net.c 54.5 KB
Newer Older
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
/*
 * QEMU System Emulator
 *
 * Copyright (c) 2003-2008 Fabrice Bellard
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */
#include <unistd.h>
#include <fcntl.h>
#include <signal.h>
#include <time.h>
#include <errno.h>
#include <sys/time.h>
#include <zlib.h>

J
Juan Quintela 已提交
32
/* Needed early for CONFIG_BSD etc. */
B
blueswir1 已提交
33 34
#include "config-host.h"

35 36 37 38 39 40
#ifndef _WIN32
#include <sys/times.h>
#include <sys/wait.h>
#include <termios.h>
#include <sys/mman.h>
#include <sys/ioctl.h>
B
blueswir1 已提交
41
#include <sys/resource.h>
42
#include <sys/socket.h>
B
blueswir1 已提交
43
#include <net/if.h>
44 45 46
#include <dirent.h>
#include <netdb.h>
#include <sys/select.h>
J
Juan Quintela 已提交
47
#ifdef CONFIG_BSD
48
#include <sys/stat.h>
A
Aurelien Jarno 已提交
49
#if defined(__FreeBSD__) || defined(__FreeBSD_kernel__) || defined(__DragonFly__)
50
#include <libutil.h>
B
blueswir1 已提交
51 52
#else
#include <util.h>
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
#endif
#ifdef __linux__
#include <pty.h>
#include <malloc.h>
#include <linux/rtc.h>

/* For the benefit of older linux systems which don't supply it,
   we use a local copy of hpet.h. */
/* #include <linux/hpet.h> */
#include "hpet.h"

#include <linux/ppdev.h>
#include <linux/parport.h>
#endif
#ifdef __sun__
#include <sys/stat.h>
#include <sys/ethernet.h>
#include <sys/sockio.h>
#include <netinet/arp.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/ip_icmp.h> // must come after ip.h
#include <netinet/udp.h>
#include <netinet/tcp.h>
#include <net/if.h>
#include <syslog.h>
#include <stropts.h>
#endif
#endif
#endif

#if defined(__OpenBSD__)
#include <util.h>
#endif

89 90
#include "qemu-common.h"
#include "net.h"
91
#include "net/tap.h"
92
#include "net/slirp.h"
93
#include "net/vde.h"
94 95 96 97 98 99
#include "monitor.h"
#include "sysemu.h"
#include "qemu-timer.h"
#include "qemu-char.h"
#include "audio/audio.h"
#include "qemu_socket.h"
100
#include "qemu-log.h"
101
#include "qemu-config.h"
102

103
static QTAILQ_HEAD(, VLANState) vlans;
104
static QTAILQ_HEAD(, VLANClientState) non_vlan_clients;
105 106 107 108

/***********************************************************/
/* network device redirectors */

109
#if defined(DEBUG_NET)
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
static void hex_dump(FILE *f, const uint8_t *buf, int size)
{
    int len, i, j, c;

    for(i=0;i<size;i+=16) {
        len = size - i;
        if (len > 16)
            len = 16;
        fprintf(f, "%08x ", i);
        for(j=0;j<16;j++) {
            if (j < len)
                fprintf(f, " %02x", buf[i+j]);
            else
                fprintf(f, "   ");
        }
        fprintf(f, " ");
        for(j=0;j<len;j++) {
            c = buf[i+j];
            if (c < ' ' || c > '~')
                c = '.';
            fprintf(f, "%c", c);
        }
        fprintf(f, "\n");
    }
}
#endif

static int parse_macaddr(uint8_t *macaddr, const char *p)
{
    int i;
    char *last_char;
    long int offset;

    errno = 0;
    offset = strtol(p, &last_char, 0);    
    if (0 == errno && '\0' == *last_char &&
            offset >= 0 && offset <= 0xFFFFFF) {
        macaddr[3] = (offset & 0xFF0000) >> 16;
        macaddr[4] = (offset & 0xFF00) >> 8;
        macaddr[5] = offset & 0xFF;
        return 0;
    } else {
        for(i = 0; i < 6; i++) {
            macaddr[i] = strtol(p, (char **)&p, 16);
            if (i == 5) {
                if (*p != '\0')
                    return -1;
            } else {
                if (*p != ':' && *p != '-')
                    return -1;
                p++;
            }
        }
        return 0;    
    }

    return -1;
}

static int get_str_sep(char *buf, int buf_size, const char **pp, int sep)
{
    const char *p, *p1;
    int len;
    p = *pp;
    p1 = strchr(p, sep);
    if (!p1)
        return -1;
    len = p1 - p;
    p1++;
    if (buf_size > 0) {
        if (len > buf_size - 1)
            len = buf_size - 1;
        memcpy(buf, p, len);
        buf[len] = '\0';
    }
    *pp = p1;
    return 0;
}

int parse_host_src_port(struct sockaddr_in *haddr,
                        struct sockaddr_in *saddr,
                        const char *input_str)
{
    char *str = strdup(input_str);
    char *host_str = str;
    char *src_str;
    const char *src_str2;
    char *ptr;

    /*
     * Chop off any extra arguments at the end of the string which
     * would start with a comma, then fill in the src port information
     * if it was provided else use the "any address" and "any port".
     */
    if ((ptr = strchr(str,',')))
        *ptr = '\0';

    if ((src_str = strchr(input_str,'@'))) {
        *src_str = '\0';
        src_str++;
    }

    if (parse_host_port(haddr, host_str) < 0)
        goto fail;

    src_str2 = src_str;
    if (!src_str || *src_str == '\0')
        src_str2 = ":0";

    if (parse_host_port(saddr, src_str2) < 0)
        goto fail;

    free(str);
    return(0);

fail:
    free(str);
    return -1;
}

int parse_host_port(struct sockaddr_in *saddr, const char *str)
{
    char buf[512];
    struct hostent *he;
    const char *p, *r;
    int port;

    p = str;
    if (get_str_sep(buf, sizeof(buf), &p, ':') < 0)
        return -1;
    saddr->sin_family = AF_INET;
    if (buf[0] == '\0') {
        saddr->sin_addr.s_addr = 0;
    } else {
244
        if (qemu_isdigit(buf[0])) {
245 246 247 248 249 250 251 252 253 254 255 256 257 258 259
            if (!inet_aton(buf, &saddr->sin_addr))
                return -1;
        } else {
            if ((he = gethostbyname(buf)) == NULL)
                return - 1;
            saddr->sin_addr = *(struct in_addr *)he->h_addr;
        }
    }
    port = strtol(p, (char **)&r, 0);
    if (r == p)
        return -1;
    saddr->sin_port = htons(port);
    return 0;
}

260 261 262
void qemu_format_nic_info_str(VLANClientState *vc, uint8_t macaddr[6])
{
    snprintf(vc->info_str, sizeof(vc->info_str),
263 264
             "model=%s,macaddr=%02x:%02x:%02x:%02x:%02x:%02x",
             vc->model,
265 266 267 268
             macaddr[0], macaddr[1], macaddr[2],
             macaddr[3], macaddr[4], macaddr[5]);
}

G
Gerd Hoffmann 已提交
269 270 271 272 273 274 275 276 277 278 279 280 281 282 283
void qemu_macaddr_default_if_unset(MACAddr *macaddr)
{
    static int index = 0;
    static const MACAddr zero = { .a = { 0,0,0,0,0,0 } };

    if (memcmp(macaddr, &zero, sizeof(zero)) != 0)
        return;
    macaddr->a[0] = 0x52;
    macaddr->a[1] = 0x54;
    macaddr->a[2] = 0x00;
    macaddr->a[3] = 0x12;
    macaddr->a[4] = 0x34;
    macaddr->a[5] = 0x56 + index++;
}

284 285 286 287 288 289
static char *assign_name(VLANClientState *vc1, const char *model)
{
    VLANState *vlan;
    char buf[256];
    int id = 0;

290
    QTAILQ_FOREACH(vlan, &vlans, next) {
291 292
        VLANClientState *vc;

293 294
        QTAILQ_FOREACH(vc, &vlan->clients, next) {
            if (vc != vc1 && strcmp(vc->model, model) == 0) {
295
                id++;
296 297
            }
        }
298 299 300 301
    }

    snprintf(buf, sizeof(buf), "%s.%d", model, id);

