summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
blob: 319d4288edddeaca2fb273fa7e1b211ed8619beb (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
/*
 * Copyright (c) 2004, 2005 Topspin Communications.  All rights reserved.
 * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
 * Copyright (c) 2004 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/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/moduleparam.h>
#include <linux/ip.h>
#include <linux/in.h>
#include <linux/igmp.h>
#include <linux/inetdevice.h>
#include <linux/delay.h>
#include <linux/completion.h>
#include <linux/slab.h>

#include <net/dst.h>

#include "ipoib.h"

#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
static int mcast_debug_level;

module_param(mcast_debug_level, int, 0644);
MODULE_PARM_DESC(mcast_debug_level,
		 "Enable multicast debug tracing if > 0");
#endif

struct ipoib_mcast_iter {
	struct net_device *dev;
	union ib_gid       mgid;
	unsigned long      created;
	unsigned int       queuelen;
	unsigned int       complete;
	unsigned int       send_only;
};

/* join state that allows creating mcg with sendonly member request */
#define SENDONLY_FULLMEMBER_JOIN	8

/*
 * This should be called with the priv->lock held
 */
static void __ipoib_mcast_schedule_join_thread(struct ipoib_dev_priv *priv,
					       struct ipoib_mcast *mcast,
					       bool delay)
{
	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
		return;

	/*
	 * We will be scheduling *something*, so cancel whatever is
	 * currently scheduled first
	 */
	cancel_delayed_work(&priv->mcast_task);
	if (mcast && delay) {
		/*
		 * We had a failure and want to schedule a retry later
		 */
		mcast->backoff *= 2;
		if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
			mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;
		mcast->delay_until = jiffies + (mcast->backoff * HZ);
		/*
		 * Mark this mcast for its delay, but restart the
		 * task immediately.  The join task will make sure to
		 * clear out all entries without delays, and then
		 * schedule itself to run again when the earliest
		 * delay expires
		 */
		queue_delayed_work(priv->wq, &priv->mcast_task, 0);
	} else if (delay) {
		/*
		 * Special case of retrying after a failure to
		 * allocate the broadcast multicast group, wait
		 * 1 second and try again
		 */
		queue_delayed_work(priv->wq, &priv->mcast_task, HZ);
	} else
		queue_delayed_work(priv->wq, &priv->mcast_task, 0);
}

static void ipoib_mcast_free(struct ipoib_mcast *mcast)
{
	struct net_device *dev = mcast->dev;
	int tx_dropped = 0;

	ipoib_dbg_mcast(ipoib_priv(dev), "deleting multicast group %pI6\n",
			mcast->mcmember.mgid.raw);

	/* remove all neigh connected to this mcast */
	ipoib_del_neighs_by_gid(dev, mcast->mcmember.mgid.raw);

	if (mcast->ah)
		ipoib_put_ah(mcast->ah);

	while (!skb_queue_empty(&mcast->pkt_queue)) {
		++tx_dropped;
		dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue));
	}

	netif_tx_lock_bh(dev);
	dev->stats.tx_dropped += tx_dropped;
	netif_tx_unlock_bh(dev);

	kfree(mcast);
}

static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev)
{
	struct ipoib_mcast *mcast;

	mcast = kzalloc(sizeof(*mcast), GFP_ATOMIC);
	if (!mcast)
		return NULL;

	mcast->dev = dev;
	mcast->created = jiffies;
	mcast->delay_until = jiffies;
	mcast->backoff = 1;

	INIT_LIST_HEAD(&mcast->list);
	INIT_LIST_HEAD(&mcast->neigh_list);
	skb_queue_head_init(&mcast->pkt_queue);

	return mcast;
}

static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
{
	struct ipoib_dev_priv *priv = ipoib_priv(dev);
	struct rb_node *n = priv->multicast_tree.rb_node;

	while (n) {
		struct ipoib_mcast *mcast;
		int ret;

		mcast = rb_entry(n, struct ipoib_mcast, rb_node);

		ret = memcmp(mgid, mcast->mcmember.mgid.raw,
			     sizeof (union ib_gid));
		if (ret < 0)
			n = n->rb_left;
		else if (ret > 0)
			n = n->rb_right;
		else
			return mcast;
	}

