aboutsummaryrefslogtreecommitdiff
path: root/hw/net/virtio-net.c
blob: 4d2cdd23d50ba1e2456c5f3e0e5fa7927b1fbfa3 (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
/*
 * Virtio Network Device
 *
 * Copyright IBM, Corp. 2007
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include "qemu/iov.h"
#include "hw/virtio/virtio.h"
#include "net/net.h"
#include "net/checksum.h"
#include "net/tap.h"
#include "qemu/error-report.h"
#include "qemu/timer.h"
#include "hw/virtio/virtio-net.h"
#include "net/vhost_net.h"
#include "hw/virtio/virtio-bus.h"

#define VIRTIO_NET_VM_VERSION    11

#define MAC_TABLE_ENTRIES    64
#define MAX_VLAN    (1 << 12)   /* Per 802.1Q definition */

/*
 * Calculate the number of bytes up to and including the given 'field' of
 * 'container'.
 */
#define endof(container, field) \
    (offsetof(container, field) + sizeof(((container *)0)->field))

typedef struct VirtIOFeature {
    uint32_t flags;
    size_t end;
} VirtIOFeature;

static VirtIOFeature feature_sizes[] = {
    {.flags = 1 << VIRTIO_NET_F_MAC,
     .end = endof(struct virtio_net_config, mac)},
    {.flags = 1 << VIRTIO_NET_F_STATUS,
     .end = endof(struct virtio_net_config, status)},
    {.flags = 1 << VIRTIO_NET_F_MQ,
     .end = endof(struct virtio_net_config, max_virtqueue_pairs)},
    {}
};

static VirtIONetQueue *virtio_net_get_subqueue(NetClientState *nc)
{
    VirtIONet *n = qemu_get_nic_opaque(nc);

    return &n->vqs[nc->queue_index];
}

static int vq2q(int queue_index)
{
    return queue_index / 2;
}

/* TODO
 * - we could suppress RX interrupt if we were so inclined.
 */

static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config)
{
    VirtIONet *n = VIRTIO_NET(vdev);
    struct virtio_net_config netcfg;

    stw_p(&netcfg.status, n->status);
    stw_p(&netcfg.max_virtqueue_pairs, n->max_queues);
    memcpy(netcfg.mac, n->mac, ETH_ALEN);
    memcpy(config, &netcfg, n->config_size);
}

static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config)
{
    VirtIONet *n = VIRTIO_NET(vdev);
    struct virtio_net_config netcfg = {};

    memcpy(&netcfg, config, n->config_size);

    if (!(vdev->guest_features >> VIRTIO_NET_F_CTRL_MAC_ADDR & 1) &&
        memcmp(netcfg.mac, n->mac, ETH_ALEN)) {
        memcpy(n->mac, netcfg.mac, ETH_ALEN);
        qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac);
    }
}

static bool virtio_net_started(VirtIONet *n, uint8_t status)
{
    VirtIODevice *vdev = VIRTIO_DEVICE(n);
    return (status & VIRTIO_CONFIG_S_DRIVER_OK) &&
        (n->status & VIRTIO_NET_S_LINK_UP) && vdev->vm_running;
}

static void virtio_net_vhost_status(VirtIONet *n, uint8_t status)
{
    VirtIODevice *vdev = VIRTIO_DEVICE(n);
    NetClientState *nc = qemu_get_queue(n->nic);
    int queues = n->multiqueue ? n->max_queues : 1;

    if (!nc->peer) {
        return;
    }
    if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
        return;
    }

    if (!tap_get_vhost_net(nc->peer)) {
        return;
    }

    if (!!n->vhost_started == virtio_net_started(n, status) &&
                              !nc->peer->link_down) {
        return;
    }
    if (!n->vhost_started) {
        int r;
        if (!vhost_net_query(tap_get_vhost_net(nc->peer), vdev)) {
            return;
        }
        n->vhost_started = 1;
        r = vhost_net_start(vdev, n->nic->ncs, queues);
        if (r < 0) {
            error_report("unable to start vhost net: %d: "
                         "falling back on userspace virtio", -r);
            n->vhost_started = 0;
        }
    } else {
        vhost_net_stop(vdev, n->nic->ncs, queues);
        n->vhost_started = 0;
    }
}

static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
{
    VirtIONet *n = VIRTIO_NET(vdev);
    VirtIONetQueue *q;
    int i;
    uint8_t queue_status;

    virtio_net_vhost_status(n, status);

    for (i = 0; i < n->max_queues; i++) {
        q = &n->vqs[i];

        if ((!n->multiqueue && i != 0) || i >= n->curr_queues) {
            queue_status = 0;
        } else {
            queue_status = status;
        }

        if (!q->tx_waiting) {
            continue;
        }

        if (virtio_net_started(n, queue_status) && !n->vhost_started) {
            if (q->tx_timer) {
                qemu_mod_timer(q->tx_timer,
                               qemu_get_clock_ns(vm_clock) + n->tx_timeout);
            } else {
                qemu_bh_schedule(q->tx_bh);
            }
        } else {
            if (q->tx_timer) {
                qemu_del_timer(q->tx_timer);
            } else {
                qemu_bh_cancel(q->tx_bh);
            }
        }
    }
}

static void virtio_net_set_link_status(NetClientState *nc)
{
    VirtIONet *n = qemu_get_nic_opaque(nc);
    VirtIODevice *vdev = VIRTIO_DEVICE(n);
    uint16_t old_status = n->status;

    if (nc->link_down)
        n->status &= ~VIRTIO_NET_S_LINK_UP;
    else
        n->status |= VIRTIO_NET_S_LINK_UP;

    if (n->status != old_status)
        virtio_notify_config(vdev);

    virtio_net_set_status(vdev, vdev->status);
}

static void virtio_net_reset(VirtIODevice *vdev)
{
    VirtIONet *n = VIRTIO_NET(vdev);

    /* Reset back to compatibility mode */
    n->promisc = 1;
    n->allmulti = 0;
    n->alluni = 0;
    n->nomulti = 0;
    n->nouni = 0;
    n->nobcast = 0;
    /* multiqueue is disabled by default */
    n->curr_queues = 1;

