Net patches

index 1fbf2f3..b6903ae 100644
@@ -2536,14 +2536,19 @@ static void virtio_net_tx_complete(NetClientState *nc, ssize_t len)
 
     virtio_queue_set_notification(q->tx_vq, 1);
     ret = virtio_net_flush_tx(q);
-    if (q->tx_bh && ret >= n->tx_burst) {
+    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);
-        qemu_bh_schedule(q->tx_bh);
+        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;
     }
 }

@@ -2644,6 +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);

@@ -2661,15 +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);
     }

@@ -2702,6 +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. */

@@ -2716,8 +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)

index f306ebe..5bd14ca 100644
@@ -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:

index 884f473..54c67e1 100644
@@ -35,48 +35,36 @@
 #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"
 
 typedef struct NetStreamState {
     NetClientState nc;
-    int listen_fd;
-    int fd;
+    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*/
-    bool read_poll;               /* waiting to receive data? */
-    bool write_poll;              /* waiting to transmit data? */
 } NetStreamState;
 
-static void net_stream_send(void *opaque);
-static void net_stream_accept(void *opaque);
-static void net_stream_writable(void *opaque);
+static void net_stream_listen(QIONetListener *listener,
+                              QIOChannelSocket *cioc,
+                              void *opaque);
 
-static void net_stream_update_fd_handler(NetStreamState *s)
+static gboolean net_stream_writable(QIOChannel *ioc,
+                                    GIOCondition condition,
+                                    gpointer data)
 {
-    qemu_set_fd_handler(s->fd,
-                        s->read_poll ? net_stream_send : NULL,
-                        s->write_poll ? net_stream_writable : NULL,
-                        s);
-}
-
-static void net_stream_read_poll(NetStreamState *s, bool enable)
-{
-    s->read_poll = enable;
-    net_stream_update_fd_handler(s);
-}
-
-static void net_stream_write_poll(NetStreamState *s, bool enable)
-{
-    s->write_poll = enable;
-    net_stream_update_fd_handler(s);
-}
-
-static void net_stream_writable(void *opaque)
-{
-    NetStreamState *s = opaque;
+    NetStreamState *s = data;
 
-    net_stream_write_poll(s, false);
+    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,

@@ -93,13 +81,15 @@ static ssize_t net_stream_receive(NetClientState *nc, const uint8_t *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;
-    ret = iov_send(s->fd, iov, 2, s->send_index, remaining);
-
-    if (ret == -1 && errno == EAGAIN) {
+    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) {

@@ -108,19 +98,25 @@ static ssize_t net_stream_receive(NetClientState *nc, const uint8_t *buf,
     }
     if (ret < (ssize_t)remaining) {
         s->send_index += ret;
-        net_stream_write_poll(s, true);
+        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->read_poll) {
-        net_stream_read_poll(s, true);
+    if (!s->ioc_read_tag) {
+        s->ioc_read_tag = qio_channel_add_watch(s->ioc, G_IO_IN,
+                                                net_stream_send, s, NULL);
     }
 }
 

@@ -131,19 +127,24 @@ static void net_stream_rs_finalize(SocketReadState *rs)
     if (qemu_send_packet_async(&s->nc, rs->buf,
                                rs->packet_len,
                                net_stream_send_completed) == 0) {
-        net_stream_read_poll(s, false);
+        if (s->ioc_read_tag) {
+            g_source_remove(s->ioc_read_tag);
+            s->ioc_read_tag = 0;
+        }
     }
 }
 
-static void net_stream_send(void *opaque)
+static gboolean net_stream_send(QIOChannel *ioc,
+                                GIOCondition condition,
+                                gpointer data)
 {
-    NetStreamState *s = opaque;
+    NetStreamState *s = data;
     int size;
     int ret;
-    uint8_t buf1[NET_BUFSIZE];
-    const uint8_t *buf;
+    char buf1[NET_BUFSIZE];
+    const char *buf;
 
-    size = recv(s->fd, buf1, sizeof(buf1), 0);
+    size = qio_channel_read(s->ioc, buf1, sizeof(buf1), NULL);
     if (size < 0) {
         if (errno != EWOULDBLOCK) {
             goto eoc;

@@ -151,51 +152,63 @@ static void net_stream_send(void *opaque)
     } else if (size == 0) {
         /* end of connection */
     eoc:
-        net_stream_read_poll(s, false);
-        net_stream_write_poll(s, false);
-        if (s->listen_fd != -1) {
-            qemu_set_fd_handler(s->listen_fd, net_stream_accept, NULL, s);
+        s->ioc_read_tag = 0;
+        if (s->ioc_write_tag) {
+            g_source_remove(s->ioc_write_tag);
+            s->ioc_write_tag = 0;
         }
-        closesocket(s->fd);
+        if (s->listener) {
+            qio_net_listener_set_client_func(s->listener, net_stream_listen,
+                                             s, NULL);
+        }
+        object_unref(OBJECT(s->ioc));
+        s->ioc = NULL;
 
-        s->fd = -1;
         net_socket_rs_init(&s->rs, net_stream_rs_finalize, false);
         s->nc.link_down = true;
         qemu_set_info_str(&s->nc, "");
 
-        return;
+        return G_SOURCE_REMOVE;
     }
     buf = buf1;
 
