summaryrefslogtreecommitdiff
path: root/drivers/net/xen-netback/interface.c
blob: 08b0e3d0b7eb77acf3b886d50eeee424b44a2275 (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
/*
 * Network-device interface management.
 *
 * Copyright (c) 2004-2005, Keir Fraser
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License version 2
 * as published by the Free Software Foundation; or, when distributed
 * separately from the Linux kernel or incorporated into other
 * software packages, subject to the following license:
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this source file (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use, copy, modify,
 * merge, publish, distribute, sublicense, and/or sell copies of the Software,
 * and to permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * 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 "common.h"

#include <linux/kthread.h>
#include <linux/sched/task.h>
#include <linux/ethtool.h>
#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>
#include <linux/vmalloc.h>

#include <xen/events.h>
#include <asm/xen/hypercall.h>
#include <xen/balloon.h>

#define XENVIF_QUEUE_LENGTH 32
#define XENVIF_NAPI_WEIGHT  64

/* Number of bytes allowed on the internal guest Rx queue. */
#define XENVIF_RX_QUEUE_BYTES (XEN_NETIF_RX_RING_SIZE/2 * PAGE_SIZE)

/* This function is used to set SKBFL_ZEROCOPY_ENABLE as well as
 * increasing the inflight counter. We need to increase the inflight
 * counter because core driver calls into xenvif_zerocopy_callback
 * which calls xenvif_skb_zerocopy_complete.
 */
void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue,
				 struct sk_buff *skb)
{
	skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_ENABLE;
	atomic_inc(&queue->inflight_packets);
}

void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue)
{
	atomic_dec(&queue->inflight_packets);

	/* Wake the dealloc thread _after_ decrementing inflight_packets so
	 * that if kthread_stop() has already been called, the dealloc thread
	 * does not wait forever with nothing to wake it.
	 */
	wake_up(&queue->dealloc_wq);
}

int xenvif_schedulable(struct xenvif *vif)
{
	return netif_running(vif->dev) &&
		test_bit(VIF_STATUS_CONNECTED, &vif->status) &&
		!vif->disabled;
}

static bool xenvif_handle_tx_interrupt(struct xenvif_queue *queue)
{
	bool rc;

	rc = RING_HAS_UNCONSUMED_REQUESTS(&queue->tx);
	if (rc)
		napi_schedule(&queue->napi);
	return rc;
}

static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id)
{
	struct xenvif_queue *queue = dev_id;
	int old;

	old = atomic_fetch_or(NETBK_TX_EOI, &queue->eoi_pending);
	WARN(old & NETBK_TX_EOI, "Interrupt while EOI pending\n");

	if (!xenvif_handle_tx_interrupt(queue)) {
		atomic_andnot(NETBK_TX_EOI, &queue->eoi_pending);
		xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS);
	}

	return IRQ_HANDLED;
}

static int xenvif_poll(struct napi_struct *napi, int budget)
{
	struct xenvif_queue *queue =
		container_of(napi, struct xenvif_queue, napi);
	int work_done;

	/* This vif is rogue, we pretend we've there is nothing to do
	 * for this vif to deschedule it from NAPI. But this interface
	 * will be turned off in thread context later.
	 */
	if (unlikely(queue->vif->disabled)) {
		napi_complete(napi);
		return 0;
	}

	work_done = xenvif_tx_action(queue, budget);

	if (work_done < budget) {
		napi_complete_done(napi, work_done);
		/* If the queue is rate-limited, it shall be
		 * rescheduled in the timer callback.
		 */
		if (likely(!queue->rate_limited))
			xenvif_napi_schedule_or_enable_events(queue);
	}

	return work_done;
}

static bool xenvif_handle_rx_interrupt(struct xenvif_queue *queue)
{
	bool rc;

	rc = xenvif_have_rx_work(queue, false);
	if (rc)
		xenvif_kick_thread(queue);
	return rc;
}

static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id)
{
	struct xenvif_queue *queue = dev_id;
	int old;

	old = atomic_fetch_or(NETBK_RX_EOI, &queue->eoi_pending);
	WARN(old & NETBK_RX_EOI, "Interrupt while EOI pending\n");

	if (!xenvif_handle_rx_interrupt(queue)) {
		atomic_andnot(NETBK_RX_EOI, &queue->eoi_pending);
		xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS);
	}

	return IRQ_HANDLED;
}

irqreturn_t xenvif_interrupt(int irq, void *dev_id)
{
	struct xenvif_queue *queue = dev_id;
	int old;

	old = atomic_fetch_or(NETBK_COMMON_EOI, &queue->eoi_pending);
	WARN(old, "Interrupt while EOI pending\n");

