summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/core/verbs.c
blob: b99b3cc283b650b9d001bccbfe0bcfdee6100573 (plain)
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
/*
 * Copyright (c) 2004 Mellanox Technologies Ltd.  All rights reserved.
 * Copyright (c) 2004 Infinicon Corporation.  All rights reserved.
 * Copyright (c) 2004 Intel Corporation.  All rights reserved.
 * Copyright (c) 2004 Topspin Corporation.  All rights reserved.
 * Copyright (c) 2004 Voltaire Corporation.  All rights reserved.
 * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
 * Copyright (c) 2005, 2006 Cisco Systems.  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/errno.h>
#include <linux/err.h>
#include <linux/export.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <net/addrconf.h>
#include <linux/security.h>

#include <rdma/ib_verbs.h>
#include <rdma/ib_cache.h>
#include <rdma/ib_addr.h>
#include <rdma/rw.h>
#include <rdma/lag.h>

#include "core_priv.h"
#include <trace/events/rdma_core.h>

static int ib_resolve_eth_dmac(struct ib_device *device,
			       struct rdma_ah_attr *ah_attr);

static const char * const ib_events[] = {
	[IB_EVENT_CQ_ERR]		= "CQ error",
	[IB_EVENT_QP_FATAL]		= "QP fatal error",
	[IB_EVENT_QP_REQ_ERR]		= "QP request error",
	[IB_EVENT_QP_ACCESS_ERR]	= "QP access error",
	[IB_EVENT_COMM_EST]		= "communication established",
	[IB_EVENT_SQ_DRAINED]		= "send queue drained",
	[IB_EVENT_PATH_MIG]		= "path migration successful",
	[IB_EVENT_PATH_MIG_ERR]		= "path migration error",
	[IB_EVENT_DEVICE_FATAL]		= "device fatal error",
	[IB_EVENT_PORT_ACTIVE]		= "port active",
	[IB_EVENT_PORT_ERR]		= "port error",
	[IB_EVENT_LID_CHANGE]		= "LID change",
	[IB_EVENT_PKEY_CHANGE]		= "P_key change",
	[IB_EVENT_SM_CHANGE]		= "SM change",
	[IB_EVENT_SRQ_ERR]		= "SRQ error",
	[IB_EVENT_SRQ_LIMIT_REACHED]	= "SRQ limit reached",
	[IB_EVENT_QP_LAST_WQE_REACHED]	= "last WQE reached",
	[IB_EVENT_CLIENT_REREGISTER]	= "client reregister",
	[IB_EVENT_GID_CHANGE]		= "GID changed",
};

const char *__attribute_const__ ib_event_msg(enum ib_event_type event)
{
	size_t index = event;

	return (index < ARRAY_SIZE(ib_events) && ib_events[index]) ?
			ib_events[index] : "unrecognized event";
}
EXPORT_SYMBOL(ib_event_msg);

static const char * const wc_statuses[] = {
	[IB_WC_SUCCESS]			= "success",
	[IB_WC_LOC_LEN_ERR]		= "local length error",
	[IB_WC_LOC_QP_OP_ERR]		= "local QP operation error",
	[IB_WC_LOC_EEC_OP_ERR]		= "local EE context operation error",
	[IB_WC_LOC_PROT_ERR]		= "local protection error",
	[IB_WC_WR_FLUSH_ERR]		= "WR flushed",
	[IB_WC_MW_BIND_ERR]		= "memory bind operation error",
	[IB_WC_BAD_RESP_ERR]		= "bad response error",
	[IB_WC_LOC_ACCESS_ERR]		= "local access error",
	[IB_WC_REM_INV_REQ_ERR]		= "remote invalid request error",
	[IB_WC_REM_ACCESS_ERR]		= "remote access error",
	[IB_WC_REM_OP_ERR]		= "remote operation error",
	[IB_WC_RETRY_EXC_ERR]		= "transport retry counter exceeded",
	[IB_WC_RNR_RETRY_EXC_ERR]	= "RNR retry counter exceeded",
	[IB_WC_LOC_RDD_VIOL_ERR]	= "local RDD violation error",
	[IB_WC_REM_INV_RD_REQ_ERR]	= "remote invalid RD request",
	[IB_WC_REM_ABORT_ERR]		= "operation aborted",
	[IB_WC_INV_EECN_ERR]		= "invalid EE context number",
	[IB_WC_INV_EEC_STATE_ERR]	= "invalid EE context state",
	[IB_WC_FATAL_ERR]		= "fatal error",
	[IB_WC_RESP_TIMEOUT_ERR]	= "response timeout error",
	[IB_WC_GENERAL_ERR]		= "general error",
};

const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status)
{
	size_t index = status;

	return (index < ARRAY_SIZE(wc_statuses) && wc_statuses[index]) ?
			wc_statuses[index] : "unrecognized status";
}
EXPORT_SYMBOL(ib_wc_status_msg);

__attribute_const__ int ib_rate_to_mult(enum ib_rate rate)
{
	switch (rate) {
	case IB_RATE_2_5_GBPS: return   1;
	case IB_RATE_5_GBPS:   return   2;
	case IB_RATE_10_GBPS:  return   4;
	case IB_RATE_20_GBPS:  return   8;
	case IB_RATE_30_GBPS:  return  12;
	case IB_RATE_40_GBPS:  return  16;
	case IB_RATE_60_GBPS:  return  24;
	case IB_RATE_80_GBPS:  return  32;
	case IB_RATE_120_GBPS: return  48;
	case IB_RATE_14_GBPS:  return   6;
	case IB_RATE_56_GBPS:  return  22;
	case IB_RATE_112_GBPS: return  45;
	case IB_RATE_168_GBPS: return  67;
	case IB_RATE_25_GBPS:  return  10;
	case IB_RATE_100_GBPS: return  40;
	case IB_RATE_200_GBPS: return  80;
	case IB_RATE_300_GBPS: return 120;
	case IB_RATE_28_GBPS:  return  11;
	case IB_RATE_50_GBPS:  return  20;
	case IB_RATE_400_GBPS: return 160;
	case IB_RATE_600_GBPS: return 240;
	default:	       return  -1;
	}
}
EXPORT_SYMBOL(ib_rate_to_mult);

__attribute_const__ enum ib_rate mult_to_ib_rate(int mult)
{
	switch (mult) {
	case 1:   return IB_RATE_2_5_GBPS;
	case 2:   return IB_RATE_5_GBPS;
	case 4:   return IB_RATE_10_GBPS;
	case 8:   return IB_RATE_20_GBPS;
	case 12:  return IB_RATE_30_GBPS;
	case 16:  return IB_RATE_40_GBPS;
	case 24:  return IB_RATE_60_GBPS;
	case 32:  return IB_RATE_80_GBPS;
	case 48:  return IB_RATE_120_GBPS;
	case 6:   return IB_RATE_14_GBPS;
	case 22:  return IB_RATE_56_GBPS;
	case 45:  return IB_RATE_112_GBPS;
	case 67:  return IB_RATE_168_GBPS;
	case 10:  return IB_RATE_25_GBPS;
	case 40:  return IB_RATE_100_GBPS;
	case 80:  return IB_RATE_200_GBPS;
	case 120: return IB_RATE_300_GBPS;
	case 11:  return IB_RATE_28_GBPS;
	case 20:  return IB_RATE_50_GBPS;
	case 160: return IB_RATE_400_GBPS;
	case 240: return IB_RATE_600_GBPS;
	default:  return IB_RATE_PORT_CURRENT;
	}
}
EXPORT_SYMBOL(mult_to_ib_rate);

__attribute_const__ int ib_rate_to_mbps(enum ib_rate rate)
{
	switch (rate) {
	case IB_RATE_2_5_GBPS: return 2500;
	case IB_RATE_5_GBPS:   return 5000;
	case IB_RATE_10_GBPS:  return 10000;
	case IB_RATE_20_GBPS:  return 20000;
	case IB_RATE_30_GBPS:  return 30000;
	case IB_RATE_40_GBPS:  return 40000;
	case IB_RATE_60_GBPS:  return 60000;
	case IB_RATE_80_GBPS:  return 80000;
	case IB_RATE_120_GBPS: return 120000;
	case IB_RATE_14_GBPS:  return 14062;
	case IB_RATE_56_GBPS:  return 56250;
	case IB_RATE_112_GBPS: return 112500;
	case IB_RATE_168_GBPS: return 168750;
	case IB_RATE_25_GBPS:  return 25781;
	case IB_RATE_100_GBPS: return 103125;
	case IB_RATE_200_GBPS: return 206250;
	case IB_RATE_300_GBPS: return 309375;
	case IB_RATE_28_GBPS:  return 28125;
	case IB_RATE_50_GBPS:  return 53125;
	case IB_RATE_400_GBPS: return 425000;
	case IB_RATE_600_GBPS: return 637500;
	default:	       return -1;
	}
}
EXPORT_SYMBOL(ib_rate_to_mbps);

__attribute_const__ enum rdma_transport_type
rdma_node_get_transport(unsigned int node_type)
{

	if (node_type == RDMA_NODE_USNIC)
		return RDMA_TRANSPORT_USNIC;
	if (node_type == RDMA_NODE_USNIC_UDP)
		return RDMA_TRANSPORT_USNIC_UDP;
	if (node_type == RDMA_NODE_RNIC)
		return RDMA_TRANSPORT_IWARP;
	if (node_type == RDMA_NODE_UNSPECIFIED)
		return RDMA_TRANSPORT_UNSPECIFIED;

	return RDMA_TRANSPORT_IB;
}
EXPORT_SYMBOL(rdma_node_get_transport);

enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device,
					      u32 port_num)
{
	enum rdma_transport_type lt;
	if (device->ops.get_link_layer)
		return device->ops.get_link_layer(device, port_num);

	lt = rdma_node_get_transport(device->node_type);
	if (lt == RDMA_TRANSPORT_IB)
		return IB_LINK_LAYER_INFINIBAND;

	return IB_LINK_LAYER_ETHERNET;
}
EXPORT_SYMBOL(rdma_port_get_link_layer);

/* Protection domains */

/**
 * __ib_alloc_pd - Allocates an unused protection domain.
 * @device: The device on which to allocate the protection domain.
 * @flags: protection domain flags
 * @caller: caller's build-time module name
 *
 * A protection domain object provides an association between QPs, shared
 * receive queues, address handles, memory regions, and memory windows.
 *
 * Every PD has a local_dma_lkey which can be used as the lkey value for local
 * memory operations.
 */
struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags,
		const char *caller)
{
	struct ib_pd *pd;
	int mr_access_flags = 0;
	int ret;

	pd = rdma_zalloc_drv_obj(device, ib_pd);
	if (!pd)
		return ERR_PTR(-ENOMEM);

	pd->device = device;
	pd->flags = flags;

	rdma_restrack_new(&pd->res, RDMA_RESTRACK_PD);
	rdma_restrack_set_name(&pd->res, caller);

	ret = device->ops.alloc_pd(pd, NULL);
	if (ret) {
		rdma_restrack_put(&pd->res);
		kfree(pd);
		return ERR_PTR(ret);
	}
	rdma_restrack_add(&pd->res);

	if (device->attrs.kernel_cap_flags & IBK_LOCAL_DMA_LKEY)
		pd->local_dma_lkey = device->local_dma_lkey;
	else
		mr_access_flags |= IB_ACCESS_LOCAL_WRITE;

	if (flags & IB_PD_UNSAFE_GLOBAL_RKEY) {
		pr_warn("%s: enabling unsafe global rkey\n", caller);
		mr_access_flags |= IB_ACCESS_REMOTE_READ | IB_ACCESS_REMOTE_WRITE;
	}

	if (mr_access_flags) {
		struct ib_mr *mr;

		mr = pd->device->ops.get_dma_mr(pd, mr_access_flags);
		if (IS_ERR(mr)) {
			ib_dealloc_pd(pd);
			return ERR_CAST(mr);
		}

		mr->device	= pd->device;
		mr->pd		= pd;
		mr->type        = IB_MR_TYPE_DMA;
		mr->uobject	= NULL;
		mr->need_inval	= false;

		pd->__internal_mr = mr;

		if (!(device->attrs.kernel_cap_flags & IBK_LOCAL_DMA_LKEY))
			pd->local_dma_lkey = pd->__internal_mr->lkey;

		if (flags & IB_PD_UNSAFE_GLOBAL_RKEY)
			pd->unsafe_global_rkey = pd->__internal_mr->rkey;
	}

	return pd;
}
EXPORT_SYMBOL(__ib_alloc_pd);

/**
 * ib_dealloc_pd_user - Deallocates a protection domain.
 * @pd: The protection domain to deallocate.
 * @udata: Valid user data or NULL for kernel object
 *
 * It is an error to call this function while any resources in the pd still
 * exist.  The caller is responsible to synchronously destroy them and
 * guarantee no new allocations will happen.
 */
int ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata)
{
	int ret;

	if (pd->__internal_mr) {
		ret = pd->device->ops.dereg_mr(pd->__internal_mr, NULL);
		WARN_ON(ret);
		pd->__internal_mr = NULL;
	}

	ret = pd->device->ops.dealloc_pd(pd, udata);
	if (ret)
		return ret;

	rdma_restrack_del(&pd->res);
	kfree(pd);
	return ret;
}
EXPORT_SYMBOL(ib_dealloc_pd_user);

