summaryrefslogtreecommitdiffstats
path: root/drivers/net/hyperv/netvsc_drv.c
blob: b12808ab343230194e984d2cc41d7d8d8cef532f (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
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
/*
 * 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"

#define RING_SIZE_MIN 64
#define LINKCHANGE_INT (2 * HZ)

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

static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
				NETIF_MSG_LINK | NETIF_MSG_IFUP |
				NETIF_MSG_IFDOWN | NETIF_MSG_RX_ERR |
				NETIF_MSG_TX_ERR;

static int debug = -1;
module_param(debug, int, S_IRUGO);
MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");

static void do_set_multicast(struct work_struct *w)
{
	struct net_device_context *ndevctx =
		container_of(w, struct net_device_context, work);
	struct hv_device *device_obj = ndevctx->device_ctx;
	struct net_device *ndev = hv_get_drvdata(device_obj);
	struct netvsc_device *nvdev = ndevctx->nvdev;
	struct rndis_device *rdev;

	if (!nvdev)
		return;

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

	if (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 netvsc_device *nvdev = net_device_to_netvsc_device(net);
	struct rndis_device *rdev;
	int ret = 0;

	netif_carrier_off(net);

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

	netif_tx_wake_all_queues(net);

	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 netvsc_device *nvdev = net_device_ctx->nvdev;
	int ret;
	u32 aread, awrite, i, msec = 10, retry = 0, retry_max = 20;
	struct vmbus_channel *chn;

	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(nvdev);
	if (ret != 0) {
		netdev_err(net, "unable to close device (ret %d).\n", ret);
		return ret;
	}

	/* Ensure pending bytes in ring are read */
	while (true) {
		aread = 0;
		for (i = 0; i < nvdev->num_chn; i++) {
			chn = nvdev->chan_table[i].channel;
			if (!chn)
				continue;

			hv_get_ringbuffer_availbytes(&chn->inbound, &aread,
						     &awrite);

			if (aread)
				break;

			hv_get_ringbuffer_availbytes(&chn->outbound, &aread,
						     &awrite);

			if (aread)
				break;
		}

		retry++;
		if (retry > retry_max || aread == 0)
			break;

		msleep(msec);

		if (msec < 1000)
			msec *= 2;
	}

	if (aread) {
		netdev_err(net, "Ring buffer not empty after closing rndis\n");
		ret = -ETIMEDOUT;
	}

	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;
}

/*
 * Select queue for transmit.
 *
 * If a valid queue has already been assigned, then use that.
 * Otherwise compute tx queue based on hash and the send table.
 *
 * This is basically similar to default (__netdev_pick_tx) with the added step
 * of using the host send_table when no other queue has been assigned.
 *
 * TODO support XPS - but get_xps_queue not exported
 */
static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
			void *accel_priv, select_queue_fallback_t fallback)
{
	struct net_device_context *net_device_ctx = netdev_priv(ndev);
	struct netvsc_device *nvsc_dev = net_device_ctx->nvdev;
	struct sock *sk = skb->sk;
	int q_idx = sk_tx_queue_get(sk);

	if (q_idx < 0 || skb->ooo_okay ||
	    q_idx >= ndev->real_num_tx_queues) {
		u16 hash = __skb_tx_hash(ndev, skb, VRSS_SEND_TAB_SIZE);
		int new_idx;

		new_idx = nvsc_dev->send_table[hash]
			% nvsc_dev->num_chn;

		if (q_idx != new_idx && sk &&
		    sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache))
			sk_tx_queue_set(sk, new_idx);

		q_idx = new_idx;
	}

	if (unlikely(!nvsc_dev->chan_table[q_idx].channel))
		q_idx = 0;

	return q_idx;
}

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_netvsc_packet *packet,
			   struct hv_page_buffer **page_buf)
{
	struct hv_page_buffer *pb = *page_buf;
	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: RNDIS header and PPI
	 * 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]);

	packet->rmsg_size = len;
	packet->rmsg_pgcnt = 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 net_checksum_info(struct sk_buff *skb)
{
	if (skb->protocol == htons(ETH_P_IP)) {
		struct iphdr *ip = ip_hdr(skb);

		if (ip->protocol == IPPROTO_TCP)
			return TRANSPORT_INFO_IPV4_TCP;
		else if (ip->protocol == IPPROTO_UDP)
			return TRANSPORT_INFO_IPV4_UDP;
	} else {
		struct ipv6hdr *ip6 = ipv6_hdr(skb);

		if (ip6->nexthdr == IPPROTO_TCP)
			return TRANSPORT_INFO_IPV6_TCP;
		else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)
			return TRANSPORT_INFO_IPV6_UDP;
	}

	return TRANSPORT_INFO_NOT_IP;
}

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 = NULL;
	int ret;
	unsigned int num_data_pgs;
	struct rndis_message *rndis_msg;
	struct rndis_packet *rndis_pkt;
	u32 rndis_msg_size;
	struct rndis_per_packet_info *ppi;
	u32 hash;
	struct hv_page_buffer page_buf[MAX_PAGE_BUFFER_COUNT];
	struct hv_page_buffer *pb = page_buf;

