Free Electrons

Embedded Linux Experts

   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
/*
 * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved.
 * Copyright (c) 2015 System Fabric Works, Inc. 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/dma-mapping.h>
#include <net/addrconf.h>
#include "rxe.h"
#include "rxe_loc.h"
#include "rxe_queue.h"
#include "rxe_hw_counters.h"

static int rxe_query_device(struct ib_device *dev,
			    struct ib_device_attr *attr,
			    struct ib_udata *uhw)
{
	struct rxe_dev *rxe = to_rdev(dev);

	if (uhw->inlen || uhw->outlen)
		return -EINVAL;

	*attr = rxe->attr;
	return 0;
}

static void rxe_eth_speed_to_ib_speed(int speed, u8 *active_speed,
				      u8 *active_width)
{
	if (speed <= 1000) {
		*active_width = IB_WIDTH_1X;
		*active_speed = IB_SPEED_SDR;
	} else if (speed <= 10000) {
		*active_width = IB_WIDTH_1X;
		*active_speed = IB_SPEED_FDR10;
	} else if (speed <= 20000) {
		*active_width = IB_WIDTH_4X;
		*active_speed = IB_SPEED_DDR;
	} else if (speed <= 30000) {
		*active_width = IB_WIDTH_4X;
		*active_speed = IB_SPEED_QDR;
	} else if (speed <= 40000) {
		*active_width = IB_WIDTH_4X;
		*active_speed = IB_SPEED_FDR10;
	} else {
		*active_width = IB_WIDTH_4X;
		*active_speed = IB_SPEED_EDR;
	}
}

static int rxe_query_port(struct ib_device *dev,
			  u8 port_num, struct ib_port_attr *attr)
{
	struct rxe_dev *rxe = to_rdev(dev);
	struct rxe_port *port;
	u32 speed;

	if (unlikely(port_num != 1)) {
		pr_warn("invalid port_number %d\n", port_num);
		goto err1;
	}

	port = &rxe->port;

	/* *attr being zeroed by the caller, avoid zeroing it here */
	*attr = port->attr;

	mutex_lock(&rxe->usdev_lock);
	if (rxe->ndev->ethtool_ops->get_link_ksettings) {
		struct ethtool_link_ksettings ks;

		rxe->ndev->ethtool_ops->get_link_ksettings(rxe->ndev, &ks);
		speed = ks.base.speed;
	} else if (rxe->ndev->ethtool_ops->get_settings) {
		struct ethtool_cmd cmd;

		rxe->ndev->ethtool_ops->get_settings(rxe->ndev, &cmd);
		speed = cmd.speed;
	} else {
		pr_warn("%s speed is unknown, defaulting to 1000\n",
			rxe->ndev->name);
		speed = 1000;
	}
	rxe_eth_speed_to_ib_speed(speed, &attr->active_speed,
				  &attr->active_width);
	mutex_unlock(&rxe->usdev_lock);

	return 0;

err1:
	return -EINVAL;
}

static int rxe_query_gid(struct ib_device *device,
			 u8 port_num, int index, union ib_gid *gid)
{
	int ret;

	if (index > RXE_PORT_GID_TBL_LEN)
		return -EINVAL;

	ret = ib_get_cached_gid(device, port_num, index, gid, NULL);
	if (ret == -EAGAIN) {
		memcpy(gid, &zgid, sizeof(*gid));
		return 0;
	}

	return ret;
}

static int rxe_add_gid(struct ib_device *device, u8 port_num, unsigned int
		       index, const union ib_gid *gid,
		       const struct ib_gid_attr *attr, void **context)
{
	if (index >= RXE_PORT_GID_TBL_LEN)
		return -EINVAL;
	return 0;
}

static int rxe_del_gid(struct ib_device *device, u8 port_num, unsigned int
		       index, void **context)
{
	if (index >= RXE_PORT_GID_TBL_LEN)
		return -EINVAL;
	return 0;
}

static struct net_device *rxe_get_netdev(struct ib_device *device,
					 u8 port_num)
{
	struct rxe_dev *rxe = to_rdev(device);

	if (rxe->ndev) {
		dev_hold(rxe->ndev);
		return rxe->ndev;
	}

	return NULL;
}

static int rxe_query_pkey(struct ib_device *device,
			  u8 port_num, u16 index, u16 *pkey)
{
	struct rxe_dev *rxe = to_rdev(device);
	struct rxe_port *port;

	if (unlikely(port_num != 1)) {
		dev_warn(device->dev.parent, "invalid port_num = %d\n",
			 port_num);
		goto err1;
	}

	port = &rxe->port;

	if (unlikely(index >= port->attr.pkey_tbl_len)) {
		dev_warn(device->dev.parent, "invalid index = %d\n",
			 index);
		goto err1;
	}

