Archipelago » qemu

/*

 * 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 "net.h"

#include "config-host.h"

#include "net/tap.h"

#include "net/socket.h"

#include "net/dump.h"

#include "net/slirp.h"

#include "net/vde.h"

#include "net/util.h"

#include "monitor.h"

#include "sysemu.h"

#include "qemu-common.h"

#include "qemu_socket.h"

static QTAILQ_HEAD(, VLANState) vlans;

static QTAILQ_HEAD(, VLANClientState) non_vlan_clients;

int default_net = 1;

/***********************************************************/

/* network device redirectors */

#if defined(DEBUG_NET)

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 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 {

        if (qemu_isdigit(buf[0])) {

            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;

}

void qemu_format_nic_info_str(VLANClientState *vc, uint8_t macaddr[6])

{

    snprintf(vc->info_str, sizeof(vc->info_str),

             "model=%s,macaddr=%02x:%02x:%02x:%02x:%02x:%02x",

             vc->model,

             macaddr[0], macaddr[1], macaddr[2],

             macaddr[3], macaddr[4], macaddr[5]);

}

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++;

}

static char *assign_name(VLANClientState *vc1, const char *model)

{

    VLANState *vlan;

    char buf[256];

    int id = 0;

    QTAILQ_FOREACH(vlan, &vlans, next) {

        VLANClientState *vc;

        QTAILQ_FOREACH(vc, &vlan->clients, next) {

            if (vc != vc1 && strcmp(vc->model, model) == 0) {

                id++;

            }

        }

    }

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

    return qemu_strdup(buf);

}

static ssize_t qemu_deliver_packet(VLANClientState *sender,

                                   unsigned flags,

                                   const uint8_t *data,

                                   size_t size,

                                   void *opaque);

static ssize_t qemu_deliver_packet_iov(VLANClientState *sender,

                                       unsigned flags,

                                       const struct iovec *iov,

                                       int iovcnt,

                                       void *opaque);

VLANClientState *qemu_new_net_client(NetClientInfo *info,

                                     VLANState *vlan,

                                     VLANClientState *peer,

                                     const char *model,

                                     const char *name)

{

    VLANClientState *vc;

    assert(info->size >= sizeof(VLANClientState));

    vc = qemu_mallocz(info->size);

    vc->info = info;

    vc->model = qemu_strdup(model);

    if (name) {

        vc->name = qemu_strdup(name);

    } else {

        vc->name = assign_name(vc, model);

    }

    if (vlan) {

        assert(!peer);

        vc->vlan = vlan;

        QTAILQ_INSERT_TAIL(&vc->vlan->clients, vc, next);

    } else {

        if (peer) {

            vc->peer = peer;

            peer->peer = vc;

        }

        QTAILQ_INSERT_TAIL(&non_vlan_clients, vc, next);

        vc->send_queue = qemu_new_net_queue(qemu_deliver_packet,

                                            qemu_deliver_packet_iov,

                                            vc);

    }

    return vc;

}

NICState *qemu_new_nic(NetClientInfo *info,

                       NICConf *conf,

                       const char *model,

                       const char *name,

                       void *opaque)

{

    VLANClientState *nc;

    NICState *nic;

    assert(info->type == NET_CLIENT_TYPE_NIC);

    assert(info->size >= sizeof(NICState));

    nc = qemu_new_net_client(info, conf->vlan, conf->peer, model, name);

    nic = DO_UPCAST(NICState, nc, nc);

    nic->conf = conf;

    nic->opaque = opaque;

    return nic;

}

void qemu_del_vlan_client(VLANClientState *vc)

{

    if (vc->vlan) {

        QTAILQ_REMOVE(&vc->vlan->clients, vc, next);

    } else {

        if (vc->send_queue) {

            qemu_del_net_queue(vc->send_queue);

        }

        QTAILQ_REMOVE(&non_vlan_clients, vc, next);

        if (vc->peer) {

            vc->peer->peer = NULL;

        }

    }

    if (vc->info->cleanup) {

        vc->info->cleanup(vc);

    }

    qemu_free(vc->name);

    qemu_free(vc->model);

    qemu_free(vc);

}

VLANClientState *

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;

    }

    QTAILQ_FOREACH(vc, &vlan->clients, next) {

        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;

}

void qemu_foreach_nic(qemu_nic_foreach func, void *opaque)

{

    VLANClientState *nc;

    VLANState *vlan;

    QTAILQ_FOREACH(nc, &non_vlan_clients, next) {

        if (nc->info->type == NET_CLIENT_TYPE_NIC) {

            func(DO_UPCAST(NICState, nc, nc), opaque);

