summaryrefslogtreecommitdiffstats
path: root/drivers/net/virtio_net.c
blob: 656a02e28e266ed6c51777fcb81e5312e8dc9ec7 (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
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
/* A 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>
#include <linux/slab.h>
#include <linux/cpu.h>

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

static bool csum = true, gso = true;
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_DRIVER_VERSION "1.0.0"

struct virtnet_stats {
	struct u64_stats_sync tx_syncp;
	struct u64_stats_sync rx_syncp;
	u64 tx_bytes;
	u64 tx_packets;

	u64 rx_bytes;
	u64 rx_packets;
};

/* Internal representation of a send virtqueue */
struct send_queue {
	/* Virtqueue associated with this send _queue */
	struct virtqueue *vq;

	/* TX: fragments + linear part + virtio header */
	struct scatterlist sg[MAX_SKB_FRAGS + 2];

	/* Name of the send queue: output.$index */
	char name[40];
};

/* Internal representation of a receive virtqueue */
struct receive_queue {
	/* Virtqueue associated with this receive_queue */
	struct virtqueue *vq;

	struct napi_struct napi;

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

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

	/* RX: fragments + linear part + virtio header */
	struct scatterlist sg[MAX_SKB_FRAGS + 2];

	/* Name of this receive queue: input.$index */
	char name[40];
};

struct virtnet_info {
	struct virtio_device *vdev;
	struct virtqueue *cvq;
	struct net_device *dev;
	struct send_queue *sq;
	struct receive_queue *rq;
	unsigned int status;

	/* Max # of queue pairs supported by the device */
	u16 max_queue_pairs;

	/* # of queue pairs currently used by the driver */
	u16 curr_queue_pairs;

	/* 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;

	/* Has control virtqueue */
	bool has_cvq;

	/* Host can handle any s/g split between our header and packet data */
	bool any_header_sg;

	/* enable config space updates */
	bool config_enable;

	/* Active statistics */
	struct virtnet_stats __percpu *stats;

	/* Work struct for refilling if we run low on memory. */
	struct delayed_work refill;

	/* Work struct for config space updates */
	struct work_struct config_work;

	/* Lock for config space updates */
	struct mutex config_lock;

	/* Page_frag for GFP_KERNEL packet buffer allocation when we run
	 * low on memory.
	 */
	struct page_frag alloc_frag;

	/* Does the affinity hint is set for virtqueues? */
	bool affinity_hint_set;

	/* Per-cpu variable to show the mapping from CPU to virtqueue */
	int __percpu *vq_index;

	/* CPU hot plug notifier */
	struct notifier_block nb;
};

struct skb_vnet_hdr {
	union {
		struct virtio_net_hdr hdr;
		struct virtio_net_hdr_mrg_rxbuf mhdr;
	};
};

struct padded_vnet_hdr {
	struct virtio_net_hdr hdr;
	/*
	 * virtio_net_hdr should be in a separated sg buffer because of a
	 * QEMU bug, and data sg buffer shares same page with this header sg.
	 * This padding makes next sg 16 byte aligned after virtio_net_hdr.
	 */
	char padding[6];
};

/* Converting between virtqueue no. and kernel tx/rx queue no.
 * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq
 */
static int vq2txq(struct virtqueue *vq)
{
	return (vq->index - 1) / 2;
}

static int txq2vq(int txq)
{
	return txq * 2 + 1;
}

static int vq2rxq(struct virtqueue *vq)
{
	return vq->index / 2;
}

static int rxq2vq(int rxq)
{
	return rxq * 2;
}

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

/*
 * private is used to chain pages for big packets, put the whole
 * most recent used list in the beginning for reuse
 */
static void give_pages(struct receive_queue *rq, struct page *page)
{
	struct page *end;

	/* Find end of list, sew whole thing into vi->rq.pages. */
	for (end = page; end->private; end = (struct page *)end->private);
	end->private = (unsigned long)rq->pages;
	rq->pages = page;
}

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

	if (p) {
		rq->pages = (struct page *)p->private;
		/* clear private here, it is used to chain pages */
		p->private = 0;
	} else
		p = alloc_page(gfp_mask);
	return p;
}

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

	/* Suppress further interrupts. */
	virtqueue_disable_cb(vq);

	/* We were probably waiting for more output buffers. */
	netif_wake_subqueue(vi->dev, vq2txq(vq));
}

/* Called from bottom half context */
static struct sk_buff *page_to_skb(struct receive_queue *rq,
				   struct page *page, unsigned int offset,
				   unsigned int len, unsigned int truesize)
{
	struct virtnet_info *vi = rq->vq->vdev->priv;
	struct sk_buff *skb;
	struct skb_vnet_hdr *hdr;
	unsigned int copy, hdr_len, hdr_padded_len;
	char *p;

	p = page_address(page) + offset;

	/* copy small packet so we can reuse these pages for small data */
	skb = netdev_alloc_skb_ip_align(vi->dev, GOOD_COPY_LEN);
	if (unlikely(!skb))
		return NULL;

	hdr = skb_vnet_hdr(skb);

	if (vi->mergeable_rx_bufs) {
		hdr_len = sizeof hdr->mhdr;
		hdr_padded_len = sizeof hdr->mhdr;
	} else {
		hdr_len = sizeof hdr->hdr;
		hdr_padded_len = sizeof(struct padded_vnet_hdr);
	}

	memcpy(hdr, p, hdr_len);

	len -= hdr_len;
	offset += hdr_padded_len;
	p += hdr_padded_len;

	copy = len;
	if (copy > skb_tailroom(skb))
		copy = skb_tailroom(skb);
	memcpy(skb_put(skb, copy), p, copy);

	len -= copy;
	offset += copy;

	if (vi->mergeable_rx_bufs) {
		if (len)
			skb_add_rx_frag(skb, 0, page, offset, len, truesize);
		else
			put_page(page);
		return skb;
	}