    /* Flush any MAC and VLAN filter table state */
    n->mac_table.in_use = 0;
    n->mac_table.first_multi = 0;
    n->mac_table.multi_overflow = 0;
    n->mac_table.uni_overflow = 0;
    memset(n->mac_table.macs, 0, MAC_TABLE_ENTRIES * ETH_ALEN);
    memcpy(&n->mac[0], &n->nic->conf->macaddr, sizeof(n->mac));
    memset(n->vlans, 0, MAX_VLAN >> 3);
}

static void peer_test_vnet_hdr(VirtIONet *n)
{
    NetClientState *nc = qemu_get_queue(n->nic);
    if (!nc->peer) {
        return;
    }

    if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
        return;
    }

    n->has_vnet_hdr = tap_has_vnet_hdr(nc->peer);
}

static int peer_has_vnet_hdr(VirtIONet *n)
{
    return n->has_vnet_hdr;
}

static int peer_has_ufo(VirtIONet *n)
{
    if (!peer_has_vnet_hdr(n))
        return 0;

    n->has_ufo = tap_has_ufo(qemu_get_queue(n->nic)->peer);

    return n->has_ufo;
}

static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs)
{
    int i;
    NetClientState *nc;

    n->mergeable_rx_bufs = mergeable_rx_bufs;

    n->guest_hdr_len = n->mergeable_rx_bufs ?
        sizeof(struct virtio_net_hdr_mrg_rxbuf) : sizeof(struct virtio_net_hdr);

    for (i = 0; i < n->max_queues; i++) {
        nc = qemu_get_subqueue(n->nic, i);

        if (peer_has_vnet_hdr(n) &&
            tap_has_vnet_hdr_len(nc->peer, n->guest_hdr_len)) {
            tap_set_vnet_hdr_len(nc->peer, n->guest_hdr_len);
            n->host_hdr_len = n->guest_hdr_len;
        }
    }
}

static int peer_attach(VirtIONet *n, int index)
{
    NetClientState *nc = qemu_get_subqueue(n->nic, index);

    if (!nc->peer) {
        return 0;
    }

    if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
        return 0;
    }

    return tap_enable(nc->peer);
}

static int peer_detach(VirtIONet *n, int index)
{
    NetClientState *nc = qemu_get_subqueue(n->nic, index);

    if (!nc->peer) {
        return 0;
    }

    if (nc->peer->info->type !=  NET_CLIENT_OPTIONS_KIND_TAP) {
        return 0;
    }

    return tap_disable(nc->peer);
}

static void virtio_net_set_queues(VirtIONet *n)
{
    int i;

    for (i = 0; i < n->max_queues; i++) {
        if (i < n->curr_queues) {
            assert(!peer_attach(n, i));
        } else {
            assert(!peer_detach(n, i));
        }
    }
}

static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue, int ctrl);

static uint32_t virtio_net_get_features(VirtIODevice *vdev, uint32_t features)
{
    VirtIONet *n = VIRTIO_NET(vdev);
    NetClientState *nc = qemu_get_queue(n->nic);

    features |= (1 << VIRTIO_NET_F_MAC);

    if (!peer_has_vnet_hdr(n)) {
        features &= ~(0x1 << VIRTIO_NET_F_CSUM);
        features &= ~(0x1 << VIRTIO_NET_F_HOST_TSO4);
        features &= ~(0x1 << VIRTIO_NET_F_HOST_TSO6);
        features &= ~(0x1 << VIRTIO_NET_F_HOST_ECN);

        features &= ~(0x1 << VIRTIO_NET_F_GUEST_CSUM);
        features &= ~(0x1 << VIRTIO_NET_F_GUEST_TSO4);
        features &= ~(0x1 << VIRTIO_NET_F_GUEST_TSO6);
        features &= ~(0x1 << VIRTIO_NET_F_GUEST_ECN);
    }

    if (!peer_has_vnet_hdr(n) || !peer_has_ufo(n)) {
        features &= ~(0x1 << VIRTIO_NET_F_GUEST_UFO);
        features &= ~(0x1 << VIRTIO_NET_F_HOST_UFO);
    }

    if (!nc->peer || nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
        return features;
    }
    if (!tap_get_vhost_net(nc->peer)) {
        return features;
    }
    return vhost_net_get_features(tap_get_vhost_net(nc->peer), features);
}

static uint32_t virtio_net_bad_features(VirtIODevice *vdev)
{
    uint32_t features = 0;

    /* Linux kernel 2.6.25.  It understood MAC (as everyone must),
     * but also these: */
    features |= (1 << VIRTIO_NET_F_MAC);
    features |= (1 << VIRTIO_NET_F_CSUM);
    features |= (1 << VIRTIO_NET_F_HOST_TSO4);
    features |= (1 << VIRTIO_NET_F_HOST_TSO6);
    features |= (1 << VIRTIO_NET_F_HOST_ECN);

    return features;
}

static void virtio_net_set_features(VirtIODevice *vdev, uint32_t features)
{
    VirtIONet *n = VIRTIO_NET(vdev);
    int i;

    virtio_net_set_multiqueue(n, !!(features & (1 << VIRTIO_NET_F_MQ)),
                              !!(features & (1 << VIRTIO_NET_F_CTRL_VQ)));

    virtio_net_set_mrg_rx_bufs(n, !!(features & (1 << VIRTIO_NET_F_MRG_RXBUF)));

    if (n->has_vnet_hdr) {
        tap_set_offload(qemu_get_subqueue(n->nic, 0)->peer,
                        (features >> VIRTIO_NET_F_GUEST_CSUM) & 1,
                        (features >> VIRTIO_NET_F_GUEST_TSO4) & 1,
                        (features >> VIRTIO_NET_F_GUEST_TSO6) & 1,
                        (features >> VIRTIO_NET_F_GUEST_ECN)  & 1,
                        (features >> VIRTIO_NET_F_GUEST_UFO)  & 1);
    }

    for (i = 0;  i < n->max_queues; i++) {
        NetClientState *nc = qemu_get_subqueue(n->nic, i);

        if (!nc->peer || nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
            continue;
        }
        if (!tap_get_vhost_net(nc->peer)) {
            continue;
        }
        vhost_net_ack_features(tap_get_vhost_net(nc->peer), features);
    }
}

static int virtio_net_handle_rx_mode(VirtIONet *n, uint8_t cmd,
                                     struct iovec *iov, unsigned int iov_cnt)
{
    uint8_t on;
    size_t s;

    s = iov_to_buf(iov, iov_cnt, 0, &on, sizeof(on));
    if (s != sizeof(on)) {
        return VIRTIO_NET_ERR;
    }

