cxgb4_main.c 138 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 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085
/*
 * This file is part of the Chelsio T4 Ethernet driver for Linux.
 *
 * Copyright (c) 2003-2014 Chelsio Communications, Inc. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/bitmap.h>
#include <linux/crc32.h>
#include <linux/ctype.h>
#include <linux/debugfs.h>
#include <linux/err.h>
#include <linux/etherdevice.h>
#include <linux/firmware.h>
#include <linux/if.h>
#include <linux/if_vlan.h>
#include <linux/init.h>
#include <linux/log2.h>
#include <linux/mdio.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/mutex.h>
#include <linux/netdevice.h>
#include <linux/pci.h>
#include <linux/aer.h>
#include <linux/rtnetlink.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/sockios.h>
#include <linux/vmalloc.h>
#include <linux/workqueue.h>
#include <net/neighbour.h>
#include <net/netevent.h>
#include <net/addrconf.h>
#include <net/bonding.h>
#include <net/addrconf.h>
#include <asm/uaccess.h>

#include "cxgb4.h"
#include "t4_regs.h"
#include "t4_values.h"
#include "t4_msg.h"
#include "t4fw_api.h"
#include "t4fw_version.h"
#include "cxgb4_dcb.h"
#include "cxgb4_debugfs.h"
#include "clip_tbl.h"
#include "l2t.h"

char cxgb4_driver_name[] = KBUILD_MODNAME;

#ifdef DRV_VERSION
#undef DRV_VERSION
#endif
#define DRV_VERSION "2.0.0-ko"
const char cxgb4_driver_version[] = DRV_VERSION;
#define DRV_DESC "Chelsio T4/T5/T6 Network Driver"

/* Host shadow copy of ingress filter entry.  This is in host native format
 * and doesn't match the ordering or bit order, etc. of the hardware of the
 * firmware command.  The use of bit-field structure elements is purely to
 * remind ourselves of the field size limitations and save memory in the case
 * where the filter table is large.
 */
struct filter_entry {
	/* Administrative fields for filter.
	 */
	u32 valid:1;            /* filter allocated and valid */
	u32 locked:1;           /* filter is administratively locked */

	u32 pending:1;          /* filter action is pending firmware reply */
	u32 smtidx:8;           /* Source MAC Table index for smac */
	struct l2t_entry *l2t;  /* Layer Two Table entry for dmac */

	/* The filter itself.  Most of this is a straight copy of information
	 * provided by the extended ioctl().  Some fields are translated to
	 * internal forms -- for instance the Ingress Queue ID passed in from
	 * the ioctl() is translated into the Absolute Ingress Queue ID.
	 */
	struct ch_filter_specification fs;
};

#define DFLT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK | \
			 NETIF_MSG_TIMER | NETIF_MSG_IFDOWN | NETIF_MSG_IFUP |\
			 NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)

/* Macros needed to support the PCI Device ID Table ...
 */
#define CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN \
	static const struct pci_device_id cxgb4_pci_tbl[] = {
#define CH_PCI_DEVICE_ID_FUNCTION 0x4

/* Include PCI Device IDs for both PF4 and PF0-3 so our PCI probe() routine is
 * called for both.
 */
#define CH_PCI_DEVICE_ID_FUNCTION2 0x0

#define CH_PCI_ID_TABLE_ENTRY(devid) \
		{PCI_VDEVICE(CHELSIO, (devid)), 4}

#define CH_PCI_DEVICE_ID_TABLE_DEFINE_END \
		{ 0, } \
	}

#include "t4_pci_id_tbl.h"

#define FW4_FNAME "cxgb4/t4fw.bin"
#define FW5_FNAME "cxgb4/t5fw.bin"
#define FW6_FNAME "cxgb4/t6fw.bin"
#define FW4_CFNAME "cxgb4/t4-config.txt"
#define FW5_CFNAME "cxgb4/t5-config.txt"
#define FW6_CFNAME "cxgb4/t6-config.txt"
#define PHY_AQ1202_FIRMWARE "cxgb4/aq1202_fw.cld"
#define PHY_BCM84834_FIRMWARE "cxgb4/bcm8483.bin"
#define PHY_AQ1202_DEVICEID 0x4409
#define PHY_BCM84834_DEVICEID 0x4486

MODULE_DESCRIPTION(DRV_DESC);
MODULE_AUTHOR("Chelsio Communications");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_VERSION(DRV_VERSION);
MODULE_DEVICE_TABLE(pci, cxgb4_pci_tbl);
MODULE_FIRMWARE(FW4_FNAME);
MODULE_FIRMWARE(FW5_FNAME);
MODULE_FIRMWARE(FW6_FNAME);

/*
 * Normally we're willing to become the firmware's Master PF but will be happy
 * if another PF has already become the Master and initialized the adapter.
 * Setting "force_init" will cause this driver to forcibly establish itself as
 * the Master PF and initialize the adapter.
 */
static uint force_init;

module_param(force_init, uint, 0644);
MODULE_PARM_DESC(force_init, "Forcibly become Master PF and initialize adapter");

/*
 * Normally if the firmware we connect to has Configuration File support, we
 * use that and only fall back to the old Driver-based initialization if the
 * Configuration File fails for some reason.  If force_old_init is set, then
 * we'll always use the old Driver-based initialization sequence.
 */
static uint force_old_init;

module_param(force_old_init, uint, 0644);
MODULE_PARM_DESC(force_old_init, "Force old initialization sequence, deprecated"
		 " parameter");

static int dflt_msg_enable = DFLT_MSG_ENABLE;

module_param(dflt_msg_enable, int, 0644);
MODULE_PARM_DESC(dflt_msg_enable, "Chelsio T4 default message enable bitmap");

/*
 * The driver uses the best interrupt scheme available on a platform in the
 * order MSI-X, MSI, legacy INTx interrupts.  This parameter determines which
 * of these schemes the driver may consider as follows:
 *
 * msi = 2: choose from among all three options
 * msi = 1: only consider MSI and INTx interrupts
 * msi = 0: force INTx interrupts
 */
static int msi = 2;

module_param(msi, int, 0644);
MODULE_PARM_DESC(msi, "whether to use INTx (0), MSI (1) or MSI-X (2)");

/*
 * Queue interrupt hold-off timer values.  Queues default to the first of these
 * upon creation.
 */
static unsigned int intr_holdoff[SGE_NTIMERS - 1] = { 5, 10, 20, 50, 100 };

module_param_array(intr_holdoff, uint, NULL, 0644);
MODULE_PARM_DESC(intr_holdoff, "values for queue interrupt hold-off timers "
		 "0..4 in microseconds, deprecated parameter");

static unsigned int intr_cnt[SGE_NCOUNTERS - 1] = { 4, 8, 16 };

module_param_array(intr_cnt, uint, NULL, 0644);
MODULE_PARM_DESC(intr_cnt,
		 "thresholds 1..3 for queue interrupt packet counters, "
		 "deprecated parameter");

/*
 * Normally we tell the chip to deliver Ingress Packets into our DMA buffers
 * offset by 2 bytes in order to have the IP headers line up on 4-byte
 * boundaries.  This is a requirement for many architectures which will throw
 * a machine check fault if an attempt is made to access one of the 4-byte IP
 * header fields on a non-4-byte boundary.  And it's a major performance issue
 * even on some architectures which allow it like some implementations of the
 * x86 ISA.  However, some architectures don't mind this and for some very
 * edge-case performance sensitive applications (like forwarding large volumes
 * of small packets), setting this DMA offset to 0 will decrease the number of
 * PCI-E Bus transfers enough to measurably affect performance.
 */
static int rx_dma_offset = 2;

static bool vf_acls;

#ifdef CONFIG_PCI_IOV
module_param(vf_acls, bool, 0644);
MODULE_PARM_DESC(vf_acls, "if set enable virtualization L2 ACL enforcement, "
		 "deprecated parameter");

/* Configure the number of PCI-E Virtual Function which are to be instantiated
 * on SR-IOV Capable Physical Functions.
 */
static unsigned int num_vf[NUM_OF_PF_WITH_SRIOV];

module_param_array(num_vf, uint, NULL, 0644);
MODULE_PARM_DESC(num_vf, "number of VFs for each of PFs 0-3");
#endif

/* TX Queue select used to determine what algorithm to use for selecting TX
 * queue. Select between the kernel provided function (select_queue=0) or user
 * cxgb_select_queue function (select_queue=1)
 *
 * Default: select_queue=0
 */
static int select_queue;
module_param(select_queue, int, 0644);
MODULE_PARM_DESC(select_queue,
		 "Select between kernel provided method of selecting or driver method of selecting TX queue. Default is kernel method.");

static unsigned int tp_vlan_pri_map = HW_TPL_FR_MT_PR_IV_P_FC;

module_param(tp_vlan_pri_map, uint, 0644);
MODULE_PARM_DESC(tp_vlan_pri_map, "global compressed filter configuration, "
		 "deprecated parameter");

static struct dentry *cxgb4_debugfs_root;

static LIST_HEAD(adapter_list);
static DEFINE_MUTEX(uld_mutex);
/* Adapter list to be accessed from atomic context */
static LIST_HEAD(adap_rcu_list);
static DEFINE_SPINLOCK(adap_rcu_lock);
static struct cxgb4_uld_info ulds[CXGB4_ULD_MAX];
static const char *uld_str[] = { "RDMA", "iSCSI" };

static void link_report(struct net_device *dev)
{
	if (!netif_carrier_ok(dev))
		netdev_info(dev, "link down\n");
	else {
		static const char *fc[] = { "no", "Rx", "Tx", "Tx/Rx" };

		const char *s;
		const struct port_info *p = netdev_priv(dev);

		switch (p->link_cfg.speed) {
		case 10000:
			s = "10Gbps";
			break;
		case 1000:
			s = "1000Mbps";
			break;
		case 100:
			s = "100Mbps";
			break;
		case 40000:
			s = "40Gbps";
			break;
		default:
			pr_info("%s: unsupported speed: %d\n",
				dev->name, p->link_cfg.speed);
			return;
		}

		netdev_info(dev, "link up, %s, full-duplex, %s PAUSE\n", s,
			    fc[p->link_cfg.fc]);
	}
}

#ifdef CONFIG_CHELSIO_T4_DCB
/* Set up/tear down Data Center Bridging Priority mapping for a net device. */
static void dcb_tx_queue_prio_enable(struct net_device *dev, int enable)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adap = pi->adapter;
	struct sge_eth_txq *txq = &adap->sge.ethtxq[pi->first_qset];
	int i;

	/* We use a simple mapping of Port TX Queue Index to DCB
	 * Priority when we're enabling DCB.
	 */
	for (i = 0; i < pi->nqsets; i++, txq++) {
		u32 name, value;
		int err;

		name = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DMAQ) |
			FW_PARAMS_PARAM_X_V(
				FW_PARAMS_PARAM_DMAQ_EQ_DCBPRIO_ETH) |
			FW_PARAMS_PARAM_YZ_V(txq->q.cntxt_id));
		value = enable ? i : 0xffffffff;

		/* Since we can be called while atomic (from "interrupt
		 * level") we need to issue the Set Parameters Commannd
		 * without sleeping (timeout < 0).
		 */
		err = t4_set_params_timeout(adap, adap->mbox, adap->pf, 0, 1,
					    &name, &value,
					    -FW_CMD_MAX_TIMEOUT);

		if (err)
			dev_err(adap->pdev_dev,
				"Can't %s DCB Priority on port %d, TX Queue %d: err=%d\n",
				enable ? "set" : "unset", pi->port_id, i, -err);
		else
			txq->dcb_prio = value;
	}
}
#endif /* CONFIG_CHELSIO_T4_DCB */

void t4_os_link_changed(struct adapter *adapter, int port_id, int link_stat)
{
	struct net_device *dev = adapter->port[port_id];

	/* Skip changes from disabled ports. */
	if (netif_running(dev) && link_stat != netif_carrier_ok(dev)) {
		if (link_stat)
			netif_carrier_on(dev);
		else {
#ifdef CONFIG_CHELSIO_T4_DCB
			cxgb4_dcb_state_init(dev);
			dcb_tx_queue_prio_enable(dev, false);
#endif /* CONFIG_CHELSIO_T4_DCB */
			netif_carrier_off(dev);
		}

		link_report(dev);
	}
}

void t4_os_portmod_changed(const struct adapter *adap, int port_id)
{
	static const char *mod_str[] = {
		NULL, "LR", "SR", "ER", "passive DA", "active DA", "LRM"
	};

	const struct net_device *dev = adap->port[port_id];
	const struct port_info *pi = netdev_priv(dev);

	if (pi->mod_type == FW_PORT_MOD_TYPE_NONE)
		netdev_info(dev, "port module unplugged\n");
	else if (pi->mod_type < ARRAY_SIZE(mod_str))
		netdev_info(dev, "%s module inserted\n", mod_str[pi->mod_type]);
}

/*
 * Configure the exact and hash address filters to handle a port's multicast
 * and secondary unicast MAC addresses.
 */
static int set_addr_filters(const struct net_device *dev, bool sleep)
{
	u64 mhash = 0;
	u64 uhash = 0;
	bool free = true;
	u16 filt_idx[7];
	const u8 *addr[7];
	int ret, naddr = 0;
	const struct netdev_hw_addr *ha;
	int uc_cnt = netdev_uc_count(dev);
	int mc_cnt = netdev_mc_count(dev);
	const struct port_info *pi = netdev_priv(dev);
	unsigned int mb = pi->adapter->pf;

	/* first do the secondary unicast addresses */
	netdev_for_each_uc_addr(ha, dev) {
		addr[naddr++] = ha->addr;
		if (--uc_cnt == 0 || naddr >= ARRAY_SIZE(addr)) {
			ret = t4_alloc_mac_filt(pi->adapter, mb, pi->viid, free,
					naddr, addr, filt_idx, &uhash, sleep);
			if (ret < 0)
				return ret;

			free = false;
			naddr = 0;
		}
	}

	/* next set up the multicast addresses */
	netdev_for_each_mc_addr(ha, dev) {
		addr[naddr++] = ha->addr;
		if (--mc_cnt == 0 || naddr >= ARRAY_SIZE(addr)) {
			ret = t4_alloc_mac_filt(pi->adapter, mb, pi->viid, free,
					naddr, addr, filt_idx, &mhash, sleep);
			if (ret < 0)
				return ret;

			free = false;
			naddr = 0;
		}
	}

	return t4_set_addr_hash(pi->adapter, mb, pi->viid, uhash != 0,
				uhash | mhash, sleep);
}

int dbfifo_int_thresh = 10; /* 10 == 640 entry threshold */
module_param(dbfifo_int_thresh, int, 0644);
MODULE_PARM_DESC(dbfifo_int_thresh, "doorbell fifo interrupt threshold");

/*
 * usecs to sleep while draining the dbfifo
 */
static int dbfifo_drain_delay = 1000;
module_param(dbfifo_drain_delay, int, 0644);
MODULE_PARM_DESC(dbfifo_drain_delay,
		 "usecs to sleep while draining the dbfifo");

/*
 * Set Rx properties of a port, such as promiscruity, address filters, and MTU.
 * If @mtu is -1 it is left unchanged.
 */
static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok)
{
	int ret;
	struct port_info *pi = netdev_priv(dev);

	ret = set_addr_filters(dev, sleep_ok);
	if (ret == 0)
		ret = t4_set_rxmode(pi->adapter, pi->adapter->pf, pi->viid, mtu,
				    (dev->flags & IFF_PROMISC) ? 1 : 0,
				    (dev->flags & IFF_ALLMULTI) ? 1 : 0, 1, -1,
				    sleep_ok);
	return ret;
}

/**
 *	link_start - enable a port
 *	@dev: the port to enable
 *
 *	Performs the MAC and PHY actions needed to enable a port.
 */
static int link_start(struct net_device *dev)
{
	int ret;
	struct port_info *pi = netdev_priv(dev);
	unsigned int mb = pi->adapter->pf;

	/*
	 * We do not set address filters and promiscuity here, the stack does
	 * that step explicitly.
	 */
	ret = t4_set_rxmode(pi->adapter, mb, pi->viid, dev->mtu, -1, -1, -1,
			    !!(dev->features & NETIF_F_HW_VLAN_CTAG_RX), true);
	if (ret == 0) {
		ret = t4_change_mac(pi->adapter, mb, pi->viid,
				    pi->xact_addr_filt, dev->dev_addr, true,
				    true);
		if (ret >= 0) {
			pi->xact_addr_filt = ret;
			ret = 0;
		}
	}
	if (ret == 0)
		ret = t4_link_l1cfg(pi->adapter, mb, pi->tx_chan,
				    &pi->link_cfg);
	if (ret == 0) {
		local_bh_disable();
		ret = t4_enable_vi_params(pi->adapter, mb, pi->viid, true,
					  true, CXGB4_DCB_ENABLED);
		local_bh_enable();
	}

	return ret;
}

int cxgb4_dcb_enabled(const struct net_device *dev)
{
#ifdef CONFIG_CHELSIO_T4_DCB
	struct port_info *pi = netdev_priv(dev);

	if (!pi->dcb.enabled)
		return 0;

	return ((pi->dcb.state == CXGB4_DCB_STATE_FW_ALLSYNCED) ||
		(pi->dcb.state == CXGB4_DCB_STATE_HOST));
#else
	return 0;
#endif
}
EXPORT_SYMBOL(cxgb4_dcb_enabled);

#ifdef CONFIG_CHELSIO_T4_DCB
/* Handle a Data Center Bridging update message from the firmware. */
static void dcb_rpl(struct adapter *adap, const struct fw_port_cmd *pcmd)
{
	int port = FW_PORT_CMD_PORTID_G(ntohl(pcmd->op_to_portid));
	struct net_device *dev = adap->port[port];
	int old_dcb_enabled = cxgb4_dcb_enabled(dev);
	int new_dcb_enabled;

	cxgb4_dcb_handle_fw_update(adap, pcmd);
	new_dcb_enabled = cxgb4_dcb_enabled(dev);

	/* If the DCB has become enabled or disabled on the port then we're
	 * going to need to set up/tear down DCB Priority parameters for the
	 * TX Queues associated with the port.
	 */
	if (new_dcb_enabled != old_dcb_enabled)
		dcb_tx_queue_prio_enable(dev, new_dcb_enabled);
}
#endif /* CONFIG_CHELSIO_T4_DCB */

/* Clear a filter and release any of its resources that we own.  This also
 * clears the filter's "pending" status.
 */
static void clear_filter(struct adapter *adap, struct filter_entry *f)
{
	/* If the new or old filter have loopback rewriteing rules then we'll
	 * need to free any existing Layer Two Table (L2T) entries of the old
	 * filter rule.  The firmware will handle freeing up any Source MAC
	 * Table (SMT) entries used for rewriting Source MAC Addresses in
	 * loopback rules.
	 */
	if (f->l2t)
		cxgb4_l2t_release(f->l2t);

	/* The zeroing of the filter rule below clears the filter valid,
	 * pending, locked flags, l2t pointer, etc. so it's all we need for
	 * this operation.
	 */
	memset(f, 0, sizeof(*f));
}

/* Handle a filter write/deletion reply.
 */
static void filter_rpl(struct adapter *adap, const struct cpl_set_tcb_rpl *rpl)
{
	unsigned int idx = GET_TID(rpl);
	unsigned int nidx = idx - adap->tids.ftid_base;
	unsigned int ret;
	struct filter_entry *f;

	if (idx >= adap->tids.ftid_base && nidx <
	   (adap->tids.nftids + adap->tids.nsftids)) {
		idx = nidx;
		ret = TCB_COOKIE_G(rpl->cookie);
		f = &adap->tids.ftid_tab[idx];

		if (ret == FW_FILTER_WR_FLT_DELETED) {
			/* Clear the filter when we get confirmation from the
			 * hardware that the filter has been deleted.
			 */
			clear_filter(adap, f);
		} else if (ret == FW_FILTER_WR_SMT_TBL_FULL) {
			dev_err(adap->pdev_dev, "filter %u setup failed due to full SMT\n",
				idx);
			clear_filter(adap, f);
		} else if (ret == FW_FILTER_WR_FLT_ADDED) {
			f->smtidx = (be64_to_cpu(rpl->oldval) >> 24) & 0xff;
			f->pending = 0;  /* asynchronous setup completed */
			f->valid = 1;
		} else {
			/* Something went wrong.  Issue a warning about the
			 * problem and clear everything out.
			 */
			dev_err(adap->pdev_dev, "filter %u setup failed with error %u\n",
				idx, ret);
			clear_filter(adap, f);
		}
	}
}

/* Response queue handler for the FW event queue.
 */
static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
			  const struct pkt_gl *gl)
{
	u8 opcode = ((const struct rss_header *)rsp)->opcode;

	rsp++;                                          /* skip RSS header */

	/* FW can send EGR_UPDATEs encapsulated in a CPL_FW4_MSG.
	 */
	if (unlikely(opcode == CPL_FW4_MSG &&
	   ((const struct cpl_fw4_msg *)rsp)->type == FW_TYPE_RSSCPL)) {
		rsp++;
		opcode = ((const struct rss_header *)rsp)->opcode;
		rsp++;
		if (opcode != CPL_SGE_EGR_UPDATE) {
			dev_err(q->adap->pdev_dev, "unexpected FW4/CPL %#x on FW event queue\n"
				, opcode);
			goto out;
		}
	}

	if (likely(opcode == CPL_SGE_EGR_UPDATE)) {
		const struct cpl_sge_egr_update *p = (void *)rsp;
		unsigned int qid = EGR_QID_G(ntohl(p->opcode_qid));
		struct sge_txq *txq;

		txq = q->adap->sge.egr_map[qid - q->adap->sge.egr_start];
		txq->restarts++;
		if ((u8 *)txq < (u8 *)q->adap->sge.ofldtxq) {
			struct sge_eth_txq *eq;

			eq = container_of(txq, struct sge_eth_txq, q);
			netif_tx_wake_queue(eq->txq);
		} else {
			struct sge_ofld_txq *oq;

			oq = container_of(txq, struct sge_ofld_txq, q);
			tasklet_schedule(&oq->qresume_tsk);
		}
	} else if (opcode == CPL_FW6_MSG || opcode == CPL_FW4_MSG) {
		const struct cpl_fw6_msg *p = (void *)rsp;