	*pkey = port->pkey_tbl[index];
	return 0;

err1:
	return -EINVAL;
}

static int rxe_modify_device(struct ib_device *dev,
			     int mask, struct ib_device_modify *attr)
{
	struct rxe_dev *rxe = to_rdev(dev);

	if (mask & IB_DEVICE_MODIFY_SYS_IMAGE_GUID)
		rxe->attr.sys_image_guid = cpu_to_be64(attr->sys_image_guid);

	if (mask & IB_DEVICE_MODIFY_NODE_DESC) {
		memcpy(rxe->ib_dev.node_desc,
		       attr->node_desc, sizeof(rxe->ib_dev.node_desc));
	}

	return 0;
}

static int rxe_modify_port(struct ib_device *dev,
			   u8 port_num, int mask, struct ib_port_modify *attr)
{
	struct rxe_dev *rxe = to_rdev(dev);
	struct rxe_port *port;

	if (unlikely(port_num != 1)) {
		pr_warn("invalid port_num = %d\n", port_num);
		goto err1;
	}

	port = &rxe->port;

	port->attr.port_cap_flags |= attr->set_port_cap_mask;
	port->attr.port_cap_flags &= ~attr->clr_port_cap_mask;

	if (mask & IB_PORT_RESET_QKEY_CNTR)
		port->attr.qkey_viol_cntr = 0;

	return 0;

err1:
	return -EINVAL;
}

static enum rdma_link_layer rxe_get_link_layer(struct ib_device *dev,
					       u8 port_num)
{
	struct rxe_dev *rxe = to_rdev(dev);

	return rxe_link_layer(rxe, port_num);
}

static struct ib_ucontext *rxe_alloc_ucontext(struct ib_device *dev,
					      struct ib_udata *udata)
{
	struct rxe_dev *rxe = to_rdev(dev);
	struct rxe_ucontext *uc;

	uc = rxe_alloc(&rxe->uc_pool);
	return uc ? &uc->ibuc : ERR_PTR(-ENOMEM);
}

static int rxe_dealloc_ucontext(struct ib_ucontext *ibuc)
{
	struct rxe_ucontext *uc = to_ruc(ibuc);

	rxe_drop_ref(uc);
	return 0;
}

static int rxe_port_immutable(struct ib_device *dev, u8 port_num,
			      struct ib_port_immutable *immutable)
{
	int err;
	struct ib_port_attr attr;

	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;

	err = ib_query_port(dev, port_num, &attr);
	if (err)
		return err;

	immutable->pkey_tbl_len = attr.pkey_tbl_len;
	immutable->gid_tbl_len = attr.gid_tbl_len;
	immutable->max_mad_size = IB_MGMT_MAD_SIZE;

	return 0;
}

static struct ib_pd *rxe_alloc_pd(struct ib_device *dev,
				  struct ib_ucontext *context,
				  struct ib_udata *udata)
{
	struct rxe_dev *rxe = to_rdev(dev);
	struct rxe_pd *pd;

	pd = rxe_alloc(&rxe->pd_pool);
	return pd ? &pd->ibpd : ERR_PTR(-ENOMEM);
}

static int rxe_dealloc_pd(struct ib_pd *ibpd)
{
	struct rxe_pd *pd = to_rpd(ibpd);

	rxe_drop_ref(pd);
	return 0;
}

static int rxe_init_av(struct rxe_dev *rxe, struct rdma_ah_attr *attr,
		       struct rxe_av *av)
{
	int err;
	union ib_gid sgid;
	struct ib_gid_attr sgid_attr;

	err = ib_get_cached_gid(&rxe->ib_dev, rdma_ah_get_port_num(attr),
				rdma_ah_read_grh(attr)->sgid_index, &sgid,
				&sgid_attr);
	if (err) {
		pr_err("Failed to query sgid. err = %d\n", err);
		return err;
	}

	err = rxe_av_from_attr(rxe, rdma_ah_get_port_num(attr), av, attr);
	if (!err)
		err = rxe_av_fill_ip_info(rxe, av, attr, &sgid_attr, &sgid);

	if (sgid_attr.ndev)
		dev_put(sgid_attr.ndev);
	return err;
}

static struct ib_ah *rxe_create_ah(struct ib_pd *ibpd,
				   struct rdma_ah_attr *attr,
				   struct ib_udata *udata)

{
	int err;
	struct rxe_dev *rxe = to_rdev(ibpd->device);
	struct rxe_pd *pd = to_rpd(ibpd);
	struct rxe_ah *ah;

	err = rxe_av_chk_attr(rxe, attr);
	if (err)
		goto err1;

	ah = rxe_alloc(&rxe->ah_pool);
	if (!ah) {
		err = -ENOMEM;
		goto err1;
	}

	rxe_add_ref(pd);
	ah->pd = pd;

	err = rxe_init_av(rxe, attr, &ah->av);
	if (err)
		goto err2;

	return &ah->ibah;

err2:
	rxe_drop_ref(pd);
	rxe_drop_ref(ah);
err1:
	return ERR_PTR(err);
}

static int rxe_modify_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr)
{
	int err;
	struct rxe_dev *rxe = to_rdev(ibah->device);
	struct rxe_ah *ah = to_rah(ibah);

	err = rxe_av_chk_attr(rxe, attr);
	if (err)
		return err;

	err = rxe_init_av(rxe, attr, &ah->av);
	if (err)
		return err;

	return 0;
}

static int rxe_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr)
{
	struct rxe_dev *rxe = to_rdev(ibah->device);
	struct rxe_ah *ah = to_rah(ibah);

	memset(attr, 0, sizeof(*attr));
	attr->type = ibah->type;
	rxe_av_to_attr(rxe, &ah->av, attr);
	return 0;
}