	/* Use bitwise or as we need to call both functions. */
	if ((!xenvif_handle_tx_interrupt(queue) |
	     !xenvif_handle_rx_interrupt(queue))) {
		atomic_andnot(NETBK_COMMON_EOI, &queue->eoi_pending);
		xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS);
	}

	return IRQ_HANDLED;
}

int xenvif_queue_stopped(struct xenvif_queue *queue)
{
	struct net_device *dev = queue->vif->dev;
	unsigned int id = queue->id;
	return netif_tx_queue_stopped(netdev_get_tx_queue(dev, id));
}

void xenvif_wake_queue(struct xenvif_queue *queue)
{
	struct net_device *dev = queue->vif->dev;
	unsigned int id = queue->id;
	netif_tx_wake_queue(netdev_get_tx_queue(dev, id));
}

static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
			       struct net_device *sb_dev)
{
	struct xenvif *vif = netdev_priv(dev);
	unsigned int size = vif->hash.size;
	unsigned int num_queues;

	/* If queues are not set up internally - always return 0
	 * as the packet going to be dropped anyway */
	num_queues = READ_ONCE(vif->num_queues);
	if (num_queues < 1)
		return 0;

	if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
		return netdev_pick_tx(dev, skb, NULL) %
		       dev->real_num_tx_queues;

	xenvif_set_skb_hash(vif, skb);

	if (size == 0)
		return skb_get_hash_raw(skb) % dev->real_num_tx_queues;

	return vif->hash.mapping[vif->hash.mapping_sel]
				[skb_get_hash_raw(skb) % size];
}

static netdev_tx_t
xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct xenvif *vif = netdev_priv(dev);
	struct xenvif_queue *queue = NULL;
	unsigned int num_queues;
	u16 index;
	struct xenvif_rx_cb *cb;

	BUG_ON(skb->dev != dev);

	/* Drop the packet if queues are not set up.
	 * This handler should be called inside an RCU read section
	 * so we don't need to enter it here explicitly.
	 */
	num_queues = READ_ONCE(vif->num_queues);
	if (num_queues < 1)
		goto drop;

	/* Obtain the queue to be used to transmit this packet */
	index = skb_get_queue_mapping(skb);
	if (index >= num_queues) {
		pr_warn_ratelimited("Invalid queue %hu for packet on interface %s\n",
				    index, vif->dev->name);
		index %= num_queues;
	}
	queue = &vif->queues[index];

	/* Drop the packet if queue is not ready */
	if (queue->task == NULL ||
	    queue->dealloc_task == NULL ||
	    !xenvif_schedulable(vif))
		goto drop;

	if (vif->multicast_control && skb->pkt_type == PACKET_MULTICAST) {
		struct ethhdr *eth = (struct ethhdr *)skb->data;

		if (!xenvif_mcast_match(vif, eth->h_dest))
			goto drop;
	}

	cb = XENVIF_RX_CB(skb);
	cb->expires = jiffies + vif->drain_timeout;

	/* If there is no hash algorithm configured then make sure there
	 * is no hash information in the socket buffer otherwise it
	 * would be incorrectly forwarded to the frontend.
	 */
	if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
		skb_clear_hash(skb);

	xenvif_rx_queue_tail(queue, skb);
	xenvif_kick_thread(queue);

	return NETDEV_TX_OK;

 drop:
	vif->dev->stats.tx_dropped++;
	dev_kfree_skb(skb);
	return NETDEV_TX_OK;
}

static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
{
	struct xenvif *vif = netdev_priv(dev);
	struct xenvif_queue *queue = NULL;
	unsigned int num_queues;
	u64 rx_bytes = 0;
	u64 rx_packets = 0;
	u64 tx_bytes = 0;
	u64 tx_packets = 0;
	unsigned int index;

	rcu_read_lock();
	num_queues = READ_ONCE(vif->num_queues);