-    ret = net_fill_rstate(&s->rs, buf, size);
+    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->fd != -1) {
-        net_stream_read_poll(s, false);
-        net_stream_write_poll(s, false);
-        close(s->fd);
-        s->fd = -1;
+    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_fd != -1) {
-        qemu_set_fd_handler(s->listen_fd, NULL, NULL, NULL);
-        closesocket(s->listen_fd);
-        s->listen_fd = -1;
+    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 void net_stream_connect(void *opaque)
-{
-    NetStreamState *s = opaque;
-    net_stream_read_poll(s, true);
-}
-
 static NetClientInfo net_stream_info = {
     .type = NET_CLIENT_DRIVER_STREAM,
     .size = sizeof(NetStreamState),

@@ -203,76 +216,66 @@ static NetClientInfo net_stream_info = {
     .cleanup = net_stream_cleanup,
 };
 
-static NetStreamState *net_stream_fd_init(NetClientState *peer,
-                                          const char *model,
-                                          const char *name,
-                                          int fd, int is_connected)
+static void net_stream_listen(QIONetListener *listener,
+                              QIOChannelSocket *cioc,
+                              void *opaque)
 {
-    NetClientState *nc;
-    NetStreamState *s;
-
-    nc = qemu_new_net_client(&net_stream_info, peer, model, name);
+    NetStreamState *s = opaque;
+    SocketAddress *addr;
+    char *uri;
 
-    qemu_set_info_str(nc, "fd=%d", fd);
+    object_ref(OBJECT(cioc));
 
-    s = DO_UPCAST(NetStreamState, nc, nc);
+    qio_net_listener_set_client_func(s->listener, NULL, s, NULL);
 
-    s->fd = fd;
-    s->listen_fd = -1;
-    net_socket_rs_init(&s->rs, net_stream_rs_finalize, false);
+    s->ioc = QIO_CHANNEL(cioc);
+    qio_channel_set_name(s->ioc, "stream-server");
+    s->nc.link_down = false;
 
-    /* Disable Nagle algorithm on TCP sockets to reduce latency */
-    socket_set_nodelay(fd);
+    s->ioc_read_tag = qio_channel_add_watch(s->ioc, G_IO_IN, net_stream_send,
+                                            s, NULL);
 
-    if (is_connected) {
-        net_stream_connect(s);
+    if (cioc->localAddr.ss_family == AF_UNIX) {
+        addr = qio_channel_socket_get_local_address(cioc, NULL);
     } else {
-        qemu_set_fd_handler(s->fd, NULL, net_stream_connect, s);
+        addr = qio_channel_socket_get_remote_address(cioc, NULL);
     }
-    return s;
+    g_assert(addr != NULL);
+    uri = socket_uri(addr);
+    qemu_set_info_str(&s->nc, uri);
+    g_free(uri);
+    qapi_free_SocketAddress(addr);
 }
 
-static void net_stream_accept(void *opaque)
+static void net_stream_server_listening(QIOTask *task, gpointer opaque)
 {
     NetStreamState *s = opaque;
-    struct sockaddr_storage saddr;
-    socklen_t len;
-    int fd;
-
-    for (;;) {
-        len = sizeof(saddr);
-        fd = qemu_accept(s->listen_fd, (struct sockaddr *)&saddr, &len);
-        if (fd < 0 && errno != EINTR) {
-            return;
-        } else if (fd >= 0) {
-            qemu_set_fd_handler(s->listen_fd, NULL, NULL, NULL);
-            break;
-        }
-    }
+    QIOChannelSocket *listen_sioc = QIO_CHANNEL_SOCKET(s->listen_ioc);
+    SocketAddress *addr;
+    int ret;
 
-    s->fd = fd;
-    s->nc.link_down = false;
-    net_stream_connect(s);
-    switch (saddr.ss_family) {
-    case AF_INET: {
-        struct sockaddr_in *saddr_in = (struct sockaddr_in *)&saddr;
-
-        qemu_set_info_str(&s->nc, "connection from %s:%d",
-                          inet_ntoa(saddr_in->sin_addr),
-                          ntohs(saddr_in->sin_port));
-        break;
+    if (listen_sioc->fd < 0) {
+        qemu_set_info_str(&s->nc, "connection error");
+        return;
     }
-    case AF_UNIX: {
-        struct sockaddr_un saddr_un;
 
-        len = sizeof(saddr_un);
-        getsockname(s->listen_fd, (struct sockaddr *)&saddr_un, &len);
-        qemu_set_info_str(&s->nc, "connect from %s", saddr_un.sun_path);
-        break;
-    }
-    default:
-        g_assert_not_reached();
+    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,

@@ -283,105 +286,61 @@ static int net_stream_server_init(NetClientState *peer,
 {
     NetClientState *nc;
     NetStreamState *s;
-    int fd, ret;
+    QIOChannelSocket *listen_sioc = qio_channel_socket_new();
 
-    switch (addr->type) {
-    case SOCKET_ADDRESS_TYPE_INET: {
-        struct sockaddr_in saddr_in;
-
-        if (convert_host_port(&saddr_in, addr->u.inet.host, addr->u.inet.port,
-                              errp) < 0) {
-            return -1;
-        }
-
-        fd = qemu_socket(PF_INET, SOCK_STREAM, 0);
-        if (fd < 0) {
-            error_setg_errno(errp, errno, "can't create stream socket");
-            return -1;
-        }
-        qemu_socket_set_nonblock(fd);
+    nc = qemu_new_net_client(&net_stream_info, peer, model, name);
+    s = DO_UPCAST(NetStreamState, nc, nc);
 
