lock.c 158 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 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304
/******************************************************************************
*******************************************************************************
**
**  Copyright (C) 2005-2010 Red Hat, Inc.  All rights reserved.
**
**  This copyrighted material is made available to anyone wishing to use,
**  modify, copy, or redistribute it subject to the terms and conditions
**  of the GNU General Public License v.2.
**
*******************************************************************************
******************************************************************************/

/* Central locking logic has four stages:

   dlm_lock()
   dlm_unlock()

   request_lock(ls, lkb)
   convert_lock(ls, lkb)
   unlock_lock(ls, lkb)
   cancel_lock(ls, lkb)

   _request_lock(r, lkb)
   _convert_lock(r, lkb)
   _unlock_lock(r, lkb)
   _cancel_lock(r, lkb)

   do_request(r, lkb)
   do_convert(r, lkb)
   do_unlock(r, lkb)
   do_cancel(r, lkb)

   Stage 1 (lock, unlock) is mainly about checking input args and
   splitting into one of the four main operations:

       dlm_lock          = request_lock
       dlm_lock+CONVERT  = convert_lock
       dlm_unlock        = unlock_lock
       dlm_unlock+CANCEL = cancel_lock

   Stage 2, xxxx_lock(), just finds and locks the relevant rsb which is
   provided to the next stage.

   Stage 3, _xxxx_lock(), determines if the operation is local or remote.
   When remote, it calls send_xxxx(), when local it calls do_xxxx().

   Stage 4, do_xxxx(), is the guts of the operation.  It manipulates the
   given rsb and lkb and queues callbacks.

   For remote operations, send_xxxx() results in the corresponding do_xxxx()
   function being executed on the remote node.  The connecting send/receive
   calls on local (L) and remote (R) nodes:

   L: send_xxxx()              ->  R: receive_xxxx()
                                   R: do_xxxx()
   L: receive_xxxx_reply()     <-  R: send_xxxx_reply()
*/
#include <linux/types.h>
#include <linux/rbtree.h>
#include <linux/slab.h>
#include "dlm_internal.h"
#include <linux/dlm_device.h>
#include "memory.h"
#include "lowcomms.h"
#include "requestqueue.h"
#include "util.h"
#include "dir.h"
#include "member.h"
#include "lockspace.h"
#include "ast.h"
#include "lock.h"
#include "rcom.h"
#include "recover.h"
#include "lvb_table.h"
#include "user.h"
#include "config.h"

static int send_request(struct dlm_rsb *r, struct dlm_lkb *lkb);
static int send_convert(struct dlm_rsb *r, struct dlm_lkb *lkb);
static int send_unlock(struct dlm_rsb *r, struct dlm_lkb *lkb);
static int send_cancel(struct dlm_rsb *r, struct dlm_lkb *lkb);
static int send_grant(struct dlm_rsb *r, struct dlm_lkb *lkb);
static int send_bast(struct dlm_rsb *r, struct dlm_lkb *lkb, int mode);
static int send_lookup(struct dlm_rsb *r, struct dlm_lkb *lkb);
static int send_remove(struct dlm_rsb *r);
static int _request_lock(struct dlm_rsb *r, struct dlm_lkb *lkb);
static int _cancel_lock(struct dlm_rsb *r, struct dlm_lkb *lkb);
static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb,
				    struct dlm_message *ms);
static int receive_extralen(struct dlm_message *ms);
static void do_purge(struct dlm_ls *ls, int nodeid, int pid);
static void del_timeout(struct dlm_lkb *lkb);
static void toss_rsb(struct kref *kref);

/*
 * Lock compatibilty matrix - thanks Steve
 * UN = Unlocked state. Not really a state, used as a flag
 * PD = Padding. Used to make the matrix a nice power of two in size
 * Other states are the same as the VMS DLM.
 * Usage: matrix[grmode+1][rqmode+1]  (although m[rq+1][gr+1] is the same)
 */

static const int __dlm_compat_matrix[8][8] = {
      /* UN NL CR CW PR PW EX PD */
        {1, 1, 1, 1, 1, 1, 1, 0},       /* UN */
        {1, 1, 1, 1, 1, 1, 1, 0},       /* NL */
        {1, 1, 1, 1, 1, 1, 0, 0},       /* CR */
        {1, 1, 1, 1, 0, 0, 0, 0},       /* CW */
        {1, 1, 1, 0, 1, 0, 0, 0},       /* PR */
        {1, 1, 1, 0, 0, 0, 0, 0},       /* PW */
        {1, 1, 0, 0, 0, 0, 0, 0},       /* EX */
        {0, 0, 0, 0, 0, 0, 0, 0}        /* PD */
};

/*
 * This defines the direction of transfer of LVB data.
 * Granted mode is the row; requested mode is the column.
 * Usage: matrix[grmode+1][rqmode+1]
 * 1 = LVB is returned to the caller
 * 0 = LVB is written to the resource
 * -1 = nothing happens to the LVB
 */

const int dlm_lvb_operations[8][8] = {
        /* UN   NL  CR  CW  PR  PW  EX  PD*/
        {  -1,  1,  1,  1,  1,  1,  1, -1 }, /* UN */
        {  -1,  1,  1,  1,  1,  1,  1,  0 }, /* NL */
        {  -1, -1,  1,  1,  1,  1,  1,  0 }, /* CR */
        {  -1, -1, -1,  1,  1,  1,  1,  0 }, /* CW */
        {  -1, -1, -1, -1,  1,  1,  1,  0 }, /* PR */
        {  -1,  0,  0,  0,  0,  0,  1,  0 }, /* PW */
        {  -1,  0,  0,  0,  0,  0,  0,  0 }, /* EX */
        {  -1,  0,  0,  0,  0,  0,  0,  0 }  /* PD */
};

#define modes_compat(gr, rq) \
	__dlm_compat_matrix[(gr)->lkb_grmode + 1][(rq)->lkb_rqmode + 1]

int dlm_modes_compat(int mode1, int mode2)
{
	return __dlm_compat_matrix[mode1 + 1][mode2 + 1];
}

/*
 * Compatibility matrix for conversions with QUECVT set.
 * Granted mode is the row; requested mode is the column.
 * Usage: matrix[grmode+1][rqmode+1]
 */

static const int __quecvt_compat_matrix[8][8] = {
      /* UN NL CR CW PR PW EX PD */
        {0, 0, 0, 0, 0, 0, 0, 0},       /* UN */
        {0, 0, 1, 1, 1, 1, 1, 0},       /* NL */
        {0, 0, 0, 1, 1, 1, 1, 0},       /* CR */
        {0, 0, 0, 0, 1, 1, 1, 0},       /* CW */
        {0, 0, 0, 1, 0, 1, 1, 0},       /* PR */
        {0, 0, 0, 0, 0, 0, 1, 0},       /* PW */
        {0, 0, 0, 0, 0, 0, 0, 0},       /* EX */
        {0, 0, 0, 0, 0, 0, 0, 0}        /* PD */
};

void dlm_print_lkb(struct dlm_lkb *lkb)
{
	printk(KERN_ERR "lkb: nodeid %d id %x remid %x exflags %x flags %x "
	       "sts %d rq %d gr %d wait_type %d wait_nodeid %d seq %llu\n",
	       lkb->lkb_nodeid, lkb->lkb_id, lkb->lkb_remid, lkb->lkb_exflags,
	       lkb->lkb_flags, lkb->lkb_status, lkb->lkb_rqmode,
	       lkb->lkb_grmode, lkb->lkb_wait_type, lkb->lkb_wait_nodeid,
	       (unsigned long long)lkb->lkb_recover_seq);
}

static void dlm_print_rsb(struct dlm_rsb *r)
{
	printk(KERN_ERR "rsb: nodeid %d master %d dir %d flags %lx first %x "
	       "rlc %d name %s\n",
	       r->res_nodeid, r->res_master_nodeid, r->res_dir_nodeid,
	       r->res_flags, r->res_first_lkid, r->res_recover_locks_count,
	       r->res_name);
}

void dlm_dump_rsb(struct dlm_rsb *r)
{
	struct dlm_lkb *lkb;

	dlm_print_rsb(r);

	printk(KERN_ERR "rsb: root_list empty %d recover_list empty %d\n",
	       list_empty(&r->res_root_list), list_empty(&r->res_recover_list));
	printk(KERN_ERR "rsb lookup list\n");
	list_for_each_entry(lkb, &r->res_lookup, lkb_rsb_lookup)
		dlm_print_lkb(lkb);
	printk(KERN_ERR "rsb grant queue:\n");
	list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue)
		dlm_print_lkb(lkb);
	printk(KERN_ERR "rsb convert queue:\n");
	list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue)
		dlm_print_lkb(lkb);
	printk(KERN_ERR "rsb wait queue:\n");
	list_for_each_entry(lkb, &r->res_waitqueue, lkb_statequeue)
		dlm_print_lkb(lkb);
}

/* Threads cannot use the lockspace while it's being recovered */

static inline void dlm_lock_recovery(struct dlm_ls *ls)
{
	down_read(&ls->ls_in_recovery);
}

void dlm_unlock_recovery(struct dlm_ls *ls)
{
	up_read(&ls->ls_in_recovery);
}

int dlm_lock_recovery_try(struct dlm_ls *ls)
{
	return down_read_trylock(&ls->ls_in_recovery);
}

static inline int can_be_queued(struct dlm_lkb *lkb)
{
	return !(lkb->lkb_exflags & DLM_LKF_NOQUEUE);
}

static inline int force_blocking_asts(struct dlm_lkb *lkb)
{
	return (lkb->lkb_exflags & DLM_LKF_NOQUEUEBAST);
}

static inline int is_demoted(struct dlm_lkb *lkb)
{
	return (lkb->lkb_sbflags & DLM_SBF_DEMOTED);
}

static inline int is_altmode(struct dlm_lkb *lkb)
{
	return (lkb->lkb_sbflags & DLM_SBF_ALTMODE);
}

static inline int is_granted(struct dlm_lkb *lkb)
{
	return (lkb->lkb_status == DLM_LKSTS_GRANTED);
}

static inline int is_remote(struct dlm_rsb *r)
{
	DLM_ASSERT(r->res_nodeid >= 0, dlm_print_rsb(r););
	return !!r->res_nodeid;
}

static inline int is_process_copy(struct dlm_lkb *lkb)
{
	return (lkb->lkb_nodeid && !(lkb->lkb_flags & DLM_IFL_MSTCPY));
}

static inline int is_master_copy(struct dlm_lkb *lkb)
{
	return (lkb->lkb_flags & DLM_IFL_MSTCPY) ? 1 : 0;
}

static inline int middle_conversion(struct dlm_lkb *lkb)
{
	if ((lkb->lkb_grmode==DLM_LOCK_PR && lkb->lkb_rqmode==DLM_LOCK_CW) ||
	    (lkb->lkb_rqmode==DLM_LOCK_PR && lkb->lkb_grmode==DLM_LOCK_CW))
		return 1;
	return 0;
}

static inline int down_conversion(struct dlm_lkb *lkb)
{
	return (!middle_conversion(lkb) && lkb->lkb_rqmode < lkb->lkb_grmode);
}

static inline int is_overlap_unlock(struct dlm_lkb *lkb)
{
	return lkb->lkb_flags & DLM_IFL_OVERLAP_UNLOCK;
}

static inline int is_overlap_cancel(struct dlm_lkb *lkb)
{
	return lkb->lkb_flags & DLM_IFL_OVERLAP_CANCEL;
}

static inline int is_overlap(struct dlm_lkb *lkb)
{
	return (lkb->lkb_flags & (DLM_IFL_OVERLAP_UNLOCK |
				  DLM_IFL_OVERLAP_CANCEL));
}

static void queue_cast(struct dlm_rsb *r, struct dlm_lkb *lkb, int rv)
{
	if (is_master_copy(lkb))
		return;

	del_timeout(lkb);

	DLM_ASSERT(lkb->lkb_lksb, dlm_print_lkb(lkb););

	/* if the operation was a cancel, then return -DLM_ECANCEL, if a
	   timeout caused the cancel then return -ETIMEDOUT */
	if (rv == -DLM_ECANCEL && (lkb->lkb_flags & DLM_IFL_TIMEOUT_CANCEL)) {
		lkb->lkb_flags &= ~DLM_IFL_TIMEOUT_CANCEL;
		rv = -ETIMEDOUT;
	}

	if (rv == -DLM_ECANCEL && (lkb->lkb_flags & DLM_IFL_DEADLOCK_CANCEL)) {
		lkb->lkb_flags &= ~DLM_IFL_DEADLOCK_CANCEL;
		rv = -EDEADLK;
	}

	dlm_add_cb(lkb, DLM_CB_CAST, lkb->lkb_grmode, rv, lkb->lkb_sbflags);
}

static inline void queue_cast_overlap(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	queue_cast(r, lkb,
		   is_overlap_unlock(lkb) ? -DLM_EUNLOCK : -DLM_ECANCEL);
}

static void queue_bast(struct dlm_rsb *r, struct dlm_lkb *lkb, int rqmode)
{
	if (is_master_copy(lkb)) {
		send_bast(r, lkb, rqmode);
	} else {
		dlm_add_cb(lkb, DLM_CB_BAST, rqmode, 0, 0);
	}
}

/*
 * Basic operations on rsb's and lkb's
 */

/* This is only called to add a reference when the code already holds
   a valid reference to the rsb, so there's no need for locking. */

static inline void hold_rsb(struct dlm_rsb *r)
{
	kref_get(&r->res_ref);
}

void dlm_hold_rsb(struct dlm_rsb *r)
{
	hold_rsb(r);
}

/* When all references to the rsb are gone it's transferred to
   the tossed list for later disposal. */

static void put_rsb(struct dlm_rsb *r)
{
	struct dlm_ls *ls = r->res_ls;
	uint32_t bucket = r->res_bucket;

	spin_lock(&ls->ls_rsbtbl[bucket].lock);
	kref_put(&r->res_ref, toss_rsb);
	spin_unlock(&ls->ls_rsbtbl[bucket].lock);
}

void dlm_put_rsb(struct dlm_rsb *r)
{
	put_rsb(r);
}

static int pre_rsb_struct(struct dlm_ls *ls)
{
	struct dlm_rsb *r1, *r2;
	int count = 0;

	spin_lock(&ls->ls_new_rsb_spin);
	if (ls->ls_new_rsb_count > dlm_config.ci_new_rsb_count / 2) {
		spin_unlock(&ls->ls_new_rsb_spin);
		return 0;
	}
	spin_unlock(&ls->ls_new_rsb_spin);

	r1 = dlm_allocate_rsb(ls);
	r2 = dlm_allocate_rsb(ls);

	spin_lock(&ls->ls_new_rsb_spin);
	if (r1) {
		list_add(&r1->res_hashchain, &ls->ls_new_rsb);
		ls->ls_new_rsb_count++;
	}
	if (r2) {
		list_add(&r2->res_hashchain, &ls->ls_new_rsb);
		ls->ls_new_rsb_count++;
	}
	count = ls->ls_new_rsb_count;
	spin_unlock(&ls->ls_new_rsb_spin);

	if (!count)
		return -ENOMEM;
	return 0;
}

/* If ls->ls_new_rsb is empty, return -EAGAIN, so the caller can
   unlock any spinlocks, go back and call pre_rsb_struct again.
   Otherwise, take an rsb off the list and return it. */

static int get_rsb_struct(struct dlm_ls *ls, char *name, int len,
			  struct dlm_rsb **r_ret)
{
	struct dlm_rsb *r;
	int count;

	spin_lock(&ls->ls_new_rsb_spin);
	if (list_empty(&ls->ls_new_rsb)) {
		count = ls->ls_new_rsb_count;
		spin_unlock(&ls->ls_new_rsb_spin);
		log_debug(ls, "find_rsb retry %d %d %s",
			  count, dlm_config.ci_new_rsb_count, name);
		return -EAGAIN;
	}

	r = list_first_entry(&ls->ls_new_rsb, struct dlm_rsb, res_hashchain);
	list_del(&r->res_hashchain);
	/* Convert the empty list_head to a NULL rb_node for tree usage: */
	memset(&r->res_hashnode, 0, sizeof(struct rb_node));
	ls->ls_new_rsb_count--;
	spin_unlock(&ls->ls_new_rsb_spin);

	r->res_ls = ls;
	r->res_length = len;
	memcpy(r->res_name, name, len);
	mutex_init(&r->res_mutex);

	INIT_LIST_HEAD(&r->res_lookup);
	INIT_LIST_HEAD(&r->res_grantqueue);
	INIT_LIST_HEAD(&r->res_convertqueue);
	INIT_LIST_HEAD(&r->res_waitqueue);
	INIT_LIST_HEAD(&r->res_root_list);
	INIT_LIST_HEAD(&r->res_recover_list);

	*r_ret = r;
	return 0;
}

static int rsb_cmp(struct dlm_rsb *r, const char *name, int nlen)
{
	char maxname[DLM_RESNAME_MAXLEN];

	memset(maxname, 0, DLM_RESNAME_MAXLEN);
	memcpy(maxname, name, nlen);
	return memcmp(r->res_name, maxname, DLM_RESNAME_MAXLEN);
}

int dlm_search_rsb_tree(struct rb_root *tree, char *name, int len,
			struct dlm_rsb **r_ret)
{
	struct rb_node *node = tree->rb_node;
	struct dlm_rsb *r;
	int rc;

	while (node) {
		r = rb_entry(node, struct dlm_rsb, res_hashnode);
		rc = rsb_cmp(r, name, len);
		if (rc < 0)
			node = node->rb_left;
		else if (rc > 0)
			node = node->rb_right;
		else
			goto found;
	}
	*r_ret = NULL;
	return -EBADR;

 found:
	*r_ret = r;
	return 0;
}

static int rsb_insert(struct dlm_rsb *rsb, struct rb_root *tree)
{
	struct rb_node **newn = &tree->rb_node;
	struct rb_node *parent = NULL;
	int rc;

	while (*newn) {
		struct dlm_rsb *cur = rb_entry(*newn, struct dlm_rsb,
					       res_hashnode);

		parent = *newn;
		rc = rsb_cmp(cur, rsb->res_name, rsb->res_length);
		if (rc < 0)
			newn = &parent->rb_left;
		else if (rc > 0)
			newn = &parent->rb_right;
		else {
			log_print("rsb_insert match");
			dlm_dump_rsb(rsb);
			dlm_dump_rsb(cur);
			return -EEXIST;
		}
	}

	rb_link_node(&rsb->res_hashnode, parent, newn);
	rb_insert_color(&rsb->res_hashnode, tree);
	return 0;
}

/*
 * Find rsb in rsbtbl and potentially create/add one
 *
 * Delaying the release of rsb's has a similar benefit to applications keeping
 * NL locks on an rsb, but without the guarantee that the cached master value
 * will still be valid when the rsb is reused.  Apps aren't always smart enough
 * to keep NL locks on an rsb that they may lock again shortly; this can lead
 * to excessive master lookups and removals if we don't delay the release.
 *
 * Searching for an rsb means looking through both the normal list and toss
 * list.  When found on the toss list the rsb is moved to the normal list with
 * ref count of 1; when found on normal list the ref count is incremented.
 *
 * rsb's on the keep list are being used locally and refcounted.
 * rsb's on the toss list are not being used locally, and are not refcounted.
 *
 * The toss list rsb's were either
 * - previously used locally but not any more (were on keep list, then
 *   moved to toss list when last refcount dropped)
 * - created and put on toss list as a directory record for a lookup
 *   (we are the dir node for the res, but are not using the res right now,
 *   but some other node is)
 *
 * The purpose of find_rsb() is to return a refcounted rsb for local use.
 * So, if the given rsb is on the toss list, it is moved to the keep list
 * before being returned.
 *
 * toss_rsb() happens when all local usage of the rsb is done, i.e. no
 * more refcounts exist, so the rsb is moved from the keep list to the
 * toss list.
 *
 * rsb's on both keep and toss lists are used for doing a name to master
 * lookups.  rsb's that are in use locally (and being refcounted) are on
 * the keep list, rsb's that are not in use locally (not refcounted) and
 * only exist for name/master lookups are on the toss list.
 *
 * rsb's on the toss list who's dir_nodeid is not local can have stale
 * name/master mappings.  So, remote requests on such rsb's can potentially
 * return with an error, which means the mapping is stale and needs to
 * be updated with a new lookup.  (The idea behind MASTER UNCERTAIN and
 * first_lkid is to keep only a single outstanding request on an rsb
 * while that rsb has a potentially stale master.)
 */

static int find_rsb_dir(struct dlm_ls *ls, char *name, int len,
			uint32_t hash, uint32_t b,
			int dir_nodeid, int from_nodeid,
			unsigned int flags, struct dlm_rsb **r_ret)
{
	struct dlm_rsb *r = NULL;
	int our_nodeid = dlm_our_nodeid();
	int from_local = 0;
	int from_other = 0;
	int from_dir = 0;
	int create = 0;
	int error;

	if (flags & R_RECEIVE_REQUEST) {
		if (from_nodeid == dir_nodeid)
			from_dir = 1;
		else
			from_other = 1;
	} else if (flags & R_REQUEST) {
		from_local = 1;
	}

	/*
	 * flags & R_RECEIVE_RECOVER is from dlm_recover_master_copy, so
	 * from_nodeid has sent us a lock in dlm_recover_locks, believing
	 * we're the new master.  Our local recovery may not have set
	 * res_master_nodeid to our_nodeid yet, so allow either.  Don't
	 * create the rsb; dlm_recover_process_copy() will handle EBADR
	 * by resending.
	 *
	 * If someone sends us a request, we are the dir node, and we do
	 * not find the rsb anywhere, then recreate it.  This happens if
	 * someone sends us a request after we have removed/freed an rsb
	 * from our toss list.  (They sent a request instead of lookup
	 * because they are using an rsb from their toss list.)
	 */

	if (from_local || from_dir ||
	    (from_other && (dir_nodeid == our_nodeid))) {
		create = 1;
	}

 retry:
	if (create) {
		error = pre_rsb_struct(ls);
		if (error < 0)
			goto out;
	}

	spin_lock(&ls->ls_rsbtbl[b].lock);

	error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].keep, name, len, &r);
	if (error)
		goto do_toss;
	
	/*
	 * rsb is active, so we can't check master_nodeid without lock_rsb.
	 */

	kref_get(&r->res_ref);
	error = 0;
	goto out_unlock;


 do_toss:
	error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, &r);
	if (error)
		goto do_new;

	/*
	 * rsb found inactive (master_nodeid may be out of date unless
	 * we are the dir_nodeid or were the master)  No other thread
	 * is using this rsb because it's on the toss list, so we can
	 * look at or update res_master_nodeid without lock_rsb.
	 */

	if ((r->res_master_nodeid != our_nodeid) && from_other) {
		/* our rsb was not master, and another node (not the dir node)
		   has sent us a request */
		log_debug(ls, "find_rsb toss from_other %d master %d dir %d %s",
			  from_nodeid, r->res_master_nodeid, dir_nodeid,
			  r->res_name);
		error = -ENOTBLK;
		goto out_unlock;
	}

	if ((r->res_master_nodeid != our_nodeid) && from_dir) {
		/* don't think this should ever happen */
		log_error(ls, "find_rsb toss from_dir %d master %d",
			  from_nodeid, r->res_master_nodeid);
		dlm_print_rsb(r);
		/* fix it and go on */
		r->res_master_nodeid = our_nodeid;
		r->res_nodeid = 0;
		rsb_clear_flag(r, RSB_MASTER_UNCERTAIN);
		r->res_first_lkid = 0;
	}

	if (from_local && (r->res_master_nodeid != our_nodeid)) {
		/* Because we have held no locks on this rsb,
		   res_master_nodeid could have become stale. */
		rsb_set_flag(r, RSB_MASTER_UNCERTAIN);
		r->res_first_lkid = 0;
	}

	rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[b].toss);
	error = rsb_insert(r, &ls->ls_rsbtbl[b].keep);
	goto out_unlock;


 do_new:
	/*
	 * rsb not found
	 */

	if (error == -EBADR && !create)
		goto out_unlock;

	error = get_rsb_struct(ls, name, len, &r);
	if (error == -EAGAIN) {
		spin_unlock(&ls->ls_rsbtbl[b].lock);
		goto retry;
	}
	if (error)
		goto out_unlock;

	r->res_hash = hash;
	r->res_bucket = b;
	r->res_dir_nodeid = dir_nodeid;
	kref_init(&r->res_ref);

	if (from_dir) {
		/* want to see how often this happens */
		log_debug(ls, "find_rsb new from_dir %d recreate %s",
			  from_nodeid, r->res_name);
		r->res_master_nodeid = our_nodeid;
		r->res_nodeid = 0;
		goto out_add;
	}

	if (from_other && (dir_nodeid != our_nodeid)) {
		/* should never happen */
		log_error(ls, "find_rsb new from_other %d dir %d our %d %s",
			  from_nodeid, dir_nodeid, our_nodeid, r->res_name);
		dlm_free_rsb(r);
		r = NULL;
		error = -ENOTBLK;
		goto out_unlock;
	}

	if (from_other) {
		log_debug(ls, "find_rsb new from_other %d dir %d %s",
			  from_nodeid, dir_nodeid, r->res_name);
	}

	if (dir_nodeid == our_nodeid) {
		/* When we are the dir nodeid, we can set the master
		   node immediately */
		r->res_master_nodeid = our_nodeid;
		r->res_nodeid = 0;
	} else {
		/* set_master will send_lookup to dir_nodeid */
		r->res_master_nodeid = 0;
		r->res_nodeid = -1;
	}

 out_add:
	error = rsb_insert(r, &ls->ls_rsbtbl[b].keep);
 out_unlock:
	spin_unlock(&ls->ls_rsbtbl[b].lock);
 out:
	*r_ret = r;
	return error;
}

