summaryrefslogtreecommitdiffstats
path: root/source4/scripting/python/uuidmodule.c
diff options
context:
space:
mode:
authorAndrew Bartlett <abartlet@samba.org>2012-04-16 15:36:15 +1000
committerAndrew Bartlett <abartlet@samba.org>2012-04-18 12:05:00 +1000
commitce9676839b50ad34cead8f7f02488272a2bb3c85 (patch)
tree0adee5acee5cdd3d04de1b2b7ce8c7eb4bca42b9 /source4/scripting/python/uuidmodule.c
parentea5a9b21fb384524c8370c6d7a712b35e170fd06 (diff)
downloadsamba-ce9676839b50ad34cead8f7f02488272a2bb3c85.tar.gz
samba-ce9676839b50ad34cead8f7f02488272a2bb3c85.tar.xz
samba-ce9676839b50ad34cead8f7f02488272a2bb3c85.zip
s3-lib: Add file_id_string()
Diffstat (limited to 'source4/scripting/python/uuidmodule.c')
0 files changed, 0 insertions, 0 deletions
generated by cgit (git 2.34.1) at 2026-01-12 06:38:53 +0000
119'>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 
/* libguestfs
 * Copyright (C) 2009-2010 Red Hat Inc.
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#include <config.h>

#define _BSD_SOURCE /* for mkdtemp, usleep */

#include <stdio.h>
#include <stdlib.h>
#include <stdarg.h>
#include <stddef.h>
#include <stdint.h>
#include <inttypes.h>
#include <unistd.h>
#include <string.h>
#include <fcntl.h>
#include <time.h>
#include <sys/stat.h>
#include <sys/select.h>
#include <dirent.h>
#include <signal.h>

#include <rpc/types.h>
#include <rpc/xdr.h>

#ifdef HAVE_ERRNO_H
#include <errno.h>
#endif

#ifdef HAVE_SYS_TYPES_H
#include <sys/types.h>
#endif

#ifdef HAVE_SYS_WAIT_H
#include <sys/wait.h>
#endif

#ifdef HAVE_SYS_SOCKET_H
#include <sys/socket.h>
#endif

#ifdef HAVE_SYS_UN_H
#include <sys/un.h>
#endif

#include <arpa/inet.h>
#include <netinet/in.h>

#include "c-ctype.h"
#include "glthread/lock.h"
#include "ignore-value.h"

#include "guestfs.h"
#include "guestfs-internal.h"
#include "guestfs-internal-actions.h"
#include "guestfs_protocol.h"

#ifdef HAVE_GETTEXT
#include "gettext.h"
#define _(str) dgettext(PACKAGE, (str))
//#define N_(str) dgettext(PACKAGE, (str))
#else
#define _(str) str
//#define N_(str) str
#endif

#define error guestfs_error
#define perrorf guestfs_perrorf
#define safe_malloc guestfs_safe_malloc
#define safe_realloc guestfs_safe_realloc
#define safe_strdup guestfs_safe_strdup
//#define safe_memdup guestfs_safe_memdup

#ifdef __linux__
#define CAN_CHECK_PEER_EUID 1
#else
#define CAN_CHECK_PEER_EUID 0
#endif

static void default_error_cb (guestfs_h *g, void *data, const char *msg);
static int send_to_daemon (guestfs_h *g, const void *v_buf, size_t n);
static int recv_from_daemon (guestfs_h *g, uint32_t *size_rtn, void **buf_rtn);
static int accept_from_daemon (guestfs_h *g);
static int check_peer_euid (guestfs_h *g, int sock, uid_t *rtn);
static void close_handles (void);
static int qemu_supports (guestfs_h *g, const char *option);

#define UNIX_PATH_MAX 108

#ifndef MAX
#define MAX(a,b) ((a)>(b)?(a):(b))
#endif

#ifdef __APPLE__
#define xdr_uint32_t xdr_u_int32_t
#endif

/* Network configuration of the appliance.  Note these addresses are
 * only meaningful within the context of the running appliance.  QEMU
 * translates network connections to these magic addresses into
 * userspace calls on the host (eg. connect(2)).  qemu-doc has a nice
 * diagram which is also useful to refer to.
 *
 * NETWORK: The network.
 *
 * ROUTER: The address of the "host", ie. this library.
 *
 * [Note: If you change NETWORK and ROUTER then you also have to
 * change the network configuration in appliance/init].
 *
 * GUESTFWD_ADDR, GUESTFWD_PORT: The guestfwd feature of qemu
 * magically connects this pseudo-address to the guestfwd channel.  In
 * typical Linux configurations of libguestfs, guestfwd is not
 * actually used any more.
 */
#define NETWORK "169.254.0.0/16"
#define ROUTER "169.254.2.2"
#define GUESTFWD_ADDR "169.254.2.4"
#define GUESTFWD_PORT "6666"

/* GuestFS handle and connection. */
enum state { CONFIG, LAUNCHING, READY, BUSY, NO_HANDLE };

struct guestfs_h
{
  struct guestfs_h *next;	/* Linked list of open handles. */

  /* State: see the state machine diagram in the man page guestfs(3). */
  enum state state;

  int fd[2];			/* Stdin/stdout of qemu. */
  int sock;			/* Daemon communications socket. */
  pid_t pid;			/* Qemu PID. */
  pid_t recoverypid;		/* Recovery process PID. */

  struct timeval launch_t;      /* The time that we called guestfs_launch. */

  char *tmpdir;			/* Temporary directory containing socket. */

  char *qemu_help, *qemu_version; /* Output of qemu -help, qemu -version. */

  char **cmdline;		/* Qemu command line. */
  int cmdline_size;

  int verbose;
  int trace;
  int autosync;
  int direct;
  int recovery_proc;

  char *path;			/* Path to kernel, initrd. */
  char *qemu;			/* Qemu binary. */
  char *append;			/* Append to kernel command line. */

  int memsize;			/* Size of RAM (megabytes). */

  int selinux;                  /* selinux enabled? */

  char *last_error;

  /* Callbacks. */
  guestfs_abort_cb           abort_cb;
  guestfs_error_handler_cb   error_cb;
  void *                     error_cb_data;
  guestfs_log_message_cb     log_message_cb;
  void *                     log_message_cb_data;
  guestfs_subprocess_quit_cb subprocess_quit_cb;
  void *                     subprocess_quit_cb_data;
  guestfs_launch_done_cb     launch_done_cb;
  void *                     launch_done_cb_data;
  guestfs_close_cb           close_cb;
  void *                     close_cb_data;

  int msg_next_serial;
};

gl_lock_define_initialized (static, handles_lock);
static guestfs_h *handles = NULL;
static int atexit_handler_set = 0;

guestfs_h *
guestfs_create (void)
{
  guestfs_h *g;
  const char *str;

  g = malloc (sizeof (*g));
  if (!g) return NULL;

  memset (g, 0, sizeof (*g));

  g->state = CONFIG;

  g->fd[0] = -1;
  g->fd[1] = -1;
  g->sock = -1;

  g->abort_cb = abort;
  g->error_cb = default_error_cb;
  g->error_cb_data = NULL;

  g->recovery_proc = 1;

  str = getenv ("LIBGUESTFS_DEBUG");
  g->verbose = str != NULL && STREQ (str, "1");

  str = getenv ("LIBGUESTFS_TRACE");
  g->trace = str != NULL && STREQ (str, "1");

  str = getenv ("LIBGUESTFS_PATH");
  g->path = str != NULL ? strdup (str) : strdup (GUESTFS_DEFAULT_PATH);
  if (!g->path) goto error;

  str = getenv ("LIBGUESTFS_QEMU");
  g->qemu = str != NULL ? strdup (str) : strdup (QEMU);
  if (!g->qemu) goto error;

  str = getenv ("LIBGUESTFS_APPEND");
  if (str) {
    g->append = strdup (str);
    if (!g->append) goto error;
  }

  /* Choose a suitable memory size.  Previously we tried to choose
   * a minimal memory size, but this isn't really necessary since
   * recent QEMU and KVM don't do anything nasty like locking
   * memory into core any more.  Thus we can safely choose a
   * large, generous amount of memory, and it'll just get swapped
   * on smaller systems.
   */
  str = getenv ("LIBGUESTFS_MEMSIZE");
  if (str) {
    if (sscanf (str, "%d", &g->memsize) != 1 || g->memsize <= 256) {
      fprintf (stderr, "libguestfs: non-numeric or too small value for LIBGUESTFS_MEMSIZE\n");
      goto error;
    }
  } else
    g->memsize = 500;

  /* Start with large serial numbers so they are easy to spot
   * inside the protocol.
   */
  g->msg_next_serial = 0x00123400;

