Merge remote-tracking branch 'stefanha/net' into staging

* stefanha/net:
  net: EAGAIN handling for net/socket.c TCP
  net: EAGAIN handling for net/socket.c UDP
  net: asynchronous send/receive infrastructure for net/socket.c
  net: broadcast hub packets if at least one port can receive
  net: fix usbnet_receive() packet drops
  net: clean up usbnet_receive()
  net: add -netdev options to man page
  net: do not report queued packets as sent
  net: add receive_disabled logic to iov delivery path
  eepro100: Fix network hang when rx buffers run out
  xen: flush queue when getting an event
  e1000: flush queue whenever can_receive can go from false to true
  net: notify iothread after flushing queue

11 files changed, 186 insertions, 63 deletions

diff --git a/hw/e1000.c b/hw/e1000.c
index ae8a6c5..ec3a7c4 100644
--- a/hw/e1000.c
+++ b/hw/e1000.c
@@ -295,6 +295,7 @@ set_rx_control(E1000State *s, int index, uint32_t val)
     s->rxbuf_min_shift = ((val / E1000_RCTL_RDMTS_QUAT) & 3) + 1;
     DBGOUT(RX, "RCTL: %d, mac_reg[RCTL] = 0x%x\n", s->mac_reg[RDT],
            s->mac_reg[RCTL]);
+    qemu_flush_queued_packets(&s->nic->nc);
 }
 
 static void
@@ -926,6 +927,9 @@ set_rdt(E1000State *s, int index, uint32_t val)
 {
     s->check_rxov = 0;
     s->mac_reg[index] = val & 0xffff;
+    if (e1000_has_rxbufs(s, 1)) {
+        qemu_flush_queued_packets(&s->nic->nc);
+    }
 }
 
 static void
diff --git a/hw/eepro100.c b/hw/eepro100.c
index 50d117e..5b23116 100644
--- a/hw/eepro100.c
+++ b/hw/eepro100.c
@@ -1036,6 +1036,7 @@ static void eepro100_ru_command(EEPRO100State * s, uint8_t val)
         }
         set_ru_state(s, ru_ready);
         s->ru_offset = e100_read_reg4(s, SCBPointer);
+        qemu_flush_queued_packets(&s->nic->nc);
         TRACE(OTHER, logout("val=0x%02x (rx start)\n", val));
         break;
     case RX_RESUME:
@@ -1770,7 +1771,8 @@ static ssize_t nic_receive(NetClientState *nc, const uint8_t * buf, size_t size)
     if (rfd_command & COMMAND_EL) {
         /* EL bit is set, so this was the last frame. */
         logout("receive: Running out of frames\n");
-        set_ru_state(s, ru_suspended);
+        set_ru_state(s, ru_no_resources);
+        eepro100_rnr_interrupt(s);
     }
     if (rfd_command & COMMAND_S) {
         /* S bit is set. */
diff --git a/hw/usb/dev-network.c b/hw/usb/dev-network.c
index c84892c..e4a4359 100644
--- a/hw/usb/dev-network.c
+++ b/hw/usb/dev-network.c
@@ -1001,6 +1001,13 @@ static int rndis_keepalive_response(USBNetState *s,
     return 0;
 }
 
+/* Prepare to receive the next packet */
+static void usb_net_reset_in_buf(USBNetState *s)
+{
+    s->in_ptr = s->in_len = 0;
+    qemu_flush_queued_packets(&s->nic->nc);
+}
+
 static int rndis_parse(USBNetState *s, uint8_t *data, int length)
 {
     uint32_t msg_type;
@@ -1025,7 +1032,8 @@ static int rndis_parse(USBNetState *s, uint8_t *data, int length)
 
     case RNDIS_RESET_MSG:
         rndis_clear_responsequeue(s);
-        s->out_ptr = s->in_ptr = s->in_len = 0;
+        s->out_ptr = 0;
+        usb_net_reset_in_buf(s);
         return rndis_reset_response(s, (rndis_reset_msg_type *) data);
 
     case RNDIS_KEEPALIVE_MSG:
@@ -1135,7 +1143,7 @@ static int usb_net_handle_datain(USBNetState *s, USBPacket *p)
     int ret = USB_RET_NAK;
 
