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 #ifndef _LINUX_PSI_H #define _LINUX_PSI_H #include <linux/jump_label.h> #include <linux/psi_types.h> #include <linux/sched.h> #include <linux/poll.h> struct seq_file; struct css_set; #ifdef CONFIG_PSI extern struct static_key_false psi_disabled; extern struct psi_group psi_system; void psi_init(void); void psi_task_change(struct task_struct *task, int clear, int set); void psi_task_switch(struct task_struct *prev, struct task_struct *next, bool sleep); void psi_memstall_tick(struct task_struct *task, int cpu); void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); #ifdef CONFIG_CGROUPS int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, size_t nbytes, enum psi_res res); void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); #endif #else /* CONFIG_PSI */ static inline void psi_init(void) {} static inline void psi_memstall_enter(unsigned long *flags) {} static inline void psi_memstall_leave(unsigned long *flags) {} #ifdef CONFIG_CGROUPS static inline int psi_cgroup_alloc(struct cgroup *cgrp) { return 0; } static inline void psi_cgroup_free(struct cgroup *cgrp) { } static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) { rcu_assign_pointer(p->cgroups, to); } #endif #endif /* CONFIG_PSI */ #endif /* _LINUX_PSI_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM x86_fpu #if !defined(_TRACE_FPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FPU_H #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(x86_fpu, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu), TP_STRUCT__entry( __field(struct fpu *, fpu) __field(bool, load_fpu) __field(u64, xfeatures) __field(u64, xcomp_bv) ), TP_fast_assign( __entry->fpu = fpu; __entry->load_fpu = test_thread_flag(TIF_NEED_FPU_LOAD); if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { __entry->xfeatures = fpu->state.xsave.header.xfeatures; __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv; } ), TP_printk("x86/fpu: %p load: %d xfeatures: %llx xcomp_bv: %llx", __entry->fpu, __entry->load_fpu, __entry->xfeatures, __entry->xcomp_bv ) ); DEFINE_EVENT(x86_fpu, x86_fpu_before_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_after_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_before_restore, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_after_restore, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_regs_activated, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_init_state, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_dropped, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_copy_src, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_copy_dst, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_xstate_check_failed, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH asm/trace/ #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE fpu #endif /* _TRACE_FPU_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 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 // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/namespace.c * * (C) Copyright Al Viro 2000, 2001 * * Based on code from fs/super.c, copyright Linus Torvalds and others. * Heavily rewritten. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/capability.h> #include <linux/mnt_namespace.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/idr.h> #include <linux/init.h> /* init_rootfs */ #include <linux/fs_struct.h> /* get_fs_root et.al. */ #include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ #include <linux/file.h> #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/memblock.h> #include <linux/task_work.h> #include <linux/sched/task.h> #include <uapi/linux/mount.h> #include <linux/fs_context.h> #include <linux/shmem_fs.h> #include "pnode.h" #include "internal.h" /* Maximum number of mounts in a mount namespace */ unsigned int sysctl_mount_max __read_mostly = 100000; static unsigned int m_hash_mask __read_mostly; static unsigned int m_hash_shift __read_mostly; static unsigned int mp_hash_mask __read_mostly; static unsigned int mp_hash_shift __read_mostly; static __initdata unsigned long mhash_entries; static int __init set_mhash_entries(char *str) { if (!str) return 0; mhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mhash_entries=", set_mhash_entries); static __initdata unsigned long mphash_entries; static int __init set_mphash_entries(char *str) { if (!str) return 0; mphash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mphash_entries=", set_mphash_entries); static u64 event; static DEFINE_IDA(mnt_id_ida); static DEFINE_IDA(mnt_group_ida); static struct hlist_head *mount_hashtable __read_mostly; static struct hlist_head *mountpoint_hashtable __read_mostly; static struct kmem_cache *mnt_cache __read_mostly; static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ /* /sys/fs */ struct kobject *fs_kobj; EXPORT_SYMBOL_GPL(fs_kobj); /* * vfsmount lock may be taken for read to prevent changes to the * vfsmount hash, ie. during mountpoint lookups or walking back * up the tree. * * It should be taken for write in all cases where the vfsmount * tree or hash is modified or when a vfsmount structure is modified. */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> m_hash_shift); return &mount_hashtable[tmp & m_hash_mask]; } static inline struct hlist_head *mp_hash(struct dentry *dentry) { unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> mp_hash_shift); return &mountpoint_hashtable[tmp & mp_hash_mask]; } static int mnt_alloc_id(struct mount *mnt) { int res = ida_alloc(&mnt_id_ida, GFP_KERNEL); if (res < 0) return res; mnt->mnt_id = res; return 0; } static void mnt_free_id(struct mount *mnt) { ida_free(&mnt_id_ida, mnt->mnt_id); } /* * Allocate a new peer group ID */ static int mnt_alloc_group_id(struct mount *mnt) { int res = ida_alloc_min(&mnt_group_ida, 1, GFP_KERNEL); if (res < 0) return res; mnt->mnt_group_id = res; return 0; } /* * Release a peer group ID */ void mnt_release_group_id(struct mount *mnt) { ida_free(&mnt_group_ida, mnt->mnt_group_id); mnt->mnt_group_id = 0; } /* * vfsmount lock must be held for read */ static inline void mnt_add_count(struct mount *mnt, int n) { #ifdef CONFIG_SMP this_cpu_add(mnt->mnt_pcp->mnt_count, n); #else preempt_disable(); mnt->mnt_count += n; preempt_enable(); #endif } /* * vfsmount lock must be held for write */ int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count; } return count; #else return mnt->mnt_count; #endif } static struct mount *alloc_vfsmnt(const char *name) { struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); if (mnt) { int err; err = mnt_alloc_id(mnt); if (err) goto out_free_cache; if (name) { mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL); if (!mnt->mnt_devname) goto out_free_id; } #ifdef CONFIG_SMP mnt->mnt_pcp = alloc_percpu(struct mnt_pcp); if (!mnt->mnt_pcp) goto out_free_devname; this_cpu_add(mnt->mnt_pcp->mnt_count, 1); #else mnt->mnt_count = 1; mnt->mnt_writers = 0; #endif INIT_HLIST_NODE(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); INIT_LIST_HEAD(&mnt->mnt_expire); INIT_LIST_HEAD(&mnt->mnt_share); INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); } return mnt; #ifdef CONFIG_SMP out_free_devname: kfree_const(mnt->mnt_devname); #endif out_free_id: mnt_free_id(mnt); out_free_cache: kmem_cache_free(mnt_cache, mnt); return NULL; } /* * Most r/o checks on a fs are for operations that take * discrete amounts of time, like a write() or unlink(). * We must keep track of when those operations start * (for permission checks) and when they end, so that * we can determine when writes are able to occur to * a filesystem. */ /* * __mnt_is_readonly: check whether a mount is read-only * @mnt: the mount to check for its write status * * This shouldn't be used directly ouside of the VFS. * It does not guarantee that the filesystem will stay * r/w, just that it is right *now*. This can not and * should not be used in place of IS_RDONLY(inode). * mnt_want/drop_write() will _keep_ the filesystem * r/w. */ bool __mnt_is_readonly(struct vfsmount *mnt) { return (mnt->mnt_flags & MNT_READONLY) || sb_rdonly(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(__mnt_is_readonly); static inline void mnt_inc_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_inc(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers++; #endif } static inline void mnt_dec_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_dec(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers--; #endif } static unsigned int mnt_get_writers(struct mount *mnt) { #ifdef CONFIG_SMP unsigned int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers; } return count; #else return mnt->mnt_writers; #endif } static int mnt_is_readonly(struct vfsmount *mnt) { if (mnt->mnt_sb->s_readonly_remount) return 1; /* Order wrt setting s_flags/s_readonly_remount in do_remount() */ smp_rmb(); return __mnt_is_readonly(mnt); } /* * Most r/o & frozen checks on a fs are for operations that take discrete * amounts of time, like a write() or unlink(). We must keep track of when * those operations start (for permission checks) and when they end, so that we * can determine when writes are able to occur to a filesystem. */ /** * __mnt_want_write - get write access to a mount without freeze protection * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mnt it read-write) before * returning success. This operation does not protect against filesystem being * frozen. When the write operation is finished, __mnt_drop_write() must be * called. This is effectively a refcount. */ int __mnt_want_write(struct vfsmount *m) { struct mount *mnt = real_mount(m); int ret = 0; preempt_disable(); mnt_inc_writers(mnt); /* * The store to mnt_inc_writers must be visible before we pass * MNT_WRITE_HOLD loop below, so that the slowpath can see our * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) cpu_relax(); /* * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will * be set to match its requirements. So we must not load that until * MNT_WRITE_HOLD is cleared. */ smp_rmb(); if (mnt_is_readonly(m)) { mnt_dec_writers(mnt); ret = -EROFS; } preempt_enable(); return ret; } /** * mnt_want_write - get write access to a mount * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mount is read-write, filesystem * is not frozen) before returning success. When the write operation is * finished, mnt_drop_write() must be called. This is effectively a refcount. */ int mnt_want_write(struct vfsmount *m) { int ret; sb_start_write(m->mnt_sb); ret = __mnt_want_write(m); if (ret) sb_end_write(m->mnt_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write); /** * mnt_clone_write - get write access to a mount * @mnt: the mount on which to take a write * * This is effectively like mnt_want_write, except * it must only be used to take an extra write reference * on a mountpoint that we already know has a write reference * on it. This allows some optimisation. * * After finished, mnt_drop_write must be called as usual to * drop the reference. */ int mnt_clone_write(struct vfsmount *mnt) { /* superblock may be r/o */ if (__mnt_is_readonly(mnt)) return -EROFS; preempt_disable(); mnt_inc_writers(real_mount(mnt)); preempt_enable(); return 0; } EXPORT_SYMBOL_GPL(mnt_clone_write); /** * __mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like __mnt_want_write, but it takes a file and can * do some optimisations if the file is open for write already */ int __mnt_want_write_file(struct file *file) { if (!(file->f_mode & FMODE_WRITER)) return __mnt_want_write(file->f_path.mnt); else return mnt_clone_write(file->f_path.mnt); } /** * mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_want_write, but it takes a file and can * do some optimisations if the file is open for write already */ int mnt_want_write_file(struct file *file) { int ret; sb_start_write(file_inode(file)->i_sb); ret = __mnt_want_write_file(file); if (ret) sb_end_write(file_inode(file)->i_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write_file); /** * __mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done * performing writes to it. Must be matched with * __mnt_want_write() call above. */ void __mnt_drop_write(struct vfsmount *mnt) { preempt_disable(); mnt_dec_writers(real_mount(mnt)); preempt_enable(); } /** * mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done performing writes to it and * also allows filesystem to be frozen again. Must be matched with * mnt_want_write() call above. */ void mnt_drop_write(struct vfsmount *mnt) { __mnt_drop_write(mnt); sb_end_write(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(mnt_drop_write); void __mnt_drop_write_file(struct file *file) { __mnt_drop_write(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) { __mnt_drop_write_file(file); sb_end_write(file_inode(file)->i_sb); } EXPORT_SYMBOL(mnt_drop_write_file); static int mnt_make_readonly(struct mount *mnt) { int ret = 0; lock_mount_hash(); mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; /* * After storing MNT_WRITE_HOLD, we'll read the counters. This store * should be visible before we do. */ smp_mb(); /* * With writers on hold, if this value is zero, then there are * definitely no active writers (although held writers may subsequently * increment the count, they'll have to wait, and decrement it after * seeing MNT_READONLY). * * It is OK to have counter incremented on one CPU and decremented on * another: the sum will add up correctly. The danger would be when we * sum up each counter, if we read a counter before it is incremented, * but then read another CPU's count which it has been subsequently * decremented from -- we would see more decrements than we should. * MNT_WRITE_HOLD protects against this scenario, because * mnt_want_write first increments count, then smp_mb, then spins on * MNT_WRITE_HOLD, so it can't be decremented by another CPU while * we're counting up here. */ if (mnt_get_writers(mnt) > 0) ret = -EBUSY; else mnt->mnt.mnt_flags |= MNT_READONLY; /* * MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers * that become unheld will see MNT_READONLY. */ smp_wmb(); mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; unlock_mount_hash(); return ret; } static int __mnt_unmake_readonly(struct mount *mnt) { lock_mount_hash(); mnt->mnt.mnt_flags &= ~MNT_READONLY; unlock_mount_hash(); return 0; } int sb_prepare_remount_readonly(struct super_block *sb) { struct mount *mnt; int err = 0; /* Racy optimization. Recheck the counter under MNT_WRITE_HOLD */ if (atomic_long_read(&sb->s_remove_count)) return -EBUSY; lock_mount_hash(); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (!(mnt->mnt.mnt_flags & MNT_READONLY)) { mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; smp_mb(); if (mnt_get_writers(mnt) > 0) { err = -EBUSY; break; } } } if (!err && atomic_long_read(&sb->s_remove_count)) err = -EBUSY; if (!err) { sb->s_readonly_remount = 1; smp_wmb(); } list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } unlock_mount_hash(); return err; } static void free_vfsmnt(struct mount *mnt) { kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); #endif kmem_cache_free(mnt_cache, mnt); } static void delayed_free_vfsmnt(struct rcu_head *head) { free_vfsmnt(container_of(head, struct mount, mnt_rcu)); } /* call under rcu_read_lock */ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) { struct mount *mnt; if (read_seqretry(&mount_lock, seq)) return 1; if (bastard == NULL) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); smp_mb(); // see mntput_no_expire() if (likely(!read_seqretry(&mount_lock, seq))) return 0; if (bastard->mnt_flags & MNT_SYNC_UMOUNT) { mnt_add_count(mnt, -1); return 1; } lock_mount_hash(); if (unlikely(bastard->mnt_flags & MNT_DOOMED)) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; } unlock_mount_hash(); /* caller will mntput() */ return -1; } /* call under rcu_read_lock */ bool legitimize_mnt(struct vfsmount *bastard, unsigned seq) { int res = __legitimize_mnt(bastard, seq); if (likely(!res)) return true; if (unlikely(res < 0)) { rcu_read_unlock(); mntput(bastard); rcu_read_lock(); } return false; } /* * find the first mount at @dentry on vfsmount @mnt. * call under rcu_read_lock() */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { struct hlist_head *head = m_hash(mnt, dentry); struct mount *p; hlist_for_each_entry_rcu(p, head, mnt_hash) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) return p; return NULL; } /* * lookup_mnt - Return the first child mount mounted at path * * "First" means first mounted chronologically. If you create the * following mounts: * * mount /dev/sda1 /mnt * mount /dev/sda2 /mnt * mount /dev/sda3 /mnt * * Then lookup_mnt() on the base /mnt dentry in the root mount will * return successively the root dentry and vfsmount of /dev/sda1, then * /dev/sda2, then /dev/sda3, then NULL. * * lookup_mnt takes a reference to the found vfsmount. */ struct vfsmount *lookup_mnt(const struct path *path) { struct mount *child_mnt; struct vfsmount *m; unsigned seq; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); child_mnt = __lookup_mnt(path->mnt, path->dentry); m = child_mnt ? &child_mnt->mnt : NULL; } while (!legitimize_mnt(m, seq)); rcu_read_unlock(); return m; } static inline void lock_ns_list(struct mnt_namespace *ns) { spin_lock(&ns->ns_lock); } static inline void unlock_ns_list(struct mnt_namespace *ns) { spin_unlock(&ns->ns_lock); } static inline bool mnt_is_cursor(struct mount *mnt) { return mnt->mnt.mnt_flags & MNT_CURSOR; } /* * __is_local_mountpoint - Test to see if dentry is a mountpoint in the * current mount namespace. * * The common case is dentries are not mountpoints at all and that * test is handled inline. For the slow case when we are actually * dealing with a mountpoint of some kind, walk through all of the * mounts in the current mount namespace and test to see if the dentry * is a mountpoint. * * The mount_hashtable is not usable in the context because we * need to identify all mounts that may be in the current mount * namespace not just a mount that happens to have some specified * parent mount. */ bool __is_local_mountpoint(struct dentry *dentry) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mount *mnt; bool is_covered = false; down_read(&namespace_sem); lock_ns_list(ns); list_for_each_entry(mnt, &ns->list, mnt_list) { if (mnt_is_cursor(mnt)) continue; is_covered = (mnt->mnt_mountpoint == dentry); if (is_covered) break; } unlock_ns_list(ns); up_read(&namespace_sem); return is_covered; } static struct mountpoint *lookup_mountpoint(struct dentry *dentry) { struct hlist_head *chain = mp_hash(dentry); struct mountpoint *mp; hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { mp->m_count++; return mp; } } return NULL; } static struct mountpoint *get_mountpoint(struct dentry *dentry) { struct mountpoint *mp, *new = NULL; int ret; if (d_mountpoint(dentry)) { /* might be worth a WARN_ON() */ if (d_unlinked(dentry)) return ERR_PTR(-ENOENT); mountpoint: read_seqlock_excl(&mount_lock); mp = lookup_mountpoint(dentry); read_sequnlock_excl(&mount_lock); if (mp) goto done; } if (!new) new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* Exactly one processes may set d_mounted */ ret = d_set_mounted(dentry); /* Someone else set d_mounted? */ if (ret == -EBUSY) goto mountpoint; /* The dentry is not available as a mountpoint? */ mp = ERR_PTR(ret); if (ret) goto done; /* Add the new mountpoint to the hash table */ read_seqlock_excl(&mount_lock); new->m_dentry = dget(dentry); new->m_count = 1; hlist_add_head(&new->m_hash, mp_hash(dentry)); INIT_HLIST_HEAD(&new->m_list); read_sequnlock_excl(&mount_lock); mp = new; new = NULL; done: kfree(new); return mp; } /* * vfsmount lock must be held. Additionally, the caller is responsible * for serializing calls for given disposal list. */ static void __put_mountpoint(struct mountpoint *mp, struct list_head *list) { if (!--mp->m_count) { struct dentry *dentry = mp->m_dentry; BUG_ON(!hlist_empty(&mp->m_list)); spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); dput_to_list(dentry, list); hlist_del(&mp->m_hash); kfree(mp); } } /* called with namespace_lock and vfsmount lock */ static void put_mountpoint(struct mountpoint *mp) { __put_mountpoint(mp, &ex_mountpoints); } static inline int check_mnt(struct mount *mnt) { return mnt->mnt_ns == current->nsproxy->mnt_ns; } /* * vfsmount lock must be held for write */ static void touch_mnt_namespace(struct mnt_namespace *ns) { if (ns) { ns->event = ++event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static void __touch_mnt_namespace(struct mnt_namespace *ns) { if (ns && ns->event != event) { ns->event = event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static struct mountpoint *unhash_mnt(struct mount *mnt) { struct mountpoint *mp; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); hlist_del_init_rcu(&mnt->mnt_hash); hlist_del_init(&mnt->mnt_mp_list); mp = mnt->mnt_mp; mnt->mnt_mp = NULL; return mp; } /* * vfsmount lock must be held for write */ static void umount_mnt(struct mount *mnt) { put_mountpoint(unhash_mnt(mnt)); } /* * vfsmount lock must be held for write */ void mnt_set_mountpoint(struct mount *mnt, struct mountpoint *mp, struct mount *child_mnt) { mp->m_count++; mnt_add_count(mnt, 1); /* essentially, that's mntget */ child_mnt->mnt_mountpoint = mp->m_dentry; child_mnt->mnt_parent = mnt; child_mnt->mnt_mp = mp; hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } static void __attach_mnt(struct mount *mnt, struct mount *parent) { hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } /* * vfsmount lock must be held for write */ static void attach_mnt(struct mount *mnt, struct mount *parent, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); __attach_mnt(mnt, parent); } void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { struct mountpoint *old_mp = mnt->mnt_mp; struct mount *old_parent = mnt->mnt_parent; list_del_init(&mnt->mnt_child); hlist_del_init(&mnt->mnt_mp_list); hlist_del_init_rcu(&mnt->mnt_hash); attach_mnt(mnt, parent, mp); put_mountpoint(old_mp); mnt_add_count(old_parent, -1); } /* * vfsmount lock must be held for write */ static void commit_tree(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m; LIST_HEAD(head); struct mnt_namespace *n = parent->mnt_ns; BUG_ON(parent == mnt); list_add_tail(&head, &mnt->mnt_list); list_for_each_entry(m, &head, mnt_list) m->mnt_ns = n; list_splice(&head, n->list.prev); n->mounts += n->pending_mounts; n->pending_mounts = 0; __attach_mnt(mnt, parent); touch_mnt_namespace(n); } static struct mount *next_mnt(struct mount *p, struct mount *root) { struct list_head *next = p->mnt_mounts.next; if (next == &p->mnt_mounts) { while (1) { if (p == root) return NULL; next = p->mnt_child.next; if (next != &p->mnt_parent->mnt_mounts) break; p = p->mnt_parent; } } return list_entry(next, struct mount, mnt_child); } static struct mount *skip_mnt_tree(struct mount *p) { struct list_head *prev = p->mnt_mounts.prev; while (prev != &p->mnt_mounts) { p = list_entry(prev, struct mount, mnt_child); prev = p->mnt_mounts.prev; } return p; } /** * vfs_create_mount - Create a mount for a configured superblock * @fc: The configuration context with the superblock attached * * Create a mount to an already configured superblock. If necessary, the * caller should invoke vfs_get_tree() before calling this. * * Note that this does not attach the mount to anything. */ struct vfsmount *vfs_create_mount(struct fs_context *fc) { struct mount *mnt; if (!fc->root) return ERR_PTR(-EINVAL); mnt = alloc_vfsmnt(fc->source ?: "none"); if (!mnt) return ERR_PTR(-ENOMEM); if (fc->sb_flags & SB_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; atomic_inc(&fc->root->d_sb->s_active); mnt->mnt.mnt_sb = fc->root->d_sb; mnt->mnt.mnt_root = dget(fc->root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); unlock_mount_hash(); return &mnt->mnt; } EXPORT_SYMBOL(vfs_create_mount); struct vfsmount *fc_mount(struct fs_context *fc) { int err = vfs_get_tree(fc); if (!err) { up_write(&fc->root->d_sb->s_umount); return vfs_create_mount(fc); } return ERR_PTR(err); } EXPORT_SYMBOL(fc_mount); struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { struct fs_context *fc; struct vfsmount *mnt; int ret = 0; if (!type) return ERR_PTR(-EINVAL); fc = fs_context_for_mount(type, flags); if (IS_ERR(fc)) return ERR_CAST(fc); if (name) ret = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!ret) ret = parse_monolithic_mount_data(fc, data); if (!ret) mnt = fc_mount(fc); else mnt = ERR_PTR(ret); put_fs_context(fc); return mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); struct vfsmount * vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, const char *name, void *data) { /* Until it is worked out how to pass the user namespace * through from the parent mount to the submount don't support * unprivileged mounts with submounts. */ if (mountpoint->d_sb->s_user_ns != &init_user_ns) return ERR_PTR(-EPERM); return vfs_kern_mount(type, SB_SUBMOUNT, name, data); } EXPORT_SYMBOL_GPL(vfs_submount); static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { struct super_block *sb = old->mnt.mnt_sb; struct mount *mnt; int err; mnt = alloc_vfsmnt(old->mnt_devname); if (!mnt) return ERR_PTR(-ENOMEM); if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE)) mnt->mnt_group_id = 0; /* not a peer of original */ else mnt->mnt_group_id = old->mnt_group_id; if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { err = mnt_alloc_group_id(mnt); if (err) goto out_free; } mnt->mnt.mnt_flags = old->mnt.mnt_flags; mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &sb->s_mounts); unlock_mount_hash(); if ((flag & CL_SLAVE) || ((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) { list_add(&mnt->mnt_slave, &old->mnt_slave_list); mnt->mnt_master = old; CLEAR_MNT_SHARED(mnt); } else if (!(flag & CL_PRIVATE)) { if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old)) list_add(&mnt->mnt_share, &old->mnt_share); if (IS_MNT_SLAVE(old)) list_add(&mnt->mnt_slave, &old->mnt_slave); mnt->mnt_master = old->mnt_master; } else { CLEAR_MNT_SHARED(mnt); } if (flag & CL_MAKE_SHARED) set_mnt_shared(mnt); /* stick the duplicate mount on the same expiry list * as the original if that was on one */ if (flag & CL_EXPIRE) { if (!list_empty(&old->mnt_expire)) list_add(&mnt->mnt_expire, &old->mnt_expire); } return mnt; out_free: mnt_free_id(mnt); free_vfsmnt(mnt); return ERR_PTR(err); } static void cleanup_mnt(struct mount *mnt) { struct hlist_node *p; struct mount *m; /* * The warning here probably indicates that somebody messed * up a mnt_want/drop_write() pair. If this happens, the * filesystem was probably unable to make r/w->r/o transitions. * The locking used to deal with mnt_count decrement provides barriers, * so mnt_get_writers() below is safe. */ WARN_ON(mnt_get_writers(mnt)); if (unlikely(mnt->mnt_pins.first)) mnt_pin_kill(mnt); hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } fsnotify_vfsmount_delete(&mnt->mnt); dput(mnt->mnt.mnt_root); deactivate_super(mnt->mnt.mnt_sb); mnt_free_id(mnt); call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt); } static void __cleanup_mnt(struct rcu_head *head) { cleanup_mnt(container_of(head, struct mount, mnt_rcu)); } static LLIST_HEAD(delayed_mntput_list); static void delayed_mntput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_mntput_list); struct mount *m, *t; llist_for_each_entry_safe(m, t, node, mnt_llist) cleanup_mnt(m); } static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { LIST_HEAD(list); int count; rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { /* * Since we don't do lock_mount_hash() here, * ->mnt_ns can change under us. However, if it's * non-NULL, then there's a reference that won't * be dropped until after an RCU delay done after * turning ->mnt_ns NULL. So if we observe it * non-NULL under rcu_read_lock(), the reference * we are dropping is not the final one. */ mnt_add_count(mnt, -1); rcu_read_unlock(); return; } lock_mount_hash(); /* * make sure that if __legitimize_mnt() has not seen us grab * mount_lock, we'll see their refcount increment here. */ smp_mb(); mnt_add_count(mnt, -1); count = mnt_get_count(mnt); if (count != 0) { WARN_ON(count < 0); rcu_read_unlock(); unlock_mount_hash(); return; } if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) { rcu_read_unlock(); unlock_mount_hash(); return; } mnt->mnt.mnt_flags |= MNT_DOOMED; rcu_read_unlock(); list_del(&mnt->mnt_instance); if (unlikely(!list_empty(&mnt->mnt_mounts))) { struct mount *p, *tmp; list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { __put_mountpoint(unhash_mnt(p), &list); hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children); } } unlock_mount_hash(); shrink_dentry_list(&list); if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) { struct task_struct *task = current; if (likely(!(task->flags & PF_KTHREAD))) { init_task_work(&mnt->mnt_rcu, __cleanup_mnt); if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME)) return; } if (llist_add(&mnt->mnt_llist, &delayed_mntput_list)) schedule_delayed_work(&delayed_mntput_work, 1); return; } cleanup_mnt(mnt); } void mntput(struct vfsmount *mnt) { if (mnt) { struct mount *m = real_mount(mnt); /* avoid cacheline pingpong, hope gcc doesn't get "smart" */ if (unlikely(m->mnt_expiry_mark)) m->mnt_expiry_mark = 0; mntput_no_expire(m); } } EXPORT_SYMBOL(mntput); struct vfsmount *mntget(struct vfsmount *mnt) { if (mnt) mnt_add_count(real_mount(mnt), 1); return mnt; } EXPORT_SYMBOL(mntget); /* path_is_mountpoint() - Check if path is a mount in the current * namespace. * * d_mountpoint() can only be used reliably to establish if a dentry is * not mounted in any namespace and that common case is handled inline. * d_mountpoint() isn't aware of the possibility there may be multiple * mounts using a given dentry in a different namespace. This function * checks if the passed in path is a mountpoint rather than the dentry * alone. */ bool path_is_mountpoint(const struct path *path) { unsigned seq; bool res; if (!d_mountpoint(path->dentry)) return false; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); res = __path_is_mountpoint(path); } while (read_seqretry(&mount_lock, seq)); rcu_read_unlock(); return res; } EXPORT_SYMBOL(path_is_mountpoint); struct vfsmount *mnt_clone_internal(const struct path *path) { struct mount *p; p = clone_mnt(real_mount(path->mnt), path->dentry, CL_PRIVATE); if (IS_ERR(p)) return ERR_CAST(p); p->mnt.mnt_flags |= MNT_INTERNAL; return &p->mnt; } #ifdef CONFIG_PROC_FS static struct mount *mnt_list_next(struct mnt_namespace *ns, struct list_head *p) { struct mount *mnt, *ret = NULL; lock_ns_list(ns); list_for_each_continue(p, &ns->list) { mnt = list_entry(p, typeof(*mnt), mnt_list); if (!mnt_is_cursor(mnt)) { ret = mnt; break; } } unlock_ns_list(ns); return ret; } /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_mounts *p = m->private; struct list_head *prev; down_read(&namespace_sem); if (!