        }

    }

    QTAILQ_FOREACH(vlan, &vlans, next) {

        QTAILQ_FOREACH(nc, &vlan->clients, next) {

            if (nc->info->type == NET_CLIENT_TYPE_NIC) {

                func(DO_UPCAST(NICState, nc, nc), opaque);

            }

        }

    }

}

int qemu_can_send_packet(VLANClientState *sender)

{

    VLANState *vlan = sender->vlan;

    VLANClientState *vc;

    if (sender->peer) {

        if (sender->peer->receive_disabled) {

            return 0;

        } else if (sender->peer->info->can_receive &&

                   !sender->peer->info->can_receive(sender->peer)) {

            return 0;

        } else {

            return 1;

        }

    }

    if (!sender->vlan) {

        return 1;

    }

    QTAILQ_FOREACH(vc, &vlan->clients, next) {

        if (vc == sender) {

            continue;

        }

        /* no can_receive() handler, they can always receive */

        if (!vc->info->can_receive || vc->info->can_receive(vc)) {

            return 1;

        }

    }

    return 0;

}

static ssize_t qemu_deliver_packet(VLANClientState *sender,

                                   unsigned flags,

                                   const uint8_t *data,

                                   size_t size,

                                   void *opaque)

{

    VLANClientState *vc = opaque;

    ssize_t ret;

    if (vc->link_down) {

        return size;

    }

    if (vc->receive_disabled) {

        return 0;

    }

    if (flags & QEMU_NET_PACKET_FLAG_RAW && vc->info->receive_raw) {

        ret = vc->info->receive_raw(vc, data, size);

    } else {

        ret = vc->info->receive(vc, data, size);

    }

    if (ret == 0) {

        vc->receive_disabled = 1;

    };

    return ret;

}

static ssize_t qemu_vlan_deliver_packet(VLANClientState *sender,

                                        unsigned flags,

                                        const uint8_t *buf,

                                        size_t size,

                                        void *opaque)

{

    VLANState *vlan = opaque;

    VLANClientState *vc;

    ssize_t ret = -1;

    QTAILQ_FOREACH(vc, &vlan->clients, next) {

        ssize_t len;

        if (vc == sender) {

            continue;

        }

        if (vc->link_down) {

            ret = size;

            continue;

        }

        if (vc->receive_disabled) {

            ret = 0;

            continue;

        }

        if (flags & QEMU_NET_PACKET_FLAG_RAW && vc->info->receive_raw) {

            len = vc->info->receive_raw(vc, buf, size);

        } else {

            len = vc->info->receive(vc, buf, size);

        }

        if (len == 0) {

            vc->receive_disabled = 1;

        }

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

    }

    return ret;

}

void qemu_purge_queued_packets(VLANClientState *vc)

{

    NetQueue *queue;

    if (!vc->peer && !vc->vlan) {

        return;

    }

    if (vc->peer) {

        queue = vc->peer->send_queue;

    } else {

        queue = vc->vlan->send_queue;

    }

    qemu_net_queue_purge(queue, vc);

}

void qemu_flush_queued_packets(VLANClientState *vc)

{

    NetQueue *queue;

    vc->receive_disabled = 0;

    if (vc->vlan) {

        queue = vc->vlan->send_queue;

    } else {

        queue = vc->send_queue;

    }

    qemu_net_queue_flush(queue);

}

static ssize_t qemu_send_packet_async_with_flags(VLANClientState *sender,

                                                 unsigned flags,

                                                 const uint8_t *buf, int size,

                                                 NetPacketSent *sent_cb)

{

    NetQueue *queue;

#ifdef DEBUG_NET

    printf("qemu_send_packet_async:\n");

    hex_dump(stdout, buf, size);

#endif

    if (sender->link_down || (!sender->peer && !sender->vlan)) {

        return size;

    }

    if (sender->peer) {

        queue = sender->peer->send_queue;

    } else {

        queue = sender->vlan->send_queue;

    }

    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);

}

void qemu_send_packet(VLANClientState *vc, const uint8_t *buf, int size)

{

    qemu_send_packet_async(vc, buf, size, NULL);

}

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);

}

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;

    }

    return vc->info->receive(vc, buffer, offset);

}

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;

}

static ssize_t qemu_deliver_packet_iov(VLANClientState *sender,

                                       unsigned flags,

                                       const struct iovec *iov,

                                       int iovcnt,

                                       void *opaque)

{

    VLANClientState *vc = opaque;

    if (vc->link_down) {

        return calc_iov_length(iov, iovcnt);

    }

    if (vc->info->receive_iov) {

        return vc->info->receive_iov(vc, iov, iovcnt);

    } else {

        return vc_sendv_compat(vc, iov, iovcnt);

