aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/core/cma.c
blob: d951896ff7fc9f6023db24c6280d22870f98f946 (plain) (blame)
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
/*
 * Copyright (c) 2005 Voltaire Inc.  All rights reserved.
 * Copyright (c) 2002-2005, Network Appliance, Inc. All rights reserved.
 * Copyright (c) 1999-2005, Mellanox Technologies, Inc. All rights reserved.
 * Copyright (c) 2005-2006 Intel Corporation.  All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <linux/completion.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/mutex.h>
#include <linux/random.h>
#include <linux/idr.h>
#include <linux/inetdevice.h>

#include <net/tcp.h>

#include <rdma/rdma_cm.h>
#include <rdma/rdma_cm_ib.h>
#include <rdma/ib_cache.h>
#include <rdma/ib_cm.h>
#include <rdma/ib_sa.h>
#include <rdma/iw_cm.h>

MODULE_AUTHOR("Sean Hefty");
MODULE_DESCRIPTION("Generic RDMA CM Agent");
MODULE_LICENSE("Dual BSD/GPL");

#define CMA_CM_RESPONSE_TIMEOUT 20
#define CMA_MAX_CM_RETRIES 15
#define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)

static void cma_add_one(struct ib_device *device);
static void cma_remove_one(struct ib_device *device);

static struct ib_client cma_client = {
	.name   = "cma",
	.add    = cma_add_one,
	.remove = cma_remove_one
};

static struct ib_sa_client sa_client;
static struct rdma_addr_client addr_client;
static LIST_HEAD(dev_list);
static LIST_HEAD(listen_any_list);
static DEFINE_MUTEX(lock);
static struct workqueue_struct *cma_wq;
static DEFINE_IDR(sdp_ps);
static DEFINE_IDR(tcp_ps);
static DEFINE_IDR(udp_ps);
static DEFINE_IDR(ipoib_ps);
static int next_port;

struct cma_device {
	struct list_head	list;
	struct ib_device	*device;
	struct completion	comp;
	atomic_t		refcount;
	struct list_head	id_list;
};

enum cma_state {
	CMA_IDLE,
	CMA_ADDR_QUERY,
	CMA_ADDR_RESOLVED,
	CMA_ROUTE_QUERY,
	CMA_ROUTE_RESOLVED,
	CMA_CONNECT,
	CMA_DISCONNECT,
	CMA_ADDR_BOUND,
	CMA_LISTEN,
	CMA_DEVICE_REMOVAL,
	CMA_DESTROYING
};

struct rdma_bind_list {
	struct idr		*ps;
	struct hlist_head	owners;
	unsigned short		port;
};

/*
 * Device removal can occur at anytime, so we need extra handling to
 * serialize notifying the user of device removal with other callbacks.
 * We do this by disabling removal notification while a callback is in process,
 * and reporting it after the callback completes.
 */
struct rdma_id_private {
	struct rdma_cm_id	id;

	struct rdma_bind_list	*bind_list;
	struct hlist_node	node;
	struct list_head	list; /* listen_any_list or cma_device.list */
	struct list_head	listen_list; /* per device listens */
	struct cma_device	*cma_dev;
	struct list_head	mc_list;

	int			internal_id;
	enum cma_state		state;
	spinlock_t		lock;
	struct mutex		qp_mutex;

	struct completion	comp;
	atomic_t		refcount;
	struct mutex		handler_mutex;

	int			backlog;
	int			timeout_ms;
	struct ib_sa_query	*query;
	int			query_id;
	union {
		struct ib_cm_id	*ib;
		struct iw_cm_id	*iw;
	} cm_id;

	u32			seq_num;
	u32			qkey;
	u32			qp_num;
	u8			srq;
	u8			tos;
};

struct cma_multicast {
	struct rdma_id_private *id_priv;
	union {
		struct ib_sa_multicast *ib;
	} multicast;
	struct list_head	list;
	void			*context;
	struct sockaddr_storage	addr;
};

struct cma_work {
	struct work_struct	work;
	struct rdma_id_private	*id;
	enum cma_state		old_state;
	enum cma_state		new_state;
	struct rdma_cm_event	event;
};

struct cma_ndev_work {
	struct work_struct	work;
	struct rdma_id_private	*id;
	struct rdma_cm_event	event;
};

union cma_ip_addr {
	struct in6_addr ip6;
	struct {
		__be32 pad[3];
		__be32 addr;
	} ip4;
};

struct cma_hdr {
	u8 cma_version;
	u8 ip_version;	/* IP version: 7:4 */
	__be16 port;
	union cma_ip_addr src_addr;
	union cma_ip_addr dst_addr;
};

struct sdp_hh {
	u8 bsdh[16];
	u8 sdp_version; /* Major version: 7:4 */
	u8 ip_version;	/* IP version: 7:4 */
	u8 sdp_specific1[10];
	__be16 port;
	__be16 sdp_specific2;
	union cma_ip_addr src_addr;
	union cma_ip_addr dst_addr;
};

struct sdp_hah {
	u8 bsdh[16];
	u8 sdp_version;
};

#define CMA_VERSION 0x00
#define SDP_MAJ_VERSION 0x2

static int cma_comp(struct rdma_id_private *id_priv, enum cma_state comp)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&id_priv->lock, flags);
	ret = (id_priv->state == comp);
	spin_unlock_irqrestore(&id_priv->lock, flags);
	return ret;
}

static int cma_comp_exch(struct rdma_id_private *id_priv,
			 enum cma_state comp, enum cma_state exch)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&id_priv->lock, flags);
	if ((ret = (id_priv->state == comp)))
		id_priv->state = exch;
	spin_unlock_irqrestore(&id_priv->lock, flags);
	return ret;
}

static enum cma_state cma_exch(struct rdma_id_private *id_priv,
			       enum cma_state exch)
{
	unsigned long flags;
	enum cma_state old;

	spin_lock_irqsave(&id_priv->lock, flags);
	old = id_priv->state;
	id_priv->state = exch;
	spin_unlock_irqrestore(&id_priv->lock, flags);
	return old;
}

static inline u8 cma_get_ip_ver(struct cma_hdr *hdr)
{
	return hdr->ip_version >> 4;
}

static inline void cma_set_ip_ver(struct cma_hdr *hdr, u8 ip_ver)
{
	hdr->ip_version = (ip_ver << 4) | (hdr->ip_version & 0xF);
}

static inline u8 sdp_get_majv(u8 sdp_version)
{
	return sdp_version >> 4;
}

static inline u8 sdp_get_ip_ver(struct sdp_hh *hh)
{
	return hh->ip_version >> 4;
}

static inline void sdp_set_ip_ver(struct sdp_hh *hh, u8 ip_ver)
{
	hh->ip_version = (ip_ver << 4) | (hh->ip_version & 0xF);
}

static inline int cma_is_ud_ps(enum rdma_port_space ps)
{
	return (ps == RDMA_PS_UDP || ps == RDMA_PS_IPOIB);
}

static void cma_attach_to_dev(struct rdma_id_private *id_priv,
			      struct cma_device *cma_dev)
{
	atomic_inc(&cma_dev->refcount);
	id_priv->cma_dev = cma_dev;
	id_priv->id.device = cma_dev->device;
	list_add_tail(&id_priv->list, &cma_dev->id_list);
}

static inline void cma_deref_dev(struct cma_device *cma_dev)
{
	if (atomic_dec_and_test(&cma_dev->refcount))
		complete(&cma_dev->comp);
}

static void cma_detach_from_dev(struct rdma_id_private *id_priv)
{
	list_del(&id_priv->list);
	cma_deref_dev(id_priv->cma_dev);
	id_priv->cma_dev = NULL;
}

static int cma_set_qkey(struct ib_device *device, u8 port_num,
			enum rdma_port_space ps,
			struct rdma_dev_addr *dev_addr, u32 *qkey)
{
	struct ib_sa_mcmember_rec rec;
	int ret = 0;

	switch (ps) {
	case RDMA_PS_UDP:
		*qkey = RDMA_UDP_QKEY;
		break;
	case RDMA_PS_IPOIB:
		ib_addr_get_mgid(dev_addr, &rec.mgid);
		ret = ib_sa_get_mcmember_rec(device, port_num, &rec.mgid, &rec);
		*qkey = be32_to_cpu(rec.qkey);
		break;
	default:
		break;
	}
	return ret;
}

static int cma_acquire_dev(struct rdma_id_private *id_priv)
{
	struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
	struct cma_device *cma_dev;
	union ib_gid gid;
	int ret = -ENODEV;

	switch (rdma_node_get_transport(dev_addr->dev_type)) {
	case RDMA_TRANSPORT_IB:
		ib_addr_get_sgid(dev_addr, &gid);
		break;
	case RDMA_TRANSPORT_IWARP:
		iw_addr_get_sgid(dev_addr, &gid);
		break;
	default:
		return -ENODEV;
	}

	list_for_each_entry(cma_dev, &dev_list, list) {
		ret = ib_find_cached_gid(cma_dev->device, &gid,
					 &id_priv->id.port_num, NULL);
		if (!ret) {
			ret = cma_set_qkey(cma_dev->device,
					   id_priv->id.port_num,
					   id_priv->id.ps, dev_addr,
					   &id_priv->qkey);
			if (!ret)
				cma_attach_to_dev(id_priv, cma_dev);
			break;
		}
	}
	return ret;
}

static void cma_deref_id(struct rdma_id_private *id_priv)
{
	if (atomic_dec_and_test(&id_priv->refcount))
		complete(&id_priv->comp);
}

static int cma_disable_callback(struct rdma_id_private *id_priv,
			      enum cma_state state)
{
	mutex_lock(&id_priv->handler_mutex);
	if (id_priv->state != state) {
		mutex_unlock(&id_priv->handler_mutex);
		return -EINVAL;
	}
	return 0;
}

static int cma_has_cm_dev(struct rdma_id_private *id_priv)
{
	return (id_priv->id.device && id_priv->cm_id.ib);
}

struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler,
				  void *context, enum rdma_port_space ps)
{
	struct rdma_id_private *id_priv;

	id_priv = kzalloc(sizeof *id_priv, GFP_KERNEL);
	if (!id_priv)
		return ERR_PTR(-ENOMEM);

	id_priv->state = CMA_IDLE;
	id_priv->id.context = context;
	id_priv->id.event_handler = event_handler;
	id_priv->id.ps = ps;
	spin_lock_init(&id_priv->lock);
	mutex_init(&id_priv->qp_mutex);
	init_completion(&id_priv->comp);
	atomic_set(&id_priv->refcount, 1);
	mutex_init(&id_priv->handler_mutex);
	INIT_LIST_HEAD(&id_priv->listen_list);
	INIT_LIST_HEAD(&id_priv->mc_list);
	get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num);

	return &id_priv->id;
}
EXPORT_SYMBOL(rdma_create_id);

static int cma_init_ud_qp(struct rdma_id_private *id_priv, struct ib_qp *qp)
{
	struct ib_qp_attr qp_attr;
	int qp_attr_mask, ret;

	qp_attr.qp_state = IB_QPS_INIT;
	ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask);
	if (ret)
		return ret;

	ret = ib_modify_qp(qp, &qp_attr, qp_attr_mask);
	if (ret)
		return ret;

	qp_attr.qp_state = IB_QPS_RTR;
	ret = ib_modify_qp(qp, &qp_attr, IB_QP_STATE);
	if (ret)
		return ret;

	qp_attr.qp_state = IB_QPS_RTS;
	qp_attr.sq_psn = 0;
	ret = ib_modify_qp(qp, &qp_attr, IB_QP_STATE | IB_QP_SQ_PSN);

	return ret;
}

static int cma_init_conn_qp(struct rdma_id_private *id_priv, struct ib_qp *qp)
{
	struct ib_qp_attr qp_attr;
	int qp_attr_mask, ret;

	qp_attr.qp_state = IB_QPS_INIT;
	ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask);
	if (ret)
		return ret;

	return ib_modify_qp(qp, &qp_attr, qp_attr_mask);
}

int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd,
		   struct ib_qp_init_attr *qp_init_attr)
{
	struct rdma_id_private *id_priv;
	struct ib_qp *qp;
	int ret;

	id_priv = container_of(id, struct rdma_id_private, id);
	if (id->device != pd->device)
		return -EINVAL;

	qp = ib_create_qp(pd, qp_init_attr);
	if (IS_ERR(qp))
		return PTR_ERR(qp);

	if (cma_is_ud_ps(id_priv->id.ps))
		ret = cma_init_ud_qp(id_priv, qp);
	else
		ret = cma_init_conn_qp(id_priv, qp);
	if (ret)
		goto err;

	id->qp = qp;
	id_priv->qp_num = qp->qp_num;
	id_priv->srq = (qp->srq != NULL);
	return 0;
err:
	ib_destroy_qp(qp);
	return ret;
}
EXPORT_SYMBOL(rdma_create_qp);

void rdma_destroy_qp(struct rdma_cm_id *id)
{
	struct rdma_id_private *id_priv;

	id_priv = container_of(id, struct rdma_id_private, id);
	mutex_lock(&id_priv->qp_mutex);
	ib_destroy_qp(id_priv->id.qp);
	id_priv->id.qp = NULL;
	mutex_unlock(&id_priv->qp_mutex);
}
EXPORT_SYMBOL(rdma_destroy_qp);

static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
			     struct rdma_conn_param *conn_param)
{
	struct ib_qp_attr qp_attr;
	int qp_attr_mask, ret;

	mutex_lock(&id_priv->qp_mutex);
	if (!id_priv->id.qp) {
		ret = 0;
		goto out;
	}