*pos) { prev = &p->ns->list; } else { prev = &p->cursor.mnt_list; /* Read after we'd reached the end? */ if (list_empty(prev)) return NULL; } return mnt_list_next(p->ns, prev); } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct proc_mounts *p = m->private; struct mount *mnt = v; ++*pos; return mnt_list_next(p->ns, &mnt->mnt_list); } static void m_stop(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *mnt = v; lock_ns_list(p->ns); if (mnt) list_move_tail(&p->cursor.mnt_list, &mnt->mnt_list); else list_del_init(&p->cursor.mnt_list); unlock_ns_list(p->ns); up_read(&namespace_sem); } static int m_show(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *r = v; return p->show(m, &r->mnt); } const struct seq_operations mounts_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = m_show, }; void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor) { down_read(&namespace_sem); lock_ns_list(ns); list_del(&cursor->mnt_list); unlock_ns_list(ns); up_read(&namespace_sem); } #endif /* CONFIG_PROC_FS */ /** * may_umount_tree - check if a mount tree is busy * @mnt: root of mount tree * * This is called to check if a tree of mounts has any * open files, pwds, chroots or sub mounts that are * busy. */ int may_umount_tree(struct vfsmount *m) { struct mount *mnt = real_mount(m); int actual_refs = 0; int minimum_refs = 0; struct mount *p; BUG_ON(!m); /* write lock needed for mnt_get_count */ lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { actual_refs += mnt_get_count(p); minimum_refs += 2; } unlock_mount_hash(); if (actual_refs > minimum_refs) return 0; return 1; } EXPORT_SYMBOL(may_umount_tree); /** * may_umount - check if a mount point is busy * @mnt: root of mount * * This is called to check if a mount point has any * open files, pwds, chroots or sub mounts. If the * mount has sub mounts this will return busy * regardless of whether the sub mounts are busy. * * Doesn't take quota and stuff into account. IOW, in some cases it will * give false negatives. The main reason why it's here is that we need * a non-destructive way to look for easily umountable filesystems. */ int may_umount(struct vfsmount *mnt) { int ret = 1; down_read(&namespace_sem); lock_mount_hash(); if (propagate_mount_busy(real_mount(mnt), 2)) ret = 0; unlock_mount_hash(); up_read(&namespace_sem); return ret; } EXPORT_SYMBOL(may_umount); static void namespace_unlock(void) { struct hlist_head head; struct hlist_node *p; struct mount *m; LIST_HEAD(list); hlist_move_list(&unmounted, &head); list_splice_init(&ex_mountpoints, &list); up_write(&namespace_sem); shrink_dentry_list(&list); if (likely(hlist_empty(&head))) return; synchronize_rcu_expedited(); hlist_for_each_entry_safe(m, p, &head, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } } static inline void namespace_lock(void) { down_write(&namespace_sem); } enum umount_tree_flags { UMOUNT_SYNC = 1, UMOUNT_PROPAGATE = 2, UMOUNT_CONNECTED = 4, }; static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how) { /* Leaving mounts connected is only valid for lazy umounts */ if (how & UMOUNT_SYNC) return true; /* A mount without a parent has nothing to be connected to */ if (!mnt_has_parent(mnt)) return true; /* Because the reference counting rules change when mounts are * unmounted and connected, umounted mounts may not be * connected to mounted mounts. */ if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) return true; /* Has it been requested that the mount remain connected? */ if (how & UMOUNT_CONNECTED) return false; /* Is the mount locked such that it needs to remain connected? */ if (IS_MNT_LOCKED(mnt)) return false; /* By default disconnect the mount */ return true; } /* * mount_lock must be held * namespace_sem must be held for write */ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) { LIST_HEAD(tmp_list); struct mount *p; if (how & UMOUNT_PROPAGATE) propagate_mount_unlock(mnt); /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; list_move(&p->mnt_list, &tmp_list); } /* Hide the mounts from mnt_mounts */ list_for_each_entry(p, &tmp_list, mnt_list) { list_del_init(&p->mnt_child); } /* Add propogated mounts to the tmp_list */ if (how & UMOUNT_PROPAGATE) propagate_umount(&tmp_list); while (!list_empty(&tmp_list)) { struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); ns = p->mnt_ns; if (ns) { ns->mounts--; __touch_mnt_namespace(ns); } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { /* Don't forget about p */ list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); } } change_mnt_propagation(p, MS_PRIVATE); if (disconnect) hlist_add_head(&p->mnt_umount, &unmounted); } } static void shrink_submounts(struct mount *mnt); static int do_umount_root(struct super_block *sb) { int ret = 0; down_write(&sb->s_umount); if (!sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY, SB_RDONLY); if (IS_ERR(fc)) { ret = PTR_ERR(fc); } else { ret = parse_monolithic_mount_data(fc, NULL); if (!ret) ret = reconfigure_super(fc); put_fs_context(fc); } } up_write(&sb->s_umount); return ret; } static int do_umount(struct mount *mnt, int flags) { struct super_block *sb = mnt->mnt.mnt_sb; int retval; retval = security_sb_umount(&mnt->mnt, flags); if (retval) return retval; /* * Allow userspace to request a mountpoint be expired rather than * unmounting unconditionally. Unmount only happens if: * (1) the mark is already set (the mark is cleared by mntput()) * (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount] */ if (flags & MNT_EXPIRE) { if (&mnt->mnt == current->fs->root.mnt || flags & (MNT_FORCE | MNT_DETACH)) return -EINVAL; /* * probably don't strictly need the lock here if we examined * all race cases, but it's a slowpath. */ lock_mount_hash(); if (mnt_get_count(mnt) != 2) { unlock_mount_hash(); return -EBUSY; } unlock_mount_hash(); if (!xchg(&mnt->mnt_expiry_mark, 1)) return -EAGAIN; } /* * If we may have to abort operations to get out of this * mount, and they will themselves hold resources we must * allow the fs to do things. In the Unix tradition of * 'Gee thats tricky lets do it in userspace' the umount_begin * might fail to complete on the first run through as other tasks * must return, and the like. Thats for the mount program to worry * about for the moment. */ if (flags & MNT_FORCE && sb->s_op->umount_begin) { sb->s_op->umount_begin(sb); } /* * No sense to grab the lock for this test, but test itself looks * somewhat bogus. Suggestions for better replacement? * Ho-hum... In principle, we might treat that as umount + switch * to rootfs. GC would eventually take care of the old vfsmount. * Actually it makes sense, especially if rootfs would contain a * /reboot - static binary that would close all descriptors and * call reboot(9). Then init(8) could umount root and exec /reboot. */ if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) { /* * Special case for "unmounting" root ... * we just try to remount it readonly. */ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return do_umount_root(sb); } namespace_lock(); lock_mount_hash(); /* Recheck MNT_LOCKED with the locks held */ retval = -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) goto out; event++; if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } } out: unlock_mount_hash(); namespace_unlock(); return retval; } /* * __detach_mounts - lazily unmount all mounts on the specified dentry * * During unlink, rmdir, and d_drop it is possible to loose the path * to an existing mountpoint, and wind up leaking the mount. * detach_mounts allows lazily unmounting those mounts instead of * leaking them. * * The caller may hold dentry->d_inode->i_mutex. */ void __detach_mounts(struct dentry *dentry) { struct mountpoint *mp; struct mount *mnt; namespace_lock(); lock_mount_hash(); mp = lookup_mountpoint(dentry); if (!mp) goto out_unlock; event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { umount_mnt(mnt); hlist_add_head(&mnt->mnt_umount, &unmounted); } else umount_tree(mnt, UMOUNT_CONNECTED); } put_mountpoint(mp); out_unlock: unlock_mount_hash(); namespace_unlock(); } /* * Is the caller allowed to modify his namespace? */ static inline bool may_mount(void) { return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } #ifdef CONFIG_MANDATORY_FILE_LOCKING static bool may_mandlock(void) { pr_warn_once("======================================================\n" "WARNING: the mand mount option is being deprecated and\n" " will be removed in v5.15!\n" "======================================================\n"); return capable(CAP_SYS_ADMIN); } #else static inline bool may_mandlock(void) { pr_warn("VFS: \"mand\" mount option not supported"); return false; } #endif static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); if (!may_mount()) return -EPERM; if (path->dentry != path->mnt->mnt_root) return -EINVAL; if (!check_mnt(mnt)) return -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ return -EINVAL; if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } // caller is responsible for flags being sane int path_umount(struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); int ret; ret = can_umount(path, flags); if (!ret) ret = do_umount(mnt, flags); /* we mustn't call path_put() as that would clear mnt_expiry_mark */ dput(path->dentry); mntput_no_expire(mnt); return ret; } static int ksys_umount(char __user *name, int flags) { int lookup_flags = LOOKUP_MOUNTPOINT; struct path path; int ret; // basic validity checks done first if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) return -EINVAL; if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; ret = user_path_at(AT_FDCWD, name, lookup_flags, &path); if (ret) return ret; return path_umount(&path, flags); } SYSCALL_DEFINE2(umount, char __user *, name, int, flags) { return ksys_umount(name, flags); } #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* * The 2.0 compatible umount. No flags. */ SYSCALL_DEFINE1(oldumount, char __user *, name) { return ksys_umount(name, 0); } #endif static bool is_mnt_ns_file(struct dentry *dentry) { /* Is this a proxy for a mount namespace? */ return dentry->d_op == &ns_dentry_operations && dentry->d_fsdata == &mntns_operations; } static struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) { return &mnt->ns; } static bool mnt_ns_loop(struct dentry *dentry) { /* Could bind mounting the mount namespace inode cause a * mount namespace loop? */ struct mnt_namespace *mnt_ns; if (!is_mnt_ns_file(dentry)) return false; mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode)); return current->nsproxy->mnt_ns->seq >= mnt_ns->seq; } struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, int flag) { struct mount *res, *p, *q, *r, *parent; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(mnt)) return ERR_PTR(-EINVAL); if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry)) return ERR_PTR(-EINVAL); res = q = clone_mnt(mnt, dentry, flag); if (IS_ERR(q)) return q; q->mnt_mountpoint = mnt->mnt_mountpoint; p = mnt; list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) { struct mount *s; if (!is_subdir(r->mnt_mountpoint, dentry)) continue; for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { if (s->mnt.mnt_flags & MNT_LOCKED) { /* Both unbindable and locked. */ q = ERR_PTR(-EPERM); goto out; } else { s = skip_mnt_tree(s); continue; } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { s = skip_mnt_tree(s); continue; } while (p != s->mnt_parent) { p = p->mnt_parent; q = q->mnt_parent; } p = s; parent = q; q = clone_mnt(p, p->mnt.mnt_root, flag); if (IS_ERR(q)) goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); attach_mnt(q, parent, p->mnt_mp); unlock_mount_hash(); } } return res; out: if (res) { lock_mount_hash(); umount_tree(res, UMOUNT_SYNC); unlock_mount_hash(); } return q; } /* Caller should check returned pointer for errors */ struct vfsmount *collect_mounts(const struct path *path) { struct mount *tree; namespace_lock(); if (!check_mnt(real_mount(path->mnt))) tree = ERR_PTR(-EINVAL); else tree = copy_tree(real_mount(path->mnt), path->dentry, CL_COPY_ALL | CL_PRIVATE); namespace_unlock(); if (IS_ERR(tree)) return ERR_CAST(tree); return &tree->mnt; } static void free_mnt_ns(struct mnt_namespace *); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool); void dissolve_on_fput(struct vfsmount *mnt) { struct mnt_namespace *ns; namespace_lock(); lock_mount_hash(); ns = real_mount(mnt)->mnt_ns; if (ns) { if (is_anon_ns(ns)) umount_tree(real_mount(mnt), UMOUNT_CONNECTED); else ns = NULL; } unlock_mount_hash(); namespace_unlock(); if (ns) free_mnt_ns(ns); } void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } static bool has_locked_children(struct mount *mnt, struct dentry *dentry) { struct mount *child; list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { if (!is_subdir(child->mnt_mountpoint, dentry)) continue; if (child->mnt.mnt_flags & MNT_LOCKED) return true; } return false; } /** * clone_private_mount - create a private clone of a path * * This creates a new vfsmount, which will be the clone of @path. The new will * not be attached anywhere in the namespace and will be private (i.e. changes * to the originating mount won't be propagated into this). * * Release with mntput(). */ struct vfsmount *clone_private_mount(const struct path *path) { struct mount *old_mnt = real_mount(path->mnt); struct mount *new_mnt; down_read(&namespace_sem); if (IS_MNT_UNBINDABLE(old_mnt)) goto invalid; if (!check_mnt(old_mnt)) goto invalid; if (has_locked_children(old_mnt, path->dentry)) goto invalid; new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); up_read(&namespace_sem); if (IS_ERR(new_mnt)) return ERR_CAST(new_mnt); /* Longterm mount to be removed by kern_unmount*() */ new_mnt->mnt_ns = MNT_NS_INTERNAL; return &new_mnt->mnt; invalid: up_read(&namespace_sem); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(clone_private_mount); int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { struct mount *mnt; int res = f(root, arg); if (res) return res; list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) { res = f(&mnt->mnt, arg); if (res) return res; } return 0; } static void lock_mnt_tree(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { int flags = p->mnt.mnt_flags; /* Don't allow unprivileged users to change mount flags */ flags |= MNT_LOCK_ATIME; if (flags & MNT_READONLY) flags |= MNT_LOCK_READONLY; if (flags & MNT_NODEV) flags |= MNT_LOCK_NODEV; if (flags & MNT_NOSUID) flags |= MNT_LOCK_NOSUID; if (flags & MNT_NOEXEC) flags |= MNT_LOCK_NOEXEC; /* Don't allow unprivileged users to reveal what is under a mount */ if (list_empty(&p->mnt_expire)) flags |= MNT_LOCKED; p->mnt.mnt_flags = flags; } } static void cleanup_group_ids(struct mount *mnt, struct mount *end) { struct mount *p; for (p = mnt; p != end; p = next_mnt(p, mnt)) { if (p->mnt_group_id && !IS_MNT_SHARED(p)) mnt_release_group_id(p); } } static int invent_group_ids(struct mount *mnt, bool recurse) { struct mount *p; for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) { if (!p->mnt_group_id && !IS_MNT_SHARED(p)) { int err = mnt_alloc_group_id(p); if (err) { cleanup_group_ids(mnt, p); return err; } } } return 0; } int count_mounts(struct mnt_namespace *ns, struct mount *mnt) { unsigned int max = READ_ONCE(sysctl_mount_max); unsigned int mounts = 0, old, pending, sum; struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) mounts++; old = ns->mounts; pending = ns->pending_mounts; sum = old + pending; if ((old > sum) || (pending > sum) || (max < sum) || (mounts > (max - sum))) return -ENOSPC; ns->pending_mounts = pending + mounts; return 0; } /* * @source_mnt : mount tree to be attached * @nd : place the mount tree @source_mnt is attached * @parent_nd : if non-null, detach the source_mnt from its parent and * store the parent mount and mountpoint dentry. * (done when source_mnt is moved) * * NOTE: in the table below explains the semantics when a source mount * of a given type is attached to a destination mount of a given type. * --------------------------------------------------------------------------- * | BIND MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (++) | shared (+) | shared(+++)| invalid | * | | | | | | * |non-shared| shared (+) | private | slave (*) | invalid | * *************************************************************************** * A bind operation clones the source mount and mounts the clone on the * destination mount. * * (++) the cloned mount is propagated to all the mounts in the propagation * tree of the destination mount and the cloned mount is added to * the peer group of the source mount. * (+) the cloned mount is created under the destination mount and is marked * as shared. The cloned mount is added to the peer group of the source * mount. * (+++) the mount is propagated to all the mounts in the propagation tree * of the destination mount and the cloned mount is made slave * of the same master as that of the source mount. The cloned mount * is marked as 'shared and slave'. * (*) the cloned mount is made a slave of the same master as that of the * source mount. * * --------------------------------------------------------------------------- * | MOVE MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (+) | shared (+) | shared(+++) | invalid | * | | | | | | * |non-shared| shared (+*) | private | slave (*) | unbindable | * *************************************************************************** * * (+) the mount is moved to the destination. And is then propagated to * all the mounts in the propagation tree of the destination mount. * (+*) the mount is moved to the destination. * (+++) the mount is moved to the destination and is then propagated to * all the mounts belonging to the destination mount's propagation tree. * the mount is marked as 'shared and slave'. * (*) the mount continues to be a slave at the new location. * * if the source mount is a tree, the operations explained above is * applied to each mount in the tree. * Must be called without spinlocks held, since this function can sleep * in allocations. */ static int attach_recursive_mnt(struct mount *source_mnt, struct mount *dest_mnt, struct mountpoint *dest_mp, bool moving) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; HLIST_HEAD(tree_list); struct mnt_namespace *ns = dest_mnt->mnt_ns; struct mountpoint *smp; struct mount *child, *p; struct hlist_node *n; int err; /* Preallocate a mountpoint in case the new mounts need * to be tucked under other mounts. */ smp = get_mountpoint(source_mnt->mnt.mnt_root); if (IS_ERR(smp)) return PTR_ERR(smp); /* Is there space to add these mounts to the mount namespace? */ if (!moving) { err = count_mounts(ns, source_mnt); if (err) goto out; } if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); lock_mount_hash(); if (err) goto out_cleanup_ids; for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); } else { lock_mount_hash(); } if (moving) { unhash_mnt(source_mnt); attach_mnt(source_mnt, dest_mnt, dest_mp); touch_mnt_namespace(source_mnt->mnt_ns); } else { if (source_mnt->mnt_ns) { /* move from anon - the caller will destroy */ list_del_init(&source_mnt->mnt_ns->list); } mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); commit_tree(source_mnt); } hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); q = __lookup_mnt(&child->mnt_parent->mnt, child->mnt_mountpoint); if (q) mnt_change_mountpoint(child, smp, q); /* Notice when we are propagating across user namespaces */ if (child->mnt_parent->mnt_ns->user_ns != user_ns) lock_mnt_tree(child); child->mnt.mnt_flags &= ~MNT_LOCKED; commit_tree(child); } put_mountpoint(smp); unlock_mount_hash(); return 0; out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: ns->pending_mounts = 0; read_seqlock_excl(&mount_lock); put_mountpoint(smp); read_sequnlock_excl(&mount_lock); return err; } static struct mountpoint *lock_mount(struct path *path) { struct vfsmount *mnt; struct dentry *dentry = path->dentry; retry: inode_lock(dentry->d_inode); if (unlikely(cant_mount(dentry))) { inode_unlock(dentry->d_inode); return ERR_PTR(-ENOENT); } namespace_lock(); mnt = lookup_mnt(path); if (likely(!mnt)) { struct mountpoint *mp = get_mountpoint(dentry); if (IS_ERR(mp)) { namespace_unlock(); inode_unlock(dentry->d_inode); return mp; } return mp; } namespace_unlock(); inode_unlock(path->dentry->d_inode); path_put(path); path->mnt = mnt; dentry = path->dentry = dget(mnt->mnt_root); goto retry; } static void unlock_mount(struct mountpoint *where) { struct dentry *dentry = where->m_dentry; read_seqlock_excl(&mount_lock); put_mountpoint(where); read_sequnlock_excl(&mount_lock); namespace_unlock(); inode_unlock(dentry->d_inode); } static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) { if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER) return -EINVAL; if (d_is_dir(mp->m_dentry) != d_is_dir(mnt->mnt.mnt_root)) return -ENOTDIR; return attach_recursive_mnt(mnt, p, mp, false); } /* * Sanity check the flags to change_mnt_propagation. */ static int flags_to_propagation_type(int ms_flags) { int type = ms_flags & ~(MS_REC | MS_SILENT); /* Fail if any non-propagation flags are set */ if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return 0; /* Only one propagation flag should be set */ if (!is_power_of_2(type)) return 0; return type; } /* * recursively change the type of the mountpoint. */ static int do_change_type(struct path *path, int ms_flags) { struct mount *m; struct mount *mnt = real_mount(path->mnt); int recurse = ms_flags & MS_REC; int type; int err = 0; if (path->dentry != path->mnt->mnt_root) return -EINVAL; type = flags_to_propagation_type(ms_flags); if (!type) return -EINVAL; namespace_lock(); if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) goto out_unlock; } lock_mount_hash(); for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL)) change_mnt_propagation(m, type); unlock_mount_hash(); out_unlock: namespace_unlock(); return err; } static struct mount *__do_loopback(struct path *old_path, int recurse) { struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt); if (IS_MNT_UNBINDABLE(old)) return mnt; if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations) return mnt; if (!recurse && has_locked_children(old, old_path->dentry)) return mnt; if (recurse) mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE); else mnt = clone_mnt(old, old_path->dentry, 0); if (!IS_ERR(mnt)) mnt->mnt.mnt_flags &= ~MNT_LOCKED; return mnt; } /* * do loopback mount. */ static int do_loopback(struct path *path, const char *old_name, int recurse) { struct path old_path; struct mount *mnt = NULL, *parent; struct mountpoint *mp; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path); if (err) return err; err = -EINVAL; if (mnt_ns_loop(old_path.dentry)) goto out; mp = lock_mount(path); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto out; } parent = real_mount(path->mnt); if (!check_mnt(parent)) goto out2; mnt = __do_loopback(&old_path, recurse); if (IS_ERR(mnt)) { err = PTR_ERR(mnt); goto out2; } err = graft_tree(mnt, parent, mp); if (err) { lock_mount_hash(); umount_tree(mnt, UMOUNT_SYNC); unlock_mount_hash(); } out2: unlock_mount(mp); out: path_put(&old_path); return err; } static struct file *open_detached_copy(struct path *path, bool recursive) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct mnt_namespace *ns = alloc_mnt_ns(user_ns, true); struct mount *mnt, *p; struct file *file; if (IS_ERR(ns)) return ERR_CAST(ns); namespace_lock(); mnt = __do_loopback(path, recursive); if (IS_ERR(mnt)) { namespace_unlock(); free_mnt_ns(ns); return ERR_CAST(mnt); } lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt_ns = ns; ns->mounts++; } ns->root = mnt; list_add_tail(&ns->list, &mnt->mnt_list); mntget(&mnt->mnt); unlock_mount_hash(); namespace_unlock(); mntput(path->mnt); path->mnt = &mnt->mnt; file = dentry_open(path, O_PATH, current_cred()); if (IS_ERR(file)) dissolve_on_fput(path->mnt); else file->f_mode |= FMODE_NEED_UNMOUNT; return file; } SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags) { struct file *file; struct path path; int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; bool detached = flags & OPEN_TREE_CLONE; int error; int fd; BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC); if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC)) return -EINVAL; if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE) return -EINVAL; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (detached && !may_mount()) return -EPERM; fd = get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) return fd; error = user_path_at(dfd, filename, lookup_flags, &path); if (unlikely(error)) { file = ERR_PTR(error); } else { if (detached) file = open_detached_copy(&path, flags & AT_RECURSIVE); else file = dentry_open(&path, O_PATH, current_cred()); path_put(&path); } if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } fd_install(fd, file); return fd; } /* * Don't allow locked mount flags to be cleared. * * No locks need to be held here while testing the various MNT_LOCK * flags because those flags can never be cleared once they are set. */ static bool can_change_locked_flags(struct mount *mnt, unsigned int mnt_flags) { unsigned int fl = mnt->mnt.mnt_flags; if ((fl & MNT_LOCK_READONLY) && !(mnt_flags & MNT_READONLY)) return false; if ((fl & MNT_LOCK_NODEV) && !(mnt_flags & MNT_NODEV)) return false; if ((fl & MNT_LOCK_NOSUID) && !(mnt_flags & MNT_NOSUID)) return false; if ((fl & MNT_LOCK_NOEXEC) && !(mnt_flags & MNT_NOEXEC)) return false; if ((fl & MNT_LOCK_ATIME) && ((fl & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) return false; return true; } static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags) { bool readonly_request = (mnt_flags & MNT_READONLY); if (readonly_request == __mnt_is_readonly(&mnt->mnt)) return 0; if (readonly_request) return mnt_make_readonly(mnt); return __mnt_unmake_readonly(mnt); } /* * Update the user-settable attributes on a mount. The caller must hold * sb->s_umount for writing. */ static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags) { lock_mount_hash(); mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; mnt->mnt.mnt_flags = mnt_flags; touch_mnt_namespace(mnt->mnt_ns); unlock_mount_hash(); } static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; if (!__mnt_is_readonly(mnt) && (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) { char *buf = (char *)__get_free_page(GFP_KERNEL); char *mntpath = buf ? d_path(mountpoint, buf, PAGE_SIZE) : ERR_PTR(-ENOMEM); struct tm tm; time64_to_tm(sb->s_time_max, 0, &tm); pr_warn("%s filesystem being %s at %s supports timestamps until %04ld (0x%llx)\n", sb->s_type->name, is_mounted(mnt) ? "remounted" : "mounted", mntpath, tm.tm_year+1900, (unsigned long long)sb->s_time_max); free_page((unsigned long)buf); } } /* * Handle reconfiguration of the mountpoint only without alteration of the * superblock it refers to. This is triggered by specifying MS_REMOUNT|MS_BIND * to mount(2). */ static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags) { struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); int ret; if (!check_mnt(mnt)) return -EINVAL; if (path->dentry != mnt->mnt.mnt_root) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; down_write(&sb->s_umount); ret = change_mount_ro_state(mnt, mnt_flags); if (ret == 0) set_mount_attributes(mnt, mnt_flags); up_write(&sb->s_umount); mnt_warn_timestamp_expiry(path, &mnt->mnt); return ret; } /* * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. */ static int do_remount(struct path *path, int ms_flags, int sb_flags, int mnt_flags, void *data) { int err; struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); struct fs_context *fc; if (!check_mnt(mnt)) return -EINVAL; if (path->dentry != path->mnt->mnt_root) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; fc = fs_context_for_reconfigure(path->dentry, sb_flags, MS_RMT_MASK); if (IS_ERR(fc)) return PTR_ERR(fc); fc->oldapi = true; err = parse_monolithic_mount_data(fc, data); if (!err) { down_write(&sb->s_umount); err = -EPERM; if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { err = reconfigure_super(fc); if (!err) set_mount_attributes(mnt, mnt_flags); } up_write(&sb->s_umount); } mnt_warn_timestamp_expiry(path, &mnt->mnt); put_fs_context(fc); return err; } static inline int tree_contains_unbindable(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { if (IS_MNT_UNBINDABLE(p)) return 1; } return 0; } /* * Check that there aren't references to earlier/same mount namespaces in the * specified subtree. Such references can act as pins for mount namespaces * that aren't checked by the mount-cycle checking code, thereby allowing * cycles to be made. */ static bool check_for_nsfs_mounts(struct mount *subtree) { struct mount *p; bool ret = false; lock_mount_hash(); for (p = subtree; p; p = next_mnt(p, subtree)) if (mnt_ns_loop(p->mnt.mnt_root)) goto out; ret = true; out: unlock_mount_hash(); return ret; } static int do_move_mount(struct path *old_path, struct path *new_path) { struct mnt_namespace *ns; struct mount *p; struct mount *old; struct mount *parent; struct mountpoint *mp, *old_mp; int err; bool attached; mp = lock_mount(new_path); if (IS_ERR(mp)) return PTR_ERR(mp); old = real_mount(old_path->mnt); p = real_mount(new_path->mnt); parent = old->mnt_parent; attached = mnt_has_parent(old); old_mp = old->mnt_mp; ns = old->mnt_ns; err = -EINVAL; /* The mountpoint must be in our namespace. */ if (!check_mnt(p)) goto out; /* The thing moved must be mounted... */ if (!is_mounted(&old->mnt)) goto out; /* ... and either ours or the root of anon namespace */ if (!(attached ? check_mnt(old) : is_anon_ns(ns))) goto out; if (old->mnt.mnt_flags & MNT_LOCKED) goto out; if (old_path->dentry != old_path->mnt->mnt_root) goto out; if (d_is_dir(new_path->dentry) != d_is_dir(old_path->dentry)) goto out; /* * Don't move a mount residing in a shared parent. */ if (attached && IS_MNT_SHARED(parent)) goto out; /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. */ if (IS_MNT_SHARED(p) && tree_contains_unbindable(old)) goto out; err = -ELOOP; if (!check_for_nsfs_mounts(old)) goto out; for (; mnt_has_parent(p); p = p->mnt_parent) if (p == old) goto out; err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, attached); if (err) goto out; /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old->mnt_expire); if (attached) put_mountpoint(old_mp); out: unlock_mount(mp); if (!err) { if (attached) mntput_no_expire(parent); else free_mnt_ns(ns); } return err; } static int do_move_mount_old(struct path *path, const char *old_name) { struct path old_path; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); if (err) return err; err = do_move_mount(&old_path, path); path_put(&old_path); return err; } /* * add a mount into a namespace's mount tree */ static int do_add_mount(struct mount *newmnt, struct mountpoint *mp, struct path *path, int mnt_flags) { struct mount *parent = real_mount(path->mnt); mnt_flags &= ~MNT_INTERNAL_FLAGS; if (unlikely(!check_mnt(parent))) { /* that's acceptable only for automounts done in private ns */ if (!(mnt_flags & MNT_SHRINKABLE)) return -EINVAL; /* ... and for those we'd better have mountpoint still alive */ if (!parent->mnt_ns) return -EINVAL; } /* Refuse the same filesystem on the same mount point */ if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb && path->mnt->mnt_root == path->dentry) return -EBUSY; if (d_is_symlink(newmnt->mnt.mnt_root)) return -EINVAL; newmnt->mnt.mnt_flags = mnt_flags; return graft_tree(newmnt, parent, mp); } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags); /* * Create a new mount using a superblock configuration and request it * be added to the namespace tree. */ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint, unsigned int mnt_flags) { struct vfsmount *mnt; struct mountpoint *mp; struct super_block *sb = fc->root->d_sb; int error; error = security_sb_kern_mount(sb); if (!error && mount_too_revealing(sb, &mnt_flags)) error = -EPERM; if (unlikely(error)) { fc_drop_locked(fc); return error; } up_write(&sb->s_umount); mnt = vfs_create_mount(fc); if (IS_ERR(mnt)) return PTR_ERR(mnt); mnt_warn_timestamp_expiry(mountpoint, mnt); mp = lock_mount(mountpoint); if (IS_ERR(mp)) { mntput(mnt); return PTR_ERR(mp); } error = do_add_mount(real_mount(mnt), mp, mountpoint, mnt_flags); unlock_mount(mp); if (error < 0) mntput(mnt); return error; } /* * create a new mount for userspace and request it to be added into the * namespace's tree */ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, int mnt_flags, const char *name, void *data) { struct file_system_type *type; struct fs_context *fc; const char *subtype = NULL; int err = 0; if (!fstype) return -EINVAL; type = get_fs_type(fstype); if (!type) return -ENODEV; if (type->fs_flags & FS_HAS_SUBTYPE) { subtype = strchr(fstype, '.'); if (subtype) { subtype++; if (!*subtype) { put_filesystem(type); return -EINVAL; } } } fc = fs_context_for_mount(type, sb_flags); put_filesystem(type); if (IS_ERR(fc)) return PTR_ERR(fc); if (subtype) err = vfs_parse_fs_string(fc, "subtype", subtype, strlen(subtype)); if (!err && name) err = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!err) err = parse_monolithic_mount_data(fc, data); if (!err && !mount_capable(fc)) err = -EPERM; if (!err) err = vfs_get_tree(fc); if (!err) err = do_new_mount_fc(fc, path, mnt_flags); put_fs_context(fc); return err; } int finish_automount(struct vfsmount *m, struct path *path) { struct dentry *dentry = path->dentry; struct mountpoint *mp; struct mount *mnt; int err; if (!m) return 0; if (IS_ERR(m)) return PTR_ERR(m); mnt = real_mount(m); /* The new mount record should have at least 2 refs to prevent it being * expired before we get a chance to add it */ BUG_ON(mnt_get_count(mnt) < 2); if (m->mnt_sb == path->mnt->mnt_sb && m->mnt_root == dentry) { err = -ELOOP; goto discard; } /* * we don't want to use lock_mount() - in this case finding something * that overmounts our mountpoint to be means "quitely drop what we've * got", not "try to mount it on top". */ inode_lock(dentry->d_inode); namespace_lock(); if (unlikely(cant_mount(dentry))) { err = -ENOENT; goto discard_locked; } rcu_read_lock(); if (unlikely(__lookup_mnt(path->mnt, dentry))) { rcu_read_unlock(); err = 0; goto discard_locked; } rcu_read_unlock(); mp = get_mountpoint(dentry); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto discard_locked; } err = do_add_mount(mnt, mp, path, path->mnt->mnt_flags | MNT_SHRINKABLE); unlock_mount(mp); if (unlikely(err)) goto discard; mntput(m); return 0; discard_locked: namespace_unlock(); inode_unlock(dentry->d_inode); discard: /* remove m from any expiration list it may be on */ if (!list_empty(&mnt->mnt_expire)) { namespace_lock(); list_del_init(&mnt->mnt_expire); namespace_unlock(); } mntput(m); mntput(m); return err; } /** * mnt_set_expiry - Put a mount on an expiration list * @mnt: The mount to list. * @expiry_list: The list to add the mount to. */ void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list) { namespace_lock(); list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list); namespace_unlock(); } EXPORT_SYMBOL(mnt_set_expiry); /* * process a list of expirable mountpoints with the intent of discarding any * mountpoints that aren't in use and haven't been touched since last we came * here */ void mark_mounts_for_expiry(struct list_head *mounts) { struct mount *mnt, *next; LIST_HEAD(graveyard); if (list_empty(mounts)) return; namespace_lock(); lock_mount_hash(); /* extract from the expiration list every vfsmount that matches the * following criteria: * - only referenced by its parent vfsmount * - still marked for expiry (marked on the last call here; marks are * cleared by mntput()) */ list_for_each_entry_safe(mnt, next, mounts, mnt_expire) { if (!xchg(&mnt->mnt_expiry_mark, 1) || propagate_mount_busy(mnt, 1)) continue; list_move(&mnt->mnt_expire, &graveyard); } while (!list_empty(&graveyard)) { mnt = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(mnt->mnt_ns); umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); } unlock_mount_hash(); namespace_unlock(); } EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); /* * Ripoff of 'select_parent()' * * search the list of submounts for a given mountpoint, and move any * shrinkable submounts to the 'graveyard' list. */ static int select_submounts(struct mount *parent, struct list_head *graveyard) { struct mount *this_parent = parent; struct list_head *next; int found = 0; repeat: next = this_parent->mnt_mounts.next; resume: while (next != &this_parent->mnt_mounts) { struct list_head *tmp = next; struct mount *mnt = list_entry(tmp, struct mount, mnt_child); next = tmp->next; if (!(mnt->mnt.mnt_flags & MNT_SHRINKABLE)) continue; /* * Descend a level if the d_mounts list is non-empty. */ if (!list_empty(&mnt->mnt_mounts)) { this_parent = mnt; goto repeat; } if (!propagate_mount_busy(mnt, 1)) { list_move_tail(&mnt->mnt_expire, graveyard); found++; } } /* * All done at this level ... ascend and resume the search */ if (this_parent != parent) { next = this_parent->mnt_child.next; this_parent = this_parent->mnt_parent; goto resume; } return found; } /* * process a list of expirable mountpoints with the intent of discarding any * submounts of a specific parent mountpoint * * mount_lock must be held for write */ static void shrink_submounts(struct mount *mnt) { LIST_HEAD(graveyard); struct mount *m; /* extract submounts of 'mountpoint' from the expiration list */ while (select_submounts(mnt, &graveyard)) { while (!list_empty(&graveyard)) { m = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(m->mnt_ns); umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC); } } } static void *copy_mount_options(const void __user * data) { char *copy; unsigned left, offset; if (!data) return NULL; copy = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!copy) return ERR_PTR(-ENOMEM); left = copy_from_user(copy, data, PAGE_SIZE); /* * Not all architectures have an exact copy_from_user(). Resort to * byte at a time. */ offset = PAGE_SIZE - left; while (left) { char c; if (get_user(c, (const char __user *)data + offset)) break; copy[offset] = c; left--; offset++; } if (left == PAGE_SIZE) { kfree(copy); return ERR_PTR(-EFAULT); } return copy; } static char *copy_mount_string(const void __user *data) { return data ? strndup_user(data, PATH_MAX) : NULL; } /* * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to * be given to the mount() call (ie: read-only, no-dev, no-suid etc). * * data is a (void *) that can point to any structure up to * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent * information (or be NULL). * * Pre-0.97 versions of mount() didn't have a flags word. * When the flags word was introduced its top half was required * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9. * Therefore, if this magic number is present, it carries no information * and must be discarded. */ int path_mount(const char *dev_name, struct path *path, const char *type_page, unsigned long flags, void *data_page) { unsigned int mnt_flags = 0, sb_flags; int ret; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; /* Basic sanity checks */ if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; if (flags & MS_NOUSER) return -EINVAL; ret = security_sb_mount(dev_name, path, type_page, flags, data_page); if (ret) return ret; if (!may_mount()) return -EPERM; if ((flags & SB_MANDLOCK) && !may_mandlock()) return -EPERM; /* Default to relatime unless overriden */ if (!