summaryrefslogtreecommitdiffstats
path: root/drivers/net/hyperv/netvsc_drv.c
blob: 31e55fba7cadd03d9e19221139727272b9eeec77 (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
/*
 * Copyright (c) 2009, Microsoft Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope 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, see <http://www.gnu.org/licenses/>.
 *
 * Authors:
 *   Haiyang Zhang <haiyangz@microsoft.com>
 *   Hank Janssen  <hjanssen@microsoft.com>
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/init.h>
#include <linux/atomic.h>
#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/device.h>
#include <linux/io.h>
#include <linux/delay.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/if_vlan.h>
#include <linux/in.h>
#include <linux/slab.h>
#include <net/arp.h>
#include <net/route.h>
#include <net/sock.h>
#include <net/pkt_sched.h>

#include "hyperv_net.h"

struct net_device_context {
	/* point back to our device context */
	struct hv_device *device_ctx;
	struct delayed_work dwork;
	struct work_struct work;
};

#define RING_SIZE_MIN 64
static int ring_size = 128;
module_param(ring_size, int, S_IRUGO);
MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");

static void do_set_multicast(struct work_struct *w)
{
	struct net_device_context *ndevctx =
		container_of(w, struct net_device_context, work);
	struct netvsc_device *nvdev;
	struct rndis_device *rdev;

	nvdev = hv_get_drvdata(ndevctx->device_ctx);
	if (nvdev == NULL || nvdev->ndev == NULL)
		return;

	rdev = nvdev->extension;
	if (rdev == NULL)
		return;

	if (nvdev->ndev->flags & IFF_PROMISC)
		rndis_filter_set_packet_filter(rdev,
			NDIS_PACKET_TYPE_PROMISCUOUS);
	else
		rndis_filter_set_packet_filter(rdev,
			NDIS_PACKET_TYPE_BROADCAST |
			NDIS_PACKET_TYPE_ALL_MULTICAST |
			NDIS_PACKET_TYPE_DIRECTED);
}

static void netvsc_set_multicast_list(struct net_device *net)
{
	struct net_device_context *net_device_ctx = netdev_priv(net);

	schedule_work(&net_device_ctx->work);
}

static int netvsc_open(struct net_device *net)
{
	struct net_device_context *net_device_ctx = netdev_priv(net);
	struct hv_device *device_obj = net_device_ctx->device_ctx;
	struct netvsc_device *nvdev;
	struct rndis_device *rdev;
	int ret = 0;

	netif_carrier_off(net);

	/* Open up the device */
	ret = rndis_filter_open(device_obj);
	if (ret != 0) {
		netdev_err(net, "unable to open device (ret %d).\n", ret);
		return ret;
	}

	netif_start_queue(net);

	nvdev = hv_get_drvdata(device_obj);
	rdev = nvdev->extension;
	if (!rdev->link_state)
		netif_carrier_on(net);

	return ret;
}

static int netvsc_close(struct net_device *net)
{
	struct net_device_context *net_device_ctx = netdev_priv(net);
	struct hv_device *device_obj = net_device_ctx->device_ctx;
	int ret;

	netif_tx_disable(net);

	/* Make sure netvsc_set_multicast_list doesn't re-enable filter! */
	cancel_work_sync(&net_device_ctx->work);
	ret = rndis_filter_close(device_obj);
	if (ret != 0)
		netdev_err(net, "unable to close device (ret %d).\n", ret);

	return ret;
}

static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size,
				int pkt_type)
{
	struct rndis_packet *rndis_pkt;
	struct rndis_per_packet_info *ppi;

	rndis_pkt = &msg->msg.pkt;
	rndis_pkt->data_offset += ppi_size;

	ppi = (struct rndis_per_packet_info *)((void *)rndis_pkt +
		rndis_pkt->per_pkt_info_offset + rndis_pkt->per_pkt_info_len);

	ppi->size = ppi_size;
	ppi->type = pkt_type;
	ppi->ppi_offset = sizeof(struct rndis_per_packet_info);

	rndis_pkt->per_pkt_info_len += ppi_size;

	return ppi;
}

static void netvsc_xmit_completion(void *context)
{
	struct hv_netvsc_packet *packet = (struct hv_netvsc_packet *)context;
	struct sk_buff *skb = (struct sk_buff *)
		(unsigned long)packet->completion.send.send_completion_tid;

	kfree(packet);

	if (skb)
		dev_kfree_skb_any(skb);
}

static u32 fill_pg_buf(struct page *page, u32 offset, u32 len,
			struct hv_page_buffer *pb)
{
	int j = 0;

