root.hpa)); vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); } static bool is_obsolete_root(struct kvm *kvm, hpa_t root_hpa) { struct kvm_mmu_page *sp; if (!VALID_PAGE(root_hpa)) return false; /* * When freeing obsolete roots, treat roots as obsolete if they don't * have an associated shadow page, as it's impossible to determine if * such roots are fresh or stale. This does mean KVM will get false * positives and free roots that don't strictly need to be freed, but * such false positives are relatively rare: * * (a) only PAE paging and nested NPT have roots without shadow pages * (or any shadow paging flavor with a dummy root, see note below) * (b) remote reloads due to a memslot update obsoletes _all_ roots * (c) KVM doesn't track previous roots for PAE paging, and the guest * is unlikely to zap an in-use PGD. * * Note! Dummy roots are unique in that they are obsoleted by memslot * _creation_! See also FNAME(fetch). */ sp = root_to_sp(root_hpa); return !sp || is_obsolete_sp(kvm, sp); } static void __kvm_mmu_free_obsolete_roots(struct kvm *kvm, struct kvm_mmu *mmu) { unsigned long roots_to_free = 0; int i; if (is_obsolete_root(kvm, mmu->root.hpa)) roots_to_free |= KVM_MMU_ROOT_CURRENT; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { if (is_obsolete_root(kvm, mmu->prev_roots[i].hpa)) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); } if (roots_to_free) kvm_mmu_free_roots(kvm, mmu, roots_to_free); } void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu) { __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.root_mmu); __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_free_obsolete_roots); static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, int *bytes) { u64 gentry = 0; int r; /* * Assume that the pte write on a page table of the same type * as the current vcpu paging mode since we update the sptes only * when they have the same mode. */ if (is_pae(vcpu) && *bytes == 4) { /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ *gpa &= ~(gpa_t)7; *bytes = 8; } if (*bytes == 4 || *bytes == 8) { r = kvm_vcpu_read_guest_atomic(vcpu, *gpa, &gentry, *bytes); if (r) gentry = 0; } return gentry; } /* * If we're seeing too many writes to a page, it may no longer be a page table, * or we may be forking, in which case it is better to unmap the page. */ static bool detect_write_flooding(struct kvm_mmu_page *sp) { /* * Skip write-flooding detected for the sp whose level is 1, because * it can become unsync, then the guest page is not write-protected. */ if (sp->role.level == PG_LEVEL_4K) return false; atomic_inc(&sp->write_flooding_count); return atomic_read(&sp->write_flooding_count) >= 3; } /* * Misaligned accesses are too much trouble to fix up; also, they usually * indicate a page is not used as a page table. */ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, int bytes) { unsigned offset, pte_size, misaligned; offset = offset_in_page(gpa); pte_size = sp->role.has_4_byte_gpte ? 4 : 8; /* * Sometimes, the OS only writes the last one bytes to update status * bits, for example, in linux, andb instruction is used in clear_bit(). */ if (!(offset & (pte_size - 1)) && bytes == 1) return false; misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); misaligned |= bytes < 4; return misaligned; } static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) { unsigned page_offset, quadrant; u64 *spte; int level; page_offset = offset_in_page(gpa); level = sp->role.level; *nspte = 1; if (sp->role.has_4_byte_gpte) { page_offset <<= 1; /* 32->64 */ /* * A 32-bit pde maps 4MB while the shadow pdes map * only 2MB. So we need to double the offset again * and zap two pdes instead of one. */ if (level == PT32_ROOT_LEVEL) { page_offset &= ~7; /* kill rounding error */ page_offset <<= 1; *nspte = 2; } quadrant = page_offset >> PAGE_SHIFT; page_offset &= ~PAGE_MASK; if (quadrant != sp->role.quadrant) return NULL; } spte = &sp->spt[page_offset / sizeof(*spte)]; return spte; } void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes) { gfn_t gfn = gpa >> PAGE_SHIFT; struct kvm_mmu_page *sp; LIST_HEAD(invalid_list); u64 entry, gentry, *spte; int npte; bool flush = false; /* * When emulating guest writes, ensure the written value is visible to * any task that is handling page faults before checking whether or not * KVM is shadowing a guest PTE. This ensures either KVM will create * the correct SPTE in the page fault handler, or this task will see * a non-zero indirect_shadow_pages. Pairs with the smp_mb() in * account_shadowed(). */ smp_mb(); if (!vcpu->kvm->arch.indirect_shadow_pages) return; write_lock(&vcpu->kvm->mmu_lock); gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes); ++vcpu->kvm->stat.mmu_pte_write; for_each_gfn_valid_sp_with_gptes(vcpu->kvm, sp, gfn) { if (detect_write_misaligned(sp, gpa, bytes) || detect_write_flooding(sp)) { kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); ++vcpu->kvm->stat.mmu_flooded; continue; } spte = get_written_sptes(sp, gpa, &npte); if (!spte) continue; while (npte--) { entry = *spte; mmu_page_zap_pte(vcpu->kvm, sp, spte, NULL); if (gentry && sp->role.level != PG_LEVEL_4K) ++vcpu->kvm->stat.mmu_pde_zapped; if (is_shadow_present_pte(entry)) flush = true; ++spte; } } kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, flush); write_unlock(&vcpu->kvm->mmu_lock); } static bool is_write_to_guest_page_table(u64 error_code) { const u64 mask = PFERR_GUEST_PAGE_MASK | PFERR_WRITE_MASK | PFERR_PRESENT_MASK; return (error_code & mask) == mask; } static int kvm_mmu_write_protect_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, int *emulation_type) { bool direct = vcpu->arch.mmu->root_role.direct; /* * Do not try to unprotect and retry if the vCPU re-faulted on the same * RIP with the same address that was previously unprotected, as doing * so will likely put the vCPU into an infinite. E.g. if the vCPU uses * a non-page-table modifying instruction on the PDE that points to the * instruction, then unprotecting the gfn will unmap the instruction's * code, i.e. make it impossible for the instruction to ever complete. */ if (vcpu->arch.last_retry_eip == kvm_rip_read(vcpu) && vcpu->arch.last_retry_addr == cr2_or_gpa) return RET_PF_EMULATE; /* * Reset the unprotect+retry values that guard against infinite loops. * The values will be refreshed if KVM explicitly unprotects a gfn and * retries, in all other cases it's safe to retry in the future even if * the next page fault happens on the same RIP+address. */ vcpu->arch.last_retry_eip = 0; vcpu->arch.last_retry_addr = 0; /* * It should be impossible to reach this point with an MMIO cache hit, * as RET_PF_WRITE_PROTECTED is returned if and only if there's a valid, * writable memslot, and creating a memslot should invalidate the MMIO * cache by way of changing the memslot generation. WARN and disallow * retry if MMIO is detected, as retrying MMIO emulation is pointless * and could put the vCPU into an infinite loop because the processor * will keep faulting on the non-existent MMIO address. */ if (WARN_ON_ONCE(mmio_info_in_cache(vcpu, cr2_or_gpa, direct))) return RET_PF_EMULATE; /* * Before emulating the instruction, check to see if the access was due * to a read-only violation while the CPU was walking non-nested NPT * page tables, i.e. for a direct MMU, for _guest_ page tables in L1. * If L1 is sharing (a subset of) its page tables with L2, e.g. by * having nCR3 share lower level page tables with hCR3, then when KVM * (L0) write-protects the nested NPTs, i.e. npt12 entries, KVM is also * unknowingly write-protecting L1's guest page tables, which KVM isn't * shadowing. * * Because the CPU (by default) walks NPT page tables using a write * access (to ensure the CPU can do A/D updates), page walks in L1 can * trigger write faults for the above case even when L1 isn't modifying * PTEs. As a result, KVM will unnecessarily emulate (or at least, try * to emulate) an excessive number of L1 instructions; because L1's MMU * isn't