(flags & MS_NOATIME)) mnt_flags |= MNT_RELATIME; /* Separate the per-mountpoint flags */ if (flags & MS_NOSUID) mnt_flags |= MNT_NOSUID; if (flags & MS_NODEV) mnt_flags |= MNT_NODEV; if (flags & MS_NOEXEC) mnt_flags |= MNT_NOEXEC; if (flags & MS_NOATIME) mnt_flags |= MNT_NOATIME; if (flags & MS_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (flags & MS_STRICTATIME) mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; if (flags & MS_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; /* The default atime for remount is preservation */ if ((flags & MS_REMOUNT) && ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME | MS_STRICTATIME)) == 0)) { mnt_flags &= ~MNT_ATIME_MASK; mnt_flags |= path->mnt->mnt_flags & MNT_ATIME_MASK; } sb_flags = flags & (SB_RDONLY | SB_SYNCHRONOUS | SB_MANDLOCK | SB_DIRSYNC | SB_SILENT | SB_POSIXACL | SB_LAZYTIME | SB_I_VERSION); if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND)) return do_reconfigure_mnt(path, mnt_flags); if (flags & MS_REMOUNT) return do_remount(path, flags, sb_flags, mnt_flags, data_page); if (flags & MS_BIND) return do_loopback(path, dev_name, flags & MS_REC); if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return do_change_type(path, flags); if (flags & MS_MOVE) return do_move_mount_old(path, dev_name); return do_new_mount(path, type_page, sb_flags, mnt_flags, dev_name, data_page); } long do_mount(const char *dev_name, const char __user *dir_name, const char *type_page, unsigned long flags, void *data_page) { struct path path; int ret; ret = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path); if (ret) return ret; ret = path_mount(dev_name, &path, type_page, flags, data_page); path_put(&path); return ret; } static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_MNT_NAMESPACES); } static void dec_mnt_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_MNT_NAMESPACES); } static void free_mnt_ns(struct mnt_namespace *ns) { if (!is_anon_ns(ns)) ns_free_inum(&ns->ns); dec_mnt_namespaces(ns->ucounts); put_user_ns(ns->user_ns); kfree(ns); } /* * Assign a sequence number so we can detect when we attempt to bind * mount a reference to an older mount namespace into the current * mount namespace, preventing reference counting loops. A 64bit * number incrementing at 10Ghz will take 12,427 years to wrap which * is effectively never, so we can ignore the possibility. */ static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool anon) { struct mnt_namespace *new_ns; struct ucounts *ucounts; int ret; ucounts = inc_mnt_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL); if (!new_ns) { dec_mnt_namespaces(ucounts); return ERR_PTR(-ENOMEM); } if (!anon) { ret = ns_alloc_inum(&new_ns->ns); if (ret) { kfree(new_ns); dec_mnt_namespaces(ucounts); return ERR_PTR(ret); } } new_ns->ns.ops = &mntns_operations; if (!anon) new_ns->seq = atomic64_add_return(1, &mnt_ns_seq); atomic_set(&new_ns->count, 1); INIT_LIST_HEAD(&new_ns->list); init_waitqueue_head(&new_ns->poll); spin_lock_init(&new_ns->ns_lock); new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; return new_ns; } __latent_entropy struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, struct user_namespace *user_ns, struct fs_struct *new_fs) { struct mnt_namespace *new_ns; struct vfsmount *rootmnt = NULL, *pwdmnt = NULL; struct mount *p, *q; struct mount *old; struct mount *new; int copy_flags; BUG_ON(!ns); if (likely(!(flags & CLONE_NEWNS))) { get_mnt_ns(ns); return ns; } old = ns->root; new_ns = alloc_mnt_ns(user_ns, false); if (IS_ERR(new_ns)) return new_ns; namespace_lock(); /* First pass: copy the tree topology */ copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE; if (user_ns != ns->user_ns) copy_flags |= CL_SHARED_TO_SLAVE; new = copy_tree(old, old->mnt.mnt_root, copy_flags); if (IS_ERR(new)) { namespace_unlock(); free_mnt_ns(new_ns); return ERR_CAST(new); } if (user_ns != ns->user_ns) { lock_mount_hash(); lock_mnt_tree(new); unlock_mount_hash(); } new_ns->root = new; list_add_tail(&new_ns->list, &new->mnt_list); /* * Second pass: switch the tsk->fs->* elements and mark new vfsmounts * as belonging to new namespace. We have already acquired a private * fs_struct, so tsk->fs->lock is not needed. */ p = old; q = new; while (p) { q->mnt_ns = new_ns; new_ns->mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); rootmnt = &p->mnt; } if (&p->mnt == new_fs->pwd.mnt) { new_fs->pwd.mnt = mntget(&q->mnt); pwdmnt = &p->mnt; } } p = next_mnt(p, old); q = next_mnt(q, new); if (!q) break; while (p->mnt.mnt_root != q->mnt.mnt_root) p = next_mnt(p, old); } namespace_unlock(); if (rootmnt) mntput(rootmnt); if (pwdmnt) mntput(pwdmnt); return new_ns; } struct dentry *mount_subtree(struct vfsmount *m, const char *name) { struct mount *mnt = real_mount(m); struct mnt_namespace *ns; struct super_block *s; struct path path; int err; ns = alloc_mnt_ns(&init_user_ns, true); if (IS_ERR(ns)) { mntput(m); return ERR_CAST(ns); } mnt->mnt_ns = ns; ns->root = mnt; ns->mounts++; list_add(&mnt->mnt_list, &ns->list); err = vfs_path_lookup(m->mnt_root, m, name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); put_mnt_ns(ns); if (err) return ERR_PTR(err); /* trade a vfsmount reference for active sb one */ s = path.mnt->mnt_sb; atomic_inc(&s->s_active); mntput(path.mnt); /* lock the sucker */ down_write(&s->s_umount); /* ... and return the root of (sub)tree on it */ return path.dentry; } EXPORT_SYMBOL(mount_subtree); SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, char __user *, type, unsigned long, flags, void __user *, data) { int ret; char *kernel_type; char *kernel_dev; void *options; kernel_type = copy_mount_string(type); ret = PTR_ERR(kernel_type); if (IS_ERR(kernel_type)) goto out_type; kernel_dev = copy_mount_string(dev_name); ret = PTR_ERR(kernel_dev); if (IS_ERR(kernel_dev)) goto out_dev; options = copy_mount_options(data); ret = PTR_ERR(options); if (IS_ERR(options)) goto out_data; ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options); kfree(options); out_data: kfree(kernel_dev); out_dev: kfree(kernel_type); out_type: return ret; } /* * Create a kernel mount representation for a new, prepared superblock * (specified by fs_fd) and attach to an open_tree-like file descriptor. */ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, unsigned int, attr_flags) { struct mnt_namespace *ns; struct fs_context *fc; struct file *file; struct path newmount; struct mount *mnt; struct fd f; unsigned int mnt_flags = 0; long ret; if (!may_mount()) return -EPERM; if ((flags & ~(FSMOUNT_CLOEXEC)) != 0) return -EINVAL; if (attr_flags & ~(MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME)) return -EINVAL; if (attr_flags & MOUNT_ATTR_RDONLY) mnt_flags |= MNT_READONLY; if (attr_flags & MOUNT_ATTR_NOSUID) mnt_flags |= MNT_NOSUID; if (attr_flags & MOUNT_ATTR_NODEV) mnt_flags |= MNT_NODEV; if (attr_flags & MOUNT_ATTR_NOEXEC) mnt_flags |= MNT_NOEXEC; if (attr_flags & MOUNT_ATTR_NODIRATIME) mnt_flags |= MNT_NODIRATIME; switch (attr_flags & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_STRICTATIME: break; case MOUNT_ATTR_NOATIME: mnt_flags |= MNT_NOATIME; break; case MOUNT_ATTR_RELATIME: mnt_flags |= MNT_RELATIME; break; default: return -EINVAL; } f = fdget(fs_fd); if (!f.file) return -EBADF; ret = -EINVAL; if (f.file->f_op != &fscontext_fops) goto err_fsfd; fc = f.file->private_data; ret = mutex_lock_interruptible(&fc->uapi_mutex); if (ret < 0) goto err_fsfd; /* There must be a valid superblock or we can't mount it */ ret = -EINVAL; if (!fc->root) goto err_unlock; ret = -EPERM; if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) { pr_warn("VFS: Mount too revealing\n"); goto err_unlock; } ret = -EBUSY; if (fc->phase != FS_CONTEXT_AWAITING_MOUNT) goto err_unlock; ret = -EPERM; if ((fc->sb_flags & SB_MANDLOCK) && !may_mandlock()) goto err_unlock; newmount.mnt = vfs_create_mount(fc); if (IS_ERR(newmount.mnt)) { ret = PTR_ERR(newmount.mnt); goto err_unlock; } newmount.dentry = dget(fc->root); newmount.mnt->mnt_flags = mnt_flags; /* We've done the mount bit - now move the file context into more or * less the same state as if we'd done an fspick(). We don't want to * do any memory allocation or anything like that at this point as we * don't want to have to handle any errors incurred. */ vfs_clean_context(fc); ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true); if (IS_ERR(ns)) { ret = PTR_ERR(ns); goto err_path; } mnt = real_mount(newmount.mnt); mnt->mnt_ns = ns; ns->root = mnt; ns->mounts = 1; list_add(&mnt->mnt_list, &ns->list); mntget(newmount.mnt); /* Attach to an apparent O_PATH fd with a note that we need to unmount * it, not just simply put it. */ file = dentry_open(&newmount, O_PATH, fc->cred); if (IS_ERR(file)) { dissolve_on_fput(newmount.mnt); ret = PTR_ERR(file); goto err_path; } file->f_mode |= FMODE_NEED_UNMOUNT; ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0); if (ret >= 0) fd_install(ret, file); else fput(file); err_path: path_put(&newmount); err_unlock: mutex_unlock(&fc->uapi_mutex); err_fsfd: fdput(f); return ret; } /* * Move a mount from one place to another. In combination with * fsopen()/fsmount() this is used to install a new mount and in combination * with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy * a mount subtree. * * Note the flags value is a combination of MOVE_MOUNT_* flags. */ SYSCALL_DEFINE5(move_mount, int, from_dfd, const char __user *, from_pathname, int, to_dfd, const char __user *, to_pathname, unsigned int, flags) { struct path from_path, to_path; unsigned int lflags; int ret = 0; if (!may_mount()) return -EPERM; if (flags & ~MOVE_MOUNT__MASK) return -EINVAL; /* If someone gives a pathname, they aren't permitted to move * from an fd that requires unmount as we can't get at the flag * to clear it afterwards. */ lflags = 0; if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_F_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(from_dfd, from_pathname, lflags, &from_path); if (ret < 0) return ret; lflags = 0; if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_T_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(to_dfd, to_pathname, lflags, &to_path); if (ret < 0) goto out_from; ret = security_move_mount(&from_path, &to_path); if (ret < 0) goto out_to; ret = do_move_mount(&from_path, &to_path); out_to: path_put(&to_path); out_from: path_put(&from_path); return ret; } /* * Return true if path is reachable from root * * namespace_sem or mount_lock is held */ bool is_path_reachable(struct mount *mnt, struct dentry *dentry, const struct path *root) { while (&mnt->mnt != root->mnt && mnt_has_parent(mnt)) { dentry = mnt->mnt_mountpoint; mnt = mnt->mnt_parent; } return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry); } bool path_is_under(const struct path *path1, const struct path *path2) { bool res; read_seqlock_excl(&mount_lock); res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2); read_sequnlock_excl(&mount_lock); return res; } EXPORT_SYMBOL(path_is_under); /* * pivot_root Semantics: * Moves the root file system of the current process to the directory put_old, * makes new_root as the new root file system of the current process, and sets * root/cwd of all processes which had them on the current root to new_root. * * Restrictions: * The new_root and put_old must be directories, and must not be on the * same file system as the current process root. The put_old must be * underneath new_root, i.e. adding a non-zero number of /.. to the string * pointed to by put_old must yield the same directory as new_root. No other * file system may be mounted on put_old. After all, new_root is a mountpoint. * * Also, the current root cannot be on the 'rootfs' (initial ramfs) filesystem. * See Documentation/filesystems/ramfs-rootfs-initramfs.rst for alternatives * in this situation. * * Notes: * - we don't move root/cwd if they are not at the root (reason: if something * cared enough to change them, it's probably wrong to force them elsewhere) * - it's okay to pick a root that isn't the root of a file system, e.g. * /nfs/my_root where /nfs is the mount point. It must be a mountpoint, * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root * first. */ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, const char __user *, put_old) { struct path new, old, root; struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent; struct mountpoint *old_mp, *root_mp; int error; if (!may_mount()) return -EPERM; error = user_path_at(AT_FDCWD, new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &new); if (error) goto out0; error = user_path_at(AT_FDCWD, put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old); if (error) goto out1; error = security_sb_pivotroot(&old, &new); if (error) goto out2; get_fs_root(current->fs, &root); old_mp = lock_mount(&old); error = PTR_ERR(old_mp); if (IS_ERR(old_mp)) goto out3; error = -EINVAL; new_mnt = real_mount(new.mnt); root_mnt = real_mount(root.mnt); old_mnt = real_mount(old.mnt); ex_parent = new_mnt->mnt_parent; root_parent = root_mnt->mnt_parent; if (IS_MNT_SHARED(old_mnt) || IS_MNT_SHARED(ex_parent) || IS_MNT_SHARED(root_parent)) goto out4; if (!check_mnt(root_mnt) || !check_mnt(new_mnt)) goto out4; if (new_mnt->mnt.mnt_flags & MNT_LOCKED) goto out4; error = -ENOENT; if (d_unlinked(new.dentry)) goto out4; error = -EBUSY; if (new_mnt == root_mnt || old_mnt == root_mnt) goto out4; /* loop, on the same file system */ error = -EINVAL; if (root.mnt->mnt_root != root.dentry) goto out4; /* not a mountpoint */ if (!mnt_has_parent(root_mnt)) goto out4; /* not attached */ if (new.mnt->mnt_root != new.dentry) goto out4; /* not a mountpoint */ if (!mnt_has_parent(new_mnt)) goto out4; /* not attached */ /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old.dentry, &new)) goto out4; /* make certain new is below the root */ if (!is_path_reachable(new_mnt, new.dentry, &root)) goto out4; lock_mount_hash(); umount_mnt(new_mnt); root_mp = unhash_mnt(root_mnt); /* we'll need its mountpoint */ if (root_mnt->mnt.mnt_flags & MNT_LOCKED) { new_mnt->mnt.mnt_flags |= MNT_LOCKED; root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; } /* mount old root on put_old */ attach_mnt(root_mnt, old_mnt, old_mp); /* mount new_root on / */ attach_mnt(new_mnt, root_parent, root_mp); mnt_add_count(root_parent, -1); touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ list_del_init(&new_mnt->mnt_expire); put_mountpoint(root_mp); unlock_mount_hash(); chroot_fs_refs(&root, &new); error = 0; out4: unlock_mount(old_mp); if (!error) mntput_no_expire(ex_parent); out3: path_put(&root); out2: path_put(&old); out1: path_put(&new); out0: return error; } static void __init init_mount_tree(void) { struct vfsmount *mnt; struct mount *m; struct mnt_namespace *ns; struct path root; mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", NULL); if (IS_ERR(mnt)) panic("Can't create rootfs"); ns = alloc_mnt_ns(&init_user_ns, false); if (IS_ERR(ns)) panic("Can't allocate initial namespace"); m = real_mount(mnt); m->mnt_ns = ns; ns->root = m; ns->mounts = 1; list_add(&m->mnt_list, &ns->list); init_task.nsproxy->mnt_ns = ns; get_mnt_ns(ns); root.mnt = mnt; root.dentry = mnt->mnt_root; mnt->mnt_flags |= MNT_LOCKED; set_fs_pwd(current->fs, &root); set_fs_root(current->fs, &root); } void __init mnt_init(void) { int err; mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); mount_hashtable = alloc_large_system_hash("Mount-cache", sizeof(struct hlist_head), mhash_entries, 19, HASH_ZERO, &m_hash_shift, &m_hash_mask, 0, 0); mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", sizeof(struct hlist_head), mphash_entries, 19, HASH_ZERO, &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); kernfs_init(); err = sysfs_init(); if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", __func__, err); fs_kobj = kobject_create_and_add("fs", NULL); if (!fs_kobj) printk(KERN_WARNING "%s: kobj create error\n", __func__); shmem_init(); init_rootfs(); init_mount_tree(); } void put_mnt_ns(struct mnt_namespace *ns) { if (!atomic_dec_and_test(&ns->count)) return; drop_collected_mounts(&ns->root->mnt); free_mnt_ns(ns); } struct vfsmount *kern_mount(struct file_system_type *type) { struct vfsmount *mnt; mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (!IS_ERR(mnt)) { /* * it is a longterm mount, don't release mnt until * we unmount before file sys is unregistered */ real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; } return mnt; } EXPORT_SYMBOL_GPL(kern_mount); void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ if (!IS_ERR_OR_NULL(mnt)) { real_mount(mnt)->mnt_ns = NULL; synchronize_rcu(); /* yecchhh... */ mntput(mnt); } } EXPORT_SYMBOL(kern_unmount); void kern_unmount_array(struct vfsmount *mnt[], unsigned int num) { unsigned int i; for (i = 0; i < num; i++) if (mnt[i]) real_mount(mnt[i])->mnt_ns = NULL; synchronize_rcu_expedited(); for (i = 0; i < num; i++) mntput(mnt[i]); } EXPORT_SYMBOL(kern_unmount_array); bool our_mnt(struct vfsmount *mnt) { return check_mnt(real_mount(mnt)); } bool current_chrooted(void) { /* Does the current process have a non-standard root */ struct path ns_root; struct path fs_root; bool chrooted; /* Find the namespace root */ ns_root.mnt = &current->nsproxy->mnt_ns->root->mnt; ns_root.dentry = ns_root.mnt->mnt_root; path_get(&ns_root); while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root)) ; get_fs_root(current->fs, &fs_root); chrooted = !path_equal(&fs_root, &ns_root); path_put(&fs_root); path_put(&ns_root); return chrooted; } static bool mnt_already_visible(struct mnt_namespace *ns, const struct super_block *sb, int *new_mnt_flags) { int new_flags = *new_mnt_flags; struct mount *mnt; bool visible = false; down_read(&namespace_sem); lock_ns_list(ns); list_for_each_entry(mnt, &ns->list, mnt_list) { struct mount *child; int mnt_flags; if (mnt_is_cursor(mnt)) continue; if (mnt->mnt.mnt_sb->s_type != sb->s_type) continue; /* This mount is not fully visible if it's root directory * is not the root directory of the filesystem. */ if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; /* A local view of the mount flags */ mnt_flags = mnt->mnt.mnt_flags; /* Don't miss readonly hidden in the superblock flags */ if (sb_rdonly(mnt->mnt.mnt_sb)) mnt_flags |= MNT_LOCK_READONLY; /* Verify the mount flags are equal to or more permissive * than the proposed new mount. */ if ((mnt_flags & MNT_LOCK_READONLY) && !(new_flags & MNT_READONLY)) continue; if ((mnt_flags & MNT_LOCK_ATIME) && ((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) continue; /* This mount is not fully visible if there are any * locked child mounts that cover anything except for * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; /* Only worry about locked mounts */ if (!(child->mnt.mnt_flags & MNT_LOCKED)) continue; /* Is the directory permanetly empty? */ if (!is_empty_dir_inode(inode)) goto next; } /* Preserve the locked attributes */ *new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \ MNT_LOCK_ATIME); visible = true; goto found; next: ; } found: unlock_ns_list(ns); up_read(&namespace_sem); return visible; } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags) { const unsigned long required_iflags = SB_I_NOEXEC | SB_I_NODEV; struct mnt_namespace *ns = current->nsproxy->mnt_ns; unsigned long s_iflags; if (ns->user_ns == &init_user_ns) return false; /* Can this filesystem be too revealing? */ s_iflags = sb->s_iflags; if (!(s_iflags & SB_I_USERNS_VISIBLE)) return false; if ((s_iflags & required_iflags) != required_iflags) { WARN_ONCE(1, "Expected s_iflags to contain 0x%lx\n", required_iflags); return true; } return !mnt_already_visible(ns, sb, new_mnt_flags); } bool mnt_may_suid(struct vfsmount *mnt) { /* * Foreign mounts (accessed via fchdir or through /proc * symlinks) are always treated as if they are nosuid. This * prevents namespaces from trusting potentially unsafe * suid/sgid bits, file caps, or security labels that originate * in other namespaces. */ return !(mnt->mnt_flags & MNT_NOSUID) && check_mnt(real_mount(mnt)) && current_in_userns(mnt->mnt_sb->s_user_ns); } static struct ns_common *mntns_get(struct task_struct *task) { struct ns_common *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = &nsproxy->mnt_ns->ns; get_mnt_ns(to_mnt_ns(ns)); } task_unlock(task); return ns; } static void mntns_put(struct ns_common *ns) { put_mnt_ns(to_mnt_ns(ns)); } static int mntns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct fs_struct *fs = nsset->fs; struct mnt_namespace *mnt_ns = to_mnt_ns(ns), *old_mnt_ns; struct user_namespace *user_ns = nsset->cred->user_ns; struct path root; int err; if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(user_ns, CAP_SYS_CHROOT) || !ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; if (is_anon_ns(mnt_ns)) return -EINVAL; if (fs->users != 1) return -EINVAL; get_mnt_ns(mnt_ns); old_mnt_ns = nsproxy->mnt_ns; nsproxy->mnt_ns = mnt_ns; /* Find the root */ err = vfs_path_lookup(mnt_ns->root->mnt.mnt_root, &mnt_ns->root->mnt, "/", LOOKUP_DOWN, &root); if (err) { /* revert to old namespace */ nsproxy->mnt_ns = old_mnt_ns; put_mnt_ns(mnt_ns); return err; } put_mnt_ns(old_mnt_ns); /* Update the pwd and root */ set_fs_pwd(fs, &root); set_fs_root(fs, &root); path_put(&root); return 0; } static struct user_namespace *mntns_owner(struct ns_common *ns) { return to_mnt_ns(ns)->user_ns; } const struct proc_ns_operations mntns_operations = { .name = "mnt", .type = CLONE_NEWNS, .get = mntns_get, .put = mntns_put, .install = mntns_install, .owner = mntns_owner, };
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 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 // SPDX-License-Identifier: GPL-2.0-or-later /* * libata-core.c - helper library for ATA * * Copyright 2003-2004 Red Hat, Inc. All rights reserved. * Copyright 2003-2004 Jeff Garzik * * libata documentation is available via 'make {ps|pdf}docs', * as Documentation/driver-api/libata.rst * * Hardware documentation available from http://www.t13.org/ and * http://www.sata-io.org/ * * Standards documents from: * http://www.t13.org (ATA standards, PCI DMA IDE spec) * http://www.t10.org (SCSI MMC - for ATAPI MMC) * http://www.sata-io.org (SATA) * http://www.compactflash.org (CF) * http://www.qic.org (QIC157 - Tape and DSC) * http://www.ce-ata.org (CE-ATA: not supported) * * libata is essentially a library of internal helper functions for * low-level ATA host controller drivers. As such, the API/ABI is * likely to change as new drivers are added and updated. * Do not depend on ABI/API stability. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/pci.h> #include <linux/init.h> #include <linux/list.h> #include <linux/mm.h> #include <linux/spinlock.h> #include <linux/blkdev.h> #include <linux/delay.h> #include <linux/timer.h> #include <linux/time.h> #include <linux/interrupt.h> #include <linux/completion.h> #include <linux/suspend.h> #include <linux/workqueue.h> #include <linux/scatterlist.h> #include <linux/io.h> #include <linux/log2.h> #include <linux/slab.h> #include <linux/glob.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_host.h> #include <linux/libata.h> #include <asm/byteorder.h> #include <asm/unaligned.h> #include <linux/cdrom.h> #include <linux/ratelimit.h> #include <linux/leds.h> #include <linux/pm_runtime.h> #include <linux/platform_device.h> #include <asm/setup.h> #define CREATE_TRACE_POINTS #include <trace/events/libata.h> #include "libata.h" #include "libata-transport.h" const struct ata_port_operations ata_base_port_ops = { .prereset = ata_std_prereset, .postreset = ata_std_postreset, .error_handler = ata_std_error_handler, .sched_eh = ata_std_sched_eh, .end_eh = ata_std_end_eh, }; const struct ata_port_operations sata_port_ops = { .inherits = &ata_base_port_ops, .qc_defer = ata_std_qc_defer, .hardreset = sata_std_hardreset, }; EXPORT_SYMBOL_GPL(sata_port_ops); static unsigned int ata_dev_init_params(struct ata_device *dev, u16 heads, u16 sectors); static unsigned int ata_dev_set_xfermode(struct ata_device *dev); static void ata_dev_xfermask(struct ata_device *dev); static unsigned long ata_dev_blacklisted(const struct ata_device *dev); atomic_t ata_print_id = ATOMIC_INIT(0); #ifdef CONFIG_ATA_FORCE struct ata_force_param { const char *name; u8 cbl; u8 spd_limit; unsigned long xfer_mask; unsigned int horkage_on; unsigned int horkage_off; u16 lflags; }; struct ata_force_ent { int port; int device; struct ata_force_param param; }; static struct ata_force_ent *ata_force_tbl; static int ata_force_tbl_size; static char ata_force_param_buf[COMMAND_LINE_SIZE] __initdata; /* param_buf is thrown away after initialization, disallow read */ module_param_string(force, ata_force_param_buf, sizeof(ata_force_param_buf), 0); MODULE_PARM_DESC(force, "Force ATA configurations including cable type, link speed and transfer mode (see Documentation/admin-guide/kernel-parameters.rst for details)"); #endif static int atapi_enabled = 1; module_param(atapi_enabled, int, 0444); MODULE_PARM_DESC(atapi_enabled, "Enable discovery of ATAPI devices (0=off, 1=on [default])"); static int atapi_dmadir = 0; module_param(atapi_dmadir, int, 0444); MODULE_PARM_DESC(atapi_dmadir, "Enable ATAPI DMADIR bridge support (0=off [default], 1=on)"); int atapi_passthru16 = 1; module_param(atapi_passthru16, int, 0444); MODULE_PARM_DESC(atapi_passthru16, "Enable ATA_16 passthru for ATAPI devices (0=off, 1=on [default])"); int libata_fua = 0; module_param_named(fua, libata_fua, int, 0444); MODULE_PARM_DESC(fua, "FUA support (0=off [default], 1=on)"); static int ata_ignore_hpa; module_param_named(ignore_hpa, ata_ignore_hpa, int, 0644); MODULE_PARM_DESC(ignore_hpa, "Ignore HPA limit (0=keep BIOS limits, 1=ignore limits, using full disk)"); static int libata_dma_mask = ATA_DMA_MASK_ATA|ATA_DMA_MASK_ATAPI|ATA_DMA_MASK_CFA; module_param_named(dma, libata_dma_mask, int, 0444); MODULE_PARM_DESC(dma, "DMA enable/disable (0x1==ATA, 0x2==ATAPI, 0x4==CF)"); static int ata_probe_timeout; module_param(ata_probe_timeout, int, 0444); MODULE_PARM_DESC(ata_probe_timeout, "Set ATA probing timeout (seconds)"); int libata_noacpi = 0; module_param_named(noacpi, libata_noacpi, int, 0444); MODULE_PARM_DESC(noacpi, "Disable the use of ACPI in probe/suspend/resume (0=off [default], 1=on)"); int libata_allow_tpm = 0; module_param_named(allow_tpm, libata_allow_tpm, int, 0444); MODULE_PARM_DESC(allow_tpm, "Permit the use of TPM commands (0=off [default], 1=on)"); static int atapi_an; module_param(atapi_an, int, 0444); MODULE_PARM_DESC(atapi_an, "Enable ATAPI AN media presence notification (0=0ff [default], 1=on)"); MODULE_AUTHOR("Jeff Garzik"); MODULE_DESCRIPTION("Library module for ATA devices"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); static bool ata_sstatus_online(u32 sstatus) { return (sstatus & 0xf) == 0x3; } /** * ata_link_next - link iteration helper * @link: the previous link, NULL to start * @ap: ATA port containing links to iterate * @mode: iteration mode, one of ATA_LITER_* * * LOCKING: * Host lock or EH context. * * RETURNS: * Pointer to the next link. */ struct ata_link *ata_link_next(struct ata_link *link, struct ata_port *ap, enum ata_link_iter_mode mode) { BUG_ON(mode != ATA_LITER_EDGE && mode != ATA_LITER_PMP_FIRST && mode != ATA_LITER_HOST_FIRST); /* NULL link indicates start of iteration */ if (!link) switch (mode) { case ATA_LITER_EDGE: case ATA_LITER_PMP_FIRST: if (sata_pmp_attached(ap)) return ap->pmp_link; fallthrough; case ATA_LITER_HOST_FIRST: return &ap->link; } /* we just iterated over the host link, what's next? */ if (link == &ap->link) switch (mode) { case ATA_LITER_HOST_FIRST: if (sata_pmp_attached(ap)) return ap->pmp_link; fallthrough; case ATA_LITER_PMP_FIRST: if (unlikely(ap->slave_link)) return ap->slave_link; fallthrough; case ATA_LITER_EDGE: return NULL; } /* slave_link excludes PMP */ if (unlikely(link == ap->slave_link)) return NULL; /* we were over a PMP link */ if (++link < ap->pmp_link + ap->nr_pmp_links) return link; if (mode == ATA_LITER_PMP_FIRST) return &ap->link; return NULL; } EXPORT_SYMBOL_GPL(ata_link_next); /** * ata_dev_next - device iteration helper * @dev: the previous device, NULL to start * @link: ATA link containing devices to iterate * @mode: iteration mode, one of ATA_DITER_* * * LOCKING: * Host lock or EH context. * * RETURNS: * Pointer to the next device. */ struct ata_device *ata_dev_next(struct ata_device *dev, struct ata_link *link, enum ata_dev_iter_mode mode) { BUG_ON(mode != ATA_DITER_ENABLED && mode != ATA_DITER_ENABLED_REVERSE && mode != ATA_DITER_ALL && mode != ATA_DITER_ALL_REVERSE); /* NULL dev indicates start of iteration */ if (!dev) switch (mode) { case ATA_DITER_ENABLED: case ATA_DITER_ALL: dev = link->device; goto check; case ATA_DITER_ENABLED_REVERSE: case ATA_DITER_ALL_REVERSE: dev = link->device + ata_link_max_devices(link) - 1; goto check; } next: /* move to the next one */ switch (mode) { case ATA_DITER_ENABLED: case ATA_DITER_ALL: if (++dev < link->device + ata_link_max_devices(link)) goto check; return NULL; case ATA_DITER_ENABLED_REVERSE: case ATA_DITER_ALL_REVERSE: if (--dev >= link->device) goto check; return NULL; } check: if ((mode == ATA_DITER_ENABLED || mode == ATA_DITER_ENABLED_REVERSE) && !ata_dev_enabled(dev)) goto next; return dev; } EXPORT_SYMBOL_GPL(ata_dev_next); /** * ata_dev_phys_link - find physical link for a device * @dev: ATA device to look up physical link for * * Look up physical link which @dev is attached to. Note that * this is different from @dev->link only when @dev is on slave * link. For all other cases, it's the same as @dev->link. * * LOCKING: * Don't care. * * RETURNS: * Pointer to the found physical link. */ struct ata_link *ata_dev_phys_link(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; if (!ap->slave_link) return dev->link; if (!dev->devno) return &ap->link; return ap->slave_link; } #ifdef CONFIG_ATA_FORCE /** * ata_force_cbl - force cable type according to libata.force * @ap: ATA port of interest * * Force cable type according to libata.force and whine about it. * The last entry which has matching port number is used, so it * can be specified as part of device force parameters. For * example, both "a:40c,1.00:udma4" and "1.00:40c,udma4" have the * same effect. * * LOCKING: * EH context. */ void ata_force_cbl(struct ata_port *ap) { int i; for (i = ata_force_tbl_size - 1; i >= 0; i--) { const struct ata_force_ent *fe = &ata_force_tbl[i]; if (fe->port != -1 && fe->port != ap->print_id) continue; if (fe->param.cbl == ATA_CBL_NONE) continue; ap->cbl = fe->param.cbl; ata_port_notice(ap, "FORCE: cable set to %s\n", fe->param.name); return; } } /** * ata_force_link_limits - force link limits according to libata.force * @link: ATA link of interest * * Force link flags and SATA spd limit according to libata.force * and whine about it. When only the port part is specified * (e.g. 1:), the limit applies to all links connected to both * the host link and all fan-out ports connected via PMP. If the * device part is specified as 0 (e.g. 1.00:), it specifies the * first fan-out link not the host link. Device number 15 always * points to the host link whether PMP is attached or not. If the * controller has slave link, device number 16 points to it. * * LOCKING: * EH context. */ static void ata_force_link_limits(struct ata_link *link) { bool did_spd = false; int linkno = link->pmp; int i; if (ata_is_host_link(link)) linkno += 15; for (i = ata_force_tbl_size - 1; i >= 0; i--) { const struct ata_force_ent *fe = &ata_force_tbl[i]; if (fe->port != -1 && fe->port != link->ap->print_id) continue; if (fe->device != -1 && fe->device != linkno) continue; /* only honor the first spd limit */ if (!did_spd && fe->param.spd_limit) { link->hw_sata_spd_limit = (1 << fe->param.spd_limit) - 1; ata_link_notice(link, "FORCE: PHY spd limit set to %s\n", fe->param.name); did_spd = true; } /* let lflags stack */ if (fe->param.lflags) { link->flags |= fe->param.lflags; ata_link_notice(link, "FORCE: link flag 0x%x forced -> 0x%x\n", fe->param.lflags, link->flags); } } } /** * ata_force_xfermask - force xfermask according to libata.force * @dev: ATA device of interest * * Force xfer_mask according to libata.force and whine about it. * For consistency with link selection, device number 15 selects * the first device connected to the host link. * * LOCKING: * EH context. */ static void ata_force_xfermask(struct ata_device *dev) { int devno = dev->link->pmp + dev->devno; int alt_devno = devno; int i; /* allow n.15/16 for devices attached to host port */ if (ata_is_host_link(dev->link)) alt_devno += 15; for (i = ata_force_tbl_size - 1; i >= 0; i--) { const struct ata_force_ent *fe = &ata_force_tbl[i]; unsigned long pio_mask, mwdma_mask, udma_mask; if (fe->port != -1 && fe->port != dev->link->ap->print_id) continue; if (fe->device != -1 && fe->device != devno && fe->device != alt_devno) continue; if (!fe->param.xfer_mask) continue; ata_unpack_xfermask(fe->param.xfer_mask, &pio_mask, &mwdma_mask, &udma_mask); if (udma_mask) dev->udma_mask = udma_mask; else if (mwdma_mask) { dev->udma_mask = 0; dev->mwdma_mask = mwdma_mask; } else { dev->udma_mask = 0; dev->mwdma_mask = 0; dev->pio_mask = pio_mask; } ata_dev_notice(dev, "FORCE: xfer_mask set to %s\n", fe->param.name); return; } } /** * ata_force_horkage - force horkage according to libata.force * @dev: ATA device of interest * * Force horkage according to libata.force and whine about it. * For consistency with link selection, device number 15 selects * the first device connected to the host link. * * LOCKING: * EH context. */ static void ata_force_horkage(struct ata_device *dev) { int devno = dev->link->pmp + dev->devno; int alt_devno = devno; int i; /* allow n.15/16 for devices attached to host port */ if (ata_is_host_link(dev->link)) alt_devno += 15; for (i = 0; i < ata_force_tbl_size; i++) { const struct ata_force_ent *fe = &ata_force_tbl[i]; if (fe->port != -1 && fe->port != dev->link->ap->print_id) continue; if (fe->device != -1 && fe->device != devno && fe->device != alt_devno) continue; if (!