aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/ulp/ipoib/ipoib_ib.c
blob: 93f74567897e6dcf385c24621266e52de4de3e66 (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
/*
 * 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.
 *
 * $Id: ipoib_ib.c 1386 2004-12-27 16:23:17Z roland $
 */

#include <linux/delay.h>
#include <linux/dma-mapping.h>

#include <rdma/ib_cache.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;

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

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

	ah->ah = ib_create_ah(pd, attr);
	if (IS_ERR(ah->ah)) {
		kfree(ah);
		ah = NULL;
	} else
		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 int ipoib_ib_post_receive(struct net_device *dev, int id)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	struct ib_sge list;
	struct ib_recv_wr param;
	struct ib_recv_wr *bad_wr;
	int ret;

	list.addr     = priv->rx_ring[id].mapping;
	list.length   = IPOIB_BUF_SIZE;
	list.lkey     = priv->mr->lkey;

	param.next    = NULL;
	param.wr_id   = id | IPOIB_OP_RECV;
	param.sg_list = &list;
	param.num_sge = 1;

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

	return ret;
}

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

	skb = dev_alloc_skb(IPOIB_BUF_SIZE + 4);
	if (!skb)
		return -ENOMEM;

	/*
	 * IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte
	 * header.  So we need 4 more bytes to get to 48 and align the
	 * IP header to a multiple of 16.
	 */
	skb_reserve(skb, 4);

	addr = ib_dma_map_single(priv->ca, skb->data, IPOIB_BUF_SIZE,
				 DMA_FROM_DEVICE);
	if (unlikely(ib_dma_mapping_error(priv->ca, addr))) {
		dev_kfree_skb_any(skb);
		return -EIO;
	}

	priv->rx_ring[id].skb     = skb;
	priv->rx_ring[id].mapping = addr;

	return 0;
}

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 addr;

	ipoib_dbg_data(priv, "recv completion: id %d, op %d, status: %d\n",
		       wr_id, wc->opcode, 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;
	addr = priv->rx_ring[wr_id].mapping;

	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);
		ib_dma_unmap_single(priv->ca, addr,
				    IPOIB_BUF_SIZE, DMA_FROM_DEVICE);
		dev_kfree_skb_any(skb);
		priv->rx_ring[wr_id].skb = NULL;
		return;
	}

	/*
	 * 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))) {
		++priv->stats.rx_dropped;
		goto repost;
	}

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

	ib_dma_unmap_single(priv->ca, addr, IPOIB_BUF_SIZE, DMA_FROM_DEVICE);

	skb_put(skb, wc->byte_len);
	skb_pull(skb, IB_GRH_BYTES);

	if (wc->slid != priv->local_lid ||
	    wc->src_qp != priv->qp->qp_num) {
		skb->protocol = ((struct ipoib_header *) skb->data)->proto;
		skb_reset_mac_header(skb);
		skb_pull(skb, IPOIB_ENCAP_LEN);

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

		skb->dev = dev;
		/* XXX get correct PACKET_ type here */
		skb->pkt_type = PACKET_HOST;
		netif_rx_ni(skb);
	} else {
		ipoib_dbg_data(priv, "dropping loopback packet\n");
		dev_kfree_skb_any(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);
}

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;
	unsigned long flags;

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

	ib_dma_unmap_single(priv->ca, tx_req->mapping,
			    tx_req->skb->len, DMA_TO_DEVICE);

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

	dev_kfree_skb_any(tx_req->skb);

	spin_lock_irqsave(&priv->tx_lock, flags);
	++priv->tx_tail;
	if (unlikely(test_bit(IPOIB_FLAG_NETIF_STOPPED, &priv->flags)) &&
	    priv->tx_head - priv->tx_tail <= ipoib_sendq_size >> 1) {
		clear_bit(IPOIB_FLAG_NETIF_STOPPED, &priv->flags);
		netif_wake_queue(dev);
	}
	spin_unlock_irqrestore(&priv->tx_lock, flags);

	if (wc->status != IB_WC_SUCCESS &&
	    wc->status != IB_WC_WR_FLUSH_ERR)
		ipoib_warn(priv, "failed send event "
			   "(status=%d, wrid=%d vend_err %x)\n",
			   wc->status, wr_id, wc->vendor_err);
}

static void ipoib_ib_handle_wc(struct net_device *dev, struct ib_wc *wc)
{
	if (wc->wr_id & IPOIB_CM_OP_SRQ)
		ipoib_cm_handle_rx_wc(dev, wc);
	else if (wc->wr_id & IPOIB_OP_RECV)
		ipoib_ib_handle_rx_wc(dev, wc);
	else
		ipoib_ib_handle_tx_wc(dev, wc);
}

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

	ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
	do {
		n = ib_poll_cq(cq, IPOIB_NUM_WC, priv->ibwc);
		for (i = 0; i < n; ++i)
			ipoib_ib_handle_wc(dev, priv->ibwc + i);
	} while (n == IPOIB_NUM_WC);
}

static inline int post_send(struct ipoib_dev_priv *priv,
			    unsigned int wr_id,
			    struct ib_ah *address, u32 qpn,
			    u64 addr, int len)
{
	struct ib_send_wr *bad_wr;

	priv->tx_sge.addr             = addr;
	priv->tx_sge.length           = len;

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

	return ib_post_send(priv->qp, &priv->tx_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;
	u64 addr;

	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);
		++priv->stats.tx_dropped;
		++priv->stats.tx_errors;
		ipoib_cm_skb_too_long(dev, skb, priv->mcast_mtu);
		return;
	}