302
    return qemu_strdup(buf);
303 304
}

305
static ssize_t qemu_deliver_packet(VLANClientState *sender,
306
                                   unsigned flags,
307 308 309 310
                                   const uint8_t *data,
                                   size_t size,
                                   void *opaque);
static ssize_t qemu_deliver_packet_iov(VLANClientState *sender,
311
                                       unsigned flags,
312 313 314 315
                                       const struct iovec *iov,
                                       int iovcnt,
                                       void *opaque);

M
Mark McLoughlin 已提交
316 317
VLANClientState *qemu_new_vlan_client(net_client_type type,
                                      VLANState *vlan,
318
                                      VLANClientState *peer,
319
                                      const char *model,
320
                                      const char *name,
321 322
                                      NetCanReceive *can_receive,
                                      NetReceive *receive,
323
                                      NetReceive *receive_raw,
324
                                      NetReceiveIOV *receive_iov,
325
                                      NetCleanup *cleanup,
326 327
                                      void *opaque)
{
328 329
    VLANClientState *vc;

330
    vc = qemu_mallocz(sizeof(VLANClientState));
331

M
Mark McLoughlin 已提交
332
    vc->type = type;
333
    vc->model = qemu_strdup(model);
334
    if (name)
335
        vc->name = qemu_strdup(name);
336 337
    else
        vc->name = assign_name(vc, model);
338 339
    vc->can_receive = can_receive;
    vc->receive = receive;
340
    vc->receive_raw = receive_raw;
341
    vc->receive_iov = receive_iov;
342
    vc->cleanup = cleanup;
343
    vc->opaque = opaque;
344

345
    if (vlan) {
346
        assert(!peer);
347 348
        vc->vlan = vlan;
        QTAILQ_INSERT_TAIL(&vc->vlan->clients, vc, next);
349
    } else {
350 351 352 353
        if (peer) {
            vc->peer = peer;
            peer->peer = vc;
        }
354
        QTAILQ_INSERT_TAIL(&non_vlan_clients, vc, next);
355 356 357 358

        vc->send_queue = qemu_new_net_queue(qemu_deliver_packet,
                                            qemu_deliver_packet_iov,
                                            vc);
359
    }
360 361 362 363 364 365

    return vc;
}

void qemu_del_vlan_client(VLANClientState *vc)
{
366 367
    if (vc->vlan) {
        QTAILQ_REMOVE(&vc->vlan->clients, vc, next);
368
    } else {
369 370 371
        if (vc->send_queue) {
            qemu_del_net_queue(vc->send_queue);
        }
372
        QTAILQ_REMOVE(&non_vlan_clients, vc, next);
373 374 375
        if (vc->peer) {
            vc->peer->peer = NULL;
        }
376
    }
377

378 379 380 381 382 383 384
    if (vc->cleanup) {
        vc->cleanup(vc);
    }

    qemu_free(vc->name);
    qemu_free(vc->model);
    qemu_free(vc);
385 386
}

387 388
VLANClientState *qemu_find_vlan_client(VLANState *vlan, void *opaque)
{
389
    VLANClientState *vc;
390

391 392 393 394 395
    QTAILQ_FOREACH(vc, &vlan->clients, next) {
        if (vc->opaque == opaque) {
            return vc;
        }
    }
396 397 398 399

    return NULL;
}

400
VLANClientState *
401 402 403 404 405 406 407 408 409 410 411 412
qemu_find_vlan_client_by_name(Monitor *mon, int vlan_id,
                              const char *client_str)
{
    VLANState *vlan;
    VLANClientState *vc;

    vlan = qemu_find_vlan(vlan_id, 0);
    if (!vlan) {
        monitor_printf(mon, "unknown VLAN %d\n", vlan_id);
        return NULL;
    }

413
    QTAILQ_FOREACH(vc, &vlan->clients, next) {
414 415 416 417 418 419 420 421 422 423 424 425
        if (!strcmp(vc->name, client_str)) {
            break;
        }
    }
    if (!vc) {
        monitor_printf(mon, "can't find device %s on VLAN %d\n",
                       client_str, vlan_id);
    }

    return vc;
}

426
int qemu_can_send_packet(VLANClientState *sender)
427
{
428
    VLANState *vlan = sender->vlan;
429 430
    VLANClientState *vc;

431
    if (sender->peer) {
432 433 434 435
        if (sender->peer->receive_disabled) {
            return 0;
        } else if (sender->peer->can_receive &&
                   !sender->peer->can_receive(sender->peer)) {
436
            return 0;
437 438
        } else {
            return 1;
439 440 441
        }
    }

442 443 444 445
    if (!sender->vlan) {
        return 1;
    }

446
    QTAILQ_FOREACH(vc, &vlan->clients, next) {
447 448 449 450
        if (vc == sender) {
            continue;
        }

451
        /* no can_receive() handler, they can always receive */
452
        if (!vc->can_receive || vc->can_receive(vc)) {
453
            return 1;
454 455 456 457 458
        }
    }
    return 0;
}

459
static ssize_t qemu_deliver_packet(VLANClientState *sender,
460
                                   unsigned flags,
461 462 463 464 465
                                   const uint8_t *data,
                                   size_t size,
                                   void *opaque)
{
    VLANClientState *vc = opaque;
466
    ssize_t ret;
467 468 469 470 471

    if (vc->link_down) {
        return size;
    }

472 473 474 475 476 477 478 479 480 481 482 483 484 485 486
    if (vc->receive_disabled) {
        return 0;
    }

    if (flags & QEMU_NET_PACKET_FLAG_RAW && vc->receive_raw) {
        ret = vc->receive_raw(vc, data, size);
    } else {
        ret = vc->receive(vc, data, size);
    }

    if (ret == 0) {
        vc->receive_disabled = 1;
    };

    return ret;
487 488
}

489
static ssize_t qemu_vlan_deliver_packet(VLANClientState *sender,
490
                                        unsigned flags,
491 492 493
                                        const uint8_t *buf,
                                        size_t size,
                                        void *opaque)
494
{
495
    VLANState *vlan = opaque;
496
    VLANClientState *vc;
497
    ssize_t ret = -1;
498

499
    QTAILQ_FOREACH(vc, &vlan->clients, next) {
500 501 502 503
        ssize_t len;

        if (vc == sender) {
            continue;
504
        }
505 506 507 508 509 510

        if (vc->link_down) {
            ret = size;
            continue;
        }

511 512 513 514 515 516
        if (vc->receive_disabled) {
            ret = 0;
            continue;
        }

        if (flags & QEMU_NET_PACKET_FLAG_RAW && vc->receive_raw) {
517
            len = vc->receive_raw(vc, buf, size);
518
        } else {
519
            len = vc->receive(vc, buf, size);
520 521 522 523 524
        }

        if (len == 0) {
            vc->receive_disabled = 1;
        }
525 526

        ret = (ret >= 0) ? ret : len;
527

528
    }
529 530

    return ret;
531 532
}

533 534
void qemu_purge_queued_packets(VLANClientState *vc)
{
535 536 537
    NetQueue *queue;

    if (!vc->peer && !vc->vlan) {
538
        return;
539
    }
540

541 542 543 544 545 546 547
    if (vc->peer) {
        queue = vc->peer->send_queue;
    } else {
        queue = vc->vlan->send_queue;
    }

    qemu_net_queue_purge(queue, vc);
548 549
}

550
void qemu_flush_queued_packets(VLANClientState *vc)
551
{
552 553
    NetQueue *queue;

554 555
    vc->receive_disabled = 0;

556 557 558 559 560
    if (vc->vlan) {
        queue = vc->vlan->send_queue;
    } else {
        queue = vc->send_queue;
    }
561

562
    qemu_net_queue_flush(queue);
563 564
}

565 566 567 568
static ssize_t qemu_send_packet_async_with_flags(VLANClientState *sender,
                                                 unsigned flags,
                                                 const uint8_t *buf, int size,
                                                 NetPacketSent *sent_cb)
569
{
570
    NetQueue *queue;
571

572
#ifdef DEBUG_NET
573
    printf("qemu_send_packet_async:\n");
574 575
    hex_dump(stdout, buf, size);
#endif
576

577 578 579 580 581 582 583 584 585 586
    if (sender->link_down || (!sender->peer && !sender->vlan)) {
        return size;
    }

    if (sender->peer) {
        queue = sender->peer->send_queue;
    } else {
        queue = sender->vlan->send_queue;
    }

