aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
blob: b5e6a7be603df5388fb5d03ba55e997142babbe1 (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
/*
 * 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.
 *
 * $Id: ipoib_multicast.c 1362 2004-12-18 15:56:29Z roland $
 */

#include <linux/skbuff.h>
#include <linux/rtnetlink.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 <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

static DEFINE_MUTEX(mcast_mutex);

/* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
struct ipoib_mcast {
	struct ib_sa_mcmember_rec mcmember;
	struct ipoib_ah          *ah;

	struct rb_node    rb_node;
	struct list_head  list;
	struct completion done;

	int                 query_id;
	struct ib_sa_query *query;

	unsigned long created;
	unsigned long backoff;

	unsigned long flags;
	unsigned char logcount;

	struct list_head  neigh_list;

	struct sk_buff_head pkt_queue;

	struct net_device *dev;
};

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;
};

static void ipoib_mcast_free(struct ipoib_mcast *mcast)
{
	struct net_device *dev = mcast->dev;
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ipoib_neigh *neigh, *tmp;
	unsigned long flags;
	int tx_dropped = 0;

	ipoib_dbg_mcast(netdev_priv(dev),
			"deleting multicast group " IPOIB_GID_FMT "\n",
			IPOIB_GID_ARG(mcast->mcmember.mgid));

	spin_lock_irqsave(&priv->lock, flags);

	list_for_each_entry_safe(neigh, tmp, &mcast->neigh_list, list) {
		/*
		 * It's safe to call ipoib_put_ah() inside priv->lock
		 * here, because we know that mcast->ah will always
		 * hold one more reference, so ipoib_put_ah() will
		 * never do more than decrement the ref count.
		 */
		if (neigh->ah)
			ipoib_put_ah(neigh->ah);
		ipoib_neigh_free(neigh);
	}

	spin_unlock_irqrestore(&priv->lock, flags);

	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));
	}

	spin_lock_irqsave(&priv->tx_lock, flags);
	priv->stats.tx_dropped += tx_dropped;
	spin_unlock_irqrestore(&priv->tx_lock, flags);

	kfree(mcast);
}

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

	mcast = kzalloc(sizeof *mcast, can_sleep ? GFP_KERNEL : GFP_ATOMIC);
	if (!mcast)
		return NULL;

	mcast->dev = dev;
	mcast->created = 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 = netdev_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 = netdev_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 = netdev_priv(dev);
	struct ipoib_ah *ah;
	int ret;

	mcast->mcmember = *mcmember;

	/* Set the 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))) {
		priv->qkey = be32_to_cpu(priv->broadcast->mcmember.qkey);
		priv->tx_wr.wr.ud.remote_qkey = priv->qkey;
	}

	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 " IPOIB_GID_FMT
				   " already attached\n",
				   IPOIB_GID_ARG(mcast->mcmember.mgid));

			return 0;
		}

		ret = ipoib_mcast_attach(dev, be16_to_cpu(mcast->mcmember.mlid),
					 &mcast->mcmember.mgid);
		if (ret < 0) {
			ipoib_warn(priv, "couldn't attach QP to multicast group "
				   IPOIB_GID_FMT "\n",
				   IPOIB_GID_ARG(mcast->mcmember.mgid));

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

	{
		struct ib_ah_attr av = {
			.dlid	       = be16_to_cpu(mcast->mcmember.mlid),
			.port_num      = priv->port,
			.sl	       = mcast->mcmember.sl,
			.ah_flags      = IB_AH_GRH,
			.static_rate   = mcast->mcmember.rate,
			.grh	       = {
				.flow_label    = be32_to_cpu(mcast->mcmember.flow_label),
				.hop_limit     = mcast->mcmember.hop_limit,
				.sgid_index    = 0,
				.traffic_class = mcast->mcmember.traffic_class
			}
		};
		av.grh.dgid = mcast->mcmember.mgid;

		ah = ipoib_create_ah(dev, priv->pd, &av);
		if (!ah) {
			ipoib_warn(priv, "ib_address_create failed\n");
		} else {
			spin_lock_irq(&priv->lock);
			mcast->ah = ah;
			spin_unlock_irq(&priv->lock);

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

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

		skb->dev = dev;

		if (!skb->dst || !skb->dst->neighbour) {
			/* put pseudoheader back on for next time */
			skb_push(skb, sizeof (struct ipoib_pseudoheader));
		}

		if (dev_queue_xmit(skb))
			ipoib_warn(priv, "dev_queue_xmit failed to requeue packet\n");
		spin_lock_irq(&priv->tx_lock);
	}
	spin_unlock_irq(&priv->tx_lock);

	return 0;
}

static void
ipoib_mcast_sendonly_join_complete(int status,
				   struct ib_sa_mcmember_rec *mcmember,
				   void *mcast_ptr)
{
	struct ipoib_mcast *mcast = mcast_ptr;
	struct net_device *dev = mcast->dev;
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	if (!status)
		ipoib_mcast_join_finish(mcast, mcmember);
	else {
		if (mcast->logcount++ < 20)
			ipoib_dbg_mcast(netdev_priv(dev), "multicast join failed for "
					IPOIB_GID_FMT ", status %d\n",
					IPOIB_GID_ARG(mcast->mcmember.mgid), status);