	/* 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. If skb is scattered around
	 * more pages we try linearizing it.
	 */

	num_data_pgs = netvsc_get_slots(skb) + 2;

	if (unlikely(num_data_pgs > MAX_PAGE_BUFFER_COUNT)) {
		++net_device_ctx->eth_stats.tx_scattered;

		if (skb_linearize(skb))
			goto no_memory;

		num_data_pgs = netvsc_get_slots(skb) + 2;
		if (num_data_pgs > MAX_PAGE_BUFFER_COUNT) {
			++net_device_ctx->eth_stats.tx_too_big;
			goto drop;
		}
	}

	/*
	 * Place the rndis header in the skb head room and
	 * the skb->cb will be used for hv_netvsc_packet
	 * structure.
	 */
	ret = skb_cow_head(skb, RNDIS_AND_PPI_SIZE);
	if (ret)
		goto no_memory;

	/* Use the skb control buffer for building up the packet */
	BUILD_BUG_ON(sizeof(struct hv_netvsc_packet) >
			FIELD_SIZEOF(struct sk_buff, cb));
	packet = (struct hv_netvsc_packet *)skb->cb;

	packet->q_idx = skb_get_queue_mapping(skb);

	packet->total_data_buflen = skb->len;
	packet->total_bytes = skb->len;
	packet->total_packets = 1;

	rndis_msg = (struct rndis_message *)skb->head;

	memset(rndis_msg, 0, RNDIS_AND_PPI_SIZE);

	/* Add the rndis header */
	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);

	hash = skb_get_hash_raw(skb);
	if (hash != 0 && net->real_num_tx_queues > 1) {
		rndis_msg_size += NDIS_HASH_PPI_SIZE;
		ppi = init_ppi_data(rndis_msg, NDIS_HASH_PPI_SIZE,
				    NBL_HASH_VALUE);
		*(u32 *)((void *)ppi + ppi->ppi_offset) = hash;
	}

	if (skb_vlan_tag_present(skb)) {
		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 = skb->vlan_tci & VLAN_VID_MASK;
		vlan->pri = (skb->vlan_tci & VLAN_PRIO_MASK) >>
				VLAN_PRIO_SHIFT;
	}

	if (skb_is_gso(skb)) {
		struct ndis_tcp_lso_info *lso_info;

		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 (skb->protocol == htons(ETH_P_IP)) {
			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 = skb_transport_offset(skb);
		lso_info->lso_v2_transmit.mss = skb_shinfo(skb)->gso_size;
	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
		if (net_checksum_info(skb) & net_device_ctx->tx_checksum_mask) {
			struct ndis_tcp_ip_checksum_info *csum_info;

			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);

			csum_info->transmit.tcp_header_offset = skb_transport_offset(skb);

			if (skb->protocol == htons(ETH_P_IP)) {
				csum_info->transmit.is_ipv4 = 1;

				if (ip_hdr(skb)->protocol == IPPROTO_TCP)
					csum_info->transmit.tcp_checksum = 1;
				else
					csum_info->transmit.udp_checksum = 1;
			} else {
				csum_info->transmit.is_ipv6 = 1;

				if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
					csum_info->transmit.tcp_checksum = 1;
				else
					csum_info->transmit.udp_checksum = 1;
			}
		} else {
			/* Can't do offload of this type of checksum */
			if (skb_checksum_help(skb))
				goto drop;
		}
	}

	/* Start filling in the page buffers with the rndis hdr */
	rndis_msg->msg_len += rndis_msg_size;
	packet->total_data_buflen = rndis_msg->msg_len;
	packet->page_buf_cnt = init_page_array(rndis_msg, rndis_msg_size,
					       skb, packet, &pb);

	/* timestamp packet in software */
	skb_tx_timestamp(skb);
	ret = netvsc_send(net_device_ctx->device_ctx, packet,
			  rndis_msg, &pb, skb);
	if (likely(ret == 0))
		return NETDEV_TX_OK;

	if (ret == -EAGAIN) {
		++net_device_ctx->eth_stats.tx_busy;
		return NETDEV_TX_BUSY;
	}

	if (ret == -ENOSPC)
		++net_device_ctx->eth_stats.tx_no_space;

drop:
	dev_kfree_skb_any(skb);
	net->stats.tx_dropped++;

	return NETDEV_TX_OK;

no_memory:
	++net_device_ctx->eth_stats.tx_no_memory;
	goto drop;
}
/*
 * netvsc_linkstatus_callback - Link up/down notification
 */
void netvsc_linkstatus_callback(struct hv_device *device_obj,
				struct rndis_message *resp)
{
	struct rndis_indicate_status *indicate = &resp->msg.indicate_status;
	struct net_device *net;
	struct net_device_context *ndev_ctx;
	struct netvsc_reconfig *event;
	unsigned long flags;

	net = hv_get_drvdata(device_obj);

	if (!net)
		return;

	ndev_ctx = netdev_priv(net);

	/* Update the physical link speed when changing to another vSwitch */
	if (indicate->status == RNDIS_STATUS_LINK_SPEED_CHANGE) {
		u32 speed;

		speed = *(u32 *)((void *)indicate + indicate->
				 status_buf_offset) / 10000;
		ndev_ctx->speed = speed;
		return;
	}

