Eric Lee / smarc-fsl-linux-kernel

pci-hyperv.c 96.6 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) Microsoft Corporation.
 *
 * Author:
 *   Jake Oshins <jakeo@microsoft.com>
 *
 * This driver acts as a paravirtual front-end for PCI Express root buses.
 * When a PCI Express function (either an entire device or an SR-IOV
 * Virtual Function) is being passed through to the VM, this driver exposes
 * a new bus to the guest VM.  This is modeled as a root PCI bus because
 * no bridges are being exposed to the VM.  In fact, with a "Generation 2"
 * VM within Hyper-V, there may seem to be no PCI bus at all in the VM
 * until a device as been exposed using this driver.
 *
 * Each root PCI bus has its own PCI domain, which is called "Segment" in
 * the PCI Firmware Specifications.  Thus while each device passed through
 * to the VM using this front-end will appear at "device 0", the domain will
 * be unique.  Typically, each bus will have one PCI function on it, though
 * this driver does support more than one.
 *
 * In order to map the interrupts from the device through to the guest VM,
 * this driver also implements an IRQ Domain, which handles interrupts (either
 * MSI or MSI-X) associated with the functions on the bus.  As interrupts are
 * set up, torn down, or reaffined, this driver communicates with the
 * underlying hypervisor to adjust the mappings in the I/O MMU so that each
 * interrupt will be delivered to the correct virtual processor at the right
 * vector.  This driver does not support level-triggered (line-based)
 * interrupts, and will report that the Interrupt Line register in the
 * function's configuration space is zero.
 *
 * The rest of this driver mostly maps PCI concepts onto underlying Hyper-V
 * facilities.  For instance, the configuration space of a function exposed
 * by Hyper-V is mapped into a single page of memory space, and the
 * read and write handlers for config space must be aware of this mechanism.
 * Similarly, device setup and teardown involves messages sent to and from
 * the PCI back-end driver in Hyper-V.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/delay.h>
#include <linux/semaphore.h>
#include <linux/irqdomain.h>
#include <asm/irqdomain.h>
#include <asm/apic.h>
#include <linux/irq.h>
#include <linux/msi.h>
#include <linux/hyperv.h>
#include <linux/refcount.h>
#include <asm/mshyperv.h>

/*
 * Protocol versions. The low word is the minor version, the high word the
 * major version.
 */

#define PCI_MAKE_VERSION(major, minor) ((u32)(((major) << 16) | (minor)))
#define PCI_MAJOR_VERSION(version) ((u32)(version) >> 16)
#define PCI_MINOR_VERSION(version) ((u32)(version) & 0xff)

enum pci_protocol_version_t {
	PCI_PROTOCOL_VERSION_1_1 = PCI_MAKE_VERSION(1, 1),	/* Win10 */
	PCI_PROTOCOL_VERSION_1_2 = PCI_MAKE_VERSION(1, 2),	/* RS1 */
	PCI_PROTOCOL_VERSION_1_3 = PCI_MAKE_VERSION(1, 3),	/* Vibranium */
};

#define CPU_AFFINITY_ALL	-1ULL

/*
 * Supported protocol versions in the order of probing - highest go
 * first.
 */
static enum pci_protocol_version_t pci_protocol_versions[] = {
	PCI_PROTOCOL_VERSION_1_3,
	PCI_PROTOCOL_VERSION_1_2,
	PCI_PROTOCOL_VERSION_1_1,
};

#define PCI_CONFIG_MMIO_LENGTH	0x2000
#define CFG_PAGE_OFFSET 0x1000
#define CFG_PAGE_SIZE (PCI_CONFIG_MMIO_LENGTH - CFG_PAGE_OFFSET)

#define MAX_SUPPORTED_MSI_MESSAGES 0x400

#define STATUS_REVISION_MISMATCH 0xC0000059

/* space for 32bit serial number as string */
#define SLOT_NAME_SIZE 11

/*
 * Message Types
 */

enum pci_message_type {
	/*
	 * Version 1.1
	 */
	PCI_MESSAGE_BASE                = 0x42490000,
	PCI_BUS_RELATIONS               = PCI_MESSAGE_BASE + 0,
	PCI_QUERY_BUS_RELATIONS         = PCI_MESSAGE_BASE + 1,
	PCI_POWER_STATE_CHANGE          = PCI_MESSAGE_BASE + 4,
	PCI_QUERY_RESOURCE_REQUIREMENTS = PCI_MESSAGE_BASE + 5,
	PCI_QUERY_RESOURCE_RESOURCES    = PCI_MESSAGE_BASE + 6,
	PCI_BUS_D0ENTRY                 = PCI_MESSAGE_BASE + 7,
	PCI_BUS_D0EXIT                  = PCI_MESSAGE_BASE + 8,
	PCI_READ_BLOCK                  = PCI_MESSAGE_BASE + 9,
	PCI_WRITE_BLOCK                 = PCI_MESSAGE_BASE + 0xA,
	PCI_EJECT                       = PCI_MESSAGE_BASE + 0xB,
	PCI_QUERY_STOP                  = PCI_MESSAGE_BASE + 0xC,
	PCI_REENABLE                    = PCI_MESSAGE_BASE + 0xD,
	PCI_QUERY_STOP_FAILED           = PCI_MESSAGE_BASE + 0xE,
	PCI_EJECTION_COMPLETE           = PCI_MESSAGE_BASE + 0xF,
	PCI_RESOURCES_ASSIGNED          = PCI_MESSAGE_BASE + 0x10,
	PCI_RESOURCES_RELEASED          = PCI_MESSAGE_BASE + 0x11,
	PCI_INVALIDATE_BLOCK            = PCI_MESSAGE_BASE + 0x12,
	PCI_QUERY_PROTOCOL_VERSION      = PCI_MESSAGE_BASE + 0x13,
	PCI_CREATE_INTERRUPT_MESSAGE    = PCI_MESSAGE_BASE + 0x14,
	PCI_DELETE_INTERRUPT_MESSAGE    = PCI_MESSAGE_BASE + 0x15,
	PCI_RESOURCES_ASSIGNED2		= PCI_MESSAGE_BASE + 0x16,
	PCI_CREATE_INTERRUPT_MESSAGE2	= PCI_MESSAGE_BASE + 0x17,
	PCI_DELETE_INTERRUPT_MESSAGE2	= PCI_MESSAGE_BASE + 0x18, /* unused */
	PCI_BUS_RELATIONS2		= PCI_MESSAGE_BASE + 0x19,
	PCI_MESSAGE_MAXIMUM
};

/*
 * Structures defining the virtual PCI Express protocol.
 */

union pci_version {
	struct {
		u16 minor_version;
		u16 major_version;
	} parts;
	u32 version;
} __packed;

/*
 * Function numbers are 8-bits wide on Express, as interpreted through ARI,
 * which is all this driver does.  This representation is the one used in
 * Windows, which is what is expected when sending this back and forth with
 * the Hyper-V parent partition.
 */
union win_slot_encoding {
	struct {
		u32	dev:5;
		u32	func:3;
		u32	reserved:24;
	} bits;
	u32 slot;
} __packed;

/*
 * Pretty much as defined in the PCI Specifications.
 */
struct pci_function_description {
	u16	v_id;	/* vendor ID */
	u16	d_id;	/* device ID */
	u8	rev;
	u8	prog_intf;
	u8	subclass;
	u8	base_class;
	u32	subsystem_id;
	union win_slot_encoding win_slot;
	u32	ser;	/* serial number */
} __packed;

enum pci_device_description_flags {
	HV_PCI_DEVICE_FLAG_NONE			= 0x0,
	HV_PCI_DEVICE_FLAG_NUMA_AFFINITY	= 0x1,
};

struct pci_function_description2 {
	u16	v_id;	/* vendor ID */
	u16	d_id;	/* device ID */
	u8	rev;
	u8	prog_intf;
	u8	subclass;
	u8	base_class;
	u32	subsystem_id;
	union	win_slot_encoding win_slot;
	u32	ser;	/* serial number */
	u32	flags;
	u16	virtual_numa_node;
	u16	reserved;
} __packed;

/**
 * struct hv_msi_desc
 * @vector:		IDT entry
 * @delivery_mode:	As defined in Intel's Programmer's
 *			Reference Manual, Volume 3, Chapter 8.
 * @vector_count:	Number of contiguous entries in the
 *			Interrupt Descriptor Table that are
 *			occupied by this Message-Signaled
 *			Interrupt. For "MSI", as first defined
 *			in PCI 2.2, this can be between 1 and
 *			32. For "MSI-X," as first defined in PCI
 *			3.0, this must be 1, as each MSI-X table
 *			entry would have its own descriptor.
 * @reserved:		Empty space
 * @cpu_mask:		All the target virtual processors.
 */
struct hv_msi_desc {
	u8	vector;
	u8	delivery_mode;
	u16	vector_count;
	u32	reserved;
	u64	cpu_mask;
} __packed;

/**
 * struct hv_msi_desc2 - 1.2 version of hv_msi_desc
 * @vector:		IDT entry
 * @delivery_mode:	As defined in Intel's Programmer's
 *			Reference Manual, Volume 3, Chapter 8.
 * @vector_count:	Number of contiguous entries in the
 *			Interrupt Descriptor Table that are
 *			occupied by this Message-Signaled
 *			Interrupt. For "MSI", as first defined
 *			in PCI 2.2, this can be between 1 and
 *			32. For "MSI-X," as first defined in PCI
 *			3.0, this must be 1, as each MSI-X table
 *			entry would have its own descriptor.
 * @processor_count:	number of bits enabled in array.
 * @processor_array:	All the target virtual processors.
 */
struct hv_msi_desc2 {
	u8	vector;
	u8	delivery_mode;
	u16	vector_count;
	u16	processor_count;
	u16	processor_array[32];
} __packed;

/**
 * struct tran_int_desc
 * @reserved:		unused, padding
 * @vector_count:	same as in hv_msi_desc
 * @data:		This is the "data payload" value that is
 *			written by the device when it generates
 *			a message-signaled interrupt, either MSI
 *			or MSI-X.
 * @address:		This is the address to which the data
 *			payload is written on interrupt
 *			generation.
 */
struct tran_int_desc {
	u16	reserved;
	u16	vector_count;
	u32	data;
	u64	address;
} __packed;

/*
 * A generic message format for virtual PCI.
 * Specific message formats are defined later in the file.
 */

struct pci_message {
	u32 type;
} __packed;

struct pci_child_message {
	struct pci_message message_type;
	union win_slot_encoding wslot;
} __packed;

struct pci_incoming_message {
	struct vmpacket_descriptor hdr;
	struct pci_message message_type;
} __packed;

struct pci_response {
	struct vmpacket_descriptor hdr;
	s32 status;			/* negative values are failures */
} __packed;

struct pci_packet {
	void (*completion_func)(void *context, struct pci_response *resp,
				int resp_packet_size);
	void *compl_ctxt;

	struct pci_message message[];
};

/*
 * Specific message types supporting the PCI protocol.
 */

/*
 * Version negotiation message. Sent from the guest to the host.
 * The guest is free to try different versions until the host
 * accepts the version.
 *
 * pci_version: The protocol version requested.
 * is_last_attempt: If TRUE, this is the last version guest will request.
 * reservedz: Reserved field, set to zero.
 */

struct pci_version_request {
	struct pci_message message_type;
	u32 protocol_version;
} __packed;

/*
 * Bus D0 Entry.  This is sent from the guest to the host when the virtual
 * bus (PCI Express port) is ready for action.
 */

struct pci_bus_d0_entry {
	struct pci_message message_type;
	u32 reserved;
	u64 mmio_base;
} __packed;

struct pci_bus_relations {
	struct pci_incoming_message incoming;
	u32 device_count;
	struct pci_function_description func[];
} __packed;

struct pci_bus_relations2 {
	struct pci_incoming_message incoming;
	u32 device_count;
	struct pci_function_description2 func[];
} __packed;

struct pci_q_res_req_response {
	struct vmpacket_descriptor hdr;
	s32 status;			/* negative values are failures */
	u32 probed_bar[PCI_STD_NUM_BARS];
} __packed;

struct pci_set_power {
	struct pci_message message_type;
	union win_slot_encoding wslot;
	u32 power_state;		/* In Windows terms */
	u32 reserved;
} __packed;

struct pci_set_power_response {
	struct vmpacket_descriptor hdr;
	s32 status;			/* negative values are failures */
	union win_slot_encoding wslot;
	u32 resultant_state;		/* In Windows terms */
	u32 reserved;
} __packed;

struct pci_resources_assigned {
	struct pci_message message_type;
	union win_slot_encoding wslot;
	u8 memory_range[0x14][6];	/* not used here */
	u32 msi_descriptors;
	u32 reserved[4];
} __packed;

struct pci_resources_assigned2 {
	struct pci_message message_type;
	union win_slot_encoding wslot;
	u8 memory_range[0x14][6];	/* not used here */
	u32 msi_descriptor_count;
	u8 reserved[70];
} __packed;

struct pci_create_interrupt {
	struct pci_message message_type;
	union win_slot_encoding wslot;
	struct hv_msi_desc int_desc;
} __packed;

struct pci_create_int_response {
	struct pci_response response;
	u32 reserved;
	struct tran_int_desc int_desc;
} __packed;

struct pci_create_interrupt2 {
	struct pci_message message_type;
	union win_slot_encoding wslot;
	struct hv_msi_desc2 int_desc;
} __packed;

struct pci_delete_interrupt {
	struct pci_message message_type;
	union win_slot_encoding wslot;
	struct tran_int_desc int_desc;
} __packed;

/*
 * Note: the VM must pass a valid block id, wslot and bytes_requested.
 */
struct pci_read_block {
	struct pci_message message_type;
	u32 block_id;
	union win_slot_encoding wslot;
	u32 bytes_requested;
} __packed;

struct pci_read_block_response {
	struct vmpacket_descriptor hdr;
	u32 status;
	u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX];
} __packed;

