summaryrefslogtreecommitdiff
path: root/include/rdma/ib_verbs.h
blob: 6c5712ae559d8fb7d964553dbfad6c5b2b565d96 (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
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
/*
 * Copyright (c) 2004 Mellanox Technologies Ltd.  All rights reserved.
 * Copyright (c) 2004 Infinicon Corporation.  All rights reserved.
 * Copyright (c) 2004, 2020 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, 2007 Cisco Systems.  All rights reserved.
 */

#ifndef IB_VERBS_H
#define IB_VERBS_H

#include <linux/ethtool.h>
#include <linux/types.h>
#include <linux/device.h>
#include <linux/dma-mapping.h>
#include <linux/kref.h>
#include <linux/list.h>
#include <linux/rwsem.h>
#include <linux/workqueue.h>
#include <linux/irq_poll.h>
#include <uapi/linux/if_ether.h>
#include <net/ipv6.h>
#include <net/ip.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/refcount.h>
#include <linux/if_link.h>
#include <linux/atomic.h>
#include <linux/mmu_notifier.h>
#include <linux/uaccess.h>
#include <linux/cgroup_rdma.h>
#include <linux/irqflags.h>
#include <linux/preempt.h>
#include <linux/dim.h>
#include <uapi/rdma/ib_user_verbs.h>
#include <rdma/rdma_counter.h>
#include <rdma/restrack.h>
#include <rdma/signature.h>
#include <uapi/rdma/rdma_user_ioctl.h>
#include <uapi/rdma/ib_user_ioctl_verbs.h>

#define IB_FW_VERSION_NAME_MAX	ETHTOOL_FWVERS_LEN

struct ib_umem_odp;
struct ib_uqp_object;
struct ib_usrq_object;
struct ib_uwq_object;
struct rdma_cm_id;
struct ib_port;
struct hw_stats_device_data;

extern struct workqueue_struct *ib_wq;
extern struct workqueue_struct *ib_comp_wq;
extern struct workqueue_struct *ib_comp_unbound_wq;

struct ib_ucq_object;

__printf(3, 4) __cold
void ibdev_printk(const char *level, const struct ib_device *ibdev,
		  const char *format, ...);
__printf(2, 3) __cold
void ibdev_emerg(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_alert(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_crit(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_err(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_warn(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_notice(const struct ib_device *ibdev, const char *format, ...);
__printf(2, 3) __cold
void ibdev_info(const struct ib_device *ibdev, const char *format, ...);

#if defined(CONFIG_DYNAMIC_DEBUG) || \
	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
#define ibdev_dbg(__dev, format, args...)                       \
	dynamic_ibdev_dbg(__dev, format, ##args)
#else
__printf(2, 3) __cold
static inline
void ibdev_dbg(const struct ib_device *ibdev, const char *format, ...) {}
#endif

#define ibdev_level_ratelimited(ibdev_level, ibdev, fmt, ...)           \
do {                                                                    \
	static DEFINE_RATELIMIT_STATE(_rs,                              \
				      DEFAULT_RATELIMIT_INTERVAL,       \
				      DEFAULT_RATELIMIT_BURST);         \
	if (__ratelimit(&_rs))                                          \
		ibdev_level(ibdev, fmt, ##__VA_ARGS__);                 \
} while (0)

#define ibdev_emerg_ratelimited(ibdev, fmt, ...) \
	ibdev_level_ratelimited(ibdev_emerg, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_alert_ratelimited(ibdev, fmt, ...) \
	ibdev_level_ratelimited(ibdev_alert, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_crit_ratelimited(ibdev, fmt, ...) \
	ibdev_level_ratelimited(ibdev_crit, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_err_ratelimited(ibdev, fmt, ...) \
	ibdev_level_ratelimited(ibdev_err, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_warn_ratelimited(ibdev, fmt, ...) \
	ibdev_level_ratelimited(ibdev_warn, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_notice_ratelimited(ibdev, fmt, ...) \
	ibdev_level_ratelimited(ibdev_notice, ibdev, fmt, ##__VA_ARGS__)
#define ibdev_info_ratelimited(ibdev, fmt, ...) \
	ibdev_level_ratelimited(ibdev_info, ibdev, fmt, ##__VA_ARGS__)

#if defined(CONFIG_DYNAMIC_DEBUG) || \
	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
/* descriptor check is first to prevent flooding with "callbacks suppressed" */
#define ibdev_dbg_ratelimited(ibdev, fmt, ...)                          \
do {                                                                    \
	static DEFINE_RATELIMIT_STATE(_rs,                              \
				      DEFAULT_RATELIMIT_INTERVAL,       \
				      DEFAULT_RATELIMIT_BURST);         \
	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);                 \
	if (DYNAMIC_DEBUG_BRANCH(descriptor) && __ratelimit(&_rs))      \
		__dynamic_ibdev_dbg(&descriptor, ibdev, fmt,            \
				    ##__VA_ARGS__);                     \
} while (0)
#else
__printf(2, 3) __cold
static inline
void ibdev_dbg_ratelimited(const struct ib_device *ibdev, const char *format, ...) {}
#endif

union ib_gid {
	u8	raw[16];
	struct {
		__be64	subnet_prefix;
		__be64	interface_id;
	} global;
};

extern union ib_gid zgid;

enum ib_gid_type {
	IB_GID_TYPE_IB = IB_UVERBS_GID_TYPE_IB,
	IB_GID_TYPE_ROCE = IB_UVERBS_GID_TYPE_ROCE_V1,
	IB_GID_TYPE_ROCE_UDP_ENCAP = IB_UVERBS_GID_TYPE_ROCE_V2,
	IB_GID_TYPE_SIZE
};

#define ROCE_V2_UDP_DPORT      4791
struct ib_gid_attr {
	struct net_device __rcu	*ndev;
	struct ib_device	*device;
	union ib_gid		gid;
	enum ib_gid_type	gid_type;
	u16			index;
	u32			port_num;
};

enum {
	/* set the local administered indication */
	IB_SA_WELL_KNOWN_GUID	= BIT_ULL(57) | 2,
};

enum rdma_transport_type {
	RDMA_TRANSPORT_IB,
	RDMA_TRANSPORT_IWARP,
	RDMA_TRANSPORT_USNIC,
	RDMA_TRANSPORT_USNIC_UDP,
	RDMA_TRANSPORT_UNSPECIFIED,
};

enum rdma_protocol_type {
	RDMA_PROTOCOL_IB,
	RDMA_PROTOCOL_IBOE,
	RDMA_PROTOCOL_IWARP,
	RDMA_PROTOCOL_USNIC_UDP
};

__attribute_const__ enum rdma_transport_type
rdma_node_get_transport(unsigned int node_type);

enum rdma_network_type {
	RDMA_NETWORK_IB,
	RDMA_NETWORK_ROCE_V1,
	RDMA_NETWORK_IPV4,
	RDMA_NETWORK_IPV6
};

static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type network_type)
{
	if (network_type == RDMA_NETWORK_IPV4 ||
	    network_type == RDMA_NETWORK_IPV6)
		return IB_GID_TYPE_ROCE_UDP_ENCAP;
	else if (network_type == RDMA_NETWORK_ROCE_V1)
		return IB_GID_TYPE_ROCE;
	else
		return IB_GID_TYPE_IB;
}

static inline enum rdma_network_type
rdma_gid_attr_network_type(const struct ib_gid_attr *attr)
{
	if (attr->gid_type == IB_GID_TYPE_IB)
		return RDMA_NETWORK_IB;

	if (attr->gid_type == IB_GID_TYPE_ROCE)
		return RDMA_NETWORK_ROCE_V1;

	if (ipv6_addr_v4mapped((struct in6_addr *)&attr->gid))
		return RDMA_NETWORK_IPV4;
	else
		return RDMA_NETWORK_IPV6;
}

enum rdma_link_layer {
	IB_LINK_LAYER_UNSPECIFIED,
	IB_LINK_LAYER_INFINIBAND,
	IB_LINK_LAYER_ETHERNET,
};

enum ib_device_cap_flags {
	IB_DEVICE_RESIZE_MAX_WR = IB_UVERBS_DEVICE_RESIZE_MAX_WR,
	IB_DEVICE_BAD_PKEY_CNTR = IB_UVERBS_DEVICE_BAD_PKEY_CNTR,
	IB_DEVICE_BAD_QKEY_CNTR = IB_UVERBS_DEVICE_BAD_QKEY_CNTR,
	IB_DEVICE_RAW_MULTI = IB_UVERBS_DEVICE_RAW_MULTI,
	IB_DEVICE_AUTO_PATH_MIG = IB_UVERBS_DEVICE_AUTO_PATH_MIG,
	IB_DEVICE_CHANGE_PHY_PORT = IB_UVERBS_DEVICE_CHANGE_PHY_PORT,
	IB_DEVICE_UD_AV_PORT_ENFORCE = IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE,
	IB_DEVICE_CURR_QP_STATE_MOD = IB_UVERBS_DEVICE_CURR_QP_STATE_MOD,
	IB_DEVICE_SHUTDOWN_PORT = IB_UVERBS_DEVICE_SHUTDOWN_PORT,
	/* IB_DEVICE_INIT_TYPE = IB_UVERBS_DEVICE_INIT_TYPE, (not in use) */
	IB_DEVICE_PORT_ACTIVE_EVENT = IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT,
	IB_DEVICE_SYS_IMAGE_GUID = IB_UVERBS_DEVICE_SYS_IMAGE_GUID,
	IB_DEVICE_RC_RNR_NAK_GEN = IB_UVERBS_DEVICE_RC_RNR_NAK_GEN,
	IB_DEVICE_SRQ_RESIZE = IB_UVERBS_DEVICE_SRQ_RESIZE,
	IB_DEVICE_N_NOTIFY_CQ = IB_UVERBS_DEVICE_N_NOTIFY_CQ,

	/* Reserved, old SEND_W_INV = 1 << 16,*/
	IB_DEVICE_MEM_WINDOW = IB_UVERBS_DEVICE_MEM_WINDOW,
	/*
	 * Devices should set IB_DEVICE_UD_IP_SUM if they support
	 * insertion of UDP and TCP checksum on outgoing UD IPoIB
	 * messages and can verify the validity of checksum for
	 * incoming messages.  Setting this flag implies that the
	 * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode.
	 */
	IB_DEVICE_UD_IP_CSUM = IB_UVERBS_DEVICE_UD_IP_CSUM,
	IB_DEVICE_XRC = IB_UVERBS_DEVICE_XRC,

	/*
	 * This device supports the IB "base memory management extension",
	 * which includes support for fast registrations (IB_WR_REG_MR,
	 * IB_WR_LOCAL_INV and IB_WR_SEND_WITH_INV verbs).  This flag should
	 * also be set by any iWarp device which must support FRs to comply
	 * to the iWarp verbs spec.  iWarp devices also support the
	 * IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the
	 * stag.
	 */
	IB_DEVICE_MEM_MGT_EXTENSIONS = IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS,
	IB_DEVICE_MEM_WINDOW_TYPE_2A = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A,
	IB_DEVICE_MEM_WINDOW_TYPE_2B = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B,
	IB_DEVICE_RC_IP_CSUM = IB_UVERBS_DEVICE_RC_IP_CSUM,
	/* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */
	IB_DEVICE_RAW_IP_CSUM = IB_UVERBS_DEVICE_RAW_IP_CSUM,
	IB_DEVICE_MANAGED_FLOW_STEERING =
		IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING,
	/* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */
	IB_DEVICE_RAW_SCATTER_FCS = IB_UVERBS_DEVICE_RAW_SCATTER_FCS,
	/* The device supports padding incoming writes to cacheline. */
	IB_DEVICE_PCI_WRITE_END_PADDING =
		IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING,
	/* Placement type attributes */
	IB_DEVICE_FLUSH_GLOBAL = IB_UVERBS_DEVICE_FLUSH_GLOBAL,
	IB_DEVICE_FLUSH_PERSISTENT = IB_UVERBS_DEVICE_FLUSH_PERSISTENT,
	IB_DEVICE_ATOMIC_WRITE = IB_UVERBS_DEVICE_ATOMIC_WRITE,
};

enum ib_kernel_cap_flags {
	/*
	 * This device supports a per-device lkey or stag that can be
	 * used without performing a memory registration for the local
	 * memory.  Note that ULPs should never check this flag, but
	 * instead of use the local_dma_lkey flag in the ib_pd structure,
	 * which will always contain a usable lkey.
	 */
	IBK_LOCAL_DMA_LKEY = 1 << 0,
	/* IB_QP_CREATE_INTEGRITY_EN is supported to implement T10-PI */
	IBK_INTEGRITY_HANDOVER = 1 << 1,
	/* IB_ACCESS_ON_DEMAND is supported during reg_user_mr() */
	IBK_ON_DEMAND_PAGING = 1 << 2,
	/* IB_MR_TYPE_SG_GAPS is supported */
	IBK_SG_GAPS_REG = 1 << 3,
	/* Driver supports RDMA_NLDEV_CMD_DELLINK */
	IBK_ALLOW_USER_UNREG = 1 << 4,

	/* ipoib will use IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK */
	IBK_BLOCK_MULTICAST_LOOPBACK = 1 << 5,
	/* iopib will use IB_QP_CREATE_IPOIB_UD_LSO for its QPs */
	IBK_UD_TSO = 1 << 6,
	/* iopib will use the device ops:
	 *   get_vf_config
	 *   get_vf_guid
	 *   get_vf_stats
	 *   set_vf_guid
	 *   set_vf_link_state
	 */
	IBK_VIRTUAL_FUNCTION = 1 << 7,
	/* ipoib will use IB_QP_CREATE_NETDEV_USE for its QPs */
	IBK_RDMA_NETDEV_OPA = 1 << 8,
};

enum ib_atomic_cap {
	IB_ATOMIC_NONE,
	IB_ATOMIC_HCA,
	IB_ATOMIC_GLOB
};

enum ib_odp_general_cap_bits {
	IB_ODP_SUPPORT		= 1 << 0,
	IB_ODP_SUPPORT_IMPLICIT = 1 << 1,
};

enum ib_odp_transport_cap_bits {
	IB_ODP_SUPPORT_SEND	= 1 << 0,
	IB_ODP_SUPPORT_RECV	= 1 << 1,
	IB_ODP_SUPPORT_WRITE	= 1 << 2,
	IB_ODP_SUPPORT_READ	= 1 << 3,
	IB_ODP_SUPPORT_ATOMIC	= 1 << 4,
	IB_ODP_SUPPORT_SRQ_RECV	= 1 << 5,
};

struct ib_odp_caps {
	uint64_t general_caps;
	struct {
		uint32_t  rc_odp_caps;
		uint32_t  uc_odp_caps;
		uint32_t  ud_odp_caps;
		uint32_t  xrc_odp_caps;
	} per_transport_caps;
};

struct ib_rss_caps {
	/* Corresponding bit will be set if qp type from
	 * 'enum ib_qp_type' is supported, e.g.
	 * supported_qpts |= 1 << IB_QPT_UD
	 */
	u32 supported_qpts;
	u32 max_rwq_indirection_tables;
	u32 max_rwq_indirection_table_size;
};

enum ib_tm_cap_flags {
	/*  Support tag matching with rendezvous offload for RC transport */
	IB_TM_CAP_RNDV_RC = 1 << 0,
};

struct ib_tm_caps {
	/* Max size of RNDV header */
	u32 max_rndv_hdr_size;
	/* Max number of entries in tag matching list */
	u32 max_num_tags;
	/* From enum ib_tm_cap_flags */
	u32 flags;
	/* Max number of outstanding list operations */
	u32 max_ops;
	/* Max number of SGE in tag matching entry */
	u32 max_sge;
};

struct ib_cq_init_attr {
	unsigned int	cqe;
	u32		comp_vector;
	u32		flags;
};

enum ib_cq_attr_mask {
	IB_CQ_MODERATE = 1 << 0,
};

struct ib_cq_caps {
	u16     max_cq_moderation_count;
	u16     max_cq_moderation_period;
};

struct ib_dm_mr_attr {
	u64		length;
	u64		offset;
	u32		access_flags;
};

struct ib_dm_alloc_attr {
	u64	length;
	u32	alignment;
	u32	flags;
};

struct ib_device_attr {
	u64			fw_ver;
	__be64			sys_image_guid;
	u64			max_mr_size;
	u64			page_size_cap;
	u32			vendor_id;
	u32			vendor_part_id;
	u32			hw_ver;
	int			max_qp;
	int			max_qp_wr;
	u64			device_cap_flags;
	u64			kernel_cap_flags;
	int			max_send_sge;
	int			max_recv_sge;
	int			max_sge_rd;
	int			max_cq;
	int			max_cqe;
	int			max_mr;
	int			max_pd;
	int			max_qp_rd_atom;
	int			max_ee_rd_atom;
	int			max_res_rd_atom;
	int			max_qp_init_rd_atom;
	int			max_ee_init_rd_atom;
	enum ib_atomic_cap	atomic_cap;
	enum ib_atomic_cap	masked_atomic_cap;
	int			max_ee;
	int			max_rdd;
	int			max_mw;
	int			max_raw_ipv6_qp;
	int			max_raw_ethy_qp;
	int			max_mcast_grp;
	int			max_mcast_qp_attach;
	int			max_total_mcast_qp_attach;
	int			max_ah;
	int			max_srq;
	int			max_srq_wr;
	int			max_srq_sge;
	unsigned int		max_fast_reg_page_list_len;
	unsigned int		max_pi_fast_reg_page_list_len;
	u16			max_pkeys;
	u8			local_ca_ack_delay;
	int			sig_prot_cap;
	int			sig_guard_cap;
	struct ib_odp_caps	odp_caps;
	uint64_t		timestamp_mask;
	uint64_t		hca_core_clock; /* in KHZ */
	struct ib_rss_caps	rss_caps;
	u32			max_wq_type_rq;
	u32			raw_packet_caps; /* Use ib_raw_packet_caps enum */
	struct ib_tm_caps	tm_caps;
	struct ib_cq_caps       cq_caps;
	u64			max_dm_size;
	/* Max entries for sgl for optimized performance per READ */
	u32			max_sgl_rd;
};

enum ib_mtu {
	IB_MTU_256  = 1,
	IB_MTU_512  = 2,
	IB_MTU_1024 = 3,
	IB_MTU_2048 = 4,
	IB_MTU_4096 = 5
};

enum opa_mtu {
	OPA_MTU_8192 = 6,
	OPA_MTU_10240 = 7
};

static inline int ib_mtu_enum_to_int(enum ib_mtu mtu)
{
	switch (mtu) {
	case IB_MTU_256:  return  256;
	case IB_MTU_512:  return  512;
	case IB_MTU_1024: return 1024;
	case IB_MTU_2048: return 2048;
	case IB_MTU_4096: return 4096;
	default: 	  return -1;
	}
}

static inline enum ib_mtu ib_mtu_int_to_enum(int mtu)
{
	if (mtu >= 4096)
		return IB_MTU_4096;
	else if (mtu >= 2048)
		return IB_MTU_2048;
	else if (mtu >= 1024)
		return IB_MTU_1024;
	else if (mtu >= 512)
		return IB_MTU_512;
	else
		return IB_MTU_256;
}

static inline int opa_mtu_enum_to_int(enum opa_mtu mtu)
{
	switch (mtu) {
	case OPA_MTU_8192:
		return 8192;
	case OPA_MTU_10240:
		return 10240;
	default:
		return(ib_mtu_enum_to_int((enum ib_mtu)mtu));
	}
}

static inline enum opa_mtu opa_mtu_int_to_enum(int mtu)
{
	if (mtu >= 10240)
		return OPA_MTU_10240;
	else if (mtu >= 8192)
		return OPA_MTU_8192;
	else
		return ((enum opa_mtu)ib_mtu_int_to_enum(mtu));
}

enum ib_port_state {
	IB_PORT_NOP		= 0,
	IB_PORT_DOWN		= 1,
	IB_PORT_INIT		= 2,
	IB_PORT_ARMED		= 3,
	IB_PORT_ACTIVE		= 4,
	IB_PORT_ACTIVE_DEFER	= 5
};

enum ib_port_phys_state {
	IB_PORT_PHYS_STATE_SLEEP = 1,
	IB_PORT_PHYS_STATE_POLLING = 2,
	IB_PORT_PHYS_STATE_DISABLED = 3,
	IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING = 4,
	IB_PORT_PHYS_STATE_LINK_UP = 5,
	IB_PORT_PHYS_STATE_LINK_ERROR_RECOVERY = 6,
	IB_PORT_PHYS_STATE_PHY_TEST = 7,
};

enum ib_port_width {
	IB_WIDTH_1X	= 1,
	IB_WIDTH_2X	= 16,
	IB_WIDTH_4X	= 2,
	IB_WIDTH_8X	= 4,
	IB_WIDTH_12X	= 8
};

static inline int ib_width_enum_to_int(enum ib_port_width width)
{
	switch (width) {
	case IB_WIDTH_1X:  return  1;
	case IB_WIDTH_2X:  return  2;
	case IB_WIDTH_4X:  return  4;
	case IB_WIDTH_8X:  return  8;
	case IB_WIDTH_12X: return 12;
	default: 	  return -1;
	}
}

enum ib_port_speed {
	IB_SPEED_SDR	= 1,
	IB_SPEED_DDR	= 2,
	IB_SPEED_QDR	= 4,
	IB_SPEED_FDR10	= 8,
	IB_SPEED_FDR	= 16,
	IB_SPEED_EDR	= 32,
	IB_SPEED_HDR	= 64,
	IB_SPEED_NDR	= 128,
	IB_SPEED_XDR	= 256,
};

enum ib_stat_flag {
	IB_STAT_FLAG_OPTIONAL = 1 << 0,
};