	return NULL;
}

static int __ipoib_mcast_add(struct net_device *dev, struct ipoib_mcast *mcast)
{
	struct ipoib_dev_priv *priv = ipoib_priv(dev);
	struct rb_node **n = &priv->multicast_tree.rb_node, *pn = NULL;

	while (*n) {
		struct ipoib_mcast *tmcast;
		int ret;

		pn = *n;
		tmcast = rb_entry(pn, struct ipoib_mcast, rb_node);

		ret = memcmp(mcast->mcmember.mgid.raw, tmcast->mcmember.mgid.raw,
			     sizeof (union ib_gid));
		if (ret < 0)
			n = &pn->rb_left;
		else if (ret > 0)
			n = &pn->rb_right;
		else
			return -EEXIST;
	}

	rb_link_node(&mcast->rb_node, pn, n);
	rb_insert_color(&mcast->rb_node, &priv->multicast_tree);

	return 0;
}

static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
				   struct ib_sa_mcmember_rec *mcmember)
{
	struct net_device *dev = mcast->dev;
	struct ipoib_dev_priv *priv = ipoib_priv(dev);
	struct rdma_netdev *rn = netdev_priv(dev);
	struct ipoib_ah *ah;
	struct rdma_ah_attr av;
	int ret;
	int set_qkey = 0;
	int mtu;

	mcast->mcmember = *mcmember;

	/* Set the multicast MTU and cached Q_Key before we attach if it's
	 * the broadcast group.
	 */
	if (!memcmp(mcast->mcmember.mgid.raw, priv->dev->broadcast + 4,
		    sizeof (union ib_gid))) {
		spin_lock_irq(&priv->lock);
		if (!priv->broadcast) {
			spin_unlock_irq(&priv->lock);
			return -EAGAIN;
		}
		/*update priv member according to the new mcast*/
		priv->broadcast->mcmember.qkey = mcmember->qkey;
		priv->broadcast->mcmember.mtu = mcmember->mtu;
		priv->broadcast->mcmember.traffic_class = mcmember->traffic_class;
		priv->broadcast->mcmember.rate = mcmember->rate;
		priv->broadcast->mcmember.sl = mcmember->sl;
		priv->broadcast->mcmember.flow_label = mcmember->flow_label;
		priv->broadcast->mcmember.hop_limit = mcmember->hop_limit;
		/* assume if the admin and the mcast are the same both can be changed */
		mtu = rdma_mtu_enum_to_int(priv->ca,  priv->port,
					   priv->broadcast->mcmember.mtu);
		if (priv->mcast_mtu == priv->admin_mtu)
			priv->admin_mtu = IPOIB_UD_MTU(mtu);
		priv->mcast_mtu = IPOIB_UD_MTU(mtu);
		rn->mtu = priv->mcast_mtu;

		priv->qkey = be32_to_cpu(priv->broadcast->mcmember.qkey);
		spin_unlock_irq(&priv->lock);
		priv->tx_wr.remote_qkey = priv->qkey;
		set_qkey = 1;
	}

	if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
		if (test_and_set_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
			ipoib_warn(priv, "multicast group %pI6 already attached\n",
				   mcast->mcmember.mgid.raw);

			return 0;
		}

		ret = rn->attach_mcast(dev, priv->ca, &mcast->mcmember.mgid,
				       be16_to_cpu(mcast->mcmember.mlid),
				       set_qkey, priv->qkey);
		if (ret < 0) {
			ipoib_warn(priv, "couldn't attach QP to multicast group %pI6\n",
				   mcast->mcmember.mgid.raw);

			clear_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags);
			return ret;
		}
	}

	memset(&av, 0, sizeof(av));
	av.type = rdma_ah_find_type(priv->ca, priv->port);
	rdma_ah_set_dlid(&av, be16_to_cpu(mcast->mcmember.mlid));
	rdma_ah_set_port_num(&av, priv->port);
	rdma_ah_set_sl(&av, mcast->mcmember.sl);
	rdma_ah_set_static_rate(&av, mcast->mcmember.rate);

	rdma_ah_set_grh(&av, &mcast->mcmember.mgid,
			be32_to_cpu(mcast->mcmember.flow_label),
			0, mcast->mcmember.hop_limit,
			mcast->mcmember.traffic_class);