-        socket_set_fast_reuse(fd);
+    s->listen_ioc = QIO_CHANNEL(listen_sioc);
+    qio_channel_socket_listen_async(listen_sioc, addr, 0,
+                                    net_stream_server_listening, s,
+                                    NULL, NULL);
 
-        ret = bind(fd, (struct sockaddr *)&saddr_in, sizeof(saddr_in));
-        if (ret < 0) {
-            error_setg_errno(errp, errno, "can't bind ip=%s to socket",
-                             inet_ntoa(saddr_in.sin_addr));
-            closesocket(fd);
-            return -1;
-        }
-        break;
-    }
-    case SOCKET_ADDRESS_TYPE_UNIX: {
-        struct sockaddr_un saddr_un;
-
-        ret = unlink(addr->u.q_unix.path);
-        if (ret < 0 && errno != ENOENT) {
-            error_setg_errno(errp, errno, "failed to unlink socket %s",
-                             addr->u.q_unix.path);
-            return -1;
-        }
+    return 0;
+}
 
-        saddr_un.sun_family = PF_UNIX;
-        ret = snprintf(saddr_un.sun_path, sizeof(saddr_un.sun_path), "%s",
-                       addr->u.q_unix.path);
-        if (ret < 0 || ret >= sizeof(saddr_un.sun_path)) {
-            error_setg(errp, "UNIX socket path '%s' is too long",
-                       addr->u.q_unix.path);
-            error_append_hint(errp, "Path must be less than %zu bytes\n",
-                              sizeof(saddr_un.sun_path));
-            return -1;
-        }
+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;
 
-        fd = qemu_socket(PF_UNIX, SOCK_STREAM, 0);
-        if (fd < 0) {
-            error_setg_errno(errp, errno, "can't create stream socket");
-            return -1;
-        }
-        qemu_socket_set_nonblock(fd);
-
-        ret = bind(fd, (struct sockaddr *)&saddr_un, sizeof(saddr_un));
-        if (ret < 0) {
-            error_setg_errno(errp, errno, "can't create socket with path: %s",
-                             saddr_un.sun_path);
-            closesocket(fd);
-            return -1;
-        }
-        break;
-    }
-    case SOCKET_ADDRESS_TYPE_FD:
-        fd = monitor_fd_param(monitor_cur(), addr->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;
-        }
-        break;
-    default:
-        error_setg(errp, "only support inet or fd type");
-        return -1;
+    if (sioc->fd < 0) {
+        qemu_set_info_str(&s->nc, "connection error");
+        goto error;
     }
 
-    ret = listen(fd, 0);
-    if (ret < 0) {
-        error_setg_errno(errp, errno, "can't listen on socket");
-        closesocket(fd);
-        return -1;
+    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);
 
-    nc = qemu_new_net_client(&net_stream_info, peer, model, name);
-    s = DO_UPCAST(NetStreamState, nc, nc);
-    s->fd = -1;
-    s->listen_fd = fd;
-    s->nc.link_down = true;
     net_socket_rs_init(&s->rs, net_stream_rs_finalize, false);
 
-    qemu_set_fd_handler(s->listen_fd, net_stream_accept, NULL, s);
-    return 0;
+    /* 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_free_SocketAddress(addr);
+
+    return;
+error:
+    object_unref(OBJECT(s->ioc));
+    s->ioc = NULL;
 }
 
 static int net_stream_client_init(NetClientState *peer,

@@ -391,118 +350,19 @@ static int net_stream_client_init(NetClientState *peer,
                                   Error **errp)
 {
     NetStreamState *s;
-    struct sockaddr_in saddr_in;
-    struct sockaddr_un saddr_un;
-    int fd, connected, ret;
-
-    switch (addr->type) {
-    case SOCKET_ADDRESS_TYPE_INET:
-        if (convert_host_port(&saddr_in, addr->u.inet.host, addr->u.inet.port,
-                              errp) < 0) {
-            return -1;
-        }
+    NetClientState *nc;
+    QIOChannelSocket *sioc = qio_channel_socket_new();
 
-        fd = qemu_socket(PF_INET, SOCK_STREAM, 0);
-        if (fd < 0) {
-            error_setg_errno(errp, errno, "can't create stream socket");
-            return -1;
-        }
-        qemu_socket_set_nonblock(fd);
-
-        connected = 0;
-        for (;;) {
-            ret = connect(fd, (struct sockaddr *)&saddr_in, sizeof(saddr_in));
-            if (ret < 0) {
-                if (errno == EINTR || errno == EWOULDBLOCK) {
-                    /* continue */
-                } else if (errno == EINPROGRESS ||
-                           errno == EALREADY) {
-                    break;
-                } else {
-                    error_setg_errno(errp, errno, "can't connect socket");
-                    closesocket(fd);
-                    return -1;
-                }
-            } else {
-                connected = 1;
-                break;
-            }
-        }
-        break;
-    case SOCKET_ADDRESS_TYPE_UNIX:
-        saddr_un.sun_family = PF_UNIX;
-        ret = snprintf(saddr_un.sun_path, sizeof(saddr_un.sun_path), "%s",
-                       addr->u.q_unix.path);
-        if (ret < 0 || ret >= sizeof(saddr_un.sun_path)) {
-            error_setg(errp, "UNIX socket path '%s' is too long",
-                       addr->u.q_unix.path);
-            error_append_hint(errp, "Path must be less than %zu bytes\n",
-                              sizeof(saddr_un.sun_path));
-            return -1;
-        }
+    nc = qemu_new_net_client(&net_stream_info, peer, model, name);
+    s = DO_UPCAST(NetStreamState, nc, nc);
 
