diff --git a/hmp-commands.hx b/hmp-commands.hx index 12b6d4e2dc..673e39a697 100644 --- a/hmp-commands.hx +++ b/hmp-commands.hx @@ -1276,7 +1276,7 @@ ERST { .name = "netdev_add", .args_type = "netdev:O", - .params = "[user|tap|socket|vde|bridge|hubport|netmap|vhost-user" + .params = "[user|tap|socket|stream|dgram|vde|bridge|hubport|netmap|vhost-user" #ifdef CONFIG_VMNET "|vmnet-host|vmnet-shared|vmnet-bridged" #endif diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index e9f696b4cf..b6903aea54 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -2526,6 +2526,7 @@ static void virtio_net_tx_complete(NetClientState *nc, ssize_t len) VirtIONet *n = qemu_get_nic_opaque(nc); VirtIONetQueue *q = virtio_net_get_subqueue(nc); VirtIODevice *vdev = VIRTIO_DEVICE(n); + int ret; virtqueue_push(q->tx_vq, q->async_tx.elem, 0); virtio_notify(vdev, q->tx_vq); @@ -2534,7 +2535,22 @@ static void virtio_net_tx_complete(NetClientState *nc, ssize_t len) q->async_tx.elem = NULL; virtio_queue_set_notification(q->tx_vq, 1); - virtio_net_flush_tx(q); + ret = virtio_net_flush_tx(q); + if (ret >= n->tx_burst) { + /* + * the flush has been stopped by tx_burst + * we will not receive notification for the + * remainining part, so re-schedule + */ + virtio_queue_set_notification(q->tx_vq, 0); + if (q->tx_bh) { + qemu_bh_schedule(q->tx_bh); + } else { + timer_mod(q->tx_timer, + qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + n->tx_timeout); + } + q->tx_waiting = 1; + } } /* TX */ @@ -2633,6 +2649,8 @@ drop: return num_packets; } +static void virtio_net_tx_timer(void *opaque); + static void virtio_net_handle_tx_timer(VirtIODevice *vdev, VirtQueue *vq) { VirtIONet *n = VIRTIO_NET(vdev); @@ -2650,15 +2668,13 @@ static void virtio_net_handle_tx_timer(VirtIODevice *vdev, VirtQueue *vq) } if (q->tx_waiting) { - virtio_queue_set_notification(vq, 1); + /* We already have queued packets, immediately flush */ timer_del(q->tx_timer); - q->tx_waiting = 0; - if (virtio_net_flush_tx(q) == -EINVAL) { - return; - } + virtio_net_tx_timer(q); } else { + /* re-arm timer to flush it (and more) on next tick */ timer_mod(q->tx_timer, - qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + n->tx_timeout); + qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + n->tx_timeout); q->tx_waiting = 1; virtio_queue_set_notification(vq, 0); } @@ -2691,6 +2707,8 @@ static void virtio_net_tx_timer(void *opaque) VirtIONetQueue *q = opaque; VirtIONet *n = q->n; VirtIODevice *vdev = VIRTIO_DEVICE(n); + int ret; + /* This happens when device was stopped but BH wasn't. */ if (!vdev->vm_running) { /* Make sure tx waiting is set, so we'll run when restarted. */ @@ -2705,8 +2723,33 @@ static void virtio_net_tx_timer(void *opaque) return; } + ret = virtio_net_flush_tx(q); + if (ret == -EBUSY || ret == -EINVAL) { + return; + } + /* + * If we flush a full burst of packets, assume there are + * more coming and immediately rearm + */ + if (ret >= n->tx_burst) { + q->tx_waiting = 1; + timer_mod(q->tx_timer, + qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + n->tx_timeout); + return; + } + /* + * If less than a full burst, re-enable notification and flush + * anything that may have come in while we weren't looking. If + * we find something, assume the guest is still active and rearm + */ virtio_queue_set_notification(q->tx_vq, 1); - virtio_net_flush_tx(q); + ret = virtio_net_flush_tx(q); + if (ret > 0) { + virtio_queue_set_notification(q->tx_vq, 0); + q->tx_waiting = 1; + timer_mod(q->tx_timer, + qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + n->tx_timeout); + } } static void virtio_net_tx_bh(void *opaque) diff --git a/hw/net/xen_nic.c b/hw/net/xen_nic.c index 5c815b4f0c..7d92c2d022 100644 --- a/hw/net/xen_nic.c +++ b/hw/net/xen_nic.c @@ -296,9 +296,8 @@ static int net_init(struct XenLegacyDevice *xendev) netdev->nic = qemu_new_nic(&net_xen_info, &netdev->conf, "xen", NULL, netdev); - snprintf(qemu_get_queue(netdev->nic)->info_str, - sizeof(qemu_get_queue(netdev->nic)->info_str), - "nic: xenbus vif macaddr=%s", netdev->mac); + qemu_set_info_str(qemu_get_queue(netdev->nic), + "nic: xenbus vif macaddr=%s", netdev->mac); /* fill info */ xenstore_write_be_int(&netdev->xendev, "feature-rx-copy", 1); diff --git a/hw/virtio/vhost-shadow-virtqueue.c b/hw/virtio/vhost-shadow-virtqueue.c index 596d4434d2..5bd14cad96 100644 --- a/hw/virtio/vhost-shadow-virtqueue.c +++ b/hw/virtio/vhost-shadow-virtqueue.c @@ -33,6 +33,7 @@ bool vhost_svq_valid_features(uint64_t features, Error **errp) ++b) { switch (b) { case VIRTIO_F_ANY_LAYOUT: + case VIRTIO_RING_F_EVENT_IDX: continue; case VIRTIO_F_ACCESS_PLATFORM: @@ -218,12 +219,22 @@ static bool vhost_svq_add_split(VhostShadowVirtqueue *svq, static void vhost_svq_kick(VhostShadowVirtqueue *svq) { + bool needs_kick; + /* * We need to expose the available array entries before checking the used * flags */ smp_mb(); - if (svq->vring.used->flags & VRING_USED_F_NO_NOTIFY) { + + if (virtio_vdev_has_feature(svq->vdev, VIRTIO_RING_F_EVENT_IDX)) { + uint16_t avail_event = *(uint16_t *)(&svq->vring.used->ring[svq->vring.num]); + needs_kick = vring_need_event(avail_event, svq->shadow_avail_idx, svq->shadow_avail_idx - 1); + } else { + needs_kick = !(svq->vring.used->flags & VRING_USED_F_NO_NOTIFY); + } + + if (!needs_kick) { return; } @@ -369,15 +380,27 @@ static bool vhost_svq_more_used(VhostShadowVirtqueue *svq) */ static bool vhost_svq_enable_notification(VhostShadowVirtqueue *svq) { - svq->vring.avail->flags &= ~cpu_to_le16(VRING_AVAIL_F_NO_INTERRUPT); - /* Make sure the flag is written before the read of used_idx */ + if (virtio_vdev_has_feature(svq->vdev, VIRTIO_RING_F_EVENT_IDX)) { + uint16_t *used_event = (uint16_t *)&svq->vring.avail->ring[svq->vring.num]; + *used_event = svq->shadow_used_idx; + } else { + svq->vring.avail->flags &= ~cpu_to_le16(VRING_AVAIL_F_NO_INTERRUPT); + } + + /* Make sure the event is enabled before the read of used_idx */ smp_mb(); return !vhost_svq_more_used(svq); } static void vhost_svq_disable_notification(VhostShadowVirtqueue *svq) { - svq->vring.avail->flags |= cpu_to_le16(VRING_AVAIL_F_NO_INTERRUPT); + /* + * No need to disable notification in the event idx case, since used event + * index is already an index too far away. + */ + if (!virtio_vdev_has_feature(svq->vdev, VIRTIO_RING_F_EVENT_IDX)) { + svq->vring.avail->flags |= cpu_to_le16(VRING_AVAIL_F_NO_INTERRUPT); + } } static uint16_t vhost_svq_last_desc_of_chain(const VhostShadowVirtqueue *svq, @@ -570,16 +593,16 @@ void vhost_svq_get_vring_addr(const VhostShadowVirtqueue *svq, size_t vhost_svq_driver_area_size(const VhostShadowVirtqueue *svq) { size_t desc_size = sizeof(vring_desc_t) * svq->vring.num; - size_t avail_size = offsetof(vring_avail_t, ring) + - sizeof(uint16_t) * svq->vring.num; + size_t avail_size = offsetof(vring_avail_t, ring[svq->vring.num]) + + sizeof(uint16_t); return ROUND_UP(desc_size + avail_size, qemu_real_host_page_size()); } size_t vhost_svq_device_area_size(const VhostShadowVirtqueue *svq) { - size_t used_size = offsetof(vring_used_t, ring) + - sizeof(vring_used_elem_t) * svq->vring.num; + size_t used_size = offsetof(vring_used_t, ring[svq->vring.num]) + + sizeof(uint16_t); return ROUND_UP(used_size, qemu_real_host_page_size()); } diff --git a/include/net/net.h b/include/net/net.h index 81d0b21def..3db75ff841 100644 --- a/include/net/net.h +++ b/include/net/net.h @@ -177,6 +177,7 @@ ssize_t qemu_send_packet_async(NetClientState *nc, const uint8_t *buf, void qemu_purge_queued_packets(NetClientState *nc); void qemu_flush_queued_packets(NetClientState *nc); void qemu_flush_or_purge_queued_packets(NetClientState *nc, bool purge); +void qemu_set_info_str(NetClientState *nc, const char *fmt, ...); void qemu_format_nic_info_str(NetClientState *nc, uint8_t macaddr[6]); bool qemu_has_ufo(NetClientState *nc); bool qemu_has_vnet_hdr(NetClientState *nc); @@ -220,9 +221,11 @@ extern NICInfo