	/*
	 * Verify that we can indeed put this data into a skb.
	 * This is here to handle cases when the device erroneously
	 * tries to receive more than is possible. This is usually
	 * the case of a broken device.
	 */
	if (unlikely(len > MAX_SKB_FRAGS * PAGE_SIZE)) {
		net_dbg_ratelimited("%s: too much data\n", skb->dev->name);
		dev_kfree_skb(skb);
		return NULL;
	}
	BUG_ON(offset >= PAGE_SIZE);
	while (len) {
		unsigned int frag_size = min((unsigned)PAGE_SIZE - offset, len);
		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, offset,
				frag_size, truesize);
		len -= frag_size;
		page = (struct page *)page->private;
		offset = 0;
	}

	if (page)
		give_pages(rq, page);

	return skb;
}

static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb)
{
	struct skb_vnet_hdr *hdr = skb_vnet_hdr(head_skb);
	struct sk_buff *curr_skb = head_skb;
	char *buf;
	struct page *page;
	int num_buf, len;

	num_buf = hdr->mhdr.num_buffers;
	while (--num_buf) {
		int num_skb_frags = skb_shinfo(curr_skb)->nr_frags;
		buf = virtqueue_get_buf(rq->vq, &len);
		if (unlikely(!buf)) {
			pr_debug("%s: rx error: %d buffers missing\n",
				 head_skb->dev->name, hdr->mhdr.num_buffers);
			head_skb->dev->stats.rx_length_errors++;
			return -EINVAL;
		}
		if (unlikely(len > MAX_PACKET_LEN)) {
			pr_debug("%s: rx error: merge buffer too long\n",
				 head_skb->dev->name);
			len = MAX_PACKET_LEN;
		}
		if (unlikely(num_skb_frags == MAX_SKB_FRAGS)) {
			struct sk_buff *nskb = alloc_skb(0, GFP_ATOMIC);
			if (unlikely(!nskb)) {
				head_skb->dev->stats.rx_dropped++;
				return -ENOMEM;
			}
			if (curr_skb == head_skb)
				skb_shinfo(curr_skb)->frag_list = nskb;
			else
				curr_skb->next = nskb;
			curr_skb = nskb;
			head_skb->truesize += nskb->truesize;
			num_skb_frags = 0;
		}
		if (curr_skb != head_skb) {
			head_skb->data_len += len;
			head_skb->len += len;
			head_skb->truesize += MAX_PACKET_LEN;
		}
		page = virt_to_head_page(buf);
		skb_add_rx_frag(curr_skb, num_skb_frags, page,
				buf - (char *)page_address(page), len,
				MAX_PACKET_LEN);
		--rq->num;
	}
	return 0;
}

static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
{
	struct virtnet_info *vi = rq->vq->vdev->priv;
	struct net_device *dev = vi->dev;
	struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
	struct sk_buff *skb;
	struct page *page;
	struct skb_vnet_hdr *hdr;

	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++;
		if (vi->big_packets)
			give_pages(rq, buf);
		else if (vi->mergeable_rx_bufs)
			put_page(virt_to_head_page(buf));
		else
			dev_kfree_skb(buf);
		return;
	}

	if (!vi->mergeable_rx_bufs && !vi->big_packets) {
		skb = buf;
		len -= sizeof(struct virtio_net_hdr);
		skb_trim(skb, len);
	} else if (vi->mergeable_rx_bufs) {
		struct page *page = virt_to_head_page(buf);
		skb = page_to_skb(rq, page,
				  (char *)buf - (char *)page_address(page),
				  len, MAX_PACKET_LEN);
		if (unlikely(!skb)) {
			dev->stats.rx_dropped++;
			put_page(page);
			return;
		}
		if (receive_mergeable(rq, skb)) {
			dev_kfree_skb(skb);
			return;
		}
	} else {
		page = buf;
		skb = page_to_skb(rq, page, 0, len, PAGE_SIZE);
		if (unlikely(!skb)) {
			dev->stats.rx_dropped++;
			give_pages(rq, page);
			return;
		}
	}

	hdr = skb_vnet_hdr(skb);

	u64_stats_update_begin(&stats->rx_syncp);
	stats->rx_bytes += skb->len;
	stats->rx_packets++;
	u64_stats_update_end(&stats->rx_syncp);

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

	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->hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
		pr_debug("GSO!\n");
		switch (hdr->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:
			net_warn_ratelimited("%s: bad gso type %u.\n",
					     dev->name, hdr->hdr.gso_type);
			goto frame_err;
		}

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

		skb_shinfo(skb)->gso_size = hdr->hdr.gso_size;
		if (skb_shinfo(skb)->gso_size == 0) {
			net_warn_ratelimited("%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++;
	dev_kfree_skb(skb);
}

static int add_recvbuf_small(struct receive_queue *rq, gfp_t gfp)
{
	struct virtnet_info *vi = rq->vq->vdev->priv;
	struct sk_buff *skb;
	struct skb_vnet_hdr *hdr;
	int err;

	skb = __netdev_alloc_skb_ip_align(vi->dev, MAX_PACKET_LEN, gfp);
	if (unlikely(!skb))
		return -ENOMEM;

	skb_put(skb, MAX_PACKET_LEN);

	hdr = skb_vnet_hdr(skb);
	sg_set_buf(rq->sg, &hdr->hdr, sizeof hdr->hdr);