/* Address handles */

/**
 * rdma_copy_ah_attr - Copy rdma ah attribute from source to destination.
 * @dest:       Pointer to destination ah_attr. Contents of the destination
 *              pointer is assumed to be invalid and attribute are overwritten.
 * @src:        Pointer to source ah_attr.
 */
void rdma_copy_ah_attr(struct rdma_ah_attr *dest,
		       const struct rdma_ah_attr *src)
{
	*dest = *src;
	if (dest->grh.sgid_attr)
		rdma_hold_gid_attr(dest->grh.sgid_attr);
}
EXPORT_SYMBOL(rdma_copy_ah_attr);

/**
 * rdma_replace_ah_attr - Replace valid ah_attr with new new one.
 * @old:        Pointer to existing ah_attr which needs to be replaced.
 *              old is assumed to be valid or zero'd
 * @new:        Pointer to the new ah_attr.
 *
 * rdma_replace_ah_attr() first releases any reference in the old ah_attr if
 * old the ah_attr is valid; after that it copies the new attribute and holds
 * the reference to the replaced ah_attr.
 */
void rdma_replace_ah_attr(struct rdma_ah_attr *old,
			  const struct rdma_ah_attr *new)
{
	rdma_destroy_ah_attr(old);
	*old = *new;
	if (old->grh.sgid_attr)
		rdma_hold_gid_attr(old->grh.sgid_attr);
}
EXPORT_SYMBOL(rdma_replace_ah_attr);

/**
 * rdma_move_ah_attr - Move ah_attr pointed by source to destination.
 * @dest:       Pointer to destination ah_attr to copy to.
 *              dest is assumed to be valid or zero'd
 * @src:        Pointer to the new ah_attr.
 *
 * rdma_move_ah_attr() first releases any reference in the destination ah_attr
 * if it is valid. This also transfers ownership of internal references from
 * src to dest, making src invalid in the process. No new reference of the src
 * ah_attr is taken.
 */
void rdma_move_ah_attr(struct rdma_ah_attr *dest, struct rdma_ah_attr *src)
{
	rdma_destroy_ah_attr(dest);
	*dest = *src;
	src->grh.sgid_attr = NULL;
}
EXPORT_SYMBOL(rdma_move_ah_attr);

/*
 * Validate that the rdma_ah_attr is valid for the device before passing it
 * off to the driver.
 */
static int rdma_check_ah_attr(struct ib_device *device,
			      struct rdma_ah_attr *ah_attr)
{
	if (!rdma_is_port_valid(device, ah_attr->port_num))
		return -EINVAL;

	if ((rdma_is_grh_required(device, ah_attr->port_num) ||
	     ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) &&
	    !(ah_attr->ah_flags & IB_AH_GRH))
		return -EINVAL;

	if (ah_attr->grh.sgid_attr) {
		/*
		 * Make sure the passed sgid_attr is consistent with the
		 * parameters
		 */
		if (ah_attr->grh.sgid_attr->index != ah_attr->grh.sgid_index ||
		    ah_attr->grh.sgid_attr->port_num != ah_attr->port_num)
			return -EINVAL;
	}
	return 0;
}

/*
 * If the ah requires a GRH then ensure that sgid_attr pointer is filled in.
 * On success the caller is responsible to call rdma_unfill_sgid_attr().
 */
static int rdma_fill_sgid_attr(struct ib_device *device,
			       struct rdma_ah_attr *ah_attr,
			       const struct ib_gid_attr **old_sgid_attr)
{
	const struct ib_gid_attr *sgid_attr;
	struct ib_global_route *grh;
	int ret;

	*old_sgid_attr = ah_attr->grh.sgid_attr;

	ret = rdma_check_ah_attr(device, ah_attr);
	if (ret)
		return ret;

	if (!(ah_attr->ah_flags & IB_AH_GRH))
		return 0;

	grh = rdma_ah_retrieve_grh(ah_attr);
	if (grh->sgid_attr)
		return 0;

	sgid_attr =
		rdma_get_gid_attr(device, ah_attr->port_num, grh->sgid_index);
	if (IS_ERR(sgid_attr))
		return PTR_ERR(sgid_attr);

	/* Move ownerhip of the kref into the ah_attr */
	grh->sgid_attr = sgid_attr;
	return 0;
}

static void rdma_unfill_sgid_attr(struct rdma_ah_attr *ah_attr,
				  const struct ib_gid_attr *old_sgid_attr)
{
	/*
	 * Fill didn't change anything, the caller retains ownership of
	 * whatever it passed
	 */
	if (ah_attr->grh.sgid_attr == old_sgid_attr)
		return;

	/*
	 * Otherwise, we need to undo what rdma_fill_sgid_attr so the caller
	 * doesn't see any change in the rdma_ah_attr. If we get here
	 * old_sgid_attr is NULL.
	 */
	rdma_destroy_ah_attr(ah_attr);
}

static const struct ib_gid_attr *
rdma_update_sgid_attr(struct rdma_ah_attr *ah_attr,
		      const struct ib_gid_attr *old_attr)
{
	if (old_attr)
		rdma_put_gid_attr(old_attr);
	if (ah_attr->ah_flags & IB_AH_GRH) {
		rdma_hold_gid_attr(ah_attr->grh.sgid_attr);
		return ah_attr->grh.sgid_attr;
	}
	return NULL;
}

static struct ib_ah *_rdma_create_ah(struct ib_pd *pd,
				     struct rdma_ah_attr *ah_attr,
				     u32 flags,
				     struct ib_udata *udata,
				     struct net_device *xmit_slave)
{
	struct rdma_ah_init_attr init_attr = {};
	struct ib_device *device = pd->device;
	struct ib_ah *ah;
	int ret;

	might_sleep_if(flags & RDMA_CREATE_AH_SLEEPABLE);

	if (!udata && !device->ops.create_ah)
		return ERR_PTR(-EOPNOTSUPP);

	ah = rdma_zalloc_drv_obj_gfp(
		device, ib_ah,
		(flags & RDMA_CREATE_AH_SLEEPABLE) ? GFP_KERNEL : GFP_ATOMIC);
	if (!ah)
		return ERR_PTR(-ENOMEM);

	ah->device = device;
	ah->pd = pd;
	ah->type = ah_attr->type;
	ah->sgid_attr = rdma_update_sgid_attr(ah_attr, NULL);
	init_attr.ah_attr = ah_attr;
	init_attr.flags = flags;
	init_attr.xmit_slave = xmit_slave;

	if (udata)
		ret = device->ops.create_user_ah(ah, &init_attr, udata);
	else
		ret = device->ops.create_ah(ah, &init_attr, NULL);
	if (ret) {
		if (ah->sgid_attr)
			rdma_put_gid_attr(ah->sgid_attr);
		kfree(ah);
		return ERR_PTR(ret);
	}

	atomic_inc(&pd->usecnt);
	return ah;
}

/**
 * rdma_create_ah - Creates an address handle for the
 * given address vector.
 * @pd: The protection domain associated with the address handle.
 * @ah_attr: The attributes of the address vector.
 * @flags: Create address handle flags (see enum rdma_create_ah_flags).
 *
 * It returns 0 on success and returns appropriate error code on error.
 * The address handle is used to reference a local or global destination
 * in all UD QP post sends.
 */
struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr,
			     u32 flags)
{
	const struct ib_gid_attr *old_sgid_attr;
	struct net_device *slave;
	struct ib_ah *ah;
	int ret;

	ret = rdma_fill_sgid_attr(pd->device, ah_attr, &old_sgid_attr);
	if (ret)
		return ERR_PTR(ret);
	slave = rdma_lag_get_ah_roce_slave(pd->device, ah_attr,
					   (flags & RDMA_CREATE_AH_SLEEPABLE) ?
					   GFP_KERNEL : GFP_ATOMIC);
	if (IS_ERR(slave)) {
		rdma_unfill_sgid_attr(ah_attr, old_sgid_attr);
		return (void *)slave;
	}
	ah = _rdma_create_ah(pd, ah_attr, flags, NULL, slave);
	rdma_lag_put_ah_roce_slave(slave);
	rdma_unfill_sgid_attr(ah_attr, old_sgid_attr);
	return ah;
}
EXPORT_SYMBOL(rdma_create_ah);

/**
 * rdma_create_user_ah - Creates an address handle for the
 * given address vector.
 * It resolves destination mac address for ah attribute of RoCE type.
 * @pd: The protection domain associated with the address handle.
 * @ah_attr: The attributes of the address vector.
 * @udata: pointer to user's input output buffer information need by
 *         provider driver.
 *
 * It returns 0 on success and returns appropriate error code on error.
 * The address handle is used to reference a local or global destination
 * in all UD QP post sends.
 */
struct ib_ah *rdma_create_user_ah(struct ib_pd *pd,
				  struct rdma_ah_attr *ah_attr,
				  struct ib_udata *udata)
{
	const struct ib_gid_attr *old_sgid_attr;
	struct ib_ah *ah;
	int err;

	err = rdma_fill_sgid_attr(pd->device, ah_attr, &old_sgid_attr);
	if (err)
		return ERR_PTR(err);

	if (ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) {
		err = ib_resolve_eth_dmac(pd->device, ah_attr);
		if (err) {
			ah = ERR_PTR(err);
			goto out;
		}
	}

	ah = _rdma_create_ah(pd, ah_attr, RDMA_CREATE_AH_SLEEPABLE,
			     udata, NULL);

out:
	rdma_unfill_sgid_attr(ah_attr, old_sgid_attr);
	return ah;
}
EXPORT_SYMBOL(rdma_create_user_ah);

int ib_get_rdma_header_version(const union rdma_network_hdr *hdr)
{
	const struct iphdr *ip4h = (struct iphdr *)&hdr->roce4grh;
	struct iphdr ip4h_checked;
	const struct ipv6hdr *ip6h = (struct ipv6hdr *)&hdr->ibgrh;

	/* If it's IPv6, the version must be 6, otherwise, the first
	 * 20 bytes (before the IPv4 header) are garbled.
	 */
	if (ip6h->version != 6)
		return (ip4h->version == 4) ? 4 : 0;
	/* version may be 6 or 4 because the first 20 bytes could be garbled */

	/* RoCE v2 requires no options, thus header length
	 * must be 5 words
	 */
	if (ip4h->ihl != 5)
		return 6;

	/* Verify checksum.
	 * We can't write on scattered buffers so we need to copy to
	 * temp buffer.
	 */
	memcpy(&ip4h_checked, ip4h, sizeof(ip4h_checked));
	ip4h_checked.check = 0;
	ip4h_checked.check = ip_fast_csum((u8 *)&ip4h_checked, 5);
	/* if IPv4 header checksum is OK, believe it */
	if (ip4h->check == ip4h_checked.check)
		return 4;
	return 6;
}
EXPORT_SYMBOL(ib_get_rdma_header_version);

static enum rdma_network_type ib_get_net_type_by_grh(struct ib_device *device,
						     u32 port_num,
						     const struct ib_grh *grh)
{
	int grh_version;

	if (rdma_protocol_ib(device, port_num))
		return RDMA_NETWORK_IB;

	grh_version = ib_get_rdma_header_version((union rdma_network_hdr *)grh);

	if (grh_version == 4)
		return RDMA_NETWORK_IPV4;

	if (grh->next_hdr == IPPROTO_UDP)
		return RDMA_NETWORK_IPV6;

	return RDMA_NETWORK_ROCE_V1;
}

struct find_gid_index_context {
	u16 vlan_id;
	enum ib_gid_type gid_type;
};

static bool find_gid_index(const union ib_gid *gid,
			   const struct ib_gid_attr *gid_attr,
			   void *context)
{
	struct find_gid_index_context *ctx = context;
	u16 vlan_id = 0xffff;
	int ret;

	if (ctx->gid_type != gid_attr->gid_type)
		return false;

	ret = rdma_read_gid_l2_fields(gid_attr, &vlan_id, NULL);
	if (ret)
		return false;

	return ctx->vlan_id == vlan_id;
}

static const struct ib_gid_attr *
get_sgid_attr_from_eth(struct ib_device *device, u32 port_num,
		       u16 vlan_id, const union ib_gid *sgid,
		       enum ib_gid_type gid_type)
{
	struct find_gid_index_context context = {.vlan_id = vlan_id,
						 .gid_type = gid_type};

	return rdma_find_gid_by_filter(device, sgid, port_num, find_gid_index,
				       &context);
}

int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr,
			      enum rdma_network_type net_type,
			      union ib_gid *sgid, union ib_gid *dgid)
{
	struct sockaddr_in  src_in;
	struct sockaddr_in  dst_in;
	__be32 src_saddr, dst_saddr;

	if (!sgid || !dgid)
		return -EINVAL;

	if (net_type == RDMA_NETWORK_IPV4) {
		memcpy(&src_in.sin_addr.s_addr,
		       &hdr->roce4grh.saddr, 4);
		memcpy(&dst_in.sin_addr.s_addr,
		       &hdr->roce4grh.daddr, 4);
		src_saddr = src_in.sin_addr.s_addr;
		dst_saddr = dst_in.sin_addr.s_addr;
		ipv6_addr_set_v4mapped(src_saddr,
				       (struct in6_addr *)sgid);
		ipv6_addr_set_v4mapped(dst_saddr,
				       (struct in6_addr *)dgid);
		return 0;
	} else if (net_type == RDMA_NETWORK_IPV6 ||
		   net_type == RDMA_NETWORK_IB || RDMA_NETWORK_ROCE_V1) {
		*dgid = hdr->ibgrh.dgid;
		*sgid = hdr->ibgrh.sgid;
		return 0;
	} else {
		return -EINVAL;
	}
}
EXPORT_SYMBOL(ib_get_gids_from_rdma_hdr);