    if (cmd == VIRTIO_NET_CTRL_RX_PROMISC) {
        n->promisc = on;
    } else if (cmd == VIRTIO_NET_CTRL_RX_ALLMULTI) {
        n->allmulti = on;
    } else if (cmd == VIRTIO_NET_CTRL_RX_ALLUNI) {
        n->alluni = on;
    } else if (cmd == VIRTIO_NET_CTRL_RX_NOMULTI) {
        n->nomulti = on;
    } else if (cmd == VIRTIO_NET_CTRL_RX_NOUNI) {
        n->nouni = on;
    } else if (cmd == VIRTIO_NET_CTRL_RX_NOBCAST) {
        n->nobcast = on;
    } else {
        return VIRTIO_NET_ERR;
    }

    return VIRTIO_NET_OK;
}

static int virtio_net_handle_mac(VirtIONet *n, uint8_t cmd,
                                 struct iovec *iov, unsigned int iov_cnt)
{
    struct virtio_net_ctrl_mac mac_data;
    size_t s;

    if (cmd == VIRTIO_NET_CTRL_MAC_ADDR_SET) {
        if (iov_size(iov, iov_cnt) != sizeof(n->mac)) {
            return VIRTIO_NET_ERR;
        }
        s = iov_to_buf(iov, iov_cnt, 0, &n->mac, sizeof(n->mac));
        assert(s == sizeof(n->mac));
        qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac);
        return VIRTIO_NET_OK;
    }

    if (cmd != VIRTIO_NET_CTRL_MAC_TABLE_SET) {
        return VIRTIO_NET_ERR;
    }

    n->mac_table.in_use = 0;
    n->mac_table.first_multi = 0;
    n->mac_table.uni_overflow = 0;
    n->mac_table.multi_overflow = 0;
    memset(n->mac_table.macs, 0, MAC_TABLE_ENTRIES * ETH_ALEN);

    s = iov_to_buf(iov, iov_cnt, 0, &mac_data.entries,
                   sizeof(mac_data.entries));
    mac_data.entries = ldl_p(&mac_data.entries);
    if (s != sizeof(mac_data.entries)) {
        return VIRTIO_NET_ERR;
    }
    iov_discard_front(&iov, &iov_cnt, s);

    if (mac_data.entries * ETH_ALEN > iov_size(iov, iov_cnt)) {
        return VIRTIO_NET_ERR;
    }

    if (mac_data.entries <= MAC_TABLE_ENTRIES) {
        s = iov_to_buf(iov, iov_cnt, 0, n->mac_table.macs,
                       mac_data.entries * ETH_ALEN);
        if (s != mac_data.entries * ETH_ALEN) {
            return VIRTIO_NET_ERR;
        }
        n->mac_table.in_use += mac_data.entries;
    } else {
        n->mac_table.uni_overflow = 1;
    }

    iov_discard_front(&iov, &iov_cnt, mac_data.entries * ETH_ALEN);

    n->mac_table.first_multi = n->mac_table.in_use;

    s = iov_to_buf(iov, iov_cnt, 0, &mac_data.entries,
                   sizeof(mac_data.entries));
    mac_data.entries = ldl_p(&mac_data.entries);
    if (s != sizeof(mac_data.entries)) {
        return VIRTIO_NET_ERR;
    }

    iov_discard_front(&iov, &iov_cnt, s);

    if (mac_data.entries * ETH_ALEN != iov_size(iov, iov_cnt)) {
        return VIRTIO_NET_ERR;
    }

    if (n->mac_table.in_use + mac_data.entries <= MAC_TABLE_ENTRIES) {
        s = iov_to_buf(iov, iov_cnt, 0, n->mac_table.macs,
                       mac_data.entries * ETH_ALEN);
        if (s != mac_data.entries * ETH_ALEN) {
            return VIRTIO_NET_ERR;
        }
        n->mac_table.in_use += mac_data.entries;
    } else {
        n->mac_table.multi_overflow = 1;
    }

    return VIRTIO_NET_OK;
}

static int virtio_net_handle_vlan_table(VirtIONet *n, uint8_t cmd,
                                        struct iovec *iov, unsigned int iov_cnt)
{
    uint16_t vid;
    size_t s;

    s = iov_to_buf(iov, iov_cnt, 0, &vid, sizeof(vid));
    vid = lduw_p(&vid);
    if (s != sizeof(vid)) {
        return VIRTIO_NET_ERR;
    }

    if (vid >= MAX_VLAN)
        return VIRTIO_NET_ERR;

    if (cmd == VIRTIO_NET_CTRL_VLAN_ADD)
        n->vlans[vid >> 5] |= (1U << (vid & 0x1f));
    else if (cmd == VIRTIO_NET_CTRL_VLAN_DEL)
        n->vlans[vid >> 5] &= ~(1U << (vid & 0x1f));
    else
        return VIRTIO_NET_ERR;

    return VIRTIO_NET_OK;
}

static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd,
                                struct iovec *iov, unsigned int iov_cnt)
{
    VirtIODevice *vdev = VIRTIO_DEVICE(n);
    struct virtio_net_ctrl_mq mq;
    size_t s;
    uint16_t queues;

    s = iov_to_buf(iov, iov_cnt, 0, &mq, sizeof(mq));
    if (s != sizeof(mq)) {
        return VIRTIO_NET_ERR;
    }

    if (cmd != VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET) {
        return VIRTIO_NET_ERR;
    }

    queues = lduw_p(&mq.virtqueue_pairs);

    if (queues < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN ||
        queues > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX ||
        queues > n->max_queues ||
        !n->multiqueue) {
        return VIRTIO_NET_ERR;
    }

    n->curr_queues = queues;
    /* stop the backend before changing the number of queues to avoid handling a
     * disabled queue */
    virtio_net_set_status(vdev, vdev->status);
    virtio_net_set_queues(n);

    return VIRTIO_NET_OK;
}
static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
{
    VirtIONet *n = VIRTIO_NET(vdev);
    struct virtio_net_ctrl_hdr ctrl;
    virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
    VirtQueueElement elem;
    size_t s;
    struct iovec *iov;
    unsigned int iov_cnt;

    while (virtqueue_pop(vq, &elem)) {
        if (iov_size(elem.in_sg, elem.in_num) < sizeof(status) ||
            iov_size(elem.out_sg, elem.out_num) < sizeof(ctrl)) {
            error_report("virtio-net ctrl missing headers");
            exit(1);
        }