#ifdef CONFIG_CHELSIO_T4_DCB
		const struct fw_port_cmd *pcmd = (const void *)p->data;
		unsigned int cmd = FW_CMD_OP_G(ntohl(pcmd->op_to_portid));
		unsigned int action =
			FW_PORT_CMD_ACTION_G(ntohl(pcmd->action_to_len16));

		if (cmd == FW_PORT_CMD &&
		    action == FW_PORT_ACTION_GET_PORT_INFO) {
			int port = FW_PORT_CMD_PORTID_G(
					be32_to_cpu(pcmd->op_to_portid));
			struct net_device *dev = q->adap->port[port];
			int state_input = ((pcmd->u.info.dcbxdis_pkd &
					    FW_PORT_CMD_DCBXDIS_F)
					   ? CXGB4_DCB_INPUT_FW_DISABLED
					   : CXGB4_DCB_INPUT_FW_ENABLED);

			cxgb4_dcb_state_fsm(dev, state_input);
		}

		if (cmd == FW_PORT_CMD &&
		    action == FW_PORT_ACTION_L2_DCB_CFG)
			dcb_rpl(q->adap, pcmd);
		else
#endif
			if (p->type == 0)
				t4_handle_fw_rpl(q->adap, p->data);
	} else if (opcode == CPL_L2T_WRITE_RPL) {
		const struct cpl_l2t_write_rpl *p = (void *)rsp;

		do_l2t_write_rpl(q->adap, p);
	} else if (opcode == CPL_SET_TCB_RPL) {
		const struct cpl_set_tcb_rpl *p = (void *)rsp;

		filter_rpl(q->adap, p);
	} else
		dev_err(q->adap->pdev_dev,
			"unexpected CPL %#x on FW event queue\n", opcode);
out:
	return 0;
}

/**
 *	uldrx_handler - response queue handler for ULD queues
 *	@q: the response queue that received the packet
 *	@rsp: the response queue descriptor holding the offload message
 *	@gl: the gather list of packet fragments
 *
 *	Deliver an ingress offload packet to a ULD.  All processing is done by
 *	the ULD, we just maintain statistics.
 */
static int uldrx_handler(struct sge_rspq *q, const __be64 *rsp,
			 const struct pkt_gl *gl)
{
	struct sge_ofld_rxq *rxq = container_of(q, struct sge_ofld_rxq, rspq);

	/* FW can send CPLs encapsulated in a CPL_FW4_MSG.
	 */
	if (((const struct rss_header *)rsp)->opcode == CPL_FW4_MSG &&
	    ((const struct cpl_fw4_msg *)(rsp + 1))->type == FW_TYPE_RSSCPL)
		rsp += 2;

	if (ulds[q->uld].rx_handler(q->adap->uld_handle[q->uld], rsp, gl)) {
		rxq->stats.nomem++;
		return -1;
	}
	if (gl == NULL)
		rxq->stats.imm++;
	else if (gl == CXGB4_MSG_AN)
		rxq->stats.an++;
	else
		rxq->stats.pkts++;
	return 0;
}

static void disable_msi(struct adapter *adapter)
{
	if (adapter->flags & USING_MSIX) {
		pci_disable_msix(adapter->pdev);
		adapter->flags &= ~USING_MSIX;
	} else if (adapter->flags & USING_MSI) {
		pci_disable_msi(adapter->pdev);
		adapter->flags &= ~USING_MSI;
	}
}

/*
 * Interrupt handler for non-data events used with MSI-X.
 */
static irqreturn_t t4_nondata_intr(int irq, void *cookie)
{
	struct adapter *adap = cookie;
	u32 v = t4_read_reg(adap, MYPF_REG(PL_PF_INT_CAUSE_A));

	if (v & PFSW_F) {
		adap->swintr = 1;
		t4_write_reg(adap, MYPF_REG(PL_PF_INT_CAUSE_A), v);
	}
	if (adap->flags & MASTER_PF)
		t4_slow_intr_handler(adap);
	return IRQ_HANDLED;
}

/*
 * Name the MSI-X interrupts.
 */
static void name_msix_vecs(struct adapter *adap)
{
	int i, j, msi_idx = 2, n = sizeof(adap->msix_info[0].desc);

	/* non-data interrupts */
	snprintf(adap->msix_info[0].desc, n, "%s", adap->port[0]->name);

	/* FW events */
	snprintf(adap->msix_info[1].desc, n, "%s-FWeventq",
		 adap->port[0]->name);

	/* Ethernet queues */
	for_each_port(adap, j) {
		struct net_device *d = adap->port[j];
		const struct port_info *pi = netdev_priv(d);

		for (i = 0; i < pi->nqsets; i++, msi_idx++)
			snprintf(adap->msix_info[msi_idx].desc, n, "%s-Rx%d",
				 d->name, i);
	}

	/* offload queues */
	for_each_ofldrxq(&adap->sge, i)
		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-ofld%d",
			 adap->port[0]->name, i);

	for_each_rdmarxq(&adap->sge, i)
		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-rdma%d",
			 adap->port[0]->name, i);

	for_each_rdmaciq(&adap->sge, i)
		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-rdma-ciq%d",
			 adap->port[0]->name, i);
}

static int request_msix_queue_irqs(struct adapter *adap)
{
	struct sge *s = &adap->sge;
	int err, ethqidx, ofldqidx = 0, rdmaqidx = 0, rdmaciqqidx = 0;
	int msi_index = 2;

	err = request_irq(adap->msix_info[1].vec, t4_sge_intr_msix, 0,
			  adap->msix_info[1].desc, &s->fw_evtq);
	if (err)
		return err;

	for_each_ethrxq(s, ethqidx) {
		err = request_irq(adap->msix_info[msi_index].vec,
				  t4_sge_intr_msix, 0,
				  adap->msix_info[msi_index].desc,
				  &s->ethrxq[ethqidx].rspq);
		if (err)
			goto unwind;
		msi_index++;
	}
	for_each_ofldrxq(s, ofldqidx) {
		err = request_irq(adap->msix_info[msi_index].vec,
				  t4_sge_intr_msix, 0,
				  adap->msix_info[msi_index].desc,
				  &s->ofldrxq[ofldqidx].rspq);
		if (err)
			goto unwind;
		msi_index++;
	}
	for_each_rdmarxq(s, rdmaqidx) {
		err = request_irq(adap->msix_info[msi_index].vec,
				  t4_sge_intr_msix, 0,
				  adap->msix_info[msi_index].desc,
				  &s->rdmarxq[rdmaqidx].rspq);
		if (err)
			goto unwind;
		msi_index++;
	}
	for_each_rdmaciq(s, rdmaciqqidx) {
		err = request_irq(adap->msix_info[msi_index].vec,
				  t4_sge_intr_msix, 0,
				  adap->msix_info[msi_index].desc,
				  &s->rdmaciq[rdmaciqqidx].rspq);
		if (err)
			goto unwind;
		msi_index++;
	}
	return 0;

unwind:
	while (--rdmaciqqidx >= 0)
		free_irq(adap->msix_info[--msi_index].vec,
			 &s->rdmaciq[rdmaciqqidx].rspq);
	while (--rdmaqidx >= 0)
		free_irq(adap->msix_info[--msi_index].vec,
			 &s->rdmarxq[rdmaqidx].rspq);
	while (--ofldqidx >= 0)
		free_irq(adap->msix_info[--msi_index].vec,
			 &s->ofldrxq[ofldqidx].rspq);
	while (--ethqidx >= 0)
		free_irq(adap->msix_info[--msi_index].vec,
			 &s->ethrxq[ethqidx].rspq);
	free_irq(adap->msix_info[1].vec, &s->fw_evtq);
	return err;
}

static void free_msix_queue_irqs(struct adapter *adap)
{
	int i, msi_index = 2;
	struct sge *s = &adap->sge;

	free_irq(adap->msix_info[1].vec, &s->fw_evtq);
	for_each_ethrxq(s, i)
		free_irq(adap->msix_info[msi_index++].vec, &s->ethrxq[i].rspq);
	for_each_ofldrxq(s, i)
		free_irq(adap->msix_info[msi_index++].vec, &s->ofldrxq[i].rspq);
	for_each_rdmarxq(s, i)
		free_irq(adap->msix_info[msi_index++].vec, &s->rdmarxq[i].rspq);
	for_each_rdmaciq(s, i)
		free_irq(adap->msix_info[msi_index++].vec, &s->rdmaciq[i].rspq);
}

/**
 *	cxgb4_write_rss - write the RSS table for a given port
 *	@pi: the port
 *	@queues: array of queue indices for RSS
 *
 *	Sets up the portion of the HW RSS table for the port's VI to distribute
 *	packets to the Rx queues in @queues.
 *	Should never be called before setting up sge eth rx queues
 */
int cxgb4_write_rss(const struct port_info *pi, const u16 *queues)
{
	u16 *rss;
	int i, err;
	struct adapter *adapter = pi->adapter;
	const struct sge_eth_rxq *rxq;

	rxq = &adapter->sge.ethrxq[pi->first_qset];
	rss = kmalloc(pi->rss_size * sizeof(u16), GFP_KERNEL);
	if (!rss)
		return -ENOMEM;

	/* map the queue indices to queue ids */
	for (i = 0; i < pi->rss_size; i++, queues++)
		rss[i] = rxq[*queues].rspq.abs_id;

	err = t4_config_rss_range(adapter, adapter->pf, pi->viid, 0,
				  pi->rss_size, rss, pi->rss_size);
	/* If Tunnel All Lookup isn't specified in the global RSS
	 * Configuration, then we need to specify a default Ingress
	 * Queue for any ingress packets which aren't hashed.  We'll
	 * use our first ingress queue ...
	 */
	if (!err)
		err = t4_config_vi_rss(adapter, adapter->mbox, pi->viid,
				       FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F |
				       FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F |
				       FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F |
				       FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F |
				       FW_RSS_VI_CONFIG_CMD_UDPEN_F,
				       rss[0]);
	kfree(rss);
	return err;
}

/**
 *	setup_rss - configure RSS
 *	@adap: the adapter
 *
 *	Sets up RSS for each port.
 */
static int setup_rss(struct adapter *adap)
{
	int i, j, err;

	for_each_port(adap, i) {
		const struct port_info *pi = adap2pinfo(adap, i);

		/* Fill default values with equal distribution */
		for (j = 0; j < pi->rss_size; j++)
			pi->rss[j] = j % pi->nqsets;

		err = cxgb4_write_rss(pi, pi->rss);
		if (err)
			return err;
	}
	return 0;
}

/*
 * Return the channel of the ingress queue with the given qid.
 */
static unsigned int rxq_to_chan(const struct sge *p, unsigned int qid)
{
	qid -= p->ingr_start;
	return netdev2pinfo(p->ingr_map[qid]->netdev)->tx_chan;
}

/*
 * Wait until all NAPI handlers are descheduled.
 */
static void quiesce_rx(struct adapter *adap)
{
	int i;

	for (i = 0; i < adap->sge.ingr_sz; i++) {
		struct sge_rspq *q = adap->sge.ingr_map[i];

		if (q && q->handler) {
			napi_disable(&q->napi);
			local_bh_disable();
			while (!cxgb_poll_lock_napi(q))
				mdelay(1);
			local_bh_enable();
		}

	}
}

/* Disable interrupt and napi handler */
static void disable_interrupts(struct adapter *adap)
{
	if (adap->flags & FULL_INIT_DONE) {
		t4_intr_disable(adap);
		if (adap->flags & USING_MSIX) {
			free_msix_queue_irqs(adap);
			free_irq(adap->msix_info[0].vec, adap);
		} else {
			free_irq(adap->pdev->irq, adap);
		}
		quiesce_rx(adap);
	}
}

/*
 * Enable NAPI scheduling and interrupt generation for all Rx queues.
 */
static void enable_rx(struct adapter *adap)
{
	int i;

	for (i = 0; i < adap->sge.ingr_sz; i++) {
		struct sge_rspq *q = adap->sge.ingr_map[i];

		if (!q)
			continue;
		if (q->handler) {
			cxgb_busy_poll_init_lock(q);
			napi_enable(&q->napi);
		}
		/* 0-increment GTS to start the timer and enable interrupts */
		t4_write_reg(adap, MYPF_REG(SGE_PF_GTS_A),
			     SEINTARM_V(q->intr_params) |
			     INGRESSQID_V(q->cntxt_id));
	}
}

static int alloc_ofld_rxqs(struct adapter *adap, struct sge_ofld_rxq *q,
			   unsigned int nq, unsigned int per_chan, int msi_idx,
			   u16 *ids)
{
	int i, err;

	for (i = 0; i < nq; i++, q++) {
		if (msi_idx > 0)
			msi_idx++;
		err = t4_sge_alloc_rxq(adap, &q->rspq, false,
				       adap->port[i / per_chan],
				       msi_idx, q->fl.size ? &q->fl : NULL,
				       uldrx_handler, 0);
		if (err)
			return err;
		memset(&q->stats, 0, sizeof(q->stats));
		if (ids)
			ids[i] = q->rspq.abs_id;
	}
	return 0;
}

/**
 *	setup_sge_queues - configure SGE Tx/Rx/response queues
 *	@adap: the adapter
 *
 *	Determines how many sets of SGE queues to use and initializes them.
 *	We support multiple queue sets per port if we have MSI-X, otherwise
 *	just one queue set per port.
 */
static int setup_sge_queues(struct adapter *adap)
{
	int err, msi_idx, i, j;
	struct sge *s = &adap->sge;

	bitmap_zero(s->starving_fl, s->egr_sz);
	bitmap_zero(s->txq_maperr, s->egr_sz);

	if (adap->flags & USING_MSIX)
		msi_idx = 1;         /* vector 0 is for non-queue interrupts */
	else {
		err = t4_sge_alloc_rxq(adap, &s->intrq, false, adap->port[0], 0,
				       NULL, NULL, -1);
		if (err)
			return err;
		msi_idx = -((int)s->intrq.abs_id + 1);
	}

	/* NOTE: If you add/delete any Ingress/Egress Queue allocations in here,
	 * don't forget to update the following which need to be
	 * synchronized to and changes here.
	 *
	 * 1. The calculations of MAX_INGQ in cxgb4.h.
	 *
	 * 2. Update enable_msix/name_msix_vecs/request_msix_queue_irqs
	 *    to accommodate any new/deleted Ingress Queues
	 *    which need MSI-X Vectors.
	 *
	 * 3. Update sge_qinfo_show() to include information on the
	 *    new/deleted queues.
	 */
	err = t4_sge_alloc_rxq(adap, &s->fw_evtq, true, adap->port[0],
			       msi_idx, NULL, fwevtq_handler, -1);
	if (err) {
freeout:	t4_free_sge_resources(adap);
		return err;
	}

	for_each_port(adap, i) {
		struct net_device *dev = adap->port[i];
		struct port_info *pi = netdev_priv(dev);
		struct sge_eth_rxq *q = &s->ethrxq[pi->first_qset];
		struct sge_eth_txq *t = &s->ethtxq[pi->first_qset];

		for (j = 0; j < pi->nqsets; j++, q++) {
			if (msi_idx > 0)
				msi_idx++;
			err = t4_sge_alloc_rxq(adap, &q->rspq, false, dev,
					       msi_idx, &q->fl,
					       t4_ethrx_handler,
					       t4_get_mps_bg_map(adap,
								 pi->tx_chan));
			if (err)
				goto freeout;
			q->rspq.idx = j;
			memset(&q->stats, 0, sizeof(q->stats));
		}
		for (j = 0; j < pi->nqsets; j++, t++) {
			err = t4_sge_alloc_eth_txq(adap, t, dev,
					netdev_get_tx_queue(dev, j),
					s->fw_evtq.cntxt_id);
			if (err)
				goto freeout;
		}
	}

	j = s->ofldqsets / adap->params.nports; /* ofld queues per channel */
	for_each_ofldrxq(s, i) {
		err = t4_sge_alloc_ofld_txq(adap, &s->ofldtxq[i],
					    adap->port[i / j],
					    s->fw_evtq.cntxt_id);
		if (err)
			goto freeout;
	}

#define ALLOC_OFLD_RXQS(firstq, nq, per_chan, ids) do { \
	err = alloc_ofld_rxqs(adap, firstq, nq, per_chan, msi_idx, ids); \
	if (err) \
		goto freeout; \
	if (msi_idx > 0) \
		msi_idx += nq; \
} while (0)

	ALLOC_OFLD_RXQS(s->ofldrxq, s->ofldqsets, j, s->ofld_rxq);
	ALLOC_OFLD_RXQS(s->rdmarxq, s->rdmaqs, 1, s->rdma_rxq);
	j = s->rdmaciqs / adap->params.nports; /* rdmaq queues per channel */
	ALLOC_OFLD_RXQS(s->rdmaciq, s->rdmaciqs, j, s->rdma_ciq);

#undef ALLOC_OFLD_RXQS

	for_each_port(adap, i) {
		/*
		 * Note that ->rdmarxq[i].rspq.cntxt_id below is 0 if we don't
		 * have RDMA queues, and that's the right value.
		 */
		err = t4_sge_alloc_ctrl_txq(adap, &s->ctrlq[i], adap->port[i],
					    s->fw_evtq.cntxt_id,
					    s->rdmarxq[i].rspq.cntxt_id);
		if (err)
			goto freeout;
	}

	t4_write_reg(adap, is_t4(adap->params.chip) ?
				MPS_TRC_RSS_CONTROL_A :
				MPS_T5_TRC_RSS_CONTROL_A,
		     RSSCONTROL_V(netdev2pinfo(adap->port[0])->tx_chan) |
		     QUEUENUMBER_V(s->ethrxq[0].rspq.abs_id));
	return 0;
}

/*
 * Allocate a chunk of memory using kmalloc or, if that fails, vmalloc.
 * The allocated memory is cleared.
 */
void *t4_alloc_mem(size_t size)
{
	void *p = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);

	if (!p)
		p = vzalloc(size);
	return p;
}

/*
 * Free memory allocated through alloc_mem().
 */
void t4_free_mem(void *addr)
{
	kvfree(addr);
}

/* Send a Work Request to write the filter at a specified index.  We construct
 * a Firmware Filter Work Request to have the work done and put the indicated
 * filter into "pending" mode which will prevent any further actions against
 * it till we get a reply from the firmware on the completion status of the
 * request.
 */
static int set_filter_wr(struct adapter *adapter, int fidx)
{
	struct filter_entry *f = &adapter->tids.ftid_tab[fidx];
	struct sk_buff *skb;
	struct fw_filter_wr *fwr;
	unsigned int ftid;

	skb = alloc_skb(sizeof(*fwr), GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	/* If the new filter requires loopback Destination MAC and/or VLAN
	 * rewriting then we need to allocate a Layer 2 Table (L2T) entry for
	 * the filter.
	 */
	if (f->fs.newdmac || f->fs.newvlan) {
		/* allocate L2T entry for new filter */
		f->l2t = t4_l2t_alloc_switching(adapter->l2t);
		if (f->l2t == NULL) {
			kfree_skb(skb);
			return -EAGAIN;
		}
		if (t4_l2t_set_switching(adapter, f->l2t, f->fs.vlan,
					f->fs.eport, f->fs.dmac)) {
			cxgb4_l2t_release(f->l2t);
			f->l2t = NULL;
			kfree_skb(skb);
			return -ENOMEM;
		}
	}

	ftid = adapter->tids.ftid_base + fidx;

	fwr = (struct fw_filter_wr *)__skb_put(skb, sizeof(*fwr));
	memset(fwr, 0, sizeof(*fwr));

	/* It would be nice to put most of the following in t4_hw.c but most
	 * of the work is translating the cxgbtool ch_filter_specification
	 * into the Work Request and the definition of that structure is
	 * currently in cxgbtool.h which isn't appropriate to pull into the
	 * common code.  We may eventually try to come up with a more neutral
	 * filter specification structure but for now it's easiest to simply
	 * put this fairly direct code in line ...
	 */
	fwr->op_pkd = htonl(FW_WR_OP_V(FW_FILTER_WR));
	fwr->len16_pkd = htonl(FW_WR_LEN16_V(sizeof(*fwr)/16));
	fwr->tid_to_iq =
		htonl(FW_FILTER_WR_TID_V(ftid) |
		      FW_FILTER_WR_RQTYPE_V(f->fs.type) |
		      FW_FILTER_WR_NOREPLY_V(0) |
		      FW_FILTER_WR_IQ_V(f->fs.iq));
	fwr->del_filter_to_l2tix =
		htonl(FW_FILTER_WR_RPTTID_V(f->fs.rpttid) |
		      FW_FILTER_WR_DROP_V(f->fs.action == FILTER_DROP) |
		      FW_FILTER_WR_DIRSTEER_V(f->fs.dirsteer) |
		      FW_FILTER_WR_MASKHASH_V(f->fs.maskhash) |
		      FW_FILTER_WR_DIRSTEERHASH_V(f->fs.dirsteerhash) |
		      FW_FILTER_WR_LPBK_V(f->fs.action == FILTER_SWITCH) |
		      FW_FILTER_WR_DMAC_V(f->fs.newdmac) |
		      FW_FILTER_WR_SMAC_V(f->fs.newsmac) |
		      FW_FILTER_WR_INSVLAN_V(f->fs.newvlan == VLAN_INSERT ||
					     f->fs.newvlan == VLAN_REWRITE) |
		      FW_FILTER_WR_RMVLAN_V(f->fs.newvlan == VLAN_REMOVE ||
					    f->fs.newvlan == VLAN_REWRITE) |
		      FW_FILTER_WR_HITCNTS_V(f->fs.hitcnts) |
		      FW_FILTER_WR_TXCHAN_V(f->fs.eport) |
		      FW_FILTER_WR_PRIO_V(f->fs.prio) |
		      FW_FILTER_WR_L2TIX_V(f->l2t ? f->l2t->idx : 0));
	fwr->ethtype = htons(f->fs.val.ethtype);
	fwr->ethtypem = htons(f->fs.mask.ethtype);
	fwr->frag_to_ovlan_vldm =
		(FW_FILTER_WR_FRAG_V(f->fs.val.frag) |
		 FW_FILTER_WR_FRAGM_V(f->fs.mask.frag) |
		 FW_FILTER_WR_IVLAN_VLD_V(f->fs.val.ivlan_vld) |
		 FW_FILTER_WR_OVLAN_VLD_V(f->fs.val.ovlan_vld) |
		 FW_FILTER_WR_IVLAN_VLDM_V(f->fs.mask.ivlan_vld) |
		 FW_FILTER_WR_OVLAN_VLDM_V(f->fs.mask.ovlan_vld));
	fwr->smac_sel = 0;
	fwr->rx_chan_rx_rpl_iq =
		htons(FW_FILTER_WR_RX_CHAN_V(0) |
		      FW_FILTER_WR_RX_RPL_IQ_V(adapter->sge.fw_evtq.abs_id));
	fwr->maci_to_matchtypem =
		htonl(FW_FILTER_WR_MACI_V(f->fs.val.macidx) |
		      FW_FILTER_WR_MACIM_V(f->fs.mask.macidx) |
		      FW_FILTER_WR_FCOE_V(f->fs.val.fcoe) |
		      FW_FILTER_WR_FCOEM_V(f->fs.mask.fcoe) |
		      FW_FILTER_WR_PORT_V(f->fs.val.iport) |
		      FW_FILTER_WR_PORTM_V(f->fs.mask.iport) |
		      FW_FILTER_WR_MATCHTYPE_V(f->fs.val.matchtype) |
		      FW_FILTER_WR_MATCHTYPEM_V(f->fs.mask.matchtype));
	fwr->ptcl = f->fs.val.proto;
	fwr->ptclm = f->fs.mask.proto;
	fwr->ttyp = f->fs.val.tos;
	fwr->ttypm = f->fs.mask.tos;
	fwr->ivlan = htons(f->fs.val.ivlan);
	fwr->ivlanm = htons(f->fs.mask.ivlan);
	fwr->ovlan = htons(f->fs.val.ovlan);
	fwr->ovlanm = htons(f->fs.mask.ovlan);
	memcpy(fwr->lip, f->fs.val.lip, sizeof(fwr->lip));
	memcpy(fwr->lipm, f->fs.mask.lip, sizeof(fwr->lipm));
	memcpy(fwr->fip, f->fs.val.fip, sizeof(fwr->fip));
	memcpy(fwr->fipm, f->fs.mask.fip, sizeof(fwr->fipm));
	fwr->lp = htons(f->fs.val.lport);
	fwr->lpm = htons(f->fs.mask.lport);
	fwr->fp = htons(f->fs.val.fport);
	fwr->fpm = htons(f->fs.mask.fport);
	if (f->fs.newsmac)
		memcpy(fwr->sma, f->fs.smac, sizeof(fwr->sma));