/*
 * Note: the VM must pass a valid block id, wslot and byte_count.
 */
struct pci_write_block {
	struct pci_message message_type;
	u32 block_id;
	union win_slot_encoding wslot;
	u32 byte_count;
	u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX];
} __packed;

struct pci_dev_inval_block {
	struct pci_incoming_message incoming;
	union win_slot_encoding wslot;
	u64 block_mask;
} __packed;

struct pci_dev_incoming {
	struct pci_incoming_message incoming;
	union win_slot_encoding wslot;
} __packed;

struct pci_eject_response {
	struct pci_message message_type;
	union win_slot_encoding wslot;
	u32 status;
} __packed;

static int pci_ring_size = (4 * PAGE_SIZE);

/*
 * Driver specific state.
 */

enum hv_pcibus_state {
	hv_pcibus_init = 0,
	hv_pcibus_probed,
	hv_pcibus_installed,
	hv_pcibus_removing,
	hv_pcibus_removed,
	hv_pcibus_maximum
};

struct hv_pcibus_device {
	struct pci_sysdata sysdata;
	/* Protocol version negotiated with the host */
	enum pci_protocol_version_t protocol_version;
	enum hv_pcibus_state state;
	refcount_t remove_lock;
	struct hv_device *hdev;
	resource_size_t low_mmio_space;
	resource_size_t high_mmio_space;
	struct resource *mem_config;
	struct resource *low_mmio_res;
	struct resource *high_mmio_res;
	struct completion *survey_event;
	struct completion remove_event;
	struct pci_bus *pci_bus;
	spinlock_t config_lock;	/* Avoid two threads writing index page */
	spinlock_t device_list_lock;	/* Protect lists below */
	void __iomem *cfg_addr;

	struct list_head resources_for_children;

	struct list_head children;
	struct list_head dr_list;

	struct msi_domain_info msi_info;
	struct msi_controller msi_chip;
	struct irq_domain *irq_domain;

	spinlock_t retarget_msi_interrupt_lock;

	struct workqueue_struct *wq;

	/* Highest slot of child device with resources allocated */
	int wslot_res_allocated;

	/* hypercall arg, must not cross page boundary */
	struct hv_retarget_device_interrupt retarget_msi_interrupt_params;

	/*
	 * Don't put anything here: retarget_msi_interrupt_params must be last
	 */
};

/*
 * Tracks "Device Relations" messages from the host, which must be both
 * processed in order and deferred so that they don't run in the context
 * of the incoming packet callback.
 */
struct hv_dr_work {
	struct work_struct wrk;
	struct hv_pcibus_device *bus;
};

struct hv_pcidev_description {
	u16	v_id;	/* vendor ID */
	u16	d_id;	/* device ID */
	u8	rev;
	u8	prog_intf;
	u8	subclass;
	u8	base_class;
	u32	subsystem_id;
	union	win_slot_encoding win_slot;
	u32	ser;	/* serial number */
	u32	flags;
	u16	virtual_numa_node;
};

struct hv_dr_state {
	struct list_head list_entry;
	u32 device_count;
	struct hv_pcidev_description func[];
};

enum hv_pcichild_state {
	hv_pcichild_init = 0,
	hv_pcichild_requirements,
	hv_pcichild_resourced,
	hv_pcichild_ejecting,
	hv_pcichild_maximum
};

struct hv_pci_dev {
	/* List protected by pci_rescan_remove_lock */
	struct list_head list_entry;
	refcount_t refs;
	enum hv_pcichild_state state;
	struct pci_slot *pci_slot;
	struct hv_pcidev_description desc;
	bool reported_missing;
	struct hv_pcibus_device *hbus;
	struct work_struct wrk;

	void (*block_invalidate)(void *context, u64 block_mask);
	void *invalidate_context;

	/*
	 * What would be observed if one wrote 0xFFFFFFFF to a BAR and then
	 * read it back, for each of the BAR offsets within config space.
	 */
	u32 probed_bar[PCI_STD_NUM_BARS];
};

struct hv_pci_compl {
	struct completion host_event;
	s32 completion_status;
};

static void hv_pci_onchannelcallback(void *context);

/**
 * hv_pci_generic_compl() - Invoked for a completion packet
 * @context:		Set up by the sender of the packet.
 * @resp:		The response packet
 * @resp_packet_size:	Size in bytes of the packet
 *
 * This function is used to trigger an event and report status
 * for any message for which the completion packet contains a
 * status and nothing else.
 */
static void hv_pci_generic_compl(void *context, struct pci_response *resp,
				 int resp_packet_size)
{
	struct hv_pci_compl *comp_pkt = context;

	if (resp_packet_size >= offsetofend(struct pci_response, status))
		comp_pkt->completion_status = resp->status;
	else
		comp_pkt->completion_status = -1;

	complete(&comp_pkt->host_event);
}

static struct hv_pci_dev *get_pcichild_wslot(struct hv_pcibus_device *hbus,
						u32 wslot);

static void get_pcichild(struct hv_pci_dev *hpdev)
{
	refcount_inc(&hpdev->refs);
}

static void put_pcichild(struct hv_pci_dev *hpdev)
{
	if (refcount_dec_and_test(&hpdev->refs))
		kfree(hpdev);
}

static void get_hvpcibus(struct hv_pcibus_device *hv_pcibus);
static void put_hvpcibus(struct hv_pcibus_device *hv_pcibus);

/*
 * There is no good way to get notified from vmbus_onoffer_rescind(),
 * so let's use polling here, since this is not a hot path.
 */
static int wait_for_response(struct hv_device *hdev,
			     struct completion *comp)
{
	while (true) {
		if (hdev->channel->rescind) {
			dev_warn_once(&hdev->device, "The device is gone.\n");
			return -ENODEV;
		}

		if (wait_for_completion_timeout(comp, HZ / 10))
			break;
	}

	return 0;
}

/**
 * devfn_to_wslot() - Convert from Linux PCI slot to Windows
 * @devfn:	The Linux representation of PCI slot
 *
 * Windows uses a slightly different representation of PCI slot.
 *
 * Return: The Windows representation
 */
static u32 devfn_to_wslot(int devfn)
{
	union win_slot_encoding wslot;

	wslot.slot = 0;
	wslot.bits.dev = PCI_SLOT(devfn);
	wslot.bits.func = PCI_FUNC(devfn);

	return wslot.slot;
}

/**
 * wslot_to_devfn() - Convert from Windows PCI slot to Linux
 * @wslot:	The Windows representation of PCI slot
 *
 * Windows uses a slightly different representation of PCI slot.
 *
 * Return: The Linux representation
 */
static int wslot_to_devfn(u32 wslot)
{
	union win_slot_encoding slot_no;

	slot_no.slot = wslot;
	return PCI_DEVFN(slot_no.bits.dev, slot_no.bits.func);
}

/*
 * PCI Configuration Space for these root PCI buses is implemented as a pair
 * of pages in memory-mapped I/O space.  Writing to the first page chooses
 * the PCI function being written or read.  Once the first page has been
 * written to, the following page maps in the entire configuration space of
 * the function.
 */

/**
 * _hv_pcifront_read_config() - Internal PCI config read
 * @hpdev:	The PCI driver's representation of the device
 * @where:	Offset within config space
 * @size:	Size of the transfer
 * @val:	Pointer to the buffer receiving the data
 */
static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where,
				     int size, u32 *val)
{
	unsigned long flags;
	void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where;

	/*
	 * If the attempt is to read the IDs or the ROM BAR, simulate that.
	 */
	if (where + size <= PCI_COMMAND) {
		memcpy(val, ((u8 *)&hpdev->desc.v_id) + where, size);
	} else if (where >= PCI_CLASS_REVISION && where + size <=
		   PCI_CACHE_LINE_SIZE) {
		memcpy(val, ((u8 *)&hpdev->desc.rev) + where -
		       PCI_CLASS_REVISION, size);
	} else if (where >= PCI_SUBSYSTEM_VENDOR_ID && where + size <=
		   PCI_ROM_ADDRESS) {
		memcpy(val, (u8 *)&hpdev->desc.subsystem_id + where -
		       PCI_SUBSYSTEM_VENDOR_ID, size);
	} else if (where >= PCI_ROM_ADDRESS && where + size <=
		   PCI_CAPABILITY_LIST) {
		/* ROM BARs are unimplemented */
		*val = 0;
	} else if (where >= PCI_INTERRUPT_LINE && where + size <=
		   PCI_INTERRUPT_PIN) {
		/*
		 * Interrupt Line and Interrupt PIN are hard-wired to zero
		 * because this front-end only supports message-signaled
		 * interrupts.
		 */
		*val = 0;
	} else if (where + size <= CFG_PAGE_SIZE) {
		spin_lock_irqsave(&hpdev->hbus->config_lock, flags);
		/* Choose the function to be read. (See comment above) */
		writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr);
		/* Make sure the function was chosen before we start reading. */
		mb();
		/* Read from that function's config space. */
		switch (size) {
		case 1:
			*val = readb(addr);
			break;
		case 2:
			*val = readw(addr);
			break;
		default:
			*val = readl(addr);
			break;
		}
		/*
		 * Make sure the read was done before we release the spinlock
		 * allowing consecutive reads/writes.
		 */
		mb();
		spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);
	} else {
		dev_err(&hpdev->hbus->hdev->device,
			"Attempt to read beyond a function's config space.\n");
	}
}

static u16 hv_pcifront_get_vendor_id(struct hv_pci_dev *hpdev)
{
	u16 ret;
	unsigned long flags;
	void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET +
			     PCI_VENDOR_ID;

	spin_lock_irqsave(&hpdev->hbus->config_lock, flags);

	/* Choose the function to be read. (See comment above) */
	writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr);
	/* Make sure the function was chosen before we start reading. */
	mb();
	/* Read from that function's config space. */
	ret = readw(addr);
	/*
	 * mb() is not required here, because the spin_unlock_irqrestore()
	 * is a barrier.
	 */

	spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);

	return ret;
}

/**
 * _hv_pcifront_write_config() - Internal PCI config write
 * @hpdev:	The PCI driver's representation of the device
 * @where:	Offset within config space
 * @size:	Size of the transfer
 * @val:	The data being transferred
 */
static void _hv_pcifront_write_config(struct hv_pci_dev *hpdev, int where,
				      int size, u32 val)
{
	unsigned long flags;
	void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where;

	if (where >= PCI_SUBSYSTEM_VENDOR_ID &&
	    where + size <= PCI_CAPABILITY_LIST) {
		/* SSIDs and ROM BARs are read-only */
	} else if (where >= PCI_COMMAND && where + size <= CFG_PAGE_SIZE) {
		spin_lock_irqsave(&hpdev->hbus->config_lock, flags);
		/* Choose the function to be written. (See comment above) */
		writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr);
		/* Make sure the function was chosen before we start writing. */
		wmb();
		/* Write to that function's config space. */
		switch (size) {
		case 1:
			writeb(val, addr);
			break;
		case 2:
			writew(val, addr);
			break;
		default:
			writel(val, addr);
			break;
		}
		/*
		 * Make sure the write was done before we release the spinlock
		 * allowing consecutive reads/writes.
		 */
		mb();
		spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);
	} else {
		dev_err(&hpdev->hbus->hdev->device,
			"Attempt to write beyond a function's config space.\n");
	}
}

/**
 * hv_pcifront_read_config() - Read configuration space
 * @bus: PCI Bus structure
 * @devfn: Device/function
 * @where: Offset from base
 * @size: Byte/word/dword
 * @val: Value to be read
 *
 * Return: PCIBIOS_SUCCESSFUL on success
 *	   PCIBIOS_DEVICE_NOT_FOUND on failure
 */
static int hv_pcifront_read_config(struct pci_bus *bus, unsigned int devfn,
				   int where, int size, u32 *val)
{
	struct hv_pcibus_device *hbus =
		container_of(bus->sysdata, struct hv_pcibus_device, sysdata);
	struct hv_pci_dev *hpdev;

	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(devfn));
	if (!hpdev)
		return PCIBIOS_DEVICE_NOT_FOUND;

	_hv_pcifront_read_config(hpdev, where, size, val);

	put_pcichild(hpdev);
	return PCIBIOS_SUCCESSFUL;
}

/**
 * hv_pcifront_write_config() - Write configuration space
 * @bus: PCI Bus structure
 * @devfn: Device/function
 * @where: Offset from base
 * @size: Byte/word/dword
 * @val: Value to be written to device
 *
 * Return: PCIBIOS_SUCCESSFUL on success
 *	   PCIBIOS_DEVICE_NOT_FOUND on failure
 */
static int hv_pcifront_write_config(struct pci_bus *bus, unsigned int devfn,
				    int where, int size, u32 val)
{
	struct hv_pcibus_device *hbus =
	    container_of(bus->sysdata, struct hv_pcibus_device, sysdata);
	struct hv_pci_dev *hpdev;

	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(devfn));
	if (!hpdev)
		return PCIBIOS_DEVICE_NOT_FOUND;

	_hv_pcifront_write_config(hpdev, where, size, val);

	put_pcichild(hpdev);
	return PCIBIOS_SUCCESSFUL;
}

/* PCIe operations */
static struct pci_ops hv_pcifront_ops = {
	.read  = hv_pcifront_read_config,
	.write = hv_pcifront_write_config,
};

/*
 * Paravirtual backchannel
 *
 * Hyper-V SR-IOV provides a backchannel mechanism in software for
 * communication between a VF driver and a PF driver.  These
 * "configuration blocks" are similar in concept to PCI configuration space,
 * but instead of doing reads and writes in 32-bit chunks through a very slow
 * path, packets of up to 128 bytes can be sent or received asynchronously.
 *
 * Nearly every SR-IOV device contains just such a communications channel in
 * hardware, so using this one in software is usually optional.  Using the
 * software channel, however, allows driver implementers to leverage software
 * tools that fuzz the communications channel looking for vulnerabilities.
 *
 * The usage model for these packets puts the responsibility for reading or
 * writing on the VF driver.  The VF driver sends a read or a write packet,
 * indicating which "block" is being referred to by number.
 *
 * If the PF driver wishes to initiate communication, it can "invalidate" one or
 * more of the first 64 blocks.  This invalidation is delivered via a callback
 * supplied by the VF driver by this driver.
 *
 * No protocol is implied, except that supplied by the PF and VF drivers.
 */

struct hv_read_config_compl {
	struct hv_pci_compl comp_pkt;
	void *buf;
	unsigned int len;
	unsigned int bytes_returned;
};

