summaryrefslogtreecommitdiff
path: root/drivers/infiniband/core/sa_query.c
blob: 8cf15d4a8ac438db82971ad3d3bc16649a5ed6da (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
/*
 * Copyright (c) 2004 Topspin Communications.  All rights reserved.
 * Copyright (c) 2005 Voltaire, Inc.  All rights reserved.
 * Copyright (c) 2006 Intel Corporation.  All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/err.h>
#include <linux/random.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/dma-mapping.h>
#include <linux/kref.h>
#include <linux/idr.h>
#include <linux/workqueue.h>
#include <uapi/linux/if_ether.h>
#include <rdma/ib_pack.h>
#include <rdma/ib_cache.h>
#include <rdma/rdma_netlink.h>
#include <net/netlink.h>
#include <uapi/rdma/ib_user_sa.h>
#include <rdma/ib_marshall.h>
#include <rdma/ib_addr.h>
#include <rdma/opa_addr.h>
#include "sa.h"
#include "core_priv.h"

#define IB_SA_LOCAL_SVC_TIMEOUT_MIN		100
#define IB_SA_LOCAL_SVC_TIMEOUT_DEFAULT		2000
#define IB_SA_LOCAL_SVC_TIMEOUT_MAX		200000
#define IB_SA_CPI_MAX_RETRY_CNT			3
#define IB_SA_CPI_RETRY_WAIT			1000 /*msecs */
static int sa_local_svc_timeout_ms = IB_SA_LOCAL_SVC_TIMEOUT_DEFAULT;

struct ib_sa_sm_ah {
	struct ib_ah        *ah;
	struct kref          ref;
	u16		     pkey_index;
	u8		     src_path_mask;
};

enum rdma_class_port_info_type {
	RDMA_CLASS_PORT_INFO_IB,
	RDMA_CLASS_PORT_INFO_OPA
};

struct rdma_class_port_info {
	enum rdma_class_port_info_type type;
	union {
		struct ib_class_port_info ib;
		struct opa_class_port_info opa;
	};
};

struct ib_sa_classport_cache {
	bool valid;
	int retry_cnt;
	struct rdma_class_port_info data;
};

struct ib_sa_port {
	struct ib_mad_agent *agent;
	struct ib_sa_sm_ah  *sm_ah;
	struct work_struct   update_task;
	struct ib_sa_classport_cache classport_info;
	struct delayed_work ib_cpi_work;
	spinlock_t                   classport_lock; /* protects class port info set */
	spinlock_t           ah_lock;
	u8                   port_num;
};

struct ib_sa_device {
	int                     start_port, end_port;
	struct ib_event_handler event_handler;
	struct ib_sa_port port[0];
};

struct ib_sa_query {
	void (*callback)(struct ib_sa_query *, int, struct ib_sa_mad *);
	void (*release)(struct ib_sa_query *);
	struct ib_sa_client    *client;
	struct ib_sa_port      *port;
	struct ib_mad_send_buf *mad_buf;
	struct ib_sa_sm_ah     *sm_ah;
	int			id;
	u32			flags;
	struct list_head	list; /* Local svc request list */
	u32			seq; /* Local svc request sequence number */
	unsigned long		timeout; /* Local svc timeout */
	u8			path_use; /* How will the pathrecord be used */
};

#define IB_SA_ENABLE_LOCAL_SERVICE	0x00000001
#define IB_SA_CANCEL			0x00000002
#define IB_SA_QUERY_OPA			0x00000004

struct ib_sa_service_query {
	void (*callback)(int, struct ib_sa_service_rec *, void *);
	void *context;
	struct ib_sa_query sa_query;
};

struct ib_sa_path_query {
	void (*callback)(int, struct sa_path_rec *, void *);
	void *context;
	struct ib_sa_query sa_query;
	struct sa_path_rec *conv_pr;
};

struct ib_sa_guidinfo_query {
	void (*callback)(int, struct ib_sa_guidinfo_rec *, void *);
	void *context;
	struct ib_sa_query sa_query;
};

struct ib_sa_classport_info_query {
	void (*callback)(void *);
	void *context;
	struct ib_sa_query sa_query;
};

struct ib_sa_mcmember_query {
	void (*callback)(int, struct ib_sa_mcmember_rec *, void *);
	void *context;
	struct ib_sa_query sa_query;
};

static LIST_HEAD(ib_nl_request_list);
static DEFINE_SPINLOCK(ib_nl_request_lock);
static atomic_t ib_nl_sa_request_seq;
static struct workqueue_struct *ib_nl_wq;
static struct delayed_work ib_nl_timed_work;
static const struct nla_policy ib_nl_policy[LS_NLA_TYPE_MAX] = {
	[LS_NLA_TYPE_PATH_RECORD]	= {.type = NLA_BINARY,
		.len = sizeof(struct ib_path_rec_data)},
	[LS_NLA_TYPE_TIMEOUT]		= {.type = NLA_U32},
	[LS_NLA_TYPE_SERVICE_ID]	= {.type = NLA_U64},
	[LS_NLA_TYPE_DGID]		= {.type = NLA_BINARY,
		.len = sizeof(struct rdma_nla_ls_gid)},
	[LS_NLA_TYPE_SGID]		= {.type = NLA_BINARY,
		.len = sizeof(struct rdma_nla_ls_gid)},
	[LS_NLA_TYPE_TCLASS]		= {.type = NLA_U8},
	[LS_NLA_TYPE_PKEY]		= {.type = NLA_U16},
	[LS_NLA_TYPE_QOS_CLASS]		= {.type = NLA_U16},
};


static void ib_sa_add_one(struct ib_device *device);
static void ib_sa_remove_one(struct ib_device *device, void *client_data);

static struct ib_client sa_client = {
	.name   = "sa",
	.add    = ib_sa_add_one,
	.remove = ib_sa_remove_one
};

static DEFINE_SPINLOCK(idr_lock);
static DEFINE_IDR(query_idr);

static DEFINE_SPINLOCK(tid_lock);
static u32 tid;

#define PATH_REC_FIELD(field) \
	.struct_offset_bytes = offsetof(struct sa_path_rec, field),	\
	.struct_size_bytes   = sizeof((struct sa_path_rec *)0)->field,	\
	.field_name          = "sa_path_rec:" #field

static const struct ib_field path_rec_table[] = {
	{ PATH_REC_FIELD(service_id),
	  .offset_words = 0,
	  .offset_bits  = 0,
	  .size_bits    = 64 },
	{ PATH_REC_FIELD(dgid),
	  .offset_words = 2,
	  .offset_bits  = 0,
	  .size_bits    = 128 },
	{ PATH_REC_FIELD(sgid),
	  .offset_words = 6,
	  .offset_bits  = 0,
	  .size_bits    = 128 },
	{ PATH_REC_FIELD(ib.dlid),
	  .offset_words = 10,
	  .offset_bits  = 0,
	  .size_bits    = 16 },
	{ PATH_REC_FIELD(ib.slid),
	  .offset_words = 10,
	  .offset_bits  = 16,
	  .size_bits    = 16 },
	{ PATH_REC_FIELD(ib.raw_traffic),
	  .offset_words = 11,
	  .offset_bits  = 0,
	  .size_bits    = 1 },
	{ RESERVED,
	  .offset_words = 11,
	  .offset_bits  = 1,
	  .size_bits    = 3 },
	{ PATH_REC_FIELD(flow_label),
	  .offset_words = 11,
	  .offset_bits  = 4,
	  .size_bits    = 20 },
	{ PATH_REC_FIELD(hop_limit),
	  .offset_words = 11,
	  .offset_bits  = 24,
	  .size_bits    = 8 },
	{ PATH_REC_FIELD(traffic_class),
	  .offset_words = 12,
	  .offset_bits  = 0,
	  .size_bits    = 8 },
	{ PATH_REC_FIELD(reversible),
	  .offset_words = 12,
	  .offset_bits  = 8,
	  .size_bits    = 1 },
	{ PATH_REC_FIELD(numb_path),
	  .offset_words = 12,
	  .offset_bits  = 9,
	  .size_bits    = 7 },
	{ PATH_REC_FIELD(pkey),
	  .offset_words = 12,
	  .offset_bits  = 16,
	  .size_bits    = 16 },
	{ PATH_REC_FIELD(qos_class),
	  .offset_words = 13,
	  .offset_bits  = 0,
	  .size_bits    = 12 },
	{ PATH_REC_FIELD(sl),
	  .offset_words = 13,
	  .offset_bits  = 12,
	  .size_bits    = 4 },
	{ PATH_REC_FIELD(mtu_selector),
	  .offset_words = 13,
	  .offset_bits  = 16,
	  .size_bits    = 2 },
	{ PATH_REC_FIELD(mtu),
	  .offset_words = 13,
	  .offset_bits  = 18,
	  .size_bits    = 6 },
	{ PATH_REC_FIELD(rate_selector),
	  .offset_words = 13,
	  .offset_bits  = 24,
	  .size_bits    = 2 },
	{ PATH_REC_FIELD(rate),
	  .offset_words = 13,
	  .offset_bits  = 26,
	  .size_bits    = 6 },
	{ PATH_REC_FIELD(packet_life_time_selector),
	  .offset_words = 14,
	  .offset_bits  = 0,
	  .size_bits    = 2 },
	{ PATH_REC_FIELD(packet_life_time),
	  .offset_words = 14,
	  .offset_bits  = 2,
	  .size_bits    = 6 },
	{ PATH_REC_FIELD(preference),
	  .offset_words = 14,
	  .offset_bits  = 8,
	  .size_bits    = 8 },
	{ RESERVED,
	  .offset_words = 14,
	  .offset_bits  = 16,
	  .size_bits    = 48 },
};