	/* Need to update QP attributes from default values. */
	qp_attr.qp_state = IB_QPS_INIT;
	ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask);
	if (ret)
		goto out;

	ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask);
	if (ret)
		goto out;

	qp_attr.qp_state = IB_QPS_RTR;
	ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask);
	if (ret)
		goto out;

	if (conn_param)
		qp_attr.max_dest_rd_atomic = conn_param->responder_resources;
	ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask);
out:
	mutex_unlock(&id_priv->qp_mutex);
	return ret;
}

static int cma_modify_qp_rts(struct rdma_id_private *id_priv,
			     struct rdma_conn_param *conn_param)
{
	struct ib_qp_attr qp_attr;
	int qp_attr_mask, ret;

	mutex_lock(&id_priv->qp_mutex);
	if (!id_priv->id.qp) {
		ret = 0;
		goto out;
	}

	qp_attr.qp_state = IB_QPS_RTS;
	ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask);
	if (ret)
		goto out;

	if (conn_param)
		qp_attr.max_rd_atomic = conn_param->initiator_depth;
	ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask);
out:
	mutex_unlock(&id_priv->qp_mutex);
	return ret;
}

static int cma_modify_qp_err(struct rdma_id_private *id_priv)
{
	struct ib_qp_attr qp_attr;
	int ret;

	mutex_lock(&id_priv->qp_mutex);
	if (!id_priv->id.qp) {
		ret = 0;
		goto out;
	}

	qp_attr.qp_state = IB_QPS_ERR;
	ret = ib_modify_qp(id_priv->id.qp, &qp_attr, IB_QP_STATE);
out:
	mutex_unlock(&id_priv->qp_mutex);
	return ret;
}

static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv,
			       struct ib_qp_attr *qp_attr, int *qp_attr_mask)
{
	struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
	int ret;

	ret = ib_find_cached_pkey(id_priv->id.device, id_priv->id.port_num,
				  ib_addr_get_pkey(dev_addr),
				  &qp_attr->pkey_index);
	if (ret)
		return ret;

	qp_attr->port_num = id_priv->id.port_num;
	*qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT;

	if (cma_is_ud_ps(id_priv->id.ps)) {
		qp_attr->qkey = id_priv->qkey;
		*qp_attr_mask |= IB_QP_QKEY;
	} else {
		qp_attr->qp_access_flags = 0;
		*qp_attr_mask |= IB_QP_ACCESS_FLAGS;
	}
	return 0;
}

int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
		       int *qp_attr_mask)
{
	struct rdma_id_private *id_priv;
	int ret = 0;

	id_priv = container_of(id, struct rdma_id_private, id);
	switch (rdma_node_get_transport(id_priv->id.device->node_type)) {
	case RDMA_TRANSPORT_IB:
		if (!id_priv->cm_id.ib || cma_is_ud_ps(id_priv->id.ps))
			ret = cma_ib_init_qp_attr(id_priv, qp_attr, qp_attr_mask);
		else
			ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, qp_attr,
						 qp_attr_mask);
		if (qp_attr->qp_state == IB_QPS_RTR)
			qp_attr->rq_psn = id_priv->seq_num;
		break;
	case RDMA_TRANSPORT_IWARP:
		if (!id_priv->cm_id.iw) {
			qp_attr->qp_access_flags = 0;
			*qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS;
		} else
			ret = iw_cm_init_qp_attr(id_priv->cm_id.iw, qp_attr,
						 qp_attr_mask);
		break;
	default:
		ret = -ENOSYS;
		break;
	}

	return ret;
}
EXPORT_SYMBOL(rdma_init_qp_attr);

static inline int cma_zero_addr(struct sockaddr *addr)
{
	struct in6_addr *ip6;

	if (addr->sa_family == AF_INET)
		return ipv4_is_zeronet(
			((struct sockaddr_in *)addr)->sin_addr.s_addr);
	else {
		ip6 = &((struct sockaddr_in6 *) addr)->sin6_addr;
		return (ip6->s6_addr32[0] | ip6->s6_addr32[1] |
			ip6->s6_addr32[2] | ip6->s6_addr32[3]) == 0;
	}
}

static inline int cma_loopback_addr(struct sockaddr *addr)
{
	return ipv4_is_loopback(((struct sockaddr_in *) addr)->sin_addr.s_addr);
}

static inline int cma_any_addr(struct sockaddr *addr)
{
	return cma_zero_addr(addr) || cma_loopback_addr(addr);
}

static inline __be16 cma_port(struct sockaddr *addr)
{
	if (addr->sa_family == AF_INET)
		return ((struct sockaddr_in *) addr)->sin_port;
	else
		return ((struct sockaddr_in6 *) addr)->sin6_port;
}

static inline int cma_any_port(struct sockaddr *addr)
{
	return !cma_port(addr);
}

static int cma_get_net_info(void *hdr, enum rdma_port_space ps,
			    u8 *ip_ver, __be16 *port,
			    union cma_ip_addr **src, union cma_ip_addr **dst)
{
	switch (ps) {
	case RDMA_PS_SDP:
		if (sdp_get_majv(((struct sdp_hh *) hdr)->sdp_version) !=
		    SDP_MAJ_VERSION)
			return -EINVAL;

		*ip_ver	= sdp_get_ip_ver(hdr);
		*port	= ((struct sdp_hh *) hdr)->port;
		*src	= &((struct sdp_hh *) hdr)->src_addr;
		*dst	= &((struct sdp_hh *) hdr)->dst_addr;
		break;
	default:
		if (((struct cma_hdr *) hdr)->cma_version != CMA_VERSION)
			return -EINVAL;

		*ip_ver	= cma_get_ip_ver(hdr);
		*port	= ((struct cma_hdr *) hdr)->port;
		*src	= &((struct cma_hdr *) hdr)->src_addr;
		*dst	= &((struct cma_hdr *) hdr)->dst_addr;
		break;
	}

	if (*ip_ver != 4 && *ip_ver != 6)
		return -EINVAL;
	return 0;
}

static void cma_save_net_info(struct rdma_addr *addr,
			      struct rdma_addr *listen_addr,
			      u8 ip_ver, __be16 port,
			      union cma_ip_addr *src, union cma_ip_addr *dst)
{
	struct sockaddr_in *listen4, *ip4;
	struct sockaddr_in6 *listen6, *ip6;

	switch (ip_ver) {
	case 4:
		listen4 = (struct sockaddr_in *) &listen_addr->src_addr;
		ip4 = (struct sockaddr_in *) &addr->src_addr;
		ip4->sin_family = listen4->sin_family;
		ip4->sin_addr.s_addr = dst->ip4.addr;
		ip4->sin_port = listen4->sin_port;

		ip4 = (struct sockaddr_in *) &addr->dst_addr;
		ip4->sin_family = listen4->sin_family;
		ip4->sin_addr.s_addr = src->ip4.addr;
		ip4->sin_port = port;
		break;
	case 6:
		listen6 = (struct sockaddr_in6 *) &listen_addr->src_addr;
		ip6 = (struct sockaddr_in6 *) &addr->src_addr;
		ip6->sin6_family = listen6->sin6_family;
		ip6->sin6_addr = dst->ip6;
		ip6->sin6_port = listen6->sin6_port;

		ip6 = (struct sockaddr_in6 *) &addr->dst_addr;
		ip6->sin6_family = listen6->sin6_family;
		ip6->sin6_addr = src->ip6;
		ip6->sin6_port = port;
		break;
	default:
		break;
	}
}

static inline int cma_user_data_offset(enum rdma_port_space ps)
{
	switch (ps) {
	case RDMA_PS_SDP:
		return 0;
	default:
		return sizeof(struct cma_hdr);
	}
}

static void cma_cancel_route(struct rdma_id_private *id_priv)
{
	switch (rdma_node_get_transport(id_priv->id.device->node_type)) {
	case RDMA_TRANSPORT_IB:
		if (id_priv->query)
			ib_sa_cancel_query(id_priv->query_id, id_priv->query);
		break;
	default:
		break;
	}
}

static void cma_cancel_listens(struct rdma_id_private *id_priv)
{
	struct rdma_id_private *dev_id_priv;

	/*
	 * Remove from listen_any_list to prevent added devices from spawning
	 * additional listen requests.
	 */
	mutex_lock(&lock);
	list_del(&id_priv->list);

	while (!list_empty(&id_priv->listen_list)) {
		dev_id_priv = list_entry(id_priv->listen_list.next,
					 struct rdma_id_private, listen_list);
		/* sync with device removal to avoid duplicate destruction */
		list_del_init(&dev_id_priv->list);
		list_del(&dev_id_priv->listen_list);
		mutex_unlock(&lock);

		rdma_destroy_id(&dev_id_priv->id);
		mutex_lock(&lock);
	}
	mutex_unlock(&lock);
}

static void cma_cancel_operation(struct rdma_id_private *id_priv,
				 enum cma_state state)
{
	switch (state) {
	case CMA_ADDR_QUERY:
		rdma_addr_cancel(&id_priv->id.route.addr.dev_addr);
		break;
	case CMA_ROUTE_QUERY:
		cma_cancel_route(id_priv);
		break;
	case CMA_LISTEN:
		if (cma_any_addr((struct sockaddr *) &id_priv->id.route.addr.src_addr)
				&& !id_priv->cma_dev)
			cma_cancel_listens(id_priv);
		break;
	default:
		break;
	}
}

static void cma_release_port(struct rdma_id_private *id_priv)
{
	struct rdma_bind_list *bind_list = id_priv->bind_list;

	if (!bind_list)
		return;

	mutex_lock(&lock);
	hlist_del(&id_priv->node);
	if (hlist_empty(&bind_list->owners)) {
		idr_remove(bind_list->ps, bind_list->port);
		kfree(bind_list);
	}
	mutex_unlock(&lock);
}

static void cma_leave_mc_groups(struct rdma_id_private *id_priv)
{
	struct cma_multicast *mc;

	while (!list_empty(&id_priv->mc_list)) {
		mc = container_of(id_priv->mc_list.next,
				  struct cma_multicast, list);
		list_del(&mc->list);
		ib_sa_free_multicast(mc->multicast.ib);
		kfree(mc);
	}
}

void rdma_destroy_id(struct rdma_cm_id *id)
{
	struct rdma_id_private *id_priv;
	enum cma_state state;