/**
 * hv_pci_read_config_compl() - Invoked when a response packet
 * for a read config block operation arrives.
 * @context:		Identifies the read config operation
 * @resp:		The response packet itself
 * @resp_packet_size:	Size in bytes of the response packet
 */
static void hv_pci_read_config_compl(void *context, struct pci_response *resp,
				     int resp_packet_size)
{
	struct hv_read_config_compl *comp = context;
	struct pci_read_block_response *read_resp =
		(struct pci_read_block_response *)resp;
	unsigned int data_len, hdr_len;

	hdr_len = offsetof(struct pci_read_block_response, bytes);
	if (resp_packet_size < hdr_len) {
		comp->comp_pkt.completion_status = -1;
		goto out;
	}

	data_len = resp_packet_size - hdr_len;
	if (data_len > 0 && read_resp->status == 0) {
		comp->bytes_returned = min(comp->len, data_len);
		memcpy(comp->buf, read_resp->bytes, comp->bytes_returned);
	} else {
		comp->bytes_returned = 0;
	}

	comp->comp_pkt.completion_status = read_resp->status;
out:
	complete(&comp->comp_pkt.host_event);
}

/**
 * hv_read_config_block() - Sends a read config block request to
 * the back-end driver running in the Hyper-V parent partition.
 * @pdev:		The PCI driver's representation for this device.
 * @buf:		Buffer into which the config block will be copied.
 * @len:		Size in bytes of buf.
 * @block_id:		Identifies the config block which has been requested.
 * @bytes_returned:	Size which came back from the back-end driver.
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_read_config_block(struct pci_dev *pdev, void *buf,
				unsigned int len, unsigned int block_id,
				unsigned int *bytes_returned)
{
	struct hv_pcibus_device *hbus =
		container_of(pdev->bus->sysdata, struct hv_pcibus_device,
			     sysdata);
	struct {
		struct pci_packet pkt;
		char buf[sizeof(struct pci_read_block)];
	} pkt;
	struct hv_read_config_compl comp_pkt;
	struct pci_read_block *read_blk;
	int ret;

	if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX)
		return -EINVAL;

	init_completion(&comp_pkt.comp_pkt.host_event);
	comp_pkt.buf = buf;
	comp_pkt.len = len;

	memset(&pkt, 0, sizeof(pkt));
	pkt.pkt.completion_func = hv_pci_read_config_compl;
	pkt.pkt.compl_ctxt = &comp_pkt;
	read_blk = (struct pci_read_block *)&pkt.pkt.message;
	read_blk->message_type.type = PCI_READ_BLOCK;
	read_blk->wslot.slot = devfn_to_wslot(pdev->devfn);
	read_blk->block_id = block_id;
	read_blk->bytes_requested = len;

	ret = vmbus_sendpacket(hbus->hdev->channel, read_blk,
			       sizeof(*read_blk), (unsigned long)&pkt.pkt,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (ret)
		return ret;

	ret = wait_for_response(hbus->hdev, &comp_pkt.comp_pkt.host_event);
	if (ret)
		return ret;

	if (comp_pkt.comp_pkt.completion_status != 0 ||
	    comp_pkt.bytes_returned == 0) {
		dev_err(&hbus->hdev->device,
			"Read Config Block failed: 0x%x, bytes_returned=%d\n",
			comp_pkt.comp_pkt.completion_status,
			comp_pkt.bytes_returned);
		return -EIO;
	}

	*bytes_returned = comp_pkt.bytes_returned;
	return 0;
}

/**
 * hv_pci_write_config_compl() - Invoked when a response packet for a write
 * config block operation arrives.
 * @context:		Identifies the write config operation
 * @resp:		The response packet itself
 * @resp_packet_size:	Size in bytes of the response packet
 */
static void hv_pci_write_config_compl(void *context, struct pci_response *resp,
				      int resp_packet_size)
{
	struct hv_pci_compl *comp_pkt = context;

	comp_pkt->completion_status = resp->status;
	complete(&comp_pkt->host_event);
}

/**
 * hv_write_config_block() - Sends a write config block request to the
 * back-end driver running in the Hyper-V parent partition.
 * @pdev:		The PCI driver's representation for this device.
 * @buf:		Buffer from which the config block will	be copied.
 * @len:		Size in bytes of buf.
 * @block_id:		Identifies the config block which is being written.
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_write_config_block(struct pci_dev *pdev, void *buf,
				unsigned int len, unsigned int block_id)
{
	struct hv_pcibus_device *hbus =
		container_of(pdev->bus->sysdata, struct hv_pcibus_device,
			     sysdata);
	struct {
		struct pci_packet pkt;
		char buf[sizeof(struct pci_write_block)];
		u32 reserved;
	} pkt;
	struct hv_pci_compl comp_pkt;
	struct pci_write_block *write_blk;
	u32 pkt_size;
	int ret;

	if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX)
		return -EINVAL;

	init_completion(&comp_pkt.host_event);

	memset(&pkt, 0, sizeof(pkt));
	pkt.pkt.completion_func = hv_pci_write_config_compl;
	pkt.pkt.compl_ctxt = &comp_pkt;
	write_blk = (struct pci_write_block *)&pkt.pkt.message;
	write_blk->message_type.type = PCI_WRITE_BLOCK;
	write_blk->wslot.slot = devfn_to_wslot(pdev->devfn);
	write_blk->block_id = block_id;
	write_blk->byte_count = len;
	memcpy(write_blk->bytes, buf, len);
	pkt_size = offsetof(struct pci_write_block, bytes) + len;
	/*
	 * This quirk is required on some hosts shipped around 2018, because
	 * these hosts don't check the pkt_size correctly (new hosts have been
	 * fixed since early 2019). The quirk is also safe on very old hosts
	 * and new hosts, because, on them, what really matters is the length
	 * specified in write_blk->byte_count.
	 */
	pkt_size += sizeof(pkt.reserved);

	ret = vmbus_sendpacket(hbus->hdev->channel, write_blk, pkt_size,
			       (unsigned long)&pkt.pkt, VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (ret)
		return ret;

	ret = wait_for_response(hbus->hdev, &comp_pkt.host_event);
	if (ret)
		return ret;

	if (comp_pkt.completion_status != 0) {
		dev_err(&hbus->hdev->device,
			"Write Config Block failed: 0x%x\n",
			comp_pkt.completion_status);
		return -EIO;
	}

	return 0;
}

/**
 * hv_register_block_invalidate() - Invoked when a config block invalidation
 * arrives from the back-end driver.
 * @pdev:		The PCI driver's representation for this device.
 * @context:		Identifies the device.
 * @block_invalidate:	Identifies all of the blocks being invalidated.
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_register_block_invalidate(struct pci_dev *pdev, void *context,
					void (*block_invalidate)(void *context,
								 u64 block_mask))
{
	struct hv_pcibus_device *hbus =
		container_of(pdev->bus->sysdata, struct hv_pcibus_device,
			     sysdata);
	struct hv_pci_dev *hpdev;

	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
	if (!hpdev)
		return -ENODEV;

	hpdev->block_invalidate = block_invalidate;
	hpdev->invalidate_context = context;

	put_pcichild(hpdev);
	return 0;

}

/* Interrupt management hooks */
static void hv_int_desc_free(struct hv_pci_dev *hpdev,
			     struct tran_int_desc *int_desc)
{
	struct pci_delete_interrupt *int_pkt;
	struct {
		struct pci_packet pkt;
		u8 buffer[sizeof(struct pci_delete_interrupt)];
	} ctxt;

	memset(&ctxt, 0, sizeof(ctxt));
	int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message;
	int_pkt->message_type.type =
		PCI_DELETE_INTERRUPT_MESSAGE;
	int_pkt->wslot.slot = hpdev->desc.win_slot.slot;
	int_pkt->int_desc = *int_desc;
	vmbus_sendpacket(hpdev->hbus->hdev->channel, int_pkt, sizeof(*int_pkt),
			 (unsigned long)&ctxt.pkt, VM_PKT_DATA_INBAND, 0);
	kfree(int_desc);
}

/**
 * hv_msi_free() - Free the MSI.
 * @domain:	The interrupt domain pointer
 * @info:	Extra MSI-related context
 * @irq:	Identifies the IRQ.
 *
 * The Hyper-V parent partition and hypervisor are tracking the
 * messages that are in use, keeping the interrupt redirection
 * table up to date.  This callback sends a message that frees
 * the IRT entry and related tracking nonsense.
 */
static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info,
			unsigned int irq)
{
	struct hv_pcibus_device *hbus;
	struct hv_pci_dev *hpdev;
	struct pci_dev *pdev;
	struct tran_int_desc *int_desc;
	struct irq_data *irq_data = irq_domain_get_irq_data(domain, irq);
	struct msi_desc *msi = irq_data_get_msi_desc(irq_data);

	pdev = msi_desc_to_pci_dev(msi);
	hbus = info->data;
	int_desc = irq_data_get_irq_chip_data(irq_data);
	if (!int_desc)
		return;

	irq_data->chip_data = NULL;
	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
	if (!hpdev) {
		kfree(int_desc);
		return;
	}

	hv_int_desc_free(hpdev, int_desc);
	put_pcichild(hpdev);
}

static int hv_set_affinity(struct irq_data *data, const struct cpumask *dest,
			   bool force)
{
	struct irq_data *parent = data->parent_data;

	return parent->chip->irq_set_affinity(parent, dest, force);
}

static void hv_irq_mask(struct irq_data *data)
{
	pci_msi_mask_irq(data);
}

/**
 * hv_irq_unmask() - "Unmask" the IRQ by setting its current
 * affinity.
 * @data:	Describes the IRQ
 *
 * Build new a destination for the MSI and make a hypercall to
 * update the Interrupt Redirection Table. "Device Logical ID"
 * is built out of this PCI bus's instance GUID and the function
 * number of the device.
 */
static void hv_irq_unmask(struct irq_data *data)
{
	struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
	struct irq_cfg *cfg = irqd_cfg(data);
	struct hv_retarget_device_interrupt *params;
	struct hv_pcibus_device *hbus;
	struct cpumask *dest;
	cpumask_var_t tmp;
	struct pci_bus *pbus;
	struct pci_dev *pdev;
	unsigned long flags;
	u32 var_size = 0;
	int cpu, nr_bank;
	u64 res;

	dest = irq_data_get_effective_affinity_mask(data);
	pdev = msi_desc_to_pci_dev(msi_desc);
	pbus = pdev->bus;
	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);

	spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags);

	params = &hbus->retarget_msi_interrupt_params;
	memset(params, 0, sizeof(*params));
	params->partition_id = HV_PARTITION_ID_SELF;
	params->int_entry.source = 1; /* MSI(-X) */
	hv_set_msi_entry_from_desc(&params->int_entry.msi_entry, msi_desc);
	params->device_id = (hbus->hdev->dev_instance.b[5] << 24) |
			   (hbus->hdev->dev_instance.b[4] << 16) |
			   (hbus->hdev->dev_instance.b[7] << 8) |
			   (hbus->hdev->dev_instance.b[6] & 0xf8) |
			   PCI_FUNC(pdev->devfn);
	params->int_target.vector = cfg->vector;

	/*
	 * Honoring apic->irq_delivery_mode set to dest_Fixed by
	 * setting the HV_DEVICE_INTERRUPT_TARGET_MULTICAST flag results in a
	 * spurious interrupt storm. Not doing so does not seem to have a
	 * negative effect (yet?).
	 */

	if (hbus->protocol_version >= PCI_PROTOCOL_VERSION_1_2) {
		/*
		 * PCI_PROTOCOL_VERSION_1_2 supports the VP_SET version of the
		 * HVCALL_RETARGET_INTERRUPT hypercall, which also coincides
		 * with >64 VP support.
		 * ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED
		 * is not sufficient for this hypercall.
		 */
		params->int_target.flags |=
			HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;

		if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) {
			res = 1;
			goto exit_unlock;
		}

		cpumask_and(tmp, dest, cpu_online_mask);
		nr_bank = cpumask_to_vpset(&params->int_target.vp_set, tmp);
		free_cpumask_var(tmp);

		if (nr_bank <= 0) {
			res = 1;
			goto exit_unlock;
		}

		/*
		 * var-sized hypercall, var-size starts after vp_mask (thus
		 * vp_set.format does not count, but vp_set.valid_bank_mask
		 * does).
		 */
		var_size = 1 + nr_bank;
	} else {
		for_each_cpu_and(cpu, dest, cpu_online_mask) {
			params->int_target.vp_mask |=
				(1ULL << hv_cpu_number_to_vp_number(cpu));
		}
	}

	res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17),
			      params, NULL);

exit_unlock:
	spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags);

	/*
	 * During hibernation, when a CPU is offlined, the kernel tries
	 * to move the interrupt to the remaining CPUs that haven't
	 * been offlined yet. In this case, the below hv_do_hypercall()
	 * always fails since the vmbus channel has been closed:
	 * refer to cpu_disable_common() -> fixup_irqs() ->
	 * irq_migrate_all_off_this_cpu() -> migrate_one_irq().
	 *
	 * Suppress the error message for hibernation because the failure
	 * during hibernation does not matter (at this time all the devices
	 * have been frozen). Note: the correct affinity info is still updated
	 * into the irqdata data structure in migrate_one_irq() ->
	 * irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
	 * resumes, hv_pci_restore_msi_state() is able to correctly restore
	 * the interrupt with the correct affinity.
	 */
	if (res && hbus->state != hv_pcibus_removing)
		dev_err(&hbus->hdev->device,
			"%s() failed: %#llx", __func__, res);

	pci_msi_unmask_irq(data);
}

struct compose_comp_ctxt {
	struct hv_pci_compl comp_pkt;
	struct tran_int_desc int_desc;
};

static void hv_pci_compose_compl(void *context, struct pci_response *resp,
				 int resp_packet_size)
{
	struct compose_comp_ctxt *comp_pkt = context;
	struct pci_create_int_response *int_resp =
		(struct pci_create_int_response *)resp;

	comp_pkt->comp_pkt.completion_status = resp->status;
	comp_pkt->int_desc = int_resp->int_desc;
	complete(&comp_pkt->comp_pkt.host_event);
}

static u32 hv_compose_msi_req_v1(
	struct pci_create_interrupt *int_pkt, struct cpumask *affinity,
	u32 slot, u8 vector)
{
	int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE;
	int_pkt->wslot.slot = slot;
	int_pkt->int_desc.vector = vector;
	int_pkt->int_desc.vector_count = 1;
	int_pkt->int_desc.delivery_mode = dest_Fixed;