#define OPA_PATH_REC_FIELD(field) \
	.struct_offset_bytes = \
		offsetof(struct sa_path_rec, field), \
	.struct_size_bytes   = \
		sizeof((struct sa_path_rec *)0)->field,	\
	.field_name          = "sa_path_rec:" #field

static const struct ib_field opa_path_rec_table[] = {
	{ OPA_PATH_REC_FIELD(service_id),
	  .offset_words = 0,
	  .offset_bits  = 0,
	  .size_bits    = 64 },
	{ OPA_PATH_REC_FIELD(dgid),
	  .offset_words = 2,
	  .offset_bits  = 0,
	  .size_bits    = 128 },
	{ OPA_PATH_REC_FIELD(sgid),
	  .offset_words = 6,
	  .offset_bits  = 0,
	  .size_bits    = 128 },
	{ OPA_PATH_REC_FIELD(opa.dlid),
	  .offset_words = 10,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ OPA_PATH_REC_FIELD(opa.slid),
	  .offset_words = 11,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ OPA_PATH_REC_FIELD(opa.raw_traffic),
	  .offset_words = 12,
	  .offset_bits  = 0,
	  .size_bits    = 1 },
	{ RESERVED,
	  .offset_words = 12,
	  .offset_bits  = 1,
	  .size_bits    = 3 },
	{ OPA_PATH_REC_FIELD(flow_label),
	  .offset_words = 12,
	  .offset_bits  = 4,
	  .size_bits    = 20 },
	{ OPA_PATH_REC_FIELD(hop_limit),
	  .offset_words = 12,
	  .offset_bits  = 24,
	  .size_bits    = 8 },
	{ OPA_PATH_REC_FIELD(traffic_class),
	  .offset_words = 13,
	  .offset_bits  = 0,
	  .size_bits    = 8 },
	{ OPA_PATH_REC_FIELD(reversible),
	  .offset_words = 13,
	  .offset_bits  = 8,
	  .size_bits    = 1 },
	{ OPA_PATH_REC_FIELD(numb_path),
	  .offset_words = 13,
	  .offset_bits  = 9,
	  .size_bits    = 7 },
	{ OPA_PATH_REC_FIELD(pkey),
	  .offset_words = 13,
	  .offset_bits  = 16,
	  .size_bits    = 16 },
	{ OPA_PATH_REC_FIELD(opa.l2_8B),
	  .offset_words = 14,
	  .offset_bits  = 0,
	  .size_bits    = 1 },
	{ OPA_PATH_REC_FIELD(opa.l2_10B),
	  .offset_words = 14,
	  .offset_bits  = 1,
	  .size_bits    = 1 },
	{ OPA_PATH_REC_FIELD(opa.l2_9B),
	  .offset_words = 14,
	  .offset_bits  = 2,
	  .size_bits    = 1 },
	{ OPA_PATH_REC_FIELD(opa.l2_16B),
	  .offset_words = 14,
	  .offset_bits  = 3,
	  .size_bits    = 1 },
	{ RESERVED,
	  .offset_words = 14,
	  .offset_bits  = 4,
	  .size_bits    = 2 },
	{ OPA_PATH_REC_FIELD(opa.qos_type),
	  .offset_words = 14,
	  .offset_bits  = 6,
	  .size_bits    = 2 },
	{ OPA_PATH_REC_FIELD(opa.qos_priority),
	  .offset_words = 14,
	  .offset_bits  = 8,
	  .size_bits    = 8 },
	{ RESERVED,
	  .offset_words = 14,
	  .offset_bits  = 16,
	  .size_bits    = 3 },
	{ OPA_PATH_REC_FIELD(sl),
	  .offset_words = 14,
	  .offset_bits  = 19,
	  .size_bits    = 5 },
	{ RESERVED,
	  .offset_words = 14,
	  .offset_bits  = 24,
	  .size_bits    = 8 },
	{ OPA_PATH_REC_FIELD(mtu_selector),
	  .offset_words = 15,
	  .offset_bits  = 0,
	  .size_bits    = 2 },
	{ OPA_PATH_REC_FIELD(mtu),
	  .offset_words = 15,
	  .offset_bits  = 2,
	  .size_bits    = 6 },
	{ OPA_PATH_REC_FIELD(rate_selector),
	  .offset_words = 15,
	  .offset_bits  = 8,
	  .size_bits    = 2 },
	{ OPA_PATH_REC_FIELD(rate),
	  .offset_words = 15,
	  .offset_bits  = 10,
	  .size_bits    = 6 },
	{ OPA_PATH_REC_FIELD(packet_life_time_selector),
	  .offset_words = 15,
	  .offset_bits  = 16,
	  .size_bits    = 2 },
	{ OPA_PATH_REC_FIELD(packet_life_time),
	  .offset_words = 15,
	  .offset_bits  = 18,
	  .size_bits    = 6 },
	{ OPA_PATH_REC_FIELD(preference),
	  .offset_words = 15,
	  .offset_bits  = 24,
	  .size_bits    = 8 },
};

#define MCMEMBER_REC_FIELD(field) \
	.struct_offset_bytes = offsetof(struct ib_sa_mcmember_rec, field),	\
	.struct_size_bytes   = sizeof ((struct ib_sa_mcmember_rec *) 0)->field,	\
	.field_name          = "sa_mcmember_rec:" #field

static const struct ib_field mcmember_rec_table[] = {
	{ MCMEMBER_REC_FIELD(mgid),
	  .offset_words = 0,
	  .offset_bits  = 0,
	  .size_bits    = 128 },
	{ MCMEMBER_REC_FIELD(port_gid),
	  .offset_words = 4,
	  .offset_bits  = 0,
	  .size_bits    = 128 },
	{ MCMEMBER_REC_FIELD(qkey),
	  .offset_words = 8,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ MCMEMBER_REC_FIELD(mlid),
	  .offset_words = 9,
	  .offset_bits  = 0,
	  .size_bits    = 16 },
	{ MCMEMBER_REC_FIELD(mtu_selector),
	  .offset_words = 9,
	  .offset_bits  = 16,
	  .size_bits    = 2 },
	{ MCMEMBER_REC_FIELD(mtu),
	  .offset_words = 9,
	  .offset_bits  = 18,
	  .size_bits    = 6 },
	{ MCMEMBER_REC_FIELD(traffic_class),
	  .offset_words = 9,
	  .offset_bits  = 24,
	  .size_bits    = 8 },
	{ MCMEMBER_REC_FIELD(pkey),
	  .offset_words = 10,
	  .offset_bits  = 0,
	  .size_bits    = 16 },
	{ MCMEMBER_REC_FIELD(rate_selector),
	  .offset_words = 10,
	  .offset_bits  = 16,
	  .size_bits    = 2 },
	{ MCMEMBER_REC_FIELD(rate),
	  .offset_words = 10,
	  .offset_bits  = 18,
	  .size_bits    = 6 },
	{ MCMEMBER_REC_FIELD(packet_life_time_selector),
	  .offset_words = 10,
	  .offset_bits  = 24,
	  .size_bits    = 2 },
	{ MCMEMBER_REC_FIELD(packet_life_time),
	  .offset_words = 10,
	  .offset_bits  = 26,
	  .size_bits    = 6 },
	{ MCMEMBER_REC_FIELD(sl),
	  .offset_words = 11,
	  .offset_bits  = 0,
	  .size_bits    = 4 },
	{ MCMEMBER_REC_FIELD(flow_label),
	  .offset_words = 11,
	  .offset_bits  = 4,
	  .size_bits    = 20 },
	{ MCMEMBER_REC_FIELD(hop_limit),
	  .offset_words = 11,
	  .offset_bits  = 24,
	  .size_bits    = 8 },
	{ MCMEMBER_REC_FIELD(scope),
	  .offset_words = 12,
	  .offset_bits  = 0,
	  .size_bits    = 4 },
	{ MCMEMBER_REC_FIELD(join_state),
	  .offset_words = 12,
	  .offset_bits  = 4,
	  .size_bits    = 4 },
	{ MCMEMBER_REC_FIELD(proxy_join),
	  .offset_words = 12,
	  .offset_bits  = 8,
	  .size_bits    = 1 },
	{ RESERVED,
	  .offset_words = 12,
	  .offset_bits  = 9,
	  .size_bits    = 23 },
};

#define SERVICE_REC_FIELD(field) \
	.struct_offset_bytes = offsetof(struct ib_sa_service_rec, field),	\
	.struct_size_bytes   = sizeof ((struct ib_sa_service_rec *) 0)->field,	\
	.field_name          = "sa_service_rec:" #field

static const struct ib_field service_rec_table[] = {
	{ SERVICE_REC_FIELD(id),
	  .offset_words = 0,
	  .offset_bits  = 0,
	  .size_bits    = 64 },
	{ SERVICE_REC_FIELD(gid),
	  .offset_words = 2,
	  .offset_bits  = 0,
	  .size_bits    = 128 },
	{ SERVICE_REC_FIELD(pkey),
	  .offset_words = 6,
	  .offset_bits  = 0,
	  .size_bits    = 16 },
	{ SERVICE_REC_FIELD(lease),
	  .offset_words = 7,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ SERVICE_REC_FIELD(key),
	  .offset_words = 8,
	  .offset_bits  = 0,
	  .size_bits    = 128 },
	{ SERVICE_REC_FIELD(name),
	  .offset_words = 12,
	  .offset_bits  = 0,
	  .size_bits    = 64*8 },
	{ SERVICE_REC_FIELD(data8),
	  .offset_words = 28,
	  .offset_bits  = 0,
	  .size_bits    = 16*8 },
	{ SERVICE_REC_FIELD(data16),
	  .offset_words = 32,
	  .offset_bits  = 0,
	  .size_bits    = 8*16 },
	{ SERVICE_REC_FIELD(data32),
	  .offset_words = 36,
	  .offset_bits  = 0,
	  .size_bits    = 4*32 },
	{ SERVICE_REC_FIELD(data64),
	  .offset_words = 40,
	  .offset_bits  = 0,
	  .size_bits    = 2*64 },
};

#define CLASSPORTINFO_REC_FIELD(field) \
	.struct_offset_bytes = offsetof(struct ib_class_port_info, field),	\
	.struct_size_bytes   = sizeof((struct ib_class_port_info *)0)->field,	\
	.field_name          = "ib_class_port_info:" #field

static const struct ib_field ib_classport_info_rec_table[] = {
	{ CLASSPORTINFO_REC_FIELD(base_version),
	  .offset_words = 0,
	  .offset_bits  = 0,
	  .size_bits    = 8 },
	{ CLASSPORTINFO_REC_FIELD(class_version),
	  .offset_words = 0,
	  .offset_bits  = 8,
	  .size_bits    = 8 },
	{ CLASSPORTINFO_REC_FIELD(capability_mask),
	  .offset_words = 0,
	  .offset_bits  = 16,
	  .size_bits    = 16 },
	{ CLASSPORTINFO_REC_FIELD(cap_mask2_resp_time),
	  .offset_words = 1,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ CLASSPORTINFO_REC_FIELD(redirect_gid),
	  .offset_words = 2,
	  .offset_bits  = 0,
	  .size_bits    = 128 },
	{ CLASSPORTINFO_REC_FIELD(redirect_tcslfl),
	  .offset_words = 6,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ CLASSPORTINFO_REC_FIELD(redirect_lid),
	  .offset_words = 7,
	  .offset_bits  = 0,
	  .size_bits    = 16 },
	{ CLASSPORTINFO_REC_FIELD(redirect_pkey),
	  .offset_words = 7,
	  .offset_bits  = 16,
	  .size_bits    = 16 },

	{ CLASSPORTINFO_REC_FIELD(redirect_qp),
	  .offset_words = 8,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ CLASSPORTINFO_REC_FIELD(redirect_qkey),
	  .offset_words = 9,
	  .offset_bits  = 0,
	  .size_bits    = 32 },

