aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/virtio_net.c
blob: 2a6e81d5b579aa9032ae633bb80b6444bcf1ae40 (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
/* A simple network driver using virtio.
 *
 * Copyright 2007 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
//#define DEBUG
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/virtio.h>
#include <linux/virtio_net.h>
#include <linux/scatterlist.h>
#include <linux/if_vlan.h>

static int napi_weight = 128;
module_param(napi_weight, int, 0444);

static int csum = 1, gso = 1;
module_param(csum, bool, 0444);
module_param(gso, bool, 0444);

/* FIXME: MTU in config. */
#define MAX_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
#define GOOD_COPY_LEN	128

#define VIRTNET_SEND_COMMAND_SG_MAX    2

struct virtnet_info
{
	struct virtio_device *vdev;
	struct virtqueue *rvq, *svq, *cvq;
	struct net_device *dev;
	struct napi_struct napi;
	unsigned int status;

	/* The skb we couldn't send because buffers were full. */
	struct sk_buff *last_xmit_skb;

	/* If we need to free in a timer, this is it. */
	struct timer_list xmit_free_timer;

	/* Number of input buffers, and max we've ever had. */
	unsigned int num, max;

	/* For cleaning up after transmission. */
	struct tasklet_struct tasklet;
	bool free_in_tasklet;

	/* I like... big packets and I cannot lie! */
	bool big_packets;

	/* Host will merge rx buffers for big packets (shake it! shake it!) */
	bool mergeable_rx_bufs;

	/* Receive & send queues. */
	struct sk_buff_head recv;
	struct sk_buff_head send;

	/* Chain pages by the private ptr. */
	struct page *pages;
};

static inline void *skb_vnet_hdr(struct sk_buff *skb)
{
	return (struct virtio_net_hdr *)skb->cb;
}

static void give_a_page(struct virtnet_info *vi, struct page *page)
{
	page->private = (unsigned long)vi->pages;
	vi->pages = page;
}

static void trim_pages(struct virtnet_info *vi, struct sk_buff *skb)
{
	unsigned int i;

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
		give_a_page(vi, skb_shinfo(skb)->frags[i].page);
	skb_shinfo(skb)->nr_frags = 0;
	skb->data_len = 0;
}

static struct page *get_a_page(struct virtnet_info *vi, gfp_t gfp_mask)
{
	struct page *p = vi->pages;

	if (p)
		vi->pages = (struct page *)p->private;
	else
		p = alloc_page(gfp_mask);
	return p;
}

static void skb_xmit_done(struct virtqueue *svq)
{
	struct virtnet_info *vi = svq->vdev->priv;

	/* Suppress further interrupts. */
	svq->vq_ops->disable_cb(svq);

	/* We were probably waiting for more output buffers. */
	netif_wake_queue(vi->dev);

	/* Make sure we re-xmit last_xmit_skb: if there are no more packets
	 * queued, start_xmit won't be called. */
	tasklet_schedule(&vi->tasklet);
}

static void receive_skb(struct net_device *dev, struct sk_buff *skb,
			unsigned len)
{
	struct virtnet_info *vi = netdev_priv(dev);
	struct virtio_net_hdr *hdr = skb_vnet_hdr(skb);
	int err;
	int i;

	if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) {
		pr_debug("%s: short packet %i\n", dev->name, len);
		dev->stats.rx_length_errors++;
		goto drop;
	}

	if (vi->mergeable_rx_bufs) {
		struct virtio_net_hdr_mrg_rxbuf *mhdr = skb_vnet_hdr(skb);
		unsigned int copy;
		char *p = page_address(skb_shinfo(skb)->frags[0].page);

		if (len > PAGE_SIZE)
			len = PAGE_SIZE;
		len -= sizeof(struct virtio_net_hdr_mrg_rxbuf);

		memcpy(hdr, p, sizeof(*mhdr));
		p += sizeof(*mhdr);

