Archipelago » qemu

/*

 * Virtio Network Device

 *

 * Copyright IBM, Corp. 2007

 *

 * Authors:

 *  Anthony Liguori   <aliguori@us.ibm.com>

 *

 * This work is licensed under the terms of the GNU GPL, version 2.  See

 * the COPYING file in the top-level directory.

 *

 */

#include "qemu/iov.h"

#include "hw/virtio/virtio.h"

#include "net/net.h"

#include "net/checksum.h"

#include "net/tap.h"

#include "qemu/error-report.h"

#include "qemu/timer.h"

#include "hw/virtio/virtio-net.h"

#include "net/vhost_net.h"

#include "hw/virtio/virtio-bus.h"

#define VIRTIO_NET_VM_VERSION    11

#define MAC_TABLE_ENTRIES    64

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

/*

 * Calculate the number of bytes up to and including the given 'field' of

 * 'container'.

 */

#define endof(container, field) \

    (offsetof(container, field) + sizeof(((container *)0)->field))

typedef struct VirtIOFeature {

    uint32_t flags;

    size_t end;

} VirtIOFeature;

static VirtIOFeature feature_sizes[] = {

    {.flags = 1 << VIRTIO_NET_F_MAC,

     .end = endof(struct virtio_net_config, mac)},

    {.flags = 1 << VIRTIO_NET_F_STATUS,

     .end = endof(struct virtio_net_config, status)},

    {.flags = 1 << VIRTIO_NET_F_MQ,

     .end = endof(struct virtio_net_config, max_virtqueue_pairs)},

    {}

};

static VirtIONetQueue *virtio_net_get_subqueue(NetClientState *nc)

{

    VirtIONet *n = qemu_get_nic_opaque(nc);

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

}

static int vq2q(int queue_index)

{

    return queue_index / 2;

}

/* TODO

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

 */

static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config)

{

    VirtIONet *n = VIRTIO_NET(vdev);

    struct virtio_net_config netcfg;

    stw_p(&netcfg.status, n->status);

    stw_p(&netcfg.max_virtqueue_pairs, n->max_queues);

    memcpy(netcfg.mac, n->mac, ETH_ALEN);

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

}

static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config)

{

    VirtIONet *n = VIRTIO_NET(vdev);

    struct virtio_net_config netcfg = {};

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

    if (!(vdev->guest_features >> VIRTIO_NET_F_CTRL_MAC_ADDR & 1) &&

        memcmp(netcfg.mac, n->mac, ETH_ALEN)) {

        memcpy(n->mac, netcfg.mac, ETH_ALEN);

        qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac);

    }

}

static bool virtio_net_started(VirtIONet *n, uint8_t status)

{

    VirtIODevice *vdev = VIRTIO_DEVICE(n);

    return (status & VIRTIO_CONFIG_S_DRIVER_OK) &&

        (n->status & VIRTIO_NET_S_LINK_UP) && vdev->vm_running;

}

static void virtio_net_vhost_status(VirtIONet *n, uint8_t status)

{

    VirtIODevice *vdev = VIRTIO_DEVICE(n);

    NetClientState *nc = qemu_get_queue(n->nic);

    int queues = n->multiqueue ? n->max_queues : 1;

    if (!nc->peer) {

        return;

    }

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

        return;

    }

    if (!tap_get_vhost_net(nc->peer)) {

        return;

    }

    if (!!n->vhost_started ==

        (virtio_net_started(n, status) && !nc->peer->link_down)) {

        return;

    }

    if (!n->vhost_started) {

        int r;

        if (!vhost_net_query(tap_get_vhost_net(nc->peer), vdev)) {

            return;

        }

        n->vhost_started = 1;

        r = vhost_net_start(vdev, n->nic->ncs, queues);

        if (r < 0) {

            error_report("unable to start vhost net: %d: "

                         "falling back on userspace virtio", -r);

            n->vhost_started = 0;

        }

    } else {

        vhost_net_stop(vdev, n->nic->ncs, queues);

        n->vhost_started = 0;

    }

}

static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)

{

    VirtIONet *n = VIRTIO_NET(vdev);

    VirtIONetQueue *q;

    int i;

    uint8_t queue_status;

    virtio_net_vhost_status(n, status);

    for (i = 0; i < n->max_queues; i++) {

        q = &n->vqs[i];

        if ((!n->multiqueue && i != 0) || i >= n->curr_queues) {

            queue_status = 0;

