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
|
/*
* vhost-user
*
* Copyright (c) 2013 Virtual Open Systems Sarl.
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*
*/
#include "qemu/osdep.h"
#include "qapi/error.h"
#include "hw/virtio/virtio-dmabuf.h"
#include "hw/virtio/vhost.h"
#include "hw/virtio/virtio-crypto.h"
#include "hw/virtio/vhost-user.h"
#include "hw/virtio/vhost-backend.h"
#include "hw/virtio/virtio.h"
#include "hw/virtio/virtio-net.h"
#include "chardev/char-fe.h"
#include "io/channel-socket.h"
#include "system/kvm.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
#include "qemu/uuid.h"
#include "qemu/sockets.h"
#include "system/runstate.h"
#include "system/cryptodev.h"
#include "migration/postcopy-ram.h"
#include "trace.h"
#include "exec/ramblock.h"
#include <sys/ioctl.h>
#include <sys/socket.h>
#include <sys/un.h>
#include "standard-headers/linux/vhost_types.h"
#ifdef CONFIG_LINUX
#include <linux/userfaultfd.h>
#endif
#define VHOST_MEMORY_BASELINE_NREGIONS 8
#define VHOST_USER_F_PROTOCOL_FEATURES 30
#define VHOST_USER_BACKEND_MAX_FDS 8
#if defined(TARGET_PPC) || defined(TARGET_PPC64)
#include "hw/ppc/spapr.h"
#define VHOST_USER_MAX_RAM_SLOTS SPAPR_MAX_RAM_SLOTS
#else
#define VHOST_USER_MAX_RAM_SLOTS 512
#endif
/*
* Maximum size of virtio device config space
*/
#define VHOST_USER_MAX_CONFIG_SIZE 256
#define VHOST_USER_PROTOCOL_FEATURE_MASK ((1 << VHOST_USER_PROTOCOL_F_MAX) - 1)
typedef enum VhostUserRequest {
VHOST_USER_NONE = 0,
VHOST_USER_GET_FEATURES = 1,
VHOST_USER_SET_FEATURES = 2,
VHOST_USER_SET_OWNER = 3,
VHOST_USER_RESET_OWNER = 4,
VHOST_USER_SET_MEM_TABLE = 5,
VHOST_USER_SET_LOG_BASE = 6,
VHOST_USER_SET_LOG_FD = 7,
VHOST_USER_SET_VRING_NUM = 8,
VHOST_USER_SET_VRING_ADDR = 9,
VHOST_USER_SET_VRING_BASE = 10,
VHOST_USER_GET_VRING_BASE = 11,
VHOST_USER_SET_VRING_KICK = 12,
VHOST_USER_SET_VRING_CALL = 13,
VHOST_USER_SET_VRING_ERR = 14,
VHOST_USER_GET_PROTOCOL_FEATURES = 15,
VHOST_USER_SET_PROTOCOL_FEATURES = 16,
VHOST_USER_GET_QUEUE_NUM = 17,
VHOST_USER_SET_VRING_ENABLE = 18,
VHOST_USER_SEND_RARP = 19,
VHOST_USER_NET_SET_MTU = 20,
VHOST_USER_SET_BACKEND_REQ_FD = 21,
VHOST_USER_IOTLB_MSG = 22,
VHOST_USER_SET_VRING_ENDIAN = 23,
VHOST_USER_GET_CONFIG = 24,
VHOST_USER_SET_CONFIG = 25,
VHOST_USER_CREATE_CRYPTO_SESSION = 26,
VHOST_USER_CLOSE_CRYPTO_SESSION = 27,
VHOST_USER_POSTCOPY_ADVISE = 28,
VHOST_USER_POSTCOPY_LISTEN = 29,
VHOST_USER_POSTCOPY_END = 30,
VHOST_USER_GET_INFLIGHT_FD = 31,
VHOST_USER_SET_INFLIGHT_FD = 32,
VHOST_USER_GPU_SET_SOCKET = 33,
VHOST_USER_RESET_DEVICE = 34,
/* Message number 35 reserved for VHOST_USER_VRING_KICK. */
VHOST_USER_GET_MAX_MEM_SLOTS = 36,
VHOST_USER_ADD_MEM_REG = 37,
VHOST_USER_REM_MEM_REG = 38,
VHOST_USER_SET_STATUS = 39,
VHOST_USER_GET_STATUS = 40,
VHOST_USER_GET_SHARED_OBJECT = 41,
VHOST_USER_SET_DEVICE_STATE_FD = 42,
VHOST_USER_CHECK_DEVICE_STATE = 43,
VHOST_USER_MAX
} VhostUserRequest;
typedef enum VhostUserBackendRequest {
VHOST_USER_BACKEND_NONE = 0,
VHOST_USER_BACKEND_IOTLB_MSG = 1,
VHOST_USER_BACKEND_CONFIG_CHANGE_MSG = 2,
VHOST_USER_BACKEND_VRING_HOST_NOTIFIER_MSG = 3,
VHOST_USER_BACKEND_SHARED_OBJECT_ADD = 6,
VHOST_USER_BACKEND_SHARED_OBJECT_REMOVE = 7,
VHOST_USER_BACKEND_SHARED_OBJECT_LOOKUP = 8,
VHOST_USER_BACKEND_MAX
} VhostUserBackendRequest;
typedef struct VhostUserMemoryRegion {
uint64_t guest_phys_addr;
uint64_t memory_size;
uint64_t userspace_addr;
uint64_t mmap_offset;
} VhostUserMemoryRegion;
typedef struct VhostUserMemory {
uint32_t nregions;
uint32_t padding;
VhostUserMemoryRegion regions[VHOST_MEMORY_BASELINE_NREGIONS];
} VhostUserMemory;
typedef struct VhostUserMemRegMsg {
uint64_t padding;
VhostUserMemoryRegion region;
} VhostUserMemRegMsg;
typedef struct VhostUserLog {
uint64_t mmap_size;
uint64_t mmap_offset;
} VhostUserLog;
typedef struct VhostUserConfig {
uint32_t offset;
uint32_t size;
uint32_t flags;
uint8_t region[VHOST_USER_MAX_CONFIG_SIZE];
} VhostUserConfig;
#define VHOST_CRYPTO_SYM_HMAC_MAX_KEY_LEN 512
#define VHOST_CRYPTO_SYM_CIPHER_MAX_KEY_LEN 64
#define VHOST_CRYPTO_ASYM_MAX_KEY_LEN 1024
typedef struct VhostUserCryptoSession {
uint64_t op_code;
union {
struct {
CryptoDevBackendSymSessionInfo session_setup_data;
uint8_t key[VHOST_CRYPTO_SYM_CIPHER_MAX_KEY_LEN];
uint8_t auth_key[VHOST_CRYPTO_SYM_HMAC_MAX_KEY_LEN];
} sym;
struct {
CryptoDevBackendAsymSessionInfo session_setup_data;
uint8_t key[VHOST_CRYPTO_ASYM_MAX_KEY_LEN];
} asym;
} u;
/* session id for success, -1 on errors */
int64_t session_id;
} VhostUserCryptoSession;
static VhostUserConfig c __attribute__ ((unused));
#define VHOST_USER_CONFIG_HDR_SIZE (sizeof(c.offset) \
+ sizeof(c.size) \
+ sizeof(c.flags))
typedef struct VhostUserVringArea {
uint64_t u64;
uint64_t size;
uint64_t offset;
} VhostUserVringArea;
typedef struct VhostUserInflight {
uint64_t mmap_size;
uint64_t mmap_offset;
uint16_t num_queues;
uint16_t queue_size;
} VhostUserInflight;
typedef struct VhostUserShared {
unsigned char uuid[16];
} VhostUserShared;
typedef struct {
VhostUserRequest request;
#define VHOST_USER_VERSION_MASK (0x3)
#define VHOST_USER_REPLY_MASK (0x1 << 2)
#define VHOST_USER_NEED_REPLY_MASK (0x1 << 3)
uint32_t flags;
uint32_t size; /* the following payload size */
} QEMU_PACKED VhostUserHeader;
/* Request payload of VHOST_USER_SET_DEVICE_STATE_FD */
typedef struct VhostUserTransferDeviceState {
uint32_t direction;
uint32_t phase;
} VhostUserTransferDeviceState;
typedef union {
#define VHOST_USER_VRING_IDX_MASK (0xff)
#define VHOST_USER_VRING_NOFD_MASK (0x1 << 8)
uint64_t u64;
struct vhost_vring_state state;
struct vhost_vring_addr addr;
VhostUserMemory memory;
VhostUserMemRegMsg mem_reg;
VhostUserLog log;
struct vhost_iotlb_msg iotlb;
VhostUserConfig config;
VhostUserCryptoSession session;
VhostUserVringArea area;
VhostUserInflight inflight;
VhostUserShared object;
VhostUserTransferDeviceState transfer_state;
} VhostUserPayload;
typedef struct VhostUserMsg {
VhostUserHeader hdr;
VhostUserPayload payload;
} QEMU_PACKED VhostUserMsg;
static VhostUserMsg m __attribute__ ((unused));
#define VHOST_USER_HDR_SIZE (sizeof(VhostUserHeader))
#define VHOST_USER_PAYLOAD_SIZE (sizeof(VhostUserPayload))
/* The version of the protocol we support */
#define VHOST_USER_VERSION (0x1)
struct vhost_user {
struct vhost_dev *dev;
/* Shared between vhost devs of the same virtio device */
VhostUserState *user;
QIOChannel *backend_ioc;
GSource *backend_src;
NotifierWithReturn postcopy_notifier;
struct PostCopyFD postcopy_fd;
uint64_t postcopy_client_bases[VHOST_USER_MAX_RAM_SLOTS];
/* Length of the region_rb and region_rb_offset arrays */
size_t region_rb_len;
/* RAMBlock associated with a given region */
RAMBlock **region_rb;
/*
* The offset from the start of the RAMBlock to the start of the
* vhost region.
*/
ram_addr_t *region_rb_offset;
/* True once we've entered postcopy_listen */
bool postcopy_listen;
/* Our current regions */
int num_shadow_regions;
struct vhost_memory_region shadow_regions[VHOST_USER_MAX_RAM_SLOTS];
};
struct scrub_regions {
struct vhost_memory_region *region;
int reg_idx;
int fd_idx;
};
static int vhost_user_read_header(struct vhost_dev *dev, VhostUserMsg *msg)
{
struct vhost_user *u = dev->opaque;
CharBackend *chr = u->user->chr;
uint8_t *p = (uint8_t *) msg;
int r, size = VHOST_USER_HDR_SIZE;
r = qemu_chr_fe_read_all(chr, p, size);
if (r != size) {
int saved_errno = errno;
error_report("Failed to read msg header. Read %d instead of %d."
" Original request %d.", r, size, msg->hdr.request);
return r < 0 ? -saved_errno : -EIO;
}
/* validate received flags */
if (msg->hdr.flags != (VHOST_USER_REPLY_MASK | VHOST_USER_VERSION)) {
error_report("Failed to read msg header."
" Flags 0x%x instead of 0x%x.", msg->hdr.flags,
VHOST_USER_REPLY_MASK | VHOST_USER_VERSION);
return -EPROTO;
}
trace_vhost_user_read(msg->hdr.request, msg->hdr.flags);
return 0;
}
static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
{
struct vhost_user *u = dev->opaque;
CharBackend *chr = u->user->chr;
uint8_t *p = (uint8_t *) msg;
int r, size;
r = vhost_user_read_header(dev, msg);
if (r < 0) {
return r;
}
/* validate message size is sane */
if (msg->hdr.size > VHOST_USER_PAYLOAD_SIZE) {
error_report("Failed to read msg header."