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

	err = virtqueue_add_inbuf(rq->vq, rq->sg, 2, skb, gfp);
	if (err < 0)
		dev_kfree_skb(skb);

	return err;
}

static int add_recvbuf_big(struct receive_queue *rq, gfp_t gfp)
{
	struct page *first, *list = NULL;
	char *p;
	int i, err, offset;

	/* page in rq->sg[MAX_SKB_FRAGS + 1] is list tail */
	for (i = MAX_SKB_FRAGS + 1; i > 1; --i) {
		first = get_a_page(rq, gfp);
		if (!first) {
			if (list)
				give_pages(rq, list);
			return -ENOMEM;
		}
		sg_set_buf(&rq->sg[i], page_address(first), PAGE_SIZE);

		/* chain new page in list head to match sg */
		first->private = (unsigned long)list;
		list = first;
	}

	first = get_a_page(rq, gfp);
	if (!first) {
		give_pages(rq, list);
		return -ENOMEM;
	}
	p = page_address(first);

	/* rq->sg[0], rq->sg[1] share the same page */
	/* a separated rq->sg[0] for virtio_net_hdr only due to QEMU bug */
	sg_set_buf(&rq->sg[0], p, sizeof(struct virtio_net_hdr));

	/* rq->sg[1] for data packet, from offset */
	offset = sizeof(struct padded_vnet_hdr);
	sg_set_buf(&rq->sg[1], p + offset, PAGE_SIZE - offset);

	/* chain first in list head */
	first->private = (unsigned long)list;
	err = virtqueue_add_inbuf(rq->vq, rq->sg, MAX_SKB_FRAGS + 2,
				  first, gfp);
	if (err < 0)
		give_pages(rq, first);

	return err;
}

static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
{
	struct virtnet_info *vi = rq->vq->vdev->priv;
	char *buf = NULL;
	int err;

	if (gfp & __GFP_WAIT) {
		if (skb_page_frag_refill(MAX_PACKET_LEN, &vi->alloc_frag,
					 gfp)) {
			buf = (char *)page_address(vi->alloc_frag.page) +
			      vi->alloc_frag.offset;
			get_page(vi->alloc_frag.page);
			vi->alloc_frag.offset += MAX_PACKET_LEN;
		}
	} else {
		buf = netdev_alloc_frag(MAX_PACKET_LEN);
	}
	if (!buf)
		return -ENOMEM;

	sg_init_one(rq->sg, buf, MAX_PACKET_LEN);
	err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, buf, gfp);
	if (err < 0)
		put_page(virt_to_head_page(buf));

	return err;
}

/*
 * Returns false if we couldn't fill entirely (OOM).
 *
 * Normally run in the receive path, but can also be run from ndo_open
 * before we're receiving packets, or from refill_work which is
 * careful to disable receiving (using napi_disable).
 */
static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
{
	struct virtnet_info *vi = rq->vq->vdev->priv;
	int err;
	bool oom;

	do {
		if (vi->mergeable_rx_bufs)
			err = add_recvbuf_mergeable(rq, gfp);
		else if (vi->big_packets)
			err = add_recvbuf_big(rq, gfp);
		else
			err = add_recvbuf_small(rq, gfp);

		oom = err == -ENOMEM;
		if (err)
			break;
		++rq->num;
	} while (rq->vq->num_free);
	if (unlikely(rq->num > rq->max))
		rq->max = rq->num;
	virtqueue_kick(rq->vq);
	return !oom;
}

static void skb_recv_done(struct virtqueue *rvq)
{
	struct virtnet_info *vi = rvq->vdev->priv;
	struct receive_queue *rq = &vi->rq[vq2rxq(rvq)];

	/* Schedule NAPI, Suppress further interrupts if successful. */
	if (napi_schedule_prep(&rq->napi)) {
		virtqueue_disable_cb(rvq);
		__napi_schedule(&rq->napi);
	}
}

static void virtnet_napi_enable(struct receive_queue *rq)
{
	napi_enable(&rq->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(&rq->napi)) {
		virtqueue_disable_cb(rq->vq);
		local_bh_disable();
		__napi_schedule(&rq->napi);
		local_bh_enable();
	}
}

static void refill_work(struct work_struct *work)
{
	struct virtnet_info *vi =
		container_of(work, struct virtnet_info, refill.work);
	bool still_empty;
	int i;

	for (i = 0; i < vi->curr_queue_pairs; i++) {
		struct receive_queue *rq = &vi->rq[i];

		napi_disable(&rq->napi);
		still_empty = !try_fill_recv(rq, GFP_KERNEL);
		virtnet_napi_enable(rq);

		/* In theory, this can happen: if we don't get any buffers in
		 * we will *never* try to fill again.
		 */
		if (still_empty)
			schedule_delayed_work(&vi->refill, HZ/2);
	}
}

static int virtnet_poll(struct napi_struct *napi, int budget)
{
	struct receive_queue *rq =
		container_of(napi, struct receive_queue, napi);
	struct virtnet_info *vi = rq->vq->vdev->priv;
	void *buf;
	unsigned int r, len, received = 0;

again:
	while (received < budget &&
	       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
		receive_buf(rq, buf, len);
		--rq->num;
		received++;
	}

	if (rq->num < rq->max / 2) {
		if (!try_fill_recv(rq, GFP_ATOMIC))
			schedule_delayed_work(&vi->refill, 0);
	}