/**
 * struct rdma_stat_desc
 * @name - The name of the counter
 * @flags - Flags of the counter; For example, IB_STAT_FLAG_OPTIONAL
 * @priv - Driver private information; Core code should not use
 */
struct rdma_stat_desc {
	const char *name;
	unsigned int flags;
	const void *priv;
};

/**
 * struct rdma_hw_stats
 * @lock - Mutex to protect parallel write access to lifespan and values
 *    of counters, which are 64bits and not guaranteed to be written
 *    atomicaly on 32bits systems.
 * @timestamp - Used by the core code to track when the last update was
 * @lifespan - Used by the core code to determine how old the counters
 *   should be before being updated again.  Stored in jiffies, defaults
 *   to 10 milliseconds, drivers can override the default be specifying
 *   their own value during their allocation routine.
 * @descs - Array of pointers to static descriptors used for the counters
 *   in directory.
 * @is_disabled - A bitmap to indicate each counter is currently disabled
 *   or not.
 * @num_counters - How many hardware counters there are.  If name is
 *   shorter than this number, a kernel oops will result.  Driver authors
 *   are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters)
 *   in their code to prevent this.
 * @value - Array of u64 counters that are accessed by the sysfs code and
 *   filled in by the drivers get_stats routine
 */
struct rdma_hw_stats {
	struct mutex	lock; /* Protect lifespan and values[] */
	unsigned long	timestamp;
	unsigned long	lifespan;
	const struct rdma_stat_desc *descs;
	unsigned long	*is_disabled;
	int		num_counters;
	u64		value[] __counted_by(num_counters);
};

#define RDMA_HW_STATS_DEFAULT_LIFESPAN 10

struct rdma_hw_stats *rdma_alloc_hw_stats_struct(
	const struct rdma_stat_desc *descs, int num_counters,
	unsigned long lifespan);

void rdma_free_hw_stats_struct(struct rdma_hw_stats *stats);

/* Define bits for the various functionality this port needs to be supported by
 * the core.
 */
/* Management                           0x00000FFF */
#define RDMA_CORE_CAP_IB_MAD            0x00000001
#define RDMA_CORE_CAP_IB_SMI            0x00000002
#define RDMA_CORE_CAP_IB_CM             0x00000004
#define RDMA_CORE_CAP_IW_CM             0x00000008
#define RDMA_CORE_CAP_IB_SA             0x00000010
#define RDMA_CORE_CAP_OPA_MAD           0x00000020

/* Address format                       0x000FF000 */
#define RDMA_CORE_CAP_AF_IB             0x00001000
#define RDMA_CORE_CAP_ETH_AH            0x00002000
#define RDMA_CORE_CAP_OPA_AH            0x00004000
#define RDMA_CORE_CAP_IB_GRH_REQUIRED   0x00008000

/* Protocol                             0xFFF00000 */
#define RDMA_CORE_CAP_PROT_IB           0x00100000
#define RDMA_CORE_CAP_PROT_ROCE         0x00200000
#define RDMA_CORE_CAP_PROT_IWARP        0x00400000
#define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000
#define RDMA_CORE_CAP_PROT_RAW_PACKET   0x01000000
#define RDMA_CORE_CAP_PROT_USNIC        0x02000000

#define RDMA_CORE_PORT_IB_GRH_REQUIRED (RDMA_CORE_CAP_IB_GRH_REQUIRED \
					| RDMA_CORE_CAP_PROT_ROCE     \
					| RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP)

#define RDMA_CORE_PORT_IBA_IB          (RDMA_CORE_CAP_PROT_IB  \
					| RDMA_CORE_CAP_IB_MAD \
					| RDMA_CORE_CAP_IB_SMI \
					| RDMA_CORE_CAP_IB_CM  \
					| RDMA_CORE_CAP_IB_SA  \
					| RDMA_CORE_CAP_AF_IB)
#define RDMA_CORE_PORT_IBA_ROCE        (RDMA_CORE_CAP_PROT_ROCE \
					| RDMA_CORE_CAP_IB_MAD  \
					| RDMA_CORE_CAP_IB_CM   \
					| RDMA_CORE_CAP_AF_IB   \
					| RDMA_CORE_CAP_ETH_AH)
#define RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP			\
					(RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP \
					| RDMA_CORE_CAP_IB_MAD  \
					| RDMA_CORE_CAP_IB_CM   \
					| RDMA_CORE_CAP_AF_IB   \
					| RDMA_CORE_CAP_ETH_AH)
#define RDMA_CORE_PORT_IWARP           (RDMA_CORE_CAP_PROT_IWARP \
					| RDMA_CORE_CAP_IW_CM)
#define RDMA_CORE_PORT_INTEL_OPA       (RDMA_CORE_PORT_IBA_IB  \
					| RDMA_CORE_CAP_OPA_MAD)

#define RDMA_CORE_PORT_RAW_PACKET	(RDMA_CORE_CAP_PROT_RAW_PACKET)

#define RDMA_CORE_PORT_USNIC		(RDMA_CORE_CAP_PROT_USNIC)

struct ib_port_attr {
	u64			subnet_prefix;
	enum ib_port_state	state;
	enum ib_mtu		max_mtu;
	enum ib_mtu		active_mtu;
	u32                     phys_mtu;
	int			gid_tbl_len;
	unsigned int		ip_gids:1;
	/* This is the value from PortInfo CapabilityMask, defined by IBA */
	u32			port_cap_flags;
	u32			max_msg_sz;
	u32			bad_pkey_cntr;
	u32			qkey_viol_cntr;
	u16			pkey_tbl_len;
	u32			sm_lid;
	u32			lid;
	u8			lmc;
	u8			max_vl_num;
	u8			sm_sl;
	u8			subnet_timeout;
	u8			init_type_reply;
	u8			active_width;
	u16			active_speed;
	u8                      phys_state;
	u16			port_cap_flags2;
};

enum ib_device_modify_flags {
	IB_DEVICE_MODIFY_SYS_IMAGE_GUID	= 1 << 0,
	IB_DEVICE_MODIFY_NODE_DESC	= 1 << 1
};

#define IB_DEVICE_NODE_DESC_MAX 64

struct ib_device_modify {
	u64	sys_image_guid;
	char	node_desc[IB_DEVICE_NODE_DESC_MAX];
};

enum ib_port_modify_flags {
	IB_PORT_SHUTDOWN		= 1,
	IB_PORT_INIT_TYPE		= (1<<2),
	IB_PORT_RESET_QKEY_CNTR		= (1<<3),
	IB_PORT_OPA_MASK_CHG		= (1<<4)
};

struct ib_port_modify {
	u32	set_port_cap_mask;
	u32	clr_port_cap_mask;
	u8	init_type;
};

enum ib_event_type {
	IB_EVENT_CQ_ERR,
	IB_EVENT_QP_FATAL,
	IB_EVENT_QP_REQ_ERR,
	IB_EVENT_QP_ACCESS_ERR,
	IB_EVENT_COMM_EST,
	IB_EVENT_SQ_DRAINED,
	IB_EVENT_PATH_MIG,
	IB_EVENT_PATH_MIG_ERR,
	IB_EVENT_DEVICE_FATAL,
	IB_EVENT_PORT_ACTIVE,
	IB_EVENT_PORT_ERR,
	IB_EVENT_LID_CHANGE,
	IB_EVENT_PKEY_CHANGE,
	IB_EVENT_SM_CHANGE,
	IB_EVENT_SRQ_ERR,
	IB_EVENT_SRQ_LIMIT_REACHED,
	IB_EVENT_QP_LAST_WQE_REACHED,
	IB_EVENT_CLIENT_REREGISTER,
	IB_EVENT_GID_CHANGE,
	IB_EVENT_WQ_FATAL,
};

const char *__attribute_const__ ib_event_msg(enum ib_event_type event);

struct ib_event {
	struct ib_device	*device;
	union {
		struct ib_cq	*cq;
		struct ib_qp	*qp;
		struct ib_srq	*srq;
		struct ib_wq	*wq;
		u32		port_num;
	} element;
	enum ib_event_type	event;
};

struct ib_event_handler {
	struct ib_device *device;
	void            (*handler)(struct ib_event_handler *, struct ib_event *);
	struct list_head  list;
};

#define INIT_IB_EVENT_HANDLER(_ptr, _device, _handler)		\
	do {							\
		(_ptr)->device  = _device;			\
		(_ptr)->handler = _handler;			\
		INIT_LIST_HEAD(&(_ptr)->list);			\
	} while (0)

struct ib_global_route {
	const struct ib_gid_attr *sgid_attr;
	union ib_gid	dgid;
	u32		flow_label;
	u8		sgid_index;
	u8		hop_limit;
	u8		traffic_class;
};

struct ib_grh {
	__be32		version_tclass_flow;
	__be16		paylen;
	u8		next_hdr;
	u8		hop_limit;
	union ib_gid	sgid;
	union ib_gid	dgid;
};

union rdma_network_hdr {
	struct ib_grh ibgrh;
	struct {
		/* The IB spec states that if it's IPv4, the header
		 * is located in the last 20 bytes of the header.
		 */
		u8		reserved[20];
		struct iphdr	roce4grh;
	};
};

#define IB_QPN_MASK		0xFFFFFF

enum {
	IB_MULTICAST_QPN = 0xffffff
};

#define IB_LID_PERMISSIVE	cpu_to_be16(0xFFFF)
#define IB_MULTICAST_LID_BASE	cpu_to_be16(0xC000)

enum ib_ah_flags {
	IB_AH_GRH	= 1
};

enum ib_rate {
	IB_RATE_PORT_CURRENT = 0,
	IB_RATE_2_5_GBPS = 2,
	IB_RATE_5_GBPS   = 5,
	IB_RATE_10_GBPS  = 3,
	IB_RATE_20_GBPS  = 6,
	IB_RATE_30_GBPS  = 4,
	IB_RATE_40_GBPS  = 7,
	IB_RATE_60_GBPS  = 8,
	IB_RATE_80_GBPS  = 9,
	IB_RATE_120_GBPS = 10,
	IB_RATE_14_GBPS  = 11,
	IB_RATE_56_GBPS  = 12,
	IB_RATE_112_GBPS = 13,
	IB_RATE_168_GBPS = 14,
	IB_RATE_25_GBPS  = 15,
	IB_RATE_100_GBPS = 16,
	IB_RATE_200_GBPS = 17,
	IB_RATE_300_GBPS = 18,
	IB_RATE_28_GBPS  = 19,
	IB_RATE_50_GBPS  = 20,
	IB_RATE_400_GBPS = 21,
	IB_RATE_600_GBPS = 22,
	IB_RATE_800_GBPS = 23,
};

/**
 * ib_rate_to_mult - Convert the IB rate enum to a multiple of the
 * base rate of 2.5 Gbit/sec.  For example, IB_RATE_5_GBPS will be
 * converted to 2, since 5 Gbit/sec is 2 * 2.5 Gbit/sec.
 * @rate: rate to convert.
 */
__attribute_const__ int ib_rate_to_mult(enum ib_rate rate);

/**
 * ib_rate_to_mbps - Convert the IB rate enum to Mbps.
 * For example, IB_RATE_2_5_GBPS will be converted to 2500.
 * @rate: rate to convert.
 */
__attribute_const__ int ib_rate_to_mbps(enum ib_rate rate);


/**
 * enum ib_mr_type - memory region type
 * @IB_MR_TYPE_MEM_REG:       memory region that is used for
 *                            normal registration
 * @IB_MR_TYPE_SG_GAPS:       memory region that is capable to
 *                            register any arbitrary sg lists (without
 *                            the normal mr constraints - see
 *                            ib_map_mr_sg)
 * @IB_MR_TYPE_DM:            memory region that is used for device
 *                            memory registration
 * @IB_MR_TYPE_USER:          memory region that is used for the user-space
 *                            application
 * @IB_MR_TYPE_DMA:           memory region that is used for DMA operations
 *                            without address translations (VA=PA)
 * @IB_MR_TYPE_INTEGRITY:     memory region that is used for
 *                            data integrity operations
 */
enum ib_mr_type {
	IB_MR_TYPE_MEM_REG,
	IB_MR_TYPE_SG_GAPS,
	IB_MR_TYPE_DM,
	IB_MR_TYPE_USER,
	IB_MR_TYPE_DMA,
	IB_MR_TYPE_INTEGRITY,
};

enum ib_mr_status_check {
	IB_MR_CHECK_SIG_STATUS = 1,
};

/**
 * struct ib_mr_status - Memory region status container
 *
 * @fail_status: Bitmask of MR checks status. For each
 *     failed check a corresponding status bit is set.
 * @sig_err: Additional info for IB_MR_CEHCK_SIG_STATUS
 *     failure.
 */
struct ib_mr_status {
	u32		    fail_status;
	struct ib_sig_err   sig_err;
};

/**
 * mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate
 * enum.
 * @mult: multiple to convert.
 */
__attribute_const__ enum ib_rate mult_to_ib_rate(int mult);

struct rdma_ah_init_attr {
	struct rdma_ah_attr *ah_attr;
	u32 flags;
	struct net_device *xmit_slave;
};

enum rdma_ah_attr_type {
	RDMA_AH_ATTR_TYPE_UNDEFINED,
	RDMA_AH_ATTR_TYPE_IB,
	RDMA_AH_ATTR_TYPE_ROCE,
	RDMA_AH_ATTR_TYPE_OPA,
};

struct ib_ah_attr {
	u16			dlid;
	u8			src_path_bits;
};

struct roce_ah_attr {
	u8			dmac[ETH_ALEN];
};

struct opa_ah_attr {
	u32			dlid;
	u8			src_path_bits;
	bool			make_grd;
};

struct rdma_ah_attr {
	struct ib_global_route	grh;
	u8			sl;
	u8			static_rate;
	u32			port_num;
	u8			ah_flags;
	enum rdma_ah_attr_type type;
	union {
		struct ib_ah_attr ib;
		struct roce_ah_attr roce;
		struct opa_ah_attr opa;
	};
};

enum ib_wc_status {
	IB_WC_SUCCESS,
	IB_WC_LOC_LEN_ERR,
	IB_WC_LOC_QP_OP_ERR,
	IB_WC_LOC_EEC_OP_ERR,
	IB_WC_LOC_PROT_ERR,
	IB_WC_WR_FLUSH_ERR,
	IB_WC_MW_BIND_ERR,
	IB_WC_BAD_RESP_ERR,
	IB_WC_LOC_ACCESS_ERR,
	IB_WC_REM_INV_REQ_ERR,
	IB_WC_REM_ACCESS_ERR,
	IB_WC_REM_OP_ERR,
	IB_WC_RETRY_EXC_ERR,
	IB_WC_RNR_RETRY_EXC_ERR,
	IB_WC_LOC_RDD_VIOL_ERR,
	IB_WC_REM_INV_RD_REQ_ERR,
	IB_WC_REM_ABORT_ERR,
	IB_WC_INV_EECN_ERR,
	IB_WC_INV_EEC_STATE_ERR,
	IB_WC_FATAL_ERR,
	IB_WC_RESP_TIMEOUT_ERR,
	IB_WC_GENERAL_ERR
};

const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status);

enum ib_wc_opcode {
	IB_WC_SEND = IB_UVERBS_WC_SEND,
	IB_WC_RDMA_WRITE = IB_UVERBS_WC_RDMA_WRITE,
	IB_WC_RDMA_READ = IB_UVERBS_WC_RDMA_READ,
	IB_WC_COMP_SWAP = IB_UVERBS_WC_COMP_SWAP,
	IB_WC_FETCH_ADD = IB_UVERBS_WC_FETCH_ADD,
	IB_WC_BIND_MW = IB_UVERBS_WC_BIND_MW,
	IB_WC_LOCAL_INV = IB_UVERBS_WC_LOCAL_INV,
	IB_WC_LSO = IB_UVERBS_WC_TSO,
	IB_WC_ATOMIC_WRITE = IB_UVERBS_WC_ATOMIC_WRITE,
	IB_WC_REG_MR,
	IB_WC_MASKED_COMP_SWAP,
	IB_WC_MASKED_FETCH_ADD,
	IB_WC_FLUSH = IB_UVERBS_WC_FLUSH,
/*
 * Set value of IB_WC_RECV so consumers can test if a completion is a
 * receive by testing (opcode & IB_WC_RECV).
 */
	IB_WC_RECV			= 1 << 7,
	IB_WC_RECV_RDMA_WITH_IMM
};

enum ib_wc_flags {
	IB_WC_GRH		= 1,
	IB_WC_WITH_IMM		= (1<<1),
	IB_WC_WITH_INVALIDATE	= (1<<2),
	IB_WC_IP_CSUM_OK	= (1<<3),
	IB_WC_WITH_SMAC		= (1<<4),
	IB_WC_WITH_VLAN		= (1<<5),
	IB_WC_WITH_NETWORK_HDR_TYPE	= (1<<6),
};

struct ib_wc {
	union {
		u64		wr_id;
		struct ib_cqe	*wr_cqe;
	};
	enum ib_wc_status	status;
	enum ib_wc_opcode	opcode;
	u32			vendor_err;
	u32			byte_len;
	struct ib_qp	       *qp;
	union {
		__be32		imm_data;
		u32		invalidate_rkey;
	} ex;
	u32			src_qp;
	u32			slid;
	int			wc_flags;
	u16			pkey_index;
	u8			sl;
	u8			dlid_path_bits;
	u32 port_num; /* valid only for DR SMPs on switches */
	u8			smac[ETH_ALEN];
	u16			vlan_id;
	u8			network_hdr_type;
};

enum ib_cq_notify_flags {
	IB_CQ_SOLICITED			= 1 << 0,
	IB_CQ_NEXT_COMP			= 1 << 1,
	IB_CQ_SOLICITED_MASK		= IB_CQ_SOLICITED | IB_CQ_NEXT_COMP,
	IB_CQ_REPORT_MISSED_EVENTS	= 1 << 2,
};

enum ib_srq_type {
	IB_SRQT_BASIC = IB_UVERBS_SRQT_BASIC,
	IB_SRQT_XRC = IB_UVERBS_SRQT_XRC,
	IB_SRQT_TM = IB_UVERBS_SRQT_TM,
};

static inline bool ib_srq_has_cq(enum ib_srq_type srq_type)
{
	return srq_type == IB_SRQT_XRC ||
	       srq_type == IB_SRQT_TM;
}

enum ib_srq_attr_mask {
	IB_SRQ_MAX_WR	= 1 << 0,
	IB_SRQ_LIMIT	= 1 << 1,
};

struct ib_srq_attr {
	u32	max_wr;
	u32	max_sge;
	u32	srq_limit;
};

struct ib_srq_init_attr {
	void		      (*event_handler)(struct ib_event *, void *);
	void		       *srq_context;
	struct ib_srq_attr	attr;
	enum ib_srq_type	srq_type;

	struct {
		struct ib_cq   *cq;
		union {
			struct {
				struct ib_xrcd *xrcd;
			} xrc;

			struct {
				u32		max_num_tags;
			} tag_matching;
		};
	} ext;
};

struct ib_qp_cap {
	u32	max_send_wr;
	u32	max_recv_wr;
	u32	max_send_sge;
	u32	max_recv_sge;
	u32	max_inline_data;

	/*
	 * Maximum number of rdma_rw_ctx structures in flight at a time.
	 * ib_create_qp() will calculate the right amount of needed WRs
	 * and MRs based on this.
	 */
	u32	max_rdma_ctxs;
};

enum ib_sig_type {
	IB_SIGNAL_ALL_WR,
	IB_SIGNAL_REQ_WR
};

enum ib_qp_type {
	/*
	 * IB_QPT_SMI and IB_QPT_GSI have to be the first two entries
	 * here (and in that order) since the MAD layer uses them as
	 * indices into a 2-entry table.
	 */
	IB_QPT_SMI,
	IB_QPT_GSI,