        } else {

            queue_status = status;

        }

        if (!q->tx_waiting) {

            continue;

        }

        if (virtio_net_started(n, queue_status) && !n->vhost_started) {

            if (q->tx_timer) {

                qemu_mod_timer(q->tx_timer,

                               qemu_get_clock_ns(vm_clock) + n->tx_timeout);

            } else {

                qemu_bh_schedule(q->tx_bh);

            }

        } else {

            if (q->tx_timer) {

                qemu_del_timer(q->tx_timer);

            } else {

                qemu_bh_cancel(q->tx_bh);

            }

        }

    }

}

static void virtio_net_set_link_status(NetClientState *nc)

{

    VirtIONet *n = qemu_get_nic_opaque(nc);

    VirtIODevice *vdev = VIRTIO_DEVICE(n);

    uint16_t old_status = n->status;

    if (nc->link_down)

        n->status &= ~VIRTIO_NET_S_LINK_UP;

    else

        n->status |= VIRTIO_NET_S_LINK_UP;

    if (n->status != old_status)

        virtio_notify_config(vdev);

    virtio_net_set_status(vdev, vdev->status);

}

static void virtio_net_reset(VirtIODevice *vdev)

{

    VirtIONet *n = VIRTIO_NET(vdev);

    /* Reset back to compatibility mode */

    n->promisc = 1;

    n->allmulti = 0;

    n->alluni = 0;

    n->nomulti = 0;

    n->nouni = 0;

    n->nobcast = 0;

    /* multiqueue is disabled by default */

    n->curr_queues = 1;

    /* Flush any MAC and VLAN filter table state */

    n->mac_table.in_use = 0;

    n->mac_table.first_multi = 0;

    n->mac_table.multi_overflow = 0;

    n->mac_table.uni_overflow = 0;

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

    memcpy(&n->mac[0], &n->nic->conf->macaddr, sizeof(n->mac));

    memset(n->vlans, 0, MAX_VLAN >> 3);

}

static void peer_test_vnet_hdr(VirtIONet *n)

{

    NetClientState *nc = qemu_get_queue(n->nic);

    if (!nc->peer) {

        return;

    }

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

        return;

    }

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

}

static int peer_has_vnet_hdr(VirtIONet *n)

{

    return n->has_vnet_hdr;

}

static int peer_has_ufo(VirtIONet *n)

{

    if (!peer_has_vnet_hdr(n))

        return 0;

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

    return n->has_ufo;

}

static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs)

{

    int i;

    NetClientState *nc;

    n->mergeable_rx_bufs = mergeable_rx_bufs;

    n->guest_hdr_len = n->mergeable_rx_bufs ?

        sizeof(struct virtio_net_hdr_mrg_rxbuf) : sizeof(struct virtio_net_hdr);

    for (i = 0; i < n->max_queues; i++) {

        nc = qemu_get_subqueue(n->nic, i);

        if (peer_has_vnet_hdr(n) &&

            tap_has_vnet_hdr_len(nc->peer, n->guest_hdr_len)) {

            tap_set_vnet_hdr_len(nc->peer, n->guest_hdr_len);

            n->host_hdr_len = n->guest_hdr_len;

        }

    }

}

static int peer_attach(VirtIONet *n, int index)

{

    NetClientState *nc = qemu_get_subqueue(n->nic, index);

    if (!nc->peer) {

        return 0;

    }

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

        return 0;

    }

    return tap_enable(nc->peer);

}

static int peer_detach(VirtIONet *n, int index)

{

    NetClientState *nc = qemu_get_subqueue(n->nic, index);

    if (!nc->peer) {

        return 0;

    }

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

        return 0;

    }

    return tap_disable(nc->peer);

}

static void virtio_net_set_queues(VirtIONet *n)

{

    int i;

    for (i = 0; i < n->max_queues; i++) {

        if (i < n->curr_queues) {

            assert(!peer_attach(n, i));

        } else {

            assert(!peer_detach(n, i));

        }

    }

}

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

static uint32_t virtio_net_get_features(VirtIODevice *vdev, uint32_t features)

{

    VirtIONet *n = VIRTIO_NET(vdev);