	id_priv = container_of(id, struct rdma_id_private, id);
	state = cma_exch(id_priv, CMA_DESTROYING);
	cma_cancel_operation(id_priv, state);

	mutex_lock(&lock);
	if (id_priv->cma_dev) {
		mutex_unlock(&lock);
		switch (rdma_node_get_transport(id->device->node_type)) {
		case RDMA_TRANSPORT_IB:
			if (id_priv->cm_id.ib && !IS_ERR(id_priv->cm_id.ib))
				ib_destroy_cm_id(id_priv->cm_id.ib);
			break;
		case RDMA_TRANSPORT_IWARP:
			if (id_priv->cm_id.iw && !IS_ERR(id_priv->cm_id.iw))
				iw_destroy_cm_id(id_priv->cm_id.iw);
			break;
		default:
			break;
		}
		cma_leave_mc_groups(id_priv);
		mutex_lock(&lock);
		cma_detach_from_dev(id_priv);
	}
	mutex_unlock(&lock);

	cma_release_port(id_priv);
	cma_deref_id(id_priv);
	wait_for_completion(&id_priv->comp);

	if (id_priv->internal_id)
		cma_deref_id(id_priv->id.context);

	kfree(id_priv->id.route.path_rec);
	kfree(id_priv);
}
EXPORT_SYMBOL(rdma_destroy_id);

static int cma_rep_recv(struct rdma_id_private *id_priv)
{
	int ret;

	ret = cma_modify_qp_rtr(id_priv, NULL);
	if (ret)
		goto reject;

	ret = cma_modify_qp_rts(id_priv, NULL);
	if (ret)
		goto reject;

	ret = ib_send_cm_rtu(id_priv->cm_id.ib, NULL, 0);
	if (ret)
		goto reject;

	return 0;
reject:
	cma_modify_qp_err(id_priv);
	ib_send_cm_rej(id_priv->cm_id.ib, IB_CM_REJ_CONSUMER_DEFINED,
		       NULL, 0, NULL, 0);
	return ret;
}

static int cma_verify_rep(struct rdma_id_private *id_priv, void *data)
{
	if (id_priv->id.ps == RDMA_PS_SDP &&
	    sdp_get_majv(((struct sdp_hah *) data)->sdp_version) !=
	    SDP_MAJ_VERSION)
		return -EINVAL;

	return 0;
}

static void cma_set_rep_event_data(struct rdma_cm_event *event,
				   struct ib_cm_rep_event_param *rep_data,
				   void *private_data)
{
	event->param.conn.private_data = private_data;
	event->param.conn.private_data_len = IB_CM_REP_PRIVATE_DATA_SIZE;
	event->param.conn.responder_resources = rep_data->responder_resources;
	event->param.conn.initiator_depth = rep_data->initiator_depth;
	event->param.conn.flow_control = rep_data->flow_control;
	event->param.conn.rnr_retry_count = rep_data->rnr_retry_count;
	event->param.conn.srq = rep_data->srq;
	event->param.conn.qp_num = rep_data->remote_qpn;
}

static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
{
	struct rdma_id_private *id_priv = cm_id->context;
	struct rdma_cm_event event;
	int ret = 0;

	if ((ib_event->event != IB_CM_TIMEWAIT_EXIT &&
		cma_disable_callback(id_priv, CMA_CONNECT)) ||
	    (ib_event->event == IB_CM_TIMEWAIT_EXIT &&
		cma_disable_callback(id_priv, CMA_DISCONNECT)))
		return 0;

	memset(&event, 0, sizeof event);
	switch (ib_event->event) {
	case IB_CM_REQ_ERROR:
	case IB_CM_REP_ERROR:
		event.event = RDMA_CM_EVENT_UNREACHABLE;
		event.status = -ETIMEDOUT;
		break;
	case IB_CM_REP_RECEIVED:
		event.status = cma_verify_rep(id_priv, ib_event->private_data);
		if (event.status)
			event.event = RDMA_CM_EVENT_CONNECT_ERROR;
		else if (id_priv->id.qp && id_priv->id.ps != RDMA_PS_SDP) {
			event.status = cma_rep_recv(id_priv);
			event.event = event.status ? RDMA_CM_EVENT_CONNECT_ERROR :
						     RDMA_CM_EVENT_ESTABLISHED;
		} else
			event.event = RDMA_CM_EVENT_CONNECT_RESPONSE;
		cma_set_rep_event_data(&event, &ib_event->param.rep_rcvd,
				       ib_event->private_data);
		break;
	case IB_CM_RTU_RECEIVED:
	case IB_CM_USER_ESTABLISHED:
		event.event = RDMA_CM_EVENT_ESTABLISHED;
		break;
	case IB_CM_DREQ_ERROR:
		event.status = -ETIMEDOUT; /* fall through */
	case IB_CM_DREQ_RECEIVED:
	case IB_CM_DREP_RECEIVED:
		if (!cma_comp_exch(id_priv, CMA_CONNECT, CMA_DISCONNECT))
			goto out;
		event.event = RDMA_CM_EVENT_DISCONNECTED;
		break;
	case IB_CM_TIMEWAIT_EXIT:
		event.event = RDMA_CM_EVENT_TIMEWAIT_EXIT;
		break;
	case IB_CM_MRA_RECEIVED:
		/* ignore event */
		goto out;
	case IB_CM_REJ_RECEIVED:
		cma_modify_qp_err(id_priv);
		event.status = ib_event->param.rej_rcvd.reason;
		event.event = RDMA_CM_EVENT_REJECTED;
		event.param.conn.private_data = ib_event->private_data;
		event.param.conn.private_data_len = IB_CM_REJ_PRIVATE_DATA_SIZE;
		break;
	default:
		printk(KERN_ERR "RDMA CMA: unexpected IB CM event: %d\n",
		       ib_event->event);
		goto out;
	}

	ret = id_priv->id.event_handler(&id_priv->id, &event);
	if (ret) {
		/* Destroy the CM ID by returning a non-zero value. */
		id_priv->cm_id.ib = NULL;
		cma_exch(id_priv, CMA_DESTROYING);
		mutex_unlock(&id_priv->handler_mutex);
		rdma_destroy_id(&id_priv->id);
		return ret;
	}
out:
	mutex_unlock(&id_priv->handler_mutex);
	return ret;
}

static struct rdma_id_private *cma_new_conn_id(struct rdma_cm_id *listen_id,
					       struct ib_cm_event *ib_event)
{
	struct rdma_id_private *id_priv;
	struct rdma_cm_id *id;
	struct rdma_route *rt;
	union cma_ip_addr *src, *dst;
	__be16 port;
	u8 ip_ver;
	int ret;

	if (cma_get_net_info(ib_event->private_data, listen_id->ps,
			     &ip_ver, &port, &src, &dst))
		goto err;

	id = rdma_create_id(listen_id->event_handler, listen_id->context,
			    listen_id->ps);
	if (IS_ERR(id))
		goto err;

	cma_save_net_info(&id->route.addr, &listen_id->route.addr,
			  ip_ver, port, src, dst);

	rt = &id->route;
	rt->num_paths = ib_event->param.req_rcvd.alternate_path ? 2 : 1;
	rt->path_rec = kmalloc(sizeof *rt->path_rec * rt->num_paths,
			       GFP_KERNEL);
	if (!rt->path_rec)
		goto destroy_id;

	rt->path_rec[0] = *ib_event->param.req_rcvd.primary_path;
	if (rt->num_paths == 2)
		rt->path_rec[1] = *ib_event->param.req_rcvd.alternate_path;

	ib_addr_set_dgid(&rt->addr.dev_addr, &rt->path_rec[0].dgid);
	ret = rdma_translate_ip((struct sockaddr *) &id->route.addr.src_addr,
				&id->route.addr.dev_addr);
	if (ret)
		goto destroy_id;

	id_priv = container_of(id, struct rdma_id_private, id);
	id_priv->state = CMA_CONNECT;
	return id_priv;

destroy_id:
	rdma_destroy_id(id);
err:
	return NULL;
}

static struct rdma_id_private *cma_new_udp_id(struct rdma_cm_id *listen_id,
					      struct ib_cm_event *ib_event)
{
	struct rdma_id_private *id_priv;
	struct rdma_cm_id *id;
	union cma_ip_addr *src, *dst;
	__be16 port;
	u8 ip_ver;
	int ret;

	id = rdma_create_id(listen_id->event_handler, listen_id->context,
			    listen_id->ps);
	if (IS_ERR(id))
		return NULL;


	if (cma_get_net_info(ib_event->private_data, listen_id->ps,
			     &ip_ver, &port, &src, &dst))
		goto err;

	cma_save_net_info(&id->route.addr, &listen_id->route.addr,
			  ip_ver, port, src, dst);

	ret = rdma_translate_ip((struct sockaddr *) &id->route.addr.src_addr,
				&id->route.addr.dev_addr);
	if (ret)
		goto err;

	id_priv = container_of(id, struct rdma_id_private, id);
	id_priv->state = CMA_CONNECT;
	return id_priv;
err:
	rdma_destroy_id(id);
	return NULL;
}

static void cma_set_req_event_data(struct rdma_cm_event *event,
				   struct ib_cm_req_event_param *req_data,
				   void *private_data, int offset)
{
	event->param.conn.private_data = private_data + offset;
	event->param.conn.private_data_len = IB_CM_REQ_PRIVATE_DATA_SIZE - offset;
	event->param.conn.responder_resources = req_data->responder_resources;
	event->param.conn.initiator_depth = req_data->initiator_depth;
	event->param.conn.flow_control = req_data->flow_control;
	event->param.conn.retry_count = req_data->retry_count;
	event->param.conn.rnr_retry_count = req_data->rnr_retry_count;
	event->param.conn.srq = req_data->srq;
	event->param.conn.qp_num = req_data->remote_qpn;
}

static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
{
	struct rdma_id_private *listen_id, *conn_id;
	struct rdma_cm_event event;
	int offset, ret;

	listen_id = cm_id->context;
	if (cma_disable_callback(listen_id, CMA_LISTEN))
		return -ECONNABORTED;

	memset(&event, 0, sizeof event);
	offset = cma_user_data_offset(listen_id->id.ps);
	event.event = RDMA_CM_EVENT_CONNECT_REQUEST;
	if (cma_is_ud_ps(listen_id->id.ps)) {
		conn_id = cma_new_udp_id(&listen_id->id, ib_event);
		event.param.ud.private_data = ib_event->private_data + offset;
		event.param.ud.private_data_len =
				IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE - offset;
	} else {
		conn_id = cma_new_conn_id(&listen_id->id, ib_event);
		cma_set_req_event_data(&event, &ib_event->param.req_rcvd,
				       ib_event->private_data, offset);
	}
	if (!conn_id) {
		ret = -ENOMEM;
		goto out;
	}

	mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING);
	mutex_lock(&lock);
	ret = cma_acquire_dev(conn_id);
	mutex_unlock(&lock);
	if (ret)
		goto release_conn_id;

	conn_id->cm_id.ib = cm_id;
	cm_id->context = conn_id;
	cm_id->cm_handler = cma_ib_handler;

	ret = conn_id->id.event_handler(&conn_id->id, &event);
	if (!ret) {
		/*
		 * Acquire mutex to prevent user executing rdma_destroy_id()
		 * while we're accessing the cm_id.
		 */
		mutex_lock(&lock);
		if (cma_comp(conn_id, CMA_CONNECT) &&
		    !cma_is_ud_ps(conn_id->id.ps))
			ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
		mutex_unlock(&lock);
		mutex_unlock(&conn_id->handler_mutex);
		goto out;
	}