     if (s->in_ptr > s->in_len) {
-        s->in_ptr = s->in_len = 0;
+        usb_net_reset_in_buf(s);
         ret = USB_RET_NAK;
         return ret;
     }
@@ -1152,7 +1160,7 @@ static int usb_net_handle_datain(USBNetState *s, USBPacket *p)
     if (s->in_ptr >= s->in_len &&
                     (is_rndis(s) || (s->in_len & (64 - 1)) || !ret)) {
         /* no short packet necessary */
-        s->in_ptr = s->in_len = 0;
+        usb_net_reset_in_buf(s);
     }
 
 #ifdef TRAFFIC_DEBUG
@@ -1250,20 +1258,32 @@ static int usb_net_handle_data(USBDevice *dev, USBPacket *p)
 static ssize_t usbnet_receive(NetClientState *nc, const uint8_t *buf, size_t size)
 {
     USBNetState *s = DO_UPCAST(NICState, nc, nc)->opaque;
-    struct rndis_packet_msg_type *msg;
+    uint8_t *in_buf = s->in_buf;
+    size_t total_size = size;
 
     if (is_rndis(s)) {
-        msg = (struct rndis_packet_msg_type *) s->in_buf;
         if (s->rndis_state != RNDIS_DATA_INITIALIZED) {
             return -1;
         }
-        if (size + sizeof(struct rndis_packet_msg_type) > sizeof(s->in_buf))
-            return -1;
+        total_size += sizeof(struct rndis_packet_msg_type);
+    }
+    if (total_size > sizeof(s->in_buf)) {
+        return -1;
+    }
 
+    /* Only accept packet if input buffer is empty */
+    if (s->in_len > 0) {
+        return 0;
+    }
+
+    if (is_rndis(s)) {
+        struct rndis_packet_msg_type *msg;
+
+        msg = (struct rndis_packet_msg_type *)in_buf;
         memset(msg, 0, sizeof(struct rndis_packet_msg_type));
         msg->MessageType = cpu_to_le32(RNDIS_PACKET_MSG);
-        msg->MessageLength = cpu_to_le32(size + sizeof(struct rndis_packet_msg_type));
-        msg->DataOffset = cpu_to_le32(sizeof(struct rndis_packet_msg_type) - 8);
+        msg->MessageLength = cpu_to_le32(size + sizeof(*msg));
+        msg->DataOffset = cpu_to_le32(sizeof(*msg) - 8);
         msg->DataLength = cpu_to_le32(size);
         /* msg->OOBDataOffset;
          * msg->OOBDataLength;
@@ -1273,14 +1293,11 @@ static ssize_t usbnet_receive(NetClientState *nc, const uint8_t *buf, size_t siz
          * msg->VcHandle;
          * msg->Reserved;
          */
-        memcpy(msg + 1, buf, size);
-        s->in_len = size + sizeof(struct rndis_packet_msg_type);
-    } else {
-        if (size > sizeof(s->in_buf))
-            return -1;
-        memcpy(s->in_buf, buf, size);
-        s->in_len = size;
+        in_buf += sizeof(*msg);
     }
+
+    memcpy(in_buf, buf, size);
+    s->in_len = total_size;
     s->in_ptr = 0;
     return size;
 }
diff --git a/hw/virtio-net.c b/hw/virtio-net.c
index b1998b2..6490743 100644
--- a/hw/virtio-net.c
+++ b/hw/virtio-net.c
@@ -447,10 +447,6 @@ static void virtio_net_handle_rx(VirtIODevice *vdev, VirtQueue *vq)
     VirtIONet *n = to_virtio_net(vdev);
 
     qemu_flush_queued_packets(&n->nic->nc);
-
-    /* We now have RX buffers, signal to the IO thread to break out of the
-     * select to re-poll the tap file descriptor */
-    qemu_notify_event();
 }
 
 static int virtio_net_can_receive(NetClientState *nc)
diff --git a/hw/xen_nic.c b/hw/xen_nic.c
index 8b79bfb..cf7d559 100644
--- a/hw/xen_nic.c
+++ b/hw/xen_nic.c
@@ -415,6 +415,7 @@ static void net_event(struct XenDevice *xendev)
 {
     struct XenNetDev *netdev = container_of(xendev, struct XenNetDev, xendev);
     net_tx_packets(netdev);
+    qemu_flush_queued_packets(&netdev->nic->nc);
 }
 
 static int net_free(struct XenDevice *xendev)
diff --git a/net.c b/net.c
index e5d25d4..a187a7b 100644
--- a/net.c
+++ b/net.c
@@ -357,7 +357,12 @@ void qemu_flush_queued_packets(NetClientState *nc)
 {
     nc->receive_disabled = 0;
 