	/* Handle these link change statuses below */
	if (indicate->status != RNDIS_STATUS_NETWORK_CHANGE &&
	    indicate->status != RNDIS_STATUS_MEDIA_CONNECT &&
	    indicate->status != RNDIS_STATUS_MEDIA_DISCONNECT)
		return;

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

	event = kzalloc(sizeof(*event), GFP_ATOMIC);
	if (!event)
		return;
	event->event = indicate->status;

	spin_lock_irqsave(&ndev_ctx->lock, flags);
	list_add_tail(&event->list, &ndev_ctx->reconfig_events);
	spin_unlock_irqrestore(&ndev_ctx->lock, flags);

	schedule_delayed_work(&ndev_ctx->dwork, 0);
}

static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
					     struct napi_struct *napi,
					     const struct ndis_tcp_ip_checksum_info *csum_info,
					     const struct ndis_pkt_8021q_info *vlan,
					     void *data, u32 buflen)
{
	struct sk_buff *skb;

	skb = napi_alloc_skb(napi, buflen);
	if (!skb)
		return skb;

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

	skb->protocol = eth_type_trans(skb, net);

	/* skb is already created with CHECKSUM_NONE */
	skb_checksum_none_assert(skb);

	/*
	 * In Linux, the IP checksum is always checked.
	 * Do L4 checksum offload if enabled and present.
	 */
	if (csum_info && (net->features & NETIF_F_RXCSUM)) {
		if (csum_info->receive.tcp_checksum_succeeded ||
		    csum_info->receive.udp_checksum_succeeded)
			skb->ip_summed = CHECKSUM_UNNECESSARY;
	}

	if (vlan) {
		u16 vlan_tci = vlan->vlanid | (vlan->pri << VLAN_PRIO_SHIFT);

		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
				       vlan_tci);
	}

	return skb;
}

/*
 * netvsc_recv_callback -  Callback when we receive a packet from the
 * "wire" on the specified device.
 */
int netvsc_recv_callback(struct net_device *net,
			 struct vmbus_channel *channel,
			 void  *data, u32 len,
			 const struct ndis_tcp_ip_checksum_info *csum_info,
			 const struct ndis_pkt_8021q_info *vlan)
{
	struct net_device_context *net_device_ctx = netdev_priv(net);
	struct netvsc_device *net_device = net_device_ctx->nvdev;
	u16 q_idx = channel->offermsg.offer.sub_channel_index;
	struct netvsc_channel *nvchan = &net_device->chan_table[q_idx];
	struct net_device *vf_netdev;
	struct sk_buff *skb;
	struct netvsc_stats *rx_stats;

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

	/*
	 * If necessary, inject this packet into the VF interface.
	 * On Hyper-V, multicast and brodcast packets are only delivered
	 * to the synthetic interface (after subjecting these to
	 * policy filters on the host). Deliver these via the VF
	 * interface in the guest.
	 */
	rcu_read_lock();
	vf_netdev = rcu_dereference(net_device_ctx->vf_netdev);
	if (vf_netdev && (vf_netdev->flags & IFF_UP))
		net = vf_netdev;

	/* Allocate a skb - TODO direct I/O to pages? */
	skb = netvsc_alloc_recv_skb(net, &nvchan->napi,
				    csum_info, vlan, data, len);
	if (unlikely(!skb)) {
		++net->stats.rx_dropped;
		rcu_read_unlock();
		return NVSP_STAT_FAIL;
	}

	if (net != vf_netdev)
		skb_record_rx_queue(skb, q_idx);

	/*
	 * Even if injecting the packet, record the statistics
	 * on the synthetic device because modifying the VF device
	 * statistics will not work correctly.
	 */
	rx_stats = &nvchan->rx_stats;
	u64_stats_update_begin(&rx_stats->syncp);
	rx_stats->packets++;
	rx_stats->bytes += len;

	if (skb->pkt_type == PACKET_BROADCAST)
		++rx_stats->broadcast;
	else if (skb->pkt_type == PACKET_MULTICAST)
		++rx_stats->multicast;
	u64_stats_update_end(&rx_stats->syncp);

	napi_gro_receive(&nvchan->napi, skb);
	rcu_read_unlock();

	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 void netvsc_get_channels(struct net_device *net,
				struct ethtool_channels *channel)
{
	struct net_device_context *net_device_ctx = netdev_priv(net);
	struct netvsc_device *nvdev = net_device_ctx->nvdev;

	if (nvdev) {
		channel->max_combined	= nvdev->max_chn;
		channel->combined_count = nvdev->num_chn;
	}
}

static int netvsc_set_queues(struct net_device *net, struct hv_device *dev,
			     u32 num_chn)
{
	struct netvsc_device_info device_info;
	int ret;

	memset(&device_info, 0, sizeof(device_info));
	device_info.num_chn = num_chn;
	device_info.ring_size = ring_size;
	device_info.max_num_vrss_chns = num_chn;

	ret = rndis_filter_device_add(dev, &device_info);
	if (ret)
		return ret;

	ret = netif_set_real_num_tx_queues(net, num_chn);
	if (ret)
		return ret;

	ret = netif_set_real_num_rx_queues(net, num_chn);

	return ret;
}

static int netvsc_set_channels(struct net_device *net,
			       struct ethtool_channels *channels)
{
	struct net_device_context *net_device_ctx = netdev_priv(net);
	struct hv_device *dev = net_device_ctx->device_ctx;
	struct netvsc_device *nvdev = net_device_ctx->nvdev;
	unsigned int count = channels->combined_count;
	int ret;