nd_table[MAX_NICS]; extern const char *host_net_devices[]; /* from net.c */ -int net_client_parse(QemuOptsList *opts_list, const char *str); +bool netdev_is_modern(const char *optarg); +void netdev_parse_modern(const char *optarg); +void net_client_parse(QemuOptsList *opts_list, const char *str); void show_netdevs(void); -int net_init_clients(Error **errp); +void net_init_clients(void); void net_check_clients(void); void net_cleanup(void); void hmp_host_net_add(Monitor *mon, const QDict *qdict); diff --git a/include/qemu/sockets.h b/include/qemu/sockets.h index 036745e586..214058d8e3 100644 --- a/include/qemu/sockets.h +++ b/include/qemu/sockets.h @@ -58,6 +58,7 @@ NetworkAddressFamily inet_netfamily(int family); int unix_listen(const char *path, Error **errp); int unix_connect(const char *path, Error **errp); +char *socket_uri(SocketAddress *addr); SocketAddress *socket_parse(const char *str, Error **errp); int socket_connect(SocketAddress *addr, Error **errp); int socket_listen(SocketAddress *addr, int num, Error **errp); @@ -65,6 +66,8 @@ void socket_listen_cleanup(int fd, Error **errp); int socket_dgram(SocketAddress *remote, SocketAddress *local, Error **errp); /* Old, ipv4 only bits. Don't use for new code. */ +int convert_host_port(struct sockaddr_in *saddr, const char *host, + const char *port, Error **errp); int parse_host_port(struct sockaddr_in *saddr, const char *str, Error **errp); int socket_init(void); @@ -139,5 +142,4 @@ SocketAddress *socket_address_flatten(SocketAddressLegacy *addr); * Return 0 on success. */ int socket_address_parse_named_fd(SocketAddress *addr, Error **errp); - #endif /* QEMU_SOCKETS_H */ diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c index bab86c5537..01b789a79e 100644 --- a/monitor/hmp-cmds.c +++ b/monitor/hmp-cmds.c @@ -199,27 +199,6 @@ void hmp_info_mice(Monitor *mon, const QDict *qdict) qapi_free_MouseInfoList(mice_list); } -static char *SocketAddress_to_str(SocketAddress *addr) -{ - switch (addr->type) { - case SOCKET_ADDRESS_TYPE_INET: - return g_strdup_printf("tcp:%s:%s", - addr->u.inet.host, - addr->u.inet.port); - case SOCKET_ADDRESS_TYPE_UNIX: - return g_strdup_printf("unix:%s", - addr->u.q_unix.path); - case SOCKET_ADDRESS_TYPE_FD: - return g_strdup_printf("fd:%s", addr->u.fd.str); - case SOCKET_ADDRESS_TYPE_VSOCK: - return g_strdup_printf("tcp:%s:%s", - addr->u.vsock.cid, - addr->u.vsock.port); - default: - return g_strdup("unknown address type"); - } -} - void hmp_info_migrate(Monitor *mon, const QDict *qdict) { MigrationInfo *info; @@ -382,7 +361,7 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict) monitor_printf(mon, "socket address: [\n"); for (addr = info->socket_address; addr; addr = addr->next) { - char *s = SocketAddress_to_str(addr->value); + char *s = socket_uri(addr->value); monitor_printf(mon, "\t%s\n", s); g_free(s); } diff --git a/net/clients.h b/net/clients.h index c9157789f2..ed8bdfff1e 100644 --- a/net/clients.h +++ b/net/clients.h @@ -40,6 +40,12 @@ int net_init_hubport(const Netdev *netdev, const char *name, int net_init_socket(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp); +int net_init_stream(const Netdev *netdev, const char *name, + NetClientState *peer, Error **errp); + +int net_init_dgram(const Netdev *netdev, const char *name, + NetClientState *peer, Error **errp); + int net_init_tap(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp); diff --git a/net/dgram.c b/net/dgram.c new file mode 100644 index 0000000000..9f7bf38376 --- /dev/null +++ b/net/dgram.c @@ -0,0 +1,623 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2008 Fabrice Bellard + * Copyright (c) 2022 Red Hat, Inc. + * + * 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 "qemu/osdep.h" + +#include "net/net.h" +#include "clients.h" +#include "monitor/monitor.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "qemu/option.h" +#include "qemu/sockets.h" +#include "qemu/iov.h" +#include "qemu/main-loop.h" +#include "qemu/cutils.h" + +typedef struct NetDgramState { + NetClientState nc; + int fd; + SocketReadState rs; + bool read_poll; /* waiting to receive data? */ + bool write_poll; /* waiting to transmit data? */ + /* contains destination iff connectionless */ + struct sockaddr *dest_addr; + socklen_t dest_len; +} NetDgramState; + +static void net_dgram_send(void *opaque); +static void net_dgram_writable(void *opaque); + +static void net_dgram_update_fd_handler(NetDgramState *s) +{ + qemu_set_fd_handler(s->fd, + s->read_poll ? net_dgram_send : NULL, + s->write_poll ? net_dgram_writable : NULL, + s); +} + +static void net_dgram_read_poll(NetDgramState *s, bool enable) +{ + s->read_poll = enable; + net_dgram_update_fd_handler(s); +} + +static void net_dgram_write_poll(NetDgramState *s, bool enable) +{ + s->write_poll = enable; + net_dgram_update_fd_handler(s); +} + +static void net_dgram_writable(void *opaque) +{ + NetDgramState *s = opaque; + + net_dgram_write_poll(s, false); + + qemu_flush_queued_packets(&s->nc); +} + +static ssize_t net_dgram_receive(NetClientState *nc, + const uint8_t *buf, size_t size) +{ + NetDgramState *s = DO_UPCAST(NetDgramState, nc, nc); + ssize_t ret; + + do { + if (s->dest_addr) { + ret = sendto(s->fd, buf, size, 0, s->dest_addr, s->dest_len); + } else { + ret = send(s->fd, buf, size, 0); + } + } while (ret == -1 && errno == EINTR); + + if (ret == -1 && errno == EAGAIN) { + net_dgram_write_poll(s, true); + return 0; + } + return ret; +} + +static void net_dgram_send_completed(NetClientState *nc, ssize_t len) +{ + NetDgramState *s = DO_UPCAST(NetDgramState, nc, nc); + + if (!s->read_poll) { + net_dgram_read_poll(s, true); + } +} + +static void net_dgram_rs_finalize(SocketReadState *rs) +{ + NetDgramState *s = container_of(rs, NetDgramState, rs); + + if (qemu_send_packet_async(&s->nc, rs->buf, + rs->packet_len, + net_dgram_send_completed) == 0) { + net_dgram_read_poll(s, false); + } +} + +static void net_dgram_send(void *opaque) +{ + NetDgramState *s = opaque; + int size; + + size = recv(s->fd, s->rs.buf, sizeof(s->rs.buf), 0); + if (size < 0) { + return; + } + if (size == 0) { + /* end of connection */ + net_dgram_read_poll(s, false); + net_dgram_write_poll(s, false); + return; + } + if (qemu_send_packet_async(&s->nc, s->rs.buf, size, + net_dgram_send_completed) == 0) { + net_dgram_read_poll(s, false); + } +} + +static int net_dgram_mcast_create(struct sockaddr_in *mcastaddr, + struct in_addr *localaddr, + Error **errp) +{ + struct ip_mreq imr; + int fd; + int val, ret; +#ifdef __OpenBSD__ + unsigned char loop; +#else + int loop; +#endif + + if (!IN_MULTICAST(ntohl(mcastaddr->sin_addr.s_addr))) { + error_setg(errp, "specified mcastaddr %s (0x%08x) " + "does not contain a multicast address", + inet_ntoa(mcastaddr->sin_addr), + (int)ntohl(mcastaddr->sin_addr.s_addr)); + return -1; + } + + fd = qemu_socket(PF_INET, SOCK_DGRAM, 0); + if (fd < 0) { + error_setg_errno(errp, errno, "can't create datagram socket"); + return -1; + } + + /* + * Allow multiple sockets to bind the same multicast ip and port by setting + * SO_REUSEADDR. This is the only situation where SO_REUSEADDR should be set + * on windows. Use socket_set_fast_reuse otherwise as it sets SO_REUSEADDR + * only on posix systems. + */ + val = 1; + ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &val, sizeof(val)); + if (ret < 0) { + error_setg_errno(errp, errno, "can't set socket option SO_REUSEADDR"); + goto fail; + } + + ret = bind(fd, (struct sockaddr *)mcastaddr, sizeof(*mcastaddr)); + if (ret < 0) { + error_setg_errno(errp, errno, "can't bind ip=%s to socket", + inet_ntoa(mcastaddr->sin_addr)); + goto fail; + } + + /* Add host to multicast group */ + imr.imr_multiaddr = mcastaddr->sin_addr; + if (localaddr) { + imr.imr_interface = *localaddr; + } else { + imr.imr_interface.s_addr = htonl(INADDR_ANY); + } + + ret = setsockopt(fd, IPPROTO_IP, IP_ADD_MEMBERSHIP, + &imr, sizeof(struct ip_mreq)); + if (ret < 