  /* Link the handles onto a global list. */
  gl_lock_lock (handles_lock);
  g->next = handles;
  handles = g;
  if (!atexit_handler_set) {
    atexit (close_handles);
    atexit_handler_set = 1;
  }
  gl_lock_unlock (handles_lock);

  if (g->verbose)
    fprintf (stderr, "new guestfs handle %p\n", g);

  return g;

 error:
  free (g->path);
  free (g->qemu);
  free (g->append);
  free (g);
  return NULL;
}

void
guestfs_close (guestfs_h *g)
{
  int i;
  char filename[256];
  guestfs_h *gg;

  if (g->state == NO_HANDLE) {
    /* Not safe to call 'error' here, so ... */
    fprintf (stderr, _("guestfs_close: called twice on the same handle\n"));
    return;
  }

  if (g->verbose)
    fprintf (stderr, "closing guestfs handle %p (state %d)\n", g, g->state);

  /* Run user close callback before anything else. */
  if (g->close_cb)
    g->close_cb (g, g->close_cb_data);

  /* Try to sync if autosync flag is set. */
  if (g->autosync && g->state == READY) {
    guestfs_umount_all (g);
    guestfs_sync (g);
  }

  /* Remove any handlers that might be called back before we kill the
   * subprocess.
   */
  g->log_message_cb = NULL;

  if (g->state != CONFIG)
    guestfs_kill_subprocess (g);

  /* Close sockets. */
  if (g->fd[0] >= 0)
    close (g->fd[0]);
  if (g->fd[1] >= 0)
    close (g->fd[1]);
  if (g->sock >= 0)
    close (g->sock);
  g->fd[0] = -1;
  g->fd[1] = -1;
  g->sock = -1;

  /* Wait for subprocess(es) to exit. */
  waitpid (g->pid, NULL, 0);
  if (g->recoverypid > 0) waitpid (g->recoverypid, NULL, 0);

  /* Remove tmpfiles. */
  if (g->tmpdir) {
    snprintf (filename, sizeof filename, "%s/sock", g->tmpdir);
    unlink (filename);

    snprintf (filename, sizeof filename, "%s/initrd", g->tmpdir);
    unlink (filename);

    snprintf (filename, sizeof filename, "%s/kernel", g->tmpdir);
    unlink (filename);

    rmdir (g->tmpdir);

    free (g->tmpdir);
  }

  if (g->cmdline) {
    for (i = 0; i < g->cmdline_size; ++i)
      free (g->cmdline[i]);
    free (g->cmdline);
  }

  /* Mark the handle as dead before freeing it. */
  g->state = NO_HANDLE;

  gl_lock_lock (handles_lock);
  if (handles == g)
    handles = g->next;
  else {
    for (gg = handles; gg->next != g; gg = gg->next)
      ;
    gg->next = g->next;
  }
  gl_lock_unlock (handles_lock);

  free (g->last_error);
  free (g->path);
  free (g->qemu);
  free (g->append);
  free (g->qemu_help);
  free (g->qemu_version);
  free (g);
}

/* Close all open handles (called from atexit(3)). */
static void
close_handles (void)
{
  while (handles) guestfs_close (handles);
}

const char *
guestfs_last_error (guestfs_h *g)
{
  return g->last_error;
}

static void
set_last_error (guestfs_h *g, const char *msg)
{
  free (g->last_error);
  g->last_error = strdup (msg);
}

static void
default_error_cb (guestfs_h *g, void *data, const char *msg)
{
  fprintf (stderr, _("libguestfs: error: %s\n"), msg);
}

void
guestfs_error (guestfs_h *g, const char *fs, ...)
{
  va_list args;
  char *msg;

  va_start (args, fs);
  int err = vasprintf (&msg, fs, args);
  va_end (args);

  if (err < 0) return;

  if (g->error_cb) g->error_cb (g, g->error_cb_data, msg);
  set_last_error (g, msg);

  free (msg);
}

void
guestfs_perrorf (guestfs_h *g, const char *fs, ...)
{
  va_list args;
  char *msg;
  int errnum = errno;

  va_start (args, fs);
  int err = vasprintf (&msg, fs, args);
  va_end (args);

  if (err < 0) return;

#if !defined(_GNU_SOURCE) || defined(__APPLE__)
  char buf[256];
  strerror_r (errnum, buf, sizeof buf);
#else
  char _buf[256];
  char *buf;
  buf = strerror_r (errnum, _buf, sizeof _buf);
#endif

  msg = safe_realloc (g, msg, strlen (msg) + 2 + strlen (buf) + 1);
  strcat (msg, ": ");
  strcat (msg, buf);

  if (g->error_cb) g->error_cb (g, g->error_cb_data, msg);
  set_last_error (g, msg);

  free (msg);
}

void *
guestfs_safe_malloc (guestfs_h *g, size_t nbytes)
{
  void *ptr = malloc (nbytes);
  if (nbytes > 0 && !ptr) g->abort_cb ();
  return ptr;
}

/* Return 1 if an array of N objects, each of size S, cannot exist due
   to size arithmetic overflow.  S must be positive and N must be
   nonnegative.  This is a macro, not an inline function, so that it
   works correctly even when SIZE_MAX < N.

   By gnulib convention, SIZE_MAX represents overflow in size
   calculations, so the conservative dividend to use here is
   SIZE_MAX - 1, since SIZE_MAX might represent an overflowed value.
   However, malloc (SIZE_MAX) fails on all known hosts where
   sizeof (ptrdiff_t) <= sizeof (size_t), so do not bother to test for
   exactly-SIZE_MAX allocations on such hosts; this avoids a test and
   branch when S is known to be 1.  */
# define xalloc_oversized(n, s) \
    ((size_t) (sizeof (ptrdiff_t) <= sizeof (size_t) ? -1 : -2) / (s) < (n))

/* Technically we should add an autoconf test for this, testing for the desired
   functionality, like what's done in gnulib, but for now, this is fine.  */
#if defined(__GLIBC__)
#define HAVE_GNU_CALLOC (__GLIBC__ >= 2)
#else
#define HAVE_GNU_CALLOC 0
#endif

/* Allocate zeroed memory for N elements of S bytes, with error
   checking.  S must be nonzero.  */
void *
guestfs_safe_calloc (guestfs_h *g, size_t n, size_t s)
{
  /* From gnulib's calloc function in xmalloc.c.  */
  void *p;
  /* Test for overflow, since some calloc implementations don't have
     proper overflow checks.  But omit overflow and size-zero tests if
     HAVE_GNU_CALLOC, since GNU calloc catches overflow and never
     returns NULL if successful.  */
  if ((! HAVE_GNU_CALLOC && xalloc_oversized (n, s))
      || (! (p = calloc (n, s)) && (HAVE_GNU_CALLOC || n != 0)))
    g->abort_cb ();
  return p;
}

void *
guestfs_safe_realloc (guestfs_h *g, void *ptr, int nbytes)
{
  void *p = realloc (ptr, nbytes);
  if (nbytes > 0 && !p) g->abort_cb ();
  return p;
}

char *
guestfs_safe_strdup (guestfs_h *g, const char *str)
{
  char *s = strdup (str);
  if (!s) g->abort_cb ();
  return s;
}

void *
guestfs_safe_memdup (guestfs_h *g, void *ptr, size_t size)
{
  void *p = malloc (size);
  if (!p) g->abort_cb ();
  memcpy (p, ptr, size);
  return p;
}

static int
xwrite (int fd, const void *v_buf, size_t len)
{
  const char *buf = v_buf;
  int r;

  while (len > 0) {
    r = write (fd, buf, len);
    if (r == -1)
      return -1;

    buf += r;
    len -= r;
  }

  return 0;
}

void
guestfs_set_out_of_memory_handler (guestfs_h *g, guestfs_abort_cb cb)
{
  g->abort_cb = cb;
}

guestfs_abort_cb
guestfs_get_out_of_memory_handler (guestfs_h *g)
{
  return g->abort_cb;
}

void
guestfs_set_error_handler (guestfs_h *g, guestfs_error_handler_cb cb, void *data)
{
  g->error_cb = cb;
  g->error_cb_data = data;
}

guestfs_error_handler_cb
guestfs_get_error_handler (guestfs_h *g, void **data_rtn)
{
  if (data_rtn) *data_rtn = g->error_cb_data;
  return g->error_cb;
}

int
guestfs__set_verbose (guestfs_h *g, int v)
{
  g->verbose = !!v;
  return 0;
}

int
guestfs__get_verbose (guestfs_h *g)
{
  return g->verbose;
}

int
guestfs__set_autosync (guestfs_h *g, int a)
{
  g->autosync = !!a;
  return 0;
}

int
guestfs__get_autosync (guestfs_h *g)
{
  return g->autosync;
}

int
guestfs__set_path (guestfs_h *g, const char *path)
{
  free (g->path);
  g->path = NULL;

  g->path =
    path == NULL ?
    safe_strdup (g, GUESTFS_DEFAULT_PATH) : safe_strdup (g, path);
  return 0;
}

const char *
guestfs__get_path (guestfs_h *g)
{
  return g->path;
}

int
guestfs__set_qemu (guestfs_h *g, const char *qemu)
{
  free (g->qemu);
  g->qemu = NULL;

  g->qemu = qemu == NULL ? safe_strdup (g, QEMU) : safe_strdup (g, qemu);
  return 0;
}