	/*
	 * Create MSI w/ dummy vCPU set, overwritten by subsequent retarget in
	 * hv_irq_unmask().
	 */
	int_pkt->int_desc.cpu_mask = CPU_AFFINITY_ALL;

	return sizeof(*int_pkt);
}

static u32 hv_compose_msi_req_v2(
	struct pci_create_interrupt2 *int_pkt, struct cpumask *affinity,
	u32 slot, u8 vector)
{
	int cpu;

	int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE2;
	int_pkt->wslot.slot = slot;
	int_pkt->int_desc.vector = vector;
	int_pkt->int_desc.vector_count = 1;
	int_pkt->int_desc.delivery_mode = dest_Fixed;

	/*
	 * Create MSI w/ dummy vCPU set targeting just one vCPU, overwritten
	 * by subsequent retarget in hv_irq_unmask().
	 */
	cpu = cpumask_first_and(affinity, cpu_online_mask);
	int_pkt->int_desc.processor_array[0] =
		hv_cpu_number_to_vp_number(cpu);
	int_pkt->int_desc.processor_count = 1;

	return sizeof(*int_pkt);
}

/**
 * hv_compose_msi_msg() - Supplies a valid MSI address/data
 * @data:	Everything about this MSI
 * @msg:	Buffer that is filled in by this function
 *
 * This function unpacks the IRQ looking for target CPU set, IDT
 * vector and mode and sends a message to the parent partition
 * asking for a mapping for that tuple in this partition.  The
 * response supplies a data value and address to which that data
 * should be written to trigger that interrupt.
 */
static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
{
	struct irq_cfg *cfg = irqd_cfg(data);
	struct hv_pcibus_device *hbus;
	struct vmbus_channel *channel;
	struct hv_pci_dev *hpdev;
	struct pci_bus *pbus;
	struct pci_dev *pdev;
	struct cpumask *dest;
	struct compose_comp_ctxt comp;
	struct tran_int_desc *int_desc;
	struct {
		struct pci_packet pci_pkt;
		union {
			struct pci_create_interrupt v1;
			struct pci_create_interrupt2 v2;
		} int_pkts;
	} __packed ctxt;

	u32 size;
	int ret;

	pdev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data));
	dest = irq_data_get_effective_affinity_mask(data);
	pbus = pdev->bus;
	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
	channel = hbus->hdev->channel;
	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
	if (!hpdev)
		goto return_null_message;

	/* Free any previous message that might have already been composed. */
	if (data->chip_data) {
		int_desc = data->chip_data;
		data->chip_data = NULL;
		hv_int_desc_free(hpdev, int_desc);
	}

	int_desc = kzalloc(sizeof(*int_desc), GFP_ATOMIC);
	if (!int_desc)
		goto drop_reference;

	memset(&ctxt, 0, sizeof(ctxt));
	init_completion(&comp.comp_pkt.host_event);
	ctxt.pci_pkt.completion_func = hv_pci_compose_compl;
	ctxt.pci_pkt.compl_ctxt = &comp;

	switch (hbus->protocol_version) {
	case PCI_PROTOCOL_VERSION_1_1:
		size = hv_compose_msi_req_v1(&ctxt.int_pkts.v1,
					dest,
					hpdev->desc.win_slot.slot,
					cfg->vector);
		break;

	case PCI_PROTOCOL_VERSION_1_2:
	case PCI_PROTOCOL_VERSION_1_3:
		size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2,
					dest,
					hpdev->desc.win_slot.slot,
					cfg->vector);
		break;

	default:
		/* As we only negotiate protocol versions known to this driver,
		 * this path should never hit. However, this is it not a hot
		 * path so we print a message to aid future updates.
		 */
		dev_err(&hbus->hdev->device,
			"Unexpected vPCI protocol, update driver.");
		goto free_int_desc;
	}

	ret = vmbus_sendpacket(hpdev->hbus->hdev->channel, &ctxt.int_pkts,
			       size, (unsigned long)&ctxt.pci_pkt,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (ret) {
		dev_err(&hbus->hdev->device,
			"Sending request for interrupt failed: 0x%x",
			comp.comp_pkt.completion_status);
		goto free_int_desc;
	}

	/*
	 * Prevents hv_pci_onchannelcallback() from running concurrently
	 * in the tasklet.
	 */
	tasklet_disable(&channel->callback_event);

	/*
	 * Since this function is called with IRQ locks held, can't
	 * do normal wait for completion; instead poll.
	 */
	while (!try_wait_for_completion(&comp.comp_pkt.host_event)) {
		unsigned long flags;

		/* 0xFFFF means an invalid PCI VENDOR ID. */
		if (hv_pcifront_get_vendor_id(hpdev) == 0xFFFF) {
			dev_err_once(&hbus->hdev->device,
				     "the device has gone\n");
			goto enable_tasklet;
		}

		/*
		 * Make sure that the ring buffer data structure doesn't get
		 * freed while we dereference the ring buffer pointer.  Test
		 * for the channel's onchannel_callback being NULL within a
		 * sched_lock critical section.  See also the inline comments
		 * in vmbus_reset_channel_cb().
		 */
		spin_lock_irqsave(&channel->sched_lock, flags);
		if (unlikely(channel->onchannel_callback == NULL)) {
			spin_unlock_irqrestore(&channel->sched_lock, flags);
			goto enable_tasklet;
		}
		hv_pci_onchannelcallback(hbus);
		spin_unlock_irqrestore(&channel->sched_lock, flags);

		if (hpdev->state == hv_pcichild_ejecting) {
			dev_err_once(&hbus->hdev->device,
				     "the device is being ejected\n");
			goto enable_tasklet;
		}

		udelay(100);
	}

	tasklet_enable(&channel->callback_event);

	if (comp.comp_pkt.completion_status < 0) {
		dev_err(&hbus->hdev->device,
			"Request for interrupt failed: 0x%x",
			comp.comp_pkt.completion_status);
		goto free_int_desc;
	}

	/*
	 * Record the assignment so that this can be unwound later. Using
	 * irq_set_chip_data() here would be appropriate, but the lock it takes
	 * is already held.
	 */
	*int_desc = comp.int_desc;
	data->chip_data = int_desc;

	/* Pass up the result. */
	msg->address_hi = comp.int_desc.address >> 32;
	msg->address_lo = comp.int_desc.address & 0xffffffff;
	msg->data = comp.int_desc.data;

	put_pcichild(hpdev);
	return;

enable_tasklet:
	tasklet_enable(&channel->callback_event);
free_int_desc:
	kfree(int_desc);
drop_reference:
	put_pcichild(hpdev);
return_null_message:
	msg->address_hi = 0;
	msg->address_lo = 0;
	msg->data = 0;
}

/* HW Interrupt Chip Descriptor */
static struct irq_chip hv_msi_irq_chip = {
	.name			= "Hyper-V PCIe MSI",
	.irq_compose_msi_msg	= hv_compose_msi_msg,
	.irq_set_affinity	= hv_set_affinity,
	.irq_ack		= irq_chip_ack_parent,
	.irq_mask		= hv_irq_mask,
	.irq_unmask		= hv_irq_unmask,
};

static struct msi_domain_ops hv_msi_ops = {
	.msi_prepare	= pci_msi_prepare,
	.msi_free	= hv_msi_free,
};

/**
 * hv_pcie_init_irq_domain() - Initialize IRQ domain
 * @hbus:	The root PCI bus
 *
 * This function creates an IRQ domain which will be used for
 * interrupts from devices that have been passed through.  These
 * devices only support MSI and MSI-X, not line-based interrupts
 * or simulations of line-based interrupts through PCIe's
 * fabric-layer messages.  Because interrupts are remapped, we
 * can support multi-message MSI here.
 *
 * Return: '0' on success and error value on failure
 */
static int hv_pcie_init_irq_domain(struct hv_pcibus_device *hbus)
{
	hbus->msi_info.chip = &hv_msi_irq_chip;
	hbus->msi_info.ops = &hv_msi_ops;
	hbus->msi_info.flags = (MSI_FLAG_USE_DEF_DOM_OPS |
		MSI_FLAG_USE_DEF_CHIP_OPS | MSI_FLAG_MULTI_PCI_MSI |
		MSI_FLAG_PCI_MSIX);
	hbus->msi_info.handler = handle_edge_irq;
	hbus->msi_info.handler_name = "edge";
	hbus->msi_info.data = hbus;
	hbus->irq_domain = pci_msi_create_irq_domain(hbus->sysdata.fwnode,
						     &hbus->msi_info,
						     x86_vector_domain);
	if (!hbus->irq_domain) {
		dev_err(&hbus->hdev->device,
			"Failed to build an MSI IRQ domain\n");
		return -ENODEV;
	}

	return 0;
}

/**
 * get_bar_size() - Get the address space consumed by a BAR
 * @bar_val:	Value that a BAR returned after -1 was written
 *              to it.
 *
 * This function returns the size of the BAR, rounded up to 1
 * page.  It has to be rounded up because the hypervisor's page
 * table entry that maps the BAR into the VM can't specify an
 * offset within a page.  The invariant is that the hypervisor
 * must place any BARs of smaller than page length at the
 * beginning of a page.
 *
 * Return:	Size in bytes of the consumed MMIO space.
 */
static u64 get_bar_size(u64 bar_val)
{
	return round_up((1 + ~(bar_val & PCI_BASE_ADDRESS_MEM_MASK)),
			PAGE_SIZE);
}

/**
 * survey_child_resources() - Total all MMIO requirements
 * @hbus:	Root PCI bus, as understood by this driver
 */
static void survey_child_resources(struct hv_pcibus_device *hbus)
{
	struct hv_pci_dev *hpdev;
	resource_size_t bar_size = 0;
	unsigned long flags;
	struct completion *event;
	u64 bar_val;
	int i;

	/* If nobody is waiting on the answer, don't compute it. */
	event = xchg(&hbus->survey_event, NULL);
	if (!event)
		return;

	/* If the answer has already been computed, go with it. */
	if (hbus->low_mmio_space || hbus->high_mmio_space) {
		complete(event);
		return;
	}

	spin_lock_irqsave(&hbus->device_list_lock, flags);

	/*
	 * Due to an interesting quirk of the PCI spec, all memory regions
	 * for a child device are a power of 2 in size and aligned in memory,
	 * so it's sufficient to just add them up without tracking alignment.
	 */
	list_for_each_entry(hpdev, &hbus->children, list_entry) {
		for (i = 0; i < PCI_STD_NUM_BARS; i++) {
			if (hpdev->probed_bar[i] & PCI_BASE_ADDRESS_SPACE_IO)
				dev_err(&hbus->hdev->device,
					"There's an I/O BAR in this list!\n");

			if (hpdev->probed_bar[i] != 0) {
				/*
				 * A probed BAR has all the upper bits set that
				 * can be changed.
				 */

				bar_val = hpdev->probed_bar[i];
				if (bar_val & PCI_BASE_ADDRESS_MEM_TYPE_64)
					bar_val |=
					((u64)hpdev->probed_bar[++i] << 32);
				else
					bar_val |= 0xffffffff00000000ULL;

				bar_size = get_bar_size(bar_val);

				if (bar_val & PCI_BASE_ADDRESS_MEM_TYPE_64)
					hbus->high_mmio_space += bar_size;
				else
					hbus->low_mmio_space += bar_size;
			}
		}
	}

	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
	complete(event);
}

/**
 * prepopulate_bars() - Fill in BARs with defaults
 * @hbus:	Root PCI bus, as understood by this driver
 *
 * The core PCI driver code seems much, much happier if the BARs
 * for a device have values upon first scan. So fill them in.
 * The algorithm below works down from large sizes to small,
 * attempting to pack the assignments optimally. The assumption,
 * enforced in other parts of the code, is that the beginning of
 * the memory-mapped I/O space will be aligned on the largest
 * BAR size.
 */
static void prepopulate_bars(struct hv_pcibus_device *hbus)
{
	resource_size_t high_size = 0;
	resource_size_t low_size = 0;
	resource_size_t high_base = 0;
	resource_size_t low_base = 0;
	resource_size_t bar_size;
	struct hv_pci_dev *hpdev;
	unsigned long flags;
	u64 bar_val;
	u32 command;
	bool high;
	int i;

	if (hbus->low_mmio_space) {
		low_size = 1ULL << (63 - __builtin_clzll(hbus->low_mmio_space));
		low_base = hbus->low_mmio_res->start;
	}

	if (hbus->high_mmio_space) {
		high_size = 1ULL <<
			(63 - __builtin_clzll(hbus->high_mmio_space));
		high_base = hbus->high_mmio_res->start;
	}

	spin_lock_irqsave(&hbus->device_list_lock, flags);

	/*
	 * Clear the memory enable bit, in case it's already set. This occurs
	 * in the suspend path of hibernation, where the device is suspended,
	 * resumed and suspended again: see hibernation_snapshot() and
	 * hibernation_platform_enter().
	 *
	 * If the memory enable bit is already set, Hyper-V sliently ignores
	 * the below BAR updates, and the related PCI device driver can not
	 * work, because reading from the device register(s) always returns
	 * 0xFFFFFFFF.
	 */
	list_for_each_entry(hpdev, &hbus->children, list_entry) {
		_hv_pcifront_read_config(hpdev, PCI_COMMAND, 2, &command);
		command &= ~PCI_COMMAND_MEMORY;
		_hv_pcifront_write_config(hpdev, PCI_COMMAND, 2, command);
	}