	/* Destroy the CM ID by returning a non-zero value. */
	conn_id->cm_id.ib = NULL;

release_conn_id:
	cma_exch(conn_id, CMA_DESTROYING);
	mutex_unlock(&conn_id->handler_mutex);
	rdma_destroy_id(&conn_id->id);

out:
	mutex_unlock(&listen_id->handler_mutex);
	return ret;
}

static __be64 cma_get_service_id(enum rdma_port_space ps, struct sockaddr *addr)
{
	return cpu_to_be64(((u64)ps << 16) + be16_to_cpu(cma_port(addr)));
}

static void cma_set_compare_data(enum rdma_port_space ps, struct sockaddr *addr,
				 struct ib_cm_compare_data *compare)
{
	struct cma_hdr *cma_data, *cma_mask;
	struct sdp_hh *sdp_data, *sdp_mask;
	__be32 ip4_addr;
	struct in6_addr ip6_addr;

	memset(compare, 0, sizeof *compare);
	cma_data = (void *) compare->data;
	cma_mask = (void *) compare->mask;
	sdp_data = (void *) compare->data;
	sdp_mask = (void *) compare->mask;

	switch (addr->sa_family) {
	case AF_INET:
		ip4_addr = ((struct sockaddr_in *) addr)->sin_addr.s_addr;
		if (ps == RDMA_PS_SDP) {
			sdp_set_ip_ver(sdp_data, 4);
			sdp_set_ip_ver(sdp_mask, 0xF);
			sdp_data->dst_addr.ip4.addr = ip4_addr;
			sdp_mask->dst_addr.ip4.addr = htonl(~0);
		} else {
			cma_set_ip_ver(cma_data, 4);
			cma_set_ip_ver(cma_mask, 0xF);
			cma_data->dst_addr.ip4.addr = ip4_addr;
			cma_mask->dst_addr.ip4.addr = htonl(~0);
		}
		break;
	case AF_INET6:
		ip6_addr = ((struct sockaddr_in6 *) addr)->sin6_addr;
		if (ps == RDMA_PS_SDP) {
			sdp_set_ip_ver(sdp_data, 6);
			sdp_set_ip_ver(sdp_mask, 0xF);
			sdp_data->dst_addr.ip6 = ip6_addr;
			memset(&sdp_mask->dst_addr.ip6, 0xFF,
			       sizeof sdp_mask->dst_addr.ip6);
		} else {
			cma_set_ip_ver(cma_data, 6);
			cma_set_ip_ver(cma_mask, 0xF);
			cma_data->dst_addr.ip6 = ip6_addr;
			memset(&cma_mask->dst_addr.ip6, 0xFF,
			       sizeof cma_mask->dst_addr.ip6);
		}
		break;
	default:
		break;
	}
}

static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event)
{
	struct rdma_id_private *id_priv = iw_id->context;
	struct rdma_cm_event event;
	struct sockaddr_in *sin;
	int ret = 0;

	if (cma_disable_callback(id_priv, CMA_CONNECT))
		return 0;

	memset(&event, 0, sizeof event);
	switch (iw_event->event) {
	case IW_CM_EVENT_CLOSE:
		event.event = RDMA_CM_EVENT_DISCONNECTED;
		break;
	case IW_CM_EVENT_CONNECT_REPLY:
		sin = (struct sockaddr_in *) &id_priv->id.route.addr.src_addr;
		*sin = iw_event->local_addr;
		sin = (struct sockaddr_in *) &id_priv->id.route.addr.dst_addr;
		*sin = iw_event->remote_addr;
		switch (iw_event->status) {
		case 0:
			event.event = RDMA_CM_EVENT_ESTABLISHED;
			break;
		case -ECONNRESET:
		case -ECONNREFUSED:
			event.event = RDMA_CM_EVENT_REJECTED;
			break;
		case -ETIMEDOUT:
			event.event = RDMA_CM_EVENT_UNREACHABLE;
			break;
		default:
			event.event = RDMA_CM_EVENT_CONNECT_ERROR;
			break;
		}
		break;
	case IW_CM_EVENT_ESTABLISHED:
		event.event = RDMA_CM_EVENT_ESTABLISHED;
		break;
	default:
		BUG_ON(1);
	}

	event.status = iw_event->status;
	event.param.conn.private_data = iw_event->private_data;
	event.param.conn.private_data_len = iw_event->private_data_len;
	ret = id_priv->id.event_handler(&id_priv->id, &event);
	if (ret) {
		/* Destroy the CM ID by returning a non-zero value. */
		id_priv->cm_id.iw = NULL;
		cma_exch(id_priv, CMA_DESTROYING);
		mutex_unlock(&id_priv->handler_mutex);
		rdma_destroy_id(&id_priv->id);
		return ret;
	}

	mutex_unlock(&id_priv->handler_mutex);
	return ret;
}

static int iw_conn_req_handler(struct iw_cm_id *cm_id,
			       struct iw_cm_event *iw_event)
{
	struct rdma_cm_id *new_cm_id;
	struct rdma_id_private *listen_id, *conn_id;
	struct sockaddr_in *sin;
	struct net_device *dev = NULL;
	struct rdma_cm_event event;
	int ret;
	struct ib_device_attr attr;

	listen_id = cm_id->context;
	if (cma_disable_callback(listen_id, CMA_LISTEN))
		return -ECONNABORTED;

	/* Create a new RDMA id for the new IW CM ID */
	new_cm_id = rdma_create_id(listen_id->id.event_handler,
				   listen_id->id.context,
				   RDMA_PS_TCP);
	if (IS_ERR(new_cm_id)) {
		ret = -ENOMEM;
		goto out;
	}
	conn_id = container_of(new_cm_id, struct rdma_id_private, id);
	mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING);
	conn_id->state = CMA_CONNECT;

	dev = ip_dev_find(&init_net, iw_event->local_addr.sin_addr.s_addr);
	if (!dev) {
		ret = -EADDRNOTAVAIL;
		mutex_unlock(&conn_id->handler_mutex);
		rdma_destroy_id(new_cm_id);
		goto out;
	}
	ret = rdma_copy_addr(&conn_id->id.route.addr.dev_addr, dev, NULL);
	if (ret) {
		mutex_unlock(&conn_id->handler_mutex);
		rdma_destroy_id(new_cm_id);
		goto out;
	}

	mutex_lock(&lock);
	ret = cma_acquire_dev(conn_id);
	mutex_unlock(&lock);
	if (ret) {
		mutex_unlock(&conn_id->handler_mutex);
		rdma_destroy_id(new_cm_id);
		goto out;
	}

	conn_id->cm_id.iw = cm_id;
	cm_id->context = conn_id;
	cm_id->cm_handler = cma_iw_handler;

	sin = (struct sockaddr_in *) &new_cm_id->route.addr.src_addr;
	*sin = iw_event->local_addr;
	sin = (struct sockaddr_in *) &new_cm_id->route.addr.dst_addr;
	*sin = iw_event->remote_addr;

	ret = ib_query_device(conn_id->id.device, &attr);
	if (ret) {
		mutex_unlock(&conn_id->handler_mutex);
		rdma_destroy_id(new_cm_id);
		goto out;
	}

	memset(&event, 0, sizeof event);
	event.event = RDMA_CM_EVENT_CONNECT_REQUEST;
	event.param.conn.private_data = iw_event->private_data;
	event.param.conn.private_data_len = iw_event->private_data_len;
	event.param.conn.initiator_depth = attr.max_qp_init_rd_atom;
	event.param.conn.responder_resources = attr.max_qp_rd_atom;
	ret = conn_id->id.event_handler(&conn_id->id, &event);
	if (ret) {
		/* User wants to destroy the CM ID */
		conn_id->cm_id.iw = NULL;
		cma_exch(conn_id, CMA_DESTROYING);
		mutex_unlock(&conn_id->handler_mutex);
		rdma_destroy_id(&conn_id->id);
		goto out;
	}

	mutex_unlock(&conn_id->handler_mutex);

out:
	if (dev)
		dev_put(dev);
	mutex_unlock(&listen_id->handler_mutex);
	return ret;
}

static int cma_ib_listen(struct rdma_id_private *id_priv)
{
	struct ib_cm_compare_data compare_data;
	struct sockaddr *addr;
	__be64 svc_id;
	int ret;

	id_priv->cm_id.ib = ib_create_cm_id(id_priv->id.device, cma_req_handler,
					    id_priv);
	if (IS_ERR(id_priv->cm_id.ib))
		return PTR_ERR(id_priv->cm_id.ib);

	addr = (struct sockaddr *) &id_priv->id.route.addr.src_addr;
	svc_id = cma_get_service_id(id_priv->id.ps, addr);
	if (cma_any_addr(addr))
		ret = ib_cm_listen(id_priv->cm_id.ib, svc_id, 0, NULL);
	else {
		cma_set_compare_data(id_priv->id.ps, addr, &compare_data);
		ret = ib_cm_listen(id_priv->cm_id.ib, svc_id, 0, &compare_data);
	}

	if (ret) {
		ib_destroy_cm_id(id_priv->cm_id.ib);
		id_priv->cm_id.ib = NULL;
	}

	return ret;
}

static int cma_iw_listen(struct rdma_id_private *id_priv, int backlog)
{
	int ret;
	struct sockaddr_in *sin;

	id_priv->cm_id.iw = iw_create_cm_id(id_priv->id.device,
					    iw_conn_req_handler,
					    id_priv);
	if (IS_ERR(id_priv->cm_id.iw))
		return PTR_ERR(id_priv->cm_id.iw);

	sin = (struct sockaddr_in *) &id_priv->id.route.addr.src_addr;
	id_priv->cm_id.iw->local_addr = *sin;

	ret = iw_cm_listen(id_priv->cm_id.iw, backlog);

	if (ret) {
		iw_destroy_cm_id(id_priv->cm_id.iw);
		id_priv->cm_id.iw = NULL;
	}

	return ret;
}

static int cma_listen_handler(struct rdma_cm_id *id,
			      struct rdma_cm_event *event)
{
	struct rdma_id_private *id_priv = id->context;

	id->context = id_priv->id.context;
	id->event_handler = id_priv->id.event_handler;
	return id_priv->id.event_handler(id, event);
}

static void cma_listen_on_dev(struct rdma_id_private *id_priv,
			      struct cma_device *cma_dev)
{
	struct rdma_id_private *dev_id_priv;
	struct rdma_cm_id *id;
	int ret;

	id = rdma_create_id(cma_listen_handler, id_priv, id_priv->id.ps);
	if (IS_ERR(id))
		return;

	dev_id_priv = container_of(id, struct rdma_id_private, id);

	dev_id_priv->state = CMA_ADDR_BOUND;
	memcpy(&id->route.addr.src_addr, &id_priv->id.route.addr.src_addr,
	       ip_addr_size((struct sockaddr *) &id_priv->id.route.addr.src_addr));

	cma_attach_to_dev(dev_id_priv, cma_dev);
	list_add_tail(&dev_id_priv->listen_list, &id_priv->listen_list);
	atomic_inc(&id_priv->refcount);
	dev_id_priv->internal_id = 1;

	ret = rdma_listen(id, id_priv->backlog);
	if (ret)
		printk(KERN_WARNING "RDMA CMA: cma_listen_on_dev, error %d, "
		       "listening on device %s\n", ret, cma_dev->device->name);
}

static void cma_listen_on_all(struct rdma_id_private *id_priv)
{
	struct cma_device *cma_dev;

	mutex_lock(&lock);
	list_add_tail(&id_priv->list, &listen_any_list);
	list_for_each_entry(cma_dev, &dev_list, list)
		cma_listen_on_dev(id_priv, cma_dev);
	mutex_unlock(&lock);
}

static int cma_bind_any(struct rdma_cm_id *id, sa_family_t af)
{
	struct sockaddr_in addr_in;

	memset(&addr_in, 0, sizeof addr_in);
	addr_in.sin_family = af;
	return rdma_bind_addr(id, (struct sockaddr *) &addr_in);
}

int rdma_listen(struct rdma_cm_id *id, int backlog)
{
	struct rdma_id_private *id_priv;
	int ret;