	/* Deal with compund pages by ignoring unused part
	 * of the page.
	 */
	page += (offset >> PAGE_SHIFT);
	offset &= ~PAGE_MASK;

	while (len > 0) {
		unsigned long bytes;

		bytes = PAGE_SIZE - offset;
		if (bytes > len)
			bytes = len;
		pb[j].pfn = page_to_pfn(page);
		pb[j].offset = offset;
		pb[j].len = bytes;

		offset += bytes;
		len -= bytes;

		if (offset == PAGE_SIZE && len) {
			page++;
			offset = 0;
			j++;
		}
	}

	return j + 1;
}

static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
			   struct hv_page_buffer *pb)
{
	u32 slots_used = 0;
	char *data = skb->data;
	int frags = skb_shinfo(skb)->nr_frags;
	int i;

	/* The packet is laid out thus:
	 * 1. hdr
	 * 2. skb linear data
	 * 3. skb fragment data
	 */
	if (hdr != NULL)
		slots_used += fill_pg_buf(virt_to_page(hdr),
					offset_in_page(hdr),
					len, &pb[slots_used]);

	slots_used += fill_pg_buf(virt_to_page(data),
				offset_in_page(data),
				skb_headlen(skb), &pb[slots_used]);

	for (i = 0; i < frags; i++) {
		skb_frag_t *frag = skb_shinfo(skb)->frags + i;

		slots_used += fill_pg_buf(skb_frag_page(frag),
					frag->page_offset,
					skb_frag_size(frag), &pb[slots_used]);
	}
	return slots_used;
}

static int count_skb_frag_slots(struct sk_buff *skb)
{
	int i, frags = skb_shinfo(skb)->nr_frags;
	int pages = 0;

	for (i = 0; i < frags; i++) {
		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
		unsigned long size = skb_frag_size(frag);
		unsigned long offset = frag->page_offset;

		/* Skip unused frames from start of page */
		offset &= ~PAGE_MASK;
		pages += PFN_UP(offset + size);
	}
	return pages;
}

static int netvsc_get_slots(struct sk_buff *skb)
{
	char *data = skb->data;
	unsigned int offset = offset_in_page(data);
	unsigned int len = skb_headlen(skb);
	int slots;
	int frag_slots;

	slots = DIV_ROUND_UP(offset + len, PAGE_SIZE);
	frag_slots = count_skb_frag_slots(skb);
	return slots + frag_slots;
}

static u32 get_net_transport_info(struct sk_buff *skb, u32 *trans_off)
{
	u32 ret_val = TRANSPORT_INFO_NOT_IP;

	if ((eth_hdr(skb)->h_proto != htons(ETH_P_IP)) &&
		(eth_hdr(skb)->h_proto != htons(ETH_P_IPV6))) {
		goto not_ip;
	}

	*trans_off = skb_transport_offset(skb);

	if ((eth_hdr(skb)->h_proto == htons(ETH_P_IP))) {
		struct iphdr *iphdr = ip_hdr(skb);

		if (iphdr->protocol == IPPROTO_TCP)
			ret_val = TRANSPORT_INFO_IPV4_TCP;
		else if (iphdr->protocol == IPPROTO_UDP)
			ret_val = TRANSPORT_INFO_IPV4_UDP;
	} else {
		if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
			ret_val = TRANSPORT_INFO_IPV6_TCP;
		else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)
			ret_val = TRANSPORT_INFO_IPV6_UDP;
	}

not_ip:
	return ret_val;
}

static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
{
	struct net_device_context *net_device_ctx = netdev_priv(net);
	struct hv_netvsc_packet *packet;
	int ret;
	unsigned int num_data_pgs;
	struct rndis_message *rndis_msg;
	struct rndis_packet *rndis_pkt;
	u32 rndis_msg_size;
	bool isvlan;
	struct rndis_per_packet_info *ppi;
	struct ndis_tcp_ip_checksum_info *csum_info;
	struct ndis_tcp_lso_info *lso_info;
	int  hdr_offset;
	u32 net_trans_info;