(~dev->horkage & fe->param.horkage_on) && !(dev->horkage & fe->param.horkage_off)) continue; dev->horkage |= fe->param.horkage_on; dev->horkage &= ~fe->param.horkage_off; ata_dev_notice(dev, "FORCE: horkage modified (%s)\n", fe->param.name); } } #else static inline void ata_force_link_limits(struct ata_link *link) { } static inline void ata_force_xfermask(struct ata_device *dev) { } static inline void ata_force_horkage(struct ata_device *dev) { } #endif /** * atapi_cmd_type - Determine ATAPI command type from SCSI opcode * @opcode: SCSI opcode * * Determine ATAPI command type from @opcode. * * LOCKING: * None. * * RETURNS: * ATAPI_{READ|WRITE|READ_CD|PASS_THRU|MISC} */ int atapi_cmd_type(u8 opcode) { switch (opcode) { case GPCMD_READ_10: case GPCMD_READ_12: return ATAPI_READ; case GPCMD_WRITE_10: case GPCMD_WRITE_12: case GPCMD_WRITE_AND_VERIFY_10: return ATAPI_WRITE; case GPCMD_READ_CD: case GPCMD_READ_CD_MSF: return ATAPI_READ_CD; case ATA_16: case ATA_12: if (atapi_passthru16) return ATAPI_PASS_THRU; fallthrough; default: return ATAPI_MISC; } } EXPORT_SYMBOL_GPL(atapi_cmd_type); static const u8 ata_rw_cmds[] = { /* pio multi */ ATA_CMD_READ_MULTI, ATA_CMD_WRITE_MULTI, ATA_CMD_READ_MULTI_EXT, ATA_CMD_WRITE_MULTI_EXT, 0, 0, 0, ATA_CMD_WRITE_MULTI_FUA_EXT, /* pio */ ATA_CMD_PIO_READ, ATA_CMD_PIO_WRITE, ATA_CMD_PIO_READ_EXT, ATA_CMD_PIO_WRITE_EXT, 0, 0, 0, 0, /* dma */ ATA_CMD_READ, ATA_CMD_WRITE, ATA_CMD_READ_EXT, ATA_CMD_WRITE_EXT, 0, 0, 0, ATA_CMD_WRITE_FUA_EXT }; /** * ata_rwcmd_protocol - set taskfile r/w commands and protocol * @tf: command to examine and configure * @dev: device tf belongs to * * Examine the device configuration and tf->flags to calculate * the proper read/write commands and protocol to use. * * LOCKING: * caller. */ static int ata_rwcmd_protocol(struct ata_taskfile *tf, struct ata_device *dev) { u8 cmd; int index, fua, lba48, write; fua = (tf->flags & ATA_TFLAG_FUA) ? 4 : 0; lba48 = (tf->flags & ATA_TFLAG_LBA48) ? 2 : 0; write = (tf->flags & ATA_TFLAG_WRITE) ? 1 : 0; if (dev->flags & ATA_DFLAG_PIO) { tf->protocol = ATA_PROT_PIO; index = dev->multi_count ? 0 : 8; } else if (lba48 && (dev->link->ap->flags & ATA_FLAG_PIO_LBA48)) { /* Unable to use DMA due to host limitation */ tf->protocol = ATA_PROT_PIO; index = dev->multi_count ? 0 : 8; } else { tf->protocol = ATA_PROT_DMA; index = 16; } cmd = ata_rw_cmds[index + fua + lba48 + write]; if (cmd) { tf->command = cmd; return 0; } return -1; } /** * ata_tf_read_block - Read block address from ATA taskfile * @tf: ATA taskfile of interest * @dev: ATA device @tf belongs to * * LOCKING: * None. * * Read block address from @tf. This function can handle all * three address formats - LBA, LBA48 and CHS. tf->protocol and * flags select the address format to use. * * RETURNS: * Block address read from @tf. */ u64 ata_tf_read_block(const struct ata_taskfile *tf, struct ata_device *dev) { u64 block = 0; if (tf->flags & ATA_TFLAG_LBA) { if (tf->flags & ATA_TFLAG_LBA48) { block |= (u64)tf->hob_lbah << 40; block |= (u64)tf->hob_lbam << 32; block |= (u64)tf->hob_lbal << 24; } else block |= (tf->device & 0xf) << 24; block |= tf->lbah << 16; block |= tf->lbam << 8; block |= tf->lbal; } else { u32 cyl, head, sect; cyl = tf->lbam | (tf->lbah << 8); head = tf->device & 0xf; sect = tf->lbal; if (!sect) { ata_dev_warn(dev, "device reported invalid CHS sector 0\n"); return U64_MAX; } block = (cyl * dev->heads + head) * dev->sectors + sect - 1; } return block; } /** * ata_build_rw_tf - Build ATA taskfile for given read/write request * @tf: Target ATA taskfile * @dev: ATA device @tf belongs to * @block: Block address * @n_block: Number of blocks * @tf_flags: RW/FUA etc... * @tag: tag * @class: IO priority class * * LOCKING: * None. * * Build ATA taskfile @tf for read/write request described by * @block, @n_block, @tf_flags and @tag on @dev. * * RETURNS: * * 0 on success, -ERANGE if the request is too large for @dev, * -EINVAL if the request is invalid. */ int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev, u64 block, u32 n_block, unsigned int tf_flags, unsigned int tag, int class) { tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; tf->flags |= tf_flags; if (ata_ncq_enabled(dev) && !ata_tag_internal(tag)) { /* yay, NCQ */ if (!lba_48_ok(block, n_block)) return -ERANGE; tf->protocol = ATA_PROT_NCQ; tf->flags |= ATA_TFLAG_LBA | ATA_TFLAG_LBA48; if (tf->flags & ATA_TFLAG_WRITE) tf->command = ATA_CMD_FPDMA_WRITE; else tf->command = ATA_CMD_FPDMA_READ; tf->nsect = tag << 3; tf->hob_feature = (n_block >> 8) & 0xff; tf->feature = n_block & 0xff; tf->hob_lbah = (block >> 40) & 0xff; tf->hob_lbam = (block >> 32) & 0xff; tf->hob_lbal = (block >> 24) & 0xff; tf->lbah = (block >> 16) & 0xff; tf->lbam = (block >> 8) & 0xff; tf->lbal = block & 0xff; tf->device = ATA_LBA; if (tf->flags & ATA_TFLAG_FUA) tf->device |= 1 << 7; if (dev->flags & ATA_DFLAG_NCQ_PRIO) { if (class == IOPRIO_CLASS_RT) tf->hob_nsect |= ATA_PRIO_HIGH << ATA_SHIFT_PRIO; } } else if (dev->flags & ATA_DFLAG_LBA) { tf->flags |= ATA_TFLAG_LBA; if (lba_28_ok(block, n_block)) { /* use LBA28 */ tf->device |= (block >> 24) & 0xf; } else if (lba_48_ok(block, n_block)) { if (!(dev->flags & ATA_DFLAG_LBA48)) return -ERANGE; /* use LBA48 */ tf->flags |= ATA_TFLAG_LBA48; tf->hob_nsect = (n_block >> 8) & 0xff; tf->hob_lbah = (block >> 40) & 0xff; tf->hob_lbam = (block >> 32) & 0xff; tf->hob_lbal = (block >> 24) & 0xff; } else /* request too large even for LBA48 */ return -ERANGE; if (unlikely(ata_rwcmd_protocol(tf, dev) < 0)) return -EINVAL; tf->nsect = n_block & 0xff; tf->lbah = (block >> 16) & 0xff; tf->lbam = (block >> 8) & 0xff; tf->lbal = block & 0xff; tf->device |= ATA_LBA; } else { /* CHS */ u32 sect, head, cyl, track; /* The request -may- be too large for CHS addressing. */ if (!lba_28_ok(block, n_block)) return -ERANGE; if (unlikely(ata_rwcmd_protocol(tf, dev) < 0)) return -EINVAL; /* Convert LBA to CHS */ track = (u32)block / dev->sectors; cyl = track / dev->heads; head = track % dev->heads; sect = (u32)block % dev->sectors + 1; DPRINTK("block %u track %u cyl %u head %u sect %u\n", (u32)block, track, cyl, head, sect); /* Check whether the converted CHS can fit. Cylinder: 0-65535 Head: 0-15 Sector: 1-255*/ if ((cyl >> 16) || (head >> 4) || (sect >> 8) || (!sect)) return -ERANGE; tf->nsect = n_block & 0xff; /* Sector count 0 means 256 sectors */ tf->lbal = sect; tf->lbam = cyl; tf->lbah = cyl >> 8; tf->device |= head; } return 0; } /** * ata_pack_xfermask - Pack pio, mwdma and udma masks into xfer_mask * @pio_mask: pio_mask * @mwdma_mask: mwdma_mask * @udma_mask: udma_mask * * Pack @pio_mask, @mwdma_mask and @udma_mask into a single * unsigned int xfer_mask. * * LOCKING: * None. * * RETURNS: * Packed xfer_mask. */ unsigned long ata_pack_xfermask(unsigned long pio_mask, unsigned long mwdma_mask, unsigned long udma_mask) { return ((pio_mask << ATA_SHIFT_PIO) & ATA_MASK_PIO) | ((mwdma_mask << ATA_SHIFT_MWDMA) & ATA_MASK_MWDMA) | ((udma_mask << ATA_SHIFT_UDMA) & ATA_MASK_UDMA); } EXPORT_SYMBOL_GPL(ata_pack_xfermask); /** * ata_unpack_xfermask - Unpack xfer_mask into pio, mwdma and udma masks * @xfer_mask: xfer_mask to unpack * @pio_mask: resulting pio_mask * @mwdma_mask: resulting mwdma_mask * @udma_mask: resulting udma_mask * * Unpack @xfer_mask into @pio_mask, @mwdma_mask and @udma_mask. * Any NULL destination masks will be ignored. */ void ata_unpack_xfermask(unsigned long xfer_mask, unsigned long *pio_mask, unsigned long *mwdma_mask, unsigned long *udma_mask) { if (pio_mask) *pio_mask = (xfer_mask & ATA_MASK_PIO) >> ATA_SHIFT_PIO; if (mwdma_mask) *mwdma_mask = (xfer_mask & ATA_MASK_MWDMA) >> ATA_SHIFT_MWDMA; if (udma_mask) *udma_mask = (xfer_mask & ATA_MASK_UDMA) >> ATA_SHIFT_UDMA; } static const struct ata_xfer_ent { int shift, bits; u8 base; } ata_xfer_tbl[] = { { ATA_SHIFT_PIO, ATA_NR_PIO_MODES, XFER_PIO_0 }, { ATA_SHIFT_MWDMA, ATA_NR_MWDMA_MODES, XFER_MW_DMA_0 }, { ATA_SHIFT_UDMA, ATA_NR_UDMA_MODES, XFER_UDMA_0 }, { -1, }, }; /** * ata_xfer_mask2mode - Find matching XFER_* for the given xfer_mask * @xfer_mask: xfer_mask of interest * * Return matching XFER_* value for @xfer_mask. Only the highest * bit of @xfer_mask is considered. * * LOCKING: * None. * * RETURNS: * Matching XFER_* value, 0xff if no match found. */ u8 ata_xfer_mask2mode(unsigned long xfer_mask) { int highbit = fls(xfer_mask) - 1; const struct ata_xfer_ent *ent; for (ent = ata_xfer_tbl; ent->shift >= 0; ent++) if (highbit >= ent->shift && highbit < ent->shift + ent->bits) return ent->base + highbit - ent->shift; return 0xff; } EXPORT_SYMBOL_GPL(ata_xfer_mask2mode); /** * ata_xfer_mode2mask - Find matching xfer_mask for XFER_* * @xfer_mode: XFER_* of interest * * Return matching xfer_mask for @xfer_mode. * * LOCKING: * None. * * RETURNS: * Matching xfer_mask, 0 if no match found. */ unsigned long ata_xfer_mode2mask(u8 xfer_mode) { const struct ata_xfer_ent *ent; for (ent = ata_xfer_tbl; ent->shift >= 0; ent++) if (xfer_mode >= ent->base && xfer_mode < ent->base + ent->bits) return ((2 << (ent->shift + xfer_mode - ent->base)) - 1) & ~((1 << ent->shift) - 1); return 0; } EXPORT_SYMBOL_GPL(ata_xfer_mode2mask); /** * ata_xfer_mode2shift - Find matching xfer_shift for XFER_* * @xfer_mode: XFER_* of interest * * Return matching xfer_shift for @xfer_mode. * * LOCKING: * None. * * RETURNS: * Matching xfer_shift, -1 if no match found. */ int ata_xfer_mode2shift(unsigned long xfer_mode) { const struct ata_xfer_ent *ent; for (ent = ata_xfer_tbl; ent->shift >= 0; ent++) if (xfer_mode >= ent->base && xfer_mode < ent->base + ent->bits) return ent->shift; return -1; } EXPORT_SYMBOL_GPL(ata_xfer_mode2shift); /** * ata_mode_string - convert xfer_mask to string * @xfer_mask: mask of bits supported; only highest bit counts. * * Determine string which represents the highest speed * (highest bit in @modemask). * * LOCKING: * None. * * RETURNS: * Constant C string representing highest speed listed in * @mode_mask, or the constant C string "<n/a>". */ const char *ata_mode_string(unsigned long xfer_mask) { static const char * const xfer_mode_str[] = { "PIO0", "PIO1", "PIO2", "PIO3", "PIO4", "PIO5", "PIO6", "MWDMA0", "MWDMA1", "MWDMA2", "MWDMA3", "MWDMA4", "UDMA/16", "UDMA/25", "UDMA/33", "UDMA/44", "UDMA/66", "UDMA/100", "UDMA/133", "UDMA7", }; int highbit; highbit = fls(xfer_mask) - 1; if (highbit >= 0 && highbit < ARRAY_SIZE(xfer_mode_str)) return xfer_mode_str[highbit]; return "<n/a>"; } EXPORT_SYMBOL_GPL(ata_mode_string); const char *sata_spd_string(unsigned int spd) { static const char * const spd_str[] = { "1.5 Gbps", "3.0 Gbps", "6.0 Gbps", }; if (spd == 0 || (spd - 1) >= ARRAY_SIZE(spd_str)) return "<unknown>"; return spd_str[spd - 1]; } /** * ata_dev_classify - determine device type based on ATA-spec signature * @tf: ATA taskfile register set for device to be identified * * Determine from taskfile register contents whether a device is * ATA or ATAPI, as per "Signature and persistence" section * of ATA/PI spec (volume 1, sect 5.14). * * LOCKING: * None. * * RETURNS: * Device type, %ATA_DEV_ATA, %ATA_DEV_ATAPI, %ATA_DEV_PMP, * %ATA_DEV_ZAC, or %ATA_DEV_UNKNOWN the event of failure. */ unsigned int ata_dev_classify(const struct ata_taskfile *tf) { /* Apple's open source Darwin code hints that some devices only * put a proper signature into the LBA mid/high registers, * So, we only check those. It's sufficient for uniqueness. * * ATA/ATAPI-7 (d1532v1r1: Feb. 19, 2003) specified separate * signatures for ATA and ATAPI devices attached on SerialATA, * 0x3c/0xc3 and 0x69/0x96 respectively. However, SerialATA * spec has never mentioned about using different signatures * for ATA/ATAPI devices. Then, Serial ATA II: Port * Multiplier specification began to use 0x69/0x96 to identify * port multpliers and 0x3c/0xc3 to identify SEMB device. * ATA/ATAPI-7 dropped descriptions about 0x3c/0xc3 and * 0x69/0x96 shortly and described them as reserved for * SerialATA. * * We follow the current spec and consider that 0x69/0x96 * identifies a port multiplier and 0x3c/0xc3 a SEMB device. * Unfortunately, WDC WD1600JS-62MHB5 (a hard drive) reports * SEMB signature. This is worked around in * ata_dev_read_id(). */ if ((tf->lbam == 0) && (tf->lbah == 0)) { DPRINTK("found ATA device by sig\n"); return ATA_DEV_ATA; } if ((tf->lbam == 0x14) && (tf->lbah == 0xeb)) { DPRINTK("found ATAPI device by sig\n"); return ATA_DEV_ATAPI; } if ((tf->lbam == 0x69) && (tf->lbah == 0x96)) { DPRINTK("found PMP device by sig\n"); return ATA_DEV_PMP; } if ((tf->lbam == 0x3c) && (tf->lbah == 0xc3)) { DPRINTK("found SEMB device by sig (could be ATA device)\n"); return ATA_DEV_SEMB; } if ((tf->lbam == 0xcd) && (tf->lbah == 0xab)) { DPRINTK("found ZAC device by sig\n"); return ATA_DEV_ZAC; } DPRINTK("unknown device\n"); return ATA_DEV_UNKNOWN; } EXPORT_SYMBOL_GPL(ata_dev_classify); /** * ata_id_string - Convert IDENTIFY DEVICE page into string * @id: IDENTIFY DEVICE results we will examine * @s: string into which data is output * @ofs: offset into identify device page * @len: length of string to return. must be an even number. * * The strings in the IDENTIFY DEVICE page are broken up into * 16-bit chunks. Run through the string, and output each * 8-bit chunk linearly, regardless of platform. * * LOCKING: * caller. */ void ata_id_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len) { unsigned int c; BUG_ON(len & 1); while (len > 0) { c = id[ofs] >> 8; *s = c; s++; c = id[ofs] & 0xff; *s = c; s++; ofs++; len -= 2; } } EXPORT_SYMBOL_GPL(ata_id_string); /** * ata_id_c_string - Convert IDENTIFY DEVICE page into C string * @id: IDENTIFY DEVICE results we will examine * @s: string into which data is output * @ofs: offset into identify device page * @len: length of string to return. must be an odd number. * * This function is identical to ata_id_string except that it * trims trailing spaces and terminates the resulting string with * null. @len must be actual maximum length (even number) + 1. * * LOCKING: * caller. */ void ata_id_c_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len) { unsigned char *p; ata_id_string(id, s, ofs, len - 1); p = s + strnlen(s, len - 1); while (p > s && p[-1] == ' ') p--; *p = '\0'; } EXPORT_SYMBOL_GPL(ata_id_c_string); static u64 ata_id_n_sectors(const u16 *id) { if (ata_id_has_lba(id)) { if (ata_id_has_lba48(id)) return ata_id_u64(id, ATA_ID_LBA_CAPACITY_2); else return ata_id_u32(id, ATA_ID_LBA_CAPACITY); } else { if (ata_id_current_chs_valid(id)) return id[ATA_ID_CUR_CYLS] * id[ATA_ID_CUR_HEADS] * id[ATA_ID_CUR_SECTORS]; else return id[ATA_ID_CYLS] * id[ATA_ID_HEADS] * id[ATA_ID_SECTORS]; } } u64 ata_tf_to_lba48(const struct ata_taskfile *tf) { u64 sectors = 0; sectors |= ((u64)(tf->hob_lbah & 0xff)) << 40; sectors |= ((u64)(tf->hob_lbam & 0xff)) << 32; sectors |= ((u64)(tf->hob_lbal & 0xff)) << 24; sectors |= (tf->lbah & 0xff) << 16; sectors |= (tf->lbam & 0xff) << 8; sectors |= (tf->lbal & 0xff); return sectors; } u64 ata_tf_to_lba(const struct ata_taskfile *tf) { u64 sectors = 0; sectors |= (tf->device & 0x0f) << 24; sectors |= (tf->lbah & 0xff) << 16; sectors |= (tf->lbam & 0xff) << 8; sectors |= (tf->lbal & 0xff); return sectors; } /** * ata_read_native_max_address - Read native max address * @dev: target device * @max_sectors: out parameter for the result native max address * * Perform an LBA48 or LBA28 native size query upon the device in * question. * * RETURNS: * 0 on success, -EACCES if command is aborted by the drive. * -EIO on other errors. */ static int ata_read_native_max_address(struct ata_device *dev, u64 *max_sectors) { unsigned int err_mask; struct ata_taskfile tf; int lba48 = ata_id_has_lba48(dev->id); ata_tf_init(dev, &tf); /* always clear all address registers */ tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR; if (lba48) { tf.command = ATA_CMD_READ_NATIVE_MAX_EXT; tf.flags |= ATA_TFLAG_LBA48; } else tf.command = ATA_CMD_READ_NATIVE_MAX; tf.protocol = ATA_PROT_NODATA; tf.device |= ATA_LBA; err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); if (err_mask) { ata_dev_warn(dev, "failed to read native max address (err_mask=0x%x)\n", err_mask); if (err_mask == AC_ERR_DEV && (tf.feature & ATA_ABORTED)) return -EACCES; return -EIO; } if (lba48) *max_sectors = ata_tf_to_lba48(&tf) + 1; else *max_sectors = ata_tf_to_lba(&tf) + 1; if (dev->horkage & ATA_HORKAGE_HPA_SIZE) (*max_sectors)--; return 0; } /** * ata_set_max_sectors - Set max sectors * @dev: target device * @new_sectors: new max sectors value to set for the device * * Set max sectors of @dev to @new_sectors. * * RETURNS: * 0 on success, -EACCES if command is aborted or denied (due to * previous non-volatile SET_MAX) by the drive. -EIO on other * errors. */ static int ata_set_max_sectors(struct ata_device *dev, u64 new_sectors) { unsigned int err_mask; struct ata_taskfile tf; int lba48 = ata_id_has_lba48(dev->id); new_sectors--; ata_tf_init(dev, &tf); tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR; if (lba48) { tf.command = ATA_CMD_SET_MAX_EXT; tf.flags |= ATA_TFLAG_LBA48; tf.hob_lbal = (new_sectors >> 24) & 0xff; tf.hob_lbam = (new_sectors >> 32) & 0xff; tf.hob_lbah = (new_sectors >> 40) & 0xff; } else { tf.command = ATA_CMD_SET_MAX; tf.device |= (new_sectors >> 24) & 0xf; } tf.protocol = ATA_PROT_NODATA; tf.device |= ATA_LBA; tf.lbal = (new_sectors >> 0) & 0xff; tf.lbam = (new_sectors >> 8) & 0xff; tf.lbah = (new_sectors >> 16) & 0xff; err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); if (err_mask) { ata_dev_warn(dev, "failed to set max address (err_mask=0x%x)\n", err_mask); if (err_mask == AC_ERR_DEV && (tf.feature & (ATA_ABORTED | ATA_IDNF))) return -EACCES; return -EIO; } return 0; } /** * ata_hpa_resize - Resize a device with an HPA set * @dev: Device to resize * * Read the size of an LBA28 or LBA48 disk with HPA features and resize * it if required to the full size of the media. The caller must check * the drive has the HPA feature set enabled. * * RETURNS: * 0 on success, -errno on failure. */ static int ata_hpa_resize(struct ata_device *dev) { struct ata_eh_context *ehc = &dev->link->eh_context; int print_info = ehc->i.flags & ATA_EHI_PRINTINFO; bool unlock_hpa = ata_ignore_hpa || dev->flags & ATA_DFLAG_UNLOCK_HPA; u64 sectors = ata_id_n_sectors(dev->id); u64 native_sectors; int rc; /* do we need to do it? */ if ((dev->class != ATA_DEV_ATA && dev->class != ATA_DEV_ZAC) || !ata_id_has_lba(dev->id) || !ata_id_hpa_enabled(dev->id) || (dev->horkage & ATA_HORKAGE_BROKEN_HPA)) return 0; /* read native max address */ rc = ata_read_native_max_address(dev, &native_sectors); if (rc) { /* If device aborted the command or HPA isn't going to * be unlocked, skip HPA resizing. */ if (rc == -EACCES || !unlock_hpa) { ata_dev_warn(dev, "HPA support seems broken, skipping HPA handling\n"); dev->horkage |= ATA_HORKAGE_BROKEN_HPA; /* we can continue if device aborted the command */ if (rc == -EACCES) rc = 0; } return rc; } dev->n_native_sectors = native_sectors; /* nothing to do? */ if (native_sectors <= sectors || !unlock_hpa) { if (!print_info || native_sectors == sectors) return 0; if (native_sectors > sectors) ata_dev_info(dev, "HPA detected: current %llu, native %llu\n", (unsigned long long)sectors, (unsigned long long)native_sectors); else if (native_sectors < sectors) ata_dev_warn(dev, "native sectors (%llu) is smaller than sectors (%llu)\n", (unsigned long long)native_sectors, (unsigned long long)sectors); return 0; } /* let's unlock HPA */ rc = ata_set_max_sectors(dev, native_sectors); if (rc == -EACCES) { /* if device aborted the command, skip HPA resizing */ ata_dev_warn(dev, "device aborted resize (%llu -> %llu), skipping HPA handling\n", (unsigned long long)sectors, (unsigned long long)native_sectors); dev->horkage |= ATA_HORKAGE_BROKEN_HPA; return 0; } else if (rc) return rc; /* re-read IDENTIFY data */ rc = ata_dev_reread_id(dev, 0); if (rc) { ata_dev_err(dev, "failed to re-read IDENTIFY data after HPA resizing\n"); return rc; } if (print_info) { u64 new_sectors = ata_id_n_sectors(dev->id); ata_dev_info(dev, "HPA unlocked: %llu -> %llu, native %llu\n", (unsigned long long)sectors, (unsigned long long)new_sectors, (unsigned long long)native_sectors); } return 0; } /** * ata_dump_id - IDENTIFY DEVICE info debugging output * @id: IDENTIFY DEVICE page to dump * * Dump selected 16-bit words from the given IDENTIFY DEVICE * page. * * LOCKING: * caller. */ static inline void ata_dump_id(const u16 *id) { DPRINTK("49==0x%04x " "53==0x%04x " "63==0x%04x " "64==0x%04x " "75==0x%04x \n", id[49], id[53], id[63], id[64], id[75]); DPRINTK("80==0x%04x " "81==0x%04x " "82==0x%04x " "83==0x%04x " "84==0x%04x \n", id[80], id[81], id[82], id[83], id[84]); DPRINTK("88==0x%04x " "93==0x%04x\n", id[88], id[93]); } /** * ata_id_xfermask - Compute xfermask from the given IDENTIFY data * @id: IDENTIFY data to compute xfer mask from * * Compute the xfermask for this device. This is not as trivial * as it seems if we must consider early devices correctly. * * FIXME: pre IDE drive timing (do we care ?). * * LOCKING: * None. * * RETURNS: * Computed xfermask */ unsigned long ata_id_xfermask(const u16 *id) { unsigned long pio_mask, mwdma_mask, udma_mask; /* Usual case. Word 53 indicates word 64 is valid */ if (id[ATA_ID_FIELD_VALID] & (1 << 1)) { pio_mask = id[ATA_ID_PIO_MODES] & 0x03; pio_mask <<= 3; pio_mask |= 0x7; } else { /* If word 64 isn't valid then Word 51 high byte holds * the PIO timing number for the maximum. Turn it into * a mask. */ u8 mode = (id[ATA_ID_OLD_PIO_MODES] >> 8) & 0xFF; if (mode < 5) /* Valid PIO range */ pio_mask = (2 << mode) - 1; else pio_mask = 1; /* But wait.. there's more. Design your standards by * committee and you too can get a free iordy field to * process. However its the speeds not the modes that * are supported... Note drivers using the timing API * will get this right anyway */ } mwdma_mask = id[ATA_ID_MWDMA_MODES] & 0x07; if (ata_id_is_cfa(id)) { /* * Process compact flash extended modes */ int pio = (id[ATA_ID_CFA_MODES] >> 0) & 0x7; int dma = (id[ATA_ID_CFA_MODES] >> 3) & 0x7; if (pio) pio_mask |= (1 << 5); if (pio > 1) pio_mask |= (1 << 6); if (dma) mwdma_mask |= (1 << 3); if (dma > 1) mwdma_mask |= (1 << 4); } udma_mask = 0; if (id[ATA_ID_FIELD_VALID] & (1 << 2)) udma_mask = id[ATA_ID_UDMA_MODES] & 0xff; return ata_pack_xfermask(pio_mask, mwdma_mask, udma_mask); } EXPORT_SYMBOL_GPL(ata_id_xfermask); static void ata_qc_complete_internal(struct ata_queued_cmd *qc) { struct completion *waiting = qc->private_data; complete(waiting); } /** * ata_exec_internal_sg - execute libata internal command * @dev: Device to which the command is sent * @tf: Taskfile registers for the command and the result * @cdb: CDB for packet command * @dma_dir: Data transfer direction of the command * @sgl: sg list for the data buffer of the command * @n_elem: Number of sg entries * @timeout: Timeout in msecs (0 for default) * * Executes libata internal command with timeout. @tf contains * command on entry and result on return. Timeout and error * conditions are reported via return value. No recovery action * is taken after a command times out. It's caller's duty to * clean up after timeout. * * LOCKING: * None. Should be called with kernel context, might sleep. * * RETURNS: * Zero on success, AC_ERR_* mask on failure */ unsigned ata_exec_internal_sg(struct ata_device *dev, struct ata_taskfile *tf, const u8 *cdb, int dma_dir, struct scatterlist *sgl, unsigned int n_elem, unsigned long timeout) { struct ata_link *link = dev->link; struct ata_port *ap = link->ap; u8 command = tf->command; int auto_timeout = 0; struct ata_queued_cmd *qc; unsigned int preempted_tag; u32 preempted_sactive; u64 preempted_qc_active; int preempted_nr_active_links; DECLARE_COMPLETION_ONSTACK(wait); unsigned long flags; unsigned int err_mask; int rc; spin_lock_irqsave(ap->lock, flags); /* no internal command while frozen */ if (ap->pflags & ATA_PFLAG_FROZEN) { spin_unlock_irqrestore(ap->lock, flags); return AC_ERR_SYSTEM; } /* initialize internal qc */ qc = __ata_qc_from_tag(ap, ATA_TAG_INTERNAL); qc->tag = ATA_TAG_INTERNAL; qc->hw_tag = 0; qc->scsicmd = NULL; qc->ap = ap; qc->dev = dev; ata_qc_reinit(qc); preempted_tag = link->active_tag; preempted_sactive = link->sactive; preempted_qc_active = ap->qc_active; preempted_nr_active_links = ap->nr_active_links; link->active_tag = ATA_TAG_POISON; link->sactive = 0; ap->qc_active = 0; ap->nr_active_links = 0; /* prepare & issue qc */ qc->tf = *tf; if (cdb) memcpy(qc->cdb, cdb, ATAPI_CDB_LEN); /* some SATA bridges need us to indicate data xfer direction */ if (tf->protocol == ATAPI_PROT_DMA && (dev->flags & ATA_DFLAG_DMADIR) && dma_dir == DMA_FROM_DEVICE) qc->tf.feature |= ATAPI_DMADIR; qc->flags |= ATA_QCFLAG_RESULT_TF; qc->dma_dir = dma_dir; if (dma_dir != DMA_NONE) { unsigned int i, buflen = 0; struct scatterlist *sg; for_each_sg(sgl, sg, n_elem, i) buflen += sg->length; ata_sg_init(qc, sgl, n_elem); qc->nbytes = buflen; } qc->private_data = &wait; qc->complete_fn = ata_qc_complete_internal; ata_qc_issue(qc); spin_unlock_irqrestore(ap->lock, flags); if (!timeout) { if (ata_probe_timeout) timeout = ata_probe_timeout * 1000; else { timeout = ata_internal_cmd_timeout(dev, command); auto_timeout = 1; } } if (ap->ops->error_handler) ata_eh_release(ap); rc = wait_for_completion_timeout(&wait, msecs_to_jiffies(timeout)); if (ap->ops->error_handler) ata_eh_acquire(ap); ata_sff_flush_pio_task(ap); if (!rc) { spin_lock_irqsave(ap->lock, flags); /* We're racing with irq here. If we lose, the * following test prevents us from completing the qc * twice. If we win, the port is frozen and will be * cleaned up by ->post_internal_cmd(). */ if (qc->flags & ATA_QCFLAG_ACTIVE) { qc->err_mask |= AC_ERR_TIMEOUT; if (ap->ops->error_handler) ata_port_freeze(ap); else ata_qc_complete(qc); if (ata_msg_warn(ap)) ata_dev_warn(dev, "qc timeout (cmd 0x%x)\n", command); } spin_unlock_irqrestore(ap->lock, flags); } /* do post_internal_cmd */ if (ap->ops->post_internal_cmd) ap->ops->post_internal_cmd(qc); /* perform minimal error analysis */ if (qc->flags & ATA_QCFLAG_FAILED) { if (qc->result_tf.command & (ATA_ERR | ATA_DF)) qc->err_mask |= AC_ERR_DEV; if (!qc->err_mask) qc->err_mask |= AC_ERR_OTHER; if (qc->err_mask & ~AC_ERR_OTHER) qc->err_mask &= ~AC_ERR_OTHER; } else if (qc->tf.command == ATA_CMD_REQ_SENSE_DATA) { qc->result_tf.command |= ATA_SENSE; } /* finish up */ spin_lock_irqsave(ap->lock, flags); *tf = qc->result_tf; err_mask = qc->err_mask; ata_qc_free(qc); link->active_tag = preempted_tag; link->sactive = preempted_sactive; ap->qc_active = preempted_qc_active; ap->nr_active_links = preempted_nr_active_links; spin_unlock_irqrestore(ap->lock, flags); if ((err_mask & AC_ERR_TIMEOUT) && auto_timeout) ata_internal_cmd_timed_out(dev, command); return err_mask; } /** * ata_exec_internal - execute libata internal command * @dev: Device to which the command is sent * @tf: Taskfile registers for the command and the result * @cdb: CDB for packet command * @dma_dir: Data transfer direction of the command * @buf: Data buffer of the command * @buflen: Length of data buffer * @timeout: Timeout in msecs (0 for default) * * Wrapper around ata_exec_internal_sg() which takes simple * buffer instead of sg list. * * LOCKING: * None. Should be called with kernel context, might sleep. * * RETURNS: * Zero on success, AC_ERR_* mask on failure */ unsigned ata_exec_internal(struct ata_device *dev, struct ata_taskfile *tf, const u8 *cdb, int dma_dir, void *buf, unsigned int buflen, unsigned long timeout) { struct scatterlist *psg = NULL, sg; unsigned int n_elem = 0; if (dma_dir != DMA_NONE) { WARN_ON(!buf); sg_init_one(&sg, buf, buflen); psg = &sg; n_elem++; } return ata_exec_internal_sg(dev, tf, cdb, dma_dir, psg, n_elem, timeout); } /** * ata_pio_need_iordy - check if iordy needed * @adev: ATA device * * Check if the current speed of the device requires IORDY. Used * by various controllers for chip configuration. */ unsigned int ata_pio_need_iordy(const struct ata_device *adev) { /* Don't set IORDY if we're preparing for reset. IORDY may * lead to controller lock up on certain controllers if the * port is not occupied. See bko#11703 for details. */ if (adev->link->ap->pflags & ATA_PFLAG_RESETTING) return 0; /* Controller doesn't support IORDY. Probably a pointless * check as the caller should know this. */ if (adev->link->ap->flags & ATA_FLAG_NO_IORDY) return 0; /* CF spec. r4.1 Table 22 says no iordy on PIO5 and PIO6. */ if (ata_id_is_cfa(adev->id) && (adev->pio_mode == XFER_PIO_5 || adev->pio_mode == XFER_PIO_6)) return 0; /* PIO3 and higher it is mandatory */ if (adev->pio_mode > XFER_PIO_2) return 1; /* We turn it on when possible */ if (ata_id_has_iordy(adev->id)) return 1; return 0; } EXPORT_SYMBOL_GPL(ata_pio_need_iordy); /** * ata_pio_mask_no_iordy - Return the non IORDY mask * @adev: ATA device * * Compute the highest mode possible if we are not using iordy. Return * -1 if no iordy mode is available. */ static u32 ata_pio_mask_no_iordy(const struct ata_device *adev) { /* If we have no drive specific rule, then PIO 2 is non IORDY */ if (adev->id[ATA_ID_FIELD_VALID] & 2) { /* EIDE */ u16 pio = adev->id[ATA_ID_EIDE_PIO]; /* Is the speed faster than the drive allows non IORDY ? */ if (pio) { /* This is cycle times not frequency - watch the logic! */ if (pio > 240) /* PIO2 is 240nS per cycle */ return 3 << ATA_SHIFT_PIO; return 7 << ATA_SHIFT_PIO; } } return 3 << ATA_SHIFT_PIO; } /** * ata_do_dev_read_id - default ID read method * @dev: device * @tf: proposed taskfile * @id: data buffer * * Issue the identify taskfile and hand back the buffer containing * identify data. For some RAID controllers and for pre ATA devices * this function is wrapped or replaced by the driver */ unsigned int ata_do_dev_read_id(struct ata_device *dev, struct ata_taskfile *tf, u16 *id) { return ata_exec_internal(dev, tf, NULL, DMA_FROM_DEVICE, id, sizeof(id[0]) * ATA_ID_WORDS, 0); } EXPORT_SYMBOL_GPL(ata_do_dev_read_id); /** * ata_dev_read_id - Read ID data from the specified device * @dev: target device * @p_class: pointer to class of the target device (may be changed) * @flags: ATA_READID_* flags * @id: buffer to read IDENTIFY data into * * Read ID data from the specified device. ATA_CMD_ID_ATA is * performed on ATA devices and ATA_CMD_ID_ATAPI on ATAPI * devices. This function also issues ATA_CMD_INIT_DEV_PARAMS * for pre-ATA4 drives. * * FIXME: ATA_CMD_ID_ATA is optional for early drives and right * now we abort if we hit that case. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 on success, -errno otherwise. */ int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class, unsigned int flags, u16 *id) { struct ata_port *ap = dev->link->ap; unsigned int class = *p_class; struct ata_taskfile tf; unsigned int err_mask = 0; const char *reason; bool is_semb = class == ATA_DEV_SEMB; int may_fallback = 1, tried_spinup = 0; int rc; if (ata_msg_ctl(ap)) ata_dev_dbg(dev, "%s: ENTER\n", __func__); retry: ata_tf_init(dev, &tf); switch (class) { case ATA_DEV_SEMB: class = ATA_DEV_ATA; /* some hard drives report SEMB sig */ fallthrough; case ATA_DEV_ATA: case ATA_DEV_ZAC: tf.command = ATA_CMD_ID_ATA; break; case ATA_DEV_ATAPI: tf.command = ATA_CMD_ID_ATAPI; break; default: rc = -ENODEV; reason = "unsupported class"; goto err_out; } tf.protocol = ATA_PROT_PIO; /* Some devices choke if TF registers contain garbage. Make * sure those are properly initialized. */ tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; /* Device presence detection is unreliable on some * controllers. Always poll IDENTIFY if available. */ tf.flags |= ATA_TFLAG_POLLING; if (ap->ops->read_id) err_mask = ap->ops->read_id(dev, &tf, id); else err_mask = ata_do_dev_read_id(dev, &tf, id); if (err_mask) { if (err_mask & AC_ERR_NODEV_HINT) { ata_dev_dbg(dev, "NODEV after polling detection\n"); return -ENOENT; } if (is_semb) { ata_dev_info(dev, "IDENTIFY failed on device w/ SEMB sig, disabled\n"); /* SEMB is not supported yet */ *p_class = ATA_DEV_SEMB_UNSUP; return 0; } if ((err_mask == AC_ERR_DEV) && (tf.feature & ATA_ABORTED)) { /* Device or controller might have reported * the wrong device class. Give a shot at the * other IDENTIFY if the current one is * aborted by the device. */ if (may_fallback) { may_fallback = 0; if (class == ATA_DEV_ATA) class = ATA_DEV_ATAPI; else class = ATA_DEV_ATA; goto retry; } /* Control reaches here iff the device aborted * both flavors of IDENTIFYs which happens * sometimes with phantom devices. */ ata_dev_dbg(dev, "both IDENTIFYs aborted, assuming NODEV\n"); return -ENOENT; } rc = -EIO; reason = "I/O error"; goto err_out; } if (dev->horkage & ATA_HORKAGE_DUMP_ID) { ata_dev_dbg(dev, "dumping IDENTIFY data, " "class=%d may_fallback=%d tried_spinup=%d\n", class, may_fallback, tried_spinup); print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET, 16, 2, id, ATA_ID_WORDS * sizeof(*id), true); } /* Falling back doesn't make sense if ID data was read * successfully at least once. */ may_fallback = 0; swap_buf_le16(id, ATA_ID_WORDS); /* sanity check */ rc = -EINVAL; reason = "device reports invalid type"; if (class == ATA_DEV_ATA || class == ATA_DEV_ZAC) { if (!ata_id_is_ata(id) && !ata_id_is_cfa(id)) goto err_out; if (ap->host->flags & ATA_HOST_IGNORE_ATA && ata_id_is_ata(id)) { ata_dev_dbg(dev, "host indicates ignore ATA devices, ignored\n"); return -ENOENT; } } else { if (ata_id_is_ata(id)) goto err_out; } if (!tried_spinup && (id[2] == 0x37c8 || id[2] == 0x738c)) { tried_spinup = 1; /* * Drive powered-up in standby mode, and requires a specific * SET_FEATURES spin-up subcommand before it will accept * anything other than the original IDENTIFY command. */ err_mask = ata_dev_set_feature(dev, SETFEATURES_SPINUP, 0); if (err_mask && id[2] != 0x738c) { rc = -EIO; reason = "SPINUP failed"; goto err_out; } /* * If the drive initially returned incomplete IDENTIFY info, * we now must reissue the IDENTIFY command. */ if (id[2] == 0x37c8) goto retry; } if ((flags & ATA_READID_POSTRESET) && (class == ATA_DEV_ATA || class == ATA_DEV_ZAC)) { /* * The exact sequence expected by certain pre-ATA4 drives is: * SRST RESET * IDENTIFY (optional in early ATA) * INITIALIZE DEVICE PARAMETERS (later IDE and ATA) * anything else.. * Some drives were very specific about that exact sequence. * * Note that ATA4 says lba is mandatory so the second check * should never trigger. */ if (ata_id_major_version(id) < 4 || !ata_id_has_lba(id)) { err_mask = ata_dev_init_params(dev, id[3], id[6]); if (err_mask) { rc = -EIO; reason = "INIT_DEV_PARAMS failed"; goto err_out; } /* current CHS translation info (id[53-58]) might be * changed. reread the identify device info. */ flags &= ~ATA_READID_POSTRESET; goto retry; } } *p_class = class; return 0; err_out: if (ata_msg_warn(ap)) ata_dev_warn(dev, "failed to IDENTIFY (%s, err_mask=0x%x)\n", reason, err_mask); return rc; } /** * ata_read_log_page - read a specific log page * @dev: target device * @log: log to read * @page: page to read * @buf: buffer to store read page * @sectors: number of sectors to read * * Read log page using READ_LOG_EXT command. * * LOCKING: * Kernel thread context (may sleep). * * RETURNS: * 0 on success, AC_ERR_* mask otherwise. */ unsigned int ata_read_log_page(struct ata_device *dev, u8 log, u8 page, void *buf, unsigned int sectors) { unsigned long ap_flags = dev->link->ap->flags; struct ata_taskfile tf; unsigned int err_mask; bool dma = false; DPRINTK("read log page - log 0x%x, page 0x%x\n", log, page); /* * Return error without actually issuing the command on controllers * which e.g. lockup on a read log page. */ if (ap_flags & ATA_FLAG_NO_LOG_PAGE) return AC_ERR_DEV; retry: ata_tf_init(dev, &tf); if (dev->dma_mode && ata_id_has_read_log_dma_ext(dev->id) && !