X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=hw%2Fnet%2Fvirtio-net.c;h=06bfe4bcc933a11b8ac554e51b07a4e1d3a8884a;hb=5705653ff8666ffb247971361904f902aa033351;hp=e3c2db32505b8a0be1643afea174a9609f96ba6a;hpb=0030ff40472b9ebf0e0595afbc8d7e428218c5d7;p=mirror_qemu.git diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index e3c2db3250..06bfe4bcc9 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -11,6 +11,7 @@ * */ +#include "qemu/osdep.h" #include "qemu/iov.h" #include "hw/virtio/virtio.h" #include "net/net.h" @@ -30,6 +31,11 @@ #define MAC_TABLE_ENTRIES 64 #define MAX_VLAN (1 << 12) /* Per 802.1Q definition */ +/* previously fixed value */ +#define VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE 256 +/* for now, only allow larger queues; with virtio-1, guest can downsize */ +#define VIRTIO_NET_RX_QUEUE_MIN_SIZE VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE + /* * Calculate the number of bytes up to and including the given 'field' of * 'container'. @@ -86,8 +92,8 @@ static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config) memcpy(&netcfg, config, n->config_size); - if (!virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR) && - !virtio_has_feature(vdev, VIRTIO_F_VERSION_1) && + if (!virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR) && + !virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_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); @@ -128,6 +134,13 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) if (!n->vhost_started) { int r, i; + if (n->needs_vnet_hdr_swap) { + error_report("backend does not support %s vnet headers; " + "falling back on userspace virtio", + virtio_is_big_endian(vdev) ? "BE" : "LE"); + return; + } + /* Any packets outstanding? Purge them to avoid touching rings * when vhost is running. */ @@ -152,6 +165,59 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) } } +static int virtio_net_set_vnet_endian_one(VirtIODevice *vdev, + NetClientState *peer, + bool enable) +{ + if (virtio_is_big_endian(vdev)) { + return qemu_set_vnet_be(peer, enable); + } else { + return qemu_set_vnet_le(peer, enable); + } +} + +static bool virtio_net_set_vnet_endian(VirtIODevice *vdev, NetClientState *ncs, + int queues, bool enable) +{ + int i; + + for (i = 0; i < queues; i++) { + if (virtio_net_set_vnet_endian_one(vdev, ncs[i].peer, enable) < 0 && + enable) { + while (--i >= 0) { + virtio_net_set_vnet_endian_one(vdev, ncs[i].peer, false); + } + + return true; + } + } + + return false; +} + +static void virtio_net_vnet_endian_status(VirtIONet *n, uint8_t status) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(n); + int queues = n->multiqueue ? n->max_queues : 1; + + if (virtio_net_started(n, status)) { + /* Before using the device, we tell the network backend about the + * endianness to use when parsing vnet headers. If the backend + * can't do it, we fallback onto fixing the headers in the core + * virtio-net code. + */ + n->needs_vnet_hdr_swap = virtio_net_set_vnet_endian(vdev, n->nic->ncs, + queues, true); + } else if (virtio_net_started(n, vdev->status)) { + /* After using the device, we need to reset the network backend to + * the default (guest native endianness), otherwise the guest may + * lose network connectivity if it is rebooted into a different + * endianness. + */ + virtio_net_set_vnet_endian(vdev, n->nic->ncs, queues, false); + } +} + static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status) { VirtIONet *n = VIRTIO_NET(vdev); @@ -159,9 +225,12 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status) int i; uint8_t queue_status; + virtio_net_vnet_endian_status(n, status); virtio_net_vhost_status(n, status); for (i = 0; i < n->max_queues; i++) { + NetClientState *ncs = qemu_get_subqueue(n->nic, i); + bool queue_started; q = &n->vqs[i]; if ((!n->multiqueue && i != 0) || i >= n->curr_queues) { @@ -169,12 +238,18 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status) } else { queue_status = status; } + queue_started = + virtio_net_started(n, queue_status) && !n->vhost_started; + + if (queue_started) { + qemu_flush_queued_packets(ncs); + } if (!q->tx_waiting) { continue; } - if (virtio_net_started(n, queue_status) && !n->vhost_started) { + if (queue_started) { if (q->tx_timer) { timer_mod(q->tx_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + n->tx_timeout); @@ -296,7 +371,7 @@ static RxFilterInfo *virtio_net_query_rxfilter(NetClientState *nc) info->multicast_table = str_list; info->vlan_table = get_vlan_table(n); - if (!virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VLAN)) { + if (!virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_VLAN)) { info->vlan = RX_STATE_ALL; } else if (!info->vlan_table) { info->vlan = RX_STATE_NONE; @@ -398,7 +473,11 @@ static int peer_attach(VirtIONet *n, int index) return 0; } - if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) { + if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_USER) { + vhost_set_vring_enable(nc->peer, 1); + } + + if (nc->peer->info->type != NET_CLIENT_DRIVER_TAP) { return 0; } @@ -413,7 +492,11 @@ static int peer_detach(VirtIONet *n, int index) return 0; } - if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) { + if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_USER) { + vhost_set_vring_enable(nc->peer, 0); + } + + if (nc->peer->info->type != NET_CLIENT_DRIVER_TAP) { return 0; } @@ -438,7 +521,8 @@ static void virtio_net_set_queues(VirtIONet *n) static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue); -static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features) +static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features, + Error **errp) { VirtIONet *n = VIRTIO_NET(vdev); NetClientState *nc = qemu_get_queue(n->nic); @@ -520,13 +604,13 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features) int i; virtio_net_set_multiqueue(n, - __virtio_has_feature(features, VIRTIO_NET_F_MQ)); + virtio_has_feature(features, VIRTIO_NET_F_MQ)); virtio_net_set_mrg_rx_bufs(n, - __virtio_has_feature(features, - VIRTIO_NET_F_MRG_RXBUF), - __virtio_has_feature(features, - VIRTIO_F_VERSION_1)); + virtio_has_feature(features, + VIRTIO_NET_F_MRG_RXBUF), + virtio_has_feature(features, + VIRTIO_F_VERSION_1)); if (n->has_vnet_hdr) { n->curr_guest_offloads = @@ -543,7 +627,7 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features) vhost_net_ack_features(get_vhost_net(nc->peer), features); } - if (__virtio_has_feature(features, VIRTIO_NET_F_CTRL_VLAN)) { + if (virtio_has_feature(features, VIRTIO_NET_F_CTRL_VLAN)) { memset(n->vlans, 0, MAX_VLAN >> 3); } else { memset(n->vlans, 0xff, MAX_VLAN >> 3); @@ -590,7 +674,7 @@ static int virtio_net_handle_offloads(VirtIONet *n, uint8_t cmd, uint64_t offloads; size_t s; - if (!virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) { + if (!virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) { return