		/* Flush out any queued packets */
		spin_lock_irq(&priv->tx_lock);
		while (!skb_queue_empty(&mcast->pkt_queue)) {
			++priv->stats.tx_dropped;
			dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue));
		}
		spin_unlock_irq(&priv->tx_lock);

		/* Clear the busy flag so we try again */
		clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
	}

	complete(&mcast->done);
}

static int ipoib_mcast_sendonly_join(struct ipoib_mcast *mcast)
{
	struct net_device *dev = mcast->dev;
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ib_sa_mcmember_rec rec = {
#if 0				/* Some SMs don't support send-only yet */
		.join_state = 4
#else
		.join_state = 1
#endif
	};
	int ret = 0;

	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) {
		ipoib_dbg_mcast(priv, "device shutting down, no multicast joins\n");
		return -ENODEV;
	}

	if (test_and_set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) {
		ipoib_dbg_mcast(priv, "multicast entry busy, skipping\n");
		return -EBUSY;
	}

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

	init_completion(&mcast->done);

	ret = ib_sa_mcmember_rec_set(priv->ca, priv->port, &rec,
				     IB_SA_MCMEMBER_REC_MGID		|
				     IB_SA_MCMEMBER_REC_PORT_GID	|
				     IB_SA_MCMEMBER_REC_PKEY		|
				     IB_SA_MCMEMBER_REC_JOIN_STATE,
				     1000, GFP_ATOMIC,
				     ipoib_mcast_sendonly_join_complete,
				     mcast, &mcast->query);
	if (ret < 0) {
		ipoib_warn(priv, "ib_sa_mcmember_rec_set failed (ret = %d)\n",
			   ret);
	} else {
		ipoib_dbg_mcast(priv, "no multicast record for " IPOIB_GID_FMT
				", starting join\n",
				IPOIB_GID_ARG(mcast->mcmember.mgid));

		mcast->query_id = ret;
	}

	return ret;
}

static void ipoib_mcast_join_complete(int status,
				      struct ib_sa_mcmember_rec *mcmember,
				      void *mcast_ptr)
{
	struct ipoib_mcast *mcast = mcast_ptr;
	struct net_device *dev = mcast->dev;
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	ipoib_dbg_mcast(priv, "join completion for " IPOIB_GID_FMT
			" (status %d)\n",
			IPOIB_GID_ARG(mcast->mcmember.mgid), status);

	if (!status && !ipoib_mcast_join_finish(mcast, mcmember)) {
		mcast->backoff = 1;
		mutex_lock(&mcast_mutex);
		if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
			queue_work(ipoib_workqueue, &priv->mcast_task);
		mutex_unlock(&mcast_mutex);
		complete(&mcast->done);
		return;
	}

	if (status == -EINTR) {
		complete(&mcast->done);
		return;
	}

	if (status && mcast->logcount++ < 20) {
		if (status == -ETIMEDOUT || status == -EINTR) {
			ipoib_dbg_mcast(priv, "multicast join failed for " IPOIB_GID_FMT
					", status %d\n",
					IPOIB_GID_ARG(mcast->mcmember.mgid),
					status);
		} else {
			ipoib_warn(priv, "multicast join failed for "
				   IPOIB_GID_FMT ", status %d\n",
				   IPOIB_GID_ARG(mcast->mcmember.mgid),
				   status);
		}
	}

	mcast->backoff *= 2;
	if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
		mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;

	mutex_lock(&mcast_mutex);

	spin_lock_irq(&priv->lock);
	mcast->query = NULL;

	if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) {
		if (status == -ETIMEDOUT)
			queue_work(ipoib_workqueue, &priv->mcast_task);
		else
			queue_delayed_work(ipoib_workqueue, &priv->mcast_task,
					   mcast->backoff * HZ);
	} else
		complete(&mcast->done);
	spin_unlock_irq(&priv->lock);
	mutex_unlock(&mcast_mutex);

	return;
}

static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast,
			     int create)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ib_sa_mcmember_rec rec = {
		.join_state = 1
	};
	ib_sa_comp_mask comp_mask;
	int ret = 0;

	ipoib_dbg_mcast(priv, "joining MGID " IPOIB_GID_FMT "\n",
			IPOIB_GID_ARG(mcast->mcmember.mgid));