        iov = elem.out_sg;
        iov_cnt = elem.out_num;
        s = iov_to_buf(iov, iov_cnt, 0, &ctrl, sizeof(ctrl));
        iov_discard_front(&iov, &iov_cnt, sizeof(ctrl));
        if (s != sizeof(ctrl)) {
            status = VIRTIO_NET_ERR;
        } else if (ctrl.class == VIRTIO_NET_CTRL_RX) {
            status = virtio_net_handle_rx_mode(n, ctrl.cmd, iov, iov_cnt);
        } else if (ctrl.class == VIRTIO_NET_CTRL_MAC) {
            status = virtio_net_handle_mac(n, ctrl.cmd, iov, iov_cnt);
        } else if (ctrl.class == VIRTIO_NET_CTRL_VLAN) {
            status = virtio_net_handle_vlan_table(n, ctrl.cmd, iov, iov_cnt);
        } else if (ctrl.class == VIRTIO_NET_CTRL_MQ) {
            status = virtio_net_handle_mq(n, ctrl.cmd, iov, iov_cnt);
        }

        s = iov_from_buf(elem.in_sg, elem.in_num, 0, &status, sizeof(status));
        assert(s == sizeof(status));

        virtqueue_push(vq, &elem, sizeof(status));
        virtio_notify(vdev, vq);
    }
}

/* RX */

static void virtio_net_handle_rx(VirtIODevice *vdev, VirtQueue *vq)
{
    VirtIONet *n = VIRTIO_NET(vdev);
    int queue_index = vq2q(virtio_get_queue_index(vq));

    qemu_flush_queued_packets(qemu_get_subqueue(n->nic, queue_index));
}

static int virtio_net_can_receive(NetClientState *nc)
{
    VirtIONet *n = qemu_get_nic_opaque(nc);
    VirtIODevice *vdev = VIRTIO_DEVICE(n);
    VirtIONetQueue *q = virtio_net_get_subqueue(nc);

    if (!vdev->vm_running) {
        return 0;
    }

    if (nc->queue_index >= n->curr_queues) {
        return 0;
    }

    if (!virtio_queue_ready(q->rx_vq) ||
        !(vdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) {
        return 0;
    }

    return 1;
}

static int virtio_net_has_buffers(VirtIONetQueue *q, int bufsize)
{
    VirtIONet *n = q->n;
    if (virtio_queue_empty(q->rx_vq) ||
        (n->mergeable_rx_bufs &&
         !virtqueue_avail_bytes(q->rx_vq, bufsize, 0))) {
        virtio_queue_set_notification(q->rx_vq, 1);

        /* To avoid a race condition where the guest has made some buffers
         * available after the above check but before notification was
         * enabled, check for available buffers again.
         */
        if (virtio_queue_empty(q->rx_vq) ||
            (n->mergeable_rx_bufs &&
             !virtqueue_avail_bytes(q->rx_vq, bufsize, 0))) {
            return 0;
        }
    }

    virtio_queue_set_notification(q->rx_vq, 0);
    return 1;
}

/* dhclient uses AF_PACKET but doesn't pass auxdata to the kernel so
 * it never finds out that the packets don't have valid checksums.  This
 * causes dhclient to get upset.  Fedora's carried a patch for ages to
 * fix this with Xen but it hasn't appeared in an upstream release of
 * dhclient yet.
 *
 * To avoid breaking existing guests, we catch udp packets and add
 * checksums.  This is terrible but it's better than hacking the guest
 * kernels.
 *
 * N.B. if we introduce a zero-copy API, this operation is no longer free so
 * we should provide a mechanism to disable it to avoid polluting the host
 * cache.
 */
static void work_around_broken_dhclient(struct virtio_net_hdr *hdr,
                                        uint8_t *buf, size_t size)
{
    if ((hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && /* missing csum */
        (size > 27 && size < 1500) && /* normal sized MTU */
        (buf[12] == 0x08 && buf[13] == 0x00) && /* ethertype == IPv4 */
        (buf[23] == 17) && /* ip.protocol == UDP */
        (buf[34] == 0 && buf[35] == 67)) { /* udp.srcport == bootps */
        net_checksum_calculate(buf, size);
        hdr->flags &= ~VIRTIO_NET_HDR_F_NEEDS_CSUM;
    }
}

static void receive_header(VirtIONet *n, const struct iovec *iov, int iov_cnt,
                           const void *buf, size_t size)
{
    if (n->has_vnet_hdr) {
        /* FIXME this cast is evil */
        void *wbuf = (void *)buf;
        work_around_broken_dhclient(wbuf, wbuf + n->host_hdr_len,
                                    size - n->host_hdr_len);
        iov_from_buf(iov, iov_cnt, 0, buf, sizeof(struct virtio_net_hdr));
    } else {
        struct virtio_net_hdr hdr = {
            .flags = 0,
            .gso_type = VIRTIO_NET_HDR_GSO_NONE
        };
        iov_from_buf(iov, iov_cnt, 0, &hdr, sizeof hdr);
    }
}

static int receive_filter(VirtIONet *n, const uint8_t *buf, int size)
{
    static const uint8_t bcast[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
    static const uint8_t vlan[] = {0x81, 0x00};
    uint8_t *ptr = (uint8_t *)buf;
    int i;

    if (n->promisc)
        return 1;

    ptr += n->host_hdr_len;

    if (!memcmp(&ptr[12], vlan, sizeof(vlan))) {
        int vid = be16_to_cpup((uint16_t *)(ptr + 14)) & 0xfff;
        if (!(n->vlans[vid >> 5] & (1U << (vid & 0x1f))))
            return 0;
    }

    if (ptr[0] & 1) { // multicast
        if (!memcmp(ptr, bcast, sizeof(bcast))) {
            return !n->nobcast;
        } else if (n->nomulti) {
            return 0;
        } else if (n->allmulti || n->mac_table.multi_overflow) {
            return 1;
        }

        for (i = n->mac_table.first_multi; i < n->mac_table.in_use; i++) {
            if (!memcmp(ptr, &n->mac_table.macs[i * ETH_ALEN], ETH_ALEN)) {
                return 1;
            }
        }
    } else { // unicast
        if (n->nouni) {
            return 0;
        } else if (n->alluni || n->mac_table.uni_overflow) {
            return 1;
        } else if (!memcmp(ptr, n->mac, ETH_ALEN)) {
            return 1;
        }