/* During recovery, other nodes can send us new MSTCPY locks (from
   dlm_recover_locks) before we've made ourself master (in
   dlm_recover_masters). */

static int find_rsb_nodir(struct dlm_ls *ls, char *name, int len,
			  uint32_t hash, uint32_t b,
			  int dir_nodeid, int from_nodeid,
			  unsigned int flags, struct dlm_rsb **r_ret)
{
	struct dlm_rsb *r = NULL;
	int our_nodeid = dlm_our_nodeid();
	int recover = (flags & R_RECEIVE_RECOVER);
	int error;

 retry:
	error = pre_rsb_struct(ls);
	if (error < 0)
		goto out;

	spin_lock(&ls->ls_rsbtbl[b].lock);

	error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].keep, name, len, &r);
	if (error)
		goto do_toss;

	/*
	 * rsb is active, so we can't check master_nodeid without lock_rsb.
	 */

	kref_get(&r->res_ref);
	goto out_unlock;


 do_toss:
	error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, &r);
	if (error)
		goto do_new;

	/*
	 * rsb found inactive. No other thread is using this rsb because
	 * it's on the toss list, so we can look at or update
	 * res_master_nodeid without lock_rsb.
	 */

	if (!recover && (r->res_master_nodeid != our_nodeid) && from_nodeid) {
		/* our rsb is not master, and another node has sent us a
		   request; this should never happen */
		log_error(ls, "find_rsb toss from_nodeid %d master %d dir %d",
			  from_nodeid, r->res_master_nodeid, dir_nodeid);
		dlm_print_rsb(r);
		error = -ENOTBLK;
		goto out_unlock;
	}

	if (!recover && (r->res_master_nodeid != our_nodeid) &&
	    (dir_nodeid == our_nodeid)) {
		/* our rsb is not master, and we are dir; may as well fix it;
		   this should never happen */
		log_error(ls, "find_rsb toss our %d master %d dir %d",
			  our_nodeid, r->res_master_nodeid, dir_nodeid);
		dlm_print_rsb(r);
		r->res_master_nodeid = our_nodeid;
		r->res_nodeid = 0;
	}

	rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[b].toss);
	error = rsb_insert(r, &ls->ls_rsbtbl[b].keep);
	goto out_unlock;


 do_new:
	/*
	 * rsb not found
	 */

	error = get_rsb_struct(ls, name, len, &r);
	if (error == -EAGAIN) {
		spin_unlock(&ls->ls_rsbtbl[b].lock);
		goto retry;
	}
	if (error)
		goto out_unlock;

	r->res_hash = hash;
	r->res_bucket = b;
	r->res_dir_nodeid = dir_nodeid;
	r->res_master_nodeid = dir_nodeid;
	r->res_nodeid = (dir_nodeid == our_nodeid) ? 0 : dir_nodeid;
	kref_init(&r->res_ref);

	error = rsb_insert(r, &ls->ls_rsbtbl[b].keep);
 out_unlock:
	spin_unlock(&ls->ls_rsbtbl[b].lock);
 out:
	*r_ret = r;
	return error;
}

static int find_rsb(struct dlm_ls *ls, char *name, int len, int from_nodeid,
		    unsigned int flags, struct dlm_rsb **r_ret)
{
	uint32_t hash, b;
	int dir_nodeid;

	if (len > DLM_RESNAME_MAXLEN)
		return -EINVAL;

	hash = jhash(name, len, 0);
	b = hash & (ls->ls_rsbtbl_size - 1);

	dir_nodeid = dlm_hash2nodeid(ls, hash);

	if (dlm_no_directory(ls))
		return find_rsb_nodir(ls, name, len, hash, b, dir_nodeid,
				      from_nodeid, flags, r_ret);
	else
		return find_rsb_dir(ls, name, len, hash, b, dir_nodeid,
				      from_nodeid, flags, r_ret);
}

/* we have received a request and found that res_master_nodeid != our_nodeid,
   so we need to return an error or make ourself the master */

static int validate_master_nodeid(struct dlm_ls *ls, struct dlm_rsb *r,
				  int from_nodeid)
{
	if (dlm_no_directory(ls)) {
		log_error(ls, "find_rsb keep from_nodeid %d master %d dir %d",
			  from_nodeid, r->res_master_nodeid,
			  r->res_dir_nodeid);
		dlm_print_rsb(r);
		return -ENOTBLK;
	}

	if (from_nodeid != r->res_dir_nodeid) {
		/* our rsb is not master, and another node (not the dir node)
	   	   has sent us a request.  this is much more common when our
	   	   master_nodeid is zero, so limit debug to non-zero.  */

		if (r->res_master_nodeid) {
			log_debug(ls, "validate master from_other %d master %d "
				  "dir %d first %x %s", from_nodeid,
				  r->res_master_nodeid, r->res_dir_nodeid,
				  r->res_first_lkid, r->res_name);
		}
		return -ENOTBLK;
	} else {
		/* our rsb is not master, but the dir nodeid has sent us a
	   	   request; this could happen with master 0 / res_nodeid -1 */

		if (r->res_master_nodeid) {
			log_error(ls, "validate master from_dir %d master %d "
				  "first %x %s",
				  from_nodeid, r->res_master_nodeid,
				  r->res_first_lkid, r->res_name);
		}

		r->res_master_nodeid = dlm_our_nodeid();
		r->res_nodeid = 0;
		return 0;
	}
}

/*
 * We're the dir node for this res and another node wants to know the
 * master nodeid.  During normal operation (non recovery) this is only
 * called from receive_lookup(); master lookups when the local node is
 * the dir node are done by find_rsb().
 *
 * normal operation, we are the dir node for a resource
 * . _request_lock
 * . set_master
 * . send_lookup
 * . receive_lookup
 * . dlm_master_lookup flags 0
 *
 * recover directory, we are rebuilding dir for all resources
 * . dlm_recover_directory
 * . dlm_rcom_names
 *   remote node sends back the rsb names it is master of and we are dir of
 * . dlm_master_lookup RECOVER_DIR (fix_master 0, from_master 1)
 *   we either create new rsb setting remote node as master, or find existing
 *   rsb and set master to be the remote node.
 *
 * recover masters, we are finding the new master for resources
 * . dlm_recover_masters
 * . recover_master
 * . dlm_send_rcom_lookup
 * . receive_rcom_lookup
 * . dlm_master_lookup RECOVER_MASTER (fix_master 1, from_master 0)
 */

int dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, char *name, int len,
		      unsigned int flags, int *r_nodeid, int *result)
{
	struct dlm_rsb *r = NULL;
	uint32_t hash, b;
	int from_master = (flags & DLM_LU_RECOVER_DIR);
	int fix_master = (flags & DLM_LU_RECOVER_MASTER);
	int our_nodeid = dlm_our_nodeid();
	int dir_nodeid, error, toss_list = 0;

	if (len > DLM_RESNAME_MAXLEN)
		return -EINVAL;

	if (from_nodeid == our_nodeid) {
		log_error(ls, "dlm_master_lookup from our_nodeid %d flags %x",
			  our_nodeid, flags);
		return -EINVAL;
	}

	hash = jhash(name, len, 0);
	b = hash & (ls->ls_rsbtbl_size - 1);

	dir_nodeid = dlm_hash2nodeid(ls, hash);
	if (dir_nodeid != our_nodeid) {
		log_error(ls, "dlm_master_lookup from %d dir %d our %d h %x %d",
			  from_nodeid, dir_nodeid, our_nodeid, hash,
			  ls->ls_num_nodes);
		*r_nodeid = -1;
		return -EINVAL;
	}

 retry:
	error = pre_rsb_struct(ls);
	if (error < 0)
		return error;

	spin_lock(&ls->ls_rsbtbl[b].lock);
	error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].keep, name, len, &r);
	if (!error) {
		/* because the rsb is active, we need to lock_rsb before
		   checking/changing re_master_nodeid */

		hold_rsb(r);
		spin_unlock(&ls->ls_rsbtbl[b].lock);
		lock_rsb(r);
		goto found;
	}

	error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, &r);
	if (error)
		goto not_found;

	/* because the rsb is inactive (on toss list), it's not refcounted
	   and lock_rsb is not used, but is protected by the rsbtbl lock */

	toss_list = 1;
 found:
	if (r->res_dir_nodeid != our_nodeid) {
		/* should not happen, but may as well fix it and carry on */
		log_error(ls, "dlm_master_lookup res_dir %d our %d %s",
			  r->res_dir_nodeid, our_nodeid, r->res_name);
		r->res_dir_nodeid = our_nodeid;
	}

	if (fix_master && dlm_is_removed(ls, r->res_master_nodeid)) {
		/* Recovery uses this function to set a new master when
		   the previous master failed.  Setting NEW_MASTER will
		   force dlm_recover_masters to call recover_master on this
		   rsb even though the res_nodeid is no longer removed. */

		r->res_master_nodeid = from_nodeid;
		r->res_nodeid = from_nodeid;
		rsb_set_flag(r, RSB_NEW_MASTER);

		if (toss_list) {
			/* I don't think we should ever find it on toss list. */
			log_error(ls, "dlm_master_lookup fix_master on toss");
			dlm_dump_rsb(r);
		}
	}

	if (from_master && (r->res_master_nodeid != from_nodeid)) {
		/* this will happen if from_nodeid became master during
		   a previous recovery cycle, and we aborted the previous
		   cycle before recovering this master value */

		log_limit(ls, "dlm_master_lookup from_master %d "
			  "master_nodeid %d res_nodeid %d first %x %s",
			  from_nodeid, r->res_master_nodeid, r->res_nodeid,
			  r->res_first_lkid, r->res_name);

		if (r->res_master_nodeid == our_nodeid) {
			log_error(ls, "from_master %d our_master", from_nodeid);
			dlm_dump_rsb(r);
			dlm_send_rcom_lookup_dump(r, from_nodeid);
			goto out_found;
		}

		r->res_master_nodeid = from_nodeid;
		r->res_nodeid = from_nodeid;
		rsb_set_flag(r, RSB_NEW_MASTER);
	}

	if (!r->res_master_nodeid) {
		/* this will happen if recovery happens while we're looking
		   up the master for this rsb */

		log_debug(ls, "dlm_master_lookup master 0 to %d first %x %s",
			  from_nodeid, r->res_first_lkid, r->res_name);
		r->res_master_nodeid = from_nodeid;
		r->res_nodeid = from_nodeid;
	}

	if (!from_master && !fix_master &&
	    (r->res_master_nodeid == from_nodeid)) {
		/* this can happen when the master sends remove, the dir node
		   finds the rsb on the keep list and ignores the remove,
		   and the former master sends a lookup */

		log_limit(ls, "dlm_master_lookup from master %d flags %x "
			  "first %x %s", from_nodeid, flags,
			  r->res_first_lkid, r->res_name);
	}

 out_found:
	*r_nodeid = r->res_master_nodeid;
	if (result)
		*result = DLM_LU_MATCH;

	if (toss_list) {
		r->res_toss_time = jiffies;
		/* the rsb was inactive (on toss list) */
		spin_unlock(&ls->ls_rsbtbl[b].lock);
	} else {
		/* the rsb was active */
		unlock_rsb(r);
		put_rsb(r);
	}
	return 0;

 not_found:
	error = get_rsb_struct(ls, name, len, &r);
	if (error == -EAGAIN) {
		spin_unlock(&ls->ls_rsbtbl[b].lock);
		goto retry;
	}
	if (error)
		goto out_unlock;

	r->res_hash = hash;
	r->res_bucket = b;
	r->res_dir_nodeid = our_nodeid;
	r->res_master_nodeid = from_nodeid;
	r->res_nodeid = from_nodeid;
	kref_init(&r->res_ref);
	r->res_toss_time = jiffies;

	error = rsb_insert(r, &ls->ls_rsbtbl[b].toss);
	if (error) {
		/* should never happen */
		dlm_free_rsb(r);
		spin_unlock(&ls->ls_rsbtbl[b].lock);
		goto retry;
	}

	if (result)
		*result = DLM_LU_ADD;
	*r_nodeid = from_nodeid;
	error = 0;
 out_unlock:
	spin_unlock(&ls->ls_rsbtbl[b].lock);
	return error;
}

static void dlm_dump_rsb_hash(struct dlm_ls *ls, uint32_t hash)
{
	struct rb_node *n;
	struct dlm_rsb *r;
	int i;

	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
		spin_lock(&ls->ls_rsbtbl[i].lock);
		for (n = rb_first(&ls->ls_rsbtbl[i].keep); n; n = rb_next(n)) {
			r = rb_entry(n, struct dlm_rsb, res_hashnode);
			if (r->res_hash == hash)
				dlm_dump_rsb(r);
		}
		spin_unlock(&ls->ls_rsbtbl[i].lock);
	}
}

void dlm_dump_rsb_name(struct dlm_ls *ls, char *name, int len)
{
	struct dlm_rsb *r = NULL;
	uint32_t hash, b;
	int error;

	hash = jhash(name, len, 0);
	b = hash & (ls->ls_rsbtbl_size - 1);

	spin_lock(&ls->ls_rsbtbl[b].lock);
	error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].keep, name, len, &r);
	if (!error)
		goto out_dump;

	error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, &r);
	if (error)
		goto out;
 out_dump:
	dlm_dump_rsb(r);
 out:
	spin_unlock(&ls->ls_rsbtbl[b].lock);
}

static void toss_rsb(struct kref *kref)
{
	struct dlm_rsb *r = container_of(kref, struct dlm_rsb, res_ref);
	struct dlm_ls *ls = r->res_ls;

	DLM_ASSERT(list_empty(&r->res_root_list), dlm_print_rsb(r););
	kref_init(&r->res_ref);
	rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[r->res_bucket].keep);
	rsb_insert(r, &ls->ls_rsbtbl[r->res_bucket].toss);
	r->res_toss_time = jiffies;
	ls->ls_rsbtbl[r->res_bucket].flags |= DLM_RTF_SHRINK;
	if (r->res_lvbptr) {
		dlm_free_lvb(r->res_lvbptr);
		r->res_lvbptr = NULL;
	}
}

/* See comment for unhold_lkb */

static void unhold_rsb(struct dlm_rsb *r)
{
	int rv;
	rv = kref_put(&r->res_ref, toss_rsb);
	DLM_ASSERT(!rv, dlm_dump_rsb(r););
}

static void kill_rsb(struct kref *kref)
{
	struct dlm_rsb *r = container_of(kref, struct dlm_rsb, res_ref);

	/* All work is done after the return from kref_put() so we
	   can release the write_lock before the remove and free. */

	DLM_ASSERT(list_empty(&r->res_lookup), dlm_dump_rsb(r););
	DLM_ASSERT(list_empty(&r->res_grantqueue), dlm_dump_rsb(r););
	DLM_ASSERT(list_empty(&r->res_convertqueue), dlm_dump_rsb(r););
	DLM_ASSERT(list_empty(&r->res_waitqueue), dlm_dump_rsb(r););
	DLM_ASSERT(list_empty(&r->res_root_list), dlm_dump_rsb(r););
	DLM_ASSERT(list_empty(&r->res_recover_list), dlm_dump_rsb(r););
}

/* Attaching/detaching lkb's from rsb's is for rsb reference counting.
   The rsb must exist as long as any lkb's for it do. */

static void attach_lkb(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	hold_rsb(r);
	lkb->lkb_resource = r;
}

static void detach_lkb(struct dlm_lkb *lkb)
{
	if (lkb->lkb_resource) {
		put_rsb(lkb->lkb_resource);
		lkb->lkb_resource = NULL;
	}
}

static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret)
{
	struct dlm_lkb *lkb;
	int rv;

	lkb = dlm_allocate_lkb(ls);
	if (!lkb)
		return -ENOMEM;

	lkb->lkb_nodeid = -1;
	lkb->lkb_grmode = DLM_LOCK_IV;
	kref_init(&lkb->lkb_ref);
	INIT_LIST_HEAD(&lkb->lkb_ownqueue);
	INIT_LIST_HEAD(&lkb->lkb_rsb_lookup);
	INIT_LIST_HEAD(&lkb->lkb_time_list);
	INIT_LIST_HEAD(&lkb->lkb_cb_list);
	mutex_init(&lkb->lkb_cb_mutex);
	INIT_WORK(&lkb->lkb_cb_work, dlm_callback_work);

	idr_preload(GFP_NOFS);
	spin_lock(&ls->ls_lkbidr_spin);
	rv = idr_alloc(&ls->ls_lkbidr, lkb, 1, 0, GFP_NOWAIT);
	if (rv >= 0)
		lkb->lkb_id = rv;
	spin_unlock(&ls->ls_lkbidr_spin);
	idr_preload_end();

	if (rv < 0) {
		log_error(ls, "create_lkb idr error %d", rv);
		return rv;
	}

	*lkb_ret = lkb;
	return 0;
}

static int find_lkb(struct dlm_ls *ls, uint32_t lkid, struct dlm_lkb **lkb_ret)
{
	struct dlm_lkb *lkb;

	spin_lock(&ls->ls_lkbidr_spin);
	lkb = idr_find(&ls->ls_lkbidr, lkid);
	if (lkb)
		kref_get(&lkb->lkb_ref);
	spin_unlock(&ls->ls_lkbidr_spin);

	*lkb_ret = lkb;
	return lkb ? 0 : -ENOENT;
}

static void kill_lkb(struct kref *kref)
{
	struct dlm_lkb *lkb = container_of(kref, struct dlm_lkb, lkb_ref);

	/* All work is done after the return from kref_put() so we
	   can release the write_lock before the detach_lkb */

	DLM_ASSERT(!lkb->lkb_status, dlm_print_lkb(lkb););
}

/* __put_lkb() is used when an lkb may not have an rsb attached to
   it so we need to provide the lockspace explicitly */

static int __put_lkb(struct dlm_ls *ls, struct dlm_lkb *lkb)
{
	uint32_t lkid = lkb->lkb_id;

	spin_lock(&ls->ls_lkbidr_spin);
	if (kref_put(&lkb->lkb_ref, kill_lkb)) {
		idr_remove(&ls->ls_lkbidr, lkid);
		spin_unlock(&ls->ls_lkbidr_spin);

		detach_lkb(lkb);

		/* for local/process lkbs, lvbptr points to caller's lksb */
		if (lkb->lkb_lvbptr && is_master_copy(lkb))
			dlm_free_lvb(lkb->lkb_lvbptr);
		dlm_free_lkb(lkb);
		return 1;
	} else {
		spin_unlock(&ls->ls_lkbidr_spin);
		return 0;
	}
}

int dlm_put_lkb(struct dlm_lkb *lkb)
{
	struct dlm_ls *ls;

	DLM_ASSERT(lkb->lkb_resource, dlm_print_lkb(lkb););
	DLM_ASSERT(lkb->lkb_resource->res_ls, dlm_print_lkb(lkb););

	ls = lkb->lkb_resource->res_ls;
	return __put_lkb(ls, lkb);
}

/* This is only called to add a reference when the code already holds
   a valid reference to the lkb, so there's no need for locking. */

static inline void hold_lkb(struct dlm_lkb *lkb)
{
	kref_get(&lkb->lkb_ref);
}

/* This is called when we need to remove a reference and are certain
   it's not the last ref.  e.g. del_lkb is always called between a
   find_lkb/put_lkb and is always the inverse of a previous add_lkb.
   put_lkb would work fine, but would involve unnecessary locking */

static inline void unhold_lkb(struct dlm_lkb *lkb)
{
	int rv;
	rv = kref_put(&lkb->lkb_ref, kill_lkb);
	DLM_ASSERT(!rv, dlm_print_lkb(lkb););
}

static void lkb_add_ordered(struct list_head *new, struct list_head *head,
			    int mode)
{
	struct dlm_lkb *lkb = NULL;

	list_for_each_entry(lkb, head, lkb_statequeue)
		if (lkb->lkb_rqmode < mode)
			break;

	__list_add(new, lkb->lkb_statequeue.prev, &lkb->lkb_statequeue);
}

/* add/remove lkb to rsb's grant/convert/wait queue */

static void add_lkb(struct dlm_rsb *r, struct dlm_lkb *lkb, int status)
{
	kref_get(&lkb->lkb_ref);

	DLM_ASSERT(!lkb->lkb_status, dlm_print_lkb(lkb););

	lkb->lkb_timestamp = ktime_get();

	lkb->lkb_status = status;

	switch (status) {
	case DLM_LKSTS_WAITING:
		if (lkb->lkb_exflags & DLM_LKF_HEADQUE)
			list_add(&lkb->lkb_statequeue, &r->res_waitqueue);
		else
			list_add_tail(&lkb->lkb_statequeue, &r->res_waitqueue);
		break;
	case DLM_LKSTS_GRANTED:
		/* convention says granted locks kept in order of grmode */
		lkb_add_ordered(&lkb->lkb_statequeue, &r->res_grantqueue,
				lkb->lkb_grmode);
		break;
	case DLM_LKSTS_CONVERT:
		if (lkb->lkb_exflags & DLM_LKF_HEADQUE)
			list_add(&lkb->lkb_statequeue, &r->res_convertqueue);
		else
			list_add_tail(&lkb->lkb_statequeue,
				      &r->res_convertqueue);
		break;
	default:
		DLM_ASSERT(0, dlm_print_lkb(lkb); printk("sts=%d\n", status););
	}
}

static void del_lkb(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	lkb->lkb_status = 0;
	list_del(&lkb->lkb_statequeue);
	unhold_lkb(lkb);
}

static void move_lkb(struct dlm_rsb *r, struct dlm_lkb *lkb, int sts)
{
	hold_lkb(lkb);
	del_lkb(r, lkb);
	add_lkb(r, lkb, sts);
	unhold_lkb(lkb);
}

static int msg_reply_type(int mstype)
{
	switch (mstype) {
	case DLM_MSG_REQUEST:
		return DLM_MSG_REQUEST_REPLY;
	case DLM_MSG_CONVERT:
		return DLM_MSG_CONVERT_REPLY;
	case DLM_MSG_UNLOCK:
		return DLM_MSG_UNLOCK_REPLY;
	case DLM_MSG_CANCEL:
		return DLM_MSG_CANCEL_REPLY;
	case DLM_MSG_LOOKUP:
		return DLM_MSG_LOOKUP_REPLY;
	}
	return -1;
}

static int nodeid_warned(int nodeid, int num_nodes, int *warned)
{
	int i;

	for (i = 0; i < num_nodes; i++) {
		if (!warned[i]) {
			warned[i] = nodeid;
			return 0;
		}
		if (warned[i] == nodeid)
			return 1;
	}
	return 0;
}

void dlm_scan_waiters(struct dlm_ls *ls)
{
	struct dlm_lkb *lkb;
	ktime_t zero = ktime_set(0, 0);
	s64 us;
	s64 debug_maxus = 0;
	u32 debug_scanned = 0;
	u32 debug_expired = 0;
	int num_nodes = 0;
	int *warned = NULL;

	if (!dlm_config.ci_waitwarn_us)
		return;

	mutex_lock(&ls->ls_waiters_mutex);

	list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
		if (ktime_equal(lkb->lkb_wait_time, zero))
			continue;

		debug_scanned++;

		us = ktime_to_us(ktime_sub(ktime_get(), lkb->lkb_wait_time));

		if (us < dlm_config.ci_waitwarn_us)
			continue;

		lkb->lkb_wait_time = zero;

		debug_expired++;
		if (us > debug_maxus)
			debug_maxus = us;

		if (!num_nodes) {
			num_nodes = ls->ls_num_nodes;
			warned = kzalloc(num_nodes * sizeof(int), GFP_KERNEL);
		}
		if (!warned)
			continue;
		if (nodeid_warned(lkb->lkb_wait_nodeid, num_nodes, warned))
			continue;

		log_error(ls, "waitwarn %x %lld %d us check connection to "
			  "node %d", lkb->lkb_id, (long long)us,
			  dlm_config.ci_waitwarn_us, lkb->lkb_wait_nodeid);
	}
	mutex_unlock(&ls->ls_waiters_mutex);
	kfree(warned);

	if (debug_expired)
		log_debug(ls, "scan_waiters %u warn %u over %d us max %lld us",
			  debug_scanned, debug_expired,
			  dlm_config.ci_waitwarn_us, (long long)debug_maxus);
}