	/* We do not support separate count for rx, tx, or other */
	if (count == 0 ||
	    channels->rx_count || channels->tx_count || channels->other_count)
		return -EINVAL;

	if (count > net->num_tx_queues || count > net->num_rx_queues)
		return -EINVAL;

	if (net_device_ctx->start_remove || !nvdev || nvdev->destroy)
		return -ENODEV;

	if (nvdev->nvsp_version < NVSP_PROTOCOL_VERSION_5)
		return -EINVAL;

	if (count > nvdev->max_chn)
		return -EINVAL;

	ret = netvsc_close(net);
	if (ret)
		return ret;

	net_device_ctx->start_remove = true;
	rndis_filter_device_remove(dev, nvdev);

	ret = netvsc_set_queues(net, dev, count);
	if (ret == 0)
		nvdev->num_chn = count;
	else
		netvsc_set_queues(net, dev, nvdev->num_chn);

	netvsc_open(net);
	net_device_ctx->start_remove = false;

	/* We may have missed link change notifications */
	schedule_delayed_work(&net_device_ctx->dwork, 0);

	return ret;
}

static bool
netvsc_validate_ethtool_ss_cmd(const struct ethtool_link_ksettings *cmd)
{
	struct ethtool_link_ksettings diff1 = *cmd;
	struct ethtool_link_ksettings diff2 = {};

	diff1.base.speed = 0;
	diff1.base.duplex = 0;
	/* advertising and cmd are usually set */
	ethtool_link_ksettings_zero_link_mode(&diff1, advertising);
	diff1.base.cmd = 0;
	/* We set port to PORT_OTHER */
	diff2.base.port = PORT_OTHER;

	return !memcmp(&diff1, &diff2, sizeof(diff1));
}

static void netvsc_init_settings(struct net_device *dev)
{
	struct net_device_context *ndc = netdev_priv(dev);

	ndc->speed = SPEED_UNKNOWN;
	ndc->duplex = DUPLEX_UNKNOWN;
}

static int netvsc_get_link_ksettings(struct net_device *dev,
				     struct ethtool_link_ksettings *cmd)
{
	struct net_device_context *ndc = netdev_priv(dev);

	cmd->base.speed = ndc->speed;
	cmd->base.duplex = ndc->duplex;
	cmd->base.port = PORT_OTHER;

	return 0;
}

static int netvsc_set_link_ksettings(struct net_device *dev,
				     const struct ethtool_link_ksettings *cmd)
{
	struct net_device_context *ndc = netdev_priv(dev);
	u32 speed;

	speed = cmd->base.speed;
	if (!ethtool_validate_speed(speed) ||
	    !ethtool_validate_duplex(cmd->base.duplex) ||
	    !netvsc_validate_ethtool_ss_cmd(cmd))
		return -EINVAL;

	ndc->speed = speed;
	ndc->duplex = cmd->base.duplex;

	return 0;
}

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

	if (ndevctx->start_remove || !nvdev || nvdev->destroy)
		return -ENODEV;

	ret = netvsc_close(ndev);
	if (ret)
		goto out;

	memset(&device_info, 0, sizeof(device_info));
	device_info.ring_size = ring_size;
	device_info.num_chn = nvdev->num_chn;
	device_info.max_num_vrss_chns = nvdev->num_chn;

	ndevctx->start_remove = true;
	rndis_filter_device_remove(hdev, nvdev);

	/* 'nvdev' has been freed in rndis_filter_device_remove() ->
	 * netvsc_device_remove () -> free_netvsc_device().
	 * We mustn't access it before it's re-created in
	 * rndis_filter_device_add() -> netvsc_device_add().
	 */

	ndev->mtu = mtu;

	rndis_filter_device_add(hdev, &device_info);

out:
	netvsc_open(ndev);
	ndevctx->start_remove = false;