/* Resolve destination mac address and hop limit for unicast destination
 * GID entry, considering the source GID entry as well.
 * ah_attribute must have have valid port_num, sgid_index.
 */
static int ib_resolve_unicast_gid_dmac(struct ib_device *device,
				       struct rdma_ah_attr *ah_attr)
{
	struct ib_global_route *grh = rdma_ah_retrieve_grh(ah_attr);
	const struct ib_gid_attr *sgid_attr = grh->sgid_attr;
	int hop_limit = 0xff;
	int ret = 0;

	/* If destination is link local and source GID is RoCEv1,
	 * IP stack is not used.
	 */
	if (rdma_link_local_addr((struct in6_addr *)grh->dgid.raw) &&
	    sgid_attr->gid_type == IB_GID_TYPE_ROCE) {
		rdma_get_ll_mac((struct in6_addr *)grh->dgid.raw,
				ah_attr->roce.dmac);
		return ret;
	}

	ret = rdma_addr_find_l2_eth_by_grh(&sgid_attr->gid, &grh->dgid,
					   ah_attr->roce.dmac,
					   sgid_attr, &hop_limit);

	grh->hop_limit = hop_limit;
	return ret;
}

/*
 * This function initializes address handle attributes from the incoming packet.
 * Incoming packet has dgid of the receiver node on which this code is
 * getting executed and, sgid contains the GID of the sender.
 *
 * When resolving mac address of destination, the arrived dgid is used
 * as sgid and, sgid is used as dgid because sgid contains destinations
 * GID whom to respond to.
 *
 * On success the caller is responsible to call rdma_destroy_ah_attr on the
 * attr.
 */
int ib_init_ah_attr_from_wc(struct ib_device *device, u32 port_num,
			    const struct ib_wc *wc, const struct ib_grh *grh,
			    struct rdma_ah_attr *ah_attr)
{
	u32 flow_class;
	int ret;
	enum rdma_network_type net_type = RDMA_NETWORK_IB;
	enum ib_gid_type gid_type = IB_GID_TYPE_IB;
	const struct ib_gid_attr *sgid_attr;
	int hoplimit = 0xff;
	union ib_gid dgid;
	union ib_gid sgid;

	might_sleep();

	memset(ah_attr, 0, sizeof *ah_attr);
	ah_attr->type = rdma_ah_find_type(device, port_num);
	if (rdma_cap_eth_ah(device, port_num)) {
		if (wc->wc_flags & IB_WC_WITH_NETWORK_HDR_TYPE)
			net_type = wc->network_hdr_type;
		else
			net_type = ib_get_net_type_by_grh(device, port_num, grh);
		gid_type = ib_network_to_gid_type(net_type);
	}
	ret = ib_get_gids_from_rdma_hdr((union rdma_network_hdr *)grh, net_type,
					&sgid, &dgid);
	if (ret)
		return ret;

	rdma_ah_set_sl(ah_attr, wc->sl);
	rdma_ah_set_port_num(ah_attr, port_num);

	if (rdma_protocol_roce(device, port_num)) {
		u16 vlan_id = wc->wc_flags & IB_WC_WITH_VLAN ?
				wc->vlan_id : 0xffff;

		if (!(wc->wc_flags & IB_WC_GRH))
			return -EPROTOTYPE;

		sgid_attr = get_sgid_attr_from_eth(device, port_num,
						   vlan_id, &dgid,
						   gid_type);
		if (IS_ERR(sgid_attr))
			return PTR_ERR(sgid_attr);

		flow_class = be32_to_cpu(grh->version_tclass_flow);
		rdma_move_grh_sgid_attr(ah_attr,
					&sgid,
					flow_class & 0xFFFFF,
					hoplimit,
					(flow_class >> 20) & 0xFF,
					sgid_attr);

		ret = ib_resolve_unicast_gid_dmac(device, ah_attr);
		if (ret)
			rdma_destroy_ah_attr(ah_attr);

		return ret;
	} else {
		rdma_ah_set_dlid(ah_attr, wc->slid);
		rdma_ah_set_path_bits(ah_attr, wc->dlid_path_bits);

		if ((wc->wc_flags & IB_WC_GRH) == 0)
			return 0;

		if (dgid.global.interface_id !=
					cpu_to_be64(IB_SA_WELL_KNOWN_GUID)) {
			sgid_attr = rdma_find_gid_by_port(
				device, &dgid, IB_GID_TYPE_IB, port_num, NULL);
		} else
			sgid_attr = rdma_get_gid_attr(device, port_num, 0);

		if (IS_ERR(sgid_attr))
			return PTR_ERR(sgid_attr);
		flow_class = be32_to_cpu(grh->version_tclass_flow);
		rdma_move_grh_sgid_attr(ah_attr,
					&sgid,
					flow_class & 0xFFFFF,
					hoplimit,
					(flow_class >> 20) & 0xFF,
					sgid_attr);

		return 0;
	}
}
EXPORT_SYMBOL(ib_init_ah_attr_from_wc);

/**
 * rdma_move_grh_sgid_attr - Sets the sgid attribute of GRH, taking ownership
 * of the reference
 *
 * @attr:	Pointer to AH attribute structure
 * @dgid:	Destination GID
 * @flow_label:	Flow label
 * @hop_limit:	Hop limit
 * @traffic_class: traffic class
 * @sgid_attr:	Pointer to SGID attribute
 *
 * This takes ownership of the sgid_attr reference. The caller must ensure
 * rdma_destroy_ah_attr() is called before destroying the rdma_ah_attr after
 * calling this function.
 */
void rdma_move_grh_sgid_attr(struct rdma_ah_attr *attr, union ib_gid *dgid,
			     u32 flow_label, u8 hop_limit, u8 traffic_class,
			     const struct ib_gid_attr *sgid_attr)
{
	rdma_ah_set_grh(attr, dgid, flow_label, sgid_attr->index, hop_limit,
			traffic_class);
	attr->grh.sgid_attr = sgid_attr;
}
EXPORT_SYMBOL(rdma_move_grh_sgid_attr);

/**
 * rdma_destroy_ah_attr - Release reference to SGID attribute of
 * ah attribute.
 * @ah_attr: Pointer to ah attribute
 *
 * Release reference to the SGID attribute of the ah attribute if it is
 * non NULL. It is safe to call this multiple times, and safe to call it on
 * a zero initialized ah_attr.
 */
void rdma_destroy_ah_attr(struct rdma_ah_attr *ah_attr)
{
	if (ah_attr->grh.sgid_attr) {
		rdma_put_gid_attr(ah_attr->grh.sgid_attr);
		ah_attr->grh.sgid_attr = NULL;
	}
}
EXPORT_SYMBOL(rdma_destroy_ah_attr);

struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc,
				   const struct ib_grh *grh, u32 port_num)
{
	struct rdma_ah_attr ah_attr;
	struct ib_ah *ah;
	int ret;

	ret = ib_init_ah_attr_from_wc(pd->device, port_num, wc, grh, &ah_attr);
	if (ret)
		return ERR_PTR(ret);

	ah = rdma_create_ah(pd, &ah_attr, RDMA_CREATE_AH_SLEEPABLE);

	rdma_destroy_ah_attr(&ah_attr);
	return ah;
}
EXPORT_SYMBOL(ib_create_ah_from_wc);

int rdma_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr)
{
	const struct ib_gid_attr *old_sgid_attr;
	int ret;

	if (ah->type != ah_attr->type)
		return -EINVAL;

	ret = rdma_fill_sgid_attr(ah->device, ah_attr, &old_sgid_attr);
	if (ret)
		return ret;

	ret = ah->device->ops.modify_ah ?
		ah->device->ops.modify_ah(ah, ah_attr) :
		-EOPNOTSUPP;

	ah->sgid_attr = rdma_update_sgid_attr(ah_attr, ah->sgid_attr);
	rdma_unfill_sgid_attr(ah_attr, old_sgid_attr);
	return ret;
}
EXPORT_SYMBOL(rdma_modify_ah);

int rdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr)
{
	ah_attr->grh.sgid_attr = NULL;

	return ah->device->ops.query_ah ?
		ah->device->ops.query_ah(ah, ah_attr) :
		-EOPNOTSUPP;
}
EXPORT_SYMBOL(rdma_query_ah);

int rdma_destroy_ah_user(struct ib_ah *ah, u32 flags, struct ib_udata *udata)
{
	const struct ib_gid_attr *sgid_attr = ah->sgid_attr;
	struct ib_pd *pd;
	int ret;

	might_sleep_if(flags & RDMA_DESTROY_AH_SLEEPABLE);

	pd = ah->pd;

	ret = ah->device->ops.destroy_ah(ah, flags);
	if (ret)
		return ret;

	atomic_dec(&pd->usecnt);
	if (sgid_attr)
		rdma_put_gid_attr(sgid_attr);

	kfree(ah);
	return ret;
}
EXPORT_SYMBOL(rdma_destroy_ah_user);

/* Shared receive queues */

/**
 * ib_create_srq_user - Creates a SRQ associated with the specified protection
 *   domain.
 * @pd: The protection domain associated with the SRQ.
 * @srq_init_attr: A list of initial attributes required to create the
 *   SRQ.  If SRQ creation succeeds, then the attributes are updated to
 *   the actual capabilities of the created SRQ.
 * @uobject: uobject pointer if this is not a kernel SRQ
 * @udata: udata pointer if this is not a kernel SRQ
 *
 * srq_attr->max_wr and srq_attr->max_sge are read the determine the
 * requested size of the SRQ, and set to the actual values allocated
 * on return.  If ib_create_srq() succeeds, then max_wr and max_sge
 * will always be at least as large as the requested values.
 */
struct ib_srq *ib_create_srq_user(struct ib_pd *pd,
				  struct ib_srq_init_attr *srq_init_attr,
				  struct ib_usrq_object *uobject,
				  struct ib_udata *udata)
{
	struct ib_srq *srq;
	int ret;

	srq = rdma_zalloc_drv_obj(pd->device, ib_srq);
	if (!srq)
		return ERR_PTR(-ENOMEM);

	srq->device = pd->device;
	srq->pd = pd;
	srq->event_handler = srq_init_attr->event_handler;
	srq->srq_context = srq_init_attr->srq_context;
	srq->srq_type = srq_init_attr->srq_type;
	srq->uobject = uobject;

	if (ib_srq_has_cq(srq->srq_type)) {
		srq->ext.cq = srq_init_attr->ext.cq;
		atomic_inc(&srq->ext.cq->usecnt);
	}
	if (srq->srq_type == IB_SRQT_XRC) {
		srq->ext.xrc.xrcd = srq_init_attr->ext.xrc.xrcd;
		if (srq->ext.xrc.xrcd)
			atomic_inc(&srq->ext.xrc.xrcd->usecnt);
	}
	atomic_inc(&pd->usecnt);

	rdma_restrack_new(&srq->res, RDMA_RESTRACK_SRQ);
	rdma_restrack_parent_name(&srq->res, &pd->res);

	ret = pd->device->ops.create_srq(srq, srq_init_attr, udata);
	if (ret) {
		rdma_restrack_put(&srq->res);
		atomic_dec(&pd->usecnt);
		if (srq->srq_type == IB_SRQT_XRC && srq->ext.xrc.xrcd)
			atomic_dec(&srq->ext.xrc.xrcd->usecnt);
		if (ib_srq_has_cq(srq->srq_type))
			atomic_dec(&srq->ext.cq->usecnt);
		kfree(srq);
		return ERR_PTR(ret);
	}

	rdma_restrack_add(&srq->res);

	return srq;
}
EXPORT_SYMBOL(ib_create_srq_user);

int ib_modify_srq(struct ib_srq *srq,
		  struct ib_srq_attr *srq_attr,
		  enum ib_srq_attr_mask srq_attr_mask)
{
	return srq->device->ops.modify_srq ?
		srq->device->ops.modify_srq(srq, srq_attr, srq_attr_mask,
					    NULL) : -EOPNOTSUPP;
}
EXPORT_SYMBOL(ib_modify_srq);

int ib_query_srq(struct ib_srq *srq,
		 struct ib_srq_attr *srq_attr)
{
	return srq->device->ops.query_srq ?
		srq->device->ops.query_srq(srq, srq_attr) : -EOPNOTSUPP;
}
EXPORT_SYMBOL(ib_query_srq);

int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata)
{
	int ret;

	if (atomic_read(&srq->usecnt))
		return -EBUSY;

	ret = srq->device->ops.destroy_srq(srq, udata);
	if (ret)
		return ret;

	atomic_dec(&srq->pd->usecnt);
	if (srq->srq_type == IB_SRQT_XRC && srq->ext.xrc.xrcd)
		atomic_dec(&srq->ext.xrc.xrcd->usecnt);
	if (ib_srq_has_cq(srq->srq_type))
		atomic_dec(&srq->ext.cq->usecnt);
	rdma_restrack_del(&srq->res);
	kfree(srq);

	return ret;
}
EXPORT_SYMBOL(ib_destroy_srq_user);

/* Queue pairs */

static void __ib_shared_qp_event_handler(struct ib_event *event, void *context)
{
	struct ib_qp *qp = context;
	unsigned long flags;

	spin_lock_irqsave(&qp->device->qp_open_list_lock, flags);
	list_for_each_entry(event->element.qp, &qp->open_list, open_list)
		if (event->element.qp->event_handler)
			event->element.qp->event_handler(event, event->element.qp->qp_context);
	spin_unlock_irqrestore(&qp->device->qp_open_list_lock, flags);
}

static struct ib_qp *__ib_open_qp(struct ib_qp *real_qp,
				  void (*event_handler)(struct ib_event *, void *),
				  void *qp_context)
{
	struct ib_qp *qp;
	unsigned long flags;
	int err;

