Linux Audio

Check our new training course

Embedded Linux Audio

Check our new training course
with Creative Commons CC-BY-SA
lecture materials

Bootlin logo

Elixir Cross Referencer

Loading...
   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
/*
 * Copyright (c) 2004, 2005 Topspin Communications.  All rights reserved.
 * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
 * Copyright (c) 2005 Mellanox Technologies. All rights reserved.
 * Copyright (c) 2004, 2005 Voltaire, 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/delay.h>
#include <linux/moduleparam.h>
#include <linux/dma-mapping.h>
#include <linux/slab.h>

#include <linux/ip.h>
#include <linux/tcp.h>

#include "ipoib.h"

#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG_DATA
static int data_debug_level;

module_param(data_debug_level, int, 0644);
MODULE_PARM_DESC(data_debug_level,
		 "Enable data path debug tracing if > 0");
#endif

static DEFINE_MUTEX(pkey_mutex);

struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
				 struct ib_pd *pd, struct ib_ah_attr *attr)
{
	struct ipoib_ah *ah;
	struct ib_ah *vah;

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

	ah->dev       = dev;
	ah->last_send = 0;
	kref_init(&ah->ref);

	vah = ib_create_ah(pd, attr);
	if (IS_ERR(vah)) {
		kfree(ah);
		ah = (struct ipoib_ah *)vah;
	} else {
		ah->ah = vah;
		ipoib_dbg(netdev_priv(dev), "Created ah %p\n", ah->ah);
	}

	return ah;
}

void ipoib_free_ah(struct kref *kref)
{
	struct ipoib_ah *ah = container_of(kref, struct ipoib_ah, ref);
	struct ipoib_dev_priv *priv = netdev_priv(ah->dev);

	unsigned long flags;

	spin_lock_irqsave(&priv->lock, flags);
	list_add_tail(&ah->list, &priv->dead_ahs);
	spin_unlock_irqrestore(&priv->lock, flags);
}

static void ipoib_ud_dma_unmap_rx(struct ipoib_dev_priv *priv,
				  u64 mapping[IPOIB_UD_RX_SG])
{
	ib_dma_unmap_single(priv->ca, mapping[0],
			    IPOIB_UD_BUF_SIZE(priv->max_ib_mtu),
			    DMA_FROM_DEVICE);
}

static int ipoib_ib_post_receive(struct net_device *dev, int id)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ib_recv_wr *bad_wr;
	int ret;

	priv->rx_wr.wr_id   = id | IPOIB_OP_RECV;
	priv->rx_sge[0].addr = priv->rx_ring[id].mapping[0];
	priv->rx_sge[1].addr = priv->rx_ring[id].mapping[1];


	ret = ib_post_recv(priv->qp, &priv->rx_wr, &bad_wr);
	if (unlikely(ret)) {
		ipoib_warn(priv, "receive failed for buf %d (%d)\n", id, ret);
		ipoib_ud_dma_unmap_rx(priv, priv->rx_ring[id].mapping);
		dev_kfree_skb_any(priv->rx_ring[id].skb);
		priv->rx_ring[id].skb = NULL;
	}

	return ret;
}

static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct sk_buff *skb;
	int buf_size;
	u64 *mapping;

	buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);

	skb = dev_alloc_skb(buf_size + IPOIB_HARD_LEN);
	if (unlikely(!skb))
		return NULL;

	/*
	 * the IP header will be at IPOIP_HARD_LEN + IB_GRH_BYTES, that is
	 * 64 bytes aligned
	 */
	skb_reserve(skb, sizeof(struct ipoib_pseudo_header));

	mapping = priv->rx_ring[id].mapping;
	mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size,
				       DMA_FROM_DEVICE);
	if (unlikely(ib_dma_mapping_error(priv->ca, mapping[0])))
		goto error;

	priv->rx_ring[id].skb = skb;
	return skb;
error:
	dev_kfree_skb_any(skb);
	return NULL;
}

static int ipoib_ib_post_receives(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	int i;

