summaryrefslogtreecommitdiffstats
path: root/hw/net/net_tx_pkt.c
blob: 9560e4a49ebd0e2676b2aa6180cb6f8dddc2a486 (plain) (blame)
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
/*
 * QEMU TX packets abstractions
 *
 * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com)
 *
 * Developed by Daynix Computing LTD (http://www.daynix.com)
 *
 * Authors:
 * Dmitry Fleytman <dmitry@daynix.com>
 * Tamir Shomer <tamirs@daynix.com>
 * Yan Vugenfirer <yan@daynix.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 *
 */

#include "qemu/osdep.h"
#include "net_tx_pkt.h"
#include "net/eth.h"
#include "net/checksum.h"
#include "net/tap.h"
#include "net/net.h"
#include "hw/pci/pci.h"

enum {
    NET_TX_PKT_VHDR_FRAG = 0,
    NET_TX_PKT_L2HDR_FRAG,
    NET_TX_PKT_L3HDR_FRAG,
    NET_TX_PKT_PL_START_FRAG
};

/* TX packet private context */
struct NetTxPkt {
    PCIDevice *pci_dev;

    struct virtio_net_hdr virt_hdr;
    bool has_virt_hdr;

    struct iovec *raw;
    uint32_t raw_frags;
    uint32_t max_raw_frags;

    struct iovec *vec;

    uint8_t l2_hdr[ETH_MAX_L2_HDR_LEN];
    uint8_t l3_hdr[ETH_MAX_IP_DGRAM_LEN];

    uint32_t payload_len;

    uint32_t payload_frags;
    uint32_t max_payload_frags;

    uint16_t hdr_len;
    eth_pkt_types_e packet_type;
    uint8_t l4proto;

    bool is_loopback;
};

void net_tx_pkt_init(struct NetTxPkt **pkt, PCIDevice *pci_dev,
    uint32_t max_frags, bool has_virt_hdr)
{
    struct NetTxPkt *p = g_malloc0(sizeof *p);

    p->pci_dev = pci_dev;

    p->vec = g_new(struct iovec, max_frags + NET_TX_PKT_PL_START_FRAG);

    p->raw = g_new(struct iovec, max_frags);

    p->max_payload_frags = max_frags;
    p->max_raw_frags = max_frags;
    p->has_virt_hdr = has_virt_hdr;
    p->vec[NET_TX_PKT_VHDR_FRAG].iov_base = &p->virt_hdr;
    p->vec[NET_TX_PKT_VHDR_FRAG].iov_len =
        p->has_virt_hdr ? sizeof p->virt_hdr : 0;
    p->vec[NET_TX_PKT_L2HDR_FRAG].iov_base = &p->l2_hdr;
    p->vec[NET_TX_PKT_L3HDR_FRAG].iov_base = &p->l3_hdr;

    *pkt = p;
}

void net_tx_pkt_uninit(struct NetTxPkt *pkt)
{
    if (pkt) {
        g_free(pkt->vec);
        g_free(pkt->raw);
        g_free(pkt);
    }
}

void net_tx_pkt_update_ip_hdr_checksum(struct NetTxPkt *pkt)
{
    uint16_t csum;
    assert(pkt);
    struct ip_header *ip_hdr;
    ip_hdr = pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_base;

    ip_hdr->ip_len = cpu_to_be16(pkt->payload_len +
        pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_len);

    ip_hdr->ip_sum = 0;
    csum = net_raw_checksum((uint8_t *)ip_hdr,
        pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_len);
    ip_hdr->ip_sum = cpu_to_be16(csum);
}

void net_tx_pkt_update_ip_checksums(struct NetTxPkt *pkt)
{
    uint16_t csum;
    uint32_t cntr, cso;
    assert(pkt);
    uint8_t gso_type = pkt->virt_hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN;
    void *ip_hdr = pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_base;

    if (pkt->payload_len + pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_len >
        ETH_MAX_IP_DGRAM_LEN) {
        return;
    }

    if (gso_type == VIRTIO_NET_HDR_GSO_TCPV4 ||
        gso_type == VIRTIO_NET_HDR_GSO_UDP) {
        /* Calculate IP header checksum */
        net_tx_pkt_update_ip_hdr_checksum(pkt);