-    qemu_net_queue_flush(nc->send_queue);
+    if (qemu_net_queue_flush(nc->send_queue)) {
+        /* We emptied the queue successfully, signal to the IO thread to repoll
+         * the file descriptor (for tap, for example).
+         */
+        qemu_notify_event();
+    }
 }
 
 static ssize_t qemu_send_packet_async_with_flags(NetClientState *sender,
@@ -418,16 +423,27 @@ ssize_t qemu_deliver_packet_iov(NetClientState *sender,
                                 void *opaque)
 {
     NetClientState *nc = opaque;
+    int ret;
 
     if (nc->link_down) {
         return iov_size(iov, iovcnt);
     }
 
+    if (nc->receive_disabled) {
+        return 0;
+    }
+
     if (nc->info->receive_iov) {
-        return nc->info->receive_iov(nc, iov, iovcnt);
+        ret = nc->info->receive_iov(nc, iov, iovcnt);
     } else {
-        return nc_sendv_compat(nc, iov, iovcnt);
+        ret = nc_sendv_compat(nc, iov, iovcnt);
     }
+
+    if (ret == 0) {
+        nc->receive_disabled = 1;
+    }
+
+    return ret;
 }
 
 ssize_t qemu_sendv_packet_async(NetClientState *sender,
diff --git a/net/hub.c b/net/hub.c
index ac157e3..650a8b4 100644
--- a/net/hub.c
+++ b/net/hub.c
@@ -97,12 +97,12 @@ static int net_hub_port_can_receive(NetClientState *nc)
             continue;
         }
 
-        if (!qemu_can_send_packet(&port->nc)) {
-            return 0;
+        if (qemu_can_send_packet(&port->nc)) {
+            return 1;
         }
     }
 
-    return 1;
+    return 0;
 }
 
 static ssize_t net_hub_port_receive(NetClientState *nc,
diff --git a/net/queue.c b/net/queue.c
index e8030aa..254f280 100644
--- a/net/queue.c
+++ b/net/queue.c
@@ -83,12 +83,12 @@ void qemu_del_net_queue(NetQueue *queue)
     g_free(queue);
 }
 
-static ssize_t qemu_net_queue_append(NetQueue *queue,
-                                     NetClientState *sender,
-                                     unsigned flags,
-                                     const uint8_t *buf,
-                                     size_t size,
-                                     NetPacketSent *sent_cb)
+static void qemu_net_queue_append(NetQueue *queue,
+                                  NetClientState *sender,
+                                  unsigned flags,
+                                  const uint8_t *buf,
+                                  size_t size,
+                                  NetPacketSent *sent_cb)
 {
     NetPacket *packet;
 
@@ -100,16 +100,14 @@ static ssize_t qemu_net_queue_append(NetQueue *queue,
     memcpy(packet->data, buf, size);
 
     QTAILQ_INSERT_TAIL(&queue->packets, packet, entry);
-
-    return size;
 }
 
-static ssize_t qemu_net_queue_append_iov(NetQueue *queue,
-                                         NetClientState *sender,
-                                         unsigned flags,
-                                         const struct iovec *iov,
-                                         int iovcnt,
-                                         NetPacketSent *sent_cb)
+static void qemu_net_queue_append_iov(NetQueue *queue,
+                                      NetClientState *sender,
+                                      unsigned flags,
+                                      const struct iovec *iov,
+                                      int iovcnt,
+                                      NetPacketSent *sent_cb)
 {
     NetPacket *packet;
     size_t max_len = 0;
@@ -133,8 +131,6 @@ static ssize_t qemu_net_queue_append_iov(NetQueue *queue,
     }
 