	/* We may have missed link change notifications */
	schedule_delayed_work(&ndevctx->dwork, 0);

	return ret;
}

static void netvsc_get_stats64(struct net_device *net,
			       struct rtnl_link_stats64 *t)
{
	struct net_device_context *ndev_ctx = netdev_priv(net);
	struct netvsc_device *nvdev = ndev_ctx->nvdev;
	int i;

	if (!nvdev)
		return;

	for (i = 0; i < nvdev->num_chn; i++) {
		const struct netvsc_channel *nvchan = &nvdev->chan_table[i];
		const struct netvsc_stats *stats;
		u64 packets, bytes, multicast;
		unsigned int start;

		stats = &nvchan->tx_stats;
		do {
			start = u64_stats_fetch_begin_irq(&stats->syncp);
			packets = stats->packets;
			bytes = stats->bytes;
		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));

		t->tx_bytes	+= bytes;
		t->tx_packets	+= packets;

		stats = &nvchan->rx_stats;
		do {
			start = u64_stats_fetch_begin_irq(&stats->syncp);
			packets = stats->packets;
			bytes = stats->bytes;
			multicast = stats->multicast + stats->broadcast;
		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));

		t->rx_bytes	+= bytes;
		t->rx_packets	+= packets;
		t->multicast	+= multicast;
	}

	t->tx_dropped	= net->stats.tx_dropped;
	t->tx_errors	= net->stats.tx_errors;

	t->rx_dropped	= net->stats.rx_dropped;
	t->rx_errors	= net->stats.rx_errors;
}

static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
{
	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(ndev, 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 {
	char name[ETH_GSTRING_LEN];
	u16 offset;
} netvsc_stats[] = {
	{ "tx_scattered", offsetof(struct netvsc_ethtool_stats, tx_scattered) },
	{ "tx_no_memory",  offsetof(struct netvsc_ethtool_stats, tx_no_memory) },
	{ "tx_no_space",  offsetof(struct netvsc_ethtool_stats, tx_no_space) },
	{ "tx_too_big",	  offsetof(struct netvsc_ethtool_stats, tx_too_big) },
	{ "tx_busy",	  offsetof(struct netvsc_ethtool_stats, tx_busy) },
};

#define NETVSC_GLOBAL_STATS_LEN	ARRAY_SIZE(netvsc_stats)

/* 4 statistics per queue (rx/tx packets/bytes) */
#define NETVSC_QUEUE_STATS_LEN(dev) ((dev)->num_chn * 4)

static int netvsc_get_sset_count(struct net_device *dev, int string_set)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct netvsc_device *nvdev = ndc->nvdev;

	switch (string_set) {
	case ETH_SS_STATS:
		return NETVSC_GLOBAL_STATS_LEN + NETVSC_QUEUE_STATS_LEN(nvdev);
	default:
		return -EINVAL;
	}
}

static void netvsc_get_ethtool_stats(struct net_device *dev,
				     struct ethtool_stats *stats, u64 *data)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct netvsc_device *nvdev = ndc->nvdev;
	const void *nds = &ndc->eth_stats;
	const struct netvsc_stats *qstats;
	unsigned int start;
	u64 packets, bytes;
	int i, j;

	for (i = 0; i < NETVSC_GLOBAL_STATS_LEN; i++)
		data[i] = *(unsigned long *)(nds + netvsc_stats[i].offset);

	for (j = 0; j < nvdev->num_chn; j++) {
		qstats = &nvdev->chan_table[j].tx_stats;

		do {
			start = u64_stats_fetch_begin_irq(&qstats->syncp);
			packets = qstats->packets;
			bytes = qstats->bytes;
		} while (u64_stats_fetch_retry_irq(&qstats->syncp, start));
		data[i++] = packets;
		data[i++] = bytes;

		qstats = &nvdev->chan_table[j].rx_stats;
		do {
			start = u64_stats_fetch_begin_irq(&qstats->syncp);
			packets = qstats->packets;
			bytes = qstats->bytes;
		} while (u64_stats_fetch_retry_irq(&qstats->syncp, start));
		data[i++] = packets;
		data[i++] = bytes;
	}
}

static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct netvsc_device *nvdev = ndc->nvdev;
	u8 *p = data;
	int i;

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

		p += i * ETH_GSTRING_LEN;
		for (i = 0; i < nvdev->num_chn; i++) {
			sprintf(p, "tx_queue_%u_packets", i);
			p += ETH_GSTRING_LEN;
			sprintf(p, "tx_queue_%u_bytes", i);
			p += ETH_GSTRING_LEN;
			sprintf(p, "rx_queue_%u_packets", i);
			p += ETH_GSTRING_LEN;
			sprintf(p, "rx_queue_%u_bytes", i);
			p += ETH_GSTRING_LEN;
		}

		break;
	}
}

static int
netvsc_get_rss_hash_opts(struct netvsc_device *nvdev,
			 struct ethtool_rxnfc *info)
{
	info->data = RXH_IP_SRC | RXH_IP_DST;

	switch (info->flow_type) {
	case TCP_V4_FLOW:
	case TCP_V6_FLOW:
		info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
		/* fallthrough */
	case UDP_V4_FLOW:
	case UDP_V6_FLOW:
	case IPV4_FLOW:
	case IPV6_FLOW:
		break;
	default:
		info->data = 0;
		break;
	}

	return 0;
}

static int
netvsc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
		 u32 *rules)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct netvsc_device *nvdev = ndc->nvdev;

	switch (info->cmd) {
	case ETHTOOL_GRXRINGS:
		info->data = nvdev->num_chn;
		return 0;

	case ETHTOOL_GRXFH:
		return netvsc_get_rss_hash_opts(nvdev, info);
	}
	return -EOPNOTSUPP;
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void netvsc_poll_controller(struct net_device *net)
{
	/* As netvsc_start_xmit() works synchronous we don't have to
	 * trigger anything here.
	 */
}
#endif