	for (i = 0; i < ipoib_recvq_size; ++i) {
		if (!ipoib_alloc_rx_skb(dev, i)) {
			ipoib_warn(priv, "failed to allocate receive buffer %d\n", i);
			return -ENOMEM;
		}
		if (ipoib_ib_post_receive(dev, i)) {
			ipoib_warn(priv, "ipoib_ib_post_receive failed for buf %d\n", i);
			return -EIO;
		}
	}

	return 0;
}

static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	unsigned int wr_id = wc->wr_id & ~IPOIB_OP_RECV;
	struct sk_buff *skb;
	u64 mapping[IPOIB_UD_RX_SG];
	union ib_gid *dgid;

	ipoib_dbg_data(priv, "recv completion: id %d, status: %d\n",
		       wr_id, wc->status);

	if (unlikely(wr_id >= ipoib_recvq_size)) {
		ipoib_warn(priv, "recv completion event with wrid %d (> %d)\n",
			   wr_id, ipoib_recvq_size);
		return;
	}

	skb  = priv->rx_ring[wr_id].skb;

	if (unlikely(wc->status != IB_WC_SUCCESS)) {
		if (wc->status != IB_WC_WR_FLUSH_ERR)
			ipoib_warn(priv, "failed recv event "
				   "(status=%d, wrid=%d vend_err %x)\n",
				   wc->status, wr_id, wc->vendor_err);
		ipoib_ud_dma_unmap_rx(priv, priv->rx_ring[wr_id].mapping);
		dev_kfree_skb_any(skb);
		priv->rx_ring[wr_id].skb = NULL;
		return;
	}

	/*
	 * Drop packets that this interface sent, ie multicast packets
	 * that the HCA has replicated.
	 */
	if (wc->slid == priv->local_lid && wc->src_qp == priv->qp->qp_num)
		goto repost;

	memcpy(mapping, priv->rx_ring[wr_id].mapping,
	       IPOIB_UD_RX_SG * sizeof *mapping);

	/*
	 * If we can't allocate a new RX buffer, dump
	 * this packet and reuse the old buffer.
	 */
	if (unlikely(!ipoib_alloc_rx_skb(dev, wr_id))) {
		++dev->stats.rx_dropped;
		goto repost;
	}

	ipoib_dbg_data(priv, "received %d bytes, SLID 0x%04x\n",
		       wc->byte_len, wc->slid);

	ipoib_ud_dma_unmap_rx(priv, mapping);

	skb_put(skb, wc->byte_len);

	/* First byte of dgid signals multicast when 0xff */
	dgid = &((struct ib_grh *)skb->data)->dgid;

	if (!(wc->wc_flags & IB_WC_GRH) || dgid->raw[0] != 0xff)
		skb->pkt_type = PACKET_HOST;
	else if (memcmp(dgid, dev->broadcast + 4, sizeof(union ib_gid)) == 0)
		skb->pkt_type = PACKET_BROADCAST;
	else
		skb->pkt_type = PACKET_MULTICAST;

	skb_pull(skb, IB_GRH_BYTES);

	skb->protocol = ((struct ipoib_header *) skb->data)->proto;
	skb_add_pseudo_hdr(skb);

	++dev->stats.rx_packets;
	dev->stats.rx_bytes += skb->len;

	skb->dev = dev;
	if ((dev->features & NETIF_F_RXCSUM) &&
			likely(wc->wc_flags & IB_WC_IP_CSUM_OK))
		skb->ip_summed = CHECKSUM_UNNECESSARY;

	napi_gro_receive(&priv->napi, skb);

repost:
	if (unlikely(ipoib_ib_post_receive(dev, wr_id)))
		ipoib_warn(priv, "ipoib_ib_post_receive failed "
			   "for buf %d\n", wr_id);
}

int ipoib_dma_map_tx(struct ib_device *ca, struct ipoib_tx_buf *tx_req)
{
	struct sk_buff *skb = tx_req->skb;
	u64 *mapping = tx_req->mapping;
	int i;
	int off;

	if (skb_headlen(skb)) {
		mapping[0] = ib_dma_map_single(ca, skb->data, skb_headlen(skb),
					       DMA_TO_DEVICE);
		if (unlikely(ib_dma_mapping_error(ca, mapping[0])))
			return -EIO;

		off = 1;
	} else
		off = 0;