	/* Out of packets? */
	if (received < budget) {
		r = virtqueue_enable_cb_prepare(rq->vq);
		napi_complete(napi);
		if (unlikely(virtqueue_poll(rq->vq, r)) &&
		    napi_schedule_prep(napi)) {
			virtqueue_disable_cb(rq->vq);
			__napi_schedule(napi);
			goto again;
		}
	}

	return received;
}

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

	for (i = 0; i < vi->max_queue_pairs; i++) {
		if (i < vi->curr_queue_pairs)
			/* Make sure we have some buffers: if oom use wq. */
			if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
				schedule_delayed_work(&vi->refill, 0);
		virtnet_napi_enable(&vi->rq[i]);
	}

	return 0;
}

static void free_old_xmit_skbs(struct send_queue *sq)
{
	struct sk_buff *skb;
	unsigned int len;
	struct virtnet_info *vi = sq->vq->vdev->priv;
	struct virtnet_stats *stats = this_cpu_ptr(vi->stats);

	while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) {
		pr_debug("Sent skb %p\n", skb);

		u64_stats_update_begin(&stats->tx_syncp);
		stats->tx_bytes += skb->len;
		stats->tx_packets++;
		u64_stats_update_end(&stats->tx_syncp);

		dev_kfree_skb_any(skb);
	}
}

static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
{
	struct skb_vnet_hdr *hdr;
	const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
	struct virtnet_info *vi = sq->vq->vdev->priv;
	unsigned num_sg;
	unsigned hdr_len;
	bool can_push;

	pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);
	if (vi->mergeable_rx_bufs)
		hdr_len = sizeof hdr->mhdr;
	else
		hdr_len = sizeof hdr->hdr;

	can_push = vi->any_header_sg &&
		!((unsigned long)skb->data & (__alignof__(*hdr) - 1)) &&
		!skb_header_cloned(skb) && skb_headroom(skb) >= hdr_len;
	/* Even if we can, don't push here yet as this would skew
	 * csum_start offset below. */
	if (can_push)
		hdr = (struct skb_vnet_hdr *)(skb->data - hdr_len);
	else
		hdr = skb_vnet_hdr(skb);

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

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

	if (vi->mergeable_rx_bufs)
		hdr->mhdr.num_buffers = 0;

	if (can_push) {
		__skb_push(skb, hdr_len);
		num_sg = skb_to_sgvec(skb, sq->sg, 0, skb->len);
		/* Pull header back to avoid skew in tx bytes calculations. */
		__skb_pull(skb, hdr_len);
	} else {
		sg_set_buf(sq->sg, hdr, hdr_len);
		num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len) + 1;
	}
	return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, skb, GFP_ATOMIC);
}

static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);
	int qnum = skb_get_queue_mapping(skb);
	struct send_queue *sq = &vi->sq[qnum];
	int err;

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

	/* Try to transmit */
	err = xmit_skb(sq, skb);

	/* This should not happen! */
	if (unlikely(err)) {
		dev->stats.tx_fifo_errors++;
		if (net_ratelimit())
			dev_warn(&dev->dev,
				 "Unexpected TXQ (%d) queue failure: %d\n", qnum, err);
		dev->stats.tx_dropped++;
		kfree_skb(skb);
		return NETDEV_TX_OK;
	}
	virtqueue_kick(sq->vq);

	/* Don't wait up for transmitted skbs to be freed. */
	skb_orphan(skb);
	nf_reset(skb);

	/* Apparently nice girls don't return TX_BUSY; stop the queue
	 * before it gets out of hand.  Naturally, this wastes entries. */
	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
		netif_stop_subqueue(dev, qnum);
		if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
			/* More just got used, free them then recheck. */
			free_old_xmit_skbs(sq);
			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
				netif_start_subqueue(dev, qnum);
				virtqueue_disable_cb(sq->vq);
			}
		}
	}

	return NETDEV_TX_OK;
}

/*
 * 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 *out,
				 struct scatterlist *in)
{
	struct scatterlist *sgs[4], hdr, stat;
	struct virtio_net_ctrl_hdr ctrl;
	virtio_net_ctrl_ack status = ~0;
	unsigned out_num = 0, in_num = 0, tmp;

	/* Caller should know better */
	BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));

	ctrl.class = class;
	ctrl.cmd = cmd;
	/* Add header */
	sg_init_one(&hdr, &ctrl, sizeof(ctrl));
	sgs[out_num++] = &hdr;

	if (out)
		sgs[out_num++] = out;
	if (in)
		sgs[out_num + in_num++] = in;

	/* Add return status. */
	sg_init_one(&stat, &status, sizeof(status));
	sgs[out_num + in_num++] = &stat;

	BUG_ON(out_num + in_num > ARRAY_SIZE(sgs));
	BUG_ON(virtqueue_add_sgs(vi->cvq, sgs, out_num, in_num, vi, GFP_ATOMIC)
	       < 0);

	virtqueue_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 (!virtqueue_get_buf(vi->cvq, &tmp))
		cpu_relax();

	return status == VIRTIO_NET_OK;
}

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;
	struct sockaddr *addr = p;
	struct scatterlist sg;