	/* Pick addresses for the BARs. */
	do {
		list_for_each_entry(hpdev, &hbus->children, list_entry) {
			for (i = 0; i < PCI_STD_NUM_BARS; i++) {
				bar_val = hpdev->probed_bar[i];
				if (bar_val == 0)
					continue;
				high = bar_val & PCI_BASE_ADDRESS_MEM_TYPE_64;
				if (high) {
					bar_val |=
						((u64)hpdev->probed_bar[i + 1]
						 << 32);
				} else {
					bar_val |= 0xffffffffULL << 32;
				}
				bar_size = get_bar_size(bar_val);
				if (high) {
					if (high_size != bar_size) {
						i++;
						continue;
					}
					_hv_pcifront_write_config(hpdev,
						PCI_BASE_ADDRESS_0 + (4 * i),
						4,
						(u32)(high_base & 0xffffff00));
					i++;
					_hv_pcifront_write_config(hpdev,
						PCI_BASE_ADDRESS_0 + (4 * i),
						4, (u32)(high_base >> 32));
					high_base += bar_size;
				} else {
					if (low_size != bar_size)
						continue;
					_hv_pcifront_write_config(hpdev,
						PCI_BASE_ADDRESS_0 + (4 * i),
						4,
						(u32)(low_base & 0xffffff00));
					low_base += bar_size;
				}
			}
			if (high_size <= 1 && low_size <= 1) {
				/* Set the memory enable bit. */
				_hv_pcifront_read_config(hpdev, PCI_COMMAND, 2,
							 &command);
				command |= PCI_COMMAND_MEMORY;
				_hv_pcifront_write_config(hpdev, PCI_COMMAND, 2,
							  command);
				break;
			}
		}

		high_size >>= 1;
		low_size >>= 1;
	}  while (high_size || low_size);

	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
}

/*
 * Assign entries in sysfs pci slot directory.
 *
 * Note that this function does not need to lock the children list
 * because it is called from pci_devices_present_work which
 * is serialized with hv_eject_device_work because they are on the
 * same ordered workqueue. Therefore hbus->children list will not change
 * even when pci_create_slot sleeps.
 */
static void hv_pci_assign_slots(struct hv_pcibus_device *hbus)
{
	struct hv_pci_dev *hpdev;
	char name[SLOT_NAME_SIZE];
	int slot_nr;

	list_for_each_entry(hpdev, &hbus->children, list_entry) {
		if (hpdev->pci_slot)
			continue;

		slot_nr = PCI_SLOT(wslot_to_devfn(hpdev->desc.win_slot.slot));
		snprintf(name, SLOT_NAME_SIZE, "%u", hpdev->desc.ser);
		hpdev->pci_slot = pci_create_slot(hbus->pci_bus, slot_nr,
					  name, NULL);
		if (IS_ERR(hpdev->pci_slot)) {
			pr_warn("pci_create slot %s failed\n", name);
			hpdev->pci_slot = NULL;
		}
	}
}

/*
 * Remove entries in sysfs pci slot directory.
 */
static void hv_pci_remove_slots(struct hv_pcibus_device *hbus)
{
	struct hv_pci_dev *hpdev;

	list_for_each_entry(hpdev, &hbus->children, list_entry) {
		if (!hpdev->pci_slot)
			continue;
		pci_destroy_slot(hpdev->pci_slot);
		hpdev->pci_slot = NULL;
	}
}

/*
 * Set NUMA node for the devices on the bus
 */
static void hv_pci_assign_numa_node(struct hv_pcibus_device *hbus)
{
	struct pci_dev *dev;
	struct pci_bus *bus = hbus->pci_bus;
	struct hv_pci_dev *hv_dev;

	list_for_each_entry(dev, &bus->devices, bus_list) {
		hv_dev = get_pcichild_wslot(hbus, devfn_to_wslot(dev->devfn));
		if (!hv_dev)
			continue;

		if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY)
			set_dev_node(&dev->dev, hv_dev->desc.virtual_numa_node);

		put_pcichild(hv_dev);
	}
}

/**
 * create_root_hv_pci_bus() - Expose a new root PCI bus
 * @hbus:	Root PCI bus, as understood by this driver
 *
 * Return: 0 on success, -errno on failure
 */
static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus)
{
	/* Register the device */
	hbus->pci_bus = pci_create_root_bus(&hbus->hdev->device,
					    0, /* bus number is always zero */
					    &hv_pcifront_ops,
					    &hbus->sysdata,
					    &hbus->resources_for_children);
	if (!hbus->pci_bus)
		return -ENODEV;

	hbus->pci_bus->msi = &hbus->msi_chip;
	hbus->pci_bus->msi->dev = &hbus->hdev->device;

	pci_lock_rescan_remove();
	pci_scan_child_bus(hbus->pci_bus);
	hv_pci_assign_numa_node(hbus);
	pci_bus_assign_resources(hbus->pci_bus);
	hv_pci_assign_slots(hbus);
	pci_bus_add_devices(hbus->pci_bus);
	pci_unlock_rescan_remove();
	hbus->state = hv_pcibus_installed;
	return 0;
}

struct q_res_req_compl {
	struct completion host_event;
	struct hv_pci_dev *hpdev;
};

/**
 * q_resource_requirements() - Query Resource Requirements
 * @context:		The completion context.
 * @resp:		The response that came from the host.
 * @resp_packet_size:	The size in bytes of resp.
 *
 * This function is invoked on completion of a Query Resource
 * Requirements packet.
 */
static void q_resource_requirements(void *context, struct pci_response *resp,
				    int resp_packet_size)
{
	struct q_res_req_compl *completion = context;
	struct pci_q_res_req_response *q_res_req =
		(struct pci_q_res_req_response *)resp;
	int i;

	if (resp->status < 0) {
		dev_err(&completion->hpdev->hbus->hdev->device,
			"query resource requirements failed: %x\n",
			resp->status);
	} else {
		for (i = 0; i < PCI_STD_NUM_BARS; i++) {
			completion->hpdev->probed_bar[i] =
				q_res_req->probed_bar[i];
		}
	}

	complete(&completion->host_event);
}

/**
 * new_pcichild_device() - Create a new child device
 * @hbus:	The internal struct tracking this root PCI bus.
 * @desc:	The information supplied so far from the host
 *              about the device.
 *
 * This function creates the tracking structure for a new child
 * device and kicks off the process of figuring out what it is.
 *
 * Return: Pointer to the new tracking struct
 */
static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus,
		struct hv_pcidev_description *desc)
{
	struct hv_pci_dev *hpdev;
	struct pci_child_message *res_req;
	struct q_res_req_compl comp_pkt;
	struct {
		struct pci_packet init_packet;
		u8 buffer[sizeof(struct pci_child_message)];
	} pkt;
	unsigned long flags;
	int ret;

	hpdev = kzalloc(sizeof(*hpdev), GFP_KERNEL);
	if (!hpdev)
		return NULL;

	hpdev->hbus = hbus;

	memset(&pkt, 0, sizeof(pkt));
	init_completion(&comp_pkt.host_event);
	comp_pkt.hpdev = hpdev;
	pkt.init_packet.compl_ctxt = &comp_pkt;
	pkt.init_packet.completion_func = q_resource_requirements;
	res_req = (struct pci_child_message *)&pkt.init_packet.message;
	res_req->message_type.type = PCI_QUERY_RESOURCE_REQUIREMENTS;
	res_req->wslot.slot = desc->win_slot.slot;

	ret = vmbus_sendpacket(hbus->hdev->channel, res_req,
			       sizeof(struct pci_child_message),
			       (unsigned long)&pkt.init_packet,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (ret)
		goto error;

	if (wait_for_response(hbus->hdev, &comp_pkt.host_event))
		goto error;

	hpdev->desc = *desc;
	refcount_set(&hpdev->refs, 1);
	get_pcichild(hpdev);
	spin_lock_irqsave(&hbus->device_list_lock, flags);

	list_add_tail(&hpdev->list_entry, &hbus->children);
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
	return hpdev;

error:
	kfree(hpdev);
	return NULL;
}

/**
 * get_pcichild_wslot() - Find device from slot
 * @hbus:	Root PCI bus, as understood by this driver
 * @wslot:	Location on the bus
 *
 * This function looks up a PCI device and returns the internal
 * representation of it.  It acquires a reference on it, so that
 * the device won't be deleted while somebody is using it.  The
 * caller is responsible for calling put_pcichild() to release
 * this reference.
 *
 * Return:	Internal representation of a PCI device
 */
static struct hv_pci_dev *get_pcichild_wslot(struct hv_pcibus_device *hbus,
					     u32 wslot)
{
	unsigned long flags;
	struct hv_pci_dev *iter, *hpdev = NULL;

	spin_lock_irqsave(&hbus->device_list_lock, flags);
	list_for_each_entry(iter, &hbus->children, list_entry) {
		if (iter->desc.win_slot.slot == wslot) {
			hpdev = iter;
			get_pcichild(hpdev);
			break;
		}
	}
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);

	return hpdev;
}

/**
 * pci_devices_present_work() - Handle new list of child devices
 * @work:	Work struct embedded in struct hv_dr_work
 *
 * "Bus Relations" is the Windows term for "children of this
 * bus."  The terminology is preserved here for people trying to
 * debug the interaction between Hyper-V and Linux.  This
 * function is called when the parent partition reports a list
 * of functions that should be observed under this PCI Express
 * port (bus).
 *
 * This function updates the list, and must tolerate being
 * called multiple times with the same information.  The typical
 * number of child devices is one, with very atypical cases
 * involving three or four, so the algorithms used here can be
 * simple and inefficient.
 *
 * It must also treat the omission of a previously observed device as
 * notification that the device no longer exists.
 *
 * Note that this function is serialized with hv_eject_device_work(),
 * because both are pushed to the ordered workqueue hbus->wq.
 */
static void pci_devices_present_work(struct work_struct *work)
{
	u32 child_no;
	bool found;
	struct hv_pcidev_description *new_desc;
	struct hv_pci_dev *hpdev;
	struct hv_pcibus_device *hbus;
	struct list_head removed;
	struct hv_dr_work *dr_wrk;
	struct hv_dr_state *dr = NULL;
	unsigned long flags;

	dr_wrk = container_of(work, struct hv_dr_work, wrk);
	hbus = dr_wrk->bus;
	kfree(dr_wrk);

	INIT_LIST_HEAD(&removed);

	/* Pull this off the queue and process it if it was the last one. */
	spin_lock_irqsave(&hbus->device_list_lock, flags);
	while (!list_empty(&hbus->dr_list)) {
		dr = list_first_entry(&hbus->dr_list, struct hv_dr_state,
				      list_entry);
		list_del(&dr->list_entry);

		/* Throw this away if the list still has stuff in it. */
		if (!list_empty(&hbus->dr_list)) {
			kfree(dr);
			continue;
		}
	}
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);

	if (!dr) {
		put_hvpcibus(hbus);
		return;
	}

	/* First, mark all existing children as reported missing. */
	spin_lock_irqsave(&hbus->device_list_lock, flags);
	list_for_each_entry(hpdev, &hbus->children, list_entry) {
		hpdev->reported_missing = true;
	}
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);

	/* Next, add back any reported devices. */
	for (child_no = 0; child_no < dr->device_count; child_no++) {
		found = false;
		new_desc = &dr->func[child_no];

		spin_lock_irqsave(&hbus->device_list_lock, flags);
		list_for_each_entry(hpdev, &hbus->children, list_entry) {
			if ((hpdev->desc.win_slot.slot == new_desc->win_slot.slot) &&
			    (hpdev->desc.v_id == new_desc->v_id) &&
			    (hpdev->desc.d_id == new_desc->d_id) &&
			    (hpdev->desc.ser == new_desc->ser)) {
				hpdev->reported_missing = false;
				found = true;
			}
		}
		spin_unlock_irqrestore(&hbus->device_list_lock, flags);

		if (!found) {
			hpdev = new_pcichild_device(hbus, new_desc);
			if (!hpdev)
				dev_err(&hbus->hdev->device,
					"couldn't record a child device.\n");
		}
	}

	/* Move missing children to a list on the stack. */
	spin_lock_irqsave(&hbus->device_list_lock, flags);
	do {
		found = false;
		list_for_each_entry(hpdev, &hbus->children, list_entry) {
			if (hpdev->reported_missing) {
				found = true;
				put_pcichild(hpdev);
				list_move_tail(&hpdev->list_entry, &removed);
				break;
			}
		}
	} while (found);
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);

	/* Delete everything that should no longer exist. */
	while (!list_empty(&removed)) {
		hpdev = list_first_entry(&removed, struct hv_pci_dev,
					 list_entry);
		list_del(&hpdev->list_entry);

		if (hpdev->pci_slot)
			pci_destroy_slot(hpdev->pci_slot);

		put_pcichild(hpdev);
	}

	switch (hbus->state) {
	case hv_pcibus_installed:
		/*
		 * Tell the core to rescan bus
		 * because there may have been changes.
		 */
		pci_lock_rescan_remove();
		pci_scan_child_bus(hbus->pci_bus);
		hv_pci_assign_numa_node(hbus);
		hv_pci_assign_slots(hbus);
		pci_unlock_rescan_remove();
		break;

	case hv_pcibus_init:
	case hv_pcibus_probed:
		survey_child_resources(hbus);
		break;

	default:
		break;
	}

	put_hvpcibus(hbus);
	kfree(dr);
}

/**
 * hv_pci_start_relations_work() - Queue work to start device discovery
 * @hbus:	Root PCI bus, as understood by this driver
 * @dr:		The list of children returned from host
 *
 * Return:  0 on success, -errno on failure
 */
static int hv_pci_start_relations_work(struct hv_pcibus_device *hbus,
				       struct hv_dr_state *dr)
{
	struct hv_dr_work *dr_wrk;
	unsigned long flags;
	bool pending_dr;

	if (hbus->state == hv_pcibus_removing) {
		dev_info(&hbus->hdev->device,
			 "PCI VMBus BUS_RELATIONS: ignored\n");
		return -ENOENT;
	}

	dr_wrk = kzalloc(sizeof(*dr_wrk), GFP_NOWAIT);
	if (!dr_wrk)
		return -ENOMEM;