    NetClientState *nc = qemu_get_queue(n->nic);

    features |= (1 << VIRTIO_NET_F_MAC);

    if (!peer_has_vnet_hdr(n)) {

        features &= ~(0x1 << VIRTIO_NET_F_CSUM);

        features &= ~(0x1 << VIRTIO_NET_F_HOST_TSO4);

        features &= ~(0x1 << VIRTIO_NET_F_HOST_TSO6);

        features &= ~(0x1 << VIRTIO_NET_F_HOST_ECN);

        features &= ~(0x1 << VIRTIO_NET_F_GUEST_CSUM);

        features &= ~(0x1 << VIRTIO_NET_F_GUEST_TSO4);

        features &= ~(0x1 << VIRTIO_NET_F_GUEST_TSO6);

        features &= ~(0x1 << VIRTIO_NET_F_GUEST_ECN);

    }

    if (!peer_has_vnet_hdr(n) || !peer_has_ufo(n)) {

        features &= ~(0x1 << VIRTIO_NET_F_GUEST_UFO);

        features &= ~(0x1 << VIRTIO_NET_F_HOST_UFO);

    }

    if (!nc->peer || nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {

        return features;

    }

    if (!tap_get_vhost_net(nc->peer)) {

        return features;

    }

    return vhost_net_get_features(tap_get_vhost_net(nc->peer), features);

}

static uint32_t virtio_net_bad_features(VirtIODevice *vdev)

{

    uint32_t features = 0;

    /* Linux kernel 2.6.25.  It understood MAC (as everyone must),

     * but also these: */

    features |= (1 << VIRTIO_NET_F_MAC);

    features |= (1 << VIRTIO_NET_F_CSUM);

    features |= (1 << VIRTIO_NET_F_HOST_TSO4);

    features |= (1 << VIRTIO_NET_F_HOST_TSO6);

    features |= (1 << VIRTIO_NET_F_HOST_ECN);

    return features;

}

static void virtio_net_apply_guest_offloads(VirtIONet *n)

{

    tap_set_offload(qemu_get_subqueue(n->nic, 0)->peer,

            !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_CSUM)),

            !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_TSO4)),

            !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_TSO6)),

            !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_ECN)),

            !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_UFO)));

}

static uint64_t virtio_net_guest_offloads_by_features(uint32_t features)

{

    static const uint64_t guest_offloads_mask =

        (1ULL << VIRTIO_NET_F_GUEST_CSUM) |

        (1ULL << VIRTIO_NET_F_GUEST_TSO4) |

        (1ULL << VIRTIO_NET_F_GUEST_TSO6) |

        (1ULL << VIRTIO_NET_F_GUEST_ECN)  |

        (1ULL << VIRTIO_NET_F_GUEST_UFO);

    return guest_offloads_mask & features;

}

static inline uint64_t virtio_net_supported_guest_offloads(VirtIONet *n)

{

    VirtIODevice *vdev = VIRTIO_DEVICE(n);

    return virtio_net_guest_offloads_by_features(vdev->guest_features);

}

static void virtio_net_set_features(VirtIODevice *vdev, uint32_t features)

{

    VirtIONet *n = VIRTIO_NET(vdev);

    int i;

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

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

    if (n->has_vnet_hdr) {

        n->curr_guest_offloads =

            virtio_net_guest_offloads_by_features(features);

        virtio_net_apply_guest_offloads(n);

    }

    for (i = 0;  i < n->max_queues; i++) {

        NetClientState *nc = qemu_get_subqueue(n->nic, i);

        if (!nc->peer || nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {

            continue;

        }

        if (!tap_get_vhost_net(nc->peer)) {

            continue;

        }

        vhost_net_ack_features(tap_get_vhost_net(nc->peer), features);

    }

}

static int virtio_net_handle_rx_mode(VirtIONet *n, uint8_t cmd,

                                     struct iovec *iov, unsigned int iov_cnt)

{

    uint8_t on;

    size_t s;

    s = iov_to_buf(iov, iov_cnt, 0, &on, sizeof(on));

    if (s != sizeof(on)) {

        return VIRTIO_NET_ERR;

    }

    if (cmd == VIRTIO_NET_CTRL_RX_PROMISC) {

        n->promisc = on;