	/* We will atmost need two pages to describe the rndis
	 * header. We can only transmit MAX_PAGE_BUFFER_COUNT number
	 * of pages in a single packet.
	 */
	num_data_pgs = netvsc_get_slots(skb) + 2;
	if (num_data_pgs > MAX_PAGE_BUFFER_COUNT) {
		netdev_err(net, "Packet too big: %u\n", skb->len);
		dev_kfree_skb(skb);
		net->stats.tx_dropped++;
		return NETDEV_TX_OK;
	}

	/* Allocate a netvsc packet based on # of frags. */
	packet = kzalloc(sizeof(struct hv_netvsc_packet) +
			 (num_data_pgs * sizeof(struct hv_page_buffer)) +
			 sizeof(struct rndis_message) +
			 NDIS_VLAN_PPI_SIZE +
			 NDIS_CSUM_PPI_SIZE +
			 NDIS_LSO_PPI_SIZE, GFP_ATOMIC);
	if (!packet) {
		/* out of memory, drop packet */
		netdev_err(net, "unable to allocate hv_netvsc_packet\n");

		dev_kfree_skb(skb);
		net->stats.tx_dropped++;
		return NETDEV_TX_OK;
	}

	packet->vlan_tci = skb->vlan_tci;

	packet->is_data_pkt = true;
	packet->total_data_buflen = skb->len;

	packet->rndis_msg = (struct rndis_message *)((unsigned long)packet +
				sizeof(struct hv_netvsc_packet) +
				(num_data_pgs * sizeof(struct hv_page_buffer)));

	/* Set the completion routine */
	packet->completion.send.send_completion = netvsc_xmit_completion;
	packet->completion.send.send_completion_ctx = packet;
	packet->completion.send.send_completion_tid = (unsigned long)skb;

	isvlan = packet->vlan_tci & VLAN_TAG_PRESENT;

	/* Add the rndis header */
	rndis_msg = packet->rndis_msg;
	rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET;
	rndis_msg->msg_len = packet->total_data_buflen;
	rndis_pkt = &rndis_msg->msg.pkt;
	rndis_pkt->data_offset = sizeof(struct rndis_packet);
	rndis_pkt->data_len = packet->total_data_buflen;
	rndis_pkt->per_pkt_info_offset = sizeof(struct rndis_packet);

	rndis_msg_size = RNDIS_MESSAGE_SIZE(struct rndis_packet);

	if (isvlan) {
		struct ndis_pkt_8021q_info *vlan;

		rndis_msg_size += NDIS_VLAN_PPI_SIZE;
		ppi = init_ppi_data(rndis_msg, NDIS_VLAN_PPI_SIZE,
					IEEE_8021Q_INFO);
		vlan = (struct ndis_pkt_8021q_info *)((void *)ppi +
						ppi->ppi_offset);
		vlan->vlanid = packet->vlan_tci & VLAN_VID_MASK;
		vlan->pri = (packet->vlan_tci & VLAN_PRIO_MASK) >>
				VLAN_PRIO_SHIFT;
	}

	net_trans_info = get_net_transport_info(skb, &hdr_offset);
	if (net_trans_info == TRANSPORT_INFO_NOT_IP)
		goto do_send;

	/*
	 * Setup the sendside checksum offload only if this is not a
	 * GSO packet.
	 */
	if (skb_is_gso(skb))
		goto do_lso;

	rndis_msg_size += NDIS_CSUM_PPI_SIZE;
	ppi = init_ppi_data(rndis_msg, NDIS_CSUM_PPI_SIZE,
			    TCPIP_CHKSUM_PKTINFO);

	csum_info = (struct ndis_tcp_ip_checksum_info *)((void *)ppi +
			ppi->ppi_offset);

	if (net_trans_info & (INFO_IPV4 << 16))
		csum_info->transmit.is_ipv4 = 1;
	else
		csum_info->transmit.is_ipv6 = 1;

	if (net_trans_info & INFO_TCP) {
		csum_info->transmit.tcp_checksum = 1;
		csum_info->transmit.tcp_header_offset = hdr_offset;
	} else if (net_trans_info & INFO_UDP) {
		/* UDP checksum offload is not supported on ws2008r2.
		 * Furthermore, on ws2012 and ws2012r2, there are some
		 * issues with udp checksum offload from Linux guests.
		 * (these are host issues).
		 * For now compute the checksum here.
		 */
		struct udphdr *uh;
		u16 udp_len;