shadowed by KVM, there is no need to write-protect L1's gPTEs * and thus no need to emulate in order to guarantee forward progress. * * Try to unprotect the gfn, i.e. zap any shadow pages, so that L1 can * proceed without triggering emulation. If one or more shadow pages * was zapped, skip emulation and resume L1 to let it natively execute * the instruction. If no shadow pages were zapped, then the write- * fault is due to something else entirely, i.e. KVM needs to emulate, * as resuming the guest will put it into an infinite loop. * * Note, this code also applies to Intel CPUs, even though it is *very* * unlikely that an L1 will share its page tables (IA32/PAE/paging64 * format) with L2's page tables (EPT format). * * For indirect MMUs, i.e. if KVM is shadowing the current MMU, try to * unprotect the gfn and retry if an event is awaiting reinjection. If * KVM emulates multiple instructions before completing event injection, * the event could be delayed beyond what is architecturally allowed, * e.g. KVM could inject an IRQ after the TPR has been raised. */ if (((direct && is_write_to_guest_page_table(error_code)) || (!direct && kvm_event_needs_reinjection(vcpu))) && kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa)) return RET_PF_RETRY; /* * The gfn is write-protected, but if KVM detects its emulating an * instruction that is unlikely to be used to modify page tables, or if * emulation fails, KVM can try to unprotect the gfn and let the CPU * re-execute the instruction that caused the page fault. Do not allow * retrying an instruction from a nested guest as KVM is only explicitly * shadowing L1's page tables, i.e. unprotecting something for L1 isn't * going to magically fix whatever issue caused L2 to fail. */ if (!is_guest_mode(vcpu)) *emulation_type |= EMULTYPE_ALLOW_RETRY_PF; return RET_PF_EMULATE; } int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { int r, emulation_type = EMULTYPE_PF; bool direct = vcpu->arch.mmu->root_role.direct; if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) return RET_PF_RETRY; /* * Except for reserved faults (emulated MMIO is shared-only), set the * PFERR_PRIVATE_ACCESS flag for software-protected VMs based on the gfn's * current attributes, which are the source of truth for such VMs. Note, * this wrong for nested MMUs as the GPA is an L2 GPA, but KVM doesn't * currently supported nested virtualization (among many other things) * for software-protected VMs. */ if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && !(error_code & PFERR_RSVD_MASK) && vcpu->kvm->arch.vm_type == KVM_X86_SW_PROTECTED_VM && kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(cr2_or_gpa))) error_code |= PFERR_PRIVATE_ACCESS; r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { if (WARN_ON_ONCE(error_code & PFERR_PRIVATE_ACCESS)) return -EFAULT; r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); if (r == RET_PF_EMULATE) goto emulate; } if (r == RET_PF_INVALID) { vcpu->stat.pf_taken++; r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, error_code, false, &emulation_type, NULL); if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm)) return -EIO; } if (r < 0) return r; if (r == RET_PF_WRITE_PROTECTED) r = kvm_mmu_write_protect_fault(vcpu, cr2_or_gpa, error_code, &emulation_type); if (r == RET_PF_FIXED) vcpu->stat.pf_fixed++; else if (r == RET_PF_EMULATE) vcpu->stat.pf_emulate++; else if (r == RET_PF_SPURIOUS) vcpu->stat.pf_spurious++; /* * None of handle_mmio_page_fault(), kvm_mmu_do_page_fault(), or * kvm_mmu_write_protect_fault() return RET_PF_CONTINUE. * kvm_mmu_do_page_fault() only uses RET_PF_CONTINUE internally to * indicate continuing the page fault handling until to the final * page table mapping phase. */ WARN_ON_ONCE(r == RET_PF_CONTINUE); if (r != RET_PF_EMULATE) return r; emulate: return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_page_fault); void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg) { u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; int root_level, leaf, level; leaf = get_sptes_lockless(vcpu, gpa, sptes, &root_level); if (unlikely(leaf < 0)) return; pr_err("%s %llx", msg, gpa); for (level = root_level; level >= leaf; level--) pr_cont(", spte[%d] = 0x%llx", level, sptes[level]); pr_cont("\n"); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_print_sptes); static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, u64 addr, hpa_t root_hpa) { struct kvm_shadow_walk_iterator iterator; vcpu_clear_mmio_info(vcpu, addr); /* * Walking and synchronizing SPTEs both assume they are operating in * the context of the current MMU, and would need to be reworked if * this is ever used to sync the guest_mmu, e.g. to emulate INVEPT. */ if (WARN_ON_ONCE(mmu != vcpu->arch.mmu)) return; if (!VALID_PAGE(root_hpa)) return; write_lock(&vcpu->kvm->mmu_lock); for_each_shadow_entry_using_root(vcpu, root_hpa, addr, iterator) { struct kvm_mmu_page *sp = sptep_to_sp(iterator.sptep); if (sp->unsync) { int ret = kvm_sync_spte(vcpu, sp, iterator.index); if (ret < 0) mmu_page_zap_pte(vcpu->kvm, sp, iterator.sptep, NULL); if (ret) kvm_flush_remote_tlbs_sptep(vcpu->kvm, iterator.sptep); } if (!sp->unsync_children) break; } write_unlock(&vcpu->kvm->mmu_lock); } void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, u64 addr, unsigned long roots) { int i; WARN_ON_ONCE(roots & ~KVM_MMU_ROOTS_ALL); /* It's actually a GPA for vcpu->arch.guest_mmu. */ if (mmu != &vcpu->arch.guest_mmu) { /* INVLPG on a non-canonical address is a NOP according to the SDM. */ if (is_noncanonical_invlpg_address(addr, vcpu)) return; kvm_x86_call(flush_tlb_gva)(vcpu, addr); } if (!mmu->sync_spte) return; if (roots & KVM_MMU_ROOT_CURRENT) __kvm_mmu_invalidate_addr(vcpu, mmu, addr, mmu->root.hpa); for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { if (roots & KVM_MMU_ROOT_PREVIOUS(i)) __kvm_mmu_invalidate_addr(vcpu, mmu, addr, mmu->prev_roots[i].hpa); } } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_invalidate_addr); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { /* * INVLPG is required to invalidate any global mappings for the VA, * irrespective of PCID. Blindly sync all roots as it would take * roughly the same amount of work/time to determine whether any of the * previous roots have a global mapping. * * Mappings not reachable via the current or previous cached roots will * be synced when switching to that new cr3, so nothing needs to be * done here for them. */ kvm_mmu_invalidate_addr(vcpu, vcpu->arch.walk_mmu, gva, KVM_MMU_ROOTS_ALL); ++vcpu->stat.invlpg; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_invlpg); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) { struct kvm_mmu *mmu = vcpu->arch.mmu; unsigned long roots = 0; uint i; if (pcid == kvm_get_active_pcid(vcpu)) roots |= KVM_MMU_ROOT_CURRENT; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { if (VALID_PAGE(mmu->prev_roots[i].hpa) && pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd)) roots |= KVM_MMU_ROOT_PREVIOUS(i); } if (roots) kvm_mmu_invalidate_addr(vcpu, mmu, gva, roots); ++vcpu->stat.invlpg; /* * Mappings not reachable via the current cr3 or the prev_roots will be * synced when switching to that cr3, so nothing needs to be done here * for them. */ } void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, int tdp_max_root_level, int tdp_huge_page_level) { tdp_enabled = enable_tdp; tdp_root_level = tdp_forced_root_level; max_tdp_level = tdp_max_root_level; #ifdef CONFIG_X86_64 tdp_mmu_enabled = tdp_mmu_allowed && tdp_enabled; #endif /* * max_huge_page_level reflects KVM's MMU capabilities irrespective * of kernel support, e.g. KVM may be capable of using 1GB pages when * the kernel is not. But, KVM never creates a page size greater than * what is used by the kernel for any given HVA, i.e. the kernel's * capabilities are ultimately consulted by kvm_mmu_hugepage_adjust(). */ if (tdp_enabled) max_huge_page_level = tdp_huge_page_level; else if (boot_cpu_has(X86_FEATURE_GBPAGES)) max_huge_page_level = PG_LEVEL_1G; else max_huge_page_level = PG_LEVEL_2M; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_configure_mmu); static void free_mmu_pages(struct kvm_mmu *mmu) { if (!tdp_enabled && mmu->pae_root) set_memory_encrypted((unsigned long)mmu->pae_root, 1); free_page((unsigned long)mmu->pae_root); free_page((unsigned long)mmu->pml4_root); free_page((unsigned long)mmu->pml5_root); } static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) { struct page *page; int i; mmu->root.hpa = INVALID_PAGE; mmu->root.pgd = 0; mmu->mirror_root_hpa = INVALID_PAGE; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; /* vcpu->arch.guest_mmu isn't used when !tdp_enabled. */ if (!tdp_enabled && mmu == &vcpu->arch.guest_mmu) return 0; /* * When using PAE paging, the four PDPTEs are treated as 'root' pages, * while the PDP table is a per-vCPU construct that's allocated at MMU * creation. When emulating 32-bit mode, cr3 is only 32 bits even on * x86_64. Therefore we need to allocate the PDP table in the first * 4GB of memory, which happens to fit the DMA32 zone. TDP paging * generally doesn't use PAE paging and can skip allocating the PDP * table. The main exception, handled here, is SVM's 32-bit NPT. The * other exception is for shadowing L1's 32-bit or PAE NPT on 64-bit * KVM; that horror is handled on-demand by mmu_alloc_special_roots(). */ if (tdp_enabled && kvm_mmu_get_tdp_level(vcpu) > PT32E_ROOT_LEVEL) return 0; page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_DMA32); if (!page) return -ENOMEM; mmu->pae_root = page_address(page); /* * CR3 is only 32 bits when PAE paging is used, thus it's impossible to * get the CPU to treat the PDPTEs as encrypted. Decrypt the page so * that KVM's writes and the CPU's reads get along. Note, this is * only necessary when using shadow paging, as 64-bit NPT can get at * the C-bit even when shadowing 32-bit NPT, and SME isn't supported * by 32-bit kernels (when KVM itself uses 32-bit NPT). */ if (!tdp_enabled) set_memory_decrypted((unsigned long)mmu->pae_root, 1); else WARN_ON_ONCE(shadow_me_value); for (i = 0; i < 4; ++i) mmu->pae_root[i] = INVALID_PAE_ROOT; return 0; } int kvm_mmu_create(struct kvm_vcpu *vcpu) { int ret; vcpu->arch.mmu_pte_list_desc_cache.kmem_cache = pte_list_desc_cache; vcpu->arch.mmu_pte_list_desc_cache.gfp_zero = __GFP_ZERO; vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache; vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO; vcpu->arch.mmu_shadow_page_cache.init_value = SHADOW_NONPRESENT_VALUE; if (!vcpu->arch.mmu_shadow_page_cache.init_value) vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO; vcpu->arch.mmu = &vcpu->arch.root_mmu; vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; ret = __kvm_mmu_create(vcpu, &vcpu->arch.guest_mmu); if (ret) return ret; ret = __kvm_mmu_create(vcpu, &vcpu->arch.root_mmu); if (ret) goto fail_allocate_root; return ret; fail_allocate_root: free_mmu_pages(&vcpu->arch.guest_mmu); return ret; } #define BATCH_ZAP_PAGES 10 static void kvm_zap_obsolete_pages(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; int nr_zapped, batch = 0; LIST_HEAD(invalid_list); bool unstable; lockdep_assert_held(&kvm->slots_lock); restart: list_for_each_entry_safe_reverse(sp, node, &kvm->arch.active_mmu_pages, link) { /* * No obsolete valid page exists before a newly created page * since active_mmu_pages is a FIFO list. */ if (!is_obsolete_sp(kvm, sp)) break; /* * Invalid pages should never land back on the list of active * pages. Skip the bogus page, otherwise we'll get stuck in an * infinite loop if the page gets put back on the list (again). */ if (WARN_ON_ONCE(sp->role.invalid)) continue; /* * No need to flush the TLB since we're only zapping shadow * pages with an obsolete generation number and all vCPUS have * loaded a new root, i.e. the shadow pages being zapped cannot * be in active use by the guest. */ if (batch >= BATCH_ZAP_PAGES && cond_resched_rwlock_write(&kvm->mmu_lock)) { batch = 0; goto restart; } unstable = __kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &nr_zapped); batch += nr_zapped; if (unstable) goto restart; } /* * Kick all vCPUs (via remote TLB flush) before freeing the page tables * to ensure KVM is not in the middle of a lockless shadow page table * walk, which may reference the pages. The remote TLB flush itself is * not required and is simply a convenient way to kick vCPUs as needed. * KVM performs a local TLB flush when allocating a new root (see * kvm_mmu_load()), and the reload in the caller ensure no vCPUs are * running with an obsolete MMU. */ kvm_mmu_commit_zap_page(kvm, &invalid_list); } /* * Fast invalidate all shadow pages and use lock-break technique * to zap obsolete pages. * * It's required when memslot is being deleted or VM is being * destroyed, in these cases, we should ensure that KVM MMU does * not use any resource of the being-deleted slot or all slots * after calling the function. */ static void kvm_mmu_zap_all_fast(struct kvm *kvm) { lockdep_assert_held(&kvm->slots_lock); write_lock(&kvm->mmu_lock); trace_kvm_mmu_zap_all_fast(kvm); /* * Toggle mmu_valid_gen between '0' and '1'. Because slots_lock is * held for the entire duration of zapping obsolete pages, it's * impossible for there to be multiple invalid generations associated * with *valid* shadow pages at any given time, i.e. there is exactly * one valid generation and (at most) one invalid generation. */ kvm->arch.mmu_valid_gen = kvm->arch.mmu_valid_gen ? 0 : 1; /* * In order to ensure all vCPUs drop their soon-to-be invalid roots, * invalidating TDP MMU roots must be done while holding mmu_lock for * write and in the same critical section as making the reload request, * e.g. before kvm_zap_obsolete_pages() could drop mmu_lock and yield. */ if (tdp_mmu_enabled) { /* * External page tables don't support fast zapping, therefore * their mirrors must be invalidated separately by the caller. */ kvm_tdp_mmu_invalidate_roots(kvm, KVM_DIRECT_ROOTS); } /* * Notify all vcpus to reload its shadow page table and flush TLB. * Then all vcpus will switch to new shadow page table with the new * mmu_valid_gen. * * Note: we need to do this under the protection of mmu_lock, * otherwise, vcpu would purge shadow page but miss tlb flush. */ kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_FREE_OBSOLETE_ROOTS); kvm_zap_obsolete_pages(kvm); write_unlock(&kvm->mmu_lock); /* * Zap the invalidated TDP MMU roots, all SPTEs must be dropped before * returning to the caller, e.g. if the zap is in response to a memslot * deletion, mmu_notifier callbacks will be unable to reach the SPTEs * associated with the deleted memslot once the update completes, and * Deferring the zap until the final reference to the root is put would * lead to use-after-free. */ if (tdp_mmu_enabled) kvm_tdp_mmu_zap_invalidated_roots(kvm, true); } int kvm_mmu_init_vm(struct kvm *kvm) { int r, i; kvm->arch.shadow_mmio_value = shadow_mmio_value; INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); for (i = 0; i < KVM_NR_MMU_TYPES; ++i) INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages[i].pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); if (tdp_mmu_enabled) { kvm_mmu_init_tdp_mmu(kvm); } else { r = kvm_mmu_alloc_page_hash(kvm); if (r) return r; } kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache; kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO; kvm->arch.split_shadow_page_cache.gfp_zero = __GFP_ZERO; kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache; kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO; return 0; } static void mmu_free_vm_memory_caches(struct kvm *kvm) { kvm_mmu_free_memory_cache(&kvm->arch.split_desc_cache); kvm_mmu_free_memory_cache(&kvm->arch.split_page_header_cache); kvm_mmu_free_memory_cache(&kvm->arch.split_shadow_page_cache); } void kvm_mmu_uninit_vm(struct kvm *kvm) { kvfree(kvm->arch.mmu_page_hash); if (tdp_mmu_enabled) kvm_mmu_uninit_tdp_mmu(kvm); mmu_free_vm_memory_caches(kvm); } static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { const struct kvm_memory_slot *memslot; struct kvm_memslots *slots; struct kvm_memslot_iter iter; bool flush = false; gfn_t start, end; int i; if (!kvm_memslots_have_rmaps(kvm)) return flush; for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) { memslot = iter.slot; start = max(gfn_start, memslot->base_gfn); end = min(gfn_end, memslot->base_gfn + memslot->npages); if (WARN_ON_ONCE(start >= end)) continue; flush = __kvm_rmap_zap_gfn_range(kvm, memslot, start, end, true, flush); } } return flush; } /* * Invalidate (zap) SPTEs that cover GFNs from gfn_start and up to gfn_end * (not including it) */ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { bool flush; if (WARN_ON_ONCE(gfn_end <= gfn_start)) return; write_lock(&kvm->mmu_lock); kvm_mmu_invalidate_begin(kvm); kvm_mmu_invalidate_range_add(kvm, gfn_start, gfn_end); flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); if (tdp_mmu_enabled) flush = kvm_tdp_mmu_zap_leafs(kvm, gfn_start, gfn_end, flush); if (flush) kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start); kvm_mmu_invalidate_end(kvm); write_unlock(&kvm->mmu_lock); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_zap_gfn_range); static bool slot_rmap_write_protect(struct kvm *kvm, struct kvm_rmap_head *rmap_head, const struct kvm_memory_slot *slot) { return rmap_write_protect(rmap_head, false); } void kvm_mmu_slot_remove_write_access(struct kvm *kvm, const struct kvm_memory_slot *memslot, int start_level) { if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); walk_slot_rmaps(kvm, memslot, slot_rmap_write_protect, start_level, KVM_MAX_HUGEPAGE_LEVEL, false); write_unlock(&kvm->mmu_lock); } if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level); read_unlock(&kvm->mmu_lock); } } static inline bool need_topup(struct kvm_mmu_memory_cache *cache, int min) { return kvm_mmu_memory_cache_nr_free_objects(cache) < min; } static bool need_topup_split_caches_or_resched(struct kvm *kvm) { if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) return true; /* * In the worst case, SPLIT_DESC_CACHE_MIN_NR_OBJECTS descriptors are needed * to split a single huge page. Calculating how many are actually needed * is possible but not worth the complexity. */ return need_topup(&kvm->arch.split_desc_cache, SPLIT_DESC_CACHE_MIN_NR_OBJECTS) || need_topup(&kvm->arch.split_page_header_cache, 1) || need_topup(&kvm->arch.split_shadow_page_cache, 1); } static int topup_split_caches(struct kvm *kvm) { /* * Allocating rmap list entries when splitting huge pages for nested * MMUs is uncommon as KVM needs to use a list if and only if there is * more than one rmap entry for a gfn, i.e. requires an L1 gfn to be * aliased by multiple L2 gfns and/or from multiple nested roots with * different roles. Aliasing gfns when using TDP is atypical for VMMs; * a few gfns are often aliased during boot, e.g. when remapping BIOS, * but aliasing rarely occurs post-boot or for many gfns. If there is * only one rmap entry, rmap->val points directly at that one entry and * doesn't need to allocate a list. Buffer the cache by the default * capacity so that KVM doesn't have to drop mmu_lock to topup if KVM * encounters an aliased gfn or two. */ const int capacity = SPLIT_DESC_CACHE_MIN_NR_OBJECTS + KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE; int r; lockdep_assert_held(&kvm->slots_lock); r = __kvm_mmu_topup_memory_cache(&kvm->arch.split_desc_cache, capacity, SPLIT_DESC_CACHE_MIN_NR_OBJECTS); if (r) return r; r = kvm_mmu_topup_memory_cache(&kvm->arch.split_page_header_cache, 1); if (r) return r; return kvm_mmu_topup_memory_cache(&kvm->arch.split_shadow_page_cache, 1); } static struct kvm_mmu_page *shadow_mmu_get_sp_for_split(struct kvm *kvm, u64 *huge_sptep) { struct kvm_mmu_page *huge_sp = sptep_to_sp(huge_sptep); struct shadow_page_caches caches = {}; union kvm_mmu_page_role role; unsigned int access; gfn_t gfn; gfn = kvm_mmu_page_get_gfn(huge_sp, spte_index(huge_sptep)); access = kvm_mmu_page_get_access(huge_sp, spte_index(huge_sptep)); /* * Note, huge page splitting always uses direct shadow pages, regardless * of whether the huge page itself is mapped by a direct or indirect * shadow page, since the huge page region itself is being directly * mapped with smaller pages. */ role = kvm_mmu_child_role(huge_sptep, /*direct=*/true, access); /* Direct SPs do not require a shadowed_info_cache. */ caches.page_header_cache = &kvm->arch.split_page_header_cache; caches.shadow_page_cache = &kvm->arch.split_shadow_page_cache; /* Safe to pass NULL for vCPU since requesting a direct SP. */ return __kvm_mmu_get_shadow_page(kvm, NULL, &caches, gfn, role); } static void shadow_mmu_split_huge_page(struct kvm *kvm, const struct kvm_memory_slot *slot, u64 *huge_sptep) { struct kvm_mmu_memory_cache *cache = &kvm->arch.split_desc_cache; u64 huge_spte = READ_ONCE(*huge_sptep); struct kvm_mmu_page *sp; bool flush = false; u64 *sptep, spte; gfn_t gfn; int index; sp = shadow_mmu_get_sp_for_split(kvm, huge_sptep); for (index = 0; index < SPTE_ENT_PER_PAGE; index++) { sptep = &sp->spt[index]; gfn = kvm_mmu_page_get_gfn(sp, index); /* * The SP may already have populated SPTEs, e.g. if this huge * page is aliased by multiple sptes with the same access * permissions. These entries are guaranteed to map the same * gfn-to-pfn translation since the SP is direct, so no need to * modify them. * * However, if a given SPTE points to a lower level page table, * that lower level page table may only be partially populated. * Installing such SPTEs would effectively unmap a potion of the * huge page. Unmapping guest memory always requires a TLB flush * since a subsequent operation on the unmapped regions would * fail to detect the need to flush. */ if (is_shadow_present_pte(*sptep)) { flush |= !is_last_spte(*sptep, sp->role.level); continue; } spte = make_small_spte(kvm, huge_spte, sp->role, index); mmu_spte_set(sptep, spte); __rmap_add(kvm, cache, slot, sptep, gfn, sp->role.access); } __link_shadow_page(kvm, cache, huge_sptep, sp, flush); } static int shadow_mmu_try_split_huge_page(struct kvm *kvm, const struct kvm_memory_slot *slot, u64 *huge_sptep) { struct kvm_mmu_page *huge_sp = sptep_to_sp(huge_sptep); int level, r = 0; gfn_t gfn; u64 spte; /* Grab information for the tracepoint before dropping the MMU lock. */ gfn = kvm_mmu_page_get_gfn(huge_sp, spte_index(huge_sptep)); level = huge_sp->role.level; spte = *huge_sptep; if (kvm_mmu_available_pages(kvm) <= KVM_MIN_FREE_MMU_PAGES) { r = -ENOSPC; goto out; } if (need_topup_split_caches_or_resched(kvm)) { write_unlock(&kvm->mmu_lock); cond_resched(); /* * If the topup succeeds, return -EAGAIN to indicate that the * rmap iterator should be restarted because the MMU lock was * dropped. */ r = topup_split_caches(kvm) ?: -EAGAIN; write_lock(&kvm->mmu_lock); goto out; } shadow_mmu_split_huge_page(kvm, slot, huge_sptep); out: trace_kvm_mmu_split_huge_page(gfn, spte, level, r); return r; } static bool shadow_mmu_try_split_huge_pages(struct kvm *kvm, struct kvm_rmap_head *rmap_head, const struct kvm_memory_slot *slot) { struct rmap_iterator iter; struct kvm_mmu_page *sp; u64 *huge_sptep; int r; restart: for_each_rmap_spte(rmap_head, &iter, huge_sptep) { sp = sptep_to_sp(huge_sptep); /* TDP MMU is enabled, so rmap only contains nested MMU SPs. */ if (WARN_ON_ONCE(!sp->role.guest_mode)) continue; /* The rmaps should never contain non-leaf SPTEs. */ if (WARN_ON_ONCE(!is_large_pte(*huge_sptep))) continue; /* SPs with level >PG_LEVEL_4K should never by unsync. */ if (WARN_ON_ONCE(sp->unsync)) continue; /* Don't bother splitting huge pages on invalid SPs. */ if (sp->role.invalid) continue; r = shadow_mmu_try_split_huge_page(kvm, slot, huge_sptep); /* * The split succeeded or needs to be retried because the MMU * lock was dropped. Either way, restart the iterator to get it * back into a consistent state. */ if (!r || r == -EAGAIN) goto restart; /* The split failed and shouldn't