	{ CLASSPORTINFO_REC_FIELD(trap_gid),
	  .offset_words = 10,
	  .offset_bits  = 0,
	  .size_bits    = 128 },
	{ CLASSPORTINFO_REC_FIELD(trap_tcslfl),
	  .offset_words = 14,
	  .offset_bits  = 0,
	  .size_bits    = 32 },

	{ CLASSPORTINFO_REC_FIELD(trap_lid),
	  .offset_words = 15,
	  .offset_bits  = 0,
	  .size_bits    = 16 },
	{ CLASSPORTINFO_REC_FIELD(trap_pkey),
	  .offset_words = 15,
	  .offset_bits  = 16,
	  .size_bits    = 16 },

	{ CLASSPORTINFO_REC_FIELD(trap_hlqp),
	  .offset_words = 16,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ CLASSPORTINFO_REC_FIELD(trap_qkey),
	  .offset_words = 17,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
};

#define OPA_CLASSPORTINFO_REC_FIELD(field) \
	.struct_offset_bytes =\
		offsetof(struct opa_class_port_info, field),	\
	.struct_size_bytes   = \
		sizeof((struct opa_class_port_info *)0)->field,	\
	.field_name          = "opa_class_port_info:" #field

static const struct ib_field opa_classport_info_rec_table[] = {
	{ OPA_CLASSPORTINFO_REC_FIELD(base_version),
	  .offset_words = 0,
	  .offset_bits  = 0,
	  .size_bits    = 8 },
	{ OPA_CLASSPORTINFO_REC_FIELD(class_version),
	  .offset_words = 0,
	  .offset_bits  = 8,
	  .size_bits    = 8 },
	{ OPA_CLASSPORTINFO_REC_FIELD(cap_mask),
	  .offset_words = 0,
	  .offset_bits  = 16,
	  .size_bits    = 16 },
	{ OPA_CLASSPORTINFO_REC_FIELD(cap_mask2_resp_time),
	  .offset_words = 1,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ OPA_CLASSPORTINFO_REC_FIELD(redirect_gid),
	  .offset_words = 2,
	  .offset_bits  = 0,
	  .size_bits    = 128 },
	{ OPA_CLASSPORTINFO_REC_FIELD(redirect_tc_fl),
	  .offset_words = 6,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ OPA_CLASSPORTINFO_REC_FIELD(redirect_lid),
	  .offset_words = 7,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ OPA_CLASSPORTINFO_REC_FIELD(redirect_sl_qp),
	  .offset_words = 8,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ OPA_CLASSPORTINFO_REC_FIELD(redirect_qkey),
	  .offset_words = 9,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ OPA_CLASSPORTINFO_REC_FIELD(trap_gid),
	  .offset_words = 10,
	  .offset_bits  = 0,
	  .size_bits    = 128 },
	{ OPA_CLASSPORTINFO_REC_FIELD(trap_tc_fl),
	  .offset_words = 14,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ OPA_CLASSPORTINFO_REC_FIELD(trap_lid),
	  .offset_words = 15,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ OPA_CLASSPORTINFO_REC_FIELD(trap_hl_qp),
	  .offset_words = 16,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ OPA_CLASSPORTINFO_REC_FIELD(trap_qkey),
	  .offset_words = 17,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ OPA_CLASSPORTINFO_REC_FIELD(trap_pkey),
	  .offset_words = 18,
	  .offset_bits  = 0,
	  .size_bits    = 16 },
	{ OPA_CLASSPORTINFO_REC_FIELD(redirect_pkey),
	  .offset_words = 18,
	  .offset_bits  = 16,
	  .size_bits    = 16 },
	{ OPA_CLASSPORTINFO_REC_FIELD(trap_sl_rsvd),
	  .offset_words = 19,
	  .offset_bits  = 0,
	  .size_bits    = 8 },
	{ RESERVED,
	  .offset_words = 19,
	  .offset_bits  = 8,
	  .size_bits    = 24 },
};

#define GUIDINFO_REC_FIELD(field) \
	.struct_offset_bytes = offsetof(struct ib_sa_guidinfo_rec, field),	\
	.struct_size_bytes   = sizeof((struct ib_sa_guidinfo_rec *) 0)->field,	\
	.field_name          = "sa_guidinfo_rec:" #field

static const struct ib_field guidinfo_rec_table[] = {
	{ GUIDINFO_REC_FIELD(lid),
	  .offset_words = 0,
	  .offset_bits  = 0,
	  .size_bits    = 16 },
	{ GUIDINFO_REC_FIELD(block_num),
	  .offset_words = 0,
	  .offset_bits  = 16,
	  .size_bits    = 8 },
	{ GUIDINFO_REC_FIELD(res1),
	  .offset_words = 0,
	  .offset_bits  = 24,
	  .size_bits    = 8 },
	{ GUIDINFO_REC_FIELD(res2),
	  .offset_words = 1,
	  .offset_bits  = 0,
	  .size_bits    = 32 },
	{ GUIDINFO_REC_FIELD(guid_info_list),
	  .offset_words = 2,
	  .offset_bits  = 0,
	  .size_bits    = 512 },
};

static inline void ib_sa_disable_local_svc(struct ib_sa_query *query)
{
	query->flags &= ~IB_SA_ENABLE_LOCAL_SERVICE;
}

static inline int ib_sa_query_cancelled(struct ib_sa_query *query)
{
	return (query->flags & IB_SA_CANCEL);
}

static void ib_nl_set_path_rec_attrs(struct sk_buff *skb,
				     struct ib_sa_query *query)
{
	struct sa_path_rec *sa_rec = query->mad_buf->context[1];
	struct ib_sa_mad *mad = query->mad_buf->mad;
	ib_sa_comp_mask comp_mask = mad->sa_hdr.comp_mask;
	u16 val16;
	u64 val64;
	struct rdma_ls_resolve_header *header;

	query->mad_buf->context[1] = NULL;

	/* Construct the family header first */
	header = skb_put(skb, NLMSG_ALIGN(sizeof(*header)));
	memcpy(header->device_name, query->port->agent->device->name,
	       LS_DEVICE_NAME_MAX);
	header->port_num = query->port->port_num;

	if ((comp_mask & IB_SA_PATH_REC_REVERSIBLE) &&
	    sa_rec->reversible != 0)
		query->path_use = LS_RESOLVE_PATH_USE_GMP;
	else
		query->path_use = LS_RESOLVE_PATH_USE_UNIDIRECTIONAL;
	header->path_use = query->path_use;

	/* Now build the attributes */
	if (comp_mask & IB_SA_PATH_REC_SERVICE_ID) {
		val64 = be64_to_cpu(sa_rec->service_id);
		nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_SERVICE_ID,
			sizeof(val64), &val64);
	}
	if (comp_mask & IB_SA_PATH_REC_DGID)
		nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_DGID,
			sizeof(sa_rec->dgid), &sa_rec->dgid);
	if (comp_mask & IB_SA_PATH_REC_SGID)
		nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_SGID,
			sizeof(sa_rec->sgid), &sa_rec->sgid);
	if (comp_mask & IB_SA_PATH_REC_TRAFFIC_CLASS)
		nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_TCLASS,
			sizeof(sa_rec->traffic_class), &sa_rec->traffic_class);

	if (comp_mask & IB_SA_PATH_REC_PKEY) {
		val16 = be16_to_cpu(sa_rec->pkey);
		nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_PKEY,
			sizeof(val16), &val16);
	}
	if (comp_mask & IB_SA_PATH_REC_QOS_CLASS) {
		val16 = be16_to_cpu(sa_rec->qos_class);
		nla_put(skb, RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_QOS_CLASS,
			sizeof(val16), &val16);
	}
}

static int ib_nl_get_path_rec_attrs_len(ib_sa_comp_mask comp_mask)
{
	int len = 0;

	if (comp_mask & IB_SA_PATH_REC_SERVICE_ID)
		len += nla_total_size(sizeof(u64));
	if (comp_mask & IB_SA_PATH_REC_DGID)
		len += nla_total_size(sizeof(struct rdma_nla_ls_gid));
	if (comp_mask & IB_SA_PATH_REC_SGID)
		len += nla_total_size(sizeof(struct rdma_nla_ls_gid));
	if (comp_mask & IB_SA_PATH_REC_TRAFFIC_CLASS)
		len += nla_total_size(sizeof(u8));
	if (comp_mask & IB_SA_PATH_REC_PKEY)
		len += nla_total_size(sizeof(u16));
	if (comp_mask & IB_SA_PATH_REC_QOS_CLASS)
		len += nla_total_size(sizeof(u16));

	/*
	 * Make sure that at least some of the required comp_mask bits are
	 * set.
	 */
	if (WARN_ON(len == 0))
		return len;

	/* Add the family header */
	len += NLMSG_ALIGN(sizeof(struct rdma_ls_resolve_header));

	return len;
}

static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
{
	struct sk_buff *skb = NULL;
	struct nlmsghdr *nlh;
	void *data;
	int ret = 0;
	struct ib_sa_mad *mad;
	int len;

	mad = query->mad_buf->mad;
	len = ib_nl_get_path_rec_attrs_len(mad->sa_hdr.comp_mask);
	if (len <= 0)
		return -EMSGSIZE;

	skb = nlmsg_new(len, gfp_mask);
	if (!skb)
		return -ENOMEM;

	/* Put nlmsg header only for now */
	data = ibnl_put_msg(skb, &nlh, query->seq, 0, RDMA_NL_LS,
			    RDMA_NL_LS_OP_RESOLVE, NLM_F_REQUEST);
	if (!data) {
		nlmsg_free(skb);
		return -EMSGSIZE;
	}

	/* Add attributes */
	ib_nl_set_path_rec_attrs(skb, query);

	/* Repair the nlmsg header length */
	nlmsg_end(skb, nlh);

	ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, gfp_mask);
	if (!ret)
		ret = len;
	else
		ret = 0;

	return ret;
}

static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask)
{
	unsigned long flags;
	unsigned long delay;
	int ret;

	INIT_LIST_HEAD(&query->list);
	query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq);

