aboutsummaryrefslogtreecommitdiff
path: root/hw/virtio-net.c
blob: e83d1019c1867a96e1daa4fa8a8c0bbee2bbfbbb (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
/*
 * 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 "virtio.h"
#include "net.h"
#include "qemu-timer.h"
#include "virtio-net.h"

#define VIRTIO_NET_VM_VERSION    6

#define MAC_TABLE_ENTRIES    32
#define MAX_VLAN    (1 << 12)   /* Per 802.1Q definition */

typedef struct VirtIONet
{
    VirtIODevice vdev;
    uint8_t mac[ETH_ALEN];
    uint16_t status;
    VirtQueue *rx_vq;
    VirtQueue *tx_vq;
    VirtQueue *ctrl_vq;
    VLANClientState *vc;
    QEMUTimer *tx_timer;
    int tx_timer_active;
    int mergeable_rx_bufs;
    int promisc;
    int allmulti;
    struct {
        int in_use;
        uint8_t *macs;
    } mac_table;
    uint32_t *vlans;
} VirtIONet;

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

static VirtIONet *to_virtio_net(VirtIODevice *vdev)
{
    return (VirtIONet *)vdev;
}

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

    netcfg.status = n->status;
    memcpy(netcfg.mac, n->mac, ETH_ALEN);
    memcpy(config, &netcfg, sizeof(netcfg));
}

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

    memcpy(&netcfg, config, sizeof(netcfg));

    if (memcmp(netcfg.mac, n->mac, ETH_ALEN)) {
        memcpy(n->mac, netcfg.mac, ETH_ALEN);
        qemu_format_nic_info_str(n->vc, n->mac);
    }
}

static void virtio_net_set_link_status(VLANClientState *vc)
{
    VirtIONet *n = vc->opaque;
    uint16_t old_status = n->status;

    if (vc->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(&n->vdev);
}

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

    /* Reset back to compatibility mode */
    n->promisc = 1;
    n->allmulti = 0;

    /* Flush any MAC and VLAN filter table state */
    n->mac_table.in_use = 0;
    memset(n->mac_table.macs, 0, MAC_TABLE_ENTRIES * ETH_ALEN);
    memset(n->vlans, 0, MAX_VLAN >> 3);
}

static uint32_t virtio_net_get_features(VirtIODevice *vdev)
{
    uint32_t features = (1 << VIRTIO_NET_F_MAC) |
                        (1 << VIRTIO_NET_F_STATUS) |
                        (1 << VIRTIO_NET_F_CTRL_VQ) |
                        (1 << VIRTIO_NET_F_CTRL_RX) |
                        (1 << VIRTIO_NET_F_CTRL_VLAN);

    return features;
}

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

    n->mergeable_rx_bufs = !!(features & (1 << VIRTIO_NET_F_MRG_RXBUF));
}

static int virtio_net_handle_rx_mode(VirtIONet *n, uint8_t cmd,
                                     VirtQueueElement *elem)
{
    uint8_t on;

    if (elem->out_num != 2 || elem->out_sg[1].iov_len != sizeof(on)) {
        fprintf(stderr, "virtio-net ctrl invalid rx mode command\n");
        exit(1);
    }

    on = ldub_p(elem->out_sg[1].iov_base);

    if (cmd == VIRTIO_NET_CTRL_RX_MODE_PROMISC)
        n->promisc = on;
    else if (cmd == VIRTIO_NET_CTRL_RX_MODE_ALLMULTI)
        n->allmulti = on;
    else
        return VIRTIO_NET_ERR;

    return VIRTIO_NET_OK;
}

static int virtio_net_handle_mac(VirtIONet *n, uint8_t cmd,
                                 VirtQueueElement *elem)
{
    struct virtio_net_ctrl_mac mac_data;

    if (cmd != VIRTIO_NET_CTRL_MAC_TABLE_SET || elem->out_num != 3 ||
        elem->out_sg[1].iov_len < sizeof(mac_data) ||
        elem->out_sg[2].iov_len < sizeof(mac_data))
        return VIRTIO_NET_ERR;