(dev->horkage & ATA_HORKAGE_NO_DMA_LOG)) { tf.command = ATA_CMD_READ_LOG_DMA_EXT; tf.protocol = ATA_PROT_DMA; dma = true; } else { tf.command = ATA_CMD_READ_LOG_EXT; tf.protocol = ATA_PROT_PIO; dma = false; } tf.lbal = log; tf.lbam = page; tf.nsect = sectors; tf.hob_nsect = sectors >> 8; tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_LBA48 | ATA_TFLAG_DEVICE; err_mask = ata_exec_internal(dev, &tf, NULL, DMA_FROM_DEVICE, buf, sectors * ATA_SECT_SIZE, 0); if (err_mask && dma) { dev->horkage |= ATA_HORKAGE_NO_DMA_LOG; ata_dev_warn(dev, "READ LOG DMA EXT failed, trying PIO\n"); goto retry; } DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; } static bool ata_log_supported(struct ata_device *dev, u8 log) { struct ata_port *ap = dev->link->ap; if (ata_read_log_page(dev, ATA_LOG_DIRECTORY, 0, ap->sector_buf, 1)) return false; return get_unaligned_le16(&ap->sector_buf[log * 2]) ? true : false; } static bool ata_identify_page_supported(struct ata_device *dev, u8 page) { struct ata_port *ap = dev->link->ap; unsigned int err, i; if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE)) { ata_dev_warn(dev, "ATA Identify Device Log not supported\n"); return false; } /* * Read IDENTIFY DEVICE data log, page 0, to figure out if the page is * supported. */ err = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, 0, ap->sector_buf, 1); if (err) { ata_dev_info(dev, "failed to get Device Identify Log Emask 0x%x\n", err); return false; } for (i = 0; i < ap->sector_buf[8]; i++) { if (ap->sector_buf[9 + i] == page) return true; } return false; } static int ata_do_link_spd_horkage(struct ata_device *dev) { struct ata_link *plink = ata_dev_phys_link(dev); u32 target, target_limit; if (!sata_scr_valid(plink)) return 0; if (dev->horkage & ATA_HORKAGE_1_5_GBPS) target = 1; else return 0; target_limit = (1 << target) - 1; /* if already on stricter limit, no need to push further */ if (plink->sata_spd_limit <= target_limit) return 0; plink->sata_spd_limit = target_limit; /* Request another EH round by returning -EAGAIN if link is * going faster than the target speed. Forward progress is * guaranteed by setting sata_spd_limit to target_limit above. */ if (plink->sata_spd > target) { ata_dev_info(dev, "applying link speed limit horkage to %s\n", sata_spd_string(target)); return -EAGAIN; } return 0; } static inline u8 ata_dev_knobble(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; if (ata_dev_blacklisted(dev) & ATA_HORKAGE_BRIDGE_OK) return 0; return ((ap->cbl == ATA_CBL_SATA) && (!ata_id_is_sata(dev->id))); } static void ata_dev_config_ncq_send_recv(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; unsigned int err_mask; if (!ata_log_supported(dev, ATA_LOG_NCQ_SEND_RECV)) { ata_dev_warn(dev, "NCQ Send/Recv Log not supported\n"); return; } err_mask = ata_read_log_page(dev, ATA_LOG_NCQ_SEND_RECV, 0, ap->sector_buf, 1); if (err_mask) { ata_dev_dbg(dev, "failed to get NCQ Send/Recv Log Emask 0x%x\n", err_mask); } else { u8 *cmds = dev->ncq_send_recv_cmds; dev->flags |= ATA_DFLAG_NCQ_SEND_RECV; memcpy(cmds, ap->sector_buf, ATA_LOG_NCQ_SEND_RECV_SIZE); if (dev->horkage & ATA_HORKAGE_NO_NCQ_TRIM) { ata_dev_dbg(dev, "disabling queued TRIM support\n"); cmds[ATA_LOG_NCQ_SEND_RECV_DSM_OFFSET] &= ~ATA_LOG_NCQ_SEND_RECV_DSM_TRIM; } } } static void ata_dev_config_ncq_non_data(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; unsigned int err_mask; if (!ata_log_supported(dev, ATA_LOG_NCQ_NON_DATA)) { ata_dev_warn(dev, "NCQ Send/Recv Log not supported\n"); return; } err_mask = ata_read_log_page(dev, ATA_LOG_NCQ_NON_DATA, 0, ap->sector_buf, 1); if (err_mask) { ata_dev_dbg(dev, "failed to get NCQ Non-Data Log Emask 0x%x\n", err_mask); } else { u8 *cmds = dev->ncq_non_data_cmds; memcpy(cmds, ap->sector_buf, ATA_LOG_NCQ_NON_DATA_SIZE); } } static void ata_dev_config_ncq_prio(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; unsigned int err_mask; if (!(dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLE)) { dev->flags &= ~ATA_DFLAG_NCQ_PRIO; return; } err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, ATA_LOG_SATA_SETTINGS, ap->sector_buf, 1); if (err_mask) { ata_dev_dbg(dev, "failed to get Identify Device data, Emask 0x%x\n", err_mask); return; } if (ap->sector_buf[ATA_LOG_NCQ_PRIO_OFFSET] & BIT(3)) { dev->flags |= ATA_DFLAG_NCQ_PRIO; } else { dev->flags &= ~ATA_DFLAG_NCQ_PRIO; ata_dev_dbg(dev, "SATA page does not support priority\n"); } } static bool ata_dev_check_adapter(struct ata_device *dev, unsigned short vendor_id) { struct pci_dev *pcidev = NULL; struct device *parent_dev = NULL; for (parent_dev = dev->tdev.parent; parent_dev != NULL; parent_dev = parent_dev->parent) { if (dev_is_pci(parent_dev)) { pcidev = to_pci_dev(parent_dev); if (pcidev->vendor == vendor_id) return true; break; } } return false; } static int ata_dev_config_ncq(struct ata_device *dev, char *desc, size_t desc_sz) { struct ata_port *ap = dev->link->ap; int hdepth = 0, ddepth = ata_id_queue_depth(dev->id); unsigned int err_mask; char *aa_desc = ""; if (!ata_id_has_ncq(dev->id)) { desc[0] = '\0'; return 0; } if (!IS_ENABLED(CONFIG_SATA_HOST)) return 0; if (dev->horkage & ATA_HORKAGE_NONCQ) { snprintf(desc, desc_sz, "NCQ (not used)"); return 0; } if (dev->horkage & ATA_HORKAGE_NO_NCQ_ON_ATI && ata_dev_check_adapter(dev, PCI_VENDOR_ID_ATI)) { snprintf(desc, desc_sz, "NCQ (not used)"); return 0; } if (ap->flags & ATA_FLAG_NCQ) { hdepth = min(ap->scsi_host->can_queue, ATA_MAX_QUEUE); dev->flags |= ATA_DFLAG_NCQ; } if (!(dev->horkage & ATA_HORKAGE_BROKEN_FPDMA_AA) && (ap->flags & ATA_FLAG_FPDMA_AA) && ata_id_has_fpdma_aa(dev->id)) { err_mask = ata_dev_set_feature(dev, SETFEATURES_SATA_ENABLE, SATA_FPDMA_AA); if (err_mask) { ata_dev_err(dev, "failed to enable AA (error_mask=0x%x)\n", err_mask); if (err_mask != AC_ERR_DEV) { dev->horkage |= ATA_HORKAGE_BROKEN_FPDMA_AA; return -EIO; } } else aa_desc = ", AA"; } if (hdepth >= ddepth) snprintf(desc, desc_sz, "NCQ (depth %d)%s", ddepth, aa_desc); else snprintf(desc, desc_sz, "NCQ (depth %d/%d)%s", hdepth, ddepth, aa_desc); if ((ap->flags & ATA_FLAG_FPDMA_AUX)) { if (ata_id_has_ncq_send_and_recv(dev->id)) ata_dev_config_ncq_send_recv(dev); if (ata_id_has_ncq_non_data(dev->id)) ata_dev_config_ncq_non_data(dev); if (ata_id_has_ncq_prio(dev->id)) ata_dev_config_ncq_prio(dev); } return 0; } static void ata_dev_config_sense_reporting(struct ata_device *dev) { unsigned int err_mask; if (!ata_id_has_sense_reporting(dev->id)) return; if (ata_id_sense_reporting_enabled(dev->id)) return; err_mask = ata_dev_set_feature(dev, SETFEATURE_SENSE_DATA, 0x1); if (err_mask) { ata_dev_dbg(dev, "failed to enable Sense Data Reporting, Emask 0x%x\n", err_mask); } } static void ata_dev_config_zac(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; unsigned int err_mask; u8 *identify_buf = ap->sector_buf; dev->zac_zones_optimal_open = U32_MAX; dev->zac_zones_optimal_nonseq = U32_MAX; dev->zac_zones_max_open = U32_MAX; /* * Always set the 'ZAC' flag for Host-managed devices. */ if (dev->class == ATA_DEV_ZAC) dev->flags |= ATA_DFLAG_ZAC; else if (ata_id_zoned_cap(dev->id) == 0x01) /* * Check for host-aware devices. */ dev->flags |= ATA_DFLAG_ZAC; if (!(dev->flags & ATA_DFLAG_ZAC)) return; if (!ata_identify_page_supported(dev, ATA_LOG_ZONED_INFORMATION)) { ata_dev_warn(dev, "ATA Zoned Information Log not supported\n"); return; } /* * Read IDENTIFY DEVICE data log, page 9 (Zoned-device information) */ err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, ATA_LOG_ZONED_INFORMATION, identify_buf, 1); if (!err_mask) { u64 zoned_cap, opt_open, opt_nonseq, max_open; zoned_cap = get_unaligned_le64(&identify_buf[8]); if ((zoned_cap >> 63)) dev->zac_zoned_cap = (zoned_cap & 1); opt_open = get_unaligned_le64(&identify_buf[24]); if ((opt_open >> 63)) dev->zac_zones_optimal_open = (u32)opt_open; opt_nonseq = get_unaligned_le64(&identify_buf[32]); if ((opt_nonseq >> 63)) dev->zac_zones_optimal_nonseq = (u32)opt_nonseq; max_open = get_unaligned_le64(&identify_buf[40]); if ((max_open >> 63)) dev->zac_zones_max_open = (u32)max_open; } } static void ata_dev_config_trusted(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; u64 trusted_cap; unsigned int err; if (!ata_id_has_trusted(dev->id)) return; if (!ata_identify_page_supported(dev, ATA_LOG_SECURITY)) { ata_dev_warn(dev, "Security Log not supported\n"); return; } err = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, ATA_LOG_SECURITY, ap->sector_buf, 1); if (err) { ata_dev_dbg(dev, "failed to read Security Log, Emask 0x%x\n", err); return; } trusted_cap = get_unaligned_le64(&ap->sector_buf[40]); if (!(trusted_cap & (1ULL << 63))) { ata_dev_dbg(dev, "Trusted Computing capability qword not valid!\n"); return; } if (trusted_cap & (1 << 0)) dev->flags |= ATA_DFLAG_TRUSTED; } /** * ata_dev_configure - Configure the specified ATA/ATAPI device * @dev: Target device to configure * * Configure @dev according to @dev->id. Generic and low-level * driver specific fixups are also applied. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 on success, -errno otherwise */ int ata_dev_configure(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; struct ata_eh_context *ehc = &dev->link->eh_context; int print_info = ehc->i.flags & ATA_EHI_PRINTINFO; const u16 *id = dev->id; unsigned long xfer_mask; unsigned int err_mask; char revbuf[7]; /* XYZ-99\0 */ char fwrevbuf[ATA_ID_FW_REV_LEN+1]; char modelbuf[ATA_ID_PROD_LEN+1]; int rc; if (!ata_dev_enabled(dev) && ata_msg_info(ap)) { ata_dev_info(dev, "%s: ENTER/EXIT -- nodev\n", __func__); return 0; } if (ata_msg_probe(ap)) ata_dev_dbg(dev, "%s: ENTER\n", __func__); /* set horkage */ dev->horkage |= ata_dev_blacklisted(dev); ata_force_horkage(dev); if (dev->horkage & ATA_HORKAGE_DISABLE) { ata_dev_info(dev, "unsupported device, disabling\n"); ata_dev_disable(dev); return 0; } if ((!atapi_enabled || (ap->flags & ATA_FLAG_NO_ATAPI)) && dev->class == ATA_DEV_ATAPI) { ata_dev_warn(dev, "WARNING: ATAPI is %s, device ignored\n", atapi_enabled ? "not supported with this driver" : "disabled"); ata_dev_disable(dev); return 0; } rc = ata_do_link_spd_horkage(dev); if (rc) return rc; /* some WD SATA-1 drives have issues with LPM, turn on NOLPM for them */ if ((dev->horkage & ATA_HORKAGE_WD_BROKEN_LPM) && (id[ATA_ID_SATA_CAPABILITY] & 0xe) == 0x2) dev->horkage |= ATA_HORKAGE_NOLPM; if (ap->flags & ATA_FLAG_NO_LPM) dev->horkage |= ATA_HORKAGE_NOLPM; if (dev->horkage & ATA_HORKAGE_NOLPM) { ata_dev_warn(dev, "LPM support broken, forcing max_power\n"); dev->link->ap->target_lpm_policy = ATA_LPM_MAX_POWER; } /* let ACPI work its magic */ rc = ata_acpi_on_devcfg(dev); if (rc) return rc; /* massage HPA, do it early as it might change IDENTIFY data */ rc = ata_hpa_resize(dev); if (rc) return rc; /* print device capabilities */ if (ata_msg_probe(ap)) ata_dev_dbg(dev, "%s: cfg 49:%04x 82:%04x 83:%04x 84:%04x " "85:%04x 86:%04x 87:%04x 88:%04x\n", __func__, id[49], id[82], id[83], id[84], id[85], id[86], id[87], id[88]); /* initialize to-be-configured parameters */ dev->flags &= ~ATA_DFLAG_CFG_MASK; dev->max_sectors = 0; dev->cdb_len = 0; dev->n_sectors = 0; dev->cylinders = 0; dev->heads = 0; dev->sectors = 0; dev->multi_count = 0; /* * common ATA, ATAPI feature tests */ /* find max transfer mode; for printk only */ xfer_mask = ata_id_xfermask(id); if (ata_msg_probe(ap)) ata_dump_id(id); /* SCSI only uses 4-char revisions, dump full 8 chars from ATA */ ata_id_c_string(dev->id, fwrevbuf, ATA_ID_FW_REV, sizeof(fwrevbuf)); ata_id_c_string(dev->id, modelbuf, ATA_ID_PROD, sizeof(modelbuf)); /* ATA-specific feature tests */ if (dev->class == ATA_DEV_ATA || dev->class == ATA_DEV_ZAC) { if (ata_id_is_cfa(id)) { /* CPRM may make this media unusable */ if (id[ATA_ID_CFA_KEY_MGMT] & 1) ata_dev_warn(dev, "supports DRM functions and may not be fully accessible\n"); snprintf(revbuf, 7, "CFA"); } else { snprintf(revbuf, 7, "ATA-%d", ata_id_major_version(id)); /* Warn the user if the device has TPM extensions */ if (ata_id_has_tpm(id)) ata_dev_warn(dev, "supports DRM functions and may not be fully accessible\n"); } dev->n_sectors = ata_id_n_sectors(id); /* get current R/W Multiple count setting */ if ((dev->id[47] >> 8) == 0x80 && (dev->id[59] & 0x100)) { unsigned int max = dev->id[47] & 0xff; unsigned int cnt = dev->id[59] & 0xff; /* only recognize/allow powers of two here */ if (is_power_of_2(max) && is_power_of_2(cnt)) if (cnt <= max) dev->multi_count = cnt; } if (ata_id_has_lba(id)) { const char *lba_desc; char ncq_desc[24]; lba_desc = "LBA"; dev->flags |= ATA_DFLAG_LBA; if (ata_id_has_lba48(id)) { dev->flags |= ATA_DFLAG_LBA48; lba_desc = "LBA48"; if (dev->n_sectors >= (1UL << 28) && ata_id_has_flush_ext(id)) dev->flags |= ATA_DFLAG_FLUSH_EXT; } /* config NCQ */ rc = ata_dev_config_ncq(dev, ncq_desc, sizeof(ncq_desc)); if (rc) return rc; /* print device info to dmesg */ if (ata_msg_drv(ap) && print_info) { ata_dev_info(dev, "%s: %s, %s, max %s\n", revbuf, modelbuf, fwrevbuf, ata_mode_string(xfer_mask)); ata_dev_info(dev, "%llu sectors, multi %u: %s %s\n", (unsigned long long)dev->n_sectors, dev->multi_count, lba_desc, ncq_desc); } } else { /* CHS */ /* Default translation */ dev->cylinders = id[1]; dev->heads = id[3]; dev->sectors = id[6]; if (ata_id_current_chs_valid(id)) { /* Current CHS translation is valid. */ dev->cylinders = id[54]; dev->heads = id[55]; dev->sectors = id[56]; } /* print device info to dmesg */ if (ata_msg_drv(ap) && print_info) { ata_dev_info(dev, "%s: %s, %s, max %s\n", revbuf, modelbuf, fwrevbuf, ata_mode_string(xfer_mask)); ata_dev_info(dev, "%llu sectors, multi %u, CHS %u/%u/%u\n", (unsigned long long)dev->n_sectors, dev->multi_count, dev->cylinders, dev->heads, dev->sectors); } } /* Check and mark DevSlp capability. Get DevSlp timing variables * from SATA Settings page of Identify Device Data Log. */ if (ata_id_has_devslp(dev->id)) { u8 *sata_setting = ap->sector_buf; int i, j; dev->flags |= ATA_DFLAG_DEVSLP; err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, ATA_LOG_SATA_SETTINGS, sata_setting, 1); if (err_mask) ata_dev_dbg(dev, "failed to get Identify Device Data, Emask 0x%x\n", err_mask); else for (i = 0; i < ATA_LOG_DEVSLP_SIZE; i++) { j = ATA_LOG_DEVSLP_OFFSET + i; dev->devslp_timing[i] = sata_setting[j]; } } ata_dev_config_sense_reporting(dev); ata_dev_config_zac(dev); ata_dev_config_trusted(dev); dev->cdb_len = 32; } /* ATAPI-specific feature tests */ else if (dev->class == ATA_DEV_ATAPI) { const char *cdb_intr_string = ""; const char *atapi_an_string = ""; const char *dma_dir_string = ""; u32 sntf; rc = atapi_cdb_len(id); if ((rc < 12) || (rc > ATAPI_CDB_LEN)) { if (ata_msg_warn(ap)) ata_dev_warn(dev, "unsupported CDB len\n"); rc = -EINVAL; goto err_out_nosup; } dev->cdb_len = (unsigned int) rc; /* Enable ATAPI AN if both the host and device have * the support. If PMP is attached, SNTF is required * to enable ATAPI AN to discern between PHY status * changed notifications and ATAPI ANs. */ if (atapi_an && (ap->flags & ATA_FLAG_AN) && ata_id_has_atapi_AN(id) && (!sata_pmp_attached(ap) || sata_scr_read(&ap->link, SCR_NOTIFICATION, &sntf) == 0)) { /* issue SET feature command to turn this on */ err_mask = ata_dev_set_feature(dev, SETFEATURES_SATA_ENABLE, SATA_AN); if (err_mask) ata_dev_err(dev, "failed to enable ATAPI AN (err_mask=0x%x)\n", err_mask); else { dev->flags |= ATA_DFLAG_AN; atapi_an_string = ", ATAPI AN"; } } if (ata_id_cdb_intr(dev->id)) { dev->flags |= ATA_DFLAG_CDB_INTR; cdb_intr_string = ", CDB intr"; } if (atapi_dmadir || (dev->horkage & ATA_HORKAGE_ATAPI_DMADIR) || atapi_id_dmadir(dev->id)) { dev->flags |= ATA_DFLAG_DMADIR; dma_dir_string = ", DMADIR"; } if (ata_id_has_da(dev->id)) { dev->flags |= ATA_DFLAG_DA; zpodd_init(dev); } /* print device info to dmesg */ if (ata_msg_drv(ap) && print_info) ata_dev_info(dev, "ATAPI: %s, %s, max %s%s%s%s\n", modelbuf, fwrevbuf, ata_mode_string(xfer_mask), cdb_intr_string, atapi_an_string, dma_dir_string); } /* determine max_sectors */ dev->max_sectors = ATA_MAX_SECTORS; if (dev->flags & ATA_DFLAG_LBA48) dev->max_sectors = ATA_MAX_SECTORS_LBA48; /* Limit PATA drive on SATA cable bridge transfers to udma5, 200 sectors */ if (ata_dev_knobble(dev)) { if (ata_msg_drv(ap) && print_info) ata_dev_info(dev, "applying bridge limits\n"); dev->udma_mask &= ATA_UDMA5; dev->max_sectors = ATA_MAX_SECTORS; } if ((dev->class == ATA_DEV_ATAPI) && (atapi_command_packet_set(id) == TYPE_TAPE)) { dev->max_sectors = ATA_MAX_SECTORS_TAPE; dev->horkage |= ATA_HORKAGE_STUCK_ERR; } if (dev->horkage & ATA_HORKAGE_MAX_SEC_128) dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_128, dev->max_sectors); if (dev->horkage & ATA_HORKAGE_MAX_SEC_1024) dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_1024, dev->max_sectors); if (dev->horkage & ATA_HORKAGE_MAX_SEC_LBA48) dev->max_sectors = ATA_MAX_SECTORS_LBA48; if (ap->ops->dev_config) ap->ops->dev_config(dev); if (dev->horkage & ATA_HORKAGE_DIAGNOSTIC) { /* Let the user know. We don't want to disallow opens for rescue purposes, or in case the vendor is just a blithering idiot. Do this after the dev_config call as some controllers with buggy firmware may want to avoid reporting false device bugs */ if (print_info) { ata_dev_warn(dev, "Drive reports diagnostics failure. This may indicate a drive\n"); ata_dev_warn(dev, "fault or invalid emulation. Contact drive vendor for information.\n"); } } if ((dev->horkage & ATA_HORKAGE_FIRMWARE_WARN) && print_info) { ata_dev_warn(dev, "WARNING: device requires firmware update to be fully functional\n"); ata_dev_warn(dev, " contact the vendor or visit http://ata.wiki.kernel.org\n"); } return 0; err_out_nosup: if (ata_msg_probe(ap)) ata_dev_dbg(dev, "%s: EXIT, err\n", __func__); return rc; } /** * ata_cable_40wire - return 40 wire cable type * @ap: port * * Helper method for drivers which want to hardwire 40 wire cable * detection. */ int ata_cable_40wire(struct ata_port *ap) { return ATA_CBL_PATA40; } EXPORT_SYMBOL_GPL(ata_cable_40wire); /** * ata_cable_80wire - return 80 wire cable type * @ap: port * * Helper method for drivers which want to hardwire 80 wire cable * detection. */ int ata_cable_80wire(struct ata_port *ap) { return ATA_CBL_PATA80; } EXPORT_SYMBOL_GPL(ata_cable_80wire); /** * ata_cable_unknown - return unknown PATA cable. * @ap: port * * Helper method for drivers which have no PATA cable detection. */ int ata_cable_unknown(struct ata_port *ap) { return ATA_CBL_PATA_UNK; } EXPORT_SYMBOL_GPL(ata_cable_unknown); /** * ata_cable_ignore - return ignored PATA cable. * @ap: port * * Helper method for drivers which don't use cable type to limit * transfer mode. */ int ata_cable_ignore(struct ata_port *ap) { return ATA_CBL_PATA_IGN; } EXPORT_SYMBOL_GPL(ata_cable_ignore); /** * ata_cable_sata - return SATA cable type * @ap: port * * Helper method for drivers which have SATA cables */ int ata_cable_sata(struct ata_port *ap) { return ATA_CBL_SATA; } EXPORT_SYMBOL_GPL(ata_cable_sata); /** * ata_bus_probe - Reset and probe ATA bus * @ap: Bus to probe * * Master ATA bus probing function. Initiates a hardware-dependent * bus reset, then attempts to identify any devices found on * the bus. * * LOCKING: * PCI/etc. bus probe sem. * * RETURNS: * Zero on success, negative errno otherwise. */ int ata_bus_probe(struct ata_port *ap) { unsigned int classes[ATA_MAX_DEVICES]; int tries[ATA_MAX_DEVICES]; int rc; struct ata_device *dev; ata_for_each_dev(dev, &ap->link, ALL) tries[dev->devno] = ATA_PROBE_MAX_TRIES; retry: ata_for_each_dev(dev, &ap->link, ALL) { /* If we issue an SRST then an ATA drive (not ATAPI) * may change configuration and be in PIO0 timing. If * we do a hard reset (or are coming from power on) * this is true for ATA or ATAPI. Until we've set a * suitable controller mode we should not touch the * bus as we may be talking too fast. */ dev->pio_mode = XFER_PIO_0; dev->dma_mode = 0xff; /* If the controller has a pio mode setup function * then use it to set the chipset to rights. Don't * touch the DMA setup as that will be dealt with when * configuring devices. */ if (ap->ops->set_piomode) ap->ops->set_piomode(ap, dev); } /* reset and determine device classes */ ap->ops->phy_reset(ap); ata_for_each_dev(dev, &ap->link, ALL) { if (dev->class != ATA_DEV_UNKNOWN) classes[dev->devno] = dev->class; else classes[dev->devno] = ATA_DEV_NONE; dev->class = ATA_DEV_UNKNOWN; } /* read IDENTIFY page and configure devices. We have to do the identify specific sequence bass-ackwards so that PDIAG- is released by the slave device */ ata_for_each_dev(dev, &ap->link, ALL_REVERSE) { if (tries[dev->devno]) dev->class = classes[dev->devno]; if (!ata_dev_enabled(dev)) continue; rc = ata_dev_read_id(dev, &dev->class, ATA_READID_POSTRESET, dev->id); if (rc) goto fail; } /* Now ask for the cable type as PDIAG- should have been released */ if (ap->ops->cable_detect) ap->cbl = ap->ops->cable_detect(ap); /* We may have SATA bridge glue hiding here irrespective of * the reported cable types and sensed types. When SATA * drives indicate we have a bridge, we don't know which end * of the link the bridge is which is a problem. */ ata_for_each_dev(dev, &ap->link, ENABLED) if (ata_id_is_sata(dev->id)) ap->cbl = ATA_CBL_SATA; /* After the identify sequence we can now set up the devices. We do this in the normal order so that the user doesn't get confused */ ata_for_each_dev(dev, &ap->link, ENABLED) { ap->link.eh_context.i.flags |= ATA_EHI_PRINTINFO; rc = ata_dev_configure(dev); ap->link.eh_context.i.flags &= ~ATA_EHI_PRINTINFO; if (rc) goto fail; } /* configure transfer mode */ rc = ata_set_mode(&ap->link, &dev); if (rc) goto fail; ata_for_each_dev(dev, &ap->link, ENABLED) return 0; return -ENODEV; fail: tries[dev->devno]--; switch (rc) { case -EINVAL: /* eeek, something went very wrong, give up */ tries[dev->devno] = 0; break; case -ENODEV: /* give it just one more chance */ tries[dev->devno] = min(tries[dev->devno], 1); fallthrough; case -EIO: if (tries[dev->devno] == 1) { /* This is the last chance, better to slow * down than lose it. */ sata_down_spd_limit(&ap->link, 0); ata_down_xfermask_limit(dev, ATA_DNXFER_PIO); } } if (!tries[dev->devno]) ata_dev_disable(dev); goto retry; } /** * sata_print_link_status - Print SATA link status * @link: SATA link to printk link status about * * This function prints link speed and status of a SATA link. * * LOCKING: * None. */ static void sata_print_link_status(struct ata_link *link) { u32 sstatus, scontrol, tmp; if (sata_scr_read(link, SCR_STATUS, &sstatus)) return; sata_scr_read(link, SCR_CONTROL, &scontrol); if (ata_phys_link_online(link)) { tmp = (sstatus >> 4) & 0xf; ata_link_info(link, "SATA link up %s (SStatus %X SControl %X)\n", sata_spd_string(tmp), sstatus, scontrol); } else { ata_link_info(link, "SATA link down (SStatus %X SControl %X)\n", sstatus, scontrol); } } /** * ata_dev_pair - return other device on cable * @adev: device * * Obtain the other device on the same cable, or if none is * present NULL is returned */ struct ata_device *ata_dev_pair(struct ata_device *adev) { struct ata_link *link = adev->link; struct ata_device *pair = &link->device[1 - adev->devno]; if (!ata_dev_enabled(pair)) return NULL; return pair; } EXPORT_SYMBOL_GPL(ata_dev_pair); /** * sata_down_spd_limit - adjust SATA spd limit downward * @link: Link to adjust SATA spd limit for * @spd_limit: Additional limit * * Adjust SATA spd limit of @link downward. Note that this * function only adjusts the limit. The change must be applied * using sata_set_spd(). * * If @spd_limit is non-zero, the speed is limited to equal to or * lower than @spd_limit if such speed is supported. If * @spd_limit is slower than any supported speed, only the lowest * supported speed is allowed. * * LOCKING: * Inherited from caller. * * RETURNS: * 0 on success, negative errno on failure */ int sata_down_spd_limit(struct ata_link *link, u32 spd_limit) { u32 sstatus, spd, mask; int rc, bit; if (!sata_scr_valid(link)) return -EOPNOTSUPP; /* If SCR can be read, use it to determine the current SPD. * If not, use cached value in link->sata_spd. */ rc = sata_scr_read(link, SCR_STATUS, &sstatus); if (rc == 0 && ata_sstatus_online(sstatus)) spd = (sstatus >> 4) & 0xf; else spd = link->sata_spd; mask = link->sata_spd_limit; if (mask <= 1) return -EINVAL; /* unconditionally mask off the highest bit */ bit = fls(mask) - 1; mask &= ~(1 << bit); /* * Mask off all speeds higher than or equal to the current one. At * this point, if current SPD is not available and we previously * recorded the link speed from SStatus, the driver has already * masked off the highest bit so mask should already be 1 or 0. * Otherwise, we should not force 1.5Gbps on a link where we have * not previously recorded speed from SStatus. Just return in this * case. */ if (spd > 1) mask &= (1 << (spd - 1)) - 1; else return -EINVAL; /* were we already at the bottom? */ if (!mask) return -EINVAL; if (spd_limit) { if (mask & ((1 << spd_limit) - 1)) mask &= (1 << spd_limit) - 1; else { bit = ffs(mask) - 1; mask = 1 << bit; } } link->sata_spd_limit = mask; ata_link_warn(link, "limiting SATA link speed to %s\n", sata_spd_string(fls(mask))); return 0; } #ifdef CONFIG_ATA_ACPI /** * ata_timing_cycle2mode - find xfer mode for the specified cycle duration * @xfer_shift: ATA_SHIFT_* value for transfer type to examine. * @cycle: cycle duration in ns * * Return matching xfer mode for @cycle. The returned mode is of * the transfer type specified by @xfer_shift. If @cycle is too * slow for @xfer_shift, 0xff is returned. If @cycle is faster * than the fastest known mode, the fasted mode is returned. * * LOCKING: * None. * * RETURNS: * Matching xfer_mode, 0xff if no match found. */ u8 ata_timing_cycle2mode(unsigned int xfer_shift, int cycle) { u8 base_mode = 0xff, last_mode = 0xff; const struct ata_xfer_ent *ent; const struct ata_timing *t; for (ent = ata_xfer_tbl; ent->shift >= 0; ent++) if (ent->shift == xfer_shift) base_mode = ent->base; for (t = ata_timing_find_mode(base_mode); t && ata_xfer_mode2shift(t->mode) == xfer_shift; t++) { unsigned short this_cycle; switch (xfer_shift) { case ATA_SHIFT_PIO: case ATA_SHIFT_MWDMA: this_cycle = t->cycle; break; case ATA_SHIFT_UDMA: this_cycle = t->udma; break; default: return 0xff; } if (cycle > this_cycle) break; last_mode = t->mode; } return last_mode; } #endif /** * ata_down_xfermask_limit - adjust dev xfer masks downward * @dev: Device to adjust xfer masks * @sel: ATA_DNXFER_* selector * * Adjust xfer masks of @dev downward. Note that this function * does not apply the change. Invoking ata_set_mode() afterwards * will apply the limit. * * LOCKING: * Inherited from caller. * * RETURNS: * 0 on success, negative errno on failure */ int ata_down_xfermask_limit(struct ata_device *dev, unsigned int sel) { char buf[32]; unsigned long orig_mask, xfer_mask; unsigned long pio_mask, mwdma_mask, udma_mask; int quiet, highbit; quiet = !!(sel & ATA_DNXFER_QUIET); sel &= ~ATA_DNXFER_QUIET; xfer_mask = orig_mask = ata_pack_xfermask(dev->pio_mask, dev->mwdma_mask, dev->udma_mask); ata_unpack_xfermask(xfer_mask, &pio_mask, &mwdma_mask, &udma_mask); switch (sel) { case ATA_DNXFER_PIO: highbit = fls(pio_mask) - 1; pio_mask &= ~(1 << highbit); break; case ATA_DNXFER_DMA: if (udma_mask) { highbit = fls(udma_mask) - 1; udma_mask &= ~(1 << highbit); if (!udma_mask) return -ENOENT; } else if (mwdma_mask) { highbit = fls(mwdma_mask) - 1; mwdma_mask &= ~(1 << highbit); if (!mwdma_mask) return -ENOENT; } break; case ATA_DNXFER_40C: udma_mask &= ATA_UDMA_MASK_40C; break; case ATA_DNXFER_FORCE_PIO0: pio_mask &= 1; fallthrough; case ATA_DNXFER_FORCE_PIO: mwdma_mask = 0; udma_mask = 0; break; default: BUG(); } xfer_mask &= ata_pack_xfermask(pio_mask, mwdma_mask, udma_mask); if (!(xfer_mask & ATA_MASK_PIO) || xfer_mask == orig_mask) return -ENOENT; if (!quiet) { if (xfer_mask & (ATA_MASK_MWDMA | ATA_MASK_UDMA)) snprintf(buf, sizeof(buf), "%s:%s", ata_mode_string(xfer_mask), ata_mode_string(xfer_mask & ATA_MASK_PIO)); else snprintf(buf, sizeof(buf), "%s", ata_mode_string(xfer_mask)); ata_dev_warn(dev, "limiting speed to %s\n", buf); } ata_unpack_xfermask(xfer_mask, &dev->pio_mask, &dev->mwdma_mask, &dev->udma_mask); return 0; } static int ata_dev_set_mode(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; struct ata_eh_context *ehc = &dev->link->eh_context; const bool nosetxfer = dev->horkage & ATA_HORKAGE_NOSETXFER; const char *dev_err_whine = ""; int ign_dev_err = 0; unsigned int err_mask = 0; int rc; dev->flags &= ~ATA_DFLAG_PIO; if (dev->xfer_shift == ATA_SHIFT_PIO) dev->flags |= ATA_DFLAG_PIO; if (nosetxfer && ap->flags & ATA_FLAG_SATA && ata_id_is_sata(dev->id)) dev_err_whine = " (SET_XFERMODE skipped)"; else { if (nosetxfer) ata_dev_warn(dev, "NOSETXFER but PATA detected - can't " "skip SETXFER, might malfunction\n"); err_mask = ata_dev_set_xfermode(dev); } if (err_mask & ~AC_ERR_DEV) goto fail; /* revalidate */ ehc->i.flags |= ATA_EHI_POST_SETMODE; rc = ata_dev_revalidate(dev, ATA_DEV_UNKNOWN, 0); ehc->i.flags &= ~ATA_EHI_POST_SETMODE; if (rc) return rc; if (dev->xfer_shift == ATA_SHIFT_PIO) { /* Old CFA may refuse this command, which is just fine */ if (ata_id_is_cfa(dev->id)) ign_dev_err = 1; /* Catch several broken garbage emulations plus some pre ATA devices */ if (ata_id_major_version(dev->id) == 0 && dev->pio_mode <= XFER_PIO_2) ign_dev_err = 1; /* Some very old devices and some bad newer ones fail any kind of SET_XFERMODE request but support PIO0-2 timings and no IORDY */ if (!ata_id_has_iordy(dev->id) && dev->pio_mode <= XFER_PIO_2) ign_dev_err = 1; } /* Early MWDMA devices do DMA but don't allow DMA mode setting. Don't fail an MWDMA0 set IFF the device indicates it is in MWDMA0 */ if (dev->xfer_shift == ATA_SHIFT_MWDMA && dev->dma_mode == XFER_MW_DMA_0 && (dev->id[63] >> 8) & 1) ign_dev_err = 1; /* if the device is actually configured correctly, ignore dev err */ if (dev->xfer_mode == ata_xfer_mask2mode(ata_id_xfermask(dev->id))) ign_dev_err = 1; if (err_mask & AC_ERR_DEV) { if (!ign_dev_err) goto fail; else dev_err_whine = " (device error ignored)"; } DPRINTK("xfer_shift=%u, xfer_mode=0x%x\n", dev->xfer_shift, (int)dev->xfer_mode); if (!