	/* Mark the filter as "pending" and ship off the Filter Work Request.
	 * When we get the Work Request Reply we'll clear the pending status.
	 */
	f->pending = 1;
	set_wr_txq(skb, CPL_PRIORITY_CONTROL, f->fs.val.iport & 0x3);
	t4_ofld_send(adapter, skb);
	return 0;
}

/* Delete the filter at a specified index.
 */
static int del_filter_wr(struct adapter *adapter, int fidx)
{
	struct filter_entry *f = &adapter->tids.ftid_tab[fidx];
	struct sk_buff *skb;
	struct fw_filter_wr *fwr;
	unsigned int len, ftid;

	len = sizeof(*fwr);
	ftid = adapter->tids.ftid_base + fidx;

	skb = alloc_skb(len, GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	fwr = (struct fw_filter_wr *)__skb_put(skb, len);
	t4_mk_filtdelwr(ftid, fwr, adapter->sge.fw_evtq.abs_id);

	/* Mark the filter as "pending" and ship off the Filter Work Request.
	 * When we get the Work Request Reply we'll clear the pending status.
	 */
	f->pending = 1;
	t4_mgmt_tx(adapter, skb);
	return 0;
}

static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
			     void *accel_priv, select_queue_fallback_t fallback)
{
	int txq;

#ifdef CONFIG_CHELSIO_T4_DCB
	/* If a Data Center Bridging has been successfully negotiated on this
	 * link then we'll use the skb's priority to map it to a TX Queue.
	 * The skb's priority is determined via the VLAN Tag Priority Code
	 * Point field.
	 */
	if (cxgb4_dcb_enabled(dev)) {
		u16 vlan_tci;
		int err;

		err = vlan_get_tag(skb, &vlan_tci);
		if (unlikely(err)) {
			if (net_ratelimit())
				netdev_warn(dev,
					    "TX Packet without VLAN Tag on DCB Link\n");
			txq = 0;
		} else {
			txq = (vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
#ifdef CONFIG_CHELSIO_T4_FCOE
			if (skb->protocol == htons(ETH_P_FCOE))
				txq = skb->priority & 0x7;
#endif /* CONFIG_CHELSIO_T4_FCOE */
		}
		return txq;
	}
#endif /* CONFIG_CHELSIO_T4_DCB */

	if (select_queue) {
		txq = (skb_rx_queue_recorded(skb)
			? skb_get_rx_queue(skb)
			: smp_processor_id());

		while (unlikely(txq >= dev->real_num_tx_queues))
			txq -= dev->real_num_tx_queues;

		return txq;
	}

	return fallback(dev, skb) % dev->real_num_tx_queues;
}

static int closest_timer(const struct sge *s, int time)
{
	int i, delta, match = 0, min_delta = INT_MAX;

	for (i = 0; i < ARRAY_SIZE(s->timer_val); i++) {
		delta = time - s->timer_val[i];
		if (delta < 0)
			delta = -delta;
		if (delta < min_delta) {
			min_delta = delta;
			match = i;
		}
	}
	return match;
}

static int closest_thres(const struct sge *s, int thres)
{
	int i, delta, match = 0, min_delta = INT_MAX;

	for (i = 0; i < ARRAY_SIZE(s->counter_val); i++) {
		delta = thres - s->counter_val[i];
		if (delta < 0)
			delta = -delta;
		if (delta < min_delta) {
			min_delta = delta;
			match = i;
		}
	}
	return match;
}

/**
 *	cxgb4_set_rspq_intr_params - set a queue's interrupt holdoff parameters
 *	@q: the Rx queue
 *	@us: the hold-off time in us, or 0 to disable timer
 *	@cnt: the hold-off packet count, or 0 to disable counter
 *
 *	Sets an Rx queue's interrupt hold-off time and packet count.  At least
 *	one of the two needs to be enabled for the queue to generate interrupts.
 */
int cxgb4_set_rspq_intr_params(struct sge_rspq *q,
			       unsigned int us, unsigned int cnt)
{
	struct adapter *adap = q->adap;

	if ((us | cnt) == 0)
		cnt = 1;

	if (cnt) {
		int err;
		u32 v, new_idx;

		new_idx = closest_thres(&adap->sge, cnt);
		if (q->desc && q->pktcnt_idx != new_idx) {
			/* the queue has already been created, update it */
			v = FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DMAQ) |
			    FW_PARAMS_PARAM_X_V(
					FW_PARAMS_PARAM_DMAQ_IQ_INTCNTTHRESH) |
			    FW_PARAMS_PARAM_YZ_V(q->cntxt_id);
			err = t4_set_params(adap, adap->mbox, adap->pf, 0, 1,
					    &v, &new_idx);
			if (err)
				return err;
		}
		q->pktcnt_idx = new_idx;
	}

	us = us == 0 ? 6 : closest_timer(&adap->sge, us);
	q->intr_params = QINTR_TIMER_IDX_V(us) | QINTR_CNT_EN_V(cnt > 0);
	return 0;
}

static int cxgb_set_features(struct net_device *dev, netdev_features_t features)
{
	const struct port_info *pi = netdev_priv(dev);
	netdev_features_t changed = dev->features ^ features;
	int err;

	if (!(changed & NETIF_F_HW_VLAN_CTAG_RX))
		return 0;

	err = t4_set_rxmode(pi->adapter, pi->adapter->pf, pi->viid, -1,
			    -1, -1, -1,
			    !!(features & NETIF_F_HW_VLAN_CTAG_RX), true);
	if (unlikely(err))
		dev->features = features ^ NETIF_F_HW_VLAN_CTAG_RX;
	return err;
}

static int setup_debugfs(struct adapter *adap)
{
	if (IS_ERR_OR_NULL(adap->debugfs_root))
		return -1;

#ifdef CONFIG_DEBUG_FS
	t4_setup_debugfs(adap);
#endif
	return 0;
}

/*
 * upper-layer driver support
 */

/*
 * Allocate an active-open TID and set it to the supplied value.
 */
int cxgb4_alloc_atid(struct tid_info *t, void *data)
{
	int atid = -1;

	spin_lock_bh(&t->atid_lock);
	if (t->afree) {
		union aopen_entry *p = t->afree;

		atid = (p - t->atid_tab) + t->atid_base;
		t->afree = p->next;
		p->data = data;
		t->atids_in_use++;
	}
	spin_unlock_bh(&t->atid_lock);
	return atid;
}
EXPORT_SYMBOL(cxgb4_alloc_atid);

/*
 * Release an active-open TID.
 */
void cxgb4_free_atid(struct tid_info *t, unsigned int atid)
{
	union aopen_entry *p = &t->atid_tab[atid - t->atid_base];

	spin_lock_bh(&t->atid_lock);
	p->next = t->afree;
	t->afree = p;
	t->atids_in_use--;
	spin_unlock_bh(&t->atid_lock);
}
EXPORT_SYMBOL(cxgb4_free_atid);

/*
 * Allocate a server TID and set it to the supplied value.
 */
int cxgb4_alloc_stid(struct tid_info *t, int family, void *data)
{
	int stid;

	spin_lock_bh(&t->stid_lock);
	if (family == PF_INET) {
		stid = find_first_zero_bit(t->stid_bmap, t->nstids);
		if (stid < t->nstids)
			__set_bit(stid, t->stid_bmap);
		else
			stid = -1;
	} else {
		stid = bitmap_find_free_region(t->stid_bmap, t->nstids, 2);
		if (stid < 0)
			stid = -1;
	}
	if (stid >= 0) {
		t->stid_tab[stid].data = data;
		stid += t->stid_base;
		/* IPv6 requires max of 520 bits or 16 cells in TCAM
		 * This is equivalent to 4 TIDs. With CLIP enabled it
		 * needs 2 TIDs.
		 */
		if (family == PF_INET)
			t->stids_in_use++;
		else
			t->stids_in_use += 4;
	}
	spin_unlock_bh(&t->stid_lock);
	return stid;
}
EXPORT_SYMBOL(cxgb4_alloc_stid);

/* Allocate a server filter TID and set it to the supplied value.
 */
int cxgb4_alloc_sftid(struct tid_info *t, int family, void *data)
{
	int stid;

	spin_lock_bh(&t->stid_lock);
	if (family == PF_INET) {
		stid = find_next_zero_bit(t->stid_bmap,
				t->nstids + t->nsftids, t->nstids);
		if (stid < (t->nstids + t->nsftids))
			__set_bit(stid, t->stid_bmap);
		else
			stid = -1;
	} else {
		stid = -1;
	}
	if (stid >= 0) {
		t->stid_tab[stid].data = data;
		stid -= t->nstids;
		stid += t->sftid_base;
		t->sftids_in_use++;
	}
	spin_unlock_bh(&t->stid_lock);
	return stid;
}
EXPORT_SYMBOL(cxgb4_alloc_sftid);

/* Release a server TID.
 */
void cxgb4_free_stid(struct tid_info *t, unsigned int stid, int family)
{
	/* Is it a server filter TID? */
	if (t->nsftids && (stid >= t->sftid_base)) {
		stid -= t->sftid_base;
		stid += t->nstids;
	} else {
		stid -= t->stid_base;
	}

	spin_lock_bh(&t->stid_lock);
	if (family == PF_INET)
		__clear_bit(stid, t->stid_bmap);
	else
		bitmap_release_region(t->stid_bmap, stid, 2);
	t->stid_tab[stid].data = NULL;
	if (stid < t->nstids) {
		if (family == PF_INET)
			t->stids_in_use--;
		else
			t->stids_in_use -= 4;
	} else {
		t->sftids_in_use--;
	}
	spin_unlock_bh(&t->stid_lock);
}
EXPORT_SYMBOL(cxgb4_free_stid);

/*
 * Populate a TID_RELEASE WR.  Caller must properly size the skb.
 */
static void mk_tid_release(struct sk_buff *skb, unsigned int chan,
			   unsigned int tid)
{
	struct cpl_tid_release *req;

	set_wr_txq(skb, CPL_PRIORITY_SETUP, chan);
	req = (struct cpl_tid_release *)__skb_put(skb, sizeof(*req));
	INIT_TP_WR(req, tid);
	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_TID_RELEASE, tid));
}

/*
 * Queue a TID release request and if necessary schedule a work queue to
 * process it.
 */
static void cxgb4_queue_tid_release(struct tid_info *t, unsigned int chan,
				    unsigned int tid)
{
	void **p = &t->tid_tab[tid];
	struct adapter *adap = container_of(t, struct adapter, tids);

	spin_lock_bh(&adap->tid_release_lock);
	*p = adap->tid_release_head;
	/* Low 2 bits encode the Tx channel number */
	adap->tid_release_head = (void **)((uintptr_t)p | chan);
	if (!adap->tid_release_task_busy) {
		adap->tid_release_task_busy = true;
		queue_work(adap->workq, &adap->tid_release_task);
	}
	spin_unlock_bh(&adap->tid_release_lock);
}

/*
 * Process the list of pending TID release requests.
 */
static void process_tid_release_list(struct work_struct *work)
{
	struct sk_buff *skb;
	struct adapter *adap;

	adap = container_of(work, struct adapter, tid_release_task);

	spin_lock_bh(&adap->tid_release_lock);
	while (adap->tid_release_head) {
		void **p = adap->tid_release_head;
		unsigned int chan = (uintptr_t)p & 3;
		p = (void *)p - chan;

		adap->tid_release_head = *p;
		*p = NULL;
		spin_unlock_bh(&adap->tid_release_lock);

		while (!(skb = alloc_skb(sizeof(struct cpl_tid_release),
					 GFP_KERNEL)))
			schedule_timeout_uninterruptible(1);

		mk_tid_release(skb, chan, p - adap->tids.tid_tab);
		t4_ofld_send(adap, skb);
		spin_lock_bh(&adap->tid_release_lock);
	}
	adap->tid_release_task_busy = false;
	spin_unlock_bh(&adap->tid_release_lock);
}

/*
 * Release a TID and inform HW.  If we are unable to allocate the release
 * message we defer to a work queue.
 */
void cxgb4_remove_tid(struct tid_info *t, unsigned int chan, unsigned int tid)
{
	struct sk_buff *skb;
	struct adapter *adap = container_of(t, struct adapter, tids);

	WARN_ON(tid >= t->ntids);

	if (t->tid_tab[tid]) {
		t->tid_tab[tid] = NULL;
		if (t->hash_base && (tid >= t->hash_base))
			atomic_dec(&t->hash_tids_in_use);
		else
			atomic_dec(&t->tids_in_use);
	}

	skb = alloc_skb(sizeof(struct cpl_tid_release), GFP_ATOMIC);
	if (likely(skb)) {
		mk_tid_release(skb, chan, tid);
		t4_ofld_send(adap, skb);
	} else
		cxgb4_queue_tid_release(t, chan, tid);
}
EXPORT_SYMBOL(cxgb4_remove_tid);

/*
 * Allocate and initialize the TID tables.  Returns 0 on success.
 */
static int tid_init(struct tid_info *t)
{
	size_t size;
	unsigned int stid_bmap_size;
	unsigned int natids = t->natids;
	struct adapter *adap = container_of(t, struct adapter, tids);

	stid_bmap_size = BITS_TO_LONGS(t->nstids + t->nsftids);
	size = t->ntids * sizeof(*t->tid_tab) +
	       natids * sizeof(*t->atid_tab) +
	       t->nstids * sizeof(*t->stid_tab) +
	       t->nsftids * sizeof(*t->stid_tab) +
	       stid_bmap_size * sizeof(long) +
	       t->nftids * sizeof(*t->ftid_tab) +
	       t->nsftids * sizeof(*t->ftid_tab);

	t->tid_tab = t4_alloc_mem(size);
	if (!t->tid_tab)
		return -ENOMEM;

	t->atid_tab = (union aopen_entry *)&t->tid_tab[t->ntids];
	t->stid_tab = (struct serv_entry *)&t->atid_tab[natids];
	t->stid_bmap = (unsigned long *)&t->stid_tab[t->nstids + t->nsftids];
	t->ftid_tab = (struct filter_entry *)&t->stid_bmap[stid_bmap_size];
	spin_lock_init(&t->stid_lock);
	spin_lock_init(&t->atid_lock);

	t->stids_in_use = 0;
	t->sftids_in_use = 0;
	t->afree = NULL;
	t->atids_in_use = 0;
	atomic_set(&t->tids_in_use, 0);
	atomic_set(&t->hash_tids_in_use, 0);

	/* Setup the free list for atid_tab and clear the stid bitmap. */
	if (natids) {
		while (--natids)
			t->atid_tab[natids - 1].next = &t->atid_tab[natids];
		t->afree = t->atid_tab;
	}
	bitmap_zero(t->stid_bmap, t->nstids + t->nsftids);
	/* Reserve stid 0 for T4/T5 adapters */
	if (!t->stid_base &&
	    (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5))
		__set_bit(0, t->stid_bmap);

	return 0;
}

/**
 *	cxgb4_create_server - create an IP server
 *	@dev: the device
 *	@stid: the server TID
 *	@sip: local IP address to bind server to
 *	@sport: the server's TCP port
 *	@queue: queue to direct messages from this server to
 *
 *	Create an IP server for the given port and address.
 *	Returns <0 on error and one of the %NET_XMIT_* values on success.
 */
int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
			__be32 sip, __be16 sport, __be16 vlan,
			unsigned int queue)
{
	unsigned int chan;
	struct sk_buff *skb;
	struct adapter *adap;
	struct cpl_pass_open_req *req;
	int ret;

	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	adap = netdev2adap(dev);
	req = (struct cpl_pass_open_req *)__skb_put(skb, sizeof(*req));
	INIT_TP_WR(req, 0);
	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_PASS_OPEN_REQ, stid));
	req->local_port = sport;
	req->peer_port = htons(0);
	req->local_ip = sip;
	req->peer_ip = htonl(0);
	chan = rxq_to_chan(&adap->sge, queue);
	req->opt0 = cpu_to_be64(TX_CHAN_V(chan));
	req->opt1 = cpu_to_be64(CONN_POLICY_V(CPL_CONN_POLICY_ASK) |
				SYN_RSS_ENABLE_F | SYN_RSS_QUEUE_V(queue));
	ret = t4_mgmt_tx(adap, skb);
	return net_xmit_eval(ret);
}
EXPORT_SYMBOL(cxgb4_create_server);

/*	cxgb4_create_server6 - create an IPv6 server
 *	@dev: the device
 *	@stid: the server TID
 *	@sip: local IPv6 address to bind server to
 *	@sport: the server's TCP port
 *	@queue: queue to direct messages from this server to
 *
 *	Create an IPv6 server for the given port and address.
 *	Returns <0 on error and one of the %NET_XMIT_* values on success.
 */
int cxgb4_create_server6(const struct net_device *dev, unsigned int stid,
			 const struct in6_addr *sip, __be16 sport,
			 unsigned int queue)
{
	unsigned int chan;
	struct sk_buff *skb;
	struct adapter *adap;
	struct cpl_pass_open_req6 *req;
	int ret;

	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	adap = netdev2adap(dev);
	req = (struct cpl_pass_open_req6 *)__skb_put(skb, sizeof(*req));
	INIT_TP_WR(req, 0);
	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_PASS_OPEN_REQ6, stid));
	req->local_port = sport;
	req->peer_port = htons(0);
	req->local_ip_hi = *(__be64 *)(sip->s6_addr);
	req->local_ip_lo = *(__be64 *)(sip->s6_addr + 8);
	req->peer_ip_hi = cpu_to_be64(0);
	req->peer_ip_lo = cpu_to_be64(0);
	chan = rxq_to_chan(&adap->sge, queue);
	req->opt0 = cpu_to_be64(TX_CHAN_V(chan));
	req->opt1 = cpu_to_be64(CONN_POLICY_V(CPL_CONN_POLICY_ASK) |
				SYN_RSS_ENABLE_F | SYN_RSS_QUEUE_V(queue));
	ret = t4_mgmt_tx(adap, skb);
	return net_xmit_eval(ret);
}
EXPORT_SYMBOL(cxgb4_create_server6);

int cxgb4_remove_server(const struct net_device *dev, unsigned int stid,
			unsigned int queue, bool ipv6)
{
	struct sk_buff *skb;
	struct adapter *adap;
	struct cpl_close_listsvr_req *req;
	int ret;

	adap = netdev2adap(dev);

	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	req = (struct cpl_close_listsvr_req *)__skb_put(skb, sizeof(*req));
	INIT_TP_WR(req, 0);
	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_CLOSE_LISTSRV_REQ, stid));
	req->reply_ctrl = htons(NO_REPLY_V(0) | (ipv6 ? LISTSVR_IPV6_V(1) :
				LISTSVR_IPV6_V(0)) | QUEUENO_V(queue));
	ret = t4_mgmt_tx(adap, skb);
	return net_xmit_eval(ret);
}
EXPORT_SYMBOL(cxgb4_remove_server);

/**
 *	cxgb4_best_mtu - find the entry in the MTU table closest to an MTU
 *	@mtus: the HW MTU table
 *	@mtu: the target MTU
 *	@idx: index of selected entry in the MTU table
 *
 *	Returns the index and the value in the HW MTU table that is closest to
 *	but does not exceed @mtu, unless @mtu is smaller than any value in the
 *	table, in which case that smallest available value is selected.
 */
unsigned int cxgb4_best_mtu(const unsigned short *mtus, unsigned short mtu,
			    unsigned int *idx)
{
	unsigned int i = 0;

	while (i < NMTUS - 1 && mtus[i + 1] <= mtu)
		++i;
	if (idx)
		*idx = i;
	return mtus[i];
}
EXPORT_SYMBOL(cxgb4_best_mtu);