		copy = len;
		if (copy > skb_tailroom(skb))
			copy = skb_tailroom(skb);

		memcpy(skb_put(skb, copy), p, copy);

		len -= copy;

		if (!len) {
			give_a_page(vi, skb_shinfo(skb)->frags[0].page);
			skb_shinfo(skb)->nr_frags--;
		} else {
			skb_shinfo(skb)->frags[0].page_offset +=
				sizeof(*mhdr) + copy;
			skb_shinfo(skb)->frags[0].size = len;
			skb->data_len += len;
			skb->len += len;
		}

		while (--mhdr->num_buffers) {
			struct sk_buff *nskb;

			i = skb_shinfo(skb)->nr_frags;
			if (i >= MAX_SKB_FRAGS) {
				pr_debug("%s: packet too long %d\n", dev->name,
					 len);
				dev->stats.rx_length_errors++;
				goto drop;
			}

			nskb = vi->rvq->vq_ops->get_buf(vi->rvq, &len);
			if (!nskb) {
				pr_debug("%s: rx error: %d buffers missing\n",
					 dev->name, mhdr->num_buffers);
				dev->stats.rx_length_errors++;
				goto drop;
			}

			__skb_unlink(nskb, &vi->recv);
			vi->num--;

			skb_shinfo(skb)->frags[i] = skb_shinfo(nskb)->frags[0];
			skb_shinfo(nskb)->nr_frags = 0;
			kfree_skb(nskb);

			if (len > PAGE_SIZE)
				len = PAGE_SIZE;

			skb_shinfo(skb)->frags[i].size = len;
			skb_shinfo(skb)->nr_frags++;
			skb->data_len += len;
			skb->len += len;
		}
	} else {
		len -= sizeof(struct virtio_net_hdr);

		if (len <= MAX_PACKET_LEN)
			trim_pages(vi, skb);

		err = pskb_trim(skb, len);
		if (err) {
			pr_debug("%s: pskb_trim failed %i %d\n", dev->name,
				 len, err);
			dev->stats.rx_dropped++;
			goto drop;
		}
	}

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

	if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
		pr_debug("Needs csum!\n");
		if (!skb_partial_csum_set(skb,hdr->csum_start,hdr->csum_offset))
			goto frame_err;
	}

	skb->protocol = eth_type_trans(skb, dev);
	pr_debug("Receiving skb proto 0x%04x len %i type %i\n",
		 ntohs(skb->protocol), skb->len, skb->pkt_type);

	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
		pr_debug("GSO!\n");
		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
		case VIRTIO_NET_HDR_GSO_TCPV4:
			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
			break;
		case VIRTIO_NET_HDR_GSO_UDP:
			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
			break;
		case VIRTIO_NET_HDR_GSO_TCPV6:
			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
			break;
		default:
			if (net_ratelimit())
				printk(KERN_WARNING "%s: bad gso type %u.\n",
				       dev->name, hdr->gso_type);
			goto frame_err;
		}

		if (hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
			skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;

		skb_shinfo(skb)->gso_size = hdr->gso_size;
		if (skb_shinfo(skb)->gso_size == 0) {
			if (net_ratelimit())
				printk(KERN_WARNING "%s: zero gso size.\n",
				       dev->name);
			goto frame_err;
		}

		/* Header must be checked, and gso_segs computed. */
		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
		skb_shinfo(skb)->gso_segs = 0;
	}

	netif_receive_skb(skb);
	return;

frame_err:
	dev->stats.rx_frame_errors++;
drop:
	dev_kfree_skb(skb);
}

static void try_fill_recv_maxbufs(struct virtnet_info *vi)
{
	struct sk_buff *skb;
	struct scatterlist sg[2+MAX_SKB_FRAGS];
	int num, err, i;

	sg_init_table(sg, 2+MAX_SKB_FRAGS);
	for (;;) {
		struct virtio_net_hdr *hdr;