	INIT_WORK(&dr_wrk->wrk, pci_devices_present_work);
	dr_wrk->bus = hbus;

	spin_lock_irqsave(&hbus->device_list_lock, flags);
	/*
	 * If pending_dr is true, we have already queued a work,
	 * which will see the new dr. Otherwise, we need to
	 * queue a new work.
	 */
	pending_dr = !list_empty(&hbus->dr_list);
	list_add_tail(&dr->list_entry, &hbus->dr_list);
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);

	if (pending_dr) {
		kfree(dr_wrk);
	} else {
		get_hvpcibus(hbus);
		queue_work(hbus->wq, &dr_wrk->wrk);
	}

	return 0;
}

/**
 * hv_pci_devices_present() - Handle list of new children
 * @hbus:      Root PCI bus, as understood by this driver
 * @relations: Packet from host listing children
 *
 * Process a new list of devices on the bus. The list of devices is
 * discovered by VSP and sent to us via VSP message PCI_BUS_RELATIONS,
 * whenever a new list of devices for this bus appears.
 */
static void hv_pci_devices_present(struct hv_pcibus_device *hbus,
				   struct pci_bus_relations *relations)
{
	struct hv_dr_state *dr;
	int i;

	dr = kzalloc(struct_size(dr, func, relations->device_count),
		     GFP_NOWAIT);
	if (!dr)
		return;

	dr->device_count = relations->device_count;
	for (i = 0; i < dr->device_count; i++) {
		dr->func[i].v_id = relations->func[i].v_id;
		dr->func[i].d_id = relations->func[i].d_id;
		dr->func[i].rev = relations->func[i].rev;
		dr->func[i].prog_intf = relations->func[i].prog_intf;
		dr->func[i].subclass = relations->func[i].subclass;
		dr->func[i].base_class = relations->func[i].base_class;
		dr->func[i].subsystem_id = relations->func[i].subsystem_id;
		dr->func[i].win_slot = relations->func[i].win_slot;
		dr->func[i].ser = relations->func[i].ser;
	}

	if (hv_pci_start_relations_work(hbus, dr))
		kfree(dr);
}

/**
 * hv_pci_devices_present2() - Handle list of new children
 * @hbus:	Root PCI bus, as understood by this driver
 * @relations:	Packet from host listing children
 *
 * This function is the v2 version of hv_pci_devices_present()
 */
static void hv_pci_devices_present2(struct hv_pcibus_device *hbus,
				    struct pci_bus_relations2 *relations)
{
	struct hv_dr_state *dr;
	int i;

	dr = kzalloc(struct_size(dr, func, relations->device_count),
		     GFP_NOWAIT);
	if (!dr)
		return;

	dr->device_count = relations->device_count;
	for (i = 0; i < dr->device_count; i++) {
		dr->func[i].v_id = relations->func[i].v_id;
		dr->func[i].d_id = relations->func[i].d_id;
		dr->func[i].rev = relations->func[i].rev;
		dr->func[i].prog_intf = relations->func[i].prog_intf;
		dr->func[i].subclass = relations->func[i].subclass;
		dr->func[i].base_class = relations->func[i].base_class;
		dr->func[i].subsystem_id = relations->func[i].subsystem_id;
		dr->func[i].win_slot = relations->func[i].win_slot;
		dr->func[i].ser = relations->func[i].ser;
		dr->func[i].flags = relations->func[i].flags;
		dr->func[i].virtual_numa_node =
			relations->func[i].virtual_numa_node;
	}

	if (hv_pci_start_relations_work(hbus, dr))
		kfree(dr);
}

/**
 * hv_eject_device_work() - Asynchronously handles ejection
 * @work:	Work struct embedded in internal device struct
 *
 * This function handles ejecting a device.  Windows will
 * attempt to gracefully eject a device, waiting 60 seconds to
 * hear back from the guest OS that this completed successfully.
 * If this timer expires, the device will be forcibly removed.
 */
static void hv_eject_device_work(struct work_struct *work)
{
	struct pci_eject_response *ejct_pkt;
	struct hv_pcibus_device *hbus;
	struct hv_pci_dev *hpdev;
	struct pci_dev *pdev;
	unsigned long flags;
	int wslot;
	struct {
		struct pci_packet pkt;
		u8 buffer[sizeof(struct pci_eject_response)];
	} ctxt;

	hpdev = container_of(work, struct hv_pci_dev, wrk);
	hbus = hpdev->hbus;

	WARN_ON(hpdev->state != hv_pcichild_ejecting);

	/*
	 * Ejection can come before or after the PCI bus has been set up, so
	 * attempt to find it and tear down the bus state, if it exists.  This
	 * must be done without constructs like pci_domain_nr(hbus->pci_bus)
	 * because hbus->pci_bus may not exist yet.
	 */
	wslot = wslot_to_devfn(hpdev->desc.win_slot.slot);
	pdev = pci_get_domain_bus_and_slot(hbus->sysdata.domain, 0, wslot);
	if (pdev) {
		pci_lock_rescan_remove();
		pci_stop_and_remove_bus_device(pdev);
		pci_dev_put(pdev);
		pci_unlock_rescan_remove();
	}

	spin_lock_irqsave(&hbus->device_list_lock, flags);
	list_del(&hpdev->list_entry);
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);

	if (hpdev->pci_slot)
		pci_destroy_slot(hpdev->pci_slot);

	memset(&ctxt, 0, sizeof(ctxt));
	ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message;
	ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE;
	ejct_pkt->wslot.slot = hpdev->desc.win_slot.slot;
	vmbus_sendpacket(hbus->hdev->channel, ejct_pkt,
			 sizeof(*ejct_pkt), (unsigned long)&ctxt.pkt,
			 VM_PKT_DATA_INBAND, 0);

	/* For the get_pcichild() in hv_pci_eject_device() */
	put_pcichild(hpdev);
	/* For the two refs got in new_pcichild_device() */
	put_pcichild(hpdev);
	put_pcichild(hpdev);
	/* hpdev has been freed. Do not use it any more. */

	put_hvpcibus(hbus);
}

/**
 * hv_pci_eject_device() - Handles device ejection
 * @hpdev:	Internal device tracking struct
 *
 * This function is invoked when an ejection packet arrives.  It
 * just schedules work so that we don't re-enter the packet
 * delivery code handling the ejection.
 */
static void hv_pci_eject_device(struct hv_pci_dev *hpdev)
{
	struct hv_pcibus_device *hbus = hpdev->hbus;
	struct hv_device *hdev = hbus->hdev;

	if (hbus->state == hv_pcibus_removing) {
		dev_info(&hdev->device, "PCI VMBus EJECT: ignored\n");
		return;
	}

	hpdev->state = hv_pcichild_ejecting;
	get_pcichild(hpdev);
	INIT_WORK(&hpdev->wrk, hv_eject_device_work);
	get_hvpcibus(hbus);
	queue_work(hbus->wq, &hpdev->wrk);
}

/**
 * hv_pci_onchannelcallback() - Handles incoming packets
 * @context:	Internal bus tracking struct
 *
 * This function is invoked whenever the host sends a packet to
 * this channel (which is private to this root PCI bus).
 */
static void hv_pci_onchannelcallback(void *context)
{
	const int packet_size = 0x100;
	int ret;
	struct hv_pcibus_device *hbus = context;
	u32 bytes_recvd;
	u64 req_id;
	struct vmpacket_descriptor *desc;
	unsigned char *buffer;
	int bufferlen = packet_size;
	struct pci_packet *comp_packet;
	struct pci_response *response;
	struct pci_incoming_message *new_message;
	struct pci_bus_relations *bus_rel;
	struct pci_bus_relations2 *bus_rel2;
	struct pci_dev_inval_block *inval;
	struct pci_dev_incoming *dev_message;
	struct hv_pci_dev *hpdev;

	buffer = kmalloc(bufferlen, GFP_ATOMIC);
	if (!buffer)
		return;

	while (1) {
		ret = vmbus_recvpacket_raw(hbus->hdev->channel, buffer,
					   bufferlen, &bytes_recvd, &req_id);

		if (ret == -ENOBUFS) {
			kfree(buffer);
			/* Handle large packet */
			bufferlen = bytes_recvd;
			buffer = kmalloc(bytes_recvd, GFP_ATOMIC);
			if (!buffer)
				return;
			continue;
		}

		/* Zero length indicates there are no more packets. */
		if (ret || !bytes_recvd)
			break;

		/*
		 * All incoming packets must be at least as large as a
		 * response.
		 */
		if (bytes_recvd <= sizeof(struct pci_response))
			continue;
		desc = (struct vmpacket_descriptor *)buffer;

		switch (desc->type) {
		case VM_PKT_COMP:

			/*
			 * The host is trusted, and thus it's safe to interpret
			 * this transaction ID as a pointer.
			 */
			comp_packet = (struct pci_packet *)req_id;
			response = (struct pci_response *)buffer;
			comp_packet->completion_func(comp_packet->compl_ctxt,
						     response,
						     bytes_recvd);
			break;

		case VM_PKT_DATA_INBAND:

			new_message = (struct pci_incoming_message *)buffer;
			switch (new_message->message_type.type) {
			case PCI_BUS_RELATIONS:

				bus_rel = (struct pci_bus_relations *)buffer;
				if (bytes_recvd <
					struct_size(bus_rel, func,
						    bus_rel->device_count)) {
					dev_err(&hbus->hdev->device,
						"bus relations too small\n");
					break;
				}

				hv_pci_devices_present(hbus, bus_rel);
				break;

			case PCI_BUS_RELATIONS2:

				bus_rel2 = (struct pci_bus_relations2 *)buffer;
				if (bytes_recvd <
					struct_size(bus_rel2, func,
						    bus_rel2->device_count)) {
					dev_err(&hbus->hdev->device,
						"bus relations v2 too small\n");
					break;
				}

				hv_pci_devices_present2(hbus, bus_rel2);
				break;

			case PCI_EJECT:

				dev_message = (struct pci_dev_incoming *)buffer;
				hpdev = get_pcichild_wslot(hbus,
						      dev_message->wslot.slot);
				if (hpdev) {
					hv_pci_eject_device(hpdev);
					put_pcichild(hpdev);
				}
				break;

			case PCI_INVALIDATE_BLOCK:

				inval = (struct pci_dev_inval_block *)buffer;
				hpdev = get_pcichild_wslot(hbus,
							   inval->wslot.slot);
				if (hpdev) {
					if (hpdev->block_invalidate) {
						hpdev->block_invalidate(
						    hpdev->invalidate_context,
						    inval->block_mask);
					}
					put_pcichild(hpdev);
				}
				break;

			default:
				dev_warn(&hbus->hdev->device,
					"Unimplemented protocol message %x\n",
					new_message->message_type.type);
				break;
			}
			break;

		default:
			dev_err(&hbus->hdev->device,
				"unhandled packet type %d, tid %llx len %d\n",
				desc->type, req_id, bytes_recvd);
			break;
		}
	}

	kfree(buffer);
}

/**
 * hv_pci_protocol_negotiation() - Set up protocol
 * @hdev:		VMBus's tracking struct for this root PCI bus.
 * @version:		Array of supported channel protocol versions in
 *			the order of probing - highest go first.
 * @num_version:	Number of elements in the version array.
 *
 * This driver is intended to support running on Windows 10
 * (server) and later versions. It will not run on earlier
 * versions, as they assume that many of the operations which
 * Linux needs accomplished with a spinlock held were done via
 * asynchronous messaging via VMBus.  Windows 10 increases the
 * surface area of PCI emulation so that these actions can take
 * place by suspending a virtual processor for their duration.
 *
 * This function negotiates the channel protocol version,
 * failing if the host doesn't support the necessary protocol
 * level.
 */
static int hv_pci_protocol_negotiation(struct hv_device *hdev,
				       enum pci_protocol_version_t version[],
				       int num_version)
{
	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
	struct pci_version_request *version_req;
	struct hv_pci_compl comp_pkt;
	struct pci_packet *pkt;
	int ret;
	int i;

	/*
	 * Initiate the handshake with the host and negotiate
	 * a version that the host can support. We start with the
	 * highest version number and go down if the host cannot
	 * support it.
	 */
	pkt = kzalloc(sizeof(*pkt) + sizeof(*version_req), GFP_KERNEL);
	if (!pkt)
		return -ENOMEM;

	init_completion(&comp_pkt.host_event);
	pkt->completion_func = hv_pci_generic_compl;
	pkt->compl_ctxt = &comp_pkt;
	version_req = (struct pci_version_request *)&pkt->message;
	version_req->message_type.type = PCI_QUERY_PROTOCOL_VERSION;

	for (i = 0; i < num_version; i++) {
		version_req->protocol_version = version[i];
		ret = vmbus_sendpacket(hdev->channel, version_req,
				sizeof(struct pci_version_request),
				(unsigned long)pkt, VM_PKT_DATA_INBAND,
				VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
		if (!ret)
			ret = wait_for_response(hdev, &comp_pkt.host_event);

		if (ret) {
			dev_err(&hdev->device,
				"PCI Pass-through VSP failed to request version: %d",
				ret);
			goto exit;
		}

		if (comp_pkt.completion_status >= 0) {
			hbus->protocol_version = version[i];
			dev_info(&hdev->device,
				"PCI VMBus probing: Using version %#x\n",
				hbus->protocol_version);
			goto exit;
		}

		if (comp_pkt.completion_status != STATUS_REVISION_MISMATCH) {
			dev_err(&hdev->device,
				"PCI Pass-through VSP failed version request: %#x",
				comp_pkt.completion_status);
			ret = -EPROTO;
			goto exit;
		}

		reinit_completion(&comp_pkt.host_event);
	}

	dev_err(&hdev->device,
		"PCI pass-through VSP failed to find supported version");
	ret = -EPROTO;

exit:
	kfree(pkt);
	return ret;
}

/**
 * hv_pci_free_bridge_windows() - Release memory regions for the
 * bus
 * @hbus:	Root PCI bus, as understood by this driver
 */
static void hv_pci_free_bridge_windows(struct hv_pcibus_device *hbus)
{
	/*
	 * Set the resources back to the way they looked when they
	 * were allocated by setting IORESOURCE_BUSY again.
	 */

	if (hbus->low_mmio_space && hbus->low_mmio_res) {
		hbus->low_mmio_res->flags |= IORESOURCE_BUSY;
		vmbus_free_mmio(hbus->low_mmio_res->start,
				resource_size(hbus->low_mmio_res));
	}

	if (hbus->high_mmio_space && hbus->high_mmio_res) {
		hbus->high_mmio_res->flags |= IORESOURCE_BUSY;
		vmbus_free_mmio(hbus->high_mmio_res->start,
				resource_size(hbus->high_mmio_res));
	}
}