const char *
guestfs__get_qemu (guestfs_h *g)
{
  return g->qemu;
}

int
guestfs__set_append (guestfs_h *g, const char *append)
{
  free (g->append);
  g->append = NULL;

  g->append = append ? safe_strdup (g, append) : NULL;
  return 0;
}

const char *
guestfs__get_append (guestfs_h *g)
{
  return g->append;
}

int
guestfs__set_memsize (guestfs_h *g, int memsize)
{
  g->memsize = memsize;
  return 0;
}

int
guestfs__get_memsize (guestfs_h *g)
{
  return g->memsize;
}

int
guestfs__set_selinux (guestfs_h *g, int selinux)
{
  g->selinux = selinux;
  return 0;
}

int
guestfs__get_selinux (guestfs_h *g)
{
  return g->selinux;
}

int
guestfs__get_pid (guestfs_h *g)
{
  if (g->pid > 0)
    return g->pid;
  else {
    error (g, "get_pid: no qemu subprocess");
    return -1;
  }
}

struct guestfs_version *
guestfs__version (guestfs_h *g)
{
  struct guestfs_version *r;

  r = safe_malloc (g, sizeof *r);
  r->major = PACKAGE_VERSION_MAJOR;
  r->minor = PACKAGE_VERSION_MINOR;
  r->release = PACKAGE_VERSION_RELEASE;
  r->extra = safe_strdup (g, PACKAGE_VERSION_EXTRA);
  return r;
}

int
guestfs__set_trace (guestfs_h *g, int t)
{
  g->trace = !!t;
  return 0;
}

int
guestfs__get_trace (guestfs_h *g)
{
  return g->trace;
}

int
guestfs__set_direct (guestfs_h *g, int d)
{
  g->direct = !!d;
  return 0;
}

int
guestfs__get_direct (guestfs_h *g)
{
  return g->direct;
}

int
guestfs__set_recovery_proc (guestfs_h *g, int f)
{
  g->recovery_proc = !!f;
  return 0;
}

int
guestfs__get_recovery_proc (guestfs_h *g)
{
  return g->recovery_proc;
}

/* Add a string to the current command line. */
static void
incr_cmdline_size (guestfs_h *g)
{
  if (g->cmdline == NULL) {
    /* g->cmdline[0] is reserved for argv[0], set in guestfs_launch. */
    g->cmdline_size = 1;
    g->cmdline = safe_malloc (g, sizeof (char *));
    g->cmdline[0] = NULL;
  }

  g->cmdline_size++;
  g->cmdline = safe_realloc (g, g->cmdline, sizeof (char *) * g->cmdline_size);
}

static int
add_cmdline (guestfs_h *g, const char *str)
{
  if (g->state != CONFIG) {
    error (g,
        _("command line cannot be altered after qemu subprocess launched"));
    return -1;
  }

  incr_cmdline_size (g);
  g->cmdline[g->cmdline_size-1] = safe_strdup (g, str);
  return 0;
}

int
guestfs__config (guestfs_h *g,
                 const char *qemu_param, const char *qemu_value)
{
  if (qemu_param[0] != '-') {
    error (g, _("guestfs_config: parameter must begin with '-' character"));
    return -1;
  }

  /* A bit fascist, but the user will probably break the extra
   * parameters that we add if they try to set any of these.
   */
  if (STREQ (qemu_param, "-kernel") ||
      STREQ (qemu_param, "-initrd") ||
      STREQ (qemu_param, "-nographic") ||
      STREQ (qemu_param, "-serial") ||
      STREQ (qemu_param, "-full-screen") ||
      STREQ (qemu_param, "-std-vga") ||
      STREQ (qemu_param, "-vnc")) {
    error (g, _("guestfs_config: parameter '%s' isn't allowed"), qemu_param);
    return -1;
  }

  if (add_cmdline (g, qemu_param) != 0) return -1;

  if (qemu_value != NULL) {
    if (add_cmdline (g, qemu_value) != 0) return -1;
  }

  return 0;
}

int
guestfs__add_drive_with_if (guestfs_h *g, const char *filename,
                            const char *drive_if)
{
  size_t len = strlen (filename) + 64;
  char buf[len];

  if (strchr (filename, ',') != NULL) {
    error (g, _("filename cannot contain ',' (comma) character"));
    return -1;
  }

  /* cache=off improves reliability in the event of a host crash.
   *
   * However this option causes qemu to try to open the file with
   * O_DIRECT.  This fails on some filesystem types (notably tmpfs).
   * So we check if we can open the file with or without O_DIRECT,
   * and use cache=off (or not) accordingly.
   *
   * This test also checks for the presence of the file, which
   * is a documented semantic of this interface.
   */
  int fd = open (filename, O_RDONLY|O_DIRECT);
  if (fd >= 0) {
    close (fd);
    snprintf (buf, len, "file=%s,cache=off,if=%s", filename, drive_if);
  } else {
    fd = open (filename, O_RDONLY);
    if (fd >= 0) {
      close (fd);
      snprintf (buf, len, "file=%s,if=%s", filename, drive_if);
    } else {
      perrorf (g, "%s", filename);
      return -1;
    }
  }

  return guestfs__config (g, "-drive", buf);
}

int
guestfs__add_drive_ro_with_if (guestfs_h *g, const char *filename,
                               const char *drive_if)
{
  if (strchr (filename, ',') != NULL) {
    error (g, _("filename cannot contain ',' (comma) character"));
    return -1;
  }

  if (access (filename, F_OK) == -1) {
    perrorf (g, "%s", filename);
    return -1;
  }

  if (qemu_supports (g, NULL) == -1)
    return -1;

  /* Only SCSI and virtio drivers support readonly mode.
   * This is only supported as a QEMU feature since 2010/01.
   */
  int supports_ro = 0;
  if ((STREQ (drive_if, "scsi") || STREQ (drive_if, "virtio")) &&
      qemu_supports (g, "readonly=on"))
    supports_ro = 1;

  size_t len = strlen (filename) + 100;
  char buf[len];

  snprintf (buf, len, "file=%s,snapshot=on,%sif=%s",
            filename,
            supports_ro ? "readonly=on," : "",
            drive_if);

  return guestfs__config (g, "-drive", buf);
}

int
guestfs__add_drive (guestfs_h *g, const char *filename)
{
  return guestfs__add_drive_with_if (g, filename, DRIVE_IF);
}

int
guestfs__add_drive_ro (guestfs_h *g, const char *filename)
{
  return guestfs__add_drive_ro_with_if (g, filename, DRIVE_IF);
}

int
guestfs__add_cdrom (guestfs_h *g, const char *filename)
{
  if (strchr (filename, ',') != NULL) {
    error (g, _("filename cannot contain ',' (comma) character"));
    return -1;
  }

  if (access (filename, F_OK) == -1) {
    perrorf (g, "%s", filename);
    return -1;
  }

  return guestfs__config (g, "-cdrom", filename);
}

/* Returns true iff file is contained in dir. */
static int
dir_contains_file (const char *dir, const char *file)
{
  int dirlen = strlen (dir);
  int filelen = strlen (file);
  int len = dirlen+filelen+2;
  char path[len];

  snprintf (path, len, "%s/%s", dir, file);
  return access (path, F_OK) == 0;
}

/* Returns true iff every listed file is contained in 'dir'. */
static int
dir_contains_files (const char *dir, ...)
{
  va_list args;
  const char *file;

  va_start (args, dir);
  while ((file = va_arg (args, const char *)) != NULL) {
    if (!dir_contains_file (dir, file)) {
      va_end (args);
      return 0;
    }
  }
  va_end (args);
  return 1;
}

static void print_timestamped_message (guestfs_h *g, const char *fs, ...);
static int build_supermin_appliance (guestfs_h *g, const char *path, char **kernel, char **initrd);
static int is_openable (guestfs_h *g, const char *path, int flags);
static void print_cmdline (guestfs_h *g);

static const char *kernel_name = "vmlinuz." REPO "." host_cpu;
static const char *initrd_name = "initramfs." REPO "." host_cpu ".img";

int
guestfs__launch (guestfs_h *g)
{
  const char *tmpdir;
  char dir_template[PATH_MAX];
  int r, pmore;
  size_t len;
  int wfd[2], rfd[2];
  int tries;
  char *path, *pelem, *pend;
  char *kernel = NULL, *initrd = NULL;
  int null_vmchannel_sock;
  char unixsock[256];
  struct sockaddr_un addr;

  /* Configured? */
  if (!g->cmdline) {
    error (g, _("you must call guestfs_add_drive before guestfs_launch"));
    return -1;
  }

  if (g->state != CONFIG) {
    error (g, _("the libguestfs handle has already been launched"));
    return -1;
  }

  /* Start the clock ... */
  gettimeofday (&g->launch_t, NULL);