/* add/remove lkb from global waiters list of lkb's waiting for
   a reply from a remote node */

static int add_to_waiters(struct dlm_lkb *lkb, int mstype, int to_nodeid)
{
	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
	int error = 0;

	mutex_lock(&ls->ls_waiters_mutex);

	if (is_overlap_unlock(lkb) ||
	    (is_overlap_cancel(lkb) && (mstype == DLM_MSG_CANCEL))) {
		error = -EINVAL;
		goto out;
	}

	if (lkb->lkb_wait_type || is_overlap_cancel(lkb)) {
		switch (mstype) {
		case DLM_MSG_UNLOCK:
			lkb->lkb_flags |= DLM_IFL_OVERLAP_UNLOCK;
			break;
		case DLM_MSG_CANCEL:
			lkb->lkb_flags |= DLM_IFL_OVERLAP_CANCEL;
			break;
		default:
			error = -EBUSY;
			goto out;
		}
		lkb->lkb_wait_count++;
		hold_lkb(lkb);

		log_debug(ls, "addwait %x cur %d overlap %d count %d f %x",
			  lkb->lkb_id, lkb->lkb_wait_type, mstype,
			  lkb->lkb_wait_count, lkb->lkb_flags);
		goto out;
	}

	DLM_ASSERT(!lkb->lkb_wait_count,
		   dlm_print_lkb(lkb);
		   printk("wait_count %d\n", lkb->lkb_wait_count););

	lkb->lkb_wait_count++;
	lkb->lkb_wait_type = mstype;
	lkb->lkb_wait_time = ktime_get();
	lkb->lkb_wait_nodeid = to_nodeid; /* for debugging */
	hold_lkb(lkb);
	list_add(&lkb->lkb_wait_reply, &ls->ls_waiters);
 out:
	if (error)
		log_error(ls, "addwait error %x %d flags %x %d %d %s",
			  lkb->lkb_id, error, lkb->lkb_flags, mstype,
			  lkb->lkb_wait_type, lkb->lkb_resource->res_name);
	mutex_unlock(&ls->ls_waiters_mutex);
	return error;
}

/* We clear the RESEND flag because we might be taking an lkb off the waiters
   list as part of process_requestqueue (e.g. a lookup that has an optimized
   request reply on the requestqueue) between dlm_recover_waiters_pre() which
   set RESEND and dlm_recover_waiters_post() */

static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype,
				struct dlm_message *ms)
{
	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
	int overlap_done = 0;

	if (is_overlap_unlock(lkb) && (mstype == DLM_MSG_UNLOCK_REPLY)) {
		log_debug(ls, "remwait %x unlock_reply overlap", lkb->lkb_id);
		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK;
		overlap_done = 1;
		goto out_del;
	}

	if (is_overlap_cancel(lkb) && (mstype == DLM_MSG_CANCEL_REPLY)) {
		log_debug(ls, "remwait %x cancel_reply overlap", lkb->lkb_id);
		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
		overlap_done = 1;
		goto out_del;
	}

	/* Cancel state was preemptively cleared by a successful convert,
	   see next comment, nothing to do. */

	if ((mstype == DLM_MSG_CANCEL_REPLY) &&
	    (lkb->lkb_wait_type != DLM_MSG_CANCEL)) {
		log_debug(ls, "remwait %x cancel_reply wait_type %d",
			  lkb->lkb_id, lkb->lkb_wait_type);
		return -1;
	}

	/* Remove for the convert reply, and premptively remove for the
	   cancel reply.  A convert has been granted while there's still
	   an outstanding cancel on it (the cancel is moot and the result
	   in the cancel reply should be 0).  We preempt the cancel reply
	   because the app gets the convert result and then can follow up
	   with another op, like convert.  This subsequent op would see the
	   lingering state of the cancel and fail with -EBUSY. */

	if ((mstype == DLM_MSG_CONVERT_REPLY) &&
	    (lkb->lkb_wait_type == DLM_MSG_CONVERT) &&
	    is_overlap_cancel(lkb) && ms && !ms->m_result) {
		log_debug(ls, "remwait %x convert_reply zap overlap_cancel",
			  lkb->lkb_id);
		lkb->lkb_wait_type = 0;
		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
		lkb->lkb_wait_count--;
		goto out_del;
	}

	/* N.B. type of reply may not always correspond to type of original
	   msg due to lookup->request optimization, verify others? */

	if (lkb->lkb_wait_type) {
		lkb->lkb_wait_type = 0;
		goto out_del;
	}

	log_error(ls, "remwait error %x remote %d %x msg %d flags %x no wait",
		  lkb->lkb_id, ms ? ms->m_header.h_nodeid : 0, lkb->lkb_remid,
		  mstype, lkb->lkb_flags);
	return -1;

 out_del:
	/* the force-unlock/cancel has completed and we haven't recvd a reply
	   to the op that was in progress prior to the unlock/cancel; we
	   give up on any reply to the earlier op.  FIXME: not sure when/how
	   this would happen */

	if (overlap_done && lkb->lkb_wait_type) {
		log_error(ls, "remwait error %x reply %d wait_type %d overlap",
			  lkb->lkb_id, mstype, lkb->lkb_wait_type);
		lkb->lkb_wait_count--;
		lkb->lkb_wait_type = 0;
	}

	DLM_ASSERT(lkb->lkb_wait_count, dlm_print_lkb(lkb););

	lkb->lkb_flags &= ~DLM_IFL_RESEND;
	lkb->lkb_wait_count--;
	if (!lkb->lkb_wait_count)
		list_del_init(&lkb->lkb_wait_reply);
	unhold_lkb(lkb);
	return 0;
}

static int remove_from_waiters(struct dlm_lkb *lkb, int mstype)
{
	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
	int error;

	mutex_lock(&ls->ls_waiters_mutex);
	error = _remove_from_waiters(lkb, mstype, NULL);
	mutex_unlock(&ls->ls_waiters_mutex);
	return error;
}

/* Handles situations where we might be processing a "fake" or "stub" reply in
   which we can't try to take waiters_mutex again. */

static int remove_from_waiters_ms(struct dlm_lkb *lkb, struct dlm_message *ms)
{
	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
	int error;

	if (ms->m_flags != DLM_IFL_STUB_MS)
		mutex_lock(&ls->ls_waiters_mutex);
	error = _remove_from_waiters(lkb, ms->m_type, ms);
	if (ms->m_flags != DLM_IFL_STUB_MS)
		mutex_unlock(&ls->ls_waiters_mutex);
	return error;
}

/* If there's an rsb for the same resource being removed, ensure
   that the remove message is sent before the new lookup message.
   It should be rare to need a delay here, but if not, then it may
   be worthwhile to add a proper wait mechanism rather than a delay. */

static void wait_pending_remove(struct dlm_rsb *r)
{
	struct dlm_ls *ls = r->res_ls;
 restart:
	spin_lock(&ls->ls_remove_spin);
	if (ls->ls_remove_len &&
	    !rsb_cmp(r, ls->ls_remove_name, ls->ls_remove_len)) {
		log_debug(ls, "delay lookup for remove dir %d %s",
		  	  r->res_dir_nodeid, r->res_name);
		spin_unlock(&ls->ls_remove_spin);
		msleep(1);
		goto restart;
	}
	spin_unlock(&ls->ls_remove_spin);
}

/*
 * ls_remove_spin protects ls_remove_name and ls_remove_len which are
 * read by other threads in wait_pending_remove.  ls_remove_names
 * and ls_remove_lens are only used by the scan thread, so they do
 * not need protection.
 */

static void shrink_bucket(struct dlm_ls *ls, int b)
{
	struct rb_node *n, *next;
	struct dlm_rsb *r;
	char *name;
	int our_nodeid = dlm_our_nodeid();
	int remote_count = 0;
	int need_shrink = 0;
	int i, len, rv;

	memset(&ls->ls_remove_lens, 0, sizeof(int) * DLM_REMOVE_NAMES_MAX);

	spin_lock(&ls->ls_rsbtbl[b].lock);

	if (!(ls->ls_rsbtbl[b].flags & DLM_RTF_SHRINK)) {
		spin_unlock(&ls->ls_rsbtbl[b].lock);
		return;
	}

	for (n = rb_first(&ls->ls_rsbtbl[b].toss); n; n = next) {
		next = rb_next(n);
		r = rb_entry(n, struct dlm_rsb, res_hashnode);

		/* If we're the directory record for this rsb, and
		   we're not the master of it, then we need to wait
		   for the master node to send us a dir remove for
		   before removing the dir record. */

		if (!dlm_no_directory(ls) &&
		    (r->res_master_nodeid != our_nodeid) &&
		    (dlm_dir_nodeid(r) == our_nodeid)) {
			continue;
		}

		need_shrink = 1;

		if (!time_after_eq(jiffies, r->res_toss_time +
				   dlm_config.ci_toss_secs * HZ)) {
			continue;
		}

		if (!dlm_no_directory(ls) &&
		    (r->res_master_nodeid == our_nodeid) &&
		    (dlm_dir_nodeid(r) != our_nodeid)) {

			/* We're the master of this rsb but we're not
			   the directory record, so we need to tell the
			   dir node to remove the dir record. */

			ls->ls_remove_lens[remote_count] = r->res_length;
			memcpy(ls->ls_remove_names[remote_count], r->res_name,
			       DLM_RESNAME_MAXLEN);
			remote_count++;

			if (remote_count >= DLM_REMOVE_NAMES_MAX)
				break;
			continue;
		}

		if (!kref_put(&r->res_ref, kill_rsb)) {
			log_error(ls, "tossed rsb in use %s", r->res_name);
			continue;
		}

		rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[b].toss);
		dlm_free_rsb(r);
	}

	if (need_shrink)
		ls->ls_rsbtbl[b].flags |= DLM_RTF_SHRINK;
	else
		ls->ls_rsbtbl[b].flags &= ~DLM_RTF_SHRINK;
	spin_unlock(&ls->ls_rsbtbl[b].lock);

	/*
	 * While searching for rsb's to free, we found some that require
	 * remote removal.  We leave them in place and find them again here
	 * so there is a very small gap between removing them from the toss
	 * list and sending the removal.  Keeping this gap small is
	 * important to keep us (the master node) from being out of sync
	 * with the remote dir node for very long.
	 *
	 * From the time the rsb is removed from toss until just after
	 * send_remove, the rsb name is saved in ls_remove_name.  A new
	 * lookup checks this to ensure that a new lookup message for the
	 * same resource name is not sent just before the remove message.
	 */

	for (i = 0; i < remote_count; i++) {
		name = ls->ls_remove_names[i];
		len = ls->ls_remove_lens[i];

		spin_lock(&ls->ls_rsbtbl[b].lock);
		rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, &r);
		if (rv) {
			spin_unlock(&ls->ls_rsbtbl[b].lock);
			log_debug(ls, "remove_name not toss %s", name);
			continue;
		}

		if (r->res_master_nodeid != our_nodeid) {
			spin_unlock(&ls->ls_rsbtbl[b].lock);
			log_debug(ls, "remove_name master %d dir %d our %d %s",
				  r->res_master_nodeid, r->res_dir_nodeid,
				  our_nodeid, name);
			continue;
		}

		if (r->res_dir_nodeid == our_nodeid) {
			/* should never happen */
			spin_unlock(&ls->ls_rsbtbl[b].lock);
			log_error(ls, "remove_name dir %d master %d our %d %s",
				  r->res_dir_nodeid, r->res_master_nodeid,
				  our_nodeid, name);
			continue;
		}

		if (!time_after_eq(jiffies, r->res_toss_time +
				   dlm_config.ci_toss_secs * HZ)) {
			spin_unlock(&ls->ls_rsbtbl[b].lock);
			log_debug(ls, "remove_name toss_time %lu now %lu %s",
				  r->res_toss_time, jiffies, name);
			continue;
		}

		if (!kref_put(&r->res_ref, kill_rsb)) {
			spin_unlock(&ls->ls_rsbtbl[b].lock);
			log_error(ls, "remove_name in use %s", name);
			continue;
		}

		rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[b].toss);

		/* block lookup of same name until we've sent remove */
		spin_lock(&ls->ls_remove_spin);
		ls->ls_remove_len = len;
		memcpy(ls->ls_remove_name, name, DLM_RESNAME_MAXLEN);
		spin_unlock(&ls->ls_remove_spin);
		spin_unlock(&ls->ls_rsbtbl[b].lock);

		send_remove(r);

		/* allow lookup of name again */
		spin_lock(&ls->ls_remove_spin);
		ls->ls_remove_len = 0;
		memset(ls->ls_remove_name, 0, DLM_RESNAME_MAXLEN);
		spin_unlock(&ls->ls_remove_spin);

		dlm_free_rsb(r);
	}
}

void dlm_scan_rsbs(struct dlm_ls *ls)
{
	int i;

	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
		shrink_bucket(ls, i);
		if (dlm_locking_stopped(ls))
			break;
		cond_resched();
	}
}

static void add_timeout(struct dlm_lkb *lkb)
{
	struct dlm_ls *ls = lkb->lkb_resource->res_ls;

	if (is_master_copy(lkb))
		return;

	if (test_bit(LSFL_TIMEWARN, &ls->ls_flags) &&
	    !(lkb->lkb_exflags & DLM_LKF_NODLCKWT)) {
		lkb->lkb_flags |= DLM_IFL_WATCH_TIMEWARN;
		goto add_it;
	}
	if (lkb->lkb_exflags & DLM_LKF_TIMEOUT)
		goto add_it;
	return;

 add_it:
	DLM_ASSERT(list_empty(&lkb->lkb_time_list), dlm_print_lkb(lkb););
	mutex_lock(&ls->ls_timeout_mutex);
	hold_lkb(lkb);
	list_add_tail(&lkb->lkb_time_list, &ls->ls_timeout);
	mutex_unlock(&ls->ls_timeout_mutex);
}

static void del_timeout(struct dlm_lkb *lkb)
{
	struct dlm_ls *ls = lkb->lkb_resource->res_ls;

	mutex_lock(&ls->ls_timeout_mutex);
	if (!list_empty(&lkb->lkb_time_list)) {
		list_del_init(&lkb->lkb_time_list);
		unhold_lkb(lkb);
	}
	mutex_unlock(&ls->ls_timeout_mutex);
}

/* FIXME: is it safe to look at lkb_exflags, lkb_flags, lkb_timestamp, and
   lkb_lksb_timeout without lock_rsb?  Note: we can't lock timeout_mutex
   and then lock rsb because of lock ordering in add_timeout.  We may need
   to specify some special timeout-related bits in the lkb that are just to
   be accessed under the timeout_mutex. */

void dlm_scan_timeout(struct dlm_ls *ls)
{
	struct dlm_rsb *r;
	struct dlm_lkb *lkb;
	int do_cancel, do_warn;
	s64 wait_us;

	for (;;) {
		if (dlm_locking_stopped(ls))
			break;

		do_cancel = 0;
		do_warn = 0;
		mutex_lock(&ls->ls_timeout_mutex);
		list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list) {

			wait_us = ktime_to_us(ktime_sub(ktime_get(),
					      		lkb->lkb_timestamp));

			if ((lkb->lkb_exflags & DLM_LKF_TIMEOUT) &&
			    wait_us >= (lkb->lkb_timeout_cs * 10000))
				do_cancel = 1;

			if ((lkb->lkb_flags & DLM_IFL_WATCH_TIMEWARN) &&
			    wait_us >= dlm_config.ci_timewarn_cs * 10000)
				do_warn = 1;

			if (!do_cancel && !do_warn)
				continue;
			hold_lkb(lkb);
			break;
		}
		mutex_unlock(&ls->ls_timeout_mutex);

		if (!do_cancel && !do_warn)
			break;

		r = lkb->lkb_resource;
		hold_rsb(r);
		lock_rsb(r);

		if (do_warn) {
			/* clear flag so we only warn once */
			lkb->lkb_flags &= ~DLM_IFL_WATCH_TIMEWARN;
			if (!(lkb->lkb_exflags & DLM_LKF_TIMEOUT))
				del_timeout(lkb);
			dlm_timeout_warn(lkb);
		}

		if (do_cancel) {
			log_debug(ls, "timeout cancel %x node %d %s",
				  lkb->lkb_id, lkb->lkb_nodeid, r->res_name);
			lkb->lkb_flags &= ~DLM_IFL_WATCH_TIMEWARN;
			lkb->lkb_flags |= DLM_IFL_TIMEOUT_CANCEL;
			del_timeout(lkb);
			_cancel_lock(r, lkb);
		}

		unlock_rsb(r);
		unhold_rsb(r);
		dlm_put_lkb(lkb);
	}
}

/* This is only called by dlm_recoverd, and we rely on dlm_ls_stop() stopping
   dlm_recoverd before checking/setting ls_recover_begin. */

void dlm_adjust_timeouts(struct dlm_ls *ls)
{
	struct dlm_lkb *lkb;
	u64 adj_us = jiffies_to_usecs(jiffies - ls->ls_recover_begin);

	ls->ls_recover_begin = 0;
	mutex_lock(&ls->ls_timeout_mutex);
	list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list)
		lkb->lkb_timestamp = ktime_add_us(lkb->lkb_timestamp, adj_us);
	mutex_unlock(&ls->ls_timeout_mutex);

	if (!dlm_config.ci_waitwarn_us)
		return;

	mutex_lock(&ls->ls_waiters_mutex);
	list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
		if (ktime_to_us(lkb->lkb_wait_time))
			lkb->lkb_wait_time = ktime_get();
	}
	mutex_unlock(&ls->ls_waiters_mutex);
}

/* lkb is master or local copy */

static void set_lvb_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	int b, len = r->res_ls->ls_lvblen;

	/* b=1 lvb returned to caller
	   b=0 lvb written to rsb or invalidated
	   b=-1 do nothing */

	b =  dlm_lvb_operations[lkb->lkb_grmode + 1][lkb->lkb_rqmode + 1];

	if (b == 1) {
		if (!lkb->lkb_lvbptr)
			return;

		if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
			return;

		if (!r->res_lvbptr)
			return;

		memcpy(lkb->lkb_lvbptr, r->res_lvbptr, len);
		lkb->lkb_lvbseq = r->res_lvbseq;

	} else if (b == 0) {
		if (lkb->lkb_exflags & DLM_LKF_IVVALBLK) {
			rsb_set_flag(r, RSB_VALNOTVALID);
			return;
		}

		if (!lkb->lkb_lvbptr)
			return;

		if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
			return;

		if (!r->res_lvbptr)
			r->res_lvbptr = dlm_allocate_lvb(r->res_ls);

		if (!r->res_lvbptr)
			return;

		memcpy(r->res_lvbptr, lkb->lkb_lvbptr, len);
		r->res_lvbseq++;
		lkb->lkb_lvbseq = r->res_lvbseq;
		rsb_clear_flag(r, RSB_VALNOTVALID);
	}

	if (rsb_flag(r, RSB_VALNOTVALID))
		lkb->lkb_sbflags |= DLM_SBF_VALNOTVALID;
}

static void set_lvb_unlock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	if (lkb->lkb_grmode < DLM_LOCK_PW)
		return;

	if (lkb->lkb_exflags & DLM_LKF_IVVALBLK) {
		rsb_set_flag(r, RSB_VALNOTVALID);
		return;
	}

	if (!lkb->lkb_lvbptr)
		return;

	if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
		return;

	if (!r->res_lvbptr)
		r->res_lvbptr = dlm_allocate_lvb(r->res_ls);

	if (!r->res_lvbptr)
		return;

	memcpy(r->res_lvbptr, lkb->lkb_lvbptr, r->res_ls->ls_lvblen);
	r->res_lvbseq++;
	rsb_clear_flag(r, RSB_VALNOTVALID);
}

/* lkb is process copy (pc) */

static void set_lvb_lock_pc(struct dlm_rsb *r, struct dlm_lkb *lkb,
			    struct dlm_message *ms)
{
	int b;

	if (!lkb->lkb_lvbptr)
		return;

	if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
		return;

	b = dlm_lvb_operations[lkb->lkb_grmode + 1][lkb->lkb_rqmode + 1];
	if (b == 1) {
		int len = receive_extralen(ms);
		if (len > r->res_ls->ls_lvblen)
			len = r->res_ls->ls_lvblen;
		memcpy(lkb->lkb_lvbptr, ms->m_extra, len);
		lkb->lkb_lvbseq = ms->m_lvbseq;
	}
}

/* Manipulate lkb's on rsb's convert/granted/waiting queues
   remove_lock -- used for unlock, removes lkb from granted
   revert_lock -- used for cancel, moves lkb from convert to granted
   grant_lock  -- used for request and convert, adds lkb to granted or
                  moves lkb from convert or waiting to granted

   Each of these is used for master or local copy lkb's.  There is
   also a _pc() variation used to make the corresponding change on
   a process copy (pc) lkb. */

static void _remove_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	del_lkb(r, lkb);
	lkb->lkb_grmode = DLM_LOCK_IV;
	/* this unhold undoes the original ref from create_lkb()
	   so this leads to the lkb being freed */
	unhold_lkb(lkb);
}

static void remove_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	set_lvb_unlock(r, lkb);
	_remove_lock(r, lkb);
}

static void remove_lock_pc(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	_remove_lock(r, lkb);
}

/* returns: 0 did nothing
	    1 moved lock to granted
	   -1 removed lock */

static int revert_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	int rv = 0;

	lkb->lkb_rqmode = DLM_LOCK_IV;

	switch (lkb->lkb_status) {
	case DLM_LKSTS_GRANTED:
		break;
	case DLM_LKSTS_CONVERT:
		move_lkb(r, lkb, DLM_LKSTS_GRANTED);
		rv = 1;
		break;
	case DLM_LKSTS_WAITING:
		del_lkb(r, lkb);
		lkb->lkb_grmode = DLM_LOCK_IV;
		/* this unhold undoes the original ref from create_lkb()
		   so this leads to the lkb being freed */
		unhold_lkb(lkb);
		rv = -1;
		break;
	default:
		log_print("invalid status for revert %d", lkb->lkb_status);
	}
	return rv;
}

static int revert_lock_pc(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	return revert_lock(r, lkb);
}

static void _grant_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	if (lkb->lkb_grmode != lkb->lkb_rqmode) {
		lkb->lkb_grmode = lkb->lkb_rqmode;
		if (lkb->lkb_status)
			move_lkb(r, lkb, DLM_LKSTS_GRANTED);
		else
			add_lkb(r, lkb, DLM_LKSTS_GRANTED);
	}

	lkb->lkb_rqmode = DLM_LOCK_IV;
	lkb->lkb_highbast = 0;
}

static void grant_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	set_lvb_lock(r, lkb);
	_grant_lock(r, lkb);
}

static void grant_lock_pc(struct dlm_rsb *r, struct dlm_lkb *lkb,
			  struct dlm_message *ms)
{
	set_lvb_lock_pc(r, lkb, ms);
	_grant_lock(r, lkb);
}

/* called by grant_pending_locks() which means an async grant message must
   be sent to the requesting node in addition to granting the lock if the
   lkb belongs to a remote node. */

static void grant_lock_pending(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	grant_lock(r, lkb);
	if (is_master_copy(lkb))
		send_grant(r, lkb);
	else
		queue_cast(r, lkb, 0);
}

/* The special CONVDEADLK, ALTPR and ALTCW flags allow the master to
   change the granted/requested modes.  We're munging things accordingly in
   the process copy.
   CONVDEADLK: our grmode may have been forced down to NL to resolve a
   conversion deadlock
   ALTPR/ALTCW: our rqmode may have been changed to PR or CW to become
   compatible with other granted locks */

static void munge_demoted(struct dlm_lkb *lkb)
{
	if (lkb->lkb_rqmode == DLM_LOCK_IV || lkb->lkb_grmode == DLM_LOCK_IV) {
		log_print("munge_demoted %x invalid modes gr %d rq %d",
			  lkb->lkb_id, lkb->lkb_grmode, lkb->lkb_rqmode);
		return;
	}

	lkb->lkb_grmode = DLM_LOCK_NL;
}

static void munge_altmode(struct dlm_lkb *lkb, struct dlm_message *ms)
{
	if (ms->m_type != DLM_MSG_REQUEST_REPLY &&
	    ms->m_type != DLM_MSG_GRANT) {
		log_print("munge_altmode %x invalid reply type %d",
			  lkb->lkb_id, ms->m_type);
		return;
	}

	if (lkb->lkb_exflags & DLM_LKF_ALTPR)
		lkb->lkb_rqmode = DLM_LOCK_PR;
	else if (lkb->lkb_exflags & DLM_LKF_ALTCW)
		lkb->lkb_rqmode = DLM_LOCK_CW;
	else {
		log_print("munge_altmode invalid exflags %x", lkb->lkb_exflags);
		dlm_print_lkb(lkb);
	}
}

static inline int first_in_list(struct dlm_lkb *lkb, struct list_head *head)
{
	struct dlm_lkb *first = list_entry(head->next, struct dlm_lkb,
					   lkb_statequeue);
	if (lkb->lkb_id == first->lkb_id)
		return 1;

	return 0;
}

/* Check if the given lkb conflicts with another lkb on the queue. */

static int queue_conflict(struct list_head *head, struct dlm_lkb *lkb)
{
	struct dlm_lkb *this;

	list_for_each_entry(this, head, lkb_statequeue) {
		if (this == lkb)
			continue;
		if (!modes_compat(this, lkb))
			return 1;
	}
	return 0;
}