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

	qp->real_qp = real_qp;
	err = ib_open_shared_qp_security(qp, real_qp->device);
	if (err) {
		kfree(qp);
		return ERR_PTR(err);
	}

	qp->real_qp = real_qp;
	atomic_inc(&real_qp->usecnt);
	qp->device = real_qp->device;
	qp->event_handler = event_handler;
	qp->qp_context = qp_context;
	qp->qp_num = real_qp->qp_num;
	qp->qp_type = real_qp->qp_type;

	spin_lock_irqsave(&real_qp->device->qp_open_list_lock, flags);
	list_add(&qp->open_list, &real_qp->open_list);
	spin_unlock_irqrestore(&real_qp->device->qp_open_list_lock, flags);

	return qp;
}

struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd,
			 struct ib_qp_open_attr *qp_open_attr)
{
	struct ib_qp *qp, *real_qp;

	if (qp_open_attr->qp_type != IB_QPT_XRC_TGT)
		return ERR_PTR(-EINVAL);

	down_read(&xrcd->tgt_qps_rwsem);
	real_qp = xa_load(&xrcd->tgt_qps, qp_open_attr->qp_num);
	if (!real_qp) {
		up_read(&xrcd->tgt_qps_rwsem);
		return ERR_PTR(-EINVAL);
	}
	qp = __ib_open_qp(real_qp, qp_open_attr->event_handler,
			  qp_open_attr->qp_context);
	up_read(&xrcd->tgt_qps_rwsem);
	return qp;
}
EXPORT_SYMBOL(ib_open_qp);

static struct ib_qp *create_xrc_qp_user(struct ib_qp *qp,
					struct ib_qp_init_attr *qp_init_attr)
{
	struct ib_qp *real_qp = qp;
	int err;

	qp->event_handler = __ib_shared_qp_event_handler;
	qp->qp_context = qp;
	qp->pd = NULL;
	qp->send_cq = qp->recv_cq = NULL;
	qp->srq = NULL;
	qp->xrcd = qp_init_attr->xrcd;
	atomic_inc(&qp_init_attr->xrcd->usecnt);
	INIT_LIST_HEAD(&qp->open_list);

	qp = __ib_open_qp(real_qp, qp_init_attr->event_handler,
			  qp_init_attr->qp_context);
	if (IS_ERR(qp))
		return qp;

	err = xa_err(xa_store(&qp_init_attr->xrcd->tgt_qps, real_qp->qp_num,
			      real_qp, GFP_KERNEL));
	if (err) {
		ib_close_qp(qp);
		return ERR_PTR(err);
	}
	return qp;
}

static struct ib_qp *create_qp(struct ib_device *dev, struct ib_pd *pd,
			       struct ib_qp_init_attr *attr,
			       struct ib_udata *udata,
			       struct ib_uqp_object *uobj, const char *caller)
{
	struct ib_udata dummy = {};
	struct ib_qp *qp;
	int ret;

	if (!dev->ops.create_qp)
		return ERR_PTR(-EOPNOTSUPP);

	qp = rdma_zalloc_drv_obj_numa(dev, ib_qp);
	if (!qp)
		return ERR_PTR(-ENOMEM);

	qp->device = dev;
	qp->pd = pd;
	qp->uobject = uobj;
	qp->real_qp = qp;

	qp->qp_type = attr->qp_type;
	qp->rwq_ind_tbl = attr->rwq_ind_tbl;
	qp->srq = attr->srq;
	qp->event_handler = attr->event_handler;
	qp->port = attr->port_num;
	qp->qp_context = attr->qp_context;

	spin_lock_init(&qp->mr_lock);
	INIT_LIST_HEAD(&qp->rdma_mrs);
	INIT_LIST_HEAD(&qp->sig_mrs);

	qp->send_cq = attr->send_cq;
	qp->recv_cq = attr->recv_cq;

	rdma_restrack_new(&qp->res, RDMA_RESTRACK_QP);
	WARN_ONCE(!udata && !caller, "Missing kernel QP owner");
	rdma_restrack_set_name(&qp->res, udata ? NULL : caller);
	ret = dev->ops.create_qp(qp, attr, udata);
	if (ret)
		goto err_create;

	/*
	 * TODO: The mlx4 internally overwrites send_cq and recv_cq.
	 * Unfortunately, it is not an easy task to fix that driver.
	 */
	qp->send_cq = attr->send_cq;
	qp->recv_cq = attr->recv_cq;

	ret = ib_create_qp_security(qp, dev);
	if (ret)
		goto err_security;

	rdma_restrack_add(&qp->res);
	return qp;

err_security:
	qp->device->ops.destroy_qp(qp, udata ? &dummy : NULL);
err_create:
	rdma_restrack_put(&qp->res);
	kfree(qp);
	return ERR_PTR(ret);

}

/**
 * ib_create_qp_user - Creates a QP associated with the specified protection
 *   domain.
 * @dev: IB device
 * @pd: The protection domain associated with the QP.
 * @attr: A list of initial attributes required to create the
 *   QP.  If QP creation succeeds, then the attributes are updated to
 *   the actual capabilities of the created QP.
 * @udata: User data
 * @uobj: uverbs obect
 * @caller: caller's build-time module name
 */
struct ib_qp *ib_create_qp_user(struct ib_device *dev, struct ib_pd *pd,
				struct ib_qp_init_attr *attr,
				struct ib_udata *udata,
				struct ib_uqp_object *uobj, const char *caller)
{
	struct ib_qp *qp, *xrc_qp;

	if (attr->qp_type == IB_QPT_XRC_TGT)
		qp = create_qp(dev, pd, attr, NULL, NULL, caller);
	else
		qp = create_qp(dev, pd, attr, udata, uobj, NULL);
	if (attr->qp_type != IB_QPT_XRC_TGT || IS_ERR(qp))
		return qp;

	xrc_qp = create_xrc_qp_user(qp, attr);
	if (IS_ERR(xrc_qp)) {
		ib_destroy_qp(qp);
		return xrc_qp;
	}

	xrc_qp->uobject = uobj;
	return xrc_qp;
}
EXPORT_SYMBOL(ib_create_qp_user);

void ib_qp_usecnt_inc(struct ib_qp *qp)
{
	if (qp->pd)
		atomic_inc(&qp->pd->usecnt);
	if (qp->send_cq)
		atomic_inc(&qp->send_cq->usecnt);
	if (qp->recv_cq)
		atomic_inc(&qp->recv_cq->usecnt);
	if (qp->srq)
		atomic_inc(&qp->srq->usecnt);
	if (qp->rwq_ind_tbl)
		atomic_inc(&qp->rwq_ind_tbl->usecnt);
}
EXPORT_SYMBOL(ib_qp_usecnt_inc);

void ib_qp_usecnt_dec(struct ib_qp *qp)
{
	if (qp->rwq_ind_tbl)
		atomic_dec(&qp->rwq_ind_tbl->usecnt);
	if (qp->srq)
		atomic_dec(&qp->srq->usecnt);
	if (qp->recv_cq)
		atomic_dec(&qp->recv_cq->usecnt);
	if (qp->send_cq)
		atomic_dec(&qp->send_cq->usecnt);
	if (qp->pd)
		atomic_dec(&qp->pd->usecnt);
}
EXPORT_SYMBOL(ib_qp_usecnt_dec);

struct ib_qp *ib_create_qp_kernel(struct ib_pd *pd,
				  struct ib_qp_init_attr *qp_init_attr,
				  const char *caller)
{
	struct ib_device *device = pd->device;
	struct ib_qp *qp;
	int ret;

	/*
	 * If the callers is using the RDMA API calculate the resources
	 * needed for the RDMA READ/WRITE operations.
	 *
	 * Note that these callers need to pass in a port number.
	 */
	if (qp_init_attr->cap.max_rdma_ctxs)
		rdma_rw_init_qp(device, qp_init_attr);

	qp = create_qp(device, pd, qp_init_attr, NULL, NULL, caller);
	if (IS_ERR(qp))
		return qp;

	ib_qp_usecnt_inc(qp);

	if (qp_init_attr->cap.max_rdma_ctxs) {
		ret = rdma_rw_init_mrs(qp, qp_init_attr);
		if (ret)
			goto err;
	}

	/*
	 * Note: all hw drivers guarantee that max_send_sge is lower than
	 * the device RDMA WRITE SGE limit but not all hw drivers ensure that
	 * max_send_sge <= max_sge_rd.
	 */
	qp->max_write_sge = qp_init_attr->cap.max_send_sge;
	qp->max_read_sge = min_t(u32, qp_init_attr->cap.max_send_sge,
				 device->attrs.max_sge_rd);
	if (qp_init_attr->create_flags & IB_QP_CREATE_INTEGRITY_EN)
		qp->integrity_en = true;

	return qp;

err:
	ib_destroy_qp(qp);
	return ERR_PTR(ret);

}
EXPORT_SYMBOL(ib_create_qp_kernel);