	for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) {
		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
		mapping[i + off] = ib_dma_map_page(ca,
						 skb_frag_page(frag),
						 frag->page_offset, skb_frag_size(frag),
						 DMA_TO_DEVICE);
		if (unlikely(ib_dma_mapping_error(ca, mapping[i + off])))
			goto partial_error;
	}
	return 0;

partial_error:
	for (; i > 0; --i) {
		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];

		ib_dma_unmap_page(ca, mapping[i - !off], skb_frag_size(frag), DMA_TO_DEVICE);
	}

	if (off)
		ib_dma_unmap_single(ca, mapping[0], skb_headlen(skb), DMA_TO_DEVICE);

	return -EIO;
}

void ipoib_dma_unmap_tx(struct ipoib_dev_priv *priv,
			struct ipoib_tx_buf *tx_req)
{
	struct sk_buff *skb = tx_req->skb;
	u64 *mapping = tx_req->mapping;
	int i;
	int off;

	if (skb_headlen(skb)) {
		ib_dma_unmap_single(priv->ca, mapping[0], skb_headlen(skb),
				    DMA_TO_DEVICE);
		off = 1;
	} else
		off = 0;

	for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) {
		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

		ib_dma_unmap_page(priv->ca, mapping[i + off],
				  skb_frag_size(frag), DMA_TO_DEVICE);
	}
}

/*
 * As the result of a completion error the QP Can be transferred to SQE states.
 * The function checks if the (send)QP is in SQE state and
 * moves it back to RTS state, that in order to have it functional again.
 */
static void ipoib_qp_state_validate_work(struct work_struct *work)
{
	struct ipoib_qp_state_validate *qp_work =
		container_of(work, struct ipoib_qp_state_validate, work);

	struct ipoib_dev_priv *priv = qp_work->priv;
	struct ib_qp_attr qp_attr;
	struct ib_qp_init_attr query_init_attr;
	int ret;

	ret = ib_query_qp(priv->qp, &qp_attr, IB_QP_STATE, &query_init_attr);
	if (ret) {
		ipoib_warn(priv, "%s: Failed to query QP ret: %d\n",
			   __func__, ret);
		goto free_res;
	}
	pr_info("%s: QP: 0x%x is in state: %d\n",
		__func__, priv->qp->qp_num, qp_attr.qp_state);

	/* currently support only in SQE->RTS transition*/
	if (qp_attr.qp_state == IB_QPS_SQE) {
		qp_attr.qp_state = IB_QPS_RTS;

		ret = ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE);
		if (ret) {
			pr_warn("failed(%d) modify QP:0x%x SQE->RTS\n",
				ret, priv->qp->qp_num);
			goto free_res;
		}
		pr_info("%s: QP: 0x%x moved from IB_QPS_SQE to IB_QPS_RTS\n",
			__func__, priv->qp->qp_num);
	} else {
		pr_warn("QP (%d) will stay in state: %d\n",
			priv->qp->qp_num, qp_attr.qp_state);
	}

free_res:
	kfree(qp_work);
}

static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	unsigned int wr_id = wc->wr_id;
	struct ipoib_tx_buf *tx_req;

	ipoib_dbg_data(priv, "send completion: id %d, status: %d\n",
		       wr_id, wc->status);

	if (unlikely(wr_id >= ipoib_sendq_size)) {
		ipoib_warn(priv, "send completion event with wrid %d (> %d)\n",
			   wr_id, ipoib_sendq_size);
		return;
	}

	tx_req = &priv->tx_ring[wr_id];

	ipoib_dma_unmap_tx(priv, tx_req);

	++dev->stats.tx_packets;
	dev->stats.tx_bytes += tx_req->skb->len;

	dev_kfree_skb_any(tx_req->skb);

	++priv->tx_tail;
	if (unlikely(--priv->tx_outstanding == ipoib_sendq_size >> 1) &&
	    netif_queue_stopped(dev) &&
	    test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
		netif_wake_queue(dev);

	if (wc->status != IB_WC_SUCCESS &&
	    wc->status != IB_WC_WR_FLUSH_ERR) {
		struct ipoib_qp_state_validate *qp_work;
		ipoib_warn(priv, "failed send event "
			   "(status=%d, wrid=%d vend_err %x)\n",
			   wc->status, wr_id, wc->vendor_err);
		qp_work = kzalloc(sizeof(*qp_work), GFP_ATOMIC);
		if (!qp_work) {
			ipoib_warn(priv, "%s Failed alloc ipoib_qp_state_validate for qp: 0x%x\n",
				   __func__, priv->qp->qp_num);
			return;
		}