/*
 * "A conversion deadlock arises with a pair of lock requests in the converting
 * queue for one resource.  The granted mode of each lock blocks the requested
 * mode of the other lock."
 *
 * Part 2: if the granted mode of lkb is preventing an earlier lkb in the
 * convert queue from being granted, then deadlk/demote lkb.
 *
 * Example:
 * Granted Queue: empty
 * Convert Queue: NL->EX (first lock)
 *                PR->EX (second lock)
 *
 * The first lock can't be granted because of the granted mode of the second
 * lock and the second lock can't be granted because it's not first in the
 * list.  We either cancel lkb's conversion (PR->EX) and return EDEADLK, or we
 * demote the granted mode of lkb (from PR to NL) if it has the CONVDEADLK
 * flag set and return DEMOTED in the lksb flags.
 *
 * Originally, this function detected conv-deadlk in a more limited scope:
 * - if !modes_compat(lkb1, lkb2) && !modes_compat(lkb2, lkb1), or
 * - if lkb1 was the first entry in the queue (not just earlier), and was
 *   blocked by the granted mode of lkb2, and there was nothing on the
 *   granted queue preventing lkb1 from being granted immediately, i.e.
 *   lkb2 was the only thing preventing lkb1 from being granted.
 *
 * That second condition meant we'd only say there was conv-deadlk if
 * resolving it (by demotion) would lead to the first lock on the convert
 * queue being granted right away.  It allowed conversion deadlocks to exist
 * between locks on the convert queue while they couldn't be granted anyway.
 *
 * Now, we detect and take action on conversion deadlocks immediately when
 * they're created, even if they may not be immediately consequential.  If
 * lkb1 exists anywhere in the convert queue and lkb2 comes in with a granted
 * mode that would prevent lkb1's conversion from being granted, we do a
 * deadlk/demote on lkb2 right away and don't let it onto the convert queue.
 * I think this means that the lkb_is_ahead condition below should always
 * be zero, i.e. there will never be conv-deadlk between two locks that are
 * both already on the convert queue.
 */

static int conversion_deadlock_detect(struct dlm_rsb *r, struct dlm_lkb *lkb2)
{
	struct dlm_lkb *lkb1;
	int lkb_is_ahead = 0;

	list_for_each_entry(lkb1, &r->res_convertqueue, lkb_statequeue) {
		if (lkb1 == lkb2) {
			lkb_is_ahead = 1;
			continue;
		}

		if (!lkb_is_ahead) {
			if (!modes_compat(lkb2, lkb1))
				return 1;
		} else {
			if (!modes_compat(lkb2, lkb1) &&
			    !modes_compat(lkb1, lkb2))
				return 1;
		}
	}
	return 0;
}

/*
 * Return 1 if the lock can be granted, 0 otherwise.
 * Also detect and resolve conversion deadlocks.
 *
 * lkb is the lock to be granted
 *
 * now is 1 if the function is being called in the context of the
 * immediate request, it is 0 if called later, after the lock has been
 * queued.
 *
 * recover is 1 if dlm_recover_grant() is trying to grant conversions
 * after recovery.
 *
 * References are from chapter 6 of "VAXcluster Principles" by Roy Davis
 */

static int _can_be_granted(struct dlm_rsb *r, struct dlm_lkb *lkb, int now,
			   int recover)
{
	int8_t conv = (lkb->lkb_grmode != DLM_LOCK_IV);

	/*
	 * 6-10: Version 5.4 introduced an option to address the phenomenon of
	 * a new request for a NL mode lock being blocked.
	 *
	 * 6-11: If the optional EXPEDITE flag is used with the new NL mode
	 * request, then it would be granted.  In essence, the use of this flag
	 * tells the Lock Manager to expedite theis request by not considering
	 * what may be in the CONVERTING or WAITING queues...  As of this
	 * writing, the EXPEDITE flag can be used only with new requests for NL
	 * mode locks.  This flag is not valid for conversion requests.
	 *
	 * A shortcut.  Earlier checks return an error if EXPEDITE is used in a
	 * conversion or used with a non-NL requested mode.  We also know an
	 * EXPEDITE request is always granted immediately, so now must always
	 * be 1.  The full condition to grant an expedite request: (now &&
	 * !conv && lkb->rqmode == DLM_LOCK_NL && (flags & EXPEDITE)) can
	 * therefore be shortened to just checking the flag.
	 */

	if (lkb->lkb_exflags & DLM_LKF_EXPEDITE)
		return 1;

	/*
	 * A shortcut. Without this, !queue_conflict(grantqueue, lkb) would be
	 * added to the remaining conditions.
	 */

	if (queue_conflict(&r->res_grantqueue, lkb))
		return 0;

	/*
	 * 6-3: By default, a conversion request is immediately granted if the
	 * requested mode is compatible with the modes of all other granted
	 * locks
	 */

	if (queue_conflict(&r->res_convertqueue, lkb))
		return 0;

	/*
	 * The RECOVER_GRANT flag means dlm_recover_grant() is granting
	 * locks for a recovered rsb, on which lkb's have been rebuilt.
	 * The lkb's may have been rebuilt on the queues in a different
	 * order than they were in on the previous master.  So, granting
	 * queued conversions in order after recovery doesn't make sense
	 * since the order hasn't been preserved anyway.  The new order
	 * could also have created a new "in place" conversion deadlock.
	 * (e.g. old, failed master held granted EX, with PR->EX, NL->EX.
	 * After recovery, there would be no granted locks, and possibly
	 * NL->EX, PR->EX, an in-place conversion deadlock.)  So, after
	 * recovery, grant conversions without considering order.
	 */

	if (conv && recover)
		return 1;

	/*
	 * 6-5: But the default algorithm for deciding whether to grant or
	 * queue conversion requests does not by itself guarantee that such
	 * requests are serviced on a "first come first serve" basis.  This, in
	 * turn, can lead to a phenomenon known as "indefinate postponement".
	 *
	 * 6-7: This issue is dealt with by using the optional QUECVT flag with
	 * the system service employed to request a lock conversion.  This flag
	 * forces certain conversion requests to be queued, even if they are
	 * compatible with the granted modes of other locks on the same
	 * resource.  Thus, the use of this flag results in conversion requests
	 * being ordered on a "first come first servce" basis.
	 *
	 * DCT: This condition is all about new conversions being able to occur
	 * "in place" while the lock remains on the granted queue (assuming
	 * nothing else conflicts.)  IOW if QUECVT isn't set, a conversion
	 * doesn't _have_ to go onto the convert queue where it's processed in
	 * order.  The "now" variable is necessary to distinguish converts
	 * being received and processed for the first time now, because once a
	 * convert is moved to the conversion queue the condition below applies
	 * requiring fifo granting.
	 */

	if (now && conv && !(lkb->lkb_exflags & DLM_LKF_QUECVT))
		return 1;

	/*
	 * Even if the convert is compat with all granted locks,
	 * QUECVT forces it behind other locks on the convert queue.
	 */

	if (now && conv && (lkb->lkb_exflags & DLM_LKF_QUECVT)) {
		if (list_empty(&r->res_convertqueue))
			return 1;
		else
			return 0;
	}

	/*
	 * The NOORDER flag is set to avoid the standard vms rules on grant
	 * order.
	 */

	if (lkb->lkb_exflags & DLM_LKF_NOORDER)
		return 1;

	/*
	 * 6-3: Once in that queue [CONVERTING], a conversion request cannot be
	 * granted until all other conversion requests ahead of it are granted
	 * and/or canceled.
	 */

	if (!now && conv && first_in_list(lkb, &r->res_convertqueue))
		return 1;

	/*
	 * 6-4: By default, a new request is immediately granted only if all
	 * three of the following conditions are satisfied when the request is
	 * issued:
	 * - The queue of ungranted conversion requests for the resource is
	 *   empty.
	 * - The queue of ungranted new requests for the resource is empty.
	 * - The mode of the new request is compatible with the most
	 *   restrictive mode of all granted locks on the resource.
	 */

	if (now && !conv && list_empty(&r->res_convertqueue) &&
	    list_empty(&r->res_waitqueue))
		return 1;

	/*
	 * 6-4: Once a lock request is in the queue of ungranted new requests,
	 * it cannot be granted until the queue of ungranted conversion
	 * requests is empty, all ungranted new requests ahead of it are
	 * granted and/or canceled, and it is compatible with the granted mode
	 * of the most restrictive lock granted on the resource.
	 */

	if (!now && !conv && list_empty(&r->res_convertqueue) &&
	    first_in_list(lkb, &r->res_waitqueue))
		return 1;

	return 0;
}

static int can_be_granted(struct dlm_rsb *r, struct dlm_lkb *lkb, int now,
			  int recover, int *err)
{
	int rv;
	int8_t alt = 0, rqmode = lkb->lkb_rqmode;
	int8_t is_convert = (lkb->lkb_grmode != DLM_LOCK_IV);

	if (err)
		*err = 0;

	rv = _can_be_granted(r, lkb, now, recover);
	if (rv)
		goto out;

	/*
	 * The CONVDEADLK flag is non-standard and tells the dlm to resolve
	 * conversion deadlocks by demoting grmode to NL, otherwise the dlm
	 * cancels one of the locks.
	 */

	if (is_convert && can_be_queued(lkb) &&
	    conversion_deadlock_detect(r, lkb)) {
		if (lkb->lkb_exflags & DLM_LKF_CONVDEADLK) {
			lkb->lkb_grmode = DLM_LOCK_NL;
			lkb->lkb_sbflags |= DLM_SBF_DEMOTED;
		} else if (!(lkb->lkb_exflags & DLM_LKF_NODLCKWT)) {
			if (err)
				*err = -EDEADLK;
			else {
				log_print("can_be_granted deadlock %x now %d",
					  lkb->lkb_id, now);
				dlm_dump_rsb(r);
			}
		}
		goto out;
	}

	/*
	 * The ALTPR and ALTCW flags are non-standard and tell the dlm to try
	 * to grant a request in a mode other than the normal rqmode.  It's a
	 * simple way to provide a big optimization to applications that can
	 * use them.
	 */

	if (rqmode != DLM_LOCK_PR && (lkb->lkb_exflags & DLM_LKF_ALTPR))
		alt = DLM_LOCK_PR;
	else if (rqmode != DLM_LOCK_CW && (lkb->lkb_exflags & DLM_LKF_ALTCW))
		alt = DLM_LOCK_CW;

	if (alt) {
		lkb->lkb_rqmode = alt;
		rv = _can_be_granted(r, lkb, now, 0);
		if (rv)
			lkb->lkb_sbflags |= DLM_SBF_ALTMODE;
		else
			lkb->lkb_rqmode = rqmode;
	}
 out:
	return rv;
}

/* FIXME: I don't think that can_be_granted() can/will demote or find deadlock
   for locks pending on the convert list.  Once verified (watch for these
   log_prints), we should be able to just call _can_be_granted() and not
   bother with the demote/deadlk cases here (and there's no easy way to deal
   with a deadlk here, we'd have to generate something like grant_lock with
   the deadlk error.) */

/* Returns the highest requested mode of all blocked conversions; sets
   cw if there's a blocked conversion to DLM_LOCK_CW. */

static int grant_pending_convert(struct dlm_rsb *r, int high, int *cw,
				 unsigned int *count)
{
	struct dlm_lkb *lkb, *s;
	int recover = rsb_flag(r, RSB_RECOVER_GRANT);
	int hi, demoted, quit, grant_restart, demote_restart;
	int deadlk;

	quit = 0;
 restart:
	grant_restart = 0;
	demote_restart = 0;
	hi = DLM_LOCK_IV;

	list_for_each_entry_safe(lkb, s, &r->res_convertqueue, lkb_statequeue) {
		demoted = is_demoted(lkb);
		deadlk = 0;

		if (can_be_granted(r, lkb, 0, recover, &deadlk)) {
			grant_lock_pending(r, lkb);
			grant_restart = 1;
			if (count)
				(*count)++;
			continue;
		}

		if (!demoted && is_demoted(lkb)) {
			log_print("WARN: pending demoted %x node %d %s",
				  lkb->lkb_id, lkb->lkb_nodeid, r->res_name);
			demote_restart = 1;
			continue;
		}

		if (deadlk) {
			log_print("WARN: pending deadlock %x node %d %s",
				  lkb->lkb_id, lkb->lkb_nodeid, r->res_name);
			dlm_dump_rsb(r);
			continue;
		}

		hi = max_t(int, lkb->lkb_rqmode, hi);

		if (cw && lkb->lkb_rqmode == DLM_LOCK_CW)
			*cw = 1;
	}

	if (grant_restart)
		goto restart;
	if (demote_restart && !quit) {
		quit = 1;
		goto restart;
	}

	return max_t(int, high, hi);
}

static int grant_pending_wait(struct dlm_rsb *r, int high, int *cw,
			      unsigned int *count)
{
	struct dlm_lkb *lkb, *s;

	list_for_each_entry_safe(lkb, s, &r->res_waitqueue, lkb_statequeue) {
		if (can_be_granted(r, lkb, 0, 0, NULL)) {
			grant_lock_pending(r, lkb);
			if (count)
				(*count)++;
		} else {
			high = max_t(int, lkb->lkb_rqmode, high);
			if (lkb->lkb_rqmode == DLM_LOCK_CW)
				*cw = 1;
		}
	}

	return high;
}

/* cw of 1 means there's a lock with a rqmode of DLM_LOCK_CW that's blocked
   on either the convert or waiting queue.
   high is the largest rqmode of all locks blocked on the convert or
   waiting queue. */

static int lock_requires_bast(struct dlm_lkb *gr, int high, int cw)
{
	if (gr->lkb_grmode == DLM_LOCK_PR && cw) {
		if (gr->lkb_highbast < DLM_LOCK_EX)
			return 1;
		return 0;
	}

	if (gr->lkb_highbast < high &&
	    !__dlm_compat_matrix[gr->lkb_grmode+1][high+1])
		return 1;
	return 0;
}

static void grant_pending_locks(struct dlm_rsb *r, unsigned int *count)
{
	struct dlm_lkb *lkb, *s;
	int high = DLM_LOCK_IV;
	int cw = 0;

	if (!is_master(r)) {
		log_print("grant_pending_locks r nodeid %d", r->res_nodeid);
		dlm_dump_rsb(r);
		return;
	}

	high = grant_pending_convert(r, high, &cw, count);
	high = grant_pending_wait(r, high, &cw, count);

	if (high == DLM_LOCK_IV)
		return;

	/*
	 * If there are locks left on the wait/convert queue then send blocking
	 * ASTs to granted locks based on the largest requested mode (high)
	 * found above.
	 */

	list_for_each_entry_safe(lkb, s, &r->res_grantqueue, lkb_statequeue) {
		if (lkb->lkb_bastfn && lock_requires_bast(lkb, high, cw)) {
			if (cw && high == DLM_LOCK_PR &&
			    lkb->lkb_grmode == DLM_LOCK_PR)
				queue_bast(r, lkb, DLM_LOCK_CW);
			else
				queue_bast(r, lkb, high);
			lkb->lkb_highbast = high;
		}
	}
}

static int modes_require_bast(struct dlm_lkb *gr, struct dlm_lkb *rq)
{
	if ((gr->lkb_grmode == DLM_LOCK_PR && rq->lkb_rqmode == DLM_LOCK_CW) ||
	    (gr->lkb_grmode == DLM_LOCK_CW && rq->lkb_rqmode == DLM_LOCK_PR)) {
		if (gr->lkb_highbast < DLM_LOCK_EX)
			return 1;
		return 0;
	}

	if (gr->lkb_highbast < rq->lkb_rqmode && !modes_compat(gr, rq))
		return 1;
	return 0;
}

static void send_bast_queue(struct dlm_rsb *r, struct list_head *head,
			    struct dlm_lkb *lkb)
{
	struct dlm_lkb *gr;

	list_for_each_entry(gr, head, lkb_statequeue) {
		/* skip self when sending basts to convertqueue */
		if (gr == lkb)
			continue;
		if (gr->lkb_bastfn && modes_require_bast(gr, lkb)) {
			queue_bast(r, gr, lkb->lkb_rqmode);
			gr->lkb_highbast = lkb->lkb_rqmode;
		}
	}
}

static void send_blocking_asts(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	send_bast_queue(r, &r->res_grantqueue, lkb);
}

static void send_blocking_asts_all(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	send_bast_queue(r, &r->res_grantqueue, lkb);
	send_bast_queue(r, &r->res_convertqueue, lkb);
}

/* set_master(r, lkb) -- set the master nodeid of a resource

   The purpose of this function is to set the nodeid field in the given
   lkb using the nodeid field in the given rsb.  If the rsb's nodeid is
   known, it can just be copied to the lkb and the function will return
   0.  If the rsb's nodeid is _not_ known, it needs to be looked up
   before it can be copied to the lkb.

   When the rsb nodeid is being looked up remotely, the initial lkb
   causing the lookup is kept on the ls_waiters list waiting for the
   lookup reply.  Other lkb's waiting for the same rsb lookup are kept
   on the rsb's res_lookup list until the master is verified.

   Return values:
   0: nodeid is set in rsb/lkb and the caller should go ahead and use it
   1: the rsb master is not available and the lkb has been placed on
      a wait queue
*/

static int set_master(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	int our_nodeid = dlm_our_nodeid();

	if (rsb_flag(r, RSB_MASTER_UNCERTAIN)) {
		rsb_clear_flag(r, RSB_MASTER_UNCERTAIN);
		r->res_first_lkid = lkb->lkb_id;
		lkb->lkb_nodeid = r->res_nodeid;
		return 0;
	}

	if (r->res_first_lkid && r->res_first_lkid != lkb->lkb_id) {
		list_add_tail(&lkb->lkb_rsb_lookup, &r->res_lookup);
		return 1;
	}

	if (r->res_master_nodeid == our_nodeid) {
		lkb->lkb_nodeid = 0;
		return 0;
	}

	if (r->res_master_nodeid) {
		lkb->lkb_nodeid = r->res_master_nodeid;
		return 0;
	}

	if (dlm_dir_nodeid(r) == our_nodeid) {
		/* This is a somewhat unusual case; find_rsb will usually
		   have set res_master_nodeid when dir nodeid is local, but
		   there are cases where we become the dir node after we've
		   past find_rsb and go through _request_lock again.
		   confirm_master() or process_lookup_list() needs to be
		   called after this. */
		log_debug(r->res_ls, "set_master %x self master %d dir %d %s",
			  lkb->lkb_id, r->res_master_nodeid, r->res_dir_nodeid,
			  r->res_name);
		r->res_master_nodeid = our_nodeid;
		r->res_nodeid = 0;
		lkb->lkb_nodeid = 0;
		return 0;
	}

	wait_pending_remove(r);

	r->res_first_lkid = lkb->lkb_id;
	send_lookup(r, lkb);
	return 1;
}

static void process_lookup_list(struct dlm_rsb *r)
{
	struct dlm_lkb *lkb, *safe;

	list_for_each_entry_safe(lkb, safe, &r->res_lookup, lkb_rsb_lookup) {
		list_del_init(&lkb->lkb_rsb_lookup);
		_request_lock(r, lkb);
		schedule();
	}
}

/* confirm_master -- confirm (or deny) an rsb's master nodeid */

static void confirm_master(struct dlm_rsb *r, int error)
{
	struct dlm_lkb *lkb;

	if (!r->res_first_lkid)
		return;

	switch (error) {
	case 0:
	case -EINPROGRESS:
		r->res_first_lkid = 0;
		process_lookup_list(r);
		break;

	case -EAGAIN:
	case -EBADR:
	case -ENOTBLK:
		/* the remote request failed and won't be retried (it was
		   a NOQUEUE, or has been canceled/unlocked); make a waiting
		   lkb the first_lkid */

		r->res_first_lkid = 0;

		if (!list_empty(&r->res_lookup)) {
			lkb = list_entry(r->res_lookup.next, struct dlm_lkb,
					 lkb_rsb_lookup);
			list_del_init(&lkb->lkb_rsb_lookup);
			r->res_first_lkid = lkb->lkb_id;
			_request_lock(r, lkb);
		}
		break;

	default:
		log_error(r->res_ls, "confirm_master unknown error %d", error);
	}
}

static int set_lock_args(int mode, struct dlm_lksb *lksb, uint32_t flags,
			 int namelen, unsigned long timeout_cs,
			 void (*ast) (void *astparam),
			 void *astparam,
			 void (*bast) (void *astparam, int mode),
			 struct dlm_args *args)
{
	int rv = -EINVAL;

	/* check for invalid arg usage */

	if (mode < 0 || mode > DLM_LOCK_EX)
		goto out;

	if (!(flags & DLM_LKF_CONVERT) && (namelen > DLM_RESNAME_MAXLEN))
		goto out;

	if (flags & DLM_LKF_CANCEL)
		goto out;

	if (flags & DLM_LKF_QUECVT && !(flags & DLM_LKF_CONVERT))
		goto out;

	if (flags & DLM_LKF_CONVDEADLK && !(flags & DLM_LKF_CONVERT))
		goto out;

	if (flags & DLM_LKF_CONVDEADLK && flags & DLM_LKF_NOQUEUE)
		goto out;

	if (flags & DLM_LKF_EXPEDITE && flags & DLM_LKF_CONVERT)
		goto out;

	if (flags & DLM_LKF_EXPEDITE && flags & DLM_LKF_QUECVT)
		goto out;

	if (flags & DLM_LKF_EXPEDITE && flags & DLM_LKF_NOQUEUE)
		goto out;

	if (flags & DLM_LKF_EXPEDITE && mode != DLM_LOCK_NL)
		goto out;

	if (!ast || !lksb)
		goto out;

	if (flags & DLM_LKF_VALBLK && !lksb->sb_lvbptr)
		goto out;

	if (flags & DLM_LKF_CONVERT && !lksb->sb_lkid)
		goto out;

	/* these args will be copied to the lkb in validate_lock_args,
	   it cannot be done now because when converting locks, fields in
	   an active lkb cannot be modified before locking the rsb */

	args->flags = flags;
	args->astfn = ast;
	args->astparam = astparam;
	args->bastfn = bast;
	args->timeout = timeout_cs;
	args->mode = mode;
	args->lksb = lksb;
	rv = 0;
 out:
	return rv;
}

static int set_unlock_args(uint32_t flags, void *astarg, struct dlm_args *args)
{
	if (flags & ~(DLM_LKF_CANCEL | DLM_LKF_VALBLK | DLM_LKF_IVVALBLK |
 		      DLM_LKF_FORCEUNLOCK))
		return -EINVAL;

	if (flags & DLM_LKF_CANCEL && flags & DLM_LKF_FORCEUNLOCK)
		return -EINVAL;

	args->flags = flags;
	args->astparam = astarg;
	return 0;
}

static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
			      struct dlm_args *args)
{
	int rv = -EINVAL;

	if (args->flags & DLM_LKF_CONVERT) {
		if (lkb->lkb_flags & DLM_IFL_MSTCPY)
			goto out;

		if (args->flags & DLM_LKF_QUECVT &&
		    !__quecvt_compat_matrix[lkb->lkb_grmode+1][args->mode+1])
			goto out;

		rv = -EBUSY;
		if (lkb->lkb_status != DLM_LKSTS_GRANTED)
			goto out;

		if (lkb->lkb_wait_type)
			goto out;

		if (is_overlap(lkb))
			goto out;
	}

	lkb->lkb_exflags = args->flags;
	lkb->lkb_sbflags = 0;
	lkb->lkb_astfn = args->astfn;
	lkb->lkb_astparam = args->astparam;
	lkb->lkb_bastfn = args->bastfn;
	lkb->lkb_rqmode = args->mode;
	lkb->lkb_lksb = args->lksb;
	lkb->lkb_lvbptr = args->lksb->sb_lvbptr;
	lkb->lkb_ownpid = (int) current->pid;
	lkb->lkb_timeout_cs = args->timeout;
	rv = 0;
 out:
	if (rv)
		log_debug(ls, "validate_lock_args %d %x %x %x %d %d %s",
			  rv, lkb->lkb_id, lkb->lkb_flags, args->flags,
			  lkb->lkb_status, lkb->lkb_wait_type,
			  lkb->lkb_resource->res_name);
	return rv;
}

/* when dlm_unlock() sees -EBUSY with CANCEL/FORCEUNLOCK it returns 0
   for success */

/* note: it's valid for lkb_nodeid/res_nodeid to be -1 when we get here
   because there may be a lookup in progress and it's valid to do
   cancel/unlockf on it */

static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args)
{
	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
	int rv = -EINVAL;

	if (lkb->lkb_flags & DLM_IFL_MSTCPY) {
		log_error(ls, "unlock on MSTCPY %x", lkb->lkb_id);
		dlm_print_lkb(lkb);
		goto out;
	}

	/* an lkb may still exist even though the lock is EOL'ed due to a
	   cancel, unlock or failed noqueue request; an app can't use these
	   locks; return same error as if the lkid had not been found at all */

	if (lkb->lkb_flags & DLM_IFL_ENDOFLIFE) {
		log_debug(ls, "unlock on ENDOFLIFE %x", lkb->lkb_id);
		rv = -ENOENT;
		goto out;
	}