-        fd = qemu_socket(PF_UNIX, SOCK_STREAM, 0);
-        if (fd < 0) {
-            error_setg_errno(errp, errno, "can't create stream socket");
-            return -1;
-        }
-        qemu_socket_set_nonblock(fd);
-
-        connected = 0;
-        for (;;) {
-            ret = connect(fd, (struct sockaddr *)&saddr_un, sizeof(saddr_un));
-            if (ret < 0) {
-                if (errno == EINTR || errno == EWOULDBLOCK) {
-                    /* continue */
-                } else if (errno == EAGAIN ||
-                           errno == EALREADY) {
-                    break;
-                } else {
-                    error_setg_errno(errp, errno, "can't connect socket");
-                    closesocket(fd);
-                    return -1;
-                }
-            } else {
-                connected = 1;
-                break;
-            }
-        }
-        break;
-    case SOCKET_ADDRESS_TYPE_FD:
-        fd = monitor_fd_param(monitor_cur(), addr->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;
-        }
-        connected = 1;
-        break;
-    default:
-        error_setg(errp, "only support inet, unix or fd type");
-        return -1;
-    }
+    s->ioc = QIO_CHANNEL(sioc);
+    s->nc.link_down = true;
+
+    qio_channel_socket_connect_async(sioc, addr,
+                                     net_stream_client_connected, s,
+                                     NULL, NULL);
 
-    s = net_stream_fd_init(peer, model, name, fd, connected);
-
-    switch (addr->type) {
-    case SOCKET_ADDRESS_TYPE_INET:
-        qemu_set_info_str(&s->nc, "connect to %s:%d",
-                          inet_ntoa(saddr_in.sin_addr),
-                          ntohs(saddr_in.sin_port));
-        break;
-    case SOCKET_ADDRESS_TYPE_UNIX:
-        qemu_set_info_str(&s->nc, " connect to %s", saddr_un.sun_path);
-        break;
-    case SOCKET_ADDRESS_TYPE_FD:
-        qemu_set_info_str(&s->nc, "connect to fd %d", fd);
-        break;
-    default:
-        g_assert_not_reached();
-    }
     return 0;
 }
 

index 5339585..e20be9c 100644
@@ -40,9 +40,11 @@ typedef struct NetDgramState {
     NetClientState nc;
     int fd;
     SocketReadState rs;
-    struct sockaddr_in dgram_dst; /* contains destination iff connectionless */
     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);

@@ -84,10 +86,8 @@ static ssize_t net_dgram_receive(NetClientState *nc,
     ssize_t ret;
 
     do {
-        if (s->dgram_dst.sin_family != AF_UNIX) {
-            ret = sendto(s->fd, buf, size, 0,
-                         (struct sockaddr *)&s->dgram_dst,
-                         sizeof(s->dgram_dst));
+        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);
         }

@@ -244,6 +244,9 @@ static void net_dgram_cleanup(NetClientState *nc)
         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 = {

@@ -260,7 +263,7 @@ static NetDgramState *net_dgram_fd_init(NetClientState *peer,
                                         SocketAddress *mcast,
                                         Error **errp)
 {
-    struct sockaddr_in saddr;
+    struct sockaddr_in *saddr = NULL;
     int newfd;
     NetClientState *nc;
     NetDgramState *s;

@@ -275,31 +278,32 @@ static NetDgramState *net_dgram_fd_init(NetClientState *peer,
     qapi_free_SocketAddress(sa);
 
     /*
-     * fd passed: multicast: "learn" dgram_dst address from bound address and
+     * 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
      */
 
     if (is_fd && mcast != NULL) {
-            if (convert_host_port(&saddr, mcast->u.inet.host,
-                                  mcast->u.inet.port, errp) < 0) {
+            saddr = g_new(struct sockaddr_in, 1);
+
+            if (convert_host_port(saddr, mcast->u.inet.host, mcast->u.inet.port,
+                                  errp) < 0) {
                 goto err;
             }
             /* must be bound */
-            if (saddr.sin_addr.s_addr == 0) {
+            if (saddr->sin_addr.s_addr == 0) {
                 error_setg(errp, "can't setup multicast destination address");
                 goto err;
             }
             /* clone dgram socket */
-            newfd = net_dgram_mcast_create(&saddr, NULL, errp);
+            newfd = net_dgram_mcast_create(saddr, NULL, errp);
             if (newfd < 0) {
                 goto err;
             }
             /* clone newfd to fd, close newfd */
             dup2(newfd, fd);
             close(newfd);
-
     }
 
     nc = qemu_new_net_client(&net_dgram_socket_info, peer, model, name);

@@ -311,21 +315,20 @@ static NetDgramState *net_dgram_fd_init(NetClientState *peer,
     net_dgram_read_poll(s, true);
 