		INIT_WORK(&qp_work->work, ipoib_qp_state_validate_work);
		qp_work->priv = priv;
		queue_work(priv->wq, &qp_work->work);
	}
}

static int poll_tx(struct ipoib_dev_priv *priv)
{
	int n, i;

	n = ib_poll_cq(priv->send_cq, MAX_SEND_CQE, priv->send_wc);
	for (i = 0; i < n; ++i)
		ipoib_ib_handle_tx_wc(priv->dev, priv->send_wc + i);

	return n == MAX_SEND_CQE;
}

int ipoib_poll(struct napi_struct *napi, int budget)
{
	struct ipoib_dev_priv *priv = container_of(napi, struct ipoib_dev_priv, napi);
	struct net_device *dev = priv->dev;
	int done;
	int t;
	int n, i;

	done  = 0;

poll_more:
	while (done < budget) {
		int max = (budget - done);

		t = min(IPOIB_NUM_WC, max);
		n = ib_poll_cq(priv->recv_cq, t, priv->ibwc);

		for (i = 0; i < n; i++) {
			struct ib_wc *wc = priv->ibwc + i;

			if (wc->wr_id & IPOIB_OP_RECV) {
				++done;
				if (wc->wr_id & IPOIB_OP_CM)
					ipoib_cm_handle_rx_wc(dev, wc);
				else
					ipoib_ib_handle_rx_wc(dev, wc);
			} else
				ipoib_cm_handle_tx_wc(priv->dev, wc);
		}

		if (n != t)
			break;
	}

	if (done < budget) {
		napi_complete(napi);
		if (unlikely(ib_req_notify_cq(priv->recv_cq,
					      IB_CQ_NEXT_COMP |
					      IB_CQ_REPORT_MISSED_EVENTS)) &&
		    napi_reschedule(napi))
			goto poll_more;
	}

	return done;
}

void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr)
{
	struct net_device *dev = dev_ptr;
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	napi_schedule(&priv->napi);
}

static void drain_tx_cq(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	netif_tx_lock(dev);
	while (poll_tx(priv))
		; /* nothing */

	if (netif_queue_stopped(dev))
		mod_timer(&priv->poll_timer, jiffies + 1);

	netif_tx_unlock(dev);
}

void ipoib_send_comp_handler(struct ib_cq *cq, void *dev_ptr)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev_ptr);

	mod_timer(&priv->poll_timer, jiffies);
}

static inline int post_send(struct ipoib_dev_priv *priv,
			    unsigned int wr_id,
			    struct ib_ah *address, u32 qpn,
			    struct ipoib_tx_buf *tx_req,
			    void *head, int hlen)
{
	struct ib_send_wr *bad_wr;
	struct sk_buff *skb = tx_req->skb;

	ipoib_build_sge(priv, tx_req);

	priv->tx_wr.wr.wr_id	= wr_id;
	priv->tx_wr.remote_qpn	= qpn;
	priv->tx_wr.ah		= address;

	if (head) {
		priv->tx_wr.mss		= skb_shinfo(skb)->gso_size;
		priv->tx_wr.header	= head;
		priv->tx_wr.hlen	= hlen;
		priv->tx_wr.wr.opcode	= IB_WR_LSO;
	} else
		priv->tx_wr.wr.opcode	= IB_WR_SEND;

	return ib_post_send(priv->qp, &priv->tx_wr.wr, &bad_wr);
}

void ipoib_send(struct net_device *dev, struct sk_buff *skb,
		struct ipoib_ah *address, u32 qpn)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ipoib_tx_buf *tx_req;
	int hlen, rc;
	void *phead;