be retried (e.g. -ENOMEM). */ break; } return false; } static void kvm_shadow_mmu_try_split_huge_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t start, gfn_t end, int target_level) { int level; /* * Split huge pages starting with KVM_MAX_HUGEPAGE_LEVEL and working * down to the target level. This ensures pages are recursively split * all the way to the target level. There's no need to split pages * already at the target level. */ for (level = KVM_MAX_HUGEPAGE_LEVEL; level > target_level; level--) __walk_slot_rmaps(kvm, slot, shadow_mmu_try_split_huge_pages, level, level, start, end - 1, true, true, false); } /* Must be called with the mmu_lock held in write-mode. */ void kvm_mmu_try_split_huge_pages(struct kvm *kvm, const struct kvm_memory_slot *memslot, u64 start, u64 end, int target_level) { if (!tdp_mmu_enabled) return; if (kvm_memslots_have_rmaps(kvm)) kvm_shadow_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level); kvm_tdp_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level, false); /* * A TLB flush is unnecessary at this point for the same reasons as in * kvm_mmu_slot_try_split_huge_pages(). */ } void kvm_mmu_slot_try_split_huge_pages(struct kvm *kvm, const struct kvm_memory_slot *memslot, int target_level) { u64 start = memslot->base_gfn; u64 end = start + memslot->npages; if (!tdp_mmu_enabled) return; if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); kvm_shadow_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level); write_unlock(&kvm->mmu_lock); } read_lock(&kvm->mmu_lock); kvm_tdp_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level, true); read_unlock(&kvm->mmu_lock); /* * No TLB flush is necessary here. KVM will flush TLBs after * write-protecting and/or clearing dirty on the newly split SPTEs to * ensure that guest writes are reflected in the dirty log before the * ioctl to enable dirty logging on this memslot completes. Since the * split SPTEs retain the write and dirty bits of the huge SPTE, it is * safe for KVM to decide if a TLB flush is necessary based on the split * SPTEs. */ } static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, struct kvm_rmap_head *rmap_head, const struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; int need_tlb_flush = 0; struct kvm_mmu_page *sp; restart: for_each_rmap_spte(rmap_head, &iter, sptep) { sp = sptep_to_sp(sptep); /* * We cannot do huge page mapping for indirect shadow pages, * which are found on the last rmap (level = 1) when not using * tdp; such shadow pages are synced with the page table in * the guest, and the guest page table is using 4K page size * mapping if the indirect sp has level = 1. */ if (sp->role.direct && sp->role.level < kvm_mmu_max_mapping_level(kvm, NULL, slot, sp->gfn)) { kvm_zap_one_rmap_spte(kvm, rmap_head, sptep); if (kvm_available_flush_remote_tlbs_range()) kvm_flush_remote_tlbs_sptep(kvm, sptep); else need_tlb_flush = 1; goto restart; } } return need_tlb_flush; } static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *slot) { /* * Note, use KVM_MAX_HUGEPAGE_LEVEL - 1 since there's no need to zap * pages that are already mapped at the maximum hugepage level. */ if (walk_slot_rmaps(kvm, slot, kvm_mmu_zap_collapsible_spte, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL - 1, true)) kvm_flush_remote_tlbs_memslot(kvm, slot); } void kvm_mmu_recover_huge_pages(struct kvm *kvm, const struct kvm_memory_slot *slot) { if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); kvm_rmap_zap_collapsible_sptes(kvm, slot); write_unlock(&kvm->mmu_lock); } if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); kvm_tdp_mmu_recover_huge_pages(kvm, slot); read_unlock(&kvm->mmu_lock); } } void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, const struct kvm_memory_slot *memslot) { if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); /* * Clear dirty bits only on 4k SPTEs since the legacy MMU only * support dirty logging at a 4k granularity. */ walk_slot_rmaps_4k(kvm, memslot, __rmap_clear_dirty, false); write_unlock(&kvm->mmu_lock); } if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); kvm_tdp_mmu_clear_dirty_slot(kvm, memslot); read_unlock(&kvm->mmu_lock); } /* * The caller will flush the TLBs after this function returns. * * It's also safe to flush TLBs out of mmu lock here as currently this * function is only used for dirty logging, in which case flushing TLB * out of mmu lock also guarantees no dirty pages will be lost in * dirty_bitmap. */ } static void kvm_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; LIST_HEAD(invalid_list); int ign; write_lock(&kvm->mmu_lock); restart: list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) { if (WARN_ON_ONCE(sp->role.invalid)) continue; if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign)) goto restart; if (cond_resched_rwlock_write(&kvm->mmu_lock)) goto restart; } kvm_mmu_commit_zap_page(kvm, &invalid_list); if (tdp_mmu_enabled) kvm_tdp_mmu_zap_all(kvm); write_unlock(&kvm->mmu_lock); } void kvm_arch_flush_shadow_all(struct kvm *kvm) { kvm_mmu_zap_all(kvm); } static void kvm_mmu_zap_memslot_pages_and_flush(struct kvm *kvm, struct kvm_memory_slot *slot, bool flush) { LIST_HEAD(invalid_list); unsigned long i; if (list_empty(&kvm->arch.active_mmu_pages)) goto out_flush; /* * Since accounting information is stored in struct kvm_arch_memory_slot, * all MMU pages that are shadowing guest PTEs must be zapped before the * memslot is deleted, as freeing such pages after the memslot is freed * will result in use-after-free, e.g. in unaccount_shadowed(). */ for (i = 0; i < slot->npages; i++) { struct kvm_mmu_page *sp; gfn_t gfn = slot->base_gfn + i; for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); flush = false; cond_resched_rwlock_write(&kvm->mmu_lock); } } out_flush: kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); } static void kvm_mmu_zap_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { struct kvm_gfn_range range = { .slot = slot, .start = slot->base_gfn, .end = slot->base_gfn + slot->npages, .may_block = true, .attr_filter = KVM_FILTER_PRIVATE | KVM_FILTER_SHARED, }; bool flush; write_lock(&kvm->mmu_lock); flush = kvm_unmap_gfn_range(kvm, &range); kvm_mmu_zap_memslot_pages_and_flush(kvm, slot, flush); write_unlock(&kvm->mmu_lock); } static inline bool kvm_memslot_flush_zap_all(struct kvm *kvm) { return kvm->arch.vm_type == KVM_X86_DEFAULT_VM && kvm_check_has_quirk(kvm, KVM_X86_QUIRK_SLOT_ZAP_ALL); } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { if (kvm_memslot_flush_zap_all(kvm)) kvm_mmu_zap_all_fast(kvm); else kvm_mmu_zap_memslot(kvm, slot); } void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) { WARN_ON_ONCE(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); if (!enable_mmio_caching) return; gen &= MMIO_SPTE_GEN_MASK; /* * Generation numbers are incremented in multiples of the number of * address spaces in order to provide unique generations across all * address spaces. Strip what is effectively the address space * modifier prior to checking for a wrap of the MMIO generation so * that a wrap in any address space is detected. */ gen &= ~((u64)kvm_arch_nr_memslot_as_ids(kvm) - 1); /* * The very rare case: if the MMIO generation number has wrapped, * zap all shadow pages. */ if (unlikely(gen == 0)) { kvm_debug_ratelimited("zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_zap_all_fast(kvm); } } static void mmu_destroy_caches(void) { kmem_cache_destroy(pte_list_desc_cache); kmem_cache_destroy(mmu_page_header_cache); } static void kvm_wake_nx_recovery_thread(struct kvm *kvm) { /* * The NX recovery thread is spawned on-demand at the first KVM_RUN and * may not be valid even though the VM is globally visible. Do nothing, * as such a VM can't have any possible NX huge pages. */ struct vhost_task *nx_thread = READ_ONCE(kvm->arch.nx_huge_page_recovery_thread); if (nx_thread) vhost_task_wake(nx_thread); } static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp) { int val = *(int *)kp->arg; if (nx_hugepage_mitigation_hard_disabled) return sysfs_emit(buffer, "never\n"); if (val == -1) return sysfs_emit(buffer, "auto\n"); return param_get_bool(buffer, kp); } static bool get_nx_auto_mode(void) { /* Return true when CPU has the bug, and mitigations are ON */ return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off(); } static void __set_nx_huge_pages(bool val) { nx_huge_pages = itlb_multihit_kvm_mitigation = val; } static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) { bool old_val = nx_huge_pages; bool new_val; if (nx_hugepage_mitigation_hard_disabled) return -EPERM; /* In "auto" mode deploy workaround only if CPU has the bug. */ if (sysfs_streq(val, "off")) { new_val = 0; } else if (sysfs_streq(val, "force")) { new_val = 1; } else if (sysfs_streq(val, "auto")) { new_val = get_nx_auto_mode(); } else if (sysfs_streq(val, "never")) { new_val = 0; mutex_lock(&kvm_lock); if (!list_empty(&vm_list)) { mutex_unlock(&kvm_lock); return -EBUSY; } nx_hugepage_mitigation_hard_disabled = true; mutex_unlock(&kvm_lock); } else if (kstrtobool(val, &new_val) < 0) { return -EINVAL; } __set_nx_huge_pages(new_val); if (new_val != old_val) { struct kvm *kvm; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { mutex_lock(&kvm->slots_lock); kvm_mmu_zap_all_fast(kvm); mutex_unlock(&kvm->slots_lock); kvm_wake_nx_recovery_thread(kvm); } mutex_unlock(&kvm_lock); } return 0; } /* * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as * its default value of -1 is technically undefined behavior for a boolean. * Forward the module init call to SPTE code so that it too can handle module * params that need to be resolved/snapshot. */ void __init kvm_mmu_x86_module_init(void) { if (nx_huge_pages == -1) __set_nx_huge_pages(get_nx_auto_mode()); /* * Snapshot userspace's desire to enable the TDP MMU. Whether or not the * TDP MMU is actually enabled is determined in kvm_configure_mmu() * when the vendor module is loaded. */ tdp_mmu_allowed = tdp_mmu_enabled; kvm_mmu_spte_module_init(); } /* * The bulk of the MMU initialization is deferred until the vendor module is * loaded as many of the masks/values may be modified by VMX or SVM, i.e. need * to be reset when a potentially different vendor module is loaded. */ int kvm_mmu_vendor_module_init(void) { int ret = -ENOMEM; /* * MMU roles use union aliasing which is, generally speaking, an * undefined behavior. However, we supposedly know how compilers behave * and the current status quo is unlikely to change. Guardians below are * supposed to let us know if the assumption becomes false. */ BUILD_BUG_ON(sizeof(union kvm_mmu_page_role) != sizeof(u32)); BUILD_BUG_ON(sizeof(union kvm_mmu_extended_role) != sizeof(u32)); BUILD_BUG_ON(sizeof(union kvm_cpu_role) != sizeof(u64)); kvm_mmu_reset_all_pte_masks(); pte_list_desc_cache = KMEM_CACHE(pte_list_desc, SLAB_ACCOUNT); if (!pte_list_desc_cache) goto out; mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header", sizeof(struct kvm_mmu_page), 0, SLAB_ACCOUNT, NULL); if (!mmu_page_header_cache) goto out; return 0; out: mmu_destroy_caches(); return ret; } void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); if (tdp_mmu_enabled) { read_lock(&vcpu->kvm->mmu_lock); mmu_free_root_page(vcpu->kvm, &vcpu->arch.mmu->mirror_root_hpa, NULL); read_unlock(&vcpu->kvm->mmu_lock); } free_mmu_pages(&vcpu->arch.root_mmu); free_mmu_pages(&vcpu->arch.guest_mmu); mmu_free_memory_caches(vcpu); } void kvm_mmu_vendor_module_exit(void) { mmu_destroy_caches(); } /* * Calculate the effective recovery period, accounting for '0' meaning "let KVM * select a halving time of 1 hour". Returns true if recovery is enabled. */ static bool calc_nx_huge_pages_recovery_period(uint *period) { /* * Use READ_ONCE to get the params, this may be called outside of the * param setters, e.g. by the kthread to compute its next timeout. */ bool enabled = READ_ONCE(nx_huge_pages); uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio); if (!enabled || !ratio) return false; *period = READ_ONCE(nx_huge_pages_recovery_period_ms); if (!*period) { /* Make sure the period is not less than one second. */ ratio = min(ratio, 3600u); *period = 60 * 60 * 1000 / ratio; } return true; } static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp) { bool was_recovery_enabled, is_recovery_enabled; uint old_period, new_period; int err; if (nx_hugepage_mitigation_hard_disabled) return -EPERM; was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period); err = param_set_uint(val, kp); if (err) return err; is_recovery_enabled = calc_nx_huge_pages_recovery_period(&new_period); if (is_recovery_enabled && (!was_recovery_enabled || old_period > new_period)) { struct kvm *kvm; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_wake_nx_recovery_thread(kvm); mutex_unlock(&kvm_lock); } return err; } static unsigned long nx_huge_pages_to_zap(struct kvm *kvm, enum kvm_mmu_type mmu_type) { unsigned long pages = READ_ONCE(kvm->arch.possible_nx_huge_pages[mmu_type].nr_pages); unsigned int ratio = READ_ONCE(nx_huge_pages_recovery_ratio); return ratio ? DIV_ROUND_UP(pages, ratio) : 0; } static bool kvm_mmu_sp_dirty_logging_enabled(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memory_slot *slot; /* * Skip the memslot lookup if dirty tracking can't possibly be enabled, * as memslot lookups are relatively expensive. * * If a memslot update is in progress, reading an incorrect value of * kvm->nr_memslots_dirty_logging is not a problem: if it is becoming * zero, KVM will do an unnecessary memslot lookup; if it is becoming * nonzero, the page will be zapped unnecessarily. Either way, this * only affects efficiency in racy situations, and not correctness. */ if (!atomic_read(&kvm->nr_memslots_dirty_logging)) return false; slot = __gfn_to_memslot(kvm_memslots_for_spte_role(kvm, sp->role), sp->gfn); if (WARN_ON_ONCE(!slot)) return false; return kvm_slot_dirty_track_enabled(slot); } static void kvm_recover_nx_huge_pages(struct kvm *kvm, const enum kvm_mmu_type mmu_type) { #ifdef CONFIG_X86_64 const bool is_tdp_mmu = mmu_type == KVM_TDP_MMU; spinlock_t *tdp_mmu_pages_lock = &kvm->arch.tdp_mmu_pages_lock; #else const bool is_tdp_mmu = false; spinlock_t *tdp_mmu_pages_lock = NULL; #endif unsigned long to_zap = nx_huge_pages_to_zap(kvm, mmu_type); struct list_head *nx_huge_pages; struct kvm_mmu_page *sp; LIST_HEAD(invalid_list); bool flush = false; int rcu_idx; nx_huge_pages = &kvm->arch.possible_nx_huge_pages[mmu_type].pages; rcu_idx = srcu_read_lock(&kvm->srcu); if (is_tdp_mmu) read_lock(&kvm->mmu_lock); else write_lock(&kvm->mmu_lock); /* * Zapping TDP MMU shadow pages, including the remote TLB flush, must * be done under RCU protection, because the pages are freed via RCU * callback. */ rcu_read_lock(); for ( ; to_zap; --to_zap) { if (is_tdp_mmu) spin_lock(tdp_mmu_pages_lock); if (list_empty(nx_huge_pages)) { if (is_tdp_mmu) spin_unlock(tdp_mmu_pages_lock); break; } /* * We use a separate list instead of just using active_mmu_pages * because the number of shadow pages that be replaced with an * NX huge page is expected to be relatively small compared to * the total number of shadow pages. And because the TDP MMU * doesn't use active_mmu_pages. */ sp = list_first_entry(nx_huge_pages, struct kvm_mmu_page, possible_nx_huge_page_link); WARN_ON_ONCE(!sp->nx_huge_page_disallowed); WARN_ON_ONCE(!sp->role.direct); unaccount_nx_huge_page(kvm, sp); if (is_tdp_mmu) spin_unlock(tdp_mmu_pages_lock); /* * Do not attempt to recover any NX Huge Pages that are being * dirty tracked, as they would just be faulted back in as 4KiB * pages. The NX Huge Pages in this slot will be recovered, * along with all the other huge pages in the slot, when dirty * logging is disabled. */ if (!kvm_mmu_sp_dirty_logging_enabled(kvm, sp)) { if (is_tdp_mmu) flush |= kvm_tdp_mmu_zap_possible_nx_huge_page(kvm, sp); else kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); } WARN_ON_ONCE(sp->nx_huge_page_disallowed); if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); rcu_read_unlock(); if (is_tdp_mmu) cond_resched_rwlock_read(&kvm->mmu_lock); else cond_resched_rwlock_write(&kvm->mmu_lock); flush = false; rcu_read_lock(); } } kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); rcu_read_unlock(); if (is_tdp_mmu) read_unlock(&kvm->mmu_lock); else write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, rcu_idx); } static void kvm_nx_huge_page_recovery_worker_kill(void *data) { } static bool kvm_nx_huge_page_recovery_worker(void *data) { struct kvm *kvm = data; long remaining_time; bool enabled; uint period; int i; enabled = calc_nx_huge_pages_recovery_period(&period); if (!enabled) return false; remaining_time = kvm->arch.nx_huge_page_last + msecs_to_jiffies(period) - get_jiffies_64(); if (remaining_time > 0) { schedule_timeout(remaining_time); /* check for signals and come back */ return true; } __set_current_state(TASK_RUNNING); for (i = 0; i < KVM_NR_MMU_TYPES; ++i) kvm_recover_nx_huge_pages(kvm, i); kvm->arch.nx_huge_page_last = get_jiffies_64(); return true; } static int kvm_mmu_start_lpage_recovery(struct once *once) { struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once); struct kvm *kvm = container_of(ka, struct kvm, arch); struct vhost_task *nx_thread; kvm->arch.nx_huge_page_last = get_jiffies_64(); nx_thread = vhost_task_create(kvm_nx_huge_page_recovery_worker, kvm_nx_huge_page_recovery_worker_kill, kvm, "kvm-nx-lpage-recovery"); if (IS_ERR(nx_thread)) return PTR_ERR(nx_thread); vhost_task_start(nx_thread); /* Make the task visible only once it is fully started. */ WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread); return 0; } int kvm_mmu_post_init_vm(struct kvm *kvm) { if (nx_hugepage_mitigation_hard_disabled) return 0; return call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery); } void kvm_mmu_pre_destroy_vm(struct kvm *kvm) { if (kvm->arch.nx_huge_page_recovery_thread) vhost_task_stop(kvm->arch.nx_huge_page_recovery_thread); } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, int level) { return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG; } static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn, int level) { lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG; } static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn, int level) { lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG; } bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range) { struct kvm_memory_slot *slot = range->slot; int level; /* * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM * can simply ignore such slots. But if userspace is making memory * PRIVATE, then KVM must prevent the guest from accessing the memory * as shared. And if userspace is making memory SHARED and this point * is reached, then at least one page within the range was previously * PRIVATE, i.e. the slot's possible hugepage ranges are changing. * Zapping SPTEs in this case ensures KVM will reassess whether or not * a hugepage can be used for affected ranges. */ if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) return false; if (WARN_ON_ONCE(range->end <= range->start)) return false; /* * If the head and tail pages of the range currently allow a hugepage, * i.e. reside fully in the slot and don't have mixed attributes, then * add each corresponding hugepage range to the ongoing invalidation, * e.g. to prevent KVM from creating a hugepage in response to a fault * for a gfn whose attributes aren't changing. Note, only the range * of gfns whose attributes are being modified needs to be explicitly * unmapped, as that will unmap any existing hugepages. */ for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { gfn_t start = gfn_round_for_level(range->start, level); gfn_t end = gfn_round_for_level(range->end - 1, level); gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); if ((start != range->start || start + nr_pages > range->end) && start >= slot->base_gfn && start + nr_pages <= slot->base_gfn + slot->npages && !hugepage_test_mixed(slot, start, level)) kvm_mmu_invalidate_range_add(kvm, start, start + nr_pages); if (end == start) continue; if ((end + nr_pages) > range->end && (end + nr_pages) <= (slot->base_gfn + slot->npages) && !hugepage_test_mixed(slot, end, level)) kvm_mmu_invalidate_range_add(kvm, end, end + nr_pages); } /* Unmap the old attribute page. */ if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE) range->attr_filter = KVM_FILTER_SHARED; else range->attr_filter = KVM_FILTER_PRIVATE; return kvm_unmap_gfn_range(kvm, range); } static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long attrs) { const unsigned long start = gfn; const unsigned long end = start + KVM_PAGES_PER_HPAGE(level); if (level == PG_LEVEL_2M) return kvm_range_has_memory_attributes(kvm, start, end, ~0, attrs); for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) { if (hugepage_test_mixed(slot, gfn, level - 1) || attrs != kvm_get_memory_attributes(kvm, gfn)) return false; } return true; } bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range) { unsigned long attrs = range->arg.attributes; struct kvm_memory_slot *slot = range->slot; int level; lockdep_assert_held_write(&kvm->mmu_lock); lockdep_assert_held(&kvm->slots_lock); /* * Calculate which ranges can be mapped with hugepages even if the slot * can't map memory PRIVATE. KVM mustn't create a SHARED hugepage over * a range that has PRIVATE GFNs, and conversely converting a range to * SHARED may now allow hugepages. */ if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) return false; /* * The sequence matters here: upper levels consume the result of lower * level's scanning. */ for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); gfn_t gfn = gfn_round_for_level(range->start, level); /* Process the head page if it straddles the range. */ if (gfn != range->start || gfn + nr_pages > range->end) { /* * Skip mixed tracking if the aligned gfn isn't covered * by the memslot, KVM can't use a hugepage due to the * misaligned address regardless of memory attributes. */ if (gfn >= slot->base_gfn && gfn + nr_pages <= slot->base_gfn + slot->npages) { if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) hugepage_clear_mixed(slot, gfn, level); else hugepage_set_mixed(slot, gfn, level); } gfn += nr_pages; } /* * Pages entirely covered by the range are guaranteed to have * only the attributes which were just set. */ for ( ; gfn + nr_pages <= range->end; gfn += nr_pages) hugepage_clear_mixed(slot, gfn, level); /* * Process the last tail page if it straddles the range and is * contained by the memslot. Like the head page, KVM can't * create a hugepage if the slot size is misaligned. */ if (gfn < range->end && (gfn + nr_pages) <= (slot->base_gfn + slot->npages)) { if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) hugepage_clear_mixed(slot, gfn, level); else hugepage_set_mixed(slot, gfn, level); } } return false; } void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, struct kvm_memory_slot *slot) { int level; if (!kvm_arch_has_private_mem(kvm)) return; for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { /* * Don't bother tracking mixed attributes for pages that can't * be huge due to alignment, i.e. process only pages that are * entirely contained by the memslot. */ gfn_t end = gfn_round_for_level(slot->base_gfn + slot->npages, level); gfn_t start = gfn_round_for_level(slot->base_gfn, level); gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); gfn_t gfn; if (start < slot->base_gfn) start += nr_pages; /* * Unlike setting attributes, every potential hugepage needs to * be manually checked as the attributes may already be mixed. */ for (gfn = start; gfn < end; gfn += nr_pages) { unsigned long attrs = kvm_get_memory_attributes(kvm, gfn); if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) hugepage_clear_mixed(slot, gfn, level); else hugepage_set_mixed(slot, gfn, level); } } } #endif |