        /* Calculate IP pseudo header checksum */
        cntr = eth_calc_ip4_pseudo_hdr_csum(ip_hdr, pkt->payload_len, &cso);
        csum = cpu_to_be16(~net_checksum_finish(cntr));
    } else if (gso_type == VIRTIO_NET_HDR_GSO_TCPV6) {
        /* Calculate IP pseudo header checksum */
        cntr = eth_calc_ip6_pseudo_hdr_csum(ip_hdr, pkt->payload_len,
                                            IP_PROTO_TCP, &cso);
        csum = cpu_to_be16(~net_checksum_finish(cntr));
    } else {
        return;
    }

    iov_from_buf(&pkt->vec[NET_TX_PKT_PL_START_FRAG], pkt->payload_frags,
                 pkt->virt_hdr.csum_offset, &csum, sizeof(csum));
}

static void net_tx_pkt_calculate_hdr_len(struct NetTxPkt *pkt)
{
    pkt->hdr_len = pkt->vec[NET_TX_PKT_L2HDR_FRAG].iov_len +
        pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_len;
}

static bool net_tx_pkt_parse_headers(struct NetTxPkt *pkt)
{
    struct iovec *l2_hdr, *l3_hdr;
    size_t bytes_read;
    size_t full_ip6hdr_len;
    uint16_t l3_proto;

    assert(pkt);

    l2_hdr = &pkt->vec[NET_TX_PKT_L2HDR_FRAG];
    l3_hdr = &pkt->vec[NET_TX_PKT_L3HDR_FRAG];

    bytes_read = iov_to_buf(pkt->raw, pkt->raw_frags, 0, l2_hdr->iov_base,
                            ETH_MAX_L2_HDR_LEN);
    if (bytes_read < sizeof(struct eth_header)) {
        l2_hdr->iov_len = 0;
        return false;
    }

    l2_hdr->iov_len = sizeof(struct eth_header);
    switch (be16_to_cpu(PKT_GET_ETH_HDR(l2_hdr->iov_base)->h_proto)) {
    case ETH_P_VLAN:
        l2_hdr->iov_len += sizeof(struct vlan_header);
        break;
    case ETH_P_DVLAN:
        l2_hdr->iov_len += 2 * sizeof(struct vlan_header);
        break;
    }

    if (bytes_read < l2_hdr->iov_len) {
        l2_hdr->iov_len = 0;
        l3_hdr->iov_len = 0;
        pkt->packet_type = ETH_PKT_UCAST;
        return false;
    } else {
        l2_hdr->iov_len = ETH_MAX_L2_HDR_LEN;
        l2_hdr->iov_len = eth_get_l2_hdr_length(l2_hdr->iov_base);
        pkt->packet_type = get_eth_packet_type(l2_hdr->iov_base);
    }

    l3_proto = eth_get_l3_proto(l2_hdr, 1, l2_hdr->iov_len);

    switch (l3_proto) {
    case ETH_P_IP:
        bytes_read = iov_to_buf(pkt->raw, pkt->raw_frags, l2_hdr->iov_len,
                                l3_hdr->iov_base, sizeof(struct ip_header));

        if (bytes_read < sizeof(struct ip_header)) {
            l3_hdr->iov_len = 0;
            return false;
        }

        l3_hdr->iov_len = IP_HDR_GET_LEN(l3_hdr->iov_base);

        if (l3_hdr->iov_len < sizeof(struct ip_header)) {
            l3_hdr->iov_len = 0;
            return false;
        }

        pkt->l4proto = IP_HDR_GET_P(l3_hdr->iov_base);

        if (IP_HDR_GET_LEN(l3_hdr->iov_base) != sizeof(struct ip_header)) {
            /* copy optional IPv4 header data if any*/
            bytes_read = iov_to_buf(pkt->raw, pkt->raw_frags,
                                    l2_hdr->iov_len + sizeof(struct ip_header),
                                    l3_hdr->iov_base + sizeof(struct ip_header),
                                    l3_hdr->iov_len - sizeof(struct ip_header));
            if (bytes_read < l3_hdr->iov_len - sizeof(struct ip_header)) {
                l3_hdr->iov_len = 0;
                return false;
            }
        }