	IB_QPT_RC = IB_UVERBS_QPT_RC,
	IB_QPT_UC = IB_UVERBS_QPT_UC,
	IB_QPT_UD = IB_UVERBS_QPT_UD,
	IB_QPT_RAW_IPV6,
	IB_QPT_RAW_ETHERTYPE,
	IB_QPT_RAW_PACKET = IB_UVERBS_QPT_RAW_PACKET,
	IB_QPT_XRC_INI = IB_UVERBS_QPT_XRC_INI,
	IB_QPT_XRC_TGT = IB_UVERBS_QPT_XRC_TGT,
	IB_QPT_MAX,
	IB_QPT_DRIVER = IB_UVERBS_QPT_DRIVER,
	/* Reserve a range for qp types internal to the low level driver.
	 * These qp types will not be visible at the IB core layer, so the
	 * IB_QPT_MAX usages should not be affected in the core layer
	 */
	IB_QPT_RESERVED1 = 0x1000,
	IB_QPT_RESERVED2,
	IB_QPT_RESERVED3,
	IB_QPT_RESERVED4,
	IB_QPT_RESERVED5,
	IB_QPT_RESERVED6,
	IB_QPT_RESERVED7,
	IB_QPT_RESERVED8,
	IB_QPT_RESERVED9,
	IB_QPT_RESERVED10,
};

enum ib_qp_create_flags {
	IB_QP_CREATE_IPOIB_UD_LSO		= 1 << 0,
	IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK	=
		IB_UVERBS_QP_CREATE_BLOCK_MULTICAST_LOOPBACK,
	IB_QP_CREATE_CROSS_CHANNEL              = 1 << 2,
	IB_QP_CREATE_MANAGED_SEND               = 1 << 3,
	IB_QP_CREATE_MANAGED_RECV               = 1 << 4,
	IB_QP_CREATE_NETIF_QP			= 1 << 5,
	IB_QP_CREATE_INTEGRITY_EN		= 1 << 6,
	IB_QP_CREATE_NETDEV_USE			= 1 << 7,
	IB_QP_CREATE_SCATTER_FCS		=
		IB_UVERBS_QP_CREATE_SCATTER_FCS,
	IB_QP_CREATE_CVLAN_STRIPPING		=
		IB_UVERBS_QP_CREATE_CVLAN_STRIPPING,
	IB_QP_CREATE_SOURCE_QPN			= 1 << 10,
	IB_QP_CREATE_PCI_WRITE_END_PADDING	=
		IB_UVERBS_QP_CREATE_PCI_WRITE_END_PADDING,
	/* reserve bits 26-31 for low level drivers' internal use */
	IB_QP_CREATE_RESERVED_START		= 1 << 26,
	IB_QP_CREATE_RESERVED_END		= 1 << 31,
};

/*
 * Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler
 * callback to destroy the passed in QP.
 */

struct ib_qp_init_attr {
	/* This callback occurs in workqueue context */
	void                  (*event_handler)(struct ib_event *, void *);

	void		       *qp_context;
	struct ib_cq	       *send_cq;
	struct ib_cq	       *recv_cq;
	struct ib_srq	       *srq;
	struct ib_xrcd	       *xrcd;     /* XRC TGT QPs only */
	struct ib_qp_cap	cap;
	enum ib_sig_type	sq_sig_type;
	enum ib_qp_type		qp_type;
	u32			create_flags;

	/*
	 * Only needed for special QP types, or when using the RW API.
	 */
	u32			port_num;
	struct ib_rwq_ind_table *rwq_ind_tbl;
	u32			source_qpn;
};

struct ib_qp_open_attr {
	void                  (*event_handler)(struct ib_event *, void *);
	void		       *qp_context;
	u32			qp_num;
	enum ib_qp_type		qp_type;
};

enum ib_rnr_timeout {
	IB_RNR_TIMER_655_36 =  0,
	IB_RNR_TIMER_000_01 =  1,
	IB_RNR_TIMER_000_02 =  2,
	IB_RNR_TIMER_000_03 =  3,
	IB_RNR_TIMER_000_04 =  4,
	IB_RNR_TIMER_000_06 =  5,
	IB_RNR_TIMER_000_08 =  6,
	IB_RNR_TIMER_000_12 =  7,
	IB_RNR_TIMER_000_16 =  8,
	IB_RNR_TIMER_000_24 =  9,
	IB_RNR_TIMER_000_32 = 10,
	IB_RNR_TIMER_000_48 = 11,
	IB_RNR_TIMER_000_64 = 12,
	IB_RNR_TIMER_000_96 = 13,
	IB_RNR_TIMER_001_28 = 14,
	IB_RNR_TIMER_001_92 = 15,
	IB_RNR_TIMER_002_56 = 16,
	IB_RNR_TIMER_003_84 = 17,
	IB_RNR_TIMER_005_12 = 18,
	IB_RNR_TIMER_007_68 = 19,
	IB_RNR_TIMER_010_24 = 20,
	IB_RNR_TIMER_015_36 = 21,
	IB_RNR_TIMER_020_48 = 22,
	IB_RNR_TIMER_030_72 = 23,
	IB_RNR_TIMER_040_96 = 24,
	IB_RNR_TIMER_061_44 = 25,
	IB_RNR_TIMER_081_92 = 26,
	IB_RNR_TIMER_122_88 = 27,
	IB_RNR_TIMER_163_84 = 28,
	IB_RNR_TIMER_245_76 = 29,
	IB_RNR_TIMER_327_68 = 30,
	IB_RNR_TIMER_491_52 = 31
};

enum ib_qp_attr_mask {
	IB_QP_STATE			= 1,
	IB_QP_CUR_STATE			= (1<<1),
	IB_QP_EN_SQD_ASYNC_NOTIFY	= (1<<2),
	IB_QP_ACCESS_FLAGS		= (1<<3),
	IB_QP_PKEY_INDEX		= (1<<4),
	IB_QP_PORT			= (1<<5),
	IB_QP_QKEY			= (1<<6),
	IB_QP_AV			= (1<<7),
	IB_QP_PATH_MTU			= (1<<8),
	IB_QP_TIMEOUT			= (1<<9),
	IB_QP_RETRY_CNT			= (1<<10),
	IB_QP_RNR_RETRY			= (1<<11),
	IB_QP_RQ_PSN			= (1<<12),
	IB_QP_MAX_QP_RD_ATOMIC		= (1<<13),
	IB_QP_ALT_PATH			= (1<<14),
	IB_QP_MIN_RNR_TIMER		= (1<<15),
	IB_QP_SQ_PSN			= (1<<16),
	IB_QP_MAX_DEST_RD_ATOMIC	= (1<<17),
	IB_QP_PATH_MIG_STATE		= (1<<18),
	IB_QP_CAP			= (1<<19),
	IB_QP_DEST_QPN			= (1<<20),
	IB_QP_RESERVED1			= (1<<21),
	IB_QP_RESERVED2			= (1<<22),
	IB_QP_RESERVED3			= (1<<23),
	IB_QP_RESERVED4			= (1<<24),
	IB_QP_RATE_LIMIT		= (1<<25),

	IB_QP_ATTR_STANDARD_BITS = GENMASK(20, 0),
};

enum ib_qp_state {
	IB_QPS_RESET,
	IB_QPS_INIT,
	IB_QPS_RTR,
	IB_QPS_RTS,
	IB_QPS_SQD,
	IB_QPS_SQE,
	IB_QPS_ERR
};

enum ib_mig_state {
	IB_MIG_MIGRATED,
	IB_MIG_REARM,
	IB_MIG_ARMED
};

enum ib_mw_type {
	IB_MW_TYPE_1 = 1,
	IB_MW_TYPE_2 = 2
};

struct ib_qp_attr {
	enum ib_qp_state	qp_state;
	enum ib_qp_state	cur_qp_state;
	enum ib_mtu		path_mtu;
	enum ib_mig_state	path_mig_state;
	u32			qkey;
	u32			rq_psn;
	u32			sq_psn;
	u32			dest_qp_num;
	int			qp_access_flags;
	struct ib_qp_cap	cap;
	struct rdma_ah_attr	ah_attr;
	struct rdma_ah_attr	alt_ah_attr;
	u16			pkey_index;
	u16			alt_pkey_index;
	u8			en_sqd_async_notify;
	u8			sq_draining;
	u8			max_rd_atomic;
	u8			max_dest_rd_atomic;
	u8			min_rnr_timer;
	u32			port_num;
	u8			timeout;
	u8			retry_cnt;
	u8			rnr_retry;
	u32			alt_port_num;
	u8			alt_timeout;
	u32			rate_limit;
	struct net_device	*xmit_slave;
};

enum ib_wr_opcode {
	/* These are shared with userspace */
	IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE,
	IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM,
	IB_WR_SEND = IB_UVERBS_WR_SEND,
	IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM,
	IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ,
	IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP,
	IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD,
	IB_WR_BIND_MW = IB_UVERBS_WR_BIND_MW,
	IB_WR_LSO = IB_UVERBS_WR_TSO,
	IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV,
	IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV,
	IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV,
	IB_WR_MASKED_ATOMIC_CMP_AND_SWP =
		IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP,
	IB_WR_MASKED_ATOMIC_FETCH_AND_ADD =
		IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD,
	IB_WR_FLUSH = IB_UVERBS_WR_FLUSH,
	IB_WR_ATOMIC_WRITE = IB_UVERBS_WR_ATOMIC_WRITE,

	/* These are kernel only and can not be issued by userspace */
	IB_WR_REG_MR = 0x20,
	IB_WR_REG_MR_INTEGRITY,

	/* reserve values for low level drivers' internal use.
	 * These values will not be used at all in the ib core layer.
	 */
	IB_WR_RESERVED1 = 0xf0,
	IB_WR_RESERVED2,
	IB_WR_RESERVED3,
	IB_WR_RESERVED4,
	IB_WR_RESERVED5,
	IB_WR_RESERVED6,
	IB_WR_RESERVED7,
	IB_WR_RESERVED8,
	IB_WR_RESERVED9,
	IB_WR_RESERVED10,
};

enum ib_send_flags {
	IB_SEND_FENCE		= 1,
	IB_SEND_SIGNALED	= (1<<1),
	IB_SEND_SOLICITED	= (1<<2),
	IB_SEND_INLINE		= (1<<3),
	IB_SEND_IP_CSUM		= (1<<4),

	/* reserve bits 26-31 for low level drivers' internal use */
	IB_SEND_RESERVED_START	= (1 << 26),
	IB_SEND_RESERVED_END	= (1 << 31),
};

struct ib_sge {
	u64	addr;
	u32	length;
	u32	lkey;
};

struct ib_cqe {
	void (*done)(struct ib_cq *cq, struct ib_wc *wc);
};

struct ib_send_wr {
	struct ib_send_wr      *next;
	union {
		u64		wr_id;
		struct ib_cqe	*wr_cqe;
	};
	struct ib_sge	       *sg_list;
	int			num_sge;
	enum ib_wr_opcode	opcode;
	int			send_flags;
	union {
		__be32		imm_data;
		u32		invalidate_rkey;
	} ex;
};

struct ib_rdma_wr {
	struct ib_send_wr	wr;
	u64			remote_addr;
	u32			rkey;
};

static inline const struct ib_rdma_wr *rdma_wr(const struct ib_send_wr *wr)
{
	return container_of(wr, struct ib_rdma_wr, wr);
}

struct ib_atomic_wr {
	struct ib_send_wr	wr;
	u64			remote_addr;
	u64			compare_add;
	u64			swap;
	u64			compare_add_mask;
	u64			swap_mask;
	u32			rkey;
};

static inline const struct ib_atomic_wr *atomic_wr(const struct ib_send_wr *wr)
{
	return container_of(wr, struct ib_atomic_wr, wr);
}

struct ib_ud_wr {
	struct ib_send_wr	wr;
	struct ib_ah		*ah;
	void			*header;
	int			hlen;
	int			mss;
	u32			remote_qpn;
	u32			remote_qkey;
	u16			pkey_index; /* valid for GSI only */
	u32			port_num; /* valid for DR SMPs on switch only */
};

static inline const struct ib_ud_wr *ud_wr(const struct ib_send_wr *wr)
{
	return container_of(wr, struct ib_ud_wr, wr);
}

struct ib_reg_wr {
	struct ib_send_wr	wr;
	struct ib_mr		*mr;
	u32			key;
	int			access;
};

static inline const struct ib_reg_wr *reg_wr(const struct ib_send_wr *wr)
{
	return container_of(wr, struct ib_reg_wr, wr);
}

struct ib_recv_wr {
	struct ib_recv_wr      *next;
	union {
		u64		wr_id;
		struct ib_cqe	*wr_cqe;
	};
	struct ib_sge	       *sg_list;
	int			num_sge;
};

enum ib_access_flags {
	IB_ACCESS_LOCAL_WRITE = IB_UVERBS_ACCESS_LOCAL_WRITE,
	IB_ACCESS_REMOTE_WRITE = IB_UVERBS_ACCESS_REMOTE_WRITE,
	IB_ACCESS_REMOTE_READ = IB_UVERBS_ACCESS_REMOTE_READ,
	IB_ACCESS_REMOTE_ATOMIC = IB_UVERBS_ACCESS_REMOTE_ATOMIC,
	IB_ACCESS_MW_BIND = IB_UVERBS_ACCESS_MW_BIND,
	IB_ZERO_BASED = IB_UVERBS_ACCESS_ZERO_BASED,
	IB_ACCESS_ON_DEMAND = IB_UVERBS_ACCESS_ON_DEMAND,
	IB_ACCESS_HUGETLB = IB_UVERBS_ACCESS_HUGETLB,
	IB_ACCESS_RELAXED_ORDERING = IB_UVERBS_ACCESS_RELAXED_ORDERING,
	IB_ACCESS_FLUSH_GLOBAL = IB_UVERBS_ACCESS_FLUSH_GLOBAL,
	IB_ACCESS_FLUSH_PERSISTENT = IB_UVERBS_ACCESS_FLUSH_PERSISTENT,

	IB_ACCESS_OPTIONAL = IB_UVERBS_ACCESS_OPTIONAL_RANGE,
	IB_ACCESS_SUPPORTED =
		((IB_ACCESS_FLUSH_PERSISTENT << 1) - 1) | IB_ACCESS_OPTIONAL,
};

/*
 * XXX: these are apparently used for ->rereg_user_mr, no idea why they
 * are hidden here instead of a uapi header!
 */
enum ib_mr_rereg_flags {
	IB_MR_REREG_TRANS	= 1,
	IB_MR_REREG_PD		= (1<<1),
	IB_MR_REREG_ACCESS	= (1<<2),
	IB_MR_REREG_SUPPORTED	= ((IB_MR_REREG_ACCESS << 1) - 1)
};

struct ib_umem;

enum rdma_remove_reason {
	/*
	 * Userspace requested uobject deletion or initial try
	 * to remove uobject via cleanup. Call could fail
	 */
	RDMA_REMOVE_DESTROY,
	/* Context deletion. This call should delete the actual object itself */
	RDMA_REMOVE_CLOSE,
	/* Driver is being hot-unplugged. This call should delete the actual object itself */
	RDMA_REMOVE_DRIVER_REMOVE,
	/* uobj is being cleaned-up before being committed */
	RDMA_REMOVE_ABORT,
	/* The driver failed to destroy the uobject and is being disconnected */
	RDMA_REMOVE_DRIVER_FAILURE,
};

struct ib_rdmacg_object {
#ifdef CONFIG_CGROUP_RDMA
	struct rdma_cgroup	*cg;		/* owner rdma cgroup */
#endif
};

struct ib_ucontext {
	struct ib_device       *device;
	struct ib_uverbs_file  *ufile;

	struct ib_rdmacg_object	cg_obj;
	/*
	 * Implementation details of the RDMA core, don't use in drivers:
	 */
	struct rdma_restrack_entry res;
	struct xarray mmap_xa;
};

struct ib_uobject {
	u64			user_handle;	/* handle given to us by userspace */
	/* ufile & ucontext owning this object */
	struct ib_uverbs_file  *ufile;
	/* FIXME, save memory: ufile->context == context */
	struct ib_ucontext     *context;	/* associated user context */
	void		       *object;		/* containing object */
	struct list_head	list;		/* link to context's list */
	struct ib_rdmacg_object	cg_obj;		/* rdmacg object */
	int			id;		/* index into kernel idr */
	struct kref		ref;
	atomic_t		usecnt;		/* protects exclusive access */
	struct rcu_head		rcu;		/* kfree_rcu() overhead */

	const struct uverbs_api_object *uapi_object;
};

struct ib_udata {
	const void __user *inbuf;
	void __user *outbuf;
	size_t       inlen;
	size_t       outlen;
};

struct ib_pd {
	u32			local_dma_lkey;
	u32			flags;
	struct ib_device       *device;
	struct ib_uobject      *uobject;
	atomic_t          	usecnt; /* count all resources */

	u32			unsafe_global_rkey;

	/*
	 * Implementation details of the RDMA core, don't use in drivers:
	 */
	struct ib_mr	       *__internal_mr;
	struct rdma_restrack_entry res;
};

struct ib_xrcd {
	struct ib_device       *device;
	atomic_t		usecnt; /* count all exposed resources */
	struct inode	       *inode;
	struct rw_semaphore	tgt_qps_rwsem;
	struct xarray		tgt_qps;
};

struct ib_ah {
	struct ib_device	*device;
	struct ib_pd		*pd;
	struct ib_uobject	*uobject;
	const struct ib_gid_attr *sgid_attr;
	enum rdma_ah_attr_type	type;
};

typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context);

enum ib_poll_context {
	IB_POLL_SOFTIRQ,	   /* poll from softirq context */
	IB_POLL_WORKQUEUE,	   /* poll from workqueue */
	IB_POLL_UNBOUND_WORKQUEUE, /* poll from unbound workqueue */
	IB_POLL_LAST_POOL_TYPE = IB_POLL_UNBOUND_WORKQUEUE,

	IB_POLL_DIRECT,		   /* caller context, no hw completions */
};

struct ib_cq {
	struct ib_device       *device;
	struct ib_ucq_object   *uobject;
	ib_comp_handler   	comp_handler;
	void                  (*event_handler)(struct ib_event *, void *);
	void                   *cq_context;
	int               	cqe;
	unsigned int		cqe_used;
	atomic_t          	usecnt; /* count number of work queues */
	enum ib_poll_context	poll_ctx;
	struct ib_wc		*wc;
	struct list_head        pool_entry;
	union {
		struct irq_poll		iop;
		struct work_struct	work;
	};
	struct workqueue_struct *comp_wq;
	struct dim *dim;

	/* updated only by trace points */
	ktime_t timestamp;
	u8 interrupt:1;
	u8 shared:1;
	unsigned int comp_vector;

	/*
	 * Implementation details of the RDMA core, don't use in drivers:
	 */
	struct rdma_restrack_entry res;
};

struct ib_srq {
	struct ib_device       *device;
	struct ib_pd	       *pd;
	struct ib_usrq_object  *uobject;
	void		      (*event_handler)(struct ib_event *, void *);
	void		       *srq_context;
	enum ib_srq_type	srq_type;
	atomic_t		usecnt;

	struct {
		struct ib_cq   *cq;
		union {
			struct {
				struct ib_xrcd *xrcd;
				u32		srq_num;
			} xrc;
		};
	} ext;