/**
 *     cxgb4_best_aligned_mtu - find best MTU, [hopefully] data size aligned
 *     @mtus: the HW MTU table
 *     @header_size: Header Size
 *     @data_size_max: maximum Data Segment Size
 *     @data_size_align: desired Data Segment Size Alignment (2^N)
 *     @mtu_idxp: HW MTU Table Index return value pointer (possibly NULL)
 *
 *     Similar to cxgb4_best_mtu() but instead of searching the Hardware
 *     MTU Table based solely on a Maximum MTU parameter, we break that
 *     parameter up into a Header Size and Maximum Data Segment Size, and
 *     provide a desired Data Segment Size Alignment.  If we find an MTU in
 *     the Hardware MTU Table which will result in a Data Segment Size with
 *     the requested alignment _and_ that MTU isn't "too far" from the
 *     closest MTU, then we'll return that rather than the closest MTU.
 */
unsigned int cxgb4_best_aligned_mtu(const unsigned short *mtus,
				    unsigned short header_size,
				    unsigned short data_size_max,
				    unsigned short data_size_align,
				    unsigned int *mtu_idxp)
{
	unsigned short max_mtu = header_size + data_size_max;
	unsigned short data_size_align_mask = data_size_align - 1;
	int mtu_idx, aligned_mtu_idx;

	/* Scan the MTU Table till we find an MTU which is larger than our
	 * Maximum MTU or we reach the end of the table.  Along the way,
	 * record the last MTU found, if any, which will result in a Data
	 * Segment Length matching the requested alignment.
	 */
	for (mtu_idx = 0, aligned_mtu_idx = -1; mtu_idx < NMTUS; mtu_idx++) {
		unsigned short data_size = mtus[mtu_idx] - header_size;

		/* If this MTU minus the Header Size would result in a
		 * Data Segment Size of the desired alignment, remember it.
		 */
		if ((data_size & data_size_align_mask) == 0)
			aligned_mtu_idx = mtu_idx;

		/* If we're not at the end of the Hardware MTU Table and the
		 * next element is larger than our Maximum MTU, drop out of
		 * the loop.
		 */
		if (mtu_idx+1 < NMTUS && mtus[mtu_idx+1] > max_mtu)
			break;
	}

	/* If we fell out of the loop because we ran to the end of the table,
	 * then we just have to use the last [largest] entry.
	 */
	if (mtu_idx == NMTUS)
		mtu_idx--;

	/* If we found an MTU which resulted in the requested Data Segment
	 * Length alignment and that's "not far" from the largest MTU which is
	 * less than or equal to the maximum MTU, then use that.
	 */
	if (aligned_mtu_idx >= 0 &&
	    mtu_idx - aligned_mtu_idx <= 1)
		mtu_idx = aligned_mtu_idx;

	/* If the caller has passed in an MTU Index pointer, pass the
	 * MTU Index back.  Return the MTU value.
	 */
	if (mtu_idxp)
		*mtu_idxp = mtu_idx;
	return mtus[mtu_idx];
}
EXPORT_SYMBOL(cxgb4_best_aligned_mtu);

/**
 *	cxgb4_tp_smt_idx - Get the Source Mac Table index for this VI
 *	@chip: chip type
 *	@viid: VI id of the given port
 *
 *	Return the SMT index for this VI.
 */
unsigned int cxgb4_tp_smt_idx(enum chip_type chip, unsigned int viid)
{
	/* In T4/T5, SMT contains 256 SMAC entries organized in
	 * 128 rows of 2 entries each.
	 * In T6, SMT contains 256 SMAC entries in 256 rows.
	 * TODO: The below code needs to be updated when we add support
	 * for 256 VFs.
	 */
	if (CHELSIO_CHIP_VERSION(chip) <= CHELSIO_T5)
		return ((viid & 0x7f) << 1);
	else
		return (viid & 0x7f);
}
EXPORT_SYMBOL(cxgb4_tp_smt_idx);

/**
 *	cxgb4_port_chan - get the HW channel of a port
 *	@dev: the net device for the port
 *
 *	Return the HW Tx channel of the given port.
 */
unsigned int cxgb4_port_chan(const struct net_device *dev)
{
	return netdev2pinfo(dev)->tx_chan;
}
EXPORT_SYMBOL(cxgb4_port_chan);

unsigned int cxgb4_dbfifo_count(const struct net_device *dev, int lpfifo)
{
	struct adapter *adap = netdev2adap(dev);
	u32 v1, v2, lp_count, hp_count;

	v1 = t4_read_reg(adap, SGE_DBFIFO_STATUS_A);
	v2 = t4_read_reg(adap, SGE_DBFIFO_STATUS2_A);
	if (is_t4(adap->params.chip)) {
		lp_count = LP_COUNT_G(v1);
		hp_count = HP_COUNT_G(v1);
	} else {
		lp_count = LP_COUNT_T5_G(v1);
		hp_count = HP_COUNT_T5_G(v2);
	}
	return lpfifo ? lp_count : hp_count;
}
EXPORT_SYMBOL(cxgb4_dbfifo_count);

/**
 *	cxgb4_port_viid - get the VI id of a port
 *	@dev: the net device for the port
 *
 *	Return the VI id of the given port.
 */
unsigned int cxgb4_port_viid(const struct net_device *dev)
{
	return netdev2pinfo(dev)->viid;
}
EXPORT_SYMBOL(cxgb4_port_viid);

/**
 *	cxgb4_port_idx - get the index of a port
 *	@dev: the net device for the port
 *
 *	Return the index of the given port.
 */
unsigned int cxgb4_port_idx(const struct net_device *dev)
{
	return netdev2pinfo(dev)->port_id;
}
EXPORT_SYMBOL(cxgb4_port_idx);

void cxgb4_get_tcp_stats(struct pci_dev *pdev, struct tp_tcp_stats *v4,
			 struct tp_tcp_stats *v6)
{
	struct adapter *adap = pci_get_drvdata(pdev);

	spin_lock(&adap->stats_lock);
	t4_tp_get_tcp_stats(adap, v4, v6);
	spin_unlock(&adap->stats_lock);
}
EXPORT_SYMBOL(cxgb4_get_tcp_stats);

void cxgb4_iscsi_init(struct net_device *dev, unsigned int tag_mask,
		      const unsigned int *pgsz_order)
{
	struct adapter *adap = netdev2adap(dev);

	t4_write_reg(adap, ULP_RX_ISCSI_TAGMASK_A, tag_mask);
	t4_write_reg(adap, ULP_RX_ISCSI_PSZ_A, HPZ0_V(pgsz_order[0]) |
		     HPZ1_V(pgsz_order[1]) | HPZ2_V(pgsz_order[2]) |
		     HPZ3_V(pgsz_order[3]));
}
EXPORT_SYMBOL(cxgb4_iscsi_init);

int cxgb4_flush_eq_cache(struct net_device *dev)
{
	struct adapter *adap = netdev2adap(dev);

	return t4_sge_ctxt_flush(adap, adap->mbox);
}
EXPORT_SYMBOL(cxgb4_flush_eq_cache);

static int read_eq_indices(struct adapter *adap, u16 qid, u16 *pidx, u16 *cidx)
{
	u32 addr = t4_read_reg(adap, SGE_DBQ_CTXT_BADDR_A) + 24 * qid + 8;
	__be64 indices;
	int ret;

	spin_lock(&adap->win0_lock);
	ret = t4_memory_rw(adap, 0, MEM_EDC0, addr,
			   sizeof(indices), (__be32 *)&indices,
			   T4_MEMORY_READ);
	spin_unlock(&adap->win0_lock);
	if (!ret) {
		*cidx = (be64_to_cpu(indices) >> 25) & 0xffff;
		*pidx = (be64_to_cpu(indices) >> 9) & 0xffff;
	}
	return ret;
}

int cxgb4_sync_txq_pidx(struct net_device *dev, u16 qid, u16 pidx,
			u16 size)
{
	struct adapter *adap = netdev2adap(dev);
	u16 hw_pidx, hw_cidx;
	int ret;

	ret = read_eq_indices(adap, qid, &hw_pidx, &hw_cidx);
	if (ret)
		goto out;

	if (pidx != hw_pidx) {
		u16 delta;
		u32 val;

		if (pidx >= hw_pidx)
			delta = pidx - hw_pidx;
		else
			delta = size - hw_pidx + pidx;

		if (is_t4(adap->params.chip))
			val = PIDX_V(delta);
		else
			val = PIDX_T5_V(delta);
		wmb();
		t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL_A),
			     QID_V(qid) | val);
	}
out:
	return ret;
}
EXPORT_SYMBOL(cxgb4_sync_txq_pidx);

int cxgb4_read_tpte(struct net_device *dev, u32 stag, __be32 *tpte)
{
	struct adapter *adap;
	u32 offset, memtype, memaddr;
	u32 edc0_size, edc1_size, mc0_size, mc1_size, size;
	u32 edc0_end, edc1_end, mc0_end, mc1_end;
	int ret;

	adap = netdev2adap(dev);

	offset = ((stag >> 8) * 32) + adap->vres.stag.start;

	/* Figure out where the offset lands in the Memory Type/Address scheme.
	 * This code assumes that the memory is laid out starting at offset 0
	 * with no breaks as: EDC0, EDC1, MC0, MC1. All cards have both EDC0
	 * and EDC1.  Some cards will have neither MC0 nor MC1, most cards have
	 * MC0, and some have both MC0 and MC1.
	 */
	size = t4_read_reg(adap, MA_EDRAM0_BAR_A);
	edc0_size = EDRAM0_SIZE_G(size) << 20;
	size = t4_read_reg(adap, MA_EDRAM1_BAR_A);
	edc1_size = EDRAM1_SIZE_G(size) << 20;
	size = t4_read_reg(adap, MA_EXT_MEMORY0_BAR_A);
	mc0_size = EXT_MEM0_SIZE_G(size) << 20;

	edc0_end = edc0_size;
	edc1_end = edc0_end + edc1_size;
	mc0_end = edc1_end + mc0_size;

	if (offset < edc0_end) {
		memtype = MEM_EDC0;
		memaddr = offset;
	} else if (offset < edc1_end) {
		memtype = MEM_EDC1;
		memaddr = offset - edc0_end;
	} else {
		if (offset < mc0_end) {
			memtype = MEM_MC0;
			memaddr = offset - edc1_end;
		} else if (is_t5(adap->params.chip)) {
			size = t4_read_reg(adap, MA_EXT_MEMORY1_BAR_A);
			mc1_size = EXT_MEM1_SIZE_G(size) << 20;
			mc1_end = mc0_end + mc1_size;
			if (offset < mc1_end) {
				memtype = MEM_MC1;
				memaddr = offset - mc0_end;
			} else {
				/* offset beyond the end of any memory */
				goto err;
			}
		} else {
			/* T4/T6 only has a single memory channel */
			goto err;
		}
	}

	spin_lock(&adap->win0_lock);
	ret = t4_memory_rw(adap, 0, memtype, memaddr, 32, tpte, T4_MEMORY_READ);
	spin_unlock(&adap->win0_lock);
	return ret;

err:
	dev_err(adap->pdev_dev, "stag %#x, offset %#x out of range\n",
		stag, offset);
	return -EINVAL;
}
EXPORT_SYMBOL(cxgb4_read_tpte);

u64 cxgb4_read_sge_timestamp(struct net_device *dev)
{
	u32 hi, lo;
	struct adapter *adap;

	adap = netdev2adap(dev);
	lo = t4_read_reg(adap, SGE_TIMESTAMP_LO_A);
	hi = TSVAL_G(t4_read_reg(adap, SGE_TIMESTAMP_HI_A));

	return ((u64)hi << 32) | (u64)lo;
}
EXPORT_SYMBOL(cxgb4_read_sge_timestamp);

int cxgb4_bar2_sge_qregs(struct net_device *dev,
			 unsigned int qid,
			 enum cxgb4_bar2_qtype qtype,
			 int user,
			 u64 *pbar2_qoffset,
			 unsigned int *pbar2_qid)
{
	return t4_bar2_sge_qregs(netdev2adap(dev),
				 qid,
				 (qtype == CXGB4_BAR2_QTYPE_EGRESS
				  ? T4_BAR2_QTYPE_EGRESS
				  : T4_BAR2_QTYPE_INGRESS),
				 user,
				 pbar2_qoffset,
				 pbar2_qid);
}
EXPORT_SYMBOL(cxgb4_bar2_sge_qregs);

static struct pci_driver cxgb4_driver;

static void check_neigh_update(struct neighbour *neigh)
{
	const struct device *parent;
	const struct net_device *netdev = neigh->dev;

	if (netdev->priv_flags & IFF_802_1Q_VLAN)
		netdev = vlan_dev_real_dev(netdev);
	parent = netdev->dev.parent;
	if (parent && parent->driver == &cxgb4_driver.driver)
		t4_l2t_update(dev_get_drvdata(parent), neigh);
}

static int netevent_cb(struct notifier_block *nb, unsigned long event,
		       void *data)
{
	switch (event) {
	case NETEVENT_NEIGH_UPDATE:
		check_neigh_update(data);
		break;
	case NETEVENT_REDIRECT:
	default:
		break;
	}
	return 0;
}

static bool netevent_registered;
static struct notifier_block cxgb4_netevent_nb = {
	.notifier_call = netevent_cb
};

static void drain_db_fifo(struct adapter *adap, int usecs)
{
	u32 v1, v2, lp_count, hp_count;

	do {
		v1 = t4_read_reg(adap, SGE_DBFIFO_STATUS_A);
		v2 = t4_read_reg(adap, SGE_DBFIFO_STATUS2_A);
		if (is_t4(adap->params.chip)) {
			lp_count = LP_COUNT_G(v1);
			hp_count = HP_COUNT_G(v1);
		} else {
			lp_count = LP_COUNT_T5_G(v1);
			hp_count = HP_COUNT_T5_G(v2);
		}

		if (lp_count == 0 && hp_count == 0)
			break;
		set_current_state(TASK_UNINTERRUPTIBLE);
		schedule_timeout(usecs_to_jiffies(usecs));
	} while (1);
}

static void disable_txq_db(struct sge_txq *q)
{
	unsigned long flags;

	spin_lock_irqsave(&q->db_lock, flags);
	q->db_disabled = 1;
	spin_unlock_irqrestore(&q->db_lock, flags);
}

static void enable_txq_db(struct adapter *adap, struct sge_txq *q)
{
	spin_lock_irq(&q->db_lock);
	if (q->db_pidx_inc) {
		/* Make sure that all writes to the TX descriptors
		 * are committed before we tell HW about them.
		 */
		wmb();
		t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL_A),
			     QID_V(q->cntxt_id) | PIDX_V(q->db_pidx_inc));
		q->db_pidx_inc = 0;
	}
	q->db_disabled = 0;
	spin_unlock_irq(&q->db_lock);
}

static void disable_dbs(struct adapter *adap)
{
	int i;

	for_each_ethrxq(&adap->sge, i)
		disable_txq_db(&adap->sge.ethtxq[i].q);
	for_each_ofldrxq(&adap->sge, i)
		disable_txq_db(&adap->sge.ofldtxq[i].q);
	for_each_port(adap, i)
		disable_txq_db(&adap->sge.ctrlq[i].q);
}

static void enable_dbs(struct adapter *adap)
{
	int i;

	for_each_ethrxq(&adap->sge, i)
		enable_txq_db(adap, &adap->sge.ethtxq[i].q);
	for_each_ofldrxq(&adap->sge, i)
		enable_txq_db(adap, &adap->sge.ofldtxq[i].q);
	for_each_port(adap, i)
		enable_txq_db(adap, &adap->sge.ctrlq[i].q);
}

static void notify_rdma_uld(struct adapter *adap, enum cxgb4_control cmd)
{
	if (adap->uld_handle[CXGB4_ULD_RDMA])
		ulds[CXGB4_ULD_RDMA].control(adap->uld_handle[CXGB4_ULD_RDMA],
				cmd);
}

static void process_db_full(struct work_struct *work)
{
	struct adapter *adap;

	adap = container_of(work, struct adapter, db_full_task);

	drain_db_fifo(adap, dbfifo_drain_delay);
	enable_dbs(adap);
	notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY);
	if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5)
		t4_set_reg_field(adap, SGE_INT_ENABLE3_A,
				 DBFIFO_HP_INT_F | DBFIFO_LP_INT_F,
				 DBFIFO_HP_INT_F | DBFIFO_LP_INT_F);
	else
		t4_set_reg_field(adap, SGE_INT_ENABLE3_A,
				 DBFIFO_LP_INT_F, DBFIFO_LP_INT_F);
}

static void sync_txq_pidx(struct adapter *adap, struct sge_txq *q)
{
	u16 hw_pidx, hw_cidx;
	int ret;

	spin_lock_irq(&q->db_lock);
	ret = read_eq_indices(adap, (u16)q->cntxt_id, &hw_pidx, &hw_cidx);
	if (ret)
		goto out;
	if (q->db_pidx != hw_pidx) {
		u16 delta;
		u32 val;

		if (q->db_pidx >= hw_pidx)
			delta = q->db_pidx - hw_pidx;
		else
			delta = q->size - hw_pidx + q->db_pidx;

		if (is_t4(adap->params.chip))
			val = PIDX_V(delta);
		else
			val = PIDX_T5_V(delta);
		wmb();
		t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL_A),
			     QID_V(q->cntxt_id) | val);
	}
out:
	q->db_disabled = 0;
	q->db_pidx_inc = 0;
	spin_unlock_irq(&q->db_lock);
	if (ret)
		CH_WARN(adap, "DB drop recovery failed.\n");
}
static void recover_all_queues(struct adapter *adap)
{
	int i;

	for_each_ethrxq(&adap->sge, i)
		sync_txq_pidx(adap, &adap->sge.ethtxq[i].q);
	for_each_ofldrxq(&adap->sge, i)
		sync_txq_pidx(adap, &adap->sge.ofldtxq[i].q);
	for_each_port(adap, i)
		sync_txq_pidx(adap, &adap->sge.ctrlq[i].q);
}

static void process_db_drop(struct work_struct *work)
{
	struct adapter *adap;

	adap = container_of(work, struct adapter, db_drop_task);

	if (is_t4(adap->params.chip)) {
		drain_db_fifo(adap, dbfifo_drain_delay);
		notify_rdma_uld(adap, CXGB4_CONTROL_DB_DROP);
		drain_db_fifo(adap, dbfifo_drain_delay);
		recover_all_queues(adap);
		drain_db_fifo(adap, dbfifo_drain_delay);
		enable_dbs(adap);
		notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY);
	} else if (is_t5(adap->params.chip)) {
		u32 dropped_db = t4_read_reg(adap, 0x010ac);
		u16 qid = (dropped_db >> 15) & 0x1ffff;
		u16 pidx_inc = dropped_db & 0x1fff;
		u64 bar2_qoffset;
		unsigned int bar2_qid;
		int ret;

		ret = t4_bar2_sge_qregs(adap, qid, T4_BAR2_QTYPE_EGRESS,
					0, &bar2_qoffset, &bar2_qid);
		if (ret)
			dev_err(adap->pdev_dev, "doorbell drop recovery: "
				"qid=%d, pidx_inc=%d\n", qid, pidx_inc);
		else
			writel(PIDX_T5_V(pidx_inc) | QID_V(bar2_qid),
			       adap->bar2 + bar2_qoffset + SGE_UDB_KDOORBELL);

		/* Re-enable BAR2 WC */
		t4_set_reg_field(adap, 0x10b0, 1<<15, 1<<15);
	}

	if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5)
		t4_set_reg_field(adap, SGE_DOORBELL_CONTROL_A, DROPPED_DB_F, 0);
}

void t4_db_full(struct adapter *adap)
{
	if (is_t4(adap->params.chip)) {
		disable_dbs(adap);
		notify_rdma_uld(adap, CXGB4_CONTROL_DB_FULL);
		t4_set_reg_field(adap, SGE_INT_ENABLE3_A,
				 DBFIFO_HP_INT_F | DBFIFO_LP_INT_F, 0);
		queue_work(adap->workq, &adap->db_full_task);
	}
}

void t4_db_dropped(struct adapter *adap)
{
	if (is_t4(adap->params.chip)) {
		disable_dbs(adap);
		notify_rdma_uld(adap, CXGB4_CONTROL_DB_FULL);
	}
	queue_work(adap->workq, &adap->db_drop_task);
}

static void uld_attach(struct adapter *adap, unsigned int uld)
{
	void *handle;
	struct cxgb4_lld_info lli;
	unsigned short i;

	lli.pdev = adap->pdev;
	lli.pf = adap->pf;
	lli.l2t = adap->l2t;
	lli.tids = &adap->tids;
	lli.ports = adap->port;
	lli.vr = &adap->vres;
	lli.mtus = adap->params.mtus;
	if (uld == CXGB4_ULD_RDMA) {
		lli.rxq_ids = adap->sge.rdma_rxq;
		lli.ciq_ids = adap->sge.rdma_ciq;
		lli.nrxq = adap->sge.rdmaqs;
		lli.nciq = adap->sge.rdmaciqs;
	} else if (uld == CXGB4_ULD_ISCSI) {
		lli.rxq_ids = adap->sge.ofld_rxq;
		lli.nrxq = adap->sge.ofldqsets;
	}
	lli.ntxq = adap->sge.ofldqsets;
	lli.nchan = adap->params.nports;
	lli.nports = adap->params.nports;
	lli.wr_cred = adap->params.ofldq_wr_cred;
	lli.adapter_type = adap->params.chip;
	lli.iscsi_iolen = MAXRXDATA_G(t4_read_reg(adap, TP_PARA_REG2_A));
	lli.cclk_ps = 1000000000 / adap->params.vpd.cclk;
	lli.udb_density = 1 << adap->params.sge.eq_qpp;
	lli.ucq_density = 1 << adap->params.sge.iq_qpp;
	lli.filt_mode = adap->params.tp.vlan_pri_map;
	/* MODQ_REQ_MAP sets queues 0-3 to chan 0-3 */
	for (i = 0; i < NCHAN; i++)
		lli.tx_modq[i] = i;
	lli.gts_reg = adap->regs + MYPF_REG(SGE_PF_GTS_A);
	lli.db_reg = adap->regs + MYPF_REG(SGE_PF_KDOORBELL_A);
	lli.fw_vers = adap->params.fw_vers;
	lli.dbfifo_int_thresh = dbfifo_int_thresh;
	lli.sge_ingpadboundary = adap->sge.fl_align;
	lli.sge_egrstatuspagesize = adap->sge.stat_len;
	lli.sge_pktshift = adap->sge.pktshift;
	lli.enable_fw_ofld_conn = adap->flags & FW_OFLD_CONN;
	lli.max_ordird_qp = adap->params.max_ordird_qp;
	lli.max_ird_adapter = adap->params.max_ird_adapter;
	lli.ulptx_memwrite_dsgl = adap->params.ulptx_memwrite_dsgl;
	lli.nodeid = dev_to_node(adap->pdev_dev);

	handle = ulds[uld].add(&lli);
	if (IS_ERR(handle)) {
		dev_warn(adap->pdev_dev,
			 "could not attach to the %s driver, error %ld\n",
			 uld_str[uld], PTR_ERR(handle));
		return;
	}

	adap->uld_handle[uld] = handle;

	if (!netevent_registered) {
		register_netevent_notifier(&cxgb4_netevent_nb);
		netevent_registered = true;
	}

	if (adap->flags & FULL_INIT_DONE)
		ulds[uld].state_change(handle, CXGB4_STATE_UP);
}

static void attach_ulds(struct adapter *adap)
{
	unsigned int i;

	spin_lock(&adap_rcu_lock);
	list_add_tail_rcu(&adap->rcu_node, &adap_rcu_list);
	spin_unlock(&adap_rcu_lock);

	mutex_lock(&uld_mutex);
	list_add_tail(&adap->list_node, &adapter_list);
	for (i = 0; i < CXGB4_ULD_MAX; i++)
		if (ulds[i].add)
			uld_attach(adap, i);
	mutex_unlock(&uld_mutex);
}

static void detach_ulds(struct adapter *adap)
{
	unsigned int i;

	mutex_lock(&uld_mutex);
	list_del(&adap->list_node);
	for (i = 0; i < CXGB4_ULD_MAX; i++)
		if (adap->uld_handle[i]) {
			ulds[i].state_change(adap->uld_handle[i],
					     CXGB4_STATE_DETACH);
			adap->uld_handle[i] = NULL;
		}
	if (netevent_registered && list_empty(&adapter_list)) {
		unregister_netevent_notifier(&cxgb4_netevent_nb);
		netevent_registered = false;
	}
	mutex_unlock(&uld_mutex);

	spin_lock(&adap_rcu_lock);
	list_del_rcu(&adap->rcu_node);
	spin_unlock(&adap_rcu_lock);
}

static void notify_ulds(struct adapter *adap, enum cxgb4_state new_state)
{
	unsigned int i;

	mutex_lock(&uld_mutex);
	for (i = 0; i < CXGB4_ULD_MAX; i++)
		if (adap->uld_handle[i])
			ulds[i].state_change(adap->uld_handle[i], new_state);
	mutex_unlock(&uld_mutex);
}