		ret = skb_cow_head(skb, 0);
		if (ret)
			goto drop;

		uh = udp_hdr(skb);
		udp_len = ntohs(uh->len);
		uh->check = 0;
		uh->check = csum_tcpudp_magic(ip_hdr(skb)->saddr,
					      ip_hdr(skb)->daddr,
					      udp_len, IPPROTO_UDP,
					      csum_partial(uh, udp_len, 0));
		if (uh->check == 0)
			uh->check = CSUM_MANGLED_0;

		csum_info->transmit.udp_checksum = 0;
	}
	goto do_send;

do_lso:
	rndis_msg_size += NDIS_LSO_PPI_SIZE;
	ppi = init_ppi_data(rndis_msg, NDIS_LSO_PPI_SIZE,
			    TCP_LARGESEND_PKTINFO);

	lso_info = (struct ndis_tcp_lso_info *)((void *)ppi +
			ppi->ppi_offset);

	lso_info->lso_v2_transmit.type = NDIS_TCP_LARGE_SEND_OFFLOAD_V2_TYPE;
	if (net_trans_info & (INFO_IPV4 << 16)) {
		lso_info->lso_v2_transmit.ip_version =
			NDIS_TCP_LARGE_SEND_OFFLOAD_IPV4;
		ip_hdr(skb)->tot_len = 0;
		ip_hdr(skb)->check = 0;
		tcp_hdr(skb)->check =
		~csum_tcpudp_magic(ip_hdr(skb)->saddr,
				   ip_hdr(skb)->daddr, 0, IPPROTO_TCP, 0);
	} else {
		lso_info->lso_v2_transmit.ip_version =
			NDIS_TCP_LARGE_SEND_OFFLOAD_IPV6;
		ipv6_hdr(skb)->payload_len = 0;
		tcp_hdr(skb)->check =
		~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
				&ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0);
	}
	lso_info->lso_v2_transmit.tcp_header_offset = hdr_offset;
	lso_info->lso_v2_transmit.mss = skb_shinfo(skb)->gso_size;

do_send:
	/* Start filling in the page buffers with the rndis hdr */
	rndis_msg->msg_len += rndis_msg_size;
	packet->page_buf_cnt = init_page_array(rndis_msg, rndis_msg_size,
					skb, &packet->page_buf[0]);

	ret = netvsc_send(net_device_ctx->device_ctx, packet);

drop:
	if (ret == 0) {
		net->stats.tx_bytes += skb->len;
		net->stats.tx_packets++;
	} else {
		kfree(packet);
		if (ret != -EAGAIN) {
			dev_kfree_skb_any(skb);
			net->stats.tx_dropped++;
		}
	}

	return (ret == -EAGAIN) ? NETDEV_TX_BUSY : NETDEV_TX_OK;
}

/*
 * netvsc_linkstatus_callback - Link up/down notification
 */
void netvsc_linkstatus_callback(struct hv_device *device_obj,
				       unsigned int status)
{
	struct net_device *net;
	struct net_device_context *ndev_ctx;
	struct netvsc_device *net_device;
	struct rndis_device *rdev;

	net_device = hv_get_drvdata(device_obj);
	rdev = net_device->extension;

	rdev->link_state = status != 1;

	net = net_device->ndev;

	if (!net || net->reg_state != NETREG_REGISTERED)
		return;

	ndev_ctx = netdev_priv(net);
	if (status == 1) {
		schedule_delayed_work(&ndev_ctx->dwork, 0);
		schedule_delayed_work(&ndev_ctx->dwork, msecs_to_jiffies(20));
	} else {
		schedule_delayed_work(&ndev_ctx->dwork, 0);
	}
}

/*
 * netvsc_recv_callback -  Callback when we receive a packet from the
 * "wire" on the specified device.
 */
int netvsc_recv_callback(struct hv_device *device_obj,
				struct hv_netvsc_packet *packet,
				struct ndis_tcp_ip_checksum_info *csum_info)
{
	struct net_device *net;
	struct sk_buff *skb;

	net = ((struct netvsc_device *)hv_get_drvdata(device_obj))->ndev;
	if (!net || net->reg_state != NETREG_REGISTERED) {
		packet->status = NVSP_STAT_FAIL;
		return 0;
	}