static int rxe_destroy_ah(struct ib_ah *ibah)
{
	struct rxe_ah *ah = to_rah(ibah);

	rxe_drop_ref(ah->pd);
	rxe_drop_ref(ah);
	return 0;
}

static int post_one_recv(struct rxe_rq *rq, struct ib_recv_wr *ibwr)
{
	int err;
	int i;
	u32 length;
	struct rxe_recv_wqe *recv_wqe;
	int num_sge = ibwr->num_sge;

	if (unlikely(queue_full(rq->queue))) {
		err = -ENOMEM;
		goto err1;
	}

	if (unlikely(num_sge > rq->max_sge)) {
		err = -EINVAL;
		goto err1;
	}

	length = 0;
	for (i = 0; i < num_sge; i++)
		length += ibwr->sg_list[i].length;

	recv_wqe = producer_addr(rq->queue);
	recv_wqe->wr_id = ibwr->wr_id;
	recv_wqe->num_sge = num_sge;

	memcpy(recv_wqe->dma.sge, ibwr->sg_list,
	       num_sge * sizeof(struct ib_sge));

	recv_wqe->dma.length		= length;
	recv_wqe->dma.resid		= length;
	recv_wqe->dma.num_sge		= num_sge;
	recv_wqe->dma.cur_sge		= 0;
	recv_wqe->dma.sge_offset	= 0;

	/* make sure all changes to the work queue are written before we
	 * update the producer pointer
	 */
	smp_wmb();

	advance_producer(rq->queue);
	return 0;

err1:
	return err;
}

static struct ib_srq *rxe_create_srq(struct ib_pd *ibpd,
				     struct ib_srq_init_attr *init,
				     struct ib_udata *udata)
{
	int err;
	struct rxe_dev *rxe = to_rdev(ibpd->device);
	struct rxe_pd *pd = to_rpd(ibpd);
	struct rxe_srq *srq;
	struct ib_ucontext *context = udata ? ibpd->uobject->context : NULL;

	err = rxe_srq_chk_attr(rxe, NULL, &init->attr, IB_SRQ_INIT_MASK);
	if (err)
		goto err1;

	srq = rxe_alloc(&rxe->srq_pool);
	if (!srq) {
		err = -ENOMEM;
		goto err1;
	}

	rxe_add_index(srq);
	rxe_add_ref(pd);
	srq->pd = pd;

	err = rxe_srq_from_init(rxe, srq, init, context, udata);
	if (err)
		goto err2;

	return &srq->ibsrq;

err2:
	rxe_drop_ref(pd);
	rxe_drop_index(srq);
	rxe_drop_ref(srq);
err1:
	return ERR_PTR(err);
}

static int rxe_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
			  enum ib_srq_attr_mask mask,
			  struct ib_udata *udata)
{
	int err;
	struct rxe_srq *srq = to_rsrq(ibsrq);
	struct rxe_dev *rxe = to_rdev(ibsrq->device);

	err = rxe_srq_chk_attr(rxe, srq, attr, mask);
	if (err)
		goto err1;

	err = rxe_srq_from_attr(rxe, srq, attr, mask, udata);
	if (err)
		goto err1;

	return 0;

err1:
	return err;
}

static int rxe_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr)
{
	struct rxe_srq *srq = to_rsrq(ibsrq);

	if (srq->error)
		return -EINVAL;

	attr->max_wr = srq->rq.queue->buf->index_mask;
	attr->max_sge = srq->rq.max_sge;
	attr->srq_limit = srq->limit;
	return 0;
}

static int rxe_destroy_srq(struct ib_srq *ibsrq)
{
	struct rxe_srq *srq = to_rsrq(ibsrq);

	if (srq->rq.queue)
		rxe_queue_cleanup(srq->rq.queue);

	rxe_drop_ref(srq->pd);
	rxe_drop_index(srq);
	rxe_drop_ref(srq);

	return 0;
}

static int rxe_post_srq_recv(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
			     struct ib_recv_wr **bad_wr)
{
	int err = 0;
	unsigned long flags;
	struct rxe_srq *srq = to_rsrq(ibsrq);

	spin_lock_irqsave(&srq->rq.producer_lock, flags);

	while (wr) {
		err = post_one_recv(&srq->rq, wr);
		if (unlikely(err))
			break;
		wr = wr->next;
	}

	spin_unlock_irqrestore(&srq->rq.producer_lock, flags);

	if (err)
		*bad_wr = wr;

	return err;
}

static struct ib_qp *rxe_create_qp(struct ib_pd *ibpd,
				   struct ib_qp_init_attr *init,
				   struct ib_udata *udata)
{
	int err;
	struct rxe_dev *rxe = to_rdev(ibpd->device);
	struct rxe_pd *pd = to_rpd(ibpd);
	struct rxe_qp *qp;

	err = rxe_qp_chk_init(rxe, init);
	if (err)
		goto err1;

	qp = rxe_alloc(&rxe->qp_pool);
	if (!qp) {
		err = -ENOMEM;
		goto err1;
	}

	if (udata) {
		if (udata->inlen) {
			err = -EINVAL;
			goto err2;
		}
		qp->is_user = 1;
	}

	rxe_add_index(qp);