	/* an lkb may be waiting for an rsb lookup to complete where the
	   lookup was initiated by another lock */

	if (!list_empty(&lkb->lkb_rsb_lookup)) {
		if (args->flags & (DLM_LKF_CANCEL | DLM_LKF_FORCEUNLOCK)) {
			log_debug(ls, "unlock on rsb_lookup %x", lkb->lkb_id);
			list_del_init(&lkb->lkb_rsb_lookup);
			queue_cast(lkb->lkb_resource, lkb,
				   args->flags & DLM_LKF_CANCEL ?
				   -DLM_ECANCEL : -DLM_EUNLOCK);
			unhold_lkb(lkb); /* undoes create_lkb() */
		}
		/* caller changes -EBUSY to 0 for CANCEL and FORCEUNLOCK */
		rv = -EBUSY;
		goto out;
	}

	/* cancel not allowed with another cancel/unlock in progress */

	if (args->flags & DLM_LKF_CANCEL) {
		if (lkb->lkb_exflags & DLM_LKF_CANCEL)
			goto out;

		if (is_overlap(lkb))
			goto out;

		/* don't let scand try to do a cancel */
		del_timeout(lkb);

		if (lkb->lkb_flags & DLM_IFL_RESEND) {
			lkb->lkb_flags |= DLM_IFL_OVERLAP_CANCEL;
			rv = -EBUSY;
			goto out;
		}

		/* there's nothing to cancel */
		if (lkb->lkb_status == DLM_LKSTS_GRANTED &&
		    !lkb->lkb_wait_type) {
			rv = -EBUSY;
			goto out;
		}

		switch (lkb->lkb_wait_type) {
		case DLM_MSG_LOOKUP:
		case DLM_MSG_REQUEST:
			lkb->lkb_flags |= DLM_IFL_OVERLAP_CANCEL;
			rv = -EBUSY;
			goto out;
		case DLM_MSG_UNLOCK:
		case DLM_MSG_CANCEL:
			goto out;
		}
		/* add_to_waiters() will set OVERLAP_CANCEL */
		goto out_ok;
	}

	/* do we need to allow a force-unlock if there's a normal unlock
	   already in progress?  in what conditions could the normal unlock
	   fail such that we'd want to send a force-unlock to be sure? */

	if (args->flags & DLM_LKF_FORCEUNLOCK) {
		if (lkb->lkb_exflags & DLM_LKF_FORCEUNLOCK)
			goto out;

		if (is_overlap_unlock(lkb))
			goto out;

		/* don't let scand try to do a cancel */
		del_timeout(lkb);

		if (lkb->lkb_flags & DLM_IFL_RESEND) {
			lkb->lkb_flags |= DLM_IFL_OVERLAP_UNLOCK;
			rv = -EBUSY;
			goto out;
		}

		switch (lkb->lkb_wait_type) {
		case DLM_MSG_LOOKUP:
		case DLM_MSG_REQUEST:
			lkb->lkb_flags |= DLM_IFL_OVERLAP_UNLOCK;
			rv = -EBUSY;
			goto out;
		case DLM_MSG_UNLOCK:
			goto out;
		}
		/* add_to_waiters() will set OVERLAP_UNLOCK */
		goto out_ok;
	}

	/* normal unlock not allowed if there's any op in progress */
	rv = -EBUSY;
	if (lkb->lkb_wait_type || lkb->lkb_wait_count)
		goto out;

 out_ok:
	/* an overlapping op shouldn't blow away exflags from other op */
	lkb->lkb_exflags |= args->flags;
	lkb->lkb_sbflags = 0;
	lkb->lkb_astparam = args->astparam;
	rv = 0;
 out:
	if (rv)
		log_debug(ls, "validate_unlock_args %d %x %x %x %x %d %s", rv,
			  lkb->lkb_id, lkb->lkb_flags, lkb->lkb_exflags,
			  args->flags, lkb->lkb_wait_type,
			  lkb->lkb_resource->res_name);
	return rv;
}

/*
 * Four stage 4 varieties:
 * do_request(), do_convert(), do_unlock(), do_cancel()
 * These are called on the master node for the given lock and
 * from the central locking logic.
 */

static int do_request(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	int error = 0;

	if (can_be_granted(r, lkb, 1, 0, NULL)) {
		grant_lock(r, lkb);
		queue_cast(r, lkb, 0);
		goto out;
	}

	if (can_be_queued(lkb)) {
		error = -EINPROGRESS;
		add_lkb(r, lkb, DLM_LKSTS_WAITING);
		add_timeout(lkb);
		goto out;
	}

	error = -EAGAIN;
	queue_cast(r, lkb, -EAGAIN);
 out:
	return error;
}

static void do_request_effects(struct dlm_rsb *r, struct dlm_lkb *lkb,
			       int error)
{
	switch (error) {
	case -EAGAIN:
		if (force_blocking_asts(lkb))
			send_blocking_asts_all(r, lkb);
		break;
	case -EINPROGRESS:
		send_blocking_asts(r, lkb);
		break;
	}
}

static int do_convert(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	int error = 0;
	int deadlk = 0;

	/* changing an existing lock may allow others to be granted */

	if (can_be_granted(r, lkb, 1, 0, &deadlk)) {
		grant_lock(r, lkb);
		queue_cast(r, lkb, 0);
		goto out;
	}

	/* can_be_granted() detected that this lock would block in a conversion
	   deadlock, so we leave it on the granted queue and return EDEADLK in
	   the ast for the convert. */

	if (deadlk) {
		/* it's left on the granted queue */
		revert_lock(r, lkb);
		queue_cast(r, lkb, -EDEADLK);
		error = -EDEADLK;
		goto out;
	}

	/* is_demoted() means the can_be_granted() above set the grmode
	   to NL, and left us on the granted queue.  This auto-demotion
	   (due to CONVDEADLK) might mean other locks, and/or this lock, are
	   now grantable.  We have to try to grant other converting locks
	   before we try again to grant this one. */

	if (is_demoted(lkb)) {
		grant_pending_convert(r, DLM_LOCK_IV, NULL, NULL);
		if (_can_be_granted(r, lkb, 1, 0)) {
			grant_lock(r, lkb);
			queue_cast(r, lkb, 0);
			goto out;
		}
		/* else fall through and move to convert queue */
	}

	if (can_be_queued(lkb)) {
		error = -EINPROGRESS;
		del_lkb(r, lkb);
		add_lkb(r, lkb, DLM_LKSTS_CONVERT);
		add_timeout(lkb);
		goto out;
	}

	error = -EAGAIN;
	queue_cast(r, lkb, -EAGAIN);
 out:
	return error;
}

static void do_convert_effects(struct dlm_rsb *r, struct dlm_lkb *lkb,
			       int error)
{
	switch (error) {
	case 0:
		grant_pending_locks(r, NULL);
		/* grant_pending_locks also sends basts */
		break;
	case -EAGAIN:
		if (force_blocking_asts(lkb))
			send_blocking_asts_all(r, lkb);
		break;
	case -EINPROGRESS:
		send_blocking_asts(r, lkb);
		break;
	}
}

static int do_unlock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	remove_lock(r, lkb);
	queue_cast(r, lkb, -DLM_EUNLOCK);
	return -DLM_EUNLOCK;
}

static void do_unlock_effects(struct dlm_rsb *r, struct dlm_lkb *lkb,
			      int error)
{
	grant_pending_locks(r, NULL);
}

/* returns: 0 did nothing, -DLM_ECANCEL canceled lock */

static int do_cancel(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	int error;

	error = revert_lock(r, lkb);
	if (error) {
		queue_cast(r, lkb, -DLM_ECANCEL);
		return -DLM_ECANCEL;
	}
	return 0;
}

static void do_cancel_effects(struct dlm_rsb *r, struct dlm_lkb *lkb,
			      int error)
{
	if (error)
		grant_pending_locks(r, NULL);
}

/*
 * Four stage 3 varieties:
 * _request_lock(), _convert_lock(), _unlock_lock(), _cancel_lock()
 */

/* add a new lkb to a possibly new rsb, called by requesting process */

static int _request_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	int error;

	/* set_master: sets lkb nodeid from r */

	error = set_master(r, lkb);
	if (error < 0)
		goto out;
	if (error) {
		error = 0;
		goto out;
	}

	if (is_remote(r)) {
		/* receive_request() calls do_request() on remote node */
		error = send_request(r, lkb);
	} else {
		error = do_request(r, lkb);
		/* for remote locks the request_reply is sent
		   between do_request and do_request_effects */
		do_request_effects(r, lkb, error);
	}
 out:
	return error;
}

/* change some property of an existing lkb, e.g. mode */

static int _convert_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	int error;

	if (is_remote(r)) {
		/* receive_convert() calls do_convert() on remote node */
		error = send_convert(r, lkb);
	} else {
		error = do_convert(r, lkb);
		/* for remote locks the convert_reply is sent
		   between do_convert and do_convert_effects */
		do_convert_effects(r, lkb, error);
	}

	return error;
}

/* remove an existing lkb from the granted queue */

static int _unlock_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	int error;

	if (is_remote(r)) {
		/* receive_unlock() calls do_unlock() on remote node */
		error = send_unlock(r, lkb);
	} else {
		error = do_unlock(r, lkb);
		/* for remote locks the unlock_reply is sent
		   between do_unlock and do_unlock_effects */
		do_unlock_effects(r, lkb, error);
	}

	return error;
}

/* remove an existing lkb from the convert or wait queue */

static int _cancel_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	int error;

	if (is_remote(r)) {
		/* receive_cancel() calls do_cancel() on remote node */
		error = send_cancel(r, lkb);
	} else {
		error = do_cancel(r, lkb);
		/* for remote locks the cancel_reply is sent
		   between do_cancel and do_cancel_effects */
		do_cancel_effects(r, lkb, error);
	}

	return error;
}

/*
 * Four stage 2 varieties:
 * request_lock(), convert_lock(), unlock_lock(), cancel_lock()
 */

static int request_lock(struct dlm_ls *ls, struct dlm_lkb *lkb, char *name,
			int len, struct dlm_args *args)
{
	struct dlm_rsb *r;
	int error;

	error = validate_lock_args(ls, lkb, args);
	if (error)
		return error;

	error = find_rsb(ls, name, len, 0, R_REQUEST, &r);
	if (error)
		return error;

	lock_rsb(r);

	attach_lkb(r, lkb);
	lkb->lkb_lksb->sb_lkid = lkb->lkb_id;

	error = _request_lock(r, lkb);

	unlock_rsb(r);
	put_rsb(r);
	return error;
}

static int convert_lock(struct dlm_ls *ls, struct dlm_lkb *lkb,
			struct dlm_args *args)
{
	struct dlm_rsb *r;
	int error;

	r = lkb->lkb_resource;

	hold_rsb(r);
	lock_rsb(r);

	error = validate_lock_args(ls, lkb, args);
	if (error)
		goto out;

	error = _convert_lock(r, lkb);
 out:
	unlock_rsb(r);
	put_rsb(r);
	return error;
}

static int unlock_lock(struct dlm_ls *ls, struct dlm_lkb *lkb,
		       struct dlm_args *args)
{
	struct dlm_rsb *r;
	int error;

	r = lkb->lkb_resource;

	hold_rsb(r);
	lock_rsb(r);

	error = validate_unlock_args(lkb, args);
	if (error)
		goto out;

	error = _unlock_lock(r, lkb);
 out:
	unlock_rsb(r);
	put_rsb(r);
	return error;
}

static int cancel_lock(struct dlm_ls *ls, struct dlm_lkb *lkb,
		       struct dlm_args *args)
{
	struct dlm_rsb *r;
	int error;

	r = lkb->lkb_resource;

	hold_rsb(r);
	lock_rsb(r);

	error = validate_unlock_args(lkb, args);
	if (error)
		goto out;

	error = _cancel_lock(r, lkb);
 out:
	unlock_rsb(r);
	put_rsb(r);
	return error;
}

/*
 * Two stage 1 varieties:  dlm_lock() and dlm_unlock()
 */

int dlm_lock(dlm_lockspace_t *lockspace,
	     int mode,
	     struct dlm_lksb *lksb,
	     uint32_t flags,
	     void *name,
	     unsigned int namelen,
	     uint32_t parent_lkid,
	     void (*ast) (void *astarg),
	     void *astarg,
	     void (*bast) (void *astarg, int mode))
{
	struct dlm_ls *ls;
	struct dlm_lkb *lkb;
	struct dlm_args args;
	int error, convert = flags & DLM_LKF_CONVERT;

	ls = dlm_find_lockspace_local(lockspace);
	if (!ls)
		return -EINVAL;

	dlm_lock_recovery(ls);

	if (convert)
		error = find_lkb(ls, lksb->sb_lkid, &lkb);
	else
		error = create_lkb(ls, &lkb);

	if (error)
		goto out;

	error = set_lock_args(mode, lksb, flags, namelen, 0, ast,
			      astarg, bast, &args);
	if (error)
		goto out_put;

	if (convert)
		error = convert_lock(ls, lkb, &args);
	else
		error = request_lock(ls, lkb, name, namelen, &args);

	if (error == -EINPROGRESS)
		error = 0;
 out_put:
	if (convert || error)
		__put_lkb(ls, lkb);
	if (error == -EAGAIN || error == -EDEADLK)
		error = 0;
 out:
	dlm_unlock_recovery(ls);
	dlm_put_lockspace(ls);
	return error;
}

int dlm_unlock(dlm_lockspace_t *lockspace,
	       uint32_t lkid,
	       uint32_t flags,
	       struct dlm_lksb *lksb,
	       void *astarg)
{
	struct dlm_ls *ls;
	struct dlm_lkb *lkb;
	struct dlm_args args;
	int error;

	ls = dlm_find_lockspace_local(lockspace);
	if (!ls)
		return -EINVAL;

	dlm_lock_recovery(ls);

	error = find_lkb(ls, lkid, &lkb);
	if (error)
		goto out;

	error = set_unlock_args(flags, astarg, &args);
	if (error)
		goto out_put;

	if (flags & DLM_LKF_CANCEL)
		error = cancel_lock(ls, lkb, &args);
	else
		error = unlock_lock(ls, lkb, &args);

	if (error == -DLM_EUNLOCK || error == -DLM_ECANCEL)
		error = 0;
	if (error == -EBUSY && (flags & (DLM_LKF_CANCEL | DLM_LKF_FORCEUNLOCK)))
		error = 0;
 out_put:
	dlm_put_lkb(lkb);
 out:
	dlm_unlock_recovery(ls);
	dlm_put_lockspace(ls);
	return error;
}

/*
 * send/receive routines for remote operations and replies
 *
 * send_args
 * send_common
 * send_request			receive_request
 * send_convert			receive_convert
 * send_unlock			receive_unlock
 * send_cancel			receive_cancel
 * send_grant			receive_grant
 * send_bast			receive_bast
 * send_lookup			receive_lookup
 * send_remove			receive_remove
 *
 * 				send_common_reply
 * receive_request_reply	send_request_reply
 * receive_convert_reply	send_convert_reply
 * receive_unlock_reply		send_unlock_reply
 * receive_cancel_reply		send_cancel_reply
 * receive_lookup_reply		send_lookup_reply
 */

static int _create_message(struct dlm_ls *ls, int mb_len,
			   int to_nodeid, int mstype,
			   struct dlm_message **ms_ret,
			   struct dlm_mhandle **mh_ret)
{
	struct dlm_message *ms;
	struct dlm_mhandle *mh;
	char *mb;

	/* get_buffer gives us a message handle (mh) that we need to
	   pass into lowcomms_commit and a message buffer (mb) that we
	   write our data into */

	mh = dlm_lowcomms_get_buffer(to_nodeid, mb_len, GFP_NOFS, &mb);
	if (!mh)
		return -ENOBUFS;

	memset(mb, 0, mb_len);

	ms = (struct dlm_message *) mb;

	ms->m_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
	ms->m_header.h_lockspace = ls->ls_global_id;
	ms->m_header.h_nodeid = dlm_our_nodeid();
	ms->m_header.h_length = mb_len;
	ms->m_header.h_cmd = DLM_MSG;

	ms->m_type = mstype;

	*mh_ret = mh;
	*ms_ret = ms;
	return 0;
}

static int create_message(struct dlm_rsb *r, struct dlm_lkb *lkb,
			  int to_nodeid, int mstype,
			  struct dlm_message **ms_ret,
			  struct dlm_mhandle **mh_ret)
{
	int mb_len = sizeof(struct dlm_message);

	switch (mstype) {
	case DLM_MSG_REQUEST:
	case DLM_MSG_LOOKUP:
	case DLM_MSG_REMOVE:
		mb_len += r->res_length;
		break;
	case DLM_MSG_CONVERT:
	case DLM_MSG_UNLOCK:
	case DLM_MSG_REQUEST_REPLY:
	case DLM_MSG_CONVERT_REPLY:
	case DLM_MSG_GRANT:
		if (lkb && lkb->lkb_lvbptr)
			mb_len += r->res_ls->ls_lvblen;
		break;
	}

	return _create_message(r->res_ls, mb_len, to_nodeid, mstype,
			       ms_ret, mh_ret);
}

/* further lowcomms enhancements or alternate implementations may make
   the return value from this function useful at some point */

static int send_message(struct dlm_mhandle *mh, struct dlm_message *ms)
{
	dlm_message_out(ms);
	dlm_lowcomms_commit_buffer(mh);
	return 0;
}

static void send_args(struct dlm_rsb *r, struct dlm_lkb *lkb,
		      struct dlm_message *ms)
{
	ms->m_nodeid   = lkb->lkb_nodeid;
	ms->m_pid      = lkb->lkb_ownpid;
	ms->m_lkid     = lkb->lkb_id;
	ms->m_remid    = lkb->lkb_remid;
	ms->m_exflags  = lkb->lkb_exflags;
	ms->m_sbflags  = lkb->lkb_sbflags;
	ms->m_flags    = lkb->lkb_flags;
	ms->m_lvbseq   = lkb->lkb_lvbseq;
	ms->m_status   = lkb->lkb_status;
	ms->m_grmode   = lkb->lkb_grmode;
	ms->m_rqmode   = lkb->lkb_rqmode;
	ms->m_hash     = r->res_hash;

	/* m_result and m_bastmode are set from function args,
	   not from lkb fields */

	if (lkb->lkb_bastfn)
		ms->m_asts |= DLM_CB_BAST;
	if (lkb->lkb_astfn)
		ms->m_asts |= DLM_CB_CAST;

	/* compare with switch in create_message; send_remove() doesn't
	   use send_args() */

	switch (ms->m_type) {
	case DLM_MSG_REQUEST:
	case DLM_MSG_LOOKUP:
		memcpy(ms->m_extra, r->res_name, r->res_length);
		break;
	case DLM_MSG_CONVERT:
	case DLM_MSG_UNLOCK:
	case DLM_MSG_REQUEST_REPLY:
	case DLM_MSG_CONVERT_REPLY:
	case DLM_MSG_GRANT:
		if (!lkb->lkb_lvbptr)
			break;
		memcpy(ms->m_extra, lkb->lkb_lvbptr, r->res_ls->ls_lvblen);
		break;
	}
}

static int send_common(struct dlm_rsb *r, struct dlm_lkb *lkb, int mstype)
{
	struct dlm_message *ms;
	struct dlm_mhandle *mh;
	int to_nodeid, error;

	to_nodeid = r->res_nodeid;

	error = add_to_waiters(lkb, mstype, to_nodeid);
	if (error)
		return error;

	error = create_message(r, lkb, to_nodeid, mstype, &ms, &mh);
	if (error)
		goto fail;

	send_args(r, lkb, ms);

	error = send_message(mh, ms);
	if (error)
		goto fail;
	return 0;

 fail:
	remove_from_waiters(lkb, msg_reply_type(mstype));
	return error;
}

static int send_request(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	return send_common(r, lkb, DLM_MSG_REQUEST);
}

static int send_convert(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	int error;

	error = send_common(r, lkb, DLM_MSG_CONVERT);

	/* down conversions go without a reply from the master */
	if (!error && down_conversion(lkb)) {
		remove_from_waiters(lkb, DLM_MSG_CONVERT_REPLY);
		r->res_ls->ls_stub_ms.m_flags = DLM_IFL_STUB_MS;
		r->res_ls->ls_stub_ms.m_type = DLM_MSG_CONVERT_REPLY;
		r->res_ls->ls_stub_ms.m_result = 0;
		__receive_convert_reply(r, lkb, &r->res_ls->ls_stub_ms);
	}

	return error;
}

/* FIXME: if this lkb is the only lock we hold on the rsb, then set
   MASTER_UNCERTAIN to force the next request on the rsb to confirm
   that the master is still correct. */

static int send_unlock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	return send_common(r, lkb, DLM_MSG_UNLOCK);
}

static int send_cancel(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	return send_common(r, lkb, DLM_MSG_CANCEL);
}

static int send_grant(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	struct dlm_message *ms;
	struct dlm_mhandle *mh;
	int to_nodeid, error;

	to_nodeid = lkb->lkb_nodeid;

	error = create_message(r, lkb, to_nodeid, DLM_MSG_GRANT, &ms, &mh);
	if (error)
		goto out;

	send_args(r, lkb, ms);

	ms->m_result = 0;

	error = send_message(mh, ms);
 out:
	return error;
}

static int send_bast(struct dlm_rsb *r, struct dlm_lkb *lkb, int mode)
{
	struct dlm_message *ms;
	struct dlm_mhandle *mh;
	int to_nodeid, error;

	to_nodeid = lkb->lkb_nodeid;

	error = create_message(r, NULL, to_nodeid, DLM_MSG_BAST, &ms, &mh);
	if (error)
		goto out;

	send_args(r, lkb, ms);

	ms->m_bastmode = mode;

	error = send_message(mh, ms);
 out:
	return error;
}

static int send_lookup(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
	struct dlm_message *ms;
	struct dlm_mhandle *mh;
	int to_nodeid, error;

	to_nodeid = dlm_dir_nodeid(r);

	error = add_to_waiters(lkb, DLM_MSG_LOOKUP, to_nodeid);
	if (error)
		return error;

	error = create_message(r, NULL, to_nodeid, DLM_MSG_LOOKUP, &ms, &mh);
	if (error)
		goto fail;

	send_args(r, lkb, ms);

	error = send_message(mh, ms);
	if (error)
		goto fail;
	return 0;

 fail:
	remove_from_waiters(lkb, DLM_MSG_LOOKUP_REPLY);
	return error;
}

static int send_remove(struct dlm_rsb *r)
{
	struct dlm_message *ms;
	struct dlm_mhandle *mh;
	int to_nodeid, error;

	to_nodeid = dlm_dir_nodeid(r);

	error = create_message(r, NULL, to_nodeid, DLM_MSG_REMOVE, &ms, &mh);
	if (error)
		goto out;

	memcpy(ms->m_extra, r->res_name, r->res_length);
	ms->m_hash = r->res_hash;

	error = send_message(mh, ms);
 out:
	return error;
}

static int send_common_reply(struct dlm_rsb *r, struct dlm_lkb *lkb,
			     int mstype, int rv)
{
	struct dlm_message *ms;
	struct dlm_mhandle *mh;
	int to_nodeid, error;

	to_nodeid = lkb->lkb_nodeid;

	error = create_message(r, lkb, to_nodeid, mstype, &ms, &mh);
	if (error)
		goto out;

	send_args(r, lkb, ms);

	ms->m_result = rv;

	error = send_message(mh, ms);
 out:
	return error;
}

static int send_request_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, int rv)
{
	return send_common_reply(r, lkb, DLM_MSG_REQUEST_REPLY, rv);
}

static int send_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, int rv)
{
	return send_common_reply(r, lkb, DLM_MSG_CONVERT_REPLY, rv);
}

static int send_unlock_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, int rv)
{
	return send_common_reply(r, lkb, DLM_MSG_UNLOCK_REPLY, rv);
}

static int send_cancel_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, int rv)
{
	return send_common_reply(r, lkb, DLM_MSG_CANCEL_REPLY, rv);
}

static int send_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms_in,
			     int ret_nodeid, int rv)
{
	struct dlm_rsb *r = &ls->ls_stub_rsb;
	struct dlm_message *ms;
	struct dlm_mhandle *mh;
	int error, nodeid = ms_in->m_header.h_nodeid;

	error = create_message(r, NULL, nodeid, DLM_MSG_LOOKUP_REPLY, &ms, &mh);
	if (error)
		goto out;

	ms->m_lkid = ms_in->m_lkid;
	ms->m_result = rv;
	ms->m_nodeid = ret_nodeid;

	error = send_message(mh, ms);
 out:
	return error;
}

/* which args we save from a received message depends heavily on the type
   of message, unlike the send side where we can safely send everything about
   the lkb for any type of message */

static void receive_flags(struct dlm_lkb *lkb, struct dlm_message *ms)
{
	lkb->lkb_exflags = ms->m_exflags;
	lkb->lkb_sbflags = ms->m_sbflags;
	lkb->lkb_flags = (lkb->lkb_flags & 0xFFFF0000) |
		         (ms->m_flags & 0x0000FFFF);
}

static void receive_flags_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
{
	if (ms->m_flags == DLM_IFL_STUB_MS)
		return;

	lkb->lkb_sbflags = ms->m_sbflags;
	lkb->lkb_flags = (lkb->lkb_flags & 0xFFFF0000) |
		         (ms->m_flags & 0x0000FFFF);
}

static int receive_extralen(struct dlm_message *ms)
{
	return (ms->m_header.h_length - sizeof(struct dlm_message));
}

static int receive_lvb(struct dlm_ls *ls, struct dlm_lkb *lkb,
		       struct dlm_message *ms)
{
	int len;

	if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
		if (!lkb->lkb_lvbptr)
			lkb->lkb_lvbptr = dlm_allocate_lvb(ls);
		if (!lkb->lkb_lvbptr)
			return -ENOMEM;
		len = receive_extralen(ms);
		if (len > ls->ls_lvblen)
			len = ls->ls_lvblen;
		memcpy(lkb->lkb_lvbptr, ms->m_extra, len);
	}
	return 0;
}

static void fake_bastfn(void *astparam, int mode)
{
	log_print("fake_bastfn should not be called");
}

static void fake_astfn(void *astparam)
{
	log_print("fake_astfn should not be called");
}

static int receive_request_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
				struct dlm_message *ms)
{
	lkb->lkb_nodeid = ms->m_header.h_nodeid;
	lkb->lkb_ownpid = ms->m_pid;
	lkb->lkb_remid = ms->m_lkid;
	lkb->lkb_grmode = DLM_LOCK_IV;
	lkb->lkb_rqmode = ms->m_rqmode;

	lkb->lkb_bastfn = (ms->m_asts & DLM_CB_BAST) ? &fake_bastfn : NULL;
	lkb->lkb_astfn = (ms->m_asts & DLM_CB_CAST) ? &fake_astfn : NULL;

	if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
		/* lkb was just created so there won't be an lvb yet */
		lkb->lkb_lvbptr = dlm_allocate_lvb(ls);
		if (!lkb->lkb_lvbptr)
			return -ENOMEM;
	}

	return 0;
}

static int receive_convert_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
				struct dlm_message *ms)
{
	if (lkb->lkb_status != DLM_LKSTS_GRANTED)
		return -EBUSY;

	if (receive_lvb(ls, lkb, ms))
		return -ENOMEM;

	lkb->lkb_rqmode = ms->m_rqmode;
	lkb->lkb_lvbseq = ms->m_lvbseq;

	return 0;
}

static int receive_unlock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
			       struct dlm_message *ms)
{
	if (receive_lvb(ls, lkb, ms))
		return -ENOMEM;
	return 0;
}