VIRTIO_NET_ERR; } @@ -796,25 +880,32 @@ static int virtio_net_handle_mq(VirtIONet *n, uint8_t cmd, 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; + VirtQueueElement *elem; size_t s; struct iovec *iov, *iov2; 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); + for (;;) { + elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); + if (!elem) { + break; + } + if (iov_size(elem->in_sg, elem->in_num) < sizeof(status) || + iov_size(elem->out_sg, elem->out_num) < sizeof(ctrl)) { + virtio_error(vdev, "virtio-net ctrl missing headers"); + virtqueue_detach_element(vq, elem, 0); + g_free(elem); + break; } - iov_cnt = elem.out_num; - iov2 = iov = g_memdup(elem.out_sg, sizeof(struct iovec) * elem.out_num); + iov_cnt = elem->out_num; + iov2 = iov = g_memdup(elem->out_sg, sizeof(struct iovec) * 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)) { @@ -833,12 +924,13 @@ static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq) 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)); + s = iov_from_buf(elem->in_sg, elem->in_num, 0, &status, sizeof(status)); assert(s == sizeof(status)); - virtqueue_push(vq, &elem, sizeof(status)); + virtqueue_push(vq, elem, sizeof(status)); virtio_notify(vdev, vq); g_free(iov2); + g_free(elem); } } @@ -940,7 +1032,10 @@ static void receive_header(VirtIONet *n, const struct iovec *iov, int iov_cnt, void *wbuf = (void *)buf; work_around_broken_dhclient(wbuf, wbuf + n->host_hdr_len, size - n->host_hdr_len); - virtio_net_hdr_swap(VIRTIO_DEVICE(n), wbuf); + + if (n->needs_vnet_hdr_swap) { + virtio_net_hdr_swap(VIRTIO_DEVICE(n), wbuf); + } iov_from_buf(iov, iov_cnt, 0, buf, sizeof(struct virtio_net_hdr)); } else { struct virtio_net_hdr hdr = { @@ -964,7 +1059,7 @@ static int receive_filter(VirtIONet *n, const uint8_t *buf, int size) ptr += n->host_hdr_len; if (!memcmp(&ptr[12], vlan, sizeof(vlan))) { - int vid = be16_to_cpup((uint16_t *)(ptr + 14)) & 0xfff; + int vid = lduw_be_p(ptr + 14) & 0xfff; if (!(n->vlans[vid >> 5] & (1U << (vid & 0x1f)))) return 0; } @@ -1027,40 +1122,45 @@ static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, size_t offset = i = 0; while (offset < size) { - VirtQueueElement elem; + VirtQueueElement *elem; int len, total; - const struct iovec *sg = elem.in_sg; + const struct iovec *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%" PRIx64, - i, n->mergeable_rx_bufs, offset, size, - n->guest_hdr_len, n->host_hdr_len, - vdev->guest_features); - exit(1); + elem = virtqueue_pop(q->rx_vq, sizeof(VirtQueueElement)); + if (!elem) { + if (i) { + virtio_error(vdev, "virtio-net unexpected empty queue: " + "i %zd mergeable %d offset %zd, size %zd, " + "guest hdr len %zd, host hdr len %zd " + "guest features 0x%" PRIx64, + i, n->mergeable_rx_bufs, offset, size, + n->guest_hdr_len, n->host_hdr_len, + vdev->guest_features); + } + return -1; } - if (elem.in_num < 1) { - error_report("virtio-net receive queue contains no in buffers"); - exit(1); + if (elem->in_num < 1) { + virtio_error(vdev, + "virtio-net receive queue contains no in buffers"); + virtqueue_detach_element(q->rx_vq, elem, 0); + g_free(elem); + return -1; } + sg = elem->in_sg; 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, + sg, elem->in_num, offsetof(typeof(mhdr), num_buffers), sizeof(mhdr.num_buffers)); } - receive_header(n, sg, elem.in_num, buf, size); + 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; @@ -1069,7 +1169,7 @@ static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, size_t } /* copy in packet. ugh */ - len = iov_from_buf(sg, elem.in_num, guest_offset, + len = iov_from_buf(sg, elem->in_num, guest_offset, buf + offset, size - offset); total += len; offset += len; @@ -1077,18 +1177,14 @@ static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, size_t * 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 + virtqueue_discard(q->rx_vq, elem, total); + g_free(elem); return size; } /* signal other side */ - virtqueue_fill(q->rx_vq, &elem, total, i++); + virtqueue_fill(q->rx_vq, elem, total, i++); + g_free(elem); } if (mhdr_cnt) { @@ -1112,10 +1208,11 @@ static void virtio_net_tx_complete(NetClientState *nc, ssize_t len) VirtIONetQueue *q = virtio_net_get_subqueue(nc); VirtIODevice *vdev = VIRTIO_DEVICE(n); - virtqueue_push(q->tx_vq, &q->async_tx.elem, 0); + virtqueue_push(q->tx_vq, q->async_tx.elem, 0); virtio_notify(vdev, q->tx_vq); - q->async_tx.elem.out_num = q->async_tx.len = 0; + g_free(q->async_tx.elem); + q->async_tx.elem = NULL; virtio_queue_set_notification(q->tx_vq, 1); virtio_net_flush_tx(q); @@ -1126,37 +1223,60 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q) { VirtIONet *n = q->n; VirtIODevice *vdev = VIRTIO_DEVICE(n); - VirtQueueElement elem; + VirtQueueElement *elem; int32_t num_packets = 0; int queue_index = vq2q(virtio_get_queue_index(q->tx_vq)); if (!(vdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) { return num_packets; } - if (q->async_tx.elem.out_num) { + if (q->async_tx.elem) { virtio_queue_set_notification(q->tx_vq, 0); return num_packets; } - while (virtqueue_pop(q->tx_vq, &elem)) { - ssize_t ret, len; - unsigned int out_num = elem.out_num; - struct iovec *out_sg = &elem.out_sg[0]; - struct iovec sg[VIRTQUEUE_MAX_SIZE]; + for (;;) { + ssize_t ret; + unsigned int out_num; + struct iovec sg[VIRTQUEUE_MAX_SIZE], sg2[VIRTQUEUE_MAX_SIZE + 1], *out_sg; + struct virtio_net_hdr_mrg_rxbuf mhdr; + + elem = virtqueue_pop(q->tx_vq, sizeof(VirtQueueElement)); + if (!elem) { + break; + } + out_num = elem->out_num; + out_sg = elem->out_sg; if (out_num < 1) { - error_report("virtio-net header not in first element"); - exit(1); + virtio_error(vdev, "virtio-net header not in first element"); + virtqueue_detach_element(q->tx_vq, elem, 0); + g_free(elem); + return -EINVAL; } if (n->has_vnet_hdr) { - if (out_sg[0].iov_len < n->guest_hdr_len) { - error_report("virtio-net header incorrect"); - exit(1); + if (iov_to_buf(out_sg, out_num, 0, &mhdr, n->guest_hdr_len) < + n->guest_hdr_len) { + virtio_error(vdev, "virtio-net header incorrect"); + virtqueue_detach_element(q->tx_vq, elem, 0); + g_free(elem); + return -EINVAL; } - virtio_net_hdr_swap(vdev, (void *) out_sg[0].iov_base); + if (n->needs_vnet_hdr_swap) { + virtio_net_hdr_swap(vdev, (void *) &mhdr); + sg2[0].iov_base = &mhdr; + sg2[0].iov_len = n->guest_hdr_len; + out_num = iov_copy(&sg2[1], ARRAY_SIZE(sg2) - 1, + out_sg, out_num, + n->guest_hdr_len, -1); + if (out_num == VIRTQUEUE_MAX_SIZE) { + goto drop; + } + out_num += 1; + out_sg = sg2; + } } - /* * If host wants to see the guest header as is, we can * pass it on unchanged. Otherwise, copy just the parts @@ -1174,21 +1294,18 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q) out_sg = sg; } - len = n->guest_hdr_len; - ret = qemu_sendv_packet_async(qemu_get_subqueue(n->nic, queue_index), out_sg, out_num, virtio_net_tx_complete); if (ret == 0) { virtio_queue_set_notification(q->tx_vq, 0); q->async_tx.elem = elem; - q->async_tx.len = len; return -EBUSY; } - len += ret; - - virtqueue_push(q->tx_vq, &elem, 0); +drop: + virtqueue_push(q->tx_vq, elem, 0); virtio_notify(vdev, q->tx_vq); + g_free(elem); if (++num_packets >= n->tx_burst) { break; @@ -1212,7 +1329,9 @@ static void virtio_net_handle_tx_timer(VirtIODevice *vdev, VirtQueue *vq) virtio_queue_set_notification(vq, 1); timer_del(q->tx_timer); q->tx_waiting = 0; - virtio_net_flush_tx(q); + if (virtio_net_flush_tx(q) == -EINVAL) { + return; + } } else { timer_mod(q->tx_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + n->tx_timeout); @@ -1283,8 +1402,9 @@ static void virtio_net_tx_bh(void *opaque) } ret = virtio_net_flush_tx(q); - if (ret == -EBUSY) { - return; /* Notification re-enable handled by tx_complete */ + if (ret == -EBUSY || ret == -EINVAL) { + return; /* Notification re-enable handled by tx_complete or device + * broken */ } /* If we flush a full burst of packets, assume there are @@ -1299,29 +1419,99 @@ static void virtio_net_tx_bh(void *opaque) * anything that may have come in while we weren't looking. If * we find something, assume the guest is still active and reschedule */ virtio_queue_set_notification(q->tx_vq, 1); - if (virtio_net_flush_tx(q) > 0) { + ret = virtio_net_flush_tx(q); + if (ret == -EINVAL) { + return; + } else if (ret > 0) { virtio_queue_set_notification(q->tx_vq, 0); qemu_bh_schedule(q->tx_bh); q->tx_waiting = 1; } } -static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue) +static void virtio_net_add_queue(VirtIONet *n, int index) { - n->multiqueue = multiqueue; + VirtIODevice *vdev = VIRTIO_DEVICE(n); - virtio_net_set_queues(n); + n->vqs[index].rx_vq = virtio_add_queue(vdev, n->net_conf.rx_queue_size, + virtio_net_handle_rx); + if (n->net_conf.tx && !strcmp(n->net_conf.tx, "timer")) { + n->vqs[index].tx_vq = + virtio_add_queue(vdev, 256, virtio_net_handle_tx_timer); + n->vqs[index].tx_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, + virtio_net_tx_timer, + &n->vqs[index]); + } else { + n->vqs[index].tx_vq = + virtio_add_queue(vdev, 256, virtio_net_handle_tx_bh); + n->vqs[index].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[index]); + } + + n->vqs[index].tx_waiting = 0; + n->vqs[index].n = n; } -static void virtio_net_save(QEMUFile *f, void *opaque) +static void virtio_net_del_queue(VirtIONet *n, int index) { - VirtIONet *n = opaque; VirtIODevice *vdev = VIRTIO_DEVICE(n); + VirtIONetQueue *q = &n->vqs[index]; + NetClientState *nc = qemu_get_subqueue(n->nic, index); - /* At this point, backend must be stopped, otherwise - * it might keep writing to memory. */ - assert(!n->vhost_started); - virtio_save(vdev, f); + qemu_purge_queued_packets(nc); + + virtio_del_queue(vdev, index * 2); + if (q->tx_timer) { + timer_del(q->tx_timer); + timer_free(q->tx_timer); + } else { + qemu_bh_delete(q->tx_bh); + } + virtio_del_queue(vdev, index * 2 + 1); +} + +static void virtio_net_change_num_queues(VirtIONet *n, int new_max_queues) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(n); + int old_num_queues = virtio_get_num_queues(vdev); + int new_num_queues = new_max_queues * 2 + 1; + int i; + + assert(old_num_queues >= 3); + assert(old_num_queues % 2 == 1); + + if (old_num_queues == new_num_queues) { + return; + } + + /* + * We always need to remove and add ctrl vq if + * old_num_queues != new_num_queues. Remove ctrl_vq first, + * and then we only enter one of the following too loops. + */ + virtio_del_queue(vdev, old_num_queues - 1); + + for (i = new_num_queues - 1; i < old_num_queues - 1; i += 2) { + /* new_num_queues < old_num_queues */ + virtio_net_del_queue(n, i / 2); + } + + for (i = old_num_queues - 1; i < new_num_queues - 1; i += 2) { + /* new_num_queues > old_num_queues */ + virtio_net_add_queue(n, i / 2); + } + + /* add ctrl_vq last */ + n->ctrl_vq = virtio_add_queue(vdev, 64, virtio_net_handle_ctrl); +} + +static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue) +{ + int max = multiqueue ? n->max_queues : 1; + + n->multiqueue = multiqueue; + virtio_net_change_num_queues(n, max); + + virtio_net_set_queues(n); } static void virtio_net_save_device(VirtIODevice *vdev, QEMUFile *f) @@ -1354,22 +1544,11 @@ static void virtio_net_save_device(VirtIODevice *vdev, QEMUFile *f) } } - if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) { + if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) { qemu_put_be64(f, n->curr_guest_offloads); } } -static int virtio_net_load(QEMUFile *f, void *opaque, int version_id) -{ - VirtIONet *n = opaque; - VirtIODevice *vdev = VIRTIO_DEVICE(n); - - if (version_id < 2 || version_id > VIRTIO_NET_VM_VERSION) - return -EINVAL; - - return virtio_load(vdev, f, version_id); -} - static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f, int version_id) { @@ -1380,70 +1559,52 @@ static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f, n->vqs[0].tx_waiting = qemu_get_be32(f); virtio_net_set_mrg_rx_bufs(n, qemu_get_be32(f), - virtio_has_feature(vdev, VIRTIO_F_VERSION_1)); + virtio_vdev_has_feature(vdev, + VIRTIO_F_VERSION_1)); - if (version_id >= 3) - n->status = qemu_get_be16(f); + n->status = qemu_get_be16(f); - if (version_id >= 4) { - if (version_id < 8) { - n->promisc = qemu_get_be32(f); - n->allmulti = qemu_get_be32(f); - } else { - n->promisc = qemu_get_byte(f); - n->allmulti = qemu_get_byte(f); - } - } + n->promisc = qemu_get_byte(f); + n->allmulti = qemu_get_byte(f); - if (version_id >= 5) { - n->mac_table.in_use = qemu_get_be32(f); - /* MAC_TABLE_ENTRIES may be different from the saved image */ - if (n->mac_table.in_use <= MAC_TABLE_ENTRIES) { - qemu_get_buffer(f, n->mac_table.macs, - n->mac_table.in_use * ETH_ALEN); - } else { - int64_t i; - - /* Overflow detected - can happen if source has a larger MAC table. - * We simply set overflow flag so there's no need to maintain the - * table of addresses, discard them all. - * Note: 64 bit math to avoid integer overflow. - */ - for (i = 0; i < (int64_t)n->mac_table.in_use * ETH_ALEN; ++i) { - qemu_get_byte(f); - } - n->mac_table.multi_overflow = n->mac_table.uni_overflow = 1; - n->mac_table.in_use = 0; + n->mac_table.in_use = qemu_get_be32(f); + /* MAC_TABLE_ENTRIES may be different from the saved image */ + if (n->mac_table.in_use <= MAC_TABLE_ENTRIES) { + qemu_get_buffer(f, n->mac_table.macs, + n->mac_table.in_use * ETH_ALEN); + } else { + int64_t i; + + /* Overflow detected - can happen if source has a larger MAC table. + * We simply set overflow flag so there's no need to maintain the + * table of addresses, discard them all. + * Note: 64 bit math to avoid integer overflow. + */ + for (i = 0; i < (int64_t)n->mac_table.in_use * ETH_ALEN; ++i) { + qemu_get_byte(f); } + n->mac_table.multi_overflow = n->mac_table.uni_overflow = 