587 588 589 590 591 592 593 594 595
    return qemu_net_queue_send(queue, sender, flags, buf, size, sent_cb);
}

ssize_t qemu_send_packet_async(VLANClientState *sender,
                               const uint8_t *buf, int size,
                               NetPacketSent *sent_cb)
{
    return qemu_send_packet_async_with_flags(sender, QEMU_NET_PACKET_FLAG_NONE,
                                             buf, size, sent_cb);
596 597 598 599 600
}

void qemu_send_packet(VLANClientState *vc, const uint8_t *buf, int size)
{
    qemu_send_packet_async(vc, buf, size, NULL);
601 602
}

603 604 605 606 607 608
ssize_t qemu_send_packet_raw(VLANClientState *vc, const uint8_t *buf, int size)
{
    return qemu_send_packet_async_with_flags(vc, QEMU_NET_PACKET_FLAG_RAW,
                                             buf, size, NULL);
}

A
aliguori 已提交
609 610 611 612 613 614 615 616 617 618 619 620 621 622 623
static ssize_t vc_sendv_compat(VLANClientState *vc, const struct iovec *iov,
                               int iovcnt)
{
    uint8_t buffer[4096];
    size_t offset = 0;
    int i;

    for (i = 0; i < iovcnt; i++) {
        size_t len;

        len = MIN(sizeof(buffer) - offset, iov[i].iov_len);
        memcpy(buffer + offset, iov[i].iov_base, len);
        offset += len;
    }

624
    return vc->receive(vc, buffer, offset);
A
aliguori 已提交
625 626
}

627 628 629 630 631 632 633 634 635 636
static ssize_t calc_iov_length(const struct iovec *iov, int iovcnt)
{
    size_t offset = 0;
    int i;

    for (i = 0; i < iovcnt; i++)
        offset += iov[i].iov_len;
    return offset;
}

637
static ssize_t qemu_deliver_packet_iov(VLANClientState *sender,
638
                                       unsigned flags,
639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655
                                       const struct iovec *iov,
                                       int iovcnt,
                                       void *opaque)
{
    VLANClientState *vc = opaque;

    if (vc->link_down) {
        return calc_iov_length(iov, iovcnt);
    }

    if (vc->receive_iov) {
        return vc->receive_iov(vc, iov, iovcnt);
    } else {
        return vc_sendv_compat(vc, iov, iovcnt);
    }
}

656
static ssize_t qemu_vlan_deliver_packet_iov(VLANClientState *sender,
657
                                            unsigned flags,
658 659 660
                                            const struct iovec *iov,
                                            int iovcnt,
                                            void *opaque)
A
aliguori 已提交
661
{
662
    VLANState *vlan = opaque;
A
aliguori 已提交
663
    VLANClientState *vc;
664
    ssize_t ret = -1;
665

666
    QTAILQ_FOREACH(vc, &vlan->clients, next) {
667 668 669 670 671 672 673 674 675 676 677
        ssize_t len;

        if (vc == sender) {
            continue;
        }

        if (vc->link_down) {
            ret = calc_iov_length(iov, iovcnt);
            continue;
        }

678 679
        assert(!(flags & QEMU_NET_PACKET_FLAG_RAW));

680 681 682 683 684 685 686 687 688 689 690 691
        if (vc->receive_iov) {
            len = vc->receive_iov(vc, iov, iovcnt);
        } else {
            len = vc_sendv_compat(vc, iov, iovcnt);
        }

        ret = (ret >= 0) ? ret : len;
    }

    return ret;
}

692 693 694
ssize_t qemu_sendv_packet_async(VLANClientState *sender,
                                const struct iovec *iov, int iovcnt,
                                NetPacketSent *sent_cb)
695
{
696 697 698
    NetQueue *queue;

    if (sender->link_down || (!sender->peer && !sender->vlan)) {
699 700 701
        return calc_iov_length(iov, iovcnt);
    }

702 703 704 705 706 707
    if (sender->peer) {
        queue = sender->peer->send_queue;
    } else {
        queue = sender->vlan->send_queue;
    }

708 709 710
    return qemu_net_queue_send_iov(queue, sender,
                                   QEMU_NET_PACKET_FLAG_NONE,
                                   iov, iovcnt, sent_cb);
A
aliguori 已提交
711 712
}

713 714 715 716 717 718
ssize_t
qemu_sendv_packet(VLANClientState *vc, const struct iovec *iov, int iovcnt)
{
    return qemu_sendv_packet_async(vc, iov, iovcnt, NULL);
}

719 720 721 722 723
/* network connection */
typedef struct NetSocketState {
    VLANClientState *vc;
    int fd;
    int state; /* 0 = getting length, 1 = getting data */
724 725
    unsigned int index;
    unsigned int packet_len;
726 727 728 729 730 731
    uint8_t buf[4096];
    struct sockaddr_in dgram_dst; /* contains inet host and port destination iff connectionless (SOCK_DGRAM) */
} NetSocketState;

typedef struct NetSocketListenState {
    VLANState *vlan;
732
    char *model;
733
    char *name;
734 735 736 737
    int fd;
} NetSocketListenState;

/* XXX: we consider we can send the whole packet without blocking */
738
static ssize_t net_socket_receive(VLANClientState *vc, const uint8_t *buf, size_t size)
739
{
740
    NetSocketState *s = vc->opaque;
741 742 743 744
    uint32_t len;
    len = htonl(size);

    send_all(s->fd, (const uint8_t *)&len, sizeof(len));
745
    return send_all(s->fd, buf, size);
746 747
}

748
static ssize_t net_socket_receive_dgram(VLANClientState *vc, const uint8_t *buf, size_t size)
749
{
750
    NetSocketState *s = vc->opaque;
751

752
    return sendto(s->fd, (const void *)buf, size, 0,
753
                  (struct sockaddr *)&s->dgram_dst, sizeof(s->dgram_dst));
754 755 756 757 758
}

static void net_socket_send(void *opaque)
{
    NetSocketState *s = opaque;
759 760
    int size, err;
    unsigned l;
761 762 763
    uint8_t buf1[4096];
    const uint8_t *buf;

B
Blue Swirl 已提交
764
    size = recv(s->fd, (void *)buf1, sizeof(buf1), 0);
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
    if (size < 0) {
        err = socket_error();
        if (err != EWOULDBLOCK)
            goto eoc;
    } else if (size == 0) {
        /* end of connection */
    eoc:
        qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
        closesocket(s->fd);
        return;
    }
    buf = buf1;
    while (size > 0) {
        /* reassemble a packet from the network */
        switch(s->state) {
        case 0:
            l = 4 - s->index;
            if (l > size)
                l = size;
            memcpy(s->buf + s->index, buf, l);
            buf += l;
            size -= l;
            s->index += l;
            if (s->index == 4) {
                /* got length */
                s->packet_len = ntohl(*(uint32_t *)s->buf);
                s->index = 0;
                s->state = 1;
            }
            break;
        case 1:
            l = s->packet_len - s->index;
            if (l > size)
                l = size;
799 800 801 802 803 804 805 806 807
            if (s->index + l <= sizeof(s->buf)) {
                memcpy(s->buf + s->index, buf, l);
            } else {
                fprintf(stderr, "serious error: oversized packet received,"
                    "connection terminated.\n");
                s->state = 0;
                goto eoc;
            }

808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825
            s->index += l;
            buf += l;
            size -= l;
            if (s->index >= s->packet_len) {
                qemu_send_packet(s->vc, s->buf, s->packet_len);
                s->index = 0;
                s->state = 0;
            }
            break;
        }
    }
}

static void net_socket_send_dgram(void *opaque)
{
    NetSocketState *s = opaque;
    int size;

B
Blue Swirl 已提交
826
    size = recv(s->fd, (void *)s->buf, sizeof(s->buf), 0);
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
    if (size < 0)
        return;
    if (size == 0) {
        /* end of connection */
        qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
        return;
    }
    qemu_send_packet(s->vc, s->buf, size);
}

static int net_socket_mcast_create(struct sockaddr_in *mcastaddr)
{
    struct ip_mreq imr;
    int fd;
    int val, ret;
    if (!IN_MULTICAST(ntohl(mcastaddr->sin_addr.s_addr))) {
	fprintf(stderr, "qemu: error: specified mcastaddr \"%s\" (0x%08x) does not contain a multicast address\n",
		inet_ntoa(mcastaddr->sin_addr),
                (int)ntohl(mcastaddr->sin_addr.s_addr));
	return -1;