        for (i = 0; i < n->mac_table.first_multi; i++) {
            if (!memcmp(ptr, &n->mac_table.macs[i * ETH_ALEN], ETH_ALEN)) {
                return 1;
            }
        }
    }

    return 0;
}

static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, size_t size)
{
    VirtIONet *n = qemu_get_nic_opaque(nc);
    VirtIONetQueue *q = virtio_net_get_subqueue(nc);
    VirtIODevice *vdev = VIRTIO_DEVICE(n);
    struct iovec mhdr_sg[VIRTQUEUE_MAX_SIZE];
    struct virtio_net_hdr_mrg_rxbuf mhdr;
    unsigned mhdr_cnt = 0;
    size_t offset, i, guest_offset;

    if (!virtio_net_can_receive(nc)) {
        return -1;
    }

    /* hdr_len refers to the header we supply to the guest */
    if (!virtio_net_has_buffers(q, size + n->guest_hdr_len - n->host_hdr_len)) {
        return 0;
    }

    if (!receive_filter(n, buf, size))
        return size;

    offset = i = 0;

    while (offset < size) {
        VirtQueueElement elem;
        int len, total;
        const struct iovec *sg = elem.in_sg;

        total = 0;

        if (virtqueue_pop(q->rx_vq, &elem) == 0) {
            if (i == 0)
                return -1;
            error_report("virtio-net unexpected empty queue: "
                    "i %zd mergeable %d offset %zd, size %zd, "
                    "guest hdr len %zd, host hdr len %zd guest features 0x%x",
                    i, n->mergeable_rx_bufs, offset, size,
                    n->guest_hdr_len, n->host_hdr_len, vdev->guest_features);
            exit(1);
        }

        if (elem.in_num < 1) {
            error_report("virtio-net receive queue contains no in buffers");
            exit(1);
        }

        if (i == 0) {
            assert(offset == 0);
            if (n->mergeable_rx_bufs) {
                mhdr_cnt = iov_copy(mhdr_sg, ARRAY_SIZE(mhdr_sg),
                                    sg, elem.in_num,
                                    offsetof(typeof(mhdr), num_buffers),
                                    sizeof(mhdr.num_buffers));
            }

            receive_header(n, sg, elem.in_num, buf, size);
            offset = n->host_hdr_len;
            total += n->guest_hdr_len;
            guest_offset = n->guest_hdr_len;
        } else {
            guest_offset = 0;
        }

        /* copy in packet.  ugh */
        len = iov_from_buf(sg, elem.in_num, guest_offset,
                           buf + offset, size - offset);
        total += len;
        offset += len;
        /* If buffers can't be merged, at this point we
         * must have consumed the complete packet.
         * Otherwise, drop it. */
        if (!n->mergeable_rx_bufs && offset < size) {
#if 0
            error_report("virtio-net truncated non-mergeable packet: "
                         "i %zd mergeable %d offset %zd, size %zd, "
                         "guest hdr len %zd, host hdr len %zd",
                         i, n->mergeable_rx_bufs,
                         offset, size, n->guest_hdr_len, n->host_hdr_len);
#endif
            return size;
        }

        /* signal other side */
        virtqueue_fill(q->rx_vq, &elem, total, i++);
    }

    if (mhdr_cnt) {
        stw_p(&mhdr.num_buffers, i);
        iov_from_buf(mhdr_sg, mhdr_cnt,
                     0,
                     &mhdr.num_buffers, sizeof mhdr.num_buffers);
    }

    virtqueue_flush(q->rx_vq, i);
    virtio_notify(vdev, q->rx_vq);

    return size;
}

static int32_t virtio_net_flush_tx(VirtIONetQueue *q);

static void virtio_net_tx_complete(NetClientState *nc, ssize_t len)
{
    VirtIONet *n = qemu_get_nic_opaque(nc);
    VirtIONetQueue *q = virtio_net_get_subqueue(nc);
    VirtIODevice *vdev = VIRTIO_DEVICE(n);

    virtqueue_push(q->tx_vq, &q->async_tx.elem, 0);
    virtio_notify(vdev, q->tx_vq);

    q->async_tx.elem.out_num = q->async_tx.len = 0;

    virtio_queue_set_notification(q->tx_vq, 1);
    virtio_net_flush_tx(q);
}

/* TX */
static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
{
    VirtIONet *n = q->n;
    VirtIODevice *vdev = VIRTIO_DEVICE(n);
    VirtQueueElement elem;
    int32_t num_packets = 0;
    int queue_index = vq2q(virtio_get_queue_index(q->tx_vq));
    if (!(vdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) {
        return num_packets;
    }

    assert(vdev->vm_running);

    if (q->async_tx.elem.out_num) {
        virtio_queue_set_notification(q->tx_vq, 0);
        return num_packets;
    }

    while (virtqueue_pop(q->tx_vq, &elem)) {
        ssize_t ret, len;
        unsigned int out_num = elem.out_num;
        struct iovec *out_sg = &elem.out_sg[0];
        struct iovec sg[VIRTQUEUE_MAX_SIZE];

        if (out_num < 1) {
            error_report("virtio-net header not in first element");
            exit(1);
        }

        /*
         * If host wants to see the guest header as is, we can
         * pass it on unchanged. Otherwise, copy just the parts
         * that host is interested in.
         */
        assert(n->host_hdr_len <= n->guest_hdr_len);
        if (n->host_hdr_len != n->guest_hdr_len) {
            unsigned sg_num = iov_copy(sg, ARRAY_SIZE(sg),
                                       out_sg, out_num,
                                       0, n->host_hdr_len);
            sg_num += iov_copy(sg + sg_num, ARRAY_SIZE(sg) - sg_num,
                             out_sg, out_num,
                             n->guest_hdr_len, -1);
            out_num = sg_num;
            out_sg = sg;
        }

        len = n->guest_hdr_len;

        ret = qemu_sendv_packet_async(qemu_get_subqueue(n->nic, queue_index),
                                      out_sg, out_num, virtio_net_tx_complete);
        if (ret == 0) {
            virtio_queue_set_notification(q->tx_vq, 0);
            q->async_tx.elem = elem;
            q->async_tx.len  = len;
            return -EBUSY;
        }

        len += ret;

        virtqueue_push(q->tx_vq, &elem, 0);
        virtio_notify(vdev, q->tx_vq);

        if (++num_packets >= n->tx_burst) {
            break;
        }
    }
    return num_packets;
}

static void virtio_net_handle_tx_timer(VirtIODevice *vdev, VirtQueue *vq)
{
    VirtIONet *n = VIRTIO_NET(vdev);
    VirtIONetQueue *q = &n->vqs[vq2q(virtio_get_queue_index(vq))];