" Size %d exceeds the maximum %zu.", msg->hdr.size,
VHOST_USER_PAYLOAD_SIZE);
return -EPROTO;
}
if (msg->hdr.size) {
p += VHOST_USER_HDR_SIZE;
size = msg->hdr.size;
r = qemu_chr_fe_read_all(chr, p, size);
if (r != size) {
int saved_errno = errno;
error_report("Failed to read msg payload."
" Read %d instead of %d.", r, msg->hdr.size);
return r < 0 ? -saved_errno : -EIO;
}
}
return 0;
}
static int process_message_reply(struct vhost_dev *dev,
const VhostUserMsg *msg)
{
int ret;
VhostUserMsg msg_reply;
if ((msg->hdr.flags & VHOST_USER_NEED_REPLY_MASK) == 0) {
return 0;
}
ret = vhost_user_read(dev, &msg_reply);
if (ret < 0) {
return ret;
}
if (msg_reply.hdr.request != msg->hdr.request) {
error_report("Received unexpected msg type. "
"Expected %d received %d",
msg->hdr.request, msg_reply.hdr.request);
return -EPROTO;
}
return msg_reply.payload.u64 ? -EIO : 0;
}
static bool vhost_user_per_device_request(VhostUserRequest request)
{
switch (request) {
case VHOST_USER_SET_OWNER:
case VHOST_USER_RESET_OWNER:
case VHOST_USER_SET_MEM_TABLE:
case VHOST_USER_GET_QUEUE_NUM:
case VHOST_USER_NET_SET_MTU:
case VHOST_USER_RESET_DEVICE:
case VHOST_USER_ADD_MEM_REG:
case VHOST_USER_REM_MEM_REG:
case VHOST_USER_SET_LOG_BASE:
return true;
default:
return false;
}
}
/* most non-init callers ignore the error */
static int vhost_user_write(struct vhost_dev *dev, VhostUserMsg *msg,
int *fds, int fd_num)
{
struct vhost_user *u = dev->opaque;
CharBackend *chr = u->user->chr;
int ret, size = VHOST_USER_HDR_SIZE + msg->hdr.size;
/*
* Some devices, like virtio-scsi, are implemented as a single vhost_dev,
* while others, like virtio-net, contain multiple vhost_devs. For
* operations such as configuring device memory mappings or issuing device
* resets, which affect the whole device instead of individual VQs,
* vhost-user messages should only be sent once.
*
* Devices with multiple vhost_devs are given an associated dev->vq_index
* so per_device requests are only sent if vq_index is 0.
*/
if (vhost_user_per_device_request(msg->hdr.request)
&& dev->vq_index != 0) {
msg->hdr.flags &= ~VHOST_USER_NEED_REPLY_MASK;
return 0;
}
if (qemu_chr_fe_set_msgfds(chr, fds, fd_num) < 0) {
error_report("Failed to set msg fds.");
return -EINVAL;
}
ret = qemu_chr_fe_write_all(chr, (const uint8_t *) msg, size);
if (ret != size) {
int saved_errno = errno;
error_report("Failed to write msg."
" Wrote %d instead of %d.", ret, size);
return ret < 0 ? -saved_errno : -EIO;
}
trace_vhost_user_write(msg->hdr.request, msg->hdr.flags);
return 0;
}
int vhost_user_gpu_set_socket(struct vhost_dev *dev, int fd)
{
VhostUserMsg msg = {
.hdr.request = VHOST_USER_GPU_SET_SOCKET,
.hdr.flags = VHOST_USER_VERSION,
};
return vhost_user_write(dev, &msg, &fd, 1);
}
static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base,
struct vhost_log *log)
{
int fds[VHOST_USER_MAX_RAM_SLOTS];
size_t fd_num = 0;
bool shmfd = virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_LOG_SHMFD);
int ret;
VhostUserMsg msg = {
.hdr.request = VHOST_USER_SET_LOG_BASE,
.hdr.flags = VHOST_USER_VERSION,
.payload.log.mmap_size = log->size * sizeof(*(log->log)),
.payload.log.mmap_offset = 0,
.hdr.size = sizeof(msg.payload.log),
};
/* Send only once with first queue pair */
if (dev->vq_index != 0) {
return 0;
}
if (shmfd && log->fd != -1) {
fds[fd_num++] = log->fd;
}
ret = vhost_user_write(dev, &msg, fds, fd_num);
if (ret < 0) {
return ret;
}
if (shmfd) {
msg.hdr.size = 0;
ret = vhost_user_read(dev, &msg);
if (ret < 0) {
return ret;
}
if (msg.hdr.request != VHOST_USER_SET_LOG_BASE) {
error_report("Received unexpected msg type. "
"Expected %d received %d",
VHOST_USER_SET_LOG_BASE, msg.hdr.request);
return -EPROTO;
}
}
return 0;
}
static MemoryRegion *vhost_user_get_mr_data(uint64_t addr, ram_addr_t *offset,
int *fd)
{
MemoryRegion *mr;
assert((uintptr_t)addr == addr);
mr = memory_region_from_host((void *)(uintptr_t)addr, offset);
*fd = memory_region_get_fd(mr);
*offset += mr->ram_block->fd_offset;
return mr;
}
static void vhost_user_fill_msg_region(VhostUserMemoryRegion *dst,
struct vhost_memory_region *src,
uint64_t mmap_offset)
{
assert(src != NULL && dst != NULL);
dst->userspace_addr = src->userspace_addr;
dst->memory_size = src->memory_size;
dst->guest_phys_addr = src->guest_phys_addr;
dst->mmap_offset = mmap_offset;
}
static int vhost_user_fill_set_mem_table_msg(struct vhost_user *u,
struct vhost_dev *dev,
VhostUserMsg *msg,
int *fds, size_t *fd_num,
bool track_ramblocks)
{
int i, fd;
ram_addr_t offset;
MemoryRegion *mr;
struct vhost_memory_region *reg;
VhostUserMemoryRegion region_buffer;
msg->hdr.request = VHOST_USER_SET_MEM_TABLE;
for (i = 0; i < dev->mem->nregions; ++i) {
reg = dev->mem->regions + i;
mr = vhost_user_get_mr_data(reg->userspace_addr, &offset, &fd);
if (fd > 0) {
if (track_ramblocks) {
assert(*fd_num < VHOST_MEMORY_BASELINE_NREGIONS);
trace_vhost_user_set_mem_table_withfd(*fd_num, mr->name,
reg->memory_size,
reg->guest_phys_addr,
reg->userspace_addr,
offset);
u->region_rb_offset[i] = offset;
u->region_rb[i] = mr->ram_block;
} else if (*fd_num == VHOST_MEMORY_BASELINE_NREGIONS) {
error_report("Failed preparing vhost-user memory table msg");
return -ENOBUFS;
}
vhost_user_fill_msg_region(®ion_buffer, reg, offset);
msg->payload.memory.regions[*fd_num] = region_buffer;
fds[(*fd_num)++] = fd;
} else if (track_ramblocks) {
u->region_rb_offset[i] = 0;
u->region_rb[i] = NULL;
}
}
msg->payload.memory.nregions = *fd_num;
if (!*fd_num) {
error_report("Failed initializing vhost-user memory map, "
"consider using -object memory-backend-file share=on");
return -EINVAL;
}
msg->hdr.size = sizeof(msg->payload.memory.nregions);
msg->hdr.size += sizeof(msg->payload.memory.padding);
msg->hdr.size += *fd_num * sizeof(VhostUserMemoryRegion);
return 0;
}
static inline bool reg_equal(struct vhost_memory_region *shadow_reg,
struct vhost_memory_region *vdev_reg)
{
return shadow_reg->guest_phys_addr == vdev_reg->guest_phys_addr &&
shadow_reg->userspace_addr == vdev_reg->userspace_addr &&
shadow_reg->memory_size == vdev_reg->memory_size;
}
static void scrub_shadow_regions(struct vhost_dev *dev,
struct scrub_regions *add_reg,
int *nr_add_reg,
struct scrub_regions *rem_reg,
int *nr_rem_reg, uint64_t *shadow_pcb,
bool track_ramblocks)
{
struct vhost_user *u = dev->opaque;
bool found[VHOST_USER_MAX_RAM_SLOTS] = {};
struct vhost_memory_region *reg, *shadow_reg;
int i, j, fd, add_idx = 0, rm_idx = 0, fd_num = 0;
ram_addr_t offset;
MemoryRegion *mr;
bool matching;
/*
* Find memory regions present in our shadow state which are not in
* the device's current memory state.
*
* Mark regions in both the shadow and device state as "found".
*/
for (i = 0; i < u->num_shadow_regions; i++) {
shadow_reg = &u->shadow_regions[i];
matching = false;
for (j = 0; j < dev->mem->nregions; j++) {
reg = &dev->mem->regions[j];
mr = vhost_user_get_mr_data(reg->userspace_addr, &offset, &fd);
if (reg_equal(shadow_reg, reg)) {
matching = true;
found[j] = true;
if (track_ramblocks) {
/*
* Reset postcopy client bases, region_rb, and
* region_rb_offset in case regions are removed.
*/
if (fd > 0) {
u->region_rb_offset[j] = offset;
u->region_rb[j] = mr->ram_block;
shadow_pcb[j] = u->postcopy_client_bases[i];
} else {
u->region_rb_offset[j] = 0;
u->region_rb[j] = NULL;
}
}
break;
}
}
/*
* If the region was not found in the current device memory state
* create an entry for it in the removed list.
*/
if (!matching) {
rem_reg[rm_idx].region = shadow_reg;
rem_reg[rm_idx++].reg_idx = i;
}
}
/*
* For regions not marked "found", create entries in the added list.
*
* Note their indexes in the device memory state and the indexes of their
* file descriptors.
*/
for (i = 0; i < dev->mem->nregions; i++) {
reg = &dev->mem->regions[i];
vhost_user_get_mr_data(reg->userspace_addr, &offset, &fd);
if (fd > 0) {
++fd_num;
}
/*
* If the region was in both the shadow and device state we don't
* need to send a VHOST_USER_ADD_MEM_REG message for it.
*/
if (found[i]) {
continue;
}
add_reg[add_idx].region = reg;
add_reg[add_idx].reg_idx = i;
add_reg[add_idx++].fd_idx = fd_num;
}
*nr_rem_reg = rm_idx;
*nr_add_reg = add_idx;
return;
}
static int send_remove_regions(struct vhost_dev *dev,
struct scrub_regions *remove_reg,
int nr_rem_reg, VhostUserMsg *msg,
bool reply_supported)
{
struct vhost_user *u = dev->opaque;
struct vhost_memory_region *shadow_reg;
int i, fd, shadow_reg_idx, ret;
ram_addr_t offset;
VhostUserMemoryRegion region_buffer;
/*
* The regions in remove_reg appear in the same order they do in the
* shadow table. Therefore we can minimize memory copies by iterating
* through remove_reg backwards.