	err = rxe_qp_from_init(rxe, qp, pd, init, udata, ibpd);
	if (err)
		goto err3;

	return &qp->ibqp;

err3:
	rxe_drop_index(qp);
err2:
	rxe_drop_ref(qp);
err1:
	return ERR_PTR(err);
}

static int rxe_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
			 int mask, struct ib_udata *udata)
{
	int err;
	struct rxe_dev *rxe = to_rdev(ibqp->device);
	struct rxe_qp *qp = to_rqp(ibqp);

	err = rxe_qp_chk_attr(rxe, qp, attr, mask);
	if (err)
		goto err1;

	err = rxe_qp_from_attr(qp, attr, mask, udata);
	if (err)
		goto err1;

	return 0;

err1:
	return err;
}

static int rxe_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
			int mask, struct ib_qp_init_attr *init)
{
	struct rxe_qp *qp = to_rqp(ibqp);

	rxe_qp_to_init(qp, init);
	rxe_qp_to_attr(qp, attr, mask);

	return 0;
}

static int rxe_destroy_qp(struct ib_qp *ibqp)
{
	struct rxe_qp *qp = to_rqp(ibqp);

	rxe_qp_destroy(qp);
	rxe_drop_index(qp);
	rxe_drop_ref(qp);
	return 0;
}

static int validate_send_wr(struct rxe_qp *qp, struct ib_send_wr *ibwr,
			    unsigned int mask, unsigned int length)
{
	int num_sge = ibwr->num_sge;
	struct rxe_sq *sq = &qp->sq;

	if (unlikely(num_sge > sq->max_sge))
		goto err1;

	if (unlikely(mask & WR_ATOMIC_MASK)) {
		if (length < 8)
			goto err1;

		if (atomic_wr(ibwr)->remote_addr & 0x7)
			goto err1;
	}

	if (unlikely((ibwr->send_flags & IB_SEND_INLINE) &&
		     (length > sq->max_inline)))
		goto err1;

	return 0;

err1:
	return -EINVAL;
}

static void init_send_wr(struct rxe_qp *qp, struct rxe_send_wr *wr,
			 struct ib_send_wr *ibwr)
{
	wr->wr_id = ibwr->wr_id;
	wr->num_sge = ibwr->num_sge;
	wr->opcode = ibwr->opcode;
	wr->send_flags = ibwr->send_flags;

	if (qp_type(qp) == IB_QPT_UD ||
	    qp_type(qp) == IB_QPT_SMI ||
	    qp_type(qp) == IB_QPT_GSI) {
		wr->wr.ud.remote_qpn = ud_wr(ibwr)->remote_qpn;
		wr->wr.ud.remote_qkey = ud_wr(ibwr)->remote_qkey;
		if (qp_type(qp) == IB_QPT_GSI)
			wr->wr.ud.pkey_index = ud_wr(ibwr)->pkey_index;
		if (wr->opcode == IB_WR_SEND_WITH_IMM)
			wr->ex.imm_data = ibwr->ex.imm_data;
	} else {
		switch (wr->opcode) {
		case IB_WR_RDMA_WRITE_WITH_IMM:
			wr->ex.imm_data = ibwr->ex.imm_data;
		case IB_WR_RDMA_READ:
		case IB_WR_RDMA_WRITE:
			wr->wr.rdma.remote_addr = rdma_wr(ibwr)->remote_addr;
			wr->wr.rdma.rkey	= rdma_wr(ibwr)->rkey;
			break;
		case IB_WR_SEND_WITH_IMM:
			wr->ex.imm_data = ibwr->ex.imm_data;
			break;
		case IB_WR_SEND_WITH_INV:
			wr->ex.invalidate_rkey = ibwr->ex.invalidate_rkey;
			break;
		case IB_WR_ATOMIC_CMP_AND_SWP:
		case IB_WR_ATOMIC_FETCH_AND_ADD:
			wr->wr.atomic.remote_addr =
				atomic_wr(ibwr)->remote_addr;
			wr->wr.atomic.compare_add =
				atomic_wr(ibwr)->compare_add;
			wr->wr.atomic.swap = atomic_wr(ibwr)->swap;
			wr->wr.atomic.rkey = atomic_wr(ibwr)->rkey;
			break;
		case IB_WR_LOCAL_INV:
			wr->ex.invalidate_rkey = ibwr->ex.invalidate_rkey;
		break;
		case IB_WR_REG_MR:
			wr->wr.reg.mr = reg_wr(ibwr)->mr;
			wr->wr.reg.key = reg_wr(ibwr)->key;
			wr->wr.reg.access = reg_wr(ibwr)->access;
		break;
		default:
			break;
		}
	}
}

static int init_send_wqe(struct rxe_qp *qp, struct ib_send_wr *ibwr,
			 unsigned int mask, unsigned int length,
			 struct rxe_send_wqe *wqe)
{
	int num_sge = ibwr->num_sge;
	struct ib_sge *sge;
	int i;
	u8 *p;

	init_send_wr(qp, &wqe->wr, ibwr);

	if (qp_type(qp) == IB_QPT_UD ||
	    qp_type(qp) == IB_QPT_SMI ||
	    qp_type(qp) == IB_QPT_GSI)
		memcpy(&wqe->av, &to_rah(ud_wr(ibwr)->ah)->av, sizeof(wqe->av));