        break;

    case ETH_P_IPV6:
    {
        eth_ip6_hdr_info hdrinfo;

        if (!eth_parse_ipv6_hdr(pkt->raw, pkt->raw_frags, l2_hdr->iov_len,
                                &hdrinfo)) {
            l3_hdr->iov_len = 0;
            return false;
        }

        pkt->l4proto = hdrinfo.l4proto;
        full_ip6hdr_len = hdrinfo.full_hdr_len;

        if (full_ip6hdr_len > ETH_MAX_IP_DGRAM_LEN) {
            l3_hdr->iov_len = 0;
            return false;
        }

        bytes_read = iov_to_buf(pkt->raw, pkt->raw_frags, l2_hdr->iov_len,
                                l3_hdr->iov_base, full_ip6hdr_len);

        if (bytes_read < full_ip6hdr_len) {
            l3_hdr->iov_len = 0;
            return false;
        } else {
            l3_hdr->iov_len = full_ip6hdr_len;
        }
        break;
    }
    default:
        l3_hdr->iov_len = 0;
        break;
    }

    net_tx_pkt_calculate_hdr_len(pkt);
    return true;
}

static void net_tx_pkt_rebuild_payload(struct NetTxPkt *pkt)
{
    pkt->payload_len = iov_size(pkt->raw, pkt->raw_frags) - pkt->hdr_len;
    pkt->payload_frags = iov_copy(&pkt->vec[NET_TX_PKT_PL_START_FRAG],
                                pkt->max_payload_frags,
                                pkt->raw, pkt->raw_frags,
                                pkt->hdr_len, pkt->payload_len);
}

bool net_tx_pkt_parse(struct NetTxPkt *pkt)
{
    if (net_tx_pkt_parse_headers(pkt)) {
        net_tx_pkt_rebuild_payload(pkt);
        return true;
    } else {
        return false;
    }
}

struct virtio_net_hdr *net_tx_pkt_get_vhdr(struct NetTxPkt *pkt)
{
    assert(pkt);
    return &pkt->virt_hdr;
}

static uint8_t net_tx_pkt_get_gso_type(struct NetTxPkt *pkt,
                                          bool tso_enable)
{
    uint8_t rc = VIRTIO_NET_HDR_GSO_NONE;
    uint16_t l3_proto;

    l3_proto = eth_get_l3_proto(&pkt->vec[NET_TX_PKT_L2HDR_FRAG], 1,
        pkt->vec[NET_TX_PKT_L2HDR_FRAG].iov_len);

    if (!tso_enable) {
        goto func_exit;
    }

    rc = eth_get_gso_type(l3_proto, pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_base,
                          pkt->l4proto);

func_exit:
    return rc;
}

void net_tx_pkt_build_vheader(struct NetTxPkt *pkt, bool tso_enable,
    bool csum_enable, uint32_t gso_size)
{
    struct tcp_hdr l4hdr;
    assert(pkt);

    /* csum has to be enabled if tso is. */
    assert(csum_enable || !tso_enable);

    pkt->virt_hdr.gso_type = net_tx_pkt_get_gso_type(pkt, tso_enable);

    switch (pkt->virt_hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
    case VIRTIO_NET_HDR_GSO_NONE:
        pkt->virt_hdr.hdr_len = 0;
        pkt->virt_hdr.gso_size = 0;
        break;

    case VIRTIO_NET_HDR_GSO_UDP:
        pkt->virt_hdr.gso_size = gso_size;
        pkt->virt_hdr.hdr_len = pkt->hdr_len + sizeof(struct udp_header);
        break;