0) { + error_setg_errno(errp, errno, + "can't add socket to multicast group %s", + inet_ntoa(imr.imr_multiaddr)); + goto fail; + } + + /* Force mcast msgs to loopback (eg. several QEMUs in same host */ + loop = 1; + ret = setsockopt(fd, IPPROTO_IP, IP_MULTICAST_LOOP, + &loop, sizeof(loop)); + if (ret < 0) { + error_setg_errno(errp, errno, + "can't force multicast message to loopback"); + goto fail; + } + + /* If a bind address is given, only send packets from that address */ + if (localaddr != NULL) { + ret = setsockopt(fd, IPPROTO_IP, IP_MULTICAST_IF, + localaddr, sizeof(*localaddr)); + if (ret < 0) { + error_setg_errno(errp, errno, + "can't set the default network send interface"); + goto fail; + } + } + + qemu_socket_set_nonblock(fd); + return fd; +fail: + if (fd >= 0) { + closesocket(fd); + } + return -1; +} + +static void net_dgram_cleanup(NetClientState *nc) +{ + NetDgramState *s = DO_UPCAST(NetDgramState, nc, nc); + if (s->fd != -1) { + net_dgram_read_poll(s, false); + net_dgram_write_poll(s, false); + close(s->fd); + s->fd = -1; + } + g_free(s->dest_addr); + s->dest_addr = NULL; + s->dest_len = 0; +} + +static NetClientInfo net_dgram_socket_info = { + .type = NET_CLIENT_DRIVER_DGRAM, + .size = sizeof(NetDgramState), + .receive = net_dgram_receive, + .cleanup = net_dgram_cleanup, +}; + +static NetDgramState *net_dgram_fd_init(NetClientState *peer, + const char *model, + const char *name, + int fd, + Error **errp) +{ + NetClientState *nc; + NetDgramState *s; + + nc = qemu_new_net_client(&net_dgram_socket_info, peer, model, name); + + s = DO_UPCAST(NetDgramState, nc, nc); + + s->fd = fd; + net_socket_rs_init(&s->rs, net_dgram_rs_finalize, false); + net_dgram_read_poll(s, true); + + return s; +} + +static int net_dgram_mcast_init(NetClientState *peer, + const char *model, + const char *name, + SocketAddress *remote, + SocketAddress *local, + Error **errp) +{ + NetDgramState *s; + int fd, ret; + struct sockaddr_in *saddr; + + if (remote->type != SOCKET_ADDRESS_TYPE_INET) { + error_setg(errp, "multicast only support inet type"); + return -1; + } + + saddr = g_new(struct sockaddr_in, 1); + if (convert_host_port(saddr, remote->u.inet.host, remote->u.inet.port, + errp) < 0) { + g_free(saddr); + return -1; + } + + if (!local) { + fd = net_dgram_mcast_create(saddr, NULL, errp); + if (fd < 0) { + g_free(saddr); + return -1; + } + } else { + switch (local->type) { + case SOCKET_ADDRESS_TYPE_INET: { + struct in_addr localaddr; + + if (inet_aton(local->u.inet.host, &localaddr) == 0) { + g_free(saddr); + error_setg(errp, "localaddr '%s' is not a valid IPv4 address", + local->u.inet.host); + return -1; + } + + fd = net_dgram_mcast_create(saddr, &localaddr, errp); + if (fd < 0) { + g_free(saddr); + return -1; + } + break; + } + case SOCKET_ADDRESS_TYPE_FD: { + int newfd; + + fd = monitor_fd_param(monitor_cur(), local->u.fd.str, errp); + if (fd == -1) { + g_free(saddr); + return -1; + } + ret = qemu_socket_try_set_nonblock(fd); + if (ret < 0) { + g_free(saddr); + error_setg_errno(errp, -ret, "%s: Can't use file descriptor %d", + name, fd); + return -1; + } + + /* + * fd passed: multicast: "learn" dest_addr 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 + */ + + saddr = g_new(struct sockaddr_in, 1); + + if (convert_host_port(saddr, local->u.inet.host, local->u.inet.port, + errp) < 0) { + g_free(saddr); + closesocket(fd); + return -1; + } + + /* must be bound */ + if (saddr->sin_addr.s_addr == 0) { + error_setg(errp, "can't setup multicast destination address"); + g_free(saddr); + closesocket(fd); + return -1; + } + /* clone dgram socket */ + newfd = net_dgram_mcast_create(saddr, NULL, errp); + if (newfd < 0) { + g_free(saddr); + closesocket(fd); + return -1; + } + /* clone newfd to fd, close newfd */ + dup2(newfd, fd); + close(newfd); + break; + } + default: + g_free(saddr); + error_setg(errp, "only support inet or fd type for local"); + return -1; + } + } + + s = net_dgram_fd_init(peer, model, name, fd, errp); + if (!s) { + g_free(saddr); + return -1; + } + + g_assert(s->dest_addr == NULL); + s->dest_addr = (struct sockaddr *)saddr; + s->dest_len = sizeof(*saddr); + + if (!local) { + qemu_set_info_str(&s->nc, "mcast=%s:%d", + inet_ntoa(saddr->sin_addr), + ntohs(saddr->sin_port)); + } else { + switch (local->type) { + case SOCKET_ADDRESS_TYPE_INET: + qemu_set_info_str(&s->nc, "mcast=%s:%d", + inet_ntoa(saddr->sin_addr), + ntohs(saddr->sin_port)); + break; + case SOCKET_ADDRESS_TYPE_FD: + qemu_set_info_str(&s->nc, "fd=%d (cloned mcast=%s:%d)", + fd, inet_ntoa(saddr->sin_addr), + ntohs(saddr->sin_port)); + break; + default: + g_assert_not_reached(); + } + } + + return 0; + +} + + +int net_init_dgram(const Netdev *netdev, const char *name, + NetClientState *peer, Error **errp) +{ + NetDgramState *s; + int fd, ret; + SocketAddress *remote, *local; + struct sockaddr *dest_addr; + struct sockaddr_in laddr_in, raddr_in; + struct sockaddr_un laddr_un, raddr_un; + socklen_t dest_len; + + assert(netdev->type == NET_CLIENT_DRIVER_DGRAM); + + remote = netdev->u.dgram.remote; + local = netdev->u.dgram.local; + + /* detect multicast address */ + if (remote && remote->type == SOCKET_ADDRESS_TYPE_INET) { + struct sockaddr_in mcastaddr; + + if (convert_host_port(&mcastaddr, remote->u.inet.host, + remote->u.inet.port, errp) < 0) { + return -1; + } + + if (IN_MULTICAST(ntohl(mcastaddr.sin_addr.s_addr))) { + return net_dgram_mcast_init(peer, "dram", name, remote, local, + errp); + } + } + + /* unicast address */ + if (!local) { + error_setg(errp, "dgram requires local= parameter"); + return -1; + } + + if (remote) { + if (local->type == SOCKET_ADDRESS_TYPE_FD) { + error_setg(errp, "don't set remote with local.fd"); + return -1; + } + if (remote->type != local->type) { + error_setg(errp, "remote and local types must be the same"); + return -1; + } + } else { + if (local->type != SOCKET_ADDRESS_TYPE_FD) { + error_setg(errp, + "type=inet or type=unix requires remote parameter"); + return -1; + } + } + + switch (local->type) { + case SOCKET_ADDRESS_TYPE_INET: + if (convert_host_port(&laddr_in, local->u.inet.host, local->u.inet.port, + errp) < 0) { + return -1; + } + + if (convert_host_port(&raddr_in, remote->u.inet.host, + remote->u.inet.port, errp) < 0) { + return -1; + } + + fd = qemu_socket(PF_INET, SOCK_DGRAM, 0); + if (fd < 0) { + error_setg_errno(errp, errno, "can't create datagram socket"); + return -1; + } + + ret = socket_set_fast_reuse(fd); + if (ret < 0) { + error_setg_errno(errp, errno, + "can't set socket option SO_REUSEADDR"); + closesocket(fd); + return -1; + } + ret = bind(fd, (struct sockaddr *)&laddr_in, sizeof(laddr_in)); + if (ret < 0) { + error_setg_errno(errp, errno, "can't bind ip=%s to socket", + inet_ntoa(laddr_in.sin_addr)); + closesocket(fd); + return -1; + } + qemu_socket_set_nonblock(fd); + + dest_len = sizeof(raddr_in); + dest_addr = g_malloc(dest_len); + memcpy(dest_addr, &raddr_in, dest_len); + break; + case SOCKET_ADDRESS_TYPE_UNIX: + ret = unlink(local->u.q_unix.path); + if (ret < 0 && errno != ENOENT) { + error_setg_errno(errp, errno, "failed to unlink socket %s", + local->u.q_unix.path); + return -1; + } + + laddr_un.sun_family = PF_UNIX; + ret = snprintf(laddr_un.sun_path, sizeof(laddr_un.sun_path), "%s", + local->u.q_unix.path); + if (ret < 0 || ret >= sizeof(laddr_un.sun_path)) { + error_setg(errp, "UNIX socket path '%s' is too long", + local->u.q_unix.path); + error_append_hint(errp, "Path must be less than %zu bytes\n", + sizeof(laddr_un.sun_path)); + } + + raddr_un.sun_family = PF_UNIX; + ret = snprintf(raddr_un.sun_path, sizeof(raddr_un.sun_path), "%s", + remote->u.q_unix.path); + if (ret < 0 || ret >= sizeof(raddr_un.sun_path)) { + error_setg(errp, "UNIX socket path '%s' is too long", + remote->u.q_unix.path); + error_append_hint(errp, "Path must be less than %zu bytes\n", + sizeof(raddr_un.sun_path)); + } + + fd = qemu_socket(PF_UNIX, SOCK_DGRAM, 0); + if (fd < 0) { + error_setg_errno(errp, errno, "can't create datagram socket"); + return -1; + } + + ret = bind(fd, (struct sockaddr *)&laddr_un, sizeof(laddr_un)); + if (ret < 0) { + error_setg_errno(errp, errno, "can't bind unix=%s to socket", + laddr_un.sun_path); + closesocket(fd); + return -1; + } + qemu_socket_set_nonblock(fd); + + dest_len = sizeof(raddr_un); + dest_addr = g_malloc(dest_len); + memcpy(dest_addr, &raddr_un, dest_len); + break; + case SOCKET_ADDRESS_TYPE_FD: + fd = monitor_fd_param(monitor_cur(), local->u.fd.str, errp); + if (fd == -1) { + return -1; + } + ret = qemu_socket_try_set_nonblock(fd); + if (ret < 0) { + error_setg_errno(errp, -ret, "%s: Can't use file descriptor %d", + name, fd); + return -1; + } + dest_addr = NULL; + dest_len = 0; + break; + default: + error_setg(errp, "only support inet or fd type for local"); + return -1; + } + + s = net_dgram_fd_init(peer, "dgram", name, fd, errp); + if (!s) { + return -1; + } + + if (remote) { + g_assert(s->dest_addr == NULL); + s->dest_addr = dest_addr; + s->dest_len = dest_len; + } + + switch (local->type) { + case SOCKET_ADDRESS_TYPE_INET: + qemu_set_info_str(&s->nc, "udp=%s:%d/%s:%d", + inet_ntoa(laddr_in.sin_addr), + ntohs(laddr_in.sin_port), + inet_ntoa(raddr_in.sin_addr), + ntohs(raddr_in.sin_port)); + break; + case SOCKET_ADDRESS_TYPE_UNIX: + qemu_set_info_str(&s->nc, "udp=%s:%s", + laddr_un.sun_path, raddr_un.sun_path); + break; + case SOCKET_ADDRESS_TYPE_FD: { + SocketAddress *sa; + SocketAddressType sa_type; + + sa = socket_local_address(fd, errp); + if (sa) { + sa_type = sa->type; + qapi_free_SocketAddress(sa); + + qemu_set_info_str(&s->nc, "fd=%d %s", fd, + SocketAddressType_str(sa_type)); + } else { + qemu_set_info_str(&s->nc, "fd=%d", fd); + } + break; + } + default: + g_assert_not_reached(); + } + + return 0; +} diff --git a/net/hub.c b/net/hub.c index 1375738bf1..67ca534856 100644 --- a/net/hub.c +++ b/net/hub.c @@ -313,6 +313,8 @@ void net_hub_check_clients(void) case NET_CLIENT_DRIVER_USER: case NET_CLIENT_DRIVER_TAP: case NET_CLIENT_DRIVER_SOCKET: + case NET_CLIENT_DRIVER_STREAM: + case NET_CLIENT_DRIVER_DGRAM: case NET_CLIENT_DRIVER_VDE: case NET_CLIENT_DRIVER_VHOST_USER: has_host_dev = 1; diff --git a/net/l2tpv3.c b/net/l2tpv3.c index af373e5c30..350041a0d6 100644 --- a/net/l2tpv3.c +++ b/net/l2tpv3.c @@ -723,8 +723,7 @@ int net_init_l2tpv3(const Netdev *netdev, l2tpv3_read_poll(s, true); - snprintf(s->nc.info_str, sizeof(s->nc.info_str), - "l2tpv3: connected"); + qemu_set_info_str(&s->nc, "l2tpv3: connected"); return 0; outerr: qemu_del_net_client(nc); diff --git a/net/meson.build b/net/meson.build index d1be76daf3..6cd1e3dab3 100644 --- a/net/meson.build +++ b/net/meson.build @@ -13,6 +13,8 @@ softmmu_ss.add(files( 'net.c', 'queue.c', 'socket.c', + 'stream.c', + 'dgram.c', 'util.c', )) diff --git a/net/net.c b/net/net.c index 2db160e063..840ad9dca5 100644 --- a/net/net.c +++ b/net/net.c @@ -48,12 +48,14 @@ #include "qemu/qemu-print.h" #include "qemu/main-loop.h" #include "qemu/option.h" +#include "qemu/keyval.h" #include "qapi/error.h" #include "qapi/opts-visitor.h" #include "sysemu/runstate.h" #include "net/colo-compare.h" #include "net/filter.h" #include "qapi/string-output-visitor.h" +#include "qapi/qobject-input-visitor.h" /* Net bridge is currently not supported for W32. */ #if !defined(_WIN32) @@ -63,18 +65,60 @@ static VMChangeStateEntry *net_change_state_entry; static QTAILQ_HEAD(, NetClientState) net_clients; +typedef struct NetdevQueueEntry { + Netdev *nd; + Location loc; + QSIMPLEQ_ENTRY(NetdevQueueEntry) entry; +} NetdevQueueEntry; + +typedef QSIMPLEQ_HEAD(, NetdevQueueEntry) NetdevQueue; + +static NetdevQueue nd_queue = QSIMPLEQ_HEAD_INITIALIZER(nd_queue); + /***********************************************************/ /* network device redirectors */ +int convert_host_port(struct sockaddr_in *saddr, const char *host, + const char *port, Error **errp) +{ + struct hostent *he; + const char *r; + long p; + + memset(saddr, 0, sizeof(*saddr)); + + saddr->sin_family = AF_INET; + if (host[0] == '\0') { + saddr->sin_addr.s_addr = 0; + } else { + if (qemu_isdigit(host[0])) { + if (!inet_aton(host, &saddr->sin_addr)) { + error_setg(errp, "host address '%s' is not a valid " + "IPv4 address", host); + return -1; + } + } else { + he = gethostbyname(host); + if (he == NULL) { + error_setg(errp, "can't resolve host address '%s'", host); + return -1; + } + saddr->sin_addr = *(struct in_addr *)he->h_addr; + } + } + if (qemu_strtol(port, &r, 0, &p) != 0) { + error_setg(errp, "port number '%s' is invalid", port); + return -1; + } + saddr->sin_port = htons(p); + return 0; +} + int parse_host_port(struct sockaddr_in *saddr, const char *str, Error **errp) { gchar **substrings; - struct hostent *he; - const char *addr, *p, *r; - int port, ret = 0; - - memset(saddr, 0, sizeof(*saddr)); + int ret; substrings = g_strsplit(str, ":", 2); if (!substrings || !substrings[0] || !substrings[1]) { @@ -84,37 +128,7 @@ int parse_host_port(struct sockaddr_in *saddr, const char *str, goto out; } - addr = substrings[0]; - p = substrings[1]; - - saddr->sin_family = AF_INET; - if (addr[0] == '\0') { - saddr->sin_addr.s_addr = 0; - } else { - if (qemu_isdigit(addr[0])) { - if (!inet_aton(addr, &saddr->sin_addr)) { - error_setg(errp, "host address '%s' is not a valid " - "IPv4 address", addr); - ret = -1; - goto out; - } - } else { - he = gethostbyname(addr); - if (he == NULL) { - error_setg(errp, "can't resolve host address '%s'", addr); - ret = -1; - goto out; - } - saddr->sin_addr = *(struct in_addr *)he->h_addr; - } - } - port = strtol(p, (char **)&r, 0); - if (r == p) { - error_setg(errp, "port number '%s' is invalid", p); - ret = -1; - goto out; - } - saddr->sin_port = htons(port); + ret = convert_host_port(saddr, substrings[0], substrings[1], errp); out: g_strfreev(substrings); @@ -128,13 +142,20 @@ char *qemu_mac_strdup_printf(const uint8_t *macaddr) macaddr[3], macaddr[4], macaddr[5]); } +void qemu_set_info_str(NetClientState *nc, const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vsnprintf(nc->info_str, sizeof(nc->info_str), fmt, ap); + va_end(ap); +} + void qemu_format_nic_info_str(NetClientState *nc, uint8_t macaddr[6]) { - snprintf(nc->info_str, sizeof(nc->info_str), - "model=%s,macaddr=%02x:%02x:%02x:%02x:%02x:%02x", - nc->model, - macaddr[0], macaddr[1], macaddr[2], - macaddr[3], macaddr[4], macaddr[5]); + qemu_set_info_str(nc, "model=%s,macaddr=%02x:%02x:%02x:%02x:%02x:%02x", + nc->model, macaddr[0], macaddr[1], macaddr[2], + macaddr[3], macaddr[4], macaddr[5]); } static int mac_table[256] = {0}; @@ -1001,6 +1022,8 @@ static int (* const net_client_init_fun[NET_CLIENT_DRIVER__MAX])( #endif [NET_CLIENT_DRIVER_TAP] = net_init_tap, [NET_CLIENT_DRIVER_SOCKET] = net_init_socket, + [NET_CLIENT_DRIVER_STREAM] = net_init_stream, + [NET_CLIENT_DRIVER_DGRAM] = net_init_dgram, #ifdef CONFIG_VDE [NET_CLIENT_DRIVER_VDE] = net_init_vde, #endif @@ -1036,19 +1059,23 @@ static int net_client_init1(const Netdev *netdev, bool is_netdev, Error **errp) if (is_netdev) { if (netdev->type == NET_CLIENT_DRIVER_NIC || !net_client_init_fun[netdev->type]) { - error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "type", - "a netdev backend type"); + error_setg(errp, "network backend '%s' is not compiled into this binary", + NetClientDriver_str(netdev->type)); return -1; } } else { if (netdev->type == NET_CLIENT_DRIVER_NONE) { return 0; /* nothing to do */ } - if (netdev->type == NET_CLIENT_DRIVER_HUBPORT || - !net_client_init_fun[netdev->type]) { - error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "type", - "a net backend type (maybe it is not compiled " - "into this binary)"); + if (netdev->type == NET_CLIENT_DRIVER_HUBPORT) { + error_setg(errp, "network backend '%s' is only supported with -netdev/-nic", + NetClientDriver_str(netdev->type)); + return -1; + } + + if (!net_client_init_fun[netdev->type]) { + error_setg(errp, "network backend '%s' is not compiled into this binary", + NetClientDriver_str(netdev->type)); return -1; } @@ -1088,6 +1115,8 @@ void show_netdevs(void) int idx; const char *available_netdevs[] = { "socket", + "stream", + "dgram", "hubport", "tap", #ifdef CONFIG_SLIRP @@ -1560,36 +1589,97 @@ out: return ret; } -int net_init_clients(Error **errp) +static void netdev_init_modern(void) +{ + while (!QSIMPLEQ_EMPTY(&nd_queue)) { + NetdevQueueEntry *nd = QSIMPLEQ_FIRST(&nd_queue); + + QSIMPLEQ_REMOVE_HEAD(&nd_queue, entry); + loc_push_restore(&nd->loc); + net_client_init1(nd->nd, true, &error_fatal); + loc_pop(&nd->loc); + qapi_free_Netdev(nd->nd); + g_free(nd); + } +} + +void net_init_clients(void) { net_change_state_entry = qemu_add_vm_change_state_handler(net_vm_change_state_handler, NULL); QTAILQ_INIT(&net_clients); - if (qemu_opts_foreach(qemu_find_opts("netdev"), - net_init_netdev, NULL, errp)) { - return -1; - } + netdev_init_modern(); - if (qemu_opts_foreach(qemu_find_opts("nic"), net_param_nic, NULL, errp)) { - return -1; - } + qemu_opts_foreach(qemu_find_opts("netdev"), net_init_netdev, NULL, + &error_fatal); - if (qemu_opts_foreach(qemu_find_opts("net"), net_init_client, NULL, errp)) { - return -1; - } + qemu_opts_foreach(qemu_find_opts("nic"), net_param_nic, NULL, + &error_fatal); - return 0; + qemu_opts_foreach(qemu_find_opts("net"), net_init_client, NULL, + &error_fatal); } -int net_client_parse(QemuOptsList *opts_list, const char *optarg) +/* + * Does this -netdev argument use modern rather than traditional syntax? + * Modern syntax is to be parsed with netdev_parse_modern(). + * Traditional syntax is to be parsed with net_client_parse(). + */ +bool netdev_is_modern(const char *optarg) { - if (!qemu_opts_parse_noisily(opts_list, optarg, true)) { - return -1; + QemuOpts *opts; + bool is_modern; + const char *type; + static QemuOptsList dummy_opts = { + .name = "netdev", + .implied_opt_name = "type", + .head = QTAILQ_HEAD_INITIALIZER(dummy_opts.head), + .desc = { { } }, + }; + + if (optarg[0] == '{') { + /* This is JSON, which means it's modern syntax */ + return true; } - return 0; + opts = qemu_opts_create(&dummy_opts, NULL, false, &error_abort); + qemu_opts_do_parse(opts, optarg, dummy_opts.implied_opt_name, + &error_abort); + type = qemu_opt_get(opts, "type"); + is_modern = !g_strcmp0(type, "stream") || !g_strcmp0(type, "dgram"); + + qemu_opts_reset(&dummy_opts); + + return is_modern; +} + +/* + * netdev_parse_modern() uses modern, more expressive syntax than + * net_client_parse(), but supports only the -netdev option. + * netdev_parse_modern() appends to @nd_queue, whereas net_client_parse() + * appends to @qemu_netdev_opts. + */ +void netdev_parse_modern(const char *optarg) +{ + Visitor *v; + NetdevQueueEntry *nd; + + v = qobject_input_visitor_new_str(optarg, "type", &error_fatal); + nd = g_new(NetdevQueueEntry, 1); + visit_type_Netdev(v, NULL, &nd->nd, &error_fatal); + visit_free(v); + loc_save(&nd->loc); + + QSIMPLEQ_INSERT_TAIL(&nd_queue, nd, entry); +} + +void net_client_parse(QemuOptsList *opts_list, const char *optarg) +{ + if (!qemu_opts_parse_noisily(opts_list, optarg, true)) { + exit(1); + } } /* From FreeBSD */ diff --git a/net/slirp.c b/net/slirp.c index 8679be6444..14a8d59277 100644 --- a/net/slirp.c +++ b/net/slirp.c @@ -611,9 +611,8 @@ static int net_slirp_init(NetClientState *peer, const char *model, nc = qemu_new_net_client(&net_slirp_info, peer, model, name); - snprintf(nc->info_str, sizeof(nc->info_str), - "net=%s,restrict=%s", inet_ntoa(net), - restricted ? "on" : "off"); + qemu_set_info_str(nc, "net=%s,restrict=%s", inet_ntoa(net), + restricted ? "on" : "off"); s = DO_UPCAST(SlirpState, nc, nc); diff --git a/net/socket.c b/net/socket.c index bfd8596250..4944bb70d5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -179,7 +179,7 @@ static void net_socket_send(void *opaque) s->fd = -1; net_socket_rs_init(&s->rs, net_socket_rs_finalize, false); s->nc.link_down = true; - memset(s->nc.info_str, 0, sizeof(s->nc.info_str)); + qemu_set_info_str(&s->nc, ""); return; } @@ -387,16 +387,15 @@ static NetSocketState *net_socket_fd_init_dgram(NetClientState *peer, /* mcast: save bound address as dst */ if (is_connected && mcast != NULL) { s->dgram_dst = saddr; - snprintf(nc->info_str, sizeof(nc->info_str), - "socket: fd=%d (cloned mcast=%s:%d)", - fd, inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port)); + qemu_set_info_str(nc, "socket: fd=%d (cloned mcast=%s:%d)", fd, + inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port)); } else { if (sa_type == SOCKET_ADDRESS_TYPE_UNIX) { s->dgram_dst.sin_family = AF_UNIX; } - snprintf(nc->info_str, sizeof(nc->info_str), - "socket: fd=%d %s", fd, SocketAddressType_str(sa_type)); + qemu_set_info_str(nc, "socket: fd=%d %s", fd, + SocketAddressType_str(sa_type)); } return s; @@ -430,7 +429,7 @@ static NetSocketState *net_socket_fd_init_stream(NetClientState *peer, nc = qemu_new_net_client(&net_socket_info, peer, model, name); - snprintf(nc->info_str, sizeof(nc->info_str), "socket: fd=%d", fd); + qemu_set_info_str(nc, "socket: fd=%d", fd); s = DO_UPCAST(NetSocketState, nc, nc); @@ -497,9 +496,8 @@ static void net_socket_accept(void *opaque) s->fd = fd; s->nc.link_down = false; net_socket_connect(s); - snprintf(s->nc.info_str, sizeof(s->nc.info_str), - "socket: connection from %s:%d", - inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port)); + qemu_set_info_str(&s->nc, "socket: connection from %s:%d", + inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port)); } static int net_socket_listen_init(NetClientState *peer, @@ -579,8 +577,7 @@ static int net_socket_connect_init(NetClientState *peer, if (errno == EINTR || errno == EWOULDBLOCK) { /* continue */ } else if (errno == EINPROGRESS || - errno == EALREADY || - errno == EINVAL) { + errno == EALREADY) { break; } else { error_setg_errno(errp, errno, "can't connect socket"); @@ -597,9 +594,8 @@ static int net_socket_connect_init(NetClientState *peer, return -1; } - snprintf(s->nc.info_str, sizeof(s->nc.info_str), - "socket: connect to %s:%d", - inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port)); + qemu_set_info_str(&s->nc, "socket: connect to %s:%d", + inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port)); return 0; } @@ -642,9 +638,8 @@ static int net_socket_mcast_init(NetClientState *peer, s->dgram_dst = saddr; - snprintf(s->nc.info_str, sizeof(s->nc.info_str), - "socket: mcast=%s:%d", - inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port)); + qemu_set_info_str(&s->nc, "socket: mcast=%s:%d", + inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port)); return 0; } @@ -697,9 +692,8 @@ static int net_socket_udp_init(NetClientState *peer, s->dgram_dst = raddr; - snprintf(s->nc.info_str, sizeof(s->nc.info_str), - "socket: udp=%s:%d", - inet_ntoa(raddr.sin_addr), ntohs(raddr.sin_port)); + qemu_set_info_str(&s->nc, "socket: udp=%s:%d", inet_ntoa(raddr.sin_addr), + ntohs(raddr.sin_port)); return 0; } diff --git a/net/stream.c b/net/stream.c new file mode 100644 index 0000000000..53b7040cc4 --- /dev/null +++ b/net/stream.c @@ -0,0 +1,386 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2008 Fabrice Bellard + * Copyright (c) 2022 Red Hat, Inc. + * + * 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 "qemu/osdep.h" + +#include "net/net.h" +#include "clients.h" +#include "monitor/monitor.