static const struct {
	int			valid;
	enum ib_qp_attr_mask	req_param[IB_QPT_MAX];
	enum ib_qp_attr_mask	opt_param[IB_QPT_MAX];
} qp_state_table[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = {
	[IB_QPS_RESET] = {
		[IB_QPS_RESET] = { .valid = 1 },
		[IB_QPS_INIT]  = {
			.valid = 1,
			.req_param = {
				[IB_QPT_UD]  = (IB_QP_PKEY_INDEX		|
						IB_QP_PORT			|
						IB_QP_QKEY),
				[IB_QPT_RAW_PACKET] = IB_QP_PORT,
				[IB_QPT_UC]  = (IB_QP_PKEY_INDEX		|
						IB_QP_PORT			|
						IB_QP_ACCESS_FLAGS),
				[IB_QPT_RC]  = (IB_QP_PKEY_INDEX		|
						IB_QP_PORT			|
						IB_QP_ACCESS_FLAGS),
				[IB_QPT_XRC_INI] = (IB_QP_PKEY_INDEX		|
						IB_QP_PORT			|
						IB_QP_ACCESS_FLAGS),
				[IB_QPT_XRC_TGT] = (IB_QP_PKEY_INDEX		|
						IB_QP_PORT			|
						IB_QP_ACCESS_FLAGS),
				[IB_QPT_SMI] = (IB_QP_PKEY_INDEX		|
						IB_QP_QKEY),
				[IB_QPT_GSI] = (IB_QP_PKEY_INDEX		|
						IB_QP_QKEY),
			}
		},
	},
	[IB_QPS_INIT]  = {
		[IB_QPS_RESET] = { .valid = 1 },
		[IB_QPS_ERR] =   { .valid = 1 },
		[IB_QPS_INIT]  = {
			.valid = 1,
			.opt_param = {
				[IB_QPT_UD]  = (IB_QP_PKEY_INDEX		|
						IB_QP_PORT			|
						IB_QP_QKEY),
				[IB_QPT_UC]  = (IB_QP_PKEY_INDEX		|
						IB_QP_PORT			|
						IB_QP_ACCESS_FLAGS),
				[IB_QPT_RC]  = (IB_QP_PKEY_INDEX		|
						IB_QP_PORT			|
						IB_QP_ACCESS_FLAGS),
				[IB_QPT_XRC_INI] = (IB_QP_PKEY_INDEX		|
						IB_QP_PORT			|
						IB_QP_ACCESS_FLAGS),
				[IB_QPT_XRC_TGT] = (IB_QP_PKEY_INDEX		|
						IB_QP_PORT			|
						IB_QP_ACCESS_FLAGS),
				[IB_QPT_SMI] = (IB_QP_PKEY_INDEX		|
						IB_QP_QKEY),
				[IB_QPT_GSI] = (IB_QP_PKEY_INDEX		|
						IB_QP_QKEY),
			}
		},
		[IB_QPS_RTR]   = {
			.valid = 1,
			.req_param = {
				[IB_QPT_UC]  = (IB_QP_AV			|
						IB_QP_PATH_MTU			|
						IB_QP_DEST_QPN			|
						IB_QP_RQ_PSN),
				[IB_QPT_RC]  = (IB_QP_AV			|
						IB_QP_PATH_MTU			|
						IB_QP_DEST_QPN			|
						IB_QP_RQ_PSN			|
						IB_QP_MAX_DEST_RD_ATOMIC	|
						IB_QP_MIN_RNR_TIMER),
				[IB_QPT_XRC_INI] = (IB_QP_AV			|
						IB_QP_PATH_MTU			|
						IB_QP_DEST_QPN			|
						IB_QP_RQ_PSN),
				[IB_QPT_XRC_TGT] = (IB_QP_AV			|
						IB_QP_PATH_MTU			|
						IB_QP_DEST_QPN			|
						IB_QP_RQ_PSN			|
						IB_QP_MAX_DEST_RD_ATOMIC	|
						IB_QP_MIN_RNR_TIMER),
			},
			.opt_param = {
				 [IB_QPT_UD]  = (IB_QP_PKEY_INDEX		|
						 IB_QP_QKEY),
				 [IB_QPT_UC]  = (IB_QP_ALT_PATH			|
						 IB_QP_ACCESS_FLAGS		|
						 IB_QP_PKEY_INDEX),
				 [IB_QPT_RC]  = (IB_QP_ALT_PATH			|
						 IB_QP_ACCESS_FLAGS		|
						 IB_QP_PKEY_INDEX),
				 [IB_QPT_XRC_INI] = (IB_QP_ALT_PATH		|
						 IB_QP_ACCESS_FLAGS		|
						 IB_QP_PKEY_INDEX),
				 [IB_QPT_XRC_TGT] = (IB_QP_ALT_PATH		|
						 IB_QP_ACCESS_FLAGS		|
						 IB_QP_PKEY_INDEX),
				 [IB_QPT_SMI] = (IB_QP_PKEY_INDEX		|
						 IB_QP_QKEY),
				 [IB_QPT_GSI] = (IB_QP_PKEY_INDEX		|
						 IB_QP_QKEY),
			 },
		},
	},
	[IB_QPS_RTR]   = {
		[IB_QPS_RESET] = { .valid = 1 },
		[IB_QPS_ERR] =   { .valid = 1 },
		[IB_QPS_RTS]   = {
			.valid = 1,
			.req_param = {
				[IB_QPT_UD]  = IB_QP_SQ_PSN,
				[IB_QPT_UC]  = IB_QP_SQ_PSN,
				[IB_QPT_RC]  = (IB_QP_TIMEOUT			|
						IB_QP_RETRY_CNT			|
						IB_QP_RNR_RETRY			|
						IB_QP_SQ_PSN			|
						IB_QP_MAX_QP_RD_ATOMIC),
				[IB_QPT_XRC_INI] = (IB_QP_TIMEOUT		|
						IB_QP_RETRY_CNT			|
						IB_QP_RNR_RETRY			|
						IB_QP_SQ_PSN			|
						IB_QP_MAX_QP_RD_ATOMIC),
				[IB_QPT_XRC_TGT] = (IB_QP_TIMEOUT		|
						IB_QP_SQ_PSN),
				[IB_QPT_SMI] = IB_QP_SQ_PSN,
				[IB_QPT_GSI] = IB_QP_SQ_PSN,
			},
			.opt_param = {
				 [IB_QPT_UD]  = (IB_QP_CUR_STATE		|
						 IB_QP_QKEY),
				 [IB_QPT_UC]  = (IB_QP_CUR_STATE		|
						 IB_QP_ALT_PATH			|
						 IB_QP_ACCESS_FLAGS		|
						 IB_QP_PATH_MIG_STATE),
				 [IB_QPT_RC]  = (IB_QP_CUR_STATE		|
						 IB_QP_ALT_PATH			|
						 IB_QP_ACCESS_FLAGS		|
						 IB_QP_MIN_RNR_TIMER		|
						 IB_QP_PATH_MIG_STATE),
				 [IB_QPT_XRC_INI] = (IB_QP_CUR_STATE		|
						 IB_QP_ALT_PATH			|
						 IB_QP_ACCESS_FLAGS		|
						 IB_QP_PATH_MIG_STATE),
				 [IB_QPT_XRC_TGT] = (IB_QP_CUR_STATE		|
						 IB_QP_ALT_PATH			|
						 IB_QP_ACCESS_FLAGS		|
						 IB_QP_MIN_RNR_TIMER		|
						 IB_QP_PATH_MIG_STATE),
				 [IB_QPT_SMI] = (IB_QP_CUR_STATE		|
						 IB_QP_QKEY),
				 [IB_QPT_GSI] = (IB_QP_CUR_STATE		|
						 IB_QP_QKEY),
				 [IB_QPT_RAW_PACKET] = IB_QP_RATE_LIMIT,
			 }
		}
	},
	[IB_QPS_RTS]   = {
		[IB_QPS_RESET] = { .valid = 1 },
		[IB_QPS_ERR] =   { .valid = 1 },
		[IB_QPS_RTS]   = {
			.valid = 1,
			.opt_param = {
				[IB_QPT_UD]  = (IB_QP_CUR_STATE			|
						IB_QP_QKEY),
				[IB_QPT_UC]  = (IB_QP_CUR_STATE			|
						IB_QP_ACCESS_FLAGS		|
						IB_QP_ALT_PATH			|
						IB_QP_PATH_MIG_STATE),
				[IB_QPT_RC]  = (IB_QP_CUR_STATE			|
						IB_QP_ACCESS_FLAGS		|
						IB_QP_ALT_PATH			|
						IB_QP_PATH_MIG_STATE		|
						IB_QP_MIN_RNR_TIMER),
				[IB_QPT_XRC_INI] = (IB_QP_CUR_STATE		|
						IB_QP_ACCESS_FLAGS		|
						IB_QP_ALT_PATH			|
						IB_QP_PATH_MIG_STATE),
				[IB_QPT_XRC_TGT] = (IB_QP_CUR_STATE		|
						IB_QP_ACCESS_FLAGS		|
						IB_QP_ALT_PATH			|
						IB_QP_PATH_MIG_STATE		|
						IB_QP_MIN_RNR_TIMER),
				[IB_QPT_SMI] = (IB_QP_CUR_STATE			|
						IB_QP_QKEY),
				[IB_QPT_GSI] = (IB_QP_CUR_STATE			|
						IB_QP_QKEY),
				[IB_QPT_RAW_PACKET] = IB_QP_RATE_LIMIT,
			}
		},
		[IB_QPS_SQD]   = {
			.valid = 1,
			.opt_param = {
				[IB_QPT_UD]  = IB_QP_EN_SQD_ASYNC_NOTIFY,
				[IB_QPT_UC]  = IB_QP_EN_SQD_ASYNC_NOTIFY,
				[IB_QPT_RC]  = IB_QP_EN_SQD_ASYNC_NOTIFY,
				[IB_QPT_XRC_INI] = IB_QP_EN_SQD_ASYNC_NOTIFY,
				[IB_QPT_XRC_TGT] = IB_QP_EN_SQD_ASYNC_NOTIFY, /* ??? */
				[IB_QPT_SMI] = IB_QP_EN_SQD_ASYNC_NOTIFY,
				[IB_QPT_GSI] = IB_QP_EN_SQD_ASYNC_NOTIFY
			}
		},
	},
	[IB_QPS_SQD]   = {
		[IB_QPS_RESET] = { .valid = 1 },
		[IB_QPS_ERR] =   { .valid = 1 },
		[IB_QPS_RTS]   = {
			.valid = 1,
			.opt_param = {
				[IB_QPT_UD]  = (IB_QP_CUR_STATE			|
						IB_QP_QKEY),
				[IB_QPT_UC]  = (IB_QP_CUR_STATE			|
						IB_QP_ALT_PATH			|
						IB_QP_ACCESS_FLAGS		|
						IB_QP_PATH_MIG_STATE),
				[IB_QPT_RC]  = (IB_QP_CUR_STATE			|
						IB_QP_ALT_PATH			|
						IB_QP_ACCESS_FLAGS		|
						IB_QP_MIN_RNR_TIMER		|
						IB_QP_PATH_MIG_STATE),
				[IB_QPT_XRC_INI] = (IB_QP_CUR_STATE		|
						IB_QP_ALT_PATH			|
						IB_QP_ACCESS_FLAGS		|
						IB_QP_PATH_MIG_STATE),
				[IB_QPT_XRC_TGT] = (IB_QP_CUR_STATE		|
						IB_QP_ALT_PATH			|
						IB_QP_ACCESS_FLAGS		|
						IB_QP_MIN_RNR_TIMER		|
						IB_QP_PATH_MIG_STATE),
				[IB_QPT_SMI] = (IB_QP_CUR_STATE			|
						IB_QP_QKEY),
				[IB_QPT_GSI] = (IB_QP_CUR_STATE			|
						IB_QP_QKEY),
			}
		},
		[IB_QPS_SQD]   = {
			.valid = 1,
			.opt_param = {
				[IB_QPT_UD]  = (IB_QP_PKEY_INDEX		|
						IB_QP_QKEY),
				[IB_QPT_UC]  = (IB_QP_AV			|
						IB_QP_ALT_PATH			|
						IB_QP_ACCESS_FLAGS		|
						IB_QP_PKEY_INDEX		|
						IB_QP_PATH_MIG_STATE),
				[IB_QPT_RC]  = (IB_QP_PORT			|
						IB_QP_AV			|
						IB_QP_TIMEOUT			|
						IB_QP_RETRY_CNT			|
						IB_QP_RNR_RETRY			|
						IB_QP_MAX_QP_RD_ATOMIC		|
						IB_QP_MAX_DEST_RD_ATOMIC	|
						IB_QP_ALT_PATH			|
						IB_QP_ACCESS_FLAGS		|
						IB_QP_PKEY_INDEX		|
						IB_QP_MIN_RNR_TIMER		|
						IB_QP_PATH_MIG_STATE),
				[IB_QPT_XRC_INI] = (IB_QP_PORT			|
						IB_QP_AV			|
						IB_QP_TIMEOUT			|
						IB_QP_RETRY_CNT			|
						IB_QP_RNR_RETRY			|
						IB_QP_MAX_QP_RD_ATOMIC		|
						IB_QP_ALT_PATH			|
						IB_QP_ACCESS_FLAGS		|
						IB_QP_PKEY_INDEX		|
						IB_QP_PATH_MIG_STATE),
				[IB_QPT_XRC_TGT] = (IB_QP_PORT			|
						IB_QP_AV			|
						IB_QP_TIMEOUT			|
						IB_QP_MAX_DEST_RD_ATOMIC	|
						IB_QP_ALT_PATH			|
						IB_QP_ACCESS_FLAGS		|
						IB_QP_PKEY_INDEX		|
						IB_QP_MIN_RNR_TIMER		|
						IB_QP_PATH_MIG_STATE),
				[IB_QPT_SMI] = (IB_QP_PKEY_INDEX		|
						IB_QP_QKEY),
				[IB_QPT_GSI] = (IB_QP_PKEY_INDEX		|
						IB_QP_QKEY),
			}
		}
	},
	[IB_QPS_SQE]   = {
		[IB_QPS_RESET] = { .valid = 1 },
		[IB_QPS_ERR] =   { .valid = 1 },
		[IB_QPS_RTS]   = {
			.valid = 1,
			.opt_param = {
				[IB_QPT_UD]  = (IB_QP_CUR_STATE			|
						IB_QP_QKEY),
				[IB_QPT_UC]  = (IB_QP_CUR_STATE			|
						IB_QP_ACCESS_FLAGS),
				[IB_QPT_SMI] = (IB_QP_CUR_STATE			|
						IB_QP_QKEY),
				[IB_QPT_GSI] = (IB_QP_CUR_STATE			|
						IB_QP_QKEY),
			}
		}
	},
	[IB_QPS_ERR] = {
		[IB_QPS_RESET] = { .valid = 1 },
		[IB_QPS_ERR] =   { .valid = 1 }
	}
};

bool ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
			enum ib_qp_type type, enum ib_qp_attr_mask mask)
{
	enum ib_qp_attr_mask req_param, opt_param;

	if (mask & IB_QP_CUR_STATE  &&
	    cur_state != IB_QPS_RTR && cur_state != IB_QPS_RTS &&
	    cur_state != IB_QPS_SQD && cur_state != IB_QPS_SQE)
		return false;

	if (!qp_state_table[cur_state][next_state].valid)
		return false;

	req_param = qp_state_table[cur_state][next_state].req_param[type];
	opt_param = qp_state_table[cur_state][next_state].opt_param[type];

	if ((mask & req_param) != req_param)
		return false;

	if (mask & ~(req_param | opt_param | IB_QP_STATE))
		return false;

	return true;
}
EXPORT_SYMBOL(ib_modify_qp_is_ok);

/**
 * ib_resolve_eth_dmac - Resolve destination mac address
 * @device:		Device to consider
 * @ah_attr:		address handle attribute which describes the
 *			source and destination parameters
 * ib_resolve_eth_dmac() resolves destination mac address and L3 hop limit It
 * returns 0 on success or appropriate error code. It initializes the
 * necessary ah_attr fields when call is successful.
 */
static int ib_resolve_eth_dmac(struct ib_device *device,
			       struct rdma_ah_attr *ah_attr)
{
	int ret = 0;

	if (rdma_is_multicast_addr((struct in6_addr *)ah_attr->grh.dgid.raw)) {
		if (ipv6_addr_v4mapped((struct in6_addr *)ah_attr->grh.dgid.raw)) {
			__be32 addr = 0;

			memcpy(&addr, ah_attr->grh.dgid.raw + 12, 4);
			ip_eth_mc_map(addr, (char *)ah_attr->roce.dmac);
		} else {
			ipv6_eth_mc_map((struct in6_addr *)ah_attr->grh.dgid.raw,
					(char *)ah_attr->roce.dmac);
		}
	} else {
		ret = ib_resolve_unicast_gid_dmac(device, ah_attr);
	}
	return ret;
}

static bool is_qp_type_connected(const struct ib_qp *qp)
{
	return (qp->qp_type == IB_QPT_UC ||
		qp->qp_type == IB_QPT_RC ||
		qp->qp_type == IB_QPT_XRC_INI ||
		qp->qp_type == IB_QPT_XRC_TGT);
}

/*
 * IB core internal function to perform QP attributes modification.
 */
static int _ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *attr,
			 int attr_mask, struct ib_udata *udata)
{
	u32 port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
	const struct ib_gid_attr *old_sgid_attr_av;
	const struct ib_gid_attr *old_sgid_attr_alt_av;
	int ret;

	attr->xmit_slave = NULL;
	if (attr_mask & IB_QP_AV) {
		ret = rdma_fill_sgid_attr(qp->device, &attr->ah_attr,
					  &old_sgid_attr_av);
		if (ret)
			return ret;

		if (attr->ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE &&
		    is_qp_type_connected(qp)) {
			struct net_device *slave;