     /* mcast: save bound address as dst */
-    if (is_fd && mcast != NULL) {
-        s->dgram_dst = saddr;
+    if (saddr) {
+        g_assert(s->dest_addr == NULL);
+        s->dest_addr = (struct sockaddr *)saddr;
+        s->dest_len = sizeof(*saddr);
         qemu_set_info_str(nc, "fd=%d (cloned mcast=%s:%d)", fd,
-                          inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
+                          inet_ntoa(saddr->sin_addr), ntohs(saddr->sin_port));
     } else {
-        if (sa_type == SOCKET_ADDRESS_TYPE_UNIX) {
-            s->dgram_dst.sin_family = AF_UNIX;
-        }
-
         qemu_set_info_str(nc, "fd=%d %s", fd, SocketAddressType_str(sa_type));
     }
 
     return s;
 
 err:
+    g_free(saddr);
     closesocket(fd);
     return NULL;
 }

@@ -339,21 +342,24 @@ static int net_dgram_mcast_init(NetClientState *peer,
 {
     NetDgramState *s;
     int fd, ret;
-    struct sockaddr_in saddr;
+    struct sockaddr_in *saddr;
 
     if (remote->type != SOCKET_ADDRESS_TYPE_INET) {
         error_setg(errp, "multicast only support inet type");
         return -1;
     }
 
-    if (convert_host_port(&saddr, remote->u.inet.host, remote->u.inet.port,
+    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);
+        fd = net_dgram_mcast_create(saddr, NULL, errp);
         if (fd < 0) {
+            g_free(saddr);
             return -1;
         }
     } else {

@@ -362,13 +368,15 @@ static int net_dgram_mcast_init(NetClientState *peer,
             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);
+            fd = net_dgram_mcast_create(saddr, &localaddr, errp);
             if (fd < 0) {
+                g_free(saddr);
                 return -1;
             }
             break;

@@ -376,16 +384,19 @@ static int net_dgram_mcast_init(NetClientState *peer,
         case SOCKET_ADDRESS_TYPE_FD:
             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;
             }
             break;
         default:
+            g_free(saddr);
             error_setg(errp, "only support inet or fd type for local");
             return -1;
         }

@@ -395,13 +406,17 @@ static int net_dgram_mcast_init(NetClientState *peer,
                           local->type == SOCKET_ADDRESS_TYPE_FD,
                           remote, errp);
     if (!s) {
+        g_free(saddr);
         return -1;
     }
 
-    s->dgram_dst = saddr;
+    g_assert(s->dest_addr == NULL);
+    s->dest_addr = (struct sockaddr *)saddr;
+    s->dest_len = sizeof(*saddr);
+
+    qemu_set_info_str(&s->nc, "mcast=%s:%d", inet_ntoa(saddr->sin_addr),
+                      ntohs(saddr->sin_port));
 
-    qemu_set_info_str(&s->nc, "mcast=%s:%d", inet_ntoa(saddr.sin_addr),
-                      ntohs(saddr.sin_port));
     return 0;
 
 }

@@ -412,9 +427,10 @@ int net_init_dgram(const Netdev *netdev, const char *name,
 {
     NetDgramState *s;
     int fd, ret;
-    struct sockaddr_in raddr_in;
-    struct sockaddr_in laddr_in;
     SocketAddress *remote, *local;
+    struct sockaddr *dest_addr;
+    struct sockaddr_in laddr_in, raddr_in;
+    socklen_t dest_len;
 
     assert(netdev->type == NET_CLIENT_DRIVER_DGRAM);
 

@@ -491,6 +507,10 @@ int net_init_dgram(const Netdev *netdev, const char *name,
             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_FD:
         fd = monitor_fd_param(monitor_cur(), local->u.fd.str, errp);

@@ -503,6 +523,8 @@ int net_init_dgram(const Netdev *netdev, const char *name,
                              name, fd);
             return -1;
         }
+        dest_addr = NULL;
+        dest_len = 0;
         break;
     default:
         error_setg(errp, "only support inet or fd type for local");

@@ -515,7 +537,9 @@ int net_init_dgram(const Netdev *netdev, const char *name,
     }
 
     if (remote) {
-        s->dgram_dst = raddr_in;
+        g_assert(s->dest_addr == NULL);
+        s->dest_addr = dest_addr;
+        s->dest_len = dest_len;
     }
 
     switch (local->type) {

index f5c0fad..f306ebe 100644
@@ -218,12 +218,22 @@ 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;
     }
 

index e20be9c..e581cc6 100644
@@ -259,52 +259,11 @@ static NetClientInfo net_dgram_socket_info = {
 static NetDgramState *net_dgram_fd_init(NetClientState *peer,
                                         const char *model,
                                         const char *name,
-                                        int fd, int is_fd,
-                                        SocketAddress *mcast,
+                                        int fd,
                                         Error **errp)
 {
-    struct sockaddr_in *saddr = NULL;
-    int newfd;
     NetClientState *nc;
     NetDgramState *s;
-    SocketAddress *sa;
-    SocketAddressType sa_type;
-
-    sa = socket_local_address(fd, errp);
-    if (!sa) {
-        return NULL;
-    }
-    sa_type = sa->type;
-    qapi_free_SocketAddress(sa);
-
-    /*
-     * 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
-     */
-
-    if (is_fd && mcast != NULL) {
-            saddr = g_new(struct sockaddr_in, 1);
-
-            if (convert_host_port(saddr, mcast->u.inet.host, mcast->u.inet.port,
-                                  errp) < 0) {
-                goto err;
-            }
-            /* must be bound */
-            if (saddr->sin_addr.s_addr == 0) {
-                error_setg(errp, "can't setup multicast destination address");
-                goto err;
-            }
-            /* clone dgram socket */
-            newfd = net_dgram_mcast_create(saddr, NULL, errp);
-            if (newfd < 0) {
-                goto err;
-            }
-            /* clone newfd to fd, close newfd */
-            dup2(newfd, fd);
-            close(newfd);
-    }
 
     nc = qemu_new_net_client(&net_dgram_socket_info, peer, model, name);
 