/* We fill in the stub-lkb fields with the info that send_xxxx_reply()
   uses to send a reply and that the remote end uses to process the reply. */

static void setup_stub_lkb(struct dlm_ls *ls, struct dlm_message *ms)
{
	struct dlm_lkb *lkb = &ls->ls_stub_lkb;
	lkb->lkb_nodeid = ms->m_header.h_nodeid;
	lkb->lkb_remid = ms->m_lkid;
}

/* This is called after the rsb is locked so that we can safely inspect
   fields in the lkb. */

static int validate_message(struct dlm_lkb *lkb, struct dlm_message *ms)
{
	int from = ms->m_header.h_nodeid;
	int error = 0;

	switch (ms->m_type) {
	case DLM_MSG_CONVERT:
	case DLM_MSG_UNLOCK:
	case DLM_MSG_CANCEL:
		if (!is_master_copy(lkb) || lkb->lkb_nodeid != from)
			error = -EINVAL;
		break;

	case DLM_MSG_CONVERT_REPLY:
	case DLM_MSG_UNLOCK_REPLY:
	case DLM_MSG_CANCEL_REPLY:
	case DLM_MSG_GRANT:
	case DLM_MSG_BAST:
		if (!is_process_copy(lkb) || lkb->lkb_nodeid != from)
			error = -EINVAL;
		break;

	case DLM_MSG_REQUEST_REPLY:
		if (!is_process_copy(lkb))
			error = -EINVAL;
		else if (lkb->lkb_nodeid != -1 && lkb->lkb_nodeid != from)
			error = -EINVAL;
		break;

	default:
		error = -EINVAL;
	}

	if (error)
		log_error(lkb->lkb_resource->res_ls,
			  "ignore invalid message %d from %d %x %x %x %d",
			  ms->m_type, from, lkb->lkb_id, lkb->lkb_remid,
			  lkb->lkb_flags, lkb->lkb_nodeid);
	return error;
}

static void send_repeat_remove(struct dlm_ls *ls, char *ms_name, int len)
{
	char name[DLM_RESNAME_MAXLEN + 1];
	struct dlm_message *ms;
	struct dlm_mhandle *mh;
	struct dlm_rsb *r;
	uint32_t hash, b;
	int rv, dir_nodeid;

	memset(name, 0, sizeof(name));
	memcpy(name, ms_name, len);

	hash = jhash(name, len, 0);
	b = hash & (ls->ls_rsbtbl_size - 1);

	dir_nodeid = dlm_hash2nodeid(ls, hash);

	log_error(ls, "send_repeat_remove dir %d %s", dir_nodeid, name);

	spin_lock(&ls->ls_rsbtbl[b].lock);
	rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].keep, name, len, &r);
	if (!rv) {
		spin_unlock(&ls->ls_rsbtbl[b].lock);
		log_error(ls, "repeat_remove on keep %s", name);
		return;
	}

	rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, &r);
	if (!rv) {
		spin_unlock(&ls->ls_rsbtbl[b].lock);
		log_error(ls, "repeat_remove on toss %s", name);
		return;
	}

	/* use ls->remove_name2 to avoid conflict with shrink? */

	spin_lock(&ls->ls_remove_spin);
	ls->ls_remove_len = len;
	memcpy(ls->ls_remove_name, name, DLM_RESNAME_MAXLEN);
	spin_unlock(&ls->ls_remove_spin);
	spin_unlock(&ls->ls_rsbtbl[b].lock);

	rv = _create_message(ls, sizeof(struct dlm_message) + len,
			     dir_nodeid, DLM_MSG_REMOVE, &ms, &mh);
	if (rv)
		return;

	memcpy(ms->m_extra, name, len);
	ms->m_hash = hash;

	send_message(mh, ms);

	spin_lock(&ls->ls_remove_spin);
	ls->ls_remove_len = 0;
	memset(ls->ls_remove_name, 0, DLM_RESNAME_MAXLEN);
	spin_unlock(&ls->ls_remove_spin);
}

static int receive_request(struct dlm_ls *ls, struct dlm_message *ms)
{
	struct dlm_lkb *lkb;
	struct dlm_rsb *r;
	int from_nodeid;
	int error, namelen = 0;

	from_nodeid = ms->m_header.h_nodeid;

	error = create_lkb(ls, &lkb);
	if (error)
		goto fail;

	receive_flags(lkb, ms);
	lkb->lkb_flags |= DLM_IFL_MSTCPY;
	error = receive_request_args(ls, lkb, ms);
	if (error) {
		__put_lkb(ls, lkb);
		goto fail;
	}

	/* The dir node is the authority on whether we are the master
	   for this rsb or not, so if the master sends us a request, we should
	   recreate the rsb if we've destroyed it.   This race happens when we
	   send a remove message to the dir node at the same time that the dir
	   node sends us a request for the rsb. */

	namelen = receive_extralen(ms);

	error = find_rsb(ls, ms->m_extra, namelen, from_nodeid,
			 R_RECEIVE_REQUEST, &r);
	if (error) {
		__put_lkb(ls, lkb);
		goto fail;
	}

	lock_rsb(r);

	if (r->res_master_nodeid != dlm_our_nodeid()) {
		error = validate_master_nodeid(ls, r, from_nodeid);
		if (error) {
			unlock_rsb(r);
			put_rsb(r);
			__put_lkb(ls, lkb);
			goto fail;
		}
	}

	attach_lkb(r, lkb);
	error = do_request(r, lkb);
	send_request_reply(r, lkb, error);
	do_request_effects(r, lkb, error);

	unlock_rsb(r);
	put_rsb(r);

	if (error == -EINPROGRESS)
		error = 0;
	if (error)
		dlm_put_lkb(lkb);
	return 0;

 fail:
	/* TODO: instead of returning ENOTBLK, add the lkb to res_lookup
	   and do this receive_request again from process_lookup_list once
	   we get the lookup reply.  This would avoid a many repeated
	   ENOTBLK request failures when the lookup reply designating us
	   as master is delayed. */

	/* We could repeatedly return -EBADR here if our send_remove() is
	   delayed in being sent/arriving/being processed on the dir node.
	   Another node would repeatedly lookup up the master, and the dir
	   node would continue returning our nodeid until our send_remove
	   took effect.

	   We send another remove message in case our previous send_remove
	   was lost/ignored/missed somehow. */

	if (error != -ENOTBLK) {
		log_limit(ls, "receive_request %x from %d %d",
			  ms->m_lkid, from_nodeid, error);
	}

	if (namelen && error == -EBADR) {
		send_repeat_remove(ls, ms->m_extra, namelen);
		msleep(1000);
	}

	setup_stub_lkb(ls, ms);
	send_request_reply(&ls->ls_stub_rsb, &ls->ls_stub_lkb, error);
	return error;
}

static int receive_convert(struct dlm_ls *ls, struct dlm_message *ms)
{
	struct dlm_lkb *lkb;
	struct dlm_rsb *r;
	int error, reply = 1;

	error = find_lkb(ls, ms->m_remid, &lkb);
	if (error)
		goto fail;

	if (lkb->lkb_remid != ms->m_lkid) {
		log_error(ls, "receive_convert %x remid %x recover_seq %llu "
			  "remote %d %x", lkb->lkb_id, lkb->lkb_remid,
			  (unsigned long long)lkb->lkb_recover_seq,
			  ms->m_header.h_nodeid, ms->m_lkid);
		error = -ENOENT;
		goto fail;
	}

	r = lkb->lkb_resource;

	hold_rsb(r);
	lock_rsb(r);

	error = validate_message(lkb, ms);
	if (error)
		goto out;

	receive_flags(lkb, ms);

	error = receive_convert_args(ls, lkb, ms);
	if (error) {
		send_convert_reply(r, lkb, error);
		goto out;
	}

	reply = !down_conversion(lkb);

	error = do_convert(r, lkb);
	if (reply)
		send_convert_reply(r, lkb, error);
	do_convert_effects(r, lkb, error);
 out:
	unlock_rsb(r);
	put_rsb(r);
	dlm_put_lkb(lkb);
	return 0;

 fail:
	setup_stub_lkb(ls, ms);
	send_convert_reply(&ls->ls_stub_rsb, &ls->ls_stub_lkb, error);
	return error;
}

static int receive_unlock(struct dlm_ls *ls, struct dlm_message *ms)
{
	struct dlm_lkb *lkb;
	struct dlm_rsb *r;
	int error;

	error = find_lkb(ls, ms->m_remid, &lkb);
	if (error)
		goto fail;

	if (lkb->lkb_remid != ms->m_lkid) {
		log_error(ls, "receive_unlock %x remid %x remote %d %x",
			  lkb->lkb_id, lkb->lkb_remid,
			  ms->m_header.h_nodeid, ms->m_lkid);
		error = -ENOENT;
		goto fail;
	}

	r = lkb->lkb_resource;

	hold_rsb(r);
	lock_rsb(r);

	error = validate_message(lkb, ms);
	if (error)
		goto out;

	receive_flags(lkb, ms);

	error = receive_unlock_args(ls, lkb, ms);
	if (error) {
		send_unlock_reply(r, lkb, error);
		goto out;
	}

	error = do_unlock(r, lkb);
	send_unlock_reply(r, lkb, error);
	do_unlock_effects(r, lkb, error);
 out:
	unlock_rsb(r);
	put_rsb(r);
	dlm_put_lkb(lkb);
	return 0;

 fail:
	setup_stub_lkb(ls, ms);
	send_unlock_reply(&ls->ls_stub_rsb, &ls->ls_stub_lkb, error);
	return error;
}

static int receive_cancel(struct dlm_ls *ls, struct dlm_message *ms)
{
	struct dlm_lkb *lkb;
	struct dlm_rsb *r;
	int error;

	error = find_lkb(ls, ms->m_remid, &lkb);
	if (error)
		goto fail;

	receive_flags(lkb, ms);

	r = lkb->lkb_resource;

	hold_rsb(r);
	lock_rsb(r);

	error = validate_message(lkb, ms);
	if (error)
		goto out;

	error = do_cancel(r, lkb);
	send_cancel_reply(r, lkb, error);
	do_cancel_effects(r, lkb, error);
 out:
	unlock_rsb(r);
	put_rsb(r);
	dlm_put_lkb(lkb);
	return 0;

 fail:
	setup_stub_lkb(ls, ms);
	send_cancel_reply(&ls->ls_stub_rsb, &ls->ls_stub_lkb, error);
	return error;
}

static int receive_grant(struct dlm_ls *ls, struct dlm_message *ms)
{
	struct dlm_lkb *lkb;
	struct dlm_rsb *r;
	int error;

	error = find_lkb(ls, ms->m_remid, &lkb);
	if (error)
		return error;

	r = lkb->lkb_resource;

	hold_rsb(r);
	lock_rsb(r);

	error = validate_message(lkb, ms);
	if (error)
		goto out;

	receive_flags_reply(lkb, ms);
	if (is_altmode(lkb))
		munge_altmode(lkb, ms);
	grant_lock_pc(r, lkb, ms);
	queue_cast(r, lkb, 0);
 out:
	unlock_rsb(r);
	put_rsb(r);
	dlm_put_lkb(lkb);
	return 0;
}

static int receive_bast(struct dlm_ls *ls, struct dlm_message *ms)
{
	struct dlm_lkb *lkb;
	struct dlm_rsb *r;
	int error;

	error = find_lkb(ls, ms->m_remid, &lkb);
	if (error)
		return error;

	r = lkb->lkb_resource;

	hold_rsb(r);
	lock_rsb(r);

	error = validate_message(lkb, ms);
	if (error)
		goto out;

	queue_bast(r, lkb, ms->m_bastmode);
	lkb->lkb_highbast = ms->m_bastmode;
 out:
	unlock_rsb(r);
	put_rsb(r);
	dlm_put_lkb(lkb);
	return 0;
}

static void receive_lookup(struct dlm_ls *ls, struct dlm_message *ms)
{
	int len, error, ret_nodeid, from_nodeid, our_nodeid;

	from_nodeid = ms->m_header.h_nodeid;
	our_nodeid = dlm_our_nodeid();

	len = receive_extralen(ms);

	error = dlm_master_lookup(ls, from_nodeid, ms->m_extra, len, 0,
				  &ret_nodeid, NULL);

	/* Optimization: we're master so treat lookup as a request */
	if (!error && ret_nodeid == our_nodeid) {
		receive_request(ls, ms);
		return;
	}
	send_lookup_reply(ls, ms, ret_nodeid, error);
}

static void receive_remove(struct dlm_ls *ls, struct dlm_message *ms)
{
	char name[DLM_RESNAME_MAXLEN+1];
	struct dlm_rsb *r;
	uint32_t hash, b;
	int rv, len, dir_nodeid, from_nodeid;

	from_nodeid = ms->m_header.h_nodeid;

	len = receive_extralen(ms);

	if (len > DLM_RESNAME_MAXLEN) {
		log_error(ls, "receive_remove from %d bad len %d",
			  from_nodeid, len);
		return;
	}

	dir_nodeid = dlm_hash2nodeid(ls, ms->m_hash);
	if (dir_nodeid != dlm_our_nodeid()) {
		log_error(ls, "receive_remove from %d bad nodeid %d",
			  from_nodeid, dir_nodeid);
		return;
	}

	/* Look for name on rsbtbl.toss, if it's there, kill it.
	   If it's on rsbtbl.keep, it's being used, and we should ignore this
	   message.  This is an expected race between the dir node sending a
	   request to the master node at the same time as the master node sends
	   a remove to the dir node.  The resolution to that race is for the
	   dir node to ignore the remove message, and the master node to
	   recreate the master rsb when it gets a request from the dir node for
	   an rsb it doesn't have. */

	memset(name, 0, sizeof(name));
	memcpy(name, ms->m_extra, len);

	hash = jhash(name, len, 0);
	b = hash & (ls->ls_rsbtbl_size - 1);

	spin_lock(&ls->ls_rsbtbl[b].lock);

	rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, &r);
	if (rv) {
		/* verify the rsb is on keep list per comment above */
		rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].keep, name, len, &r);
		if (rv) {
			/* should not happen */
			log_error(ls, "receive_remove from %d not found %s",
				  from_nodeid, name);
			spin_unlock(&ls->ls_rsbtbl[b].lock);
			return;
		}
		if (r->res_master_nodeid != from_nodeid) {
			/* should not happen */
			log_error(ls, "receive_remove keep from %d master %d",
				  from_nodeid, r->res_master_nodeid);
			dlm_print_rsb(r);
			spin_unlock(&ls->ls_rsbtbl[b].lock);
			return;
		}

		log_debug(ls, "receive_remove from %d master %d first %x %s",
			  from_nodeid, r->res_master_nodeid, r->res_first_lkid,
			  name);
		spin_unlock(&ls->ls_rsbtbl[b].lock);
		return;
	}

	if (r->res_master_nodeid != from_nodeid) {
		log_error(ls, "receive_remove toss from %d master %d",
			  from_nodeid, r->res_master_nodeid);
		dlm_print_rsb(r);
		spin_unlock(&ls->ls_rsbtbl[b].lock);
		return;
	}

	if (kref_put(&r->res_ref, kill_rsb)) {
		rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[b].toss);
		spin_unlock(&ls->ls_rsbtbl[b].lock);
		dlm_free_rsb(r);
	} else {
		log_error(ls, "receive_remove from %d rsb ref error",
			  from_nodeid);
		dlm_print_rsb(r);
		spin_unlock(&ls->ls_rsbtbl[b].lock);
	}
}

static void receive_purge(struct dlm_ls *ls, struct dlm_message *ms)
{
	do_purge(ls, ms->m_nodeid, ms->m_pid);
}

static int receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms)
{
	struct dlm_lkb *lkb;
	struct dlm_rsb *r;
	int error, mstype, result;
	int from_nodeid = ms->m_header.h_nodeid;

	error = find_lkb(ls, ms->m_remid, &lkb);
	if (error)
		return error;

	r = lkb->lkb_resource;
	hold_rsb(r);
	lock_rsb(r);

	error = validate_message(lkb, ms);
	if (error)
		goto out;

	mstype = lkb->lkb_wait_type;
	error = remove_from_waiters(lkb, DLM_MSG_REQUEST_REPLY);
	if (error) {
		log_error(ls, "receive_request_reply %x remote %d %x result %d",
			  lkb->lkb_id, from_nodeid, ms->m_lkid, ms->m_result);
		dlm_dump_rsb(r);
		goto out;
	}

	/* Optimization: the dir node was also the master, so it took our
	   lookup as a request and sent request reply instead of lookup reply */
	if (mstype == DLM_MSG_LOOKUP) {
		r->res_master_nodeid = from_nodeid;
		r->res_nodeid = from_nodeid;
		lkb->lkb_nodeid = from_nodeid;
	}

	/* this is the value returned from do_request() on the master */
	result = ms->m_result;

	switch (result) {
	case -EAGAIN:
		/* request would block (be queued) on remote master */
		queue_cast(r, lkb, -EAGAIN);
		confirm_master(r, -EAGAIN);
		unhold_lkb(lkb); /* undoes create_lkb() */
		break;

	case -EINPROGRESS:
	case 0:
		/* request was queued or granted on remote master */
		receive_flags_reply(lkb, ms);
		lkb->lkb_remid = ms->m_lkid;
		if (is_altmode(lkb))
			munge_altmode(lkb, ms);
		if (result) {
			add_lkb(r, lkb, DLM_LKSTS_WAITING);
			add_timeout(lkb);
		} else {
			grant_lock_pc(r, lkb, ms);
			queue_cast(r, lkb, 0);
		}
		confirm_master(r, result);
		break;

	case -EBADR:
	case -ENOTBLK:
		/* find_rsb failed to find rsb or rsb wasn't master */
		log_limit(ls, "receive_request_reply %x from %d %d "
			  "master %d dir %d first %x %s", lkb->lkb_id,
			  from_nodeid, result, r->res_master_nodeid,
			  r->res_dir_nodeid, r->res_first_lkid, r->res_name);

		if (r->res_dir_nodeid != dlm_our_nodeid() &&
		    r->res_master_nodeid != dlm_our_nodeid()) {
			/* cause _request_lock->set_master->send_lookup */
			r->res_master_nodeid = 0;
			r->res_nodeid = -1;
			lkb->lkb_nodeid = -1;
		}

		if (is_overlap(lkb)) {
			/* we'll ignore error in cancel/unlock reply */
			queue_cast_overlap(r, lkb);
			confirm_master(r, result);
			unhold_lkb(lkb); /* undoes create_lkb() */
		} else {
			_request_lock(r, lkb);

			if (r->res_master_nodeid == dlm_our_nodeid())
				confirm_master(r, 0);
		}
		break;

	default:
		log_error(ls, "receive_request_reply %x error %d",
			  lkb->lkb_id, result);
	}

	if (is_overlap_unlock(lkb) && (result == 0 || result == -EINPROGRESS)) {
		log_debug(ls, "receive_request_reply %x result %d unlock",
			  lkb->lkb_id, result);
		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK;
		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
		send_unlock(r, lkb);
	} else if (is_overlap_cancel(lkb) && (result == -EINPROGRESS)) {
		log_debug(ls, "receive_request_reply %x cancel", lkb->lkb_id);
		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK;
		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
		send_cancel(r, lkb);
	} else {
		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK;
	}
 out:
	unlock_rsb(r);
	put_rsb(r);
	dlm_put_lkb(lkb);
	return 0;
}

static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb,
				    struct dlm_message *ms)
{
	/* this is the value returned from do_convert() on the master */
	switch (ms->m_result) {
	case -EAGAIN:
		/* convert would block (be queued) on remote master */
		queue_cast(r, lkb, -EAGAIN);
		break;

	case -EDEADLK:
		receive_flags_reply(lkb, ms);
		revert_lock_pc(r, lkb);
		queue_cast(r, lkb, -EDEADLK);
		break;

	case -EINPROGRESS:
		/* convert was queued on remote master */
		receive_flags_reply(lkb, ms);
		if (is_demoted(lkb))
			munge_demoted(lkb);
		del_lkb(r, lkb);
		add_lkb(r, lkb, DLM_LKSTS_CONVERT);
		add_timeout(lkb);
		break;

	case 0:
		/* convert was granted on remote master */
		receive_flags_reply(lkb, ms);
		if (is_demoted(lkb))
			munge_demoted(lkb);
		grant_lock_pc(r, lkb, ms);
		queue_cast(r, lkb, 0);
		break;

	default:
		log_error(r->res_ls, "receive_convert_reply %x remote %d %x %d",
			  lkb->lkb_id, ms->m_header.h_nodeid, ms->m_lkid,
			  ms->m_result);
		dlm_print_rsb(r);
		dlm_print_lkb(lkb);
	}
}

static void _receive_convert_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
{
	struct dlm_rsb *r = lkb->lkb_resource;
	int error;

	hold_rsb(r);
	lock_rsb(r);

	error = validate_message(lkb, ms);
	if (error)
		goto out;

	/* stub reply can happen with waiters_mutex held */
	error = remove_from_waiters_ms(lkb, ms);
	if (error)
		goto out;

	__receive_convert_reply(r, lkb, ms);
 out:
	unlock_rsb(r);
	put_rsb(r);
}

static int receive_convert_reply(struct dlm_ls *ls, struct dlm_message *ms)
{
	struct dlm_lkb *lkb;
	int error;

	error = find_lkb(ls, ms->m_remid, &lkb);
	if (error)
		return error;

	_receive_convert_reply(lkb, ms);
	dlm_put_lkb(lkb);
	return 0;
}

static void _receive_unlock_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
{
	struct dlm_rsb *r = lkb->lkb_resource;
	int error;

	hold_rsb(r);
	lock_rsb(r);

	error = validate_message(lkb, ms);
	if (error)
		goto out;

	/* stub reply can happen with waiters_mutex held */
	error = remove_from_waiters_ms(lkb, ms);
	if (error)
		goto out;

	/* this is the value returned from do_unlock() on the master */

	switch (ms->m_result) {
	case -DLM_EUNLOCK:
		receive_flags_reply(lkb, ms);
		remove_lock_pc(r, lkb);
		queue_cast(r, lkb, -DLM_EUNLOCK);
		break;
	case -ENOENT:
		break;
	default:
		log_error(r->res_ls, "receive_unlock_reply %x error %d",
			  lkb->lkb_id, ms->m_result);
	}
 out:
	unlock_rsb(r);
	put_rsb(r);
}

static int receive_unlock_reply(struct dlm_ls *ls, struct dlm_message *ms)
{
	struct dlm_lkb *lkb;
	int error;

	error = find_lkb(ls, ms->m_remid, &lkb);
	if (error)
		return error;

	_receive_unlock_reply(lkb, ms);
	dlm_put_lkb(lkb);
	return 0;
}

static void _receive_cancel_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
{
	struct dlm_rsb *r = lkb->lkb_resource;
	int error;

	hold_rsb(r);
	lock_rsb(r);

	error = validate_message(lkb, ms);
	if (error)
		goto out;

	/* stub reply can happen with waiters_mutex held */
	error = remove_from_waiters_ms(lkb, ms);
	if (error)
		goto out;