	id_priv = container_of(id, struct rdma_id_private, id);
	if (id_priv->state == CMA_IDLE) {
		ret = cma_bind_any(id, AF_INET);
		if (ret)
			return ret;
	}

	if (!cma_comp_exch(id_priv, CMA_ADDR_BOUND, CMA_LISTEN))
		return -EINVAL;

	id_priv->backlog = backlog;
	if (id->device) {
		switch (rdma_node_get_transport(id->device->node_type)) {
		case RDMA_TRANSPORT_IB:
			ret = cma_ib_listen(id_priv);
			if (ret)
				goto err;
			break;
		case RDMA_TRANSPORT_IWARP:
			ret = cma_iw_listen(id_priv, backlog);
			if (ret)
				goto err;
			break;
		default:
			ret = -ENOSYS;
			goto err;
		}
	} else
		cma_listen_on_all(id_priv);

	return 0;
err:
	id_priv->backlog = 0;
	cma_comp_exch(id_priv, CMA_LISTEN, CMA_ADDR_BOUND);
	return ret;
}
EXPORT_SYMBOL(rdma_listen);

void rdma_set_service_type(struct rdma_cm_id *id, int tos)
{
	struct rdma_id_private *id_priv;

	id_priv = container_of(id, struct rdma_id_private, id);
	id_priv->tos = (u8) tos;
}
EXPORT_SYMBOL(rdma_set_service_type);

static void cma_query_handler(int status, struct ib_sa_path_rec *path_rec,
			      void *context)
{
	struct cma_work *work = context;
	struct rdma_route *route;

	route = &work->id->id.route;

	if (!status) {
		route->num_paths = 1;
		*route->path_rec = *path_rec;
	} else {
		work->old_state = CMA_ROUTE_QUERY;
		work->new_state = CMA_ADDR_RESOLVED;
		work->event.event = RDMA_CM_EVENT_ROUTE_ERROR;
		work->event.status = status;
	}

	queue_work(cma_wq, &work->work);
}

static int cma_query_ib_route(struct rdma_id_private *id_priv, int timeout_ms,
			      struct cma_work *work)
{
	struct rdma_addr *addr = &id_priv->id.route.addr;
	struct ib_sa_path_rec path_rec;
	ib_sa_comp_mask comp_mask;
	struct sockaddr_in6 *sin6;

	memset(&path_rec, 0, sizeof path_rec);
	ib_addr_get_sgid(&addr->dev_addr, &path_rec.sgid);
	ib_addr_get_dgid(&addr->dev_addr, &path_rec.dgid);
	path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(&addr->dev_addr));
	path_rec.numb_path = 1;
	path_rec.reversible = 1;
	path_rec.service_id = cma_get_service_id(id_priv->id.ps,
							(struct sockaddr *) &addr->dst_addr);

	comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
		    IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
		    IB_SA_PATH_REC_REVERSIBLE | IB_SA_PATH_REC_SERVICE_ID;

	if (addr->src_addr.ss_family == AF_INET) {
		path_rec.qos_class = cpu_to_be16((u16) id_priv->tos);
		comp_mask |= IB_SA_PATH_REC_QOS_CLASS;
	} else {
		sin6 = (struct sockaddr_in6 *) &addr->src_addr;
		path_rec.traffic_class = (u8) (be32_to_cpu(sin6->sin6_flowinfo) >> 20);
		comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS;
	}

	id_priv->query_id = ib_sa_path_rec_get(&sa_client, id_priv->id.device,
					       id_priv->id.port_num, &path_rec,
					       comp_mask, timeout_ms,
					       GFP_KERNEL, cma_query_handler,
					       work, &id_priv->query);

	return (id_priv->query_id < 0) ? id_priv->query_id : 0;
}

static void cma_work_handler(struct work_struct *_work)
{
	struct cma_work *work = container_of(_work, struct cma_work, work);
	struct rdma_id_private *id_priv = work->id;
	int destroy = 0;

	mutex_lock(&id_priv->handler_mutex);
	if (!cma_comp_exch(id_priv, work->old_state, work->new_state))
		goto out;

	if (id_priv->id.event_handler(&id_priv->id, &work->event)) {
		cma_exch(id_priv, CMA_DESTROYING);
		destroy = 1;
	}
out:
	mutex_unlock(&id_priv->handler_mutex);
	cma_deref_id(id_priv);
	if (destroy)
		rdma_destroy_id(&id_priv->id);
	kfree(work);
}

static void cma_ndev_work_handler(struct work_struct *_work)
{
	struct cma_ndev_work *work = container_of(_work, struct cma_ndev_work, work);
	struct rdma_id_private *id_priv = work->id;
	int destroy = 0;

	mutex_lock(&id_priv->handler_mutex);
	if (id_priv->state == CMA_DESTROYING ||
	    id_priv->state == CMA_DEVICE_REMOVAL)
		goto out;

	if (id_priv->id.event_handler(&id_priv->id, &work->event)) {
		cma_exch(id_priv, CMA_DESTROYING);
		destroy = 1;
	}

out:
	mutex_unlock(&id_priv->handler_mutex);
	cma_deref_id(id_priv);
	if (destroy)
		rdma_destroy_id(&id_priv->id);
	kfree(work);
}

static int cma_resolve_ib_route(struct rdma_id_private *id_priv, int timeout_ms)
{
	struct rdma_route *route = &id_priv->id.route;
	struct cma_work *work;
	int ret;

	work = kzalloc(sizeof *work, GFP_KERNEL);
	if (!work)
		return -ENOMEM;

	work->id = id_priv;
	INIT_WORK(&work->work, cma_work_handler);
	work->old_state = CMA_ROUTE_QUERY;
	work->new_state = CMA_ROUTE_RESOLVED;
	work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED;

	route->path_rec = kmalloc(sizeof *route->path_rec, GFP_KERNEL);
	if (!route->path_rec) {
		ret = -ENOMEM;
		goto err1;
	}

	ret = cma_query_ib_route(id_priv, timeout_ms, work);
	if (ret)
		goto err2;

	return 0;
err2:
	kfree(route->path_rec);
	route->path_rec = NULL;
err1:
	kfree(work);
	return ret;
}

int rdma_set_ib_paths(struct rdma_cm_id *id,
		      struct ib_sa_path_rec *path_rec, int num_paths)
{
	struct rdma_id_private *id_priv;
	int ret;

	id_priv = container_of(id, struct rdma_id_private, id);
	if (!cma_comp_exch(id_priv, CMA_ADDR_RESOLVED, CMA_ROUTE_RESOLVED))
		return -EINVAL;

	id->route.path_rec = kmalloc(sizeof *path_rec * num_paths, GFP_KERNEL);
	if (!id->route.path_rec) {
		ret = -ENOMEM;
		goto err;
	}

	memcpy(id->route.path_rec, path_rec, sizeof *path_rec * num_paths);
	return 0;
err:
	cma_comp_exch(id_priv, CMA_ROUTE_RESOLVED, CMA_ADDR_RESOLVED);
	return ret;
}
EXPORT_SYMBOL(rdma_set_ib_paths);

static int cma_resolve_iw_route(struct rdma_id_private *id_priv, int timeout_ms)
{
	struct cma_work *work;

	work = kzalloc(sizeof *work, GFP_KERNEL);
	if (!work)
		return -ENOMEM;

	work->id = id_priv;
	INIT_WORK(&work->work, cma_work_handler);
	work->old_state = CMA_ROUTE_QUERY;
	work->new_state = CMA_ROUTE_RESOLVED;
	work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED;
	queue_work(cma_wq, &work->work);
	return 0;
}

int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms)
{
	struct rdma_id_private *id_priv;
	int ret;

	id_priv = container_of(id, struct rdma_id_private, id);
	if (!cma_comp_exch(id_priv, CMA_ADDR_RESOLVED, CMA_ROUTE_QUERY))
		return -EINVAL;

	atomic_inc(&id_priv->refcount);
	switch (rdma_node_get_transport(id->device->node_type)) {
	case RDMA_TRANSPORT_IB:
		ret = cma_resolve_ib_route(id_priv, timeout_ms);
		break;
	case RDMA_TRANSPORT_IWARP:
		ret = cma_resolve_iw_route(id_priv, timeout_ms);
		break;
	default:
		ret = -ENOSYS;
		break;
	}
	if (ret)
		goto err;

	return 0;
err:
	cma_comp_exch(id_priv, CMA_ROUTE_QUERY, CMA_ADDR_RESOLVED);
	cma_deref_id(id_priv);
	return ret;
}
EXPORT_SYMBOL(rdma_resolve_route);

static int cma_bind_loopback(struct rdma_id_private *id_priv)
{
	struct cma_device *cma_dev;
	struct ib_port_attr port_attr;
	union ib_gid gid;
	u16 pkey;
	int ret;
	u8 p;

	mutex_lock(&lock);
	if (list_empty(&dev_list)) {
		ret = -ENODEV;
		goto out;
	}
	list_for_each_entry(cma_dev, &dev_list, list)
		for (p = 1; p <= cma_dev->device->phys_port_cnt; ++p)
			if (!ib_query_port(cma_dev->device, p, &port_attr) &&
			    port_attr.state == IB_PORT_ACTIVE)
				goto port_found;

	p = 1;
	cma_dev = list_entry(dev_list.next, struct cma_device, list);

port_found:
	ret = ib_get_cached_gid(cma_dev->device, p, 0, &gid);
	if (ret)
		goto out;

	ret = ib_get_cached_pkey(cma_dev->device, p, 0, &pkey);
	if (ret)
		goto out;

	ib_addr_set_sgid(&id_priv->id.route.addr.dev_addr, &gid);
	ib_addr_set_pkey(&id_priv->id.route.addr.dev_addr, pkey);
	id_priv->id.port_num = p;
	cma_attach_to_dev(id_priv, cma_dev);
out:
	mutex_unlock(&lock);
	return ret;
}

static void addr_handler(int status, struct sockaddr *src_addr,
			 struct rdma_dev_addr *dev_addr, void *context)
{
	struct rdma_id_private *id_priv = context;
	struct rdma_cm_event event;

	memset(&event, 0, sizeof event);
	mutex_lock(&id_priv->handler_mutex);

	/*
	 * Grab mutex to block rdma_destroy_id() from removing the device while
	 * we're trying to acquire it.
	 */
	mutex_lock(&lock);
	if (!cma_comp_exch(id_priv, CMA_ADDR_QUERY, CMA_ADDR_RESOLVED)) {
		mutex_unlock(&lock);
		goto out;
	}

	if (!status && !id_priv->cma_dev)
		status = cma_acquire_dev(id_priv);
	mutex_unlock(&lock);

	if (status) {
		if (!cma_comp_exch(id_priv, CMA_ADDR_RESOLVED, CMA_ADDR_BOUND))
			goto out;
		event.event = RDMA_CM_EVENT_ADDR_ERROR;
		event.status = status;
	} else {
		memcpy(&id_priv->id.route.addr.src_addr, src_addr,
		       ip_addr_size(src_addr));
		event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
	}

	if (id_priv->id.event_handler(&id_priv->id, &event)) {
		cma_exch(id_priv, CMA_DESTROYING);
		mutex_unlock(&id_priv->handler_mutex);
		cma_deref_id(id_priv);
		rdma_destroy_id(&id_priv->id);
		return;
	}
out:
	mutex_unlock(&id_priv->handler_mutex);
	cma_deref_id(id_priv);
}

static int cma_resolve_loopback(struct rdma_id_private *id_priv)
{
	struct cma_work *work;
	struct sockaddr_in *src_in, *dst_in;
	union ib_gid gid;
	int ret;

	work = kzalloc(sizeof *work, GFP_KERNEL);
	if (!work)
		return -ENOMEM;

	if (!id_priv->cma_dev) {
		ret = cma_bind_loopback(id_priv);
		if (ret)
			goto err;
	}

	ib_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid);
	ib_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid);