	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 (create) {
		comp_mask |=
			IB_SA_MCMEMBER_REC_QKEY		|
			IB_SA_MCMEMBER_REC_SL		|
			IB_SA_MCMEMBER_REC_FLOW_LABEL	|
			IB_SA_MCMEMBER_REC_TRAFFIC_CLASS;

		rec.qkey	  = priv->broadcast->mcmember.qkey;
		rec.sl		  = priv->broadcast->mcmember.sl;
		rec.flow_label	  = priv->broadcast->mcmember.flow_label;
		rec.traffic_class = priv->broadcast->mcmember.traffic_class;
	}

	init_completion(&mcast->done);

	ret = ib_sa_mcmember_rec_set(priv->ca, priv->port, &rec, comp_mask,
				     mcast->backoff * 1000, GFP_ATOMIC,
				     ipoib_mcast_join_complete,
				     mcast, &mcast->query);

	if (ret < 0) {
		ipoib_warn(priv, "ib_sa_mcmember_rec_set failed, status %d\n", ret);

		mcast->backoff *= 2;
		if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
			mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;

		mutex_lock(&mcast_mutex);
		if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
			queue_delayed_work(ipoib_workqueue,
					   &priv->mcast_task,
					   mcast->backoff * HZ);
		mutex_unlock(&mcast_mutex);
	} else
		mcast->query_id = ret;
}

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

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

	if (ib_query_gid(priv->ca, priv->port, 0, &priv->local_gid))
		ipoib_warn(priv, "ib_gid_entry_get() failed\n");
	else
		memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));

	{
		struct ib_port_attr attr;

		if (!ib_query_port(priv->ca, priv->port, &attr)) {
			priv->local_lid  = attr.lid;
			priv->local_rate = attr.active_speed *
				ib_width_enum_to_int(attr.active_width);
		} else
			ipoib_warn(priv, "ib_query_port failed\n");
	}

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

		broadcast = ipoib_mcast_alloc(dev, 1);
		if (!broadcast) {
			ipoib_warn(priv, "failed to allocate broadcast group\n");
			mutex_lock(&mcast_mutex);
			if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
				queue_delayed_work(ipoib_workqueue,
						   &priv->mcast_task, HZ);
			mutex_unlock(&mcast_mutex);
			return;
		}

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

		__ipoib_mcast_add(dev, priv->broadcast);
		spin_unlock_irq(&priv->lock);
	}

	if (!test_bit(IPOIB_MCAST_FLAG_ATTACHED, &priv->broadcast->flags)) {
		ipoib_mcast_join(dev, priv->broadcast, 0);
		return;
	}

	while (1) {
		struct ipoib_mcast *mcast = NULL;

		spin_lock_irq(&priv->lock);
		list_for_each_entry(mcast, &priv->multicast_list, list) {
			if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)
			    && !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)
			    && !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
				/* Found the next unjoined group */
				break;
			}
		}
		spin_unlock_irq(&priv->lock);

		if (&mcast->list == &priv->multicast_list) {
			/* All done */
			break;
		}

		ipoib_mcast_join(dev, mcast, 1);
		return;
	}

	priv->mcast_mtu = ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu) -
		IPOIB_ENCAP_LEN;
	dev->mtu = min(priv->mcast_mtu, priv->admin_mtu);

	ipoib_dbg_mcast(priv, "successfully joined all multicast groups\n");

	clear_bit(IPOIB_MCAST_RUN, &priv->flags);
	netif_carrier_on(dev);
}

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

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

	mutex_lock(&mcast_mutex);
	if (!test_and_set_bit(IPOIB_MCAST_RUN, &priv->flags))
		queue_work(ipoib_workqueue, &priv->mcast_task);
	mutex_unlock(&mcast_mutex);

	spin_lock_irq(&priv->lock);
	set_bit(IPOIB_MCAST_STARTED, &priv->flags);
	spin_unlock_irq(&priv->lock);

	return 0;
}

static void wait_for_mcast_join(struct ipoib_dev_priv *priv,
				struct ipoib_mcast *mcast)
{
	spin_lock_irq(&priv->lock);
	if (mcast && mcast->query) {
		ib_sa_cancel_query(mcast->query_id, mcast->query);
		mcast->query = NULL;
		spin_unlock_irq(&priv->lock);
		ipoib_dbg_mcast(priv, "waiting for MGID " IPOIB_GID_FMT "\n",
				IPOIB_GID_ARG(mcast->mcmember.mgid));
		wait_for_completion(&mcast->done);
	}
	else
		spin_unlock_irq(&priv->lock);
}

int ipoib_mcast_stop_thread(struct net_device *dev, int flush)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ipoib_mcast *mcast;