     QTAILQ_INSERT_TAIL(&queue->packets, packet, entry);
-
-    return packet->size;
 }
 
 static ssize_t qemu_net_queue_deliver(NetQueue *queue,
@@ -177,7 +173,8 @@ ssize_t qemu_net_queue_send(NetQueue *queue,
     ssize_t ret;
 
     if (queue->delivering || !qemu_can_send_packet(sender)) {
-        return qemu_net_queue_append(queue, sender, flags, data, size, sent_cb);
+        qemu_net_queue_append(queue, sender, flags, data, size, sent_cb);
+        return 0;
     }
 
     ret = qemu_net_queue_deliver(queue, sender, flags, data, size);
@@ -201,8 +198,8 @@ ssize_t qemu_net_queue_send_iov(NetQueue *queue,
     ssize_t ret;
 
     if (queue->delivering || !qemu_can_send_packet(sender)) {
-        return qemu_net_queue_append_iov(queue, sender, flags,
-                                         iov, iovcnt, sent_cb);
+        qemu_net_queue_append_iov(queue, sender, flags, iov, iovcnt, sent_cb);
+        return 0;
     }
 
     ret = qemu_net_queue_deliver_iov(queue, sender, flags, iov, iovcnt);
@@ -228,7 +225,7 @@ void qemu_net_queue_purge(NetQueue *queue, NetClientState *from)
     }
 }
 
-void qemu_net_queue_flush(NetQueue *queue)
+bool qemu_net_queue_flush(NetQueue *queue)
 {
     while (!QTAILQ_EMPTY(&queue->packets)) {
         NetPacket *packet;
@@ -244,7 +241,7 @@ void qemu_net_queue_flush(NetQueue *queue)
                                      packet->size);
         if (ret == 0) {
             QTAILQ_INSERT_HEAD(&queue->packets, packet, entry);
-            break;
+            return false;
         }
 
         if (packet->sent_cb) {
@@ -253,4 +250,5 @@ void qemu_net_queue_flush(NetQueue *queue)
 
         g_free(packet);
     }
+    return true;
 }
diff --git a/net/queue.h b/net/queue.h
index 9d44a9b..fc02b33 100644
--- a/net/queue.h
+++ b/net/queue.h
@@ -53,6 +53,6 @@ ssize_t qemu_net_queue_send_iov(NetQueue *queue,
                                 NetPacketSent *sent_cb);
 
 void qemu_net_queue_purge(NetQueue *queue, NetClientState *from);
-void qemu_net_queue_flush(NetQueue *queue);
+bool qemu_net_queue_flush(NetQueue *queue);
 
 #endif /* QEMU_NET_QUEUE_H */
diff --git a/net/socket.c b/net/socket.c
index 7c602e4..5e0c92e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -32,6 +32,7 @@
 #include "qemu-error.h"
 #include "qemu-option.h"
 #include "qemu_socket.h"
+#include "iov.h"
 
 typedef struct NetSocketState {
     NetClientState nc;
@@ -40,29 +41,106 @@ typedef struct NetSocketState {
     int state; /* 0 = getting length, 1 = getting data */
     unsigned int index;
     unsigned int packet_len;
+    unsigned int send_index;      /* number of bytes sent (only SOCK_STREAM) */
     uint8_t buf[4096];
     struct sockaddr_in dgram_dst; /* contains inet host and port destination iff connectionless (SOCK_DGRAM) */
+    IOHandler *send_fn;           /* differs between SOCK_STREAM/SOCK_DGRAM */
+    bool read_poll;               /* waiting to receive data? */
+    bool write_poll;              /* waiting to transmit data? */
 } NetSocketState;
 