*/
for (i = nr_rem_reg - 1; i >= 0; i--) {
shadow_reg = remove_reg[i].region;
shadow_reg_idx = remove_reg[i].reg_idx;
vhost_user_get_mr_data(shadow_reg->userspace_addr, &offset, &fd);
if (fd > 0) {
msg->hdr.request = VHOST_USER_REM_MEM_REG;
vhost_user_fill_msg_region(®ion_buffer, shadow_reg, 0);
msg->payload.mem_reg.region = region_buffer;
ret = vhost_user_write(dev, msg, NULL, 0);
if (ret < 0) {
return ret;
}
if (reply_supported) {
ret = process_message_reply(dev, msg);
if (ret) {
return ret;
}
}
}
/*
* At this point we know the backend has unmapped the region. It is now
* safe to remove it from the shadow table.
*/
memmove(&u->shadow_regions[shadow_reg_idx],
&u->shadow_regions[shadow_reg_idx + 1],
sizeof(struct vhost_memory_region) *
(u->num_shadow_regions - shadow_reg_idx - 1));
u->num_shadow_regions--;
}
return 0;
}
static int send_add_regions(struct vhost_dev *dev,
struct scrub_regions *add_reg, int nr_add_reg,
VhostUserMsg *msg, uint64_t *shadow_pcb,
bool reply_supported, bool track_ramblocks)
{
struct vhost_user *u = dev->opaque;
int i, fd, ret, reg_idx, reg_fd_idx;
struct vhost_memory_region *reg;
MemoryRegion *mr;
ram_addr_t offset;
VhostUserMsg msg_reply;
VhostUserMemoryRegion region_buffer;
for (i = 0; i < nr_add_reg; i++) {
reg = add_reg[i].region;
reg_idx = add_reg[i].reg_idx;
reg_fd_idx = add_reg[i].fd_idx;
mr = vhost_user_get_mr_data(reg->userspace_addr, &offset, &fd);
if (fd > 0) {
if (track_ramblocks) {
trace_vhost_user_set_mem_table_withfd(reg_fd_idx, mr->name,
reg->memory_size,
reg->guest_phys_addr,
reg->userspace_addr,
offset);
u->region_rb_offset[reg_idx] = offset;
u->region_rb[reg_idx] = mr->ram_block;
}
msg->hdr.request = VHOST_USER_ADD_MEM_REG;
vhost_user_fill_msg_region(®ion_buffer, reg, offset);
msg->payload.mem_reg.region = region_buffer;
ret = vhost_user_write(dev, msg, &fd, 1);
if (ret < 0) {
return ret;
}
if (track_ramblocks) {
uint64_t reply_gpa;
ret = vhost_user_read(dev, &msg_reply);
if (ret < 0) {
return ret;
}
reply_gpa = msg_reply.payload.mem_reg.region.guest_phys_addr;
if (msg_reply.hdr.request != VHOST_USER_ADD_MEM_REG) {
error_report("%s: Received unexpected msg type."
"Expected %d received %d", __func__,
VHOST_USER_ADD_MEM_REG,
msg_reply.hdr.request);
return -EPROTO;
}
/*
* We're using the same structure, just reusing one of the
* fields, so it should be the same size.
*/
if (msg_reply.hdr.size != msg->hdr.size) {
error_report("%s: Unexpected size for postcopy reply "
"%d vs %d", __func__, msg_reply.hdr.size,
msg->hdr.size);
return -EPROTO;
}
/* Get the postcopy client base from the backend's reply. */
if (reply_gpa == dev->mem->regions[reg_idx].guest_phys_addr) {
shadow_pcb[reg_idx] =
msg_reply.payload.mem_reg.region.userspace_addr;
trace_vhost_user_set_mem_table_postcopy(
msg_reply.payload.mem_reg.region.userspace_addr,
msg->payload.mem_reg.region.userspace_addr,
reg_fd_idx, reg_idx);
} else {
error_report("%s: invalid postcopy reply for region. "
"Got guest physical address %" PRIX64 ", expected "
"%" PRIX64, __func__, reply_gpa,
dev->mem->regions[reg_idx].guest_phys_addr);
return -EPROTO;
}
} else if (reply_supported) {
ret = process_message_reply(dev, msg);
if (ret) {
return ret;
}
}
} else if (track_ramblocks) {
u->region_rb_offset[reg_idx] = 0;
u->region_rb[reg_idx] = NULL;
}
/*
* At this point, we know the backend has mapped in the new
* region, if the region has a valid file descriptor.
*
* The region should now be added to the shadow table.
*/
u->shadow_regions[u->num_shadow_regions].guest_phys_addr =
reg->guest_phys_addr;
u->shadow_regions[u->num_shadow_regions].userspace_addr =
reg->userspace_addr;
u->shadow_regions[u->num_shadow_regions].memory_size =
reg->memory_size;
u->num_shadow_regions++;
}
return 0;
}
static int vhost_user_add_remove_regions(struct vhost_dev *dev,
VhostUserMsg *msg,
bool reply_supported,
bool track_ramblocks)
{
struct vhost_user *u = dev->opaque;
struct scrub_regions add_reg[VHOST_USER_MAX_RAM_SLOTS];
struct scrub_regions rem_reg[VHOST_USER_MAX_RAM_SLOTS];
uint64_t shadow_pcb[VHOST_USER_MAX_RAM_SLOTS] = {};
int nr_add_reg, nr_rem_reg;
int ret;
msg->hdr.size = sizeof(msg->payload.mem_reg);
/* Find the regions which need to be removed or added. */
scrub_shadow_regions(dev, add_reg, &nr_add_reg, rem_reg, &nr_rem_reg,
shadow_pcb, track_ramblocks);
if (nr_rem_reg) {
ret = send_remove_regions(dev, rem_reg, nr_rem_reg, msg,
reply_supported);
if (ret < 0) {
goto err;
}
}
if (nr_add_reg) {
ret = send_add_regions(dev, add_reg, nr_add_reg, msg, shadow_pcb,
reply_supported, track_ramblocks);
if (ret < 0) {
goto err;
}
}
if (track_ramblocks) {
memcpy(u->postcopy_client_bases, shadow_pcb,
sizeof(uint64_t) * VHOST_USER_MAX_RAM_SLOTS);
/*
* Now we've registered this with the postcopy code, we ack to the
* client, because now we're in the position to be able to deal with
* any faults it generates.
*/
/* TODO: Use this for failure cases as well with a bad value. */
msg->hdr.size = sizeof(msg->payload.u64);
msg->payload.u64 = 0; /* OK */
ret = vhost_user_write(dev, msg, NULL, 0);
if (ret < 0) {
return ret;
}
}
return 0;
err:
if (track_ramblocks) {
memcpy(u->postcopy_client_bases, shadow_pcb,
sizeof(uint64_t) * VHOST_USER_MAX_RAM_SLOTS);
}
return ret;
}
static int vhost_user_set_mem_table_postcopy(struct vhost_dev *dev,
struct vhost_memory *mem,
bool reply_supported,
bool config_mem_slots)
{
struct vhost_user *u = dev->opaque;
int fds[VHOST_MEMORY_BASELINE_NREGIONS];
size_t fd_num = 0;
VhostUserMsg msg_reply;
int region_i, msg_i;
int ret;
VhostUserMsg msg = {
.hdr.flags = VHOST_USER_VERSION,
};
if (u->region_rb_len < dev->mem->nregions) {
u->region_rb = g_renew(RAMBlock*, u->region_rb, dev->mem->nregions);
u->region_rb_offset = g_renew(ram_addr_t, u->region_rb_offset,
dev->mem->nregions);
memset(&(u->region_rb[u->region_rb_len]), '\0',
sizeof(RAMBlock *) * (dev->mem->nregions - u->region_rb_len));
memset(&(u->region_rb_offset[u->region_rb_len]), '\0',
sizeof(ram_addr_t) * (dev->mem->nregions - u->region_rb_len));
u->region_rb_len = dev->mem->nregions;
}
if (config_mem_slots) {
ret = vhost_user_add_remove_regions(dev, &msg, reply_supported, true);
if (ret < 0) {
return ret;
}
} else {
ret = vhost_user_fill_set_mem_table_msg(u, dev, &msg, fds, &fd_num,
true);
if (ret < 0) {
return ret;
}
ret = vhost_user_write(dev, &msg, fds, fd_num);
if (ret < 0) {
return ret;
}
ret = vhost_user_read(dev, &msg_reply);
if (ret < 0) {
return ret;
}
if (msg_reply.hdr.request != VHOST_USER_SET_MEM_TABLE) {
error_report("%s: Received unexpected msg type."
"Expected %d received %d", __func__,
VHOST_USER_SET_MEM_TABLE, msg_reply.hdr.request);
return -EPROTO;
}
/*
* We're using the same structure, just reusing one of the
* fields, so it should be the same size.
*/
if (msg_reply.hdr.size != msg.hdr.size) {
error_report("%s: Unexpected size for postcopy reply "
"%d vs %d", __func__, msg_reply.hdr.size,
msg.hdr.size);
return -EPROTO;
}
memset(u->postcopy_client_bases, 0,
sizeof(uint64_t) * VHOST_USER_MAX_RAM_SLOTS);
/*
* They're in the same order as the regions that were sent
* but some of the regions were skipped (above) if they
* didn't have fd's
*/
for (msg_i = 0, region_i = 0;
region_i < dev->mem->nregions;
region_i++) {
if (msg_i < fd_num &&
msg_reply.payload.memory.regions[msg_i].guest_phys_addr ==
dev->mem->regions[region_i].guest_phys_addr) {
u->postcopy_client_bases[region_i] =
msg_reply.payload.memory.regions[msg_i].userspace_addr;
trace_vhost_user_set_mem_table_postcopy(
msg_reply.payload.memory.regions[msg_i].userspace_addr,
msg.payload.memory.regions[msg_i].userspace_addr,
msg_i, region_i);
msg_i++;
}
}
if (msg_i != fd_num) {
error_report("%s: postcopy reply not fully consumed "
"%d vs %zd",
__func__, msg_i, fd_num);
return -EIO;
}
/*
* Now we've registered this with the postcopy code, we ack to the
* client, because now we're in the position to be able to deal
* with any faults it generates.