    } else if (cmd == VIRTIO_NET_CTRL_RX_ALLMULTI) {

        n->allmulti = on;

    } else if (cmd == VIRTIO_NET_CTRL_RX_ALLUNI) {

        n->alluni = on;

    } else if (cmd == VIRTIO_NET_CTRL_RX_NOMULTI) {

        n->nomulti = on;

    } else if (cmd == VIRTIO_NET_CTRL_RX_NOUNI) {

        n->nouni = on;

    } else if (cmd == VIRTIO_NET_CTRL_RX_NOBCAST) {

        n->nobcast = on;

    } else {

        return VIRTIO_NET_ERR;

    }

    return VIRTIO_NET_OK;

}

static int virtio_net_handle_offloads(VirtIONet *n, uint8_t cmd,

                                     struct iovec *iov, unsigned int iov_cnt)

{

    VirtIODevice *vdev = VIRTIO_DEVICE(n);

    uint64_t offloads;

    size_t s;

    if (!((1 << VIRTIO_NET_F_CTRL_GUEST_OFFLOADS) & vdev->guest_features)) {

        return VIRTIO_NET_ERR;

    }

    s = iov_to_buf(iov, iov_cnt, 0, &offloads, sizeof(offloads));

    if (s != sizeof(offloads)) {

        return VIRTIO_NET_ERR;

    }

    if (cmd == VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET) {

        uint64_t supported_offloads;

        if (!n->has_vnet_hdr) {

            return VIRTIO_NET_ERR;

        }

        supported_offloads = virtio_net_supported_guest_offloads(n);

        if (offloads & ~supported_offloads) {

            return VIRTIO_NET_ERR;

        }

        n->curr_guest_offloads = offloads;

        virtio_net_apply_guest_offloads(n);

        return VIRTIO_NET_OK;

    } else {

        return VIRTIO_NET_ERR;

    }

}

static int virtio_net_handle_mac(VirtIONet *n, uint8_t cmd,

                                 struct iovec *iov, unsigned int iov_cnt)

{

    struct virtio_net_ctrl_mac mac_data;

    size_t s;

    if (cmd == VIRTIO_NET_CTRL_MAC_ADDR_SET) {

        if (iov_size(iov, iov_cnt) != sizeof(n->mac)) {

            return VIRTIO_NET_ERR;

        }

        s = iov_to_buf(iov, iov_cnt, 0, &n->mac, sizeof(n->mac));

        assert(s == sizeof(n->mac));

        qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac);

        return VIRTIO_NET_OK;

    }

    if (cmd != VIRTIO_NET_CTRL_MAC_TABLE_SET) {

        return VIRTIO_NET_ERR;

    }

    n->mac_table.in_use = 0;

    n->mac_table.first_multi = 0;

    n->mac_table.uni_overflow = 0;

    n->mac_table.multi_overflow = 0;

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

    s = iov_to_buf(iov, iov_cnt, 0, &mac_data.entries,

                   sizeof(mac_data.entries));

    mac_data.entries = ldl_p(&mac_data.entries);

    if (s != sizeof(mac_data.entries)) {

        return VIRTIO_NET_ERR;

    }

    iov_discard_front(&iov, &iov_cnt, s);

    if (mac_data.entries * ETH_ALEN > iov_size(iov, iov_cnt)) {

        return VIRTIO_NET_ERR;

    }

    if (mac_data.entries <= MAC_TABLE_ENTRIES) {

        s = iov_to_buf(iov, iov_cnt, 0, n->mac_table.macs,

                       mac_data.entries * ETH_ALEN);

        if (s != mac_data.entries * ETH_ALEN) {

            return VIRTIO_NET_ERR;

        }

        n->mac_table.in_use += mac_data.entries;

    } else {

        n->mac_table.uni_overflow = 1;

    }

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

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

    s = iov_to_buf(iov, iov_cnt, 0, &mac_data.entries,

                   sizeof(mac_data.entries));

    mac_data.entries = ldl_p(&mac_data.entries);

    if (s != sizeof(mac_data.entries)) {

        return VIRTIO_NET_ERR;

    }

    iov_discard_front(&iov, &iov_cnt, s);

    if (mac_data.entries * ETH_ALEN != iov_size(iov, iov_cnt)) {

        return VIRTIO_NET_ERR;