    case VIRTIO_NET_HDR_GSO_TCPV4:
    case VIRTIO_NET_HDR_GSO_TCPV6:
        iov_to_buf(&pkt->vec[NET_TX_PKT_PL_START_FRAG], pkt->payload_frags,
                   0, &l4hdr, sizeof(l4hdr));
        pkt->virt_hdr.hdr_len = pkt->hdr_len + l4hdr.th_off * sizeof(uint32_t);
        pkt->virt_hdr.gso_size = gso_size;
        break;

    default:
        g_assert_not_reached();
    }

    if (csum_enable) {
        switch (pkt->l4proto) {
        case IP_PROTO_TCP:
            pkt->virt_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
            pkt->virt_hdr.csum_start = pkt->hdr_len;
            pkt->virt_hdr.csum_offset = offsetof(struct tcp_hdr, th_sum);
            break;
        case IP_PROTO_UDP:
            pkt->virt_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
            pkt->virt_hdr.csum_start = pkt->hdr_len;
            pkt->virt_hdr.csum_offset = offsetof(struct udp_hdr, uh_sum);
            break;
        default:
            break;
        }
    }
}

void net_tx_pkt_setup_vlan_header_ex(struct NetTxPkt *pkt,
    uint16_t vlan, uint16_t vlan_ethtype)
{
    bool is_new;
    assert(pkt);

    eth_setup_vlan_headers_ex(pkt->vec[NET_TX_PKT_L2HDR_FRAG].iov_base,
        vlan, vlan_ethtype, &is_new);

    /* update l2hdrlen */
    if (is_new) {
        pkt->hdr_len += sizeof(struct vlan_header);
        pkt->vec[NET_TX_PKT_L2HDR_FRAG].iov_len +=
            sizeof(struct vlan_header);
    }
}

bool net_tx_pkt_add_raw_fragment(struct NetTxPkt *pkt, hwaddr pa,
    size_t len)
{
    hwaddr mapped_len = 0;
    struct iovec *ventry;
    assert(pkt);
    assert(pkt->max_raw_frags > pkt->raw_frags);

    if (!len) {
        return true;
     }

    ventry = &pkt->raw[pkt->raw_frags];
    mapped_len = len;

    ventry->iov_base = pci_dma_map(pkt->pci_dev, pa,
                                   &mapped_len, DMA_DIRECTION_TO_DEVICE);

    if ((ventry->iov_base != NULL) && (len == mapped_len)) {
        ventry->iov_len = mapped_len;
        pkt->raw_frags++;
        return true;
    } else {
        return false;
    }
}

bool net_tx_pkt_has_fragments(struct NetTxPkt *pkt)
{
    return pkt->raw_frags > 0;
}

eth_pkt_types_e net_tx_pkt_get_packet_type(struct NetTxPkt *pkt)
{
    assert(pkt);

    return pkt->packet_type;
}

size_t net_tx_pkt_get_total_len(struct NetTxPkt *pkt)
{
    assert(pkt);

    return pkt->hdr_len + pkt->payload_len;
}

void net_tx_pkt_dump(struct NetTxPkt *pkt)
{
#ifdef NET_TX_PKT_DEBUG
    assert(pkt);

    printf("TX PKT: hdr_len: %d, pkt_type: 0x%X, l2hdr_len: %lu, "
        "l3hdr_len: %lu, payload_len: %u\n", pkt->hdr_len, pkt->packet_type,
        pkt->vec[NET_TX_PKT_L2HDR_FRAG].iov_len,
        pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_len, pkt->payload_len);
#endif
}

void net_tx_pkt_reset(struct NetTxPkt *pkt)
{
    int i;

    /* no assert, as reset can be called before tx_pkt_init */
    if (!pkt) {
        return;
    }

    memset(&pkt->virt_hdr, 0, sizeof(pkt->virt_hdr));

    assert(pkt->vec);

    pkt->payload_len = 0;
    pkt->payload_frags = 0;

    assert(pkt->raw);
    for (i = 0; i < pkt->raw_frags; i++) {
        assert(pkt->raw[i].iov_base);
        pci_dma_unmap(pkt->pci_dev, pkt->raw[i].iov_base, pkt->raw[i].iov_len,
                      DMA_DIRECTION_TO_DEVICE, 0);
    }
    pkt->raw_frags = 0;