    }
    fd = socket(PF_INET, SOCK_DGRAM, 0);
    if (fd < 0) {
        perror("socket(PF_INET, SOCK_DGRAM)");
        return -1;
    }

    val = 1;
    ret=setsockopt(fd, SOL_SOCKET, SO_REUSEADDR,
                   (const char *)&val, sizeof(val));
    if (ret < 0) {
	perror("setsockopt(SOL_SOCKET, SO_REUSEADDR)");
	goto fail;
    }

    ret = bind(fd, (struct sockaddr *)mcastaddr, sizeof(*mcastaddr));
    if (ret < 0) {
        perror("bind");
        goto fail;
    }

    /* Add host to multicast group */
    imr.imr_multiaddr = mcastaddr->sin_addr;
    imr.imr_interface.s_addr = htonl(INADDR_ANY);

    ret = setsockopt(fd, IPPROTO_IP, IP_ADD_MEMBERSHIP,
                     (const char *)&imr, sizeof(struct ip_mreq));
    if (ret < 0) {
	perror("setsockopt(IP_ADD_MEMBERSHIP)");
	goto fail;
    }

    /* Force mcast msgs to loopback (eg. several QEMUs in same host */
    val = 1;
    ret=setsockopt(fd, IPPROTO_IP, IP_MULTICAST_LOOP,
                   (const char *)&val, sizeof(val));
    if (ret < 0) {
	perror("setsockopt(SOL_IP, IP_MULTICAST_LOOP)");
	goto fail;
    }

    socket_set_nonblock(fd);
    return fd;
fail:
    if (fd >= 0)
        closesocket(fd);
    return -1;
}

897 898 899 900 901 902 903 904
static void net_socket_cleanup(VLANClientState *vc)
{
    NetSocketState *s = vc->opaque;
    qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
    close(s->fd);
    qemu_free(s);
}

905 906 907
static NetSocketState *net_socket_fd_init_dgram(VLANState *vlan,
                                                const char *model,
                                                const char *name,
908
                                                int fd, int is_connected)
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
{
    struct sockaddr_in saddr;
    int newfd;
    socklen_t saddr_len;
    NetSocketState *s;

    /* fd passed: multicast: "learn" dgram_dst address from bound address and save it
     * Because this may be "shared" socket from a "master" process, datagrams would be recv()
     * by ONLY ONE process: we must "clone" this dgram socket --jjo
     */

    if (is_connected) {
	if (getsockname(fd, (struct sockaddr *) &saddr, &saddr_len) == 0) {
	    /* must be bound */
	    if (saddr.sin_addr.s_addr==0) {
		fprintf(stderr, "qemu: error: init_dgram: fd=%d unbound, cannot setup multicast dst addr\n",
			fd);
		return NULL;
	    }
	    /* clone dgram socket */
	    newfd = net_socket_mcast_create(&saddr);
	    if (newfd < 0) {
		/* error already reported by net_socket_mcast_create() */
		close(fd);
		return NULL;
	    }
	    /* clone newfd to fd, close newfd */
	    dup2(newfd, fd);
	    close(newfd);

	} else {
	    fprintf(stderr, "qemu: error: init_dgram: fd=%d failed getsockname(): %s\n",
		    fd, strerror(errno));
	    return NULL;
	}
    }

    s = qemu_mallocz(sizeof(NetSocketState));
    s->fd = fd;

M
Mark McLoughlin 已提交
949 950
    s->vc = qemu_new_vlan_client(NET_CLIENT_TYPE_SOCKET,
                                 vlan, NULL, model, name, NULL,
951
                                 net_socket_receive_dgram, NULL, NULL,
952
                                 net_socket_cleanup, s);
953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970
    qemu_set_fd_handler(s->fd, net_socket_send_dgram, NULL, s);

    /* mcast: save bound address as dst */
    if (is_connected) s->dgram_dst=saddr;

    snprintf(s->vc->info_str, sizeof(s->vc->info_str),
	    "socket: fd=%d (%s mcast=%s:%d)",
	    fd, is_connected? "cloned" : "",
	    inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
    return s;
}

static void net_socket_connect(void *opaque)
{
    NetSocketState *s = opaque;
    qemu_set_fd_handler(s->fd, net_socket_send, NULL, s);
}

971 972 973
static NetSocketState *net_socket_fd_init_stream(VLANState *vlan,
                                                 const char *model,
                                                 const char *name,
974
                                                 int fd, int is_connected)
975 976 977 978
{
    NetSocketState *s;
    s = qemu_mallocz(sizeof(NetSocketState));
    s->fd = fd;
M
Mark McLoughlin 已提交
979 980
    s->vc = qemu_new_vlan_client(NET_CLIENT_TYPE_SOCKET,
                                 vlan, NULL, model, name, NULL,
981
                                 net_socket_receive, NULL, NULL,
982
                                 net_socket_cleanup, s);
983 984 985 986 987 988 989 990 991 992
    snprintf(s->vc->info_str, sizeof(s->vc->info_str),
             "socket: fd=%d", fd);
    if (is_connected) {
        net_socket_connect(s);
    } else {
        qemu_set_fd_handler(s->fd, NULL, net_socket_connect, s);
    }
    return s;
}

993 994
static NetSocketState *net_socket_fd_init(VLANState *vlan,
                                          const char *model, const char *name,
995
                                          int fd, int is_connected)
996
{
M
Michael S. Tsirkin 已提交
997
    int so_type = -1, optlen=sizeof(so_type);
998 999 1000 1001 1002 1003 1004 1005

    if(getsockopt(fd, SOL_SOCKET, SO_TYPE, (char *)&so_type,
        (socklen_t *)&optlen)< 0) {
	fprintf(stderr, "qemu: error: getsockopt(SO_TYPE) for fd=%d failed\n", fd);
	return NULL;
    }
    switch(so_type) {
    case SOCK_DGRAM:
1006
        return net_socket_fd_init_dgram(vlan, model, name, fd, is_connected);
1007
    case SOCK_STREAM:
1008
        return net_socket_fd_init_stream(vlan, model, name, fd, is_connected);
1009 1010 1011
    default:
        /* who knows ... this could be a eg. a pty, do warn and continue as stream */
        fprintf(stderr, "qemu: warning: socket type=%d for fd=%d is not SOCK_DGRAM or SOCK_STREAM\n", so_type, fd);
1012
        return net_socket_fd_init_stream(vlan, model, name, fd, is_connected);
1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
    }
    return NULL;
}

static void net_socket_accept(void *opaque)
{
    NetSocketListenState *s = opaque;
    NetSocketState *s1;
    struct sockaddr_in saddr;
    socklen_t len;
    int fd;

    for(;;) {
        len = sizeof(saddr);
        fd = accept(s->fd, (struct sockaddr *)&saddr, &len);
        if (fd < 0 && errno != EINTR) {
            return;
        } else if (fd >= 0) {
            break;
        }
    }
1034
    s1 = net_socket_fd_init(s->vlan, s->model, s->name, fd, 1);
1035 1036 1037 1038 1039 1040 1041 1042 1043
    if (!s1) {
        closesocket(fd);
    } else {
        snprintf(s1->vc->info_str, sizeof(s1->vc->info_str),
                 "socket: connection from %s:%d",
                 inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
    }
}

1044 1045 1046
static int net_socket_listen_init(VLANState *vlan,
                                  const char *model,
                                  const char *name,
1047
                                  const char *host_str)
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
{
    NetSocketListenState *s;
    int fd, val, ret;
    struct sockaddr_in saddr;

    if (parse_host_port(&saddr, host_str) < 0)
        return -1;

    s = qemu_mallocz(sizeof(NetSocketListenState));

    fd = socket(PF_INET, SOCK_STREAM, 0);
    if (fd < 0) {
        perror("socket");
        return -1;
    }
    socket_set_nonblock(fd);

    /* allow fast reuse */
    val = 1;
    setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, (const char *)&val, sizeof(val));

    ret = bind(fd, (struct sockaddr *)&saddr, sizeof(saddr));
    if (ret < 0) {
        perror("bind");
        return -1;
    }
    ret = listen(fd, 0);
    if (ret < 0) {
        perror("listen");
        return -1;
    }
    s->vlan = vlan;
1080 1081
    s->model = qemu_strdup(model);
    s->name = name ? qemu_strdup(name) : NULL;
1082 1083 1084 1085 1086
    s->fd = fd;
    qemu_set_fd_handler(fd, net_socket_accept, NULL, s);
    return 0;
}