  /* Make the temporary directory. */
#ifdef P_tmpdir
  tmpdir = P_tmpdir;
#else
  tmpdir = "/tmp";
#endif

  tmpdir = getenv ("TMPDIR") ? : tmpdir;
  snprintf (dir_template, sizeof dir_template, "%s/libguestfsXXXXXX", tmpdir);

  if (!g->tmpdir) {
    g->tmpdir = safe_strdup (g, dir_template);
    if (mkdtemp (g->tmpdir) == NULL) {
      perrorf (g, _("%s: cannot create temporary directory"), dir_template);
      goto cleanup0;
    }
  }

  /* First search g->path for the supermin appliance, and try to
   * synthesize a kernel and initrd from that.  If it fails, we
   * try the path search again looking for a backup ordinary
   * appliance.
   */
  pelem = path = safe_strdup (g, g->path);
  do {
    pend = strchrnul (pelem, ':');
    pmore = *pend == ':';
    *pend = '\0';
    len = pend - pelem;

    /* Empty element of "." means cwd. */
    if (len == 0 || (len == 1 && *pelem == '.')) {
      if (g->verbose)
        fprintf (stderr,
                 "looking for supermin appliance in current directory\n");
      if (dir_contains_files (".",
                              "supermin.d", "kmod.whitelist", NULL)) {
        if (build_supermin_appliance (g, ".", &kernel, &initrd) == -1)
          return -1;
        break;
      }
    }
    /* Look at <path>/supermin* etc. */
    else {
      if (g->verbose)
        fprintf (stderr, "looking for supermin appliance in %s\n", pelem);

      if (dir_contains_files (pelem,
                              "supermin.d", "kmod.whitelist", NULL)) {
        if (build_supermin_appliance (g, pelem, &kernel, &initrd) == -1)
          return -1;
        break;
      }
    }

    pelem = pend + 1;
  } while (pmore);

  free (path);

  if (kernel == NULL || initrd == NULL) {
    /* Search g->path for the kernel and initrd. */
    pelem = path = safe_strdup (g, g->path);
    do {
      pend = strchrnul (pelem, ':');
      pmore = *pend == ':';
      *pend = '\0';
      len = pend - pelem;

      /* Empty element or "." means cwd. */
      if (len == 0 || (len == 1 && *pelem == '.')) {
        if (g->verbose)
          fprintf (stderr,
                   "looking for appliance in current directory\n");
        if (dir_contains_files (".", kernel_name, initrd_name, NULL)) {
          kernel = safe_strdup (g, kernel_name);
          initrd = safe_strdup (g, initrd_name);
          break;
        }
      }
      /* Look at <path>/kernel etc. */
      else {
        if (g->verbose)
          fprintf (stderr, "looking for appliance in %s\n", pelem);

        if (dir_contains_files (pelem, kernel_name, initrd_name, NULL)) {
          kernel = safe_malloc (g, len + strlen (kernel_name) + 2);
          initrd = safe_malloc (g, len + strlen (initrd_name) + 2);
          sprintf (kernel, "%s/%s", pelem, kernel_name);
          sprintf (initrd, "%s/%s", pelem, initrd_name);
          break;
        }
      }

      pelem = pend + 1;
    } while (pmore);

    free (path);
  }

  if (kernel == NULL || initrd == NULL) {
    error (g, _("cannot find %s or %s on LIBGUESTFS_PATH (current path = %s)"),
           kernel_name, initrd_name, g->path);
    goto cleanup0;
  }

  if (g->verbose)
    print_timestamped_message (g, "begin testing qemu features");

  /* Get qemu help text and version. */
  if (qemu_supports (g, NULL) == -1)
    goto cleanup0;

  /* Choose which vmchannel implementation to use. */
  if (CAN_CHECK_PEER_EUID && qemu_supports (g, "-net user")) {
    /* The "null vmchannel" implementation.  Requires SLIRP (user mode
     * networking in qemu) but no other vmchannel support.  The daemon
     * will connect back to a random port number on localhost.
     */
    struct sockaddr_in addr;
    socklen_t addrlen = sizeof addr;

    g->sock = socket (AF_INET, SOCK_STREAM, IPPROTO_TCP);
    if (g->sock == -1) {
      perrorf (g, "socket");
      goto cleanup0;
    }
    addr.sin_family = AF_INET;
    addr.sin_port = htons (0);
    addr.sin_addr.s_addr = htonl (INADDR_LOOPBACK);
    if (bind (g->sock, (struct sockaddr *) &addr, addrlen) == -1) {
      perrorf (g, "bind");
      goto cleanup0;
    }

    if (listen (g->sock, 256) == -1) {
      perrorf (g, "listen");
      goto cleanup0;
    }

    if (getsockname (g->sock, (struct sockaddr *) &addr, &addrlen) == -1) {
      perrorf (g, "getsockname");
      goto cleanup0;
    }

    if (fcntl (g->sock, F_SETFL, O_NONBLOCK) == -1) {
      perrorf (g, "fcntl");
      goto cleanup0;
    }

    null_vmchannel_sock = ntohs (addr.sin_port);
    if (g->verbose)
      fprintf (stderr, "null_vmchannel_sock = %d\n", null_vmchannel_sock);
  } else {
    /* Using some vmchannel impl.  We need to create a local Unix
     * domain socket for qemu to use.
     */
    snprintf (unixsock, sizeof unixsock, "%s/sock", g->tmpdir);
    unlink (unixsock);
    null_vmchannel_sock = 0;
  }

  if (!g->direct) {
    if (pipe (wfd) == -1 || pipe (rfd) == -1) {
      perrorf (g, "pipe");
      goto cleanup0;
    }
  }

  if (g->verbose)
    print_timestamped_message (g, "finished testing qemu features");

  r = fork ();
  if (r == -1) {
    perrorf (g, "fork");
    if (!g->direct) {
      close (wfd[0]);
      close (wfd[1]);
      close (rfd[0]);
      close (rfd[1]);
    }
    goto cleanup0;
  }

  if (r == 0) {			/* Child (qemu). */
    char buf[256];
    const char *vmchannel = NULL;

    /* Set up the full command line.  Do this in the subprocess so we
     * don't need to worry about cleaning up.
     */
    g->cmdline[0] = g->qemu;

    /* qemu sometimes needs this option to enable hardware
     * virtualization, but some versions of 'qemu-kvm' will use KVM
     * regardless (even where this option appears in the help text).
     * It is rumoured that there are versions of qemu where supplying
     * this option when hardware virtualization is not available will
     * cause qemu to fail, so we we have to check at least that
     * /dev/kvm is openable.  That's not reliable, since /dev/kvm
     * might be openable by qemu but not by us (think: SELinux) in
     * which case the user would not get hardware virtualization,
     * although at least shouldn't fail.  A giant clusterfuck with the
     * qemu command line, again.
     */
    if (qemu_supports (g, "-enable-kvm") &&
        is_openable (g, "/dev/kvm", O_RDWR))
      add_cmdline (g, "-enable-kvm");

    /* Newer versions of qemu (from around 2009/12) changed the
     * behaviour of monitors so that an implicit '-monitor stdio' is
     * assumed if we are in -nographic mode and there is no other
     * -monitor option.  Only a single stdio device is allowed, so
     * this broke the '-serial stdio' option.  There is a new flag
     * called -nodefaults which gets rid of all this default crud, so
     * let's use that to avoid this and any future surprises.
     */
    if (qemu_supports (g, "-nodefaults"))
      add_cmdline (g, "-nodefaults");

    add_cmdline (g, "-nographic");
    add_cmdline (g, "-serial");
    add_cmdline (g, "stdio");

    snprintf (buf, sizeof buf, "%d", g->memsize);
    add_cmdline (g, "-m");
    add_cmdline (g, buf);

    /* Force exit instead of reboot on panic */
    add_cmdline (g, "-no-reboot");

    /* These options recommended by KVM developers to improve reliability. */
    if (qemu_supports (g, "-no-hpet"))
      add_cmdline (g, "-no-hpet");

    if (qemu_supports (g, "-rtc-td-hack"))
      add_cmdline (g, "-rtc-td-hack");

    /* If qemu has SLIRP (user mode network) enabled then we can get
     * away with "no vmchannel", where we just connect back to a random
     * host port.
     */
    if (null_vmchannel_sock) {
      add_cmdline (g, "-net");
      add_cmdline (g, "user,vlan=0,net=" NETWORK);

      snprintf (buf, sizeof buf,
                "guestfs_vmchannel=tcp:" ROUTER ":%d",
                null_vmchannel_sock);
      vmchannel = strdup (buf);
    }