	/*
	 * Implementation details of the RDMA core, don't use in drivers:
	 */
	struct rdma_restrack_entry res;
};

enum ib_raw_packet_caps {
	/*
	 * Strip cvlan from incoming packet and report it in the matching work
	 * completion is supported.
	 */
	IB_RAW_PACKET_CAP_CVLAN_STRIPPING =
		IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING,
	/*
	 * Scatter FCS field of an incoming packet to host memory is supported.
	 */
	IB_RAW_PACKET_CAP_SCATTER_FCS = IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS,
	/* Checksum offloads are supported (for both send and receive). */
	IB_RAW_PACKET_CAP_IP_CSUM = IB_UVERBS_RAW_PACKET_CAP_IP_CSUM,
	/*
	 * When a packet is received for an RQ with no receive WQEs, the
	 * packet processing is delayed.
	 */
	IB_RAW_PACKET_CAP_DELAY_DROP = IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP,
};

enum ib_wq_type {
	IB_WQT_RQ = IB_UVERBS_WQT_RQ,
};

enum ib_wq_state {
	IB_WQS_RESET,
	IB_WQS_RDY,
	IB_WQS_ERR
};

struct ib_wq {
	struct ib_device       *device;
	struct ib_uwq_object   *uobject;
	void		    *wq_context;
	void		    (*event_handler)(struct ib_event *, void *);
	struct ib_pd	       *pd;
	struct ib_cq	       *cq;
	u32		wq_num;
	enum ib_wq_state       state;
	enum ib_wq_type	wq_type;
	atomic_t		usecnt;
};

enum ib_wq_flags {
	IB_WQ_FLAGS_CVLAN_STRIPPING	= IB_UVERBS_WQ_FLAGS_CVLAN_STRIPPING,
	IB_WQ_FLAGS_SCATTER_FCS		= IB_UVERBS_WQ_FLAGS_SCATTER_FCS,
	IB_WQ_FLAGS_DELAY_DROP		= IB_UVERBS_WQ_FLAGS_DELAY_DROP,
	IB_WQ_FLAGS_PCI_WRITE_END_PADDING =
				IB_UVERBS_WQ_FLAGS_PCI_WRITE_END_PADDING,
};

struct ib_wq_init_attr {
	void		       *wq_context;
	enum ib_wq_type	wq_type;
	u32		max_wr;
	u32		max_sge;
	struct	ib_cq	       *cq;
	void		    (*event_handler)(struct ib_event *, void *);
	u32		create_flags; /* Use enum ib_wq_flags */
};

enum ib_wq_attr_mask {
	IB_WQ_STATE		= 1 << 0,
	IB_WQ_CUR_STATE		= 1 << 1,
	IB_WQ_FLAGS		= 1 << 2,
};

struct ib_wq_attr {
	enum	ib_wq_state	wq_state;
	enum	ib_wq_state	curr_wq_state;
	u32			flags; /* Use enum ib_wq_flags */
	u32			flags_mask; /* Use enum ib_wq_flags */
};

struct ib_rwq_ind_table {
	struct ib_device	*device;
	struct ib_uobject      *uobject;
	atomic_t		usecnt;
	u32		ind_tbl_num;
	u32		log_ind_tbl_size;
	struct ib_wq	**ind_tbl;
};

struct ib_rwq_ind_table_init_attr {
	u32		log_ind_tbl_size;
	/* Each entry is a pointer to Receive Work Queue */
	struct ib_wq	**ind_tbl;
};

enum port_pkey_state {
	IB_PORT_PKEY_NOT_VALID = 0,
	IB_PORT_PKEY_VALID = 1,
	IB_PORT_PKEY_LISTED = 2,
};

struct ib_qp_security;

struct ib_port_pkey {
	enum port_pkey_state	state;
	u16			pkey_index;
	u32			port_num;
	struct list_head	qp_list;
	struct list_head	to_error_list;
	struct ib_qp_security  *sec;
};

struct ib_ports_pkeys {
	struct ib_port_pkey	main;
	struct ib_port_pkey	alt;
};

struct ib_qp_security {
	struct ib_qp	       *qp;
	struct ib_device       *dev;
	/* Hold this mutex when changing port and pkey settings. */
	struct mutex		mutex;
	struct ib_ports_pkeys  *ports_pkeys;
	/* A list of all open shared QP handles.  Required to enforce security
	 * properly for all users of a shared QP.
	 */
	struct list_head        shared_qp_list;
	void                   *security;
	bool			destroying;
	atomic_t		error_list_count;
	struct completion	error_complete;
	int			error_comps_pending;
};

/*
 * @max_write_sge: Maximum SGE elements per RDMA WRITE request.
 * @max_read_sge:  Maximum SGE elements per RDMA READ request.
 */
struct ib_qp {
	struct ib_device       *device;
	struct ib_pd	       *pd;
	struct ib_cq	       *send_cq;
	struct ib_cq	       *recv_cq;
	spinlock_t		mr_lock;
	int			mrs_used;
	struct list_head	rdma_mrs;
	struct list_head	sig_mrs;
	struct ib_srq	       *srq;
	struct completion	srq_completion;
	struct ib_xrcd	       *xrcd; /* XRC TGT QPs only */
	struct list_head	xrcd_list;

	/* count times opened, mcast attaches, flow attaches */
	atomic_t		usecnt;
	struct list_head	open_list;
	struct ib_qp           *real_qp;
	struct ib_uqp_object   *uobject;
	void                  (*event_handler)(struct ib_event *, void *);
	void                  (*registered_event_handler)(struct ib_event *, void *);
	void		       *qp_context;
	/* sgid_attrs associated with the AV's */
	const struct ib_gid_attr *av_sgid_attr;
	const struct ib_gid_attr *alt_path_sgid_attr;
	u32			qp_num;
	u32			max_write_sge;
	u32			max_read_sge;
	enum ib_qp_type		qp_type;
	struct ib_rwq_ind_table *rwq_ind_tbl;
	struct ib_qp_security  *qp_sec;
	u32			port;

	bool			integrity_en;
	/*
	 * Implementation details of the RDMA core, don't use in drivers:
	 */
	struct rdma_restrack_entry     res;

	/* The counter the qp is bind to */
	struct rdma_counter    *counter;
};

struct ib_dm {
	struct ib_device  *device;
	u32		   length;
	u32		   flags;
	struct ib_uobject *uobject;
	atomic_t	   usecnt;
};

struct ib_mr {
	struct ib_device  *device;
	struct ib_pd	  *pd;
	u32		   lkey;
	u32		   rkey;
	u64		   iova;
	u64		   length;
	unsigned int	   page_size;
	enum ib_mr_type	   type;
	bool		   need_inval;
	union {
		struct ib_uobject	*uobject;	/* user */
		struct list_head	qp_entry;	/* FR */
	};

	struct ib_dm      *dm;
	struct ib_sig_attrs *sig_attrs; /* only for IB_MR_TYPE_INTEGRITY MRs */
	/*
	 * Implementation details of the RDMA core, don't use in drivers:
	 */
	struct rdma_restrack_entry res;
};

struct ib_mw {
	struct ib_device	*device;
	struct ib_pd		*pd;
	struct ib_uobject	*uobject;
	u32			rkey;
	enum ib_mw_type         type;
};

/* Supported steering options */
enum ib_flow_attr_type {
	/* steering according to rule specifications */
	IB_FLOW_ATTR_NORMAL		= 0x0,
	/* default unicast and multicast rule -
	 * receive all Eth traffic which isn't steered to any QP
	 */
	IB_FLOW_ATTR_ALL_DEFAULT	= 0x1,
	/* default multicast rule -
	 * receive all Eth multicast traffic which isn't steered to any QP
	 */
	IB_FLOW_ATTR_MC_DEFAULT		= 0x2,
	/* sniffer rule - receive all port traffic */
	IB_FLOW_ATTR_SNIFFER		= 0x3
};

/* Supported steering header types */
enum ib_flow_spec_type {
	/* L2 headers*/
	IB_FLOW_SPEC_ETH		= 0x20,
	IB_FLOW_SPEC_IB			= 0x22,
	/* L3 header*/
	IB_FLOW_SPEC_IPV4		= 0x30,
	IB_FLOW_SPEC_IPV6		= 0x31,
	IB_FLOW_SPEC_ESP                = 0x34,
	/* L4 headers*/
	IB_FLOW_SPEC_TCP		= 0x40,
	IB_FLOW_SPEC_UDP		= 0x41,
	IB_FLOW_SPEC_VXLAN_TUNNEL	= 0x50,
	IB_FLOW_SPEC_GRE		= 0x51,
	IB_FLOW_SPEC_MPLS		= 0x60,
	IB_FLOW_SPEC_INNER		= 0x100,
	/* Actions */
	IB_FLOW_SPEC_ACTION_TAG         = 0x1000,
	IB_FLOW_SPEC_ACTION_DROP        = 0x1001,
	IB_FLOW_SPEC_ACTION_HANDLE	= 0x1002,
	IB_FLOW_SPEC_ACTION_COUNT       = 0x1003,
};
#define IB_FLOW_SPEC_LAYER_MASK	0xF0
#define IB_FLOW_SPEC_SUPPORT_LAYERS 10

enum ib_flow_flags {
	IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */
	IB_FLOW_ATTR_FLAGS_EGRESS = 1UL << 2, /* Egress flow */
	IB_FLOW_ATTR_FLAGS_RESERVED  = 1UL << 3  /* Must be last */
};

struct ib_flow_eth_filter {
	u8	dst_mac[6];
	u8	src_mac[6];
	__be16	ether_type;
	__be16	vlan_tag;
};

struct ib_flow_spec_eth {
	u32			  type;
	u16			  size;
	struct ib_flow_eth_filter val;
	struct ib_flow_eth_filter mask;
};

struct ib_flow_ib_filter {
	__be16 dlid;
	__u8   sl;
};

struct ib_flow_spec_ib {
	u32			 type;
	u16			 size;
	struct ib_flow_ib_filter val;
	struct ib_flow_ib_filter mask;
};

/* IPv4 header flags */
enum ib_ipv4_flags {
	IB_IPV4_DONT_FRAG = 0x2, /* Don't enable packet fragmentation */
	IB_IPV4_MORE_FRAG = 0X4  /* For All fragmented packets except the
				    last have this flag set */
};

struct ib_flow_ipv4_filter {
	__be32	src_ip;
	__be32	dst_ip;
	u8	proto;
	u8	tos;
	u8	ttl;
	u8	flags;
};

struct ib_flow_spec_ipv4 {
	u32			   type;
	u16			   size;
	struct ib_flow_ipv4_filter val;
	struct ib_flow_ipv4_filter mask;
};

struct ib_flow_ipv6_filter {
	u8	src_ip[16];
	u8	dst_ip[16];
	__be32	flow_label;
	u8	next_hdr;
	u8	traffic_class;
	u8	hop_limit;
} __packed;

struct ib_flow_spec_ipv6 {
	u32			   type;
	u16			   size;
	struct ib_flow_ipv6_filter val;
	struct ib_flow_ipv6_filter mask;
};

struct ib_flow_tcp_udp_filter {
	__be16	dst_port;
	__be16	src_port;
};

struct ib_flow_spec_tcp_udp {
	u32			      type;
	u16			      size;
	struct ib_flow_tcp_udp_filter val;
	struct ib_flow_tcp_udp_filter mask;
};

struct ib_flow_tunnel_filter {
	__be32	tunnel_id;
};

/* ib_flow_spec_tunnel describes the Vxlan tunnel
 * the tunnel_id from val has the vni value
 */
struct ib_flow_spec_tunnel {
	u32			      type;
	u16			      size;
	struct ib_flow_tunnel_filter  val;
	struct ib_flow_tunnel_filter  mask;
};

struct ib_flow_esp_filter {
	__be32	spi;
	__be32  seq;
};

struct ib_flow_spec_esp {
	u32                           type;
	u16			      size;
	struct ib_flow_esp_filter     val;
	struct ib_flow_esp_filter     mask;
};

struct ib_flow_gre_filter {
	__be16 c_ks_res0_ver;
	__be16 protocol;
	__be32 key;
};

struct ib_flow_spec_gre {
	u32                           type;
	u16			      size;
	struct ib_flow_gre_filter     val;
	struct ib_flow_gre_filter     mask;
};

struct ib_flow_mpls_filter {
	__be32 tag;
};

struct ib_flow_spec_mpls {
	u32                           type;
	u16			      size;
	struct ib_flow_mpls_filter     val;
	struct ib_flow_mpls_filter     mask;
};

struct ib_flow_spec_action_tag {
	enum ib_flow_spec_type	      type;
	u16			      size;
	u32                           tag_id;
};

struct ib_flow_spec_action_drop {
	enum ib_flow_spec_type	      type;
	u16			      size;
};

struct ib_flow_spec_action_handle {
	enum ib_flow_spec_type	      type;
	u16			      size;
	struct ib_flow_action	     *act;
};

enum ib_counters_description {
	IB_COUNTER_PACKETS,
	IB_COUNTER_BYTES,
};

struct ib_flow_spec_action_count {
	enum ib_flow_spec_type type;
	u16 size;
	struct ib_counters *counters;
};

union ib_flow_spec {
	struct {
		u32			type;
		u16			size;
	};
	struct ib_flow_spec_eth		eth;
	struct ib_flow_spec_ib		ib;
	struct ib_flow_spec_ipv4        ipv4;
	struct ib_flow_spec_tcp_udp	tcp_udp;
	struct ib_flow_spec_ipv6        ipv6;
	struct ib_flow_spec_tunnel      tunnel;
	struct ib_flow_spec_esp		esp;
	struct ib_flow_spec_gre		gre;
	struct ib_flow_spec_mpls	mpls;
	struct ib_flow_spec_action_tag  flow_tag;
	struct ib_flow_spec_action_drop drop;
	struct ib_flow_spec_action_handle action;
	struct ib_flow_spec_action_count flow_count;
};

struct ib_flow_attr {
	enum ib_flow_attr_type type;
	u16	     size;
	u16	     priority;
	u32	     flags;
	u8	     num_of_specs;
	u32	     port;
	union ib_flow_spec flows[];
};

struct ib_flow {
	struct ib_qp		*qp;
	struct ib_device	*device;
	struct ib_uobject	*uobject;
};

enum ib_flow_action_type {
	IB_FLOW_ACTION_UNSPECIFIED,
	IB_FLOW_ACTION_ESP = 1,
};

struct ib_flow_action_attrs_esp_keymats {
	enum ib_uverbs_flow_action_esp_keymat			protocol;
	union {
		struct ib_uverbs_flow_action_esp_keymat_aes_gcm aes_gcm;
	} keymat;
};

struct ib_flow_action_attrs_esp_replays {
	enum ib_uverbs_flow_action_esp_replay			protocol;
	union {
		struct ib_uverbs_flow_action_esp_replay_bmp	bmp;
	} replay;
};

enum ib_flow_action_attrs_esp_flags {
	/* All user-space flags at the top: Use enum ib_uverbs_flow_action_esp_flags
	 * This is done in order to share the same flags between user-space and
	 * kernel and spare an unnecessary translation.
	 */

	/* Kernel flags */
	IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED	= 1ULL << 32,
	IB_FLOW_ACTION_ESP_FLAGS_MOD_ESP_ATTRS	= 1ULL << 33,
};

struct ib_flow_spec_list {
	struct ib_flow_spec_list	*next;
	union ib_flow_spec		spec;
};

struct ib_flow_action_attrs_esp {
	struct ib_flow_action_attrs_esp_keymats		*keymat;
	struct ib_flow_action_attrs_esp_replays		*replay;
	struct ib_flow_spec_list			*encap;
	/* Used only if IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED is enabled.
	 * Value of 0 is a valid value.
	 */
	u32						esn;
	u32						spi;
	u32						seq;
	u32						tfc_pad;
	/* Use enum ib_flow_action_attrs_esp_flags */
	u64						flags;
	u64						hard_limit_pkts;
};

struct ib_flow_action {
	struct ib_device		*device;
	struct ib_uobject		*uobject;
	enum ib_flow_action_type	type;
	atomic_t			usecnt;
};

struct ib_mad;

enum ib_process_mad_flags {
	IB_MAD_IGNORE_MKEY	= 1,
	IB_MAD_IGNORE_BKEY	= 2,
	IB_MAD_IGNORE_ALL	= IB_MAD_IGNORE_MKEY | IB_MAD_IGNORE_BKEY
};

enum ib_mad_result {
	IB_MAD_RESULT_FAILURE  = 0,      /* (!SUCCESS is the important flag) */
	IB_MAD_RESULT_SUCCESS  = 1 << 0, /* MAD was successfully processed   */
	IB_MAD_RESULT_REPLY    = 1 << 1, /* Reply packet needs to be sent    */
	IB_MAD_RESULT_CONSUMED = 1 << 2  /* Packet consumed: stop processing */
};

struct ib_port_cache {
	u64		      subnet_prefix;
	struct ib_pkey_cache  *pkey;
	struct ib_gid_table   *gid;
	u8                     lmc;
	enum ib_port_state     port_state;
};

struct ib_port_immutable {
	int                           pkey_tbl_len;
	int                           gid_tbl_len;
	u32                           core_cap_flags;
	u32                           max_mad_size;
};

struct ib_port_data {
	struct ib_device *ib_dev;

	struct ib_port_immutable immutable;

	spinlock_t pkey_list_lock;

	spinlock_t netdev_lock;

	struct list_head pkey_list;

	struct ib_port_cache cache;

	struct net_device __rcu *netdev;
	netdevice_tracker netdev_tracker;
	struct hlist_node ndev_hash_link;
	struct rdma_port_counter port_counter;
	struct ib_port *sysfs;
};

/* rdma netdev type - specifies protocol type */
enum rdma_netdev_t {
	RDMA_NETDEV_OPA_VNIC,
	RDMA_NETDEV_IPOIB,
};

/**
 * struct rdma_netdev - rdma netdev
 * For cases where netstack interfacing is required.
 */
struct rdma_netdev {
	void              *clnt_priv;
	struct ib_device  *hca;
	u32		   port_num;
	int                mtu;

	/*
	 * cleanup function must be specified.
	 * FIXME: This is only used for OPA_VNIC and that usage should be
	 * removed too.
	 */
	void (*free_rdma_netdev)(struct net_device *netdev);

	/* control functions */
	void (*set_id)(struct net_device *netdev, int id);
	/* send packet */
	int (*send)(struct net_device *dev, struct sk_buff *skb,
		    struct ib_ah *address, u32 dqpn);
	/* multicast */
	int (*attach_mcast)(struct net_device *dev, struct ib_device *hca,
			    union ib_gid *gid, u16 mlid,
			    int set_qkey, u32 qkey);
	int (*detach_mcast)(struct net_device *dev, struct ib_device *hca,
			    union ib_gid *gid, u16 mlid);
	/* timeout */
	void (*tx_timeout)(struct net_device *dev, unsigned int txqueue);
};

struct rdma_netdev_alloc_params {
	size_t sizeof_priv;
	unsigned int txqs;
	unsigned int rxqs;
	void *param;

	int (*initialize_rdma_netdev)(struct ib_device *device, u32 port_num,
				      struct net_device *netdev, void *param);
};

struct ib_odp_counters {
	atomic64_t faults;
	atomic64_t invalidations;
	atomic64_t prefetch;
};

struct ib_counters {
	struct ib_device	*device;
	struct ib_uobject	*uobject;
	/* num of objects attached */
	atomic_t	usecnt;
};

struct ib_counters_read_attr {
	u64	*counters_buff;
	u32	ncounters;
	u32	flags; /* use enum ib_read_counters_flags */
};

struct uverbs_attr_bundle;
struct iw_cm_id;
struct iw_cm_conn_param;

#define INIT_RDMA_OBJ_SIZE(ib_struct, drv_struct, member)                      \
	.size_##ib_struct =                                                    \
		(sizeof(struct drv_struct) +                                   \
		 BUILD_BUG_ON_ZERO(offsetof(struct drv_struct, member)) +      \
		 BUILD_BUG_ON_ZERO(                                            \
			 !__same_type(((struct drv_struct *)NULL)->member,     \
				      struct ib_struct)))

#define rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, gfp)                          \
	((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \
					   gfp, false))

#define rdma_zalloc_drv_obj_numa(ib_dev, ib_type)                              \
	((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \
					   GFP_KERNEL, true))

#define rdma_zalloc_drv_obj(ib_dev, ib_type)                                   \
	rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, GFP_KERNEL)

#define DECLARE_RDMA_OBJ_SIZE(ib_struct) size_t size_##ib_struct

struct rdma_user_mmap_entry {
	struct kref ref;
	struct ib_ucontext *ucontext;
	unsigned long start_pgoff;
	size_t npages;
	bool driver_removed;
};

/* Return the offset (in bytes) the user should pass to libc's mmap() */
static inline u64
rdma_user_mmap_get_offset(const struct rdma_user_mmap_entry *entry)
{
	return (u64)entry->start_pgoff << PAGE_SHIFT;
}

/**
 * struct ib_device_ops - InfiniBand device operations
 * This structure defines all the InfiniBand device operations, providers will
 * need to define the supported operations, otherwise they will be set to null.
 */
struct ib_device_ops {
	struct module *owner;
	enum rdma_driver_id driver_id;
	u32 uverbs_abi_ver;
	unsigned int uverbs_no_driver_id_binding:1;