| 46 46 62 6 16 6 40 6 40 46 34 12 46 20 26 50 50 34 27 7 7 47 8 62 62 38 7 46 15 1 56 57 54 29 39 42 36 35 48 29 27 35 64 37 32 64 62 2 62 21 25 34 34 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * DVB USB library - provides a generic interface for a DVB USB device driver. * * dvb-usb-init.c * * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de) * * see Documentation/driver-api/media/drivers/dvb-usb.rst for more information */ #include "dvb-usb-common.h" /* debug */ int dvb_usb_debug; module_param_named(debug, dvb_usb_debug, int, 0644); MODULE_PARM_DESC(debug, "set debugging level (1=info,xfer=2,pll=4,ts=8,err=16,rc=32,fw=64,mem=128,uxfer=256 (or-able))." DVB_USB_DEBUG_STATUS); int dvb_usb_disable_rc_polling; module_param_named(disable_rc_polling, dvb_usb_disable_rc_polling, int, 0644); MODULE_PARM_DESC(disable_rc_polling, "disable remote control polling (default: 0)."); static int dvb_usb_force_pid_filter_usage; module_param_named(force_pid_filter_usage, dvb_usb_force_pid_filter_usage, int, 0444); MODULE_PARM_DESC(force_pid_filter_usage, "force all dvb-usb-devices to use a PID filter, if any (default: 0)."); static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs) { struct dvb_usb_adapter *adap; int ret, n, o; for (n = 0; n < d->props.num_adapters; n++) { adap = &d->adapter[n]; adap->dev = d; adap->id = n; memcpy(&adap->props, &d->props.adapter[n], sizeof(struct dvb_usb_adapter_properties)); for (o = 0; o < adap->props.num_frontends; o++) { struct dvb_usb_adapter_fe_properties *props = &adap->props.fe[o]; /* speed - when running at FULL speed we need a HW PID filter */ if (d->udev->speed == USB_SPEED_FULL && !(props->caps & DVB_USB_ADAP_HAS_PID_FILTER)) { err("This USB2.0 device cannot be run on a USB1.1 port. (it lacks a hardware PID filter)"); return -ENODEV; } if ((d->udev->speed == USB_SPEED_FULL && props->caps & DVB_USB_ADAP_HAS_PID_FILTER) || (props->caps & DVB_USB_ADAP_NEED_PID_FILTERING)) { info("will use the device's hardware PID filter (table count: %d).", props->pid_filter_count); adap->fe_adap[o].pid_filtering = 1; adap->fe_adap[o].max_feed_count = props->pid_filter_count; } else { info("will pass the complete MPEG2 transport stream to the software demuxer."); adap->fe_adap[o].pid_filtering = 0; adap->fe_adap[o].max_feed_count = 255; } if (!adap->fe_adap[o].pid_filtering && dvb_usb_force_pid_filter_usage && props->caps & DVB_USB_ADAP_HAS_PID_FILTER) { info("pid filter enabled by module option."); adap->fe_adap[o].pid_filtering = 1; adap->fe_adap[o].max_feed_count = props->pid_filter_count; } if (props->size_of_priv > 0) { adap->fe_adap[o].priv = kzalloc(props->size_of_priv, GFP_KERNEL); if (adap->fe_adap[o].priv == NULL) { err("no memory for priv for adapter %d fe %d.", n, o); return -ENOMEM; } } } if (adap->props.size_of_priv > 0) { adap->priv = kzalloc(adap->props.size_of_priv, GFP_KERNEL); if (adap->priv == NULL) { err("no memory for priv for adapter %d.", n); return -ENOMEM; } } ret = dvb_usb_adapter_stream_init(adap); if (ret) goto stream_init_err; ret = dvb_usb_adapter_dvb_init(adap, adapter_nrs); if (ret) goto dvb_init_err; ret = dvb_usb_adapter_frontend_init(adap); if (ret) goto frontend_init_err; /* use exclusive FE lock if there is multiple shared FEs */ if (adap->fe_adap[1].fe && adap->dvb_adap.mfe_shared < 1) adap->dvb_adap.mfe_shared = 1; d->num_adapters_initialized++; d->state |= DVB_USB_STATE_DVB; } /* * when reloading the driver w/o replugging the device * sometimes a timeout occurs, this helps */ if (d->props.generic_bulk_ctrl_endpoint != 0) { usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint)); usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint)); } return 0; frontend_init_err: dvb_usb_adapter_dvb_exit(adap); dvb_init_err: dvb_usb_adapter_stream_exit(adap); stream_init_err: kfree(adap->priv); return ret; } static int dvb_usb_adapter_exit(struct dvb_usb_device *d) { int n; for (n = 0; n < d->num_adapters_initialized; n++) { dvb_usb_adapter_frontend_exit(&d->adapter[n]); dvb_usb_adapter_dvb_exit(&d->adapter[n]); dvb_usb_adapter_stream_exit(&d->adapter[n]); kfree(d->adapter[n].priv); } d->num_adapters_initialized = 0; d->state &= ~DVB_USB_STATE_DVB; return 0; } /* general initialization functions */ static int dvb_usb_exit(struct dvb_usb_device *d) { deb_info("state before exiting everything: %x\n", d->state); dvb_usb_remote_exit(d); dvb_usb_adapter_exit(d); dvb_usb_i2c_exit(d); deb_info("state should be zero now: %x\n", d->state); d->state = DVB_USB_STATE_INIT; if (d->priv != NULL && d->props.priv_destroy != NULL) d->props.priv_destroy(d); kfree(d->priv); kfree(d); return 0; } static int dvb_usb_init(struct dvb_usb_device *d, short *adapter_nums) { int ret = 0; mutex_init(&d->data_mutex); mutex_init(&d->usb_mutex); mutex_init(&d->i2c_mutex); d->state = DVB_USB_STATE_INIT; if (d->props.size_of_priv > 0) { d->priv = kzalloc(d->props.size_of_priv, GFP_KERNEL); if (d->priv == NULL) { err("no memory for priv in 'struct dvb_usb_device'"); return -ENOMEM; } if (d->props.priv_init != NULL) { ret = d->props.priv_init(d); if (ret != 0) goto err_priv_init; } } /* check the capabilities and set appropriate variables */ dvb_usb_device_power_ctrl(d, 1); ret = dvb_usb_i2c_init(d); if (ret) goto err_i2c_init; ret = dvb_usb_adapter_init(d, adapter_nums); if (ret) goto err_adapter_init; if ((ret = dvb_usb_remote_init(d))) err("could not initialize remote control."); dvb_usb_device_power_ctrl(d, 0); return 0; err_adapter_init: dvb_usb_adapter_exit(d); dvb_usb_i2c_exit(d); err_i2c_init: if (d->priv && d->props.priv_destroy) d->props.priv_destroy(d); err_priv_init: kfree(d->priv); d->priv = NULL; return ret; } /* determine the name and the state of the just found USB device */ static const struct dvb_usb_device_description *dvb_usb_find_device(struct usb_device *udev, const struct dvb_usb_device_properties *props, int *cold) { int i, j; const struct dvb_usb_device_description *desc = NULL; *cold = -1; for (i = 0; i < props->num_device_descs; i++) { for (j = 0; j < DVB_USB_ID_MAX_NUM && props->devices[i].cold_ids[j] != NULL; j++) { deb_info("check for cold %x %x\n", props->devices[i].cold_ids[j]->idVendor, props->devices[i].cold_ids[j]->idProduct); if (props->devices[i].cold_ids[j]->idVendor == le16_to_cpu(udev->descriptor.idVendor) && props->devices[i].cold_ids[j]->idProduct == le16_to_cpu(udev->descriptor.idProduct)) { *cold = 1; desc = &props->devices[i]; break; } } if (desc != NULL) break; for (j = 0; j < DVB_USB_ID_MAX_NUM && props->devices[i].warm_ids[j] != NULL; j++) { deb_info("check for warm %x %x\n", props->devices[i].warm_ids[j]->idVendor, props->devices[i].warm_ids[j]->idProduct); if (props->devices[i].warm_ids[j]->idVendor == le16_to_cpu(udev->descriptor.idVendor) && props->devices[i].warm_ids[j]->idProduct == le16_to_cpu(udev->descriptor.idProduct)) { *cold = 0; desc = &props->devices[i]; break; } } } if (desc != NULL && props->identify_state != NULL) props->identify_state(udev, props, &desc, cold); return desc; } int dvb_usb_device_power_ctrl(struct dvb_usb_device *d, int onoff) { if (onoff) d->powered++; else d->powered--; if (d->powered == 0 || (onoff && d->powered == 1)) { /* when switching from 1 to 0 or from 0 to 1 */ deb_info("power control: %d\n", onoff); if (d->props.power_ctrl) return d->props.power_ctrl(d, onoff); } return 0; } /* * USB */ int dvb_usb_device_init(struct usb_interface *intf, const struct dvb_usb_device_properties *props, struct module *owner, struct dvb_usb_device **du, short *adapter_nums) { struct usb_device *udev = interface_to_usbdev(intf); struct dvb_usb_device *d = NULL; const struct dvb_usb_device_description *desc = NULL; int ret = -ENOMEM, cold = 0; if (du != NULL) *du = NULL; d = kzalloc_obj(*d); if (!d) { err("no memory for 'struct dvb_usb_device'"); return -ENOMEM; } memcpy(&d->props, props, sizeof(struct dvb_usb_device_properties)); desc = dvb_usb_find_device(udev, &d->props, &cold); if (!desc) { deb_err("something went very wrong, device was not found in current device list - let's see what comes next.\n") |