1; + n->mac_table.in_use = 0; } - if (version_id >= 6) - qemu_get_buffer(f, (uint8_t *)n->vlans, MAX_VLAN >> 3); + qemu_get_buffer(f, (uint8_t *)n->vlans, MAX_VLAN >> 3); - if (version_id >= 7) { - if (qemu_get_be32(f) && !peer_has_vnet_hdr(n)) { - error_report("virtio-net: saved image requires vnet_hdr=on"); - return -1; - } + if (qemu_get_be32(f) && !peer_has_vnet_hdr(n)) { + error_report("virtio-net: saved image requires vnet_hdr=on"); + return -1; } - if (version_id >= 9) { - n->mac_table.multi_overflow = qemu_get_byte(f); - n->mac_table.uni_overflow = qemu_get_byte(f); - } + n->mac_table.multi_overflow = qemu_get_byte(f); + n->mac_table.uni_overflow = qemu_get_byte(f); - if (version_id >= 10) { - n->alluni = qemu_get_byte(f); - n->nomulti = qemu_get_byte(f); - n->nouni = qemu_get_byte(f); - n->nobcast = qemu_get_byte(f); - } + n->alluni = qemu_get_byte(f); + n->nomulti = qemu_get_byte(f); + n->nouni = qemu_get_byte(f); + n->nobcast = qemu_get_byte(f); - if (version_id >= 11) { - if (qemu_get_byte(f) && !peer_has_ufo(n)) { - error_report("virtio-net: saved image requires TUN_F_UFO support"); - return -1; - } + if (qemu_get_byte(f) && !peer_has_ufo(n)) { + error_report("virtio-net: saved image requires TUN_F_UFO support"); + return -1; } if (n->max_queues > 1) { @@ -1463,7 +1624,7 @@ static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f, } } - if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) { + if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) { n->curr_guest_offloads = qemu_get_be64(f); } else { n->curr_guest_offloads = virtio_net_supported_guest_offloads(n); @@ -1490,8 +1651,8 @@ static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f, qemu_get_subqueue(n->nic, i)->link_down = link_down; } - if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ANNOUNCE) && - virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) { + if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_GUEST_ANNOUNCE) && + virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) { n->announce_counter = SELF_ANNOUNCE_ROUNDS; timer_mod(n->announce_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL)); } @@ -1500,7 +1661,7 @@ static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f, } static NetClientInfo net_virtio_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = virtio_net_can_receive, .receive = virtio_net_receive, @@ -1562,6 +1723,22 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) virtio_net_set_config_size(n, n->host_features); virtio_init(vdev, "virtio-net", VIRTIO_ID_NET, n->config_size); + /* + * We set a lower limit on RX queue size to what it always was. + * Guests that want a smaller ring can always resize it without + * help from us (using virtio 1 and up). + */ + if (n->net_conf.rx_queue_size < VIRTIO_NET_RX_QUEUE_MIN_SIZE || + n->net_conf.rx_queue_size > VIRTQUEUE_MAX_SIZE || + (n->net_conf.rx_queue_size & (n->net_conf.rx_queue_size - 1))) { + error_setg(errp, "Invalid rx_queue_size (= %" PRIu16 "), " + "must be a power of 2 between %d and %d.", + n->net_conf.rx_queue_size, VIRTIO_NET_RX_QUEUE_MIN_SIZE, + VIRTQUEUE_MAX_SIZE); + virtio_cleanup(vdev); + return; + } + n->max_queues = MAX(n->nic_conf.peers.queues, 1); if (n->max_queues * 2 + 1 > VIRTIO_QUEUE_MAX) { error_setg(errp, "Invalid number of queues (= %" PRIu32 "), " @@ -1583,21 +1760,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) } for (i = 0; i < n->max_queues; i++) { - n->vqs[i].rx_vq = virtio_add_queue(vdev, 256, virtio_net_handle_rx); - if (n->net_conf.tx && !strcmp(n->net_conf.tx, "timer")) { - n->vqs[i].tx_vq = - virtio_add_queue(vdev, 256, virtio_net_handle_tx_timer); - n->vqs[i].tx_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, - virtio_net_tx_timer, - &n->vqs[i]); - } else { - n->vqs[i].tx_vq = - virtio_add_queue(vdev, 256, virtio_net_handle_tx_bh); - n->vqs[i].tx_bh = qemu_bh_new(virtio_net_tx_bh, &n->vqs[i]); - } - - n->vqs[i].tx_waiting = 0; - n->vqs[i].n = n; + virtio_net_add_queue(n, i); } n->ctrl_vq = virtio_add_queue(vdev, 64, virtio_net_handle_ctrl); @@ -1643,21 +1806,17 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) nc->rxfilter_notify_enabled = 1; n->qdev = dev; - register_savevm(dev, "virtio-net", -1, VIRTIO_NET_VM_VERSION, - virtio_net_save, virtio_net_load, n); } static void virtio_net_device_unrealize(DeviceState *dev, Error **errp) { VirtIODevice *vdev = VIRTIO_DEVICE(dev); VirtIONet *n = VIRTIO_NET(dev); - int i; + int i, max_queues; /* This will stop vhost backend if appropriate. */ virtio_net_set_status(vdev, 0); - unregister_savevm(dev, "virtio-net", n); - g_free(n->netclient_name); n->netclient_name = NULL; g_free(n->netclient_type); @@ -1666,18 +1825,9 @@ static void virtio_net_device_unrealize(DeviceState *dev, Error **errp) g_free(n->mac_table.macs); g_free(n->vlans); - for (i = 0; i < n->max_queues; i++) { - VirtIONetQueue *q = &n->vqs[i]; - NetClientState *nc = qemu_get_subqueue(n->nic, i); - - qemu_purge_queued_packets(nc); - - if (q->tx_timer) { - timer_del(q->tx_timer); - timer_free(q->tx_timer); - } else if (q->tx_bh) { - qemu_bh_delete(q->tx_bh); - } + max_queues = n->multiqueue ? n->max_queues : 1; + for (i = 0; i < max_queues; i++) { + virtio_net_del_queue(n, i); } timer_del(n->announce_timer); @@ -1701,9 +1851,27 @@ static void virtio_net_instance_init(Object *obj) DEVICE(n), NULL); } +static void virtio_net_pre_save(void *opaque) +{ + VirtIONet *n = opaque; + + /* At this point, backend must be stopped, otherwise + * it might keep writing to memory. */ + assert(!n->vhost_started); +} + +static const VMStateDescription vmstate_virtio_net = { + .name = "virtio-net", + .minimum_version_id = VIRTIO_NET_VM_VERSION, + .version_id = VIRTIO_NET_VM_VERSION, + .fields = (VMStateField[]) { + VMSTATE_VIRTIO_DEVICE, + VMSTATE_END_OF_LIST() + }, + .pre_save = virtio_net_pre_save, +}; + static Property virtio_net_properties[] = { - DEFINE_PROP_BIT("any_layout", VirtIONet, host_features, - VIRTIO_F_ANY_LAYOUT, true), DEFINE_PROP_BIT("csum", VirtIONet, host_features, VIRTIO_NET_F_CSUM, true), DEFINE_PROP_BIT("guest_csum", VirtIONet, host_features, VIRTIO_NET_F_GUEST_CSUM, true), @@ -1748,6 +1916,8 @@ static Property virtio_net_properties[] = { TX_TIMER_INTERVAL), DEFINE_PROP_INT32("x-txburst", VirtIONet, net_conf.txburst, TX_BURST), DEFINE_PROP_STRING("tx", VirtIONet, net_conf.tx), + DEFINE_PROP_UINT16("rx_queue_size", VirtIONet, net_conf.rx_queue_size, + VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE), DEFINE_PROP_END_OF_LIST(), }; @@ -1757,6 +1927,7 @@ static void virtio_net_class_init(ObjectClass *klass, void *data) VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); dc->props = virtio_net_properties; + dc->vmsd = &vmstate_virtio_net; set_bit(DEVICE_CATEGORY_NETWORK, dc->categories); vdc->realize = virtio_net_device_realize; vdc->unrealize = virtio_net_device_unrealize;