@@ -314,23 +273,7 @@ static NetDgramState *net_dgram_fd_init(NetClientState *peer,
     net_socket_rs_init(&s->rs, net_dgram_rs_finalize, false);
     net_dgram_read_poll(s, true);
 
-    /* mcast: save bound address as dst */
-    if (saddr) {
-        g_assert(s->dest_addr == NULL);
-        s->dest_addr = (struct sockaddr *)saddr;
-        s->dest_len = sizeof(*saddr);
-        qemu_set_info_str(nc, "fd=%d (cloned mcast=%s:%d)", fd,
-                          inet_ntoa(saddr->sin_addr), ntohs(saddr->sin_port));
-    } else {
-        qemu_set_info_str(nc, "fd=%d %s", fd, SocketAddressType_str(sa_type));
-    }
-
     return s;
-
-err:
-    g_free(saddr);
-    closesocket(fd);
-    return NULL;
 }
 
 static int net_dgram_mcast_init(NetClientState *peer,

@@ -381,7 +324,9 @@ static int net_dgram_mcast_init(NetClientState *peer,
             }
             break;
         }
-        case SOCKET_ADDRESS_TYPE_FD:
+        case SOCKET_ADDRESS_TYPE_FD: {
+            int newfd;
+
             fd = monitor_fd_param(monitor_cur(), local->u.fd.str, errp);
             if (fd == -1) {
                 g_free(saddr);

@@ -394,7 +339,42 @@ static int net_dgram_mcast_init(NetClientState *peer,
                                  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");

@@ -402,9 +382,7 @@ static int net_dgram_mcast_init(NetClientState *peer,
         }
     }
 
-    s = net_dgram_fd_init(peer, model, name, fd,
-                          local->type == SOCKET_ADDRESS_TYPE_FD,
-                          remote, errp);
+    s = net_dgram_fd_init(peer, model, name, fd, errp);
     if (!s) {
         g_free(saddr);
         return -1;

@@ -414,8 +392,26 @@ static int net_dgram_mcast_init(NetClientState *peer,
     s->dest_addr = (struct sockaddr *)saddr;
     s->dest_len = sizeof(*saddr);
 
-    qemu_set_info_str(&s->nc, "mcast=%s:%d", inet_ntoa(saddr->sin_addr),
-                      ntohs(saddr->sin_port));
+    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;
 

@@ -531,7 +527,7 @@ int net_init_dgram(const Netdev *netdev, const char *name,
         return -1;
     }
 
-    s = net_dgram_fd_init(peer, "dgram", name, fd, 0, NULL, errp);
+    s = net_dgram_fd_init(peer, "dgram", name, fd, errp);
     if (!s) {
         return -1;
     }

@@ -550,9 +546,22 @@ int net_init_dgram(const Netdev *netdev, const char *name,
                           inet_ntoa(raddr_in.sin_addr),
                           ntohs(raddr_in.sin_port));
         break;
-    case SOCKET_ADDRESS_TYPE_FD:
-        qemu_set_info_str(&s->nc, "fd=%d", fd);
+    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();
     }

index e9f696b..1fbf2f3 100644
@@ -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 +2535,17 @@ 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 (q->tx_bh && 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);
+        qemu_bh_schedule(q->tx_bh);
+        q->tx_waiting = 1;
+    }
 }
 
 /* TX */

index 2db160e..8ddafac 100644
@@ -1036,19 +1036,23 @@ 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;
         }
 

index 036745e..db4bedb 100644
@@ -65,6 +65,8 @@ 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);

87 lines not on this page · raw message

index a518f84..f5c0fad 100644
@@ -369,15 +369,27 @@ 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,

index c915778..ed8bdff 100644
@@ -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);
 

537 lines not on this page · raw message

index 1375738..67ca534 100644
@@ -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;

index f29a59c..840ad9d 100644
@@ -48,6 +48,7 @@
 #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"

@@ -1021,6 +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

@@ -1112,6 +1115,8 @@ void show_netdevs(void)
     int idx;
     const char *available_netdevs[] = {
         "socket",
+        "stream",
+        "dgram",
         "hubport",
         "tap",
 #ifdef CONFIG_SLIRP

@@ -1624,7 +1629,30 @@ void net_init_clients(void)
  */
 bool netdev_is_modern(const char *optarg)
 {
-    return false;
+    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;
+    }
+
+    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;
 }
 
 /*

425 lines not on this page · raw message

index 4bc3fd0..eebf29f 100644
@@ -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,

index 55023e7..025dbf1 100644
@@ -220,6 +220,8 @@ extern NICInfo nd_table[MAX_NICS];
 extern const char *host_net_devices[];
 
 /* from net.c */
+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);
 void net_init_clients(void);