/**
 *	cxgb4_register_uld - register an upper-layer driver
 *	@type: the ULD type
 *	@p: the ULD methods
 *
 *	Registers an upper-layer driver with this driver and notifies the ULD
 *	about any presently available devices that support its type.  Returns
 *	%-EBUSY if a ULD of the same type is already registered.
 */
int cxgb4_register_uld(enum cxgb4_uld type, const struct cxgb4_uld_info *p)
{
	int ret = 0;
	struct adapter *adap;

	if (type >= CXGB4_ULD_MAX)
		return -EINVAL;
	mutex_lock(&uld_mutex);
	if (ulds[type].add) {
		ret = -EBUSY;
		goto out;
	}
	ulds[type] = *p;
	list_for_each_entry(adap, &adapter_list, list_node)
		uld_attach(adap, type);
out:	mutex_unlock(&uld_mutex);
	return ret;
}
EXPORT_SYMBOL(cxgb4_register_uld);

/**
 *	cxgb4_unregister_uld - unregister an upper-layer driver
 *	@type: the ULD type
 *
 *	Unregisters an existing upper-layer driver.
 */
int cxgb4_unregister_uld(enum cxgb4_uld type)
{
	struct adapter *adap;

	if (type >= CXGB4_ULD_MAX)
		return -EINVAL;
	mutex_lock(&uld_mutex);
	list_for_each_entry(adap, &adapter_list, list_node)
		adap->uld_handle[type] = NULL;
	ulds[type].add = NULL;
	mutex_unlock(&uld_mutex);
	return 0;
}
EXPORT_SYMBOL(cxgb4_unregister_uld);

#if IS_ENABLED(CONFIG_IPV6)
static int cxgb4_inet6addr_handler(struct notifier_block *this,
				   unsigned long event, void *data)
{
	struct inet6_ifaddr *ifa = data;
	struct net_device *event_dev = ifa->idev->dev;
	const struct device *parent = NULL;
#if IS_ENABLED(CONFIG_BONDING)
	struct adapter *adap;
#endif
	if (event_dev->priv_flags & IFF_802_1Q_VLAN)
		event_dev = vlan_dev_real_dev(event_dev);
#if IS_ENABLED(CONFIG_BONDING)
	if (event_dev->flags & IFF_MASTER) {
		list_for_each_entry(adap, &adapter_list, list_node) {
			switch (event) {
			case NETDEV_UP:
				cxgb4_clip_get(adap->port[0],
					       (const u32 *)ifa, 1);
				break;
			case NETDEV_DOWN:
				cxgb4_clip_release(adap->port[0],
						   (const u32 *)ifa, 1);
				break;
			default:
				break;
			}
		}
		return NOTIFY_OK;
	}
#endif

	if (event_dev)
		parent = event_dev->dev.parent;

	if (parent && parent->driver == &cxgb4_driver.driver) {
		switch (event) {
		case NETDEV_UP:
			cxgb4_clip_get(event_dev, (const u32 *)ifa, 1);
			break;
		case NETDEV_DOWN:
			cxgb4_clip_release(event_dev, (const u32 *)ifa, 1);
			break;
		default:
			break;
		}
	}
	return NOTIFY_OK;
}

static bool inet6addr_registered;
static struct notifier_block cxgb4_inet6addr_notifier = {
	.notifier_call = cxgb4_inet6addr_handler
};

static void update_clip(const struct adapter *adap)
{
	int i;
	struct net_device *dev;
	int ret;

	rcu_read_lock();

	for (i = 0; i < MAX_NPORTS; i++) {
		dev = adap->port[i];
		ret = 0;

		if (dev)
			ret = cxgb4_update_root_dev_clip(dev);

		if (ret < 0)
			break;
	}
	rcu_read_unlock();
}
#endif /* IS_ENABLED(CONFIG_IPV6) */

/**
 *	cxgb_up - enable the adapter
 *	@adap: adapter being enabled
 *
 *	Called when the first port is enabled, this function performs the
 *	actions necessary to make an adapter operational, such as completing
 *	the initialization of HW modules, and enabling interrupts.
 *
 *	Must be called with the rtnl lock held.
 */
static int cxgb_up(struct adapter *adap)
{
	int err;

	err = setup_sge_queues(adap);
	if (err)
		goto out;
	err = setup_rss(adap);
	if (err)
		goto freeq;

	if (adap->flags & USING_MSIX) {
		name_msix_vecs(adap);
		err = request_irq(adap->msix_info[0].vec, t4_nondata_intr, 0,
				  adap->msix_info[0].desc, adap);
		if (err)
			goto irq_err;

		err = request_msix_queue_irqs(adap);
		if (err) {
			free_irq(adap->msix_info[0].vec, adap);
			goto irq_err;
		}
	} else {
		err = request_irq(adap->pdev->irq, t4_intr_handler(adap),
				  (adap->flags & USING_MSI) ? 0 : IRQF_SHARED,
				  adap->port[0]->name, adap);
		if (err)
			goto irq_err;
	}
	enable_rx(adap);
	t4_sge_start(adap);
	t4_intr_enable(adap);
	adap->flags |= FULL_INIT_DONE;
	notify_ulds(adap, CXGB4_STATE_UP);
#if IS_ENABLED(CONFIG_IPV6)
	update_clip(adap);
#endif
 out:
	return err;
 irq_err:
	dev_err(adap->pdev_dev, "request_irq failed, err %d\n", err);
 freeq:
	t4_free_sge_resources(adap);
	goto out;
}

static void cxgb_down(struct adapter *adapter)
{
	cancel_work_sync(&adapter->tid_release_task);
	cancel_work_sync(&adapter->db_full_task);
	cancel_work_sync(&adapter->db_drop_task);
	adapter->tid_release_task_busy = false;
	adapter->tid_release_head = NULL;

	t4_sge_stop(adapter);
	t4_free_sge_resources(adapter);
	adapter->flags &= ~FULL_INIT_DONE;
}

/*
 * net_device operations
 */
static int cxgb_open(struct net_device *dev)
{
	int err;
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;

	netif_carrier_off(dev);

	if (!(adapter->flags & FULL_INIT_DONE)) {
		err = cxgb_up(adapter);
		if (err < 0)
			return err;
	}

	err = link_start(dev);
	if (!err)
		netif_tx_start_all_queues(dev);
	return err;
}

static int cxgb_close(struct net_device *dev)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adapter = pi->adapter;

	netif_tx_stop_all_queues(dev);
	netif_carrier_off(dev);
	return t4_enable_vi(adapter, adapter->pf, pi->viid, false, false);
}

/* Return an error number if the indicated filter isn't writable ...
 */
static int writable_filter(struct filter_entry *f)
{
	if (f->locked)
		return -EPERM;
	if (f->pending)
		return -EBUSY;

	return 0;
}

/* Delete the filter at the specified index (if valid).  The checks for all
 * the common problems with doing this like the filter being locked, currently
 * pending in another operation, etc.
 */
static int delete_filter(struct adapter *adapter, unsigned int fidx)
{
	struct filter_entry *f;
	int ret;

	if (fidx >= adapter->tids.nftids + adapter->tids.nsftids)
		return -EINVAL;

	f = &adapter->tids.ftid_tab[fidx];
	ret = writable_filter(f);
	if (ret)
		return ret;
	if (f->valid)
		return del_filter_wr(adapter, fidx);

	return 0;
}

int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
		__be32 sip, __be16 sport, __be16 vlan,
		unsigned int queue, unsigned char port, unsigned char mask)
{
	int ret;
	struct filter_entry *f;
	struct adapter *adap;
	int i;
	u8 *val;

	adap = netdev2adap(dev);

	/* Adjust stid to correct filter index */
	stid -= adap->tids.sftid_base;
	stid += adap->tids.nftids;

	/* Check to make sure the filter requested is writable ...
	 */
	f = &adap->tids.ftid_tab[stid];
	ret = writable_filter(f);
	if (ret)
		return ret;

	/* Clear out any old resources being used by the filter before
	 * we start constructing the new filter.
	 */
	if (f->valid)
		clear_filter(adap, f);

	/* Clear out filter specifications */
	memset(&f->fs, 0, sizeof(struct ch_filter_specification));
	f->fs.val.lport = cpu_to_be16(sport);
	f->fs.mask.lport  = ~0;
	val = (u8 *)&sip;
	if ((val[0] | val[1] | val[2] | val[3]) != 0) {
		for (i = 0; i < 4; i++) {
			f->fs.val.lip[i] = val[i];
			f->fs.mask.lip[i] = ~0;
		}
		if (adap->params.tp.vlan_pri_map & PORT_F) {
			f->fs.val.iport = port;
			f->fs.mask.iport = mask;
		}
	}

	if (adap->params.tp.vlan_pri_map & PROTOCOL_F) {
		f->fs.val.proto = IPPROTO_TCP;
		f->fs.mask.proto = ~0;
	}

	f->fs.dirsteer = 1;
	f->fs.iq = queue;
	/* Mark filter as locked */
	f->locked = 1;
	f->fs.rpttid = 1;

	ret = set_filter_wr(adap, stid);
	if (ret) {
		clear_filter(adap, f);
		return ret;
	}

	return 0;
}
EXPORT_SYMBOL(cxgb4_create_server_filter);

int cxgb4_remove_server_filter(const struct net_device *dev, unsigned int stid,
		unsigned int queue, bool ipv6)
{
	int ret;
	struct filter_entry *f;
	struct adapter *adap;

	adap = netdev2adap(dev);

	/* Adjust stid to correct filter index */
	stid -= adap->tids.sftid_base;
	stid += adap->tids.nftids;

	f = &adap->tids.ftid_tab[stid];
	/* Unlock the filter */
	f->locked = 0;

	ret = delete_filter(adap, stid);
	if (ret)
		return ret;

	return 0;
}
EXPORT_SYMBOL(cxgb4_remove_server_filter);

static struct rtnl_link_stats64 *cxgb_get_stats(struct net_device *dev,
						struct rtnl_link_stats64 *ns)
{
	struct port_stats stats;
	struct port_info *p = netdev_priv(dev);
	struct adapter *adapter = p->adapter;

	/* Block retrieving statistics during EEH error
	 * recovery. Otherwise, the recovery might fail
	 * and the PCI device will be removed permanently
	 */
	spin_lock(&adapter->stats_lock);
	if (!netif_device_present(dev)) {
		spin_unlock(&adapter->stats_lock);
		return ns;
	}
	t4_get_port_stats_offset(adapter, p->tx_chan, &stats,
				 &p->stats_base);
	spin_unlock(&adapter->stats_lock);

	ns->tx_bytes   = stats.tx_octets;
	ns->tx_packets = stats.tx_frames;
	ns->rx_bytes   = stats.rx_octets;
	ns->rx_packets = stats.rx_frames;
	ns->multicast  = stats.rx_mcast_frames;

	/* detailed rx_errors */
	ns->rx_length_errors = stats.rx_jabber + stats.rx_too_long +
			       stats.rx_runt;
	ns->rx_over_errors   = 0;
	ns->rx_crc_errors    = stats.rx_fcs_err;
	ns->rx_frame_errors  = stats.rx_symbol_err;
	ns->rx_fifo_errors   = stats.rx_ovflow0 + stats.rx_ovflow1 +
			       stats.rx_ovflow2 + stats.rx_ovflow3 +
			       stats.rx_trunc0 + stats.rx_trunc1 +
			       stats.rx_trunc2 + stats.rx_trunc3;
	ns->rx_missed_errors = 0;

	/* detailed tx_errors */
	ns->tx_aborted_errors   = 0;
	ns->tx_carrier_errors   = 0;
	ns->tx_fifo_errors      = 0;
	ns->tx_heartbeat_errors = 0;
	ns->tx_window_errors    = 0;

	ns->tx_errors = stats.tx_error_frames;
	ns->rx_errors = stats.rx_symbol_err + stats.rx_fcs_err +
		ns->rx_length_errors + stats.rx_len_err + ns->rx_fifo_errors;
	return ns;
}

static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
{
	unsigned int mbox;
	int ret = 0, prtad, devad;
	struct port_info *pi = netdev_priv(dev);
	struct mii_ioctl_data *data = (struct mii_ioctl_data *)&req->ifr_data;

	switch (cmd) {
	case SIOCGMIIPHY:
		if (pi->mdio_addr < 0)
			return -EOPNOTSUPP;
		data->phy_id = pi->mdio_addr;
		break;
	case SIOCGMIIREG:
	case SIOCSMIIREG:
		if (mdio_phy_id_is_c45(data->phy_id)) {
			prtad = mdio_phy_id_prtad(data->phy_id);
			devad = mdio_phy_id_devad(data->phy_id);
		} else if (data->phy_id < 32) {
			prtad = data->phy_id;
			devad = 0;
			data->reg_num &= 0x1f;
		} else
			return -EINVAL;

		mbox = pi->adapter->pf;
		if (cmd == SIOCGMIIREG)
			ret = t4_mdio_rd(pi->adapter, mbox, prtad, devad,
					 data->reg_num, &data->val_out);
		else
			ret = t4_mdio_wr(pi->adapter, mbox, prtad, devad,
					 data->reg_num, data->val_in);
		break;
	case SIOCGHWTSTAMP:
		return copy_to_user(req->ifr_data, &pi->tstamp_config,
				    sizeof(pi->tstamp_config)) ?
			-EFAULT : 0;
	case SIOCSHWTSTAMP:
		if (copy_from_user(&pi->tstamp_config, req->ifr_data,
				   sizeof(pi->tstamp_config)))
			return -EFAULT;

		switch (pi->tstamp_config.rx_filter) {
		case HWTSTAMP_FILTER_NONE:
			pi->rxtstamp = false;
			break;
		case HWTSTAMP_FILTER_ALL:
			pi->rxtstamp = true;
			break;
		default:
			pi->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
			return -ERANGE;
		}

		return copy_to_user(req->ifr_data, &pi->tstamp_config,
				    sizeof(pi->tstamp_config)) ?
			-EFAULT : 0;
	default:
		return -EOPNOTSUPP;
	}
	return ret;
}

static void cxgb_set_rxmode(struct net_device *dev)
{
	/* unfortunately we can't return errors to the stack */
	set_rxmode(dev, -1, false);
}

static int cxgb_change_mtu(struct net_device *dev, int new_mtu)
{
	int ret;
	struct port_info *pi = netdev_priv(dev);

	if (new_mtu < 81 || new_mtu > MAX_MTU)         /* accommodate SACK */
		return -EINVAL;
	ret = t4_set_rxmode(pi->adapter, pi->adapter->pf, pi->viid, new_mtu, -1,
			    -1, -1, -1, true);
	if (!ret)
		dev->mtu = new_mtu;
	return ret;
}

static int cxgb_set_mac_addr(struct net_device *dev, void *p)
{
	int ret;
	struct sockaddr *addr = p;
	struct port_info *pi = netdev_priv(dev);

	if (!is_valid_ether_addr(addr->sa_data))
		return -EADDRNOTAVAIL;

	ret = t4_change_mac(pi->adapter, pi->adapter->pf, pi->viid,
			    pi->xact_addr_filt, addr->sa_data, true, true);
	if (ret < 0)
		return ret;

	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
	pi->xact_addr_filt = ret;
	return 0;
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void cxgb_netpoll(struct net_device *dev)
{
	struct port_info *pi = netdev_priv(dev);
	struct adapter *adap = pi->adapter;

	if (adap->flags & USING_MSIX) {
		int i;
		struct sge_eth_rxq *rx = &adap->sge.ethrxq[pi->first_qset];

		for (i = pi->nqsets; i; i--, rx++)
			t4_sge_intr_msix(0, &rx->rspq);
	} else
		t4_intr_handler(adap)(0, adap);
}
#endif

static const struct net_device_ops cxgb4_netdev_ops = {
	.ndo_open             = cxgb_open,
	.ndo_stop             = cxgb_close,
	.ndo_start_xmit       = t4_eth_xmit,
	.ndo_select_queue     =	cxgb_select_queue,
	.ndo_get_stats64      = cxgb_get_stats,
	.ndo_set_rx_mode      = cxgb_set_rxmode,
	.ndo_set_mac_address  = cxgb_set_mac_addr,
	.ndo_set_features     = cxgb_set_features,
	.ndo_validate_addr    = eth_validate_addr,
	.ndo_do_ioctl         = cxgb_ioctl,
	.ndo_change_mtu       = cxgb_change_mtu,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller  = cxgb_netpoll,
#endif
#ifdef CONFIG_CHELSIO_T4_FCOE
	.ndo_fcoe_enable      = cxgb_fcoe_enable,
	.ndo_fcoe_disable     = cxgb_fcoe_disable,
#endif /* CONFIG_CHELSIO_T4_FCOE */
#ifdef CONFIG_NET_RX_BUSY_POLL
	.ndo_busy_poll        = cxgb_busy_poll,
#endif

};

void t4_fatal_err(struct adapter *adap)
{
	t4_set_reg_field(adap, SGE_CONTROL_A, GLOBALENABLE_F, 0);
	t4_intr_disable(adap);
	dev_alert(adap->pdev_dev, "encountered fatal error, adapter stopped\n");
}

static void setup_memwin(struct adapter *adap)
{
	u32 nic_win_base = t4_get_util_window(adap);

	t4_setup_memwin(adap, nic_win_base, MEMWIN_NIC);
}

static void setup_memwin_rdma(struct adapter *adap)
{
	if (adap->vres.ocq.size) {
		u32 start;
		unsigned int sz_kb;

		start = t4_read_pcie_cfg4(adap, PCI_BASE_ADDRESS_2);
		start &= PCI_BASE_ADDRESS_MEM_MASK;
		start += OCQ_WIN_OFFSET(adap->pdev, &adap->vres);
		sz_kb = roundup_pow_of_two(adap->vres.ocq.size) >> 10;
		t4_write_reg(adap,
			     PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A, 3),
			     start | BIR_V(1) | WINDOW_V(ilog2(sz_kb)));
		t4_write_reg(adap,
			     PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, 3),
			     adap->vres.ocq.start);
		t4_read_reg(adap,
			    PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, 3));
	}
}

static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c)
{
	u32 v;
	int ret;

	/* get device capabilities */
	memset(c, 0, sizeof(*c));
	c->op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
			       FW_CMD_REQUEST_F | FW_CMD_READ_F);
	c->cfvalid_to_len16 = htonl(FW_LEN16(*c));
	ret = t4_wr_mbox(adap, adap->mbox, c, sizeof(*c), c);
	if (ret < 0)
		return ret;

	/* select capabilities we'll be using */
	if (c->niccaps & htons(FW_CAPS_CONFIG_NIC_VM)) {
		if (!vf_acls)
			c->niccaps ^= htons(FW_CAPS_CONFIG_NIC_VM);
		else
			c->niccaps = htons(FW_CAPS_CONFIG_NIC_VM);
	} else if (vf_acls) {
		dev_err(adap->pdev_dev, "virtualization ACLs not supported");
		return ret;
	}
	c->op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
			       FW_CMD_REQUEST_F | FW_CMD_WRITE_F);
	ret = t4_wr_mbox(adap, adap->mbox, c, sizeof(*c), NULL);
	if (ret < 0)
		return ret;

	ret = t4_config_glbl_rss(adap, adap->pf,
				 FW_RSS_GLB_CONFIG_CMD_MODE_BASICVIRTUAL,
				 FW_RSS_GLB_CONFIG_CMD_TNLMAPEN_F |
				 FW_RSS_GLB_CONFIG_CMD_TNLALLLKP_F);
	if (ret < 0)
		return ret;

	ret = t4_cfg_pfvf(adap, adap->mbox, adap->pf, 0, adap->sge.egr_sz, 64,
			  MAX_INGQ, 0, 0, 4, 0xf, 0xf, 16, FW_CMD_CAP_PF,
			  FW_CMD_CAP_PF);
	if (ret < 0)
		return ret;

	t4_sge_init(adap);

	/* tweak some settings */
	t4_write_reg(adap, TP_SHIFT_CNT_A, 0x64f8849);
	t4_write_reg(adap, ULP_RX_TDDP_PSZ_A, HPZ0_V(PAGE_SHIFT - 12));
	t4_write_reg(adap, TP_PIO_ADDR_A, TP_INGRESS_CONFIG_A);
	v = t4_read_reg(adap, TP_PIO_DATA_A);
	t4_write_reg(adap, TP_PIO_DATA_A, v & ~CSUM_HAS_PSEUDO_HDR_F);