static u32 netvsc_get_rxfh_key_size(struct net_device *dev)
{
	return NETVSC_HASH_KEYLEN;
}

static u32 netvsc_rss_indir_size(struct net_device *dev)
{
	return ITAB_NUM;
}

static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
			   u8 *hfunc)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct netvsc_device *ndev = ndc->nvdev;
	struct rndis_device *rndis_dev = ndev->extension;
	int i;

	if (hfunc)
		*hfunc = ETH_RSS_HASH_TOP;	/* Toeplitz */

	if (indir) {
		for (i = 0; i < ITAB_NUM; i++)
			indir[i] = rndis_dev->ind_table[i];
	}

	if (key)
		memcpy(key, rndis_dev->rss_key, NETVSC_HASH_KEYLEN);

	return 0;
}

static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir,
			   const u8 *key, const u8 hfunc)
{
	struct net_device_context *ndc = netdev_priv(dev);
	struct netvsc_device *ndev = ndc->nvdev;
	struct rndis_device *rndis_dev = ndev->extension;
	int i;

	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
		return -EOPNOTSUPP;

	if (indir) {
		for (i = 0; i < ITAB_NUM; i++)
			if (indir[i] >= dev->num_rx_queues)
				return -EINVAL;

		for (i = 0; i < ITAB_NUM; i++)
			rndis_dev->ind_table[i] = indir[i];
	}

	if (!key) {
		if (!indir)
			return 0;

		key = rndis_dev->rss_key;
	}

	return rndis_filter_set_rss_param(rndis_dev, key, ndev->num_chn);
}

static const struct ethtool_ops ethtool_ops = {
	.get_drvinfo	= netvsc_get_drvinfo,
	.get_link	= ethtool_op_get_link,
	.get_ethtool_stats = netvsc_get_ethtool_stats,
	.get_sset_count = netvsc_get_sset_count,
	.get_strings	= netvsc_get_strings,
	.get_channels   = netvsc_get_channels,
	.set_channels   = netvsc_set_channels,
	.get_ts_info	= ethtool_op_get_ts_info,
	.get_rxnfc	= netvsc_get_rxnfc,
	.get_rxfh_key_size = netvsc_get_rxfh_key_size,
	.get_rxfh_indir_size = netvsc_rss_indir_size,
	.get_rxfh	= netvsc_get_rxfh,
	.set_rxfh	= netvsc_set_rxfh,
	.get_link_ksettings = netvsc_get_link_ksettings,
	.set_link_ksettings = netvsc_set_link_ksettings,
};

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,
	.ndo_select_queue =		netvsc_select_queue,
	.ndo_get_stats64 =		netvsc_get_stats64,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller =		netvsc_poll_controller,
#endif
};

/*
 * Handle link status changes. For RNDIS_STATUS_NETWORK_CHANGE emulate link
 * down/up sequence. In case of RNDIS_STATUS_MEDIA_CONNECT when carrier is
 * present send GARP packet to network peers with netif_notify_peers().
 */
static void netvsc_link_change(struct work_struct *w)
{
	struct net_device_context *ndev_ctx =
		container_of(w, struct net_device_context, dwork.work);
	struct hv_device *device_obj = ndev_ctx->device_ctx;
	struct net_device *net = hv_get_drvdata(device_obj);
	struct netvsc_device *net_device;
	struct rndis_device *rdev;
	struct netvsc_reconfig *event = NULL;
	bool notify = false, reschedule = false;
	unsigned long flags, next_reconfig, delay;

	rtnl_lock();
	if (ndev_ctx->start_remove)
		goto out_unlock;

	net_device = ndev_ctx->nvdev;
	rdev = net_device->extension;

	next_reconfig = ndev_ctx->last_reconfig + LINKCHANGE_INT;
	if (time_is_after_jiffies(next_reconfig)) {
		/* link_watch only sends one notification with current state
		 * per second, avoid doing reconfig more frequently. Handle
		 * wrap around.
		 */
		delay = next_reconfig - jiffies;
		delay = delay < LINKCHANGE_INT ? delay : LINKCHANGE_INT;
		schedule_delayed_work(&ndev_ctx->dwork, delay);
		goto out_unlock;
	}
	ndev_ctx->last_reconfig = jiffies;

	spin_lock_irqsave(&ndev_ctx->lock, flags);
	if (!list_empty(&ndev_ctx->reconfig_events)) {
		event = list_first_entry(&ndev_ctx->reconfig_events,
					 struct netvsc_reconfig, list);
		list_del(&event->list);
		reschedule = !list_empty(&ndev_ctx->reconfig_events);
	}
	spin_unlock_irqrestore(&ndev_ctx->lock, flags);

	if (!event)
		goto out_unlock;