    }

    if (n->mac_table.in_use + mac_data.entries <= MAC_TABLE_ENTRIES) {

        s = iov_to_buf(iov, iov_cnt, 0, n->mac_table.macs,

                       mac_data.entries * ETH_ALEN);

        if (s != mac_data.entries * ETH_ALEN) {

            return VIRTIO_NET_ERR;

        }

        n->mac_table.in_use += mac_data.entries;

    } else {

        n->mac_table.multi_overflow = 1;

    }

    return VIRTIO_NET_OK;

}

static int virtio_net_handle_vlan_table(VirtIONet *n, uint8_t cmd,

                                        struct iovec *iov, unsigned int iov_cnt)

{

    uint16_t vid;

    size_t s;

    s = iov_to_buf(iov, iov_cnt, 0, &vid, sizeof(vid));

    vid = lduw_p(&vid);

    if (s != sizeof(vid)) {

        return VIRTIO_NET_ERR;

    }

    if (vid >= MAX_VLAN)

        return VIRTIO_NET_ERR;

    if (cmd == VIRTIO_NET_CTRL_VLAN_ADD)

        n->vlans[vid >> 5] |= (1U << (vid & 0x1f));

    else if (cmd == VIRTIO_NET_CTRL_VLAN_DEL)

        n->vlans[vid >> 5] &= ~(1U << (vid & 0x1f));

    else

        return VIRTIO_NET_ERR;

    return VIRTIO_NET_OK;

}

static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd,

                                struct iovec *iov, unsigned int iov_cnt)

{

    VirtIODevice *vdev = VIRTIO_DEVICE(n);

    struct virtio_net_ctrl_mq mq;

    size_t s;

    uint16_t queues;

    s = iov_to_buf(iov, iov_cnt, 0, &mq, sizeof(mq));

    if (s != sizeof(mq)) {

        return VIRTIO_NET_ERR;

    }

    if (cmd != VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET) {

        return VIRTIO_NET_ERR;

    }

    queues = lduw_p(&mq.virtqueue_pairs);

    if (queues < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN ||

        queues > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX ||

        queues > n->max_queues ||

        !n->multiqueue) {

        return VIRTIO_NET_ERR;

    }

    n->curr_queues = queues;

    /* stop the backend before changing the number of queues to avoid handling a

     * disabled queue */

    virtio_net_set_status(vdev, vdev->status);

    virtio_net_set_queues(n);

    return VIRTIO_NET_OK;

}

static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)

{

    VirtIONet *n = VIRTIO_NET(vdev);

    struct virtio_net_ctrl_hdr ctrl;

    virtio_net_ctrl_ack status = VIRTIO_NET_ERR;

    VirtQueueElement elem;

    size_t s;

    struct iovec *iov;

    unsigned int iov_cnt;

    while (virtqueue_pop(vq, &elem)) {

        if (iov_size(elem.in_sg, elem.in_num) < sizeof(status) ||

            iov_size(elem.out_sg, elem.out_num) < sizeof(ctrl)) {

            error_report("virtio-net ctrl missing headers");

            exit(1);

        }

        iov = elem.out_sg;

        iov_cnt = elem.out_num;

        s = iov_to_buf(iov, iov_cnt, 0, &ctrl, sizeof(ctrl));

        iov_discard_front(&iov, &iov_cnt, sizeof(ctrl));

        if (s != sizeof(ctrl)) {

            status = VIRTIO_NET_ERR;

        } else if (ctrl.class == VIRTIO_NET_CTRL_RX) {

            status = virtio_net_handle_rx_mode(n, ctrl.cmd, iov, iov_cnt);

        } else if (ctrl.class == VIRTIO_NET_CTRL_MAC) {

            status = virtio_net_handle_mac(n, ctrl.cmd, iov, iov_cnt);

        } else if (ctrl.class == VIRTIO_NET_CTRL_VLAN) {

            status = virtio_net_handle_vlan_table(n, ctrl.cmd, iov, iov_cnt);

        } else if (ctrl.class == VIRTIO_NET_CTRL_MQ) {

            status = virtio_net_handle_mq(n, ctrl.cmd, iov, iov_cnt);

        } else if (ctrl.class == VIRTIO_NET_CTRL_GUEST_OFFLOADS) {

            status = virtio_net_handle_offloads(n, ctrl.cmd, iov, iov_cnt);