	/* this is the value returned from do_cancel() on the master */

	switch (ms->m_result) {
	case -DLM_ECANCEL:
		receive_flags_reply(lkb, ms);
		revert_lock_pc(r, lkb);
		queue_cast(r, lkb, -DLM_ECANCEL);
		break;
	case 0:
		break;
	default:
		log_error(r->res_ls, "receive_cancel_reply %x error %d",
			  lkb->lkb_id, ms->m_result);
	}
 out:
	unlock_rsb(r);
	put_rsb(r);
}

static int receive_cancel_reply(struct dlm_ls *ls, struct dlm_message *ms)
{
	struct dlm_lkb *lkb;
	int error;

	error = find_lkb(ls, ms->m_remid, &lkb);
	if (error)
		return error;

	_receive_cancel_reply(lkb, ms);
	dlm_put_lkb(lkb);
	return 0;
}

static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms)
{
	struct dlm_lkb *lkb;
	struct dlm_rsb *r;
	int error, ret_nodeid;
	int do_lookup_list = 0;

	error = find_lkb(ls, ms->m_lkid, &lkb);
	if (error) {
		log_error(ls, "receive_lookup_reply no lkid %x", ms->m_lkid);
		return;
	}

	/* ms->m_result is the value returned by dlm_master_lookup on dir node
	   FIXME: will a non-zero error ever be returned? */

	r = lkb->lkb_resource;
	hold_rsb(r);
	lock_rsb(r);

	error = remove_from_waiters(lkb, DLM_MSG_LOOKUP_REPLY);
	if (error)
		goto out;

	ret_nodeid = ms->m_nodeid;

	/* We sometimes receive a request from the dir node for this
	   rsb before we've received the dir node's loookup_reply for it.
	   The request from the dir node implies we're the master, so we set
	   ourself as master in receive_request_reply, and verify here that
	   we are indeed the master. */

	if (r->res_master_nodeid && (r->res_master_nodeid != ret_nodeid)) {
		/* This should never happen */
		log_error(ls, "receive_lookup_reply %x from %d ret %d "
			  "master %d dir %d our %d first %x %s",
			  lkb->lkb_id, ms->m_header.h_nodeid, ret_nodeid,
			  r->res_master_nodeid, r->res_dir_nodeid,
			  dlm_our_nodeid(), r->res_first_lkid, r->res_name);
	}

	if (ret_nodeid == dlm_our_nodeid()) {
		r->res_master_nodeid = ret_nodeid;
		r->res_nodeid = 0;
		do_lookup_list = 1;
		r->res_first_lkid = 0;
	} else if (ret_nodeid == -1) {
		/* the remote node doesn't believe it's the dir node */
		log_error(ls, "receive_lookup_reply %x from %d bad ret_nodeid",
			  lkb->lkb_id, ms->m_header.h_nodeid);
		r->res_master_nodeid = 0;
		r->res_nodeid = -1;
		lkb->lkb_nodeid = -1;
	} else {
		/* set_master() will set lkb_nodeid from r */
		r->res_master_nodeid = ret_nodeid;
		r->res_nodeid = ret_nodeid;
	}

	if (is_overlap(lkb)) {
		log_debug(ls, "receive_lookup_reply %x unlock %x",
			  lkb->lkb_id, lkb->lkb_flags);
		queue_cast_overlap(r, lkb);
		unhold_lkb(lkb); /* undoes create_lkb() */
		goto out_list;
	}

	_request_lock(r, lkb);

 out_list:
	if (do_lookup_list)
		process_lookup_list(r);
 out:
	unlock_rsb(r);
	put_rsb(r);
	dlm_put_lkb(lkb);
}

static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms,
			     uint32_t saved_seq)
{
	int error = 0, noent = 0;

	if (!dlm_is_member(ls, ms->m_header.h_nodeid)) {
		log_limit(ls, "receive %d from non-member %d %x %x %d",
			  ms->m_type, ms->m_header.h_nodeid, ms->m_lkid,
			  ms->m_remid, ms->m_result);
		return;
	}

	switch (ms->m_type) {

	/* messages sent to a master node */

	case DLM_MSG_REQUEST:
		error = receive_request(ls, ms);
		break;

	case DLM_MSG_CONVERT:
		error = receive_convert(ls, ms);
		break;

	case DLM_MSG_UNLOCK:
		error = receive_unlock(ls, ms);
		break;

	case DLM_MSG_CANCEL:
		noent = 1;
		error = receive_cancel(ls, ms);
		break;

	/* messages sent from a master node (replies to above) */

	case DLM_MSG_REQUEST_REPLY:
		error = receive_request_reply(ls, ms);
		break;

	case DLM_MSG_CONVERT_REPLY:
		error = receive_convert_reply(ls, ms);
		break;

	case DLM_MSG_UNLOCK_REPLY:
		error = receive_unlock_reply(ls, ms);
		break;

	case DLM_MSG_CANCEL_REPLY:
		error = receive_cancel_reply(ls, ms);
		break;

	/* messages sent from a master node (only two types of async msg) */

	case DLM_MSG_GRANT:
		noent = 1;
		error = receive_grant(ls, ms);
		break;

	case DLM_MSG_BAST:
		noent = 1;
		error = receive_bast(ls, ms);
		break;

	/* messages sent to a dir node */

	case DLM_MSG_LOOKUP:
		receive_lookup(ls, ms);
		break;

	case DLM_MSG_REMOVE:
		receive_remove(ls, ms);
		break;

	/* messages sent from a dir node (remove has no reply) */

	case DLM_MSG_LOOKUP_REPLY:
		receive_lookup_reply(ls, ms);
		break;

	/* other messages */

	case DLM_MSG_PURGE:
		receive_purge(ls, ms);
		break;

	default:
		log_error(ls, "unknown message type %d", ms->m_type);
	}

	/*
	 * When checking for ENOENT, we're checking the result of
	 * find_lkb(m_remid):
	 *
	 * The lock id referenced in the message wasn't found.  This may
	 * happen in normal usage for the async messages and cancel, so
	 * only use log_debug for them.
	 *
	 * Some errors are expected and normal.
	 */

	if (error == -ENOENT && noent) {
		log_debug(ls, "receive %d no %x remote %d %x saved_seq %u",
			  ms->m_type, ms->m_remid, ms->m_header.h_nodeid,
			  ms->m_lkid, saved_seq);
	} else if (error == -ENOENT) {
		log_error(ls, "receive %d no %x remote %d %x saved_seq %u",
			  ms->m_type, ms->m_remid, ms->m_header.h_nodeid,
			  ms->m_lkid, saved_seq);

		if (ms->m_type == DLM_MSG_CONVERT)
			dlm_dump_rsb_hash(ls, ms->m_hash);
	}

	if (error == -EINVAL) {
		log_error(ls, "receive %d inval from %d lkid %x remid %x "
			  "saved_seq %u",
			  ms->m_type, ms->m_header.h_nodeid,
			  ms->m_lkid, ms->m_remid, saved_seq);
	}
}

/* If the lockspace is in recovery mode (locking stopped), then normal
   messages are saved on the requestqueue for processing after recovery is
   done.  When not in recovery mode, we wait for dlm_recoverd to drain saved
   messages off the requestqueue before we process new ones. This occurs right
   after recovery completes when we transition from saving all messages on
   requestqueue, to processing all the saved messages, to processing new
   messages as they arrive. */

static void dlm_receive_message(struct dlm_ls *ls, struct dlm_message *ms,
				int nodeid)
{
	if (dlm_locking_stopped(ls)) {
		/* If we were a member of this lockspace, left, and rejoined,
		   other nodes may still be sending us messages from the
		   lockspace generation before we left. */
		if (!ls->ls_generation) {
			log_limit(ls, "receive %d from %d ignore old gen",
				  ms->m_type, nodeid);
			return;
		}

		dlm_add_requestqueue(ls, nodeid, ms);
	} else {
		dlm_wait_requestqueue(ls);
		_receive_message(ls, ms, 0);
	}
}

/* This is called by dlm_recoverd to process messages that were saved on
   the requestqueue. */

void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms,
			       uint32_t saved_seq)
{
	_receive_message(ls, ms, saved_seq);
}

/* This is called by the midcomms layer when something is received for
   the lockspace.  It could be either a MSG (normal message sent as part of
   standard locking activity) or an RCOM (recovery message sent as part of
   lockspace recovery). */

void dlm_receive_buffer(union dlm_packet *p, int nodeid)
{
	struct dlm_header *hd = &p->header;
	struct dlm_ls *ls;
	int type = 0;

	switch (hd->h_cmd) {
	case DLM_MSG:
		dlm_message_in(&p->message);
		type = p->message.m_type;
		break;
	case DLM_RCOM:
		dlm_rcom_in(&p->rcom);
		type = p->rcom.rc_type;
		break;
	default:
		log_print("invalid h_cmd %d from %u", hd->h_cmd, nodeid);
		return;
	}

	if (hd->h_nodeid != nodeid) {
		log_print("invalid h_nodeid %d from %d lockspace %x",
			  hd->h_nodeid, nodeid, hd->h_lockspace);
		return;
	}

	ls = dlm_find_lockspace_global(hd->h_lockspace);
	if (!ls) {
		if (dlm_config.ci_log_debug) {
			printk_ratelimited(KERN_DEBUG "dlm: invalid lockspace "
				"%u from %d cmd %d type %d\n",
				hd->h_lockspace, nodeid, hd->h_cmd, type);
		}

		if (hd->h_cmd == DLM_RCOM && type == DLM_RCOM_STATUS)
			dlm_send_ls_not_ready(nodeid, &p->rcom);
		return;
	}

	/* this rwsem allows dlm_ls_stop() to wait for all dlm_recv threads to
	   be inactive (in this ls) before transitioning to recovery mode */

	down_read(&ls->ls_recv_active);
	if (hd->h_cmd == DLM_MSG)
		dlm_receive_message(ls, &p->message, nodeid);
	else
		dlm_receive_rcom(ls, &p->rcom, nodeid);
	up_read(&ls->ls_recv_active);

	dlm_put_lockspace(ls);
}

static void recover_convert_waiter(struct dlm_ls *ls, struct dlm_lkb *lkb,
				   struct dlm_message *ms_stub)
{
	if (middle_conversion(lkb)) {
		hold_lkb(lkb);
		memset(ms_stub, 0, sizeof(struct dlm_message));
		ms_stub->m_flags = DLM_IFL_STUB_MS;
		ms_stub->m_type = DLM_MSG_CONVERT_REPLY;
		ms_stub->m_result = -EINPROGRESS;
		ms_stub->m_header.h_nodeid = lkb->lkb_nodeid;
		_receive_convert_reply(lkb, ms_stub);

		/* Same special case as in receive_rcom_lock_args() */
		lkb->lkb_grmode = DLM_LOCK_IV;
		rsb_set_flag(lkb->lkb_resource, RSB_RECOVER_CONVERT);
		unhold_lkb(lkb);

	} else if (lkb->lkb_rqmode >= lkb->lkb_grmode) {
		lkb->lkb_flags |= DLM_IFL_RESEND;
	}

	/* lkb->lkb_rqmode < lkb->lkb_grmode shouldn't happen since down
	   conversions are async; there's no reply from the remote master */
}

/* A waiting lkb needs recovery if the master node has failed, or
   the master node is changing (only when no directory is used) */

static int waiter_needs_recovery(struct dlm_ls *ls, struct dlm_lkb *lkb,
				 int dir_nodeid)
{
	if (dlm_no_directory(ls))
		return 1;

	if (dlm_is_removed(ls, lkb->lkb_wait_nodeid))
		return 1;

	return 0;
}

/* Recovery for locks that are waiting for replies from nodes that are now
   gone.  We can just complete unlocks and cancels by faking a reply from the
   dead node.  Requests and up-conversions we flag to be resent after
   recovery.  Down-conversions can just be completed with a fake reply like
   unlocks.  Conversions between PR and CW need special attention. */

void dlm_recover_waiters_pre(struct dlm_ls *ls)
{
	struct dlm_lkb *lkb, *safe;
	struct dlm_message *ms_stub;
	int wait_type, stub_unlock_result, stub_cancel_result;
	int dir_nodeid;

	ms_stub = kmalloc(sizeof(struct dlm_message), GFP_KERNEL);
	if (!ms_stub) {
		log_error(ls, "dlm_recover_waiters_pre no mem");
		return;
	}

	mutex_lock(&ls->ls_waiters_mutex);

	list_for_each_entry_safe(lkb, safe, &ls->ls_waiters, lkb_wait_reply) {

		dir_nodeid = dlm_dir_nodeid(lkb->lkb_resource);

		/* exclude debug messages about unlocks because there can be so
		   many and they aren't very interesting */

		if (lkb->lkb_wait_type != DLM_MSG_UNLOCK) {
			log_debug(ls, "waiter %x remote %x msg %d r_nodeid %d "
				  "lkb_nodeid %d wait_nodeid %d dir_nodeid %d",
				  lkb->lkb_id,
				  lkb->lkb_remid,
				  lkb->lkb_wait_type,
				  lkb->lkb_resource->res_nodeid,
				  lkb->lkb_nodeid,
				  lkb->lkb_wait_nodeid,
				  dir_nodeid);
		}

		/* all outstanding lookups, regardless of destination  will be
		   resent after recovery is done */

		if (lkb->lkb_wait_type == DLM_MSG_LOOKUP) {
			lkb->lkb_flags |= DLM_IFL_RESEND;
			continue;
		}

		if (!waiter_needs_recovery(ls, lkb, dir_nodeid))
			continue;

		wait_type = lkb->lkb_wait_type;
		stub_unlock_result = -DLM_EUNLOCK;
		stub_cancel_result = -DLM_ECANCEL;

		/* Main reply may have been received leaving a zero wait_type,
		   but a reply for the overlapping op may not have been
		   received.  In that case we need to fake the appropriate
		   reply for the overlap op. */

		if (!wait_type) {
			if (is_overlap_cancel(lkb)) {
				wait_type = DLM_MSG_CANCEL;
				if (lkb->lkb_grmode == DLM_LOCK_IV)
					stub_cancel_result = 0;
			}
			if (is_overlap_unlock(lkb)) {
				wait_type = DLM_MSG_UNLOCK;
				if (lkb->lkb_grmode == DLM_LOCK_IV)
					stub_unlock_result = -ENOENT;
			}

			log_debug(ls, "rwpre overlap %x %x %d %d %d",
				  lkb->lkb_id, lkb->lkb_flags, wait_type,
				  stub_cancel_result, stub_unlock_result);
		}

		switch (wait_type) {

		case DLM_MSG_REQUEST:
			lkb->lkb_flags |= DLM_IFL_RESEND;
			break;

		case DLM_MSG_CONVERT:
			recover_convert_waiter(ls, lkb, ms_stub);
			break;

		case DLM_MSG_UNLOCK:
			hold_lkb(lkb);
			memset(ms_stub, 0, sizeof(struct dlm_message));
			ms_stub->m_flags = DLM_IFL_STUB_MS;
			ms_stub->m_type = DLM_MSG_UNLOCK_REPLY;
			ms_stub->m_result = stub_unlock_result;
			ms_stub->m_header.h_nodeid = lkb->lkb_nodeid;
			_receive_unlock_reply(lkb, ms_stub);
			dlm_put_lkb(lkb);
			break;

		case DLM_MSG_CANCEL:
			hold_lkb(lkb);
			memset(ms_stub, 0, sizeof(struct dlm_message));
			ms_stub->m_flags = DLM_IFL_STUB_MS;
			ms_stub->m_type = DLM_MSG_CANCEL_REPLY;
			ms_stub->m_result = stub_cancel_result;
			ms_stub->m_header.h_nodeid = lkb->lkb_nodeid;
			_receive_cancel_reply(lkb, ms_stub);
			dlm_put_lkb(lkb);
			break;

		default:
			log_error(ls, "invalid lkb wait_type %d %d",
				  lkb->lkb_wait_type, wait_type);
		}
		schedule();
	}
	mutex_unlock(&ls->ls_waiters_mutex);
	kfree(ms_stub);
}

static struct dlm_lkb *find_resend_waiter(struct dlm_ls *ls)
{
	struct dlm_lkb *lkb;
	int found = 0;

	mutex_lock(&ls->ls_waiters_mutex);
	list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
		if (lkb->lkb_flags & DLM_IFL_RESEND) {
			hold_lkb(lkb);
			found = 1;
			break;
		}
	}
	mutex_unlock(&ls->ls_waiters_mutex);

	if (!found)
		lkb = NULL;
	return lkb;
}

/* Deal with lookups and lkb's marked RESEND from _pre.  We may now be the
   master or dir-node for r.  Processing the lkb may result in it being placed
   back on waiters. */

/* We do this after normal locking has been enabled and any saved messages
   (in requestqueue) have been processed.  We should be confident that at
   this point we won't get or process a reply to any of these waiting
   operations.  But, new ops may be coming in on the rsbs/locks here from
   userspace or remotely. */

/* there may have been an overlap unlock/cancel prior to recovery or after
   recovery.  if before, the lkb may still have a pos wait_count; if after, the
   overlap flag would just have been set and nothing new sent.  we can be
   confident here than any replies to either the initial op or overlap ops
   prior to recovery have been received. */

int dlm_recover_waiters_post(struct dlm_ls *ls)
{
	struct dlm_lkb *lkb;
	struct dlm_rsb *r;
	int error = 0, mstype, err, oc, ou;

	while (1) {
		if (dlm_locking_stopped(ls)) {
			log_debug(ls, "recover_waiters_post aborted");
			error = -EINTR;
			break;
		}

		lkb = find_resend_waiter(ls);
		if (!lkb)
			break;

		r = lkb->lkb_resource;
		hold_rsb(r);
		lock_rsb(r);

		mstype = lkb->lkb_wait_type;
		oc = is_overlap_cancel(lkb);
		ou = is_overlap_unlock(lkb);
		err = 0;

		log_debug(ls, "waiter %x remote %x msg %d r_nodeid %d "
			  "lkb_nodeid %d wait_nodeid %d dir_nodeid %d "
			  "overlap %d %d", lkb->lkb_id, lkb->lkb_remid, mstype,
			  r->res_nodeid, lkb->lkb_nodeid, lkb->lkb_wait_nodeid,
			  dlm_dir_nodeid(r), oc, ou);

		/* At this point we assume that we won't get a reply to any
		   previous op or overlap op on this lock.  First, do a big
		   remove_from_waiters() for all previous ops. */

		lkb->lkb_flags &= ~DLM_IFL_RESEND;
		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK;
		lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
		lkb->lkb_wait_type = 0;
		lkb->lkb_wait_count = 0;
		mutex_lock(&ls->ls_waiters_mutex);
		list_del_init(&lkb->lkb_wait_reply);
		mutex_unlock(&ls->ls_waiters_mutex);
		unhold_lkb(lkb); /* for waiters list */

		if (oc || ou) {
			/* do an unlock or cancel instead of resending */
			switch (mstype) {
			case DLM_MSG_LOOKUP:
			case DLM_MSG_REQUEST:
				queue_cast(r, lkb, ou ? -DLM_EUNLOCK :
							-DLM_ECANCEL);
				unhold_lkb(lkb); /* undoes create_lkb() */
				break;
			case DLM_MSG_CONVERT:
				if (oc) {
					queue_cast(r, lkb, -DLM_ECANCEL);
				} else {
					lkb->lkb_exflags |= DLM_LKF_FORCEUNLOCK;
					_unlock_lock(r, lkb);
				}
				break;
			default:
				err = 1;
			}
		} else {
			switch (mstype) {
			case DLM_MSG_LOOKUP:
			case DLM_MSG_REQUEST:
				_request_lock(r, lkb);
				if (is_master(r))
					confirm_master(r, 0);
				break;
			case DLM_MSG_CONVERT:
				_convert_lock(r, lkb);
				break;
			default:
				err = 1;
			}
		}

		if (err) {
			log_error(ls, "waiter %x msg %d r_nodeid %d "
				  "dir_nodeid %d overlap %d %d",
				  lkb->lkb_id, mstype, r->res_nodeid,
				  dlm_dir_nodeid(r), oc, ou);
		}
		unlock_rsb(r);
		put_rsb(r);
		dlm_put_lkb(lkb);
	}

	return error;
}

static void purge_mstcpy_list(struct dlm_ls *ls, struct dlm_rsb *r,
			      struct list_head *list)
{
	struct dlm_lkb *lkb, *safe;

	list_for_each_entry_safe(lkb, safe, list, lkb_statequeue) {
		if (!is_master_copy(lkb))
			continue;

		/* don't purge lkbs we've added in recover_master_copy for
		   the current recovery seq */

		if (lkb->lkb_recover_seq == ls->ls_recover_seq)
			continue;

		del_lkb(r, lkb);

		/* this put should free the lkb */
		if (!dlm_put_lkb(lkb))
			log_error(ls, "purged mstcpy lkb not released");
	}
}

void dlm_purge_mstcpy_locks(struct dlm_rsb *r)
{
	struct dlm_ls *ls = r->res_ls;

	purge_mstcpy_list(ls, r, &r->res_grantqueue);
	purge_mstcpy_list(ls, r, &r->res_convertqueue);
	purge_mstcpy_list(ls, r, &r->res_waitqueue);
}

static void purge_dead_list(struct dlm_ls *ls, struct dlm_rsb *r,
			    struct list_head *list,
			    int nodeid_gone, unsigned int *count)
{
	struct dlm_lkb *lkb, *safe;

	list_for_each_entry_safe(lkb, safe, list, lkb_statequeue) {
		if (!is_master_copy(lkb))
			continue;

		if ((lkb->lkb_nodeid == nodeid_gone) ||
		    dlm_is_removed(ls, lkb->lkb_nodeid)) {

			/* tell recover_lvb to invalidate the lvb
			   because a node holding EX/PW failed */
			if ((lkb->lkb_exflags & DLM_LKF_VALBLK) &&
			    (lkb->lkb_grmode >= DLM_LOCK_PW)) {
				rsb_set_flag(r, RSB_RECOVER_LVB_INVAL);
			}

			del_lkb(r, lkb);

			/* this put should free the lkb */
			if (!dlm_put_lkb(lkb))
				log_error(ls, "purged dead lkb not released");

			rsb_set_flag(r, RSB_RECOVER_GRANT);

			(*count)++;
		}
	}
}

/* Get rid of locks held by nodes that are gone. */

void dlm_recover_purge(struct dlm_ls *ls)
{
	struct dlm_rsb *r;
	struct dlm_member *memb;
	int nodes_count = 0;
	int nodeid_gone = 0;
	unsigned int lkb_count = 0;

	/* cache one removed nodeid to optimize the common
	   case of a single node removed */

	list_for_each_entry(memb, &ls->ls_nodes_gone, list) {
		nodes_count++;
		nodeid_gone = memb->nodeid;
	}

	if (!nodes_count)
		return;

	down_write(&ls->ls_root_sem);
	list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
		hold_rsb(r);
		lock_rsb(r);
		if (is_master(r)) {
			purge_dead_list(ls, r, &r->res_grantqueue,
					nodeid_gone, &lkb_count);
			purge_dead_list(ls, r, &r->res_convertqueue,
					nodeid_gone, &lkb_count);
			purge_dead_list(ls, r, &r->res_waitqueue,
					nodeid_gone, &lkb_count);
		}
		unlock_rsb(r);
		unhold_rsb(r);
		cond_resched();
	}
	up_write(&ls->ls_root_sem);

	if (lkb_count)
		log_rinfo(ls, "dlm_recover_purge %u locks for %u nodes",
			  lkb_count, nodes_count);
}

static struct dlm_rsb *find_grant_rsb(struct dlm_ls *ls, int bucket)
{
	struct rb_node *n;
	struct dlm_rsb *r;

	spin_lock(&ls->ls_rsbtbl[bucket].lock);
	for (n = rb_first(&ls->ls_rsbtbl[bucket].keep); n; n = rb_next(n)) {
		r = rb_entry(n, struct dlm_rsb, res_hashnode);

		if (!rsb_flag(r, RSB_RECOVER_GRANT))
			continue;
		if (!is_master(r)) {
			rsb_clear_flag(r, RSB_RECOVER_GRANT);
			continue;
		}
		hold_rsb(r);
		spin_unlock(&ls->ls_rsbtbl[bucket].lock);
		return r;
	}
	spin_unlock(&ls->ls_rsbtbl[bucket].lock);
	return NULL;
}