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "qemu/option.h" +#include "qemu/sockets.h" +#include "qemu/iov.h" +#include "qemu/main-loop.h" +#include "qemu/cutils.h" +#include "io/channel.h" +#include "io/channel-socket.h" +#include "io/net-listener.h" +#include "qapi/qapi-events-net.h" + +typedef struct NetStreamState { + NetClientState nc; + QIOChannel *listen_ioc; + QIONetListener *listener; + QIOChannel *ioc; + guint ioc_read_tag; + guint ioc_write_tag; + SocketReadState rs; + unsigned int send_index; /* number of bytes sent*/ +} NetStreamState; + +static void net_stream_listen(QIONetListener *listener, + QIOChannelSocket *cioc, + void *opaque); + +static gboolean net_stream_writable(QIOChannel *ioc, + GIOCondition condition, + gpointer data) +{ + NetStreamState *s = data; + + s->ioc_write_tag = 0; + + qemu_flush_queued_packets(&s->nc); + + return G_SOURCE_REMOVE; +} + +static ssize_t net_stream_receive(NetClientState *nc, const uint8_t *buf, + size_t size) +{ + NetStreamState *s = DO_UPCAST(NetStreamState, nc, nc); + uint32_t len = htonl(size); + struct iovec iov[] = { + { + .iov_base = &len, + .iov_len = sizeof(len), + }, { + .iov_base = (void *)buf, + .iov_len = size, + }, + }; + struct iovec local_iov[2]; + unsigned int nlocal_iov; + size_t remaining; + ssize_t ret; + + remaining = iov_size(iov, 2) - s->send_index; + nlocal_iov = iov_copy(local_iov, 2, iov, 2, s->send_index, remaining); + ret = qio_channel_writev(s->ioc, local_iov, nlocal_iov, NULL); + if (ret == QIO_CHANNEL_ERR_BLOCK) { + ret = 0; /* handled further down */ + } + if (ret == -1) { + s->send_index = 0; + return -errno; + } + if (ret < (ssize_t)remaining) { + s->send_index += ret; + s->ioc_write_tag = qio_channel_add_watch(s->ioc, G_IO_OUT, + net_stream_writable, s, NULL); + return 0; + } + s->send_index = 0; + return size; +} + +static gboolean net_stream_send(QIOChannel *ioc, + GIOCondition condition, + gpointer data); + +static void net_stream_send_completed(NetClientState *nc, ssize_t len) +{ + NetStreamState *s = DO_UPCAST(NetStreamState, nc, nc); + + if (!s->ioc_read_tag) { + s->ioc_read_tag = qio_channel_add_watch(s->ioc, G_IO_IN, + net_stream_send, s, NULL); + } +} + +static void net_stream_rs_finalize(SocketReadState *rs) +{ + NetStreamState *s = container_of(rs, NetStreamState, rs); + + if (qemu_send_packet_async(&s->nc, rs->buf, + rs->packet_len, + net_stream_send_completed) == 0) { + if (s->ioc_read_tag) { + g_source_remove(s->ioc_read_tag); + s->ioc_read_tag = 0; + } + } +} + +static gboolean net_stream_send(QIOChannel *ioc, + GIOCondition condition, + gpointer data) +{ + NetStreamState *s = data; + int size; + int ret; + char buf1[NET_BUFSIZE]; + const char *buf; + + size = qio_channel_read(s->ioc, buf1, sizeof(buf1), NULL); + if (size < 0) { + if (errno != EWOULDBLOCK) { + goto eoc; + } + } else if (size == 0) { + /* end of connection */ + eoc: + s->ioc_read_tag = 0; + if (s->ioc_write_tag) { + g_source_remove(s->ioc_write_tag); + s->ioc_write_tag = 0; + } + if (s->listener) { + qio_net_listener_set_client_func(s->listener, net_stream_listen, + s, NULL); + } + object_unref(OBJECT(s->ioc)); + s->ioc = NULL; + + net_socket_rs_init(&s->rs, net_stream_rs_finalize, false); + s->nc.link_down = true; + qemu_set_info_str(&s->nc, ""); + + qapi_event_send_netdev_stream_disconnected(s->nc.name); + + return G_SOURCE_REMOVE; + } + buf = buf1; + + ret = net_fill_rstate(&s->rs, (const uint8_t *)buf, size); + + if (ret == -1) { + goto eoc; + } + + return G_SOURCE_CONTINUE; +} + +static void net_stream_cleanup(NetClientState *nc) +{ + NetStreamState *s = DO_UPCAST(NetStreamState, nc, nc); + if (s->ioc) { + if (QIO_CHANNEL_SOCKET(s->ioc)->fd != -1) { + if (s->ioc_read_tag) { + g_source_remove(s->ioc_read_tag); + s->ioc_read_tag = 0; + } + if (s->ioc_write_tag) { + g_source_remove(s->ioc_write_tag); + s->ioc_write_tag = 0; + } + } + object_unref(OBJECT(s->ioc)); + s->ioc = NULL; + } + if (s->listen_ioc) { + if (s->listener) { + qio_net_listener_disconnect(s->listener); + object_unref(OBJECT(s->listener)); + s->listener = NULL; + } + object_unref(OBJECT(s->listen_ioc)); + s->listen_ioc = NULL; + } +} + +static NetClientInfo net_stream_info = { + .type = NET_CLIENT_DRIVER_STREAM, + .size = sizeof(NetStreamState), + .receive = net_stream_receive, + .cleanup = net_stream_cleanup, +}; + +static void net_stream_listen(QIONetListener *listener, + QIOChannelSocket *cioc, + void *opaque) +{ + NetStreamState *s = opaque; + SocketAddress *addr; + char *uri; + + object_ref(OBJECT(cioc)); + + qio_net_listener_set_client_func(s->listener, NULL, s, NULL); + + s->ioc = QIO_CHANNEL(cioc); + qio_channel_set_name(s->ioc, "stream-server"); + s->nc.link_down = false; + + s->ioc_read_tag = qio_channel_add_watch(s->ioc, G_IO_IN, net_stream_send, + s, NULL); + + if (cioc->localAddr.ss_family == AF_UNIX) { + addr = qio_channel_socket_get_local_address(cioc, NULL); + } else { + addr = qio_channel_socket_get_remote_address(cioc, NULL); + } + g_assert(addr != NULL); + uri = socket_uri(addr); + qemu_set_info_str(&s->nc, uri); + g_free(uri); + qapi_event_send_netdev_stream_connected(s->nc.name, addr); + qapi_free_SocketAddress(addr); +} + +static void net_stream_server_listening(QIOTask *task, gpointer opaque) +{ + NetStreamState *s = opaque; + QIOChannelSocket *listen_sioc = QIO_CHANNEL_SOCKET(s->listen_ioc); + SocketAddress *addr; + int ret; + + if (listen_sioc->fd < 0) { + qemu_set_info_str(&s->nc, "connection error"); + return; + } + + addr = qio_channel_socket_get_local_address(listen_sioc, NULL); + g_assert(addr != NULL); + ret = qemu_socket_try_set_nonblock(listen_sioc->fd); + if (addr->type == SOCKET_ADDRESS_TYPE_FD && ret < 0) { + qemu_set_info_str(&s->nc, "can't use file descriptor %s (errno %d)", + addr->u.fd.str, -ret); + return; + } + g_assert(ret == 0); + qapi_free_SocketAddress(addr); + + s->nc.link_down = true; + s->listener = qio_net_listener_new(); + + net_socket_rs_init(&s->rs, net_stream_rs_finalize, false); + qio_net_listener_set_client_func(s->listener, net_stream_listen, s, NULL); + qio_net_listener_add(s->listener, listen_sioc); +} + +static int net_stream_server_init(NetClientState *peer, + const char *model, + const char *name, + SocketAddress *addr, + Error **errp) +{ + NetClientState *nc; + NetStreamState *s; + QIOChannelSocket *listen_sioc = qio_channel_socket_new(); + + nc = qemu_new_net_client(&net_stream_info, peer, model, name); + s = DO_UPCAST(NetStreamState, nc, nc); + + s->listen_ioc = QIO_CHANNEL(listen_sioc); + qio_channel_socket_listen_async(listen_sioc, addr, 0, + net_stream_server_listening, s, + NULL, NULL); + + return 0; +} + +static void net_stream_client_connected(QIOTask *task, gpointer opaque) +{ + NetStreamState *s = opaque; + QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(s->ioc); + SocketAddress *addr; + gchar *uri; + int ret; + + if (sioc->fd < 0) { + qemu_set_info_str(&s->nc, "connection error"); + goto error; + } + + addr = qio_channel_socket_get_remote_address(sioc, NULL); + g_assert(addr != NULL); + uri = socket_uri(addr); + qemu_set_info_str(&s->nc, uri); + g_free(uri); + + ret = qemu_socket_try_set_nonblock(sioc->fd); + if (addr->type == SOCKET_ADDRESS_TYPE_FD && ret < 0) { + qemu_set_info_str(&s->nc, "can't use file descriptor %s (errno %d)", + addr->u.fd.str, -ret); + qapi_free_SocketAddress(addr); + goto error; + } + g_assert(ret == 0); + + net_socket_rs_init(&s->rs, net_stream_rs_finalize, false); + + /* Disable Nagle algorithm on TCP sockets to reduce latency */ + qio_channel_set_delay(s->ioc, false); + + s->ioc_read_tag = qio_channel_add_watch(s->ioc, G_IO_IN, net_stream_send, + s, NULL); + s->nc.link_down = false; + qapi_event_send_netdev_stream_connected(s->nc.name, addr); + qapi_free_SocketAddress(addr); + + return; +error: + object_unref(OBJECT(s->ioc)); + s->ioc = NULL; +} + +static int net_stream_client_init(NetClientState *peer, + const char *model, + const char *name, + SocketAddress *addr, + Error **errp) +{ + NetStreamState *s; + NetClientState *nc; + QIOChannelSocket *sioc = qio_channel_socket_new(); + + nc = qemu_new_net_client(&net_stream_info, peer, model, name); + s = DO_UPCAST(NetStreamState, nc, nc); + + s->ioc = QIO_CHANNEL(sioc); + s->nc.link_down = true; + + qio_channel_socket_connect_async(sioc, addr, + net_stream_client_connected, s, + NULL, NULL); + + return 0; +} + +int net_init_stream(const Netdev *netdev, const