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

	spin_lock_irq(&priv->lock);
	clear_bit(IPOIB_MCAST_STARTED, &priv->flags);
	spin_unlock_irq(&priv->lock);

	mutex_lock(&mcast_mutex);
	clear_bit(IPOIB_MCAST_RUN, &priv->flags);
	cancel_delayed_work(&priv->mcast_task);
	mutex_unlock(&mcast_mutex);

	if (flush)
		flush_workqueue(ipoib_workqueue);

	wait_for_mcast_join(priv, priv->broadcast);

	list_for_each_entry(mcast, &priv->multicast_list, list)
		wait_for_mcast_join(priv, mcast);

	return 0;
}

static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ib_sa_mcmember_rec rec = {
		.join_state = 1
	};
	int ret = 0;

	if (!test_and_clear_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags))
		return 0;

	ipoib_dbg_mcast(priv, "leaving MGID " IPOIB_GID_FMT "\n",
			IPOIB_GID_ARG(mcast->mcmember.mgid));

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

	/* Remove ourselves from the multicast group */
	ret = ipoib_mcast_detach(dev, be16_to_cpu(mcast->mcmember.mlid),
				 &mcast->mcmember.mgid);
	if (ret)
		ipoib_warn(priv, "ipoib_mcast_detach failed (result = %d)\n", ret);

	/*
	 * Just make one shot at leaving and don't wait for a reply;
	 * if we fail, too bad.
	 */
	ret = ib_sa_mcmember_rec_delete(priv->ca, priv->port, &rec,
					IB_SA_MCMEMBER_REC_MGID		|
					IB_SA_MCMEMBER_REC_PORT_GID	|
					IB_SA_MCMEMBER_REC_PKEY		|
					IB_SA_MCMEMBER_REC_JOIN_STATE,
					0, GFP_ATOMIC, NULL,
					mcast, &mcast->query);
	if (ret < 0)
		ipoib_warn(priv, "ib_sa_mcmember_rec_delete failed "
			   "for leave (result = %d)\n", ret);

	return 0;
}

void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ipoib_mcast *mcast;

	/*
	 * We can only be called from ipoib_start_xmit, so we're
	 * inside tx_lock -- no need to save/restore flags.
	 */
	spin_lock(&priv->lock);

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

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

		mcast = ipoib_mcast_alloc(dev, 0);
		if (!mcast) {
			ipoib_warn(priv, "unable to allocate memory for "
				   "multicast structure\n");
			++priv->stats.tx_dropped;
			dev_kfree_skb_any(skb);
			goto out;
		}

		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 (!mcast->ah) {
		if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE)
			skb_queue_tail(&mcast->pkt_queue, skb);
		else {
			++priv->stats.tx_dropped;
			dev_kfree_skb_any(skb);
		}

		if (mcast->query)
			ipoib_dbg_mcast(priv, "no address vector, "
					"but multicast join already started\n");
		else if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
			ipoib_mcast_sendonly_join(mcast);

		/*
		 * If lookup completes between here and out:, don't
		 * want to send packet twice.
		 */
		mcast = NULL;
	}

out:
	if (mcast && mcast->ah) {
		if (skb->dst            &&
		    skb->dst->neighbour &&
		    !*to_ipoib_neigh(skb->dst->neighbour)) {
			struct ipoib_neigh *neigh = ipoib_neigh_alloc(skb->dst->neighbour);

			if (neigh) {
				kref_get(&mcast->ah->ref);
				neigh->ah  	= mcast->ah;
				list_add_tail(&neigh->list, &mcast->neigh_list);
			}
		}

		ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN);
	}

unlock:
	spin_unlock(&priv->lock);
}

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

	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);

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

void ipoib_mcast_restart_task(void *dev_ptr)
{
	struct net_device *dev = dev_ptr;
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct dev_mc_list *mclist;
	struct ipoib_mcast *mcast, *tmcast;
	LIST_HEAD(remove_list);
	unsigned long flags;

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

	ipoib_mcast_stop_thread(dev, 0);

	local_irq_save(flags);
	netif_tx_lock(dev);
	spin_lock(&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 */
	for (mclist = dev->mc_list; mclist; mclist = mclist->next) {
		union ib_gid mgid;

		memcpy(mgid.raw, mclist->dmi_addr + 4, sizeof mgid);

		/* Add in the P_Key */
		mgid.raw[4] = (priv->pkey >> 8) & 0xff;
		mgid.raw[5] = priv->pkey & 0xff;

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

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

			nmcast = ipoib_mcast_alloc(dev, 0);
			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 " IPOIB_GID_FMT "\n",
					IPOIB_GID_ARG(mcast->mcmember.mgid));

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

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

	spin_unlock(&priv->lock);
	netif_tx_unlock(dev);
	local_irq_restore(flags);

	/* We have to cancel outside of the spinlock */
	list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
		wait_for_mcast_join(priv, mcast);
		ipoib_mcast_leave(mcast->dev, mcast);
		ipoib_mcast_free(mcast);
	}

	if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
		ipoib_mcast_start_thread(dev);
}

#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 = netdev_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 */