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

	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) {
		sg_init_one(&sg, addr->sa_data, dev->addr_len);
		if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC,
					  VIRTIO_NET_CTRL_MAC_ADDR_SET,
					  &sg, NULL)) {
			dev_warn(&vdev->dev,
				 "Failed to set mac address by vq command.\n");
			return -EINVAL;
		}
	} else if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) {
		vdev->config->set(vdev, offsetof(struct virtio_net_config, mac),
				  addr->sa_data, dev->addr_len);
	}

	eth_commit_mac_addr_change(dev, p);

	return 0;
}

static struct rtnl_link_stats64 *virtnet_stats(struct net_device *dev,
					       struct rtnl_link_stats64 *tot)
{
	struct virtnet_info *vi = netdev_priv(dev);
	int cpu;
	unsigned int start;

	for_each_possible_cpu(cpu) {
		struct virtnet_stats *stats = per_cpu_ptr(vi->stats, cpu);
		u64 tpackets, tbytes, rpackets, rbytes;

		do {
			start = u64_stats_fetch_begin_bh(&stats->tx_syncp);
			tpackets = stats->tx_packets;
			tbytes   = stats->tx_bytes;
		} while (u64_stats_fetch_retry_bh(&stats->tx_syncp, start));

		do {
			start = u64_stats_fetch_begin_bh(&stats->rx_syncp);
			rpackets = stats->rx_packets;
			rbytes   = stats->rx_bytes;
		} while (u64_stats_fetch_retry_bh(&stats->rx_syncp, start));

		tot->rx_packets += rpackets;
		tot->tx_packets += tpackets;
		tot->rx_bytes   += rbytes;
		tot->tx_bytes   += tbytes;
	}

	tot->tx_dropped = dev->stats.tx_dropped;
	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
	tot->rx_dropped = dev->stats.rx_dropped;
	tot->rx_length_errors = dev->stats.rx_length_errors;
	tot->rx_frame_errors = dev->stats.rx_frame_errors;

	return tot;
}

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

	for (i = 0; i < vi->curr_queue_pairs; i++)
		napi_schedule(&vi->rq[i].napi);
}
#endif

static void virtnet_ack_link_announce(struct virtnet_info *vi)
{
	rtnl_lock();
	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_ANNOUNCE,
				  VIRTIO_NET_CTRL_ANNOUNCE_ACK, NULL, NULL))
		dev_warn(&vi->dev->dev, "Failed to ack link announce.\n");
	rtnl_unlock();
}

static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
{
	struct scatterlist sg;
	struct virtio_net_ctrl_mq s;
	struct net_device *dev = vi->dev;

	if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
		return 0;

	s.virtqueue_pairs = queue_pairs;
	sg_init_one(&sg, &s, sizeof(s));

	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
				  VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg, NULL)) {
		dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n",
			 queue_pairs);
		return -EINVAL;
	} else {
		vi->curr_queue_pairs = queue_pairs;
		/* virtnet_open() will refill when device is going to up. */
		if (dev->flags & IFF_UP)
			schedule_delayed_work(&vi->refill, 0);
	}

	return 0;
}

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

	/* Make sure refill_work doesn't re-enable napi! */
	cancel_delayed_work_sync(&vi->refill);

	for (i = 0; i < vi->max_queue_pairs; i++)
		napi_disable(&vi->rq[i].napi);

	return 0;
}

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 netdev_hw_addr *ha;
	int uc_count;
	int mc_count;
	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, NULL))
		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, NULL))
		dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
			 allmulti ? "en" : "dis");

	uc_count = netdev_uc_count(dev);
	mc_count = netdev_mc_count(dev);
	/* MAC filter - use one buffer for both lists */
	buf = kzalloc(((uc_count + mc_count) * ETH_ALEN) +
		      (2 * sizeof(mac_data->entries)), GFP_ATOMIC);
	mac_data = buf;
	if (!buf)
		return;

	sg_init_table(sg, 2);

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

	sg_set_buf(&sg[0], mac_data,
		   sizeof(mac_data->entries) + (uc_count * ETH_ALEN));

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

	mac_data->entries = mc_count;
	i = 0;
	netdev_for_each_mc_addr(ha, dev)
		memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);

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

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

	kfree(buf);
}

static int virtnet_vlan_rx_add_vid(struct net_device *dev,
				   __be16 proto, 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, NULL))
		dev_warn(&dev->dev, "Failed to add VLAN ID %d.\n", vid);
	return 0;
}

static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
				    __be16 proto, 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, NULL))
		dev_warn(&dev->dev, "Failed to kill VLAN ID %d.\n", vid);
	return 0;
}

static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu)
{
	int i;
	int cpu;

	if (vi->affinity_hint_set) {
		for (i = 0; i < vi->max_queue_pairs; i++) {
			virtqueue_set_affinity(vi->rq[i].vq, -1);
			virtqueue_set_affinity(vi->sq[i].vq, -1);
		}

		vi->affinity_hint_set = false;
	}

	i = 0;
	for_each_online_cpu(cpu) {
		if (cpu == hcpu) {
			*per_cpu_ptr(vi->vq_index, cpu) = -1;
		} else {
			*per_cpu_ptr(vi->vq_index, cpu) =
				++i % vi->curr_queue_pairs;
		}
	}
}

static void virtnet_set_affinity(struct virtnet_info *vi)
{
	int i;
	int cpu;

	/* In multiqueue mode, when the number of cpu is equal to the number of
	 * queue pairs, we let the queue pairs to be private to one cpu by
	 * setting the affinity hint to eliminate the contention.
	 */
	if (vi->curr_queue_pairs == 1 ||
	    vi->max_queue_pairs != num_online_cpus()) {
		virtnet_clean_affinity(vi, -1);
		return;
	}

	i = 0;
	for_each_online_cpu(cpu) {
		virtqueue_set_affinity(vi->rq[i].vq, cpu);
		virtqueue_set_affinity(vi->sq[i].vq, cpu);
		*per_cpu_ptr(vi->vq_index, cpu) = i;
		i++;
	}

	vi->affinity_hint_set = true;
}

static int virtnet_cpu_callback(struct notifier_block *nfb,
			        unsigned long action, void *hcpu)
{
	struct virtnet_info *vi = container_of(nfb, struct virtnet_info, nb);