	switch (event->event) {
		/* Only the following events are possible due to the check in
		 * netvsc_linkstatus_callback()
		 */
	case RNDIS_STATUS_MEDIA_CONNECT:
		if (rdev->link_state) {
			rdev->link_state = false;
			netif_carrier_on(net);
			netif_tx_wake_all_queues(net);
		} else {
			notify = true;
		}
		kfree(event);
		break;
	case RNDIS_STATUS_MEDIA_DISCONNECT:
		if (!rdev->link_state) {
			rdev->link_state = true;
			netif_carrier_off(net);
			netif_tx_stop_all_queues(net);
		}
		kfree(event);
		break;
	case RNDIS_STATUS_NETWORK_CHANGE:
		/* Only makes sense if carrier is present */
		if (!rdev->link_state) {
			rdev->link_state = true;
			netif_carrier_off(net);
			netif_tx_stop_all_queues(net);
			event->event = RNDIS_STATUS_MEDIA_CONNECT;
			spin_lock_irqsave(&ndev_ctx->lock, flags);
			list_add(&event->list, &ndev_ctx->reconfig_events);
			spin_unlock_irqrestore(&ndev_ctx->lock, flags);
			reschedule = true;
		}
		break;
	}

	rtnl_unlock();

	if (notify)
		netdev_notify_peers(net);

	/* link_watch only sends one notification with current state per
	 * second, handle next reconfig event in 2 seconds.
	 */
	if (reschedule)
		schedule_delayed_work(&ndev_ctx->dwork, LINKCHANGE_INT);

	return;

out_unlock:
	rtnl_unlock();
}

static struct net_device *get_netvsc_bymac(const u8 *mac)
{
	struct net_device *dev;

	ASSERT_RTNL();

	for_each_netdev(&init_net, dev) {
		if (dev->netdev_ops != &device_ops)
			continue;	/* not a netvsc device */

		if (ether_addr_equal(mac, dev->perm_addr))
			return dev;
	}

	return NULL;
}

static struct net_device *get_netvsc_byref(struct net_device *vf_netdev)
{
	struct net_device *dev;

	ASSERT_RTNL();

	for_each_netdev(&init_net, dev) {
		struct net_device_context *net_device_ctx;

		if (dev->netdev_ops != &device_ops)
			continue;	/* not a netvsc device */

		net_device_ctx = netdev_priv(dev);
		if (net_device_ctx->nvdev == NULL)
			continue;	/* device is removed */

		if (rtnl_dereference(net_device_ctx->vf_netdev) == vf_netdev)
			return dev;	/* a match */
	}

	return NULL;
}

static int netvsc_register_vf(struct net_device *vf_netdev)
{
	struct net_device *ndev;
	struct net_device_context *net_device_ctx;
	struct netvsc_device *netvsc_dev;

	if (vf_netdev->addr_len != ETH_ALEN)
		return NOTIFY_DONE;

	/*
	 * We will use the MAC address to locate the synthetic interface to
	 * associate with the VF interface. If we don't find a matching
	 * synthetic interface, move on.
	 */
	ndev = get_netvsc_bymac(vf_netdev->perm_addr);
	if (!ndev)
		return NOTIFY_DONE;

	net_device_ctx = netdev_priv(ndev);
	netvsc_dev = net_device_ctx->nvdev;
	if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
		return NOTIFY_DONE;

	netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
	/*
	 * Take a reference on the module.
	 */
	try_module_get(THIS_MODULE);

	dev_hold(vf_netdev);
	rcu_assign_pointer(net_device_ctx->vf_netdev, vf_netdev);
	return NOTIFY_OK;
}

static int netvsc_vf_up(struct net_device *vf_netdev)
{
	struct net_device *ndev;
	struct netvsc_device *netvsc_dev;
	struct net_device_context *net_device_ctx;

	ndev = get_netvsc_byref(vf_netdev);
	if (!ndev)
		return NOTIFY_DONE;

	net_device_ctx = netdev_priv(ndev);
	netvsc_dev = net_device_ctx->nvdev;

	netdev_info(ndev, "VF up: %s\n", vf_netdev->name);

	/*
	 * Open the device before switching data path.
	 */
	rndis_filter_open(netvsc_dev);

	/*
	 * notify the host to switch the data path.
	 */
	netvsc_switch_datapath(ndev, true);
	netdev_info(ndev, "Data path switched to VF: %s\n", vf_netdev->name);

	netif_carrier_off(ndev);

	/* Now notify peers through VF device. */
	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, vf_netdev);

	return NOTIFY_OK;
}

static int netvsc_vf_down(struct net_device *vf_netdev)
{
	struct net_device *ndev;
	struct netvsc_device *netvsc_dev;
	struct net_device_context *net_device_ctx;

	ndev = get_netvsc_byref(vf_netdev);
	if (!ndev)
		return NOTIFY_DONE;

	net_device_ctx = netdev_priv(ndev);
	netvsc_dev = net_device_ctx->nvdev;

	netdev_info(ndev, "VF down: %s\n", vf_netdev->name);
	netvsc_switch_datapath(ndev, false);
	netdev_info(ndev, "Data path switched from VF: %s\n", vf_netdev->name);
	rndis_filter_close(netvsc_dev);
	netif_carrier_on(ndev);

	/* Now notify peers through netvsc device. */
	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, ndev);

	return NOTIFY_OK;
}

static int netvsc_unregister_vf(struct net_device *vf_netdev)
{
	struct net_device *ndev;
	struct net_device_context *net_device_ctx;

	ndev = get_netvsc_byref(vf_netdev);
	if (!ndev)
		return NOTIFY_DONE;

	net_device_ctx = netdev_priv(ndev);

	netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);

	RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL);
	dev_put(vf_netdev);
	module_put(THIS_MODULE);
	return NOTIFY_OK;
}

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;
	struct netvsc_device *nvdev;
	int ret;

	net = alloc_etherdev_mq(sizeof(struct net_device_context),
				VRSS_CHANNEL_MAX);
	if (!net)
		return -ENOMEM;

	netif_carrier_off(net);

	netvsc_init_settings(net);

	net_device_ctx = netdev_priv(net);
	net_device_ctx->device_ctx = dev;
	net_device_ctx->msg_enable = netif_msg_init(debug, default_msg);
	if (netif_msg_probe(net_device_ctx))
		netdev_dbg(net, "netvsc msg_enable: %d\n",
			   net_device_ctx->msg_enable);

	hv_set_drvdata(dev, net);

	net_device_ctx->start_remove = false;

	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
	INIT_WORK(&net_device_ctx->work, do_set_multicast);

	spin_lock_init(&net_device_ctx->lock);
	INIT_LIST_HEAD(&net_device_ctx->reconfig_events);

	net->netdev_ops = &device_ops;
	net->ethtool_ops = &ethtool_ops;
	SET_NETDEV_DEV(net, &dev->device);

	/* We always need headroom for rndis header */
	net->needed_headroom = RNDIS_AND_PPI_SIZE;

	/* Notify the netvsc driver of the new device */
	memset(&device_info, 0, sizeof(device_info));
	device_info.ring_size = ring_size;
	device_info.max_num_vrss_chns = min_t(u32, VRSS_CHANNEL_DEFAULT,
					      num_online_cpus());
	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);

	/* hw_features computed in rndis_filter_device_add */
	net->features = net->hw_features |
		NETIF_F_HIGHDMA | NETIF_F_SG |
		NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
	net->vlan_features = net->features;

	nvdev = net_device_ctx->nvdev;
	netif_set_real_num_tx_queues(net, nvdev->num_chn);
	netif_set_real_num_rx_queues(net, nvdev->num_chn);

	/* MTU range: 68 - 1500 or 65521 */
	net->min_mtu = NETVSC_MTU_MIN;
	if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
		net->max_mtu = NETVSC_MTU - ETH_HLEN;
	else
		net->max_mtu = ETH_DATA_LEN;

	ret = register_netdev(net);
	if (ret != 0) {
		pr_err("Unable to register netdev.\n");
		rndis_filter_device_remove(dev, nvdev);
		free_netdev(net);
	}

	return ret;
}

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

	net = hv_get_drvdata(dev);

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

	ndev_ctx = netdev_priv(net);

	/* Avoid racing with netvsc_change_mtu()/netvsc_set_channels()
	 * removing the device.
	 */
	rtnl_lock();
	ndev_ctx->start_remove = true;
	rtnl_unlock();

	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, ndev_ctx->nvdev);

	hv_set_drvdata(dev, NULL);

	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,
};

/*
 * On Hyper-V, every VF interface is matched with a corresponding
 * synthetic interface. The synthetic interface is presented first
 * to the guest. When the corresponding VF instance is registered,
 * we will take care of switching the data path.
 */
static int netvsc_netdev_event(struct notifier_block *this,
			       unsigned long event, void *ptr)
{
	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);

	/* Skip our own events */
	if (event_dev->netdev_ops == &device_ops)
		return NOTIFY_DONE;

	/* Avoid non-Ethernet type devices */
	if (event_dev->type != ARPHRD_ETHER)
		return NOTIFY_DONE;

	/* Avoid Vlan dev with same MAC registering as VF */
	if (is_vlan_dev(event_dev))
		return NOTIFY_DONE;

	/* Avoid Bonding master dev with same MAC registering as VF */
	if ((event_dev->priv_flags & IFF_BONDING) &&
	    (event_dev->flags & IFF_MASTER))
		return NOTIFY_DONE;

	switch (event) {
	case NETDEV_REGISTER:
		return netvsc_register_vf(event_dev);
	case NETDEV_UNREGISTER:
		return netvsc_unregister_vf(event_dev);
	case NETDEV_UP:
		return netvsc_vf_up(event_dev);
	case NETDEV_DOWN:
		return netvsc_vf_down(event_dev);
	default:
		return NOTIFY_DONE;
	}
}

static struct notifier_block netvsc_netdev_notifier = {
	.notifier_call = netvsc_netdev_event,
};

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

static int __init netvsc_drv_init(void)
{
	int ret;

	if (ring_size < RING_SIZE_MIN) {
		ring_size = RING_SIZE_MIN;
		pr_info("Increased ring_size to %d (min allowed)\n",
			ring_size);
	}
	ret = vmbus_driver_register(&netvsc_drv);

	if (ret)
		return ret;

	register_netdevice_notifier(&netvsc_netdev_notifier);
	return 0;
}

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

module_init(netvsc_drv_init);
module_exit(netvsc_drv_exit);