	ah = ipoib_create_ah(dev, priv->pd, &av);
	if (IS_ERR(ah)) {
		ipoib_warn(priv, "ib_address_create failed %ld\n",
			   -PTR_ERR(ah));
		/* use original error */
		return PTR_ERR(ah);
	}
	spin_lock_irq(&priv->lock);
	mcast->ah = ah;
	spin_unlock_irq(&priv->lock);

	ipoib_dbg_mcast(priv, "MGID %pI6 AV %p, LID 0x%04x, SL %d\n",
			mcast->mcmember.mgid.raw,
			mcast->ah->ah,
			be16_to_cpu(mcast->mcmember.mlid),
			mcast->mcmember.sl);

	/* actually send any queued packets */
	netif_tx_lock_bh(dev);
	while (!skb_queue_empty(&mcast->pkt_queue)) {
		struct sk_buff *skb = skb_dequeue(&mcast->pkt_queue);

		netif_tx_unlock_bh(dev);

		skb->dev = dev;

		ret = dev_queue_xmit(skb);
		if (ret)
			ipoib_warn(priv, "%s:dev_queue_xmit failed to re-queue packet, ret:%d\n",
				   __func__, ret);
		netif_tx_lock_bh(dev);
	}
	netif_tx_unlock_bh(dev);

	return 0;
}

void ipoib_mcast_carrier_on_task(struct work_struct *work)
{
	struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv,
						   carrier_on_task);
	struct ib_port_attr attr;

	if (ib_query_port(priv->ca, priv->port, &attr) ||
	    attr.state != IB_PORT_ACTIVE) {
		ipoib_dbg(priv, "Keeping carrier off until IB port is active\n");
		return;
	}
	/*
	 * Take rtnl_lock to avoid racing with ipoib_stop() and
	 * turning the carrier back on while a device is being
	 * removed.  However, ipoib_stop() will attempt to flush
	 * the workqueue while holding the rtnl lock, so loop
	 * on trylock until either we get the lock or we see
	 * FLAG_OPER_UP go away as that signals that we are bailing
	 * and can safely ignore the carrier on work.
	 */
	while (!rtnl_trylock()) {
		if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
			return;
		else
			msleep(20);
	}
	if (!ipoib_cm_admin_enabled(priv->dev))
		dev_set_mtu(priv->dev, min(priv->mcast_mtu, priv->admin_mtu));
	netif_carrier_on(priv->dev);
	rtnl_unlock();
}

static int ipoib_mcast_join_complete(int status,
				     struct ib_sa_multicast *multicast)
{
	struct ipoib_mcast *mcast = multicast->context;
	struct net_device *dev = mcast->dev;
	struct ipoib_dev_priv *priv = ipoib_priv(dev);

	ipoib_dbg_mcast(priv, "%sjoin completion for %pI6 (status %d)\n",
			test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) ?
			"sendonly " : "",
			mcast->mcmember.mgid.raw, status);

	/* We trap for port events ourselves. */
	if (status == -ENETRESET) {
		status = 0;
		goto out;
	}

	if (!status)
		status = ipoib_mcast_join_finish(mcast, &multicast->rec);

	if (!status) {
		mcast->backoff = 1;
		mcast->delay_until = jiffies;

		/*
		 * Defer carrier on work to priv->wq to avoid a
		 * deadlock on rtnl_lock here.  Requeue our multicast
		 * work too, which will end up happening right after
		 * our carrier on task work and will allow us to
		 * send out all of the non-broadcast joins
		 */
		if (mcast == priv->broadcast) {
			spin_lock_irq(&priv->lock);
			queue_work(priv->wq, &priv->carrier_on_task);
			__ipoib_mcast_schedule_join_thread(priv, NULL, 0);
			goto out_locked;
		}
	} else {
		bool silent_fail =
		    test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) &&
		    status == -EINVAL;

		if (mcast->logcount < 20) {
			if (status == -ETIMEDOUT || status == -EAGAIN ||
			    silent_fail) {
				ipoib_dbg_mcast(priv, "%smulticast join failed for %pI6, status %d\n",
						test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) ? "sendonly " : "",
						mcast->mcmember.mgid.raw, status);
			} else {
				ipoib_warn(priv, "%smulticast join failed for %pI6, status %d\n",
						test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) ? "sendonly " : "",
					   mcast->mcmember.mgid.raw, status);
			}