			/*
			 * If the user provided the qp_attr then we have to
			 * resolve it. Kerne users have to provide already
			 * resolved rdma_ah_attr's.
			 */
			if (udata) {
				ret = ib_resolve_eth_dmac(qp->device,
							  &attr->ah_attr);
				if (ret)
					goto out_av;
			}
			slave = rdma_lag_get_ah_roce_slave(qp->device,
							   &attr->ah_attr,
							   GFP_KERNEL);
			if (IS_ERR(slave)) {
				ret = PTR_ERR(slave);
				goto out_av;
			}
			attr->xmit_slave = slave;
		}
	}
	if (attr_mask & IB_QP_ALT_PATH) {
		/*
		 * FIXME: This does not track the migration state, so if the
		 * user loads a new alternate path after the HW has migrated
		 * from primary->alternate we will keep the wrong
		 * references. This is OK for IB because the reference
		 * counting does not serve any functional purpose.
		 */
		ret = rdma_fill_sgid_attr(qp->device, &attr->alt_ah_attr,
					  &old_sgid_attr_alt_av);
		if (ret)
			goto out_av;

		/*
		 * Today the core code can only handle alternate paths and APM
		 * for IB. Ban them in roce mode.
		 */
		if (!(rdma_protocol_ib(qp->device,
				       attr->alt_ah_attr.port_num) &&
		      rdma_protocol_ib(qp->device, port))) {
			ret = -EINVAL;
			goto out;
		}
	}

	if (rdma_ib_or_roce(qp->device, port)) {
		if (attr_mask & IB_QP_RQ_PSN && attr->rq_psn & ~0xffffff) {
			dev_warn(&qp->device->dev,
				 "%s rq_psn overflow, masking to 24 bits\n",
				 __func__);
			attr->rq_psn &= 0xffffff;
		}

		if (attr_mask & IB_QP_SQ_PSN && attr->sq_psn & ~0xffffff) {
			dev_warn(&qp->device->dev,
				 " %s sq_psn overflow, masking to 24 bits\n",
				 __func__);
			attr->sq_psn &= 0xffffff;
		}
	}

	/*
	 * Bind this qp to a counter automatically based on the rdma counter
	 * rules. This only set in RST2INIT with port specified
	 */
	if (!qp->counter && (attr_mask & IB_QP_PORT) &&
	    ((attr_mask & IB_QP_STATE) && attr->qp_state == IB_QPS_INIT))
		rdma_counter_bind_qp_auto(qp, attr->port_num);

	ret = ib_security_modify_qp(qp, attr, attr_mask, udata);
	if (ret)
		goto out;

	if (attr_mask & IB_QP_PORT)
		qp->port = attr->port_num;
	if (attr_mask & IB_QP_AV)
		qp->av_sgid_attr =
			rdma_update_sgid_attr(&attr->ah_attr, qp->av_sgid_attr);
	if (attr_mask & IB_QP_ALT_PATH)
		qp->alt_path_sgid_attr = rdma_update_sgid_attr(
			&attr->alt_ah_attr, qp->alt_path_sgid_attr);

out:
	if (attr_mask & IB_QP_ALT_PATH)
		rdma_unfill_sgid_attr(&attr->alt_ah_attr, old_sgid_attr_alt_av);
out_av:
	if (attr_mask & IB_QP_AV) {
		rdma_lag_put_ah_roce_slave(attr->xmit_slave);
		rdma_unfill_sgid_attr(&attr->ah_attr, old_sgid_attr_av);
	}
	return ret;
}

/**
 * ib_modify_qp_with_udata - Modifies the attributes for the specified QP.
 * @ib_qp: The QP to modify.
 * @attr: On input, specifies the QP attributes to modify.  On output,
 *   the current values of selected QP attributes are returned.
 * @attr_mask: A bit-mask used to specify which attributes of the QP
 *   are being modified.
 * @udata: pointer to user's input output buffer information
 *   are being modified.
 * It returns 0 on success and returns appropriate error code on error.
 */
int ib_modify_qp_with_udata(struct ib_qp *ib_qp, struct ib_qp_attr *attr,
			    int attr_mask, struct ib_udata *udata)
{
	return _ib_modify_qp(ib_qp->real_qp, attr, attr_mask, udata);
}
EXPORT_SYMBOL(ib_modify_qp_with_udata);

int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width)
{
	int rc;
	u32 netdev_speed;
	struct net_device *netdev;
	struct ethtool_link_ksettings lksettings;

	if (rdma_port_get_link_layer(dev, port_num) != IB_LINK_LAYER_ETHERNET)
		return -EINVAL;

	netdev = ib_device_get_netdev(dev, port_num);
	if (!netdev)
		return -ENODEV;

	rtnl_lock();
	rc = __ethtool_get_link_ksettings(netdev, &lksettings);
	rtnl_unlock();

	dev_put(netdev);

	if (!rc && lksettings.base.speed != (u32)SPEED_UNKNOWN) {
		netdev_speed = lksettings.base.speed;
	} else {
		netdev_speed = SPEED_1000;
		pr_warn("%s speed is unknown, defaulting to %u\n", netdev->name,
			netdev_speed);
	}

	if (netdev_speed <= SPEED_1000) {
		*width = IB_WIDTH_1X;
		*speed = IB_SPEED_SDR;
	} else if (netdev_speed <= SPEED_10000) {
		*width = IB_WIDTH_1X;
		*speed = IB_SPEED_FDR10;
	} else if (netdev_speed <= SPEED_20000) {
		*width = IB_WIDTH_4X;
		*speed = IB_SPEED_DDR;
	} else if (netdev_speed <= SPEED_25000) {
		*width = IB_WIDTH_1X;
		*speed = IB_SPEED_EDR;
	} else if (netdev_speed <= SPEED_40000) {
		*width = IB_WIDTH_4X;
		*speed = IB_SPEED_FDR10;
	} else {
		*width = IB_WIDTH_4X;
		*speed = IB_SPEED_EDR;
	}

	return 0;
}
EXPORT_SYMBOL(ib_get_eth_speed);

int ib_modify_qp(struct ib_qp *qp,
		 struct ib_qp_attr *qp_attr,
		 int qp_attr_mask)
{
	return _ib_modify_qp(qp->real_qp, qp_attr, qp_attr_mask, NULL);
}
EXPORT_SYMBOL(ib_modify_qp);

int ib_query_qp(struct ib_qp *qp,
		struct ib_qp_attr *qp_attr,
		int qp_attr_mask,
		struct ib_qp_init_attr *qp_init_attr)
{
	qp_attr->ah_attr.grh.sgid_attr = NULL;
	qp_attr->alt_ah_attr.grh.sgid_attr = NULL;

	return qp->device->ops.query_qp ?
		qp->device->ops.query_qp(qp->real_qp, qp_attr, qp_attr_mask,
					 qp_init_attr) : -EOPNOTSUPP;
}
EXPORT_SYMBOL(ib_query_qp);

int ib_close_qp(struct ib_qp *qp)
{
	struct ib_qp *real_qp;
	unsigned long flags;

	real_qp = qp->real_qp;
	if (real_qp == qp)
		return -EINVAL;

	spin_lock_irqsave(&real_qp->device->qp_open_list_lock, flags);
	list_del(&qp->open_list);
	spin_unlock_irqrestore(&real_qp->device->qp_open_list_lock, flags);

	atomic_dec(&real_qp->usecnt);
	if (qp->qp_sec)
		ib_close_shared_qp_security(qp->qp_sec);
	kfree(qp);

	return 0;
}
EXPORT_SYMBOL(ib_close_qp);

static int __ib_destroy_shared_qp(struct ib_qp *qp)
{
	struct ib_xrcd *xrcd;
	struct ib_qp *real_qp;
	int ret;

	real_qp = qp->real_qp;
	xrcd = real_qp->xrcd;
	down_write(&xrcd->tgt_qps_rwsem);
	ib_close_qp(qp);
	if (atomic_read(&real_qp->usecnt) == 0)
		xa_erase(&xrcd->tgt_qps, real_qp->qp_num);
	else
		real_qp = NULL;
	up_write(&xrcd->tgt_qps_rwsem);

	if (real_qp) {
		ret = ib_destroy_qp(real_qp);
		if (!ret)
			atomic_dec(&xrcd->usecnt);
	}

	return 0;
}

int ib_destroy_qp_user(struct ib_qp *qp, struct ib_udata *udata)
{
	const struct ib_gid_attr *alt_path_sgid_attr = qp->alt_path_sgid_attr;
	const struct ib_gid_attr *av_sgid_attr = qp->av_sgid_attr;
	struct ib_qp_security *sec;
	int ret;

	WARN_ON_ONCE(qp->mrs_used > 0);

	if (atomic_read(&qp->usecnt))
		return -EBUSY;

	if (qp->real_qp != qp)
		return __ib_destroy_shared_qp(qp);

	sec  = qp->qp_sec;
	if (sec)
		ib_destroy_qp_security_begin(sec);

	if (!qp->uobject)
		rdma_rw_cleanup_mrs(qp);

	rdma_counter_unbind_qp(qp, true);
	ret = qp->device->ops.destroy_qp(qp, udata);
	if (ret) {
		if (sec)
			ib_destroy_qp_security_abort(sec);
		return ret;
	}

	if (alt_path_sgid_attr)
		rdma_put_gid_attr(alt_path_sgid_attr);
	if (av_sgid_attr)
		rdma_put_gid_attr(av_sgid_attr);

	ib_qp_usecnt_dec(qp);
	if (sec)
		ib_destroy_qp_security_end(sec);

	rdma_restrack_del(&qp->res);
	kfree(qp);
	return ret;
}
EXPORT_SYMBOL(ib_destroy_qp_user);

/* Completion queues */

struct ib_cq *__ib_create_cq(struct ib_device *device,
			     ib_comp_handler comp_handler,
			     void (*event_handler)(struct ib_event *, void *),
			     void *cq_context,
			     const struct ib_cq_init_attr *cq_attr,
			     const char *caller)
{
	struct ib_cq *cq;
	int ret;

	cq = rdma_zalloc_drv_obj(device, ib_cq);
	if (!cq)
		return ERR_PTR(-ENOMEM);

	cq->device = device;
	cq->uobject = NULL;
	cq->comp_handler = comp_handler;
	cq->event_handler = event_handler;
	cq->cq_context = cq_context;
	atomic_set(&cq->usecnt, 0);

	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
	rdma_restrack_set_name(&cq->res, caller);

	ret = device->ops.create_cq(cq, cq_attr, NULL);
	if (ret) {
		rdma_restrack_put(&cq->res);
		kfree(cq);
		return ERR_PTR(ret);
	}

	rdma_restrack_add(&cq->res);
	return cq;
}
EXPORT_SYMBOL(__ib_create_cq);

int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period)
{
	if (cq->shared)
		return -EOPNOTSUPP;

	return cq->device->ops.modify_cq ?
		cq->device->ops.modify_cq(cq, cq_count,
					  cq_period) : -EOPNOTSUPP;
}
EXPORT_SYMBOL(rdma_set_cq_moderation);

int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata)
{
	int ret;

	if (WARN_ON_ONCE(cq->shared))
		return -EOPNOTSUPP;

	if (atomic_read(&cq->usecnt))
		return -EBUSY;

	ret = cq->device->ops.destroy_cq(cq, udata);
	if (ret)
		return ret;

	rdma_restrack_del(&cq->res);
	kfree(cq);
	return ret;
}
EXPORT_SYMBOL(ib_destroy_cq_user);

int ib_resize_cq(struct ib_cq *cq, int cqe)
{
	if (cq->shared)
		return -EOPNOTSUPP;

	return cq->device->ops.resize_cq ?
		cq->device->ops.resize_cq(cq, cqe, NULL) : -EOPNOTSUPP;
}
EXPORT_SYMBOL(ib_resize_cq);

/* Memory regions */

struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
			     u64 virt_addr, int access_flags)
{
	struct ib_mr *mr;

	if (access_flags & IB_ACCESS_ON_DEMAND) {
		if (!(pd->device->attrs.kernel_cap_flags &
		      IBK_ON_DEMAND_PAGING)) {
			pr_debug("ODP support not available\n");
			return ERR_PTR(-EINVAL);
		}
	}

	mr = pd->device->ops.reg_user_mr(pd, start, length, virt_addr,
					 access_flags, NULL);

	if (IS_ERR(mr))
		return mr;

	mr->device = pd->device;
	mr->type = IB_MR_TYPE_USER;
	mr->pd = pd;
	mr->dm = NULL;
	atomic_inc(&pd->usecnt);
	mr->iova =  virt_addr;
	mr->length = length;

	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
	rdma_restrack_parent_name(&mr->res, &pd->res);
	rdma_restrack_add(&mr->res);

	return mr;
}
EXPORT_SYMBOL(ib_reg_user_mr);

int ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice,
		 u32 flags, struct ib_sge *sg_list, u32 num_sge)
{
	if (!pd->device->ops.advise_mr)
		return -EOPNOTSUPP;

	if (!num_sge)
		return 0;

	return pd->device->ops.advise_mr(pd, advice, flags, sg_list, num_sge,
					 NULL);
}
EXPORT_SYMBOL(ib_advise_mr);

int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata)
{
	struct ib_pd *pd = mr->pd;
	struct ib_dm *dm = mr->dm;
	struct ib_sig_attrs *sig_attrs = mr->sig_attrs;
	int ret;

	trace_mr_dereg(mr);
	rdma_restrack_del(&mr->res);
	ret = mr->device->ops.dereg_mr(mr, udata);
	if (!ret) {
		atomic_dec(&pd->usecnt);
		if (dm)
			atomic_dec(&dm->usecnt);
		kfree(sig_attrs);
	}

	return ret;
}
EXPORT_SYMBOL(ib_dereg_mr_user);