	if (unlikely(ibwr->send_flags & IB_SEND_INLINE)) {
		p = wqe->dma.inline_data;

		sge = ibwr->sg_list;
		for (i = 0; i < num_sge; i++, sge++) {
			memcpy(p, (void *)(uintptr_t)sge->addr,
					sge->length);

			p += sge->length;
		}
	} else if (mask & WR_REG_MASK) {
		wqe->mask = mask;
		wqe->state = wqe_state_posted;
		return 0;
	} else
		memcpy(wqe->dma.sge, ibwr->sg_list,
		       num_sge * sizeof(struct ib_sge));

	wqe->iova		= (mask & WR_ATOMIC_MASK) ?
					atomic_wr(ibwr)->remote_addr :
					rdma_wr(ibwr)->remote_addr;
	wqe->mask		= mask;
	wqe->dma.length		= length;
	wqe->dma.resid		= length;
	wqe->dma.num_sge	= num_sge;
	wqe->dma.cur_sge	= 0;
	wqe->dma.sge_offset	= 0;
	wqe->state		= wqe_state_posted;
	wqe->ssn		= atomic_add_return(1, &qp->ssn);

	return 0;
}

static int post_one_send(struct rxe_qp *qp, struct ib_send_wr *ibwr,
			 unsigned int mask, u32 length)
{
	int err;
	struct rxe_sq *sq = &qp->sq;
	struct rxe_send_wqe *send_wqe;
	unsigned long flags;

	err = validate_send_wr(qp, ibwr, mask, length);
	if (err)
		return err;

	spin_lock_irqsave(&qp->sq.sq_lock, flags);

	if (unlikely(queue_full(sq->queue))) {
		err = -ENOMEM;
		goto err1;
	}

	send_wqe = producer_addr(sq->queue);

	err = init_send_wqe(qp, ibwr, mask, length, send_wqe);
	if (unlikely(err))
		goto err1;

	/*
	 * make sure all changes to the work queue are
	 * written before we update the producer pointer
	 */
	smp_wmb();

	advance_producer(sq->queue);
	spin_unlock_irqrestore(&qp->sq.sq_lock, flags);

	return 0;

err1:
	spin_unlock_irqrestore(&qp->sq.sq_lock, flags);
	return err;
}

static int rxe_post_send_kernel(struct rxe_qp *qp, struct ib_send_wr *wr,
				struct ib_send_wr **bad_wr)
{
	int err = 0;
	unsigned int mask;
	unsigned int length = 0;
	int i;
	int must_sched;

	while (wr) {
		mask = wr_opcode_mask(wr->opcode, qp);
		if (unlikely(!mask)) {
			err = -EINVAL;
			*bad_wr = wr;
			break;
		}

		if (unlikely((wr->send_flags & IB_SEND_INLINE) &&
			     !(mask & WR_INLINE_MASK))) {
			err = -EINVAL;
			*bad_wr = wr;
			break;
		}

		length = 0;
		for (i = 0; i < wr->num_sge; i++)
			length += wr->sg_list[i].length;

		err = post_one_send(qp, wr, mask, length);

		if (err) {
			*bad_wr = wr;
			break;
		}
		wr = wr->next;
	}

	/*
	 * Must sched in case of GSI QP because ib_send_mad() hold irq lock,
	 * and the requester call ip_local_out_sk() that takes spin_lock_bh.
	 */
	must_sched = (qp_type(qp) == IB_QPT_GSI) ||
			(queue_count(qp->sq.queue) > 1);

	rxe_run_task(&qp->req.task, must_sched);

	return err;
}

static int rxe_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
			 struct ib_send_wr **bad_wr)
{
	struct rxe_qp *qp = to_rqp(ibqp);

	if (unlikely(!qp->valid)) {
		*bad_wr = wr;
		return -EINVAL;
	}

	if (unlikely(qp->req.state < QP_STATE_READY)) {
		*bad_wr = wr;
		return -EINVAL;
	}

	if (qp->is_user) {
		/* Utilize process context to do protocol processing */
		rxe_run_task(&qp->req.task, 0);
		return 0;
	} else
		return rxe_post_send_kernel(qp, wr, bad_wr);
}

static int rxe_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
			 struct ib_recv_wr **bad_wr)
{
	int err = 0;
	struct rxe_qp *qp = to_rqp(ibqp);
	struct rxe_rq *rq = &qp->rq;
	unsigned long flags;

	if (unlikely((qp_state(qp) < IB_QPS_INIT) || !qp->valid)) {
		*bad_wr = wr;
		err = -EINVAL;
		goto err1;
	}

	if (unlikely(qp->srq)) {
		*bad_wr = wr;
		err = -EINVAL;
		goto err1;
	}

	spin_lock_irqsave(&rq->producer_lock, flags);

	while (wr) {
		err = post_one_recv(rq, wr);
		if (unlikely(err)) {
			*bad_wr = wr;
			break;
		}
		wr = wr->next;
	}

	spin_unlock_irqrestore(&rq->producer_lock, flags);

	if (qp->resp.state == QP_STATE_ERROR)
		rxe_run_task(&qp->resp.task, 1);