	if (skb_is_gso(skb)) {
		hlen = skb_transport_offset(skb) + tcp_hdrlen(skb);
		phead = skb->data;
		if (unlikely(!skb_pull(skb, hlen))) {
			ipoib_warn(priv, "linear data too small\n");
			++dev->stats.tx_dropped;
			++dev->stats.tx_errors;
			dev_kfree_skb_any(skb);
			return;
		}
	} else {
		if (unlikely(skb->len > priv->mcast_mtu + IPOIB_ENCAP_LEN)) {
			ipoib_warn(priv, "packet len %d (> %d) too long to send, dropping\n",
				   skb->len, priv->mcast_mtu + IPOIB_ENCAP_LEN);
			++dev->stats.tx_dropped;
			++dev->stats.tx_errors;
			ipoib_cm_skb_too_long(dev, skb, priv->mcast_mtu);
			return;
		}
		phead = NULL;
		hlen  = 0;
	}

	ipoib_dbg_data(priv, "sending packet, length=%d address=%p qpn=0x%06x\n",
		       skb->len, address, qpn);

	/*
	 * We put the skb into the tx_ring _before_ we call post_send()
	 * because it's entirely possible that the completion handler will
	 * run before we execute anything after the post_send().  That
	 * means we have to make sure everything is properly recorded and
	 * our state is consistent before we call post_send().
	 */
	tx_req = &priv->tx_ring[priv->tx_head & (ipoib_sendq_size - 1)];
	tx_req->skb = skb;
	if (unlikely(ipoib_dma_map_tx(priv->ca, tx_req))) {
		++dev->stats.tx_errors;
		dev_kfree_skb_any(skb);
		return;
	}

	if (skb->ip_summed == CHECKSUM_PARTIAL)
		priv->tx_wr.wr.send_flags |= IB_SEND_IP_CSUM;
	else
		priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM;

	if (++priv->tx_outstanding == ipoib_sendq_size) {
		ipoib_dbg(priv, "TX ring full, stopping kernel net queue\n");
		if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP))
			ipoib_warn(priv, "request notify on send CQ failed\n");
		netif_stop_queue(dev);
	}

	skb_orphan(skb);
	skb_dst_drop(skb);

	rc = post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
		       address->ah, qpn, tx_req, phead, hlen);
	if (unlikely(rc)) {
		ipoib_warn(priv, "post_send failed, error %d\n", rc);
		++dev->stats.tx_errors;
		--priv->tx_outstanding;
		ipoib_dma_unmap_tx(priv, tx_req);
		dev_kfree_skb_any(skb);
		if (netif_queue_stopped(dev))
			netif_wake_queue(dev);
	} else {
		dev->trans_start = jiffies;

		address->last_send = priv->tx_head;
		++priv->tx_head;
	}

	if (unlikely(priv->tx_outstanding > MAX_SEND_CQE))
		while (poll_tx(priv))
			; /* nothing */
}

static void __ipoib_reap_ah(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ipoib_ah *ah, *tah;
	LIST_HEAD(remove_list);
	unsigned long flags;

	netif_tx_lock_bh(dev);
	spin_lock_irqsave(&priv->lock, flags);

	list_for_each_entry_safe(ah, tah, &priv->dead_ahs, list)
		if ((int) priv->tx_tail - (int) ah->last_send >= 0) {
			list_del(&ah->list);
			ib_destroy_ah(ah->ah);
			kfree(ah);
		}

	spin_unlock_irqrestore(&priv->lock, flags);
	netif_tx_unlock_bh(dev);
}

void ipoib_reap_ah(struct work_struct *work)
{
	struct ipoib_dev_priv *priv =
		container_of(work, struct ipoib_dev_priv, ah_reap_task.work);
	struct net_device *dev = priv->dev;

	__ipoib_reap_ah(dev);

	if (!test_bit(IPOIB_STOP_REAPER, &priv->flags))
		queue_delayed_work(priv->wq, &priv->ah_reap_task,
				   round_jiffies_relative(HZ));
}

static void ipoib_flush_ah(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	cancel_delayed_work(&priv->ah_reap_task);
	flush_workqueue(priv->wq);
	ipoib_reap_ah(&priv->ah_reap_task.work);
}

static void ipoib_stop_ah(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	set_bit(IPOIB_STOP_REAPER, &priv->flags);
	ipoib_flush_ah(dev);
}

static void ipoib_ib_tx_timer_func(unsigned long ctx)
{
	drain_tx_cq((struct net_device *)ctx);
}