    /* New-style -net user,guestfwd=... syntax for guestfwd.  See:
     *
     * http://git.savannah.gnu.org/cgit/qemu.git/commit/?id=c92ef6a22d3c71538fcc48fb61ad353f7ba03b62
     *
     * The original suggested format doesn't work, see:
     *
     * http://lists.gnu.org/archive/html/qemu-devel/2009-07/msg01654.html
     *
     * However Gerd Hoffman privately suggested to me using -chardev
     * instead, which does work.
     */
    else if (qemu_supports (g, "-chardev") && qemu_supports (g, "guestfwd")) {
      snprintf (buf, sizeof buf,
                "socket,id=guestfsvmc,path=%s,server,nowait", unixsock);

      add_cmdline (g, "-chardev");
      add_cmdline (g, buf);

      snprintf (buf, sizeof buf,
                "user,vlan=0,net=" NETWORK ","
                "guestfwd=tcp:" GUESTFWD_ADDR ":" GUESTFWD_PORT
                "-chardev:guestfsvmc");

      add_cmdline (g, "-net");
      add_cmdline (g, buf);

      vmchannel = "guestfs_vmchannel=tcp:" GUESTFWD_ADDR ":" GUESTFWD_PORT;
    }

    /* Not guestfwd.  HOPEFULLY this qemu uses the older -net channel
     * syntax, or if not then we'll get a quick failure.
     */
    else {
      snprintf (buf, sizeof buf,
                "channel," GUESTFWD_PORT ":unix:%s,server,nowait", unixsock);

      add_cmdline (g, "-net");
      add_cmdline (g, buf);
      add_cmdline (g, "-net");
      add_cmdline (g, "user,vlan=0,net=" NETWORK);

      vmchannel = "guestfs_vmchannel=tcp:" GUESTFWD_ADDR ":" GUESTFWD_PORT;
    }
    add_cmdline (g, "-net");
    add_cmdline (g, "nic,model=" NET_IF ",vlan=0");

#define LINUX_CMDLINE							\
    "panic=1 "         /* force kernel to panic if daemon exits */	\
    "console=ttyS0 "   /* serial console */				\
    "udevtimeout=300 " /* good for very slow systems (RHBZ#480319) */	\
    "noapic "          /* workaround for RHBZ#502058 - ok if not SMP */ \
    "acpi=off "        /* we don't need ACPI, turn it off */		\
    "printk.time=1 "   /* display timestamp before kernel messages */   \
    "cgroup_disable=memory " /* saves us about 5 MB of RAM */

    /* Linux kernel command line. */
    snprintf (buf, sizeof buf,
              LINUX_CMDLINE
              "%s "             /* (selinux) */
              "%s "             /* (vmchannel) */
              "%s "             /* (verbose) */
              "TERM=%s "        /* (TERM environment variable) */
              "%s",             /* (append) */
              g->selinux ? "selinux=1 enforcing=0" : "selinux=0",
              vmchannel ? vmchannel : "",
              g->verbose ? "guestfs_verbose=1" : "",
              getenv ("TERM") ? : "linux",
              g->append ? g->append : "");

    add_cmdline (g, "-kernel");
    add_cmdline (g, (char *) kernel);
    add_cmdline (g, "-initrd");
    add_cmdline (g, (char *) initrd);
    add_cmdline (g, "-append");
    add_cmdline (g, buf);

    /* Finish off the command line. */
    incr_cmdline_size (g);
    g->cmdline[g->cmdline_size-1] = NULL;

    if (g->verbose)
      print_cmdline (g);

    if (!g->direct) {
      /* Set up stdin, stdout. */
      close (0);
      close (1);
      close (wfd[1]);
      close (rfd[0]);

      if (dup (wfd[0]) == -1) {
      dup_failed:
        perror ("dup failed");
        _exit (EXIT_FAILURE);
      }
      if (dup (rfd[1]) == -1)
        goto dup_failed;

      close (wfd[0]);
      close (rfd[1]);
    }

#if 0
    /* Set up a new process group, so we can signal this process
     * and all subprocesses (eg. if qemu is really a shell script).
     */
    setpgid (0, 0);
#endif

    setenv ("LC_ALL", "C", 1);

    execv (g->qemu, g->cmdline); /* Run qemu. */
    perror (g->qemu);
    _exit (EXIT_FAILURE);
  }

  /* Parent (library). */
  g->pid = r;

  free (kernel);
  kernel = NULL;
  free (initrd);
  initrd = NULL;

  /* Fork the recovery process off which will kill qemu if the parent
   * process fails to do so (eg. if the parent segfaults).
   */
  g->recoverypid = -1;
  if (g->recovery_proc) {
    r = fork ();
    if (r == 0) {
      pid_t qemu_pid = g->pid;
      pid_t parent_pid = getppid ();

      /* Writing to argv is hideously complicated and error prone.  See:
       * http://anoncvs.postgresql.org/cvsweb.cgi/pgsql/src/backend/utils/misc/ps_status.c?rev=1.33.2.1;content-type=text%2Fplain
       */

      /* Loop around waiting for one or both of the other processes to
       * disappear.  It's fair to say this is very hairy.  The PIDs that
       * we are looking at might be reused by another process.  We are
       * effectively polling.  Is the cure worse than the disease?
       */
      for (;;) {
        if (kill (qemu_pid, 0) == -1) /* qemu's gone away, we aren't needed */
          _exit (EXIT_SUCCESS);
        if (kill (parent_pid, 0) == -1) {
          /* Parent's gone away, qemu still around, so kill qemu. */
          kill (qemu_pid, 9);
          _exit (EXIT_SUCCESS);
        }
        sleep (2);
      }
    }

    /* Don't worry, if the fork failed, this will be -1.  The recovery
     * process isn't essential.
     */
    g->recoverypid = r;
  }

  if (!g->direct) {
    /* Close the other ends of the pipe. */
    close (wfd[0]);
    close (rfd[1]);

    if (fcntl (wfd[1], F_SETFL, O_NONBLOCK) == -1 ||
        fcntl (rfd[0], F_SETFL, O_NONBLOCK) == -1) {
      perrorf (g, "fcntl");
      goto cleanup1;
    }

    g->fd[0] = wfd[1];		/* stdin of child */
    g->fd[1] = rfd[0];		/* stdout of child */
  } else {
    g->fd[0] = open ("/dev/null", O_RDWR);
    if (g->fd[0] == -1) {
      perrorf (g, "open /dev/null");
      goto cleanup1;
    }
    g->fd[1] = dup (g->fd[0]);
    if (g->fd[1] == -1) {
      perrorf (g, "dup");
      close (g->fd[0]);
      goto cleanup1;
    }
  }

  if (null_vmchannel_sock) {
    int sock = -1;
    uid_t uid;

    /* Null vmchannel implementation: We listen on g->sock for a
     * connection.  The connection could come from any local process
     * so we must check it comes from the appliance (or at least
     * from our UID) for security reasons.
     */
    while (sock == -1) {
      sock = accept_from_daemon (g);
      if (sock == -1)
        goto cleanup1;

      if (check_peer_euid (g, sock, &uid) == -1)
        goto cleanup1;
      if (uid != geteuid ()) {
        fprintf (stderr,
                 "libguestfs: warning: unexpected connection from UID %d to port %d\n",
                 uid, null_vmchannel_sock);
        close (sock);
        sock = -1;
        continue;
      }
    }

    if (fcntl (sock, F_SETFL, O_NONBLOCK) == -1) {
      perrorf (g, "fcntl");
      goto cleanup1;
    }

    close (g->sock);
    g->sock = sock;
  } else {
    /* Other vmchannel.  Open the Unix socket.
     *
     * The vmchannel implementation that got merged with qemu sucks in
     * a number of ways.  Both ends do connect(2), which means that no
     * one knows what, if anything, is connected to the other end, or
     * if it becomes disconnected.  Even worse, we have to wait some
     * indeterminate time for qemu to create the socket and connect to
     * it (which happens very early in qemu's start-up), so any code
     * that uses vmchannel is inherently racy.  Hence this silly loop.
     */
    g->sock = socket (AF_UNIX, SOCK_STREAM, 0);
    if (g->sock == -1) {
      perrorf (g, "socket");
      goto cleanup1;
    }

    if (fcntl (g->sock, F_SETFL, O_NONBLOCK) == -1) {
      perrorf (g, "fcntl");
      goto cleanup1;
    }

    addr.sun_family = AF_UNIX;
    strncpy (addr.sun_path, unixsock, UNIX_PATH_MAX);
    addr.sun_path[UNIX_PATH_MAX-1] = '\0';

    tries = 100;
    /* Always sleep at least once to give qemu a small chance to start up. */
    usleep (10000);
    while (tries > 0) {
      r = connect (g->sock, (struct sockaddr *) &addr, sizeof addr);
      if ((r == -1 && errno == EINPROGRESS) || r == 0)
        goto connected;

      if (errno != ENOENT)
        perrorf (g, "connect");
      tries--;
      usleep (100000);
    }

    error (g, _("failed to connect to vmchannel socket"));
    goto cleanup1;

  connected: ;
  }

  g->state = LAUNCHING;

  /* Wait for qemu to start and to connect back to us via vmchannel and
   * send the GUESTFS_LAUNCH_FLAG message.
   */
  uint32_t size;
  void *buf = NULL;
  r = recv_from_daemon (g, &size, &buf);
  free (buf);

  if (r == -1) return -1;

  if (size != GUESTFS_LAUNCH_FLAG) {
    error (g, _("guestfs_launch failed, see earlier error messages"));
    goto cleanup1;
  }

  if (g->verbose)
    print_timestamped_message (g, "appliance is up");