		skb = netdev_alloc_skb(vi->dev, MAX_PACKET_LEN + NET_IP_ALIGN);
		if (unlikely(!skb))
			break;

		skb_reserve(skb, NET_IP_ALIGN);
		skb_put(skb, MAX_PACKET_LEN);

		hdr = skb_vnet_hdr(skb);
		sg_set_buf(sg, hdr, sizeof(*hdr));

		if (vi->big_packets) {
			for (i = 0; i < MAX_SKB_FRAGS; i++) {
				skb_frag_t *f = &skb_shinfo(skb)->frags[i];
				f->page = get_a_page(vi, GFP_ATOMIC);
				if (!f->page)
					break;

				f->page_offset = 0;
				f->size = PAGE_SIZE;

				skb->data_len += PAGE_SIZE;
				skb->len += PAGE_SIZE;

				skb_shinfo(skb)->nr_frags++;
			}
		}

		num = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1;
		skb_queue_head(&vi->recv, skb);

		err = vi->rvq->vq_ops->add_buf(vi->rvq, sg, 0, num, skb);
		if (err) {
			skb_unlink(skb, &vi->recv);
			trim_pages(vi, skb);
			kfree_skb(skb);
			break;
		}
		vi->num++;
	}
	if (unlikely(vi->num > vi->max))
		vi->max = vi->num;
	vi->rvq->vq_ops->kick(vi->rvq);
}

static void try_fill_recv(struct virtnet_info *vi)
{
	struct sk_buff *skb;
	struct scatterlist sg[1];
	int err;

	if (!vi->mergeable_rx_bufs) {
		try_fill_recv_maxbufs(vi);
		return;
	}

	for (;;) {
		skb_frag_t *f;

		skb = netdev_alloc_skb(vi->dev, GOOD_COPY_LEN + NET_IP_ALIGN);
		if (unlikely(!skb))
			break;

		skb_reserve(skb, NET_IP_ALIGN);

		f = &skb_shinfo(skb)->frags[0];
		f->page = get_a_page(vi, GFP_ATOMIC);
		if (!f->page) {
			kfree_skb(skb);
			break;
		}

		f->page_offset = 0;
		f->size = PAGE_SIZE;

		skb_shinfo(skb)->nr_frags++;

		sg_init_one(sg, page_address(f->page), PAGE_SIZE);
		skb_queue_head(&vi->recv, skb);

		err = vi->rvq->vq_ops->add_buf(vi->rvq, sg, 0, 1, skb);
		if (err) {
			skb_unlink(skb, &vi->recv);
			kfree_skb(skb);
			break;
		}
		vi->num++;
	}
	if (unlikely(vi->num > vi->max))
		vi->max = vi->num;
	vi->rvq->vq_ops->kick(vi->rvq);
}

static void skb_recv_done(struct virtqueue *rvq)
{
	struct virtnet_info *vi = rvq->vdev->priv;
	/* Schedule NAPI, Suppress further interrupts if successful. */
	if (napi_schedule_prep(&vi->napi)) {
		rvq->vq_ops->disable_cb(rvq);
		__napi_schedule(&vi->napi);
	}
}

static int virtnet_poll(struct napi_struct *napi, int budget)
{
	struct virtnet_info *vi = container_of(napi, struct virtnet_info, napi);
	struct sk_buff *skb = NULL;
	unsigned int len, received = 0;

again:
	while (received < budget &&
	       (skb = vi->rvq->vq_ops->get_buf(vi->rvq, &len)) != NULL) {
		__skb_unlink(skb, &vi->recv);
		receive_skb(vi->dev, skb, len);
		vi->num--;
		received++;
	}

	/* FIXME: If we oom and completely run out of inbufs, we need
	 * to start a timer trying to fill more. */
	if (vi->num < vi->max / 2)
		try_fill_recv(vi);