/**
 * ib_alloc_mr() - Allocates a memory region
 * @pd:            protection domain associated with the region
 * @mr_type:       memory region type
 * @max_num_sg:    maximum sg entries available for registration.
 *
 * Notes:
 * Memory registeration page/sg lists must not exceed max_num_sg.
 * For mr_type IB_MR_TYPE_MEM_REG, the total length cannot exceed
 * max_num_sg * used_page_size.
 *
 */
struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,
			  u32 max_num_sg)
{
	struct ib_mr *mr;

	if (!pd->device->ops.alloc_mr) {
		mr = ERR_PTR(-EOPNOTSUPP);
		goto out;
	}

	if (mr_type == IB_MR_TYPE_INTEGRITY) {
		WARN_ON_ONCE(1);
		mr = ERR_PTR(-EINVAL);
		goto out;
	}

	mr = pd->device->ops.alloc_mr(pd, mr_type, max_num_sg);
	if (IS_ERR(mr))
		goto out;

	mr->device = pd->device;
	mr->pd = pd;
	mr->dm = NULL;
	mr->uobject = NULL;
	atomic_inc(&pd->usecnt);
	mr->need_inval = false;
	mr->type = mr_type;
	mr->sig_attrs = NULL;

	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
	rdma_restrack_parent_name(&mr->res, &pd->res);
	rdma_restrack_add(&mr->res);
out:
	trace_mr_alloc(pd, mr_type, max_num_sg, mr);
	return mr;
}
EXPORT_SYMBOL(ib_alloc_mr);

/**
 * ib_alloc_mr_integrity() - Allocates an integrity memory region
 * @pd:                      protection domain associated with the region
 * @max_num_data_sg:         maximum data sg entries available for registration
 * @max_num_meta_sg:         maximum metadata sg entries available for
 *                           registration
 *
 * Notes:
 * Memory registration page/sg lists must not exceed max_num_sg,
 * also the integrity page/sg lists must not exceed max_num_meta_sg.
 *
 */
struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd,
				    u32 max_num_data_sg,
				    u32 max_num_meta_sg)
{
	struct ib_mr *mr;
	struct ib_sig_attrs *sig_attrs;

	if (!pd->device->ops.alloc_mr_integrity ||
	    !pd->device->ops.map_mr_sg_pi) {
		mr = ERR_PTR(-EOPNOTSUPP);
		goto out;
	}

	if (!max_num_meta_sg) {
		mr = ERR_PTR(-EINVAL);
		goto out;
	}

	sig_attrs = kzalloc(sizeof(struct ib_sig_attrs), GFP_KERNEL);
	if (!sig_attrs) {
		mr = ERR_PTR(-ENOMEM);
		goto out;
	}

	mr = pd->device->ops.alloc_mr_integrity(pd, max_num_data_sg,
						max_num_meta_sg);
	if (IS_ERR(mr)) {
		kfree(sig_attrs);
		goto out;
	}

	mr->device = pd->device;
	mr->pd = pd;
	mr->dm = NULL;
	mr->uobject = NULL;
	atomic_inc(&pd->usecnt);
	mr->need_inval = false;
	mr->type = IB_MR_TYPE_INTEGRITY;
	mr->sig_attrs = sig_attrs;

	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
	rdma_restrack_parent_name(&mr->res, &pd->res);
	rdma_restrack_add(&mr->res);
out:
	trace_mr_integ_alloc(pd, max_num_data_sg, max_num_meta_sg, mr);
	return mr;
}
EXPORT_SYMBOL(ib_alloc_mr_integrity);

/* Multicast groups */

static bool is_valid_mcast_lid(struct ib_qp *qp, u16 lid)
{
	struct ib_qp_init_attr init_attr = {};
	struct ib_qp_attr attr = {};
	int num_eth_ports = 0;
	unsigned int port;

	/* If QP state >= init, it is assigned to a port and we can check this
	 * port only.
	 */
	if (!ib_query_qp(qp, &attr, IB_QP_STATE | IB_QP_PORT, &init_attr)) {
		if (attr.qp_state >= IB_QPS_INIT) {
			if (rdma_port_get_link_layer(qp->device, attr.port_num) !=
			    IB_LINK_LAYER_INFINIBAND)
				return true;
			goto lid_check;
		}
	}

	/* Can't get a quick answer, iterate over all ports */
	rdma_for_each_port(qp->device, port)
		if (rdma_port_get_link_layer(qp->device, port) !=
		    IB_LINK_LAYER_INFINIBAND)
			num_eth_ports++;

	/* If we have at lease one Ethernet port, RoCE annex declares that
	 * multicast LID should be ignored. We can't tell at this step if the
	 * QP belongs to an IB or Ethernet port.
	 */
	if (num_eth_ports)
		return true;

	/* If all the ports are IB, we can check according to IB spec. */
lid_check:
	return !(lid < be16_to_cpu(IB_MULTICAST_LID_BASE) ||
		 lid == be16_to_cpu(IB_LID_PERMISSIVE));
}

int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
{
	int ret;

	if (!qp->device->ops.attach_mcast)
		return -EOPNOTSUPP;

	if (!rdma_is_multicast_addr((struct in6_addr *)gid->raw) ||
	    qp->qp_type != IB_QPT_UD || !is_valid_mcast_lid(qp, lid))
		return -EINVAL;

	ret = qp->device->ops.attach_mcast(qp, gid, lid);
	if (!ret)
		atomic_inc(&qp->usecnt);
	return ret;
}
EXPORT_SYMBOL(ib_attach_mcast);

int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
{
	int ret;

	if (!qp->device->ops.detach_mcast)
		return -EOPNOTSUPP;

	if (!rdma_is_multicast_addr((struct in6_addr *)gid->raw) ||
	    qp->qp_type != IB_QPT_UD || !is_valid_mcast_lid(qp, lid))
		return -EINVAL;

	ret = qp->device->ops.detach_mcast(qp, gid, lid);
	if (!ret)
		atomic_dec(&qp->usecnt);
	return ret;
}
EXPORT_SYMBOL(ib_detach_mcast);

/**
 * ib_alloc_xrcd_user - Allocates an XRC domain.
 * @device: The device on which to allocate the XRC domain.
 * @inode: inode to connect XRCD
 * @udata: Valid user data or NULL for kernel object
 */
struct ib_xrcd *ib_alloc_xrcd_user(struct ib_device *device,
				   struct inode *inode, struct ib_udata *udata)
{
	struct ib_xrcd *xrcd;
	int ret;

	if (!device->ops.alloc_xrcd)
		return ERR_PTR(-EOPNOTSUPP);

	xrcd = rdma_zalloc_drv_obj(device, ib_xrcd);
	if (!xrcd)
		return ERR_PTR(-ENOMEM);

	xrcd->device = device;
	xrcd->inode = inode;
	atomic_set(&xrcd->usecnt, 0);
	init_rwsem(&xrcd->tgt_qps_rwsem);
	xa_init(&xrcd->tgt_qps);

	ret = device->ops.alloc_xrcd(xrcd, udata);
	if (ret)
		goto err;
	return xrcd;
err:
	kfree(xrcd);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL(ib_alloc_xrcd_user);

/**
 * ib_dealloc_xrcd_user - Deallocates an XRC domain.
 * @xrcd: The XRC domain to deallocate.
 * @udata: Valid user data or NULL for kernel object
 */
int ib_dealloc_xrcd_user(struct ib_xrcd *xrcd, struct ib_udata *udata)
{
	int ret;

	if (atomic_read(&xrcd->usecnt))
		return -EBUSY;

	WARN_ON(!xa_empty(&xrcd->tgt_qps));
	ret = xrcd->device->ops.dealloc_xrcd(xrcd, udata);
	if (ret)
		return ret;
	kfree(xrcd);
	return ret;
}
EXPORT_SYMBOL(ib_dealloc_xrcd_user);

/**
 * ib_create_wq - Creates a WQ associated with the specified protection
 * domain.
 * @pd: The protection domain associated with the WQ.
 * @wq_attr: A list of initial attributes required to create the
 * WQ. If WQ creation succeeds, then the attributes are updated to
 * the actual capabilities of the created WQ.
 *
 * wq_attr->max_wr and wq_attr->max_sge determine
 * the requested size of the WQ, and set to the actual values allocated
 * on return.
 * If ib_create_wq() succeeds, then max_wr and max_sge will always be
 * at least as large as the requested values.
 */
struct ib_wq *ib_create_wq(struct ib_pd *pd,
			   struct ib_wq_init_attr *wq_attr)
{
	struct ib_wq *wq;

	if (!pd->device->ops.create_wq)
		return ERR_PTR(-EOPNOTSUPP);

	wq = pd->device->ops.create_wq(pd, wq_attr, NULL);
	if (!IS_ERR(wq)) {
		wq->event_handler = wq_attr->event_handler;
		wq->wq_context = wq_attr->wq_context;
		wq->wq_type = wq_attr->wq_type;
		wq->cq = wq_attr->cq;
		wq->device = pd->device;
		wq->pd = pd;
		wq->uobject = NULL;
		atomic_inc(&pd->usecnt);
		atomic_inc(&wq_attr->cq->usecnt);
		atomic_set(&wq->usecnt, 0);
	}
	return wq;
}
EXPORT_SYMBOL(ib_create_wq);

/**
 * ib_destroy_wq_user - Destroys the specified user WQ.
 * @wq: The WQ to destroy.
 * @udata: Valid user data
 */
int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata)
{
	struct ib_cq *cq = wq->cq;
	struct ib_pd *pd = wq->pd;
	int ret;

	if (atomic_read(&wq->usecnt))
		return -EBUSY;

	ret = wq->device->ops.destroy_wq(wq, udata);
	if (ret)
		return ret;

	atomic_dec(&pd->usecnt);
	atomic_dec(&cq->usecnt);
	return ret;
}
EXPORT_SYMBOL(ib_destroy_wq_user);

int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
		       struct ib_mr_status *mr_status)
{
	if (!mr->device->ops.check_mr_status)
		return -EOPNOTSUPP;

	return mr->device->ops.check_mr_status(mr, check_mask, mr_status);
}
EXPORT_SYMBOL(ib_check_mr_status);

int ib_set_vf_link_state(struct ib_device *device, int vf, u32 port,
			 int state)
{
	if (!device->ops.set_vf_link_state)
		return -EOPNOTSUPP;

	return device->ops.set_vf_link_state(device, vf, port, state);
}
EXPORT_SYMBOL(ib_set_vf_link_state);

int ib_get_vf_config(struct ib_device *device, int vf, u32 port,
		     struct ifla_vf_info *info)
{
	if (!device->ops.get_vf_config)
		return -EOPNOTSUPP;

	return device->ops.get_vf_config(device, vf, port, info);
}
EXPORT_SYMBOL(ib_get_vf_config);

int ib_get_vf_stats(struct ib_device *device, int vf, u32 port,
		    struct ifla_vf_stats *stats)
{
	if (!device->ops.get_vf_stats)
		return -EOPNOTSUPP;

	return device->ops.get_vf_stats(device, vf, port, stats);
}
EXPORT_SYMBOL(ib_get_vf_stats);

int ib_set_vf_guid(struct ib_device *device, int vf, u32 port, u64 guid,
		   int type)
{
	if (!device->ops.set_vf_guid)
		return -EOPNOTSUPP;

	return device->ops.set_vf_guid(device, vf, port, guid, type);
}
EXPORT_SYMBOL(ib_set_vf_guid);

int ib_get_vf_guid(struct ib_device *device, int vf, u32 port,
		   struct ifla_vf_guid *node_guid,
		   struct ifla_vf_guid *port_guid)
{
	if (!device->ops.get_vf_guid)
		return -EOPNOTSUPP;

	return device->ops.get_vf_guid(device, vf, port, node_guid, port_guid);
}
EXPORT_SYMBOL(ib_get_vf_guid);
/**
 * ib_map_mr_sg_pi() - Map the dma mapped SG lists for PI (protection
 *     information) and set an appropriate memory region for registration.
 * @mr:             memory region
 * @data_sg:        dma mapped scatterlist for data
 * @data_sg_nents:  number of entries in data_sg
 * @data_sg_offset: offset in bytes into data_sg
 * @meta_sg:        dma mapped scatterlist for metadata
 * @meta_sg_nents:  number of entries in meta_sg
 * @meta_sg_offset: offset in bytes into meta_sg
 * @page_size:      page vector desired page size
 *
 * Constraints:
 * - The MR must be allocated with type IB_MR_TYPE_INTEGRITY.
 *
 * Return: 0 on success.
 *
 * After this completes successfully, the  memory region
 * is ready for registration.
 */
int ib_map_mr_sg_pi(struct ib_mr *mr, struct scatterlist *data_sg,
		    int data_sg_nents, unsigned int *data_sg_offset,
		    struct scatterlist *meta_sg, int meta_sg_nents,
		    unsigned int *meta_sg_offset, unsigned int page_size)
{
	if (unlikely(!mr->device->ops.map_mr_sg_pi ||
		     WARN_ON_ONCE(mr->type != IB_MR_TYPE_INTEGRITY)))
		return -EOPNOTSUPP;

	mr->page_size = page_size;

	return mr->device->ops.map_mr_sg_pi(mr, data_sg, data_sg_nents,
					    data_sg_offset, meta_sg,
					    meta_sg_nents, meta_sg_offset);
}
EXPORT_SYMBOL(ib_map_mr_sg_pi);