	/* Allocate a skb - TODO direct I/O to pages? */
	skb = netdev_alloc_skb_ip_align(net, packet->total_data_buflen);
	if (unlikely(!skb)) {
		++net->stats.rx_dropped;
		packet->status = NVSP_STAT_FAIL;
		return 0;
	}

	/*
	 * Copy to skb. This copy is needed here since the memory pointed by
	 * hv_netvsc_packet cannot be deallocated
	 */
	memcpy(skb_put(skb, packet->total_data_buflen), packet->data,
		packet->total_data_buflen);

	skb->protocol = eth_type_trans(skb, net);
	if (csum_info) {
		/* We only look at the IP checksum here.
		 * Should we be dropping the packet if checksum
		 * failed? How do we deal with other checksums - TCP/UDP?
		 */
		if (csum_info->receive.ip_checksum_succeeded)
			skb->ip_summed = CHECKSUM_UNNECESSARY;
		else
			skb->ip_summed = CHECKSUM_NONE;
	}

	if (packet->vlan_tci & VLAN_TAG_PRESENT)
		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
				       packet->vlan_tci);

	net->stats.rx_packets++;
	net->stats.rx_bytes += packet->total_data_buflen;

	/*
	 * Pass the skb back up. Network stack will deallocate the skb when it
	 * is done.
	 * TODO - use NAPI?
	 */
	netif_rx(skb);

	return 0;
}

static void netvsc_get_drvinfo(struct net_device *net,
			       struct ethtool_drvinfo *info)
{
	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
	strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
}

static int netvsc_change_mtu(struct net_device *ndev, int mtu)
{
	struct net_device_context *ndevctx = netdev_priv(ndev);
	struct hv_device *hdev =  ndevctx->device_ctx;
	struct netvsc_device *nvdev = hv_get_drvdata(hdev);
	struct netvsc_device_info device_info;
	int limit = ETH_DATA_LEN;

	if (nvdev == NULL || nvdev->destroy)
		return -ENODEV;

	if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
		limit = NETVSC_MTU;

	if (mtu < 68 || mtu > limit)
		return -EINVAL;

	nvdev->start_remove = true;
	cancel_work_sync(&ndevctx->work);
	netif_tx_disable(ndev);
	rndis_filter_device_remove(hdev);

	ndev->mtu = mtu;

	ndevctx->device_ctx = hdev;
	hv_set_drvdata(hdev, ndev);
	device_info.ring_size = ring_size;
	rndis_filter_device_add(hdev, &device_info);
	netif_wake_queue(ndev);

	return 0;
}


static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
{
	struct net_device_context *ndevctx = netdev_priv(ndev);
	struct hv_device *hdev =  ndevctx->device_ctx;
	struct sockaddr *addr = p;
	char save_adr[ETH_ALEN];
	unsigned char save_aatype;
	int err;

	memcpy(save_adr, ndev->dev_addr, ETH_ALEN);
	save_aatype = ndev->addr_assign_type;

	err = eth_mac_addr(ndev, p);
	if (err != 0)
		return err;

	err = rndis_filter_set_device_mac(hdev, addr->sa_data);
	if (err != 0) {
		/* roll back to saved MAC */
		memcpy(ndev->dev_addr, save_adr, ETH_ALEN);
		ndev->addr_assign_type = save_aatype;
	}

	return err;
}


static const struct ethtool_ops ethtool_ops = {
	.get_drvinfo	= netvsc_get_drvinfo,
	.get_link	= ethtool_op_get_link,
};

static const struct net_device_ops device_ops = {
	.ndo_open =			netvsc_open,
	.ndo_stop =			netvsc_close,
	.ndo_start_xmit =		netvsc_start_xmit,
	.ndo_set_rx_mode =		netvsc_set_multicast_list,
	.ndo_change_mtu =		netvsc_change_mtu,
	.ndo_validate_addr =		eth_validate_addr,
	.ndo_set_mac_address =		netvsc_set_mac_addr,
};