			if (!silent_fail)
				mcast->logcount++;
		}

		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) &&
		    mcast->backoff >= 2) {
			/*
			 * We only retry sendonly joins once before we drop
			 * the packet and quit trying to deal with the
			 * group.  However, we leave the group in the
			 * mcast list as an unjoined group.  If we want to
			 * try joining again, we simply queue up a packet
			 * and restart the join thread.  The empty queue
			 * is why the join thread ignores this group.
			 */
			mcast->backoff = 1;
			netif_tx_lock_bh(dev);
			while (!skb_queue_empty(&mcast->pkt_queue)) {
				++dev->stats.tx_dropped;
				dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue));
			}
			netif_tx_unlock_bh(dev);
		} else {
			spin_lock_irq(&priv->lock);
			/* Requeue this join task with a backoff delay */
			__ipoib_mcast_schedule_join_thread(priv, mcast, 1);
			goto out_locked;
		}
	}
out:
	spin_lock_irq(&priv->lock);
out_locked:
	/*
	 * Make sure to set mcast->mc before we clear the busy flag to avoid
	 * racing with code that checks for BUSY before checking mcast->mc
	 */
	if (status)
		mcast->mc = NULL;
	else
		mcast->mc = multicast;
	clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
	spin_unlock_irq(&priv->lock);
	complete(&mcast->done);

	return status;
}

/*
 * Caller must hold 'priv->lock'
 */
static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
{
	struct ipoib_dev_priv *priv = ipoib_priv(dev);
	struct ib_sa_multicast *multicast;
	struct ib_sa_mcmember_rec rec = {
		.join_state = 1
	};
	ib_sa_comp_mask comp_mask;
	int ret = 0;

	if (!priv->broadcast ||
	    !test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
		return -EINVAL;

	init_completion(&mcast->done);
	set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);

	ipoib_dbg_mcast(priv, "joining MGID %pI6\n", mcast->mcmember.mgid.raw);

	rec.mgid     = mcast->mcmember.mgid;
	rec.port_gid = priv->local_gid;
	rec.pkey     = cpu_to_be16(priv->pkey);

	comp_mask =
		IB_SA_MCMEMBER_REC_MGID		|
		IB_SA_MCMEMBER_REC_PORT_GID	|
		IB_SA_MCMEMBER_REC_PKEY		|
		IB_SA_MCMEMBER_REC_JOIN_STATE;

	if (mcast != priv->broadcast) {
		/*
		 * RFC 4391:
		 *  The MGID MUST use the same P_Key, Q_Key, SL, MTU,
		 *  and HopLimit as those used in the broadcast-GID.  The rest
		 *  of attributes SHOULD follow the values used in the
		 *  broadcast-GID as well.
		 */
		comp_mask |=
			IB_SA_MCMEMBER_REC_QKEY			|
			IB_SA_MCMEMBER_REC_MTU_SELECTOR		|
			IB_SA_MCMEMBER_REC_MTU			|
			IB_SA_MCMEMBER_REC_TRAFFIC_CLASS	|
			IB_SA_MCMEMBER_REC_RATE_SELECTOR	|
			IB_SA_MCMEMBER_REC_RATE			|
			IB_SA_MCMEMBER_REC_SL			|
			IB_SA_MCMEMBER_REC_FLOW_LABEL		|
			IB_SA_MCMEMBER_REC_HOP_LIMIT;

		rec.qkey	  = priv->broadcast->mcmember.qkey;
		rec.mtu_selector  = IB_SA_EQ;
		rec.mtu		  = priv->broadcast->mcmember.mtu;
		rec.traffic_class = priv->broadcast->mcmember.traffic_class;
		rec.rate_selector = IB_SA_EQ;
		rec.rate	  = priv->broadcast->mcmember.rate;
		rec.sl		  = priv->broadcast->mcmember.sl;
		rec.flow_label	  = priv->broadcast->mcmember.flow_label;
		rec.hop_limit	  = priv->broadcast->mcmember.hop_limit;