	/*
	 * NOTE: New drivers should not make use of device_group; instead new
	 * device parameter should be exposed via netlink command. This
	 * mechanism exists only for existing drivers.
	 */
	const struct attribute_group *device_group;
	const struct attribute_group **port_groups;

	int (*post_send)(struct ib_qp *qp, const struct ib_send_wr *send_wr,
			 const struct ib_send_wr **bad_send_wr);
	int (*post_recv)(struct ib_qp *qp, const struct ib_recv_wr *recv_wr,
			 const struct ib_recv_wr **bad_recv_wr);
	void (*drain_rq)(struct ib_qp *qp);
	void (*drain_sq)(struct ib_qp *qp);
	int (*poll_cq)(struct ib_cq *cq, int num_entries, struct ib_wc *wc);
	int (*peek_cq)(struct ib_cq *cq, int wc_cnt);
	int (*req_notify_cq)(struct ib_cq *cq, enum ib_cq_notify_flags flags);
	int (*post_srq_recv)(struct ib_srq *srq,
			     const struct ib_recv_wr *recv_wr,
			     const struct ib_recv_wr **bad_recv_wr);
	int (*process_mad)(struct ib_device *device, int process_mad_flags,
			   u32 port_num, const struct ib_wc *in_wc,
			   const struct ib_grh *in_grh,
			   const struct ib_mad *in_mad, struct ib_mad *out_mad,
			   size_t *out_mad_size, u16 *out_mad_pkey_index);
	int (*query_device)(struct ib_device *device,
			    struct ib_device_attr *device_attr,
			    struct ib_udata *udata);
	int (*modify_device)(struct ib_device *device, int device_modify_mask,
			     struct ib_device_modify *device_modify);
	void (*get_dev_fw_str)(struct ib_device *device, char *str);
	const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev,
						     int comp_vector);
	int (*query_port)(struct ib_device *device, u32 port_num,
			  struct ib_port_attr *port_attr);
	int (*modify_port)(struct ib_device *device, u32 port_num,
			   int port_modify_mask,
			   struct ib_port_modify *port_modify);
	/**
	 * The following mandatory functions are used only at device
	 * registration.  Keep functions such as these at the end of this
	 * structure to avoid cache line misses when accessing struct ib_device
	 * in fast paths.
	 */
	int (*get_port_immutable)(struct ib_device *device, u32 port_num,
				  struct ib_port_immutable *immutable);
	enum rdma_link_layer (*get_link_layer)(struct ib_device *device,
					       u32 port_num);
	/**
	 * When calling get_netdev, the HW vendor's driver should return the
	 * net device of device @device at port @port_num or NULL if such
	 * a net device doesn't exist. The vendor driver should call dev_hold
	 * on this net device. The HW vendor's device driver must guarantee
	 * that this function returns NULL before the net device has finished
	 * NETDEV_UNREGISTER state.
	 */
	struct net_device *(*get_netdev)(struct ib_device *device,
					 u32 port_num);
	/**
	 * rdma netdev operation
	 *
	 * Driver implementing alloc_rdma_netdev or rdma_netdev_get_params
	 * must return -EOPNOTSUPP if it doesn't support the specified type.
	 */
	struct net_device *(*alloc_rdma_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 *));

	int (*rdma_netdev_get_params)(struct ib_device *device, u32 port_num,
				      enum rdma_netdev_t type,
				      struct rdma_netdev_alloc_params *params);
	/**
	 * query_gid should be return GID value for @device, when @port_num
	 * link layer is either IB or iWarp. It is no-op if @port_num port
	 * is RoCE link layer.
	 */
	int (*query_gid)(struct ib_device *device, u32 port_num, int index,
			 union ib_gid *gid);
	/**
	 * When calling add_gid, the HW vendor's driver should add the gid
	 * of device of port at gid index available at @attr. Meta-info of
	 * that gid (for example, the network device related to this gid) is
	 * available at @attr. @context allows the HW vendor driver to store
	 * extra information together with a GID entry. The HW vendor driver may
	 * allocate memory to contain this information and store it in @context
	 * when a new GID entry is written to. Params are consistent until the
	 * next call of add_gid or delete_gid. The function should return 0 on
	 * success or error otherwise. The function could be called
	 * concurrently for different ports. This function is only called when
	 * roce_gid_table is used.
	 */
	int (*add_gid)(const struct ib_gid_attr *attr, void **context);
	/**
	 * When calling del_gid, the HW vendor's driver should delete the
	 * gid of device @device at gid index gid_index of port port_num
	 * available in @attr.
	 * Upon the deletion of a GID entry, the HW vendor must free any
	 * allocated memory. The caller will clear @context afterwards.
	 * This function is only called when roce_gid_table is used.
	 */
	int (*del_gid)(const struct ib_gid_attr *attr, void **context);
	int (*query_pkey)(struct ib_device *device, u32 port_num, u16 index,
			  u16 *pkey);
	int (*alloc_ucontext)(struct ib_ucontext *context,
			      struct ib_udata *udata);
	void (*dealloc_ucontext)(struct ib_ucontext *context);
	int (*mmap)(struct ib_ucontext *context, struct vm_area_struct *vma);
	/**
	 * This will be called once refcount of an entry in mmap_xa reaches
	 * zero. The type of the memory that was mapped may differ between
	 * entries and is opaque to the rdma_user_mmap interface.
	 * Therefore needs to be implemented by the driver in mmap_free.
	 */
	void (*mmap_free)(struct rdma_user_mmap_entry *entry);
	void (*disassociate_ucontext)(struct ib_ucontext *ibcontext);
	int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
	int (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
	int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr,
			 struct ib_udata *udata);
	int (*create_user_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr,
			      struct ib_udata *udata);
	int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
	int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
	int (*destroy_ah)(struct ib_ah *ah, u32 flags);
	int (*create_srq)(struct ib_srq *srq,
			  struct ib_srq_init_attr *srq_init_attr,
			  struct ib_udata *udata);
	int (*modify_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr,
			  enum ib_srq_attr_mask srq_attr_mask,
			  struct ib_udata *udata);
	int (*query_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr);
	int (*destroy_srq)(struct ib_srq *srq, struct ib_udata *udata);
	int (*create_qp)(struct ib_qp *qp, struct ib_qp_init_attr *qp_init_attr,
			 struct ib_udata *udata);
	int (*modify_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
			 int qp_attr_mask, struct ib_udata *udata);
	int (*query_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
			int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr);
	int (*destroy_qp)(struct ib_qp *qp, struct ib_udata *udata);
	int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr,
			 struct uverbs_attr_bundle *attrs);
	int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period);
	int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata);
	int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata);
	struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags);
	struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length,
				     u64 virt_addr, int mr_access_flags,
				     struct ib_udata *udata);
	struct ib_mr *(*reg_user_mr_dmabuf)(struct ib_pd *pd, u64 offset,
					    u64 length, u64 virt_addr, int fd,
					    int mr_access_flags,
					    struct ib_udata *udata);
	struct ib_mr *(*rereg_user_mr)(struct ib_mr *mr, int flags, u64 start,
				       u64 length, u64 virt_addr,
				       int mr_access_flags, struct ib_pd *pd,
				       struct ib_udata *udata);
	int (*dereg_mr)(struct ib_mr *mr, struct ib_udata *udata);
	struct ib_mr *(*alloc_mr)(struct ib_pd *pd, enum ib_mr_type mr_type,
				  u32 max_num_sg);
	struct ib_mr *(*alloc_mr_integrity)(struct ib_pd *pd,
					    u32 max_num_data_sg,
					    u32 max_num_meta_sg);
	int (*advise_mr)(struct ib_pd *pd,
			 enum ib_uverbs_advise_mr_advice advice, u32 flags,
			 struct ib_sge *sg_list, u32 num_sge,
			 struct uverbs_attr_bundle *attrs);

	/*
	 * Kernel users should universally support relaxed ordering (RO), as
	 * they are designed to read data only after observing the CQE and use
	 * the DMA API correctly.
	 *
	 * Some drivers implicitly enable RO if platform supports it.
	 */
	int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
			 unsigned int *sg_offset);
	int (*check_mr_status)(struct ib_mr *mr, u32 check_mask,
			       struct ib_mr_status *mr_status);
	int (*alloc_mw)(struct ib_mw *mw, struct ib_udata *udata);
	int (*dealloc_mw)(struct ib_mw *mw);
	int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
	int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
	int (*alloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata);
	int (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata);
	struct ib_flow *(*create_flow)(struct ib_qp *qp,
				       struct ib_flow_attr *flow_attr,
				       struct ib_udata *udata);
	int (*destroy_flow)(struct ib_flow *flow_id);
	int (*destroy_flow_action)(struct ib_flow_action *action);
	int (*set_vf_link_state)(struct ib_device *device, int vf, u32 port,
				 int state);
	int (*get_vf_config)(struct ib_device *device, int vf, u32 port,
			     struct ifla_vf_info *ivf);
	int (*get_vf_stats)(struct ib_device *device, int vf, u32 port,
			    struct ifla_vf_stats *stats);
	int (*get_vf_guid)(struct ib_device *device, int vf, u32 port,
			    struct ifla_vf_guid *node_guid,
			    struct ifla_vf_guid *port_guid);
	int (*set_vf_guid)(struct ib_device *device, int vf, u32 port, u64 guid,
			   int type);
	struct ib_wq *(*create_wq)(struct ib_pd *pd,
				   struct ib_wq_init_attr *init_attr,
				   struct ib_udata *udata);
	int (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata);
	int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr,
			 u32 wq_attr_mask, struct ib_udata *udata);
	int (*create_rwq_ind_table)(struct ib_rwq_ind_table *ib_rwq_ind_table,
				    struct ib_rwq_ind_table_init_attr *init_attr,
				    struct ib_udata *udata);
	int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table);
	struct ib_dm *(*alloc_dm)(struct ib_device *device,
				  struct ib_ucontext *context,
				  struct ib_dm_alloc_attr *attr,
				  struct uverbs_attr_bundle *attrs);
	int (*dealloc_dm)(struct ib_dm *dm, struct uverbs_attr_bundle *attrs);
	struct ib_mr *(*reg_dm_mr)(struct ib_pd *pd, struct ib_dm *dm,
				   struct ib_dm_mr_attr *attr,
				   struct uverbs_attr_bundle *attrs);
	int (*create_counters)(struct ib_counters *counters,
			       struct uverbs_attr_bundle *attrs);
	int (*destroy_counters)(struct ib_counters *counters);
	int (*read_counters)(struct ib_counters *counters,
			     struct ib_counters_read_attr *counters_read_attr,
			     struct uverbs_attr_bundle *attrs);
	int (*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);

	/**
	 * alloc_hw_[device,port]_stats - Allocate a struct rdma_hw_stats and
	 *   fill in the driver initialized data.  The struct is kfree()'ed by
	 *   the sysfs core when the device is removed.  A lifespan of -1 in the
	 *   return struct tells the core to set a default lifespan.
	 */
	struct rdma_hw_stats *(*alloc_hw_device_stats)(struct ib_device *device);
	struct rdma_hw_stats *(*alloc_hw_port_stats)(struct ib_device *device,
						     u32 port_num);
	/**
	 * get_hw_stats - Fill in the counter value(s) in the stats struct.
	 * @index - The index in the value array we wish to have updated, or
	 *   num_counters if we want all stats updated
	 * Return codes -
	 *   < 0 - Error, no counters updated
	 *   index - Updated the single counter pointed to by index
	 *   num_counters - Updated all counters (will reset the timestamp
	 *     and prevent further calls for lifespan milliseconds)
	 * Drivers are allowed to update all counters in leiu of just the
	 *   one given in index at their option
	 */
	int (*get_hw_stats)(struct ib_device *device,
			    struct rdma_hw_stats *stats, u32 port, int index);

	/**
	 * modify_hw_stat - Modify the counter configuration
	 * @enable: true/false when enable/disable a counter
	 * Return codes - 0 on success or error code otherwise.
	 */
	int (*modify_hw_stat)(struct ib_device *device, u32 port,
			      unsigned int counter_index, bool enable);
	/**
	 * Allows rdma drivers to add their own restrack attributes.
	 */
	int (*fill_res_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr);
	int (*fill_res_mr_entry_raw)(struct sk_buff *msg, struct ib_mr *ibmr);
	int (*fill_res_cq_entry)(struct sk_buff *msg, struct ib_cq *ibcq);
	int (*fill_res_cq_entry_raw)(struct sk_buff *msg, struct ib_cq *ibcq);
	int (*fill_res_qp_entry)(struct sk_buff *msg, struct ib_qp *ibqp);
	int (*fill_res_qp_entry_raw)(struct sk_buff *msg, struct ib_qp *ibqp);
	int (*fill_res_cm_id_entry)(struct sk_buff *msg, struct rdma_cm_id *id);
	int (*fill_res_srq_entry)(struct sk_buff *msg, struct ib_srq *ib_srq);
	int (*fill_res_srq_entry_raw)(struct sk_buff *msg, struct ib_srq *ib_srq);

	/* Device lifecycle callbacks */
	/*
	 * Called after the device becomes registered, before clients are
	 * attached
	 */
	int (*enable_driver)(struct ib_device *dev);
	/*
	 * This is called as part of ib_dealloc_device().
	 */
	void (*dealloc_driver)(struct ib_device *dev);

	/* iWarp CM callbacks */
	void (*iw_add_ref)(struct ib_qp *qp);
	void (*iw_rem_ref)(struct ib_qp *qp);
	struct ib_qp *(*iw_get_qp)(struct ib_device *device, int qpn);
	int (*iw_connect)(struct iw_cm_id *cm_id,
			  struct iw_cm_conn_param *conn_param);
	int (*iw_accept)(struct iw_cm_id *cm_id,
			 struct iw_cm_conn_param *conn_param);
	int (*iw_reject)(struct iw_cm_id *cm_id, const void *pdata,
			 u8 pdata_len);
	int (*iw_create_listen)(struct iw_cm_id *cm_id, int backlog);
	int (*iw_destroy_listen)(struct iw_cm_id *cm_id);
	/**
	 * counter_bind_qp - Bind a QP to a counter.
	 * @counter - The counter to be bound. If counter->id is zero then
	 *   the driver needs to allocate a new counter and set counter->id
	 */
	int (*counter_bind_qp)(struct rdma_counter *counter, struct ib_qp *qp);
	/**
	 * counter_unbind_qp - Unbind the qp from the dynamically-allocated
	 *   counter and bind it onto the default one
	 */
	int (*counter_unbind_qp)(struct ib_qp *qp);
	/**
	 * counter_dealloc -De-allocate the hw counter
	 */
	int (*counter_dealloc)(struct rdma_counter *counter);
	/**
	 * counter_alloc_stats - Allocate a struct rdma_hw_stats and fill in
	 * the driver initialized data.
	 */
	struct rdma_hw_stats *(*counter_alloc_stats)(
		struct rdma_counter *counter);
	/**
	 * counter_update_stats - Query the stats value of this counter
	 */
	int (*counter_update_stats)(struct rdma_counter *counter);

	/**
	 * Allows rdma drivers to add their own restrack attributes
	 * dumped via 'rdma stat' iproute2 command.
	 */
	int (*fill_stat_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr);

	/* query driver for its ucontext properties */
	int (*query_ucontext)(struct ib_ucontext *context,
			      struct uverbs_attr_bundle *attrs);

	/*
	 * Provide NUMA node. This API exists for rdmavt/hfi1 only.
	 * Everyone else relies on Linux memory management model.
	 */
	int (*get_numa_node)(struct ib_device *dev);

	/**
	 * add_sub_dev - Add a sub IB device
	 */
	struct ib_device *(*add_sub_dev)(struct ib_device *parent,
					 enum rdma_nl_dev_type type,
					 const char *name);

	/**
	 * del_sub_dev - Delete a sub IB device
	 */
	void (*del_sub_dev)(struct ib_device *sub_dev);

	DECLARE_RDMA_OBJ_SIZE(ib_ah);
	DECLARE_RDMA_OBJ_SIZE(ib_counters);
	DECLARE_RDMA_OBJ_SIZE(ib_cq);
	DECLARE_RDMA_OBJ_SIZE(ib_mw);
	DECLARE_RDMA_OBJ_SIZE(ib_pd);
	DECLARE_RDMA_OBJ_SIZE(ib_qp);
	DECLARE_RDMA_OBJ_SIZE(ib_rwq_ind_table);
	DECLARE_RDMA_OBJ_SIZE(ib_srq);
	DECLARE_RDMA_OBJ_SIZE(ib_ucontext);
	DECLARE_RDMA_OBJ_SIZE(ib_xrcd);
};

struct ib_core_device {
	/* device must be the first element in structure until,
	 * union of ib_core_device and device exists in ib_device.
	 */
	struct device dev;
	possible_net_t rdma_net;
	struct kobject *ports_kobj;
	struct list_head port_list;
	struct ib_device *owner; /* reach back to owner ib_device */
};

struct rdma_restrack_root;
struct ib_device {
	/* Do not access @dma_device directly from ULP nor from HW drivers. */
	struct device                *dma_device;
	struct ib_device_ops	     ops;
	char                          name[IB_DEVICE_NAME_MAX];
	struct rcu_head rcu_head;

	struct list_head              event_handler_list;
	/* Protects event_handler_list */
	struct rw_semaphore event_handler_rwsem;

	/* Protects QP's event_handler calls and open_qp list */
	spinlock_t qp_open_list_lock;

	struct rw_semaphore	      client_data_rwsem;
	struct xarray                 client_data;
	struct mutex                  unregistration_lock;

	/* Synchronize GID, Pkey cache entries, subnet prefix, LMC */
	rwlock_t cache_lock;
	/**
	 * port_data is indexed by port number
	 */
	struct ib_port_data *port_data;

	int			      num_comp_vectors;

	union {
		struct device		dev;
		struct ib_core_device	coredev;
	};

	/* First group is for device attributes,
	 * Second group is for driver provided attributes (optional).
	 * Third group is for the hw_stats
	 * It is a NULL terminated array.
	 */
	const struct attribute_group	*groups[4];

	u64			     uverbs_cmd_mask;

	char			     node_desc[IB_DEVICE_NODE_DESC_MAX];
	__be64			     node_guid;
	u32			     local_dma_lkey;
	u16                          is_switch:1;
	/* Indicates kernel verbs support, should not be used in drivers */
	u16                          kverbs_provider:1;
	/* CQ adaptive moderation (RDMA DIM) */
	u16                          use_cq_dim:1;
	u8                           node_type;
	u32			     phys_port_cnt;
	struct ib_device_attr        attrs;
	struct hw_stats_device_data *hw_stats_data;

#ifdef CONFIG_CGROUP_RDMA
	struct rdmacg_device         cg_device;
#endif

	u32                          index;

	spinlock_t                   cq_pools_lock;
	struct list_head             cq_pools[IB_POLL_LAST_POOL_TYPE + 1];

	struct rdma_restrack_root *res;

	const struct uapi_definition   *driver_def;

	/*
	 * Positive refcount indicates that the device is currently
	 * registered and cannot be unregistered.
	 */
	refcount_t refcount;
	struct completion unreg_completion;
	struct work_struct unregistration_work;

	const struct rdma_link_ops *link_ops;

	/* Protects compat_devs xarray modifications */
	struct mutex compat_devs_mutex;
	/* Maintains compat devices for each net namespace */
	struct xarray compat_devs;

	/* Used by iWarp CM */
	char iw_ifname[IFNAMSIZ];
	u32 iw_driver_flags;
	u32 lag_flags;

	/* A parent device has a list of sub-devices */
	struct mutex subdev_lock;
	struct list_head subdev_list_head;

	/* A sub device has a type and a parent */
	enum rdma_nl_dev_type type;
	struct ib_device *parent;
	struct list_head subdev_list;

	enum rdma_nl_name_assign_type name_assign_type;
};

static inline void *rdma_zalloc_obj(struct ib_device *dev, size_t size,
				    gfp_t gfp, bool is_numa_aware)
{
	if (is_numa_aware && dev->ops.get_numa_node)
		return kzalloc_node(size, gfp, dev->ops.get_numa_node(dev));

	return kzalloc(size, gfp);
}

struct ib_client_nl_info;
struct ib_client {
	const char *name;
	int (*add)(struct ib_device *ibdev);
	void (*remove)(struct ib_device *, void *client_data);
	void (*rename)(struct ib_device *dev, void *client_data);
	int (*get_nl_info)(struct ib_device *ibdev, void *client_data,
			   struct ib_client_nl_info *res);
	int (*get_global_nl_info)(struct ib_client_nl_info *res);

	/* Returns the net_dev belonging to this ib_client and matching the
	 * given parameters.
	 * @dev:	 An RDMA device that the net_dev use for communication.
	 * @port:	 A physical port number on the RDMA device.
	 * @pkey:	 P_Key that the net_dev uses if applicable.
	 * @gid:	 A GID that the net_dev uses to communicate.
	 * @addr:	 An IP address the net_dev is configured with.
	 * @client_data: The device's client data set by ib_set_client_data().
	 *
	 * An ib_client that implements a net_dev on top of RDMA devices
	 * (such as IP over IB) should implement this callback, allowing the
	 * rdma_cm module to find the right net_dev for a given request.
	 *
	 * The caller is responsible for calling dev_put on the returned
	 * netdev. */
	struct net_device *(*get_net_dev_by_params)(
			struct ib_device *dev,
			u32 port,
			u16 pkey,
			const union ib_gid *gid,
			const struct sockaddr *addr,
			void *client_data);

	refcount_t uses;
	struct completion uses_zero;
	u32 client_id;

	/* kverbs are not required by the client */
	u8 no_kverbs_req:1;
};