	/* Put the request on the list first.*/
	spin_lock_irqsave(&ib_nl_request_lock, flags);
	delay = msecs_to_jiffies(sa_local_svc_timeout_ms);
	query->timeout = delay + jiffies;
	list_add_tail(&query->list, &ib_nl_request_list);
	/* Start the timeout if this is the only request */
	if (ib_nl_request_list.next == &query->list)
		queue_delayed_work(ib_nl_wq, &ib_nl_timed_work, delay);
	spin_unlock_irqrestore(&ib_nl_request_lock, flags);

	ret = ib_nl_send_msg(query, gfp_mask);
	if (ret <= 0) {
		ret = -EIO;
		/* Remove the request */
		spin_lock_irqsave(&ib_nl_request_lock, flags);
		list_del(&query->list);
		spin_unlock_irqrestore(&ib_nl_request_lock, flags);
	} else {
		ret = 0;
	}

	return ret;
}

static int ib_nl_cancel_request(struct ib_sa_query *query)
{
	unsigned long flags;
	struct ib_sa_query *wait_query;
	int found = 0;

	spin_lock_irqsave(&ib_nl_request_lock, flags);
	list_for_each_entry(wait_query, &ib_nl_request_list, list) {
		/* Let the timeout to take care of the callback */
		if (query == wait_query) {
			query->flags |= IB_SA_CANCEL;
			query->timeout = jiffies;
			list_move(&query->list, &ib_nl_request_list);
			found = 1;
			mod_delayed_work(ib_nl_wq, &ib_nl_timed_work, 1);
			break;
		}
	}
	spin_unlock_irqrestore(&ib_nl_request_lock, flags);

	return found;
}

static void send_handler(struct ib_mad_agent *agent,
			 struct ib_mad_send_wc *mad_send_wc);

static void ib_nl_process_good_resolve_rsp(struct ib_sa_query *query,
					   const struct nlmsghdr *nlh)
{
	struct ib_mad_send_wc mad_send_wc;
	struct ib_sa_mad *mad = NULL;
	const struct nlattr *head, *curr;
	struct ib_path_rec_data  *rec;
	int len, rem;
	u32 mask = 0;
	int status = -EIO;

	if (query->callback) {
		head = (const struct nlattr *) nlmsg_data(nlh);
		len = nlmsg_len(nlh);
		switch (query->path_use) {
		case LS_RESOLVE_PATH_USE_UNIDIRECTIONAL:
			mask = IB_PATH_PRIMARY | IB_PATH_OUTBOUND;
			break;

		case LS_RESOLVE_PATH_USE_ALL:
		case LS_RESOLVE_PATH_USE_GMP:
		default:
			mask = IB_PATH_PRIMARY | IB_PATH_GMP |
				IB_PATH_BIDIRECTIONAL;
			break;
		}
		nla_for_each_attr(curr, head, len, rem) {
			if (curr->nla_type == LS_NLA_TYPE_PATH_RECORD) {
				rec = nla_data(curr);
				/*
				 * Get the first one. In the future, we may
				 * need to get up to 6 pathrecords.
				 */
				if ((rec->flags & mask) == mask) {
					mad = query->mad_buf->mad;
					mad->mad_hdr.method |=
						IB_MGMT_METHOD_RESP;
					memcpy(mad->data, rec->path_rec,
					       sizeof(rec->path_rec));
					status = 0;
					break;
				}
			}
		}
		query->callback(query, status, mad);
	}

	mad_send_wc.send_buf = query->mad_buf;
	mad_send_wc.status = IB_WC_SUCCESS;
	send_handler(query->mad_buf->mad_agent, &mad_send_wc);
}

static void ib_nl_request_timeout(struct work_struct *work)
{
	unsigned long flags;
	struct ib_sa_query *query;
	unsigned long delay;
	struct ib_mad_send_wc mad_send_wc;
	int ret;

	spin_lock_irqsave(&ib_nl_request_lock, flags);
	while (!list_empty(&ib_nl_request_list)) {
		query = list_entry(ib_nl_request_list.next,
				   struct ib_sa_query, list);

		if (time_after(query->timeout, jiffies)) {
			delay = query->timeout - jiffies;
			if ((long)delay <= 0)
				delay = 1;
			queue_delayed_work(ib_nl_wq, &ib_nl_timed_work, delay);
			break;
		}

		list_del(&query->list);
		ib_sa_disable_local_svc(query);
		/* Hold the lock to protect against query cancellation */
		if (ib_sa_query_cancelled(query))
			ret = -1;
		else
			ret = ib_post_send_mad(query->mad_buf, NULL);
		if (ret) {
			mad_send_wc.send_buf = query->mad_buf;
			mad_send_wc.status = IB_WC_WR_FLUSH_ERR;
			spin_unlock_irqrestore(&ib_nl_request_lock, flags);
			send_handler(query->port->agent, &mad_send_wc);
			spin_lock_irqsave(&ib_nl_request_lock, flags);
		}
	}
	spin_unlock_irqrestore(&ib_nl_request_lock, flags);
}

int ib_nl_handle_set_timeout(struct sk_buff *skb,
			     struct nlmsghdr *nlh,
			     struct netlink_ext_ack *extack)
{
	int timeout, delta, abs_delta;
	const struct nlattr *attr;
	unsigned long flags;
	struct ib_sa_query *query;
	long delay = 0;
	struct nlattr *tb[LS_NLA_TYPE_MAX];
	int ret;

	if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
	    !(NETLINK_CB(skb).sk))
		return -EPERM;

	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
			nlmsg_len(nlh), ib_nl_policy, NULL);
	attr = (const struct nlattr *)tb[LS_NLA_TYPE_TIMEOUT];
	if (ret || !attr)
		goto settimeout_out;

	timeout = *(int *) nla_data(attr);
	if (timeout < IB_SA_LOCAL_SVC_TIMEOUT_MIN)
		timeout = IB_SA_LOCAL_SVC_TIMEOUT_MIN;
	if (timeout > IB_SA_LOCAL_SVC_TIMEOUT_MAX)
		timeout = IB_SA_LOCAL_SVC_TIMEOUT_MAX;

	delta = timeout - sa_local_svc_timeout_ms;
	if (delta < 0)
		abs_delta = -delta;
	else
		abs_delta = delta;

	if (delta != 0) {
		spin_lock_irqsave(&ib_nl_request_lock, flags);
		sa_local_svc_timeout_ms = timeout;
		list_for_each_entry(query, &ib_nl_request_list, list) {
			if (delta < 0 && abs_delta > query->timeout)
				query->timeout = 0;
			else
				query->timeout += delta;

			/* Get the new delay from the first entry */
			if (!delay) {
				delay = query->timeout - jiffies;
				if (delay <= 0)
					delay = 1;
			}
		}
		if (delay)
			mod_delayed_work(ib_nl_wq, &ib_nl_timed_work,
					 (unsigned long)delay);
		spin_unlock_irqrestore(&ib_nl_request_lock, flags);
	}

settimeout_out:
	return skb->len;
}

static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
{
	struct nlattr *tb[LS_NLA_TYPE_MAX];
	int ret;

	if (nlh->nlmsg_flags & RDMA_NL_LS_F_ERR)
		return 0;

	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
			nlmsg_len(nlh), ib_nl_policy, NULL);
	if (ret)
		return 0;

	return 1;
}

int ib_nl_handle_resolve_resp(struct sk_buff *skb,
			      struct nlmsghdr *nlh,
			      struct netlink_ext_ack *extack)
{
	unsigned long flags;
	struct ib_sa_query *query;
	struct ib_mad_send_buf *send_buf;
	struct ib_mad_send_wc mad_send_wc;
	int found = 0;
	int ret;

	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
	    !(NETLINK_CB(skb).sk))
		return -EPERM;

	spin_lock_irqsave(&ib_nl_request_lock, flags);
	list_for_each_entry(query, &ib_nl_request_list, list) {
		/*
		 * If the query is cancelled, let the timeout routine
		 * take care of it.
		 */
		if (nlh->nlmsg_seq == query->seq) {
			found = !ib_sa_query_cancelled(query);
			if (found)
				list_del(&query->list);
			break;
		}
	}

	if (!found) {
		spin_unlock_irqrestore(&ib_nl_request_lock, flags);
		goto resp_out;
	}

	send_buf = query->mad_buf;

	if (!ib_nl_is_good_resolve_resp(nlh)) {
		/* if the result is a failure, send out the packet via IB */
		ib_sa_disable_local_svc(query);
		ret = ib_post_send_mad(query->mad_buf, NULL);
		spin_unlock_irqrestore(&ib_nl_request_lock, flags);
		if (ret) {
			mad_send_wc.send_buf = send_buf;
			mad_send_wc.status = IB_WC_GENERAL_ERR;
			send_handler(query->port->agent, &mad_send_wc);
		}
	} else {
		spin_unlock_irqrestore(&ib_nl_request_lock, flags);
		ib_nl_process_good_resolve_rsp(query, nlh);
	}

resp_out:
	return skb->len;
}

static void free_sm_ah(struct kref *kref)
{
	struct ib_sa_sm_ah *sm_ah = container_of(kref, struct ib_sa_sm_ah, ref);

	rdma_destroy_ah(sm_ah->ah);
	kfree(sm_ah);
}

void ib_sa_register_client(struct ib_sa_client *client)
{
	atomic_set(&client->users, 1);
	init_completion(&client->comp);
}
EXPORT_SYMBOL(ib_sa_register_client);

void ib_sa_unregister_client(struct ib_sa_client *client)
{
	ib_sa_client_put(client);
	wait_for_completion(&client->comp);
}
EXPORT_SYMBOL(ib_sa_unregister_client);

/**
 * ib_sa_cancel_query - try to cancel an SA query
 * @id:ID of query to cancel
 * @query:query pointer to cancel
 *
 * Try to cancel an SA query.  If the id and query don't match up or
 * the query has already completed, nothing is done.  Otherwise the
 * query is canceled and will complete with a status of -EINTR.
 */
void ib_sa_cancel_query(int id, struct ib_sa_query *query)
{
	unsigned long flags;
	struct ib_mad_agent *agent;
	struct ib_mad_send_buf *mad_buf;

	spin_lock_irqsave(&idr_lock, flags);
	if (idr_find(&query_idr, id) != query) {
		spin_unlock_irqrestore(&idr_lock, flags);
		return;
	}
	agent = query->port->agent;
	mad_buf = query->mad_buf;
	spin_unlock_irqrestore(&idr_lock, flags);