(ehc->i.flags & ATA_EHI_QUIET) || ehc->i.flags & ATA_EHI_DID_HARDRESET) ata_dev_info(dev, "configured for %s%s\n", ata_mode_string(ata_xfer_mode2mask(dev->xfer_mode)), dev_err_whine); return 0; fail: ata_dev_err(dev, "failed to set xfermode (err_mask=0x%x)\n", err_mask); return -EIO; } /** * ata_do_set_mode - Program timings and issue SET FEATURES - XFER * @link: link on which timings will be programmed * @r_failed_dev: out parameter for failed device * * Standard implementation of the function used to tune and set * ATA device disk transfer mode (PIO3, UDMA6, etc.). If * ata_dev_set_mode() fails, pointer to the failing device is * returned in @r_failed_dev. * * LOCKING: * PCI/etc. bus probe sem. * * RETURNS: * 0 on success, negative errno otherwise */ int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev) { struct ata_port *ap = link->ap; struct ata_device *dev; int rc = 0, used_dma = 0, found = 0; /* step 1: calculate xfer_mask */ ata_for_each_dev(dev, link, ENABLED) { unsigned long pio_mask, dma_mask; unsigned int mode_mask; mode_mask = ATA_DMA_MASK_ATA; if (dev->class == ATA_DEV_ATAPI) mode_mask = ATA_DMA_MASK_ATAPI; else if (ata_id_is_cfa(dev->id)) mode_mask = ATA_DMA_MASK_CFA; ata_dev_xfermask(dev); ata_force_xfermask(dev); pio_mask = ata_pack_xfermask(dev->pio_mask, 0, 0); if (libata_dma_mask & mode_mask) dma_mask = ata_pack_xfermask(0, dev->mwdma_mask, dev->udma_mask); else dma_mask = 0; dev->pio_mode = ata_xfer_mask2mode(pio_mask); dev->dma_mode = ata_xfer_mask2mode(dma_mask); found = 1; if (ata_dma_enabled(dev)) used_dma = 1; } if (!found) goto out; /* step 2: always set host PIO timings */ ata_for_each_dev(dev, link, ENABLED) { if (dev->pio_mode == 0xff) { ata_dev_warn(dev, "no PIO support\n"); rc = -EINVAL; goto out; } dev->xfer_mode = dev->pio_mode; dev->xfer_shift = ATA_SHIFT_PIO; if (ap->ops->set_piomode) ap->ops->set_piomode(ap, dev); } /* step 3: set host DMA timings */ ata_for_each_dev(dev, link, ENABLED) { if (!ata_dma_enabled(dev)) continue; dev->xfer_mode = dev->dma_mode; dev->xfer_shift = ata_xfer_mode2shift(dev->dma_mode); if (ap->ops->set_dmamode) ap->ops->set_dmamode(ap, dev); } /* step 4: update devices' xfer mode */ ata_for_each_dev(dev, link, ENABLED) { rc = ata_dev_set_mode(dev); if (rc) goto out; } /* Record simplex status. If we selected DMA then the other * host channels are not permitted to do so. */ if (used_dma && (ap->host->flags & ATA_HOST_SIMPLEX)) ap->host->simplex_claimed = ap; out: if (rc) *r_failed_dev = dev; return rc; } EXPORT_SYMBOL_GPL(ata_do_set_mode); /** * ata_wait_ready - wait for link to become ready * @link: link to be waited on * @deadline: deadline jiffies for the operation * @check_ready: callback to check link readiness * * Wait for @link to become ready. @check_ready should return * positive number if @link is ready, 0 if it isn't, -ENODEV if * link doesn't seem to be occupied, other errno for other error * conditions. * * Transient -ENODEV conditions are allowed for * ATA_TMOUT_FF_WAIT. * * LOCKING: * EH context. * * RETURNS: * 0 if @link is ready before @deadline; otherwise, -errno. */ int ata_wait_ready(struct ata_link *link, unsigned long deadline, int (*check_ready)(struct ata_link *link)) { unsigned long start = jiffies; unsigned long nodev_deadline; int warned = 0; /* choose which 0xff timeout to use, read comment in libata.h */ if (link->ap->host->flags & ATA_HOST_PARALLEL_SCAN) nodev_deadline = ata_deadline(start, ATA_TMOUT_FF_WAIT_LONG); else nodev_deadline = ata_deadline(start, ATA_TMOUT_FF_WAIT); /* Slave readiness can't be tested separately from master. On * M/S emulation configuration, this function should be called * only on the master and it will handle both master and slave. */ WARN_ON(link == link->ap->slave_link); if (time_after(nodev_deadline, deadline)) nodev_deadline = deadline; while (1) { unsigned long now = jiffies; int ready, tmp; ready = tmp = check_ready(link); if (ready > 0) return 0; /* * -ENODEV could be transient. Ignore -ENODEV if link * is online. Also, some SATA devices take a long * time to clear 0xff after reset. Wait for * ATA_TMOUT_FF_WAIT[_LONG] on -ENODEV if link isn't * offline. * * Note that some PATA controllers (pata_ali) explode * if status register is read more than once when * there's no device attached. */ if (ready == -ENODEV) { if (ata_link_online(link)) ready = 0; else if ((link->ap->flags & ATA_FLAG_SATA) && !ata_link_offline(link) && time_before(now, nodev_deadline)) ready = 0; } if (ready) return ready; if (time_after(now, deadline)) return -EBUSY; if (!warned && time_after(now, start + 5 * HZ) && (deadline - now > 3 * HZ)) { ata_link_warn(link, "link is slow to respond, please be patient " "(ready=%d)\n", tmp); warned = 1; } ata_msleep(link->ap, 50); } } /** * ata_wait_after_reset - wait for link to become ready after reset * @link: link to be waited on * @deadline: deadline jiffies for the operation * @check_ready: callback to check link readiness * * Wait for @link to become ready after reset. * * LOCKING: * EH context. * * RETURNS: * 0 if @link is ready before @deadline; otherwise, -errno. */ int ata_wait_after_reset(struct ata_link *link, unsigned long deadline, int (*check_ready)(struct ata_link *link)) { ata_msleep(link->ap, ATA_WAIT_AFTER_RESET); return ata_wait_ready(link, deadline, check_ready); } EXPORT_SYMBOL_GPL(ata_wait_after_reset); /** * ata_std_prereset - prepare for reset * @link: ATA link to be reset * @deadline: deadline jiffies for the operation * * @link is about to be reset. Initialize it. Failure from * prereset makes libata abort whole reset sequence and give up * that port, so prereset should be best-effort. It does its * best to prepare for reset sequence but if things go wrong, it * should just whine, not fail. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 on success, -errno otherwise. */ int ata_std_prereset(struct ata_link *link, unsigned long deadline) { struct ata_port *ap = link->ap; struct ata_eh_context *ehc = &link->eh_context; const unsigned long *timing = sata_ehc_deb_timing(ehc); int rc; /* if we're about to do hardreset, nothing more to do */ if (ehc->i.action & ATA_EH_HARDRESET) return 0; /* if SATA, resume link */ if (ap->flags & ATA_FLAG_SATA) { rc = sata_link_resume(link, timing, deadline); /* whine about phy resume failure but proceed */ if (rc && rc != -EOPNOTSUPP) ata_link_warn(link, "failed to resume link for reset (errno=%d)\n", rc); } /* no point in trying softreset on offline link */ if (ata_phys_link_offline(link)) ehc->i.action &= ~ATA_EH_SOFTRESET; return 0; } EXPORT_SYMBOL_GPL(ata_std_prereset); /** * sata_std_hardreset - COMRESET w/o waiting or classification * @link: link to reset * @class: resulting class of attached device * @deadline: deadline jiffies for the operation * * Standard SATA COMRESET w/o waiting or classification. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 if link offline, -EAGAIN if link online, -errno on errors. */ int sata_std_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline) { const unsigned long *timing = sata_ehc_deb_timing(&link->eh_context); bool online; int rc; /* do hardreset */ rc = sata_link_hardreset(link, timing, deadline, &online, NULL); return online ? -EAGAIN : rc; } EXPORT_SYMBOL_GPL(sata_std_hardreset); /** * ata_std_postreset - standard postreset callback * @link: the target ata_link * @classes: classes of attached devices * * This function is invoked after a successful reset. Note that * the device might have been reset more than once using * different reset methods before postreset is invoked. * * LOCKING: * Kernel thread context (may sleep) */ void ata_std_postreset(struct ata_link *link, unsigned int *classes) { u32 serror; DPRINTK("ENTER\n"); /* reset complete, clear SError */ if (!sata_scr_read(link, SCR_ERROR, &serror)) sata_scr_write(link, SCR_ERROR, serror); /* print link status */ sata_print_link_status(link); DPRINTK("EXIT\n"); } EXPORT_SYMBOL_GPL(ata_std_postreset); /** * ata_dev_same_device - Determine whether new ID matches configured device * @dev: device to compare against * @new_class: class of the new device * @new_id: IDENTIFY page of the new device * * Compare @new_class and @new_id against @dev and determine * whether @dev is the device indicated by @new_class and * @new_id. * * LOCKING: * None. * * RETURNS: * 1 if @dev matches @new_class and @new_id, 0 otherwise. */ static int ata_dev_same_device(struct ata_device *dev, unsigned int new_class, const u16 *new_id) { const u16 *old_id = dev->id; unsigned char model[2][ATA_ID_PROD_LEN + 1]; unsigned char serial[2][ATA_ID_SERNO_LEN + 1]; if (dev->class != new_class) { ata_dev_info(dev, "class mismatch %d != %d\n", dev->class, new_class); return 0; } ata_id_c_string(old_id, model[0], ATA_ID_PROD, sizeof(model[0])); ata_id_c_string(new_id, model[1], ATA_ID_PROD, sizeof(model[1])); ata_id_c_string(old_id, serial[0], ATA_ID_SERNO, sizeof(serial[0])); ata_id_c_string(new_id, serial[1], ATA_ID_SERNO, sizeof(serial[1])); if (strcmp(model[0], model[1])) { ata_dev_info(dev, "model number mismatch '%s' != '%s'\n", model[0], model[1]); return 0; } if (strcmp(serial[0], serial[1])) { ata_dev_info(dev, "serial number mismatch '%s' != '%s'\n", serial[0], serial[1]); return 0; } return 1; } /** * ata_dev_reread_id - Re-read IDENTIFY data * @dev: target ATA device * @readid_flags: read ID flags * * Re-read IDENTIFY page and make sure @dev is still attached to * the port. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 on success, negative errno otherwise */ int ata_dev_reread_id(struct ata_device *dev, unsigned int readid_flags) { unsigned int class = dev->class; u16 *id = (void *)dev->link->ap->sector_buf; int rc; /* read ID data */ rc = ata_dev_read_id(dev, &class, readid_flags, id); if (rc) return rc; /* is the device still there? */ if (!ata_dev_same_device(dev, class, id)) return -ENODEV; memcpy(dev->id, id, sizeof(id[0]) * ATA_ID_WORDS); return 0; } /** * ata_dev_revalidate - Revalidate ATA device * @dev: device to revalidate * @new_class: new class code * @readid_flags: read ID flags * * Re-read IDENTIFY page, make sure @dev is still attached to the * port and reconfigure it according to the new IDENTIFY page. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 on success, negative errno otherwise */ int ata_dev_revalidate(struct ata_device *dev, unsigned int new_class, unsigned int readid_flags) { u64 n_sectors = dev->n_sectors; u64 n_native_sectors = dev->n_native_sectors; int rc; if (!ata_dev_enabled(dev)) return -ENODEV; /* fail early if !ATA && !ATAPI to avoid issuing [P]IDENTIFY to PMP */ if (ata_class_enabled(new_class) && new_class != ATA_DEV_ATA && new_class != ATA_DEV_ATAPI && new_class != ATA_DEV_ZAC && new_class != ATA_DEV_SEMB) { ata_dev_info(dev, "class mismatch %u != %u\n", dev->class, new_class); rc = -ENODEV; goto fail; } /* re-read ID */ rc = ata_dev_reread_id(dev, readid_flags); if (rc) goto fail; /* configure device according to the new ID */ rc = ata_dev_configure(dev); if (rc) goto fail; /* verify n_sectors hasn't changed */ if (dev->class != ATA_DEV_ATA || !n_sectors || dev->n_sectors == n_sectors) return 0; /* n_sectors has changed */ ata_dev_warn(dev, "n_sectors mismatch %llu != %llu\n", (unsigned long long)n_sectors, (unsigned long long)dev->n_sectors); /* * Something could have caused HPA to be unlocked * involuntarily. If n_native_sectors hasn't changed and the * new size matches it, keep the device. */ if (dev->n_native_sectors == n_native_sectors && dev->n_sectors > n_sectors && dev->n_sectors == n_native_sectors) { ata_dev_warn(dev, "new n_sectors matches native, probably " "late HPA unlock, n_sectors updated\n"); /* use the larger n_sectors */ return 0; } /* * Some BIOSes boot w/o HPA but resume w/ HPA locked. Try * unlocking HPA in those cases. * * https://bugzilla.kernel.org/show_bug.cgi?id=15396 */ if (dev->n_native_sectors == n_native_sectors && dev->n_sectors < n_sectors && n_sectors == n_native_sectors && !(dev->horkage & ATA_HORKAGE_BROKEN_HPA)) { ata_dev_warn(dev, "old n_sectors matches native, probably " "late HPA lock, will try to unlock HPA\n"); /* try unlocking HPA */ dev->flags |= ATA_DFLAG_UNLOCK_HPA; rc = -EIO; } else rc = -ENODEV; /* restore original n_[native_]sectors and fail */ dev->n_native_sectors = n_native_sectors; dev->n_sectors = n_sectors; fail: ata_dev_err(dev, "revalidation failed (errno=%d)\n", rc); return rc; } struct ata_blacklist_entry { const char *model_num; const char *model_rev; unsigned long horkage; }; static const struct ata_blacklist_entry ata_device_blacklist [] = { /* Devices with DMA related problems under Linux */ { "WDC AC11000H", NULL, ATA_HORKAGE_NODMA }, { "WDC AC22100H", NULL, ATA_HORKAGE_NODMA }, { "WDC AC32500H", NULL, ATA_HORKAGE_NODMA }, { "WDC AC33100H", NULL, ATA_HORKAGE_NODMA }, { "WDC AC31600H", NULL, ATA_HORKAGE_NODMA }, { "WDC AC32100H", "24.09P07", ATA_HORKAGE_NODMA }, { "WDC AC23200L", "21.10N21", ATA_HORKAGE_NODMA }, { "Compaq CRD-8241B", NULL, ATA_HORKAGE_NODMA }, { "CRD-8400B", NULL, ATA_HORKAGE_NODMA }, { "CRD-848[02]B", NULL, ATA_HORKAGE_NODMA }, { "CRD-84", NULL, ATA_HORKAGE_NODMA }, { "SanDisk SDP3B", NULL, ATA_HORKAGE_NODMA }, { "SanDisk SDP3B-64", NULL, ATA_HORKAGE_NODMA }, { "SANYO CD-ROM CRD", NULL, ATA_HORKAGE_NODMA }, { "HITACHI CDR-8", NULL, ATA_HORKAGE_NODMA }, { "HITACHI CDR-8[34]35",NULL, ATA_HORKAGE_NODMA }, { "Toshiba CD-ROM XM-6202B", NULL, ATA_HORKAGE_NODMA }, { "TOSHIBA CD-ROM XM-1702BC", NULL, ATA_HORKAGE_NODMA }, { "CD-532E-A", NULL, ATA_HORKAGE_NODMA }, { "E-IDE CD-ROM CR-840",NULL, ATA_HORKAGE_NODMA }, { "CD-ROM Drive/F5A", NULL, ATA_HORKAGE_NODMA }, { "WPI CDD-820", NULL, ATA_HORKAGE_NODMA }, { "SAMSUNG CD-ROM SC-148C", NULL, ATA_HORKAGE_NODMA }, { "SAMSUNG CD-ROM SC", NULL, ATA_HORKAGE_NODMA }, { "ATAPI CD-ROM DRIVE 40X MAXIMUM",NULL,ATA_HORKAGE_NODMA }, { "_NEC DV5800A", NULL, ATA_HORKAGE_NODMA }, { "SAMSUNG CD-ROM SN-124", "N001", ATA_HORKAGE_NODMA }, { "Seagate STT20000A", NULL, ATA_HORKAGE_NODMA }, { " 2GB ATA Flash Disk", "ADMA428M", ATA_HORKAGE_NODMA }, { "VRFDFC22048UCHC-TE*", NULL, ATA_HORKAGE_NODMA }, /* Odd clown on sil3726/4726 PMPs */ { "Config Disk", NULL, ATA_HORKAGE_DISABLE }, /* Weird ATAPI devices */ { "TORiSAN DVD-ROM DRD-N216", NULL, ATA_HORKAGE_MAX_SEC_128 }, { "QUANTUM DAT DAT72-000", NULL, ATA_HORKAGE_ATAPI_MOD16_DMA }, { "Slimtype DVD A DS8A8SH", NULL, ATA_HORKAGE_MAX_SEC_LBA48 }, { "Slimtype DVD A DS8A9SH", NULL, ATA_HORKAGE_MAX_SEC_LBA48 }, /* * Causes silent data corruption with higher max sects. * http://lkml.kernel.org/g/x49wpy40ysk.fsf@segfault.boston.devel.redhat.com */ { "ST380013AS", "3.20", ATA_HORKAGE_MAX_SEC_1024 }, /* * These devices time out with higher max sects. * https://bugzilla.kernel.org/show_bug.cgi?id=121671 */ { "LITEON CX1-JB*-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 }, { "LITEON EP1-*", NULL, ATA_HORKAGE_MAX_SEC_1024 }, /* Devices we expect to fail diagnostics */ /* Devices where NCQ should be avoided */ /* NCQ is slow */ { "WDC WD740ADFD-00", NULL, ATA_HORKAGE_NONCQ }, { "WDC WD740ADFD-00NLR1", NULL, ATA_HORKAGE_NONCQ, }, /* http://thread.gmane.org/gmane.linux.ide/14907 */ { "FUJITSU MHT2060BH", NULL, ATA_HORKAGE_NONCQ }, /* NCQ is broken */ { "Maxtor *", "BANC*", ATA_HORKAGE_NONCQ }, { "Maxtor 7V300F0", "VA111630", ATA_HORKAGE_NONCQ }, { "ST380817AS", "3.42", ATA_HORKAGE_NONCQ }, { "ST3160023AS", "3.42", ATA_HORKAGE_NONCQ }, { "OCZ CORE_SSD", "02.10104", ATA_HORKAGE_NONCQ }, /* Seagate NCQ + FLUSH CACHE firmware bug */ { "ST31500341AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, { "ST31000333AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, { "ST3640[36]23AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, { "ST3320[68]13AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, /* drives which fail FPDMA_AA activation (some may freeze afterwards) the ST disks also have LPM issues */ { "ST1000LM024 HN-M101MBB", NULL, ATA_HORKAGE_BROKEN_FPDMA_AA | ATA_HORKAGE_NOLPM, }, { "VB0250EAVER", "HPG7", ATA_HORKAGE_BROKEN_FPDMA_AA }, /* Blacklist entries taken from Silicon Image 3124/3132 Windows driver .inf file - also several Linux problem reports */ { "HTS541060G9SA00", "MB3OC60D", ATA_HORKAGE_NONCQ, }, { "HTS541080G9SA00", "MB4OC60D", ATA_HORKAGE_NONCQ, }, { "HTS541010G9SA00", "MBZOC60D", ATA_HORKAGE_NONCQ, }, /* https://bugzilla.kernel.org/show_bug.cgi?id=15573 */ { "C300-CTFDDAC128MAG", "0001", ATA_HORKAGE_NONCQ, }, /* Sandisk SD7/8/9s lock up hard on large trims */ { "SanDisk SD[789]*", NULL, ATA_HORKAGE_MAX_TRIM_128M, }, /* devices which puke on READ_NATIVE_MAX */ { "HDS724040KLSA80", "KFAOA20N", ATA_HORKAGE_BROKEN_HPA, }, { "WDC WD3200JD-00KLB0", "WD-WCAMR1130137", ATA_HORKAGE_BROKEN_HPA }, { "WDC WD2500JD-00HBB0", "WD-WMAL71490727", ATA_HORKAGE_BROKEN_HPA }, { "MAXTOR 6L080L4", "A93.0500", ATA_HORKAGE_BROKEN_HPA }, /* this one allows HPA unlocking but fails IOs on the area */ { "OCZ-VERTEX", "1.30", ATA_HORKAGE_BROKEN_HPA }, /* Devices which report 1 sector over size HPA */ { "ST340823A", NULL, ATA_HORKAGE_HPA_SIZE, }, { "ST320413A", NULL, ATA_HORKAGE_HPA_SIZE, }, { "ST310211A", NULL, ATA_HORKAGE_HPA_SIZE, }, /* Devices which get the IVB wrong */ { "QUANTUM FIREBALLlct10 05", "A03.0900", ATA_HORKAGE_IVB, }, /* Maybe we should just blacklist TSSTcorp... */ { "TSSTcorp CDDVDW SH-S202[HJN]", "SB0[01]", ATA_HORKAGE_IVB, }, /* Devices that do not need bridging limits applied */ { "MTRON MSP-SATA*", NULL, ATA_HORKAGE_BRIDGE_OK, }, { "BUFFALO HD-QSU2/R5", NULL, ATA_HORKAGE_BRIDGE_OK, }, /* Devices which aren't very happy with higher link speeds */ { "WD My Book", NULL, ATA_HORKAGE_1_5_GBPS, }, { "Seagate FreeAgent GoFlex", NULL, ATA_HORKAGE_1_5_GBPS, }, /* * Devices which choke on SETXFER. Applies only if both the * device and controller are SATA. */ { "PIONEER DVD-RW DVRTD08", NULL, ATA_HORKAGE_NOSETXFER }, { "PIONEER DVD-RW DVRTD08A", NULL, ATA_HORKAGE_NOSETXFER }, { "PIONEER DVD-RW DVR-215", NULL, ATA_HORKAGE_NOSETXFER }, { "PIONEER DVD-RW DVR-212D", NULL, ATA_HORKAGE_NOSETXFER }, { "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER }, /* Crucial BX100 SSD 500GB has broken LPM support */ { "CT500BX100SSD1", NULL, ATA_HORKAGE_NOLPM }, /* 512GB MX100 with MU01 firmware has both queued TRIM and LPM issues */ { "Crucial_CT512MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NOLPM, }, /* 512GB MX100 with newer firmware has only LPM issues */ { "Crucial_CT512MX100*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NOLPM, }, /* 480GB+ M500 SSDs have both queued TRIM and LPM issues */ { "Crucial_CT480M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NOLPM, }, { "Crucial_CT960M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NOLPM, }, /* These specific Samsung models/firmware-revs do not handle LPM well */ { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, }, { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM, }, { "SAMSUNG MZ7TD256HAFV-000L9", NULL, ATA_HORKAGE_NOLPM, }, { "SAMSUNG MZ7TE512HMHP-000L1", "EXT06L0Q", ATA_HORKAGE_NOLPM, }, /* devices that don't properly handle queued TRIM commands */ { "Micron_M500IT_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Micron_M500_*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial_CT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Micron_M5[15]0_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial_CT*M550*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 840*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 850*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 860*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NO_NCQ_ON_ATI, }, { "Samsung SSD 870*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NO_NCQ_ON_ATI, }, { "FCCT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, /* devices that don't properly handle TRIM commands */ { "SuperSSpeed S238*", NULL, ATA_HORKAGE_NOTRIM, }, /* * As defined, the DRAT (Deterministic Read After Trim) and RZAT * (Return Zero After Trim) flags in the ATA Command Set are * unreliable in the sense that they only define what happens if * the device successfully executed the DSM TRIM command. TRIM * is only advisory, however, and the device is free to silently * ignore all or parts of the request. * * Whitelist drives that are known to reliably return zeroes * after TRIM. */ /* * The intel 510 drive has buggy DRAT/RZAT. Explicitly exclude * that model before whitelisting all other intel SSDs. */ { "INTEL*SSDSC2MH*", NULL, 0, }, { "Micron*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "INTEL*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "SSD*INTEL*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "SAMSUNG*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "SAMSUNG*MZ7KM*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "ST[1248][0248]0[FH]*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, /* * Some WD SATA-I drives spin up and down erratically when the link * is put into the slumber mode. We don't have full list of the * affected devices. Disable LPM if the device matches one of the * known prefixes and is SATA-1. As a side effect LPM partial is * lost too. * * https://bugzilla.kernel.org/show_bug.cgi?id=57211 */ { "WDC WD800JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD1200JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD1600JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD2000JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD2500JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD3000JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD3200JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, /* End Marker */ { } }; static unsigned long ata_dev_blacklisted(const struct ata_device *dev) { unsigned char model_num[ATA_ID_PROD_LEN + 1]; unsigned char model_rev[ATA_ID_FW_REV_LEN + 1]; const struct ata_blacklist_entry *ad = ata_device_blacklist; ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num)); ata_id_c_string(dev->id, model_rev, ATA_ID_FW_REV, sizeof(model_rev)); while (ad->model_num) { if (glob_match(ad->model_num, model_num)) { if (ad->model_rev == NULL) return ad->horkage; if (glob_match(ad->model_rev, model_rev)) return ad->horkage; } ad++; } return 0; } static int ata_dma_blacklisted(const struct ata_device *dev) { /* We don't support polling DMA. * DMA blacklist those ATAPI devices with CDB-intr (and use PIO) * if the LLDD handles only interrupts in the HSM_ST_LAST state. */ if ((dev->link->ap->flags & ATA_FLAG_PIO_POLLING) && (dev->flags & ATA_DFLAG_CDB_INTR)) return 1; return (dev->horkage & ATA_HORKAGE_NODMA) ? 1 : 0; } /** * ata_is_40wire - check drive side detection * @dev: device * * Perform drive side detection decoding, allowing for device vendors * who can't follow the documentation. */ static int ata_is_40wire(struct ata_device *dev) { if (dev->horkage & ATA_HORKAGE_IVB) return ata_drive_40wire_relaxed(dev->id); return ata_drive_40wire(dev->id); } /** * cable_is_40wire - 40/80/SATA decider * @ap: port to consider * * This function encapsulates the policy for speed management * in one place. At the moment we don't cache the result but * there is a good case for setting ap->cbl to the result when * we are called with unknown cables (and figuring out if it * impacts hotplug at all). * * Return 1 if the cable appears to be 40 wire. */ static int cable_is_40wire(struct ata_port *ap) { struct ata_link *link; struct ata_device *dev; /* If the controller thinks we are 40 wire, we are. */ if (ap->cbl == ATA_CBL_PATA40) return 1; /* If the controller thinks we are 80 wire, we are. */ if (ap->cbl == ATA_CBL_PATA80 || ap->cbl == ATA_CBL_SATA) return 0; /* If the system is known to be 40 wire short cable (eg * laptop), then we allow 80 wire modes even if the drive * isn't sure. */ if (ap->cbl == ATA_CBL_PATA40_SHORT) return 0; /* If the controller doesn't know, we scan. * * Note: We look for all 40 wire detects at this point. Any * 80 wire detect is taken to be 80 wire cable because * - in many setups only the one drive (slave if present) will * give a valid detect * - if you have a non detect capable drive you don't want it * to colour the choice */ ata_for_each_link(link, ap, EDGE) { ata_for_each_dev(dev, link, ENABLED) { if (!ata_is_40wire(dev)) return 0; } } return 1; } /** * ata_dev_xfermask - Compute supported xfermask of the given device * @dev: Device to compute xfermask for * * Compute supported xfermask of @dev and store it in * dev->*_mask. This function is responsible for applying all * known limits including host controller limits, device * blacklist, etc... * * LOCKING: * None. */ static void ata_dev_xfermask(struct ata_device *dev) { struct ata_link *link = dev->link; struct ata_port *ap = link->ap; struct ata_host *host = ap->host; unsigned long xfer_mask; /* controller modes available */ xfer_mask = ata_pack_xfermask(ap->pio_mask, ap->mwdma_mask, ap->udma_mask); /* drive modes available */ xfer_mask &= ata_pack_xfermask(dev->pio_mask, dev->mwdma_mask, dev->udma_mask); xfer_mask &= ata_id_xfermask(dev->id); /* * CFA Advanced TrueIDE timings are not allowed on a shared * cable */ if (ata_dev_pair(dev)) { /* No PIO5 or PIO6 */ xfer_mask &= ~(0x03 << (ATA_SHIFT_PIO + 5)); /* No MWDMA3 or MWDMA 4 */ xfer_mask &= ~(0x03 << (ATA_SHIFT_MWDMA + 3)); } if (ata_dma_blacklisted(dev)) { xfer_mask &= ~(ATA_MASK_MWDMA | ATA_MASK_UDMA); ata_dev_warn(dev, "device is on DMA blacklist, disabling DMA\n"); } if ((host->flags & ATA_HOST_SIMPLEX) && host->simplex_claimed && host->simplex_claimed != ap) { xfer_mask &= ~(ATA_MASK_MWDMA | ATA_MASK_UDMA); ata_dev_warn(dev, "simplex DMA is claimed by other device, disabling DMA\n"); } if (ap->flags & ATA_FLAG_NO_IORDY) xfer_mask &= ata_pio_mask_no_iordy(dev); if (ap->ops->mode_filter) xfer_mask = ap->ops->mode_filter(dev, xfer_mask); /* Apply cable rule here. Don't apply it early because when * we handle hot plug the cable type can itself change. * Check this last so that we know if the transfer rate was * solely limited by the cable. * Unknown or 80 wire cables reported host side are checked * drive side as well. Cases where we know a 40wire cable * is used safely for 80 are not checked here. */ if (xfer_mask & (0xF8 << ATA_SHIFT_UDMA)) /* UDMA/44 or higher would be available */ if (cable_is_40wire(ap)) { ata_dev_warn(dev, "limited to UDMA/33 due to 40-wire cable\n"); xfer_mask &= ~(0xF8 << ATA_SHIFT_UDMA); } ata_unpack_xfermask(xfer_mask, &dev->pio_mask, &dev->mwdma_mask, &dev->udma_mask); } /** * ata_dev_set_xfermode - Issue SET FEATURES - XFER MODE command * @dev: Device to which command will be sent * * Issue SET FEATURES - XFER MODE command to device @dev * on port @ap. * * LOCKING: * PCI/etc. bus probe sem. * * RETURNS: * 0 on success, AC_ERR_* mask otherwise. */ static unsigned int ata_dev_set_xfermode(struct ata_device *dev) { struct ata_taskfile tf; unsigned int err_mask; /* set up set-features taskfile */ DPRINTK("set features - xfer mode\n"); /* Some controllers and ATAPI devices show flaky interrupt * behavior after setting xfer mode. Use polling instead. */ ata_tf_init(dev, &tf); tf.command = ATA_CMD_SET_FEATURES; tf.feature = SETFEATURES_XFER; tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE | ATA_TFLAG_POLLING; tf.protocol = ATA_PROT_NODATA; /* If we are using IORDY we must send the mode setting command */ if (ata_pio_need_iordy(dev)) tf.nsect = dev->xfer_mode; /* If the device has IORDY and the controller does not - turn it off */ else if (ata_id_has_iordy(dev->id)) tf.nsect = 0x01; else /* In the ancient relic department - skip all of this */ return 0; /* On some disks, this command causes spin-up, so we need longer timeout */ err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 15000); DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; } /** * ata_dev_set_feature - Issue SET FEATURES - SATA FEATURES * @dev: Device to which command will be sent * @enable: Whether to enable or disable the feature * @feature: The sector count represents the feature to set * * Issue SET FEATURES - SATA FEATURES command to device @dev * on port @ap with sector count * * LOCKING: * PCI/etc. bus probe sem. * * RETURNS: * 0 on success, AC_ERR_* mask otherwise. */ unsigned int ata_dev_set_feature(struct ata_device *dev, u8 enable, u8 feature) { struct ata_taskfile tf; unsigned int err_mask; unsigned long timeout = 0; /* set up set-features taskfile */ DPRINTK("set features - SATA features\n"); ata_tf_init(dev, &tf); tf.command = ATA_CMD_SET_FEATURES; tf.feature = enable; tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; tf.protocol = ATA_PROT_NODATA; tf.nsect = feature; if (enable == SETFEATURES_SPINUP) timeout = ata_probe_timeout ? ata_probe_timeout * 1000 : SETFEATURES_SPINUP_TIMEOUT; err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, timeout); DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; } EXPORT_SYMBOL_GPL(ata_dev_set_feature); /** * ata_dev_init_params - Issue INIT DEV PARAMS command * @dev: Device to which command will be sent * @heads: Number of heads (taskfile parameter) * @sectors: Number of sectors (taskfile parameter) * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 on success, AC_ERR_* mask otherwise. */ static unsigned int ata_dev_init_params(struct ata_device *dev, u16 heads, u16 sectors) { struct ata_taskfile tf; unsigned int err_mask; /* Number of sectors per track 1-255. Number of heads 1-16 */ if (sectors < 1 || sectors > 255 || heads < 1 || heads > 16) return AC_ERR_INVALID; /* set up init dev params taskfile */ DPRINTK("init dev params \n"); ata_tf_init(dev, &tf); tf.command = ATA_CMD_INIT_DEV_PARAMS; tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; tf.protocol = ATA_PROT_NODATA; tf.nsect = sectors; tf.device |= (heads - 1) & 0x0f; /* max head = num. of heads - 1 */ err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); /* A clean abort indicates an original or just out of spec drive and we should continue as we issue the setup based on the drive reported working geometry */ if (err_mask == AC_ERR_DEV && (tf.feature & ATA_ABORTED)) err_mask = 0; DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; } /** * atapi_check_dma - Check whether ATAPI DMA can be supported * @qc: Metadata associated with taskfile to check * * Allow low-level driver to filter ATA PACKET commands, returning * a status indicating whether or not it is OK to use DMA for the * supplied PACKET command. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: 0 when ATAPI DMA can be used * nonzero otherwise */ int atapi_check_dma(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; /* Don't allow DMA if it isn't multiple of 16 bytes. Quite a * few ATAPI devices choke on such DMA requests. */ if (!(qc->dev->horkage & ATA_HORKAGE_ATAPI_MOD16_DMA) && unlikely(qc->nbytes & 15)) return 1; if (ap->ops->check_atapi_dma) return ap->ops->check_atapi_dma(qc); return 0; } /** * ata_std_qc_defer - Check whether a qc needs to be deferred * @qc: ATA command in question * * Non-NCQ commands cannot run with any other command, NCQ or * not. As upper layer only knows the queue depth, we are * responsible for maintaining exclusion. This function checks * whether a new command @qc can be issued. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * ATA_DEFER_* if deferring is needed, 0 otherwise. */ int ata_std_qc_defer(struct ata_queued_cmd *qc) { struct ata_link *link = qc->dev->link; if (ata_is_ncq(qc->tf.protocol)) { if (!ata_tag_valid(link->active_tag)) return 0; } else { if (!ata_tag_valid(link->active_tag) && !link->sactive) return 0; } return ATA_DEFER_LINK; } EXPORT_SYMBOL_GPL(ata_std_qc_defer); enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc) { return AC_ERR_OK; } EXPORT_SYMBOL_GPL(ata_noop_qc_prep); /** * ata_sg_init - Associate command with scatter-gather table. * @qc: Command to be associated * @sg: Scatter-gather table. * @n_elem: Number of elements in s/g table. * * Initialize the data-related elements of queued_cmd @qc * to point to a scatter-gather table @sg, containing @n_elem * elements. * * LOCKING: * spin_lock_irqsave(host lock) */ void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem) { qc->sg = sg; qc->n_elem = n_elem; qc->cursg = qc->sg; } #ifdef CONFIG_HAS_DMA /** * ata_sg_clean - Unmap DMA memory associated with command * @qc: Command containing DMA memory to be released * * Unmap all mapped DMA memory associated with this command. * * LOCKING: * spin_lock_irqsave(host lock) */ static void ata_sg_clean(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct scatterlist *sg = qc->sg; int dir = qc->dma_dir; WARN_ON_ONCE(sg == NULL); VPRINTK("unmapping %u sg elements\n", qc->n_elem); if (qc->n_elem) dma_unmap_sg(ap->dev, sg, qc->orig_n_elem, dir); qc->flags &= ~ATA_QCFLAG_DMAMAP; qc->sg = NULL; } /** * ata_sg_setup - DMA-map the scatter-gather table associated with a command. * @qc: Command with scatter-gather table to be mapped. * * DMA-map the scatter-gather table associated with queued_cmd @qc. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * Zero on success, negative on error. * */ static int ata_sg_setup(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; unsigned int n_elem; VPRINTK("ENTER, ata%u\n", ap->print_id); n_elem = dma_map_sg(ap->dev, qc->sg, qc->n_elem, qc->dma_dir); if (n_elem < 1) return -1; VPRINTK("%d sg elements mapped\n", n_elem); qc->orig_n_elem = qc->n_elem; qc->n_elem = n_elem; qc->flags |= ATA_QCFLAG_DMAMAP; return 0; } #else /* !CONFIG_HAS_DMA */ static inline void ata_sg_clean(struct ata_queued_cmd *qc) {} static inline int ata_sg_setup(struct ata_queued_cmd *qc) { return -1; } #endif /* !CONFIG_HAS_DMA */ /** * swap_buf_le16 - swap halves of 16-bit words in place * @buf: Buffer to swap * @buf_words: Number of 16-bit words in buffer. * * Swap halves of 16-bit words if needed to convert from * little-endian byte order to native cpu byte order, or * vice-versa. * * LOCKING: * Inherited from caller. */ void swap_buf_le16(u16 *buf, unsigned int buf_words) { #ifdef __BIG_ENDIAN unsigned int i; for (i = 0; i < buf_words; i++) buf[i] = le16_to_cpu(buf[i]); #endif /* __BIG_ENDIAN */ } /** * ata_qc_new_init - Request an available ATA command, and initialize it * @dev: Device from whom we request an available command structure * @tag: tag * * LOCKING: * None. */ struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag) { struct ata_port *ap = dev->link->ap; struct ata_queued_cmd *qc; /* no command while frozen */ if (unlikely(ap->pflags & ATA_PFLAG_FROZEN)) return NULL; /* libsas case */ if (ap->flags & ATA_FLAG_SAS_HOST) { tag = ata_sas_allocate_tag(ap); if (tag < 0) return NULL; } qc = __ata_qc_from_tag(ap, tag); qc->tag = qc->hw_tag = tag; qc->scsicmd = NULL; qc->ap = ap; qc->dev = dev; ata_qc_reinit(qc); return qc; } /** * ata_qc_free - free unused ata_queued_cmd * @qc: Command to complete * * Designed to free unused ata_queued_cmd object * in case something prevents using it. * * LOCKING: * spin_lock_irqsave(host lock) */ void ata_qc_free(struct ata_queued_cmd *qc) { struct ata_port *ap; unsigned int tag; WARN_ON_ONCE(qc == NULL); /* ata_qc_from_tag _might_ return NULL */ ap = qc->ap; qc->flags = 0; tag = qc->tag; if (ata_tag_valid(tag)) { qc->tag = ATA_TAG_POISON; if (ap->flags & ATA_FLAG_SAS_HOST) ata_sas_free_tag(tag, ap); } } void __ata_qc_complete(struct ata_queued_cmd *qc) { struct ata_port *ap; struct ata_link *link; WARN_ON_ONCE(qc == NULL); /* ata_qc_from_tag _might_ return NULL */ WARN_ON_ONCE(!(qc->flags & ATA_QCFLAG_ACTIVE)); ap = qc->ap; link = qc->dev->link; if (likely(qc->flags & ATA_QCFLAG_DMAMAP)) ata_sg_clean(qc); /* command should be marked inactive atomically with qc completion */ if (ata_is_ncq(qc->tf.protocol)) { link->sactive &= ~(1 << qc->hw_tag); if (!link->sactive) ap->nr_active_links--; } else { link->active_tag = ATA_TAG_POISON; ap->nr_active_links--; } /* clear exclusive status */ if (unlikely(qc->flags & ATA_QCFLAG_CLEAR_EXCL && ap->excl_link == link)) ap->excl_link = NULL; /* atapi: mark qc as inactive to prevent the interrupt handler * from completing the command twice later, before the error handler * is called. (when rc != 0 and atapi request sense is needed) */ qc->flags &= ~ATA_QCFLAG_ACTIVE; ap->qc_active &= ~(1ULL << qc->tag); /* call completion callback */ qc->complete_fn(qc); } static void fill_result_tf(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; qc->result_tf.flags = qc->tf.flags; ap->ops->qc_fill_rtf(qc); } static void ata_verify_xfer(struct ata_queued_cmd *qc) { struct ata_device *dev = qc->dev; if (!ata_is_data(qc->tf.protocol)) return; if ((dev->mwdma_mask || dev->udma_mask) && ata_is_pio(qc->tf.protocol)) return; dev->flags &= ~ATA_DFLAG_DUBIOUS_XFER; } /** * ata_qc_complete - Complete an active ATA command * @qc: Command to complete * * Indicate to the mid and upper layers that an ATA command has * completed, with either an ok or not-ok status. * * Refrain from calling this function multiple times when * successfully completing multiple NCQ commands. * ata_qc_complete_multiple() should be used instead, which will * properly update IRQ expect state. * * LOCKING: * spin_lock_irqsave(host lock) */ void ata_qc_complete(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; /* Trigger the LED (if available) */ ledtrig_disk_activity(!!