/**
 * ib_map_mr_sg() - Map the largest prefix of a dma mapped SG list
 *     and set it the memory region.
 * @mr:            memory region
 * @sg:            dma mapped scatterlist
 * @sg_nents:      number of entries in sg
 * @sg_offset:     offset in bytes into sg
 * @page_size:     page vector desired page size
 *
 * Constraints:
 *
 * - The first sg element is allowed to have an offset.
 * - Each sg element must either be aligned to page_size or virtually
 *   contiguous to the previous element. In case an sg element has a
 *   non-contiguous offset, the mapping prefix will not include it.
 * - The last sg element is allowed to have length less than page_size.
 * - If sg_nents total byte length exceeds the mr max_num_sge * page_size
 *   then only max_num_sg entries will be mapped.
 * - If the MR was allocated with type IB_MR_TYPE_SG_GAPS, none of these
 *   constraints holds and the page_size argument is ignored.
 *
 * Returns the number of sg elements that were mapped to the memory region.
 *
 * After this completes successfully, the  memory region
 * is ready for registration.
 */
int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
		 unsigned int *sg_offset, unsigned int page_size)
{
	if (unlikely(!mr->device->ops.map_mr_sg))
		return -EOPNOTSUPP;

	mr->page_size = page_size;

	return mr->device->ops.map_mr_sg(mr, sg, sg_nents, sg_offset);
}
EXPORT_SYMBOL(ib_map_mr_sg);

/**
 * ib_sg_to_pages() - Convert the largest prefix of a sg list
 *     to a page vector
 * @mr:            memory region
 * @sgl:           dma mapped scatterlist
 * @sg_nents:      number of entries in sg
 * @sg_offset_p:   ==== =======================================================
 *                 IN   start offset in bytes into sg
 *                 OUT  offset in bytes for element n of the sg of the first
 *                      byte that has not been processed where n is the return
 *                      value of this function.
 *                 ==== =======================================================
 * @set_page:      driver page assignment function pointer
 *
 * Core service helper for drivers to convert the largest
 * prefix of given sg list to a page vector. The sg list
 * prefix converted is the prefix that meet the requirements
 * of ib_map_mr_sg.
 *
 * Returns the number of sg elements that were assigned to
 * a page vector.
 */
int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents,
		unsigned int *sg_offset_p, int (*set_page)(struct ib_mr *, u64))
{
	struct scatterlist *sg;
	u64 last_end_dma_addr = 0;
	unsigned int sg_offset = sg_offset_p ? *sg_offset_p : 0;
	unsigned int last_page_off = 0;
	u64 page_mask = ~((u64)mr->page_size - 1);
	int i, ret;

	if (unlikely(sg_nents <= 0 || sg_offset > sg_dma_len(&sgl[0])))
		return -EINVAL;

	mr->iova = sg_dma_address(&sgl[0]) + sg_offset;
	mr->length = 0;

	for_each_sg(sgl, sg, sg_nents, i) {
		u64 dma_addr = sg_dma_address(sg) + sg_offset;
		u64 prev_addr = dma_addr;
		unsigned int dma_len = sg_dma_len(sg) - sg_offset;
		u64 end_dma_addr = dma_addr + dma_len;
		u64 page_addr = dma_addr & page_mask;

		/*
		 * For the second and later elements, check whether either the
		 * end of element i-1 or the start of element i is not aligned
		 * on a page boundary.
		 */
		if (i && (last_page_off != 0 || page_addr != dma_addr)) {
			/* Stop mapping if there is a gap. */
			if (last_end_dma_addr != dma_addr)
				break;

			/*
			 * Coalesce this element with the last. If it is small
			 * enough just update mr->length. Otherwise start
			 * mapping from the next page.
			 */
			goto next_page;
		}

		do {
			ret = set_page(mr, page_addr);
			if (unlikely(ret < 0)) {
				sg_offset = prev_addr - sg_dma_address(sg);
				mr->length += prev_addr - dma_addr;
				if (sg_offset_p)
					*sg_offset_p = sg_offset;
				return i || sg_offset ? i : ret;
			}
			prev_addr = page_addr;
next_page:
			page_addr += mr->page_size;
		} while (page_addr < end_dma_addr);

		mr->length += dma_len;
		last_end_dma_addr = end_dma_addr;
		last_page_off = end_dma_addr & ~page_mask;

		sg_offset = 0;
	}

	if (sg_offset_p)
		*sg_offset_p = 0;
	return i;
}
EXPORT_SYMBOL(ib_sg_to_pages);

struct ib_drain_cqe {
	struct ib_cqe cqe;
	struct completion done;
};

static void ib_drain_qp_done(struct ib_cq *cq, struct ib_wc *wc)
{
	struct ib_drain_cqe *cqe = container_of(wc->wr_cqe, struct ib_drain_cqe,
						cqe);

	complete(&cqe->done);
}

/*
 * Post a WR and block until its completion is reaped for the SQ.
 */
static void __ib_drain_sq(struct ib_qp *qp)
{
	struct ib_cq *cq = qp->send_cq;
	struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
	struct ib_drain_cqe sdrain;
	struct ib_rdma_wr swr = {
		.wr = {
			.next = NULL,
			{ .wr_cqe	= &sdrain.cqe, },
			.opcode	= IB_WR_RDMA_WRITE,
		},
	};
	int ret;

	ret = ib_modify_qp(qp, &attr, IB_QP_STATE);
	if (ret) {
		WARN_ONCE(ret, "failed to drain send queue: %d\n", ret);
		return;
	}

	sdrain.cqe.done = ib_drain_qp_done;
	init_completion(&sdrain.done);

	ret = ib_post_send(qp, &swr.wr, NULL);
	if (ret) {
		WARN_ONCE(ret, "failed to drain send queue: %d\n", ret);
		return;
	}

	if (cq->poll_ctx == IB_POLL_DIRECT)
		while (wait_for_completion_timeout(&sdrain.done, HZ / 10) <= 0)
			ib_process_cq_direct(cq, -1);
	else
		wait_for_completion(&sdrain.done);
}

/*
 * Post a WR and block until its completion is reaped for the RQ.
 */
static void __ib_drain_rq(struct ib_qp *qp)
{
	struct ib_cq *cq = qp->recv_cq;
	struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
	struct ib_drain_cqe rdrain;
	struct ib_recv_wr rwr = {};
	int ret;

	ret = ib_modify_qp(qp, &attr, IB_QP_STATE);
	if (ret) {
		WARN_ONCE(ret, "failed to drain recv queue: %d\n", ret);
		return;
	}

	rwr.wr_cqe = &rdrain.cqe;
	rdrain.cqe.done = ib_drain_qp_done;
	init_completion(&rdrain.done);

	ret = ib_post_recv(qp, &rwr, NULL);
	if (ret) {
		WARN_ONCE(ret, "failed to drain recv queue: %d\n", ret);
		return;
	}

	if (cq->poll_ctx == IB_POLL_DIRECT)
		while (wait_for_completion_timeout(&rdrain.done, HZ / 10) <= 0)
			ib_process_cq_direct(cq, -1);
	else
		wait_for_completion(&rdrain.done);
}

/**
 * ib_drain_sq() - Block until all SQ CQEs have been consumed by the
 *		   application.
 * @qp:            queue pair to drain
 *
 * If the device has a provider-specific drain function, then
 * call that.  Otherwise call the generic drain function
 * __ib_drain_sq().
 *
 * The caller must:
 *
 * ensure there is room in the CQ and SQ for the drain work request and
 * completion.
 *
 * allocate the CQ using ib_alloc_cq().
 *
 * ensure that there are no other contexts that are posting WRs concurrently.
 * Otherwise the drain is not guaranteed.
 */
void ib_drain_sq(struct ib_qp *qp)
{
	if (qp->device->ops.drain_sq)
		qp->device->ops.drain_sq(qp);
	else
		__ib_drain_sq(qp);
	trace_cq_drain_complete(qp->send_cq);
}
EXPORT_SYMBOL(ib_drain_sq);

/**
 * ib_drain_rq() - Block until all RQ CQEs have been consumed by the
 *		   application.
 * @qp:            queue pair to drain
 *
 * If the device has a provider-specific drain function, then
 * call that.  Otherwise call the generic drain function
 * __ib_drain_rq().
 *
 * The caller must:
 *
 * ensure there is room in the CQ and RQ for the drain work request and
 * completion.
 *
 * allocate the CQ using ib_alloc_cq().
 *
 * ensure that there are no other contexts that are posting WRs concurrently.
 * Otherwise the drain is not guaranteed.
 */
void ib_drain_rq(struct ib_qp *qp)
{
	if (qp->device->ops.drain_rq)
		qp->device->ops.drain_rq(qp);
	else
		__ib_drain_rq(qp);
	trace_cq_drain_complete(qp->recv_cq);
}
EXPORT_SYMBOL(ib_drain_rq);

/**
 * ib_drain_qp() - Block until all CQEs have been consumed by the
 *		   application on both the RQ and SQ.
 * @qp:            queue pair to drain
 *
 * The caller must:
 *
 * ensure there is room in the CQ(s), SQ, and RQ for drain work requests
 * and completions.
 *
 * allocate the CQs using ib_alloc_cq().
 *
 * ensure that there are no other contexts that are posting WRs concurrently.
 * Otherwise the drain is not guaranteed.
 */
void ib_drain_qp(struct ib_qp *qp)
{
	ib_drain_sq(qp);
	if (!qp->srq)
		ib_drain_rq(qp);
}
EXPORT_SYMBOL(ib_drain_qp);

struct net_device *rdma_alloc_netdev(struct ib_device *device, u32 port_num,
				     enum rdma_netdev_t type, const char *name,
				     unsigned char name_assign_type,
				     void (*setup)(struct net_device *))
{
	struct rdma_netdev_alloc_params params;
	struct net_device *netdev;
	int rc;

	if (!device->ops.rdma_netdev_get_params)
		return ERR_PTR(-EOPNOTSUPP);

	rc = device->ops.rdma_netdev_get_params(device, port_num, type,
						&params);
	if (rc)
		return ERR_PTR(rc);

	netdev = alloc_netdev_mqs(params.sizeof_priv, name, name_assign_type,
				  setup, params.txqs, params.rxqs);
	if (!netdev)
		return ERR_PTR(-ENOMEM);

	return netdev;
}
EXPORT_SYMBOL(rdma_alloc_netdev);

int rdma_init_netdev(struct ib_device *device, u32 port_num,
		     enum rdma_netdev_t type, const char *name,
		     unsigned char name_assign_type,
		     void (*setup)(struct net_device *),
		     struct net_device *netdev)
{
	struct rdma_netdev_alloc_params params;
	int rc;

	if (!device->ops.rdma_netdev_get_params)
		return -EOPNOTSUPP;

	rc = device->ops.rdma_netdev_get_params(device, port_num, type,
						&params);
	if (rc)
		return rc;

	return params.initialize_rdma_netdev(device, port_num,
					     netdev, params.param);
}
EXPORT_SYMBOL(rdma_init_netdev);

void __rdma_block_iter_start(struct ib_block_iter *biter,
			     struct scatterlist *sglist, unsigned int nents,
			     unsigned long pgsz)
{
	memset(biter, 0, sizeof(struct ib_block_iter));
	biter->__sg = sglist;
	biter->__sg_nents = nents;

	/* Driver provides best block size to use */
	biter->__pg_bit = __fls(pgsz);
}
EXPORT_SYMBOL(__rdma_block_iter_start);

bool __rdma_block_iter_next(struct ib_block_iter *biter)
{
	unsigned int block_offset;
	unsigned int sg_delta;

	if (!biter->__sg_nents || !biter->__sg)
		return false;

	biter->__dma_addr = sg_dma_address(biter->__sg) + biter->__sg_advance;
	block_offset = biter->__dma_addr & (BIT_ULL(biter->__pg_bit) - 1);
	sg_delta = BIT_ULL(biter->__pg_bit) - block_offset;

	if (sg_dma_len(biter->__sg) - biter->__sg_advance > sg_delta) {
		biter->__sg_advance += sg_delta;
	} else {
		biter->__sg_advance = 0;
		biter->__sg = sg_next(biter->__sg);
		biter->__sg_nents--;
	}

	return true;
}
EXPORT_SYMBOL(__rdma_block_iter_next);

/**
 * rdma_alloc_hw_stats_struct - Helper function to allocate dynamic struct
 *   for the drivers.
 * @descs: array of static descriptors
 * @num_counters: number of elements in array
 * @lifespan: milliseconds between updates
 */
struct rdma_hw_stats *rdma_alloc_hw_stats_struct(
	const struct rdma_stat_desc *descs, int num_counters,
	unsigned long lifespan)
{
	struct rdma_hw_stats *stats;

	stats = kzalloc(struct_size(stats, value, num_counters), GFP_KERNEL);
	if (!stats)
		return NULL;

	stats->is_disabled = kcalloc(BITS_TO_LONGS(num_counters),
				     sizeof(*stats->is_disabled), GFP_KERNEL);
	if (!stats->is_disabled)
		goto err;

	stats->descs = descs;
	stats->num_counters = num_counters;
	stats->lifespan = msecs_to_jiffies(lifespan);
	mutex_init(&stats->lock);

	return stats;

err:
	kfree(stats);
	return NULL;
}
EXPORT_SYMBOL(rdma_alloc_hw_stats_struct);

/**
 * rdma_free_hw_stats_struct - Helper function to release rdma_hw_stats
 * @stats: statistics to release
 */
void rdma_free_hw_stats_struct(struct rdma_hw_stats *stats)
{
	if (!stats)
		return;

	kfree(stats->is_disabled);
	kfree(stats);
}
EXPORT_SYMBOL(rdma_free_hw_stats_struct);