		/*
		 * Send-only IB Multicast joins work at the core IB layer but
		 * require specific SM support.
		 * We can use such joins here only if the current SM supports that feature.
		 * However, if not, we emulate an Ethernet multicast send,
		 * which does not require a multicast subscription and will
		 * still send properly. The most appropriate thing to
		 * do is to create the group if it doesn't exist as that
		 * most closely emulates the behavior, from a user space
		 * application perspective, of Ethernet multicast operation.
		 */
		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
			rec.join_state = SENDONLY_FULLMEMBER_JOIN;
	}

	multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port,
					 &rec, comp_mask, GFP_ATOMIC,
					 ipoib_mcast_join_complete, mcast);
	if (IS_ERR(multicast)) {
		ret = PTR_ERR(multicast);
		ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret);
		/* Requeue this join task with a backoff delay */
		__ipoib_mcast_schedule_join_thread(priv, mcast, 1);
		clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
		complete(&mcast->done);
		return ret;
	}
	return 0;
}

void ipoib_mcast_join_task(struct work_struct *work)
{
	struct ipoib_dev_priv *priv =
		container_of(work, struct ipoib_dev_priv, mcast_task.work);
	struct net_device *dev = priv->dev;
	struct ib_port_attr port_attr;
	unsigned long delay_until = 0;
	struct ipoib_mcast *mcast = NULL;

	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
		return;

	if (ib_query_port(priv->ca, priv->port, &port_attr)) {
		ipoib_dbg(priv, "ib_query_port() failed\n");
		return;
	}
	if (port_attr.state != IB_PORT_ACTIVE) {
		ipoib_dbg(priv, "port state is not ACTIVE (state = %d) suspending join task\n",
			  port_attr.state);
		return;
	}
	priv->local_lid = port_attr.lid;
	netif_addr_lock_bh(dev);

	if (!test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) {
		netif_addr_unlock_bh(dev);
		return;
	}
	netif_addr_unlock_bh(dev);

	spin_lock_irq(&priv->lock);
	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
		goto out;

	if (!priv->broadcast) {
		struct ipoib_mcast *broadcast;

		broadcast = ipoib_mcast_alloc(dev);
		if (!broadcast) {
			ipoib_warn(priv, "failed to allocate broadcast group\n");
			/*
			 * Restart us after a 1 second delay to retry
			 * creating our broadcast group and attaching to
			 * it.  Until this succeeds, this ipoib dev is
			 * completely stalled (multicast wise).
			 */
			__ipoib_mcast_schedule_join_thread(priv, NULL, 1);
			goto out;
		}

		memcpy(broadcast->mcmember.mgid.raw, priv->dev->broadcast + 4,
		       sizeof (union ib_gid));
		priv->broadcast = broadcast;

		__ipoib_mcast_add(dev, priv->broadcast);
	}

	if (!test_bit(IPOIB_MCAST_FLAG_ATTACHED, &priv->broadcast->flags)) {
		if (IS_ERR_OR_NULL(priv->broadcast->mc) &&
		    !test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags)) {
			mcast = priv->broadcast;
			if (mcast->backoff > 1 &&
			    time_before(jiffies, mcast->delay_until)) {
				delay_until = mcast->delay_until;
				mcast = NULL;
			}
		}
		goto out;
	}

	/*
	 * We'll never get here until the broadcast group is both allocated
	 * and attached
	 */
	list_for_each_entry(mcast, &priv->multicast_list, list) {
		if (IS_ERR_OR_NULL(mcast->mc) &&
		    !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags) &&
		    (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) ||
		     !skb_queue_empty(&mcast->pkt_queue))) {
			if (mcast->backoff == 1 ||
			    time_after_eq(jiffies, mcast->delay_until)) {
				/* Found the next unjoined group */
				if (ipoib_mcast_join(dev, mcast)) {
					spin_unlock_irq(&priv->lock);
					return;
				}
			} else if (!delay_until ||
				 time_before(mcast->delay_until, delay_until))
				delay_until = mcast->delay_until;
		}
	}

	mcast = NULL;
	ipoib_dbg_mcast(priv, "successfully started all multicast joins\n");

out:
	if (delay_until) {
		cancel_delayed_work(&priv->mcast_task);
		queue_delayed_work(priv->wq, &priv->mcast_task,
				   delay_until - jiffies);
	}
	if (mcast)
		ipoib_mcast_join(dev, mcast);