87 lines not on this page · raw message

index e69aa43..99fb49c 100644
@@ -2801,7 +2801,11 @@ void qemu_init(int argc, char **argv)
                 break;
             case QEMU_OPTION_netdev:
                 default_net = 0;
-                net_client_parse(qemu_find_opts("netdev"), optarg);
+                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;

index 596d443..a518f84 100644
@@ -570,16 +570,16 @@ 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());
 }
 

index 6d64000..9c1b25d 100644
@@ -634,14 +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);

index e581cc6..9f7bf38 100644
@@ -426,6 +426,7 @@ int net_init_dgram(const Netdev *netdev, const char *name,
     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);

@@ -465,7 +466,8 @@ int net_init_dgram(const Netdev *netdev, const char *name,
         }
     } else {
         if (local->type != SOCKET_ADDRESS_TYPE_FD) {
-            error_setg(errp, "type=inet requires remote parameter");
+            error_setg(errp,
+                       "type=inet or type=unix requires remote parameter");
             return -1;
         }
     }

@@ -508,6 +510,53 @@ int net_init_dgram(const Netdev *netdev, const char *name,
         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) {

@@ -546,6 +595,10 @@ int net_init_dgram(const Netdev *netdev, const char *name,
                           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;

index 0a7e847..e4388fe 100644
@@ -360,8 +360,7 @@ static int net_stream_client_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");

index eebf29f..6d64000 100644
@@ -462,48 +462,6 @@ static NetClientInfo net_vhost_vdpa_cvq_info = {
 };
 
 /**
- * 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.
  *
  * Following QEMU guidelines, we offer a copy of the buffers to the device to

@@ -526,16 +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;

index db4bedb..214058d 100644
@@ -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);

@@ -141,5 +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 */

index bab86c5..01b789a 100644
@@ -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);
         }

index 83f4bd6..9f6f655 100644
@@ -1077,6 +1077,26 @@ 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("tcp:%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)
 {

index e4388fe..884f473 100644
@@ -235,7 +235,7 @@ static NetStreamState *net_stream_fd_init(NetClientState *peer,
 static void net_stream_accept(void *opaque)
 {
     NetStreamState *s = opaque;
-    struct sockaddr_in saddr;
+    struct sockaddr_storage saddr;
     socklen_t len;
     int fd;
 

@@ -253,8 +253,26 @@ static void net_stream_accept(void *opaque)
     s->fd = fd;
     s->nc.link_down = false;
     net_stream_connect(s);
-    qemu_set_info_str(&s->nc, "connection from %s:%d",
-                      inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
+    switch (saddr.ss_family) {
+    case AF_INET: {
+        struct sockaddr_in *saddr_in = (struct sockaddr_in *)&saddr;
+
+        qemu_set_info_str(&s->nc, "connection from %s:%d",
+                          inet_ntoa(saddr_in->sin_addr),
+                          ntohs(saddr_in->sin_port));
+        break;
+    }
+    case AF_UNIX: {
+        struct sockaddr_un saddr_un;
+
+        len = sizeof(saddr_un);
+        getsockname(s->listen_fd, (struct sockaddr *)&saddr_un, &len);
+        qemu_set_info_str(&s->nc, "connect from %s", saddr_un.sun_path);
+        break;
+    }
+    default:
+        g_assert_not_reached();
+    }
 }
 
 static int net_stream_server_init(NetClientState *peer,

@@ -294,6 +312,43 @@ static int net_stream_server_init(NetClientState *peer,
         }
         break;
     }
+    case SOCKET_ADDRESS_TYPE_UNIX: {
+        struct sockaddr_un saddr_un;
+
+        ret = unlink(addr->u.q_unix.path);
+        if (ret < 0 && errno != ENOENT) {
+            error_setg_errno(errp, errno, "failed to unlink socket %s",
+                             addr->u.q_unix.path);
+            return -1;
+        }
+
+        saddr_un.sun_family = PF_UNIX;
+        ret = snprintf(saddr_un.sun_path, sizeof(saddr_un.sun_path), "%s",
+                       addr->u.q_unix.path);
+        if (ret < 0 || ret >= sizeof(saddr_un.sun_path)) {
+            error_setg(errp, "UNIX socket path '%s' is too long",
+                       addr->u.q_unix.path);
+            error_append_hint(errp, "Path must be less than %zu bytes\n",
+                              sizeof(saddr_un.sun_path));
+            return -1;
+        }
+
+        fd = qemu_socket(PF_UNIX, SOCK_STREAM, 0);
+        if (fd < 0) {
+            error_setg_errno(errp, errno, "can't create stream socket");
+            return -1;
+        }
+        qemu_socket_set_nonblock(fd);
+
+        ret = bind(fd, (struct sockaddr *)&saddr_un, sizeof(saddr_un));
+        if (ret < 0) {
+            error_setg_errno(errp, errno, "can't create socket with path: %s",
+                             saddr_un.sun_path);
+            closesocket(fd);
+            return -1;
+        }
+        break;
+    }
     case SOCKET_ADDRESS_TYPE_FD:
         fd = monitor_fd_param(monitor_cur(), addr->u.fd.str, errp);
         if (fd == -1) {