	/* Aggregate tx and rx stats from each queue */
	for (index = 0; index < num_queues; ++index) {
		queue = &vif->queues[index];
		rx_bytes += queue->stats.rx_bytes;
		rx_packets += queue->stats.rx_packets;
		tx_bytes += queue->stats.tx_bytes;
		tx_packets += queue->stats.tx_packets;
	}

	rcu_read_unlock();

	vif->dev->stats.rx_bytes = rx_bytes;
	vif->dev->stats.rx_packets = rx_packets;
	vif->dev->stats.tx_bytes = tx_bytes;
	vif->dev->stats.tx_packets = tx_packets;

	return &vif->dev->stats;
}

static void xenvif_up(struct xenvif *vif)
{
	struct xenvif_queue *queue = NULL;
	unsigned int num_queues = vif->num_queues;
	unsigned int queue_index;

	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
		queue = &vif->queues[queue_index];
		napi_enable(&queue->napi);
		enable_irq(queue->tx_irq);
		if (queue->tx_irq != queue->rx_irq)
			enable_irq(queue->rx_irq);
		xenvif_napi_schedule_or_enable_events(queue);
	}
}

static void xenvif_down(struct xenvif *vif)
{
	struct xenvif_queue *queue = NULL;
	unsigned int num_queues = vif->num_queues;
	unsigned int queue_index;

	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
		queue = &vif->queues[queue_index];
		disable_irq(queue->tx_irq);
		if (queue->tx_irq != queue->rx_irq)
			disable_irq(queue->rx_irq);
		napi_disable(&queue->napi);
		del_timer_sync(&queue->credit_timeout);
	}
}

static int xenvif_open(struct net_device *dev)
{
	struct xenvif *vif = netdev_priv(dev);
	if (test_bit(VIF_STATUS_CONNECTED, &vif->status))
		xenvif_up(vif);
	netif_tx_start_all_queues(dev);
	return 0;
}

static int xenvif_close(struct net_device *dev)
{
	struct xenvif *vif = netdev_priv(dev);
	if (test_bit(VIF_STATUS_CONNECTED, &vif->status))
		xenvif_down(vif);
	netif_tx_stop_all_queues(dev);
	return 0;
}

static int xenvif_change_mtu(struct net_device *dev, int mtu)
{
	struct xenvif *vif = netdev_priv(dev);
	int max = vif->can_sg ? ETH_MAX_MTU - VLAN_ETH_HLEN : ETH_DATA_LEN;

	if (mtu > max)
		return -EINVAL;
	dev->mtu = mtu;
	return 0;
}

static netdev_features_t xenvif_fix_features(struct net_device *dev,
	netdev_features_t features)
{
	struct xenvif *vif = netdev_priv(dev);

	if (!vif->can_sg)
		features &= ~NETIF_F_SG;
	if (~(vif->gso_mask) & GSO_BIT(TCPV4))
		features &= ~NETIF_F_TSO;
	if (~(vif->gso_mask) & GSO_BIT(TCPV6))
		features &= ~NETIF_F_TSO6;
	if (!vif->ip_csum)
		features &= ~NETIF_F_IP_CSUM;
	if (!vif->ipv6_csum)
		features &= ~NETIF_F_IPV6_CSUM;

	return features;
}

static const struct xenvif_stat {
	char name[ETH_GSTRING_LEN];
	u16 offset;
} xenvif_stats[] = {
	{
		"rx_gso_checksum_fixup",
		offsetof(struct xenvif_stats, rx_gso_checksum_fixup)
	},
	/* If (sent != success + fail), there are probably packets never
	 * freed up properly!
	 */
	{
		"tx_zerocopy_sent",
		offsetof(struct xenvif_stats, tx_zerocopy_sent),
	},
	{
		"tx_zerocopy_success",
		offsetof(struct xenvif_stats, tx_zerocopy_success),
	},
	{
		"tx_zerocopy_fail",
		offsetof(struct xenvif_stats, tx_zerocopy_fail)
	},
	/* Number of packets exceeding MAX_SKB_FRAG slots. You should use
	 * a guest with the same MAX_SKB_FRAG
	 */
	{
		"tx_frag_overflow",
		offsetof(struct xenvif_stats, tx_frag_overflow)
	},
};

static int xenvif_get_sset_count(struct net_device *dev, int string_set)
{
	switch (string_set) {
	case ETH_SS_STATS:
		return ARRAY_SIZE(xenvif_stats);
	default:
		return -EINVAL;
	}
}

static void xenvif_get_ethtool_stats(struct net_device *dev,
				     struct ethtool_stats *stats, u64 * data)
{
	struct xenvif *vif = netdev_priv(dev);
	unsigned int num_queues;
	int i;
	unsigned int queue_index;