    pkt->hdr_len = 0;
    pkt->l4proto = 0;
}

static void net_tx_pkt_do_sw_csum(struct NetTxPkt *pkt)
{
    struct iovec *iov = &pkt->vec[NET_TX_PKT_L2HDR_FRAG];
    uint32_t csum_cntr;
    uint16_t csum = 0;
    uint32_t cso;
    /* num of iovec without vhdr */
    uint32_t iov_len = pkt->payload_frags + NET_TX_PKT_PL_START_FRAG - 1;
    uint16_t csl;
    size_t csum_offset = pkt->virt_hdr.csum_start + pkt->virt_hdr.csum_offset;
    uint16_t l3_proto = eth_get_l3_proto(iov, 1, iov->iov_len);

    /* Put zero to checksum field */
    iov_from_buf(iov, iov_len, csum_offset, &csum, sizeof csum);

    /* Calculate L4 TCP/UDP checksum */
    csl = pkt->payload_len;

    csum_cntr = 0;
    cso = 0;
    /* add pseudo header to csum */
    if (l3_proto == ETH_P_IP) {
        csum_cntr = eth_calc_ip4_pseudo_hdr_csum(
                pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_base,
                csl, &cso);
    } else if (l3_proto == ETH_P_IPV6) {
        csum_cntr = eth_calc_ip6_pseudo_hdr_csum(
                pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_base,
                csl, pkt->l4proto, &cso);
    }

    /* data checksum */
    csum_cntr +=
        net_checksum_add_iov(iov, iov_len, pkt->virt_hdr.csum_start, csl, cso);

    /* Put the checksum obtained into the packet */
    csum = cpu_to_be16(net_checksum_finish_nozero(csum_cntr));
    iov_from_buf(iov, iov_len, csum_offset, &csum, sizeof csum);
}

enum {
    NET_TX_PKT_FRAGMENT_L2_HDR_POS = 0,
    NET_TX_PKT_FRAGMENT_L3_HDR_POS,
    NET_TX_PKT_FRAGMENT_HEADER_NUM
};

#define NET_MAX_FRAG_SG_LIST (64)

static size_t net_tx_pkt_fetch_fragment(struct NetTxPkt *pkt,
    int *src_idx, size_t *src_offset, struct iovec *dst, int *dst_idx)
{
    size_t fetched = 0;
    struct iovec *src = pkt->vec;

    *dst_idx = NET_TX_PKT_FRAGMENT_HEADER_NUM;

    while (fetched < IP_FRAG_ALIGN_SIZE(pkt->virt_hdr.gso_size)) {

        /* no more place in fragment iov */
        if (*dst_idx == NET_MAX_FRAG_SG_LIST) {
            break;
        }

        /* no more data in iovec */
        if (*src_idx == (pkt->payload_frags + NET_TX_PKT_PL_START_FRAG)) {
            break;
        }


        dst[*dst_idx].iov_base = src[*src_idx].iov_base + *src_offset;
        dst[*dst_idx].iov_len = MIN(src[*src_idx].iov_len - *src_offset,
            IP_FRAG_ALIGN_SIZE(pkt->virt_hdr.gso_size) - fetched);

        *src_offset += dst[*dst_idx].iov_len;
        fetched += dst[*dst_idx].iov_len;

        if (*src_offset == src[*src_idx].iov_len) {
            *src_offset = 0;
            (*src_idx)++;
        }

        (*dst_idx)++;
    }

    return fetched;
}

static inline void net_tx_pkt_sendv(struct NetTxPkt *pkt,
    NetClientState *nc, const struct iovec *iov, int iov_cnt)
{
    if (pkt->is_loopback) {
        nc->info->receive_iov(nc, iov, iov_cnt);
    } else {
        qemu_sendv_packet(nc, iov, iov_cnt);
    }
}

static bool net_tx_pkt_do_sw_fragmentation(struct NetTxPkt *pkt,
    NetClientState *nc)
{
    struct iovec fragment[NET_MAX_FRAG_SG_LIST];
    size_t fragment_len = 0;
    bool more_frags = false;