	switch(action & ~CPU_TASKS_FROZEN) {
	case CPU_ONLINE:
	case CPU_DOWN_FAILED:
	case CPU_DEAD:
		virtnet_set_affinity(vi);
		break;
	case CPU_DOWN_PREPARE:
		virtnet_clean_affinity(vi, (long)hcpu);
		break;
	default:
		break;
	}

	return NOTIFY_OK;
}

static void virtnet_get_ringparam(struct net_device *dev,
				struct ethtool_ringparam *ring)
{
	struct virtnet_info *vi = netdev_priv(dev);

	ring->rx_max_pending = virtqueue_get_vring_size(vi->rq[0].vq);
	ring->tx_max_pending = virtqueue_get_vring_size(vi->sq[0].vq);
	ring->rx_pending = ring->rx_max_pending;
	ring->tx_pending = ring->tx_max_pending;
}


static void virtnet_get_drvinfo(struct net_device *dev,
				struct ethtool_drvinfo *info)
{
	struct virtnet_info *vi = netdev_priv(dev);
	struct virtio_device *vdev = vi->vdev;

	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
	strlcpy(info->version, VIRTNET_DRIVER_VERSION, sizeof(info->version));
	strlcpy(info->bus_info, virtio_bus_name(vdev), sizeof(info->bus_info));

}

/* TODO: Eliminate OOO packets during switching */
static int virtnet_set_channels(struct net_device *dev,
				struct ethtool_channels *channels)
{
	struct virtnet_info *vi = netdev_priv(dev);
	u16 queue_pairs = channels->combined_count;
	int err;

	/* We don't support separate rx/tx channels.
	 * We don't allow setting 'other' channels.
	 */
	if (channels->rx_count || channels->tx_count || channels->other_count)
		return -EINVAL;

	if (queue_pairs > vi->max_queue_pairs)
		return -EINVAL;

	get_online_cpus();
	err = virtnet_set_queues(vi, queue_pairs);
	if (!err) {
		netif_set_real_num_tx_queues(dev, queue_pairs);
		netif_set_real_num_rx_queues(dev, queue_pairs);

		virtnet_set_affinity(vi);
	}
	put_online_cpus();

	return err;
}

static void virtnet_get_channels(struct net_device *dev,
				 struct ethtool_channels *channels)
{
	struct virtnet_info *vi = netdev_priv(dev);

	channels->combined_count = vi->curr_queue_pairs;
	channels->max_combined = vi->max_queue_pairs;
	channels->max_other = 0;
	channels->rx_count = 0;
	channels->tx_count = 0;
	channels->other_count = 0;
}

static const struct ethtool_ops virtnet_ethtool_ops = {
	.get_drvinfo = virtnet_get_drvinfo,
	.get_link = ethtool_op_get_link,
	.get_ringparam = virtnet_get_ringparam,
	.set_channels = virtnet_set_channels,
	.get_channels = virtnet_get_channels,
};

#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;
}

/* To avoid contending a lock hold by a vcpu who would exit to host, select the
 * txq based on the processor id.
 */
static u16 virtnet_select_queue(struct net_device *dev, struct sk_buff *skb)
{
	int txq;
	struct virtnet_info *vi = netdev_priv(dev);

	if (skb_rx_queue_recorded(skb)) {
		txq = skb_get_rx_queue(skb);
	} else {
		txq = *__this_cpu_ptr(vi->vq_index);
		if (txq == -1)
			txq = 0;
	}

	while (unlikely(txq >= dev->real_num_tx_queues))
		txq -= dev->real_num_tx_queues;

	return txq;
}

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_get_stats64     = virtnet_stats,
	.ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid,
	.ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid,
	.ndo_select_queue     = virtnet_select_queue,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller = virtnet_netpoll,
#endif
};

static void virtnet_config_changed_work(struct work_struct *work)
{
	struct virtnet_info *vi =
		container_of(work, struct virtnet_info, config_work);
	u16 v;

	mutex_lock(&vi->config_lock);
	if (!vi->config_enable)
		goto done;

	if (virtio_config_val(vi->vdev, VIRTIO_NET_F_STATUS,
			      offsetof(struct virtio_net_config, status),
			      &v) < 0)
		goto done;

	if (v & VIRTIO_NET_S_ANNOUNCE) {
		netdev_notify_peers(vi->dev);
		virtnet_ack_link_announce(vi);
	}

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

	if (vi->status == v)
		goto done;

	vi->status = v;

	if (vi->status & VIRTIO_NET_S_LINK_UP) {
		netif_carrier_on(vi->dev);
		netif_tx_wake_all_queues(vi->dev);
	} else {
		netif_carrier_off(vi->dev);
		netif_tx_stop_all_queues(vi->dev);
	}
done:
	mutex_unlock(&vi->config_lock);
}

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

	schedule_work(&vi->config_work);
}

static void virtnet_free_queues(struct virtnet_info *vi)
{
	kfree(vi->rq);
	kfree(vi->sq);
}

static void free_receive_bufs(struct virtnet_info *vi)
{
	int i;

	for (i = 0; i < vi->max_queue_pairs; i++) {
		while (vi->rq[i].pages)
			__free_pages(get_a_page(&vi->rq[i], GFP_KERNEL), 0);
	}
}

static void free_unused_bufs(struct virtnet_info *vi)
{
	void *buf;
	int i;

	for (i = 0; i < vi->max_queue_pairs; i++) {
		struct virtqueue *vq = vi->sq[i].vq;
		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
			dev_kfree_skb(buf);
	}

	for (i = 0; i < vi->max_queue_pairs; i++) {
		struct virtqueue *vq = vi->rq[i].vq;