	/* first 4 Tx modulation queues point to consecutive Tx channels */
	adap->params.tp.tx_modq_map = 0xE4;
	t4_write_reg(adap, TP_TX_MOD_QUEUE_REQ_MAP_A,
		     TX_MOD_QUEUE_REQ_MAP_V(adap->params.tp.tx_modq_map));

	/* associate each Tx modulation queue with consecutive Tx channels */
	v = 0x84218421;
	t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A,
			  &v, 1, TP_TX_SCHED_HDR_A);
	t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A,
			  &v, 1, TP_TX_SCHED_FIFO_A);
	t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A,
			  &v, 1, TP_TX_SCHED_PCMD_A);

#define T4_TX_MODQ_10G_WEIGHT_DEFAULT 16 /* in KB units */
	if (is_offload(adap)) {
		t4_write_reg(adap, TP_TX_MOD_QUEUE_WEIGHT0_A,
			     TX_MODQ_WEIGHT0_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
			     TX_MODQ_WEIGHT1_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
			     TX_MODQ_WEIGHT2_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
			     TX_MODQ_WEIGHT3_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT));
		t4_write_reg(adap, TP_TX_MOD_CHANNEL_WEIGHT_A,
			     TX_MODQ_WEIGHT0_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
			     TX_MODQ_WEIGHT1_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
			     TX_MODQ_WEIGHT2_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
			     TX_MODQ_WEIGHT3_V(T4_TX_MODQ_10G_WEIGHT_DEFAULT));
	}

	/* get basic stuff going */
	return t4_early_init(adap, adap->pf);
}

/*
 * Max # of ATIDs.  The absolute HW max is 16K but we keep it lower.
 */
#define MAX_ATIDS 8192U

/*
 * Phase 0 of initialization: contact FW, obtain config, perform basic init.
 *
 * If the firmware we're dealing with has Configuration File support, then
 * we use that to perform all configuration
 */

/*
 * Tweak configuration based on module parameters, etc.  Most of these have
 * defaults assigned to them by Firmware Configuration Files (if we're using
 * them) but need to be explicitly set if we're using hard-coded
 * initialization.  But even in the case of using Firmware Configuration
 * Files, we'd like to expose the ability to change these via module
 * parameters so these are essentially common tweaks/settings for
 * Configuration Files and hard-coded initialization ...
 */
static int adap_init0_tweaks(struct adapter *adapter)
{
	/*
	 * Fix up various Host-Dependent Parameters like Page Size, Cache
	 * Line Size, etc.  The firmware default is for a 4KB Page Size and
	 * 64B Cache Line Size ...
	 */
	t4_fixup_host_params(adapter, PAGE_SIZE, L1_CACHE_BYTES);

	/*
	 * Process module parameters which affect early initialization.
	 */
	if (rx_dma_offset != 2 && rx_dma_offset != 0) {
		dev_err(&adapter->pdev->dev,
			"Ignoring illegal rx_dma_offset=%d, using 2\n",
			rx_dma_offset);
		rx_dma_offset = 2;
	}
	t4_set_reg_field(adapter, SGE_CONTROL_A,
			 PKTSHIFT_V(PKTSHIFT_M),
			 PKTSHIFT_V(rx_dma_offset));

	/*
	 * Don't include the "IP Pseudo Header" in CPL_RX_PKT checksums: Linux
	 * adds the pseudo header itself.
	 */
	t4_tp_wr_bits_indirect(adapter, TP_INGRESS_CONFIG_A,
			       CSUM_HAS_PSEUDO_HDR_F, 0);

	return 0;
}

/* 10Gb/s-BT PHY Support. chip-external 10Gb/s-BT PHYs are complex chips
 * unto themselves and they contain their own firmware to perform their
 * tasks ...
 */
static int phy_aq1202_version(const u8 *phy_fw_data,
			      size_t phy_fw_size)
{
	int offset;

	/* At offset 0x8 you're looking for the primary image's
	 * starting offset which is 3 Bytes wide
	 *
	 * At offset 0xa of the primary image, you look for the offset
	 * of the DRAM segment which is 3 Bytes wide.
	 *
	 * The FW version is at offset 0x27e of the DRAM and is 2 Bytes
	 * wide
	 */
	#define be16(__p) (((__p)[0] << 8) | (__p)[1])
	#define le16(__p) ((__p)[0] | ((__p)[1] << 8))
	#define le24(__p) (le16(__p) | ((__p)[2] << 16))

	offset = le24(phy_fw_data + 0x8) << 12;
	offset = le24(phy_fw_data + offset + 0xa);
	return be16(phy_fw_data + offset + 0x27e);

	#undef be16
	#undef le16
	#undef le24
}

static struct info_10gbt_phy_fw {
	unsigned int phy_fw_id;		/* PCI Device ID */
	char *phy_fw_file;		/* /lib/firmware/ PHY Firmware file */
	int (*phy_fw_version)(const u8 *phy_fw_data, size_t phy_fw_size);
	int phy_flash;			/* Has FLASH for PHY Firmware */
} phy_info_array[] = {
	{
		PHY_AQ1202_DEVICEID,
		PHY_AQ1202_FIRMWARE,
		phy_aq1202_version,
		1,
	},
	{
		PHY_BCM84834_DEVICEID,
		PHY_BCM84834_FIRMWARE,
		NULL,
		0,
	},
	{ 0, NULL, NULL },
};

static struct info_10gbt_phy_fw *find_phy_info(int devid)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(phy_info_array); i++) {
		if (phy_info_array[i].phy_fw_id == devid)
			return &phy_info_array[i];
	}
	return NULL;
}

/* Handle updating of chip-external 10Gb/s-BT PHY firmware.  This needs to
 * happen after the FW_RESET_CMD but before the FW_INITIALIZE_CMD.  On error
 * we return a negative error number.  If we transfer new firmware we return 1
 * (from t4_load_phy_fw()).  If we don't do anything we return 0.
 */
static int adap_init0_phy(struct adapter *adap)
{
	const struct firmware *phyf;
	int ret;
	struct info_10gbt_phy_fw *phy_info;

	/* Use the device ID to determine which PHY file to flash.
	 */
	phy_info = find_phy_info(adap->pdev->device);
	if (!phy_info) {
		dev_warn(adap->pdev_dev,
			 "No PHY Firmware file found for this PHY\n");
		return -EOPNOTSUPP;
	}

	/* If we have a T4 PHY firmware file under /lib/firmware/cxgb4/, then
	 * use that. The adapter firmware provides us with a memory buffer
	 * where we can load a PHY firmware file from the host if we want to
	 * override the PHY firmware File in flash.
	 */
	ret = request_firmware_direct(&phyf, phy_info->phy_fw_file,
				      adap->pdev_dev);
	if (ret < 0) {
		/* For adapters without FLASH attached to PHY for their
		 * firmware, it's obviously a fatal error if we can't get the
		 * firmware to the adapter.  For adapters with PHY firmware
		 * FLASH storage, it's worth a warning if we can't find the
		 * PHY Firmware but we'll neuter the error ...
		 */
		dev_err(adap->pdev_dev, "unable to find PHY Firmware image "
			"/lib/firmware/%s, error %d\n",
			phy_info->phy_fw_file, -ret);
		if (phy_info->phy_flash) {
			int cur_phy_fw_ver = 0;

			t4_phy_fw_ver(adap, &cur_phy_fw_ver);
			dev_warn(adap->pdev_dev, "continuing with, on-adapter "
				 "FLASH copy, version %#x\n", cur_phy_fw_ver);
			ret = 0;
		}

		return ret;
	}

	/* Load PHY Firmware onto adapter.
	 */
	ret = t4_load_phy_fw(adap, MEMWIN_NIC, &adap->win0_lock,
			     phy_info->phy_fw_version,
			     (u8 *)phyf->data, phyf->size);
	if (ret < 0)
		dev_err(adap->pdev_dev, "PHY Firmware transfer error %d\n",
			-ret);
	else if (ret > 0) {
		int new_phy_fw_ver = 0;

		if (phy_info->phy_fw_version)
			new_phy_fw_ver = phy_info->phy_fw_version(phyf->data,
								  phyf->size);
		dev_info(adap->pdev_dev, "Successfully transferred PHY "
			 "Firmware /lib/firmware/%s, version %#x\n",
			 phy_info->phy_fw_file, new_phy_fw_ver);
	}

	release_firmware(phyf);

	return ret;
}

/*
 * Attempt to initialize the adapter via a Firmware Configuration File.
 */
static int adap_init0_config(struct adapter *adapter, int reset)
{
	struct fw_caps_config_cmd caps_cmd;
	const struct firmware *cf;
	unsigned long mtype = 0, maddr = 0;
	u32 finiver, finicsum, cfcsum;
	int ret;
	int config_issued = 0;
	char *fw_config_file, fw_config_file_path[256];
	char *config_name = NULL;

	/*
	 * Reset device if necessary.
	 */
	if (reset) {
		ret = t4_fw_reset(adapter, adapter->mbox,
				  PIORSTMODE_F | PIORST_F);
		if (ret < 0)
			goto bye;
	}

	/* If this is a 10Gb/s-BT adapter make sure the chip-external
	 * 10Gb/s-BT PHYs have up-to-date firmware.  Note that this step needs
	 * to be performed after any global adapter RESET above since some
	 * PHYs only have local RAM copies of the PHY firmware.
	 */
	if (is_10gbt_device(adapter->pdev->device)) {
		ret = adap_init0_phy(adapter);
		if (ret < 0)
			goto bye;
	}
	/*
	 * If we have a T4 configuration file under /lib/firmware/cxgb4/,
	 * then use that.  Otherwise, use the configuration file stored
	 * in the adapter flash ...
	 */
	switch (CHELSIO_CHIP_VERSION(adapter->params.chip)) {
	case CHELSIO_T4:
		fw_config_file = FW4_CFNAME;
		break;
	case CHELSIO_T5:
		fw_config_file = FW5_CFNAME;
		break;
	case CHELSIO_T6:
		fw_config_file = FW6_CFNAME;
		break;
	default:
		dev_err(adapter->pdev_dev, "Device %d is not supported\n",
		       adapter->pdev->device);
		ret = -EINVAL;
		goto bye;
	}

	ret = request_firmware(&cf, fw_config_file, adapter->pdev_dev);
	if (ret < 0) {
		config_name = "On FLASH";
		mtype = FW_MEMTYPE_CF_FLASH;
		maddr = t4_flash_cfg_addr(adapter);
	} else {
		u32 params[7], val[7];

		sprintf(fw_config_file_path,
			"/lib/firmware/%s", fw_config_file);
		config_name = fw_config_file_path;

		if (cf->size >= FLASH_CFG_MAX_SIZE)
			ret = -ENOMEM;
		else {
			params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
			     FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_CF));
			ret = t4_query_params(adapter, adapter->mbox,
					      adapter->pf, 0, 1, params, val);
			if (ret == 0) {
				/*
				 * For t4_memory_rw() below addresses and
				 * sizes have to be in terms of multiples of 4
				 * bytes.  So, if the Configuration File isn't
				 * a multiple of 4 bytes in length we'll have
				 * to write that out separately since we can't
				 * guarantee that the bytes following the
				 * residual byte in the buffer returned by
				 * request_firmware() are zeroed out ...
				 */
				size_t resid = cf->size & 0x3;
				size_t size = cf->size & ~0x3;
				__be32 *data = (__be32 *)cf->data;

				mtype = FW_PARAMS_PARAM_Y_G(val[0]);
				maddr = FW_PARAMS_PARAM_Z_G(val[0]) << 16;

				spin_lock(&adapter->win0_lock);
				ret = t4_memory_rw(adapter, 0, mtype, maddr,
						   size, data, T4_MEMORY_WRITE);
				if (ret == 0 && resid != 0) {
					union {
						__be32 word;
						char buf[4];
					} last;
					int i;

					last.word = data[size >> 2];
					for (i = resid; i < 4; i++)
						last.buf[i] = 0;
					ret = t4_memory_rw(adapter, 0, mtype,
							   maddr + size,
							   4, &last.word,
							   T4_MEMORY_WRITE);
				}
				spin_unlock(&adapter->win0_lock);
			}
		}

		release_firmware(cf);
		if (ret)
			goto bye;
	}

	/*
	 * Issue a Capability Configuration command to the firmware to get it
	 * to parse the Configuration File.  We don't use t4_fw_config_file()
	 * because we want the ability to modify various features after we've
	 * processed the configuration file ...
	 */
	memset(&caps_cmd, 0, sizeof(caps_cmd));
	caps_cmd.op_to_write =
		htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
		      FW_CMD_REQUEST_F |
		      FW_CMD_READ_F);
	caps_cmd.cfvalid_to_len16 =
		htonl(FW_CAPS_CONFIG_CMD_CFVALID_F |
		      FW_CAPS_CONFIG_CMD_MEMTYPE_CF_V(mtype) |
		      FW_CAPS_CONFIG_CMD_MEMADDR64K_CF_V(maddr >> 16) |
		      FW_LEN16(caps_cmd));
	ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd, sizeof(caps_cmd),
			 &caps_cmd);

	/* If the CAPS_CONFIG failed with an ENOENT (for a Firmware
	 * Configuration File in FLASH), our last gasp effort is to use the
	 * Firmware Configuration File which is embedded in the firmware.  A
	 * very few early versions of the firmware didn't have one embedded
	 * but we can ignore those.
	 */
	if (ret == -ENOENT) {
		memset(&caps_cmd, 0, sizeof(caps_cmd));
		caps_cmd.op_to_write =
			htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
					FW_CMD_REQUEST_F |
					FW_CMD_READ_F);
		caps_cmd.cfvalid_to_len16 = htonl(FW_LEN16(caps_cmd));
		ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd,
				sizeof(caps_cmd), &caps_cmd);
		config_name = "Firmware Default";
	}

	config_issued = 1;
	if (ret < 0)
		goto bye;

	finiver = ntohl(caps_cmd.finiver);
	finicsum = ntohl(caps_cmd.finicsum);
	cfcsum = ntohl(caps_cmd.cfcsum);
	if (finicsum != cfcsum)
		dev_warn(adapter->pdev_dev, "Configuration File checksum "\
			 "mismatch: [fini] csum=%#x, computed csum=%#x\n",
			 finicsum, cfcsum);

	/*
	 * And now tell the firmware to use the configuration we just loaded.
	 */
	caps_cmd.op_to_write =
		htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
		      FW_CMD_REQUEST_F |
		      FW_CMD_WRITE_F);
	caps_cmd.cfvalid_to_len16 = htonl(FW_LEN16(caps_cmd));
	ret = t4_wr_mbox(adapter, adapter->mbox, &caps_cmd, sizeof(caps_cmd),
			 NULL);
	if (ret < 0)
		goto bye;

	/*
	 * Tweak configuration based on system architecture, module
	 * parameters, etc.
	 */
	ret = adap_init0_tweaks(adapter);
	if (ret < 0)
		goto bye;

	/*
	 * And finally tell the firmware to initialize itself using the
	 * parameters from the Configuration File.
	 */
	ret = t4_fw_initialize(adapter, adapter->mbox);
	if (ret < 0)
		goto bye;

	/* Emit Firmware Configuration File information and return
	 * successfully.
	 */
	dev_info(adapter->pdev_dev, "Successfully configured using Firmware "\
		 "Configuration File \"%s\", version %#x, computed checksum %#x\n",
		 config_name, finiver, cfcsum);
	return 0;

	/*
	 * Something bad happened.  Return the error ...  (If the "error"
	 * is that there's no Configuration File on the adapter we don't
	 * want to issue a warning since this is fairly common.)
	 */
bye:
	if (config_issued && ret != -ENOENT)
		dev_warn(adapter->pdev_dev, "\"%s\" configuration file error %d\n",
			 config_name, -ret);
	return ret;
}

static struct fw_info fw_info_array[] = {
	{
		.chip = CHELSIO_T4,
		.fs_name = FW4_CFNAME,
		.fw_mod_name = FW4_FNAME,
		.fw_hdr = {
			.chip = FW_HDR_CHIP_T4,
			.fw_ver = __cpu_to_be32(FW_VERSION(T4)),
			.intfver_nic = FW_INTFVER(T4, NIC),
			.intfver_vnic = FW_INTFVER(T4, VNIC),
			.intfver_ri = FW_INTFVER(T4, RI),
			.intfver_iscsi = FW_INTFVER(T4, ISCSI),
			.intfver_fcoe = FW_INTFVER(T4, FCOE),
		},
	}, {
		.chip = CHELSIO_T5,
		.fs_name = FW5_CFNAME,
		.fw_mod_name = FW5_FNAME,
		.fw_hdr = {
			.chip = FW_HDR_CHIP_T5,
			.fw_ver = __cpu_to_be32(FW_VERSION(T5)),
			.intfver_nic = FW_INTFVER(T5, NIC),
			.intfver_vnic = FW_INTFVER(T5, VNIC),
			.intfver_ri = FW_INTFVER(T5, RI),
			.intfver_iscsi = FW_INTFVER(T5, ISCSI),
			.intfver_fcoe = FW_INTFVER(T5, FCOE),
		},
	}, {
		.chip = CHELSIO_T6,
		.fs_name = FW6_CFNAME,
		.fw_mod_name = FW6_FNAME,
		.fw_hdr = {
			.chip = FW_HDR_CHIP_T6,
			.fw_ver = __cpu_to_be32(FW_VERSION(T6)),
			.intfver_nic = FW_INTFVER(T6, NIC),
			.intfver_vnic = FW_INTFVER(T6, VNIC),
			.intfver_ofld = FW_INTFVER(T6, OFLD),
			.intfver_ri = FW_INTFVER(T6, RI),
			.intfver_iscsipdu = FW_INTFVER(T6, ISCSIPDU),
			.intfver_iscsi = FW_INTFVER(T6, ISCSI),
			.intfver_fcoepdu = FW_INTFVER(T6, FCOEPDU),
			.intfver_fcoe = FW_INTFVER(T6, FCOE),
		},
	}

};

static struct fw_info *find_fw_info(int chip)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(fw_info_array); i++) {
		if (fw_info_array[i].chip == chip)
			return &fw_info_array[i];
	}
	return NULL;
}

/*
 * Phase 0 of initialization: contact FW, obtain config, perform basic init.
 */
static int adap_init0(struct adapter *adap)
{
	int ret;
	u32 v, port_vec;
	enum dev_state state;
	u32 params[7], val[7];
	struct fw_caps_config_cmd caps_cmd;
	int reset = 1;

	/* Grab Firmware Device Log parameters as early as possible so we have
	 * access to it for debugging, etc.
	 */
	ret = t4_init_devlog_params(adap);
	if (ret < 0)
		return ret;

	/* Contact FW, advertising Master capability */
	ret = t4_fw_hello(adap, adap->mbox, adap->mbox, MASTER_MAY, &state);
	if (ret < 0) {
		dev_err(adap->pdev_dev, "could not connect to FW, error %d\n",
			ret);
		return ret;
	}
	if (ret == adap->mbox)
		adap->flags |= MASTER_PF;

	/*
	 * If we're the Master PF Driver and the device is uninitialized,
	 * then let's consider upgrading the firmware ...  (We always want
	 * to check the firmware version number in order to A. get it for
	 * later reporting and B. to warn if the currently loaded firmware
	 * is excessively mismatched relative to the driver.)
	 */
	t4_get_fw_version(adap, &adap->params.fw_vers);
	t4_get_tp_version(adap, &adap->params.tp_vers);
	ret = t4_check_fw_version(adap);
	/* If firmware is too old (not supported by driver) force an update. */
	if (ret)
		state = DEV_STATE_UNINIT;
	if ((adap->flags & MASTER_PF) && state != DEV_STATE_INIT) {
		struct fw_info *fw_info;
		struct fw_hdr *card_fw;
		const struct firmware *fw;
		const u8 *fw_data = NULL;
		unsigned int fw_size = 0;

		/* This is the firmware whose headers the driver was compiled
		 * against
		 */
		fw_info = find_fw_info(CHELSIO_CHIP_VERSION(adap->params.chip));
		if (fw_info == NULL) {
			dev_err(adap->pdev_dev,
				"unable to get firmware info for chip %d.\n",
				CHELSIO_CHIP_VERSION(adap->params.chip));
			return -EINVAL;
		}

		/* allocate memory to read the header of the firmware on the
		 * card
		 */
		card_fw = t4_alloc_mem(sizeof(*card_fw));

		/* Get FW from from /lib/firmware/ */
		ret = request_firmware(&fw, fw_info->fw_mod_name,
				       adap->pdev_dev);
		if (ret < 0) {
			dev_err(adap->pdev_dev,
				"unable to load firmware image %s, error %d\n",
				fw_info->fw_mod_name, ret);
		} else {
			fw_data = fw->data;
			fw_size = fw->size;
		}

		/* upgrade FW logic */
		ret = t4_prep_fw(adap, fw_info, fw_data, fw_size, card_fw,
				 state, &reset);

		/* Cleaning up */
		release_firmware(fw);
		t4_free_mem(card_fw);

		if (ret < 0)
			goto bye;
	}

	/*
	 * Grab VPD parameters.  This should be done after we establish a
	 * connection to the firmware since some of the VPD parameters
	 * (notably the Core Clock frequency) are retrieved via requests to
	 * the firmware.  On the other hand, we need these fairly early on
	 * so we do this right after getting ahold of the firmware.
	 */
	ret = t4_get_vpd_params(adap, &adap->params.vpd);
	if (ret < 0)
		goto bye;

	/*
	 * Find out what ports are available to us.  Note that we need to do
	 * this before calling adap_init0_no_config() since it needs nports
	 * and portvec ...
	 */
	v =
	    FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
	    FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PORTVEC);
	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, &v, &port_vec);
	if (ret < 0)
		goto bye;

	adap->params.nports = hweight32(port_vec);
	adap->params.portvec = port_vec;

	/* If the firmware is initialized already, emit a simply note to that
	 * effect. Otherwise, it's time to try initializing the adapter.
	 */
	if (state == DEV_STATE_INIT) {
		dev_info(adap->pdev_dev, "Coming up as %s: "\
			 "Adapter already initialized\n",
			 adap->flags & MASTER_PF ? "MASTER" : "SLAVE");
	} else {
		dev_info(adap->pdev_dev, "Coming up as MASTER: "\
			 "Initializing adapter\n");