@@ -337,6 +392,7 @@ static int net_stream_client_init(NetClientState *peer,
 {
     NetStreamState *s;
     struct sockaddr_in saddr_in;
+    struct sockaddr_un saddr_un;
     int fd, connected, ret;
 
     switch (addr->type) {

@@ -373,6 +429,45 @@ static int net_stream_client_init(NetClientState *peer,
             }
         }
         break;
+    case SOCKET_ADDRESS_TYPE_UNIX:
+        saddr_un.sun_family = PF_UNIX;
+        ret = snprintf(saddr_un.sun_path, sizeof(saddr_un.sun_path), "%s",
+                       addr->u.q_unix.path);
+        if (ret < 0 || ret >= sizeof(saddr_un.sun_path)) {
+            error_setg(errp, "UNIX socket path '%s' is too long",
+                       addr->u.q_unix.path);
+            error_append_hint(errp, "Path must be less than %zu bytes\n",
+                              sizeof(saddr_un.sun_path));
+            return -1;
+        }
+
+        fd = qemu_socket(PF_UNIX, SOCK_STREAM, 0);
+        if (fd < 0) {
+            error_setg_errno(errp, errno, "can't create stream socket");
+            return -1;
+        }
+        qemu_socket_set_nonblock(fd);
+
+        connected = 0;
+        for (;;) {
+            ret = connect(fd, (struct sockaddr *)&saddr_un, sizeof(saddr_un));
+            if (ret < 0) {
+                if (errno == EINTR || errno == EWOULDBLOCK) {
+                    /* continue */
+                } else if (errno == EAGAIN ||
+                           errno == EALREADY) {
+                    break;
+                } else {
+                    error_setg_errno(errp, errno, "can't connect socket");
+                    closesocket(fd);
+                    return -1;
+                }
+            } else {
+                connected = 1;
+                break;
+            }
+        }
+        break;
     case SOCKET_ADDRESS_TYPE_FD:
         fd = monitor_fd_param(monitor_cur(), addr->u.fd.str, errp);
         if (fd == -1) {

@@ -387,7 +482,7 @@ static int net_stream_client_init(NetClientState *peer,
         connected = 1;
         break;
     default:
-        error_setg(errp, "only support inet or fd type");
+        error_setg(errp, "only support inet, unix or fd type");
         return -1;
     }
 

@@ -399,13 +494,15 @@ static int net_stream_client_init(NetClientState *peer,
                           inet_ntoa(saddr_in.sin_addr),
                           ntohs(saddr_in.sin_port));
         break;
+    case SOCKET_ADDRESS_TYPE_UNIX:
+        qemu_set_info_str(&s->nc, " connect to %s", saddr_un.sun_path);
+        break;
     case SOCKET_ADDRESS_TYPE_FD:
         qemu_set_info_str(&s->nc, "connect to fd %d", fd);
         break;
     default:
         g_assert_not_reached();
     }
-
     return 0;
 }
 

index 9f6f655..a9926af 100644
@@ -1090,7 +1090,7 @@ char *socket_uri(SocketAddress *addr)
     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",
+        return g_strdup_printf("vsock:%s:%s",
                                addr->u.vsock.cid,
                                addr->u.vsock.port);
     default:

@@ -1124,6 +1124,11 @@ 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)) {

index 81d0b21..c1c34a5 100644
@@ -222,7 +222,7 @@ extern const char *host_net_devices[];
 /* from net.c */
 int 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);

index 407bdd1..5e78880 100644
@@ -1566,27 +1566,21 @@ out:
     return ret;
 }
 
-int net_init_clients(Error **errp)
+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;
-    }
-
-    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)

index b464da2..a4ae131 100644
@@ -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);
 

index 54c67e1..53b7040 100644
@@ -38,6 +38,7 @@
 #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;

@@ -168,6 +169,8 @@ static gboolean net_stream_send(QIOChannel *ioc,
         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;

@@ -244,6 +247,7 @@ static void net_stream_listen(QIONetListener *listener,
     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);
 }
 

@@ -335,6 +339,7 @@ static void net_stream_client_connected(QIOTask *task, gpointer opaque)
     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;

index c1c34a5..55023e7 100644
@@ -220,7 +220,7 @@ 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);
+void net_client_parse(QemuOptsList *opts_list, const char *str);
 void show_netdevs(void);
 void net_init_clients(void);
 void net_check_clients(void);

index 5e78880..178257a 100644
@@ -1583,13 +1583,11 @@ void net_init_clients(void)
                       &error_fatal);
 }
 
-int net_client_parse(QemuOptsList *opts_list, const char *optarg)
+void net_client_parse(QemuOptsList *opts_list, const char *optarg)
 {
     if (!qemu_opts_parse_noisily(opts_list, optarg, true)) {
-        return -1;
+        exit(1);
     }
-
-    return 0;
 }
 
 /* From FreeBSD */

index a4ae131..e69aa43 100644
@@ -2801,21 +2801,15 @@ 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);
-                }
+                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:

index 5c815b4..7d92c2d 100644
@@ -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);

index 025dbf1..3db75ff 100644
@@ -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);

index af373e5..350041a 100644
@@ -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);

index 128a90f..f29a59c 100644
@@ -141,13 +141,20 @@ 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};

index 8679be6..14a8d59 100644
@@ -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);
 

index bfd8596..ade1ecf 100644
@@ -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,

@@ -597,9 +595,8 @@ 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 +639,8 @@ 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 +693,8 @@ 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;
 }
 

index 7466f22..a49c28b 100644
@@ -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;
 

index e203d07..1210a04 100644
@@ -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);

index 1083916..c0a0866 100644
@@ -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);
 

index b1a0247..3a6b90d 100644
@@ -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;

index 9c1b25d..854ebd61 100644
@@ -544,7 +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;

index ade1ecf..4944bb7 100644
@@ -577,8 +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");