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

    mac_data.entries = ldl_le_p(elem->out_sg[1].iov_base);

    if (sizeof(mac_data.entries) +
        (mac_data.entries * ETH_ALEN) > elem->out_sg[1].iov_len)
        return VIRTIO_NET_ERR;

    if (mac_data.entries <= MAC_TABLE_ENTRIES) {
        memcpy(n->mac_table.macs, elem->out_sg[1].iov_base + sizeof(mac_data),
               mac_data.entries * ETH_ALEN);
        n->mac_table.in_use += mac_data.entries;
    } else {
        n->promisc = 1;
        return VIRTIO_NET_OK;
    }

    mac_data.entries = ldl_le_p(elem->out_sg[2].iov_base);

    if (sizeof(mac_data.entries) +
        (mac_data.entries * ETH_ALEN) > elem->out_sg[2].iov_len)
        return VIRTIO_NET_ERR;

    if (mac_data.entries) {
        if (n->mac_table.in_use + mac_data.entries <= MAC_TABLE_ENTRIES) {
            memcpy(n->mac_table.macs + (n->mac_table.in_use * ETH_ALEN),
                   elem->out_sg[2].iov_base + sizeof(mac_data),
                   mac_data.entries * ETH_ALEN);
            n->mac_table.in_use += mac_data.entries;
        } else
            n->allmulti = 1;
    }

    return VIRTIO_NET_OK;
}

static int virtio_net_handle_vlan_table(VirtIONet *n, uint8_t cmd,
                                        VirtQueueElement *elem)
{
    uint16_t vid;

    if (elem->out_num != 2 || elem->out_sg[1].iov_len != sizeof(vid)) {
        fprintf(stderr, "virtio-net ctrl invalid vlan command\n");
        return VIRTIO_NET_ERR;
    }

    vid = lduw_le_p(elem->out_sg[1].iov_base);

    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 void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
{
    VirtIONet *n = to_virtio_net(vdev);
    struct virtio_net_ctrl_hdr ctrl;
    virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
    VirtQueueElement elem;

    while (virtqueue_pop(vq, &elem)) {
        if ((elem.in_num < 1) || (elem.out_num < 1)) {
            fprintf(stderr, "virtio-net ctrl missing headers\n");
            exit(1);
        }

        if (elem.out_sg[0].iov_len < sizeof(ctrl) ||
            elem.out_sg[elem.in_num - 1].iov_len < sizeof(status)) {
            fprintf(stderr, "virtio-net ctrl header not in correct element\n");
            exit(1);
        }

        ctrl.class = ldub_p(elem.out_sg[0].iov_base);
        ctrl.cmd = ldub_p(elem.out_sg[0].iov_base + sizeof(ctrl.class));

        if (ctrl.class == VIRTIO_NET_CTRL_RX_MODE)
            status = virtio_net_handle_rx_mode(n, ctrl.cmd, &elem);
        else if (ctrl.class == VIRTIO_NET_CTRL_MAC)
            status = virtio_net_handle_mac(n, ctrl.cmd, &elem);
        else if (ctrl.class == VIRTIO_NET_CTRL_VLAN)
            status = virtio_net_handle_vlan_table(n, ctrl.cmd, &elem);

        stb_p(elem.in_sg[elem.in_num - 1].iov_base, status);

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

/* RX */

static void virtio_net_handle_rx(VirtIODevice *vdev, VirtQueue *vq)
{
}

static int do_virtio_net_can_receive(VirtIONet *n, int bufsize)
{
    if (!virtio_queue_ready(n->rx_vq) ||
        !(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK))
        return 0;

    if (virtio_queue_empty(n->rx_vq) ||
        (n->mergeable_rx_bufs &&
         !virtqueue_avail_bytes(n->rx_vq, bufsize, 0))) {
        virtio_queue_set_notification(n->rx_vq, 1);
        return 0;
    }

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

static int virtio_net_can_receive(void *opaque)
{
    VirtIONet *n = opaque;

    return do_virtio_net_can_receive(n, VIRTIO_NET_MAX_BUFSIZE);
}

static int iov_fill(struct iovec *iov, int iovcnt, const void *buf, int count)
{
    int offset, i;

    offset = i = 0;
    while (offset < count && i < iovcnt) {
        int len = MIN(iov[i].iov_len, count - offset);
        memcpy(iov[i].iov_base, buf + offset, len);
        offset += len;
        i++;
    }

    return offset;
}

static int receive_header(VirtIONet *n, struct iovec *iov, int iovcnt,
                          const void *buf, size_t size, size_t hdr_len)
{
    struct virtio_net_hdr *hdr = iov[0].iov_base;
    int offset = 0;

    hdr->flags = 0;
    hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;