	rcu_read_lock();
	num_queues = READ_ONCE(vif->num_queues);

	for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) {
		unsigned long accum = 0;
		for (queue_index = 0; queue_index < num_queues; ++queue_index) {
			void *vif_stats = &vif->queues[queue_index].stats;
			accum += *(unsigned long *)(vif_stats + xenvif_stats[i].offset);
		}
		data[i] = accum;
	}

	rcu_read_unlock();
}

static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data)
{
	int i;

	switch (stringset) {
	case ETH_SS_STATS:
		for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
			memcpy(data + i * ETH_GSTRING_LEN,
			       xenvif_stats[i].name, ETH_GSTRING_LEN);
		break;
	}
}

static const struct ethtool_ops xenvif_ethtool_ops = {
	.get_link	= ethtool_op_get_link,

	.get_sset_count = xenvif_get_sset_count,
	.get_ethtool_stats = xenvif_get_ethtool_stats,
	.get_strings = xenvif_get_strings,
};

static const struct net_device_ops xenvif_netdev_ops = {
	.ndo_select_queue = xenvif_select_queue,
	.ndo_start_xmit	= xenvif_start_xmit,
	.ndo_get_stats	= xenvif_get_stats,
	.ndo_open	= xenvif_open,
	.ndo_stop	= xenvif_close,
	.ndo_change_mtu	= xenvif_change_mtu,
	.ndo_fix_features = xenvif_fix_features,
	.ndo_set_mac_address = eth_mac_addr,
	.ndo_validate_addr   = eth_validate_addr,
};

struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
			    unsigned int handle)
{
	int err;
	struct net_device *dev;
	struct xenvif *vif;
	char name[IFNAMSIZ] = {};

	snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle);
	/* Allocate a netdev with the max. supported number of queues.
	 * When the guest selects the desired number, it will be updated
	 * via netif_set_real_num_*_queues().
	 */
	dev = alloc_netdev_mq(sizeof(struct xenvif), name, NET_NAME_UNKNOWN,
			      ether_setup, xenvif_max_queues);
	if (dev == NULL) {
		pr_warn("Could not allocate netdev for %s\n", name);
		return ERR_PTR(-ENOMEM);
	}

	SET_NETDEV_DEV(dev, parent);

	vif = netdev_priv(dev);

	vif->domid  = domid;
	vif->handle = handle;
	vif->can_sg = 1;
	vif->ip_csum = 1;
	vif->dev = dev;
	vif->disabled = false;
	vif->drain_timeout = msecs_to_jiffies(rx_drain_timeout_msecs);
	vif->stall_timeout = msecs_to_jiffies(rx_stall_timeout_msecs);

	/* Start out with no queues. */
	vif->queues = NULL;
	vif->num_queues = 0;

	vif->xdp_headroom = 0;

	spin_lock_init(&vif->lock);
	INIT_LIST_HEAD(&vif->fe_mcast_addr);

	dev->netdev_ops	= &xenvif_netdev_ops;
	dev->hw_features = NETIF_F_SG |
		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
		NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_FRAGLIST;
	dev->features = dev->hw_features | NETIF_F_RXCSUM;
	dev->ethtool_ops = &xenvif_ethtool_ops;

	dev->tx_queue_len = XENVIF_QUEUE_LENGTH;

	dev->min_mtu = ETH_MIN_MTU;
	dev->max_mtu = ETH_MAX_MTU - VLAN_ETH_HLEN;

	/*
	 * Initialise a dummy MAC address. We choose the numerically
	 * largest non-broadcast address to prevent the address getting
	 * stolen by an Ethernet bridge for STP purposes.
	 * (FE:FF:FF:FF:FF:FF)
	 */
	eth_broadcast_addr(dev->dev_addr);
	dev->dev_addr[0] &= ~0x01;

	netif_carrier_off(dev);

	err = register_netdev(dev);
	if (err) {
		netdev_warn(dev, "Could not register device: err=%d\n", err);
		free_netdev(dev);
		return ERR_PTR(err);
	}

	netdev_dbg(dev, "Successfully created xenvif\n");