1087 1088 1089
static int net_socket_connect_init(VLANState *vlan,
                                   const char *model,
                                   const char *name,
1090
                                   const char *host_str)
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
{
    NetSocketState *s;
    int fd, connected, ret, err;
    struct sockaddr_in saddr;

    if (parse_host_port(&saddr, host_str) < 0)
        return -1;

    fd = socket(PF_INET, SOCK_STREAM, 0);
    if (fd < 0) {
        perror("socket");
        return -1;
    }
    socket_set_nonblock(fd);

    connected = 0;
    for(;;) {
        ret = connect(fd, (struct sockaddr *)&saddr, sizeof(saddr));
        if (ret < 0) {
            err = socket_error();
            if (err == EINTR || err == EWOULDBLOCK) {
            } else if (err == EINPROGRESS) {
                break;
#ifdef _WIN32
            } else if (err == WSAEALREADY) {
                break;
#endif
            } else {
                perror("connect");
                closesocket(fd);
                return -1;
            }
        } else {
            connected = 1;
            break;
        }
    }
1128
    s = net_socket_fd_init(vlan, model, name, fd, connected);
1129 1130 1131 1132 1133 1134 1135 1136
    if (!s)
        return -1;
    snprintf(s->vc->info_str, sizeof(s->vc->info_str),
             "socket: connect to %s:%d",
             inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
    return 0;
}

1137 1138 1139
static int net_socket_mcast_init(VLANState *vlan,
                                 const char *model,
                                 const char *name,
1140
                                 const char *host_str)
1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153
{
    NetSocketState *s;
    int fd;
    struct sockaddr_in saddr;

    if (parse_host_port(&saddr, host_str) < 0)
        return -1;


    fd = net_socket_mcast_create(&saddr);
    if (fd < 0)
	return -1;

1154
    s = net_socket_fd_init(vlan, model, name, fd, 0);
1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166
    if (!s)
        return -1;

    s->dgram_dst = saddr;

    snprintf(s->vc->info_str, sizeof(s->vc->info_str),
             "socket: mcast=%s:%d",
             inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
    return 0;

}

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
typedef struct DumpState {
    VLANClientState *pcap_vc;
    int fd;
    int pcap_caplen;
} DumpState;

#define PCAP_MAGIC 0xa1b2c3d4

struct pcap_file_hdr {
    uint32_t magic;
    uint16_t version_major;
    uint16_t version_minor;
    int32_t thiszone;
    uint32_t sigfigs;
    uint32_t snaplen;
    uint32_t linktype;
};

struct pcap_sf_pkthdr {
    struct {
        int32_t tv_sec;
        int32_t tv_usec;
    } ts;
    uint32_t caplen;
    uint32_t len;
};

1194
static ssize_t dump_receive(VLANClientState *vc, const uint8_t *buf, size_t size)
1195
{
1196
    DumpState *s = vc->opaque;
1197 1198 1199 1200 1201 1202
    struct pcap_sf_pkthdr hdr;
    int64_t ts;
    int caplen;

    /* Early return in case of previous error. */
    if (s->fd < 0) {
1203
        return size;
1204 1205
    }

1206
    ts = muldiv64(qemu_get_clock(vm_clock), 1000000, get_ticks_per_sec());
1207 1208
    caplen = size > s->pcap_caplen ? s->pcap_caplen : size;

J
Jan Kiszka 已提交
1209
    hdr.ts.tv_sec = ts / 1000000;
1210 1211 1212 1213 1214 1215 1216 1217 1218
    hdr.ts.tv_usec = ts % 1000000;
    hdr.caplen = caplen;
    hdr.len = size;
    if (write(s->fd, &hdr, sizeof(hdr)) != sizeof(hdr) ||
        write(s->fd, buf, caplen) != caplen) {
        qemu_log("-net dump write error - stop dump\n");
        close(s->fd);
        s->fd = -1;
    }
1219 1220

    return size;
1221 1222 1223 1224 1225 1226 1227 1228 1229 1230
}

static void net_dump_cleanup(VLANClientState *vc)
{
    DumpState *s = vc->opaque;

    close(s->fd);
    qemu_free(s);
}

1231
static int net_dump_init(VLANState *vlan, const char *device,
1232 1233 1234 1235 1236 1237 1238
                         const char *name, const char *filename, int len)
{
    struct pcap_file_hdr hdr;
    DumpState *s;

    s = qemu_malloc(sizeof(DumpState));

1239
    s->fd = open(filename, O_CREAT | O_WRONLY | O_BINARY, 0644);
1240
    if (s->fd < 0) {
1241
        qemu_error("-net dump: can't open %s\n", filename);
1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255
        return -1;
    }

    s->pcap_caplen = len;

    hdr.magic = PCAP_MAGIC;
    hdr.version_major = 2;
    hdr.version_minor = 4;
    hdr.thiszone = 0;
    hdr.sigfigs = 0;
    hdr.snaplen = s->pcap_caplen;
    hdr.linktype = 1;

    if (write(s->fd, &hdr, sizeof(hdr)) < sizeof(hdr)) {
1256
        qemu_error("-net dump write error: %s\n", strerror(errno));
1257 1258 1259 1260 1261
        close(s->fd);
        qemu_free(s);
        return -1;
    }

M
Mark McLoughlin 已提交
1262 1263
    s->pcap_vc = qemu_new_vlan_client(NET_CLIENT_TYPE_DUMP,
                                      vlan, NULL, device, name, NULL,
1264
                                      dump_receive, NULL, NULL,
1265 1266 1267 1268 1269 1270
                                      net_dump_cleanup, s);
    snprintf(s->pcap_vc->info_str, sizeof(s->pcap_vc->info_str),
             "dump to %s (len=%d)", filename, len);
    return 0;
}

1271
/* find or alloc a new VLAN */
1272
VLANState *qemu_find_vlan(int id, int allocate)
1273
{
1274 1275 1276 1277
    VLANState *vlan;

    QTAILQ_FOREACH(vlan, &vlans, next) {
        if (vlan->id == id) {
1278
            return vlan;
1279
        }
1280
    }
1281

1282 1283 1284
    if (!allocate) {
        return NULL;
    }
1285

1286 1287
    vlan = qemu_mallocz(sizeof(VLANState));
    vlan->id = id;
1288
    QTAILQ_INIT(&vlan->clients);
1289 1290 1291 1292

    vlan->send_queue = qemu_new_net_queue(qemu_vlan_deliver_packet,
                                          qemu_vlan_deliver_packet_iov,
                                          vlan);
1293 1294 1295

    QTAILQ_INSERT_TAIL(&vlans, vlan, next);

1296 1297 1298
    return vlan;
}

G
Gerd Hoffmann 已提交
1299
VLANClientState *qemu_find_netdev(const char *id)
M
Mark McLoughlin 已提交
1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311
{
    VLANClientState *vc;

    QTAILQ_FOREACH(vc, &non_vlan_clients, next) {
        if (!strcmp(vc->name, id)) {
            return vc;
        }
    }

    return NULL;
}

1312 1313 1314 1315 1316 1317 1318 1319 1320 1321
static int nic_get_free_idx(void)
{
    int index;

    for (index = 0; index < MAX_NICS; index++)
        if (!nd_table[index].used)
            return index;
    return -1;
}

1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334
int qemu_show_nic_models(const char *arg, const char *const *models)
{
    int i;

    if (!arg || strcmp(arg, "?"))
        return 0;

    fprintf(stderr, "qemu: Supported NIC models: ");
    for (i = 0 ; models[i]; i++)
        fprintf(stderr, "%s%c", models[i], models[i+1] ? ',' : '\n');
    return 1;
}

1335 1336 1337 1338 1339 1340 1341
void qemu_check_nic_model(NICInfo *nd, const char *model)
{
    const char *models[2];

    models[0] = model;
    models[1] = NULL;

1342 1343 1344 1345
    if (qemu_show_nic_models(nd->model, models))
        exit(0);
    if (qemu_find_nic_model(nd, models, model) < 0)
        exit(1);
1346 1347
}