	/* Out of packets? */
	if (received < budget) {
		napi_complete(napi);
		if (unlikely(!vi->rvq->vq_ops->enable_cb(vi->rvq))
		    && napi_schedule_prep(napi)) {
			vi->rvq->vq_ops->disable_cb(vi->rvq);
			__napi_schedule(napi);
			goto again;
		}
	}

	return received;
}

static void free_old_xmit_skbs(struct virtnet_info *vi)
{
	struct sk_buff *skb;
	unsigned int len;

	while ((skb = vi->svq->vq_ops->get_buf(vi->svq, &len)) != NULL) {
		pr_debug("Sent skb %p\n", skb);
		__skb_unlink(skb, &vi->send);
		vi->dev->stats.tx_bytes += skb->len;
		vi->dev->stats.tx_packets++;
		kfree_skb(skb);
	}
}

/* If the virtio transport doesn't always notify us when all in-flight packets
 * are consumed, we fall back to using this function on a timer to free them. */
static void xmit_free(unsigned long data)
{
	struct virtnet_info *vi = (void *)data;

	netif_tx_lock(vi->dev);

	free_old_xmit_skbs(vi);

	if (!skb_queue_empty(&vi->send))
		mod_timer(&vi->xmit_free_timer, jiffies + (HZ/10));

	netif_tx_unlock(vi->dev);
}

static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
{
	int num, err;
	struct scatterlist sg[2+MAX_SKB_FRAGS];
	struct virtio_net_hdr_mrg_rxbuf *mhdr = skb_vnet_hdr(skb);
	struct virtio_net_hdr *hdr = skb_vnet_hdr(skb);
	const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;

	sg_init_table(sg, 2+MAX_SKB_FRAGS);

	pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);

	if (skb->ip_summed == CHECKSUM_PARTIAL) {
		hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
		hdr->csum_start = skb->csum_start - skb_headroom(skb);
		hdr->csum_offset = skb->csum_offset;
	} else {
		hdr->flags = 0;
		hdr->csum_offset = hdr->csum_start = 0;
	}

	if (skb_is_gso(skb)) {
		hdr->hdr_len = skb_headlen(skb);
		hdr->gso_size = skb_shinfo(skb)->gso_size;
		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
			hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
			hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
		else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
			hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
		else
			BUG();
		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN)
			hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
	} else {
		hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
		hdr->gso_size = hdr->hdr_len = 0;
	}

	mhdr->num_buffers = 0;

	/* Encode metadata header at front. */
	if (vi->mergeable_rx_bufs)
		sg_set_buf(sg, mhdr, sizeof(*mhdr));
	else
		sg_set_buf(sg, hdr, sizeof(*hdr));

	num = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1;

	err = vi->svq->vq_ops->add_buf(vi->svq, sg, num, 0, skb);
	if (!err && !vi->free_in_tasklet)
		mod_timer(&vi->xmit_free_timer, jiffies + (HZ/10));

	return err;
}

static void xmit_tasklet(unsigned long data)
{
	struct virtnet_info *vi = (void *)data;

	netif_tx_lock_bh(vi->dev);
	if (vi->last_xmit_skb && xmit_skb(vi, vi->last_xmit_skb) == 0) {
		vi->svq->vq_ops->kick(vi->svq);
		vi->last_xmit_skb = NULL;
	}
	if (vi->free_in_tasklet)
		free_old_xmit_skbs(vi);
	netif_tx_unlock_bh(vi->dev);
}

static int start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);

again:
	/* Free up any pending old buffers before queueing new ones. */
	free_old_xmit_skbs(vi);

	/* If we has a buffer left over from last time, send it now. */
	if (unlikely(vi->last_xmit_skb) &&
	    xmit_skb(vi, vi->last_xmit_skb) != 0)
		goto stop_queue;

	vi->last_xmit_skb = NULL;