/*
 * IB block DMA iterator
 *
 * Iterates the DMA-mapped SGL in contiguous memory blocks aligned
 * to a HW supported page size.
 */
struct ib_block_iter {
	/* internal states */
	struct scatterlist *__sg;	/* sg holding the current aligned block */
	dma_addr_t __dma_addr;		/* unaligned DMA address of this block */
	size_t __sg_numblocks;		/* ib_umem_num_dma_blocks() */
	unsigned int __sg_nents;	/* number of SG entries */
	unsigned int __sg_advance;	/* number of bytes to advance in sg in next step */
	unsigned int __pg_bit;		/* alignment of current block */
};

struct ib_device *_ib_alloc_device(size_t size);
#define ib_alloc_device(drv_struct, member)                                    \
	container_of(_ib_alloc_device(sizeof(struct drv_struct) +              \
				      BUILD_BUG_ON_ZERO(offsetof(              \
					      struct drv_struct, member))),    \
		     struct drv_struct, member)

void ib_dealloc_device(struct ib_device *device);

void ib_get_device_fw_str(struct ib_device *device, char *str);

int ib_register_device(struct ib_device *device, const char *name,
		       struct device *dma_device);
void ib_unregister_device(struct ib_device *device);
void ib_unregister_driver(enum rdma_driver_id driver_id);
void ib_unregister_device_and_put(struct ib_device *device);
void ib_unregister_device_queued(struct ib_device *ib_dev);

int ib_register_client   (struct ib_client *client);
void ib_unregister_client(struct ib_client *client);

void __rdma_block_iter_start(struct ib_block_iter *biter,
			     struct scatterlist *sglist,
			     unsigned int nents,
			     unsigned long pgsz);
bool __rdma_block_iter_next(struct ib_block_iter *biter);

/**
 * rdma_block_iter_dma_address - get the aligned dma address of the current
 * block held by the block iterator.
 * @biter: block iterator holding the memory block
 */
static inline dma_addr_t
rdma_block_iter_dma_address(struct ib_block_iter *biter)
{
	return biter->__dma_addr & ~(BIT_ULL(biter->__pg_bit) - 1);
}

/**
 * rdma_for_each_block - iterate over contiguous memory blocks of the sg list
 * @sglist: sglist to iterate over
 * @biter: block iterator holding the memory block
 * @nents: maximum number of sg entries to iterate over
 * @pgsz: best HW supported page size to use
 *
 * Callers may use rdma_block_iter_dma_address() to get each
 * blocks aligned DMA address.
 */
#define rdma_for_each_block(sglist, biter, nents, pgsz)		\
	for (__rdma_block_iter_start(biter, sglist, nents,	\
				     pgsz);			\
	     __rdma_block_iter_next(biter);)

/**
 * ib_get_client_data - Get IB client context
 * @device:Device to get context for
 * @client:Client to get context for
 *
 * ib_get_client_data() returns the client context data set with
 * ib_set_client_data(). This can only be called while the client is
 * registered to the device, once the ib_client remove() callback returns this
 * cannot be called.
 */
static inline void *ib_get_client_data(struct ib_device *device,
				       struct ib_client *client)
{
	return xa_load(&device->client_data, client->client_id);
}
void  ib_set_client_data(struct ib_device *device, struct ib_client *client,
			 void *data);
void ib_set_device_ops(struct ib_device *device,
		       const struct ib_device_ops *ops);

int rdma_user_mmap_io(struct ib_ucontext *ucontext, struct vm_area_struct *vma,
		      unsigned long pfn, unsigned long size, pgprot_t prot,
		      struct rdma_user_mmap_entry *entry);
int rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext,
				struct rdma_user_mmap_entry *entry,
				size_t length);
int rdma_user_mmap_entry_insert_range(struct ib_ucontext *ucontext,
				      struct rdma_user_mmap_entry *entry,
				      size_t length, u32 min_pgoff,
				      u32 max_pgoff);

static inline int
rdma_user_mmap_entry_insert_exact(struct ib_ucontext *ucontext,
				  struct rdma_user_mmap_entry *entry,
				  size_t length, u32 pgoff)
{
	return rdma_user_mmap_entry_insert_range(ucontext, entry, length, pgoff,
						 pgoff);
}

struct rdma_user_mmap_entry *
rdma_user_mmap_entry_get_pgoff(struct ib_ucontext *ucontext,
			       unsigned long pgoff);
struct rdma_user_mmap_entry *
rdma_user_mmap_entry_get(struct ib_ucontext *ucontext,
			 struct vm_area_struct *vma);
void rdma_user_mmap_entry_put(struct rdma_user_mmap_entry *entry);

void rdma_user_mmap_entry_remove(struct rdma_user_mmap_entry *entry);

static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t len)
{
	return copy_from_user(dest, udata->inbuf, len) ? -EFAULT : 0;
}

static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len)
{
	return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0;
}

static inline bool ib_is_buffer_cleared(const void __user *p,
					size_t len)
{
	bool ret;
	u8 *buf;

	if (len > USHRT_MAX)
		return false;

	buf = memdup_user(p, len);
	if (IS_ERR(buf))
		return false;

	ret = !memchr_inv(buf, 0, len);
	kfree(buf);
	return ret;
}

static inline bool ib_is_udata_cleared(struct ib_udata *udata,
				       size_t offset,
				       size_t len)
{
	return ib_is_buffer_cleared(udata->inbuf + offset, len);
}

/**
 * ib_modify_qp_is_ok - Check that the supplied attribute mask
 * contains all required attributes and no attributes not allowed for
 * the given QP state transition.
 * @cur_state: Current QP state
 * @next_state: Next QP state
 * @type: QP type
 * @mask: Mask of supplied QP attributes
 *
 * This function is a helper function that a low-level driver's
 * modify_qp method can use to validate the consumer's input.  It
 * checks that cur_state and next_state are valid QP states, that a
 * transition from cur_state to next_state is allowed by the IB spec,
 * and that the attribute mask supplied is allowed for the transition.
 */
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);

void ib_register_event_handler(struct ib_event_handler *event_handler);
void ib_unregister_event_handler(struct ib_event_handler *event_handler);
void ib_dispatch_event(const struct ib_event *event);

int ib_query_port(struct ib_device *device,
		  u32 port_num, struct ib_port_attr *port_attr);

enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device,
					       u32 port_num);

/**
 * rdma_cap_ib_switch - Check if the device is IB switch
 * @device: Device to check
 *
 * Device driver is responsible for setting is_switch bit on
 * in ib_device structure at init time.
 *
 * Return: true if the device is IB switch.
 */
static inline bool rdma_cap_ib_switch(const struct ib_device *device)
{
	return device->is_switch;
}

/**
 * rdma_start_port - Return the first valid port number for the device
 * specified
 *
 * @device: Device to be checked
 *
 * Return start port number
 */
static inline u32 rdma_start_port(const struct ib_device *device)
{
	return rdma_cap_ib_switch(device) ? 0 : 1;
}

/**
 * rdma_for_each_port - Iterate over all valid port numbers of the IB device
 * @device - The struct ib_device * to iterate over
 * @iter - The unsigned int to store the port number
 */
#define rdma_for_each_port(device, iter)                                       \
	for (iter = rdma_start_port(device +				       \
				    BUILD_BUG_ON_ZERO(!__same_type(u32,	       \
								   iter)));    \
	     iter <= rdma_end_port(device); iter++)

/**
 * rdma_end_port - Return the last valid port number for the device
 * specified
 *
 * @device: Device to be checked
 *
 * Return last port number
 */
static inline u32 rdma_end_port(const struct ib_device *device)
{
	return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt;
}

static inline int rdma_is_port_valid(const struct ib_device *device,
				     unsigned int port)
{
	return (port >= rdma_start_port(device) &&
		port <= rdma_end_port(device));
}

static inline bool rdma_is_grh_required(const struct ib_device *device,
					u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_PORT_IB_GRH_REQUIRED;
}

static inline bool rdma_protocol_ib(const struct ib_device *device,
				    u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_PROT_IB;
}

static inline bool rdma_protocol_roce(const struct ib_device *device,
				      u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       (RDMA_CORE_CAP_PROT_ROCE | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP);
}

static inline bool rdma_protocol_roce_udp_encap(const struct ib_device *device,
						u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP;
}

static inline bool rdma_protocol_roce_eth_encap(const struct ib_device *device,
						u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_PROT_ROCE;
}

static inline bool rdma_protocol_iwarp(const struct ib_device *device,
				       u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_PROT_IWARP;
}

static inline bool rdma_ib_or_roce(const struct ib_device *device,
				   u32 port_num)
{
	return rdma_protocol_ib(device, port_num) ||
		rdma_protocol_roce(device, port_num);
}

static inline bool rdma_protocol_raw_packet(const struct ib_device *device,
					    u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_PROT_RAW_PACKET;
}

static inline bool rdma_protocol_usnic(const struct ib_device *device,
				       u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_PROT_USNIC;
}

/**
 * rdma_cap_ib_mad - Check if the port of a device supports Infiniband
 * Management Datagrams.
 * @device: Device to check
 * @port_num: Port number to check
 *
 * Management Datagrams (MAD) are a required part of the InfiniBand
 * specification and are supported on all InfiniBand devices.  A slightly
 * extended version are also supported on OPA interfaces.
 *
 * Return: true if the port supports sending/receiving of MAD packets.
 */
static inline bool rdma_cap_ib_mad(const struct ib_device *device, u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_IB_MAD;
}

/**
 * rdma_cap_opa_mad - Check if the port of device provides support for OPA
 * Management Datagrams.
 * @device: Device to check
 * @port_num: Port number to check
 *
 * Intel OmniPath devices extend and/or replace the InfiniBand Management
 * datagrams with their own versions.  These OPA MADs share many but not all of
 * the characteristics of InfiniBand MADs.
 *
 * OPA MADs differ in the following ways:
 *
 *    1) MADs are variable size up to 2K
 *       IBTA defined MADs remain fixed at 256 bytes
 *    2) OPA SMPs must carry valid PKeys
 *    3) OPA SMP packets are a different format
 *
 * Return: true if the port supports OPA MAD packet formats.
 */
static inline bool rdma_cap_opa_mad(struct ib_device *device, u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
		RDMA_CORE_CAP_OPA_MAD;
}

/**
 * rdma_cap_ib_smi - Check if the port of a device provides an Infiniband
 * Subnet Management Agent (SMA) on the Subnet Management Interface (SMI).
 * @device: Device to check
 * @port_num: Port number to check
 *
 * Each InfiniBand node is required to provide a Subnet Management Agent
 * that the subnet manager can access.  Prior to the fabric being fully
 * configured by the subnet manager, the SMA is accessed via a well known
 * interface called the Subnet Management Interface (SMI).  This interface
 * uses directed route packets to communicate with the SM to get around the
 * chicken and egg problem of the SM needing to know what's on the fabric
 * in order to configure the fabric, and needing to configure the fabric in
 * order to send packets to the devices on the fabric.  These directed
 * route packets do not need the fabric fully configured in order to reach
 * their destination.  The SMI is the only method allowed to send
 * directed route packets on an InfiniBand fabric.
 *
 * Return: true if the port provides an SMI.
 */
static inline bool rdma_cap_ib_smi(const struct ib_device *device, u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_IB_SMI;
}

/**
 * rdma_cap_ib_cm - Check if the port of device has the capability Infiniband
 * Communication Manager.
 * @device: Device to check
 * @port_num: Port number to check
 *
 * The InfiniBand Communication Manager is one of many pre-defined General
 * Service Agents (GSA) that are accessed via the General Service
 * Interface (GSI).  It's role is to facilitate establishment of connections
 * between nodes as well as other management related tasks for established
 * connections.
 *
 * Return: true if the port supports an IB CM (this does not guarantee that
 * a CM is actually running however).
 */
static inline bool rdma_cap_ib_cm(const struct ib_device *device, u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_IB_CM;
}

/**
 * rdma_cap_iw_cm - Check if the port of device has the capability IWARP
 * Communication Manager.
 * @device: Device to check
 * @port_num: Port number to check
 *
 * Similar to above, but specific to iWARP connections which have a different
 * managment protocol than InfiniBand.
 *
 * Return: true if the port supports an iWARP CM (this does not guarantee that
 * a CM is actually running however).
 */
static inline bool rdma_cap_iw_cm(const struct ib_device *device, u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_IW_CM;
}

/**
 * rdma_cap_ib_sa - Check if the port of device has the capability Infiniband
 * Subnet Administration.
 * @device: Device to check
 * @port_num: Port number to check
 *
 * An InfiniBand Subnet Administration (SA) service is a pre-defined General
 * Service Agent (GSA) provided by the Subnet Manager (SM).  On InfiniBand
 * fabrics, devices should resolve routes to other hosts by contacting the
 * SA to query the proper route.
 *
 * Return: true if the port should act as a client to the fabric Subnet
 * Administration interface.  This does not imply that the SA service is
 * running locally.
 */
static inline bool rdma_cap_ib_sa(const struct ib_device *device, u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_IB_SA;
}

/**
 * rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband
 * Multicast.
 * @device: Device to check
 * @port_num: Port number to check
 *
 * InfiniBand multicast registration is more complex than normal IPv4 or
 * IPv6 multicast registration.  Each Host Channel Adapter must register
 * with the Subnet Manager when it wishes to join a multicast group.  It
 * should do so only once regardless of how many queue pairs it subscribes
 * to this group.  And it should leave the group only after all queue pairs
 * attached to the group have been detached.
 *
 * Return: true if the port must undertake the additional adminstrative
 * overhead of registering/unregistering with the SM and tracking of the
 * total number of queue pairs attached to the multicast group.
 */
static inline bool rdma_cap_ib_mcast(const struct ib_device *device,
				     u32 port_num)
{
	return rdma_cap_ib_sa(device, port_num);
}

/**
 * rdma_cap_af_ib - Check if the port of device has the capability
 * Native Infiniband Address.
 * @device: Device to check
 * @port_num: Port number to check
 *
 * InfiniBand addressing uses a port's GUID + Subnet Prefix to make a default
 * GID.  RoCE uses a different mechanism, but still generates a GID via
 * a prescribed mechanism and port specific data.
 *
 * Return: true if the port uses a GID address to identify devices on the
 * network.
 */
static inline bool rdma_cap_af_ib(const struct ib_device *device, u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_AF_IB;
}

/**
 * rdma_cap_eth_ah - Check if the port of device has the capability
 * Ethernet Address Handle.
 * @device: Device to check
 * @port_num: Port number to check
 *
 * RoCE is InfiniBand over Ethernet, and it uses a well defined technique
 * to fabricate GIDs over Ethernet/IP specific addresses native to the
 * port.  Normally, packet headers are generated by the sending host
 * adapter, but when sending connectionless datagrams, we must manually
 * inject the proper headers for the fabric we are communicating over.
 *
 * Return: true if we are running as a RoCE port and must force the
 * addition of a Global Route Header built from our Ethernet Address
 * Handle into our header list for connectionless packets.
 */
static inline bool rdma_cap_eth_ah(const struct ib_device *device, u32 port_num)
{
	return device->port_data[port_num].immutable.core_cap_flags &
	       RDMA_CORE_CAP_ETH_AH;
}

/**
 * rdma_cap_opa_ah - Check if the port of device supports
 * OPA Address handles
 * @device: Device to check
 * @port_num: Port number to check
 *
 * Return: true if we are running on an OPA device which supports
 * the extended OPA addressing.
 */
static inline bool rdma_cap_opa_ah(struct ib_device *device, u32 port_num)
{
	return (device->port_data[port_num].immutable.core_cap_flags &
		RDMA_CORE_CAP_OPA_AH) == RDMA_CORE_CAP_OPA_AH;
}

/**
 * rdma_max_mad_size - Return the max MAD size required by this RDMA Port.
 *
 * @device: Device
 * @port_num: Port number
 *
 * This MAD size includes the MAD headers and MAD payload.  No other headers
 * are included.
 *
 * Return the max MAD size required by the Port.  Will return 0 if the port
 * does not support MADs
 */
static inline size_t rdma_max_mad_size(const struct ib_device *device,
				       u32 port_num)
{
	return device->port_data[port_num].immutable.max_mad_size;
}

/**
 * rdma_cap_roce_gid_table - Check if the port of device uses roce_gid_table
 * @device: Device to check
 * @port_num: Port number to check
 *
 * RoCE GID table mechanism manages the various GIDs for a device.
 *
 * NOTE: if allocating the port's GID table has failed, this call will still
 * return true, but any RoCE GID table API will fail.
 *
 * Return: true if the port uses RoCE GID table mechanism in order to manage
 * its GIDs.
 */
static inline bool rdma_cap_roce_gid_table(const struct ib_device *device,
					   u32 port_num)
{
	return rdma_protocol_roce(device, port_num) &&
		device->ops.add_gid && device->ops.del_gid;
}

/*
 * Check if the device supports READ W/ INVALIDATE.
 */
static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num)
{
	/*
	 * iWarp drivers must support READ W/ INVALIDATE.  No other protocol
	 * has support for it yet.
	 */
	return rdma_protocol_iwarp(dev, port_num);
}

/**
 * rdma_core_cap_opa_port - Return whether the RDMA Port is OPA or not.
 * @device: Device
 * @port_num: 1 based Port number
 *
 * Return true if port is an Intel OPA port , false if not
 */
static inline bool rdma_core_cap_opa_port(struct ib_device *device,
					  u32 port_num)
{
	return (device->port_data[port_num].immutable.core_cap_flags &
		RDMA_CORE_PORT_INTEL_OPA) == RDMA_CORE_PORT_INTEL_OPA;
}

/**
 * rdma_mtu_enum_to_int - Return the mtu of the port as an integer value.
 * @device: Device
 * @port_num: Port number
 * @mtu: enum value of MTU
 *
 * Return the MTU size supported by the port as an integer value. Will return
 * -1 if enum value of mtu is not supported.
 */
static inline int rdma_mtu_enum_to_int(struct ib_device *device, u32 port,
				       int mtu)
{
	if (rdma_core_cap_opa_port(device, port))
		return opa_mtu_enum_to_int((enum opa_mtu)mtu);
	else
		return ib_mtu_enum_to_int((enum ib_mtu)mtu);
}

/**
 * rdma_mtu_from_attr - Return the mtu of the port from the port attribute.
 * @device: Device
 * @port_num: Port number
 * @attr: port attribute
 *
 * Return the MTU size supported by the port as an integer value.
 */
static inline int rdma_mtu_from_attr(struct ib_device *device, u32 port,
				     struct ib_port_attr *attr)
{
	if (rdma_core_cap_opa_port(device, port))
		return attr->phys_mtu;
	else
		return ib_mtu_enum_to_int(attr->max_mtu);
}

int ib_set_vf_link_state(struct ib_device *device, int vf, u32 port,
			 int state);
int ib_get_vf_config(struct ib_device *device, int vf, u32 port,
		     struct ifla_vf_info *info);
int ib_get_vf_stats(struct ib_device *device, int vf, u32 port,
		    struct ifla_vf_stats *stats);
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);
int ib_set_vf_guid(struct ib_device *device, int vf, u32 port, u64 guid,
		   int type);

int ib_query_pkey(struct ib_device *device,
		  u32 port_num, u16 index, u16 *pkey);

int ib_modify_device(struct ib_device *device,
		     int device_modify_mask,
		     struct ib_device_modify *device_modify);

int ib_modify_port(struct ib_device *device,
		   u32 port_num, int port_modify_mask,
		   struct ib_port_modify *port_modify);

int ib_find_gid(struct ib_device *device, union ib_gid *gid,
		u32 *port_num, u16 *index);

int ib_find_pkey(struct ib_device *device,
		 u32 port_num, u16 pkey, u16 *index);

enum ib_pd_flags {
	/*
	 * Create a memory registration for all memory in the system and place
	 * the rkey for it into pd->unsafe_global_rkey.  This can be used by
	 * ULPs to avoid the overhead of dynamic MRs.
	 *
	 * This flag is generally considered unsafe and must only be used in
	 * extremly trusted environments.  Every use of it will log a warning
	 * in the kernel log.
	 */
	IB_PD_UNSAFE_GLOBAL_RKEY	= 0x01,
};

struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags,
		const char *caller);

/**
 * ib_alloc_pd - Allocates an unused protection domain.
 * @device: The device on which to allocate the protection domain.
 * @flags: protection domain flags
 *
 * 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.
 */
#define ib_alloc_pd(device, flags) \
	__ib_alloc_pd((device), (flags), KBUILD_MODNAME)

int ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata);

/**
 * ib_dealloc_pd - Deallocate kernel PD
 * @pd: The protection domain
 *
 * NOTE: for user PD use ib_dealloc_pd_user with valid udata!
 */
static inline void ib_dealloc_pd(struct ib_pd *pd)
{
	int ret = ib_dealloc_pd_user(pd, NULL);

	WARN_ONCE(ret, "Destroy of kernel PD shouldn't fail");
}

enum rdma_create_ah_flags {
	/* In a sleepable context */
	RDMA_CREATE_AH_SLEEPABLE = BIT(0),
};