    /* This happens when device was stopped but VCPU wasn't. */
    if (!vdev->vm_running) {
        q->tx_waiting = 1;
        return;
    }

    if (q->tx_waiting) {
        virtio_queue_set_notification(vq, 1);
        qemu_del_timer(q->tx_timer);
        q->tx_waiting = 0;
        virtio_net_flush_tx(q);
    } else {
        qemu_mod_timer(q->tx_timer,
                       qemu_get_clock_ns(vm_clock) + n->tx_timeout);
        q->tx_waiting = 1;
        virtio_queue_set_notification(vq, 0);
    }
}

static void virtio_net_handle_tx_bh(VirtIODevice *vdev, VirtQueue *vq)
{
    VirtIONet *n = VIRTIO_NET(vdev);
    VirtIONetQueue *q = &n->vqs[vq2q(virtio_get_queue_index(vq))];

    if (unlikely(q->tx_waiting)) {
        return;
    }
    q->tx_waiting = 1;
    /* This happens when device was stopped but VCPU wasn't. */
    if (!vdev->vm_running) {
        return;
    }
    virtio_queue_set_notification(vq, 0);
    qemu_bh_schedule(q->tx_bh);
}

static void virtio_net_tx_timer(void *opaque)
{
    VirtIONetQueue *q = opaque;
    VirtIONet *n = q->n;
    VirtIODevice *vdev = VIRTIO_DEVICE(n);
    assert(vdev->vm_running);

    q->tx_waiting = 0;

    /* Just in case the driver is not ready on more */
    if (!(vdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) {
        return;
    }

    virtio_queue_set_notification(q->tx_vq, 1);
    virtio_net_flush_tx(q);
}

static void virtio_net_tx_bh(void *opaque)
{
    VirtIONetQueue *q = opaque;
    VirtIONet *n = q->n;
    VirtIODevice *vdev = VIRTIO_DEVICE(n);
    int32_t ret;

    assert(vdev->vm_running);

    q->tx_waiting = 0;

    /* Just in case the driver is not ready on more */
    if (unlikely(!(vdev->status & VIRTIO_CONFIG_S_DRIVER_OK))) {
        return;
    }

    ret = virtio_net_flush_tx(q);
    if (ret == -EBUSY) {
        return; /* Notification re-enable handled by tx_complete */
    }

    /* If we flush a full burst of packets, assume there are
     * more coming and immediately reschedule */
    if (ret >= n->tx_burst) {
        qemu_bh_schedule(q->tx_bh);
        q->tx_waiting = 1;
        return;
    }

    /* If less than a full burst, re-enable notification and flush
     * anything that may have come in while we weren't looking.  If
     * we find something, assume the guest is still active and reschedule */
    virtio_queue_set_notification(q->tx_vq, 1);
    if (virtio_net_flush_tx(q) > 0) {
        virtio_queue_set_notification(q->tx_vq, 0);
        qemu_bh_schedule(q->tx_bh);
        q->tx_waiting = 1;
    }
}

static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue, int ctrl)
{
    VirtIODevice *vdev = VIRTIO_DEVICE(n);
    int i, max = multiqueue ? n->max_queues : 1;

    n->multiqueue = multiqueue;

    for (i = 2; i <= n->max_queues * 2 + 1; i++) {
        virtio_del_queue(vdev, i);
    }

    for (i = 1; i < max; i++) {
        n->vqs[i].rx_vq = virtio_add_queue(vdev, 256, virtio_net_handle_rx);
        if (n->vqs[i].tx_timer) {
            n->vqs[i].tx_vq =
                virtio_add_queue(vdev, 256, virtio_net_handle_tx_timer);
            n->vqs[i].tx_timer = qemu_new_timer_ns(vm_clock,
                                                   virtio_net_tx_timer,
                                                   &n->vqs[i]);
        } else {
            n->vqs[i].tx_vq =
                virtio_add_queue(vdev, 256, virtio_net_handle_tx_bh);
            n->vqs[i].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[i]);
        }

        n->vqs[i].tx_waiting = 0;
        n->vqs[i].n = n;
    }

    if (ctrl) {
        n->ctrl_vq = virtio_add_queue(vdev, 64, virtio_net_handle_ctrl);
    }

    virtio_net_set_queues(n);
}

static void virtio_net_save(QEMUFile *f, void *opaque)
{
    int i;
    VirtIONet *n = opaque;
    VirtIODevice *vdev = VIRTIO_DEVICE(n);

    /* At this point, backend must be stopped, otherwise
     * it might keep writing to memory. */
    assert(!n->vhost_started);
    virtio_save(vdev, f);

    qemu_put_buffer(f, n->mac, ETH_ALEN);
    qemu_put_be32(f, n->vqs[0].tx_waiting);
    qemu_put_be32(f, n->mergeable_rx_bufs);
    qemu_put_be16(f, n->status);
    qemu_put_byte(f, n->promisc);
    qemu_put_byte(f, n->allmulti);
    qemu_put_be32(f, n->mac_table.in_use);
    qemu_put_buffer(f, n->mac_table.macs, n->mac_table.in_use * ETH_ALEN);
    qemu_put_buffer(f, (uint8_t *)n->vlans, MAX_VLAN >> 3);
    qemu_put_be32(f, n->has_vnet_hdr);
    qemu_put_byte(f, n->mac_table.multi_overflow);
    qemu_put_byte(f, n->mac_table.uni_overflow);
    qemu_put_byte(f, n->alluni);
    qemu_put_byte(f, n->nomulti);
    qemu_put_byte(f, n->nouni);
    qemu_put_byte(f, n->nobcast);
    qemu_put_byte(f, n->has_ufo);
    if (n->max_queues > 1) {
        qemu_put_be16(f, n->max_queues);
        qemu_put_be16(f, n->curr_queues);
        for (i = 1; i < n->curr_queues; i++) {
            qemu_put_be32(f, n->vqs[i].tx_waiting);
        }
    }
}