	/*
	 * If the query is still on the netlink request list, schedule
	 * it to be cancelled by the timeout routine. Otherwise, it has been
	 * sent to the MAD layer and has to be cancelled from there.
	 */
	if (!ib_nl_cancel_request(query))
		ib_cancel_mad(agent, mad_buf);
}
EXPORT_SYMBOL(ib_sa_cancel_query);

static u8 get_src_path_mask(struct ib_device *device, u8 port_num)
{
	struct ib_sa_device *sa_dev;
	struct ib_sa_port   *port;
	unsigned long flags;
	u8 src_path_mask;

	sa_dev = ib_get_client_data(device, &sa_client);
	if (!sa_dev)
		return 0x7f;

	port  = &sa_dev->port[port_num - sa_dev->start_port];
	spin_lock_irqsave(&port->ah_lock, flags);
	src_path_mask = port->sm_ah ? port->sm_ah->src_path_mask : 0x7f;
	spin_unlock_irqrestore(&port->ah_lock, flags);

	return src_path_mask;
}

int ib_init_ah_attr_from_path(struct ib_device *device, u8 port_num,
			      struct sa_path_rec *rec,
			      struct rdma_ah_attr *ah_attr)
{
	int ret;
	u16 gid_index;
	int use_roce;
	struct net_device *ndev = NULL;

	memset(ah_attr, 0, sizeof *ah_attr);
	ah_attr->type = rdma_ah_find_type(device, port_num);

	rdma_ah_set_dlid(ah_attr, be32_to_cpu(sa_path_get_dlid(rec)));

	if ((ah_attr->type == RDMA_AH_ATTR_TYPE_OPA) &&
	    (rdma_ah_get_dlid(ah_attr) == be16_to_cpu(IB_LID_PERMISSIVE)))
		rdma_ah_set_make_grd(ah_attr, true);

	rdma_ah_set_sl(ah_attr, rec->sl);
	rdma_ah_set_path_bits(ah_attr, be32_to_cpu(sa_path_get_slid(rec)) &
			      get_src_path_mask(device, port_num));
	rdma_ah_set_port_num(ah_attr, port_num);
	rdma_ah_set_static_rate(ah_attr, rec->rate);
	use_roce = rdma_cap_eth_ah(device, port_num);

	if (use_roce) {
		struct net_device *idev;
		struct net_device *resolved_dev;
		struct rdma_dev_addr dev_addr = {
			.bound_dev_if = ((sa_path_get_ifindex(rec) >= 0) ?
					 sa_path_get_ifindex(rec) : 0),
			.net = sa_path_get_ndev(rec) ?
				sa_path_get_ndev(rec) :
				&init_net
		};
		union {
			struct sockaddr     _sockaddr;
			struct sockaddr_in  _sockaddr_in;
			struct sockaddr_in6 _sockaddr_in6;
		} sgid_addr, dgid_addr;

		if (!device->get_netdev)
			return -EOPNOTSUPP;

		rdma_gid2ip(&sgid_addr._sockaddr, &rec->sgid);
		rdma_gid2ip(&dgid_addr._sockaddr, &rec->dgid);

		/* validate the route */
		ret = rdma_resolve_ip_route(&sgid_addr._sockaddr,
					    &dgid_addr._sockaddr, &dev_addr);
		if (ret)
			return ret;

		if ((dev_addr.network == RDMA_NETWORK_IPV4 ||
		     dev_addr.network == RDMA_NETWORK_IPV6) &&
		    rec->rec_type != SA_PATH_REC_TYPE_ROCE_V2)
			return -EINVAL;

		idev = device->get_netdev(device, port_num);
		if (!idev)
			return -ENODEV;

		resolved_dev = dev_get_by_index(dev_addr.net,
						dev_addr.bound_dev_if);
		if (resolved_dev->flags & IFF_LOOPBACK) {
			dev_put(resolved_dev);
			resolved_dev = idev;
			dev_hold(resolved_dev);
		}
		ndev = ib_get_ndev_from_path(rec);
		rcu_read_lock();
		if ((ndev && ndev != resolved_dev) ||
		    (resolved_dev != idev &&
		     !rdma_is_upper_dev_rcu(idev, resolved_dev)))
			ret = -EHOSTUNREACH;
		rcu_read_unlock();
		dev_put(idev);
		dev_put(resolved_dev);
		if (ret) {
			if (ndev)
				dev_put(ndev);
			return ret;
		}
	}

	if (rec->hop_limit > 0 || use_roce) {
		enum ib_gid_type type = sa_conv_pathrec_to_gid_type(rec);

		ret = ib_find_cached_gid_by_port(device, &rec->sgid, type,
						 port_num, ndev, &gid_index);
		if (ret) {
			if (ndev)
				dev_put(ndev);
			return ret;
		}

		rdma_ah_set_grh(ah_attr, &rec->dgid,
				be32_to_cpu(rec->flow_label),
				gid_index, rec->hop_limit,
				rec->traffic_class);
		if (ndev)
			dev_put(ndev);
	}

	if (use_roce) {
		u8 *dmac = sa_path_get_dmac(rec);

		if (!dmac)
			return -EINVAL;
		memcpy(ah_attr->roce.dmac, dmac, ETH_ALEN);
	}

	return 0;
}
EXPORT_SYMBOL(ib_init_ah_attr_from_path);

static int alloc_mad(struct ib_sa_query *query, gfp_t gfp_mask)
{
	struct rdma_ah_attr ah_attr;
	unsigned long flags;

	spin_lock_irqsave(&query->port->ah_lock, flags);
	if (!query->port->sm_ah) {
		spin_unlock_irqrestore(&query->port->ah_lock, flags);
		return -EAGAIN;
	}
	kref_get(&query->port->sm_ah->ref);
	query->sm_ah = query->port->sm_ah;
	spin_unlock_irqrestore(&query->port->ah_lock, flags);

	/*
	 * Always check if sm_ah has valid dlid assigned,
	 * before querying for class port info
	 */
	if ((rdma_query_ah(query->sm_ah->ah, &ah_attr) < 0) ||
	    !rdma_is_valid_unicast_lid(&ah_attr)) {
		kref_put(&query->sm_ah->ref, free_sm_ah);
		return -EAGAIN;
	}
	query->mad_buf = ib_create_send_mad(query->port->agent, 1,
					    query->sm_ah->pkey_index,
					    0, IB_MGMT_SA_HDR, IB_MGMT_SA_DATA,
					    gfp_mask,
					    ((query->flags & IB_SA_QUERY_OPA) ?
					     OPA_MGMT_BASE_VERSION :
					     IB_MGMT_BASE_VERSION));
	if (IS_ERR(query->mad_buf)) {
		kref_put(&query->sm_ah->ref, free_sm_ah);
		return -ENOMEM;
	}

	query->mad_buf->ah = query->sm_ah->ah;

	return 0;
}

static void free_mad(struct ib_sa_query *query)
{
	ib_free_send_mad(query->mad_buf);
	kref_put(&query->sm_ah->ref, free_sm_ah);
}

static void init_mad(struct ib_sa_query *query, struct ib_mad_agent *agent)
{
	struct ib_sa_mad *mad = query->mad_buf->mad;
	unsigned long flags;

	memset(mad, 0, sizeof *mad);

	if (query->flags & IB_SA_QUERY_OPA) {
		mad->mad_hdr.base_version  = OPA_MGMT_BASE_VERSION;
		mad->mad_hdr.class_version = OPA_SA_CLASS_VERSION;
	} else {
		mad->mad_hdr.base_version  = IB_MGMT_BASE_VERSION;
		mad->mad_hdr.class_version = IB_SA_CLASS_VERSION;
	}
	mad->mad_hdr.mgmt_class    = IB_MGMT_CLASS_SUBN_ADM;
	spin_lock_irqsave(&tid_lock, flags);
	mad->mad_hdr.tid           =
		cpu_to_be64(((u64) agent->hi_tid) << 32 | tid++);
	spin_unlock_irqrestore(&tid_lock, flags);
}

static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask)
{
	bool preload = gfpflags_allow_blocking(gfp_mask);
	unsigned long flags;
	int ret, id;

	if (preload)
		idr_preload(gfp_mask);
	spin_lock_irqsave(&idr_lock, flags);

	id = idr_alloc(&query_idr, query, 0, 0, GFP_NOWAIT);

	spin_unlock_irqrestore(&idr_lock, flags);
	if (preload)
		idr_preload_end();
	if (id < 0)
		return id;

	query->mad_buf->timeout_ms  = timeout_ms;
	query->mad_buf->context[0] = query;
	query->id = id;

	if ((query->flags & IB_SA_ENABLE_LOCAL_SERVICE) &&
	    (!(query->flags & IB_SA_QUERY_OPA))) {
		if (!rdma_nl_chk_listeners(RDMA_NL_GROUP_LS)) {
			if (!ib_nl_make_request(query, gfp_mask))
				return id;
		}
		ib_sa_disable_local_svc(query);
	}

	ret = ib_post_send_mad(query->mad_buf, NULL);
	if (ret) {
		spin_lock_irqsave(&idr_lock, flags);
		idr_remove(&query_idr, id);
		spin_unlock_irqrestore(&idr_lock, flags);
	}

	/*
	 * It's not safe to dereference query any more, because the
	 * send may already have completed and freed the query in
	 * another context.
	 */
	return ret ? ret : id;
}

void ib_sa_unpack_path(void *attribute, struct sa_path_rec *rec)
{
	ib_unpack(path_rec_table, ARRAY_SIZE(path_rec_table), attribute, rec);
}
EXPORT_SYMBOL(ib_sa_unpack_path);

void ib_sa_pack_path(struct sa_path_rec *rec, void *attribute)
{
	ib_pack(path_rec_table, ARRAY_SIZE(path_rec_table), rec, attribute);
}
EXPORT_SYMBOL(ib_sa_pack_path);

static bool ib_sa_opa_pathrecord_support(struct ib_sa_client *client,
					 struct ib_device *device,
					 u8 port_num)
{
	struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
	struct ib_sa_port *port;
	unsigned long flags;
	bool ret = false;

	if (!sa_dev)
		return ret;

	port = &sa_dev->port[port_num - sa_dev->start_port];
	spin_lock_irqsave(&port->classport_lock, flags);
	if (!port->classport_info.valid)
		goto ret;

	if (port->classport_info.data.type == RDMA_CLASS_PORT_INFO_OPA)
		ret = opa_get_cpi_capmask2(&port->classport_info.data.opa) &
			OPA_CLASS_PORT_INFO_PR_SUPPORT;
ret:
	spin_unlock_irqrestore(&port->classport_lock, flags);
	return ret;
}

enum opa_pr_supported {
	PR_NOT_SUPPORTED,
	PR_OPA_SUPPORTED,
	PR_IB_SUPPORTED
};