/*
 * Send GARP packet to network peers after migrations.
 * After Quick Migration, the network is not immediately operational in the
 * current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, add
 * another netif_notify_peers() into a delayed work, otherwise GARP packet
 * will not be sent after quick migration, and cause network disconnection.
 * Also, we update the carrier status here.
 */
static void netvsc_link_change(struct work_struct *w)
{
	struct net_device_context *ndev_ctx;
	struct net_device *net;
	struct netvsc_device *net_device;
	struct rndis_device *rdev;
	bool notify;

	rtnl_lock();

	ndev_ctx = container_of(w, struct net_device_context, dwork.work);
	net_device = hv_get_drvdata(ndev_ctx->device_ctx);
	rdev = net_device->extension;
	net = net_device->ndev;

	if (rdev->link_state) {
		netif_carrier_off(net);
		notify = false;
	} else {
		netif_carrier_on(net);
		notify = true;
	}

	rtnl_unlock();

	if (notify)
		netdev_notify_peers(net);
}


static int netvsc_probe(struct hv_device *dev,
			const struct hv_vmbus_device_id *dev_id)
{
	struct net_device *net = NULL;
	struct net_device_context *net_device_ctx;
	struct netvsc_device_info device_info;
	int ret;

	net = alloc_etherdev(sizeof(struct net_device_context));
	if (!net)
		return -ENOMEM;

	netif_carrier_off(net);

	net_device_ctx = netdev_priv(net);
	net_device_ctx->device_ctx = dev;
	hv_set_drvdata(dev, net);
	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
	INIT_WORK(&net_device_ctx->work, do_set_multicast);

	net->netdev_ops = &device_ops;

	net->hw_features = NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_IP_CSUM |
				NETIF_F_TSO;
	net->features = NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_SG | NETIF_F_RXCSUM |
			NETIF_F_IP_CSUM | NETIF_F_TSO;

	SET_ETHTOOL_OPS(net, &ethtool_ops);
	SET_NETDEV_DEV(net, &dev->device);

	/* Notify the netvsc driver of the new device */
	device_info.ring_size = ring_size;
	ret = rndis_filter_device_add(dev, &device_info);
	if (ret != 0) {
		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
		free_netdev(net);
		hv_set_drvdata(dev, NULL);
		return ret;
	}
	memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);

	ret = register_netdev(net);
	if (ret != 0) {
		pr_err("Unable to register netdev.\n");
		rndis_filter_device_remove(dev);
		free_netdev(net);
	} else {
		schedule_delayed_work(&net_device_ctx->dwork, 0);
	}

	return ret;
}

static int netvsc_remove(struct hv_device *dev)
{
	struct net_device *net;
	struct net_device_context *ndev_ctx;
	struct netvsc_device *net_device;

	net_device = hv_get_drvdata(dev);
	net = net_device->ndev;

	if (net == NULL) {
		dev_err(&dev->device, "No net device to remove\n");
		return 0;
	}

	net_device->start_remove = true;

	ndev_ctx = netdev_priv(net);
	cancel_delayed_work_sync(&ndev_ctx->dwork);
	cancel_work_sync(&ndev_ctx->work);

	/* Stop outbound asap */
	netif_tx_disable(net);

	unregister_netdev(net);

	/*
	 * Call to the vsc driver to let it know that the device is being
	 * removed
	 */
	rndis_filter_device_remove(dev);

	free_netdev(net);
	return 0;
}

static const struct hv_vmbus_device_id id_table[] = {
	/* Network guid */
	{ HV_NIC_GUID, },
	{ },
};

MODULE_DEVICE_TABLE(vmbus, id_table);

/* The one and only one */
static struct  hv_driver netvsc_drv = {
	.name = KBUILD_MODNAME,
	.id_table = id_table,
	.probe = netvsc_probe,
	.remove = netvsc_remove,
};

static void __exit netvsc_drv_exit(void)
{
	vmbus_driver_unregister(&netvsc_drv);
}

static int __init netvsc_drv_init(void)
{
	if (ring_size < RING_SIZE_MIN) {
		ring_size = RING_SIZE_MIN;
		pr_info("Increased ring_size to %d (min allowed)\n",
			ring_size);
	}
	return vmbus_driver_register(&netvsc_drv);
}

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Microsoft Hyper-V network driver");

module_init(netvsc_drv_init);
module_exit(netvsc_drv_exit);