	/* Put new one in send queue and do transmit */
	if (likely(skb)) {
		__skb_queue_head(&vi->send, skb);
		if (xmit_skb(vi, skb) != 0) {
			vi->last_xmit_skb = skb;
			skb = NULL;
			goto stop_queue;
		}
	}
done:
	vi->svq->vq_ops->kick(vi->svq);
	return NETDEV_TX_OK;

stop_queue:
	pr_debug("%s: virtio not prepared to send\n", dev->name);
	netif_stop_queue(dev);

	/* Activate callback for using skbs: if this returns false it
	 * means some were used in the meantime. */
	if (unlikely(!vi->svq->vq_ops->enable_cb(vi->svq))) {
		vi->svq->vq_ops->disable_cb(vi->svq);
		netif_start_queue(dev);
		goto again;
	}
	if (skb) {
		/* Drop this skb: we only queue one. */
		vi->dev->stats.tx_dropped++;
		kfree_skb(skb);
	}
	goto done;
}

static int virtnet_set_mac_address(struct net_device *dev, void *p)
{
	struct virtnet_info *vi = netdev_priv(dev);
	struct virtio_device *vdev = vi->vdev;
	int ret;

	ret = eth_mac_addr(dev, p);
	if (ret)
		return ret;

	if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC))
		vdev->config->set(vdev, offsetof(struct virtio_net_config, mac),
		                  dev->dev_addr, dev->addr_len);

	return 0;
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void virtnet_netpoll(struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);

	napi_schedule(&vi->napi);
}
#endif

static int virtnet_open(struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);

	napi_enable(&vi->napi);

	/* If all buffers were filled by other side before we napi_enabled, we
	 * won't get another interrupt, so process any outstanding packets
	 * now.  virtnet_poll wants re-enable the queue, so we disable here.
	 * We synchronize against interrupts via NAPI_STATE_SCHED */
	if (napi_schedule_prep(&vi->napi)) {
		vi->rvq->vq_ops->disable_cb(vi->rvq);
		__napi_schedule(&vi->napi);
	}
	return 0;
}

/*
 * Send command via the control virtqueue and check status.  Commands
 * supported by the hypervisor, as indicated by feature bits, should
 * never fail unless improperly formated.
 */
static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
				 struct scatterlist *data, int out, int in)
{
	struct scatterlist *s, sg[VIRTNET_SEND_COMMAND_SG_MAX + 2];
	struct virtio_net_ctrl_hdr ctrl;
	virtio_net_ctrl_ack status = ~0;
	unsigned int tmp;
	int i;

	/* Caller should know better */
	BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ||
		(out + in > VIRTNET_SEND_COMMAND_SG_MAX));

	out++; /* Add header */
	in++; /* Add return status */

	ctrl.class = class;
	ctrl.cmd = cmd;

	sg_init_table(sg, out + in);

	sg_set_buf(&sg[0], &ctrl, sizeof(ctrl));
	for_each_sg(data, s, out + in - 2, i)
		sg_set_buf(&sg[i + 1], sg_virt(s), s->length);
	sg_set_buf(&sg[out + in - 1], &status, sizeof(status));

	BUG_ON(vi->cvq->vq_ops->add_buf(vi->cvq, sg, out, in, vi));

	vi->cvq->vq_ops->kick(vi->cvq);

	/*
	 * Spin for a response, the kick causes an ioport write, trapping
	 * into the hypervisor, so the request should be handled immediately.
	 */
	while (!vi->cvq->vq_ops->get_buf(vi->cvq, &tmp))
		cpu_relax();

	return status == VIRTIO_NET_OK;
}

static int virtnet_close(struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);

	napi_disable(&vi->napi);

	return 0;
}

static int virtnet_set_tx_csum(struct net_device *dev, u32 data)
{
	struct virtnet_info *vi = netdev_priv(dev);
	struct virtio_device *vdev = vi->vdev;

	if (data && !virtio_has_feature(vdev, VIRTIO_NET_F_CSUM))
		return -ENOSYS;

	return ethtool_op_set_tx_hw_csum(dev, data);
}

static void virtnet_set_rx_mode(struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);
	struct scatterlist sg[2];
	u8 promisc, allmulti;
	struct virtio_net_ctrl_mac *mac_data;
	struct dev_addr_list *addr;
	struct netdev_hw_addr *ha;
	void *buf;
	int i;