		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
			if (vi->big_packets)
				give_pages(&vi->rq[i], buf);
			else if (vi->mergeable_rx_bufs)
				put_page(virt_to_head_page(buf));
			else
				dev_kfree_skb(buf);
			--vi->rq[i].num;
		}
		BUG_ON(vi->rq[i].num != 0);
	}
}

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

	virtnet_clean_affinity(vi, -1);

	vdev->config->del_vqs(vdev);

	virtnet_free_queues(vi);
}

static int virtnet_find_vqs(struct virtnet_info *vi)
{
	vq_callback_t **callbacks;
	struct virtqueue **vqs;
	int ret = -ENOMEM;
	int i, total_vqs;
	const char **names;

	/* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by
	 * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by
	 * possible control vq.
	 */
	total_vqs = vi->max_queue_pairs * 2 +
		    virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ);

	/* Allocate space for find_vqs parameters */
	vqs = kzalloc(total_vqs * sizeof(*vqs), GFP_KERNEL);
	if (!vqs)
		goto err_vq;
	callbacks = kmalloc(total_vqs * sizeof(*callbacks), GFP_KERNEL);
	if (!callbacks)
		goto err_callback;
	names = kmalloc(total_vqs * sizeof(*names), GFP_KERNEL);
	if (!names)
		goto err_names;

	/* Parameters for control virtqueue, if any */
	if (vi->has_cvq) {
		callbacks[total_vqs - 1] = NULL;
		names[total_vqs - 1] = "control";
	}

	/* Allocate/initialize parameters for send/receive virtqueues */
	for (i = 0; i < vi->max_queue_pairs; i++) {
		callbacks[rxq2vq(i)] = skb_recv_done;
		callbacks[txq2vq(i)] = skb_xmit_done;
		sprintf(vi->rq[i].name, "input.%d", i);
		sprintf(vi->sq[i].name, "output.%d", i);
		names[rxq2vq(i)] = vi->rq[i].name;
		names[txq2vq(i)] = vi->sq[i].name;
	}

	ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
					 names);
	if (ret)
		goto err_find;

	if (vi->has_cvq) {
		vi->cvq = vqs[total_vqs - 1];
		if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN))
			vi->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
	}

	for (i = 0; i < vi->max_queue_pairs; i++) {
		vi->rq[i].vq = vqs[rxq2vq(i)];
		vi->sq[i].vq = vqs[txq2vq(i)];
	}

	kfree(names);
	kfree(callbacks);
	kfree(vqs);

	return 0;

err_find:
	kfree(names);
err_names:
	kfree(callbacks);
err_callback:
	kfree(vqs);
err_vq:
	return ret;
}

static int virtnet_alloc_queues(struct virtnet_info *vi)
{
	int i;

	vi->sq = kzalloc(sizeof(*vi->sq) * vi->max_queue_pairs, GFP_KERNEL);
	if (!vi->sq)
		goto err_sq;
	vi->rq = kzalloc(sizeof(*vi->rq) * vi->max_queue_pairs, GFP_KERNEL);
	if (!vi->rq)
		goto err_rq;

	INIT_DELAYED_WORK(&vi->refill, refill_work);
	for (i = 0; i < vi->max_queue_pairs; i++) {
		vi->rq[i].pages = NULL;
		netif_napi_add(vi->dev, &vi->rq[i].napi, virtnet_poll,
			       napi_weight);

		sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
		sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg));
	}

	return 0;

err_rq:
	kfree(vi->sq);
err_sq:
	return -ENOMEM;
}

static int init_vqs(struct virtnet_info *vi)
{
	int ret;

	/* Allocate send & receive queues */
	ret = virtnet_alloc_queues(vi);
	if (ret)
		goto err;

	ret = virtnet_find_vqs(vi);
	if (ret)
		goto err_free;

	get_online_cpus();
	virtnet_set_affinity(vi);
	put_online_cpus();

	return 0;

err_free:
	virtnet_free_queues(vi);
err:
	return ret;
}

static int virtnet_probe(struct virtio_device *vdev)
{
	int i, err;
	struct net_device *dev;
	struct virtnet_info *vi;
	u16 max_queue_pairs;

	/* Find if host supports multiqueue virtio_net device */
	err = virtio_config_val(vdev, VIRTIO_NET_F_MQ,
				offsetof(struct virtio_net_config,
				max_virtqueue_pairs), &max_queue_pairs);

	/* We need at least 2 queue's */
	if (err || max_queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN ||
	    max_queue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX ||
	    !virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
		max_queue_pairs = 1;

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

	/* Set up network device as normal. */
	dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE;
	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 (virtio_has_feature(vdev, VIRTIO_NET_F_CSUM)) {
		/* This opens up the world of extra features. */
		dev->hw_features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
		if (csum)
			dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;

		if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) {
			dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO
				| NETIF_F_TSO_ECN | NETIF_F_TSO6;
		}
		/* Individual feature bits: what can host handle? */
		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_TSO4))
			dev->hw_features |= NETIF_F_TSO;
		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_TSO6))
			dev->hw_features |= NETIF_F_TSO6;
		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN))
			dev->hw_features |= NETIF_F_TSO_ECN;
		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UFO))
			dev->hw_features |= NETIF_F_UFO;

		if (gso)
			dev->features |= dev->hw_features & (NETIF_F_ALL_TSO|NETIF_F_UFO);
		/* (!csum && gso) case will be fixed by register_netdev() */
	}
	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM))
		dev->features |= NETIF_F_RXCSUM;

	dev->vlan_features = dev->features;