    }

}

static ssize_t qemu_vlan_deliver_packet_iov(VLANClientState *sender,

                                            unsigned flags,

                                            const struct iovec *iov,

                                            int iovcnt,

                                            void *opaque)

{

    VLANState *vlan = opaque;

    VLANClientState *vc;

    ssize_t ret = -1;

    QTAILQ_FOREACH(vc, &vlan->clients, next) {

        ssize_t len;

        if (vc == sender) {

            continue;

        }

        if (vc->link_down) {

            ret = calc_iov_length(iov, iovcnt);

            continue;

        }

        assert(!(flags & QEMU_NET_PACKET_FLAG_RAW));

        if (vc->info->receive_iov) {

            len = vc->info->receive_iov(vc, iov, iovcnt);

        } else {

            len = vc_sendv_compat(vc, iov, iovcnt);

        }

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

    }

    return ret;

}

ssize_t qemu_sendv_packet_async(VLANClientState *sender,

                                const struct iovec *iov, int iovcnt,

                                NetPacketSent *sent_cb)

{

    NetQueue *queue;

    if (sender->link_down || (!sender->peer && !sender->vlan)) {

        return calc_iov_length(iov, iovcnt);

    }

    if (sender->peer) {

        queue = sender->peer->send_queue;

    } else {

        queue = sender->vlan->send_queue;

    }

    return qemu_net_queue_send_iov(queue, sender,

                                   QEMU_NET_PACKET_FLAG_NONE,

                                   iov, iovcnt, sent_cb);

}

ssize_t

qemu_sendv_packet(VLANClientState *vc, const struct iovec *iov, int iovcnt)

{

    return qemu_sendv_packet_async(vc, iov, iovcnt, NULL);

}

/* find or alloc a new VLAN */

VLANState *qemu_find_vlan(int id, int allocate)

{

    VLANState *vlan;

    QTAILQ_FOREACH(vlan, &vlans, next) {

        if (vlan->id == id) {

            return vlan;

        }

    }

    if (!allocate) {

        return NULL;

    }

    vlan = qemu_mallocz(sizeof(VLANState));

    vlan->id = id;

    QTAILQ_INIT(&vlan->clients);

    vlan->send_queue = qemu_new_net_queue(qemu_vlan_deliver_packet,

                                          qemu_vlan_deliver_packet_iov,

                                          vlan);

    QTAILQ_INSERT_TAIL(&vlans, vlan, next);

    return vlan;

}

VLANClientState *qemu_find_netdev(const char *id)

{

    VLANClientState *vc;

    QTAILQ_FOREACH(vc, &non_vlan_clients, next) {

        if (!strcmp(vc->name, id)) {

            return vc;

        }

    }

    return NULL;

}

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;

}

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;

}

void qemu_check_nic_model(NICInfo *nd, const char *model)

{

    const char *models[2];

    models[0] = model;

    models[1] = NULL;

    if (qemu_show_nic_models(nd->model, models))

        exit(0);

    if (qemu_find_nic_model(nd, models, model) < 0)

        exit(1);

}

int qemu_find_nic_model(NICInfo *nd, const char * const *models,

                        const char *default_model)

{

    int i;

    if (!nd->model)

        nd->model = qemu_strdup(default_model);

    for (i = 0 ; models[i]; i++) {

        if (strcmp(nd->model, models[i]) == 0)

            return i;

    }

    qemu_error("qemu: Unsupported NIC model: %s\n", nd->model);

    return -1;

}

int net_handle_fd_param(Monitor *mon, const char *param)

{

    if (!qemu_isdigit(param[0])) {

        int fd;

        fd = monitor_get_fd(mon, param);

        if (fd == -1) {

            qemu_error("No file descriptor named %s found", param);

            return -1;

        }

        return fd;

    } else {

        return strtol(param, NULL, 0);

    }

}

static int net_init_nic(QemuOpts *opts,

                        Monitor *mon,

                        const char *name,

                        VLANState *vlan)

{

    int idx;

    NICInfo *nd;

    const char *netdev;

    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));

    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;

    }

    if (name) {

        nd->name = qemu_strdup(name);

    }

    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") &&

        net_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;

    if (vlan) {

        nd->vlan->nb_guest_devs++;

    }

    nb_nics++;

    return idx;

}

#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", \

     }

typedef int (*net_client_init_func)(QemuOpts *opts,

                                    Monitor *mon,

                                    const char *name,

                                    VLANState *vlan);

/* 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,

            {

                .name = "netdev",

                .type = QEMU_OPT_STRING,

                .help = "id of -netdev to connect to",

            },

            {

                .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 */ }

        },

#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",