	spin_unlock_irq(&priv->lock);
}

void ipoib_mcast_start_thread(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = ipoib_priv(dev);
	unsigned long flags;

	ipoib_dbg_mcast(priv, "starting multicast thread\n");

	spin_lock_irqsave(&priv->lock, flags);
	__ipoib_mcast_schedule_join_thread(priv, NULL, 0);
	spin_unlock_irqrestore(&priv->lock, flags);
}

void ipoib_mcast_stop_thread(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = ipoib_priv(dev);

	ipoib_dbg_mcast(priv, "stopping multicast thread\n");

	cancel_delayed_work_sync(&priv->mcast_task);
}

static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
{
	struct ipoib_dev_priv *priv = ipoib_priv(dev);
	struct rdma_netdev *rn = netdev_priv(dev);
	int ret = 0;

	if (test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
		ipoib_warn(priv, "ipoib_mcast_leave on an in-flight join\n");

	if (!IS_ERR_OR_NULL(mcast->mc))
		ib_sa_free_multicast(mcast->mc);

	if (test_and_clear_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
		ipoib_dbg_mcast(priv, "leaving MGID %pI6\n",
				mcast->mcmember.mgid.raw);

		/* Remove ourselves from the multicast group */
		ret = rn->detach_mcast(dev, priv->ca, &mcast->mcmember.mgid,
				       be16_to_cpu(mcast->mcmember.mlid));
		if (ret)
			ipoib_warn(priv, "ib_detach_mcast failed (result = %d)\n", ret);
	} else if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
		ipoib_dbg(priv, "leaving with no mcmember but not a "
			  "SENDONLY join\n");

	return 0;
}

/*
 * Check if the multicast group is sendonly. If so remove it from the maps
 * and add to the remove list
 */
void ipoib_check_and_add_mcast_sendonly(struct ipoib_dev_priv *priv, u8 *mgid,
				struct list_head *remove_list)
{
	/* Is this multicast ? */
	if (*mgid == 0xff) {
		struct ipoib_mcast *mcast = __ipoib_mcast_find(priv->dev, mgid);

		if (mcast && test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
			list_del(&mcast->list);
			rb_erase(&mcast->rb_node, &priv->multicast_tree);
			list_add_tail(&mcast->list, remove_list);
		}
	}
}

void ipoib_mcast_remove_list(struct list_head *remove_list)
{
	struct ipoib_mcast *mcast, *tmcast;

	/*
	 * make sure the in-flight joins have finished before we attempt
	 * to leave
	 */
	list_for_each_entry_safe(mcast, tmcast, remove_list, list)
		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
			wait_for_completion(&mcast->done);

	list_for_each_entry_safe(mcast, tmcast, remove_list, list) {
		ipoib_mcast_leave(mcast->dev, mcast);
		ipoib_mcast_free(mcast);
	}
}

void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
{
	struct ipoib_dev_priv *priv = ipoib_priv(dev);
	struct rdma_netdev *rn = netdev_priv(dev);
	struct ipoib_mcast *mcast;
	unsigned long flags;
	void *mgid = daddr + 4;

	spin_lock_irqsave(&priv->lock, flags);

	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)		||
	    !priv->broadcast					||
	    !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &priv->broadcast->flags)) {
		++dev->stats.tx_dropped;
		dev_kfree_skb_any(skb);
		goto unlock;
	}

	mcast = __ipoib_mcast_find(dev, mgid);
	if (!mcast || !mcast->ah) {
		if (!mcast) {
			/* Let's create a new send only group now */
			ipoib_dbg_mcast(priv, "setting up send only multicast group for %pI6\n",
					mgid);

			mcast = ipoib_mcast_alloc(dev);
			if (!mcast) {
				ipoib_warn(priv, "unable to allocate memory "
					   "for multicast structure\n");
				++dev->stats.tx_dropped;
				dev_kfree_skb_any(skb);
				goto unlock;
			}

			set_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags);
			memcpy(mcast->mcmember.mgid.raw, mgid,
			       sizeof (union ib_gid));
			__ipoib_mcast_add(dev, mcast);
			list_add_tail(&mcast->list, &priv->multicast_list);
		}
		if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) {
			/* put pseudoheader back on for next time */
			skb_push(skb, sizeof(struct ipoib_pseudo_header));
			skb_queue_tail(&mcast->pkt_queue, skb);
		} else {
			++dev->stats.tx_dropped;
			dev_kfree_skb_any(skb);
		}
		if (!test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) {
			__ipoib_mcast_schedule_join_thread(priv, NULL, 0);
		}
	} else {
		struct ipoib_neigh *neigh;