err1:
	return err;
}

static struct ib_cq *rxe_create_cq(struct ib_device *dev,
				   const struct ib_cq_init_attr *attr,
				   struct ib_ucontext *context,
				   struct ib_udata *udata)
{
	int err;
	struct rxe_dev *rxe = to_rdev(dev);
	struct rxe_cq *cq;

	if (attr->flags)
		return ERR_PTR(-EINVAL);

	err = rxe_cq_chk_attr(rxe, NULL, attr->cqe, attr->comp_vector, udata);
	if (err)
		goto err1;

	cq = rxe_alloc(&rxe->cq_pool);
	if (!cq) {
		err = -ENOMEM;
		goto err1;
	}

	err = rxe_cq_from_init(rxe, cq, attr->cqe, attr->comp_vector,
			       context, udata);
	if (err)
		goto err2;

	return &cq->ibcq;

err2:
	rxe_drop_ref(cq);
err1:
	return ERR_PTR(err);
}

static int rxe_destroy_cq(struct ib_cq *ibcq)
{
	struct rxe_cq *cq = to_rcq(ibcq);

	rxe_drop_ref(cq);
	return 0;
}

static int rxe_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
{
	int err;
	struct rxe_cq *cq = to_rcq(ibcq);
	struct rxe_dev *rxe = to_rdev(ibcq->device);

	err = rxe_cq_chk_attr(rxe, cq, cqe, 0, udata);
	if (err)
		goto err1;

	err = rxe_cq_resize_queue(cq, cqe, udata);
	if (err)
		goto err1;

	return 0;

err1:
	return err;
}

static int rxe_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
{
	int i;
	struct rxe_cq *cq = to_rcq(ibcq);
	struct rxe_cqe *cqe;
	unsigned long flags;

	spin_lock_irqsave(&cq->cq_lock, flags);
	for (i = 0; i < num_entries; i++) {
		cqe = queue_head(cq->queue);
		if (!cqe)
			break;

		memcpy(wc++, &cqe->ibwc, sizeof(*wc));
		advance_consumer(cq->queue);
	}
	spin_unlock_irqrestore(&cq->cq_lock, flags);

	return i;
}

static int rxe_peek_cq(struct ib_cq *ibcq, int wc_cnt)
{
	struct rxe_cq *cq = to_rcq(ibcq);
	int count = queue_count(cq->queue);

	return (count > wc_cnt) ? wc_cnt : count;
}

static int rxe_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
{
	struct rxe_cq *cq = to_rcq(ibcq);
	unsigned long irq_flags;
	int ret = 0;

	spin_lock_irqsave(&cq->cq_lock, irq_flags);
	if (cq->notify != IB_CQ_NEXT_COMP)
		cq->notify = flags & IB_CQ_SOLICITED_MASK;

	if ((flags & IB_CQ_REPORT_MISSED_EVENTS) && !queue_empty(cq->queue))
		ret = 1;

	spin_unlock_irqrestore(&cq->cq_lock, irq_flags);

	return ret;
}

static struct ib_mr *rxe_get_dma_mr(struct ib_pd *ibpd, int access)
{
	struct rxe_dev *rxe = to_rdev(ibpd->device);
	struct rxe_pd *pd = to_rpd(ibpd);
	struct rxe_mem *mr;
	int err;

	mr = rxe_alloc(&rxe->mr_pool);
	if (!mr) {
		err = -ENOMEM;
		goto err1;
	}

	rxe_add_index(mr);

	rxe_add_ref(pd);

	err = rxe_mem_init_dma(rxe, pd, access, mr);
	if (err)
		goto err2;

	return &mr->ibmr;

err2:
	rxe_drop_ref(pd);
	rxe_drop_index(mr);
	rxe_drop_ref(mr);
err1:
	return ERR_PTR(err);
}

static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd,
				     u64 start,
				     u64 length,
				     u64 iova,
				     int access, struct ib_udata *udata)
{
	int err;
	struct rxe_dev *rxe = to_rdev(ibpd->device);
	struct rxe_pd *pd = to_rpd(ibpd);
	struct rxe_mem *mr;

	mr = rxe_alloc(&rxe->mr_pool);
	if (!mr) {
		err = -ENOMEM;
		goto err2;
	}

	rxe_add_index(mr);

	rxe_add_ref(pd);

	err = rxe_mem_init_user(rxe, pd, start, length, iova,
				access, udata, mr);
	if (err)
		goto err3;

	return &mr->ibmr;

err3:
	rxe_drop_ref(pd);
	rxe_drop_index(mr);
	rxe_drop_ref(mr);
err2:
	return ERR_PTR(err);
}

static int rxe_dereg_mr(struct ib_mr *ibmr)
{
	struct rxe_mem *mr = to_rmr(ibmr);

	mr->state = RXE_MEM_STATE_ZOMBIE;
	rxe_drop_ref(mr->pd);
	rxe_drop_index(mr);
	rxe_drop_ref(mr);
	return 0;
}

static struct ib_mr *rxe_alloc_mr(struct ib_pd *ibpd,
				  enum ib_mr_type mr_type,
				  u32 max_num_sg)
{
	struct rxe_dev *rxe = to_rdev(ibpd->device);
	struct rxe_pd *pd = to_rpd(ibpd);
	struct rxe_mem *mr;
	int err;