*/
/* TODO: Use this for failure cases as well with a bad value. */
msg.hdr.size = sizeof(msg.payload.u64);
msg.payload.u64 = 0; /* OK */
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
return ret;
}
}
return 0;
}
static int vhost_user_set_mem_table(struct vhost_dev *dev,
struct vhost_memory *mem)
{
struct vhost_user *u = dev->opaque;
int fds[VHOST_MEMORY_BASELINE_NREGIONS];
size_t fd_num = 0;
bool do_postcopy = u->postcopy_listen && u->postcopy_fd.handler;
bool reply_supported = virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_REPLY_ACK);
bool config_mem_slots =
virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS);
int ret;
if (do_postcopy) {
/*
* Postcopy has enough differences that it's best done in it's own
* version
*/
return vhost_user_set_mem_table_postcopy(dev, mem, reply_supported,
config_mem_slots);
}
VhostUserMsg msg = {
.hdr.flags = VHOST_USER_VERSION,
};
if (reply_supported) {
msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
}
if (config_mem_slots) {
ret = vhost_user_add_remove_regions(dev, &msg, reply_supported, false);
if (ret < 0) {
return ret;
}
} else {
ret = vhost_user_fill_set_mem_table_msg(u, dev, &msg, fds, &fd_num,
false);
if (ret < 0) {
return ret;
}
ret = vhost_user_write(dev, &msg, fds, fd_num);
if (ret < 0) {
return ret;
}
if (reply_supported) {
return process_message_reply(dev, &msg);
}
}
return 0;
}
static int vhost_user_set_vring_endian(struct vhost_dev *dev,
struct vhost_vring_state *ring)
{
bool cross_endian = virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_CROSS_ENDIAN);
VhostUserMsg msg = {
.hdr.request = VHOST_USER_SET_VRING_ENDIAN,
.hdr.flags = VHOST_USER_VERSION,
.payload.state = *ring,
.hdr.size = sizeof(msg.payload.state),
};
if (!cross_endian) {
error_report("vhost-user trying to send unhandled ioctl");
return -ENOTSUP;
}
return vhost_user_write(dev, &msg, NULL, 0);
}
static int vhost_user_get_u64(struct vhost_dev *dev, int request, uint64_t *u64)
{
int ret;
VhostUserMsg msg = {
.hdr.request = request,
.hdr.flags = VHOST_USER_VERSION,
};
if (vhost_user_per_device_request(request) && dev->vq_index != 0) {
return 0;
}
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
return ret;
}
ret = vhost_user_read(dev, &msg);
if (ret < 0) {
return ret;
}
if (msg.hdr.request != request) {
error_report("Received unexpected msg type. Expected %d received %d",
request, msg.hdr.request);
return -EPROTO;
}
if (msg.hdr.size != sizeof(msg.payload.u64)) {
error_report("Received bad msg size.");
return -EPROTO;
}
*u64 = msg.payload.u64;
return 0;
}
static int vhost_user_get_features(struct vhost_dev *dev, uint64_t *features)
{
if (vhost_user_get_u64(dev, VHOST_USER_GET_FEATURES, features) < 0) {
return -EPROTO;
}
return 0;
}
/* Note: "msg->hdr.flags" may be modified. */
static int vhost_user_write_sync(struct vhost_dev *dev, VhostUserMsg *msg,
bool wait_for_reply)
{
int ret;
if (wait_for_reply) {
bool reply_supported = virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_REPLY_ACK);
if (reply_supported) {
msg->hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
}
}
ret = vhost_user_write(dev, msg, NULL, 0);
if (ret < 0) {
return ret;
}
if (wait_for_reply) {
uint64_t dummy;
if (msg->hdr.flags & VHOST_USER_NEED_REPLY_MASK) {
return process_message_reply(dev, msg);
}
/*
* We need to wait for a reply but the backend does not
* support replies for the command we just sent.
* Send VHOST_USER_GET_FEATURES which makes all backends
* send a reply.
*/
return vhost_user_get_features(dev, &dummy);
}
return 0;
}
static int vhost_set_vring(struct vhost_dev *dev,
unsigned long int request,
struct vhost_vring_state *ring,
bool wait_for_reply)
{
VhostUserMsg msg = {
.hdr.request = request,
.hdr.flags = VHOST_USER_VERSION,
.payload.state = *ring,
.hdr.size = sizeof(msg.payload.state),
};
return vhost_user_write_sync(dev, &msg, wait_for_reply);
}
static int vhost_user_set_vring_num(struct vhost_dev *dev,
struct vhost_vring_state *ring)
{
return vhost_set_vring(dev, VHOST_USER_SET_VRING_NUM, ring, false);
}
static void vhost_user_host_notifier_free(VhostUserHostNotifier *n)
{
if (n->unmap_addr) {
munmap(n->unmap_addr, qemu_real_host_page_size());
n->unmap_addr = NULL;
}
if (n->destroy) {
memory_region_transaction_begin();
object_unparent(OBJECT(&n->mr));
memory_region_transaction_commit();
g_free(n);
}
}
/*
* clean-up function for notifier, will finally free the structure
* under rcu.
*/
static void vhost_user_host_notifier_remove(VhostUserHostNotifier *n,
VirtIODevice *vdev, bool destroy)
{
/*
* if destroy == false and n->addr == NULL, we have nothing to do.
* so, just return.
*/
if (!n || (!destroy && !n->addr)) {
return;
}
if (n->addr) {
if (vdev) {
memory_region_transaction_begin();
virtio_queue_set_host_notifier_mr(vdev, n->idx, &n->mr, false);
memory_region_transaction_commit();
}
assert(!n->unmap_addr);
n->unmap_addr = n->addr;
n->addr = NULL;
}
n->destroy = destroy;
call_rcu(n, vhost_user_host_notifier_free, rcu);
}
static int vhost_user_set_vring_base(struct vhost_dev *dev,
struct vhost_vring_state *ring)
{
return vhost_set_vring(dev, VHOST_USER_SET_VRING_BASE, ring, false);
}
static int vhost_user_set_vring_enable(struct vhost_dev *dev, int enable)
{
int i;
if (!virtio_has_feature(dev->features, VHOST_USER_F_PROTOCOL_FEATURES)) {
return -EINVAL;
}
for (i = 0; i < dev->nvqs; ++i) {
int ret;
struct vhost_vring_state state = {
.index = dev->vq_index + i,
.num = enable,
};
/*
* SET_VRING_ENABLE travels from guest to QEMU to vhost-user backend /
* control plane thread via unix domain socket. Virtio requests travel
* from guest to vhost-user backend / data plane thread via eventfd.
* Even if the guest enables the ring first, and pushes its first virtio
* request second (conforming to the virtio spec), the data plane thread
* in the backend may see the virtio request before the control plane
* thread sees the queue enablement. This causes (in fact, requires) the
* data plane thread to discard the virtio request (it arrived on a
* seemingly disabled queue). To prevent this out-of-order delivery,
* don't let the guest proceed to pushing the virtio request until the
* backend control plane acknowledges enabling the queue -- IOW, pass
* wait_for_reply=true below.
*/
ret = vhost_set_vring(dev, VHOST_USER_SET_VRING_ENABLE, &state, true);
if (ret < 0) {
/*
* Restoring the previous state is likely infeasible, as well as
* proceeding regardless the error, so just bail out and hope for
* the device-level recovery.
*/
return ret;
}
}
return 0;
}
static VhostUserHostNotifier *fetch_notifier(VhostUserState *u,
int idx)
{
if (idx >= u->notifiers->len) {
return NULL;
}
return g_ptr_array_index(u->notifiers, idx);
}
static int vhost_user_get_vring_base(struct vhost_dev *dev,
struct vhost_vring_state *ring)
{
int ret;
VhostUserMsg msg = {
.hdr.request = VHOST_USER_GET_VRING_BASE,
.hdr.flags = VHOST_USER_VERSION,
.payload.state = *ring,
.hdr.size = sizeof(msg.payload.state),
};
struct vhost_user *u = dev->opaque;
VhostUserHostNotifier *n = fetch_notifier(u->user, ring->index);
vhost_user_host_notifier_remove(n, dev->vdev, false);
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
return ret;
}
ret = vhost_user_read(dev, &msg);
if (ret < 0) {
return ret;
}
if (msg.hdr.request != VHOST_USER_GET_VRING_BASE) {
error_report("Received unexpected msg type. Expected %d received %d",
VHOST_USER_GET_VRING_BASE, msg.hdr.request);
return -EPROTO;
}
if (msg.hdr.size != sizeof(msg.payload.state)) {
error_report("Received bad msg size.");
return -EPROTO;
}
*ring = msg.payload.state;
return 0;
}
static int vhost_set_vring_file(struct vhost_dev *dev,
VhostUserRequest request,
struct vhost_vring_file *file)
{
int fds[VHOST_USER_MAX_RAM_SLOTS];
size_t fd_num = 0;
VhostUserMsg msg = {
.hdr.request = request,
.hdr.flags = VHOST_USER_VERSION,
.payload.u64 = file->index & VHOST_USER_VRING_IDX_MASK,
.hdr.size = sizeof(msg.payload.u64),
};
if (file->fd > 0) {
fds[fd_num++] = file->fd;
} else {
msg.payload.u64 |= VHOST_USER_VRING_NOFD_MASK;
}
return vhost_user_write(dev, &msg, fds, fd_num);
}
static int vhost_user_set_vring_kick(struct vhost_dev *dev,
struct vhost_vring_file *file)
{
return vhost_set_vring_file(dev, VHOST_USER_SET_VRING_KICK, file);
}
static int vhost_user_set_vring_call(struct vhost_dev *dev,
struct vhost_vring_file *file)
{
return vhost_set_vring_file(dev, VHOST_USER_SET_VRING_CALL, file);
}
static int vhost_user_set_vring_err(struct vhost_dev *dev,
struct vhost_vring_file *file)
{
return vhost_set_vring_file(dev, VHOST_USER_SET_VRING_ERR, file);
}
static int vhost_user_set_vring_addr(struct vhost_dev *dev,
struct vhost_vring_addr *addr)
{
VhostUserMsg msg = {
.hdr.request = VHOST_USER_SET_VRING_ADDR,
.hdr.flags = VHOST_USER_VERSION,
.payload.addr = *addr,
.hdr.size = sizeof(msg.payload.addr),
};
/*
* wait for a reply if logging is enabled to make sure
* backend is actually logging changes
*/
bool wait_for_reply = addr->flags & (1 << VHOST_VRING_F_LOG);
return vhost_user_write_sync(dev, &msg, wait_for_reply);
}
static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64,
bool wait_for_reply)
{
VhostUserMsg msg = {
.hdr.request = request,
.hdr.flags = VHOST_USER_VERSION,
.payload.u64 = u64,
.hdr.size = sizeof(msg.payload.u64),
};
return vhost_user_write_sync(dev, &msg, wait_for_reply);
}
static int vhost_user_set_status(struct vhost_dev *dev, uint8_t status)
{
return vhost_user_set_u64(dev, VHOST_USER_SET_STATUS, status, false);
}
static int vhost_user_get_status(struct vhost_dev *dev, uint8_t *status)
{
uint64_t value;
int ret;
ret = vhost_user_get_u64(dev, VHOST_USER_GET_STATUS, &value);
if (ret < 0) {
return ret;
}
*status = value;
return 0;
}
static int vhost_user_add_status(struct vhost_dev *dev, uint8_t status)
{
uint8_t s;
int ret;
ret = vhost_user_get_status(dev, &s);
if (ret < 0) {
return ret;
}
if ((s & status) == status) {
return 0;
}
s |= status;
return vhost_user_set_status(dev, s);
}
static int vhost_user_set_features(struct vhost_dev *dev,
uint64_t features)
{
/*
* wait for a reply if logging is enabled to make sure
* backend is actually logging changes
*/
bool log_enabled = features & (0x1ULL << VHOST_F_LOG_ALL);
int ret;
/*
* We need to include any extra backend only feature bits that
* might be needed by our device. Currently this includes the
* VHOST_USER_F_PROTOCOL_FEATURES bit for enabling protocol
* features.
*/
ret = vhost_user_set_u64(dev, VHOST_USER_SET_FEATURES,
features | dev->backend_features,
log_enabled);
if (virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_STATUS)) {
if (!ret) {
return vhost_user_add_status(dev, VIRTIO_CONFIG_S_FEATURES_OK);
}
}
return ret;
}
static int vhost_user_set_protocol_features(struct vhost_dev *dev,
uint64_t features)
{
return vhost_user_set_u64(dev, VHOST_USER_SET_PROTOCOL_FEATURES, features,
false);
}
static int vhost_user_set_owner(struct vhost_dev *dev)
{
VhostUserMsg msg = {
.hdr.request = VHOST_USER_SET_OWNER,
.hdr.flags = VHOST_USER_VERSION,
};
return vhost_user_write(dev, &msg, NULL, 0);
}
static int vhost_user_get_max_memslots(struct vhost_dev *dev,
uint64_t *max_memslots)
{
uint64_t backend_max_memslots;
int err;
err = vhost_user_get_u64(dev, VHOST_USER_GET_MAX_MEM_SLOTS,
&backend_max_memslots);
if (err < 0) {
return err;
}
*max_memslots = backend_max_memslots;
return 0;
}
static int vhost_user_reset_device(struct vhost_dev *dev)
{
VhostUserMsg msg = {
.hdr.flags = VHOST_USER_VERSION,
.hdr.request = VHOST_USER_RESET_DEVICE,
};
/*
* Historically, reset was not implemented so only reset devices
* that are expecting it.