int ipoib_ib_dev_open(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	int ret;

	ipoib_pkey_dev_check_presence(dev);

	if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
		ipoib_warn(priv, "P_Key 0x%04x is %s\n", priv->pkey,
			   (!(priv->pkey & 0x7fff) ? "Invalid" : "not found"));
		return -1;
	}

	ret = ipoib_init_qp(dev);
	if (ret) {
		ipoib_warn(priv, "ipoib_init_qp returned %d\n", ret);
		return -1;
	}

	ret = ipoib_ib_post_receives(dev);
	if (ret) {
		ipoib_warn(priv, "ipoib_ib_post_receives returned %d\n", ret);
		goto dev_stop;
	}

	ret = ipoib_cm_dev_open(dev);
	if (ret) {
		ipoib_warn(priv, "ipoib_cm_dev_open returned %d\n", ret);
		goto dev_stop;
	}

	clear_bit(IPOIB_STOP_REAPER, &priv->flags);
	queue_delayed_work(priv->wq, &priv->ah_reap_task,
			   round_jiffies_relative(HZ));

	if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
		napi_enable(&priv->napi);

	return 0;
dev_stop:
	if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
		napi_enable(&priv->napi);
	ipoib_ib_dev_stop(dev);
	return -1;
}

void ipoib_pkey_dev_check_presence(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	if (!(priv->pkey & 0x7fff) ||
	    ib_find_pkey(priv->ca, priv->port, priv->pkey,
			 &priv->pkey_index))
		clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
	else
		set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
}

int ipoib_ib_dev_up(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	ipoib_pkey_dev_check_presence(dev);

	if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
		ipoib_dbg(priv, "PKEY is not assigned.\n");
		return 0;
	}

	set_bit(IPOIB_FLAG_OPER_UP, &priv->flags);

	return ipoib_mcast_start_thread(dev);
}

int ipoib_ib_dev_down(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	ipoib_dbg(priv, "downing ib_dev\n");

	clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
	netif_carrier_off(dev);

	ipoib_mcast_stop_thread(dev);
	ipoib_mcast_dev_flush(dev);

	ipoib_flush_paths(dev);

	return 0;
}

static int recvs_pending(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	int pending = 0;
	int i;

	for (i = 0; i < ipoib_recvq_size; ++i)
		if (priv->rx_ring[i].skb)
			++pending;

	return pending;
}

void ipoib_drain_cq(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	int i, n;

	/*
	 * We call completion handling routines that expect to be
	 * called from the BH-disabled NAPI poll context, so disable
	 * BHs here too.
	 */
	local_bh_disable();

	do {
		n = ib_poll_cq(priv->recv_cq, IPOIB_NUM_WC, priv->ibwc);
		for (i = 0; i < n; ++i) {
			/*
			 * Convert any successful completions to flush
			 * errors to avoid passing packets up the
			 * stack after bringing the device down.
			 */
			if (priv->ibwc[i].status == IB_WC_SUCCESS)
				priv->ibwc[i].status = IB_WC_WR_FLUSH_ERR;

			if (priv->ibwc[i].wr_id & IPOIB_OP_RECV) {
				if (priv->ibwc[i].wr_id & IPOIB_OP_CM)
					ipoib_cm_handle_rx_wc(dev, priv->ibwc + i);
				else
					ipoib_ib_handle_rx_wc(dev, priv->ibwc + i);
			} else
				ipoib_cm_handle_tx_wc(dev, priv->ibwc + i);
		}
	} while (n == IPOIB_NUM_WC);

	while (poll_tx(priv))
		; /* nothing */

	local_bh_enable();
}

int ipoib_ib_dev_stop(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ib_qp_attr qp_attr;
	unsigned long begin;
	struct ipoib_tx_buf *tx_req;
	int i;

	if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
		napi_disable(&priv->napi);

	ipoib_cm_dev_stop(dev);

	/*
	 * Move our QP to the error state and then reinitialize in
	 * when all work requests have completed or have been flushed.
	 */
	qp_attr.qp_state = IB_QPS_ERR;
	if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
		ipoib_warn(priv, "Failed to modify QP to ERROR state\n");