1348 1349
int qemu_find_nic_model(NICInfo *nd, const char * const *models,
                        const char *default_model)
1350
{
1351
    int i;
1352 1353

    if (!nd->model)
1354
        nd->model = qemu_strdup(default_model);
1355

1356 1357 1358
    for (i = 0 ; models[i]; i++) {
        if (strcmp(nd->model, models[i]) == 0)
            return i;
1359 1360
    }

1361 1362
    qemu_error("qemu: Unsupported NIC model: %s\n", nd->model);
    return -1;
1363 1364
}

1365
int net_handle_fd_param(Monitor *mon, const char *param)
1366 1367 1368 1369 1370 1371
{
    if (!qemu_isdigit(param[0])) {
        int fd;

        fd = monitor_get_fd(mon, param);
        if (fd == -1) {
1372
            qemu_error("No file descriptor named %s found", param);
1373 1374 1375 1376 1377 1378 1379 1380 1381
            return -1;
        }

        return fd;
    } else {
        return strtol(param, NULL, 0);
    }
}

M
Mark McLoughlin 已提交
1382 1383 1384 1385
static int net_init_nic(QemuOpts *opts,
                        Monitor *mon,
                        const char *name,
                        VLANState *vlan)
1386 1387 1388
{
    int idx;
    NICInfo *nd;
M
Mark McLoughlin 已提交
1389
    const char *netdev;
1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400

    idx = nic_get_free_idx();
    if (idx == -1 || nb_nics >= MAX_NICS) {
        qemu_error("Too Many NICs\n");
        return -1;
    }

    nd = &nd_table[idx];

    memset(nd, 0, sizeof(*nd));

M
Mark McLoughlin 已提交
1401 1402 1403 1404 1405 1406 1407 1408 1409 1410
    if ((netdev = qemu_opt_get(opts, "netdev"))) {
        nd->netdev = qemu_find_netdev(netdev);
        if (!nd->netdev) {
            qemu_error("netdev '%s' not found\n", netdev);
            return -1;
        }
    } else {
        assert(vlan);
        nd->vlan = vlan;
    }
1411 1412 1413
    if (name) {
        nd->name = qemu_strdup(name);
    }
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
    if (qemu_opt_get(opts, "model")) {
        nd->model = qemu_strdup(qemu_opt_get(opts, "model"));
    }
    if (qemu_opt_get(opts, "addr")) {
        nd->devaddr = qemu_strdup(qemu_opt_get(opts, "addr"));
    }

    nd->macaddr[0] = 0x52;
    nd->macaddr[1] = 0x54;
    nd->macaddr[2] = 0x00;
    nd->macaddr[3] = 0x12;
    nd->macaddr[4] = 0x34;
    nd->macaddr[5] = 0x56 + idx;

    if (qemu_opt_get(opts, "macaddr") &&
        parse_macaddr(nd->macaddr, qemu_opt_get(opts, "macaddr")) < 0) {
        qemu_error("invalid syntax for ethernet address\n");
        return -1;
    }

    nd->nvectors = qemu_opt_get_number(opts, "vectors", NIC_NVECTORS_UNSPECIFIED);
    if (nd->nvectors != NIC_NVECTORS_UNSPECIFIED &&
        (nd->nvectors < 0 || nd->nvectors > 0x7ffffff)) {
        qemu_error("invalid # of vectors: %d\n", nd->nvectors);
        return -1;
    }

    nd->used = 1;
M
Mark McLoughlin 已提交
1442 1443 1444
    if (vlan) {
        nd->vlan->nb_guest_devs++;
    }
1445 1446 1447 1448 1449
    nb_nics++;

    return idx;
}

M
Mark McLoughlin 已提交
1450 1451 1452 1453
static int net_init_socket(QemuOpts *opts,
                           Monitor *mon,
                           const char *name,
                           VLANState *vlan)
M
Mark McLoughlin 已提交
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
{
    if (qemu_opt_get(opts, "fd")) {
        int fd;

        if (qemu_opt_get(opts, "listen") ||
            qemu_opt_get(opts, "connect") ||
            qemu_opt_get(opts, "mcast")) {
            qemu_error("listen=, connect= and mcast= is invalid with fd=\n");
            return -1;
        }

        fd = net_handle_fd_param(mon, qemu_opt_get(opts, "fd"));
        if (fd == -1) {
            return -1;
        }

        if (!net_socket_fd_init(vlan, "socket", name, fd, 1)) {
            close(fd);
            return -1;
        }
    } else if (qemu_opt_get(opts, "listen")) {
        const char *listen;

        if (qemu_opt_get(opts, "fd") ||
            qemu_opt_get(opts, "connect") ||
            qemu_opt_get(opts, "mcast")) {
            qemu_error("fd=, connect= and mcast= is invalid with listen=\n");
            return -1;
        }

        listen = qemu_opt_get(opts, "listen");

        if (net_socket_listen_init(vlan, "socket", name, listen) == -1) {
            return -1;
        }
    } else if (qemu_opt_get(opts, "connect")) {
        const char *connect;

        if (qemu_opt_get(opts, "fd") ||
            qemu_opt_get(opts, "listen") ||
            qemu_opt_get(opts, "mcast")) {
            qemu_error("fd=, listen= and mcast= is invalid with connect=\n");
            return -1;
        }

        connect = qemu_opt_get(opts, "connect");

        if (net_socket_connect_init(vlan, "socket", name, connect) == -1) {
            return -1;
        }
    } else if (qemu_opt_get(opts, "mcast")) {
        const char *mcast;

        if (qemu_opt_get(opts, "fd") ||
            qemu_opt_get(opts, "connect") ||
            qemu_opt_get(opts, "listen")) {
            qemu_error("fd=, connect= and listen= is invalid with mcast=\n");
            return -1;
        }

        mcast = qemu_opt_get(opts, "mcast");

        if (net_socket_mcast_init(vlan, "socket", name, mcast) == -1) {
            return -1;
        }
    } else {
        qemu_error("-socket requires fd=, listen=, connect= or mcast=\n");
        return -1;
    }

M
Mark McLoughlin 已提交
1524 1525 1526
    if (vlan) {
        vlan->nb_host_devs++;
    }
M
Mark McLoughlin 已提交
1527 1528 1529 1530

    return 0;
}

M
Mark McLoughlin 已提交
1531 1532 1533 1534
static int net_init_dump(QemuOpts *opts,
                         Monitor *mon,
                         const char *name,
                         VLANState *vlan)
M
Mark McLoughlin 已提交
1535 1536 1537 1538 1539
{
    int len;
    const char *file;
    char def_file[128];

M
Mark McLoughlin 已提交
1540
    assert(vlan);
M
Mark McLoughlin 已提交
1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552

    file = qemu_opt_get(opts, "file");
    if (!file) {
        snprintf(def_file, sizeof(def_file), "qemu-vlan%d.pcap", vlan->id);
        file = def_file;
    }

    len = qemu_opt_get_size(opts, "len", 65536);

    return net_dump_init(vlan, "dump", name, file, len);
}

1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567
#define NET_COMMON_PARAMS_DESC                     \
    {                                              \
        .name = "type",                            \
        .type = QEMU_OPT_STRING,                   \
        .help = "net client type (nic, tap etc.)", \
     }, {                                          \
        .name = "vlan",                            \
        .type = QEMU_OPT_NUMBER,                   \
        .help = "vlan number",                     \
     }, {                                          \
        .name = "name",                            \
        .type = QEMU_OPT_STRING,                   \
        .help = "identifier for monitor commands", \
     }

1568 1569
typedef int (*net_client_init_func)(QemuOpts *opts,
                                    Monitor *mon,
M
Mark McLoughlin 已提交
1570 1571
                                    const char *name,
                                    VLANState *vlan);
1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591