*/
if (!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_RESET_DEVICE)) {
return -ENOSYS;
}
return vhost_user_write(dev, &msg, NULL, 0);
}
static int vhost_user_backend_handle_config_change(struct vhost_dev *dev)
{
if (!dev->config_ops || !dev->config_ops->vhost_dev_config_notifier) {
return -ENOSYS;
}
return dev->config_ops->vhost_dev_config_notifier(dev);
}
/*
* Fetch or create the notifier for a given idx. Newly created
* notifiers are added to the pointer array that tracks them.
*/
static VhostUserHostNotifier *fetch_or_create_notifier(VhostUserState *u,
int idx)
{
VhostUserHostNotifier *n = NULL;
if (idx >= u->notifiers->len) {
g_ptr_array_set_size(u->notifiers, idx + 1);
}
n = g_ptr_array_index(u->notifiers, idx);
if (!n) {
/*
* In case notification arrive out-of-order,
* make room for current index.
*/
g_ptr_array_remove_index(u->notifiers, idx);
n = g_new0(VhostUserHostNotifier, 1);
n->idx = idx;
g_ptr_array_insert(u->notifiers, idx, n);
trace_vhost_user_create_notifier(idx, n);
}
return n;
}
static int vhost_user_backend_handle_vring_host_notifier(struct vhost_dev *dev,
VhostUserVringArea *area,
int fd)
{
int queue_idx = area->u64 & VHOST_USER_VRING_IDX_MASK;
size_t page_size = qemu_real_host_page_size();
struct vhost_user *u = dev->opaque;
VhostUserState *user = u->user;
VirtIODevice *vdev = dev->vdev;
VhostUserHostNotifier *n;
void *addr;
char *name;
if (!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_HOST_NOTIFIER) ||
vdev == NULL || queue_idx >= virtio_get_num_queues(vdev)) {
return -EINVAL;
}
/*
* Fetch notifier and invalidate any old data before setting up
* new mapped address.
*/
n = fetch_or_create_notifier(user, queue_idx);
vhost_user_host_notifier_remove(n, vdev, false);
if (area->u64 & VHOST_USER_VRING_NOFD_MASK) {
return 0;
}
/* Sanity check. */
if (area->size != page_size) {
return -EINVAL;
}
addr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
fd, area->offset);
if (addr == MAP_FAILED) {
return -EFAULT;
}
name = g_strdup_printf("vhost-user/host-notifier@%p mmaps[%d]",
user, queue_idx);
if (!n->mr.ram) { /* Don't init again after suspend. */
memory_region_init_ram_device_ptr(&n->mr, OBJECT(vdev), name,
page_size, addr);
} else {
n->mr.ram_block->host = addr;
}
g_free(name);
if (virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, true)) {
object_unparent(OBJECT(&n->mr));
munmap(addr, page_size);
return -ENXIO;
}
n->addr = addr;
return 0;
}
static int
vhost_user_backend_handle_shared_object_add(struct vhost_dev *dev,
VhostUserShared *object)
{
QemuUUID uuid;
memcpy(uuid.data, object->uuid, sizeof(object->uuid));
return !virtio_add_vhost_device(&uuid, dev);
}
/*
* Handle VHOST_USER_BACKEND_SHARED_OBJECT_REMOVE backend requests.
*
* Return: 0 on success, 1 on error.
*/
static int
vhost_user_backend_handle_shared_object_remove(struct vhost_dev *dev,
VhostUserShared *object)
{
QemuUUID uuid;
memcpy(uuid.data, object->uuid, sizeof(object->uuid));
switch (virtio_object_type(&uuid)) {
case TYPE_VHOST_DEV:
{
struct vhost_dev *owner = virtio_lookup_vhost_device(&uuid);
if (dev != owner) {
/* Not allowed to remove non-owned entries */
return 1;
}
break;
}
default:
/* Not allowed to remove non-owned entries */
return 1;
}
return !virtio_remove_resource(&uuid);
}
static bool vhost_user_send_resp(QIOChannel *ioc, VhostUserHeader *hdr,
VhostUserPayload *payload, Error **errp)
{
struct iovec iov[] = {
{ .iov_base = hdr, .iov_len = VHOST_USER_HDR_SIZE },
{ .iov_base = payload, .iov_len = hdr->size },
};
hdr->flags &= ~VHOST_USER_NEED_REPLY_MASK;
hdr->flags |= VHOST_USER_REPLY_MASK;
return !qio_channel_writev_all(ioc, iov, ARRAY_SIZE(iov), errp);
}
static bool
vhost_user_backend_send_dmabuf_fd(QIOChannel *ioc, VhostUserHeader *hdr,
VhostUserPayload *payload, Error **errp)
{
hdr->size = sizeof(payload->u64);
return vhost_user_send_resp(ioc, hdr, payload, errp);
}
int vhost_user_get_shared_object(struct vhost_dev *dev, unsigned char *uuid,
int *dmabuf_fd)
{
struct vhost_user *u = dev->opaque;
CharBackend *chr = u->user->chr;
int ret;
VhostUserMsg msg = {
.hdr.request = VHOST_USER_GET_SHARED_OBJECT,
.hdr.flags = VHOST_USER_VERSION,
};
memcpy(msg.payload.object.uuid, uuid, sizeof(msg.payload.object.uuid));
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
return ret;
}
ret = vhost_user_read(dev, &msg);
if (ret < 0) {
return ret;
}
if (msg.hdr.request != VHOST_USER_GET_SHARED_OBJECT) {
error_report("Received unexpected msg type. "
"Expected %d received %d",
VHOST_USER_GET_SHARED_OBJECT, msg.hdr.request);
return -EPROTO;
}
*dmabuf_fd = qemu_chr_fe_get_msgfd(chr);
if (*dmabuf_fd < 0) {
error_report("Failed to get dmabuf fd");
return -EIO;
}
return 0;
}
static int
vhost_user_backend_handle_shared_object_lookup(struct vhost_user *u,
QIOChannel *ioc,
VhostUserHeader *hdr,
VhostUserPayload *payload)
{
QemuUUID uuid;
CharBackend *chr = u->user->chr;
Error *local_err = NULL;
int dmabuf_fd = -1;
int fd_num = 0;
memcpy(uuid.data, payload->object.uuid, sizeof(payload->object.uuid));
payload->u64 = 0;
switch (virtio_object_type(&uuid)) {
case TYPE_DMABUF:
dmabuf_fd = virtio_lookup_dmabuf(&uuid);
break;
case TYPE_VHOST_DEV:
{
struct vhost_dev *dev = virtio_lookup_vhost_device(&uuid);
if (dev == NULL) {
payload->u64 = -EINVAL;
break;
}
int ret = vhost_user_get_shared_object(dev, uuid.data, &dmabuf_fd);
if (ret < 0) {
payload->u64 = ret;
}
break;
}
case TYPE_INVALID:
payload->u64 = -EINVAL;
break;
}
if (dmabuf_fd != -1) {
fd_num++;
}
if (qemu_chr_fe_set_msgfds(chr, &dmabuf_fd, fd_num) < 0) {
error_report("Failed to set msg fds.");
payload->u64 = -EINVAL;
}
if (!vhost_user_backend_send_dmabuf_fd(ioc, hdr, payload, &local_err)) {
error_report_err(local_err);
return -EINVAL;
}
return 0;
}
static void close_backend_channel(struct vhost_user *u)
{
g_source_destroy(u->backend_src);
g_source_unref(u->backend_src);
u->backend_src = NULL;
object_unref(OBJECT(u->backend_ioc));
u->backend_ioc = NULL;
}
static gboolean backend_read(QIOChannel *ioc, GIOCondition condition,
gpointer opaque)
{
struct vhost_dev *dev = opaque;
struct vhost_user *u = dev->opaque;
VhostUserHeader hdr = { 0, };
VhostUserPayload payload = { 0, };
Error *local_err = NULL;
gboolean rc = G_SOURCE_CONTINUE;
int ret = 0;
struct iovec iov;
g_autofree int *fd = NULL;
size_t fdsize = 0;
int i;
/* Read header */
iov.iov_base = &hdr;
iov.iov_len = VHOST_USER_HDR_SIZE;
if (qio_channel_readv_full_all(ioc, &iov, 1, &fd, &fdsize, &local_err)) {
error_report_err(local_err);
goto err;
}
if (hdr.size > VHOST_USER_PAYLOAD_SIZE) {
error_report("Failed to read msg header."
" Size %d exceeds the maximum %zu.", hdr.size,
VHOST_USER_PAYLOAD_SIZE);
goto err;
}
/* Read payload */
if (qio_channel_read_all(ioc, (char *) &payload, hdr.size, &local_err)) {
error_report_err(local_err);
goto err;
}
switch (hdr.request) {
case VHOST_USER_BACKEND_IOTLB_MSG:
ret = vhost_backend_handle_iotlb_msg(dev, &payload.iotlb);
break;
case VHOST_USER_BACKEND_CONFIG_CHANGE_MSG:
ret = vhost_user_backend_handle_config_change(dev);
break;
case VHOST_USER_BACKEND_VRING_HOST_NOTIFIER_MSG:
ret = vhost_user_backend_handle_vring_host_notifier(dev, &payload.area,
fd ? fd[0] : -1);
break;
case VHOST_USER_BACKEND_SHARED_OBJECT_ADD:
ret = vhost_user_backend_handle_shared_object_add(dev, &payload.object);
break;
case VHOST_USER_BACKEND_SHARED_OBJECT_REMOVE:
ret = vhost_user_backend_handle_shared_object_remove(dev,
&payload.object);
break;
case VHOST_USER_BACKEND_SHARED_OBJECT_LOOKUP:
ret = vhost_user_backend_handle_shared_object_lookup(dev->opaque, ioc,
&hdr, &payload);
break;
default:
error_report("Received unexpected msg type: %d.", hdr.request);
ret = -EINVAL;
}
/*
* REPLY_ACK feature handling. Other reply types has to be managed
* directly in their request handlers.