		spin_unlock_irqrestore(&priv->lock, flags);
		neigh = ipoib_neigh_get(dev, daddr);
		spin_lock_irqsave(&priv->lock, flags);
		if (!neigh) {
			neigh = ipoib_neigh_alloc(daddr, dev);
			/* Make sure that the neigh will be added only
			 * once to mcast list.
			 */
			if (neigh && list_empty(&neigh->list)) {
				kref_get(&mcast->ah->ref);
				neigh->ah	= mcast->ah;
				neigh->ah->valid = 1;
				list_add_tail(&neigh->list, &mcast->neigh_list);
			}
		}
		spin_unlock_irqrestore(&priv->lock, flags);
		mcast->ah->last_send = rn->send(dev, skb, mcast->ah->ah,
						IB_MULTICAST_QPN);
		if (neigh)
			ipoib_neigh_put(neigh);
		return;
	}

unlock:
	spin_unlock_irqrestore(&priv->lock, flags);
}

void ipoib_mcast_dev_flush(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = ipoib_priv(dev);
	LIST_HEAD(remove_list);
	struct ipoib_mcast *mcast, *tmcast;
	unsigned long flags;

	mutex_lock(&priv->mcast_mutex);
	ipoib_dbg_mcast(priv, "flushing multicast list\n");

	spin_lock_irqsave(&priv->lock, flags);

	list_for_each_entry_safe(mcast, tmcast, &priv->multicast_list, list) {
		list_del(&mcast->list);
		rb_erase(&mcast->rb_node, &priv->multicast_tree);
		list_add_tail(&mcast->list, &remove_list);
	}

	if (priv->broadcast) {
		rb_erase(&priv->broadcast->rb_node, &priv->multicast_tree);
		list_add_tail(&priv->broadcast->list, &remove_list);
		priv->broadcast = NULL;
	}

	spin_unlock_irqrestore(&priv->lock, flags);

	ipoib_mcast_remove_list(&remove_list);
	mutex_unlock(&priv->mcast_mutex);
}

static int ipoib_mcast_addr_is_valid(const u8 *addr, const u8 *broadcast)
{
	/* reserved QPN, prefix, scope */
	if (memcmp(addr, broadcast, 6))
		return 0;
	/* signature lower, pkey */
	if (memcmp(addr + 7, broadcast + 7, 3))
		return 0;
	return 1;
}

void ipoib_mcast_restart_task(struct work_struct *work)
{
	struct ipoib_dev_priv *priv =
		container_of(work, struct ipoib_dev_priv, restart_task);
	struct net_device *dev = priv->dev;
	struct netdev_hw_addr *ha;
	struct ipoib_mcast *mcast, *tmcast;
	LIST_HEAD(remove_list);
	struct ib_sa_mcmember_rec rec;

	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
		/*
		 * shortcut...on shutdown flush is called next, just
		 * let it do all the work
		 */
		return;

	ipoib_dbg_mcast(priv, "restarting multicast task\n");

	netif_addr_lock_bh(dev);
	spin_lock_irq(&priv->lock);

	/*
	 * Unfortunately, the networking core only gives us a list of all of
	 * the multicast hardware addresses. We need to figure out which ones
	 * are new and which ones have been removed
	 */

	/* Clear out the found flag */
	list_for_each_entry(mcast, &priv->multicast_list, list)
		clear_bit(IPOIB_MCAST_FLAG_FOUND, &mcast->flags);

	/* Mark all of the entries that are found or don't exist */
	netdev_for_each_mc_addr(ha, dev) {
		union ib_gid mgid;

		if (!ipoib_mcast_addr_is_valid(ha->addr, dev->broadcast))
			continue;

		memcpy(mgid.raw, ha->addr + 4, sizeof(mgid));

		mcast = __ipoib_mcast_find(dev, &mgid);
		if (!mcast || test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
			struct ipoib_mcast *nmcast;