    /* some pointers for shorter code */
    void *l2_iov_base, *l3_iov_base;
    size_t l2_iov_len, l3_iov_len;
    int src_idx =  NET_TX_PKT_PL_START_FRAG, dst_idx;
    size_t src_offset = 0;
    size_t fragment_offset = 0;

    l2_iov_base = pkt->vec[NET_TX_PKT_L2HDR_FRAG].iov_base;
    l2_iov_len = pkt->vec[NET_TX_PKT_L2HDR_FRAG].iov_len;
    l3_iov_base = pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_base;
    l3_iov_len = pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_len;

    /* Copy headers */
    fragment[NET_TX_PKT_FRAGMENT_L2_HDR_POS].iov_base = l2_iov_base;
    fragment[NET_TX_PKT_FRAGMENT_L2_HDR_POS].iov_len = l2_iov_len;
    fragment[NET_TX_PKT_FRAGMENT_L3_HDR_POS].iov_base = l3_iov_base;
    fragment[NET_TX_PKT_FRAGMENT_L3_HDR_POS].iov_len = l3_iov_len;


    /* Put as much data as possible and send */
    do {
        fragment_len = net_tx_pkt_fetch_fragment(pkt, &src_idx, &src_offset,
            fragment, &dst_idx);

        more_frags = (fragment_offset + fragment_len < pkt->payload_len);

        eth_setup_ip4_fragmentation(l2_iov_base, l2_iov_len, l3_iov_base,
            l3_iov_len, fragment_len, fragment_offset, more_frags);

        eth_fix_ip4_checksum(l3_iov_base, l3_iov_len);

        net_tx_pkt_sendv(pkt, nc, fragment, dst_idx);

        fragment_offset += fragment_len;

    } while (fragment_len && more_frags);

    return true;
}

bool net_tx_pkt_send(struct NetTxPkt *pkt, NetClientState *nc)
{
    assert(pkt);

    if (!pkt->has_virt_hdr &&
        pkt->virt_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
        net_tx_pkt_do_sw_csum(pkt);
    }

    /*
     * Since underlying infrastructure does not support IP datagrams longer
     * than 64K we should drop such packets and don't even try to send
     */
    if (VIRTIO_NET_HDR_GSO_NONE != pkt->virt_hdr.gso_type) {
        if (pkt->payload_len >
            ETH_MAX_IP_DGRAM_LEN -
            pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_len) {
            return false;
        }
    }

    if (pkt->has_virt_hdr ||
        pkt->virt_hdr.gso_type == VIRTIO_NET_HDR_GSO_NONE) {
        net_tx_pkt_fix_ip6_payload_len(pkt);
        net_tx_pkt_sendv(pkt, nc, pkt->vec,
            pkt->payload_frags + NET_TX_PKT_PL_START_FRAG);
        return true;
    }

    return net_tx_pkt_do_sw_fragmentation(pkt, nc);
}

bool net_tx_pkt_send_loopback(struct NetTxPkt *pkt, NetClientState *nc)
{
    bool res;

    pkt->is_loopback = true;
    res = net_tx_pkt_send(pkt, nc);
    pkt->is_loopback = false;

    return res;
}

void net_tx_pkt_fix_ip6_payload_len(struct NetTxPkt *pkt)
{
    struct iovec *l2 = &pkt->vec[NET_TX_PKT_L2HDR_FRAG];
    if (eth_get_l3_proto(l2, 1, l2->iov_len) == ETH_P_IPV6) {
        struct ip6_header *ip6 = (struct ip6_header *) pkt->l3_hdr;
        /*
         * TODO: if qemu would support >64K packets - add jumbo option check
         * something like that:
         * 'if (ip6->ip6_plen == 0 && !has_jumbo_option(ip6)) {'
         */
        if (ip6->ip6_plen == 0) {
            if (pkt->payload_len <= ETH_MAX_IP_DGRAM_LEN) {
                ip6->ip6_plen = htons(pkt->payload_len);
            }
            /*
             * TODO: if qemu would support >64K packets
             * add jumbo option for packets greater then 65,535 bytes
             */
        }
    }
}