    /* We only ever receive a struct virtio_net_hdr from the tapfd,
     * but we may be passing along a larger header to the guest.
     */
    iov[0].iov_base += hdr_len;
    iov[0].iov_len  -= hdr_len;

    return offset;
}

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;

#ifdef TAP_VNET_HDR
    if (tap_has_vnet_hdr(n->vc->vlan->first_client))
        ptr += sizeof(struct virtio_net_hdr);
#endif

    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) && n->allmulti)
        return 1;

    if (!memcmp(ptr, bcast, sizeof(bcast)))
        return 1;

    if (!memcmp(ptr, n->mac, ETH_ALEN))
        return 1;

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

    return 0;
}

static void virtio_net_receive(void *opaque, const uint8_t *buf, int size)
{
    VirtIONet *n = opaque;
    struct virtio_net_hdr_mrg_rxbuf *mhdr = NULL;
    size_t hdr_len, offset, i;

    if (!do_virtio_net_can_receive(n, size))
        return;

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

    /* hdr_len refers to the header we supply to the guest */
    hdr_len = n->mergeable_rx_bufs ?
        sizeof(struct virtio_net_hdr_mrg_rxbuf) : sizeof(struct virtio_net_hdr);

    offset = i = 0;

    while (offset < size) {
        VirtQueueElement elem;
        int len, total;
        struct iovec sg[VIRTQUEUE_MAX_SIZE];

        len = total = 0;

        if ((i != 0 && !n->mergeable_rx_bufs) ||
            virtqueue_pop(n->rx_vq, &elem) == 0) {
            if (i == 0)
                return;
            fprintf(stderr, "virtio-net truncating packet\n");
            exit(1);
        }

        if (elem.in_num < 1) {
            fprintf(stderr, "virtio-net receive queue contains no in buffers\n");
            exit(1);
        }

        if (!n->mergeable_rx_bufs && elem.in_sg[0].iov_len != hdr_len) {
            fprintf(stderr, "virtio-net header not in first element\n");
            exit(1);
        }

        memcpy(&sg, &elem.in_sg[0], sizeof(sg[0]) * elem.in_num);

        if (i == 0) {
            if (n->mergeable_rx_bufs)
                mhdr = (struct virtio_net_hdr_mrg_rxbuf *)sg[0].iov_base;

            offset += receive_header(n, sg, elem.in_num,
                                     buf + offset, size - offset, hdr_len);
            total += hdr_len;
        }

        /* copy in packet.  ugh */
        len = iov_fill(sg, elem.in_num,
                       buf + offset, size - offset);
        total += len;

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

        offset += len;
    }

    if (mhdr)
        mhdr->num_buffers = i;

    virtqueue_flush(n->rx_vq, i);
    virtio_notify(&n->vdev, n->rx_vq);
}

/* TX */
static void virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq)
{
    VirtQueueElement elem;
    int has_vnet_hdr = 0;

    if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK))
        return;

    while (virtqueue_pop(vq, &elem)) {
        ssize_t len = 0;
        unsigned int out_num = elem.out_num;
        struct iovec *out_sg = &elem.out_sg[0];
        unsigned hdr_len;

        /* hdr_len refers to the header received from the guest */
        hdr_len = n->mergeable_rx_bufs ?
            sizeof(struct virtio_net_hdr_mrg_rxbuf) :
            sizeof(struct virtio_net_hdr);

        if (out_num < 1 || out_sg->iov_len != hdr_len) {
            fprintf(stderr, "virtio-net header not in first element\n");
            exit(1);
        }