/**
 * hv_pci_allocate_bridge_windows() - Allocate memory regions
 * for the bus
 * @hbus:	Root PCI bus, as understood by this driver
 *
 * This function calls vmbus_allocate_mmio(), which is itself a
 * bit of a compromise.  Ideally, we might change the pnp layer
 * in the kernel such that it comprehends either PCI devices
 * which are "grandchildren of ACPI," with some intermediate bus
 * node (in this case, VMBus) or change it such that it
 * understands VMBus.  The pnp layer, however, has been declared
 * deprecated, and not subject to change.
 *
 * The workaround, implemented here, is to ask VMBus to allocate
 * MMIO space for this bus.  VMBus itself knows which ranges are
 * appropriate by looking at its own ACPI objects.  Then, after
 * these ranges are claimed, they're modified to look like they
 * would have looked if the ACPI and pnp code had allocated
 * bridge windows.  These descriptors have to exist in this form
 * in order to satisfy the code which will get invoked when the
 * endpoint PCI function driver calls request_mem_region() or
 * request_mem_region_exclusive().
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_pci_allocate_bridge_windows(struct hv_pcibus_device *hbus)
{
	resource_size_t align;
	int ret;

	if (hbus->low_mmio_space) {
		align = 1ULL << (63 - __builtin_clzll(hbus->low_mmio_space));
		ret = vmbus_allocate_mmio(&hbus->low_mmio_res, hbus->hdev, 0,
					  (u64)(u32)0xffffffff,
					  hbus->low_mmio_space,
					  align, false);
		if (ret) {
			dev_err(&hbus->hdev->device,
				"Need %#llx of low MMIO space. Consider reconfiguring the VM.\n",
				hbus->low_mmio_space);
			return ret;
		}

		/* Modify this resource to become a bridge window. */
		hbus->low_mmio_res->flags |= IORESOURCE_WINDOW;
		hbus->low_mmio_res->flags &= ~IORESOURCE_BUSY;
		pci_add_resource(&hbus->resources_for_children,
				 hbus->low_mmio_res);
	}

	if (hbus->high_mmio_space) {
		align = 1ULL << (63 - __builtin_clzll(hbus->high_mmio_space));
		ret = vmbus_allocate_mmio(&hbus->high_mmio_res, hbus->hdev,
					  0x100000000, -1,
					  hbus->high_mmio_space, align,
					  false);
		if (ret) {
			dev_err(&hbus->hdev->device,
				"Need %#llx of high MMIO space. Consider reconfiguring the VM.\n",
				hbus->high_mmio_space);
			goto release_low_mmio;
		}

		/* Modify this resource to become a bridge window. */
		hbus->high_mmio_res->flags |= IORESOURCE_WINDOW;
		hbus->high_mmio_res->flags &= ~IORESOURCE_BUSY;
		pci_add_resource(&hbus->resources_for_children,
				 hbus->high_mmio_res);
	}

	return 0;

release_low_mmio:
	if (hbus->low_mmio_res) {
		vmbus_free_mmio(hbus->low_mmio_res->start,
				resource_size(hbus->low_mmio_res));
	}

	return ret;
}

/**
 * hv_allocate_config_window() - Find MMIO space for PCI Config
 * @hbus:	Root PCI bus, as understood by this driver
 *
 * This function claims memory-mapped I/O space for accessing
 * configuration space for the functions on this bus.
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_allocate_config_window(struct hv_pcibus_device *hbus)
{
	int ret;

	/*
	 * Set up a region of MMIO space to use for accessing configuration
	 * space.
	 */
	ret = vmbus_allocate_mmio(&hbus->mem_config, hbus->hdev, 0, -1,
				  PCI_CONFIG_MMIO_LENGTH, 0x1000, false);
	if (ret)
		return ret;

	/*
	 * vmbus_allocate_mmio() gets used for allocating both device endpoint
	 * resource claims (those which cannot be overlapped) and the ranges
	 * which are valid for the children of this bus, which are intended
	 * to be overlapped by those children.  Set the flag on this claim
	 * meaning that this region can't be overlapped.
	 */

	hbus->mem_config->flags |= IORESOURCE_BUSY;

	return 0;
}

static void hv_free_config_window(struct hv_pcibus_device *hbus)
{
	vmbus_free_mmio(hbus->mem_config->start, PCI_CONFIG_MMIO_LENGTH);
}

static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs);

/**
 * hv_pci_enter_d0() - Bring the "bus" into the D0 power state
 * @hdev:	VMBus's tracking struct for this root PCI bus
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_pci_enter_d0(struct hv_device *hdev)
{
	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
	struct pci_bus_d0_entry *d0_entry;
	struct hv_pci_compl comp_pkt;
	struct pci_packet *pkt;
	int ret;

	/*
	 * Tell the host that the bus is ready to use, and moved into the
	 * powered-on state.  This includes telling the host which region
	 * of memory-mapped I/O space has been chosen for configuration space
	 * access.
	 */
	pkt = kzalloc(sizeof(*pkt) + sizeof(*d0_entry), GFP_KERNEL);
	if (!pkt)
		return -ENOMEM;

	init_completion(&comp_pkt.host_event);
	pkt->completion_func = hv_pci_generic_compl;
	pkt->compl_ctxt = &comp_pkt;
	d0_entry = (struct pci_bus_d0_entry *)&pkt->message;
	d0_entry->message_type.type = PCI_BUS_D0ENTRY;
	d0_entry->mmio_base = hbus->mem_config->start;

	ret = vmbus_sendpacket(hdev->channel, d0_entry, sizeof(*d0_entry),
			       (unsigned long)pkt, VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (!ret)
		ret = wait_for_response(hdev, &comp_pkt.host_event);

	if (ret)
		goto exit;

	if (comp_pkt.completion_status < 0) {
		dev_err(&hdev->device,
			"PCI Pass-through VSP failed D0 Entry with status %x\n",
			comp_pkt.completion_status);
		ret = -EPROTO;
		goto exit;
	}

	ret = 0;

exit:
	kfree(pkt);
	return ret;
}

/**
 * hv_pci_query_relations() - Ask host to send list of child
 * devices
 * @hdev:	VMBus's tracking struct for this root PCI bus
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_pci_query_relations(struct hv_device *hdev)
{
	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
	struct pci_message message;
	struct completion comp;
	int ret;

	/* Ask the host to send along the list of child devices */
	init_completion(&comp);
	if (cmpxchg(&hbus->survey_event, NULL, &comp))
		return -ENOTEMPTY;

	memset(&message, 0, sizeof(message));
	message.type = PCI_QUERY_BUS_RELATIONS;

	ret = vmbus_sendpacket(hdev->channel, &message, sizeof(message),
			       0, VM_PKT_DATA_INBAND, 0);
	if (!ret)
		ret = wait_for_response(hdev, &comp);

	return ret;
}

/**
 * hv_send_resources_allocated() - Report local resource choices
 * @hdev:	VMBus's tracking struct for this root PCI bus
 *
 * The host OS is expecting to be sent a request as a message
 * which contains all the resources that the device will use.
 * The response contains those same resources, "translated"
 * which is to say, the values which should be used by the
 * hardware, when it delivers an interrupt.  (MMIO resources are
 * used in local terms.)  This is nice for Windows, and lines up
 * with the FDO/PDO split, which doesn't exist in Linux.  Linux
 * is deeply expecting to scan an emulated PCI configuration
 * space.  So this message is sent here only to drive the state
 * machine on the host forward.
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_send_resources_allocated(struct hv_device *hdev)
{
	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
	struct pci_resources_assigned *res_assigned;
	struct pci_resources_assigned2 *res_assigned2;
	struct hv_pci_compl comp_pkt;
	struct hv_pci_dev *hpdev;
	struct pci_packet *pkt;
	size_t size_res;
	int wslot;
	int ret;

	size_res = (hbus->protocol_version < PCI_PROTOCOL_VERSION_1_2)
			? sizeof(*res_assigned) : sizeof(*res_assigned2);

	pkt = kmalloc(sizeof(*pkt) + size_res, GFP_KERNEL);
	if (!pkt)
		return -ENOMEM;

	ret = 0;

	for (wslot = 0; wslot < 256; wslot++) {
		hpdev = get_pcichild_wslot(hbus, wslot);
		if (!hpdev)
			continue;

		memset(pkt, 0, sizeof(*pkt) + size_res);
		init_completion(&comp_pkt.host_event);
		pkt->completion_func = hv_pci_generic_compl;
		pkt->compl_ctxt = &comp_pkt;

		if (hbus->protocol_version < PCI_PROTOCOL_VERSION_1_2) {
			res_assigned =
				(struct pci_resources_assigned *)&pkt->message;
			res_assigned->message_type.type =
				PCI_RESOURCES_ASSIGNED;
			res_assigned->wslot.slot = hpdev->desc.win_slot.slot;
		} else {
			res_assigned2 =
				(struct pci_resources_assigned2 *)&pkt->message;
			res_assigned2->message_type.type =
				PCI_RESOURCES_ASSIGNED2;
			res_assigned2->wslot.slot = hpdev->desc.win_slot.slot;
		}
		put_pcichild(hpdev);

		ret = vmbus_sendpacket(hdev->channel, &pkt->message,
				size_res, (unsigned long)pkt,
				VM_PKT_DATA_INBAND,
				VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
		if (!ret)
			ret = wait_for_response(hdev, &comp_pkt.host_event);
		if (ret)
			break;

		if (comp_pkt.completion_status < 0) {
			ret = -EPROTO;
			dev_err(&hdev->device,
				"resource allocated returned 0x%x",
				comp_pkt.completion_status);
			break;
		}

		hbus->wslot_res_allocated = wslot;
	}

	kfree(pkt);
	return ret;
}

/**
 * hv_send_resources_released() - Report local resources
 * released
 * @hdev:	VMBus's tracking struct for this root PCI bus
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_send_resources_released(struct hv_device *hdev)
{
	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
	struct pci_child_message pkt;
	struct hv_pci_dev *hpdev;
	int wslot;
	int ret;

	for (wslot = hbus->wslot_res_allocated; wslot >= 0; wslot--) {
		hpdev = get_pcichild_wslot(hbus, wslot);
		if (!hpdev)
			continue;

		memset(&pkt, 0, sizeof(pkt));
		pkt.message_type.type = PCI_RESOURCES_RELEASED;
		pkt.wslot.slot = hpdev->desc.win_slot.slot;

		put_pcichild(hpdev);

		ret = vmbus_sendpacket(hdev->channel, &pkt, sizeof(pkt), 0,
				       VM_PKT_DATA_INBAND, 0);
		if (ret)
			return ret;

		hbus->wslot_res_allocated = wslot - 1;
	}

	hbus->wslot_res_allocated = -1;

	return 0;
}

static void get_hvpcibus(struct hv_pcibus_device *hbus)
{
	refcount_inc(&hbus->remove_lock);
}

static void put_hvpcibus(struct hv_pcibus_device *hbus)
{
	if (refcount_dec_and_test(&hbus->remove_lock))
		complete(&hbus->remove_event);
}

#define HVPCI_DOM_MAP_SIZE (64 * 1024)
static DECLARE_BITMAP(hvpci_dom_map, HVPCI_DOM_MAP_SIZE);

/*
 * PCI domain number 0 is used by emulated devices on Gen1 VMs, so define 0
 * as invalid for passthrough PCI devices of this driver.
 */
#define HVPCI_DOM_INVALID 0

/**
 * hv_get_dom_num() - Get a valid PCI domain number
 * Check if the PCI domain number is in use, and return another number if
 * it is in use.
 *
 * @dom: Requested domain number
 *
 * return: domain number on success, HVPCI_DOM_INVALID on failure
 */
static u16 hv_get_dom_num(u16 dom)
{
	unsigned int i;

	if (test_and_set_bit(dom, hvpci_dom_map) == 0)
		return dom;

	for_each_clear_bit(i, hvpci_dom_map, HVPCI_DOM_MAP_SIZE) {
		if (test_and_set_bit(i, hvpci_dom_map) == 0)
			return i;
	}

	return HVPCI_DOM_INVALID;
}

/**
 * hv_put_dom_num() - Mark the PCI domain number as free
 * @dom: Domain number to be freed
 */
static void hv_put_dom_num(u16 dom)
{
	clear_bit(dom, hvpci_dom_map);
}

/**
 * hv_pci_probe() - New VMBus channel probe, for a root PCI bus
 * @hdev:	VMBus's tracking struct for this root PCI bus
 * @dev_id:	Identifies the device itself
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_pci_probe(struct hv_device *hdev,
			const struct hv_vmbus_device_id *dev_id)
{
	struct hv_pcibus_device *hbus;
	u16 dom_req, dom;
	char *name;
	bool enter_d0_retry = true;
	int ret;

	/*
	 * hv_pcibus_device contains the hypercall arguments for retargeting in
	 * hv_irq_unmask(). Those must not cross a page boundary.
	 */
	BUILD_BUG_ON(sizeof(*hbus) > HV_HYP_PAGE_SIZE);

	/*
	 * With the recent 59bb47985c1d ("mm, sl[aou]b: guarantee natural
	 * alignment for kmalloc(power-of-two)"), kzalloc() is able to allocate
	 * a 4KB buffer that is guaranteed to be 4KB-aligned. Here the size and
	 * alignment of hbus is important because hbus's field
	 * retarget_msi_interrupt_params must not cross a 4KB page boundary.
	 *
	 * Here we prefer kzalloc to get_zeroed_page(), because a buffer
	 * allocated by the latter is not tracked and scanned by kmemleak, and
	 * hence kmemleak reports the pointer contained in the hbus buffer
	 * (i.e. the hpdev struct, which is created in new_pcichild_device() and
	 * is tracked by hbus->children) as memory leak (false positive).
	 *
	 * If the kernel doesn't have 59bb47985c1d, get_zeroed_page() *must* be
	 * used to allocate the hbus buffer and we can avoid the kmemleak false
	 * positive by using kmemleak_alloc() and kmemleak_free() to ask
	 * kmemleak to track and scan the hbus buffer.
	 */
	hbus = kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
	if (!hbus)
		return -ENOMEM;
	hbus->state = hv_pcibus_init;
	hbus->wslot_res_allocated = -1;