	if (mr_type != IB_MR_TYPE_MEM_REG)
		return ERR_PTR(-EINVAL);

	mr = rxe_alloc(&rxe->mr_pool);
	if (!mr) {
		err = -ENOMEM;
		goto err1;
	}

	rxe_add_index(mr);

	rxe_add_ref(pd);

	err = rxe_mem_init_fast(rxe, pd, max_num_sg, mr);
	if (err)
		goto err2;

	return &mr->ibmr;

err2:
	rxe_drop_ref(pd);
	rxe_drop_index(mr);
	rxe_drop_ref(mr);
err1:
	return ERR_PTR(err);
}

static int rxe_set_page(struct ib_mr *ibmr, u64 addr)
{
	struct rxe_mem *mr = to_rmr(ibmr);
	struct rxe_map *map;
	struct rxe_phys_buf *buf;

	if (unlikely(mr->nbuf == mr->num_buf))
		return -ENOMEM;

	map = mr->map[mr->nbuf / RXE_BUF_PER_MAP];
	buf = &map->buf[mr->nbuf % RXE_BUF_PER_MAP];

	buf->addr = addr;
	buf->size = ibmr->page_size;
	mr->nbuf++;

	return 0;
}

static int rxe_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
			 int sg_nents, unsigned int *sg_offset)
{
	struct rxe_mem *mr = to_rmr(ibmr);
	int n;

	mr->nbuf = 0;

	n = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, rxe_set_page);

	mr->va = ibmr->iova;
	mr->iova = ibmr->iova;
	mr->length = ibmr->length;
	mr->page_shift = ilog2(ibmr->page_size);
	mr->page_mask = ibmr->page_size - 1;
	mr->offset = mr->iova & mr->page_mask;

	return n;
}

static int rxe_attach_mcast(struct ib_qp *ibqp, union ib_gid *mgid, u16 mlid)
{
	int err;
	struct rxe_dev *rxe = to_rdev(ibqp->device);
	struct rxe_qp *qp = to_rqp(ibqp);
	struct rxe_mc_grp *grp;

	/* takes a ref on grp if successful */
	err = rxe_mcast_get_grp(rxe, mgid, &grp);
	if (err)
		return err;

	err = rxe_mcast_add_grp_elem(rxe, qp, grp);

	rxe_drop_ref(grp);
	return err;
}

static int rxe_detach_mcast(struct ib_qp *ibqp, union ib_gid *mgid, u16 mlid)
{
	struct rxe_dev *rxe = to_rdev(ibqp->device);
	struct rxe_qp *qp = to_rqp(ibqp);

	return rxe_mcast_drop_grp_elem(rxe, qp, mgid);
}

static ssize_t rxe_show_parent(struct device *device,
			       struct device_attribute *attr, char *buf)
{
	struct rxe_dev *rxe = container_of(device, struct rxe_dev,
					   ib_dev.dev);

	return snprintf(buf, 16, "%s\n", rxe_parent_name(rxe, 1));
}

static DEVICE_ATTR(parent, S_IRUGO, rxe_show_parent, NULL);

static struct device_attribute *rxe_dev_attributes[] = {
	&dev_attr_parent,
};

int rxe_register_device(struct rxe_dev *rxe)
{
	int err;
	int i;
	struct ib_device *dev = &rxe->ib_dev;

	strlcpy(dev->name, "rxe%d", IB_DEVICE_NAME_MAX);
	strlcpy(dev->node_desc, "rxe", sizeof(dev->node_desc));

	dev->owner = THIS_MODULE;
	dev->node_type = RDMA_NODE_IB_CA;
	dev->phys_port_cnt = 1;
	dev->num_comp_vectors = num_possible_cpus();
	dev->dev.parent = rxe_dma_device(rxe);
	dev->local_dma_lkey = 0;
	addrconf_addr_eui48((unsigned char *)&dev->node_guid,
			    rxe->ndev->dev_addr);
	dev->dev.dma_ops = &dma_virt_ops;
	dma_coerce_mask_and_coherent(&dev->dev,
				     dma_get_required_mask(dev->dev.parent));