*/
if (hdr.flags & VHOST_USER_NEED_REPLY_MASK) {
payload.u64 = !!ret;
hdr.size = sizeof(payload.u64);
if (!vhost_user_send_resp(ioc, &hdr, &payload, &local_err)) {
error_report_err(local_err);
goto err;
}
}
goto fdcleanup;
err:
close_backend_channel(u);
rc = G_SOURCE_REMOVE;
fdcleanup:
if (fd) {
for (i = 0; i < fdsize; i++) {
close(fd[i]);
}
}
return rc;
}
static int vhost_setup_backend_channel(struct vhost_dev *dev)
{
VhostUserMsg msg = {
.hdr.request = VHOST_USER_SET_BACKEND_REQ_FD,
.hdr.flags = VHOST_USER_VERSION,
};
struct vhost_user *u = dev->opaque;
int sv[2], ret = 0;
bool reply_supported = virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_REPLY_ACK);
Error *local_err = NULL;
QIOChannel *ioc;
if (!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_BACKEND_REQ)) {
return 0;
}
if (qemu_socketpair(PF_UNIX, SOCK_STREAM, 0, sv) == -1) {
int saved_errno = errno;
error_report("socketpair() failed");
return -saved_errno;
}
ioc = QIO_CHANNEL(qio_channel_socket_new_fd(sv[0], &local_err));
if (!ioc) {
error_report_err(local_err);
return -ECONNREFUSED;
}
u->backend_ioc = ioc;
u->backend_src = qio_channel_add_watch_source(u->backend_ioc,
G_IO_IN | G_IO_HUP,
backend_read, dev, NULL, NULL);
if (reply_supported) {
msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
}
ret = vhost_user_write(dev, &msg, &sv[1], 1);
if (ret) {
goto out;
}
if (reply_supported) {
ret = process_message_reply(dev, &msg);
}
out:
close(sv[1]);
if (ret) {
close_backend_channel(u);
}
return ret;
}
#ifdef CONFIG_LINUX
/*
* Called back from the postcopy fault thread when a fault is received on our
* ufd.
* TODO: This is Linux specific
*/
static int vhost_user_postcopy_fault_handler(struct PostCopyFD *pcfd,
void *ufd)
{
struct vhost_dev *dev = pcfd->data;
struct vhost_user *u = dev->opaque;
struct uffd_msg *msg = ufd;
uint64_t faultaddr = msg->arg.pagefault.address;
RAMBlock *rb = NULL;
uint64_t rb_offset;
int i;
trace_vhost_user_postcopy_fault_handler(pcfd->idstr, faultaddr,
dev->mem->nregions);
for (i = 0; i < MIN(dev->mem->nregions, u->region_rb_len); i++) {
trace_vhost_user_postcopy_fault_handler_loop(i,
u->postcopy_client_bases[i], dev->mem->regions[i].memory_size);
if (faultaddr >= u->postcopy_client_bases[i]) {
/* Ofset of the fault address in the vhost region */
uint64_t region_offset = faultaddr - u->postcopy_client_bases[i];
if (region_offset < dev->mem->regions[i].memory_size) {
rb_offset = region_offset + u->region_rb_offset[i];
trace_vhost_user_postcopy_fault_handler_found(i,
region_offset, rb_offset);
rb = u->region_rb[i];
return postcopy_request_shared_page(pcfd, rb, faultaddr,
rb_offset);
}
}
}
error_report("%s: Failed to find region for fault %" PRIx64,
__func__, faultaddr);
return -1;
}
static int vhost_user_postcopy_waker(struct PostCopyFD *pcfd, RAMBlock *rb,
uint64_t offset)
{
struct vhost_dev *dev = pcfd->data;
struct vhost_user *u = dev->opaque;
int i;
trace_vhost_user_postcopy_waker(qemu_ram_get_idstr(rb), offset);
if (!u) {
return 0;
}
/* Translate the offset into an address in the clients address space */
for (i = 0; i < MIN(dev->mem->nregions, u->region_rb_len); i++) {
if (u->region_rb[i] == rb &&
offset >= u->region_rb_offset[i] &&
offset < (u->region_rb_offset[i] +
dev->mem->regions[i].memory_size)) {
uint64_t client_addr = (offset - u->region_rb_offset[i]) +
u->postcopy_client_bases[i];
trace_vhost_user_postcopy_waker_found(client_addr);
return postcopy_wake_shared(pcfd, client_addr, rb);
}
}
trace_vhost_user_postcopy_waker_nomatch(qemu_ram_get_idstr(rb), offset);
return 0;
}
#endif
/*
* Called at the start of an inbound postcopy on reception of the
* 'advise' command.
*/
static int vhost_user_postcopy_advise(struct vhost_dev *dev, Error **errp)
{
#ifdef CONFIG_LINUX
struct vhost_user *u = dev->opaque;
CharBackend *chr = u->user->chr;
int ufd;
int ret;
VhostUserMsg msg = {
.hdr.request = VHOST_USER_POSTCOPY_ADVISE,
.hdr.flags = VHOST_USER_VERSION,
};
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
error_setg(errp, "Failed to send postcopy_advise to vhost");
return ret;
}
ret = vhost_user_read(dev, &msg);
if (ret < 0) {
error_setg(errp, "Failed to get postcopy_advise reply from vhost");
return ret;
}
if (msg.hdr.request != VHOST_USER_POSTCOPY_ADVISE) {
error_setg(errp, "Unexpected msg type. Expected %d received %d",
VHOST_USER_POSTCOPY_ADVISE, msg.hdr.request);
return -EPROTO;
}
if (msg.hdr.size) {
error_setg(errp, "Received bad msg size.");
return -EPROTO;
}
ufd = qemu_chr_fe_get_msgfd(chr);
if (ufd < 0) {
error_setg(errp, "%s: Failed to get ufd", __func__);
return -EIO;
}
qemu_socket_set_nonblock(ufd);
/* register ufd with userfault thread */
u->postcopy_fd.fd = ufd;
u->postcopy_fd.data = dev;
u->postcopy_fd.handler = vhost_user_postcopy_fault_handler;
u->postcopy_fd.waker = vhost_user_postcopy_waker;
u->postcopy_fd.idstr = "vhost-user"; /* Need to find unique name */
postcopy_register_shared_ufd(&u->postcopy_fd);
return 0;
#else
error_setg(errp, "Postcopy not supported on non-Linux systems");
return -ENOSYS;
#endif
}
/*
* Called at the switch to postcopy on reception of the 'listen' command.
*/
static int vhost_user_postcopy_listen(struct vhost_dev *dev, Error **errp)
{
struct vhost_user *u = dev->opaque;
int ret;
VhostUserMsg msg = {
.hdr.request = VHOST_USER_POSTCOPY_LISTEN,
.hdr.flags = VHOST_USER_VERSION | VHOST_USER_NEED_REPLY_MASK,
};
u->postcopy_listen = true;
trace_vhost_user_postcopy_listen();
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
error_setg(errp, "Failed to send postcopy_listen to vhost");
return ret;
}
ret = process_message_reply(dev, &msg);
if (ret) {
error_setg(errp, "Failed to receive reply to postcopy_listen");
return ret;
}
return 0;
}
/*
* Called at the end of postcopy
*/
static int vhost_user_postcopy_end(struct vhost_dev *dev, Error **errp)
{
VhostUserMsg msg = {
.hdr.request = VHOST_USER_POSTCOPY_END,
.hdr.flags = VHOST_USER_VERSION | VHOST_USER_NEED_REPLY_MASK,
};
int ret;
struct vhost_user *u = dev->opaque;
trace_vhost_user_postcopy_end_entry();
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
error_setg(errp, "Failed to send postcopy_end to vhost");
return ret;
}
ret = process_message_reply(dev, &msg);
if (ret) {
error_setg(errp, "Failed to receive reply to postcopy_end");
return ret;
}
postcopy_unregister_shared_ufd(&u->postcopy_fd);
close(u->postcopy_fd.fd);
u->postcopy_fd.handler = NULL;
trace_vhost_user_postcopy_end_exit();
return 0;
}
static int vhost_user_postcopy_notifier(NotifierWithReturn *notifier,
void *opaque, Error **errp)
{
struct PostcopyNotifyData *pnd = opaque;
struct vhost_user *u = container_of(notifier, struct vhost_user,
postcopy_notifier);
struct vhost_dev *dev = u->dev;
switch (pnd->reason) {
case POSTCOPY_NOTIFY_PROBE:
if (!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_PAGEFAULT)) {
/* TODO: Get the device name into this error somehow */
error_setg(errp,
"vhost-user backend not capable of postcopy");
return -ENOENT;
}
break;
case POSTCOPY_NOTIFY_INBOUND_ADVISE:
return vhost_user_postcopy_advise(dev, errp);
case POSTCOPY_NOTIFY_INBOUND_LISTEN:
return vhost_user_postcopy_listen(dev, errp);
case POSTCOPY_NOTIFY_INBOUND_END:
return vhost_user_postcopy_end(dev, errp);
default:
/* We ignore notifications we don't know */
break;
}
return 0;
}
static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque,
Error **errp)
{
uint64_t features, ram_slots;
struct vhost_user *u;
VhostUserState *vus = (VhostUserState *) opaque;
int err;
assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
u = g_new0(struct vhost_user, 1);
u->user = vus;
u->dev = dev;
dev->opaque = u;
err = vhost_user_get_features(dev, &features);
if (err < 0) {
error_setg_errno(errp, -err, "vhost_backend_init failed");
return err;
}
if (virtio_has_feature(features, VHOST_USER_F_PROTOCOL_FEATURES)) {
bool supports_f_config = vus->supports_config ||
(dev->config_ops && dev->config_ops->vhost_dev_config_notifier);
uint64_t protocol_features;
dev->backend_features |= 1ULL << VHOST_USER_F_PROTOCOL_FEATURES;
err = vhost_user_get_u64(dev, VHOST_USER_GET_PROTOCOL_FEATURES,
&protocol_features);
if (err < 0) {
error_setg_errno(errp, EPROTO, "vhost_backend_init failed");
return -EPROTO;
}
/*
* We will use all the protocol features we support - although
* we suppress F_CONFIG if we know QEMUs internal code can not support
* it.