/* magic number, but compiler will warn if too small */
#define NET_MAX_DESC 20

static struct {
    const char *type;
    net_client_init_func init;
    QemuOptDesc desc[NET_MAX_DESC];
} net_client_types[] = {
    {
        .type = "none",
        .desc = {
            NET_COMMON_PARAMS_DESC,
            { /* end of list */ }
        },
    }, {
        .type = "nic",
        .init = net_init_nic,
        .desc = {
            NET_COMMON_PARAMS_DESC,
M
Mark McLoughlin 已提交
1592 1593 1594 1595 1596
            {
                .name = "netdev",
                .type = QEMU_OPT_STRING,
                .help = "id of -netdev to connect to",
            },
1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615
            {
                .name = "macaddr",
                .type = QEMU_OPT_STRING,
                .help = "MAC address",
            }, {
                .name = "model",
                .type = QEMU_OPT_STRING,
                .help = "device model (e1000, rtl8139, virtio etc.)",
            }, {
                .name = "addr",
                .type = QEMU_OPT_STRING,
                .help = "PCI device address",
            }, {
                .name = "vectors",
                .type = QEMU_OPT_NUMBER,
                .help = "number of MSI-x vectors, 0 to disable MSI-X",
            },
            { /* end of list */ }
        },
M
Mark McLoughlin 已提交
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
#ifdef CONFIG_SLIRP
    }, {
        .type = "user",
        .init = net_init_slirp,
        .desc = {
            NET_COMMON_PARAMS_DESC,
            {
                .name = "hostname",
                .type = QEMU_OPT_STRING,
                .help = "client hostname reported by the builtin DHCP server",
            }, {
                .name = "restrict",
                .type = QEMU_OPT_STRING,
                .help = "isolate the guest from the host (y|yes|n|no)",
            }, {
                .name = "ip",
                .type = QEMU_OPT_STRING,
                .help = "legacy parameter, use net= instead",
            }, {
                .name = "net",
                .type = QEMU_OPT_STRING,
                .help = "IP address and optional netmask",
            }, {
                .name = "host",
                .type = QEMU_OPT_STRING,
                .help = "guest-visible address of the host",
            }, {
                .name = "tftp",
                .type = QEMU_OPT_STRING,
                .help = "root directory of the built-in TFTP server",
            }, {
                .name = "bootfile",
                .type = QEMU_OPT_STRING,
                .help = "BOOTP filename, for use with tftp=",
            }, {
                .name = "dhcpstart",
                .type = QEMU_OPT_STRING,
                .help = "the first of the 16 IPs the built-in DHCP server can assign",
            }, {
                .name = "dns",
                .type = QEMU_OPT_STRING,
                .help = "guest-visible address of the virtual nameserver",
            }, {
                .name = "smb",
                .type = QEMU_OPT_STRING,
                .help = "root directory of the built-in SMB server",
            }, {
                .name = "smbserver",
                .type = QEMU_OPT_STRING,
                .help = "IP address of the built-in SMB server",
            }, {
                .name = "hostfwd",
                .type = QEMU_OPT_STRING,
                .help = "guest port number to forward incoming TCP or UDP connections",
            }, {
                .name = "guestfwd",
                .type = QEMU_OPT_STRING,
                .help = "IP address and port to forward guest TCP connections",
            },
            { /* end of list */ }
        },
M
Mark McLoughlin 已提交
1677 1678 1679
#endif
    }, {
        .type = "tap",
1680
        .init = net_init_tap,
M
Mark McLoughlin 已提交
1681 1682 1683 1684 1685 1686 1687
        .desc = {
            NET_COMMON_PARAMS_DESC,
            {
                .name = "ifname",
                .type = QEMU_OPT_STRING,
                .help = "interface name",
            },
1688
#ifndef _WIN32
M
Mark McLoughlin 已提交
1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704
            {
                .name = "fd",
                .type = QEMU_OPT_STRING,
                .help = "file descriptor of an already opened tap",
            }, {
                .name = "script",
                .type = QEMU_OPT_STRING,
                .help = "script to initialize the interface",
            }, {
                .name = "downscript",
                .type = QEMU_OPT_STRING,
                .help = "script to shut down the interface",
            }, {
                .name = "sndbuf",
                .type = QEMU_OPT_SIZE,
                .help = "send buffer limit"
1705 1706 1707 1708
            }, {
                .name = "vnet_hdr",
                .type = QEMU_OPT_BOOL,
                .help = "enable the IFF_VNET_HDR flag on the tap interface"
M
Mark McLoughlin 已提交
1709
            },
1710
#endif /* _WIN32 */
M
Mark McLoughlin 已提交
1711 1712
            { /* end of list */ }
        },
M
Mark McLoughlin 已提交
1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736
    }, {
        .type = "socket",
        .init = net_init_socket,
        .desc = {
            NET_COMMON_PARAMS_DESC,
            {
                .name = "fd",
                .type = QEMU_OPT_STRING,
                .help = "file descriptor of an already opened socket",
            }, {
                .name = "listen",
                .type = QEMU_OPT_STRING,
                .help = "port number, and optional hostname, to listen on",
            }, {
                .name = "connect",
                .type = QEMU_OPT_STRING,
                .help = "port number, and optional hostname, to connect to",
            }, {
                .name = "mcast",
                .type = QEMU_OPT_STRING,
                .help = "UDP multicast address and port number",
            },
            { /* end of list */ }
        },
M
Mark McLoughlin 已提交
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
#ifdef CONFIG_VDE
    }, {
        .type = "vde",
        .init = net_init_vde,
        .desc = {
            NET_COMMON_PARAMS_DESC,
            {
                .name = "sock",
                .type = QEMU_OPT_STRING,
                .help = "socket path",
            }, {
                .name = "port",
                .type = QEMU_OPT_NUMBER,
                .help = "port number",
            }, {
                .name = "group",
                .type = QEMU_OPT_STRING,
                .help = "group owner of socket",
            }, {
                .name = "mode",
                .type = QEMU_OPT_NUMBER,
                .help = "permissions for socket",
            },
            { /* end of list */ }
        },
#endif
M
Mark McLoughlin 已提交
1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778
    }, {
        .type = "dump",
        .init = net_init_dump,
        .desc = {
            NET_COMMON_PARAMS_DESC,
            {
                .name = "len",
                .type = QEMU_OPT_SIZE,
                .help = "per-packet size limit (64k default)",
            }, {
                .name = "file",
                .type = QEMU_OPT_STRING,
                .help = "dump file path (default is qemu-vlan0.pcap)",
            },
            { /* end of list */ }
        },
1779 1780 1781 1782
    },
    { /* end of list */ }
};

M
Mark McLoughlin 已提交
1783
int net_client_init(Monitor *mon, QemuOpts *opts, int is_netdev)
1784
{
1785
    const char *name;
1786 1787 1788 1789 1790 1791 1792 1793 1794
    const char *type;
    int i;

    type = qemu_opt_get(opts, "type");
    if (!type) {
        qemu_error("No type specified for -net\n");
        return -1;
    }

M
Mark McLoughlin 已提交
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
    if (is_netdev) {
        if (strcmp(type, "tap") != 0 &&
#ifdef CONFIG_SLIRP
            strcmp(type, "user") != 0 &&
#endif
#ifdef CONFIG_VDE
            strcmp(type, "vde") != 0 &&
#endif
            strcmp(type, "socket") != 0) {
            qemu_error("The '%s' network backend type is not valid with -netdev\n",
                       type);
            return -1;
        }

        if (qemu_opt_get(opts, "vlan")) {
            qemu_error("The 'vlan' parameter is not valid with -netdev\n");
            return -1;
        }
        if (qemu_opt_get(opts, "name")) {
            qemu_error("The 'name' parameter is not valid with -netdev\n");
            return -1;
        }
        if (!qemu_opts_id(opts)) {
            qemu_error("The id= parameter is required with -netdev\n");
            return -1;
        }
    }

1823 1824 1825 1826 1827
    name = qemu_opts_id(opts);
    if (!name) {
        name = qemu_opt_get(opts, "name");
    }

1828 1829
    for (i = 0; net_client_types[i].type != NULL; i++) {
        if (!strcmp(net_client_types[i].type, type)) {
M
Mark McLoughlin 已提交
1830 1831
            VLANState *vlan = NULL;

1832 1833 1834 1835
            if (qemu_opts_validate(opts, &net_client_types[i].desc[0]) == -1) {
                return -1;
            }

M
Mark McLoughlin 已提交
1836 1837 1838 1839
            /* Do not add to a vlan if it's a -netdev or a nic with a
             * netdev= parameter. */
            if (!(is_netdev ||
                  (strcmp(type, "nic") == 0 && qemu_opt_get(opts, "netdev")))) {
M
Mark McLoughlin 已提交
1840 1841 1842
                vlan = qemu_find_vlan(qemu_opt_get_number(opts, "vlan", 0), 1);
            }