/**
 * 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).
 *
 * 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);

/**
 * 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);
/**
 * ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header
 *   work completion.
 * @hdr: the L3 header to parse
 * @net_type: type of header to parse
 * @sgid: place to store source gid
 * @dgid: place to store destination gid
 */
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);

/**
 * ib_get_rdma_header_version - Get the header version
 * @hdr: the L3 header to parse
 */
int ib_get_rdma_header_version(const union rdma_network_hdr *hdr);

/**
 * ib_init_ah_attr_from_wc - Initializes address handle attributes from a
 *   work completion.
 * @device: Device on which the received message arrived.
 * @port_num: Port on which the received message arrived.
 * @wc: Work completion associated with the received message.
 * @grh: References the received global route header.  This parameter is
 *   ignored unless the work completion indicates that the GRH is valid.
 * @ah_attr: Returned attributes that can be used when creating an address
 *   handle for replying to the message.
 * When ib_init_ah_attr_from_wc() returns success,
 * (a) for IB link layer it optionally contains a reference to SGID attribute
 * when GRH is present for IB link layer.
 * (b) for RoCE link layer it contains a reference to SGID attribute.
 * User must invoke rdma_cleanup_ah_attr_gid_attr() to release reference to SGID
 * attributes which are initialized using ib_init_ah_attr_from_wc().
 *
 */
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);

/**
 * ib_create_ah_from_wc - Creates an address handle associated with the
 *   sender of the specified work completion.
 * @pd: The protection domain associated with the address handle.
 * @wc: Work completion information associated with a received message.
 * @grh: References the received global route header.  This parameter is
 *   ignored unless the work completion indicates that the GRH is valid.
 * @port_num: The outbound port number to associate with the address.
 *
 * The address handle is used to reference a local or global destination
 * in all UD QP post sends.
 */
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);

/**
 * rdma_modify_ah - Modifies the address vector associated with an address
 *   handle.
 * @ah: The address handle to modify.
 * @ah_attr: The new address vector attributes to associate with the
 *   address handle.
 */
int rdma_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);

/**
 * rdma_query_ah - Queries the address vector associated with an address
 *   handle.
 * @ah: The address handle to query.
 * @ah_attr: The address vector attributes associated with the address
 *   handle.
 */
int rdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);

enum rdma_destroy_ah_flags {
	/* In a sleepable context */
	RDMA_DESTROY_AH_SLEEPABLE = BIT(0),
};

/**
 * rdma_destroy_ah_user - Destroys an address handle.
 * @ah: The address handle to destroy.
 * @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags).
 * @udata: Valid user data or NULL for kernel objects
 */
int rdma_destroy_ah_user(struct ib_ah *ah, u32 flags, struct ib_udata *udata);

/**
 * rdma_destroy_ah - Destroys an kernel address handle.
 * @ah: The address handle to destroy.
 * @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags).
 *
 * NOTE: for user ah use rdma_destroy_ah_user with valid udata!
 */
static inline void rdma_destroy_ah(struct ib_ah *ah, u32 flags)
{
	int ret = rdma_destroy_ah_user(ah, flags, NULL);

	WARN_ONCE(ret, "Destroy of kernel AH shouldn't fail");
}

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);
static inline struct ib_srq *
ib_create_srq(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr)
{
	if (!pd->device->ops.create_srq)
		return ERR_PTR(-EOPNOTSUPP);

	return ib_create_srq_user(pd, srq_init_attr, NULL, NULL);
}

/**
 * ib_modify_srq - Modifies the attributes for the specified SRQ.
 * @srq: The SRQ to modify.
 * @srq_attr: On input, specifies the SRQ attributes to modify.  On output,
 *   the current values of selected SRQ attributes are returned.
 * @srq_attr_mask: A bit-mask used to specify which attributes of the SRQ
 *   are being modified.
 *
 * The mask may contain IB_SRQ_MAX_WR to resize the SRQ and/or
 * IB_SRQ_LIMIT to set the SRQ's limit and request notification when
 * the number of receives queued drops below the limit.
 */
int ib_modify_srq(struct ib_srq *srq,
		  struct ib_srq_attr *srq_attr,
		  enum ib_srq_attr_mask srq_attr_mask);

/**
 * ib_query_srq - Returns the attribute list and current values for the
 *   specified SRQ.
 * @srq: The SRQ to query.
 * @srq_attr: The attributes of the specified SRQ.
 */
int ib_query_srq(struct ib_srq *srq,
		 struct ib_srq_attr *srq_attr);

/**
 * ib_destroy_srq_user - Destroys the specified SRQ.
 * @srq: The SRQ to destroy.
 * @udata: Valid user data or NULL for kernel objects
 */
int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata);

/**
 * ib_destroy_srq - Destroys the specified kernel SRQ.
 * @srq: The SRQ to destroy.
 *
 * NOTE: for user srq use ib_destroy_srq_user with valid udata!
 */
static inline void ib_destroy_srq(struct ib_srq *srq)
{
	int ret = ib_destroy_srq_user(srq, NULL);

	WARN_ONCE(ret, "Destroy of kernel SRQ shouldn't fail");
}

/**
 * ib_post_srq_recv - Posts a list of work requests to the specified SRQ.
 * @srq: The SRQ to post the work request on.
 * @recv_wr: A list of work requests to post on the receive queue.
 * @bad_recv_wr: On an immediate failure, this parameter will reference
 *   the work request that failed to be posted on the QP.
 */
static inline int ib_post_srq_recv(struct ib_srq *srq,
				   const struct ib_recv_wr *recv_wr,
				   const struct ib_recv_wr **bad_recv_wr)
{
	const struct ib_recv_wr *dummy;

	return srq->device->ops.post_srq_recv(srq, recv_wr,
					      bad_recv_wr ? : &dummy);
}

struct ib_qp *ib_create_qp_kernel(struct ib_pd *pd,
				  struct ib_qp_init_attr *qp_init_attr,
				  const char *caller);
/**
 * ib_create_qp - Creates a kernel QP associated with the specific protection
 * domain.
 * @pd: The protection domain associated with the QP.
 * @init_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.
 */
static inline struct ib_qp *ib_create_qp(struct ib_pd *pd,
					 struct ib_qp_init_attr *init_attr)
{
	return ib_create_qp_kernel(pd, init_attr, KBUILD_MODNAME);
}

/**
 * ib_modify_qp_with_udata - Modifies the attributes for the specified QP.
 * @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 *qp,
			    struct ib_qp_attr *attr,
			    int attr_mask,
			    struct ib_udata *udata);

/**
 * ib_modify_qp - Modifies the attributes for the specified QP and then
 *   transitions the QP to the given state.
 * @qp: The QP to modify.
 * @qp_attr: On input, specifies the QP attributes to modify.  On output,
 *   the current values of selected QP attributes are returned.
 * @qp_attr_mask: A bit-mask used to specify which attributes of the QP
 *   are being modified.
 */
int ib_modify_qp(struct ib_qp *qp,
		 struct ib_qp_attr *qp_attr,
		 int qp_attr_mask);

/**
 * ib_query_qp - Returns the attribute list and current values for the
 *   specified QP.
 * @qp: The QP to query.
 * @qp_attr: The attributes of the specified QP.
 * @qp_attr_mask: A bit-mask used to select specific attributes to query.
 * @qp_init_attr: Additional attributes of the selected QP.
 *
 * The qp_attr_mask may be used to limit the query to gathering only the
 * selected attributes.
 */
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);

/**
 * ib_destroy_qp - Destroys the specified QP.
 * @qp: The QP to destroy.
 * @udata: Valid udata or NULL for kernel objects
 */
int ib_destroy_qp_user(struct ib_qp *qp, struct ib_udata *udata);

/**
 * ib_destroy_qp - Destroys the specified kernel QP.
 * @qp: The QP to destroy.
 *
 * NOTE: for user qp use ib_destroy_qp_user with valid udata!
 */
static inline int ib_destroy_qp(struct ib_qp *qp)
{
	return ib_destroy_qp_user(qp, NULL);
}

/**
 * ib_open_qp - Obtain a reference to an existing sharable QP.
 * @xrcd - XRC domain
 * @qp_open_attr: Attributes identifying the QP to open.
 *
 * Returns a reference to a sharable QP.
 */
struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd,
			 struct ib_qp_open_attr *qp_open_attr);

/**
 * ib_close_qp - Release an external reference to a QP.
 * @qp: The QP handle to release
 *
 * The opened QP handle is released by the caller.  The underlying
 * shared QP is not destroyed until all internal references are released.
 */
int ib_close_qp(struct ib_qp *qp);

/**
 * ib_post_send - Posts a list of work requests to the send queue of
 *   the specified QP.
 * @qp: The QP to post the work request on.
 * @send_wr: A list of work requests to post on the send queue.
 * @bad_send_wr: On an immediate failure, this parameter will reference
 *   the work request that failed to be posted on the QP.
 *
 * While IBA Vol. 1 section 11.4.1.1 specifies that if an immediate
 * error is returned, the QP state shall not be affected,
 * ib_post_send() will return an immediate error after queueing any
 * earlier work requests in the list.
 */
static inline int ib_post_send(struct ib_qp *qp,
			       const struct ib_send_wr *send_wr,
			       const struct ib_send_wr **bad_send_wr)
{
	const struct ib_send_wr *dummy;

	return qp->device->ops.post_send(qp, send_wr, bad_send_wr ? : &dummy);
}

/**
 * ib_post_recv - Posts a list of work requests to the receive queue of
 *   the specified QP.
 * @qp: The QP to post the work request on.
 * @recv_wr: A list of work requests to post on the receive queue.
 * @bad_recv_wr: On an immediate failure, this parameter will reference
 *   the work request that failed to be posted on the QP.
 */
static inline int ib_post_recv(struct ib_qp *qp,
			       const struct ib_recv_wr *recv_wr,
			       const struct ib_recv_wr **bad_recv_wr)
{
	const struct ib_recv_wr *dummy;

	return qp->device->ops.post_recv(qp, recv_wr, bad_recv_wr ? : &dummy);
}

struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe,
			    int comp_vector, enum ib_poll_context poll_ctx,
			    const char *caller);
static inline struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private,
					int nr_cqe, int comp_vector,
					enum ib_poll_context poll_ctx)
{
	return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx,
			     KBUILD_MODNAME);
}

struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private,
				int nr_cqe, enum ib_poll_context poll_ctx,
				const char *caller);

/**
 * ib_alloc_cq_any: Allocate kernel CQ
 * @dev: The IB device
 * @private: Private data attached to the CQE
 * @nr_cqe: Number of CQEs in the CQ
 * @poll_ctx: Context used for polling the CQ
 */
static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev,
					    void *private, int nr_cqe,
					    enum ib_poll_context poll_ctx)
{
	return __ib_alloc_cq_any(dev, private, nr_cqe, poll_ctx,
				 KBUILD_MODNAME);
}

void ib_free_cq(struct ib_cq *cq);
int ib_process_cq_direct(struct ib_cq *cq, int budget);

/**
 * ib_create_cq - Creates a CQ on the specified device.
 * @device: The device on which to create the CQ.
 * @comp_handler: A user-specified callback that is invoked when a
 *   completion event occurs on the CQ.
 * @event_handler: A user-specified callback that is invoked when an
 *   asynchronous event not associated with a completion occurs on the CQ.
 * @cq_context: Context associated with the CQ returned to the user via
 *   the associated completion and event handlers.
 * @cq_attr: The attributes the CQ should be created upon.
 *
 * Users can examine the cq structure to determine the actual CQ size.
 */
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);
#define ib_create_cq(device, cmp_hndlr, evt_hndlr, cq_ctxt, cq_attr) \
	__ib_create_cq((device), (cmp_hndlr), (evt_hndlr), (cq_ctxt), (cq_attr), KBUILD_MODNAME)

/**
 * ib_resize_cq - Modifies the capacity of the CQ.
 * @cq: The CQ to resize.
 * @cqe: The minimum size of the CQ.
 *
 * Users can examine the cq structure to determine the actual CQ size.
 */
int ib_resize_cq(struct ib_cq *cq, int cqe);

/**
 * rdma_set_cq_moderation - Modifies moderation params of the CQ
 * @cq: The CQ to modify.
 * @cq_count: number of CQEs that will trigger an event
 * @cq_period: max period of time in usec before triggering an event
 *
 */
int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period);

/**
 * ib_destroy_cq_user - Destroys the specified CQ.
 * @cq: The CQ to destroy.
 * @udata: Valid user data or NULL for kernel objects
 */
int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata);

/**
 * ib_destroy_cq - Destroys the specified kernel CQ.
 * @cq: The CQ to destroy.
 *
 * NOTE: for user cq use ib_destroy_cq_user with valid udata!
 */
static inline void ib_destroy_cq(struct ib_cq *cq)
{
	int ret = ib_destroy_cq_user(cq, NULL);

	WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail");
}

/**
 * ib_poll_cq - poll a CQ for completion(s)
 * @cq:the CQ being polled
 * @num_entries:maximum number of completions to return
 * @wc:array of at least @num_entries &struct ib_wc where completions
 *   will be returned
 *
 * Poll a CQ for (possibly multiple) completions.  If the return value
 * is < 0, an error occurred.  If the return value is >= 0, it is the
 * number of completions returned.  If the return value is
 * non-negative and < num_entries, then the CQ was emptied.
 */
static inline int ib_poll_cq(struct ib_cq *cq, int num_entries,
			     struct ib_wc *wc)
{
	return cq->device->ops.poll_cq(cq, num_entries, wc);
}

/**
 * ib_req_notify_cq - Request completion notification on a CQ.
 * @cq: The CQ to generate an event for.
 * @flags:
 *   Must contain exactly one of %IB_CQ_SOLICITED or %IB_CQ_NEXT_COMP
 *   to request an event on the next solicited event or next work
 *   completion at any type, respectively. %IB_CQ_REPORT_MISSED_EVENTS
 *   may also be |ed in to request a hint about missed events, as
 *   described below.
 *
 * Return Value:
 *    < 0 means an error occurred while requesting notification
 *   == 0 means notification was requested successfully, and if
 *        IB_CQ_REPORT_MISSED_EVENTS was passed in, then no events
 *        were missed and it is safe to wait for another event.  In
 *        this case is it guaranteed that any work completions added
 *        to the CQ since the last CQ poll will trigger a completion
 *        notification event.
 *    > 0 is only returned if IB_CQ_REPORT_MISSED_EVENTS was passed
 *        in.  It means that the consumer must poll the CQ again to
 *        make sure it is empty to avoid missing an event because of a
 *        race between requesting notification and an entry being
 *        added to the CQ.  This return value means it is possible
 *        (but not guaranteed) that a work completion has been added
 *        to the CQ since the last poll without triggering a
 *        completion notification event.
 */
static inline int ib_req_notify_cq(struct ib_cq *cq,
				   enum ib_cq_notify_flags flags)
{
	return cq->device->ops.req_notify_cq(cq, flags);
}

struct ib_cq *ib_cq_pool_get(struct ib_device *dev, unsigned int nr_cqe,
			     int comp_vector_hint,
			     enum ib_poll_context poll_ctx);

void ib_cq_pool_put(struct ib_cq *cq, unsigned int nr_cqe);

/*
 * Drivers that don't need a DMA mapping at the RDMA layer, set dma_device to
 * NULL. This causes the ib_dma* helpers to just stash the kernel virtual
 * address into the dma address.
 */
static inline bool ib_uses_virt_dma(struct ib_device *dev)
{
	return IS_ENABLED(CONFIG_INFINIBAND_VIRT_DMA) && !dev->dma_device;
}

/*
 * Check if a IB device's underlying DMA mapping supports P2PDMA transfers.
 */
static inline bool ib_dma_pci_p2p_dma_supported(struct ib_device *dev)
{
	if (ib_uses_virt_dma(dev))
		return false;

	return dma_pci_p2pdma_supported(dev->dma_device);
}

/**
 * ib_virt_dma_to_ptr - Convert a dma_addr to a kernel pointer
 * @dma_addr: The DMA address
 *
 * Used by ib_uses_virt_dma() devices to get back to the kernel pointer after
 * going through the dma_addr marshalling.
 */
static inline void *ib_virt_dma_to_ptr(u64 dma_addr)
{
	/* virt_dma mode maps the kvs's directly into the dma addr */
	return (void *)(uintptr_t)dma_addr;
}

/**
 * ib_virt_dma_to_page - Convert a dma_addr to a struct page
 * @dma_addr: The DMA address
 *
 * Used by ib_uses_virt_dma() device to get back to the struct page after going
 * through the dma_addr marshalling.
 */
static inline struct page *ib_virt_dma_to_page(u64 dma_addr)
{
	return virt_to_page(ib_virt_dma_to_ptr(dma_addr));
}

/**
 * ib_dma_mapping_error - check a DMA addr for error
 * @dev: The device for which the dma_addr was created
 * @dma_addr: The DMA address to check
 */
static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr)
{
	if (ib_uses_virt_dma(dev))
		return 0;
	return dma_mapping_error(dev->dma_device, dma_addr);
}

/**
 * ib_dma_map_single - Map a kernel virtual address to DMA address
 * @dev: The device for which the dma_addr is to be created
 * @cpu_addr: The kernel virtual address
 * @size: The size of the region in bytes
 * @direction: The direction of the DMA
 */
static inline u64 ib_dma_map_single(struct ib_device *dev,
				    void *cpu_addr, size_t size,
				    enum dma_data_direction direction)
{
	if (ib_uses_virt_dma(dev))
		return (uintptr_t)cpu_addr;
	return dma_map_single(dev->dma_device, cpu_addr, size, direction);
}

/**
 * ib_dma_unmap_single - Destroy a mapping created by ib_dma_map_single()
 * @dev: The device for which the DMA address was created
 * @addr: The DMA address
 * @size: The size of the region in bytes
 * @direction: The direction of the DMA
 */
static inline void ib_dma_unmap_single(struct ib_device *dev,
				       u64 addr, size_t size,
				       enum dma_data_direction direction)
{
	if (!ib_uses_virt_dma(dev))
		dma_unmap_single(dev->dma_device, addr, size, direction);
}

/**
 * ib_dma_map_page - Map a physical page to DMA address
 * @dev: The device for which the dma_addr is to be created
 * @page: The page to be mapped
 * @offset: The offset within the page
 * @size: The size of the region in bytes
 * @direction: The direction of the DMA
 */
static inline u64 ib_dma_map_page(struct ib_device *dev,
				  struct page *page,
				  unsigned long offset,
				  size_t size,
					 enum dma_data_direction direction)
{
	if (ib_uses_virt_dma(dev))
		return (uintptr_t)(page_address(page) + offset);
	return dma_map_page(dev->dma_device, page, offset, size, direction);
}

/**
 * ib_dma_unmap_page - Destroy a mapping created by ib_dma_map_page()
 * @dev: The device for which the DMA address was created
 * @addr: The DMA address
 * @size: The size of the region in bytes
 * @direction: The direction of the DMA
 */
static inline void ib_dma_unmap_page(struct ib_device *dev,
				     u64 addr, size_t size,
				     enum dma_data_direction direction)
{
	if (!ib_uses_virt_dma(dev))
		dma_unmap_page(dev->dma_device, addr, size, direction);
}

int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents);
static inline int ib_dma_map_sg_attrs(struct ib_device *dev,
				      struct scatterlist *sg, int nents,
				      enum dma_data_direction direction,
				      unsigned long dma_attrs)
{
	if (ib_uses_virt_dma(dev))
		return ib_dma_virt_map_sg(dev, sg, nents);
	return dma_map_sg_attrs(dev->dma_device, sg, nents, direction,
				dma_attrs);
}

static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev,
					 struct scatterlist *sg, int nents,
					 enum dma_data_direction direction,
					 unsigned long dma_attrs)
{
	if (!ib_uses_virt_dma(dev))
		dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction,
				   dma_attrs);
}

/**
 * ib_dma_map_sgtable_attrs - Map a scatter/gather table to DMA addresses
 * @dev: The device for which the DMA addresses are to be created
 * @sg: The sg_table object describing the buffer
 * @direction: The direction of the DMA
 * @attrs: Optional DMA attributes for the map operation
 */
static inline int ib_dma_map_sgtable_attrs(struct ib_device *dev,
					   struct sg_table *sgt,
					   enum dma_data_direction direction,
					   unsigned long dma_attrs)
{
	int nents;

	if (ib_uses_virt_dma(dev)) {
		nents = ib_dma_virt_map_sg(dev, sgt->sgl, sgt->orig_nents);
		if (!nents)
			return -EIO;
		sgt->nents = nents;
		return 0;
	}
	return dma_map_sgtable(dev->dma_device, sgt, direction, dma_attrs);
}

static inline void ib_dma_unmap_sgtable_attrs(struct ib_device *dev,
					      struct sg_table *sgt,
					      enum dma_data_direction direction,
					      unsigned long dma_attrs)
{
	if (!ib_uses_virt_dma(dev))
		dma_unmap_sgtable(dev->dma_device, sgt, direction, dma_attrs);
}