	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;
	addr = ib_dma_map_single(priv->ca, skb->data, skb->len,
				 DMA_TO_DEVICE);
	if (unlikely(ib_dma_mapping_error(priv->ca, addr))) {
		++priv->stats.tx_errors;
		dev_kfree_skb_any(skb);
		return;
	}
	tx_req->mapping = addr;

	if (unlikely(post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
			       address->ah, qpn, addr, skb->len))) {
		ipoib_warn(priv, "post_send failed\n");
		++priv->stats.tx_errors;
		ib_dma_unmap_single(priv->ca, addr, skb->len, DMA_TO_DEVICE);
		dev_kfree_skb_any(skb);
	} else {
		dev->trans_start = jiffies;

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

		if (priv->tx_head - priv->tx_tail == ipoib_sendq_size) {
			ipoib_dbg(priv, "TX ring full, stopping kernel net queue\n");
			netif_stop_queue(dev);
			set_bit(IPOIB_FLAG_NETIF_STOPPED, &priv->flags);
		}
	}
}

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);

	spin_lock_irq(&priv->tx_lock);
	spin_lock(&priv->lock);
	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(&priv->lock);
	spin_unlock_irq(&priv->tx_lock);
}

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(ipoib_workqueue, &priv->ah_reap_task, HZ);
}

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

	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);
		ipoib_ib_dev_stop(dev);
		return -1;
	}

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

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

	set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);

	return 0;
}

static void ipoib_pkey_dev_check_presence(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);
	u16 pkey_index = 0;

	if (ib_find_cached_pkey(priv->ca, priv->port, priv->pkey, &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, int flush)
{
	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);

	/* Shutdown the P_Key thread if still active */
	if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
		mutex_lock(&pkey_mutex);
		set_bit(IPOIB_PKEY_STOP, &priv->flags);
		cancel_delayed_work(&priv->pkey_task);
		mutex_unlock(&pkey_mutex);
		if (flush)
			flush_workqueue(ipoib_workqueue);
	}

	ipoib_mcast_stop_thread(dev, flush);
	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;
}

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;

	clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);

	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)];
				ib_dma_unmap_single(priv->ca,
						    tx_req->mapping,
						    tx_req->skb->len,
						    DMA_TO_DEVICE);
				dev_kfree_skb_any(tx_req->skb);
				++priv->tx_tail;
			}

			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;
				ib_dma_unmap_single(priv->ca,
						    rx_req->mapping,
						    IPOIB_BUF_SIZE,
						    DMA_FROM_DEVICE);
				dev_kfree_skb_any(rx_req->skb);
				rx_req->skb = NULL;
			}

			goto timeout;
		}

		msleep(1);
	}

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

timeout:
	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");

	/* Wait for all AHs to be reaped */
	set_bit(IPOIB_STOP_REAPER, &priv->flags);
	cancel_delayed_work(&priv->ah_reap_task);
	flush_workqueue(ipoib_workqueue);

	begin = jiffies;

	while (!list_empty(&priv->dead_ahs)) {
		__ipoib_reap_ah(dev);

		if (time_after(jiffies, begin + HZ)) {
			ipoib_warn(priv, "timing out; will leak address handles\n");
			break;
		}

		msleep(1);
	}

	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;
	}

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

	return 0;
}

void ipoib_ib_dev_flush(struct work_struct *work)
{
	struct ipoib_dev_priv *cpriv, *priv =
		container_of(work, struct ipoib_dev_priv, flush_task);
	struct net_device *dev = priv->dev;

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

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

	ipoib_dbg(priv, "flushing\n");

	ipoib_ib_dev_down(dev, 0);

	/*
	 * 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)) {
		ipoib_ib_dev_up(dev);
		ipoib_mcast_restart_task(&priv->restart_task);
	}

	mutex_lock(&priv->vlan_mutex);

	/* Flush any child interfaces too */
	list_for_each_entry(cpriv, &priv->child_intfs, list)
		ipoib_ib_dev_flush(&cpriv->flush_task);

	mutex_unlock(&priv->vlan_mutex);
}

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");

	ipoib_mcast_stop_thread(dev, 1);
	ipoib_mcast_dev_flush(dev);

	ipoib_transport_dev_cleanup(dev);
}

/*
 * Delayed P_Key Assigment Interim Support
 *
 * The following is initial implementation of delayed P_Key assigment
 * mechanism. It is using the same approach implemented for the multicast
 * group join. The single goal of this implementation is to quickly address
 * Bug #2507. This implementation will probably be removed when the P_Key
 * change async notification is available.
 */

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

	ipoib_pkey_dev_check_presence(dev);

	if (test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags))
		ipoib_open(dev);
	else {
		mutex_lock(&pkey_mutex);
		if (!test_bit(IPOIB_PKEY_STOP, &priv->flags))
			queue_delayed_work(ipoib_workqueue,
					   &priv->pkey_task,
					   HZ);
		mutex_unlock(&pkey_mutex);
	}
}

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

	/* Look for the interface pkey value in the IB Port P_Key table and */
	/* set the interface pkey assigment flag                            */
	ipoib_pkey_dev_check_presence(dev);

	/* P_Key value not assigned yet - start polling */
	if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
		mutex_lock(&pkey_mutex);
		clear_bit(IPOIB_PKEY_STOP, &priv->flags);
		queue_delayed_work(ipoib_workqueue,
				   &priv->pkey_task,
				   HZ);
		mutex_unlock(&pkey_mutex);
		return 1;
	}

	return 0;
}