(qc->tf.flags & ATA_TFLAG_WRITE)); /* XXX: New EH and old EH use different mechanisms to * synchronize EH with regular execution path. * * In new EH, a failed qc is marked with ATA_QCFLAG_FAILED. * Normal execution path is responsible for not accessing a * failed qc. libata core enforces the rule by returning NULL * from ata_qc_from_tag() for failed qcs. * * Old EH depends on ata_qc_complete() nullifying completion * requests if ATA_QCFLAG_EH_SCHEDULED is set. Old EH does * not synchronize with interrupt handler. Only PIO task is * taken care of. */ if (ap->ops->error_handler) { struct ata_device *dev = qc->dev; struct ata_eh_info *ehi = &dev->link->eh_info; if (unlikely(qc->err_mask)) qc->flags |= ATA_QCFLAG_FAILED; /* * Finish internal commands without any further processing * and always with the result TF filled. */ if (unlikely(ata_tag_internal(qc->tag))) { fill_result_tf(qc); trace_ata_qc_complete_internal(qc); __ata_qc_complete(qc); return; } /* * Non-internal qc has failed. Fill the result TF and * summon EH. */ if (unlikely(qc->flags & ATA_QCFLAG_FAILED)) { fill_result_tf(qc); trace_ata_qc_complete_failed(qc); ata_qc_schedule_eh(qc); return; } WARN_ON_ONCE(ap->pflags & ATA_PFLAG_FROZEN); /* read result TF if requested */ if (qc->flags & ATA_QCFLAG_RESULT_TF) fill_result_tf(qc); trace_ata_qc_complete_done(qc); /* Some commands need post-processing after successful * completion. */ switch (qc->tf.command) { case ATA_CMD_SET_FEATURES: if (qc->tf.feature != SETFEATURES_WC_ON && qc->tf.feature != SETFEATURES_WC_OFF && qc->tf.feature != SETFEATURES_RA_ON && qc->tf.feature != SETFEATURES_RA_OFF) break; fallthrough; case ATA_CMD_INIT_DEV_PARAMS: /* CHS translation changed */ case ATA_CMD_SET_MULTI: /* multi_count changed */ /* revalidate device */ ehi->dev_action[dev->devno] |= ATA_EH_REVALIDATE; ata_port_schedule_eh(ap); break; case ATA_CMD_SLEEP: dev->flags |= ATA_DFLAG_SLEEPING; break; } if (unlikely(dev->flags & ATA_DFLAG_DUBIOUS_XFER)) ata_verify_xfer(qc); __ata_qc_complete(qc); } else { if (qc->flags & ATA_QCFLAG_EH_SCHEDULED) return; /* read result TF if failed or requested */ if (qc->err_mask || qc->flags & ATA_QCFLAG_RESULT_TF) fill_result_tf(qc); __ata_qc_complete(qc); } } EXPORT_SYMBOL_GPL(ata_qc_complete); /** * ata_qc_get_active - get bitmask of active qcs * @ap: port in question * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * Bitmask of active qcs */ u64 ata_qc_get_active(struct ata_port *ap) { u64 qc_active = ap->qc_active; /* ATA_TAG_INTERNAL is sent to hw as tag 0 */ if (qc_active & (1ULL << ATA_TAG_INTERNAL)) { qc_active |= (1 << 0); qc_active &= ~(1ULL << ATA_TAG_INTERNAL); } return qc_active; } EXPORT_SYMBOL_GPL(ata_qc_get_active); /** * ata_qc_issue - issue taskfile to device * @qc: command to issue to device * * Prepare an ATA command to submission to device. * This includes mapping the data into a DMA-able * area, filling in the S/G table, and finally * writing the taskfile to hardware, starting the command. * * LOCKING: * spin_lock_irqsave(host lock) */ void ata_qc_issue(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct ata_link *link = qc->dev->link; u8 prot = qc->tf.protocol; /* Make sure only one non-NCQ command is outstanding. The * check is skipped for old EH because it reuses active qc to * request ATAPI sense. */ WARN_ON_ONCE(ap->ops->error_handler && ata_tag_valid(link->active_tag)); if (ata_is_ncq(prot)) { WARN_ON_ONCE(link->sactive & (1 << qc->hw_tag)); if (!link->sactive) ap->nr_active_links++; link->sactive |= 1 << qc->hw_tag; } else { WARN_ON_ONCE(link->sactive); ap->nr_active_links++; link->active_tag = qc->tag; } qc->flags |= ATA_QCFLAG_ACTIVE; ap->qc_active |= 1ULL << qc->tag; /* * We guarantee to LLDs that they will have at least one * non-zero sg if the command is a data command. */ if (ata_is_data(prot) && (!qc->sg || !qc->n_elem || !qc->nbytes)) goto sys_err; if (ata_is_dma(prot) || (ata_is_pio(prot) && (ap->flags & ATA_FLAG_PIO_DMA))) if (ata_sg_setup(qc)) goto sys_err; /* if device is sleeping, schedule reset and abort the link */ if (unlikely(qc->dev->flags & ATA_DFLAG_SLEEPING)) { link->eh_info.action |= ATA_EH_RESET; ata_ehi_push_desc(&link->eh_info, "waking up from sleep"); ata_link_abort(link); return; } qc->err_mask |= ap->ops->qc_prep(qc); if (unlikely(qc->err_mask)) goto err; trace_ata_qc_issue(qc); qc->err_mask |= ap->ops->qc_issue(qc); if (unlikely(qc->err_mask)) goto err; return; sys_err: qc->err_mask |= AC_ERR_SYSTEM; err: ata_qc_complete(qc); } /** * ata_phys_link_online - test whether the given link is online * @link: ATA link to test * * Test whether @link is online. Note that this function returns * 0 if online status of @link cannot be obtained, so * ata_link_online(link) != !ata_link_offline(link). * * LOCKING: * None. * * RETURNS: * True if the port online status is available and online. */ bool ata_phys_link_online(struct ata_link *link) { u32 sstatus; if (sata_scr_read(link, SCR_STATUS, &sstatus) == 0 && ata_sstatus_online(sstatus)) return true; return false; } /** * ata_phys_link_offline - test whether the given link is offline * @link: ATA link to test * * Test whether @link is offline. Note that this function * returns 0 if offline status of @link cannot be obtained, so * ata_link_online(link) != !ata_link_offline(link). * * LOCKING: * None. * * RETURNS: * True if the port offline status is available and offline. */ bool ata_phys_link_offline(struct ata_link *link) { u32 sstatus; if (sata_scr_read(link, SCR_STATUS, &sstatus) == 0 && !ata_sstatus_online(sstatus)) return true; return false; } /** * ata_link_online - test whether the given link is online * @link: ATA link to test * * Test whether @link is online. This is identical to * ata_phys_link_online() when there's no slave link. When * there's a slave link, this function should only be called on * the master link and will return true if any of M/S links is * online. * * LOCKING: * None. * * RETURNS: * True if the port online status is available and online. */ bool ata_link_online(struct ata_link *link) { struct ata_link *slave = link->ap->slave_link; WARN_ON(link == slave); /* shouldn't be called on slave link */ return ata_phys_link_online(link) || (slave && ata_phys_link_online(slave)); } EXPORT_SYMBOL_GPL(ata_link_online); /** * ata_link_offline - test whether the given link is offline * @link: ATA link to test * * Test whether @link is offline. This is identical to * ata_phys_link_offline() when there's no slave link. When * there's a slave link, this function should only be called on * the master link and will return true if both M/S links are * offline. * * LOCKING: * None. * * RETURNS: * True if the port offline status is available and offline. */ bool ata_link_offline(struct ata_link *link) { struct ata_link *slave = link->ap->slave_link; WARN_ON(link == slave); /* shouldn't be called on slave link */ return ata_phys_link_offline(link) && (!slave || ata_phys_link_offline(slave)); } EXPORT_SYMBOL_GPL(ata_link_offline); #ifdef CONFIG_PM static void ata_port_request_pm(struct ata_port *ap, pm_message_t mesg, unsigned int action, unsigned int ehi_flags, bool async) { struct ata_link *link; unsigned long flags; /* Previous resume operation might still be in * progress. Wait for PM_PENDING to clear. */ if (ap->pflags & ATA_PFLAG_PM_PENDING) { ata_port_wait_eh(ap); WARN_ON(ap->pflags & ATA_PFLAG_PM_PENDING); } /* request PM ops to EH */ spin_lock_irqsave(ap->lock, flags); ap->pm_mesg = mesg; ap->pflags |= ATA_PFLAG_PM_PENDING; ata_for_each_link(link, ap, HOST_FIRST) { link->eh_info.action |= action; link->eh_info.flags |= ehi_flags; } ata_port_schedule_eh(ap); spin_unlock_irqrestore(ap->lock, flags); if (!async) { ata_port_wait_eh(ap); WARN_ON(ap->pflags & ATA_PFLAG_PM_PENDING); } } /* * On some hardware, device fails to respond after spun down for suspend. As * the device won't be used before being resumed, we don't need to touch the * device. Ask EH to skip the usual stuff and proceed directly to suspend. * * http://thread.gmane.org/gmane.linux.ide/46764 */ static const unsigned int ata_port_suspend_ehi = ATA_EHI_QUIET | ATA_EHI_NO_AUTOPSY | ATA_EHI_NO_RECOVERY; static void ata_port_suspend(struct ata_port *ap, pm_message_t mesg) { ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, false); } static void ata_port_suspend_async(struct ata_port *ap, pm_message_t mesg) { ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, true); } static int ata_port_pm_suspend(struct device *dev) { struct ata_port *ap = to_ata_port(dev); if (pm_runtime_suspended(dev)) return 0; ata_port_suspend(ap, PMSG_SUSPEND); return 0; } static int ata_port_pm_freeze(struct device *dev) { struct ata_port *ap = to_ata_port(dev); if (pm_runtime_suspended(dev)) return 0; ata_port_suspend(ap, PMSG_FREEZE); return 0; } static int ata_port_pm_poweroff(struct device *dev) { ata_port_suspend(to_ata_port(dev), PMSG_HIBERNATE); return 0; } static const unsigned int ata_port_resume_ehi = ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET; static void ata_port_resume(struct ata_port *ap, pm_message_t mesg) { ata_port_request_pm(ap, mesg, ATA_EH_RESET, ata_port_resume_ehi, false); } static void ata_port_resume_async(struct ata_port *ap, pm_message_t mesg) { ata_port_request_pm(ap, mesg, ATA_EH_RESET, ata_port_resume_ehi, true); } static int ata_port_pm_resume(struct device *dev) { ata_port_resume_async(to_ata_port(dev), PMSG_RESUME); pm_runtime_disable(dev); pm_runtime_set_active(dev); pm_runtime_enable(dev); return 0; } /* * For ODDs, the upper layer will poll for media change every few seconds, * which will make it enter and leave suspend state every few seconds. And * as each suspend will cause a hard/soft reset, the gain of runtime suspend * is very little and the ODD may malfunction after constantly being reset. * So the idle callback here will not proceed to suspend if a non-ZPODD capable * ODD is attached to the port. */ static int ata_port_runtime_idle(struct device *dev) { struct ata_port *ap = to_ata_port(dev); struct ata_link *link; struct ata_device *adev; ata_for_each_link(link, ap, HOST_FIRST) { ata_for_each_dev(adev, link, ENABLED) if (adev->class == ATA_DEV_ATAPI && !zpodd_dev_enabled(adev)) return -EBUSY; } return 0; } static int ata_port_runtime_suspend(struct device *dev) { ata_port_suspend(to_ata_port(dev), PMSG_AUTO_SUSPEND); return 0; } static int ata_port_runtime_resume(struct device *dev) { ata_port_resume(to_ata_port(dev), PMSG_AUTO_RESUME); return 0; } static const struct dev_pm_ops ata_port_pm_ops = { .suspend = ata_port_pm_suspend, .resume = ata_port_pm_resume, .freeze = ata_port_pm_freeze, .thaw = ata_port_pm_resume, .poweroff = ata_port_pm_poweroff, .restore = ata_port_pm_resume, .runtime_suspend = ata_port_runtime_suspend, .runtime_resume = ata_port_runtime_resume, .runtime_idle = ata_port_runtime_idle, }; /* sas ports don't participate in pm runtime management of ata_ports, * and need to resume ata devices at the domain level, not the per-port * level. sas suspend/resume is async to allow parallel port recovery * since sas has multiple ata_port instances per Scsi_Host. */ void ata_sas_port_suspend(struct ata_port *ap) { ata_port_suspend_async(ap, PMSG_SUSPEND); } EXPORT_SYMBOL_GPL(ata_sas_port_suspend); void ata_sas_port_resume(struct ata_port *ap) { ata_port_resume_async(ap, PMSG_RESUME); } EXPORT_SYMBOL_GPL(ata_sas_port_resume); /** * ata_host_suspend - suspend host * @host: host to suspend * @mesg: PM message * * Suspend @host. Actual operation is performed by port suspend. */ int ata_host_suspend(struct ata_host *host, pm_message_t mesg) { host->dev->power.power_state = mesg; return 0; } EXPORT_SYMBOL_GPL(ata_host_suspend); /** * ata_host_resume - resume host * @host: host to resume * * Resume @host. Actual operation is performed by port resume. */ void ata_host_resume(struct ata_host *host) { host->dev->power.power_state = PMSG_ON; } EXPORT_SYMBOL_GPL(ata_host_resume); #endif const struct device_type ata_port_type = { .name = "ata_port", #ifdef CONFIG_PM .pm = &ata_port_pm_ops, #endif }; /** * ata_dev_init - Initialize an ata_device structure * @dev: Device structure to initialize * * Initialize @dev in preparation for probing. * * LOCKING: * Inherited from caller. */ void ata_dev_init(struct ata_device *dev) { struct ata_link *link = ata_dev_phys_link(dev); struct ata_port *ap = link->ap; unsigned long flags; /* SATA spd limit is bound to the attached device, reset together */ link->sata_spd_limit = link->hw_sata_spd_limit; link->sata_spd = 0; /* High bits of dev->flags are used to record warm plug * requests which occur asynchronously. Synchronize using * host lock. */ spin_lock_irqsave(ap->lock, flags); dev->flags &= ~ATA_DFLAG_INIT_MASK; dev->horkage = 0; spin_unlock_irqrestore(ap->lock, flags); memset((void *)dev + ATA_DEVICE_CLEAR_BEGIN, 0, ATA_DEVICE_CLEAR_END - ATA_DEVICE_CLEAR_BEGIN); dev->pio_mask = UINT_MAX; dev->mwdma_mask = UINT_MAX; dev->udma_mask = UINT_MAX; } /** * ata_link_init - Initialize an ata_link structure * @ap: ATA port link is attached to * @link: Link structure to initialize * @pmp: Port multiplier port number * * Initialize @link. * * LOCKING: * Kernel thread context (may sleep) */ void ata_link_init(struct ata_port *ap, struct ata_link *link, int pmp) { int i; /* clear everything except for devices */ memset((void *)link + ATA_LINK_CLEAR_BEGIN, 0, ATA_LINK_CLEAR_END - ATA_LINK_CLEAR_BEGIN); link->ap = ap; link->pmp = pmp; link->active_tag = ATA_TAG_POISON; link->hw_sata_spd_limit = UINT_MAX; /* can't use iterator, ap isn't initialized yet */ for (i = 0; i < ATA_MAX_DEVICES; i++) { struct ata_device *dev = &link->device[i]; dev->link = link; dev->devno = dev - link->device; #ifdef CONFIG_ATA_ACPI dev->gtf_filter = ata_acpi_gtf_filter; #endif ata_dev_init(dev); } } /** * sata_link_init_spd - Initialize link->sata_spd_limit * @link: Link to configure sata_spd_limit for * * Initialize ``link->[hw_]sata_spd_limit`` to the currently * configured value. * * LOCKING: * Kernel thread context (may sleep). * * RETURNS: * 0 on success, -errno on failure. */ int sata_link_init_spd(struct ata_link *link) { u8 spd; int rc; rc = sata_scr_read(link, SCR_CONTROL, &link->saved_scontrol); if (rc) return rc; spd = (link->saved_scontrol >> 4) & 0xf; if (spd) link->hw_sata_spd_limit &= (1 << spd) - 1; ata_force_link_limits(link); link->sata_spd_limit = link->hw_sata_spd_limit; return 0; } /** * ata_port_alloc - allocate and initialize basic ATA port resources * @host: ATA host this allocated port belongs to * * Allocate and initialize basic ATA port resources. * * RETURNS: * Allocate ATA port on success, NULL on failure. * * LOCKING: * Inherited from calling layer (may sleep). */ struct ata_port *ata_port_alloc(struct ata_host *host) { struct ata_port *ap; DPRINTK("ENTER\n"); ap = kzalloc(sizeof(*ap), GFP_KERNEL); if (!ap) return NULL; ap->pflags |= ATA_PFLAG_INITIALIZING | ATA_PFLAG_FROZEN; ap->lock = &host->lock; ap->print_id = -1; ap->local_port_no = -1; ap->host = host; ap->dev = host->dev; #if defined(ATA_VERBOSE_DEBUG) /* turn on all debugging levels */ ap->msg_enable = 0x00FF; #elif defined(ATA_DEBUG) ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO | ATA_MSG_CTL | ATA_MSG_WARN | ATA_MSG_ERR; #else ap->msg_enable = ATA_MSG_DRV | ATA_MSG_ERR | ATA_MSG_WARN; #endif mutex_init(&ap->scsi_scan_mutex); INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug); INIT_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); INIT_LIST_HEAD(&ap->eh_done_q); init_waitqueue_head(&ap->eh_wait_q); init_completion(&ap->park_req_pending); timer_setup(&ap->fastdrain_timer, ata_eh_fastdrain_timerfn, TIMER_DEFERRABLE); ap->cbl = ATA_CBL_NONE; ata_link_init(ap, &ap->link, 0); #ifdef ATA_IRQ_TRAP ap->stats.unhandled_irq = 1; ap->stats.idle_irq = 1; #endif ata_sff_port_init(ap); return ap; } static void ata_devres_release(struct device *gendev, void *res) { struct ata_host *host = dev_get_drvdata(gendev); int i; for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; if (!ap) continue; if (ap->scsi_host) scsi_host_put(ap->scsi_host); } dev_set_drvdata(gendev, NULL); ata_host_put(host); } static void ata_host_release(struct kref *kref) { struct ata_host *host = container_of(kref, struct ata_host, kref); int i; for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; kfree(ap->pmp_link); kfree(ap->slave_link); kfree(ap); host->ports[i] = NULL; } kfree(host); } void ata_host_get(struct ata_host *host) { kref_get(&host->kref); } void ata_host_put(struct ata_host *host) { kref_put(&host->kref, ata_host_release); } EXPORT_SYMBOL_GPL(ata_host_put); /** * ata_host_alloc - allocate and init basic ATA host resources * @dev: generic device this host is associated with * @max_ports: maximum number of ATA ports associated with this host * * Allocate and initialize basic ATA host resources. LLD calls * this function to allocate a host, initializes it fully and * attaches it using ata_host_register(). * * @max_ports ports are allocated and host->n_ports is * initialized to @max_ports. The caller is allowed to decrease * host->n_ports before calling ata_host_register(). The unused * ports will be automatically freed on registration. * * RETURNS: * Allocate ATA host on success, NULL on failure. * * LOCKING: * Inherited from calling layer (may sleep). */ struct ata_host *ata_host_alloc(struct device *dev, int max_ports) { struct ata_host *host; size_t sz; int i; void *dr; DPRINTK("ENTER\n"); /* alloc a container for our list of ATA ports (buses) */ sz = sizeof(struct ata_host) + (max_ports + 1) * sizeof(void *); host = kzalloc(sz, GFP_KERNEL); if (!host) return NULL; if (!devres_open_group(dev, NULL, GFP_KERNEL)) goto err_free; dr = devres_alloc(ata_devres_release, 0, GFP_KERNEL); if (!dr) goto err_out; devres_add(dev, dr); dev_set_drvdata(dev, host); spin_lock_init(&host->lock); mutex_init(&host->eh_mutex); host->dev = dev; host->n_ports = max_ports; kref_init(&host->kref); /* allocate ports bound to this host */ for (i = 0; i < max_ports; i++) { struct ata_port *ap; ap = ata_port_alloc(host); if (!ap) goto err_out; ap->port_no = i; host->ports[i] = ap; } devres_remove_group(dev, NULL); return host; err_out: devres_release_group(dev, NULL); err_free: kfree(host); return NULL; } EXPORT_SYMBOL_GPL(ata_host_alloc); /** * ata_host_alloc_pinfo - alloc host and init with port_info array * @dev: generic device this host is associated with * @ppi: array of ATA port_info to initialize host with * @n_ports: number of ATA ports attached to this host * * Allocate ATA host and initialize with info from @ppi. If NULL * terminated, @ppi may contain fewer entries than @n_ports. The * last entry will be used for the remaining ports. * * RETURNS: * Allocate ATA host on success, NULL on failure. * * LOCKING: * Inherited from calling layer (may sleep). */ struct ata_host *ata_host_alloc_pinfo(struct device *dev, const struct ata_port_info * const * ppi, int n_ports) { const struct ata_port_info *pi; struct ata_host *host; int i, j; host = ata_host_alloc(dev, n_ports); if (!host) return NULL; for (i = 0, j = 0, pi = NULL; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; if (ppi[j]) pi = ppi[j++]; ap->pio_mask = pi->pio_mask; ap->mwdma_mask = pi->mwdma_mask; ap->udma_mask = pi->udma_mask; ap->flags |= pi->flags; ap->link.flags |= pi->link_flags; ap->ops = pi->port_ops; if (!host->ops && (pi->port_ops != &ata_dummy_port_ops)) host->ops = pi->port_ops; } return host; } EXPORT_SYMBOL_GPL(ata_host_alloc_pinfo); static void ata_host_stop(struct device *gendev, void *res) { struct ata_host *host = dev_get_drvdata(gendev); int i; WARN_ON(!(host->flags & ATA_HOST_STARTED)); for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; if (ap->ops->port_stop) ap->ops->port_stop(ap); } if (host->ops->host_stop) host->ops->host_stop(host); } /** * ata_finalize_port_ops - finalize ata_port_operations * @ops: ata_port_operations to finalize * * An ata_port_operations can inherit from another ops and that * ops can again inherit from another. This can go on as many * times as necessary as long as there is no loop in the * inheritance chain. * * Ops tables are finalized when the host is started. NULL or * unspecified entries are inherited from the closet ancestor * which has the method and the entry is populated with it. * After finalization, the ops table directly points to all the * methods and ->inherits is no longer necessary and cleared. * * Using ATA_OP_NULL, inheriting ops can force a method to NULL. * * LOCKING: * None. */ static void ata_finalize_port_ops(struct ata_port_operations *ops) { static DEFINE_SPINLOCK(lock); const struct ata_port_operations *cur; void **begin = (void **)ops; void **end = (void **)&ops->inherits; void **pp; if (!ops || !ops->inherits) return; spin_lock(&lock); for (cur = ops->inherits; cur; cur = cur->inherits) { void **inherit = (void **)cur; for (pp = begin; pp < end; pp++, inherit++) if (!*pp) *pp = *inherit; } for (pp = begin; pp < end; pp++) if (IS_ERR(*pp)) *pp = NULL; ops->inherits = NULL; spin_unlock(&lock); } /** * ata_host_start - start and freeze ports of an ATA host * @host: ATA host to start ports for * * Start and then freeze ports of @host. Started status is * recorded in host->flags, so this function can be called * multiple times. Ports are guaranteed to get started only * once. If host->ops isn't initialized yet, its set to the * first non-dummy port ops. * * LOCKING: * Inherited from calling layer (may sleep). * * RETURNS: * 0 if all ports are started successfully, -errno otherwise. */ int ata_host_start(struct ata_host *host) { int have_stop = 0; void *start_dr = NULL; int i, rc; if (host->flags & ATA_HOST_STARTED) return 0; ata_finalize_port_ops(host->ops); for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; ata_finalize_port_ops(ap->ops); if (!host->ops && !ata_port_is_dummy(ap)) host->ops = ap->ops; if (ap->ops->port_stop) have_stop = 1; } if (host->ops && host->ops->host_stop) have_stop = 1; if (have_stop) { start_dr = devres_alloc(ata_host_stop, 0, GFP_KERNEL); if (!start_dr) return -ENOMEM; } for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; if (ap->ops->port_start) { rc = ap->ops->port_start(ap); if (rc) { if (rc != -ENODEV) dev_err(host->dev, "failed to start port %d (errno=%d)\n", i, rc); goto err_out; } } ata_eh_freeze_port(ap); } if (start_dr) devres_add(host->dev, start_dr); host->flags |= ATA_HOST_STARTED; return 0; err_out: while (--i >= 0) { struct ata_port *ap = host->ports[i]; if (ap->ops->port_stop) ap->ops->port_stop(ap); } devres_free(start_dr); return rc; } EXPORT_SYMBOL_GPL(ata_host_start); /** * ata_host_init - Initialize a host struct for sas (ipr, libsas) * @host: host to initialize * @dev: device host is attached to * @ops: port_ops * */ void ata_host_init(struct ata_host *host, struct device *dev, struct ata_port_operations *ops) { spin_lock_init(&host->lock); mutex_init(&host->eh_mutex); host->n_tags = ATA_MAX_QUEUE; host->dev = dev; host->ops = ops; kref_init(&host->kref); } EXPORT_SYMBOL_GPL(ata_host_init); void __ata_port_probe(struct ata_port *ap) { struct ata_eh_info *ehi = &ap->link.eh_info; unsigned long flags; /* kick EH for boot probing */ spin_lock_irqsave(ap->lock, flags); ehi->probe_mask |= ATA_ALL_DEVICES; ehi->action |= ATA_EH_RESET; ehi->flags |= ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET; ap->pflags &= ~ATA_PFLAG_INITIALIZING; ap->pflags |= ATA_PFLAG_LOADING; ata_port_schedule_eh(ap); spin_unlock_irqrestore(ap->lock, flags); } int ata_port_probe(struct ata_port *ap) { int rc = 0; if (ap->ops->error_handler) { __ata_port_probe(ap); ata_port_wait_eh(ap); } else { DPRINTK("ata%u: bus probe begin\n", ap->print_id); rc = ata_bus_probe(ap); DPRINTK("ata%u: bus probe end\n", ap->print_id); } return rc; } static void async_port_probe(void *data, async_cookie_t cookie) { struct ata_port *ap = data; /* * If we're not allowed to scan this host in parallel, * we need to wait until all previous scans have completed * before going further. * Jeff Garzik says this is only within a controller, so we * don't need to wait for port 0, only for later ports. */ if (!(ap->host->flags & ATA_HOST_PARALLEL_SCAN) && ap->port_no != 0) async_synchronize_cookie(cookie); (void)ata_port_probe(ap); /* in order to keep device order, we need to synchronize at this point */ async_synchronize_cookie(cookie); ata_scsi_scan_host(ap, 1); } /** * ata_host_register - register initialized ATA host * @host: ATA host to register * @sht: template for SCSI host * * Register initialized ATA host. @host is allocated using * ata_host_alloc() and fully initialized by LLD. This function * starts ports, registers @host with ATA and SCSI layers and * probe registered devices. * * LOCKING: * Inherited from calling layer (may sleep). * * RETURNS: * 0 on success, -errno otherwise. */ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht) { int i, rc; host->n_tags = clamp(sht->can_queue, 1, ATA_MAX_QUEUE); /* host must have been started */ if (!(host->flags & ATA_HOST_STARTED)) { dev_err(host->dev, "BUG: trying to register unstarted host\n"); WARN_ON(1); return -EINVAL; } /* Blow away unused ports. This happens when LLD can't * determine the exact number of ports to allocate at * allocation time. */ for (i = host->n_ports; host->ports[i]; i++) kfree(host->ports[i]); /* give ports names and add SCSI hosts */ for (i = 0; i < host->n_ports; i++) { host->ports[i]->print_id = atomic_inc_return(&ata_print_id); host->ports[i]->local_port_no = i + 1; } /* Create associated sysfs transport objects */ for (i = 0; i < host->n_ports; i++) { rc = ata_tport_add(host->dev,host->ports[i]); if (rc) { goto err_tadd; } } rc = ata_scsi_add_hosts(host, sht); if (rc) goto err_tadd; /* set cable, sata_spd_limit and report */ for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; unsigned long xfer_mask; /* set SATA cable type if still unset */ if (ap->cbl == ATA_CBL_NONE && (ap->flags & ATA_FLAG_SATA)) ap->cbl = ATA_CBL_SATA; /* init sata_spd_limit to the current value */ sata_link_init_spd(&ap->link); if (ap->slave_link) sata_link_init_spd(ap->slave_link); /* print per-port info to dmesg */ xfer_mask = ata_pack_xfermask(ap->pio_mask, ap->mwdma_mask, ap->udma_mask); if (!ata_port_is_dummy(ap)) { ata_port_info(ap, "%cATA max %s %s\n", (ap->flags & ATA_FLAG_SATA) ? 'S' : 'P', ata_mode_string(xfer_mask), ap->link.eh_info.desc); ata_ehi_clear_desc(&ap->link.eh_info); } else ata_port_info(ap, "DUMMY\n"); } /* perform each probe asynchronously */ for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; ap->cookie = async_schedule(async_port_probe, ap); } return 0; err_tadd: while (--i >= 0) { ata_tport_delete(host->ports[i]); } return rc; } EXPORT_SYMBOL_GPL(ata_host_register); /** * ata_host_activate - start host, request IRQ and register it * @host: target ATA host * @irq: IRQ to request * @irq_handler: irq_handler used when requesting IRQ * @irq_flags: irq_flags used when requesting IRQ * @sht: scsi_host_template to use when registering the host * * After allocating an ATA host and initializing it, most libata * LLDs perform three steps to activate the host - start host, * request IRQ and register it. This helper takes necessary * arguments and performs the three steps in one go. * * An invalid IRQ skips the IRQ registration and expects the host to * have set polling mode on the port. In this case, @irq_handler * should be NULL. * * LOCKING: * Inherited from calling layer (may sleep). * * RETURNS: * 0 on success, -errno otherwise. */ int ata_host_activate(struct ata_host *host, int irq, irq_handler_t irq_handler, unsigned long irq_flags, struct scsi_host_template *sht) { int i, rc; char *irq_desc; rc = ata_host_start(host); if (rc) return rc; /* Special case for polling mode */ if (!irq) { WARN_ON(irq_handler); return ata_host_register(host, sht); } irq_desc = devm_kasprintf(host->dev, GFP_KERNEL, "%s[%s]", dev_driver_string(host->dev), dev_name(host->dev)); if (!irq_desc) return -ENOMEM; rc = devm_request_irq(host->dev, irq, irq_handler, irq_flags, irq_desc, host); if (rc) return rc; for (i = 0; i < host->n_ports; i++) ata_port_desc(host->ports[i], "irq %d", irq); rc = ata_host_register(host, sht); /* if failed, just free the IRQ and leave ports alone */ if (rc) devm_free_irq(host->dev, irq, host); return rc; } EXPORT_SYMBOL_GPL(ata_host_activate); /** * ata_port_detach - Detach ATA port in preparation of device removal * @ap: ATA port to be detached * * Detach all ATA devices and the associated SCSI devices of @ap; * then, remove the associated SCSI host. @ap is guaranteed to * be quiescent on return from this function. * * LOCKING: * Kernel thread context (may sleep). */ static void ata_port_detach(struct ata_port *ap) { unsigned long flags; struct ata_link *link; struct ata_device *dev; if (!ap->ops->error_handler) goto skip_eh; /* tell EH we're leaving & flush EH */ spin_lock_irqsave(ap->lock, flags); ap->pflags |= ATA_PFLAG_UNLOADING; ata_port_schedule_eh(ap); spin_unlock_irqrestore(ap->lock, flags); /* wait till EH commits suicide */ ata_port_wait_eh(ap); /* it better be dead now */ WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED)); cancel_delayed_work_sync(&ap->hotplug_task); skip_eh: /* clean up zpodd on port removal */ ata_for_each_link(link, ap, HOST_FIRST) { ata_for_each_dev(dev, link, ALL) { if (zpodd_dev_enabled(dev)) zpodd_exit(dev); } } if (ap->pmp_link) { int i; for (i = 0; i < SATA_PMP_MAX_PORTS; i++) ata_tlink_delete(&ap->pmp_link[i]); } /* remove the associated SCSI host */ scsi_remove_host(ap->scsi_host); ata_tport_delete(ap); } /** * ata_host_detach - Detach all ports of an ATA host * @host: Host to detach * * Detach all ports of @host. * * LOCKING: * Kernel thread context (may sleep). */ void ata_host_detach(struct ata_host *host) { int i; for (i = 0; i < host->n_ports; i++) { /* Ensure ata_port probe has completed */ async_synchronize_cookie(host->ports[i]->cookie + 1); ata_port_detach(host->ports[i]); } /* the host is dead now, dissociate ACPI */ ata_acpi_dissociate(host); } EXPORT_SYMBOL_GPL(ata_host_detach); #ifdef CONFIG_PCI /** * ata_pci_remove_one - PCI layer callback for device removal * @pdev: PCI device that was removed * * PCI layer indicates to libata via this hook that hot-unplug or * module unload event has occurred. Detach all ports. Resource * release is handled via devres. * * LOCKING: * Inherited from PCI layer (may sleep). */ void ata_pci_remove_one(struct pci_dev *pdev) { struct ata_host *host = pci_get_drvdata(pdev); ata_host_detach(host); } EXPORT_SYMBOL_GPL(ata_pci_remove_one); void ata_pci_shutdown_one(struct pci_dev *pdev) { struct ata_host *host = pci_get_drvdata(pdev); int i; for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; ap->pflags |= ATA_PFLAG_FROZEN; /* Disable port interrupts */ if (ap->ops->freeze) ap->ops->freeze(ap); /* Stop the port DMA engines */ if (ap->ops->port_stop) ap->ops->port_stop(ap); } } EXPORT_SYMBOL_GPL(ata_pci_shutdown_one); /* move to PCI subsystem */ int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits) { unsigned long tmp = 0; switch (bits->width) { case 1: { u8 tmp8 = 0; pci_read_config_byte(pdev, bits->reg, &tmp8); tmp = tmp8; break; } case 2: { u16 tmp16 = 0; pci_read_config_word(pdev, bits->reg, &tmp16); tmp = tmp16; break; } case 4: { u32 tmp32 = 0; pci_read_config_dword(pdev, bits->reg, &tmp32); tmp = tmp32; break; } default: return -EINVAL; } tmp &= bits->mask; return (tmp == bits->val) ? 