	__module_get(THIS_MODULE);

	return vif;
}

int xenvif_init_queue(struct xenvif_queue *queue)
{
	int err, i;

	queue->credit_bytes = queue->remaining_credit = ~0UL;
	queue->credit_usec  = 0UL;
	timer_setup(&queue->credit_timeout, xenvif_tx_credit_callback, 0);
	queue->credit_window_start = get_jiffies_64();

	queue->rx_queue_max = XENVIF_RX_QUEUE_BYTES;

	skb_queue_head_init(&queue->rx_queue);
	skb_queue_head_init(&queue->tx_queue);

	queue->pending_cons = 0;
	queue->pending_prod = MAX_PENDING_REQS;
	for (i = 0; i < MAX_PENDING_REQS; ++i)
		queue->pending_ring[i] = i;

	spin_lock_init(&queue->callback_lock);
	spin_lock_init(&queue->response_lock);

	/* If ballooning is disabled, this will consume real memory, so you
	 * better enable it. The long term solution would be to use just a
	 * bunch of valid page descriptors, without dependency on ballooning
	 */
	err = gnttab_alloc_pages(MAX_PENDING_REQS,
				 queue->mmap_pages);
	if (err) {
		netdev_err(queue->vif->dev, "Could not reserve mmap_pages\n");
		return -ENOMEM;
	}

	for (i = 0; i < MAX_PENDING_REQS; i++) {
		queue->pending_tx_info[i].callback_struct = (struct ubuf_info)
			{ .callback = xenvif_zerocopy_callback,
			  { { .ctx = NULL,
			      .desc = i } } };
		queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;
	}

	return 0;
}

void xenvif_carrier_on(struct xenvif *vif)
{
	rtnl_lock();
	if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
		dev_set_mtu(vif->dev, ETH_DATA_LEN);
	netdev_update_features(vif->dev);
	set_bit(VIF_STATUS_CONNECTED, &vif->status);
	if (netif_running(vif->dev))
		xenvif_up(vif);
	rtnl_unlock();
}

int xenvif_connect_ctrl(struct xenvif *vif, grant_ref_t ring_ref,
			unsigned int evtchn)
{
	struct net_device *dev = vif->dev;
	void *addr;
	struct xen_netif_ctrl_sring *shared;
	RING_IDX rsp_prod, req_prod;
	int err;

	err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif),
				     &ring_ref, 1, &addr);
	if (err)
		goto err;

	shared = (struct xen_netif_ctrl_sring *)addr;
	rsp_prod = READ_ONCE(shared->rsp_prod);
	req_prod = READ_ONCE(shared->req_prod);

	BACK_RING_ATTACH(&vif->ctrl, shared, rsp_prod, XEN_PAGE_SIZE);

	err = -EIO;
	if (req_prod - rsp_prod > RING_SIZE(&vif->ctrl))
		goto err_unmap;

	err = bind_interdomain_evtchn_to_irq_lateeoi(vif->domid, evtchn);
	if (err < 0)
		goto err_unmap;

	vif->ctrl_irq = err;

	xenvif_init_hash(vif);

	err = request_threaded_irq(vif->ctrl_irq, NULL, xenvif_ctrl_irq_fn,
				   IRQF_ONESHOT, "xen-netback-ctrl", vif);
	if (err) {
		pr_warn("Could not setup irq handler for %s\n", dev->name);
		goto err_deinit;
	}

	return 0;

err_deinit:
	xenvif_deinit_hash(vif);
	unbind_from_irqhandler(vif->ctrl_irq, vif);
	vif->ctrl_irq = 0;

err_unmap:
	xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
				vif->ctrl.sring);
	vif->ctrl.sring = NULL;

err:
	return err;
}

static void xenvif_disconnect_queue(struct xenvif_queue *queue)
{
	if (queue->task) {
		kthread_stop(queue->task);
		queue->task = NULL;
	}

	if (queue->dealloc_task) {
		kthread_stop(queue->dealloc_task);
		queue->dealloc_task = NULL;
	}

	if (queue->napi.poll) {
		netif_napi_del(&queue->napi);
		queue->napi.poll = NULL;
	}

	if (queue->tx_irq) {
		unbind_from_irqhandler(queue->tx_irq, queue);
		if (queue->tx_irq == queue->rx_irq)
			queue->rx_irq = 0;
		queue->tx_irq = 0;
	}

	if (queue->rx_irq) {
		unbind_from_irqhandler(queue->rx_irq, queue);
		queue->rx_irq = 0;
	}

	xenvif_unmap_frontend_data_rings(queue);
}

int xenvif_connect_data(struct xenvif_queue *queue,
			unsigned long tx_ring_ref,
			unsigned long rx_ring_ref,
			unsigned int tx_evtchn,
			unsigned int rx_evtchn)
{
	struct task_struct *task;
	int err;