	/* We can't dynamicaly set ndo_set_rx_mode, so return gracefully */
	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
		return;

	promisc = ((dev->flags & IFF_PROMISC) != 0);
	allmulti = ((dev->flags & IFF_ALLMULTI) != 0);

	sg_init_one(sg, &promisc, sizeof(promisc));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
				  VIRTIO_NET_CTRL_RX_PROMISC,
				  sg, 1, 0))
		dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
			 promisc ? "en" : "dis");

	sg_init_one(sg, &allmulti, sizeof(allmulti));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
				  VIRTIO_NET_CTRL_RX_ALLMULTI,
				  sg, 1, 0))
		dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
			 allmulti ? "en" : "dis");

	/* MAC filter - use one buffer for both lists */
	mac_data = buf = kzalloc(((dev->uc.count + dev->mc_count) * ETH_ALEN) +
				 (2 * sizeof(mac_data->entries)), GFP_ATOMIC);
	if (!buf) {
		dev_warn(&dev->dev, "No memory for MAC address buffer\n");
		return;
	}

	sg_init_table(sg, 2);

	/* Store the unicast list and count in the front of the buffer */
	mac_data->entries = dev->uc.count;
	i = 0;
	list_for_each_entry(ha, &dev->uc.list, list)
		memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);

	sg_set_buf(&sg[0], mac_data,
		   sizeof(mac_data->entries) + (dev->uc.count * ETH_ALEN));

	/* multicast list and count fill the end */
	mac_data = (void *)&mac_data->macs[dev->uc.count][0];

	mac_data->entries = dev->mc_count;
	addr = dev->mc_list;
	for (i = 0; i < dev->mc_count; i++, addr = addr->next)
		memcpy(&mac_data->macs[i][0], addr->da_addr, ETH_ALEN);

	sg_set_buf(&sg[1], mac_data,
		   sizeof(mac_data->entries) + (dev->mc_count * ETH_ALEN));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC,
				  VIRTIO_NET_CTRL_MAC_TABLE_SET,
				  sg, 2, 0))
		dev_warn(&dev->dev, "Failed to set MAC fitler table.\n");

	kfree(buf);
}

static void virtnet_vlan_rx_add_vid(struct net_device *dev, u16 vid)
{
	struct virtnet_info *vi = netdev_priv(dev);
	struct scatterlist sg;

	sg_init_one(&sg, &vid, sizeof(vid));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
				  VIRTIO_NET_CTRL_VLAN_ADD, &sg, 1, 0))
		dev_warn(&dev->dev, "Failed to add VLAN ID %d.\n", vid);
}

static void virtnet_vlan_rx_kill_vid(struct net_device *dev, u16 vid)
{
	struct virtnet_info *vi = netdev_priv(dev);
	struct scatterlist sg;

	sg_init_one(&sg, &vid, sizeof(vid));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
				  VIRTIO_NET_CTRL_VLAN_DEL, &sg, 1, 0))
		dev_warn(&dev->dev, "Failed to kill VLAN ID %d.\n", vid);
}

static struct ethtool_ops virtnet_ethtool_ops = {
	.set_tx_csum = virtnet_set_tx_csum,
	.set_sg = ethtool_op_set_sg,
	.set_tso = ethtool_op_set_tso,
	.get_link = ethtool_op_get_link,
};