/**
 * Check if current PR query can be an OPA query.
 * Retuns PR_NOT_SUPPORTED if a path record query is not
 * possible, PR_OPA_SUPPORTED if an OPA path record query
 * is possible and PR_IB_SUPPORTED if an IB path record
 * query is possible.
 */
static int opa_pr_query_possible(struct ib_sa_client *client,
				 struct ib_device *device,
				 u8 port_num,
				 struct sa_path_rec *rec)
{
	struct ib_port_attr port_attr;

	if (ib_query_port(device, port_num, &port_attr))
		return PR_NOT_SUPPORTED;

	if (ib_sa_opa_pathrecord_support(client, device, port_num))
		return PR_OPA_SUPPORTED;

	if (port_attr.lid >= be16_to_cpu(IB_MULTICAST_LID_BASE))
		return PR_NOT_SUPPORTED;
	else
		return PR_IB_SUPPORTED;
}

static void ib_sa_path_rec_callback(struct ib_sa_query *sa_query,
				    int status,
				    struct ib_sa_mad *mad)
{
	struct ib_sa_path_query *query =
		container_of(sa_query, struct ib_sa_path_query, sa_query);

	if (mad) {
		struct sa_path_rec rec;

		if (sa_query->flags & IB_SA_QUERY_OPA) {
			ib_unpack(opa_path_rec_table,
				  ARRAY_SIZE(opa_path_rec_table),
				  mad->data, &rec);
			rec.rec_type = SA_PATH_REC_TYPE_OPA;
			query->callback(status, &rec, query->context);
		} else {
			ib_unpack(path_rec_table,
				  ARRAY_SIZE(path_rec_table),
				  mad->data, &rec);
			rec.rec_type = SA_PATH_REC_TYPE_IB;
			sa_path_set_ndev(&rec, NULL);
			sa_path_set_ifindex(&rec, 0);
			sa_path_set_dmac_zero(&rec);

			if (query->conv_pr) {
				struct sa_path_rec opa;

				memset(&opa, 0, sizeof(struct sa_path_rec));
				sa_convert_path_ib_to_opa(&opa, &rec);
				query->callback(status, &opa, query->context);
			} else {
				query->callback(status, &rec, query->context);
			}
		}
	} else
		query->callback(status, NULL, query->context);
}

static void ib_sa_path_rec_release(struct ib_sa_query *sa_query)
{
	struct ib_sa_path_query *query =
		container_of(sa_query, struct ib_sa_path_query, sa_query);

	kfree(query->conv_pr);
	kfree(query);
}

/**
 * ib_sa_path_rec_get - Start a Path get query
 * @client:SA client
 * @device:device to send query on
 * @port_num: port number to send query on
 * @rec:Path Record to send in query
 * @comp_mask:component mask to send in query
 * @timeout_ms:time to wait for response
 * @gfp_mask:GFP mask to use for internal allocations
 * @callback:function called when query completes, times out or is
 * canceled
 * @context:opaque user context passed to callback
 * @sa_query:query context, used to cancel query
 *
 * Send a Path Record Get query to the SA to look up a path.  The
 * callback function will be called when the query completes (or
 * fails); status is 0 for a successful response, -EINTR if the query
 * is canceled, -ETIMEDOUT is the query timed out, or -EIO if an error
 * occurred sending the query.  The resp parameter of the callback is
 * only valid if status is 0.
 *
 * If the return value of ib_sa_path_rec_get() is negative, it is an
 * error code.  Otherwise it is a query ID that can be used to cancel
 * the query.
 */
int ib_sa_path_rec_get(struct ib_sa_client *client,
		       struct ib_device *device, u8 port_num,
		       struct sa_path_rec *rec,
		       ib_sa_comp_mask comp_mask,
		       int timeout_ms, gfp_t gfp_mask,
		       void (*callback)(int status,
					struct sa_path_rec *resp,
					void *context),
		       void *context,
		       struct ib_sa_query **sa_query)
{
	struct ib_sa_path_query *query;
	struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
	struct ib_sa_port   *port;
	struct ib_mad_agent *agent;
	struct ib_sa_mad *mad;
	enum opa_pr_supported status;
	int ret;

	if (!sa_dev)
		return -ENODEV;

	if ((rec->rec_type != SA_PATH_REC_TYPE_IB) &&
	    (rec->rec_type != SA_PATH_REC_TYPE_OPA))
		return -EINVAL;

	port  = &sa_dev->port[port_num - sa_dev->start_port];
	agent = port->agent;

	query = kzalloc(sizeof(*query), gfp_mask);
	if (!query)
		return -ENOMEM;

	query->sa_query.port     = port;
	if (rec->rec_type == SA_PATH_REC_TYPE_OPA) {
		status = opa_pr_query_possible(client, device, port_num, rec);
		if (status == PR_NOT_SUPPORTED) {
			ret = -EINVAL;
			goto err1;
		} else if (status == PR_OPA_SUPPORTED) {
			query->sa_query.flags |= IB_SA_QUERY_OPA;
		} else {
			query->conv_pr =
				kmalloc(sizeof(*query->conv_pr), gfp_mask);
			if (!query->conv_pr) {
				ret = -ENOMEM;
				goto err1;
			}
		}
	}

	ret = alloc_mad(&query->sa_query, gfp_mask);
	if (ret)
		goto err2;

	ib_sa_client_get(client);
	query->sa_query.client = client;
	query->callback        = callback;
	query->context         = context;

	mad = query->sa_query.mad_buf->mad;
	init_mad(&query->sa_query, agent);

	query->sa_query.callback = callback ? ib_sa_path_rec_callback : NULL;
	query->sa_query.release  = ib_sa_path_rec_release;
	mad->mad_hdr.method	 = IB_MGMT_METHOD_GET;
	mad->mad_hdr.attr_id	 = cpu_to_be16(IB_SA_ATTR_PATH_REC);
	mad->sa_hdr.comp_mask	 = comp_mask;

	if (query->sa_query.flags & IB_SA_QUERY_OPA) {
		ib_pack(opa_path_rec_table, ARRAY_SIZE(opa_path_rec_table),
			rec, mad->data);
	} else if (query->conv_pr) {
		sa_convert_path_opa_to_ib(query->conv_pr, rec);
		ib_pack(path_rec_table, ARRAY_SIZE(path_rec_table),
			query->conv_pr, mad->data);
	} else {
		ib_pack(path_rec_table, ARRAY_SIZE(path_rec_table),
			rec, mad->data);
	}

	*sa_query = &query->sa_query;

	query->sa_query.flags |= IB_SA_ENABLE_LOCAL_SERVICE;
	query->sa_query.mad_buf->context[1] = (query->conv_pr) ?
						query->conv_pr : rec;

	ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
	if (ret < 0)
		goto err3;

	return ret;

err3:
	*sa_query = NULL;
	ib_sa_client_put(query->sa_query.client);
	free_mad(&query->sa_query);
err2:
	kfree(query->conv_pr);
err1:
	kfree(query);
	return ret;
}
EXPORT_SYMBOL(ib_sa_path_rec_get);

static void ib_sa_service_rec_callback(struct ib_sa_query *sa_query,
				    int status,
				    struct ib_sa_mad *mad)
{
	struct ib_sa_service_query *query =
		container_of(sa_query, struct ib_sa_service_query, sa_query);

	if (mad) {
		struct ib_sa_service_rec rec;

		ib_unpack(service_rec_table, ARRAY_SIZE(service_rec_table),
			  mad->data, &rec);
		query->callback(status, &rec, query->context);
	} else
		query->callback(status, NULL, query->context);
}

static void ib_sa_service_rec_release(struct ib_sa_query *sa_query)
{
	kfree(container_of(sa_query, struct ib_sa_service_query, sa_query));
}

/**
 * ib_sa_service_rec_query - Start Service Record operation
 * @client:SA client
 * @device:device to send request on
 * @port_num: port number to send request on
 * @method:SA method - should be get, set, or delete
 * @rec:Service Record to send in request
 * @comp_mask:component mask to send in request
 * @timeout_ms:time to wait for response
 * @gfp_mask:GFP mask to use for internal allocations
 * @callback:function called when request completes, times out or is
 * canceled
 * @context:opaque user context passed to callback
 * @sa_query:request context, used to cancel request
 *
 * Send a Service Record set/get/delete to the SA to register,
 * unregister or query a service record.
 * The callback function will be called when the request completes (or
 * fails); status is 0 for a successful response, -EINTR if the query
 * is canceled, -ETIMEDOUT is the query timed out, or -EIO if an error
 * occurred sending the query.  The resp parameter of the callback is
 * only valid if status is 0.
 *
 * If the return value of ib_sa_service_rec_query() is negative, it is an
 * error code.  Otherwise it is a request ID that can be used to cancel
 * the query.
 */
int ib_sa_service_rec_query(struct ib_sa_client *client,
			    struct ib_device *device, u8 port_num, u8 method,
			    struct ib_sa_service_rec *rec,
			    ib_sa_comp_mask comp_mask,
			    int timeout_ms, gfp_t gfp_mask,
			    void (*callback)(int status,
					     struct ib_sa_service_rec *resp,
					     void *context),
			    void *context,
			    struct ib_sa_query **sa_query)
{
	struct ib_sa_service_query *query;
	struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
	struct ib_sa_port   *port;
	struct ib_mad_agent *agent;
	struct ib_sa_mad *mad;
	int ret;

	if (!sa_dev)
		return -ENODEV;

	port  = &sa_dev->port[port_num - sa_dev->start_port];
	agent = port->agent;

	if (method != IB_MGMT_METHOD_GET &&
	    method != IB_MGMT_METHOD_SET &&
	    method != IB_SA_METHOD_DELETE)
		return -EINVAL;

	query = kzalloc(sizeof(*query), gfp_mask);
	if (!query)
		return -ENOMEM;

	query->sa_query.port     = port;
	ret = alloc_mad(&query->sa_query, gfp_mask);
	if (ret)
		goto err1;

	ib_sa_client_get(client);
	query->sa_query.client = client;
	query->callback        = callback;
	query->context         = context;

	mad = query->sa_query.mad_buf->mad;
	init_mad(&query->sa_query, agent);

	query->sa_query.callback = callback ? ib_sa_service_rec_callback : NULL;
	query->sa_query.release  = ib_sa_service_rec_release;
	mad->mad_hdr.method	 = method;
	mad->mad_hdr.attr_id	 = cpu_to_be16(IB_SA_ATTR_SERVICE_REC);
	mad->sa_hdr.comp_mask	 = comp_mask;

	ib_pack(service_rec_table, ARRAY_SIZE(service_rec_table),
		rec, mad->data);

	*sa_query = &query->sa_query;

	ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
	if (ret < 0)
		goto err2;

	return ret;

err2:
	*sa_query = NULL;
	ib_sa_client_put(query->sa_query.client);
	free_mad(&query->sa_query);

err1:
	kfree(query);
	return ret;
}
EXPORT_SYMBOL(ib_sa_service_rec_query);

static void ib_sa_mcmember_rec_callback(struct ib_sa_query *sa_query,
					int status,
					struct ib_sa_mad *mad)
{
	struct ib_sa_mcmember_query *query =
		container_of(sa_query, struct ib_sa_mcmember_query, sa_query);

	if (mad) {
		struct ib_sa_mcmember_rec rec;

		ib_unpack(mcmember_rec_table, ARRAY_SIZE(mcmember_rec_table),
			  mad->data, &rec);
		query->callback(status, &rec, query->context);
	} else
		query->callback(status, NULL, query->context);
}

static void ib_sa_mcmember_rec_release(struct ib_sa_query *sa_query)
{
	kfree(container_of(sa_query, struct ib_sa_mcmember_query, sa_query));
}

int ib_sa_mcmember_rec_query(struct ib_sa_client *client,
			     struct ib_device *device, u8 port_num,
			     u8 method,
			     struct ib_sa_mcmember_rec *rec,
			     ib_sa_comp_mask comp_mask,
			     int timeout_ms, gfp_t gfp_mask,
			     void (*callback)(int status,
					      struct ib_sa_mcmember_rec *resp,
					      void *context),
			     void *context,
			     struct ib_sa_query **sa_query)
{
	struct ib_sa_mcmember_query *query;
	struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
	struct ib_sa_port   *port;
	struct ib_mad_agent *agent;
	struct ib_sa_mad *mad;
	int ret;

	if (!sa_dev)
		return -ENODEV;

	port  = &sa_dev->port[port_num - sa_dev->start_port];
	agent = port->agent;

	query = kzalloc(sizeof(*query), gfp_mask);
	if (!query)
		return -ENOMEM;

	query->sa_query.port     = port;
	ret = alloc_mad(&query->sa_query, gfp_mask);
	if (ret)
		goto err1;

	ib_sa_client_get(client);
	query->sa_query.client = client;
	query->callback        = callback;
	query->context         = context;

	mad = query->sa_query.mad_buf->mad;
	init_mad(&query->sa_query, agent);

	query->sa_query.callback = callback ? ib_sa_mcmember_rec_callback : NULL;
	query->sa_query.release  = ib_sa_mcmember_rec_release;
	mad->mad_hdr.method	 = method;
	mad->mad_hdr.attr_id	 = cpu_to_be16(IB_SA_ATTR_MC_MEMBER_REC);
	mad->sa_hdr.comp_mask	 = comp_mask;

	ib_pack(mcmember_rec_table, ARRAY_SIZE(mcmember_rec_table),
		rec, mad->data);

	*sa_query = &query->sa_query;

	ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
	if (ret < 0)
		goto err2;

	return ret;

err2:
	*sa_query = NULL;
	ib_sa_client_put(query->sa_query.client);
	free_mad(&query->sa_query);

err1:
	kfree(query);
	return ret;
}

/* Support GuidInfoRecord */
static void ib_sa_guidinfo_rec_callback(struct ib_sa_query *sa_query,
					int status,
					struct ib_sa_mad *mad)
{
	struct ib_sa_guidinfo_query *query =
		container_of(sa_query, struct ib_sa_guidinfo_query, sa_query);

	if (mad) {
		struct ib_sa_guidinfo_rec rec;

		ib_unpack(guidinfo_rec_table, ARRAY_SIZE(guidinfo_rec_table),
			  mad->data, &rec);
		query->callback(status, &rec, query->context);
	} else
		query->callback(status, NULL, query->context);
}

static void ib_sa_guidinfo_rec_release(struct ib_sa_query *sa_query)
{
	kfree(container_of(sa_query, struct ib_sa_guidinfo_query, sa_query));
}

int ib_sa_guid_info_rec_query(struct ib_sa_client *client,
			      struct ib_device *device, u8 port_num,
			      struct ib_sa_guidinfo_rec *rec,
			      ib_sa_comp_mask comp_mask, u8 method,
			      int timeout_ms, gfp_t gfp_mask,
			      void (*callback)(int status,
					       struct ib_sa_guidinfo_rec *resp,
					       void *context),
			      void *context,
			      struct ib_sa_query **sa_query)
{
	struct ib_sa_guidinfo_query *query;
	struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
	struct ib_sa_port *port;
	struct ib_mad_agent *agent;
	struct ib_sa_mad *mad;
	int ret;

	if (!sa_dev)
		return -ENODEV;

	if (method != IB_MGMT_METHOD_GET &&
	    method != IB_MGMT_METHOD_SET &&
	    method != IB_SA_METHOD_DELETE) {
		return -EINVAL;
	}

	port  = &sa_dev->port[port_num - sa_dev->start_port];
	agent = port->agent;

	query = kzalloc(sizeof(*query), gfp_mask);
	if (!query)
		return -ENOMEM;

	query->sa_query.port = port;
	ret = alloc_mad(&query->sa_query, gfp_mask);
	if (ret)
		goto err1;

	ib_sa_client_get(client);
	query->sa_query.client = client;
	query->callback        = callback;
	query->context         = context;

	mad = query->sa_query.mad_buf->mad;
	init_mad(&query->sa_query, agent);

	query->sa_query.callback = callback ? ib_sa_guidinfo_rec_callback : NULL;
	query->sa_query.release  = ib_sa_guidinfo_rec_release;

	mad->mad_hdr.method	 = method;
	mad->mad_hdr.attr_id	 = cpu_to_be16(IB_SA_ATTR_GUID_INFO_REC);
	mad->sa_hdr.comp_mask	 = comp_mask;

	ib_pack(guidinfo_rec_table, ARRAY_SIZE(guidinfo_rec_table), rec,
		mad->data);

	*sa_query = &query->sa_query;

	ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
	if (ret < 0)
		goto err2;

	return ret;

err2:
	*sa_query = NULL;
	ib_sa_client_put(query->sa_query.client);
	free_mad(&query->sa_query);

err1:
	kfree(query);
	return ret;
}
EXPORT_SYMBOL(ib_sa_guid_info_rec_query);

bool ib_sa_sendonly_fullmem_support(struct ib_sa_client *client,
				    struct ib_device *device,
				    u8 port_num)
{
	struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
	struct ib_sa_port *port;
	bool ret = false;
	unsigned long flags;

	if (!sa_dev)
		return ret;

	port  = &sa_dev->port[port_num - sa_dev->start_port];

	spin_lock_irqsave(&port->classport_lock, flags);
	if ((port->classport_info.valid) &&
	    (port->classport_info.data.type == RDMA_CLASS_PORT_INFO_IB))
		ret = ib_get_cpi_capmask2(&port->classport_info.data.ib)
			& IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT;
	spin_unlock_irqrestore(&port->classport_lock, flags);
	return ret;
}
EXPORT_SYMBOL(ib_sa_sendonly_fullmem_support);

struct ib_classport_info_context {
	struct completion	done;
	struct ib_sa_query	*sa_query;
};

static void ib_classportinfo_cb(void *context)
{
	struct ib_classport_info_context *cb_ctx = context;

	complete(&cb_ctx->done);
}

static void ib_sa_classport_info_rec_callback(struct ib_sa_query *sa_query,
					      int status,
					      struct ib_sa_mad *mad)
{
	unsigned long flags;
	struct ib_sa_classport_info_query *query =
		container_of(sa_query, struct ib_sa_classport_info_query, sa_query);
	struct ib_sa_classport_cache *info = &sa_query->port->classport_info;

	if (mad) {
		if (sa_query->flags & IB_SA_QUERY_OPA) {
			struct opa_class_port_info rec;

			ib_unpack(opa_classport_info_rec_table,
				  ARRAY_SIZE(opa_classport_info_rec_table),
				  mad->data, &rec);

			spin_lock_irqsave(&sa_query->port->classport_lock,
					  flags);
			if (!status && !info->valid) {
				memcpy(&info->data.opa, &rec,
				       sizeof(info->data.opa));

				info->valid = true;
				info->data.type = RDMA_CLASS_PORT_INFO_OPA;
			}
			spin_unlock_irqrestore(&sa_query->port->classport_lock,
					       flags);

		} else {
			struct ib_class_port_info rec;

			ib_unpack(ib_classport_info_rec_table,
				  ARRAY_SIZE(ib_classport_info_rec_table),
				  mad->data, &rec);

			spin_lock_irqsave(&sa_query->port->classport_lock,
					  flags);
			if (!status && !info->valid) {
				memcpy(&info->data.ib, &rec,
				       sizeof(info->data.ib));

				info->valid = true;
				info->data.type = RDMA_CLASS_PORT_INFO_IB;
			}
			spin_unlock_irqrestore(&sa_query->port->classport_lock,
					       flags);
		}
	}
	query->callback(query->context);
}

static void ib_sa_classport_info_rec_release(struct ib_sa_query *sa_query)
{
	kfree(container_of(sa_query, struct ib_sa_classport_info_query,
			   sa_query));
}

static int ib_sa_classport_info_rec_query(struct ib_sa_port *port,
					  int timeout_ms,
					  void (*callback)(void *context),
					  void *context,
					  struct ib_sa_query **sa_query)
{
	struct ib_mad_agent *agent;
	struct ib_sa_classport_info_query *query;
	struct ib_sa_mad *mad;
	gfp_t gfp_mask = GFP_KERNEL;
	int ret;

	agent = port->agent;

	query = kzalloc(sizeof(*query), gfp_mask);
	if (!query)
		return -ENOMEM;

	query->sa_query.port = port;
	query->sa_query.flags |= rdma_cap_opa_ah(port->agent->device,
						 port->port_num) ?
				 IB_SA_QUERY_OPA : 0;
	ret = alloc_mad(&query->sa_query, gfp_mask);
	if (ret)
		goto err_free;

	query->callback = callback;
	query->context = context;

	mad = query->sa_query.mad_buf->mad;
	init_mad(&query->sa_query, agent);

	query->sa_query.callback = ib_sa_classport_info_rec_callback;
	query->sa_query.release  = ib_sa_classport_info_rec_release;
	mad->mad_hdr.method	 = IB_MGMT_METHOD_GET;
	mad->mad_hdr.attr_id	 = cpu_to_be16(IB_SA_ATTR_CLASS_PORTINFO);
	mad->sa_hdr.comp_mask	 = 0;
	*sa_query = &query->sa_query;

	ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
	if (ret < 0)
		goto err_free_mad;

	return ret;

err_free_mad:
	*sa_query = NULL;
	free_mad(&query->sa_query);

err_free:
	kfree(query);
	return ret;
}

static void update_ib_cpi(struct work_struct *work)
{
	struct ib_sa_port *port =
		container_of(work, struct ib_sa_port, ib_cpi_work.work);
	struct ib_classport_info_context *cb_context;
	unsigned long flags;
	int ret;

	/* If the classport info is valid, nothing
	 * to do here.
	 */
	spin_lock_irqsave(&port->classport_lock, flags);
	if (port->classport_info.valid) {
		spin_unlock_irqrestore(&port->classport_lock, flags);
		return;
	}
	spin_unlock_irqrestore(&port->classport_lock, flags);

	cb_context = kmalloc(sizeof(*cb_context), GFP_KERNEL);
	if (!cb_context)
		goto err_nomem;

	init_completion(&cb_context->done);

	ret = ib_sa_classport_info_rec_query(port, 3000,
					     ib_classportinfo_cb, cb_context,
					     &cb_context->sa_query);
	if (ret < 0)
		goto free_cb_err;
	wait_for_completion(&cb_context->done);
free_cb_err:
	kfree(cb_context);
	spin_lock_irqsave(&port->classport_lock, flags);