	BUG_ON(queue->tx_irq);
	BUG_ON(queue->task);
	BUG_ON(queue->dealloc_task);

	err = xenvif_map_frontend_data_rings(queue, tx_ring_ref,
					     rx_ring_ref);
	if (err < 0)
		goto err;

	init_waitqueue_head(&queue->wq);
	init_waitqueue_head(&queue->dealloc_wq);
	atomic_set(&queue->inflight_packets, 0);

	netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll,
			XENVIF_NAPI_WEIGHT);

	queue->stalled = true;

	task = kthread_run(xenvif_kthread_guest_rx, queue,
			   "%s-guest-rx", queue->name);
	if (IS_ERR(task))
		goto kthread_err;
	queue->task = task;

	task = kthread_run(xenvif_dealloc_kthread, queue,
			   "%s-dealloc", queue->name);
	if (IS_ERR(task))
		goto kthread_err;
	queue->dealloc_task = task;

	if (tx_evtchn == rx_evtchn) {
		/* feature-split-event-channels == 0 */
		err = bind_interdomain_evtchn_to_irqhandler_lateeoi(
			queue->vif->domid, tx_evtchn, xenvif_interrupt, 0,
			queue->name, queue);
		if (err < 0)
			goto err;
		queue->tx_irq = queue->rx_irq = err;
		disable_irq(queue->tx_irq);
	} else {
		/* feature-split-event-channels == 1 */
		snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name),
			 "%s-tx", queue->name);
		err = bind_interdomain_evtchn_to_irqhandler_lateeoi(
			queue->vif->domid, tx_evtchn, xenvif_tx_interrupt, 0,
			queue->tx_irq_name, queue);
		if (err < 0)
			goto err;
		queue->tx_irq = err;
		disable_irq(queue->tx_irq);

		snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name),
			 "%s-rx", queue->name);
		err = bind_interdomain_evtchn_to_irqhandler_lateeoi(
			queue->vif->domid, rx_evtchn, xenvif_rx_interrupt, 0,
			queue->rx_irq_name, queue);
		if (err < 0)
			goto err;
		queue->rx_irq = err;
		disable_irq(queue->rx_irq);
	}

	return 0;

kthread_err:
	pr_warn("Could not allocate kthread for %s\n", queue->name);
	err = PTR_ERR(task);
err:
	xenvif_disconnect_queue(queue);
	return err;
}

void xenvif_carrier_off(struct xenvif *vif)
{
	struct net_device *dev = vif->dev;

	rtnl_lock();
	if (test_and_clear_bit(VIF_STATUS_CONNECTED, &vif->status)) {
		netif_carrier_off(dev); /* discard queued packets */
		if (netif_running(dev))
			xenvif_down(vif);
	}
	rtnl_unlock();
}

void xenvif_disconnect_data(struct xenvif *vif)
{
	struct xenvif_queue *queue = NULL;
	unsigned int num_queues = vif->num_queues;
	unsigned int queue_index;

	xenvif_carrier_off(vif);

	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
		queue = &vif->queues[queue_index];

		xenvif_disconnect_queue(queue);
	}

	xenvif_mcast_addr_list_free(vif);
}

void xenvif_disconnect_ctrl(struct xenvif *vif)
{
	if (vif->ctrl_irq) {
		xenvif_deinit_hash(vif);
		unbind_from_irqhandler(vif->ctrl_irq, vif);
		vif->ctrl_irq = 0;
	}

	if (vif->ctrl.sring) {
		xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
					vif->ctrl.sring);
		vif->ctrl.sring = NULL;
	}
}

/* Reverse the relevant parts of xenvif_init_queue().
 * Used for queue teardown from xenvif_free(), and on the
 * error handling paths in xenbus.c:connect().
 */
void xenvif_deinit_queue(struct xenvif_queue *queue)
{
	gnttab_free_pages(MAX_PENDING_REQS, queue->mmap_pages);
}

void xenvif_free(struct xenvif *vif)
{
	struct xenvif_queue *queues = vif->queues;
	unsigned int num_queues = vif->num_queues;
	unsigned int queue_index;

	unregister_netdev(vif->dev);
	free_netdev(vif->dev);

	for (queue_index = 0; queue_index < num_queues; ++queue_index)
		xenvif_deinit_queue(&queues[queue_index]);
	vfree(queues);

	module_put(THIS_MODULE);
}