 static void net_socket_accept(void *opaque);
+static void net_socket_writable(void *opaque);
+
+/* Only read packets from socket when peer can receive them */
+static int net_socket_can_send(void *opaque)
+{
+    NetSocketState *s = opaque;
+
+    return qemu_can_send_packet(&s->nc);
+}
+
+static void net_socket_update_fd_handler(NetSocketState *s)
+{
+    qemu_set_fd_handler2(s->fd,
+                         s->read_poll  ? net_socket_can_send : NULL,
+                         s->read_poll  ? s->send_fn : NULL,
+                         s->write_poll ? net_socket_writable : NULL,
+                         s);
+}
+
+static void net_socket_read_poll(NetSocketState *s, bool enable)
+{
+    s->read_poll = enable;
+    net_socket_update_fd_handler(s);
+}
+
+static void net_socket_write_poll(NetSocketState *s, bool enable)
+{
+    s->write_poll = enable;
+    net_socket_update_fd_handler(s);
+}
+
+static void net_socket_writable(void *opaque)
+{
+    NetSocketState *s = opaque;
+
+    net_socket_write_poll(s, false);
+
+    qemu_flush_queued_packets(&s->nc);
+}
 
-/* XXX: we consider we can send the whole packet without blocking */
 static ssize_t net_socket_receive(NetClientState *nc, const uint8_t *buf, size_t size)
 {
     NetSocketState *s = DO_UPCAST(NetSocketState, nc, nc);
-    uint32_t len;
-    len = htonl(size);
-
-    send_all(s->fd, (const uint8_t *)&len, sizeof(len));
-    return send_all(s->fd, buf, size);
+    uint32_t len = htonl(size);
+    struct iovec iov[] = {
+        {
+            .iov_base = &len,
+            .iov_len  = sizeof(len),
+        }, {
+            .iov_base = (void *)buf,
+            .iov_len  = size,
+        },
+    };
+    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) {
+        ret = 0; /* handled further down */
+    }
+    if (ret == -1) {
+        s->send_index = 0;
+        return -errno;
+    }
+    if (ret < (ssize_t)remaining) {
+        s->send_index += ret;
+        net_socket_write_poll(s, true);
+        return 0;
+    }
+    s->send_index = 0;
+    return size;
 }
 
 static ssize_t net_socket_receive_dgram(NetClientState *nc, const uint8_t *buf, size_t size)
 {
     NetSocketState *s = DO_UPCAST(NetSocketState, nc, nc);
+    ssize_t ret;
+
+    do {
+        ret = sendto(s->fd, buf, size, 0,
+                     (struct sockaddr *)&s->dgram_dst,
+                     sizeof(s->dgram_dst));
+    } while (ret == -1 && errno == EINTR);
 
-    return sendto(s->fd, (const void *)buf, size, 0,
-                  (struct sockaddr *)&s->dgram_dst, sizeof(s->dgram_dst));
+    if (ret == -1 && errno == EAGAIN) {
+        net_socket_write_poll(s, true);
+        return 0;
+    }
+    return ret;
 }
 
 static void net_socket_send(void *opaque)
@@ -81,7 +159,8 @@ static void net_socket_send(void *opaque)
     } else if (size == 0) {
         /* end of connection */
     eoc:
-        qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
+        net_socket_read_poll(s, false);
+        net_socket_write_poll(s, false);
         if (s->listen_fd != -1) {
             qemu_set_fd_handler(s->listen_fd, net_socket_accept, NULL, s);
         }
@@ -152,7 +231,8 @@ static void net_socket_send_dgram(void *opaque)
         return;
     if (size == 0) {
         /* end of connection */
-        qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
+        net_socket_read_poll(s, false);
+        net_socket_write_poll(s, false);
         return;
     }
     qemu_send_packet(&s->nc, s->buf, size);
@@ -243,7 +323,8 @@ static void net_socket_cleanup(NetClientState *nc)
 {
     NetSocketState *s = DO_UPCAST(NetSocketState, nc, nc);
     if (s->fd != -1) {
-        qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
+        net_socket_read_poll(s, false);
+        net_socket_write_poll(s, false);
         close(s->fd);
         s->fd = -1;
     }
@@ -314,8 +395,8 @@ static NetSocketState *net_socket_fd_init_dgram(NetClientState *peer,
 
     s->fd = fd;
     s->listen_fd = -1;
-
-    qemu_set_fd_handler(s->fd, net_socket_send_dgram, NULL, s);
+    s->send_fn = net_socket_send_dgram;
+    net_socket_read_poll(s, true);
 
     /* mcast: save bound address as dst */
     if (is_connected) {
@@ -332,7 +413,8 @@ err:
 static void net_socket_connect(void *opaque)
 {
     NetSocketState *s = opaque;
-    qemu_set_fd_handler(s->fd, net_socket_send, NULL, s);
+    s->send_fn = net_socket_send;
+    net_socket_read_poll(s, true);
 }
 
 static NetClientInfo net_socket_info = {
diff --git a/qemu-options.hx b/qemu-options.hx
index 5f96f35..09c86c4 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -1362,6 +1362,7 @@ Valid values for @var{type} are
 Not all devices are supported on all targets.  Use -net nic,model=?
 for a list of available devices for your target.
 