1843
            if (net_client_types[i].init) {
M
Mark McLoughlin 已提交
1844
                return net_client_types[i].init(opts, mon, name, vlan);
1845 1846 1847 1848 1849 1850 1851 1852 1853 1854
            } else {
                return 0;
            }
        }
    }

    qemu_error("Invalid -net type '%s'\n", type);
    return -1;
}

1855 1856
void net_client_uninit(NICInfo *nd)
{
1857 1858 1859
    if (nd->vlan) {
        nd->vlan->nb_guest_devs--;
    }
1860
    nb_nics--;
G
Glauber Costa 已提交
1861

1862 1863 1864
    qemu_free(nd->model);
    qemu_free(nd->name);
    qemu_free(nd->devaddr);
G
Glauber Costa 已提交
1865

1866
    nd->used = 0;
1867 1868
}

1869 1870 1871
static int net_host_check_device(const char *device)
{
    int i;
1872
    const char *valid_param_list[] = { "tap", "socket", "dump"
1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888
#ifdef CONFIG_SLIRP
                                       ,"user"
#endif
#ifdef CONFIG_VDE
                                       ,"vde"
#endif
    };
    for (i = 0; i < sizeof(valid_param_list) / sizeof(char *); i++) {
        if (!strncmp(valid_param_list[i], device,
                     strlen(valid_param_list[i])))
            return 1;
    }

    return 0;
}

1889
void net_host_device_add(Monitor *mon, const QDict *qdict)
1890
{
1891
    const char *device = qdict_get_str(qdict, "device");
1892 1893
    const char *opts_str = qdict_get_try_str(qdict, "opts");
    QemuOpts *opts;
1894

1895
    if (!net_host_check_device(device)) {
A
aliguori 已提交
1896
        monitor_printf(mon, "invalid host network device %s\n", device);
1897 1898
        return;
    }
1899 1900 1901 1902 1903 1904 1905 1906 1907 1908

    opts = qemu_opts_parse(&qemu_net_opts, opts_str ? opts_str : "", NULL);
    if (!opts) {
        monitor_printf(mon, "parsing network options '%s' failed\n",
                       opts_str ? opts_str : "");
        return;
    }

    qemu_opt_set(opts, "type", device);

M
Mark McLoughlin 已提交
1909
    if (net_client_init(mon, opts, 0) < 0) {
1910 1911
        monitor_printf(mon, "adding host network device %s failed\n", device);
    }
1912 1913
}

1914
void net_host_device_remove(Monitor *mon, const QDict *qdict)
1915 1916
{
    VLANClientState *vc;
1917 1918
    int vlan_id = qdict_get_int(qdict, "vlan_id");
    const char *device = qdict_get_str(qdict, "device");
1919

1920
    vc = qemu_find_vlan_client_by_name(mon, vlan_id, device);
1921 1922 1923
    if (!vc) {
        return;
    }
1924 1925 1926 1927
    if (!net_host_check_device(vc->model)) {
        monitor_printf(mon, "invalid host network device %s\n", device);
        return;
    }
1928 1929 1930
    qemu_del_vlan_client(vc);
}

1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950
void net_set_boot_mask(int net_boot_mask)
{
    int i;

    /* Only the first four NICs may be bootable */
    net_boot_mask = net_boot_mask & 0xF;

    for (i = 0; i < nb_nics; i++) {
        if (net_boot_mask & (1 << i)) {
            nd_table[i].bootable = 1;
            net_boot_mask &= ~(1 << i);
        }
    }

    if (net_boot_mask) {
        fprintf(stderr, "Cannot boot from non-existent NIC\n");
        exit(1);
    }
}

A
aliguori 已提交
1951
void do_info_network(Monitor *mon)
1952 1953 1954
{
    VLANState *vlan;

1955 1956 1957
    QTAILQ_FOREACH(vlan, &vlans, next) {
        VLANClientState *vc;

A
aliguori 已提交
1958
        monitor_printf(mon, "VLAN %d devices:\n", vlan->id);
1959 1960

        QTAILQ_FOREACH(vc, &vlan->clients, next) {
A
aliguori 已提交
1961
            monitor_printf(mon, "  %s: %s\n", vc->name, vc->info_str);
1962
        }
1963 1964 1965
    }
}

1966
void do_set_link(Monitor *mon, const QDict *qdict)
1967 1968 1969
{
    VLANState *vlan;
    VLANClientState *vc = NULL;
1970 1971
    const char *name = qdict_get_str(qdict, "name");
    const char *up_or_down = qdict_get_str(qdict, "up_or_down");
1972

1973 1974 1975
    QTAILQ_FOREACH(vlan, &vlans, next) {
        QTAILQ_FOREACH(vc, &vlan->clients, next) {
            if (strcmp(vc->name, name) == 0) {
1976
                goto done;
1977 1978 1979
            }
        }
    }
1980
done:
1981 1982

    if (!vc) {
1983
        monitor_printf(mon, "could not find network device '%s'\n", name);
1984
        return;
1985 1986 1987 1988 1989 1990 1991
    }

    if (strcmp(up_or_down, "up") == 0)
        vc->link_down = 0;
    else if (strcmp(up_or_down, "down") == 0)
        vc->link_down = 1;
    else
A
aliguori 已提交
1992 1993
        monitor_printf(mon, "invalid link status '%s'; only 'up' or 'down' "
                       "valid\n", up_or_down);
1994

1995 1996
    if (vc->link_status_changed)
        vc->link_status_changed(vc);
1997 1998
}

1999 2000 2001
void net_cleanup(void)
{
    VLANState *vlan;
2002
    VLANClientState *vc, *next_vc;
2003

2004 2005
    QTAILQ_FOREACH(vlan, &vlans, next) {
        QTAILQ_FOREACH_SAFE(vc, &vlan->clients, next, next_vc) {
2006
            qemu_del_vlan_client(vc);
2007 2008
        }
    }
2009 2010 2011 2012

    QTAILQ_FOREACH_SAFE(vc, &non_vlan_clients, next, next_vc) {
        qemu_del_vlan_client(vc);
    }
2013 2014
}

2015
static void net_check_clients(void)
2016 2017 2018
{
    VLANState *vlan;

2019
    QTAILQ_FOREACH(vlan, &vlans, next) {
2020 2021 2022 2023 2024 2025 2026 2027 2028 2029
        if (vlan->nb_guest_devs == 0 && vlan->nb_host_devs == 0)
            continue;
        if (vlan->nb_guest_devs == 0)
            fprintf(stderr, "Warning: vlan %d with no nics\n", vlan->id);
        if (vlan->nb_host_devs == 0)
            fprintf(stderr,
                    "Warning: vlan %d is not connected to host network\n",
                    vlan->id);
    }
}
2030 2031 2032

static int net_init_client(QemuOpts *opts, void *dummy)
{
2033 2034 2035
    if (net_client_init(NULL, opts, 0) < 0)
        return -1;
    return 0;
M
Mark McLoughlin 已提交
2036 2037 2038 2039 2040
}

static int net_init_netdev(QemuOpts *opts, void *dummy)
{
    return net_client_init(NULL, opts, 1);
2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052
}

int net_init_clients(void)
{
    if (QTAILQ_EMPTY(&qemu_net_opts.head)) {
        /* if no clients, we use a default config */
        qemu_opts_set(&qemu_net_opts, NULL, "type", "nic");
#ifdef CONFIG_SLIRP
        qemu_opts_set(&qemu_net_opts, NULL, "type", "user");
#endif
    }

2053
    QTAILQ_INIT(&vlans);
2054
    QTAILQ_INIT(&non_vlan_clients);
2055

M
Mark McLoughlin 已提交
2056 2057 2058
    if (qemu_opts_foreach(&qemu_netdev_opts, net_init_netdev, NULL, 1) == -1)
        return -1;

2059 2060 2061 2062 2063 2064 2065 2066 2067
    if (qemu_opts_foreach(&qemu_net_opts, net_init_client, NULL, 1) == -1) {
        return -1;
    }

    net_check_clients();

    return 0;
}

2068
int net_client_parse(QemuOptsList *opts_list, const char *optarg)
2069
{
2070
#if defined(CONFIG_SLIRP)
2071 2072
    int ret;
    if (net_slirp_parse_legacy(opts_list, optarg, &ret)) {
2073 2074
        return ret;
    }
2075
#endif
2076

2077
    if (!qemu_opts_parse(opts_list, optarg, "type")) {
2078 2079 2080 2081 2082
        return -1;
    }

    return 0;
}