		/* Find out whether we're dealing with a version of the
		 * firmware which has configuration file support.
		 */
		params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
			     FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_CF));
		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1,
				      params, val);

		/* If the firmware doesn't support Configuration Files,
		 * return an error.
		 */
		if (ret < 0) {
			dev_err(adap->pdev_dev, "firmware doesn't support "
				"Firmware Configuration Files\n");
			goto bye;
		}

		/* The firmware provides us with a memory buffer where we can
		 * load a Configuration File from the host if we want to
		 * override the Configuration File in flash.
		 */
		ret = adap_init0_config(adap, reset);
		if (ret == -ENOENT) {
			dev_err(adap->pdev_dev, "no Configuration File "
				"present on adapter.\n");
			goto bye;
		}
		if (ret < 0) {
			dev_err(adap->pdev_dev, "could not initialize "
				"adapter, error %d\n", -ret);
			goto bye;
		}
	}

	/* Give the SGE code a chance to pull in anything that it needs ...
	 * Note that this must be called after we retrieve our VPD parameters
	 * in order to know how to convert core ticks to seconds, etc.
	 */
	ret = t4_sge_init(adap);
	if (ret < 0)
		goto bye;

	if (is_bypass_device(adap->pdev->device))
		adap->params.bypass = 1;

	/*
	 * Grab some of our basic fundamental operating parameters.
	 */
#define FW_PARAM_DEV(param) \
	(FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | \
	FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_##param))

#define FW_PARAM_PFVF(param) \
	FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) | \
	FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_##param)|  \
	FW_PARAMS_PARAM_Y_V(0) | \
	FW_PARAMS_PARAM_Z_V(0)

	params[0] = FW_PARAM_PFVF(EQ_START);
	params[1] = FW_PARAM_PFVF(L2T_START);
	params[2] = FW_PARAM_PFVF(L2T_END);
	params[3] = FW_PARAM_PFVF(FILTER_START);
	params[4] = FW_PARAM_PFVF(FILTER_END);
	params[5] = FW_PARAM_PFVF(IQFLINT_START);
	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6, params, val);
	if (ret < 0)
		goto bye;
	adap->sge.egr_start = val[0];
	adap->l2t_start = val[1];
	adap->l2t_end = val[2];
	adap->tids.ftid_base = val[3];
	adap->tids.nftids = val[4] - val[3] + 1;
	adap->sge.ingr_start = val[5];

	/* qids (ingress/egress) returned from firmware can be anywhere
	 * in the range from EQ(IQFLINT)_START to EQ(IQFLINT)_END.
	 * Hence driver needs to allocate memory for this range to
	 * store the queue info. Get the highest IQFLINT/EQ index returned
	 * in FW_EQ_*_CMD.alloc command.
	 */
	params[0] = FW_PARAM_PFVF(EQ_END);
	params[1] = FW_PARAM_PFVF(IQFLINT_END);
	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val);
	if (ret < 0)
		goto bye;
	adap->sge.egr_sz = val[0] - adap->sge.egr_start + 1;
	adap->sge.ingr_sz = val[1] - adap->sge.ingr_start + 1;

	adap->sge.egr_map = kcalloc(adap->sge.egr_sz,
				    sizeof(*adap->sge.egr_map), GFP_KERNEL);
	if (!adap->sge.egr_map) {
		ret = -ENOMEM;
		goto bye;
	}

	adap->sge.ingr_map = kcalloc(adap->sge.ingr_sz,
				     sizeof(*adap->sge.ingr_map), GFP_KERNEL);
	if (!adap->sge.ingr_map) {
		ret = -ENOMEM;
		goto bye;
	}

	/* Allocate the memory for the vaious egress queue bitmaps
	 * ie starving_fl, txq_maperr and blocked_fl.
	 */
	adap->sge.starving_fl =	kcalloc(BITS_TO_LONGS(adap->sge.egr_sz),
					sizeof(long), GFP_KERNEL);
	if (!adap->sge.starving_fl) {
		ret = -ENOMEM;
		goto bye;
	}

	adap->sge.txq_maperr = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz),
				       sizeof(long), GFP_KERNEL);
	if (!adap->sge.txq_maperr) {
		ret = -ENOMEM;
		goto bye;
	}

#ifdef CONFIG_DEBUG_FS
	adap->sge.blocked_fl = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz),
				       sizeof(long), GFP_KERNEL);
	if (!adap->sge.blocked_fl) {
		ret = -ENOMEM;
		goto bye;
	}
#endif

	params[0] = FW_PARAM_PFVF(CLIP_START);
	params[1] = FW_PARAM_PFVF(CLIP_END);
	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val);
	if (ret < 0)
		goto bye;
	adap->clipt_start = val[0];
	adap->clipt_end = val[1];

	/* query params related to active filter region */
	params[0] = FW_PARAM_PFVF(ACTIVE_FILTER_START);
	params[1] = FW_PARAM_PFVF(ACTIVE_FILTER_END);
	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val);
	/* If Active filter size is set we enable establishing
	 * offload connection through firmware work request
	 */
	if ((val[0] != val[1]) && (ret >= 0)) {
		adap->flags |= FW_OFLD_CONN;
		adap->tids.aftid_base = val[0];
		adap->tids.aftid_end = val[1];
	}

	/* If we're running on newer firmware, let it know that we're
	 * prepared to deal with encapsulated CPL messages.  Older
	 * firmware won't understand this and we'll just get
	 * unencapsulated messages ...
	 */
	params[0] = FW_PARAM_PFVF(CPLFW4MSG_ENCAP);
	val[0] = 1;
	(void)t4_set_params(adap, adap->mbox, adap->pf, 0, 1, params, val);

	/*
	 * Find out whether we're allowed to use the T5+ ULPTX MEMWRITE DSGL
	 * capability.  Earlier versions of the firmware didn't have the
	 * ULPTX_MEMWRITE_DSGL so we'll interpret a query failure as no
	 * permission to use ULPTX MEMWRITE DSGL.
	 */
	if (is_t4(adap->params.chip)) {
		adap->params.ulptx_memwrite_dsgl = false;
	} else {
		params[0] = FW_PARAM_DEV(ULPTX_MEMWRITE_DSGL);
		ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
				      1, params, val);
		adap->params.ulptx_memwrite_dsgl = (ret == 0 && val[0] != 0);
	}

	/*
	 * Get device capabilities so we can determine what resources we need
	 * to manage.
	 */
	memset(&caps_cmd, 0, sizeof(caps_cmd));
	caps_cmd.op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
				     FW_CMD_REQUEST_F | FW_CMD_READ_F);
	caps_cmd.cfvalid_to_len16 = htonl(FW_LEN16(caps_cmd));
	ret = t4_wr_mbox(adap, adap->mbox, &caps_cmd, sizeof(caps_cmd),
			 &caps_cmd);
	if (ret < 0)
		goto bye;

	if (caps_cmd.ofldcaps) {
		/* query offload-related parameters */
		params[0] = FW_PARAM_DEV(NTID);
		params[1] = FW_PARAM_PFVF(SERVER_START);
		params[2] = FW_PARAM_PFVF(SERVER_END);
		params[3] = FW_PARAM_PFVF(TDDP_START);
		params[4] = FW_PARAM_PFVF(TDDP_END);
		params[5] = FW_PARAM_DEV(FLOWC_BUFFIFO_SZ);
		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6,
				      params, val);
		if (ret < 0)
			goto bye;
		adap->tids.ntids = val[0];
		adap->tids.natids = min(adap->tids.ntids / 2, MAX_ATIDS);
		adap->tids.stid_base = val[1];
		adap->tids.nstids = val[2] - val[1] + 1;
		/*
		 * Setup server filter region. Divide the available filter
		 * region into two parts. Regular filters get 1/3rd and server
		 * filters get 2/3rd part. This is only enabled if workarond
		 * path is enabled.
		 * 1. For regular filters.
		 * 2. Server filter: This are special filters which are used
		 * to redirect SYN packets to offload queue.
		 */
		if (adap->flags & FW_OFLD_CONN && !is_bypass(adap)) {
			adap->tids.sftid_base = adap->tids.ftid_base +
					DIV_ROUND_UP(adap->tids.nftids, 3);
			adap->tids.nsftids = adap->tids.nftids -
					 DIV_ROUND_UP(adap->tids.nftids, 3);
			adap->tids.nftids = adap->tids.sftid_base -
						adap->tids.ftid_base;
		}
		adap->vres.ddp.start = val[3];
		adap->vres.ddp.size = val[4] - val[3] + 1;
		adap->params.ofldq_wr_cred = val[5];

		adap->params.offload = 1;
	}
	if (caps_cmd.rdmacaps) {
		params[0] = FW_PARAM_PFVF(STAG_START);
		params[1] = FW_PARAM_PFVF(STAG_END);
		params[2] = FW_PARAM_PFVF(RQ_START);
		params[3] = FW_PARAM_PFVF(RQ_END);
		params[4] = FW_PARAM_PFVF(PBL_START);
		params[5] = FW_PARAM_PFVF(PBL_END);
		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6,
				      params, val);
		if (ret < 0)
			goto bye;
		adap->vres.stag.start = val[0];
		adap->vres.stag.size = val[1] - val[0] + 1;
		adap->vres.rq.start = val[2];
		adap->vres.rq.size = val[3] - val[2] + 1;
		adap->vres.pbl.start = val[4];
		adap->vres.pbl.size = val[5] - val[4] + 1;

		params[0] = FW_PARAM_PFVF(SQRQ_START);
		params[1] = FW_PARAM_PFVF(SQRQ_END);
		params[2] = FW_PARAM_PFVF(CQ_START);
		params[3] = FW_PARAM_PFVF(CQ_END);
		params[4] = FW_PARAM_PFVF(OCQ_START);
		params[5] = FW_PARAM_PFVF(OCQ_END);
		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6, params,
				      val);
		if (ret < 0)
			goto bye;
		adap->vres.qp.start = val[0];
		adap->vres.qp.size = val[1] - val[0] + 1;
		adap->vres.cq.start = val[2];
		adap->vres.cq.size = val[3] - val[2] + 1;
		adap->vres.ocq.start = val[4];
		adap->vres.ocq.size = val[5] - val[4] + 1;

		params[0] = FW_PARAM_DEV(MAXORDIRD_QP);
		params[1] = FW_PARAM_DEV(MAXIRD_ADAPTER);
		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params,
				      val);
		if (ret < 0) {
			adap->params.max_ordird_qp = 8;
			adap->params.max_ird_adapter = 32 * adap->tids.ntids;
			ret = 0;
		} else {
			adap->params.max_ordird_qp = val[0];
			adap->params.max_ird_adapter = val[1];
		}
		dev_info(adap->pdev_dev,
			 "max_ordird_qp %d max_ird_adapter %d\n",
			 adap->params.max_ordird_qp,
			 adap->params.max_ird_adapter);
	}
	if (caps_cmd.iscsicaps) {
		params[0] = FW_PARAM_PFVF(ISCSI_START);
		params[1] = FW_PARAM_PFVF(ISCSI_END);
		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2,
				      params, val);
		if (ret < 0)
			goto bye;
		adap->vres.iscsi.start = val[0];
		adap->vres.iscsi.size = val[1] - val[0] + 1;
	}
#undef FW_PARAM_PFVF
#undef FW_PARAM_DEV

	/* The MTU/MSS Table is initialized by now, so load their values.  If
	 * we're initializing the adapter, then we'll make any modifications
	 * we want to the MTU/MSS Table and also initialize the congestion
	 * parameters.
	 */
	t4_read_mtu_tbl(adap, adap->params.mtus, NULL);
	if (state != DEV_STATE_INIT) {
		int i;

		/* The default MTU Table contains values 1492 and 1500.
		 * However, for TCP, it's better to have two values which are
		 * a multiple of 8 +/- 4 bytes apart near this popular MTU.
		 * This allows us to have a TCP Data Payload which is a
		 * multiple of 8 regardless of what combination of TCP Options
		 * are in use (always a multiple of 4 bytes) which is
		 * important for performance reasons.  For instance, if no
		 * options are in use, then we have a 20-byte IP header and a
		 * 20-byte TCP header.  In this case, a 1500-byte MSS would
		 * result in a TCP Data Payload of 1500 - 40 == 1460 bytes
		 * which is not a multiple of 8.  So using an MSS of 1488 in
		 * this case results in a TCP Data Payload of 1448 bytes which
		 * is a multiple of 8.  On the other hand, if 12-byte TCP Time
		 * Stamps have been negotiated, then an MTU of 1500 bytes
		 * results in a TCP Data Payload of 1448 bytes which, as
		 * above, is a multiple of 8 bytes ...
		 */
		for (i = 0; i < NMTUS; i++)
			if (adap->params.mtus[i] == 1492) {
				adap->params.mtus[i] = 1488;
				break;
			}

		t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
			     adap->params.b_wnd);
	}
	t4_init_sge_params(adap);
	adap->flags |= FW_OK;
	t4_init_tp_params(adap);
	return 0;

	/*
	 * Something bad happened.  If a command timed out or failed with EIO
	 * FW does not operate within its spec or something catastrophic
	 * happened to HW/FW, stop issuing commands.
	 */
bye:
	kfree(adap->sge.egr_map);
	kfree(adap->sge.ingr_map);
	kfree(adap->sge.starving_fl);
	kfree(adap->sge.txq_maperr);
#ifdef CONFIG_DEBUG_FS
	kfree(adap->sge.blocked_fl);
#endif
	if (ret != -ETIMEDOUT && ret != -EIO)
		t4_fw_bye(adap, adap->mbox);
	return ret;
}

/* EEH callbacks */

static pci_ers_result_t eeh_err_detected(struct pci_dev *pdev,
					 pci_channel_state_t state)
{
	int i;
	struct adapter *adap = pci_get_drvdata(pdev);

	if (!adap)
		goto out;

	rtnl_lock();
	adap->flags &= ~FW_OK;
	notify_ulds(adap, CXGB4_STATE_START_RECOVERY);
	spin_lock(&adap->stats_lock);
	for_each_port(adap, i) {
		struct net_device *dev = adap->port[i];

		netif_device_detach(dev);
		netif_carrier_off(dev);
	}
	spin_unlock(&adap->stats_lock);
	disable_interrupts(adap);
	if (adap->flags & FULL_INIT_DONE)
		cxgb_down(adap);
	rtnl_unlock();
	if ((adap->flags & DEV_ENABLED)) {
		pci_disable_device(pdev);
		adap->flags &= ~DEV_ENABLED;
	}
out:	return state == pci_channel_io_perm_failure ?
		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
}

static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev)
{
	int i, ret;
	struct fw_caps_config_cmd c;
	struct adapter *adap = pci_get_drvdata(pdev);

	if (!adap) {
		pci_restore_state(pdev);
		pci_save_state(pdev);
		return PCI_ERS_RESULT_RECOVERED;
	}

	if (!(adap->flags & DEV_ENABLED)) {
		if (pci_enable_device(pdev)) {
			dev_err(&pdev->dev, "Cannot reenable PCI "
					    "device after reset\n");
			return PCI_ERS_RESULT_DISCONNECT;
		}
		adap->flags |= DEV_ENABLED;
	}

	pci_set_master(pdev);
	pci_restore_state(pdev);
	pci_save_state(pdev);
	pci_cleanup_aer_uncorrect_error_status(pdev);

	if (t4_wait_dev_ready(adap->regs) < 0)
		return PCI_ERS_RESULT_DISCONNECT;
	if (t4_fw_hello(adap, adap->mbox, adap->pf, MASTER_MUST, NULL) < 0)
		return PCI_ERS_RESULT_DISCONNECT;
	adap->flags |= FW_OK;
	if (adap_init1(adap, &c))
		return PCI_ERS_RESULT_DISCONNECT;

	for_each_port(adap, i) {
		struct port_info *p = adap2pinfo(adap, i);

		ret = t4_alloc_vi(adap, adap->mbox, p->tx_chan, adap->pf, 0, 1,
				  NULL, NULL);
		if (ret < 0)
			return PCI_ERS_RESULT_DISCONNECT;
		p->viid = ret;
		p->xact_addr_filt = -1;
	}

	t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
		     adap->params.b_wnd);
	setup_memwin(adap);
	if (cxgb_up(adap))
		return PCI_ERS_RESULT_DISCONNECT;
	return PCI_ERS_RESULT_RECOVERED;
}

static void eeh_resume(struct pci_dev *pdev)
{
	int i;
	struct adapter *adap = pci_get_drvdata(pdev);

	if (!adap)
		return;

	rtnl_lock();
	for_each_port(adap, i) {
		struct net_device *dev = adap->port[i];

		if (netif_running(dev)) {
			link_start(dev);
			cxgb_set_rxmode(dev);
		}
		netif_device_attach(dev);
	}
	rtnl_unlock();
}

static const struct pci_error_handlers cxgb4_eeh = {
	.error_detected = eeh_err_detected,
	.slot_reset     = eeh_slot_reset,
	.resume         = eeh_resume,
};

static inline bool is_x_10g_port(const struct link_config *lc)
{
	return (lc->supported & FW_PORT_CAP_SPEED_10G) != 0 ||
	       (lc->supported & FW_PORT_CAP_SPEED_40G) != 0;
}

static inline void init_rspq(struct adapter *adap, struct sge_rspq *q,
			     unsigned int us, unsigned int cnt,
			     unsigned int size, unsigned int iqe_size)
{
	q->adap = adap;
	cxgb4_set_rspq_intr_params(q, us, cnt);
	q->iqe_len = iqe_size;
	q->size = size;
}

/*
 * Perform default configuration of DMA queues depending on the number and type
 * of ports we found and the number of available CPUs.  Most settings can be
 * modified by the admin prior to actual use.
 */
static void cfg_queues(struct adapter *adap)
{
	struct sge *s = &adap->sge;
	int i, n10g = 0, qidx = 0;
#ifndef CONFIG_CHELSIO_T4_DCB
	int q10g = 0;
#endif
	int ciq_size;

	for_each_port(adap, i)
		n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
#ifdef CONFIG_CHELSIO_T4_DCB
	/* For Data Center Bridging support we need to be able to support up
	 * to 8 Traffic Priorities; each of which will be assigned to its
	 * own TX Queue in order to prevent Head-Of-Line Blocking.
	 */
	if (adap->params.nports * 8 > MAX_ETH_QSETS) {
		dev_err(adap->pdev_dev, "MAX_ETH_QSETS=%d < %d!\n",
			MAX_ETH_QSETS, adap->params.nports * 8);
		BUG_ON(1);
	}

	for_each_port(adap, i) {
		struct port_info *pi = adap2pinfo(adap, i);

		pi->first_qset = qidx;
		pi->nqsets = 8;
		qidx += pi->nqsets;
	}
#else /* !CONFIG_CHELSIO_T4_DCB */
	/*
	 * We default to 1 queue per non-10G port and up to # of cores queues
	 * per 10G port.
	 */
	if (n10g)
		q10g = (MAX_ETH_QSETS - (adap->params.nports - n10g)) / n10g;
	if (q10g > netif_get_num_default_rss_queues())
		q10g = netif_get_num_default_rss_queues();

	for_each_port(adap, i) {
		struct port_info *pi = adap2pinfo(adap, i);

		pi->first_qset = qidx;
		pi->nqsets = is_x_10g_port(&pi->link_cfg) ? q10g : 1;
		qidx += pi->nqsets;
	}
#endif /* !CONFIG_CHELSIO_T4_DCB */

	s->ethqsets = qidx;
	s->max_ethqsets = qidx;   /* MSI-X may lower it later */

	if (is_offload(adap)) {
		/*
		 * For offload we use 1 queue/channel if all ports are up to 1G,
		 * otherwise we divide all available queues amongst the channels
		 * capped by the number of available cores.
		 */
		if (n10g) {
			i = min_t(int, ARRAY_SIZE(s->ofldrxq),
				  num_online_cpus());
			s->ofldqsets = roundup(i, adap->params.nports);
		} else
			s->ofldqsets = adap->params.nports;
		/* For RDMA one Rx queue per channel suffices */
		s->rdmaqs = adap->params.nports;
		/* Try and allow at least 1 CIQ per cpu rounding down
		 * to the number of ports, with a minimum of 1 per port.
		 * A 2 port card in a 6 cpu system: 6 CIQs, 3 / port.
		 * A 4 port card in a 6 cpu system: 4 CIQs, 1 / port.
		 * A 4 port card in a 2 cpu system: 4 CIQs, 1 / port.
		 */
		s->rdmaciqs = min_t(int, MAX_RDMA_CIQS, num_online_cpus());
		s->rdmaciqs = (s->rdmaciqs / adap->params.nports) *
				adap->params.nports;
		s->rdmaciqs = max_t(int, s->rdmaciqs, adap->params.nports);
	}

	for (i = 0; i < ARRAY_SIZE(s->ethrxq); i++) {
		struct sge_eth_rxq *r = &s->ethrxq[i];

		init_rspq(adap, &r->rspq, 5, 10, 1024, 64);
		r->fl.size = 72;
	}

	for (i = 0; i < ARRAY_SIZE(s->ethtxq); i++)
		s->ethtxq[i].q.size = 1024;

	for (i = 0; i < ARRAY_SIZE(s->ctrlq); i++)
		s->ctrlq[i].q.size = 512;

	for (i = 0; i < ARRAY_SIZE(s->ofldtxq); i++)
		s->ofldtxq[i].q.size = 1024;

	for (i = 0; i < ARRAY_SIZE(s->ofldrxq); i++) {
		struct sge_ofld_rxq *r = &s->ofldrxq[i];

		init_rspq(adap, &r->rspq, 5, 1, 1024, 64);
		r->rspq.uld = CXGB4_ULD_ISCSI;
		r->fl.size = 72;
	}

	for (i = 0; i < ARRAY_SIZE(s->rdmarxq); i++) {
		struct sge_ofld_rxq *r = &s->rdmarxq[i];

		init_rspq(adap, &r->rspq, 5, 1, 511, 64);
		r->rspq.uld = CXGB4_ULD_RDMA;
		r->fl.size = 72;
	}

	ciq_size = 64 + adap->vres.cq.size + adap->tids.nftids;
	if (ciq_size > SGE_MAX_IQ_SIZE) {
		CH_WARN(adap, "CIQ size too small for available IQs\n");
		ciq_size = SGE_MAX_IQ_SIZE;
	}

	for (i = 0; i < ARRAY_SIZE(s->rdmaciq); i++) {
		struct sge_ofld_rxq *r = &s->rdmaciq[i];

		init_rspq(adap, &r->rspq, 5, 1, ciq_size, 64);
		r->rspq.uld = CXGB4_ULD_RDMA;
	}

	init_rspq(adap, &s->fw_evtq, 0, 1, 1024, 64);
	init_rspq(adap, &s->intrq, 0, 1, 2 * MAX_INGQ, 64);
}