	/* Wait for all sends and receives to complete */
	begin = jiffies;

	while (priv->tx_head != priv->tx_tail || recvs_pending(dev)) {
		if (time_after(jiffies, begin + 5 * HZ)) {
			ipoib_warn(priv, "timing out; %d sends %d receives not completed\n",
				   priv->tx_head - priv->tx_tail, recvs_pending(dev));

			/*
			 * assume the HW is wedged and just free up
			 * all our pending work requests.
			 */
			while ((int) priv->tx_tail - (int) priv->tx_head < 0) {
				tx_req = &priv->tx_ring[priv->tx_tail &
							(ipoib_sendq_size - 1)];
				ipoib_dma_unmap_tx(priv, tx_req);
				dev_kfree_skb_any(tx_req->skb);
				++priv->tx_tail;
				--priv->tx_outstanding;
			}

			for (i = 0; i < ipoib_recvq_size; ++i) {
				struct ipoib_rx_buf *rx_req;

				rx_req = &priv->rx_ring[i];
				if (!rx_req->skb)
					continue;
				ipoib_ud_dma_unmap_rx(priv,
						      priv->rx_ring[i].mapping);
				dev_kfree_skb_any(rx_req->skb);
				rx_req->skb = NULL;
			}

			goto timeout;
		}

		ipoib_drain_cq(dev);

		msleep(1);
	}

	ipoib_dbg(priv, "All sends and receives done.\n");

timeout:
	del_timer_sync(&priv->poll_timer);
	qp_attr.qp_state = IB_QPS_RESET;
	if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
		ipoib_warn(priv, "Failed to modify QP to RESET state\n");

	ipoib_flush_ah(dev);

	ib_req_notify_cq(priv->recv_cq, IB_CQ_NEXT_COMP);

	return 0;
}

int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	priv->ca = ca;
	priv->port = port;
	priv->qp = NULL;

	if (ipoib_transport_dev_init(dev, ca)) {
		printk(KERN_WARNING "%s: ipoib_transport_dev_init failed\n", ca->name);
		return -ENODEV;
	}

	setup_timer(&priv->poll_timer, ipoib_ib_tx_timer_func,
		    (unsigned long) dev);

	if (dev->flags & IFF_UP) {
		if (ipoib_ib_dev_open(dev)) {
			ipoib_transport_dev_cleanup(dev);
			return -ENODEV;
		}
	}

	return 0;
}

/*
 * Takes whatever value which is in pkey index 0 and updates priv->pkey
 * returns 0 if the pkey value was changed.
 */
static inline int update_parent_pkey(struct ipoib_dev_priv *priv)
{
	int result;
	u16 prev_pkey;

	prev_pkey = priv->pkey;
	result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey);
	if (result) {
		ipoib_warn(priv, "ib_query_pkey port %d failed (ret = %d)\n",
			   priv->port, result);
		return result;
	}

	priv->pkey |= 0x8000;

	if (prev_pkey != priv->pkey) {
		ipoib_dbg(priv, "pkey changed from 0x%x to 0x%x\n",
			  prev_pkey, priv->pkey);
		/*
		 * Update the pkey in the broadcast address, while making sure to set
		 * the full membership bit, so that we join the right broadcast group.
		 */
		priv->dev->broadcast[8] = priv->pkey >> 8;
		priv->dev->broadcast[9] = priv->pkey & 0xff;

		/*
		 * Update the broadcast address in the priv->broadcast object,
		 * in case it already exists, otherwise no one will do that.
		 */
		if (priv->broadcast) {
			spin_lock_irq(&priv->lock);
			memcpy(priv->broadcast->mcmember.mgid.raw,
			       priv->dev->broadcast + 4,
			sizeof(union ib_gid));
			spin_unlock_irq(&priv->lock);
		}

		return 0;
	}

	return 1;
}
/*
 * returns 0 if pkey value was found in a different slot.
 */
static inline int update_child_pkey(struct ipoib_dev_priv *priv)
{
	u16 old_index = priv->pkey_index;

	priv->pkey_index = 0;
	ipoib_pkey_dev_check_presence(priv->dev);

	if (test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags) &&
	    (old_index == priv->pkey_index))
		return 1;
	return 0;
}

static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
				enum ipoib_flush_level level,
				int nesting)
{
	struct ipoib_dev_priv *cpriv;
	struct net_device *dev = priv->dev;
	int result;

	down_read_nested(&priv->vlan_rwsem, nesting);