  /* This is possible in some really strange situations, such as
   * guestfsd starts up OK but then qemu immediately exits.  Check for
   * it because the caller is probably expecting to be able to send
   * commands after this function returns.
   */
  if (g->state != READY) {
    error (g, _("qemu launched and contacted daemon, but state != READY"));
    goto cleanup1;
  }

  return 0;

 cleanup1:
  if (!g->direct) {
    close (wfd[1]);
    close (rfd[0]);
  }
  if (g->pid > 0) kill (g->pid, 9);
  if (g->recoverypid > 0) kill (g->recoverypid, 9);
  waitpid (g->pid, NULL, 0);
  if (g->recoverypid > 0) waitpid (g->recoverypid, NULL, 0);
  g->fd[0] = -1;
  g->fd[1] = -1;
  g->pid = 0;
  g->recoverypid = 0;
  memset (&g->launch_t, 0, sizeof g->launch_t);

 cleanup0:
  if (g->sock >= 0) {
    close (g->sock);
    g->sock = -1;
  }
  g->state = CONFIG;
  free (kernel);
  free (initrd);
  return -1;
}

/* This function is used to print the qemu command line before it gets
 * executed, when in verbose mode.
 */
static void
print_cmdline (guestfs_h *g)
{
  int i = 0;
  int needs_quote;

  while (g->cmdline[i]) {
    if (g->cmdline[i][0] == '-') /* -option starts a new line */
      fprintf (stderr, " \\\n   ");

    if (i > 0) fputc (' ', stderr);

    /* Does it need shell quoting?  This only deals with simple cases. */
    needs_quote = strcspn (g->cmdline[i], " ") != strlen (g->cmdline[i]);

    if (needs_quote) fputc ('\'', stderr);
    fprintf (stderr, "%s", g->cmdline[i]);
    if (needs_quote) fputc ('\'', stderr);
    i++;
  }

  fputc ('\n', stderr);
}

/* This function does the hard work of building the supermin appliance
 * on the fly.  'path' is the directory containing the control files.
 * 'kernel' and 'initrd' are where we will return the names of the
 * kernel and initrd (only initrd is built).  The work is done by
 * an external script.  We just tell it where to put the result.
 */
static int
build_supermin_appliance (guestfs_h *g, const char *path,
                          char **kernel, char **initrd)
{
  char cmd[4096];
  int r, len;

  if (g->verbose)
    print_timestamped_message (g, "begin building supermin appliance");

  len = strlen (g->tmpdir);
  *kernel = safe_malloc (g, len + 8);
  snprintf (*kernel, len+8, "%s/kernel", g->tmpdir);
  *initrd = safe_malloc (g, len + 8);
  snprintf (*initrd, len+8, "%s/initrd", g->tmpdir);

  snprintf (cmd, sizeof cmd,
            "febootstrap-supermin-helper%s "
            "-k '%s/kmod.whitelist' "
            "'%s/supermin.d' "
            host_cpu " "
            "%s %s",
            g->verbose ? " --verbose" : "",
            path,
            path,
            *kernel, *initrd);
  if (g->verbose)
    print_timestamped_message (g, "%s", cmd);

  r = system (cmd);
  if (r == -1 || WEXITSTATUS(r) != 0) {
    error (g, _("external command failed: %s"), cmd);
    free (*kernel);
    free (*initrd);
    *kernel = *initrd = NULL;
    return -1;
  }

  if (g->verbose)
    print_timestamped_message (g, "finished building supermin appliance");

  return 0;
}

/* Compute Y - X and return the result in milliseconds.
 * Approximately the same as this code:
 * http://www.mpp.mpg.de/~huber/util/timevaldiff.c
 */
static int64_t
timeval_diff (const struct timeval *x, const struct timeval *y)
{
  int64_t msec;

  msec = (y->tv_sec - x->tv_sec) * 1000;
  msec += (y->tv_usec - x->tv_usec) / 1000;
  return msec;
}

static void
print_timestamped_message (guestfs_h *g, const char *fs, ...)
{
  va_list args;
  char *msg;
  int err;
  struct timeval tv;

  va_start (args, fs);
  err = vasprintf (&msg, fs, args);
  va_end (args);

  if (err < 0) return;

  gettimeofday (&tv, NULL);

  fprintf (stderr, "[%05" PRIi64 "ms] %s\n",
           timeval_diff (&g->launch_t, &tv), msg);

  free (msg);
}

static int read_all (guestfs_h *g, FILE *fp, char **ret);

/* Test qemu binary (or wrapper) runs, and do 'qemu -help' and
 * 'qemu -version' so we know what options this qemu supports and
 * the version.
 */
static int
test_qemu (guestfs_h *g)
{
  char cmd[1024];
  FILE *fp;

  snprintf (cmd, sizeof cmd, "LC_ALL=C '%s' -nographic -help", g->qemu);

  fp = popen (cmd, "r");
  /* qemu -help should always work (qemu -version OTOH wasn't
   * supported by qemu 0.9).  If this command doesn't work then it
   * probably indicates that the qemu binary is missing.
   */
  if (!fp) {
    /* XXX This error is never printed, even if the qemu binary
     * doesn't exist.  Why?
     */
  error:
    perrorf (g, _("%s: command failed: If qemu is located on a non-standard path, try setting the LIBGUESTFS_QEMU environment variable."), cmd);
    return -1;
  }

  if (read_all (g, fp, &g->qemu_help) == -1)
    goto error;

  if (pclose (fp) == -1)
    goto error;

  snprintf (cmd, sizeof cmd, "LC_ALL=C '%s' -nographic -version 2>/dev/null",
	    g->qemu);

  fp = popen (cmd, "r");
  if (fp) {
    /* Intentionally ignore errors. */
    read_all (g, fp, &g->qemu_version);
    pclose (fp);
  }

  return 0;
}

static int
read_all (guestfs_h *g, FILE *fp, char **ret)
{
  int r, n = 0;
  char *p;

 again:
  if (feof (fp)) {
    *ret = safe_realloc (g, *ret, n + 1);
    (*ret)[n] = '\0';
    return n;
  }

  *ret = safe_realloc (g, *ret, n + BUFSIZ);
  p = &(*ret)[n];
  r = fread (p, 1, BUFSIZ, fp);
  if (ferror (fp)) {
    perrorf (g, "read");
    return -1;
  }
  n += r;
  goto again;
}

/* Test if option is supported by qemu command line (just by grepping
 * the help text).
 *
 * The first time this is used, it has to run the external qemu
 * binary.  If that fails, it returns -1.
 *
 * To just do the first-time run of the qemu binary, call this with
 * option == NULL, in which case it will return -1 if there was an
 * error doing that.
 */
static int
qemu_supports (guestfs_h *g, const char *option)
{
  if (!g->qemu_help) {
    if (test_qemu (g) == -1)
      return -1;
  }

  if (option == NULL)
    return 1;

  return strstr (g->qemu_help, option) != NULL;
}

/* Check if a file can be opened. */
static int
is_openable (guestfs_h *g, const char *path, int flags)
{
  int fd = open (path, flags);
  if (fd == -1) {
    if (g->verbose)
      perror (path);
    return 0;
  }
  close (fd);
  return 1;
}

/* Check the peer effective UID for a TCP socket.  Ideally we'd like
 * SO_PEERCRED for a loopback TCP socket.  This isn't possible on
 * Linux (but it is on Solaris!) so we read /proc/net/tcp instead.
 */
static int
check_peer_euid (guestfs_h *g, int sock, uid_t *rtn)
{
#if CAN_CHECK_PEER_EUID
  struct sockaddr_in peer;
  socklen_t addrlen = sizeof peer;

  if (getpeername (sock, (struct sockaddr *) &peer, &addrlen) == -1) {
    perrorf (g, "getpeername");
    return -1;
  }

  if (peer.sin_family != AF_INET ||
      ntohl (peer.sin_addr.s_addr) != INADDR_LOOPBACK) {
    error (g, "check_peer_euid: unexpected connection from non-IPv4, non-loopback peer (family = %d, addr = %s)",
           peer.sin_family, inet_ntoa (peer.sin_addr));
    return -1;
  }

  struct sockaddr_in our;
  addrlen = sizeof our;
  if (getsockname (sock, (struct sockaddr *) &our, &addrlen) == -1) {
    perrorf (g, "getsockname");
    return -1;
  }