	dev->uverbs_abi_ver = RXE_UVERBS_ABI_VERSION;
	dev->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT)
	    | BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL)
	    | BIT_ULL(IB_USER_VERBS_CMD_QUERY_DEVICE)
	    | BIT_ULL(IB_USER_VERBS_CMD_QUERY_PORT)
	    | BIT_ULL(IB_USER_VERBS_CMD_ALLOC_PD)
	    | BIT_ULL(IB_USER_VERBS_CMD_DEALLOC_PD)
	    | BIT_ULL(IB_USER_VERBS_CMD_CREATE_SRQ)
	    | BIT_ULL(IB_USER_VERBS_CMD_MODIFY_SRQ)
	    | BIT_ULL(IB_USER_VERBS_CMD_QUERY_SRQ)
	    | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_SRQ)
	    | BIT_ULL(IB_USER_VERBS_CMD_POST_SRQ_RECV)
	    | BIT_ULL(IB_USER_VERBS_CMD_CREATE_QP)
	    | BIT_ULL(IB_USER_VERBS_CMD_MODIFY_QP)
	    | BIT_ULL(IB_USER_VERBS_CMD_QUERY_QP)
	    | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_QP)
	    | BIT_ULL(IB_USER_VERBS_CMD_POST_SEND)
	    | BIT_ULL(IB_USER_VERBS_CMD_POST_RECV)
	    | BIT_ULL(IB_USER_VERBS_CMD_CREATE_CQ)
	    | BIT_ULL(IB_USER_VERBS_CMD_RESIZE_CQ)
	    | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_CQ)
	    | BIT_ULL(IB_USER_VERBS_CMD_POLL_CQ)
	    | BIT_ULL(IB_USER_VERBS_CMD_PEEK_CQ)
	    | BIT_ULL(IB_USER_VERBS_CMD_REQ_NOTIFY_CQ)
	    | BIT_ULL(IB_USER_VERBS_CMD_REG_MR)
	    | BIT_ULL(IB_USER_VERBS_CMD_DEREG_MR)
	    | BIT_ULL(IB_USER_VERBS_CMD_CREATE_AH)
	    | BIT_ULL(IB_USER_VERBS_CMD_MODIFY_AH)
	    | BIT_ULL(IB_USER_VERBS_CMD_QUERY_AH)
	    | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_AH)
	    | BIT_ULL(IB_USER_VERBS_CMD_ATTACH_MCAST)
	    | BIT_ULL(IB_USER_VERBS_CMD_DETACH_MCAST)
	    ;

	dev->query_device = rxe_query_device;
	dev->modify_device = rxe_modify_device;
	dev->query_port = rxe_query_port;
	dev->modify_port = rxe_modify_port;
	dev->get_link_layer = rxe_get_link_layer;
	dev->query_gid = rxe_query_gid;
	dev->get_netdev = rxe_get_netdev;
	dev->add_gid = rxe_add_gid;
	dev->del_gid = rxe_del_gid;
	dev->query_pkey = rxe_query_pkey;
	dev->alloc_ucontext = rxe_alloc_ucontext;
	dev->dealloc_ucontext = rxe_dealloc_ucontext;
	dev->mmap = rxe_mmap;
	dev->get_port_immutable = rxe_port_immutable;
	dev->alloc_pd = rxe_alloc_pd;
	dev->dealloc_pd = rxe_dealloc_pd;
	dev->create_ah = rxe_create_ah;
	dev->modify_ah = rxe_modify_ah;
	dev->query_ah = rxe_query_ah;
	dev->destroy_ah = rxe_destroy_ah;
	dev->create_srq = rxe_create_srq;
	dev->modify_srq = rxe_modify_srq;
	dev->query_srq = rxe_query_srq;
	dev->destroy_srq = rxe_destroy_srq;
	dev->post_srq_recv = rxe_post_srq_recv;
	dev->create_qp = rxe_create_qp;
	dev->modify_qp = rxe_modify_qp;
	dev->query_qp = rxe_query_qp;
	dev->destroy_qp = rxe_destroy_qp;
	dev->post_send = rxe_post_send;
	dev->post_recv = rxe_post_recv;
	dev->create_cq = rxe_create_cq;
	dev->destroy_cq = rxe_destroy_cq;
	dev->resize_cq = rxe_resize_cq;
	dev->poll_cq = rxe_poll_cq;
	dev->peek_cq = rxe_peek_cq;
	dev->req_notify_cq = rxe_req_notify_cq;
	dev->get_dma_mr = rxe_get_dma_mr;
	dev->reg_user_mr = rxe_reg_user_mr;
	dev->dereg_mr = rxe_dereg_mr;
	dev->alloc_mr = rxe_alloc_mr;
	dev->map_mr_sg = rxe_map_mr_sg;
	dev->attach_mcast = rxe_attach_mcast;
	dev->detach_mcast = rxe_detach_mcast;
	dev->get_hw_stats = rxe_ib_get_hw_stats;
	dev->alloc_hw_stats = rxe_ib_alloc_hw_stats;

	rxe->tfm = crypto_alloc_shash("crc32", 0, 0);
	if (IS_ERR(rxe->tfm)) {
		pr_err("failed to allocate crc algorithm err:%ld\n",
		       PTR_ERR(rxe->tfm));
		return PTR_ERR(rxe->tfm);
	}

	err = ib_register_device(dev, NULL);
	if (err) {
		pr_warn("rxe_register_device failed, err = %d\n", err);
		goto err1;
	}

	for (i = 0; i < ARRAY_SIZE(rxe_dev_attributes); ++i) {
		err = device_create_file(&dev->dev, rxe_dev_attributes[i]);
		if (err) {
			pr_warn("device_create_file failed, i = %d, err = %d\n",
				i, err);
			goto err2;
		}
	}

	return 0;

err2:
	ib_unregister_device(dev);
err1:
	crypto_free_shash(rxe->tfm);

	return err;
}

int rxe_unregister_device(struct rxe_dev *rxe)
{
	int i;
	struct ib_device *dev = &rxe->ib_dev;

	for (i = 0; i < ARRAY_SIZE(rxe_dev_attributes); ++i)
		device_remove_file(&dev->dev, rxe_dev_attributes[i]);

	ib_unregister_device(dev);

	return 0;
}