#define MIN_MTU 68
#define MAX_MTU 65535

static int virtnet_change_mtu(struct net_device *dev, int new_mtu)
{
	if (new_mtu < MIN_MTU || new_mtu > MAX_MTU)
		return -EINVAL;
	dev->mtu = new_mtu;
	return 0;
}

static const struct net_device_ops virtnet_netdev = {
	.ndo_open            = virtnet_open,
	.ndo_stop   	     = virtnet_close,
	.ndo_start_xmit      = start_xmit,
	.ndo_validate_addr   = eth_validate_addr,
	.ndo_set_mac_address = virtnet_set_mac_address,
	.ndo_set_rx_mode     = virtnet_set_rx_mode,
	.ndo_change_mtu	     = virtnet_change_mtu,
	.ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid,
	.ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller = virtnet_netpoll,
#endif
};

static void virtnet_update_status(struct virtnet_info *vi)
{
	u16 v;

	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS))
		return;

	vi->vdev->config->get(vi->vdev,
			      offsetof(struct virtio_net_config, status),
			      &v, sizeof(v));

	/* Ignore unknown (future) status bits */
	v &= VIRTIO_NET_S_LINK_UP;

	if (vi->status == v)
		return;

	vi->status = v;

	if (vi->status & VIRTIO_NET_S_LINK_UP) {
		netif_carrier_on(vi->dev);
		netif_wake_queue(vi->dev);
	} else {
		netif_carrier_off(vi->dev);
		netif_stop_queue(vi->dev);
	}
}

static void virtnet_config_changed(struct virtio_device *vdev)
{
	struct virtnet_info *vi = vdev->priv;

	virtnet_update_status(vi);
}

static int virtnet_probe(struct virtio_device *vdev)
{
	int err;
	struct net_device *dev;
	struct virtnet_info *vi;
	struct virtqueue *vqs[3];
	vq_callback_t *callbacks[] = { skb_recv_done, skb_xmit_done, NULL};
	const char *names[] = { "input", "output", "control" };
	int nvqs;

	/* Allocate ourselves a network device with room for our info */
	dev = alloc_etherdev(sizeof(struct virtnet_info));
	if (!dev)
		return -ENOMEM;

	/* Set up network device as normal. */
	dev->netdev_ops = &virtnet_netdev;
	dev->features = NETIF_F_HIGHDMA;
	SET_ETHTOOL_OPS(dev, &virtnet_ethtool_ops);
	SET_NETDEV_DEV(dev, &vdev->dev);

	/* Do we support "hardware" checksums? */
	if (csum && virtio_has_feature(vdev, VIRTIO_NET_F_CSUM)) {
		/* This opens up the world of extra features. */
		dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
		if (gso && virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) {
			dev->features |= NETIF_F_TSO | NETIF_F_UFO
				| NETIF_F_TSO_ECN | NETIF_F_TSO6;
		}
		/* Individual feature bits: what can host handle? */
		if (gso && virtio_has_feature(vdev, VIRTIO_NET_F_HOST_TSO4))
			dev->features |= NETIF_F_TSO;
		if (gso && virtio_has_feature(vdev, VIRTIO_NET_F_HOST_TSO6))
			dev->features |= NETIF_F_TSO6;
		if (gso && virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN))
			dev->features |= NETIF_F_TSO_ECN;
		if (gso && virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UFO))
			dev->features |= NETIF_F_UFO;
	}

	/* Configuration may specify what MAC to use.  Otherwise random. */
	if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) {
		vdev->config->get(vdev,
				  offsetof(struct virtio_net_config, mac),
				  dev->dev_addr, dev->addr_len);
	} else
		random_ether_addr(dev->dev_addr);

	/* Set up our device-specific information */
	vi = netdev_priv(dev);
	netif_napi_add(dev, &vi->napi, virtnet_poll, napi_weight);
	vi->dev = dev;
	vi->vdev = vdev;
	vdev->priv = vi;
	vi->pages = NULL;