  FILE *fp = fopen ("/proc/net/tcp", "r");
  if (fp == NULL) {
    perrorf (g, "/proc/net/tcp");
    return -1;
  }

  char line[256];
  if (fgets (line, sizeof line, fp) == NULL) { /* Drop first line. */
    error (g, "unexpected end of file in /proc/net/tcp");
    fclose (fp);
    return -1;
  }

  while (fgets (line, sizeof line, fp) != NULL) {
    unsigned line_our_addr, line_our_port, line_peer_addr, line_peer_port;
    int dummy0, dummy1, dummy2, dummy3, dummy4, dummy5, dummy6;
    int line_uid;

    if (sscanf (line, "%d:%08X:%04X %08X:%04X %02X %08X:%08X %02X:%08X %08X %d",
                &dummy0,
                &line_our_addr, &line_our_port,
                &line_peer_addr, &line_peer_port,
                &dummy1, &dummy2, &dummy3, &dummy4, &dummy5, &dummy6,
                &line_uid) == 12) {
      /* Note about /proc/net/tcp: local_address and rem_address are
       * always in network byte order.  However the port part is
       * always in host byte order.
       *
       * The sockname and peername that we got above are in network
       * byte order.  So we have to byte swap the port but not the
       * address part.
       */
      if (line_our_addr == our.sin_addr.s_addr &&
          line_our_port == ntohs (our.sin_port) &&
          line_peer_addr == peer.sin_addr.s_addr &&
          line_peer_port == ntohs (peer.sin_port)) {
        *rtn = line_uid;
        fclose (fp);
        return 0;
      }
    }
  }

  error (g, "check_peer_euid: no matching TCP connection found in /proc/net/tcp");
  fclose (fp);
  return -1;
#else /* !CAN_CHECK_PEER_EUID */
  /* This function exists but should never be called in this
   * configuration.
   */
  abort ();
#endif /* !CAN_CHECK_PEER_EUID */
}

/* You had to call this function after launch in versions <= 1.0.70,
 * but it is now a no-op.
 */
int
guestfs__wait_ready (guestfs_h *g)
{
  if (g->state != READY)  {
    error (g, _("qemu has not been launched yet"));
    return -1;
  }

  return 0;
}

int
guestfs__kill_subprocess (guestfs_h *g)
{
  if (g->state == CONFIG) {
    error (g, _("no subprocess to kill"));
    return -1;
  }

  if (g->verbose)
    fprintf (stderr, "sending SIGTERM to process %d\n", g->pid);

  if (g->pid > 0) kill (g->pid, SIGTERM);
  if (g->recoverypid > 0) kill (g->recoverypid, 9);

  return 0;
}

/* Access current state. */
int
guestfs__is_config (guestfs_h *g)
{
  return g->state == CONFIG;
}

int
guestfs__is_launching (guestfs_h *g)
{
  return g->state == LAUNCHING;
}

int
guestfs__is_ready (guestfs_h *g)
{
  return g->state == READY;
}

int
guestfs__is_busy (guestfs_h *g)
{
  return g->state == BUSY;
}

int
guestfs__get_state (guestfs_h *g)
{
  return g->state;
}

void
guestfs_set_log_message_callback (guestfs_h *g,
                                  guestfs_log_message_cb cb, void *opaque)
{
  g->log_message_cb = cb;
  g->log_message_cb_data = opaque;
}

void
guestfs_set_subprocess_quit_callback (guestfs_h *g,
                                      guestfs_subprocess_quit_cb cb, void *opaque)
{
  g->subprocess_quit_cb = cb;
  g->subprocess_quit_cb_data = opaque;
}

void
guestfs_set_launch_done_callback (guestfs_h *g,
                                  guestfs_launch_done_cb cb, void *opaque)
{
  g->launch_done_cb = cb;
  g->launch_done_cb_data = opaque;
}

void
guestfs_set_close_callback (guestfs_h *g,
                            guestfs_close_cb cb, void *opaque)
{
  g->close_cb = cb;
  g->close_cb_data = opaque;
}

/*----------------------------------------------------------------------*/

/* This is the code used to send and receive RPC messages and (for
 * certain types of message) to perform file transfers.  This code is
 * driven from the generated actions (src/guestfs-actions.c).  There
 * are five different cases to consider:
 *
 * (1) A non-daemon function.  There is no RPC involved at all, it's
 * all handled inside the library.
 *
 * (2) A simple RPC (eg. "mount").  We write the request, then read
 * the reply.  The sequence of calls is:
 *
 *   guestfs___set_busy
 *   guestfs___send
 *   guestfs___recv
 *   guestfs___end_busy
 *
 * (3) An RPC with FileOut parameters (eg. "upload").  We write the
 * request, then write the file(s), then read the reply.  The sequence
 * of calls is:
 *
 *   guestfs___set_busy
 *   guestfs___send
 *   guestfs___send_file  (possibly multiple times)
 *   guestfs___recv
 *   guestfs___end_busy
 *
 * (4) An RPC with FileIn parameters (eg. "download").  We write the
 * request, then read the reply, then read the file(s).  The sequence
 * of calls is:
 *
 *   guestfs___set_busy
 *   guestfs___send
 *   guestfs___recv
 *   guestfs___recv_file  (possibly multiple times)
 *   guestfs___end_busy
 *
 * (5) Both FileOut and FileIn parameters.  There are no calls like
 * this in the current API, but they would be implemented as a
 * combination of cases (3) and (4).
 *
 * During all writes and reads, we also select(2) on qemu stdout
 * looking for messages (guestfsd stderr and guest kernel dmesg), and
 * anything received is passed up through the log_message_cb.  This is
 * also the reason why all the sockets are non-blocking.  We also have
 * to check for EOF (qemu died).  All of this is handled by the
 * functions send_to_daemon and recv_from_daemon.
 */

int
guestfs___set_busy (guestfs_h *g)
{
  if (g->state != READY) {
    error (g, _("guestfs_set_busy: called when in state %d != READY"),
           g->state);
    return -1;
  }
  g->state = BUSY;
  return 0;
}

int
guestfs___end_busy (guestfs_h *g)
{
  switch (g->state)
    {
    case BUSY:
      g->state = READY;
      break;
    case CONFIG:
    case READY:
      break;

    case LAUNCHING:
    case NO_HANDLE:
    default:
      error (g, _("guestfs_end_busy: called when in state %d"), g->state);
      return -1;
    }
  return 0;
}

/* This is called if we detect EOF, ie. qemu died. */
static void
child_cleanup (guestfs_h *g)
{
  if (g->verbose)
    fprintf (stderr, "child_cleanup: %p: child process died\n", g);

  /*if (g->pid > 0) kill (g->pid, SIGTERM);*/
  if (g->recoverypid > 0) kill (g->recoverypid, 9);
  waitpid (g->pid, NULL, 0);
  if (g->recoverypid > 0) waitpid (g->recoverypid, NULL, 0);
  close (g->fd[0]);
  close (g->fd[1]);
  close (g->sock);
  g->fd[0] = -1;
  g->fd[1] = -1;
  g->sock = -1;
  g->pid = 0;
  g->recoverypid = 0;
  memset (&g->launch_t, 0, sizeof g->launch_t);
  g->state = CONFIG;
  if (g->subprocess_quit_cb)
    g->subprocess_quit_cb (g, g->subprocess_quit_cb_data);
}

static int
read_log_message_or_eof (guestfs_h *g, int fd, int error_if_eof)
{
  char buf[BUFSIZ];
  int n;

#if 0
  if (g->verbose)
    fprintf (stderr,
             "read_log_message_or_eof: %p g->state = %d, fd = %d\n",
             g, g->state, fd);
#endif

  /* QEMU's console emulates a 16550A serial port.  The real 16550A
   * device has a small FIFO buffer (16 bytes) which means here we see
   * lots of small reads of 1-16 bytes in length, usually single
   * bytes.
   */
  n = read (fd, buf, sizeof buf);
  if (n == 0) {
    /* Hopefully this indicates the qemu child process has died. */
    child_cleanup (g);

    if (error_if_eof) {
      /* We weren't expecting eof here (called from launch) so place
       * something in the error buffer.  RHBZ#588851.
       */
      error (g, "child process died unexpectedly");
    }
    return -1;
  }

  if (n == -1) {
    if (errno == EINTR || errno == EAGAIN)
      return 0;

    perrorf (g, "read");
    return -1;
  }

  /* In verbose mode, copy all log messages to stderr. */
  if (g->verbose)
    ignore_value (write (STDERR_FILENO, buf, n));

  /* It's an actual log message, send it upwards if anyone is listening. */
  if (g->log_message_cb)
    g->log_message_cb (g, g->log_message_cb_data, buf, n);

  return 0;
}

static int
check_for_daemon_cancellation_or_eof (guestfs_h *g, int fd)
{
  char buf[4];
  int n;
  uint32_t flag;
  XDR xdr;

  if (g->verbose)
    fprintf (stderr,
             "check_for_daemon_cancellation_or_eof: %p g->state = %d, fd = %d\n",
             g, g->state, fd);

  n = read (fd, buf, 4);
  if (n == 0) {
    /* Hopefully this indicates the qemu child process has died. */
    child_cleanup (g);
    return -1;
  }

  if (n == -1) {
    if (errno == EINTR || errno == EAGAIN)
      return 0;

    perrorf (g, "read");
    return -1;
  }

  xdrmem_create (&xdr, buf, 4, XDR_DECODE);
  xdr_uint32_t (&xdr, &flag);
  xdr_destroy (&xdr);

  if (flag != GUESTFS_CANCEL_FLAG) {
    error (g, _("check_for_daemon_cancellation_or_eof: read 0x%x from daemon, expected 0x%x\n"),
           flag, GUESTFS_CANCEL_FLAG);
    return -1;
  }

  return -2;
}

/* This writes the whole N bytes of BUF to the daemon socket.
 *
 * If the whole write is successful, it returns 0.
 * If there was an error, it returns -1.
 * If the daemon sent a cancellation message, it returns -2.
 *
 * It also checks qemu stdout for log messages and passes those up
 * through log_message_cb.
 *
 * It also checks for EOF (qemu died) and passes that up through the
 * child_cleanup function above.
 */
static int
send_to_daemon (guestfs_h *g, const void *v_buf, size_t n)
{
  const char *buf = v_buf;
  fd_set rset, rset2;
  fd_set wset, wset2;

  if (g->verbose)
    fprintf (stderr,
             "send_to_daemon: %p g->state = %d, n = %zu\n", g, g->state, n);