	/* Configuration may specify what MAC to use.  Otherwise random. */
	if (virtio_config_val_len(vdev, VIRTIO_NET_F_MAC,
				  offsetof(struct virtio_net_config, mac),
				  dev->dev_addr, dev->addr_len) < 0)
		eth_hw_addr_random(dev);

	/* Set up our device-specific information */
	vi = netdev_priv(dev);
	vi->dev = dev;
	vi->vdev = vdev;
	vdev->priv = vi;
	vi->stats = alloc_percpu(struct virtnet_stats);
	err = -ENOMEM;
	if (vi->stats == NULL)
		goto free;

	vi->vq_index = alloc_percpu(int);
	if (vi->vq_index == NULL)
		goto free_stats;

	mutex_init(&vi->config_lock);
	vi->config_enable = true;
	INIT_WORK(&vi->config_work, virtnet_config_changed_work);

	/* 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;

	if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT))
		vi->any_header_sg = true;

	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
		vi->has_cvq = true;

	/* Use single tx/rx queue pair as default */
	vi->curr_queue_pairs = 1;
	vi->max_queue_pairs = max_queue_pairs;

	/* Allocate/initialize the rx/tx queues, and invoke find_vqs */
	err = init_vqs(vi);
	if (err)
		goto free_index;

	netif_set_real_num_tx_queues(dev, 1);
	netif_set_real_num_rx_queues(dev, 1);

	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. */
	for (i = 0; i < vi->curr_queue_pairs; i++) {
		try_fill_recv(&vi->rq[i], GFP_KERNEL);

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

	vi->nb.notifier_call = &virtnet_cpu_callback;
	err = register_hotcpu_notifier(&vi->nb);
	if (err) {
		pr_debug("virtio_net: registering cpu notifier failed\n");
		goto free_recv_bufs;
	}

	/* Assume link up if device can't report link status,
	   otherwise get link status from config. */
	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
		netif_carrier_off(dev);
		schedule_work(&vi->config_work);
	} else {
		vi->status = VIRTIO_NET_S_LINK_UP;
		netif_carrier_on(dev);
	}

	pr_debug("virtnet: registered device %s with %d RX and TX vq's\n",
		 dev->name, max_queue_pairs);

	return 0;

free_recv_bufs:
	free_receive_bufs(vi);
	unregister_netdev(dev);
free_vqs:
	cancel_delayed_work_sync(&vi->refill);
	virtnet_del_vqs(vi);
	if (vi->alloc_frag.page)
		put_page(vi->alloc_frag.page);
free_index:
	free_percpu(vi->vq_index);
free_stats:
	free_percpu(vi->stats);
free:
	free_netdev(dev);
	return err;
}

static void remove_vq_common(struct virtnet_info *vi)
{
	vi->vdev->config->reset(vi->vdev);

	/* Free unused buffers in both send and recv, if any. */
	free_unused_bufs(vi);

	free_receive_bufs(vi);

	virtnet_del_vqs(vi);
}

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

	unregister_hotcpu_notifier(&vi->nb);

	/* Prevent config work handler from accessing the device. */
	mutex_lock(&vi->config_lock);
	vi->config_enable = false;
	mutex_unlock(&vi->config_lock);

	unregister_netdev(vi->dev);

	remove_vq_common(vi);
	if (vi->alloc_frag.page)
		put_page(vi->alloc_frag.page);

	flush_work(&vi->config_work);

	free_percpu(vi->vq_index);
	free_percpu(vi->stats);
	free_netdev(vi->dev);
}

#ifdef CONFIG_PM
static int virtnet_freeze(struct virtio_device *vdev)
{
	struct virtnet_info *vi = vdev->priv;
	int i;

	unregister_hotcpu_notifier(&vi->nb);

	/* Prevent config work handler from accessing the device */
	mutex_lock(&vi->config_lock);
	vi->config_enable = false;
	mutex_unlock(&vi->config_lock);

	netif_device_detach(vi->dev);
	cancel_delayed_work_sync(&vi->refill);

	if (netif_running(vi->dev))
		for (i = 0; i < vi->max_queue_pairs; i++) {
			napi_disable(&vi->rq[i].napi);
			netif_napi_del(&vi->rq[i].napi);
		}

	remove_vq_common(vi);

	flush_work(&vi->config_work);

	return 0;
}

static int virtnet_restore(struct virtio_device *vdev)
{
	struct virtnet_info *vi = vdev->priv;
	int err, i;

	err = init_vqs(vi);
	if (err)
		return err;

	if (netif_running(vi->dev))
		for (i = 0; i < vi->max_queue_pairs; i++)
			virtnet_napi_enable(&vi->rq[i]);

	netif_device_attach(vi->dev);

	for (i = 0; i < vi->curr_queue_pairs; i++)
		if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
			schedule_delayed_work(&vi->refill, 0);

	mutex_lock(&vi->config_lock);
	vi->config_enable = true;
	mutex_unlock(&vi->config_lock);

	rtnl_lock();
	virtnet_set_queues(vi, vi->curr_queue_pairs);
	rtnl_unlock();

	err = register_hotcpu_notifier(&vi->nb);
	if (err)
		return err;

	return 0;
}
#endif

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, VIRTIO_NET_F_GUEST_UFO,
	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_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ,
	VIRTIO_NET_F_CTRL_MAC_ADDR,
	VIRTIO_F_ANY_LAYOUT,
};

static struct virtio_driver virtio_net_driver = {
	.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 =	virtnet_remove,
	.config_changed = virtnet_config_changed,
#ifdef CONFIG_PM
	.freeze =	virtnet_freeze,
	.restore =	virtnet_restore,
#endif
};

module_virtio_driver(virtio_net_driver);

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