1 : 0; } EXPORT_SYMBOL_GPL(pci_test_config_bits); #ifdef CONFIG_PM void ata_pci_device_do_suspend(struct pci_dev *pdev, pm_message_t mesg) { pci_save_state(pdev); pci_disable_device(pdev); if (mesg.event & PM_EVENT_SLEEP) pci_set_power_state(pdev, PCI_D3hot); } EXPORT_SYMBOL_GPL(ata_pci_device_do_suspend); int ata_pci_device_do_resume(struct pci_dev *pdev) { int rc; pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); rc = pcim_enable_device(pdev); if (rc) { dev_err(&pdev->dev, "failed to enable device after resume (%d)\n", rc); return rc; } pci_set_master(pdev); return 0; } EXPORT_SYMBOL_GPL(ata_pci_device_do_resume); int ata_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg) { struct ata_host *host = pci_get_drvdata(pdev); int rc = 0; rc = ata_host_suspend(host, mesg); if (rc) return rc; ata_pci_device_do_suspend(pdev, mesg); return 0; } EXPORT_SYMBOL_GPL(ata_pci_device_suspend); int ata_pci_device_resume(struct pci_dev *pdev) { struct ata_host *host = pci_get_drvdata(pdev); int rc; rc = ata_pci_device_do_resume(pdev); if (rc == 0) ata_host_resume(host); return rc; } EXPORT_SYMBOL_GPL(ata_pci_device_resume); #endif /* CONFIG_PM */ #endif /* CONFIG_PCI */ /** * ata_platform_remove_one - Platform layer callback for device removal * @pdev: Platform device that was removed * * Platform layer indicates to libata via this hook that hot-unplug or * module unload event has occurred. Detach all ports. Resource * release is handled via devres. * * LOCKING: * Inherited from platform layer (may sleep). */ int ata_platform_remove_one(struct platform_device *pdev) { struct ata_host *host = platform_get_drvdata(pdev); ata_host_detach(host); return 0; } EXPORT_SYMBOL_GPL(ata_platform_remove_one); #ifdef CONFIG_ATA_FORCE static int __init ata_parse_force_one(char **cur, struct ata_force_ent *force_ent, const char **reason) { static const struct ata_force_param force_tbl[] __initconst = { { "40c", .cbl = ATA_CBL_PATA40 }, { "80c", .cbl = ATA_CBL_PATA80 }, { "short40c", .cbl = ATA_CBL_PATA40_SHORT }, { "unk", .cbl = ATA_CBL_PATA_UNK }, { "ign", .cbl = ATA_CBL_PATA_IGN }, { "sata", .cbl = ATA_CBL_SATA }, { "1.5Gbps", .spd_limit = 1 }, { "3.0Gbps", .spd_limit = 2 }, { "noncq", .horkage_on = ATA_HORKAGE_NONCQ }, { "ncq", .horkage_off = ATA_HORKAGE_NONCQ }, { "noncqtrim", .horkage_on = ATA_HORKAGE_NO_NCQ_TRIM }, { "ncqtrim", .horkage_off = ATA_HORKAGE_NO_NCQ_TRIM }, { "noncqati", .horkage_on = ATA_HORKAGE_NO_NCQ_ON_ATI }, { "ncqati", .horkage_off = ATA_HORKAGE_NO_NCQ_ON_ATI }, { "dump_id", .horkage_on = ATA_HORKAGE_DUMP_ID }, { "pio0", .xfer_mask = 1 << (ATA_SHIFT_PIO + 0) }, { "pio1", .xfer_mask = 1 << (ATA_SHIFT_PIO + 1) }, { "pio2", .xfer_mask = 1 << (ATA_SHIFT_PIO + 2) }, { "pio3", .xfer_mask = 1 << (ATA_SHIFT_PIO + 3) }, { "pio4", .xfer_mask = 1 << (ATA_SHIFT_PIO + 4) }, { "pio5", .xfer_mask = 1 << (ATA_SHIFT_PIO + 5) }, { "pio6", .xfer_mask = 1 << (ATA_SHIFT_PIO + 6) }, { "mwdma0", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 0) }, { "mwdma1", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 1) }, { "mwdma2", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 2) }, { "mwdma3", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 3) }, { "mwdma4", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 4) }, { "udma0", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 0) }, { "udma16", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 0) }, { "udma/16", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 0) }, { "udma1", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 1) }, { "udma25", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 1) }, { "udma/25", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 1) }, { "udma2", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 2) }, { "udma33", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 2) }, { "udma/33", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 2) }, { "udma3", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 3) }, { "udma44", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 3) }, { "udma/44", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 3) }, { "udma4", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 4) }, { "udma66", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 4) }, { "udma/66", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 4) }, { "udma5", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 5) }, { "udma100", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 5) }, { "udma/100", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 5) }, { "udma6", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 6) }, { "udma133", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 6) }, { "udma/133", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 6) }, { "udma7", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 7) }, { "nohrst", .lflags = ATA_LFLAG_NO_HRST }, { "nosrst", .lflags = ATA_LFLAG_NO_SRST }, { "norst", .lflags = ATA_LFLAG_NO_HRST | ATA_LFLAG_NO_SRST }, { "rstonce", .lflags = ATA_LFLAG_RST_ONCE }, { "atapi_dmadir", .horkage_on = ATA_HORKAGE_ATAPI_DMADIR }, { "disable", .horkage_on = ATA_HORKAGE_DISABLE }, }; char *start = *cur, *p = *cur; char *id, *val, *endp; const struct ata_force_param *match_fp = NULL; int nr_matches = 0, i; /* find where this param ends and update *cur */ while (*p != '\0' && *p != ',') p++; if (*p == '\0') *cur = p; else *cur = p + 1; *p = '\0'; /* parse */ p = strchr(start, ':'); if (!p) { val = strstrip(start); goto parse_val; } *p = '\0'; id = strstrip(start); val = strstrip(p + 1); /* parse id */ p = strchr(id, '.'); if (p) { *p++ = '\0'; force_ent->device = simple_strtoul(p, &endp, 10); if (p == endp || *endp != '\0') { *reason = "invalid device"; return -EINVAL; } } force_ent->port = simple_strtoul(id, &endp, 10); if (id == endp || *endp != '\0') { *reason = "invalid port/link"; return -EINVAL; } parse_val: /* parse val, allow shortcuts so that both 1.5 and 1.5Gbps work */ for (i = 0; i < ARRAY_SIZE(force_tbl); i++) { const struct ata_force_param *fp = &force_tbl[i]; if (strncasecmp(val, fp->name, strlen(val))) continue; nr_matches++; match_fp = fp; if (strcasecmp(val, fp->name) == 0) { nr_matches = 1; break; } } if (!nr_matches) { *reason = "unknown value"; return -EINVAL; } if (nr_matches > 1) { *reason = "ambiguous value"; return -EINVAL; } force_ent->param = *match_fp; return 0; } static void __init ata_parse_force_param(void) { int idx = 0, size = 1; int last_port = -1, last_device = -1; char *p, *cur, *next; /* calculate maximum number of params and allocate force_tbl */ for (p = ata_force_param_buf; *p; p++) if (*p == ',') size++; ata_force_tbl = kcalloc(size, sizeof(ata_force_tbl[0]), GFP_KERNEL); if (!ata_force_tbl) { printk(KERN_WARNING "ata: failed to extend force table, " "libata.force ignored\n"); return; } /* parse and populate the table */ for (cur = ata_force_param_buf; *cur != '\0'; cur = next) { const char *reason = ""; struct ata_force_ent te = { .port = -1, .device = -1 }; next = cur; if (ata_parse_force_one(&next, &te, &reason)) { printk(KERN_WARNING "ata: failed to parse force " "parameter \"%s\" (%s)\n", cur, reason); continue; } if (te.port == -1) { te.port = last_port; te.device = last_device; } ata_force_tbl[idx++] = te; last_port = te.port; last_device = te.device; } ata_force_tbl_size = idx; } static void ata_free_force_param(void) { kfree(ata_force_tbl); } #else static inline void ata_parse_force_param(void) { } static inline void ata_free_force_param(void) { } #endif static int __init ata_init(void) { int rc; ata_parse_force_param(); rc = ata_sff_init(); if (rc) { ata_free_force_param(); return rc; } libata_transport_init(); ata_scsi_transport_template = ata_attach_transport(); if (!ata_scsi_transport_template) { ata_sff_exit(); rc = -ENOMEM; goto err_out; } printk(KERN_DEBUG "libata version " DRV_VERSION " loaded.\n"); return 0; err_out: return rc; } static void __exit ata_exit(void) { ata_release_transport(ata_scsi_transport_template); libata_transport_exit(); ata_sff_exit(); ata_free_force_param(); } subsys_initcall(ata_init); module_exit(ata_exit); static DEFINE_RATELIMIT_STATE(ratelimit, HZ / 5, 1); int ata_ratelimit(void) { return __ratelimit(&ratelimit); } EXPORT_SYMBOL_GPL(ata_ratelimit); /** * ata_msleep - ATA EH owner aware msleep * @ap: ATA port to attribute the sleep to * @msecs: duration to sleep in milliseconds * * Sleeps @msecs. If the current task is owner of @ap's EH, the * ownership is released before going to sleep and reacquired * after the sleep is complete. IOW, other ports sharing the * @ap->host will be allowed to own the EH while this task is * sleeping. * * LOCKING: * Might sleep. */ void ata_msleep(struct ata_port *ap, unsigned int msecs) { bool owns_eh = ap && ap->host->eh_owner == current; if (owns_eh) ata_eh_release(ap); if (msecs < 20) { unsigned long usecs = msecs * USEC_PER_MSEC; usleep_range(usecs, usecs + 50); } else { msleep(msecs); } if (owns_eh) ata_eh_acquire(ap); } EXPORT_SYMBOL_GPL(ata_msleep); /** * ata_wait_register - wait until register value changes * @ap: ATA port to wait register for, can be NULL * @reg: IO-mapped register * @mask: Mask to apply to read register value * @val: Wait condition * @interval: polling interval in milliseconds * @timeout: timeout in milliseconds * * Waiting for some bits of register to change is a common * operation for ATA controllers. This function reads 32bit LE * IO-mapped register @reg and tests for the following condition. * * (*@reg & mask) != val * * If the condition is met, it returns; otherwise, the process is * repeated after @interval_msec until timeout. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * The final register value. */ u32 ata_wait_register(struct ata_port *ap, void __iomem *reg, u32 mask, u32 val, unsigned long interval, unsigned long timeout) { unsigned long deadline; u32 tmp; tmp = ioread32(reg); /* Calculate timeout _after_ the first read to make sure * preceding writes reach the controller before starting to * eat away the timeout. */ deadline = ata_deadline(jiffies, timeout); while ((tmp & mask) == val && time_before(jiffies, deadline)) { ata_msleep(ap, interval); tmp = ioread32(reg); } return tmp; } EXPORT_SYMBOL_GPL(ata_wait_register); /* * Dummy port_ops */ static unsigned int ata_dummy_qc_issue(struct ata_queued_cmd *qc) { return AC_ERR_SYSTEM; } static void ata_dummy_error_handler(struct ata_port *ap) { /* truly dummy */ } struct ata_port_operations ata_dummy_port_ops = { .qc_prep = ata_noop_qc_prep, .qc_issue = ata_dummy_qc_issue, .error_handler = ata_dummy_error_handler, .sched_eh = ata_std_sched_eh, .end_eh = ata_std_end_eh, }; EXPORT_SYMBOL_GPL(ata_dummy_port_ops); const struct ata_port_info ata_dummy_port_info = { .port_ops = &ata_dummy_port_ops, }; EXPORT_SYMBOL_GPL(ata_dummy_port_info); /* * Utility print functions */ void ata_port_printk(const struct ata_port *ap, const char *level, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk("%sata%u: %pV", level, ap->print_id, &vaf); va_end(args); } EXPORT_SYMBOL(ata_port_printk); void ata_link_printk(const struct ata_link *link, const char *level, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (sata_pmp_attached(link->ap) || link->ap->slave_link) printk("%sata%u.%02u: %pV", level, link->ap->print_id, link->pmp, &vaf); else printk("%sata%u: %pV", level, link->ap->print_id, &vaf); va_end(args); } EXPORT_SYMBOL(ata_link_printk); void ata_dev_printk(const struct ata_device *dev, const char *level, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk("%sata%u.%02u: %pV", level, dev->link->ap->print_id, dev->link->pmp + dev->devno, &vaf); va_end(args); } EXPORT_SYMBOL(ata_dev_printk); void ata_print_version(const struct device *dev, const char *version) { dev_printk(KERN_DEBUG, dev, "version %s\n", version); } EXPORT_SYMBOL(ata_print_version);
2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 2 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM ext4 #if !defined(_TRACE_EXT4_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_EXT4_H #include <linux/writeback.h> #include <linux/tracepoint.h> struct ext4_allocation_context; struct ext4_allocation_request; struct ext4_extent; struct ext4_prealloc_space; struct ext4_inode_info; struct mpage_da_data; struct ext4_map_blocks; struct extent_status; struct ext4_fsmap; struct partial_cluster; #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) #define show_mballoc_flags(flags) __print_flags(flags, "|", \ { EXT4_MB_HINT_MERGE, "HINT_MERGE" }, \ { EXT4_MB_HINT_RESERVED, "HINT_RESV" }, \ { EXT4_MB_HINT_METADATA, "HINT_MDATA" }, \ { EXT4_MB_HINT_FIRST, "HINT_FIRST" }, \ { EXT4_MB_HINT_BEST, "HINT_BEST" }, \ { EXT4_MB_HINT_DATA, "HINT_DATA" }, \ { EXT4_MB_HINT_NOPREALLOC, "HINT_NOPREALLOC" }, \ { EXT4_MB_HINT_GROUP_ALLOC, "HINT_GRP_ALLOC" }, \ { EXT4_MB_HINT_GOAL_ONLY, "HINT_GOAL_ONLY" }, \ { EXT4_MB_HINT_TRY_GOAL, "HINT_TRY_GOAL" }, \ { EXT4_MB_DELALLOC_RESERVED, "DELALLOC_RESV" }, \ { EXT4_MB_STREAM_ALLOC, "STREAM_ALLOC" }, \ { EXT4_MB_USE_ROOT_BLOCKS, "USE_ROOT_BLKS" }, \ { EXT4_MB_USE_RESERVED, "USE_RESV" }, \ { EXT4_MB_STRICT_CHECK, "STRICT_CHECK" }) #define show_map_flags(flags) __print_flags(flags, "|", \ { EXT4_GET_BLOCKS_CREATE, "CREATE" }, \ { EXT4_GET_BLOCKS_UNWRIT_EXT, "UNWRIT" }, \ { EXT4_GET_BLOCKS_DELALLOC_RESERVE, "DELALLOC" }, \ { EXT4_GET_BLOCKS_PRE_IO, "PRE_IO" }, \ { EXT4_GET_BLOCKS_CONVERT, "CONVERT" }, \ { EXT4_GET_BLOCKS_METADATA_NOFAIL, "METADATA_NOFAIL" }, \ { EXT4_GET_BLOCKS_NO_NORMALIZE, "NO_NORMALIZE" }, \ { EXT4_GET_BLOCKS_CONVERT_UNWRITTEN, "CONVERT_UNWRITTEN" }, \ { EXT4_GET_BLOCKS_ZERO, "ZERO" }, \ { EXT4_GET_BLOCKS_IO_SUBMIT, "IO_SUBMIT" }, \ { EXT4_EX_NOCACHE, "EX_NOCACHE" }) /* * __print_flags() requires that all enum values be wrapped in the * TRACE_DEFINE_ENUM macro so that the enum value can be encoded in the ftrace * ring buffer. */ TRACE_DEFINE_ENUM(BH_New); TRACE_DEFINE_ENUM(BH_Mapped); TRACE_DEFINE_ENUM(BH_Unwritten); TRACE_DEFINE_ENUM(BH_Boundary); #define show_mflags(flags) __print_flags(flags, "", \ { EXT4_MAP_NEW, "N" }, \ { EXT4_MAP_MAPPED, "M" }, \ { EXT4_MAP_UNWRITTEN, "U" }, \ { EXT4_MAP_BOUNDARY, "B" }) #define show_free_flags(flags) __print_flags(flags, "|", \ { EXT4_FREE_BLOCKS_METADATA, "METADATA" }, \ { EXT4_FREE_BLOCKS_FORGET, "FORGET" }, \ { EXT4_FREE_BLOCKS_VALIDATED, "VALIDATED" }, \ { EXT4_FREE_BLOCKS_NO_QUOT_UPDATE, "NO_QUOTA" }, \ { EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER,"1ST_CLUSTER" },\ { EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER, "LAST_CLUSTER" }) TRACE_DEFINE_ENUM(ES_WRITTEN_B); TRACE_DEFINE_ENUM(ES_UNWRITTEN_B); TRACE_DEFINE_ENUM(ES_DELAYED_B); TRACE_DEFINE_ENUM(ES_HOLE_B); TRACE_DEFINE_ENUM(ES_REFERENCED_B); #define show_extent_status(status) __print_flags(status, "", \ { EXTENT_STATUS_WRITTEN, "W" }, \ { EXTENT_STATUS_UNWRITTEN, "U" }, \ { EXTENT_STATUS_DELAYED, "D" }, \ { EXTENT_STATUS_HOLE, "H" }, \ { EXTENT_STATUS_REFERENCED, "R" }) #define show_falloc_mode(mode) __print_flags(mode, "|", \ { FALLOC_FL_KEEP_SIZE, "KEEP_SIZE"}, \ { FALLOC_FL_PUNCH_HOLE, "PUNCH_HOLE"}, \ { FALLOC_FL_NO_HIDE_STALE, "NO_HIDE_STALE"}, \ { FALLOC_FL_COLLAPSE_RANGE, "COLLAPSE_RANGE"}, \ { FALLOC_FL_ZERO_RANGE, "ZERO_RANGE"}) #define show_fc_reason(reason) \ __print_symbolic(reason, \ { EXT4_FC_REASON_XATTR, "XATTR"}, \ { EXT4_FC_REASON_CROSS_RENAME, "CROSS_RENAME"}, \ { EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \ { EXT4_FC_REASON_NOMEM, "NO_MEM"}, \ { EXT4_FC_REASON_SWAP_BOOT, "SWAP_BOOT"}, \ { EXT4_FC_REASON_RESIZE, "RESIZE"}, \ { EXT4_FC_REASON_RENAME_DIR, "RENAME_DIR"}, \ { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}, \ { EXT4_FC_REASON_INODE_JOURNAL_DATA, "INODE_JOURNAL_DATA"}) TRACE_EVENT(ext4_other_inode_update_time, TP_PROTO(struct inode *inode, ino_t orig_ino), TP_ARGS(inode, orig_ino), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, orig_ino ) __field( uid_t, uid ) __field( gid_t, gid ) __field( __u16, mode ) ), TP_fast_assign( __entry->orig_ino = orig_ino; __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->uid = i_uid_read(inode); __entry->gid = i_gid_read(inode); __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d orig_ino %lu ino %lu mode 0%o uid %u gid %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->orig_ino, (unsigned long) __entry->ino, __entry->mode, __entry->uid, __entry->gid) ); TRACE_EVENT(ext4_free_inode, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( uid_t, uid ) __field( gid_t, gid ) __field( __u64, blocks ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->uid = i_uid_read(inode); __entry->gid = i_gid_read(inode); __entry->blocks = inode->i_blocks; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o uid %u gid %u blocks %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->uid, __entry->gid, __entry->blocks) ); TRACE_EVENT(ext4_request_inode, TP_PROTO(struct inode *dir, int mode), TP_ARGS(dir, mode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, dir ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d dir %lu mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->dir, __entry->mode) ); TRACE_EVENT(ext4_allocate_inode, TP_PROTO(struct inode *inode, struct inode *dir, int mode), TP_ARGS(inode, dir, mode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, dir ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d ino %lu dir %lu mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->dir, __entry->mode) ); TRACE_EVENT(ext4_evict_inode, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, nlink ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nlink = inode->i_nlink; ), TP_printk("dev %d,%d ino %lu nlink %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->nlink) ); TRACE_EVENT(ext4_drop_inode, TP_PROTO(struct inode *inode, int drop), TP_ARGS(inode, drop), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, drop ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->drop = drop; ), TP_printk("dev %d,%d ino %lu drop %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->drop) ); TRACE_EVENT(ext4_nfs_commit_metadata, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; ), TP_printk("dev %d,%d ino %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino) ); TRACE_EVENT(ext4_mark_inode_dirty, TP_PROTO(struct inode *inode, unsigned long IP), TP_ARGS(inode, IP), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field(unsigned long, ip ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ip = IP; ), TP_printk("dev %d,%d ino %lu caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (void *)__entry->ip) ); TRACE_EVENT(ext4_begin_ordered_truncate, TP_PROTO(struct inode *inode, loff_t new_size), TP_ARGS(inode, new_size), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, new_size ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->new_size = new_size; ), TP_printk("dev %d,%d ino %lu new_size %lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->new_size) ); DECLARE_EVENT_CLASS(ext4__write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int flags), TP_ARGS(inode, pos, len, flags), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; __entry->flags = flags; ), TP_printk("dev %d,%d ino %lu pos %lld len %u flags %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->len, __entry->flags) ); DEFINE_EVENT(ext4__write_begin, ext4_write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int flags), TP_ARGS(inode, pos, len, flags) ); DEFINE_EVENT(ext4__write_begin, ext4_da_write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int flags), TP_ARGS(inode, pos, len, flags) ); DECLARE_EVENT_CLASS(ext4__write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) __field( unsigned int, copied ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; __entry->copied = copied; ), TP_printk("dev %d,%d ino %lu pos %lld len %u copied %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->len, __entry->copied) ); DEFINE_EVENT(ext4__write_end, ext4_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied) ); DEFINE_EVENT(ext4__write_end, ext4_journalled_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied) ); DEFINE_EVENT(ext4__write_end, ext4_da_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied) ); TRACE_EVENT(ext4_writepages, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( long, nr_to_write ) __field( long, pages_skipped ) __field( loff_t, range_start ) __field( loff_t, range_end ) __field( pgoff_t, writeback_index ) __field( int, sync_mode ) __field( char, for_kupdate ) __field( char, range_cyclic ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->range_start = wbc->range_start; __entry->range_end = wbc->range_end; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; __entry->range_cyclic = wbc->range_cyclic; ), TP_printk("dev %d,%d ino %lu nr_to_write %ld pages_skipped %ld " "range_start %lld range_end %lld sync_mode %d " "for_kupdate %d range_cyclic %d writeback_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, __entry->range_end, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, (unsigned long) __entry->writeback_index) ); TRACE_EVENT(ext4_da_write_pages, TP_PROTO(struct inode *inode, pgoff_t first_page, struct writeback_control *wbc), TP_ARGS(inode, first_page, wbc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, first_page ) __field( long, nr_to_write ) __field( int, sync_mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->first_page = first_page; __entry->nr_to_write = wbc->nr_to_write; __entry->sync_mode = wbc->sync_mode; ), TP_printk("dev %d,%d ino %lu first_page %lu nr_to_write %ld " "sync_mode %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->first_page, __entry->nr_to_write, __entry->sync_mode) ); TRACE_EVENT(ext4_da_write_pages_extent, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map), TP_ARGS(inode, map), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, lblk ) __field( __u32, len ) __field( __u32, flags ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = map->m_lblk; __entry->len = map->m_len; __entry->flags = map->m_flags; ), TP_printk("dev %d,%d ino %lu lblk %llu len %u flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, show_mflags(__entry->flags)) ); TRACE_EVENT(ext4_writepages_result, TP_PROTO(struct inode *inode, struct writeback_control *wbc, int ret, int pages_written), TP_ARGS(inode, wbc, ret, pages_written), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, ret ) __field( int, pages_written ) __field( long, pages_skipped ) __field( pgoff_t, writeback_index ) __field( int, sync_mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ret = ret; __entry->pages_written = pages_written; __entry->pages_skipped = wbc->pages_skipped; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->sync_mode = wbc->sync_mode; ), TP_printk("dev %d,%d ino %lu ret %d pages_written %d pages_skipped %ld " "sync_mode %d writeback_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret, __entry->pages_written, __entry->pages_skipped, __entry->sync_mode, (unsigned long) __entry->writeback_index) ); DECLARE_EVENT_CLASS(ext4__page_op, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, index ) ), TP_fast_assign( __entry->dev = page->mapping->host->i_sb->s_dev; __entry->ino = page->mapping->host->i_ino; __entry->index = page->index; ), TP_printk("dev %d,%d ino %lu page_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->index) ); DEFINE_EVENT(ext4__page_op, ext4_writepage, TP_PROTO(struct page *page), TP_ARGS(page) ); DEFINE_EVENT(ext4__page_op, ext4_readpage, TP_PROTO(struct page *page), TP_ARGS(page) ); DEFINE_EVENT(ext4__page_op, ext4_releasepage, TP_PROTO(struct page *page), TP_ARGS(page) ); DECLARE_EVENT_CLASS(ext4_invalidatepage_op, TP_PROTO(struct page *page, unsigned int offset, unsigned int length), TP_ARGS(page, offset, length), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, index ) __field( unsigned int, offset ) __field( unsigned int, length ) ), TP_fast_assign( __entry->dev = page->mapping->host->i_sb->s_dev; __entry->ino = page->mapping->host->i_ino; __entry->index = page->index; __entry->offset = offset; __entry->length = length; ), TP_printk("dev %d,%d ino %lu page_index %lu offset %u length %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->index, __entry->offset, __entry->length) ); DEFINE_EVENT(ext4_invalidatepage_op, ext4_invalidatepage, TP_PROTO(struct page *page, unsigned int offset, unsigned int length), TP_ARGS(page, offset, length) ); DEFINE_EVENT(ext4_invalidatepage_op, ext4_journalled_invalidatepage, TP_PROTO(struct page *page, unsigned int offset, unsigned int length), TP_ARGS(page, offset, length) ); TRACE_EVENT(ext4_discard_blocks, TP_PROTO(struct super_block *sb, unsigned long long blk, unsigned long long count), TP_ARGS(sb, blk, count), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u64, blk ) __field( __u64, count ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->blk = blk; __entry->count = count; ), TP_printk("dev %d,%d blk %llu count %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blk, __entry->count) ); DECLARE_EVENT_CLASS(ext4__mb_new_pa, TP_PROTO(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), TP_ARGS(ac, pa), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, pa_pstart ) __field( __u64, pa_lstart ) __field( __u32, pa_len ) ), TP_fast_assign( __entry->dev = ac->ac_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->pa_pstart = pa->pa_pstart; __entry->pa_lstart = pa->pa_lstart; __entry->pa_len = pa->pa_len; ), TP_printk("dev %d,%d ino %lu pstart %llu len %u lstart %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart) ); DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_inode_pa, TP_PROTO(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), TP_ARGS(ac, pa) ); DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_group_pa, TP_PROTO(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), TP_ARGS(ac, pa) ); TRACE_EVENT(ext4_mb_release_inode_pa, TP_PROTO(struct ext4_prealloc_space *pa, unsigned long long block, unsigned int count), TP_ARGS(pa, block, count), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( __u32, count ) ), TP_fast_assign( __entry->dev = pa->pa_inode->i_sb->s_dev; __entry->ino = pa->pa_inode->i_ino; __entry->block = block; __entry->count = count; ), TP_printk("dev %d,%d ino %lu block %llu count %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->block, __entry->count) ); TRACE_EVENT(ext4_mb_release_group_pa, TP_PROTO(struct super_block *sb, struct ext4_prealloc_space *pa), TP_ARGS(sb, pa), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u64, pa_pstart ) __field( __u32, pa_len ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->pa_pstart = pa->pa_pstart; __entry->pa_len = pa->pa_len; ), TP_printk("dev %d,%d pstart %llu len %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->pa_pstart, __entry->pa_len) ); TRACE_EVENT(ext4_discard_preallocations, TP_PROTO(struct inode *inode, unsigned int len, unsigned int needed), TP_ARGS(inode, len, needed), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, len ) __field( unsigned int, needed ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->len = len; __entry->needed = needed; ), TP_printk("dev %d,%d ino %lu len: %u needed %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->len, __entry->needed) ); TRACE_EVENT(ext4_mb_discard_preallocations, TP_PROTO(struct super_block *sb, int needed), TP_ARGS(sb, needed), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, needed ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->needed = needed; ), TP_printk("dev %d,%d needed %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->needed) ); TRACE_EVENT(ext4_request_blocks, TP_PROTO(struct ext4_allocation_request *ar), TP_ARGS(ar), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, len ) __field( __u32, logical ) __field( __u32, lleft ) __field( __u32, lright ) __field( __u64, goal ) __field( __u64, pleft ) __field( __u64, pright ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->dev = ar->inode->i_sb->s_dev; __entry->ino = ar->inode->i_ino; __entry->len = ar->len; __entry->logical = ar->logical; __entry->goal = ar->goal; __entry->lleft = ar->lleft; __entry->lright = ar->lright; __entry->pleft = ar->pleft; __entry->pright = ar->pright; __entry->flags = ar->flags; ), TP_printk("dev %d,%d ino %lu flags %s len %u lblk %u goal %llu " "lleft %u lright %u pleft %llu pright %llu ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, show_mballoc_flags(__entry->flags), __entry->len, __entry->logical, __entry->goal, __entry->lleft, __entry->lright, __entry->pleft, __entry->pright) ); TRACE_EVENT(ext4_allocate_blocks, TP_PROTO(struct ext4_allocation_request *ar, unsigned long long block), TP_ARGS(ar, block), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( unsigned int, len ) __field( __u32, logical ) __field( __u32, lleft ) __field( __u32, lright ) __field( __u64, goal ) __field( __u64, pleft ) __field( __u64, pright ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->dev = ar->inode->i_sb->s_dev; __entry->ino = ar->inode->i_ino; __entry->block = block; __entry->len = ar->len; __entry->logical = ar->logical; __entry->goal = ar->goal; __entry->lleft = ar->lleft; __entry->lright = ar->lright; __entry->pleft = ar->pleft; __entry->pright = ar->pright; __entry->flags = ar->flags; ), TP_printk("dev %d,%d ino %lu flags %s len %u block %llu lblk %u " "goal %llu lleft %u lright %u pleft %llu pright %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, show_mballoc_flags(__entry->flags), __entry->len, __entry->block, __entry->logical, __entry->goal, __entry->lleft, __entry->lright, __entry->pleft, __entry->pright) ); TRACE_EVENT(ext4_free_blocks, TP_PROTO(struct inode *inode, __u64 block, unsigned long count, int flags), TP_ARGS(inode, block, count, flags), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( unsigned long, count ) __field( int, flags ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->block = block; __entry->count = count; __entry->flags = flags; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o block %llu count %lu flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->block, __entry->count, show_free_flags(__entry->flags)) ); TRACE_EVENT(ext4_sync_file_enter, TP_PROTO(struct file *file, int datasync), TP_ARGS(file, datasync), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, parent ) __field( int, datasync ) ), TP_fast_assign( struct dentry *dentry = file->f_path.dentry; __entry->dev = dentry->d_sb->s_dev; __entry->ino = d_inode(dentry)->i_ino; __entry->datasync = datasync; __entry->parent = d_inode(dentry->d_parent)->i_ino; ), TP_printk("dev %d,%d ino %lu parent %lu datasync %d ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->parent, __entry->datasync) ); TRACE_EVENT(ext4_sync_file_exit, TP_PROTO(struct inode *inode, int ret), TP_ARGS(inode, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ret = ret; ), TP_printk("dev %d,%d ino %lu ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret) ); TRACE_EVENT(ext4_sync_fs, TP_PROTO(struct super_block *sb, int wait), TP_ARGS(sb, wait), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, wait ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->wait = wait; ), TP_printk("dev %d,%d wait %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->wait) ); TRACE_EVENT(ext4_alloc_da_blocks, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, data_blocks ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->data_blocks = EXT4_I(inode)->i_reserved_data_blocks; ), TP_printk("dev %d,%d ino %lu reserved_data_blocks %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->data_blocks) ); TRACE_EVENT(ext4_mballoc_alloc, TP_PROTO(struct ext4_allocation_context *ac), TP_ARGS(ac), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u32, orig_logical ) __field( int, orig_start ) __field( __u32, orig_group ) __field( int, orig_len ) __field( __u32, goal_logical ) __field( int, goal_start ) __field( __u32, goal_group ) __field( int, goal_len ) __field( __u32, result_logical ) __field( int, result_start ) __field( __u32, result_group ) __field( int, result_len ) __field( __u16, found ) __field( __u16, groups ) __field( __u16, buddy ) __field( __u16, flags ) __field( __u16, tail ) __field( __u8, cr ) ), TP_fast_assign( __entry->dev = ac->ac_inode->i_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->orig_logical = ac->ac_o_ex.fe_logical; __entry->orig_start = ac->ac_o_ex.fe_start; __entry->orig_group = ac->ac_o_ex.fe_group; __entry->orig_len = ac->ac_o_ex.fe_len; __entry->goal_logical = ac->ac_g_ex.fe_logical; __entry->goal_start = ac->ac_g_ex.fe_start; __entry->goal_group = ac->ac_g_ex.fe_group; __entry->goal_len = ac->ac_g_ex.fe_len; __entry->result_logical = ac->ac_f_ex.fe_logical; __entry->result_start = ac->ac_f_ex.fe_start; __entry->result_group = ac->ac_f_ex.fe_group; __entry->result_len = ac->ac_f_ex.fe_len; __entry->found = ac->ac_found; __entry->flags = ac->ac_flags; __entry->groups = ac->ac_groups_scanned; __entry->buddy = ac->ac_buddy; __entry->tail = ac->ac_tail; __entry->cr = ac->ac_criteria; ), TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u goal %u/%d/%u@%u " "result %u/%d/%u@%u blks %u grps %u cr %u flags %s " "tail %u broken %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->orig_group, __entry->orig_start, __entry->orig_len, __entry->orig_logical, __entry->goal_group, __entry->goal_start, __entry->goal_len, __entry->goal_logical, __entry->result_group, __entry->result_start, __entry->result_len, __entry->result_logical, __entry->found, __entry->groups, __entry->cr, show_mballoc_flags(__entry->flags), __entry->tail, __entry->buddy ? 1 << __entry->buddy : 0) ); TRACE_EVENT(ext4_mballoc_prealloc, TP_PROTO(struct ext4_allocation_context *ac), TP_ARGS(ac), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u32, orig_logical ) __field( int, orig_start ) __field( __u32, orig_group ) __field( int, orig_len ) __field( __u32, result_logical ) __field( int, result_start ) __field( __u32, result_group ) __field( int, result_len ) ), TP_fast_assign( __entry->dev = ac->ac_inode->i_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->orig_logical = ac->ac_o_ex.fe_logical; __entry->orig_start = ac->ac_o_ex.fe_start; __entry->orig_group = ac->ac_o_ex.fe_group; __entry->orig_len = ac->ac_o_ex.fe_len; __entry->result_logical = ac->ac_b_ex.fe_logical; __entry->result_start = ac->ac_b_ex.fe_start; __entry->result_group = ac->ac_b_ex.fe_group; __entry->result_len = ac->ac_b_ex.fe_len; ), TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u result %u/%d/%u@%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->orig_group, __entry->orig_start, __entry->orig_len, __entry->orig_logical, __entry->result_group, __entry->result_start, __entry->result_len, __entry->result_logical) ); DECLARE_EVENT_CLASS(ext4__mballoc, TP_PROTO(struct super_block *sb, struct inode *inode, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, inode, group, start, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, result_start ) __field( __u32, result_group ) __field( int, result_len ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ino = inode ? inode->i_ino : 0; __entry->result_start = start; __entry->result_group = group; __entry->result_len = len; ), TP_printk("dev %d,%d inode %lu extent %u/%d/%d ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->result_group, __entry->result_start, __entry->result_len) ); DEFINE_EVENT(ext4__mballoc, ext4_mballoc_discard, TP_PROTO(struct super_block *sb, struct inode *inode, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, inode, group, start, len) ); DEFINE_EVENT(ext4__mballoc, ext4_mballoc_free, TP_PROTO(struct super_block *sb, struct inode *inode, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, inode, group, start, len) ); TRACE_EVENT(ext4_forget, TP_PROTO(struct inode *inode, int is_metadata, __u64 block), TP_ARGS(inode, is_metadata, block), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( int, is_metadata ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->block = block; __entry->is_metadata = is_metadata; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o is_metadata %d block %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->is_metadata, __entry->block) ); TRACE_EVENT(ext4_da_update_reserve_space, TP_PROTO(struct inode *inode, int used_blocks, int quota_claim), TP_ARGS(inode, used_blocks, quota_claim), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, i_blocks ) __field( int, used_blocks ) __field( int, reserved_data_blocks ) __field( int, quota_claim ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->i_blocks = inode->i_blocks; __entry->used_blocks = used_blocks; __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->quota_claim = quota_claim; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d " "reserved_data_blocks %d quota_claim %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->i_blocks, __entry->used_blocks, __entry->reserved_data_blocks, __entry->quota_claim) ); TRACE_EVENT(ext4_da_reserve_space, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, i_blocks ) __field( int, reserved_data_blocks ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->i_blocks = inode->i_blocks; __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu " "reserved_data_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->i_blocks, __entry->reserved_data_blocks) ); TRACE_EVENT(ext4_da_release_space, TP_PROTO(struct inode *inode, int freed_blocks), TP_ARGS(inode, freed_blocks), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, i_blocks ) __field( int, freed_blocks ) __field( int, reserved_data_blocks ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->i_blocks = inode->i_blocks; __entry->freed_blocks = freed_blocks; __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu freed_blocks %d " "reserved_data_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->i_blocks, __entry->freed_blocks, __entry->reserved_data_blocks) ); DECLARE_EVENT_CLASS(ext4__bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; ),