	/* If the classport info is still not valid, the query should have
	 * failed for some reason. Retry issuing the query
	 */
	if (!port->classport_info.valid) {
		port->classport_info.retry_cnt++;
		if (port->classport_info.retry_cnt <=
		    IB_SA_CPI_MAX_RETRY_CNT) {
			unsigned long delay =
				msecs_to_jiffies(IB_SA_CPI_RETRY_WAIT);

			queue_delayed_work(ib_wq, &port->ib_cpi_work, delay);
		}
	}
	spin_unlock_irqrestore(&port->classport_lock, flags);

err_nomem:
	return;
}

static void send_handler(struct ib_mad_agent *agent,
			 struct ib_mad_send_wc *mad_send_wc)
{
	struct ib_sa_query *query = mad_send_wc->send_buf->context[0];
	unsigned long flags;

	if (query->callback)
		switch (mad_send_wc->status) {
		case IB_WC_SUCCESS:
			/* No callback -- already got recv */
			break;
		case IB_WC_RESP_TIMEOUT_ERR:
			query->callback(query, -ETIMEDOUT, NULL);
			break;
		case IB_WC_WR_FLUSH_ERR:
			query->callback(query, -EINTR, NULL);
			break;
		default:
			query->callback(query, -EIO, NULL);
			break;
		}

	spin_lock_irqsave(&idr_lock, flags);
	idr_remove(&query_idr, query->id);
	spin_unlock_irqrestore(&idr_lock, flags);

	free_mad(query);
	if (query->client)
		ib_sa_client_put(query->client);
	query->release(query);
}

static void recv_handler(struct ib_mad_agent *mad_agent,
			 struct ib_mad_send_buf *send_buf,
			 struct ib_mad_recv_wc *mad_recv_wc)
{
	struct ib_sa_query *query;

	if (!send_buf)
		return;

	query = send_buf->context[0];
	if (query->callback) {
		if (mad_recv_wc->wc->status == IB_WC_SUCCESS)
			query->callback(query,
					mad_recv_wc->recv_buf.mad->mad_hdr.status ?
					-EINVAL : 0,
					(struct ib_sa_mad *) mad_recv_wc->recv_buf.mad);
		else
			query->callback(query, -EIO, NULL);
	}

	ib_free_recv_mad(mad_recv_wc);
}

static void update_sm_ah(struct work_struct *work)
{
	struct ib_sa_port *port =
		container_of(work, struct ib_sa_port, update_task);
	struct ib_sa_sm_ah *new_ah;
	struct ib_port_attr port_attr;
	struct rdma_ah_attr   ah_attr;

	if (ib_query_port(port->agent->device, port->port_num, &port_attr)) {
		pr_warn("Couldn't query port\n");
		return;
	}

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

	kref_init(&new_ah->ref);
	new_ah->src_path_mask = (1 << port_attr.lmc) - 1;

	new_ah->pkey_index = 0;
	if (ib_find_pkey(port->agent->device, port->port_num,
			 IB_DEFAULT_PKEY_FULL, &new_ah->pkey_index))
		pr_err("Couldn't find index for default PKey\n");

	memset(&ah_attr, 0, sizeof(ah_attr));
	ah_attr.type = rdma_ah_find_type(port->agent->device,
					 port->port_num);
	rdma_ah_set_dlid(&ah_attr, port_attr.sm_lid);
	rdma_ah_set_sl(&ah_attr, port_attr.sm_sl);
	rdma_ah_set_port_num(&ah_attr, port->port_num);
	if (port_attr.grh_required) {
		if (ah_attr.type == RDMA_AH_ATTR_TYPE_OPA) {
			rdma_ah_set_make_grd(&ah_attr, true);
		} else {
			rdma_ah_set_ah_flags(&ah_attr, IB_AH_GRH);
			rdma_ah_set_subnet_prefix(&ah_attr,
						  cpu_to_be64(port_attr.subnet_prefix));
			rdma_ah_set_interface_id(&ah_attr,
						 cpu_to_be64(IB_SA_WELL_KNOWN_GUID));
		}
	}

	new_ah->ah = rdma_create_ah(port->agent->qp->pd, &ah_attr);
	if (IS_ERR(new_ah->ah)) {
		pr_warn("Couldn't create new SM AH\n");
		kfree(new_ah);
		return;
	}

	spin_lock_irq(&port->ah_lock);
	if (port->sm_ah)
		kref_put(&port->sm_ah->ref, free_sm_ah);
	port->sm_ah = new_ah;
	spin_unlock_irq(&port->ah_lock);
}

static void ib_sa_event(struct ib_event_handler *handler,
			struct ib_event *event)
{
	if (event->event == IB_EVENT_PORT_ERR    ||
	    event->event == IB_EVENT_PORT_ACTIVE ||
	    event->event == IB_EVENT_LID_CHANGE  ||
	    event->event == IB_EVENT_PKEY_CHANGE ||
	    event->event == IB_EVENT_SM_CHANGE   ||
	    event->event == IB_EVENT_CLIENT_REREGISTER) {
		unsigned long flags;
		struct ib_sa_device *sa_dev =
			container_of(handler, typeof(*sa_dev), event_handler);
		u8 port_num = event->element.port_num - sa_dev->start_port;
		struct ib_sa_port *port = &sa_dev->port[port_num];

		if (!rdma_cap_ib_sa(handler->device, port->port_num))
			return;

		spin_lock_irqsave(&port->ah_lock, flags);
		if (port->sm_ah)
			kref_put(&port->sm_ah->ref, free_sm_ah);
		port->sm_ah = NULL;
		spin_unlock_irqrestore(&port->ah_lock, flags);

		if (event->event == IB_EVENT_SM_CHANGE ||
		    event->event == IB_EVENT_CLIENT_REREGISTER ||
		    event->event == IB_EVENT_LID_CHANGE ||
		    event->event == IB_EVENT_PORT_ACTIVE) {
			unsigned long delay =
				msecs_to_jiffies(IB_SA_CPI_RETRY_WAIT);

			spin_lock_irqsave(&port->classport_lock, flags);
			port->classport_info.valid = false;
			port->classport_info.retry_cnt = 0;
			spin_unlock_irqrestore(&port->classport_lock, flags);
			queue_delayed_work(ib_wq,
					   &port->ib_cpi_work, delay);
		}
		queue_work(ib_wq, &sa_dev->port[port_num].update_task);
	}
}

static void ib_sa_add_one(struct ib_device *device)
{
	struct ib_sa_device *sa_dev;
	int s, e, i;
	int count = 0;

	s = rdma_start_port(device);
	e = rdma_end_port(device);

	sa_dev = kzalloc(sizeof *sa_dev +
			 (e - s + 1) * sizeof (struct ib_sa_port),
			 GFP_KERNEL);
	if (!sa_dev)
		return;

	sa_dev->start_port = s;
	sa_dev->end_port   = e;

	for (i = 0; i <= e - s; ++i) {
		spin_lock_init(&sa_dev->port[i].ah_lock);
		if (!rdma_cap_ib_sa(device, i + 1))
			continue;

		sa_dev->port[i].sm_ah    = NULL;
		sa_dev->port[i].port_num = i + s;

		spin_lock_init(&sa_dev->port[i].classport_lock);
		sa_dev->port[i].classport_info.valid = false;

		sa_dev->port[i].agent =
			ib_register_mad_agent(device, i + s, IB_QPT_GSI,
					      NULL, 0, send_handler,
					      recv_handler, sa_dev, 0);
		if (IS_ERR(sa_dev->port[i].agent))
			goto err;

		INIT_WORK(&sa_dev->port[i].update_task, update_sm_ah);
		INIT_DELAYED_WORK(&sa_dev->port[i].ib_cpi_work,
				  update_ib_cpi);

		count++;
	}

	if (!count)
		goto free;

	ib_set_client_data(device, &sa_client, sa_dev);

	/*
	 * We register our event handler after everything is set up,
	 * and then update our cached info after the event handler is
	 * registered to avoid any problems if a port changes state
	 * during our initialization.
	 */

	INIT_IB_EVENT_HANDLER(&sa_dev->event_handler, device, ib_sa_event);
	ib_register_event_handler(&sa_dev->event_handler);

	for (i = 0; i <= e - s; ++i) {
		if (rdma_cap_ib_sa(device, i + 1))
			update_sm_ah(&sa_dev->port[i].update_task);
	}

	return;

err:
	while (--i >= 0) {
		if (rdma_cap_ib_sa(device, i + 1))
			ib_unregister_mad_agent(sa_dev->port[i].agent);
	}
free:
	kfree(sa_dev);
	return;
}

static void ib_sa_remove_one(struct ib_device *device, void *client_data)
{
	struct ib_sa_device *sa_dev = client_data;
	int i;

	if (!sa_dev)
		return;

	ib_unregister_event_handler(&sa_dev->event_handler);
	flush_workqueue(ib_wq);

	for (i = 0; i <= sa_dev->end_port - sa_dev->start_port; ++i) {
		if (rdma_cap_ib_sa(device, i + 1)) {
			cancel_delayed_work_sync(&sa_dev->port[i].ib_cpi_work);
			ib_unregister_mad_agent(sa_dev->port[i].agent);
			if (sa_dev->port[i].sm_ah)
				kref_put(&sa_dev->port[i].sm_ah->ref, free_sm_ah);
		}

	}

	kfree(sa_dev);
}

int ib_sa_init(void)
{
	int ret;

	get_random_bytes(&tid, sizeof tid);

	atomic_set(&ib_nl_sa_request_seq, 0);

	ret = ib_register_client(&sa_client);
	if (ret) {
		pr_err("Couldn't register ib_sa client\n");
		goto err1;
	}

	ret = mcast_init();
	if (ret) {
		pr_err("Couldn't initialize multicast handling\n");
		goto err2;
	}

	ib_nl_wq = alloc_ordered_workqueue("ib_nl_sa_wq", WQ_MEM_RECLAIM);
	if (!ib_nl_wq) {
		ret = -ENOMEM;
		goto err3;
	}

	INIT_DELAYED_WORK(&ib_nl_timed_work, ib_nl_request_timeout);

	return 0;

err3:
	mcast_cleanup();
err2:
	ib_unregister_client(&sa_client);
err1:
	return ret;
}

void ib_sa_cleanup(void)
{
	cancel_delayed_work(&ib_nl_timed_work);
	flush_workqueue(ib_nl_wq);
	destroy_workqueue(ib_nl_wq);
	mcast_cleanup();
	ib_unregister_client(&sa_client);
	idr_destroy(&query_idr);
}