char *name, + NetClientState *peer, Error **errp) +{ + const NetdevStreamOptions *sock; + + assert(netdev->type == NET_CLIENT_DRIVER_STREAM); + sock = &netdev->u.stream; + + if (!sock->has_server || !sock->server) { + return net_stream_client_init(peer, "stream", name, sock->addr, errp); + } + return net_stream_server_init(peer, "stream", name, sock->addr, errp); +} diff --git a/net/tap-win32.c b/net/tap-win32.c index 7466f22e77..a49c28ba5d 100644 --- a/net/tap-win32.c +++ b/net/tap-win32.c @@ -789,8 +789,7 @@ static int tap_win32_init(NetClientState *peer, const char *model, s = DO_UPCAST(TAPState, nc, nc); - snprintf(s->nc.info_str, sizeof(s->nc.info_str), - "tap: ifname=%s", ifname); + qemu_set_info_str(&s->nc, "tap: ifname=%s", ifname); s->handle = handle; diff --git a/net/tap.c b/net/tap.c index e203d07a12..1210a0436d 100644 --- a/net/tap.c +++ b/net/tap.c @@ -630,8 +630,7 @@ int net_init_bridge(const Netdev *netdev, const char *name, } s = net_tap_fd_init(peer, "bridge", name, fd, vnet_hdr); - snprintf(s->nc.info_str, sizeof(s->nc.info_str), "helper=%s,br=%s", helper, - br); + qemu_set_info_str(&s->nc, "helper=%s,br=%s", helper, br); return 0; } @@ -690,14 +689,12 @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer, } if (tap->has_fd || tap->has_fds) { - snprintf(s->nc.info_str, sizeof(s->nc.info_str), "fd=%d", fd); + qemu_set_info_str(&s->nc, "fd=%d", fd); } else if (tap->has_helper) { - snprintf(s->nc.info_str, sizeof(s->nc.info_str), "helper=%s", - tap->helper); + qemu_set_info_str(&s->nc, "helper=%s", tap->helper); } else { - snprintf(s->nc.info_str, sizeof(s->nc.info_str), - "ifname=%s,script=%s,downscript=%s", ifname, script, - downscript); + qemu_set_info_str(&s->nc, "ifname=%s,script=%s,downscript=%s", ifname, + script, downscript); if (strcmp(downscript, "no") != 0) { snprintf(s->down_script, sizeof(s->down_script), "%s", downscript); diff --git a/net/vde.c b/net/vde.c index 1083916bcf..c0a08662cc 100644 --- a/net/vde.c +++ b/net/vde.c @@ -98,8 +98,7 @@ static int net_vde_init(NetClientState *peer, const char *model, nc = qemu_new_net_client(&net_vde_info, peer, model, name); - snprintf(nc->info_str, sizeof(nc->info_str), "sock=%s,fd=%d", - sock, vde_datafd(vde)); + qemu_set_info_str(nc, "sock=%s,fd=%d", sock, vde_datafd(vde)); s = DO_UPCAST(VDEState, nc, nc); diff --git a/net/vhost-user.c b/net/vhost-user.c index b1a0247b59..3a6b90da86 100644 --- a/net/vhost-user.c +++ b/net/vhost-user.c @@ -341,8 +341,7 @@ static int net_vhost_user_init(NetClientState *peer, const char *device, user = g_new0(struct VhostUserState, 1); for (i = 0; i < queues; i++) { nc = qemu_new_net_client(&net_vhost_user_info, peer, device, name); - snprintf(nc->info_str, sizeof(nc->info_str), "vhost-user%d to %s", - i, chr->label); + qemu_set_info_str(nc, "vhost-user%d to %s", i, chr->label); nc->queue_index = i; if (!nc0) { nc0 = nc; diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c index 4bc3fd01a8..854ebd61ae 100644 --- a/net/vhost-vdpa.c +++ b/net/vhost-vdpa.c @@ -63,7 +63,6 @@ const int vdpa_feature_bits[] = { VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_RX_EXTRA, VIRTIO_NET_F_CTRL_VLAN, - VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_CTRL_MAC_ADDR, VIRTIO_NET_F_RSS, VIRTIO_NET_F_MQ, @@ -462,48 +461,6 @@ static NetClientInfo net_vhost_vdpa_cvq_info = { .check_peer_type = vhost_vdpa_check_peer_type, }; -/** - * Do not forward commands not supported by SVQ. Otherwise, the device could - * accept it and qemu would not know how to update the device model. - */ -static bool vhost_vdpa_net_cvq_validate_cmd(const void *out_buf, size_t len) -{ - struct virtio_net_ctrl_hdr ctrl; - - if (unlikely(len < sizeof(ctrl))) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid legnth of out buffer %zu\n", __func__, len); - return false; - } - - memcpy(&ctrl, out_buf, sizeof(ctrl)); - switch (ctrl.class) { - case VIRTIO_NET_CTRL_MAC: - switch (ctrl.cmd) { - case VIRTIO_NET_CTRL_MAC_ADDR_SET: - return true; - default: - qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid mac cmd %u\n", - __func__, ctrl.cmd); - }; - break; - case VIRTIO_NET_CTRL_MQ: - switch (ctrl.cmd) { - case VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET: - return true; - default: - qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid mq cmd %u\n", - __func__, ctrl.cmd); - }; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid control class %u\n", - __func__, ctrl.class); - }; - - return false; -} - /** * Validate and copy control virtqueue commands. * @@ -527,16 +484,10 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq, .iov_len = sizeof(status), }; ssize_t dev_written = -EINVAL; - bool ok; out.iov_len = iov_to_buf(elem->out_sg, elem->out_num, 0, s->cvq_cmd_out_buffer, vhost_vdpa_net_cvq_cmd_len()); - ok = vhost_vdpa_net_cvq_validate_cmd(s->cvq_cmd_out_buffer, out.iov_len); - if (unlikely(!ok)) { - goto out; - } - dev_written = vhost_vdpa_net_cvq_add(s, out.iov_len, sizeof(status)); if (unlikely(dev_written < 0)) { goto out; @@ -593,7 +544,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer, nc = qemu_new_net_control_client(&net_vhost_vdpa_cvq_info, peer, device, name); } - snprintf(nc->info_str, sizeof(nc->info_str), TYPE_VHOST_VDPA); + qemu_set_info_str(nc, TYPE_VHOST_VDPA); s = DO_UPCAST(VhostVDPAState, nc, nc); s->vhost_vdpa.device_fd = vdpa_device_fd; @@ -683,14 +634,29 @@ int net_init_vhost_vdpa(const Netdev *netdev, const char *name, assert(netdev->type == NET_CLIENT_DRIVER_VHOST_VDPA); opts = &netdev->u.vhost_vdpa; - if (!opts->vhostdev) { - error_setg(errp, "vdpa character device not specified with vhostdev"); + if (!opts->has_vhostdev && !opts->has_vhostfd) { + error_setg(errp, + "vhost-vdpa: neither vhostdev= nor vhostfd= was specified"); return -1; } - vdpa_device_fd = qemu_open(opts->vhostdev, O_RDWR, errp); - if (vdpa_device_fd == -1) { - return -errno; + if (opts->has_vhostdev && opts->has_vhostfd) { + error_setg(errp, + "vhost-vdpa: vhostdev= and vhostfd= are mutually exclusive"); + return -1; + } + + if (opts->has_vhostdev) { + vdpa_device_fd = qemu_open(opts->vhostdev, O_RDWR, errp); + if (vdpa_device_fd == -1) { + return -errno; + } + } else if (opts->has_vhostfd) { + vdpa_device_fd = monitor_fd_param(monitor_cur(), opts->vhostfd, errp); + if (vdpa_device_fd == -1) { + error_prepend(errp, "vhost-vdpa: unable to parse vhostfd: "); + return -1; + } } r = vhost_vdpa_get_features(vdpa_device_fd, &features, errp); diff --git a/qapi/net.json b/qapi/net.json index dd088c09c5..522ac582ed 100644 --- a/qapi/net.json +++ b/qapi/net.json @@ -7,6 +7,7 @@ ## { 'include': 'common.json' } +{ 'include': 'sockets.json' } ## # @set_link: @@ -442,6 +443,8 @@ # @vhostdev: path of vhost-vdpa device # (default:'/dev/vhost-vdpa-0') # +# @vhostfd: file descriptor of an already opened vhost vdpa device +# # @queues: number of queues to be created for multiqueue vhost-vdpa # (default: 1) # @@ -456,6 +459,7 @@ { 'struct': 'NetdevVhostVDPAOptions', 'data': { '*vhostdev': 'str', + '*vhostfd': 'str', '*queues': 'int', '*x-svq': {'type': 'bool', 'features' : [ 'unstable'] } } } @@ -573,6 +577,60 @@ '*isolated': 'bool' }, 'if': 'CONFIG_VMNET' } +## +# @NetdevStreamOptions: +# +# Configuration info for stream socket netdev +# +# @addr: socket address to listen on (server=true) +# or connect to (server=false) +# @server: create server socket (default: false) +# +# Only SocketAddress types 'unix', 'inet' and 'fd' are supported. +# +# Since: 7.2 +## +{ 'struct': 'NetdevStreamOptions', + 'data': { + 'addr': 'SocketAddress', + '*server': 'bool' } } + +## +# @NetdevDgramOptions: +# +# Configuration info for datagram socket netdev. +# +# @remote: remote address +# @local: local address +# +# Only SocketAddress types 'unix', 'inet' and 'fd' are supported. +# +# If remote address is present and it's a multicast address, local address +# is optional. Otherwise local address is required