	/*
	 * Flush any child interfaces too -- they might be up even if
	 * the parent is down.
	 */
	list_for_each_entry(cpriv, &priv->child_intfs, list)
		__ipoib_ib_dev_flush(cpriv, level, nesting + 1);

	up_read(&priv->vlan_rwsem);

	if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags) &&
	    level != IPOIB_FLUSH_HEAVY) {
		ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_INITIALIZED not set.\n");
		return;
	}

	if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) {
		/* interface is down. update pkey and leave. */
		if (level == IPOIB_FLUSH_HEAVY) {
			if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags))
				update_parent_pkey(priv);
			else
				update_child_pkey(priv);
		}
		ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_ADMIN_UP not set.\n");
		return;
	}

	if (level == IPOIB_FLUSH_HEAVY) {
		/* child devices chase their origin pkey value, while non-child
		 * (parent) devices should always takes what present in pkey index 0
		 */
		if (test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
			result = update_child_pkey(priv);
			if (result) {
				/* restart QP only if P_Key index is changed */
				ipoib_dbg(priv, "Not flushing - P_Key index not changed.\n");
				return;
			}

		} else {
			result = update_parent_pkey(priv);
			/* restart QP only if P_Key value changed */
			if (result) {
				ipoib_dbg(priv, "Not flushing - P_Key value not changed.\n");
				return;
			}
		}
	}

	if (level == IPOIB_FLUSH_LIGHT) {
		int oper_up;
		ipoib_mark_paths_invalid(dev);
		/* Set IPoIB operation as down to prevent races between:
		 * the flush flow which leaves MCG and on the fly joins
		 * which can happen during that time. mcast restart task
		 * should deal with join requests we missed.
		 */
		oper_up = test_and_clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
		ipoib_mcast_dev_flush(dev);
		if (oper_up)
			set_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
		ipoib_flush_ah(dev);
	}

	if (level >= IPOIB_FLUSH_NORMAL)
		ipoib_ib_dev_down(dev);

	if (level == IPOIB_FLUSH_HEAVY) {
		rtnl_lock();
		if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
			ipoib_ib_dev_stop(dev);

		result = ipoib_ib_dev_open(dev);
		rtnl_unlock();
		if (result)
			return;

		if (netif_queue_stopped(dev))
			netif_start_queue(dev);
	}

	/*
	 * The device could have been brought down between the start and when
	 * we get here, don't bring it back up if it's not configured up
	 */
	if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) {
		if (level >= IPOIB_FLUSH_NORMAL)
			ipoib_ib_dev_up(dev);
		ipoib_mcast_restart_task(&priv->restart_task);
	}
}

void ipoib_ib_dev_flush_light(struct work_struct *work)
{
	struct ipoib_dev_priv *priv =
		container_of(work, struct ipoib_dev_priv, flush_light);

	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_LIGHT, 0);
}

void ipoib_ib_dev_flush_normal(struct work_struct *work)
{
	struct ipoib_dev_priv *priv =
		container_of(work, struct ipoib_dev_priv, flush_normal);

	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_NORMAL, 0);
}

void ipoib_ib_dev_flush_heavy(struct work_struct *work)
{
	struct ipoib_dev_priv *priv =
		container_of(work, struct ipoib_dev_priv, flush_heavy);

	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY, 0);
}

void ipoib_ib_dev_cleanup(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	ipoib_dbg(priv, "cleaning up ib_dev\n");
	/*
	 * We must make sure there are no more (path) completions
	 * that may wish to touch priv fields that are no longer valid
	 */
	ipoib_flush_paths(dev);

	ipoib_mcast_stop_thread(dev);
	ipoib_mcast_dev_flush(dev);

	/*
	 * All of our ah references aren't free until after
	 * ipoib_mcast_dev_flush(), ipoib_flush_paths, and
	 * the neighbor garbage collection is stopped and reaped.
	 * That should all be done now, so make a final ah flush.
	 */
	ipoib_stop_ah(dev);

	ipoib_transport_dev_cleanup(dev);
}