/*
 * Reduce the number of Ethernet queues across all ports to at most n.
 * n provides at least one queue per port.
 */
static void reduce_ethqs(struct adapter *adap, int n)
{
	int i;
	struct port_info *pi;

	while (n < adap->sge.ethqsets)
		for_each_port(adap, i) {
			pi = adap2pinfo(adap, i);
			if (pi->nqsets > 1) {
				pi->nqsets--;
				adap->sge.ethqsets--;
				if (adap->sge.ethqsets <= n)
					break;
			}
		}

	n = 0;
	for_each_port(adap, i) {
		pi = adap2pinfo(adap, i);
		pi->first_qset = n;
		n += pi->nqsets;
	}
}

/* 2 MSI-X vectors needed for the FW queue and non-data interrupts */
#define EXTRA_VECS 2

static int enable_msix(struct adapter *adap)
{
	int ofld_need = 0;
	int i, want, need, allocated;
	struct sge *s = &adap->sge;
	unsigned int nchan = adap->params.nports;
	struct msix_entry *entries;

	entries = kmalloc(sizeof(*entries) * (MAX_INGQ + 1),
			  GFP_KERNEL);
	if (!entries)
		return -ENOMEM;

	for (i = 0; i < MAX_INGQ + 1; ++i)
		entries[i].entry = i;

	want = s->max_ethqsets + EXTRA_VECS;
	if (is_offload(adap)) {
		want += s->rdmaqs + s->rdmaciqs + s->ofldqsets;
		/* need nchan for each possible ULD */
		ofld_need = 3 * nchan;
	}
#ifdef CONFIG_CHELSIO_T4_DCB
	/* For Data Center Bridging we need 8 Ethernet TX Priority Queues for
	 * each port.
	 */
	need = 8 * adap->params.nports + EXTRA_VECS + ofld_need;
#else
	need = adap->params.nports + EXTRA_VECS + ofld_need;
#endif
	allocated = pci_enable_msix_range(adap->pdev, entries, need, want);
	if (allocated < 0) {
		dev_info(adap->pdev_dev, "not enough MSI-X vectors left,"
			 " not using MSI-X\n");
		kfree(entries);
		return allocated;
	}

	/* Distribute available vectors to the various queue groups.
	 * Every group gets its minimum requirement and NIC gets top
	 * priority for leftovers.
	 */
	i = allocated - EXTRA_VECS - ofld_need;
	if (i < s->max_ethqsets) {
		s->max_ethqsets = i;
		if (i < s->ethqsets)
			reduce_ethqs(adap, i);
	}
	if (is_offload(adap)) {
		if (allocated < want) {
			s->rdmaqs = nchan;
			s->rdmaciqs = nchan;
		}

		/* leftovers go to OFLD */
		i = allocated - EXTRA_VECS - s->max_ethqsets -
		    s->rdmaqs - s->rdmaciqs;
		s->ofldqsets = (i / nchan) * nchan;  /* round down */
	}
	for (i = 0; i < allocated; ++i)
		adap->msix_info[i].vec = entries[i].vector;
	dev_info(adap->pdev_dev, "%d MSI-X vectors allocated, "
		 "nic %d iscsi %d rdma cpl %d rdma ciq %d\n",
		 allocated, s->max_ethqsets, s->ofldqsets, s->rdmaqs,
		 s->rdmaciqs);

	kfree(entries);
	return 0;
}

#undef EXTRA_VECS

static int init_rss(struct adapter *adap)
{
	unsigned int i;
	int err;

	err = t4_init_rss_mode(adap, adap->mbox);
	if (err)
		return err;

	for_each_port(adap, i) {
		struct port_info *pi = adap2pinfo(adap, i);

		pi->rss = kcalloc(pi->rss_size, sizeof(u16), GFP_KERNEL);
		if (!pi->rss)
			return -ENOMEM;
	}
	return 0;
}

static void print_port_info(const struct net_device *dev)
{
	char buf[80];
	char *bufp = buf;
	const char *spd = "";
	const struct port_info *pi = netdev_priv(dev);
	const struct adapter *adap = pi->adapter;

	if (adap->params.pci.speed == PCI_EXP_LNKSTA_CLS_2_5GB)
		spd = " 2.5 GT/s";
	else if (adap->params.pci.speed == PCI_EXP_LNKSTA_CLS_5_0GB)
		spd = " 5 GT/s";
	else if (adap->params.pci.speed == PCI_EXP_LNKSTA_CLS_8_0GB)
		spd = " 8 GT/s";

	if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_100M)
		bufp += sprintf(bufp, "100/");
	if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_1G)
		bufp += sprintf(bufp, "1000/");
	if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_10G)
		bufp += sprintf(bufp, "10G/");
	if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_40G)
		bufp += sprintf(bufp, "40G/");
	if (bufp != buf)
		--bufp;
	sprintf(bufp, "BASE-%s", t4_get_port_type_description(pi->port_type));

	netdev_info(dev, "Chelsio %s rev %d %s %sNIC PCIe x%d%s%s\n",
		    adap->params.vpd.id,
		    CHELSIO_CHIP_RELEASE(adap->params.chip), buf,
		    is_offload(adap) ? "R" : "", adap->params.pci.width, spd,
		    (adap->flags & USING_MSIX) ? " MSI-X" :
		    (adap->flags & USING_MSI) ? " MSI" : "");
	netdev_info(dev, "S/N: %s, P/N: %s\n",
		    adap->params.vpd.sn, adap->params.vpd.pn);
}

static void enable_pcie_relaxed_ordering(struct pci_dev *dev)
{
	pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_RELAX_EN);
}

/*
 * Free the following resources:
 * - memory used for tables
 * - MSI/MSI-X
 * - net devices
 * - resources FW is holding for us
 */
static void free_some_resources(struct adapter *adapter)
{
	unsigned int i;

	t4_free_mem(adapter->l2t);
	t4_free_mem(adapter->tids.tid_tab);
	kfree(adapter->sge.egr_map);
	kfree(adapter->sge.ingr_map);
	kfree(adapter->sge.starving_fl);
	kfree(adapter->sge.txq_maperr);
#ifdef CONFIG_DEBUG_FS
	kfree(adapter->sge.blocked_fl);
#endif
	disable_msi(adapter);

	for_each_port(adapter, i)
		if (adapter->port[i]) {
			struct port_info *pi = adap2pinfo(adapter, i);

			if (pi->viid != 0)
				t4_free_vi(adapter, adapter->mbox, adapter->pf,
					   0, pi->viid);
			kfree(adap2pinfo(adapter, i)->rss);
			free_netdev(adapter->port[i]);
		}
	if (adapter->flags & FW_OK)
		t4_fw_bye(adapter, adapter->pf);
}

#define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
#define VLAN_FEAT (NETIF_F_SG | NETIF_F_IP_CSUM | TSO_FLAGS | \
		   NETIF_F_IPV6_CSUM | NETIF_F_HIGHDMA)
#define SEGMENT_SIZE 128

static int get_chip_type(struct pci_dev *pdev, u32 pl_rev)
{
	u16 device_id;

	/* Retrieve adapter's device ID */
	pci_read_config_word(pdev, PCI_DEVICE_ID, &device_id);

	switch (device_id >> 12) {
	case CHELSIO_T4:
		return CHELSIO_CHIP_CODE(CHELSIO_T4, pl_rev);
	case CHELSIO_T5:
		return CHELSIO_CHIP_CODE(CHELSIO_T5, pl_rev);
	case CHELSIO_T6:
		return CHELSIO_CHIP_CODE(CHELSIO_T6, pl_rev);
	default:
		dev_err(&pdev->dev, "Device %d is not supported\n",
			device_id);
	}
	return -EINVAL;
}

static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
{
	int func, i, err, s_qpp, qpp, num_seg;
	struct port_info *pi;
	bool highdma = false;
	struct adapter *adapter = NULL;
	void __iomem *regs;
	u32 whoami, pl_rev;
	enum chip_type chip;

	printk_once(KERN_INFO "%s - version %s\n", DRV_DESC, DRV_VERSION);

	err = pci_request_regions(pdev, KBUILD_MODNAME);
	if (err) {
		/* Just info, some other driver may have claimed the device. */
		dev_info(&pdev->dev, "cannot obtain PCI resources\n");
		return err;
	}

	err = pci_enable_device(pdev);
	if (err) {
		dev_err(&pdev->dev, "cannot enable PCI device\n");
		goto out_release_regions;
	}

	regs = pci_ioremap_bar(pdev, 0);
	if (!regs) {
		dev_err(&pdev->dev, "cannot map device registers\n");
		err = -ENOMEM;
		goto out_disable_device;
	}

	err = t4_wait_dev_ready(regs);
	if (err < 0)
		goto out_unmap_bar0;

	/* We control everything through one PF */
	whoami = readl(regs + PL_WHOAMI_A);
	pl_rev = REV_G(readl(regs + PL_REV_A));
	chip = get_chip_type(pdev, pl_rev);
	func = CHELSIO_CHIP_VERSION(chip) <= CHELSIO_T5 ?
		SOURCEPF_G(whoami) : T6_SOURCEPF_G(whoami);
	if (func != ent->driver_data) {
		iounmap(regs);
		pci_disable_device(pdev);
		pci_save_state(pdev);        /* to restore SR-IOV later */
		goto sriov;
	}

	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
		highdma = true;
		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
		if (err) {
			dev_err(&pdev->dev, "unable to obtain 64-bit DMA for "
				"coherent allocations\n");
			goto out_unmap_bar0;
		}
	} else {
		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
		if (err) {
			dev_err(&pdev->dev, "no usable DMA configuration\n");
			goto out_unmap_bar0;
		}
	}

	pci_enable_pcie_error_reporting(pdev);
	enable_pcie_relaxed_ordering(pdev);
	pci_set_master(pdev);
	pci_save_state(pdev);

	adapter = kzalloc(sizeof(*adapter), GFP_KERNEL);
	if (!adapter) {
		err = -ENOMEM;
		goto out_unmap_bar0;
	}

	adapter->workq = create_singlethread_workqueue("cxgb4");
	if (!adapter->workq) {
		err = -ENOMEM;
		goto out_free_adapter;
	}

	/* PCI device has been enabled */
	adapter->flags |= DEV_ENABLED;

	adapter->regs = regs;
	adapter->pdev = pdev;
	adapter->pdev_dev = &pdev->dev;
	adapter->mbox = func;
	adapter->pf = func;
	adapter->msg_enable = dflt_msg_enable;
	memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map));

	spin_lock_init(&adapter->stats_lock);
	spin_lock_init(&adapter->tid_release_lock);
	spin_lock_init(&adapter->win0_lock);

	INIT_WORK(&adapter->tid_release_task, process_tid_release_list);
	INIT_WORK(&adapter->db_full_task, process_db_full);
	INIT_WORK(&adapter->db_drop_task, process_db_drop);

	err = t4_prep_adapter(adapter);
	if (err)
		goto out_free_adapter;


	if (!is_t4(adapter->params.chip)) {
		s_qpp = (QUEUESPERPAGEPF0_S +
			(QUEUESPERPAGEPF1_S - QUEUESPERPAGEPF0_S) *
			adapter->pf);
		qpp = 1 << QUEUESPERPAGEPF0_G(t4_read_reg(adapter,
		      SGE_EGRESS_QUEUES_PER_PAGE_PF_A) >> s_qpp);
		num_seg = PAGE_SIZE / SEGMENT_SIZE;

		/* Each segment size is 128B. Write coalescing is enabled only
		 * when SGE_EGRESS_QUEUES_PER_PAGE_PF reg value for the
		 * queue is less no of segments that can be accommodated in
		 * a page size.
		 */
		if (qpp > num_seg) {
			dev_err(&pdev->dev,
				"Incorrect number of egress queues per page\n");
			err = -EINVAL;
			goto out_free_adapter;
		}
		adapter->bar2 = ioremap_wc(pci_resource_start(pdev, 2),
		pci_resource_len(pdev, 2));
		if (!adapter->bar2) {
			dev_err(&pdev->dev, "cannot map device bar2 region\n");
			err = -ENOMEM;
			goto out_free_adapter;
		}
	}

	setup_memwin(adapter);
	err = adap_init0(adapter);
#ifdef CONFIG_DEBUG_FS
	bitmap_zero(adapter->sge.blocked_fl, adapter->sge.egr_sz);
#endif
	setup_memwin_rdma(adapter);
	if (err)
		goto out_unmap_bar;

	/* configure SGE_STAT_CFG_A to read WC stats */
	if (!is_t4(adapter->params.chip))
		t4_write_reg(adapter, SGE_STAT_CFG_A,
			     STATSOURCE_T5_V(7) | STATMODE_V(0));

	for_each_port(adapter, i) {
		struct net_device *netdev;

		netdev = alloc_etherdev_mq(sizeof(struct port_info),
					   MAX_ETH_QSETS);
		if (!netdev) {
			err = -ENOMEM;
			goto out_free_dev;
		}

		SET_NETDEV_DEV(netdev, &pdev->dev);

		adapter->port[i] = netdev;
		pi = netdev_priv(netdev);
		pi->adapter = adapter;
		pi->xact_addr_filt = -1;
		pi->port_id = i;
		netdev->irq = pdev->irq;

		netdev->hw_features = NETIF_F_SG | TSO_FLAGS |
			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
			NETIF_F_RXCSUM | NETIF_F_RXHASH |
			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
		if (highdma)
			netdev->hw_features |= NETIF_F_HIGHDMA;
		netdev->features |= netdev->hw_features;
		netdev->vlan_features = netdev->features & VLAN_FEAT;

		netdev->priv_flags |= IFF_UNICAST_FLT;

		netdev->netdev_ops = &cxgb4_netdev_ops;
#ifdef CONFIG_CHELSIO_T4_DCB
		netdev->dcbnl_ops = &cxgb4_dcb_ops;
		cxgb4_dcb_state_init(netdev);
#endif
		cxgb4_set_ethtool_ops(netdev);
	}

	pci_set_drvdata(pdev, adapter);

	if (adapter->flags & FW_OK) {
		err = t4_port_init(adapter, func, func, 0);
		if (err)
			goto out_free_dev;
	} else if (adapter->params.nports == 1) {
		/* If we don't have a connection to the firmware -- possibly
		 * because of an error -- grab the raw VPD parameters so we
		 * can set the proper MAC Address on the debug network
		 * interface that we've created.
		 */
		u8 hw_addr[ETH_ALEN];
		u8 *na = adapter->params.vpd.na;

		err = t4_get_raw_vpd_params(adapter, &adapter->params.vpd);
		if (!err) {
			for (i = 0; i < ETH_ALEN; i++)
				hw_addr[i] = (hex2val(na[2 * i + 0]) * 16 +
					      hex2val(na[2 * i + 1]));
			t4_set_hw_addr(adapter, 0, hw_addr);
		}
	}

	/* Configure queues and allocate tables now, they can be needed as
	 * soon as the first register_netdev completes.
	 */
	cfg_queues(adapter);

	adapter->l2t = t4_init_l2t(adapter->l2t_start, adapter->l2t_end);
	if (!adapter->l2t) {
		/* We tolerate a lack of L2T, giving up some functionality */
		dev_warn(&pdev->dev, "could not allocate L2T, continuing\n");
		adapter->params.offload = 0;
	}

#if IS_ENABLED(CONFIG_IPV6)
	adapter->clipt = t4_init_clip_tbl(adapter->clipt_start,
					  adapter->clipt_end);
	if (!adapter->clipt) {
		/* We tolerate a lack of clip_table, giving up
		 * some functionality
		 */
		dev_warn(&pdev->dev,
			 "could not allocate Clip table, continuing\n");
		adapter->params.offload = 0;
	}
#endif
	if (is_offload(adapter) && tid_init(&adapter->tids) < 0) {
		dev_warn(&pdev->dev, "could not allocate TID table, "
			 "continuing\n");
		adapter->params.offload = 0;
	}

	if (is_offload(adapter)) {
		if (t4_read_reg(adapter, LE_DB_CONFIG_A) & HASHEN_F) {
			u32 hash_base, hash_reg;

			if (chip <= CHELSIO_T5) {
				hash_reg = LE_DB_TID_HASHBASE_A;
				hash_base = t4_read_reg(adapter, hash_reg);
				adapter->tids.hash_base = hash_base / 4;
			} else {
				hash_reg = T6_LE_DB_HASH_TID_BASE_A;
				hash_base = t4_read_reg(adapter, hash_reg);
				adapter->tids.hash_base = hash_base;
			}
		}
	}

	/* See what interrupts we'll be using */
	if (msi > 1 && enable_msix(adapter) == 0)
		adapter->flags |= USING_MSIX;
	else if (msi > 0 && pci_enable_msi(pdev) == 0)
		adapter->flags |= USING_MSI;

	err = init_rss(adapter);
	if (err)
		goto out_free_dev;

	/*
	 * The card is now ready to go.  If any errors occur during device
	 * registration we do not fail the whole card but rather proceed only
	 * with the ports we manage to register successfully.  However we must
	 * register at least one net device.
	 */
	for_each_port(adapter, i) {
		pi = adap2pinfo(adapter, i);
		netif_set_real_num_tx_queues(adapter->port[i], pi->nqsets);
		netif_set_real_num_rx_queues(adapter->port[i], pi->nqsets);

		err = register_netdev(adapter->port[i]);
		if (err)
			break;
		adapter->chan_map[pi->tx_chan] = i;
		print_port_info(adapter->port[i]);
	}
	if (i == 0) {
		dev_err(&pdev->dev, "could not register any net devices\n");
		goto out_free_dev;
	}
	if (err) {
		dev_warn(&pdev->dev, "only %d net devices registered\n", i);
		err = 0;
	}

	if (cxgb4_debugfs_root) {
		adapter->debugfs_root = debugfs_create_dir(pci_name(pdev),
							   cxgb4_debugfs_root);
		setup_debugfs(adapter);
	}

	/* PCIe EEH recovery on powerpc platforms needs fundamental reset */
	pdev->needs_freset = 1;

	if (is_offload(adapter))
		attach_ulds(adapter);

sriov:
#ifdef CONFIG_PCI_IOV
	if (func < ARRAY_SIZE(num_vf) && num_vf[func] > 0)
		if (pci_enable_sriov(pdev, num_vf[func]) == 0)
			dev_info(&pdev->dev,
				 "instantiated %u virtual functions\n",
				 num_vf[func]);
#endif
	return 0;

 out_free_dev:
	free_some_resources(adapter);
 out_unmap_bar:
	if (!is_t4(adapter->params.chip))
		iounmap(adapter->bar2);
 out_free_adapter:
	if (adapter->workq)
		destroy_workqueue(adapter->workq);

	kfree(adapter);
 out_unmap_bar0:
	iounmap(regs);
 out_disable_device:
	pci_disable_pcie_error_reporting(pdev);
	pci_disable_device(pdev);
 out_release_regions:
	pci_release_regions(pdev);
	return err;
}

static void remove_one(struct pci_dev *pdev)
{
	struct adapter *adapter = pci_get_drvdata(pdev);

#ifdef CONFIG_PCI_IOV
	pci_disable_sriov(pdev);

#endif

	if (adapter) {
		int i;

		/* Tear down per-adapter Work Queue first since it can contain
		 * references to our adapter data structure.
		 */
		destroy_workqueue(adapter->workq);

		if (is_offload(adapter))
			detach_ulds(adapter);

		disable_interrupts(adapter);

		for_each_port(adapter, i)
			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
				unregister_netdev(adapter->port[i]);

		debugfs_remove_recursive(adapter->debugfs_root);

		/* If we allocated filters, free up state associated with any
		 * valid filters ...
		 */
		if (adapter->tids.ftid_tab) {
			struct filter_entry *f = &adapter->tids.ftid_tab[0];
			for (i = 0; i < (adapter->tids.nftids +
					adapter->tids.nsftids); i++, f++)
				if (f->valid)
					clear_filter(adapter, f);
		}

		if (adapter->flags & FULL_INIT_DONE)
			cxgb_down(adapter);

		free_some_resources(adapter);
#if IS_ENABLED(CONFIG_IPV6)
		t4_cleanup_clip_tbl(adapter);
#endif
		iounmap(adapter->regs);
		if (!is_t4(adapter->params.chip))
			iounmap(adapter->bar2);
		pci_disable_pcie_error_reporting(pdev);
		if ((adapter->flags & DEV_ENABLED)) {
			pci_disable_device(pdev);
			adapter->flags &= ~DEV_ENABLED;
		}
		pci_release_regions(pdev);
		synchronize_rcu();
		kfree(adapter);
	} else
		pci_release_regions(pdev);
}

static struct pci_driver cxgb4_driver = {
	.name     = KBUILD_MODNAME,
	.id_table = cxgb4_pci_tbl,
	.probe    = init_one,
	.remove   = remove_one,
	.shutdown = remove_one,
	.err_handler = &cxgb4_eeh,
};

static int __init cxgb4_init_module(void)
{
	int ret;

	/* Debugfs support is optional, just warn if this fails */
	cxgb4_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL);
	if (!cxgb4_debugfs_root)
		pr_warn("could not create debugfs entry, continuing\n");

	ret = pci_register_driver(&cxgb4_driver);
	if (ret < 0)
		debugfs_remove(cxgb4_debugfs_root);

#if IS_ENABLED(CONFIG_IPV6)
	if (!inet6addr_registered) {
		register_inet6addr_notifier(&cxgb4_inet6addr_notifier);
		inet6addr_registered = true;
	}
#endif

	return ret;
}

static void __exit cxgb4_cleanup_module(void)
{
#if IS_ENABLED(CONFIG_IPV6)
	if (inet6addr_registered) {
		unregister_inet6addr_notifier(&cxgb4_inet6addr_notifier);
		inet6addr_registered = false;
	}
#endif
	pci_unregister_driver(&cxgb4_driver);
	debugfs_remove(cxgb4_debugfs_root);  /* NULL ok */
}

module_init(cxgb4_init_module);
module_exit(cxgb4_cleanup_module);