  FD_ZERO (&rset);
  FD_ZERO (&wset);

  FD_SET (g->fd[1], &rset);     /* Read qemu stdout for log messages & EOF. */
  FD_SET (g->sock, &rset);      /* Read socket for cancellation & EOF. */
  FD_SET (g->sock, &wset);      /* Write to socket to send the data. */

  int max_fd = MAX (g->sock, g->fd[1]);

  while (n > 0) {
    rset2 = rset;
    wset2 = wset;
    int r = select (max_fd+1, &rset2, &wset2, NULL, NULL);
    if (r == -1) {
      if (errno == EINTR || errno == EAGAIN)
        continue;
      perrorf (g, "select");
      return -1;
    }

    if (FD_ISSET (g->fd[1], &rset2)) {
      if (read_log_message_or_eof (g, g->fd[1], 0) == -1)
        return -1;
    }
    if (FD_ISSET (g->sock, &rset2)) {
      r = check_for_daemon_cancellation_or_eof (g, g->sock);
      if (r < 0)
        return r;
    }
    if (FD_ISSET (g->sock, &wset2)) {
      r = write (g->sock, buf, n);
      if (r == -1) {
        if (errno == EINTR || errno == EAGAIN)
          continue;
        perrorf (g, "write");
        if (errno == EPIPE) /* Disconnected from guest (RHBZ#508713). */
          child_cleanup (g);
        return -1;
      }
      buf += r;
      n -= r;
    }
  }

  return 0;
}

/* This reads a single message, file chunk, launch flag or
 * cancellation flag from the daemon.  If something was read, it
 * returns 0, otherwise -1.
 *
 * Both size_rtn and buf_rtn must be passed by the caller as non-NULL.
 *
 * *size_rtn returns the size of the returned message or it may be
 * GUESTFS_LAUNCH_FLAG or GUESTFS_CANCEL_FLAG.
 *
 * *buf_rtn is returned containing the message (if any) or will be set
 * to NULL.  *buf_rtn must be freed by the caller.
 *
 * It also checks qemu stdout for log messages and passes those up
 * through log_message_cb.
 *
 * It also checks for EOF (qemu died) and passes that up through the
 * child_cleanup function above.
 */
static int
recv_from_daemon (guestfs_h *g, uint32_t *size_rtn, void **buf_rtn)
{
  fd_set rset, rset2;

  if (g->verbose)
    fprintf (stderr,
             "recv_from_daemon: %p g->state = %d, size_rtn = %p, buf_rtn = %p\n",
             g, g->state, size_rtn, buf_rtn);

  FD_ZERO (&rset);

  FD_SET (g->fd[1], &rset);     /* Read qemu stdout for log messages & EOF. */
  FD_SET (g->sock, &rset);      /* Read socket for data & EOF. */

  int max_fd = MAX (g->sock, g->fd[1]);

  *size_rtn = 0;
  *buf_rtn = NULL;

  char lenbuf[4];
  /* nr is the size of the message, but we prime it as -4 because we
   * have to read the message length word first.
   */
  ssize_t nr = -4;

  while (nr < (ssize_t) *size_rtn) {
    rset2 = rset;
    int r = select (max_fd+1, &rset2, NULL, NULL, NULL);
    if (r == -1) {
      if (errno == EINTR || errno == EAGAIN)
        continue;
      perrorf (g, "select");
      free (*buf_rtn);
      *buf_rtn = NULL;
      return -1;
    }

    if (FD_ISSET (g->fd[1], &rset2)) {
      if (read_log_message_or_eof (g, g->fd[1], 0) == -1) {
        free (*buf_rtn);
        *buf_rtn = NULL;
        return -1;
      }
    }
    if (FD_ISSET (g->sock, &rset2)) {
      if (nr < 0) {    /* Have we read the message length word yet? */
        r = read (g->sock, lenbuf+nr+4, -nr);
        if (r == -1) {
          if (errno == EINTR || errno == EAGAIN)
            continue;
          int err = errno;
          perrorf (g, "read");
          /* Under some circumstances we see "Connection reset by peer"
           * here when the child dies suddenly.  Catch this and call
           * the cleanup function, same as for EOF.
           */
          if (err == ECONNRESET)
            child_cleanup (g);
          return -1;
        }
        if (r == 0) {
          error (g, _("unexpected end of file when reading from daemon"));
          child_cleanup (g);
          return -1;
        }
        nr += r;

        if (nr < 0)         /* Still not got the whole length word. */
          continue;

        XDR xdr;
        xdrmem_create (&xdr, lenbuf, 4, XDR_DECODE);
        xdr_uint32_t (&xdr, size_rtn);
        xdr_destroy (&xdr);

        if (*size_rtn == GUESTFS_LAUNCH_FLAG) {
          if (g->state != LAUNCHING)
            error (g, _("received magic signature from guestfsd, but in state %d"),
                   g->state);
          else {
            g->state = READY;
            if (g->launch_done_cb)
              g->launch_done_cb (g, g->launch_done_cb_data);
          }
          return 0;
        }
        else if (*size_rtn == GUESTFS_CANCEL_FLAG)
          return 0;
        /* If this happens, it's pretty bad and we've probably lost
         * synchronization.
         */
        else if (*size_rtn > GUESTFS_MESSAGE_MAX) {
          error (g, _("message length (%u) > maximum possible size (%d)"),
                 (unsigned) *size_rtn, GUESTFS_MESSAGE_MAX);
          return -1;
        }

        /* Allocate the complete buffer, size now known. */
        *buf_rtn = safe_malloc (g, *size_rtn);
        /*FALLTHROUGH*/
      }

      size_t sizetoread = *size_rtn - nr;
      if (sizetoread > BUFSIZ) sizetoread = BUFSIZ;

      r = read (g->sock, (char *) (*buf_rtn) + nr, sizetoread);
      if (r == -1) {
        if (errno == EINTR || errno == EAGAIN)
          continue;
        perrorf (g, "read");
        free (*buf_rtn);
        *buf_rtn = NULL;
        return -1;
      }
      if (r == 0) {
        error (g, _("unexpected end of file when reading from daemon"));
        child_cleanup (g);
        free (*buf_rtn);
        *buf_rtn = NULL;
        return -1;
      }
      nr += r;
    }
  }

  /* Got the full message, caller can start processing it. */
#ifdef ENABLE_PACKET_DUMP
  if (g->verbose) {
    ssize_t i, j;

    for (i = 0; i < nr; i += 16) {
      printf ("%04zx: ", i);
      for (j = i; j < MIN (i+16, nr); ++j)
        printf ("%02x ", (*(unsigned char **)buf_rtn)[j]);
      for (; j < i+16; ++j)
        printf ("   ");
      printf ("|");
      for (j = i; j < MIN (i+16, nr); ++j)
        if (c_isprint ((*(char **)buf_rtn)[j]))
          printf ("%c", (*(char **)buf_rtn)[j]);
        else
          printf (".");
      for (; j < i+16; ++j)
        printf (" ");
      printf ("|\n");
    }
  }
#endif

  return 0;
}

/* This is very much like recv_from_daemon above, but g->sock is
 * a listening socket and we are accepting a new connection on
 * that socket instead of reading anything.  Returns the newly
 * accepted socket.
 */
static int
accept_from_daemon (guestfs_h *g)
{
  fd_set rset, rset2;

  if (g->verbose)
    fprintf (stderr,
             "accept_from_daemon: %p g->state = %d\n", g, g->state);

  FD_ZERO (&rset);

  FD_SET (g->fd[1], &rset);     /* Read qemu stdout for log messages & EOF. */
  FD_SET (g->sock, &rset);      /* Read socket for accept. */

  int max_fd = MAX (g->sock, g->fd[1]);
  int sock = -1;

  while (sock == -1) {
    /* If the qemu process has died, clean up the zombie (RHBZ#579155).
     * By partially polling in the select below we ensure that this
     * function will be called eventually.
     */
    waitpid (g->pid, NULL, WNOHANG);

    rset2 = rset;

    struct timeval tv = { .tv_sec = 1, .tv_usec = 0 };
    int r = select (max_fd+1, &rset2, NULL, NULL, &tv);
    if (r == -1) {
      if (errno == EINTR || errno == EAGAIN)
        continue;
      perrorf (g, "select");
      return -1;
    }

    if (FD_ISSET (g->fd[1], &rset2)) {