*/
protocol_features &= VHOST_USER_PROTOCOL_FEATURE_MASK;
if (supports_f_config) {
if (!virtio_has_feature(protocol_features,
VHOST_USER_PROTOCOL_F_CONFIG)) {
error_setg(errp, "vhost-user device expecting "
"VHOST_USER_PROTOCOL_F_CONFIG but the vhost-user backend does "
"not support it.");
return -EPROTO;
}
} else {
if (virtio_has_feature(protocol_features,
VHOST_USER_PROTOCOL_F_CONFIG)) {
warn_report("vhost-user backend supports "
"VHOST_USER_PROTOCOL_F_CONFIG but QEMU does not.");
protocol_features &= ~(1ULL << VHOST_USER_PROTOCOL_F_CONFIG);
}
}
/* final set of protocol features */
dev->protocol_features = protocol_features;
err = vhost_user_set_protocol_features(dev, dev->protocol_features);
if (err < 0) {
error_setg_errno(errp, EPROTO, "vhost_backend_init failed");
return -EPROTO;
}
/* query the max queues we support if backend supports Multiple Queue */
if (dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ)) {
err = vhost_user_get_u64(dev, VHOST_USER_GET_QUEUE_NUM,
&dev->max_queues);
if (err < 0) {
error_setg_errno(errp, EPROTO, "vhost_backend_init failed");
return -EPROTO;
}
} else {
dev->max_queues = 1;
}
if (dev->num_queues && dev->max_queues < dev->num_queues) {
error_setg(errp, "The maximum number of queues supported by the "
"backend is %" PRIu64, dev->max_queues);
return -EINVAL;
}
if (virtio_has_feature(features, VIRTIO_F_IOMMU_PLATFORM) &&
!(virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_BACKEND_REQ) &&
virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_REPLY_ACK))) {
error_setg(errp, "IOMMU support requires reply-ack and "
"backend-req protocol features.");
return -EINVAL;
}
/* get max memory regions if backend supports configurable RAM slots */
if (!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS)) {
u->user->memory_slots = VHOST_MEMORY_BASELINE_NREGIONS;
} else {
err = vhost_user_get_max_memslots(dev, &ram_slots);
if (err < 0) {
error_setg_errno(errp, EPROTO, "vhost_backend_init failed");
return -EPROTO;
}
if (ram_slots < u->user->memory_slots) {
error_setg(errp, "The backend specified a max ram slots limit "
"of %" PRIu64", when the prior validated limit was "
"%d. This limit should never decrease.", ram_slots,
u->user->memory_slots);
return -EINVAL;
}
u->user->memory_slots = MIN(ram_slots, VHOST_USER_MAX_RAM_SLOTS);
}
}
if (dev->migration_blocker == NULL &&
!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_LOG_SHMFD)) {
error_setg(&dev->migration_blocker,
"Migration disabled: vhost-user backend lacks "
"VHOST_USER_PROTOCOL_F_LOG_SHMFD feature.");
}
if (dev->vq_index == 0) {
err = vhost_setup_backend_channel(dev);
if (err < 0) {
error_setg_errno(errp, EPROTO, "vhost_backend_init failed");
return -EPROTO;
}
}
u->postcopy_notifier.notify = vhost_user_postcopy_notifier;
postcopy_add_notifier(&u->postcopy_notifier);
return 0;
}
static int vhost_user_backend_cleanup(struct vhost_dev *dev)
{
struct vhost_user *u;
assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
u = dev->opaque;
if (u->postcopy_notifier.notify) {
postcopy_remove_notifier(&u->postcopy_notifier);
u->postcopy_notifier.notify = NULL;
}
u->postcopy_listen = false;
if (u->postcopy_fd.handler) {
postcopy_unregister_shared_ufd(&u->postcopy_fd);
close(u->postcopy_fd.fd);
u->postcopy_fd.handler = NULL;
}
if (u->backend_ioc) {
close_backend_channel(u);
}
g_free(u->region_rb);
u->region_rb = NULL;
g_free(u->region_rb_offset);
u->region_rb_offset = NULL;
u->region_rb_len = 0;
g_free(u);
dev->opaque = 0;
return 0;
}
static int vhost_user_get_vq_index(struct vhost_dev *dev, int idx)
{
assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs);
return idx;
}
static int vhost_user_memslots_limit(struct vhost_dev *dev)
{
struct vhost_user *u = dev->opaque;
return u->user->memory_slots;
}
static bool vhost_user_requires_shm_log(struct vhost_dev *dev)
{
assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
return virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_LOG_SHMFD);
}
static int vhost_user_migration_done(struct vhost_dev *dev, char* mac_addr)
{
VhostUserMsg msg = { };
assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
/* If guest supports GUEST_ANNOUNCE do nothing */
if (virtio_has_feature(dev->acked_features, VIRTIO_NET_F_GUEST_ANNOUNCE)) {
return 0;
}
/* if backend supports VHOST_USER_PROTOCOL_F_RARP ask it to send the RARP */
if (virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_RARP)) {
msg.hdr.request = VHOST_USER_SEND_RARP;
msg.hdr.flags = VHOST_USER_VERSION;
memcpy((char *)&msg.payload.u64, mac_addr, 6);
msg.hdr.size = sizeof(msg.payload.u64);
return vhost_user_write(dev, &msg, NULL, 0);
}
return -ENOTSUP;
}
static int vhost_user_net_set_mtu(struct vhost_dev *dev, uint16_t mtu)
{
VhostUserMsg msg;
bool reply_supported = virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_REPLY_ACK);
int ret;
if (!(dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_NET_MTU))) {
return 0;
}
msg.hdr.request = VHOST_USER_NET_SET_MTU;
msg.payload.u64 = mtu;
msg.hdr.size = sizeof(msg.payload.u64);
msg.hdr.flags = VHOST_USER_VERSION;
if (reply_supported) {
msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
}
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
return ret;
}
/* If reply_ack supported, backend has to ack specified MTU is valid */
if (reply_supported) {
return process_message_reply(dev, &msg);
}
return 0;
}
static int vhost_user_send_device_iotlb_msg(struct vhost_dev *dev,
struct vhost_iotlb_msg *imsg)
{
int ret;
VhostUserMsg msg = {
.hdr.request = VHOST_USER_IOTLB_MSG,
.hdr.size = sizeof(msg.payload.iotlb),
.hdr.flags = VHOST_USER_VERSION | VHOST_USER_NEED_REPLY_MASK,
.payload.iotlb = *imsg,
};
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
return ret;
}
return process_message_reply(dev, &msg);
}
static void vhost_user_set_iotlb_callback(struct vhost_dev *dev, int enabled)
{
/* No-op as the receive channel is not dedicated to IOTLB messages. */
}
static int vhost_user_get_config(struct vhost_dev *dev, uint8_t *config,
uint32_t config_len, Error **errp)
{
int ret;
VhostUserMsg msg = {
.hdr.request = VHOST_USER_GET_CONFIG,
.hdr.flags = VHOST_USER_VERSION,
.hdr.size = VHOST_USER_CONFIG_HDR_SIZE + config_len,
};
if (!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_CONFIG)) {
error_setg(errp, "VHOST_USER_PROTOCOL_F_CONFIG not supported");
return -EINVAL;
}
assert(config_len <= VHOST_USER_MAX_CONFIG_SIZE);
msg.payload.config.offset = 0;
msg.payload.config.size = config_len;
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
error_setg_errno(errp, -ret, "vhost_get_config failed");
return ret;
}
ret = vhost_user_read(dev, &msg);
if (ret < 0) {
error_setg_errno(errp, -ret, "vhost_get_config failed");
return ret;
}
if (msg.hdr.request != VHOST_USER_GET_CONFIG) {
error_setg(errp,
"Received unexpected msg type. Expected %d received %d",
VHOST_USER_GET_CONFIG, msg.hdr.request);
return -EPROTO;
}
if (msg.hdr.size != VHOST_USER_CONFIG_HDR_SIZE + config_len) {
error_setg(errp, "Received bad msg size.");
return -EPROTO;
}
memcpy(config, msg.payload.config.region, config_len);
return 0;
}
static int vhost_user_set_config(struct vhost_dev *dev, const uint8_t *data,
uint32_t offset, uint32_t size, uint32_t flags)
{
int ret;
uint8_t *p;
bool reply_supported = virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_REPLY_ACK);
VhostUserMsg msg = {
.hdr.request = VHOST_USER_SET_CONFIG,
.hdr.flags = VHOST_USER_VERSION,
.hdr.size = VHOST_USER_CONFIG_HDR_SIZE + size,
};
if (!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_CONFIG)) {
return -ENOTSUP;
}
if (reply_supported) {
msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
}
if (size > VHOST_USER_MAX_CONFIG_SIZE) {
return -EINVAL;
}
msg.payload.config.offset = offset,
msg.payload.config.size = size,
msg.payload.config.flags = flags,
p = msg.payload.config.region;
memcpy(p, data, size);
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
return ret;
}
if (reply_supported) {
return process_message_reply(dev, &msg);
}
return 0;
}
static int vhost_user_crypto_create_session(struct vhost_dev *dev,
void *session_info,
uint64_t *session_id)
{
int ret;
bool crypto_session = virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_CRYPTO_SESSION);
CryptoDevBackendSessionInfo *backend_info = session_info;
VhostUserMsg msg = {
.hdr.request = VHOST_USER_CREATE_CRYPTO_SESSION,
.hdr.flags = VHOST_USER_VERSION,
.hdr.size = sizeof(msg.payload.session),
};
assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
if (!crypto_session) {
error_report("vhost-user trying to send unhandled ioctl");
return -ENOTSUP;
}
if (backend_info->op_code == VIRTIO_CRYPTO_AKCIPHER_CREATE_SESSION) {
CryptoDevBackendAsymSessionInfo *sess = &backend_info->u.asym_sess_info;
size_t keylen;
memcpy(&msg.payload.session.u.asym.session_setup_data, sess,
sizeof(CryptoDevBackendAsymSessionInfo));
if (sess->keylen) {
keylen = sizeof(msg.payload.session.u.asym.key);
if (sess->keylen > keylen) {
error_report("Unsupported asymmetric key size");
return -ENOTSUP;
}
memcpy(&msg.payload.session.u.asym.key, sess->key,
sess->keylen);
}
} else {
CryptoDevBackendSymSessionInfo *sess = &backend_info->u.sym_sess_info;
size_t keylen;
memcpy(&msg.payload.session.u.sym.session_setup_data, sess,
sizeof(CryptoDevBackendSymSessionInfo));
if (sess->key_len) {
keylen = sizeof(msg.payload.session.u.sym.key);
if (sess->key_len > keylen) {
error_report("Unsupported cipher key size");
return -ENOTSUP;
}
memcpy(&msg.payload.session.u.sym.key, sess->cipher_key,
sess->key_len);
}
if (sess->auth_key_len > 0) {
keylen = sizeof(msg.payload.session.u.sym.auth_key);
if (sess->auth_key_len > keylen) {
error_report("Unsupported auth key size");
return -ENOTSUP;
}
memcpy(&msg.payload.session.u.sym.auth_key, sess->auth_key,
sess->auth_key_len);
}
}
msg.payload.session.op_code = backend_info->op_code;
msg.payload.session.session_id = backend_info->session_id;
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
error_report("vhost_user_write() return %d, create session failed",
ret);
return ret;
}
ret = vhost_user_read(dev, &msg);
if (ret < 0) {
error_report("vhost_user_read() return %d, create session failed",
ret);
return ret;
}
if (msg.hdr.request != VHOST_USER_CREATE_CRYPTO_SESSION) {
error_report("Received unexpected msg type. Expected %d received %d",
VHOST_USER_CREATE_CRYPTO_SESSION, msg.hdr.request);
return -EPROTO;
}
if (msg.hdr.size != sizeof(msg.payload.session)) {
error_report("Received bad msg size.");
return -EPROTO;
}
if (msg.payload.session.session_id < 0) {
error_report("Bad session id: %" PRId64 "",
msg.payload.session.session_id);
return -EINVAL;
}
*session_id = msg.payload.session.session_id;
return 0;
}
static int
vhost_user_crypto_close_session(struct vhost_dev *dev, uint64_t session_id)
{
int ret;
bool crypto_session = virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_CRYPTO_SESSION);
VhostUserMsg msg = {
.hdr.request = VHOST_USER_CLOSE_CRYPTO_SESSION,
.hdr.flags = VHOST_USER_VERSION,
.hdr.size = sizeof(msg.payload.u64),
};
msg.payload.u64 = session_id;
if (!crypto_session) {
error_report("vhost-user trying to send unhandled ioctl");
return -ENOTSUP;
}
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
error_report("vhost_user_write() return %d, close session failed",
ret);
return ret;
}
return 0;
}
static bool vhost_user_no_private_memslots(struct vhost_dev *dev)
{
return true;
}
static int vhost_user_get_inflight_fd(struct vhost_dev *dev,
uint16_t queue_size,
struct vhost_inflight *inflight)
{
void *addr;
int fd;
int ret;
struct vhost_user *u = dev->opaque;
CharBackend *chr = u->user->chr;
VhostUserMsg msg = {
.hdr.request = VHOST_USER_GET_INFLIGHT_FD,
.hdr.flags = VHOST_USER_VERSION,
.payload.inflight.num_queues = dev->nvqs,
.payload.inflight.queue_size = queue_size,
.hdr.size = sizeof(msg.payload.inflight),
};
if (!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD)) {
return 0;
}
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
return ret;
}
ret = vhost_user_read(dev, &msg);
if (ret < 0) {
return ret;
}
if (msg.hdr.request != VHOST_USER_GET_INFLIGHT_FD) {
error_report("Received unexpected msg type. "
"Expected %d received %d",
VHOST_USER_GET_INFLIGHT_FD, msg.hdr.request);
return -EPROTO;
}
if (msg.hdr.size != sizeof(msg.payload.inflight)) {
error_report("Received bad msg size.");
return -EPROTO;
}
if (!msg.payload.inflight.mmap_size) {
return 0;
}
fd = qemu_chr_fe_get_msgfd(chr);
if (fd < 0) {
error_report("Failed to get mem fd");
return -EIO;
}
addr = mmap(0, msg.payload.inflight.mmap_size, PROT_READ | PROT_WRITE,
MAP_SHARED, fd, msg.payload.inflight.mmap_offset);
if (addr == MAP_FAILED) {
error_report("Failed to mmap mem fd");
close(fd);
return -EFAULT;
}
inflight->addr = addr;
inflight->fd = fd;
inflight->size = msg.payload.inflight.mmap_size;
inflight->offset = msg.payload.inflight.mmap_offset;
inflight->queue_size = queue_size;
return 0;
}
static int vhost_user_set_inflight_fd(struct vhost_dev *dev,
struct vhost_inflight *inflight)
{
VhostUserMsg msg = {
.hdr.request = VHOST_USER_SET_INFLIGHT_FD,
.hdr.flags = VHOST_USER_VERSION,
.payload.inflight.mmap_size = inflight->size,
.payload.inflight.mmap_offset = inflight->offset,
.payload.inflight.num_queues = dev->nvqs,
.payload.inflight.queue_size = inflight->queue_size,
.hdr.size = sizeof(msg.payload.inflight),
};
if (!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD)) {
return 0;
}
return vhost_user_write(dev, &msg, &inflight->fd, 1);
}
static void vhost_user_state_destroy(gpointer data)
{
VhostUserHostNotifier *n = (VhostUserHostNotifier *) data;
vhost_user_host_notifier_remove(n, NULL, true);
}
bool vhost_user_init(VhostUserState *user, CharBackend *chr, Error **errp)
{
if (user->chr) {
error_setg(errp, "Cannot initialize vhost-user state");
return false;
}
user->chr = chr;
user->memory_slots = 0;
user->notifiers = g_ptr_array_new_full(VIRTIO_QUEUE_MAX / 4,
&vhost_user_state_destroy);
return true;
}
void vhost_user_cleanup(VhostUserState *user)
{
if (!user->chr) {
return;
}
user->notifiers = (GPtrArray *) g_ptr_array_free(user->notifiers, true);
user->chr = NULL;
}
typedef struct {
vu_async_close_fn cb;
DeviceState *dev;
CharBackend *cd;
struct vhost_dev *vhost;
} VhostAsyncCallback;
static void vhost_user_async_close_bh(void *opaque)
{
VhostAsyncCallback *data = opaque;
data->cb(data->dev);
g_free(data);
}
/*
* We only schedule the work if the machine is running. If suspended
* we want to keep all the in-flight data as is for migration
* purposes.