static int virtio_net_load(QEMUFile *f, void *opaque, int version_id)
{
    VirtIONet *n = opaque;
    VirtIODevice *vdev = VIRTIO_DEVICE(n);
    int ret, i, link_down;

    if (version_id < 2 || version_id > VIRTIO_NET_VM_VERSION)
        return -EINVAL;

    ret = virtio_load(vdev, f);
    if (ret) {
        return ret;
    }

    qemu_get_buffer(f, n->mac, ETH_ALEN);
    n->vqs[0].tx_waiting = qemu_get_be32(f);

    virtio_net_set_mrg_rx_bufs(n, qemu_get_be32(f));

    if (version_id >= 3)
        n->status = qemu_get_be16(f);

    if (version_id >= 4) {
        if (version_id < 8) {
            n->promisc = qemu_get_be32(f);
            n->allmulti = qemu_get_be32(f);
        } else {
            n->promisc = qemu_get_byte(f);
            n->allmulti = qemu_get_byte(f);
        }
    }

    if (version_id >= 5) {
        n->mac_table.in_use = qemu_get_be32(f);
        /* MAC_TABLE_ENTRIES may be different from the saved image */
        if (n->mac_table.in_use <= MAC_TABLE_ENTRIES) {
            qemu_get_buffer(f, n->mac_table.macs,
                            n->mac_table.in_use * ETH_ALEN);
        } else if (n->mac_table.in_use) {
            uint8_t *buf = g_malloc0(n->mac_table.in_use);
            qemu_get_buffer(f, buf, n->mac_table.in_use * ETH_ALEN);
            g_free(buf);
            n->mac_table.multi_overflow = n->mac_table.uni_overflow = 1;
            n->mac_table.in_use = 0;
        }
    }
 
    if (version_id >= 6)
        qemu_get_buffer(f, (uint8_t *)n->vlans, MAX_VLAN >> 3);

    if (version_id >= 7) {
        if (qemu_get_be32(f) && !peer_has_vnet_hdr(n)) {
            error_report("virtio-net: saved image requires vnet_hdr=on");
            return -1;
        }

        if (n->has_vnet_hdr) {
            tap_set_offload(qemu_get_queue(n->nic)->peer,
                    (vdev->guest_features >> VIRTIO_NET_F_GUEST_CSUM) & 1,
                    (vdev->guest_features >> VIRTIO_NET_F_GUEST_TSO4) & 1,
                    (vdev->guest_features >> VIRTIO_NET_F_GUEST_TSO6) & 1,
                    (vdev->guest_features >> VIRTIO_NET_F_GUEST_ECN)  & 1,
                    (vdev->guest_features >> VIRTIO_NET_F_GUEST_UFO)  & 1);
        }
    }

    if (version_id >= 9) {
        n->mac_table.multi_overflow = qemu_get_byte(f);
        n->mac_table.uni_overflow = qemu_get_byte(f);
    }

    if (version_id >= 10) {
        n->alluni = qemu_get_byte(f);
        n->nomulti = qemu_get_byte(f);
        n->nouni = qemu_get_byte(f);
        n->nobcast = qemu_get_byte(f);
    }

    if (version_id >= 11) {
        if (qemu_get_byte(f) && !peer_has_ufo(n)) {
            error_report("virtio-net: saved image requires TUN_F_UFO support");
            return -1;
        }
    }

    if (n->max_queues > 1) {
        if (n->max_queues != qemu_get_be16(f)) {
            error_report("virtio-net: different max_queues ");
            return -1;
        }

        n->curr_queues = qemu_get_be16(f);
        for (i = 1; i < n->curr_queues; i++) {
            n->vqs[i].tx_waiting = qemu_get_be32(f);
        }
    }

    virtio_net_set_queues(n);

    /* Find the first multicast entry in the saved MAC filter */
    for (i = 0; i < n->mac_table.in_use; i++) {
        if (n->mac_table.macs[i * ETH_ALEN] & 1) {
            break;
        }
    }
    n->mac_table.first_multi = i;

    /* nc.link_down can't be migrated, so infer link_down according
     * to link status bit in n->status */
    link_down = (n->status & VIRTIO_NET_S_LINK_UP) == 0;
    for (i = 0; i < n->max_queues; i++) {
        qemu_get_subqueue(n->nic, i)->link_down = link_down;
    }

    return 0;
}

static void virtio_net_cleanup(NetClientState *nc)
{
    VirtIONet *n = qemu_get_nic_opaque(nc);

    n->nic = NULL;
}

static NetClientInfo net_virtio_info = {
    .type = NET_CLIENT_OPTIONS_KIND_NIC,
    .size = sizeof(NICState),
    .can_receive = virtio_net_can_receive,
    .receive = virtio_net_receive,
        .cleanup = virtio_net_cleanup,
    .link_status_changed = virtio_net_set_link_status,
};

static bool virtio_net_guest_notifier_pending(VirtIODevice *vdev, int idx)
{
    VirtIONet *n = VIRTIO_NET(vdev);
    NetClientState *nc = qemu_get_subqueue(n->nic, vq2q(idx));
    assert(n->vhost_started);
    return vhost_net_virtqueue_pending(tap_get_vhost_net(nc->peer), idx);
}

static void virtio_net_guest_notifier_mask(VirtIODevice *vdev, int idx,
                                           bool mask)
{
    VirtIONet *n = VIRTIO_NET(vdev);
    NetClientState *nc = qemu_get_subqueue(n->nic, vq2q(idx));
    assert(n->vhost_started);
    vhost_net_virtqueue_mask(tap_get_vhost_net(nc->peer),
                             vdev, idx, mask);
}

void virtio_net_set_config_size(VirtIONet *n, uint32_t host_features)
{
    int i, config_size = 0;
    for (i = 0; feature_sizes[i].flags != 0; i++) {
        if (host_features & feature_sizes[i].flags) {
            config_size = MAX(feature_sizes[i].end, config_size);
        }
    }
    n->config_size = config_size;
}

static int virtio_net_device_init(VirtIODevice *vdev)
{
    int i;