and remote address is +# optional. +# +# .. table:: Valid parameters combination table +# :widths: auto +# +# ============= ======== ===== +# remote local okay? +# ============= ======== ===== +# absent absent no +# absent not fd no +# absent fd yes +# multicast absent yes +# multicast present yes +# not multicast absent no +# not multicast present yes +# ============= ======== ===== +# +# Since: 7.2 +## +{ 'struct': 'NetdevDgramOptions', + 'data': { + '*local': 'SocketAddress', + '*remote': 'SocketAddress' } } + ## # @NetClientDriver: # @@ -584,10 +642,13 @@ # @vmnet-host since 7.1 # @vmnet-shared since 7.1 # @vmnet-bridged since 7.1 +# @stream since 7.2 +# @dgram since 7.2 ## { 'enum': 'NetClientDriver', - 'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde', - 'bridge', 'hubport', 'netmap', 'vhost-user', 'vhost-vdpa', + 'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'stream', + 'dgram', 'vde', 'bridge', 'hubport', 'netmap', 'vhost-user', + 'vhost-vdpa', { 'name': 'vmnet-host', 'if': 'CONFIG_VMNET' }, { 'name': 'vmnet-shared', 'if': 'CONFIG_VMNET' }, { 'name': 'vmnet-bridged', 'if': 'CONFIG_VMNET' }] } @@ -607,6 +668,8 @@ # 'vmnet-host' - since 7.1 # 'vmnet-shared' - since 7.1 # 'vmnet-bridged' - since 7.1 +# 'stream' since 7.2 +# 'dgram' since 7.2 ## { 'union': 'Netdev', 'base': { 'id': 'str', 'type': 'NetClientDriver' }, @@ -617,6 +680,8 @@ 'tap': 'NetdevTapOptions', 'l2tpv3': 'NetdevL2TPv3Options', 'socket': 'NetdevSocketOptions', + 'stream': 'NetdevStreamOptions', + 'dgram': 'NetdevDgramOptions', 'vde': 'NetdevVdeOptions', 'bridge': 'NetdevBridgeOptions', 'hubport': 'NetdevHubPortOptions', @@ -833,3 +898,52 @@ ## { 'event': 'FAILOVER_NEGOTIATED', 'data': {'device-id': 'str'} } + +## +# @NETDEV_STREAM_CONNECTED: +# +# Emitted when the netdev stream backend is connected +# +# @netdev-id: QEMU netdev id that is connected +# @addr: The destination address +# +# Since: 7.2 +# +# Example: +# +# <- { "event": "NETDEV_STREAM_CONNECTED", +# "data": { "netdev-id": "netdev0", +# "addr": { "port": "47666", "ipv6": true, +# "host": "::1", "type": "inet" } }, +# "timestamp": { "seconds": 1666269863, "microseconds": 311222 } } +# +# or +# +# <- { "event": "NETDEV_STREAM_CONNECTED", +# "data": { "netdev-id": "netdev0", +# "addr": { "path": "/tmp/qemu0", "type": "unix" } }, +# "timestamp": { "seconds": 1666269706, "microseconds": 413651 } } +# +## +{ 'event': 'NETDEV_STREAM_CONNECTED', + 'data': { 'netdev-id': 'str', + 'addr': 'SocketAddress' } } + +## +# @NETDEV_STREAM_DISCONNECTED: +# +# Emitted when the netdev stream backend is disconnected +# +# @netdev-id: QEMU netdev id that is disconnected +# +# Since: 7.2 +# +# Example: +# +# <- { 'event': 'NETDEV_STREAM_DISCONNECTED', +# 'data': {'netdev-id': 'netdev0'}, +# 'timestamp': {'seconds': 1663330937, 'microseconds': 526695} } +# +## +{ 'event': 'NETDEV_STREAM_DISCONNECTED', + 'data': { 'netdev-id': 'str' } } diff --git a/qemu-options.hx b/qemu-options.hx index eb38e5dc40..ceee0ddc25 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -2772,6 +2772,20 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev, "-netdev socket,id=str[,fd=h][,udp=host:port][,localaddr=host:port]\n" " configure a network backend to connect to another network\n" " using an UDP tunnel\n" + "-netdev stream,id=str[,server=on|off],addr.type=inet,addr.host=host,addr.port=port[,to=maxport][,numeric=on|off][,keep-alive=on|off][,mptcp=on|off][,addr.ipv4=on|off][,addr.ipv6=on|off]\n" + "-netdev stream,id=str[,server=on|off],addr.type=unix,addr.path=path[,abstract=on|off][,tight=on|off]\n" + "-netdev stream,id=str[,server=on|off],addr.type=fd,addr.str=file-descriptor\n" + " configure a network backend to connect to another network\n" + " using a socket connection in stream mode.\n" + "-netdev dgram,id=str,remote.type=inet,remote.host=maddr,remote.port=port[,local.type=inet,local.host=addr]\n" + "-netdev dgram,id=str,remote.type=inet,remote.host=maddr,remote.port=port[,local.type=fd,local.str=file-descriptor]\n" + " configure a network backend to connect to a multicast maddr and port\n" + " use ``local.host=addr`` to specify the host address to send packets from\n" + "-netdev dgram,id=str,local.type=inet,local.host=addr,local.port=port[,remote.type=inet,remote.host=addr,remote.port=port]\n" + "-netdev dgram,id=str,local.type=unix,local.path=path[,remote.type=unix,remote.path=path]\n" + "-netdev dgram,id=str,local.type=fd,local.str=file-descriptor\n" + " configure a network backend to connect to another network\n" + " using an UDP tunnel\n" #ifdef CONFIG_VDE "-netdev vde,id=str[,sock=socketpath][,port=n][,group=groupname][,mode=octalmode]\n" " configure a network backend to connect to port 'n' of a vde switch\n" @@ -2790,8 +2804,10 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev, " configure a vhost-user network, backed by a chardev 'dev'\n" #endif #ifdef __linux__ - "-netdev vhost-vdpa,id=str,vhostdev=/path/to/dev\n" + "-netdev vhost-vdpa,id=str[,vhostdev=/path/to/dev][,vhostfd=h]\n" " configure a vhost-vdpa network,Establish a vhost-vdpa netdev\n" + " use 'vhostdev=/path/to/dev' to open a vhost vdpa device\n" + " use 'vhostfd=h' to connect to an already opened vhost vdpa device\n" #endif #ifdef CONFIG_VMNET "-netdev vmnet-host,id=str[,isolated=on|off][,net-uuid=uuid]\n" @@ -3296,7 +3312,7 @@ SRST -netdev type=vhost-user,id=net0,chardev=chr0 \ -device virtio-net-pci,netdev=net0 -``-netdev vhost-vdpa,vhostdev=/path/to/dev`` +``-netdev vhost-vdpa[,vhostdev=/path/to/dev][,vhostfd=h]`` Establish a vhost-vdpa netdev. vDPA device is a device that uses a datapath which complies with diff --git a/softmmu/vl.c b/softmmu/vl.c index b464da25bc..99fb49c7b0 100644 --- a/softmmu/vl.c +++ b/softmmu/vl.c @@ -1904,7 +1904,7 @@ static void qemu_create_late_backends(void) qtest_server_init(qtest_chrdev, qtest_log, &error_fatal); } - net_init_clients(&error_fatal); + net_init_clients(); object_option_foreach_add(object_create_late); @@ -2801,21 +2801,19 @@ void qemu_init(int argc, char **argv) break; case QEMU_OPTION_netdev: default_net = 0; - if (net_client_parse(qemu_find_opts("netdev"), optarg) == -1) { - exit(1); + if (netdev_is_modern(optarg)) { + netdev_parse_modern(optarg); + } else { + net_client_parse(qemu_find_opts("netdev"), optarg); } break; case QEMU_OPTION_nic: default_net = 0; - if (net_client_parse(qemu_find_opts("nic"), optarg) == -1) { - exit(1); - } + net_client_parse(qemu_find_opts("nic"), optarg); break; case QEMU_OPTION_net: default_net = 0; - if (net_client_parse(qemu_find_opts("net"), optarg) == -1) { - exit(1); - } + net_client_parse(qemu_find_opts("net"), optarg); break; #ifdef CONFIG_LIBISCSI case QEMU_OPTION_iscsi: diff --git a/util/qemu-sockets.c b/util/qemu-sockets.c index 0c41ca9e42..d185245023 100644 --- a/util/qemu-sockets.c +++ b/util/qemu-sockets.c @@ -1076,6 +1076,26 @@ int unix_connect(const char *path, Error **errp) return sock; } +char *socket_uri(SocketAddress *addr) +{ + switch (addr->type) { + case SOCKET_ADDRESS_TYPE_INET: + return g_strdup_printf("tcp:%s:%s", + addr->u.inet.host, + addr->u.inet.port); + case SOCKET_ADDRESS_TYPE_UNIX: + return g_strdup_printf("unix:%s", + addr->u.q_unix.path); + case SOCKET_ADDRESS_TYPE_FD: + return g_strdup_printf("fd:%s", addr->u.fd.str); + case SOCKET_ADDRESS_TYPE_VSOCK: + return g_strdup_printf("vsock:%s:%s", + addr->u.vsock.cid, + addr->u.vsock.port); + default: + return g_strdup("unknown address type"); + } +} SocketAddress *socket_parse(const char *str, Error **errp) { @@ -1103,6 +1123,11 @@ SocketAddress *socket_parse(const char *str, Error **errp) if (vsock_parse(&addr->u.vsock, str + strlen("vsock:"), errp)) { goto fail; } + } else if (strstart(str, "tcp:", NULL)) { + addr->type = SOCKET_ADDRESS_TYPE_INET; + if (inet_parse(&addr->u.inet, str + strlen("tcp:"), errp)) { + goto fail; + } } else { addr->type = SOCKET_ADDRESS_TYPE_INET; if (inet_parse(&addr->u.inet, str, errp)) {