	/* If they give us a callback when all buffers are done, we don't need
	 * the timer. */
	vi->free_in_tasklet = virtio_has_feature(vdev,VIRTIO_F_NOTIFY_ON_EMPTY);

	/* If we can receive ANY GSO packets, we must allocate large ones. */
	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4)
	    || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6)
	    || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
		vi->big_packets = true;

	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
		vi->mergeable_rx_bufs = true;

	/* We expect two virtqueues, receive then send,
	 * and optionally control. */
	nvqs = virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ? 3 : 2;

	err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names);
	if (err)
		goto free;

	vi->rvq = vqs[0];
	vi->svq = vqs[1];

	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
		vi->cvq = vqs[2];

		if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN))
			dev->features |= NETIF_F_HW_VLAN_FILTER;
	}

	/* Initialize our empty receive and send queues. */
	skb_queue_head_init(&vi->recv);
	skb_queue_head_init(&vi->send);

	tasklet_init(&vi->tasklet, xmit_tasklet, (unsigned long)vi);

	if (!vi->free_in_tasklet)
		setup_timer(&vi->xmit_free_timer, xmit_free, (unsigned long)vi);

	err = register_netdev(dev);
	if (err) {
		pr_debug("virtio_net: registering device failed\n");
		goto free_vqs;
	}

	/* Last of all, set up some receive buffers. */
	try_fill_recv(vi);

	/* If we didn't even get one input buffer, we're useless. */
	if (vi->num == 0) {
		err = -ENOMEM;
		goto unregister;
	}

	vi->status = VIRTIO_NET_S_LINK_UP;
	virtnet_update_status(vi);
	netif_carrier_on(dev);

	pr_debug("virtnet: registered device %s\n", dev->name);
	return 0;

unregister:
	unregister_netdev(dev);
free_vqs:
	vdev->config->del_vqs(vdev);
free:
	free_netdev(dev);
	return err;
}

static void virtnet_remove(struct virtio_device *vdev)
{
	struct virtnet_info *vi = vdev->priv;
	struct sk_buff *skb;

	/* Stop all the virtqueues. */
	vdev->config->reset(vdev);

	if (!vi->free_in_tasklet)
		del_timer_sync(&vi->xmit_free_timer);

	/* Free our skbs in send and recv queues, if any. */
	while ((skb = __skb_dequeue(&vi->recv)) != NULL) {
		kfree_skb(skb);
		vi->num--;
	}
	__skb_queue_purge(&vi->send);

	BUG_ON(vi->num != 0);

	unregister_netdev(vi->dev);

	vdev->config->del_vqs(vi->vdev);

	while (vi->pages)
		__free_pages(get_a_page(vi, GFP_KERNEL), 0);

	free_netdev(vi->dev);
}

static struct virtio_device_id id_table[] = {
	{ VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID },
	{ 0 },
};

static unsigned int features[] = {
	VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM,
	VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC,
	VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6,
	VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
	VIRTIO_NET_F_GUEST_ECN, /* We don't yet handle UFO input. */
	VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ,
	VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN,
	VIRTIO_F_NOTIFY_ON_EMPTY,
};

static struct virtio_driver virtio_net = {
	.feature_table = features,
	.feature_table_size = ARRAY_SIZE(features),
	.driver.name =	KBUILD_MODNAME,
	.driver.owner =	THIS_MODULE,
	.id_table =	id_table,
	.probe =	virtnet_probe,
	.remove =	__devexit_p(virtnet_remove),
	.config_changed = virtnet_config_changed,
};

static int __init init(void)
{
	return register_virtio_driver(&virtio_net);
}

static void __exit fini(void)
{
	unregister_virtio_driver(&virtio_net);
}
module_init(init);
module_exit(fini);

MODULE_DEVICE_TABLE(virtio, id_table);
MODULE_DESCRIPTION("Virtio network driver");
MODULE_LICENSE("GPL");