+@item -netdev user,id=@var{id}[,@var{option}][,@var{option}][,...]
 @item -net user[,@var{option}][,@var{option}][,...]
 Use the user mode network stack which requires no administrator
 privilege to run. Valid options are:
@@ -1370,6 +1371,7 @@ privilege to run. Valid options are:
 @item vlan=@var{n}
 Connect user mode stack to VLAN @var{n} (@var{n} = 0 is the default).
 
+@item id=@var{id}
 @item name=@var{name}
 Assign symbolic name for use in monitor commands.
 
@@ -1495,6 +1497,7 @@ processed and applied to -net user. Mixing them with the new configuration
 syntax gives undefined results. Their use for new applications is discouraged
 as they will be removed from future versions.
 
+@item -netdev tap,id=@var{id}[,fd=@var{h}][,ifname=@var{name}][,script=@var{file}][,downscript=@var{dfile}][,helper=@var{helper}]
 @item -net tap[,vlan=@var{n}][,name=@var{name}][,fd=@var{h}][,ifname=@var{name}][,script=@var{file}][,downscript=@var{dfile}][,helper=@var{helper}]
 Connect the host TAP network interface @var{name} to VLAN @var{n}.
 
@@ -1534,6 +1537,7 @@ qemu-system-i386 linux.img \
                  -net nic -net tap,"helper=/usr/local/libexec/qemu-bridge-helper"
 @end example
 
+@item -netdev bridge,id=@var{id}[,br=@var{bridge}][,helper=@var{helper}]
 @item -net bridge[,vlan=@var{n}][,name=@var{name}][,br=@var{bridge}][,helper=@var{helper}]
 Connect a host TAP network interface to a host bridge device.
 
@@ -1556,6 +1560,7 @@ qemu-system-i386 linux.img -net bridge -net nic,model=virtio
 qemu-system-i386 linux.img -net bridge,br=qemubr0 -net nic,model=virtio
 @end example
 
+@item -netdev socket,id=@var{id}[,fd=@var{h}][,listen=[@var{host}]:@var{port}][,connect=@var{host}:@var{port}]
 @item -net socket[,vlan=@var{n}][,name=@var{name}][,fd=@var{h}] [,listen=[@var{host}]:@var{port}][,connect=@var{host}:@var{port}]
 
 Connect the VLAN @var{n} to a remote VLAN in another QEMU virtual
@@ -1578,6 +1583,7 @@ qemu-system-i386 linux.img \
                  -net socket,connect=127.0.0.1:1234
 @end example
 
+@item -netdev socket,id=@var{id}[,fd=@var{h}][,mcast=@var{maddr}:@var{port}[,localaddr=@var{addr}]]
 @item -net socket[,vlan=@var{n}][,name=@var{name}][,fd=@var{h}][,mcast=@var{maddr}:@var{port}[,localaddr=@var{addr}]]
 
 Create a VLAN @var{n} shared with another QEMU virtual
@@ -1629,6 +1635,7 @@ qemu-system-i386 linux.img \
                  -net socket,mcast=239.192.168.1:1102,localaddr=1.2.3.4
 @end example
 
+@item -netdev vde,id=@var{id}[,sock=@var{socketpath}][,port=@var{n}][,group=@var{groupname}][,mode=@var{octalmode}]
 @item -net vde[,vlan=@var{n}][,name=@var{name}][,sock=@var{socketpath}] [,port=@var{n}][,group=@var{groupname}][,mode=@var{octalmode}]
 Connect VLAN @var{n} to PORT @var{n} of a vde switch running on host and
 listening for incoming connections on @var{socketpath}. Use GROUP @var{groupname}