        /* ignore the header if GSO is not supported */
        if (!has_vnet_hdr) {
            out_num--;
            out_sg++;
            len += hdr_len;
        } else if (n->mergeable_rx_bufs) {
            /* tapfd expects a struct virtio_net_hdr */
            hdr_len -= sizeof(struct virtio_net_hdr);
            out_sg->iov_len -= hdr_len;
            len += hdr_len;
        }

        len += qemu_sendv_packet(n->vc, out_sg, out_num);

        virtqueue_push(vq, &elem, len);
        virtio_notify(&n->vdev, vq);
    }
}

static void virtio_net_handle_tx(VirtIODevice *vdev, VirtQueue *vq)
{
    VirtIONet *n = to_virtio_net(vdev);

    if (n->tx_timer_active) {
        virtio_queue_set_notification(vq, 1);
        qemu_del_timer(n->tx_timer);
        n->tx_timer_active = 0;
        virtio_net_flush_tx(n, vq);
    } else {
        qemu_mod_timer(n->tx_timer,
                       qemu_get_clock(vm_clock) + TX_TIMER_INTERVAL);
        n->tx_timer_active = 1;
        virtio_queue_set_notification(vq, 0);
    }
}

static void virtio_net_tx_timer(void *opaque)
{
    VirtIONet *n = opaque;

    n->tx_timer_active = 0;

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

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

static void virtio_net_save(QEMUFile *f, void *opaque)
{
    VirtIONet *n = opaque;

    virtio_save(&n->vdev, f);

    qemu_put_buffer(f, n->mac, ETH_ALEN);
    qemu_put_be32(f, n->tx_timer_active);
    qemu_put_be32(f, n->mergeable_rx_bufs);
    qemu_put_be16(f, n->status);
    qemu_put_be32(f, n->promisc);
    qemu_put_be32(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);
}

static int virtio_net_load(QEMUFile *f, void *opaque, int version_id)
{
    VirtIONet *n = opaque;

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

    virtio_load(&n->vdev, f);

    qemu_get_buffer(f, n->mac, ETH_ALEN);
    n->tx_timer_active = qemu_get_be32(f);
    n->mergeable_rx_bufs = qemu_get_be32(f);

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

    if (version_id >= 4) {
        n->promisc = qemu_get_be32(f);
        n->allmulti = qemu_get_be32(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) {
            qemu_fseek(f, n->mac_table.in_use * ETH_ALEN, SEEK_CUR);
            n->promisc = 1;
            n->mac_table.in_use = 0;
        }
    }
 
    if (version_id >= 6)
        qemu_get_buffer(f, (uint8_t *)n->vlans, MAX_VLAN >> 3);

    if (n->tx_timer_active) {
        qemu_mod_timer(n->tx_timer,
                       qemu_get_clock(vm_clock) + TX_TIMER_INTERVAL);
    }

    return 0;
}

PCIDevice *virtio_net_init(PCIBus *bus, NICInfo *nd, int devfn)
{
    VirtIONet *n;
    static int virtio_net_id;

    n = (VirtIONet *)virtio_init_pci(bus, "virtio-net",
                                     PCI_VENDOR_ID_REDHAT_QUMRANET,
                                     PCI_DEVICE_ID_VIRTIO_NET,
                                     PCI_VENDOR_ID_REDHAT_QUMRANET,
                                     VIRTIO_ID_NET,
                                     PCI_CLASS_NETWORK_ETHERNET, 0x00,
                                     sizeof(struct virtio_net_config),
                                     sizeof(VirtIONet));
    if (!n)
        return NULL;

    n->vdev.get_config = virtio_net_get_config;
    n->vdev.set_config = virtio_net_set_config;
    n->vdev.get_features = virtio_net_get_features;
    n->vdev.set_features = virtio_net_set_features;
    n->vdev.reset = virtio_net_reset;
    n->rx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_rx);
    n->tx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_tx);
    n->ctrl_vq = virtio_add_queue(&n->vdev, 16, virtio_net_handle_ctrl);
    memcpy(n->mac, nd->macaddr, ETH_ALEN);
    n->status = VIRTIO_NET_S_LINK_UP;
    n->vc = qemu_new_vlan_client(nd->vlan, nd->model, nd->name,
                                 virtio_net_receive, virtio_net_can_receive, n);
    n->vc->link_status_changed = virtio_net_set_link_status;

    qemu_format_nic_info_str(n->vc, n->mac);

    n->tx_timer = qemu_new_timer(vm_clock, virtio_net_tx_timer, n);
    n->tx_timer_active = 0;
    n->mergeable_rx_bufs = 0;
    n->promisc = 1; /* for compatibility */

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

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

    register_savevm("virtio-net", virtio_net_id++, VIRTIO_NET_VM_VERSION,
                    virtio_net_save, virtio_net_load, n);
    return (PCIDevice *)n;
}