        }

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

        assert(s == sizeof(status));

        virtqueue_push(vq, &elem, sizeof(status));

        virtio_notify(vdev, vq);

    }

}

/* RX */

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

{

    VirtIONet *n = VIRTIO_NET(vdev);

    int queue_index = vq2q(virtio_get_queue_index(vq));

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

}

static int virtio_net_can_receive(NetClientState *nc)

{

    VirtIONet *n = qemu_get_nic_opaque(nc);

    VirtIODevice *vdev = VIRTIO_DEVICE(n);

    VirtIONetQueue *q = virtio_net_get_subqueue(nc);

    if (!vdev->vm_running) {

        return 0;

    }

    if (nc->queue_index >= n->curr_queues) {

        return 0;

    }

    if (!virtio_queue_ready(q->rx_vq) ||

        !(vdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) {

        return 0;

    }

    return 1;

}

static int virtio_net_has_buffers(VirtIONetQueue *q, int bufsize)

{

    VirtIONet *n = q->n;

    if (virtio_queue_empty(q->rx_vq) ||

        (n->mergeable_rx_bufs &&

         !virtqueue_avail_bytes(q->rx_vq, bufsize, 0))) {

        virtio_queue_set_notification(q->rx_vq, 1);

        /* To avoid a race condition where the guest has made some buffers

         * available after the above check but before notification was

         * enabled, check for available buffers again.

         */

        if (virtio_queue_empty(q->rx_vq) ||

            (n->mergeable_rx_bufs &&

             !virtqueue_avail_bytes(q->rx_vq, bufsize, 0))) {

            return 0;

        }

    }

    virtio_queue_set_notification(q->rx_vq, 0);

    return 1;

}

/* dhclient uses AF_PACKET but doesn't pass auxdata to the kernel so

 * it never finds out that the packets don't have valid checksums.  This

 * causes dhclient to get upset.  Fedora's carried a patch for ages to

 * fix this with Xen but it hasn't appeared in an upstream release of

 * dhclient yet.

 *

 * To avoid breaking existing guests, we catch udp packets and add

 * checksums.  This is terrible but it's better than hacking the guest

 * kernels.

 *

 * N.B. if we introduce a zero-copy API, this operation is no longer free so

 * we should provide a mechanism to disable it to avoid polluting the host

 * cache.

 */

static void work_around_broken_dhclient(struct virtio_net_hdr *hdr,

                                        uint8_t *buf, size_t size)

{

    if ((hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && /* missing csum */

        (size > 27 && size < 1500) && /* normal sized MTU */

        (buf[12] == 0x08 && buf[13] == 0x00) && /* ethertype == IPv4 */

        (buf[23] == 17) && /* ip.protocol == UDP */

        (buf[34] == 0 && buf[35] == 67)) { /* udp.srcport == bootps */

        net_checksum_calculate(buf, size);

        hdr->flags &= ~VIRTIO_NET_HDR_F_NEEDS_CSUM;

    }

}

static void receive_header(VirtIONet *n, const struct iovec *iov, int iov_cnt,

                           const void *buf, size_t size)

{

    if (n->has_vnet_hdr) {

        /* FIXME this cast is evil */

        void *wbuf = (void *)buf;

        work_around_broken_dhclient(wbuf, wbuf + n->host_hdr_len,

                                    size - n->host_hdr_len);

        iov_from_buf(iov, iov_cnt, 0, buf, sizeof(struct virtio_net_hdr));

    } else {

        struct virtio_net_hdr hdr = {

            .flags = 0,

            .gso_type = VIRTIO_NET_HDR_GSO_NONE

        };

        iov_from_buf(iov, iov_cnt, 0, &hdr, sizeof hdr);

    }

}

static int receive_filter(VirtIONet *n, const uint8_t *buf, int size)

{

    static const uint8_t bcast[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};

    static const uint8_t vlan[] = {0x81, 0x00};

    uint8_t *ptr = (uint8_t *)buf;

    int i;

    if (n->promisc)

        return 1;

    ptr += n->host_hdr_len;

    if (!memcmp(&ptr[12], vlan, sizeof(vlan))) {

        int vid = be16_to_cpup((uint16_t *)(ptr + 14)) & 0xfff;

        if (!(n->vlans[vid >> 5] & (1U << (vid & 0x1f))))

            return 0;