*/
void vhost_user_async_close(DeviceState *d,
CharBackend *chardev, struct vhost_dev *vhost,
vu_async_close_fn cb)
{
if (!runstate_check(RUN_STATE_SHUTDOWN)) {
/*
* A close event may happen during a read/write, but vhost
* code assumes the vhost_dev remains setup, so delay the
* stop & clear.
*/
AioContext *ctx = qemu_get_current_aio_context();
VhostAsyncCallback *data = g_new0(VhostAsyncCallback, 1);
/* Save data for the callback */
data->cb = cb;
data->dev = d;
data->cd = chardev;
data->vhost = vhost;
/* Disable any further notifications on the chardev */
qemu_chr_fe_set_handlers(chardev,
NULL, NULL, NULL, NULL, NULL, NULL,
false);
aio_bh_schedule_oneshot(ctx, vhost_user_async_close_bh, data);
/*
* Move vhost device to the stopped state. The vhost-user device
* will be clean up and disconnected in BH. This can be useful in
* the vhost migration code. If disconnect was caught there is an
* option for the general vhost code to get the dev state without
* knowing its type (in this case vhost-user).
*
* Note if the vhost device is fully cleared by the time we
* execute the bottom half we won't continue with the cleanup.
*/
vhost->started = false;
}
}
static int vhost_user_dev_start(struct vhost_dev *dev, bool started)
{
if (!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_STATUS)) {
return 0;
}
/* Set device status only for last queue pair */
if (dev->vq_index + dev->nvqs != dev->vq_index_end) {
return 0;
}
if (started) {
return vhost_user_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE |
VIRTIO_CONFIG_S_DRIVER |
VIRTIO_CONFIG_S_DRIVER_OK);
} else {
return 0;
}
}
static void vhost_user_reset_status(struct vhost_dev *dev)
{
/* Set device status only for last queue pair */
if (dev->vq_index + dev->nvqs != dev->vq_index_end) {
return;
}
if (virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_STATUS)) {
vhost_user_set_status(dev, 0);
}
}
static bool vhost_user_supports_device_state(struct vhost_dev *dev)
{
return virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_DEVICE_STATE);
}
static int vhost_user_set_device_state_fd(struct vhost_dev *dev,
VhostDeviceStateDirection direction,
VhostDeviceStatePhase phase,
int fd,
int *reply_fd,
Error **errp)
{
int ret;
struct vhost_user *vu = dev->opaque;
VhostUserMsg msg = {
.hdr = {
.request = VHOST_USER_SET_DEVICE_STATE_FD,
.flags = VHOST_USER_VERSION,
.size = sizeof(msg.payload.transfer_state),
},
.payload.transfer_state = {
.direction = direction,
.phase = phase,
},
};
*reply_fd = -1;
if (!vhost_user_supports_device_state(dev)) {
close(fd);
error_setg(errp, "Back-end does not support migration state transfer");
return -ENOTSUP;
}
ret = vhost_user_write(dev, &msg, &fd, 1);
close(fd);
if (ret < 0) {
error_setg_errno(errp, -ret,
"Failed to send SET_DEVICE_STATE_FD message");
return ret;
}
ret = vhost_user_read(dev, &msg);
if (ret < 0) {
error_setg_errno(errp, -ret,
"Failed to receive SET_DEVICE_STATE_FD reply");
return ret;
}
if (msg.hdr.request != VHOST_USER_SET_DEVICE_STATE_FD) {
error_setg(errp,
"Received unexpected message type, expected %d, received %d",
VHOST_USER_SET_DEVICE_STATE_FD, msg.hdr.request);
return -EPROTO;
}
if (msg.hdr.size != sizeof(msg.payload.u64)) {
error_setg(errp,
"Received bad message size, expected %zu, received %" PRIu32,
sizeof(msg.payload.u64), msg.hdr.size);
return -EPROTO;
}
if ((msg.payload.u64 & 0xff) != 0) {
error_setg(errp, "Back-end did not accept migration state transfer");
return -EIO;
}
if (!(msg.payload.u64 & VHOST_USER_VRING_NOFD_MASK)) {
*reply_fd = qemu_chr_fe_get_msgfd(vu->user->chr);
if (*reply_fd < 0) {
error_setg(errp,
"Failed to get back-end-provided transfer pipe FD");
*reply_fd = -1;
return -EIO;
}
}
return 0;
}
static int vhost_user_check_device_state(struct vhost_dev *dev, Error **errp)
{
int ret;
VhostUserMsg msg = {
.hdr = {
.request = VHOST_USER_CHECK_DEVICE_STATE,
.flags = VHOST_USER_VERSION,
.size = 0,
},
};
if (!vhost_user_supports_device_state(dev)) {
error_setg(errp, "Back-end does not support migration state transfer");
return -ENOTSUP;
}
ret = vhost_user_write(dev, &msg, NULL, 0);
if (ret < 0) {
error_setg_errno(errp, -ret,
"Failed to send CHECK_DEVICE_STATE message");
return ret;
}
ret = vhost_user_read(dev, &msg);
if (ret < 0) {
error_setg_errno(errp, -ret,
"Failed to receive CHECK_DEVICE_STATE reply");
return ret;
}
if (msg.hdr.request != VHOST_USER_CHECK_DEVICE_STATE) {
error_setg(errp,
"Received unexpected message type, expected %d, received %d",
VHOST_USER_CHECK_DEVICE_STATE, msg.hdr.request);
return -EPROTO;
}
if (msg.hdr.size != sizeof(msg.payload.u64)) {
error_setg(errp,
"Received bad message size, expected %zu, received %" PRIu32,
sizeof(msg.payload.u64), msg.hdr.size);
return -EPROTO;
}
if (msg.payload.u64 != 0) {
error_setg(errp, "Back-end failed to process its internal state");
return -EIO;
}
return 0;
}
const VhostOps user_ops = {
.backend_type = VHOST_BACKEND_TYPE_USER,
.vhost_backend_init = vhost_user_backend_init,
.vhost_backend_cleanup = vhost_user_backend_cleanup,
.vhost_backend_memslots_limit = vhost_user_memslots_limit,
.vhost_backend_no_private_memslots = vhost_user_no_private_memslots,
.vhost_set_log_base = vhost_user_set_log_base,
.vhost_set_mem_table = vhost_user_set_mem_table,
.vhost_set_vring_addr = vhost_user_set_vring_addr,
.vhost_set_vring_endian = vhost_user_set_vring_endian,
.vhost_set_vring_num = vhost_user_set_vring_num,
.vhost_set_vring_base = vhost_user_set_vring_base,
.vhost_get_vring_base = vhost_user_get_vring_base,
.vhost_set_vring_kick = vhost_user_set_vring_kick,
.vhost_set_vring_call = vhost_user_set_vring_call,
.vhost_set_vring_err = vhost_user_set_vring_err,
.vhost_set_features = vhost_user_set_features,
.vhost_get_features = vhost_user_get_features,
.vhost_set_owner = vhost_user_set_owner,
.vhost_reset_device = vhost_user_reset_device,
.vhost_get_vq_index = vhost_user_get_vq_index,
.vhost_set_vring_enable = vhost_user_set_vring_enable,
.vhost_requires_shm_log = vhost_user_requires_shm_log,
.vhost_migration_done = vhost_user_migration_done,
.vhost_net_set_mtu = vhost_user_net_set_mtu,
.vhost_set_iotlb_callback = vhost_user_set_iotlb_callback,
.vhost_send_device_iotlb_msg = vhost_user_send_device_iotlb_msg,
.vhost_get_config = vhost_user_get_config,
.vhost_set_config = vhost_user_set_config,
.vhost_crypto_create_session = vhost_user_crypto_create_session,
.vhost_crypto_close_session = vhost_user_crypto_close_session,
.vhost_get_inflight_fd = vhost_user_get_inflight_fd,
.vhost_set_inflight_fd = vhost_user_set_inflight_fd,
.vhost_dev_start = vhost_user_dev_start,
.vhost_reset_status = vhost_user_reset_status,
.vhost_supports_device_state = vhost_user_supports_device_state,
.vhost_set_device_state_fd = vhost_user_set_device_state_fd,
.vhost_check_device_state = vhost_user_check_device_state,
};
|