	if (cma_zero_addr((struct sockaddr *) &id_priv->id.route.addr.src_addr)) {
		src_in = (struct sockaddr_in *)&id_priv->id.route.addr.src_addr;
		dst_in = (struct sockaddr_in *)&id_priv->id.route.addr.dst_addr;
		src_in->sin_family = dst_in->sin_family;
		src_in->sin_addr.s_addr = dst_in->sin_addr.s_addr;
	}

	work->id = id_priv;
	INIT_WORK(&work->work, cma_work_handler);
	work->old_state = CMA_ADDR_QUERY;
	work->new_state = CMA_ADDR_RESOLVED;
	work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
	queue_work(cma_wq, &work->work);
	return 0;
err:
	kfree(work);
	return ret;
}

static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
			 struct sockaddr *dst_addr)
{
	if (src_addr && src_addr->sa_family)
		return rdma_bind_addr(id, src_addr);
	else
		return cma_bind_any(id, dst_addr->sa_family);
}

int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
		      struct sockaddr *dst_addr, int timeout_ms)
{
	struct rdma_id_private *id_priv;
	int ret;

	id_priv = container_of(id, struct rdma_id_private, id);
	if (id_priv->state == CMA_IDLE) {
		ret = cma_bind_addr(id, src_addr, dst_addr);
		if (ret)
			return ret;
	}

	if (!cma_comp_exch(id_priv, CMA_ADDR_BOUND, CMA_ADDR_QUERY))
		return -EINVAL;

	atomic_inc(&id_priv->refcount);
	memcpy(&id->route.addr.dst_addr, dst_addr, ip_addr_size(dst_addr));
	if (cma_any_addr(dst_addr))
		ret = cma_resolve_loopback(id_priv);
	else
		ret = rdma_resolve_ip(&addr_client, (struct sockaddr *) &id->route.addr.src_addr,
				      dst_addr, &id->route.addr.dev_addr,
				      timeout_ms, addr_handler, id_priv);
	if (ret)
		goto err;

	return 0;
err:
	cma_comp_exch(id_priv, CMA_ADDR_QUERY, CMA_ADDR_BOUND);
	cma_deref_id(id_priv);
	return ret;
}
EXPORT_SYMBOL(rdma_resolve_addr);

static void cma_bind_port(struct rdma_bind_list *bind_list,
			  struct rdma_id_private *id_priv)
{
	struct sockaddr_in *sin;

	sin = (struct sockaddr_in *) &id_priv->id.route.addr.src_addr;
	sin->sin_port = htons(bind_list->port);
	id_priv->bind_list = bind_list;
	hlist_add_head(&id_priv->node, &bind_list->owners);
}

static int cma_alloc_port(struct idr *ps, struct rdma_id_private *id_priv,
			  unsigned short snum)
{
	struct rdma_bind_list *bind_list;
	int port, ret;

	bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL);
	if (!bind_list)
		return -ENOMEM;

	do {
		ret = idr_get_new_above(ps, bind_list, snum, &port);
	} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));

	if (ret)
		goto err1;

	if (port != snum) {
		ret = -EADDRNOTAVAIL;
		goto err2;
	}

	bind_list->ps = ps;
	bind_list->port = (unsigned short) port;
	cma_bind_port(bind_list, id_priv);
	return 0;
err2:
	idr_remove(ps, port);
err1:
	kfree(bind_list);
	return ret;
}

static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv)
{
	struct rdma_bind_list *bind_list;
	int port, ret, low, high;

	bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL);
	if (!bind_list)
		return -ENOMEM;

retry:
	/* FIXME: add proper port randomization per like inet_csk_get_port */
	do {
		ret = idr_get_new_above(ps, bind_list, next_port, &port);
	} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));

	if (ret)
		goto err1;

	inet_get_local_port_range(&low, &high);
	if (port > high) {
		if (next_port != low) {
			idr_remove(ps, port);
			next_port = low;
			goto retry;
		}
		ret = -EADDRNOTAVAIL;
		goto err2;
	}

	if (port == high)
		next_port = low;
	else
		next_port = port + 1;

	bind_list->ps = ps;
	bind_list->port = (unsigned short) port;
	cma_bind_port(bind_list, id_priv);
	return 0;
err2:
	idr_remove(ps, port);
err1:
	kfree(bind_list);
	return ret;
}

static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv)
{
	struct rdma_id_private *cur_id;
	struct sockaddr_in *sin, *cur_sin;
	struct rdma_bind_list *bind_list;
	struct hlist_node *node;
	unsigned short snum;

	sin = (struct sockaddr_in *) &id_priv->id.route.addr.src_addr;
	snum = ntohs(sin->sin_port);
	if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
		return -EACCES;

	bind_list = idr_find(ps, snum);
	if (!bind_list)
		return cma_alloc_port(ps, id_priv, snum);

	/*
	 * We don't support binding to any address if anyone is bound to
	 * a specific address on the same port.
	 */
	if (cma_any_addr((struct sockaddr *) &id_priv->id.route.addr.src_addr))
		return -EADDRNOTAVAIL;

	hlist_for_each_entry(cur_id, node, &bind_list->owners, node) {
		if (cma_any_addr((struct sockaddr *) &cur_id->id.route.addr.src_addr))
			return -EADDRNOTAVAIL;

		cur_sin = (struct sockaddr_in *) &cur_id->id.route.addr.src_addr;
		if (sin->sin_addr.s_addr == cur_sin->sin_addr.s_addr)
			return -EADDRINUSE;
	}

	cma_bind_port(bind_list, id_priv);
	return 0;
}

static int cma_get_port(struct rdma_id_private *id_priv)
{
	struct idr *ps;
	int ret;

	switch (id_priv->id.ps) {
	case RDMA_PS_SDP:
		ps = &sdp_ps;
		break;
	case RDMA_PS_TCP:
		ps = &tcp_ps;
		break;
	case RDMA_PS_UDP:
		ps = &udp_ps;
		break;
	case RDMA_PS_IPOIB:
		ps = &ipoib_ps;
		break;
	default:
		return -EPROTONOSUPPORT;
	}

	mutex_lock(&lock);
	if (cma_any_port((struct sockaddr *) &id_priv->id.route.addr.src_addr))
		ret = cma_alloc_any_port(ps, id_priv);
	else
		ret = cma_use_port(ps, id_priv);
	mutex_unlock(&lock);

	return ret;
}

int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
{
	struct rdma_id_private *id_priv;
	int ret;

	if (addr->sa_family != AF_INET)
		return -EAFNOSUPPORT;

	id_priv = container_of(id, struct rdma_id_private, id);
	if (!cma_comp_exch(id_priv, CMA_IDLE, CMA_ADDR_BOUND))
		return -EINVAL;

	if (!cma_any_addr(addr)) {
		ret = rdma_translate_ip(addr, &id->route.addr.dev_addr);
		if (ret)
			goto err1;

		mutex_lock(&lock);
		ret = cma_acquire_dev(id_priv);
		mutex_unlock(&lock);
		if (ret)
			goto err1;
	}

	memcpy(&id->route.addr.src_addr, addr, ip_addr_size(addr));
	ret = cma_get_port(id_priv);
	if (ret)
		goto err2;

	return 0;
err2:
	if (!cma_any_addr(addr)) {
		mutex_lock(&lock);
		cma_detach_from_dev(id_priv);
		mutex_unlock(&lock);
	}
err1:
	cma_comp_exch(id_priv, CMA_ADDR_BOUND, CMA_IDLE);
	return ret;
}
EXPORT_SYMBOL(rdma_bind_addr);

static int cma_format_hdr(void *hdr, enum rdma_port_space ps,
			  struct rdma_route *route)
{
	struct sockaddr_in *src4, *dst4;
	struct cma_hdr *cma_hdr;
	struct sdp_hh *sdp_hdr;

	src4 = (struct sockaddr_in *) &route->addr.src_addr;
	dst4 = (struct sockaddr_in *) &route->addr.dst_addr;

	switch (ps) {
	case RDMA_PS_SDP:
		sdp_hdr = hdr;
		if (sdp_get_majv(sdp_hdr->sdp_version) != SDP_MAJ_VERSION)
			return -EINVAL;
		sdp_set_ip_ver(sdp_hdr, 4);
		sdp_hdr->src_addr.ip4.addr = src4->sin_addr.s_addr;
		sdp_hdr->dst_addr.ip4.addr = dst4->sin_addr.s_addr;
		sdp_hdr->port = src4->sin_port;
		break;
	default:
		cma_hdr = hdr;
		cma_hdr->cma_version = CMA_VERSION;
		cma_set_ip_ver(cma_hdr, 4);
		cma_hdr->src_addr.ip4.addr = src4->sin_addr.s_addr;
		cma_hdr->dst_addr.ip4.addr = dst4->sin_addr.s_addr;
		cma_hdr->port = src4->sin_port;
		break;
	}
	return 0;
}

static int cma_sidr_rep_handler(struct ib_cm_id *cm_id,
				struct ib_cm_event *ib_event)
{
	struct rdma_id_private *id_priv = cm_id->context;
	struct rdma_cm_event event;
	struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd;
	int ret = 0;

	if (cma_disable_callback(id_priv, CMA_CONNECT))
		return 0;

	memset(&event, 0, sizeof event);
	switch (ib_event->event) {
	case IB_CM_SIDR_REQ_ERROR:
		event.event = RDMA_CM_EVENT_UNREACHABLE;
		event.status = -ETIMEDOUT;
		break;
	case IB_CM_SIDR_REP_RECEIVED:
		event.param.ud.private_data = ib_event->private_data;
		event.param.ud.private_data_len = IB_CM_SIDR_REP_PRIVATE_DATA_SIZE;
		if (rep->status != IB_SIDR_SUCCESS) {
			event.event = RDMA_CM_EVENT_UNREACHABLE;
			event.status = ib_event->param.sidr_rep_rcvd.status;
			break;
		}
		if (id_priv->qkey != rep->qkey) {
			event.event = RDMA_CM_EVENT_UNREACHABLE;
			event.status = -EINVAL;
			break;
		}
		ib_init_ah_from_path(id_priv->id.device, id_priv->id.port_num,
				     id_priv->id.route.path_rec,
				     &event.param.ud.ah_attr);
		event.param.ud.qp_num = rep->qpn;
		event.param.ud.qkey = rep->qkey;
		event.event = RDMA_CM_EVENT_ESTABLISHED;
		event.status = 0;
		break;
	default:
		printk(KERN_ERR "RDMA CMA: unexpected IB CM event: %d\n",
		       ib_event->event);
		goto out;
	}

	ret = id_priv->id.event_handler(&id_priv->id, &event);
	if (ret) {
		/* Destroy the CM ID by returning a non-zero value. */
		id_priv->cm_id.ib = NULL;
		cma_exch(id_priv, CMA_DESTROYING);
		mutex_unlock(&id_priv->handler_mutex);
		rdma_destroy_id(&id_priv->id);
		return ret;
	}
out:
	mutex_unlock(&id_priv->handler_mutex);
	return ret;
}

static int cma_resolve_ib_udp(struct rdma_id_private *id_priv,
			      struct rdma_conn_param *conn_param)
{
	struct ib_cm_sidr_req_param req;
	struct rdma_route *route;
	int ret;

	req.private_data_len = sizeof(struct cma_hdr) +
			       conn_param->private_data_len;
	req.private_data = kzalloc(req.private_data_len, GFP_ATOMIC);
	if (!req.private_data)
		return -ENOMEM;

	if (conn_param->private_data && conn_param->private_data_len)
		memcpy((void *) req.private_data + sizeof(struct cma_hdr),
		       conn_param->private_data, conn_param->private_data_len);

	route = &id_priv->id.route;
	ret = cma_format_hdr((void *) req.private_data, id_priv->id.ps, route);
	if (ret)
		goto out;

	id_priv->cm_id.ib = ib_create_cm_id(id_priv->id.device,
					    cma_sidr_rep_handler, id_priv);
	if (IS_ERR(id_priv->cm_id.ib)) {
		ret = PTR_ERR(id_priv->cm_id.ib);
		goto out;
	}