    DeviceState *qdev = DEVICE(vdev);
    VirtIONet *n = VIRTIO_NET(vdev);

    virtio_init(VIRTIO_DEVICE(n), "virtio-net", VIRTIO_ID_NET,
                                  n->config_size);

    vdev->get_config = virtio_net_get_config;
    vdev->set_config = virtio_net_set_config;
    vdev->get_features = virtio_net_get_features;
    vdev->set_features = virtio_net_set_features;
    vdev->bad_features = virtio_net_bad_features;
    vdev->reset = virtio_net_reset;
    vdev->set_status = virtio_net_set_status;
    vdev->guest_notifier_mask = virtio_net_guest_notifier_mask;
    vdev->guest_notifier_pending = virtio_net_guest_notifier_pending;
    n->max_queues = MAX(n->nic_conf.queues, 1);
    n->vqs = g_malloc0(sizeof(VirtIONetQueue) * n->max_queues);
    n->vqs[0].rx_vq = virtio_add_queue(vdev, 256, virtio_net_handle_rx);
    n->curr_queues = 1;
    n->vqs[0].n = n;
    n->tx_timeout = n->net_conf.txtimer;

    if (n->net_conf.tx && strcmp(n->net_conf.tx, "timer")
                       && strcmp(n->net_conf.tx, "bh")) {
        error_report("virtio-net: "
                     "Unknown option tx=%s, valid options: \"timer\" \"bh\"",
                     n->net_conf.tx);
        error_report("Defaulting to \"bh\"");
    }

    if (n->net_conf.tx && !strcmp(n->net_conf.tx, "timer")) {
        n->vqs[0].tx_vq = virtio_add_queue(vdev, 256,
                                           virtio_net_handle_tx_timer);
        n->vqs[0].tx_timer = qemu_new_timer_ns(vm_clock, virtio_net_tx_timer,
                                               &n->vqs[0]);
    } else {
        n->vqs[0].tx_vq = virtio_add_queue(vdev, 256,
                                           virtio_net_handle_tx_bh);
        n->vqs[0].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[0]);
    }
    n->ctrl_vq = virtio_add_queue(vdev, 64, virtio_net_handle_ctrl);
    qemu_macaddr_default_if_unset(&n->nic_conf.macaddr);
    memcpy(&n->mac[0], &n->nic_conf.macaddr, sizeof(n->mac));
    n->status = VIRTIO_NET_S_LINK_UP;

    n->nic = qemu_new_nic(&net_virtio_info, &n->nic_conf,
                          object_get_typename(OBJECT(qdev)), qdev->id, n);
    peer_test_vnet_hdr(n);
    if (peer_has_vnet_hdr(n)) {
        for (i = 0; i < n->max_queues; i++) {
            tap_using_vnet_hdr(qemu_get_subqueue(n->nic, i)->peer, true);
        }
        n->host_hdr_len = sizeof(struct virtio_net_hdr);
    } else {
        n->host_hdr_len = 0;
    }

    qemu_format_nic_info_str(qemu_get_queue(n->nic), n->nic_conf.macaddr.a);

    n->vqs[0].tx_waiting = 0;
    n->tx_burst = n->net_conf.txburst;
    virtio_net_set_mrg_rx_bufs(n, 0);
    n->promisc = 1; /* for compatibility */

    n->mac_table.macs = g_malloc0(MAC_TABLE_ENTRIES * ETH_ALEN);

    n->vlans = g_malloc0(MAX_VLAN >> 3);

    n->qdev = qdev;
    register_savevm(qdev, "virtio-net", -1, VIRTIO_NET_VM_VERSION,
                    virtio_net_save, virtio_net_load, n);

    add_boot_device_path(n->nic_conf.bootindex, qdev, "/ethernet-phy@0");
    return 0;
}

static int virtio_net_device_exit(DeviceState *qdev)
{
    VirtIONet *n = VIRTIO_NET(qdev);
    VirtIODevice *vdev = VIRTIO_DEVICE(qdev);
    int i;

    /* This will stop vhost backend if appropriate. */
    virtio_net_set_status(vdev, 0);

    unregister_savevm(qdev, "virtio-net", n);

    g_free(n->mac_table.macs);
    g_free(n->vlans);

    for (i = 0; i < n->max_queues; i++) {
        VirtIONetQueue *q = &n->vqs[i];
        NetClientState *nc = qemu_get_subqueue(n->nic, i);

        qemu_purge_queued_packets(nc);

        if (q->tx_timer) {
            qemu_del_timer(q->tx_timer);
            qemu_free_timer(q->tx_timer);
        } else {
            qemu_bh_delete(q->tx_bh);
        }
    }

    g_free(n->vqs);
    qemu_del_nic(n->nic);
    virtio_common_cleanup(vdev);

    return 0;
}

static void virtio_net_instance_init(Object *obj)
{
    VirtIONet *n = VIRTIO_NET(obj);

    /*
     * The default config_size is sizeof(struct virtio_net_config).
     * Can be overriden with virtio_net_set_config_size.
     */
    n->config_size = sizeof(struct virtio_net_config);
}

static Property virtio_net_properties[] = {
    DEFINE_NIC_PROPERTIES(VirtIONet, nic_conf),
    DEFINE_PROP_UINT32("x-txtimer", VirtIONet, net_conf.txtimer,
                                               TX_TIMER_INTERVAL),
    DEFINE_PROP_INT32("x-txburst", VirtIONet, net_conf.txburst, TX_BURST),
    DEFINE_PROP_STRING("tx", VirtIONet, net_conf.tx),
    DEFINE_PROP_END_OF_LIST(),
};

static void virtio_net_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);
    VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
    dc->exit = virtio_net_device_exit;
    dc->props = virtio_net_properties;
    vdc->init = virtio_net_device_init;
    vdc->get_config = virtio_net_get_config;
    vdc->set_config = virtio_net_set_config;
    vdc->get_features = virtio_net_get_features;
    vdc->set_features = virtio_net_set_features;
    vdc->bad_features = virtio_net_bad_features;
    vdc->reset = virtio_net_reset;
    vdc->set_status = virtio_net_set_status;
    vdc->guest_notifier_mask = virtio_net_guest_notifier_mask;
    vdc->guest_notifier_pending = virtio_net_guest_notifier_pending;
}

static const TypeInfo virtio_net_info = {
    .name = TYPE_VIRTIO_NET,
    .parent = TYPE_VIRTIO_DEVICE,
    .instance_size = sizeof(VirtIONet),
    .instance_init = virtio_net_instance_init,
    .class_init = virtio_net_class_init,
};

static void virtio_register_types(void)
{
    type_register_static(&virtio_net_info);
}

type_init(virtio_register_types)