    }

    if (ptr[0] & 1) { // multicast

        if (!memcmp(ptr, bcast, sizeof(bcast))) {

            return !n->nobcast;

        } else if (n->nomulti) {

            return 0;

        } else if (n->allmulti || n->mac_table.multi_overflow) {

            return 1;

        }

        for (i = n->mac_table.first_multi; i < n->mac_table.in_use; i++) {

            if (!memcmp(ptr, &n->mac_table.macs[i * ETH_ALEN], ETH_ALEN)) {

                return 1;

            }

        }

    } else { // unicast

        if (n->nouni) {

            return 0;

        } else if (n->alluni || n->mac_table.uni_overflow) {

            return 1;

        } else if (!memcmp(ptr, n->mac, ETH_ALEN)) {

            return 1;

        }

        for (i = 0; i < n->mac_table.first_multi; i++) {

            if (!memcmp(ptr, &n->mac_table.macs[i * ETH_ALEN], ETH_ALEN)) {

                return 1;

            }

        }

    }

    return 0;

}

static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, size_t size)

{

    VirtIONet *n = qemu_get_nic_opaque(nc);

    VirtIONetQueue *q = virtio_net_get_subqueue(nc);

    VirtIODevice *vdev = VIRTIO_DEVICE(n);

    struct iovec mhdr_sg[VIRTQUEUE_MAX_SIZE];

    struct virtio_net_hdr_mrg_rxbuf mhdr;

    unsigned mhdr_cnt = 0;

    size_t offset, i, guest_offset;

    if (!virtio_net_can_receive(nc)) {

        return -1;

    }

    /* hdr_len refers to the header we supply to the guest */

    if (!virtio_net_has_buffers(q, size + n->guest_hdr_len - n->host_hdr_len)) {

        return 0;

    }

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

        return size;

    offset = i = 0;

    while (offset < size) {

        VirtQueueElement elem;

        int len, total;

        const struct iovec *sg = elem.in_sg;

        total = 0;

        if (virtqueue_pop(q->rx_vq, &elem) == 0) {

            if (i == 0)

                return -1;

            error_report("virtio-net unexpected empty queue: "

                    "i %zd mergeable %d offset %zd, size %zd, "

                    "guest hdr len %zd, host hdr len %zd guest features 0x%x",

                    i, n->mergeable_rx_bufs, offset, size,

                    n->guest_hdr_len, n->host_hdr_len, vdev->guest_features);

            exit(1);

        }

        if (elem.in_num < 1) {

            error_report("virtio-net receive queue contains no in buffers");

            exit(1);

        }

        if (i == 0) {

            assert(offset == 0);

            if (n->mergeable_rx_bufs) {

                mhdr_cnt = iov_copy(mhdr_sg, ARRAY_SIZE(mhdr_sg),

                                    sg, elem.in_num,

                                    offsetof(typeof(mhdr), num_buffers),

                                    sizeof(mhdr.num_buffers));

            }

            receive_header(n, sg, elem.in_num, buf, size);

            offset = n->host_hdr_len;

            total += n->guest_hdr_len;

            guest_offset = n->guest_hdr_len;

        } else {

            guest_offset = 0;

        }

        /* copy in packet.  ugh */

        len = iov_from_buf(sg, elem.in_num, guest_offset,

                           buf + offset, size - offset);

        total += len;

        offset += len;

        /* If buffers can't be merged, at this point we

         * must have consumed the complete packet.

         * Otherwise, drop it. */

        if (!n->mergeable_rx_bufs && offset < size) {

#if 0

            error_report("virtio-net truncated non-mergeable packet: "

                         "i %zd mergeable %d offset %zd, size %zd, "

                         "guest hdr len %zd, host hdr len %zd",

                         i, n->mergeable_rx_bufs,

                         offset, size, n->guest_hdr_len, n->host_hdr_len);

#endif

            return size;

        }

        /* signal other side */

        virtqueue_fill(q->rx_vq, &elem, total, i++);

    }

    if (mhdr_cnt) {

        stw_p(&mhdr.num_buffers, i);

        iov_from_buf(mhdr_sg, mhdr_cnt,