	req.path = route->path_rec;
	req.service_id = cma_get_service_id(id_priv->id.ps,
					    (struct sockaddr *) &route->addr.dst_addr);
	req.timeout_ms = 1 << (CMA_CM_RESPONSE_TIMEOUT - 8);
	req.max_cm_retries = CMA_MAX_CM_RETRIES;

	ret = ib_send_cm_sidr_req(id_priv->cm_id.ib, &req);
	if (ret) {
		ib_destroy_cm_id(id_priv->cm_id.ib);
		id_priv->cm_id.ib = NULL;
	}
out:
	kfree(req.private_data);
	return ret;
}

static int cma_connect_ib(struct rdma_id_private *id_priv,
			  struct rdma_conn_param *conn_param)
{
	struct ib_cm_req_param req;
	struct rdma_route *route;
	void *private_data;
	int offset, ret;

	memset(&req, 0, sizeof req);
	offset = cma_user_data_offset(id_priv->id.ps);
	req.private_data_len = offset + conn_param->private_data_len;
	private_data = kzalloc(req.private_data_len, GFP_ATOMIC);
	if (!private_data)
		return -ENOMEM;

	if (conn_param->private_data && conn_param->private_data_len)
		memcpy(private_data + offset, conn_param->private_data,
		       conn_param->private_data_len);

	id_priv->cm_id.ib = ib_create_cm_id(id_priv->id.device, cma_ib_handler,
					    id_priv);
	if (IS_ERR(id_priv->cm_id.ib)) {
		ret = PTR_ERR(id_priv->cm_id.ib);
		goto out;
	}

	route = &id_priv->id.route;
	ret = cma_format_hdr(private_data, id_priv->id.ps, route);
	if (ret)
		goto out;
	req.private_data = private_data;

	req.primary_path = &route->path_rec[0];
	if (route->num_paths == 2)
		req.alternate_path = &route->path_rec[1];

	req.service_id = cma_get_service_id(id_priv->id.ps,
					    (struct sockaddr *) &route->addr.dst_addr);
	req.qp_num = id_priv->qp_num;
	req.qp_type = IB_QPT_RC;
	req.starting_psn = id_priv->seq_num;
	req.responder_resources = conn_param->responder_resources;
	req.initiator_depth = conn_param->initiator_depth;
	req.flow_control = conn_param->flow_control;
	req.retry_count = conn_param->retry_count;
	req.rnr_retry_count = conn_param->rnr_retry_count;
	req.remote_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT;
	req.local_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT;
	req.max_cm_retries = CMA_MAX_CM_RETRIES;
	req.srq = id_priv->srq ? 1 : 0;

	ret = ib_send_cm_req(id_priv->cm_id.ib, &req);
out:
	if (ret && !IS_ERR(id_priv->cm_id.ib)) {
		ib_destroy_cm_id(id_priv->cm_id.ib);
		id_priv->cm_id.ib = NULL;
	}

	kfree(private_data);
	return ret;
}

static int cma_connect_iw(struct rdma_id_private *id_priv,
			  struct rdma_conn_param *conn_param)
{
	struct iw_cm_id *cm_id;
	struct sockaddr_in* sin;
	int ret;
	struct iw_cm_conn_param iw_param;

	cm_id = iw_create_cm_id(id_priv->id.device, cma_iw_handler, id_priv);
	if (IS_ERR(cm_id)) {
		ret = PTR_ERR(cm_id);
		goto out;
	}

	id_priv->cm_id.iw = cm_id;

	sin = (struct sockaddr_in*) &id_priv->id.route.addr.src_addr;
	cm_id->local_addr = *sin;

	sin = (struct sockaddr_in*) &id_priv->id.route.addr.dst_addr;
	cm_id->remote_addr = *sin;

	ret = cma_modify_qp_rtr(id_priv, conn_param);
	if (ret)
		goto out;

	iw_param.ord = conn_param->initiator_depth;
	iw_param.ird = conn_param->responder_resources;
	iw_param.private_data = conn_param->private_data;
	iw_param.private_data_len = conn_param->private_data_len;
	if (id_priv->id.qp)
		iw_param.qpn = id_priv->qp_num;
	else
		iw_param.qpn = conn_param->qp_num;
	ret = iw_cm_connect(cm_id, &iw_param);
out:
	if (ret && !IS_ERR(cm_id)) {
		iw_destroy_cm_id(cm_id);
		id_priv->cm_id.iw = NULL;
	}
	return ret;
}

int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
{
	struct rdma_id_private *id_priv;
	int ret;

	id_priv = container_of(id, struct rdma_id_private, id);
	if (!cma_comp_exch(id_priv, CMA_ROUTE_RESOLVED, CMA_CONNECT))
		return -EINVAL;

	if (!id->qp) {
		id_priv->qp_num = conn_param->qp_num;
		id_priv->srq = conn_param->srq;
	}

	switch (rdma_node_get_transport(id->device->node_type)) {
	case RDMA_TRANSPORT_IB:
		if (cma_is_ud_ps(id->ps))
			ret = cma_resolve_ib_udp(id_priv, conn_param);
		else
			ret = cma_connect_ib(id_priv, conn_param);
		break;
	case RDMA_TRANSPORT_IWARP:
		ret = cma_connect_iw(id_priv, conn_param);
		break;
	default:
		ret = -ENOSYS;
		break;
	}
	if (ret)
		goto err;

	return 0;
err:
	cma_comp_exch(id_priv, CMA_CONNECT, CMA_ROUTE_RESOLVED);
	return ret;
}
EXPORT_SYMBOL(rdma_connect);

static int cma_accept_ib(struct rdma_id_private *id_priv,
			 struct rdma_conn_param *conn_param)
{
	struct ib_cm_rep_param rep;
	int ret;

	ret = cma_modify_qp_rtr(id_priv, conn_param);
	if (ret)
		goto out;

	ret = cma_modify_qp_rts(id_priv, conn_param);
	if (ret)
		goto out;

	memset(&rep, 0, sizeof rep);
	rep.qp_num = id_priv->qp_num;
	rep.starting_psn = id_priv->seq_num;
	rep.private_data = conn_param->private_data;
	rep.private_data_len = conn_param->private_data_len;
	rep.responder_resources = conn_param->responder_resources;
	rep.initiator_depth = conn_param->initiator_depth;
	rep.failover_accepted = 0;
	rep.flow_control = conn_param->flow_control;
	rep.rnr_retry_count = conn_param->rnr_retry_count;
	rep.srq = id_priv->srq ? 1 : 0;

	ret = ib_send_cm_rep(id_priv->cm_id.ib, &rep);
out:
	return ret;
}

static int cma_accept_iw(struct rdma_id_private *id_priv,
		  struct rdma_conn_param *conn_param)
{
	struct iw_cm_conn_param iw_param;
	int ret;

	ret = cma_modify_qp_rtr(id_priv, conn_param);
	if (ret)
		return ret;

	iw_param.ord = conn_param->initiator_depth;
	iw_param.ird = conn_param->responder_resources;
	iw_param.private_data = conn_param->private_data;
	iw_param.private_data_len = conn_param->private_data_len;
	if (id_priv->id.qp) {
		iw_param.qpn = id_priv->qp_num;
	} else
		iw_param.qpn = conn_param->qp_num;

	return iw_cm_accept(id_priv->cm_id.iw, &iw_param);
}

static int cma_send_sidr_rep(struct rdma_id_private *id_priv,
			     enum ib_cm_sidr_status status,
			     const void *private_data, int private_data_len)
{
	struct ib_cm_sidr_rep_param rep;

	memset(&rep, 0, sizeof rep);
	rep.status = status;
	if (status == IB_SIDR_SUCCESS) {
		rep.qp_num = id_priv->qp_num;
		rep.qkey = id_priv->qkey;
	}
	rep.private_data = private_data;
	rep.private_data_len = private_data_len;

	return ib_send_cm_sidr_rep(id_priv->cm_id.ib, &rep);
}

int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
{
	struct rdma_id_private *id_priv;
	int ret;

	id_priv = container_of(id, struct rdma_id_private, id);
	if (!cma_comp(id_priv, CMA_CONNECT))
		return -EINVAL;

	if (!id->qp && conn_param) {
		id_priv->qp_num = conn_param->qp_num;
		id_priv->srq = conn_param->srq;
	}

	switch (rdma_node_get_transport(id->device->node_type)) {
	case RDMA_TRANSPORT_IB:
		if (cma_is_ud_ps(id->ps))
			ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS,
						conn_param->private_data,
						conn_param->private_data_len);
		else if (conn_param)
			ret = cma_accept_ib(id_priv, conn_param);
		else
			ret = cma_rep_recv(id_priv);
		break;
	case RDMA_TRANSPORT_IWARP:
		ret = cma_accept_iw(id_priv, conn_param);
		break;
	default:
		ret = -ENOSYS;
		break;
	}

	if (ret)
		goto reject;

	return 0;
reject:
	cma_modify_qp_err(id_priv);
	rdma_reject(id, NULL, 0);
	return ret;
}
EXPORT_SYMBOL(rdma_accept);

int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event)
{
	struct rdma_id_private *id_priv;
	int ret;

	id_priv = container_of(id, struct rdma_id_private, id);
	if (!cma_has_cm_dev(id_priv))
		return -EINVAL;

	switch (id->device->node_type) {
	case RDMA_NODE_IB_CA:
		ret = ib_cm_notify(id_priv->cm_id.ib, event);
		break;
	default:
		ret = 0;
		break;
	}
	return ret;
}
EXPORT_SYMBOL(rdma_notify);

int rdma_reject(struct rdma_cm_id *id, const void *private_data,
		u8 private_data_len)
{
	struct rdma_id_private *id_priv;
	int ret;

	id_priv = container_of(id, struct rdma_id_private, id);
	if (!cma_has_cm_dev(id_priv))
		return -EINVAL;

	switch (rdma_node_get_transport(id->device->node_type)) {
	case RDMA_TRANSPORT_IB:
		if (cma_is_ud_ps(id->ps))
			ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT,
						private_data, private_data_len);
		else
			ret = ib_send_cm_rej(id_priv->cm_id.ib,
					     IB_CM_REJ_CONSUMER_DEFINED, NULL,
					     0, private_data, private_data_len);
		break;
	case RDMA_TRANSPORT_IWARP:
		ret = iw_cm_reject(id_priv->cm_id.iw,
				   private_data, private_data_len);
		break;
	default:
		ret = -ENOSYS;
		break;
	}
	return ret;
}
EXPORT_SYMBOL(rdma_reject);

int rdma_disconnect(struct rdma_cm_id *id)
{
	struct rdma_id_private *id_priv;
	int ret;

	id_priv = container_of(id, struct rdma_id_private, id);
	if (!cma_has_cm_dev(id_priv))
		return -EINVAL;

	switch (rdma_node_get_transport(id->device->node_type)) {
	case RDMA_TRANSPORT_IB:
		ret = cma_modify_qp_err(id_priv);
		if (ret)
			goto out;
		/* Initiate or respond to a disconnect. */
		if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0))
			ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0);
		break;
	case RDMA_TRANSPORT_IWARP:
		ret = iw_cm_disconnect(id_priv->cm_id.iw, 0);
		break;
	default:
		ret = -EINVAL;
		break;
	}
out:
	return ret;
}
EXPORT_SYMBOL(rdma_disconnect);

static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast)
{
	struct rdma_id_private *id_priv;
	struct cma_multicast *mc = multicast->context;
	struct rdma_cm_event event;
	int ret;

	id_priv = mc->id_priv;
	if (cma_disable_callback(id_priv, CMA_ADDR_BOUND) &&
	    cma_disable_callback(id_priv, CMA_ADDR_RESOLVED))
		return 0;

	mutex_lock(&id_priv->qp_mutex);
	if (!status && id_priv->id.qp)
		status = ib_attach_mcast(id_priv->id.qp, &multicast->rec.mgid,
					 multicast->rec.mlid);
	mutex_unlock(&id_priv->qp_mutex);