			/* ignore group which is directly joined by userspace */
			if (test_bit(IPOIB_FLAG_UMCAST, &priv->flags) &&
			    !ib_sa_get_mcmember_rec(priv->ca, priv->port, &mgid, &rec)) {
				ipoib_dbg_mcast(priv, "ignoring multicast entry for mgid %pI6\n",
						mgid.raw);
				continue;
			}

			/* Not found or send-only group, let's add a new entry */
			ipoib_dbg_mcast(priv, "adding multicast entry for mgid %pI6\n",
					mgid.raw);

			nmcast = ipoib_mcast_alloc(dev);
			if (!nmcast) {
				ipoib_warn(priv, "unable to allocate memory for multicast structure\n");
				continue;
			}

			set_bit(IPOIB_MCAST_FLAG_FOUND, &nmcast->flags);

			nmcast->mcmember.mgid = mgid;

			if (mcast) {
				/* Destroy the send only entry */
				list_move_tail(&mcast->list, &remove_list);

				rb_replace_node(&mcast->rb_node,
						&nmcast->rb_node,
						&priv->multicast_tree);
			} else
				__ipoib_mcast_add(dev, nmcast);

			list_add_tail(&nmcast->list, &priv->multicast_list);
		}

		if (mcast)
			set_bit(IPOIB_MCAST_FLAG_FOUND, &mcast->flags);
	}

	/* Remove all of the entries don't exist anymore */
	list_for_each_entry_safe(mcast, tmcast, &priv->multicast_list, list) {
		if (!test_bit(IPOIB_MCAST_FLAG_FOUND, &mcast->flags) &&
		    !test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
			ipoib_dbg_mcast(priv, "deleting multicast group %pI6\n",
					mcast->mcmember.mgid.raw);

			rb_erase(&mcast->rb_node, &priv->multicast_tree);

			/* Move to the remove list */
			list_move_tail(&mcast->list, &remove_list);
		}
	}

	spin_unlock_irq(&priv->lock);
	netif_addr_unlock_bh(dev);

	ipoib_mcast_remove_list(&remove_list);

	/*
	 * Double check that we are still up
	 */
	if (test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) {
		spin_lock_irq(&priv->lock);
		__ipoib_mcast_schedule_join_thread(priv, NULL, 0);
		spin_unlock_irq(&priv->lock);
	}
}

#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG

struct ipoib_mcast_iter *ipoib_mcast_iter_init(struct net_device *dev)
{
	struct ipoib_mcast_iter *iter;

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

	iter->dev = dev;
	memset(iter->mgid.raw, 0, 16);

	if (ipoib_mcast_iter_next(iter)) {
		kfree(iter);
		return NULL;
	}

	return iter;
}

int ipoib_mcast_iter_next(struct ipoib_mcast_iter *iter)
{
	struct ipoib_dev_priv *priv = ipoib_priv(iter->dev);
	struct rb_node *n;
	struct ipoib_mcast *mcast;
	int ret = 1;

	spin_lock_irq(&priv->lock);

	n = rb_first(&priv->multicast_tree);

	while (n) {
		mcast = rb_entry(n, struct ipoib_mcast, rb_node);

		if (memcmp(iter->mgid.raw, mcast->mcmember.mgid.raw,
			   sizeof (union ib_gid)) < 0) {
			iter->mgid      = mcast->mcmember.mgid;
			iter->created   = mcast->created;
			iter->queuelen  = skb_queue_len(&mcast->pkt_queue);
			iter->complete  = !!mcast->ah;
			iter->send_only = !!(mcast->flags & (1 << IPOIB_MCAST_FLAG_SENDONLY));

			ret = 0;

			break;
		}

		n = rb_next(n);
	}

	spin_unlock_irq(&priv->lock);

	return ret;
}

void ipoib_mcast_iter_read(struct ipoib_mcast_iter *iter,
			   union ib_gid *mgid,
			   unsigned long *created,
			   unsigned int *queuelen,
			   unsigned int *complete,
			   unsigned int *send_only)
{
	*mgid      = iter->mgid;
	*created   = iter->created;
	*queuelen  = iter->queuelen;
	*complete  = iter->complete;
	*send_only = iter->send_only;
}

#endif /* CONFIG_INFINIBAND_IPOIB_DEBUG */