/**
 * ib_dma_map_sg - Map a scatter/gather list to DMA addresses
 * @dev: The device for which the DMA addresses are to be created
 * @sg: The array of scatter/gather entries
 * @nents: The number of scatter/gather entries
 * @direction: The direction of the DMA
 */
static inline int ib_dma_map_sg(struct ib_device *dev,
				struct scatterlist *sg, int nents,
				enum dma_data_direction direction)
{
	return ib_dma_map_sg_attrs(dev, sg, nents, direction, 0);
}

/**
 * ib_dma_unmap_sg - Unmap a scatter/gather list of DMA addresses
 * @dev: The device for which the DMA addresses were created
 * @sg: The array of scatter/gather entries
 * @nents: The number of scatter/gather entries
 * @direction: The direction of the DMA
 */
static inline void ib_dma_unmap_sg(struct ib_device *dev,
				   struct scatterlist *sg, int nents,
				   enum dma_data_direction direction)
{
	ib_dma_unmap_sg_attrs(dev, sg, nents, direction, 0);
}

/**
 * ib_dma_max_seg_size - Return the size limit of a single DMA transfer
 * @dev: The device to query
 *
 * The returned value represents a size in bytes.
 */
static inline unsigned int ib_dma_max_seg_size(struct ib_device *dev)
{
	if (ib_uses_virt_dma(dev))
		return UINT_MAX;
	return dma_get_max_seg_size(dev->dma_device);
}

/**
 * ib_dma_sync_single_for_cpu - Prepare DMA region to be accessed by CPU
 * @dev: The device for which the DMA address was created
 * @addr: The DMA address
 * @size: The size of the region in bytes
 * @dir: The direction of the DMA
 */
static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev,
					      u64 addr,
					      size_t size,
					      enum dma_data_direction dir)
{
	if (!ib_uses_virt_dma(dev))
		dma_sync_single_for_cpu(dev->dma_device, addr, size, dir);
}

/**
 * ib_dma_sync_single_for_device - Prepare DMA region to be accessed by device
 * @dev: The device for which the DMA address was created
 * @addr: The DMA address
 * @size: The size of the region in bytes
 * @dir: The direction of the DMA
 */
static inline void ib_dma_sync_single_for_device(struct ib_device *dev,
						 u64 addr,
						 size_t size,
						 enum dma_data_direction dir)
{
	if (!ib_uses_virt_dma(dev))
		dma_sync_single_for_device(dev->dma_device, addr, size, dir);
}

/* ib_reg_user_mr - register a memory region for virtual addresses from kernel
 * space. This function should be called when 'current' is the owning MM.
 */
struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
			     u64 virt_addr, int mr_access_flags);

/* ib_advise_mr -  give an advice about an address range in a memory region */
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);
/**
 * ib_dereg_mr_user - Deregisters a memory region and removes it from the
 *   HCA translation table.
 * @mr: The memory region to deregister.
 * @udata: Valid user data or NULL for kernel object
 *
 * This function can fail, if the memory region has memory windows bound to it.
 */
int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata);

/**
 * ib_dereg_mr - Deregisters a kernel memory region and removes it from the
 *   HCA translation table.
 * @mr: The memory region to deregister.
 *
 * This function can fail, if the memory region has memory windows bound to it.
 *
 * NOTE: for user mr use ib_dereg_mr_user with valid udata!
 */
static inline int ib_dereg_mr(struct ib_mr *mr)
{
	return ib_dereg_mr_user(mr, NULL);
}

struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,
			  u32 max_num_sg);

struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd,
				    u32 max_num_data_sg,
				    u32 max_num_meta_sg);

/**
 * ib_update_fast_reg_key - updates the key portion of the fast_reg MR
 *   R_Key and L_Key.
 * @mr - struct ib_mr pointer to be updated.
 * @newkey - new key to be used.
 */
static inline void ib_update_fast_reg_key(struct ib_mr *mr, u8 newkey)
{
	mr->lkey = (mr->lkey & 0xffffff00) | newkey;
	mr->rkey = (mr->rkey & 0xffffff00) | newkey;
}

/**
 * ib_inc_rkey - increments the key portion of the given rkey. Can be used
 * for calculating a new rkey for type 2 memory windows.
 * @rkey - the rkey to increment.
 */
static inline u32 ib_inc_rkey(u32 rkey)
{
	const u32 mask = 0x000000ff;
	return ((rkey + 1) & mask) | (rkey & ~mask);
}

/**
 * ib_attach_mcast - Attaches the specified QP to a multicast group.
 * @qp: QP to attach to the multicast group.  The QP must be type
 *   IB_QPT_UD.
 * @gid: Multicast group GID.
 * @lid: Multicast group LID in host byte order.
 *
 * In order to send and receive multicast packets, subnet
 * administration must have created the multicast group and configured
 * the fabric appropriately.  The port associated with the specified
 * QP must also be a member of the multicast group.
 */
int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid);

/**
 * ib_detach_mcast - Detaches the specified QP from a multicast group.
 * @qp: QP to detach from the multicast group.
 * @gid: Multicast group GID.
 * @lid: Multicast group LID in host byte order.
 */
int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid);

struct ib_xrcd *ib_alloc_xrcd_user(struct ib_device *device,
				   struct inode *inode, struct ib_udata *udata);
int ib_dealloc_xrcd_user(struct ib_xrcd *xrcd, struct ib_udata *udata);

static inline int ib_check_mr_access(struct ib_device *ib_dev,
				     unsigned int flags)
{
	u64 device_cap = ib_dev->attrs.device_cap_flags;

	/*
	 * Local write permission is required if remote write or
	 * remote atomic permission is also requested.
	 */
	if (flags & (IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_REMOTE_WRITE) &&
	    !(flags & IB_ACCESS_LOCAL_WRITE))
		return -EINVAL;

	if (flags & ~IB_ACCESS_SUPPORTED)
		return -EINVAL;

	if (flags & IB_ACCESS_ON_DEMAND &&
	    !(ib_dev->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING))
		return -EOPNOTSUPP;

	if ((flags & IB_ACCESS_FLUSH_GLOBAL &&
	    !(device_cap & IB_DEVICE_FLUSH_GLOBAL)) ||
	    (flags & IB_ACCESS_FLUSH_PERSISTENT &&
	    !(device_cap & IB_DEVICE_FLUSH_PERSISTENT)))
		return -EOPNOTSUPP;

	return 0;
}

static inline bool ib_access_writable(int access_flags)
{
	/*
	 * We have writable memory backing the MR if any of the following
	 * access flags are set.  "Local write" and "remote write" obviously
	 * require write access.  "Remote atomic" can do things like fetch and
	 * add, which will modify memory, and "MW bind" can change permissions
	 * by binding a window.
	 */
	return access_flags &
		(IB_ACCESS_LOCAL_WRITE   | IB_ACCESS_REMOTE_WRITE |
		 IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND);
}

/**
 * ib_check_mr_status: lightweight check of MR status.
 *     This routine may provide status checks on a selected
 *     ib_mr. first use is for signature status check.
 *
 * @mr: A memory region.
 * @check_mask: Bitmask of which checks to perform from
 *     ib_mr_status_check enumeration.
 * @mr_status: The container of relevant status checks.
 *     failed checks will be indicated in the status bitmask
 *     and the relevant info shall be in the error item.
 */
int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
		       struct ib_mr_status *mr_status);

/**
 * ib_device_try_get: Hold a registration lock
 * device: The device to lock
 *
 * A device under an active registration lock cannot become unregistered. It
 * is only possible to obtain a registration lock on a device that is fully
 * registered, otherwise this function returns false.
 *
 * The registration lock is only necessary for actions which require the
 * device to still be registered. Uses that only require the device pointer to
 * be valid should use get_device(&ibdev->dev) to hold the memory.
 *
 */
static inline bool ib_device_try_get(struct ib_device *dev)
{
	return refcount_inc_not_zero(&dev->refcount);
}

void ib_device_put(struct ib_device *device);
struct ib_device *ib_device_get_by_netdev(struct net_device *ndev,
					  enum rdma_driver_id driver_id);
struct ib_device *ib_device_get_by_name(const char *name,
					enum rdma_driver_id driver_id);
struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u32 port,
					    u16 pkey, const union ib_gid *gid,
					    const struct sockaddr *addr);
int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev,
			 unsigned int port);
struct ib_wq *ib_create_wq(struct ib_pd *pd,
			   struct ib_wq_init_attr *init_attr);
int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata);

int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
		 unsigned int *sg_offset, unsigned int page_size);
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);

static inline int
ib_map_mr_sg_zbva(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
		  unsigned int *sg_offset, unsigned int page_size)
{
	int n;

	n = ib_map_mr_sg(mr, sg, sg_nents, sg_offset, page_size);
	mr->iova = 0;

	return n;
}

int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents,
		unsigned int *sg_offset, int (*set_page)(struct ib_mr *, u64));

void ib_drain_rq(struct ib_qp *qp);
void ib_drain_sq(struct ib_qp *qp);
void ib_drain_qp(struct ib_qp *qp);

int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed,
		     u8 *width);

static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr)
{
	if (attr->type == RDMA_AH_ATTR_TYPE_ROCE)
		return attr->roce.dmac;
	return NULL;
}

static inline void rdma_ah_set_dlid(struct rdma_ah_attr *attr, u32 dlid)
{
	if (attr->type == RDMA_AH_ATTR_TYPE_IB)
		attr->ib.dlid = (u16)dlid;
	else if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
		attr->opa.dlid = dlid;
}

static inline u32 rdma_ah_get_dlid(const struct rdma_ah_attr *attr)
{
	if (attr->type == RDMA_AH_ATTR_TYPE_IB)
		return attr->ib.dlid;
	else if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
		return attr->opa.dlid;
	return 0;
}

static inline void rdma_ah_set_sl(struct rdma_ah_attr *attr, u8 sl)
{
	attr->sl = sl;
}

static inline u8 rdma_ah_get_sl(const struct rdma_ah_attr *attr)
{
	return attr->sl;
}

static inline void rdma_ah_set_path_bits(struct rdma_ah_attr *attr,
					 u8 src_path_bits)
{
	if (attr->type == RDMA_AH_ATTR_TYPE_IB)
		attr->ib.src_path_bits = src_path_bits;
	else if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
		attr->opa.src_path_bits = src_path_bits;
}

static inline u8 rdma_ah_get_path_bits(const struct rdma_ah_attr *attr)
{
	if (attr->type == RDMA_AH_ATTR_TYPE_IB)
		return attr->ib.src_path_bits;
	else if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
		return attr->opa.src_path_bits;
	return 0;
}

static inline void rdma_ah_set_make_grd(struct rdma_ah_attr *attr,
					bool make_grd)
{
	if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
		attr->opa.make_grd = make_grd;
}

static inline bool rdma_ah_get_make_grd(const struct rdma_ah_attr *attr)
{
	if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
		return attr->opa.make_grd;
	return false;
}

static inline void rdma_ah_set_port_num(struct rdma_ah_attr *attr, u32 port_num)
{
	attr->port_num = port_num;
}

static inline u32 rdma_ah_get_port_num(const struct rdma_ah_attr *attr)
{
	return attr->port_num;
}

static inline void rdma_ah_set_static_rate(struct rdma_ah_attr *attr,
					   u8 static_rate)
{
	attr->static_rate = static_rate;
}

static inline u8 rdma_ah_get_static_rate(const struct rdma_ah_attr *attr)
{
	return attr->static_rate;
}

static inline void rdma_ah_set_ah_flags(struct rdma_ah_attr *attr,
					enum ib_ah_flags flag)
{
	attr->ah_flags = flag;
}

static inline enum ib_ah_flags
		rdma_ah_get_ah_flags(const struct rdma_ah_attr *attr)
{
	return attr->ah_flags;
}

static inline const struct ib_global_route
		*rdma_ah_read_grh(const struct rdma_ah_attr *attr)
{
	return &attr->grh;
}

/*To retrieve and modify the grh */
static inline struct ib_global_route
		*rdma_ah_retrieve_grh(struct rdma_ah_attr *attr)
{
	return &attr->grh;
}

static inline void rdma_ah_set_dgid_raw(struct rdma_ah_attr *attr, void *dgid)
{
	struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);

	memcpy(grh->dgid.raw, dgid, sizeof(grh->dgid));
}

static inline void rdma_ah_set_subnet_prefix(struct rdma_ah_attr *attr,
					     __be64 prefix)
{
	struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);

	grh->dgid.global.subnet_prefix = prefix;
}

static inline void rdma_ah_set_interface_id(struct rdma_ah_attr *attr,
					    __be64 if_id)
{
	struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);

	grh->dgid.global.interface_id = if_id;
}

static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr,
				   union ib_gid *dgid, u32 flow_label,
				   u8 sgid_index, u8 hop_limit,
				   u8 traffic_class)
{
	struct ib_global_route *grh = rdma_ah_retrieve_grh(attr);

	attr->ah_flags = IB_AH_GRH;
	if (dgid)
		grh->dgid = *dgid;
	grh->flow_label = flow_label;
	grh->sgid_index = sgid_index;
	grh->hop_limit = hop_limit;
	grh->traffic_class = traffic_class;
	grh->sgid_attr = NULL;
}

void rdma_destroy_ah_attr(struct rdma_ah_attr *ah_attr);
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);
void rdma_copy_ah_attr(struct rdma_ah_attr *dest,
		       const struct rdma_ah_attr *src);
void rdma_replace_ah_attr(struct rdma_ah_attr *old,
			  const struct rdma_ah_attr *new);
void rdma_move_ah_attr(struct rdma_ah_attr *dest, struct rdma_ah_attr *src);

/**
 * rdma_ah_find_type - Return address handle type.
 *
 * @dev: Device to be checked
 * @port_num: Port number
 */
static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev,
						       u32 port_num)
{
	if (rdma_protocol_roce(dev, port_num))
		return RDMA_AH_ATTR_TYPE_ROCE;
	if (rdma_protocol_ib(dev, port_num)) {
		if (rdma_cap_opa_ah(dev, port_num))
			return RDMA_AH_ATTR_TYPE_OPA;
		return RDMA_AH_ATTR_TYPE_IB;
	}
	if (dev->type == RDMA_DEVICE_TYPE_SMI)
		return RDMA_AH_ATTR_TYPE_IB;

	return RDMA_AH_ATTR_TYPE_UNDEFINED;
}

/**
 * ib_lid_cpu16 - Return lid in 16bit CPU encoding.
 *     In the current implementation the only way to
 *     get the 32bit lid is from other sources for OPA.
 *     For IB, lids will always be 16bits so cast the
 *     value accordingly.
 *
 * @lid: A 32bit LID
 */
static inline u16 ib_lid_cpu16(u32 lid)
{
	WARN_ON_ONCE(lid & 0xFFFF0000);
	return (u16)lid;
}

/**
 * ib_lid_be16 - Return lid in 16bit BE encoding.
 *
 * @lid: A 32bit LID
 */
static inline __be16 ib_lid_be16(u32 lid)
{
	WARN_ON_ONCE(lid & 0xFFFF0000);
	return cpu_to_be16((u16)lid);
}

/**
 * ib_get_vector_affinity - Get the affinity mappings of a given completion
 *   vector
 * @device:         the rdma device
 * @comp_vector:    index of completion vector
 *
 * Returns NULL on failure, otherwise a corresponding cpu map of the
 * completion vector (returns all-cpus map if the device driver doesn't
 * implement get_vector_affinity).
 */
static inline const struct cpumask *
ib_get_vector_affinity(struct ib_device *device, int comp_vector)
{
	if (comp_vector < 0 || comp_vector >= device->num_comp_vectors ||
	    !device->ops.get_vector_affinity)
		return NULL;

	return device->ops.get_vector_affinity(device, comp_vector);

}

/**
 * rdma_roce_rescan_device - Rescan all of the network devices in the system
 * and add their gids, as needed, to the relevant RoCE devices.
 *
 * @device:         the rdma device
 */
void rdma_roce_rescan_device(struct ib_device *ibdev);

struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile);

int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs);

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 *));

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);

/**
 * rdma_device_to_ibdev - Get ib_device pointer from device pointer
 *
 * @device:	device pointer for which ib_device pointer to retrieve
 *
 * rdma_device_to_ibdev() retrieves ib_device pointer from device.
 *
 */
static inline struct ib_device *rdma_device_to_ibdev(struct device *device)
{
	struct ib_core_device *coredev =
		container_of(device, struct ib_core_device, dev);

	return coredev->owner;
}

/**
 * ibdev_to_node - return the NUMA node for a given ib_device
 * @dev:	device to get the NUMA node for.
 */
static inline int ibdev_to_node(struct ib_device *ibdev)
{
	struct device *parent = ibdev->dev.parent;

	if (!parent)
		return NUMA_NO_NODE;
	return dev_to_node(parent);
}

/**
 * rdma_device_to_drv_device - Helper macro to reach back to driver's
 *			       ib_device holder structure from device pointer.
 *
 * NOTE: New drivers should not make use of this API; This API is only for
 * existing drivers who have exposed sysfs entries using
 * ops->device_group.
 */
#define rdma_device_to_drv_device(dev, drv_dev_struct, ibdev_member)           \
	container_of(rdma_device_to_ibdev(dev), drv_dev_struct, ibdev_member)

bool rdma_dev_access_netns(const struct ib_device *device,
			   const struct net *net);

#define IB_ROCE_UDP_ENCAP_VALID_PORT_MIN (0xC000)
#define IB_ROCE_UDP_ENCAP_VALID_PORT_MAX (0xFFFF)
#define IB_GRH_FLOWLABEL_MASK (0x000FFFFF)

/**
 * rdma_flow_label_to_udp_sport - generate a RoCE v2 UDP src port value based
 *                               on the flow_label
 *
 * This function will convert the 20 bit flow_label input to a valid RoCE v2
 * UDP src port 14 bit value. All RoCE V2 drivers should use this same
 * convention.
 */
static inline u16 rdma_flow_label_to_udp_sport(u32 fl)
{
	u32 fl_low = fl & 0x03fff, fl_high = fl & 0xFC000;

	fl_low ^= fl_high >> 14;
	return (u16)(fl_low | IB_ROCE_UDP_ENCAP_VALID_PORT_MIN);
}

/**
 * rdma_calc_flow_label - generate a RDMA symmetric flow label value based on
 *                        local and remote qpn values
 *
 * This function folded the multiplication results of two qpns, 24 bit each,
 * fields, and converts it to a 20 bit results.
 *
 * This function will create symmetric flow_label value based on the local
 * and remote qpn values. this will allow both the requester and responder
 * to calculate the same flow_label for a given connection.
 *
 * This helper function should be used by driver in case the upper layer
 * provide a zero flow_label value. This is to improve entropy of RDMA
 * traffic in the network.
 */
static inline u32 rdma_calc_flow_label(u32 lqpn, u32 rqpn)
{
	u64 v = (u64)lqpn * rqpn;

	v ^= v >> 20;
	v ^= v >> 40;

	return (u32)(v & IB_GRH_FLOWLABEL_MASK);
}

/**
 * rdma_get_udp_sport - Calculate and set UDP source port based on the flow
 *                      label. If flow label is not defined in GRH then
 *                      calculate it based on lqpn/rqpn.
 *
 * @fl:                 flow label from GRH
 * @lqpn:               local qp number
 * @rqpn:               remote qp number
 */
static inline u16 rdma_get_udp_sport(u32 fl, u32 lqpn, u32 rqpn)
{
	if (!fl)
		fl = rdma_calc_flow_label(lqpn, rqpn);

	return rdma_flow_label_to_udp_sport(fl);
}

const struct ib_port_immutable*
ib_port_immutable_read(struct ib_device *dev, unsigned int port);

/** ib_add_sub_device - Add a sub IB device on an existing one
 *
 * @parent: The IB device that needs to add a sub device
 * @type: The type of the new sub device
 * @name: The name of the new sub device
 *
 *
 * Return 0 on success, an error code otherwise
 */
int ib_add_sub_device(struct ib_device *parent,
		      enum rdma_nl_dev_type type,
		      const char *name);


/** ib_del_sub_device_and_put - Delect an IB sub device while holding a 'get'
 *
 * @sub: The sub device that is going to be deleted
 *
 * Return 0 on success, an error code otherwise
 */
int ib_del_sub_device_and_put(struct ib_device *sub);

static inline void ib_mark_name_assigned_by_user(struct ib_device *ibdev)
{
	ibdev->name_assign_type = RDMA_NAME_ASSIGN_TYPE_USER;
}

#endif /* IB_VERBS_H */