	/*
	 * The PCI bus "domain" is what is called "segment" in ACPI and other
	 * specs. Pull it from the instance ID, to get something usually
	 * unique. In rare cases of collision, we will find out another number
	 * not in use.
	 *
	 * Note that, since this code only runs in a Hyper-V VM, Hyper-V
	 * together with this guest driver can guarantee that (1) The only
	 * domain used by Gen1 VMs for something that looks like a physical
	 * PCI bus (which is actually emulated by the hypervisor) is domain 0.
	 * (2) There will be no overlap between domains (after fixing possible
	 * collisions) in the same VM.
	 */
	dom_req = hdev->dev_instance.b[5] << 8 | hdev->dev_instance.b[4];
	dom = hv_get_dom_num(dom_req);

	if (dom == HVPCI_DOM_INVALID) {
		dev_err(&hdev->device,
			"Unable to use dom# 0x%hx or other numbers", dom_req);
		ret = -EINVAL;
		goto free_bus;
	}

	if (dom != dom_req)
		dev_info(&hdev->device,
			 "PCI dom# 0x%hx has collision, using 0x%hx",
			 dom_req, dom);

	hbus->sysdata.domain = dom;

	hbus->hdev = hdev;
	refcount_set(&hbus->remove_lock, 1);
	INIT_LIST_HEAD(&hbus->children);
	INIT_LIST_HEAD(&hbus->dr_list);
	INIT_LIST_HEAD(&hbus->resources_for_children);
	spin_lock_init(&hbus->config_lock);
	spin_lock_init(&hbus->device_list_lock);
	spin_lock_init(&hbus->retarget_msi_interrupt_lock);
	init_completion(&hbus->remove_event);
	hbus->wq = alloc_ordered_workqueue("hv_pci_%x", 0,
					   hbus->sysdata.domain);
	if (!hbus->wq) {
		ret = -ENOMEM;
		goto free_dom;
	}

	ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0,
			 hv_pci_onchannelcallback, hbus);
	if (ret)
		goto destroy_wq;

	hv_set_drvdata(hdev, hbus);

	ret = hv_pci_protocol_negotiation(hdev, pci_protocol_versions,
					  ARRAY_SIZE(pci_protocol_versions));
	if (ret)
		goto close;

	ret = hv_allocate_config_window(hbus);
	if (ret)
		goto close;

	hbus->cfg_addr = ioremap(hbus->mem_config->start,
				 PCI_CONFIG_MMIO_LENGTH);
	if (!hbus->cfg_addr) {
		dev_err(&hdev->device,
			"Unable to map a virtual address for config space\n");
		ret = -ENOMEM;
		goto free_config;
	}

	name = kasprintf(GFP_KERNEL, "%pUL", &hdev->dev_instance);
	if (!name) {
		ret = -ENOMEM;
		goto unmap;
	}

	hbus->sysdata.fwnode = irq_domain_alloc_named_fwnode(name);
	kfree(name);
	if (!hbus->sysdata.fwnode) {
		ret = -ENOMEM;
		goto unmap;
	}

	ret = hv_pcie_init_irq_domain(hbus);
	if (ret)
		goto free_fwnode;

retry:
	ret = hv_pci_query_relations(hdev);
	if (ret)
		goto free_irq_domain;

	ret = hv_pci_enter_d0(hdev);
	/*
	 * In certain case (Kdump) the pci device of interest was
	 * not cleanly shut down and resource is still held on host
	 * side, the host could return invalid device status.
	 * We need to explicitly request host to release the resource
	 * and try to enter D0 again.
	 * Since the hv_pci_bus_exit() call releases structures
	 * of all its child devices, we need to start the retry from
	 * hv_pci_query_relations() call, requesting host to send
	 * the synchronous child device relations message before this
	 * information is needed in hv_send_resources_allocated()
	 * call later.
	 */
	if (ret == -EPROTO && enter_d0_retry) {
		enter_d0_retry = false;

		dev_err(&hdev->device, "Retrying D0 Entry\n");

		/*
		 * Hv_pci_bus_exit() calls hv_send_resources_released()
		 * to free up resources of its child devices.
		 * In the kdump kernel we need to set the
		 * wslot_res_allocated to 255 so it scans all child
		 * devices to release resources allocated in the
		 * normal kernel before panic happened.
		 */
		hbus->wslot_res_allocated = 255;
		ret = hv_pci_bus_exit(hdev, true);

		if (ret == 0)
			goto retry;

		dev_err(&hdev->device,
			"Retrying D0 failed with ret %d\n", ret);
	}
	if (ret)
		goto free_irq_domain;

	ret = hv_pci_allocate_bridge_windows(hbus);
	if (ret)
		goto exit_d0;

	ret = hv_send_resources_allocated(hdev);
	if (ret)
		goto free_windows;

	prepopulate_bars(hbus);

	hbus->state = hv_pcibus_probed;

	ret = create_root_hv_pci_bus(hbus);
	if (ret)
		goto free_windows;

	return 0;

free_windows:
	hv_pci_free_bridge_windows(hbus);
exit_d0:
	(void) hv_pci_bus_exit(hdev, true);
free_irq_domain:
	irq_domain_remove(hbus->irq_domain);
free_fwnode:
	irq_domain_free_fwnode(hbus->sysdata.fwnode);
unmap:
	iounmap(hbus->cfg_addr);
free_config:
	hv_free_config_window(hbus);
close:
	vmbus_close(hdev->channel);
destroy_wq:
	destroy_workqueue(hbus->wq);
free_dom:
	hv_put_dom_num(hbus->sysdata.domain);
free_bus:
	kfree(hbus);
	return ret;
}

static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs)
{
	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
	struct {
		struct pci_packet teardown_packet;
		u8 buffer[sizeof(struct pci_message)];
	} pkt;
	struct hv_dr_state *dr;
	struct hv_pci_compl comp_pkt;
	int ret;

	/*
	 * After the host sends the RESCIND_CHANNEL message, it doesn't
	 * access the per-channel ringbuffer any longer.
	 */
	if (hdev->channel->rescind)
		return 0;

	if (!keep_devs) {
		/* Delete any children which might still exist. */
		dr = kzalloc(sizeof(*dr), GFP_KERNEL);
		if (dr && hv_pci_start_relations_work(hbus, dr))
			kfree(dr);
	}

	ret = hv_send_resources_released(hdev);
	if (ret) {
		dev_err(&hdev->device,
			"Couldn't send resources released packet(s)\n");
		return ret;
	}

	memset(&pkt.teardown_packet, 0, sizeof(pkt.teardown_packet));
	init_completion(&comp_pkt.host_event);
	pkt.teardown_packet.completion_func = hv_pci_generic_compl;
	pkt.teardown_packet.compl_ctxt = &comp_pkt;
	pkt.teardown_packet.message[0].type = PCI_BUS_D0EXIT;

	ret = vmbus_sendpacket(hdev->channel, &pkt.teardown_packet.message,
			       sizeof(struct pci_message),
			       (unsigned long)&pkt.teardown_packet,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (ret)
		return ret;

	if (wait_for_completion_timeout(&comp_pkt.host_event, 10 * HZ) == 0)
		return -ETIMEDOUT;

	return 0;
}

/**
 * hv_pci_remove() - Remove routine for this VMBus channel
 * @hdev:	VMBus's tracking struct for this root PCI bus
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_pci_remove(struct hv_device *hdev)
{
	struct hv_pcibus_device *hbus;
	int ret;

	hbus = hv_get_drvdata(hdev);
	if (hbus->state == hv_pcibus_installed) {
		/* Remove the bus from PCI's point of view. */
		pci_lock_rescan_remove();
		pci_stop_root_bus(hbus->pci_bus);
		hv_pci_remove_slots(hbus);
		pci_remove_root_bus(hbus->pci_bus);
		pci_unlock_rescan_remove();
		hbus->state = hv_pcibus_removed;
	}

	ret = hv_pci_bus_exit(hdev, false);

	vmbus_close(hdev->channel);

	iounmap(hbus->cfg_addr);
	hv_free_config_window(hbus);
	pci_free_resource_list(&hbus->resources_for_children);
	hv_pci_free_bridge_windows(hbus);
	irq_domain_remove(hbus->irq_domain);
	irq_domain_free_fwnode(hbus->sysdata.fwnode);
	put_hvpcibus(hbus);
	wait_for_completion(&hbus->remove_event);
	destroy_workqueue(hbus->wq);

	hv_put_dom_num(hbus->sysdata.domain);

	kfree(hbus);
	return ret;
}

static int hv_pci_suspend(struct hv_device *hdev)
{
	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
	enum hv_pcibus_state old_state;
	int ret;

	/*
	 * hv_pci_suspend() must make sure there are no pending work items
	 * before calling vmbus_close(), since it runs in a process context
	 * as a callback in dpm_suspend().  When it starts to run, the channel
	 * callback hv_pci_onchannelcallback(), which runs in a tasklet
	 * context, can be still running concurrently and scheduling new work
	 * items onto hbus->wq in hv_pci_devices_present() and
	 * hv_pci_eject_device(), and the work item handlers can access the
	 * vmbus channel, which can be being closed by hv_pci_suspend(), e.g.
	 * the work item handler pci_devices_present_work() ->
	 * new_pcichild_device() writes to the vmbus channel.
	 *
	 * To eliminate the race, hv_pci_suspend() disables the channel
	 * callback tasklet, sets hbus->state to hv_pcibus_removing, and
	 * re-enables the tasklet. This way, when hv_pci_suspend() proceeds,
	 * it knows that no new work item can be scheduled, and then it flushes
	 * hbus->wq and safely closes the vmbus channel.
	 */
	tasklet_disable(&hdev->channel->callback_event);

	/* Change the hbus state to prevent new work items. */
	old_state = hbus->state;
	if (hbus->state == hv_pcibus_installed)
		hbus->state = hv_pcibus_removing;

	tasklet_enable(&hdev->channel->callback_event);

	if (old_state != hv_pcibus_installed)
		return -EINVAL;

	flush_workqueue(hbus->wq);

	ret = hv_pci_bus_exit(hdev, true);
	if (ret)
		return ret;

	vmbus_close(hdev->channel);

	return 0;
}

static int hv_pci_restore_msi_msg(struct pci_dev *pdev, void *arg)
{
	struct msi_desc *entry;
	struct irq_data *irq_data;

	for_each_pci_msi_entry(entry, pdev) {
		irq_data = irq_get_irq_data(entry->irq);
		if (WARN_ON_ONCE(!irq_data))
			return -EINVAL;

		hv_compose_msi_msg(irq_data, &entry->msg);
	}

	return 0;
}

/*
 * Upon resume, pci_restore_msi_state() -> ... ->  __pci_write_msi_msg()
 * directly writes the MSI/MSI-X registers via MMIO, but since Hyper-V
 * doesn't trap and emulate the MMIO accesses, here hv_compose_msi_msg()
 * must be used to ask Hyper-V to re-create the IOMMU Interrupt Remapping
 * Table entries.
 */
static void hv_pci_restore_msi_state(struct hv_pcibus_device *hbus)
{
	pci_walk_bus(hbus->pci_bus, hv_pci_restore_msi_msg, NULL);
}

static int hv_pci_resume(struct hv_device *hdev)
{
	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
	enum pci_protocol_version_t version[1];
	int ret;

	hbus->state = hv_pcibus_init;

	ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0,
			 hv_pci_onchannelcallback, hbus);
	if (ret)
		return ret;

	/* Only use the version that was in use before hibernation. */
	version[0] = hbus->protocol_version;
	ret = hv_pci_protocol_negotiation(hdev, version, 1);
	if (ret)
		goto out;

	ret = hv_pci_query_relations(hdev);
	if (ret)
		goto out;

	ret = hv_pci_enter_d0(hdev);
	if (ret)
		goto out;

	ret = hv_send_resources_allocated(hdev);
	if (ret)
		goto out;

	prepopulate_bars(hbus);

	hv_pci_restore_msi_state(hbus);

	hbus->state = hv_pcibus_installed;
	return 0;
out:
	vmbus_close(hdev->channel);
	return ret;
}

static const struct hv_vmbus_device_id hv_pci_id_table[] = {
	/* PCI Pass-through Class ID */
	/* 44C4F61D-4444-4400-9D52-802E27EDE19F */
	{ HV_PCIE_GUID, },
	{ },
};

MODULE_DEVICE_TABLE(vmbus, hv_pci_id_table);

static struct hv_driver hv_pci_drv = {
	.name		= "hv_pci",
	.id_table	= hv_pci_id_table,
	.probe		= hv_pci_probe,
	.remove		= hv_pci_remove,
	.suspend	= hv_pci_suspend,
	.resume		= hv_pci_resume,
};

static void __exit exit_hv_pci_drv(void)
{
	vmbus_driver_unregister(&hv_pci_drv);

	hvpci_block_ops.read_block = NULL;
	hvpci_block_ops.write_block = NULL;
	hvpci_block_ops.reg_blk_invalidate = NULL;
}

static int __init init_hv_pci_drv(void)
{
	/* Set the invalid domain number's bit, so it will not be used */
	set_bit(HVPCI_DOM_INVALID, hvpci_dom_map);

	/* Initialize PCI block r/w interface */
	hvpci_block_ops.read_block = hv_read_config_block;
	hvpci_block_ops.write_block = hv_write_config_block;
	hvpci_block_ops.reg_blk_invalidate = hv_register_block_invalidate;

	return vmbus_driver_register(&hv_pci_drv);
}

module_init(init_hv_pci_drv);
module_exit(exit_hv_pci_drv);

MODULE_DESCRIPTION("Hyper-V PCI");
MODULE_LICENSE("GPL v2");