/*
 * Attempt to grant locks on resources that we are the master of.
 * Locks may have become grantable during recovery because locks
 * from departed nodes have been purged (or not rebuilt), allowing
 * previously blocked locks to now be granted.  The subset of rsb's
 * we are interested in are those with lkb's on either the convert or
 * waiting queues.
 *
 * Simplest would be to go through each master rsb and check for non-empty
 * convert or waiting queues, and attempt to grant on those rsbs.
 * Checking the queues requires lock_rsb, though, for which we'd need
 * to release the rsbtbl lock.  This would make iterating through all
 * rsb's very inefficient.  So, we rely on earlier recovery routines
 * to set RECOVER_GRANT on any rsb's that we should attempt to grant
 * locks for.
 */

void dlm_recover_grant(struct dlm_ls *ls)
{
	struct dlm_rsb *r;
	int bucket = 0;
	unsigned int count = 0;
	unsigned int rsb_count = 0;
	unsigned int lkb_count = 0;

	while (1) {
		r = find_grant_rsb(ls, bucket);
		if (!r) {
			if (bucket == ls->ls_rsbtbl_size - 1)
				break;
			bucket++;
			continue;
		}
		rsb_count++;
		count = 0;
		lock_rsb(r);
		/* the RECOVER_GRANT flag is checked in the grant path */
		grant_pending_locks(r, &count);
		rsb_clear_flag(r, RSB_RECOVER_GRANT);
		lkb_count += count;
		confirm_master(r, 0);
		unlock_rsb(r);
		put_rsb(r);
		cond_resched();
	}

	if (lkb_count)
		log_rinfo(ls, "dlm_recover_grant %u locks on %u resources",
			  lkb_count, rsb_count);
}

static struct dlm_lkb *search_remid_list(struct list_head *head, int nodeid,
					 uint32_t remid)
{
	struct dlm_lkb *lkb;

	list_for_each_entry(lkb, head, lkb_statequeue) {
		if (lkb->lkb_nodeid == nodeid && lkb->lkb_remid == remid)
			return lkb;
	}
	return NULL;
}

static struct dlm_lkb *search_remid(struct dlm_rsb *r, int nodeid,
				    uint32_t remid)
{
	struct dlm_lkb *lkb;

	lkb = search_remid_list(&r->res_grantqueue, nodeid, remid);
	if (lkb)
		return lkb;
	lkb = search_remid_list(&r->res_convertqueue, nodeid, remid);
	if (lkb)
		return lkb;
	lkb = search_remid_list(&r->res_waitqueue, nodeid, remid);
	if (lkb)
		return lkb;
	return NULL;
}

/* needs at least dlm_rcom + rcom_lock */
static int receive_rcom_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
				  struct dlm_rsb *r, struct dlm_rcom *rc)
{
	struct rcom_lock *rl = (struct rcom_lock *) rc->rc_buf;

	lkb->lkb_nodeid = rc->rc_header.h_nodeid;
	lkb->lkb_ownpid = le32_to_cpu(rl->rl_ownpid);
	lkb->lkb_remid = le32_to_cpu(rl->rl_lkid);
	lkb->lkb_exflags = le32_to_cpu(rl->rl_exflags);
	lkb->lkb_flags = le32_to_cpu(rl->rl_flags) & 0x0000FFFF;
	lkb->lkb_flags |= DLM_IFL_MSTCPY;
	lkb->lkb_lvbseq = le32_to_cpu(rl->rl_lvbseq);
	lkb->lkb_rqmode = rl->rl_rqmode;
	lkb->lkb_grmode = rl->rl_grmode;
	/* don't set lkb_status because add_lkb wants to itself */

	lkb->lkb_bastfn = (rl->rl_asts & DLM_CB_BAST) ? &fake_bastfn : NULL;
	lkb->lkb_astfn = (rl->rl_asts & DLM_CB_CAST) ? &fake_astfn : NULL;

	if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
		int lvblen = rc->rc_header.h_length - sizeof(struct dlm_rcom) -
			 sizeof(struct rcom_lock);
		if (lvblen > ls->ls_lvblen)
			return -EINVAL;
		lkb->lkb_lvbptr = dlm_allocate_lvb(ls);
		if (!lkb->lkb_lvbptr)
			return -ENOMEM;
		memcpy(lkb->lkb_lvbptr, rl->rl_lvb, lvblen);
	}

	/* Conversions between PR and CW (middle modes) need special handling.
	   The real granted mode of these converting locks cannot be determined
	   until all locks have been rebuilt on the rsb (recover_conversion) */

	if (rl->rl_wait_type == cpu_to_le16(DLM_MSG_CONVERT) &&
	    middle_conversion(lkb)) {
		rl->rl_status = DLM_LKSTS_CONVERT;
		lkb->lkb_grmode = DLM_LOCK_IV;
		rsb_set_flag(r, RSB_RECOVER_CONVERT);
	}

	return 0;
}

/* This lkb may have been recovered in a previous aborted recovery so we need
   to check if the rsb already has an lkb with the given remote nodeid/lkid.
   If so we just send back a standard reply.  If not, we create a new lkb with
   the given values and send back our lkid.  We send back our lkid by sending
   back the rcom_lock struct we got but with the remid field filled in. */

/* needs at least dlm_rcom + rcom_lock */
int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc)
{
	struct rcom_lock *rl = (struct rcom_lock *) rc->rc_buf;
	struct dlm_rsb *r;
	struct dlm_lkb *lkb;
	uint32_t remid = 0;
	int from_nodeid = rc->rc_header.h_nodeid;
	int error;

	if (rl->rl_parent_lkid) {
		error = -EOPNOTSUPP;
		goto out;
	}

	remid = le32_to_cpu(rl->rl_lkid);

	/* In general we expect the rsb returned to be R_MASTER, but we don't
	   have to require it.  Recovery of masters on one node can overlap
	   recovery of locks on another node, so one node can send us MSTCPY
	   locks before we've made ourselves master of this rsb.  We can still
	   add new MSTCPY locks that we receive here without any harm; when
	   we make ourselves master, dlm_recover_masters() won't touch the
	   MSTCPY locks we've received early. */

	error = find_rsb(ls, rl->rl_name, le16_to_cpu(rl->rl_namelen),
			 from_nodeid, R_RECEIVE_RECOVER, &r);
	if (error)
		goto out;

	lock_rsb(r);

	if (dlm_no_directory(ls) && (dlm_dir_nodeid(r) != dlm_our_nodeid())) {
		log_error(ls, "dlm_recover_master_copy remote %d %x not dir",
			  from_nodeid, remid);
		error = -EBADR;
		goto out_unlock;
	}

	lkb = search_remid(r, from_nodeid, remid);
	if (lkb) {
		error = -EEXIST;
		goto out_remid;
	}

	error = create_lkb(ls, &lkb);
	if (error)
		goto out_unlock;

	error = receive_rcom_lock_args(ls, lkb, r, rc);
	if (error) {
		__put_lkb(ls, lkb);
		goto out_unlock;
	}

	attach_lkb(r, lkb);
	add_lkb(r, lkb, rl->rl_status);
	error = 0;
	ls->ls_recover_locks_in++;

	if (!list_empty(&r->res_waitqueue) || !list_empty(&r->res_convertqueue))
		rsb_set_flag(r, RSB_RECOVER_GRANT);

 out_remid:
	/* this is the new value returned to the lock holder for
	   saving in its process-copy lkb */
	rl->rl_remid = cpu_to_le32(lkb->lkb_id);

	lkb->lkb_recover_seq = ls->ls_recover_seq;

 out_unlock:
	unlock_rsb(r);
	put_rsb(r);
 out:
	if (error && error != -EEXIST)
		log_rinfo(ls, "dlm_recover_master_copy remote %d %x error %d",
			  from_nodeid, remid, error);
	rl->rl_result = cpu_to_le32(error);
	return error;
}

/* needs at least dlm_rcom + rcom_lock */
int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc)
{
	struct rcom_lock *rl = (struct rcom_lock *) rc->rc_buf;
	struct dlm_rsb *r;
	struct dlm_lkb *lkb;
	uint32_t lkid, remid;
	int error, result;

	lkid = le32_to_cpu(rl->rl_lkid);
	remid = le32_to_cpu(rl->rl_remid);
	result = le32_to_cpu(rl->rl_result);

	error = find_lkb(ls, lkid, &lkb);
	if (error) {
		log_error(ls, "dlm_recover_process_copy no %x remote %d %x %d",
			  lkid, rc->rc_header.h_nodeid, remid, result);
		return error;
	}

	r = lkb->lkb_resource;
	hold_rsb(r);
	lock_rsb(r);

	if (!is_process_copy(lkb)) {
		log_error(ls, "dlm_recover_process_copy bad %x remote %d %x %d",
			  lkid, rc->rc_header.h_nodeid, remid, result);
		dlm_dump_rsb(r);
		unlock_rsb(r);
		put_rsb(r);
		dlm_put_lkb(lkb);
		return -EINVAL;
	}

	switch (result) {
	case -EBADR:
		/* There's a chance the new master received our lock before
		   dlm_recover_master_reply(), this wouldn't happen if we did
		   a barrier between recover_masters and recover_locks. */

		log_debug(ls, "dlm_recover_process_copy %x remote %d %x %d",
			  lkid, rc->rc_header.h_nodeid, remid, result);
	
		dlm_send_rcom_lock(r, lkb);
		goto out;
	case -EEXIST:
	case 0:
		lkb->lkb_remid = remid;
		break;
	default:
		log_error(ls, "dlm_recover_process_copy %x remote %d %x %d unk",
			  lkid, rc->rc_header.h_nodeid, remid, result);
	}

	/* an ack for dlm_recover_locks() which waits for replies from
	   all the locks it sends to new masters */
	dlm_recovered_lock(r);
 out:
	unlock_rsb(r);
	put_rsb(r);
	dlm_put_lkb(lkb);

	return 0;
}

int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
		     int mode, uint32_t flags, void *name, unsigned int namelen,
		     unsigned long timeout_cs)
{
	struct dlm_lkb *lkb;
	struct dlm_args args;
	int error;

	dlm_lock_recovery(ls);

	error = create_lkb(ls, &lkb);
	if (error) {
		kfree(ua);
		goto out;
	}

	if (flags & DLM_LKF_VALBLK) {
		ua->lksb.sb_lvbptr = kzalloc(DLM_USER_LVB_LEN, GFP_NOFS);
		if (!ua->lksb.sb_lvbptr) {
			kfree(ua);
			__put_lkb(ls, lkb);
			error = -ENOMEM;
			goto out;
		}
	}

	/* After ua is attached to lkb it will be freed by dlm_free_lkb().
	   When DLM_IFL_USER is set, the dlm knows that this is a userspace
	   lock and that lkb_astparam is the dlm_user_args structure. */

	error = set_lock_args(mode, &ua->lksb, flags, namelen, timeout_cs,
			      fake_astfn, ua, fake_bastfn, &args);
	lkb->lkb_flags |= DLM_IFL_USER;

	if (error) {
		__put_lkb(ls, lkb);
		goto out;
	}

	error = request_lock(ls, lkb, name, namelen, &args);

	switch (error) {
	case 0:
		break;
	case -EINPROGRESS:
		error = 0;
		break;
	case -EAGAIN:
		error = 0;
		/* fall through */
	default:
		__put_lkb(ls, lkb);
		goto out;
	}

	/* add this new lkb to the per-process list of locks */
	spin_lock(&ua->proc->locks_spin);
	hold_lkb(lkb);
	list_add_tail(&lkb->lkb_ownqueue, &ua->proc->locks);
	spin_unlock(&ua->proc->locks_spin);
 out:
	dlm_unlock_recovery(ls);
	return error;
}

int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
		     int mode, uint32_t flags, uint32_t lkid, char *lvb_in,
		     unsigned long timeout_cs)
{
	struct dlm_lkb *lkb;
	struct dlm_args args;
	struct dlm_user_args *ua;
	int error;

	dlm_lock_recovery(ls);

	error = find_lkb(ls, lkid, &lkb);
	if (error)
		goto out;

	/* user can change the params on its lock when it converts it, or
	   add an lvb that didn't exist before */

	ua = lkb->lkb_ua;

	if (flags & DLM_LKF_VALBLK && !ua->lksb.sb_lvbptr) {
		ua->lksb.sb_lvbptr = kzalloc(DLM_USER_LVB_LEN, GFP_NOFS);
		if (!ua->lksb.sb_lvbptr) {
			error = -ENOMEM;
			goto out_put;
		}
	}
	if (lvb_in && ua->lksb.sb_lvbptr)
		memcpy(ua->lksb.sb_lvbptr, lvb_in, DLM_USER_LVB_LEN);

	ua->xid = ua_tmp->xid;
	ua->castparam = ua_tmp->castparam;
	ua->castaddr = ua_tmp->castaddr;
	ua->bastparam = ua_tmp->bastparam;
	ua->bastaddr = ua_tmp->bastaddr;
	ua->user_lksb = ua_tmp->user_lksb;

	error = set_lock_args(mode, &ua->lksb, flags, 0, timeout_cs,
			      fake_astfn, ua, fake_bastfn, &args);
	if (error)
		goto out_put;

	error = convert_lock(ls, lkb, &args);

	if (error == -EINPROGRESS || error == -EAGAIN || error == -EDEADLK)
		error = 0;
 out_put:
	dlm_put_lkb(lkb);
 out:
	dlm_unlock_recovery(ls);
	kfree(ua_tmp);
	return error;
}

/*
 * The caller asks for an orphan lock on a given resource with a given mode.
 * If a matching lock exists, it's moved to the owner's list of locks and
 * the lkid is returned.
 */

int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
		     int mode, uint32_t flags, void *name, unsigned int namelen,
		     unsigned long timeout_cs, uint32_t *lkid)
{
	struct dlm_lkb *lkb;
	struct dlm_user_args *ua;
	int found_other_mode = 0;
	int found = 0;
	int rv = 0;

	mutex_lock(&ls->ls_orphans_mutex);
	list_for_each_entry(lkb, &ls->ls_orphans, lkb_ownqueue) {
		if (lkb->lkb_resource->res_length != namelen)
			continue;
		if (memcmp(lkb->lkb_resource->res_name, name, namelen))
			continue;
		if (lkb->lkb_grmode != mode) {
			found_other_mode = 1;
			continue;
		}

		found = 1;
		list_del_init(&lkb->lkb_ownqueue);
		lkb->lkb_flags &= ~DLM_IFL_ORPHAN;
		*lkid = lkb->lkb_id;
		break;
	}
	mutex_unlock(&ls->ls_orphans_mutex);

	if (!found && found_other_mode) {
		rv = -EAGAIN;
		goto out;
	}

	if (!found) {
		rv = -ENOENT;
		goto out;
	}

	lkb->lkb_exflags = flags;
	lkb->lkb_ownpid = (int) current->pid;

	ua = lkb->lkb_ua;

	ua->proc = ua_tmp->proc;
	ua->xid = ua_tmp->xid;
	ua->castparam = ua_tmp->castparam;
	ua->castaddr = ua_tmp->castaddr;
	ua->bastparam = ua_tmp->bastparam;
	ua->bastaddr = ua_tmp->bastaddr;
	ua->user_lksb = ua_tmp->user_lksb;

	/*
	 * The lkb reference from the ls_orphans list was not
	 * removed above, and is now considered the reference
	 * for the proc locks list.
	 */

	spin_lock(&ua->proc->locks_spin);
	list_add_tail(&lkb->lkb_ownqueue, &ua->proc->locks);
	spin_unlock(&ua->proc->locks_spin);
 out:
	kfree(ua_tmp);
	return rv;
}

int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
		    uint32_t flags, uint32_t lkid, char *lvb_in)
{
	struct dlm_lkb *lkb;
	struct dlm_args args;
	struct dlm_user_args *ua;
	int error;

	dlm_lock_recovery(ls);

	error = find_lkb(ls, lkid, &lkb);
	if (error)
		goto out;

	ua = lkb->lkb_ua;

	if (lvb_in && ua->lksb.sb_lvbptr)
		memcpy(ua->lksb.sb_lvbptr, lvb_in, DLM_USER_LVB_LEN);
	if (ua_tmp->castparam)
		ua->castparam = ua_tmp->castparam;
	ua->user_lksb = ua_tmp->user_lksb;

	error = set_unlock_args(flags, ua, &args);
	if (error)
		goto out_put;

	error = unlock_lock(ls, lkb, &args);

	if (error == -DLM_EUNLOCK)
		error = 0;
	/* from validate_unlock_args() */
	if (error == -EBUSY && (flags & DLM_LKF_FORCEUNLOCK))
		error = 0;
	if (error)
		goto out_put;

	spin_lock(&ua->proc->locks_spin);
	/* dlm_user_add_cb() may have already taken lkb off the proc list */
	if (!list_empty(&lkb->lkb_ownqueue))
		list_move(&lkb->lkb_ownqueue, &ua->proc->unlocking);
	spin_unlock(&ua->proc->locks_spin);
 out_put:
	dlm_put_lkb(lkb);
 out:
	dlm_unlock_recovery(ls);
	kfree(ua_tmp);
	return error;
}

int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
		    uint32_t flags, uint32_t lkid)
{
	struct dlm_lkb *lkb;
	struct dlm_args args;
	struct dlm_user_args *ua;
	int error;

	dlm_lock_recovery(ls);

	error = find_lkb(ls, lkid, &lkb);
	if (error)
		goto out;

	ua = lkb->lkb_ua;
	if (ua_tmp->castparam)
		ua->castparam = ua_tmp->castparam;
	ua->user_lksb = ua_tmp->user_lksb;

	error = set_unlock_args(flags, ua, &args);
	if (error)
		goto out_put;

	error = cancel_lock(ls, lkb, &args);

	if (error == -DLM_ECANCEL)
		error = 0;
	/* from validate_unlock_args() */
	if (error == -EBUSY)
		error = 0;
 out_put:
	dlm_put_lkb(lkb);
 out:
	dlm_unlock_recovery(ls);
	kfree(ua_tmp);
	return error;
}

int dlm_user_deadlock(struct dlm_ls *ls, uint32_t flags, uint32_t lkid)
{
	struct dlm_lkb *lkb;
	struct dlm_args args;
	struct dlm_user_args *ua;
	struct dlm_rsb *r;
	int error;

	dlm_lock_recovery(ls);

	error = find_lkb(ls, lkid, &lkb);
	if (error)
		goto out;

	ua = lkb->lkb_ua;

	error = set_unlock_args(flags, ua, &args);
	if (error)
		goto out_put;

	/* same as cancel_lock(), but set DEADLOCK_CANCEL after lock_rsb */

	r = lkb->lkb_resource;
	hold_rsb(r);
	lock_rsb(r);

	error = validate_unlock_args(lkb, &args);
	if (error)
		goto out_r;
	lkb->lkb_flags |= DLM_IFL_DEADLOCK_CANCEL;

	error = _cancel_lock(r, lkb);
 out_r:
	unlock_rsb(r);
	put_rsb(r);

	if (error == -DLM_ECANCEL)
		error = 0;
	/* from validate_unlock_args() */
	if (error == -EBUSY)
		error = 0;
 out_put:
	dlm_put_lkb(lkb);
 out:
	dlm_unlock_recovery(ls);
	return error;
}

/* lkb's that are removed from the waiters list by revert are just left on the
   orphans list with the granted orphan locks, to be freed by purge */

static int orphan_proc_lock(struct dlm_ls *ls, struct dlm_lkb *lkb)
{
	struct dlm_args args;
	int error;

	hold_lkb(lkb); /* reference for the ls_orphans list */
	mutex_lock(&ls->ls_orphans_mutex);
	list_add_tail(&lkb->lkb_ownqueue, &ls->ls_orphans);
	mutex_unlock(&ls->ls_orphans_mutex);

	set_unlock_args(0, lkb->lkb_ua, &args);

	error = cancel_lock(ls, lkb, &args);
	if (error == -DLM_ECANCEL)
		error = 0;
	return error;
}

/* The FORCEUNLOCK flag allows the unlock to go ahead even if the lkb isn't
   granted.  Regardless of what rsb queue the lock is on, it's removed and
   freed.  The IVVALBLK flag causes the lvb on the resource to be invalidated
   if our lock is PW/EX (it's ignored if our granted mode is smaller.) */

static int unlock_proc_lock(struct dlm_ls *ls, struct dlm_lkb *lkb)
{
	struct dlm_args args;
	int error;

	set_unlock_args(DLM_LKF_FORCEUNLOCK | DLM_LKF_IVVALBLK,
			lkb->lkb_ua, &args);

	error = unlock_lock(ls, lkb, &args);
	if (error == -DLM_EUNLOCK)
		error = 0;
	return error;
}

/* We have to release clear_proc_locks mutex before calling unlock_proc_lock()
   (which does lock_rsb) due to deadlock with receiving a message that does
   lock_rsb followed by dlm_user_add_cb() */

static struct dlm_lkb *del_proc_lock(struct dlm_ls *ls,
				     struct dlm_user_proc *proc)
{
	struct dlm_lkb *lkb = NULL;

	mutex_lock(&ls->ls_clear_proc_locks);
	if (list_empty(&proc->locks))
		goto out;

	lkb = list_entry(proc->locks.next, struct dlm_lkb, lkb_ownqueue);
	list_del_init(&lkb->lkb_ownqueue);

	if (lkb->lkb_exflags & DLM_LKF_PERSISTENT)
		lkb->lkb_flags |= DLM_IFL_ORPHAN;
	else
		lkb->lkb_flags |= DLM_IFL_DEAD;
 out:
	mutex_unlock(&ls->ls_clear_proc_locks);
	return lkb;
}

/* The ls_clear_proc_locks mutex protects against dlm_user_add_cb() which
   1) references lkb->ua which we free here and 2) adds lkbs to proc->asts,
   which we clear here. */

/* proc CLOSING flag is set so no more device_reads should look at proc->asts
   list, and no more device_writes should add lkb's to proc->locks list; so we
   shouldn't need to take asts_spin or locks_spin here.  this assumes that
   device reads/writes/closes are serialized -- FIXME: we may need to serialize
   them ourself. */

void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc)
{
	struct dlm_lkb *lkb, *safe;

	dlm_lock_recovery(ls);

	while (1) {
		lkb = del_proc_lock(ls, proc);
		if (!lkb)
			break;
		del_timeout(lkb);
		if (lkb->lkb_exflags & DLM_LKF_PERSISTENT)
			orphan_proc_lock(ls, lkb);
		else
			unlock_proc_lock(ls, lkb);

		/* this removes the reference for the proc->locks list
		   added by dlm_user_request, it may result in the lkb
		   being freed */

		dlm_put_lkb(lkb);
	}

	mutex_lock(&ls->ls_clear_proc_locks);

	/* in-progress unlocks */
	list_for_each_entry_safe(lkb, safe, &proc->unlocking, lkb_ownqueue) {
		list_del_init(&lkb->lkb_ownqueue);
		lkb->lkb_flags |= DLM_IFL_DEAD;
		dlm_put_lkb(lkb);
	}

	list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_cb_list) {
		memset(&lkb->lkb_callbacks, 0,
		       sizeof(struct dlm_callback) * DLM_CALLBACKS_SIZE);
		list_del_init(&lkb->lkb_cb_list);
		dlm_put_lkb(lkb);
	}

	mutex_unlock(&ls->ls_clear_proc_locks);
	dlm_unlock_recovery(ls);
}

static void purge_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc)
{
	struct dlm_lkb *lkb, *safe;

	while (1) {
		lkb = NULL;
		spin_lock(&proc->locks_spin);
		if (!list_empty(&proc->locks)) {
			lkb = list_entry(proc->locks.next, struct dlm_lkb,
					 lkb_ownqueue);
			list_del_init(&lkb->lkb_ownqueue);
		}
		spin_unlock(&proc->locks_spin);

		if (!lkb)
			break;

		lkb->lkb_flags |= DLM_IFL_DEAD;
		unlock_proc_lock(ls, lkb);
		dlm_put_lkb(lkb); /* ref from proc->locks list */
	}

	spin_lock(&proc->locks_spin);
	list_for_each_entry_safe(lkb, safe, &proc->unlocking, lkb_ownqueue) {
		list_del_init(&lkb->lkb_ownqueue);
		lkb->lkb_flags |= DLM_IFL_DEAD;
		dlm_put_lkb(lkb);
	}
	spin_unlock(&proc->locks_spin);

	spin_lock(&proc->asts_spin);
	list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_cb_list) {
		memset(&lkb->lkb_callbacks, 0,
		       sizeof(struct dlm_callback) * DLM_CALLBACKS_SIZE);
		list_del_init(&lkb->lkb_cb_list);
		dlm_put_lkb(lkb);
	}
	spin_unlock(&proc->asts_spin);
}

/* pid of 0 means purge all orphans */

static void do_purge(struct dlm_ls *ls, int nodeid, int pid)
{
	struct dlm_lkb *lkb, *safe;

	mutex_lock(&ls->ls_orphans_mutex);
	list_for_each_entry_safe(lkb, safe, &ls->ls_orphans, lkb_ownqueue) {
		if (pid && lkb->lkb_ownpid != pid)
			continue;
		unlock_proc_lock(ls, lkb);
		list_del_init(&lkb->lkb_ownqueue);
		dlm_put_lkb(lkb);
	}
	mutex_unlock(&ls->ls_orphans_mutex);
}

static int send_purge(struct dlm_ls *ls, int nodeid, int pid)
{
	struct dlm_message *ms;
	struct dlm_mhandle *mh;
	int error;

	error = _create_message(ls, sizeof(struct dlm_message), nodeid,
				DLM_MSG_PURGE, &ms, &mh);
	if (error)
		return error;
	ms->m_nodeid = nodeid;
	ms->m_pid = pid;

	return send_message(mh, ms);
}

int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc,
		   int nodeid, int pid)
{
	int error = 0;

	if (nodeid && (nodeid != dlm_our_nodeid())) {
		error = send_purge(ls, nodeid, pid);
	} else {
		dlm_lock_recovery(ls);
		if (pid == current->pid)
			purge_proc_locks(ls, proc);
		else
			do_purge(ls, nodeid, pid);
		dlm_unlock_recovery(ls);
	}
	return error;
}