	memset(&event, 0, sizeof event);
	event.status = status;
	event.param.ud.private_data = mc->context;
	if (!status) {
		event.event = RDMA_CM_EVENT_MULTICAST_JOIN;
		ib_init_ah_from_mcmember(id_priv->id.device,
					 id_priv->id.port_num, &multicast->rec,
					 &event.param.ud.ah_attr);
		event.param.ud.qp_num = 0xFFFFFF;
		event.param.ud.qkey = be32_to_cpu(multicast->rec.qkey);
	} else
		event.event = RDMA_CM_EVENT_MULTICAST_ERROR;

	ret = id_priv->id.event_handler(&id_priv->id, &event);
	if (ret) {
		cma_exch(id_priv, CMA_DESTROYING);
		mutex_unlock(&id_priv->handler_mutex);
		rdma_destroy_id(&id_priv->id);
		return 0;
	}

	mutex_unlock(&id_priv->handler_mutex);
	return 0;
}

static void cma_set_mgid(struct rdma_id_private *id_priv,
			 struct sockaddr *addr, union ib_gid *mgid)
{
	unsigned char mc_map[MAX_ADDR_LEN];
	struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
	struct sockaddr_in *sin = (struct sockaddr_in *) addr;
	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) addr;

	if (cma_any_addr(addr)) {
		memset(mgid, 0, sizeof *mgid);
	} else if ((addr->sa_family == AF_INET6) &&
		   ((be32_to_cpu(sin6->sin6_addr.s6_addr32[0]) & 0xFF10A01B) ==
								 0xFF10A01B)) {
		/* IPv6 address is an SA assigned MGID. */
		memcpy(mgid, &sin6->sin6_addr, sizeof *mgid);
	} else {
		ip_ib_mc_map(sin->sin_addr.s_addr, dev_addr->broadcast, mc_map);
		if (id_priv->id.ps == RDMA_PS_UDP)
			mc_map[7] = 0x01;	/* Use RDMA CM signature */
		*mgid = *(union ib_gid *) (mc_map + 4);
	}
}

static int cma_join_ib_multicast(struct rdma_id_private *id_priv,
				 struct cma_multicast *mc)
{
	struct ib_sa_mcmember_rec rec;
	struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
	ib_sa_comp_mask comp_mask;
	int ret;

	ib_addr_get_mgid(dev_addr, &rec.mgid);
	ret = ib_sa_get_mcmember_rec(id_priv->id.device, id_priv->id.port_num,
				     &rec.mgid, &rec);
	if (ret)
		return ret;

	cma_set_mgid(id_priv, (struct sockaddr *) &mc->addr, &rec.mgid);
	if (id_priv->id.ps == RDMA_PS_UDP)
		rec.qkey = cpu_to_be32(RDMA_UDP_QKEY);
	ib_addr_get_sgid(dev_addr, &rec.port_gid);
	rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr));
	rec.join_state = 1;

	comp_mask = IB_SA_MCMEMBER_REC_MGID | IB_SA_MCMEMBER_REC_PORT_GID |
		    IB_SA_MCMEMBER_REC_PKEY | IB_SA_MCMEMBER_REC_JOIN_STATE |
		    IB_SA_MCMEMBER_REC_QKEY | IB_SA_MCMEMBER_REC_SL |
		    IB_SA_MCMEMBER_REC_FLOW_LABEL |
		    IB_SA_MCMEMBER_REC_TRAFFIC_CLASS;

	mc->multicast.ib = ib_sa_join_multicast(&sa_client, id_priv->id.device,
						id_priv->id.port_num, &rec,
						comp_mask, GFP_KERNEL,
						cma_ib_mc_handler, mc);
	if (IS_ERR(mc->multicast.ib))
		return PTR_ERR(mc->multicast.ib);

	return 0;
}

int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr,
			void *context)
{
	struct rdma_id_private *id_priv;
	struct cma_multicast *mc;
	int ret;

	id_priv = container_of(id, struct rdma_id_private, id);
	if (!cma_comp(id_priv, CMA_ADDR_BOUND) &&
	    !cma_comp(id_priv, CMA_ADDR_RESOLVED))
		return -EINVAL;

	mc = kmalloc(sizeof *mc, GFP_KERNEL);
	if (!mc)
		return -ENOMEM;

	memcpy(&mc->addr, addr, ip_addr_size(addr));
	mc->context = context;
	mc->id_priv = id_priv;

	spin_lock(&id_priv->lock);
	list_add(&mc->list, &id_priv->mc_list);
	spin_unlock(&id_priv->lock);

	switch (rdma_node_get_transport(id->device->node_type)) {
	case RDMA_TRANSPORT_IB:
		ret = cma_join_ib_multicast(id_priv, mc);
		break;
	default:
		ret = -ENOSYS;
		break;
	}

	if (ret) {
		spin_lock_irq(&id_priv->lock);
		list_del(&mc->list);
		spin_unlock_irq(&id_priv->lock);
		kfree(mc);
	}
	return ret;
}
EXPORT_SYMBOL(rdma_join_multicast);

void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr)
{
	struct rdma_id_private *id_priv;
	struct cma_multicast *mc;

	id_priv = container_of(id, struct rdma_id_private, id);
	spin_lock_irq(&id_priv->lock);
	list_for_each_entry(mc, &id_priv->mc_list, list) {
		if (!memcmp(&mc->addr, addr, ip_addr_size(addr))) {
			list_del(&mc->list);
			spin_unlock_irq(&id_priv->lock);

			if (id->qp)
				ib_detach_mcast(id->qp,
						&mc->multicast.ib->rec.mgid,
						mc->multicast.ib->rec.mlid);
			ib_sa_free_multicast(mc->multicast.ib);
			kfree(mc);
			return;
		}
	}
	spin_unlock_irq(&id_priv->lock);
}
EXPORT_SYMBOL(rdma_leave_multicast);

static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id_priv)
{
	struct rdma_dev_addr *dev_addr;
	struct cma_ndev_work *work;

	dev_addr = &id_priv->id.route.addr.dev_addr;

	if ((dev_addr->src_dev == ndev) &&
	    memcmp(dev_addr->src_dev_addr, ndev->dev_addr, ndev->addr_len)) {
		printk(KERN_INFO "RDMA CM addr change for ndev %s used by id %p\n",
		       ndev->name, &id_priv->id);
		work = kzalloc(sizeof *work, GFP_KERNEL);
		if (!work)
			return -ENOMEM;

		INIT_WORK(&work->work, cma_ndev_work_handler);
		work->id = id_priv;
		work->event.event = RDMA_CM_EVENT_ADDR_CHANGE;
		atomic_inc(&id_priv->refcount);
		queue_work(cma_wq, &work->work);
	}

	return 0;
}

static int cma_netdev_callback(struct notifier_block *self, unsigned long event,
			       void *ctx)
{
	struct net_device *ndev = (struct net_device *)ctx;
	struct cma_device *cma_dev;
	struct rdma_id_private *id_priv;
	int ret = NOTIFY_DONE;

	if (dev_net(ndev) != &init_net)
		return NOTIFY_DONE;

	if (event != NETDEV_BONDING_FAILOVER)
		return NOTIFY_DONE;

	if (!(ndev->flags & IFF_MASTER) || !(ndev->priv_flags & IFF_BONDING))
		return NOTIFY_DONE;

	mutex_lock(&lock);
	list_for_each_entry(cma_dev, &dev_list, list)
		list_for_each_entry(id_priv, &cma_dev->id_list, list) {
			ret = cma_netdev_change(ndev, id_priv);
			if (ret)
				goto out;
		}

out:
	mutex_unlock(&lock);
	return ret;
}

static struct notifier_block cma_nb = {
	.notifier_call = cma_netdev_callback
};

static void cma_add_one(struct ib_device *device)
{
	struct cma_device *cma_dev;
	struct rdma_id_private *id_priv;

	cma_dev = kmalloc(sizeof *cma_dev, GFP_KERNEL);
	if (!cma_dev)
		return;

	cma_dev->device = device;

	init_completion(&cma_dev->comp);
	atomic_set(&cma_dev->refcount, 1);
	INIT_LIST_HEAD(&cma_dev->id_list);
	ib_set_client_data(device, &cma_client, cma_dev);

	mutex_lock(&lock);
	list_add_tail(&cma_dev->list, &dev_list);
	list_for_each_entry(id_priv, &listen_any_list, list)
		cma_listen_on_dev(id_priv, cma_dev);
	mutex_unlock(&lock);
}

static int cma_remove_id_dev(struct rdma_id_private *id_priv)
{
	struct rdma_cm_event event;
	enum cma_state state;
	int ret = 0;

	/* Record that we want to remove the device */
	state = cma_exch(id_priv, CMA_DEVICE_REMOVAL);
	if (state == CMA_DESTROYING)
		return 0;

	cma_cancel_operation(id_priv, state);
	mutex_lock(&id_priv->handler_mutex);

	/* Check for destruction from another callback. */
	if (!cma_comp(id_priv, CMA_DEVICE_REMOVAL))
		goto out;

	memset(&event, 0, sizeof event);
	event.event = RDMA_CM_EVENT_DEVICE_REMOVAL;
	ret = id_priv->id.event_handler(&id_priv->id, &event);
out:
	mutex_unlock(&id_priv->handler_mutex);
	return ret;
}

static void cma_process_remove(struct cma_device *cma_dev)
{
	struct rdma_id_private *id_priv;
	int ret;

	mutex_lock(&lock);
	while (!list_empty(&cma_dev->id_list)) {
		id_priv = list_entry(cma_dev->id_list.next,
				     struct rdma_id_private, list);

		list_del(&id_priv->listen_list);
		list_del_init(&id_priv->list);
		atomic_inc(&id_priv->refcount);
		mutex_unlock(&lock);

		ret = id_priv->internal_id ? 1 : cma_remove_id_dev(id_priv);
		cma_deref_id(id_priv);
		if (ret)
			rdma_destroy_id(&id_priv->id);

		mutex_lock(&lock);
	}
	mutex_unlock(&lock);

	cma_deref_dev(cma_dev);
	wait_for_completion(&cma_dev->comp);
}

static void cma_remove_one(struct ib_device *device)
{
	struct cma_device *cma_dev;

	cma_dev = ib_get_client_data(device, &cma_client);
	if (!cma_dev)
		return;

	mutex_lock(&lock);
	list_del(&cma_dev->list);
	mutex_unlock(&lock);

	cma_process_remove(cma_dev);
	kfree(cma_dev);
}

static int cma_init(void)
{
	int ret, low, high, remaining;

	get_random_bytes(&next_port, sizeof next_port);
	inet_get_local_port_range(&low, &high);
	remaining = (high - low) + 1;
	next_port = ((unsigned int) next_port % remaining) + low;

	cma_wq = create_singlethread_workqueue("rdma_cm");
	if (!cma_wq)
		return -ENOMEM;

	ib_sa_register_client(&sa_client);
	rdma_addr_register_client(&addr_client);
	register_netdevice_notifier(&cma_nb);

	ret = ib_register_client(&cma_client);
	if (ret)
		goto err;
	return 0;

err:
	unregister_netdevice_notifier(&cma_nb);
	rdma_addr_unregister_client(&addr_client);
	ib_sa_unregister_client(&sa_client);
	destroy_workqueue(cma_wq);
	return ret;
}

static void cma_cleanup(void)
{
	ib_unregister_client(&cma_client);
	unregister_netdevice_notifier(&cma_nb);
	rdma_addr_unregister_client(&addr_client);
	ib_sa_unregister_client(&sa_client);
	destroy_workqueue(cma_wq);
	idr_destroy(&sdp_ps);
	idr_destroy(&tcp_ps);
	idr_destroy(&udp_ps);
	idr_destroy(&ipoib_ps);
}

module_init(cma_init);
module_exit(cma_cleanup);