Merge tag 'net-pull-request' of https://github.com/jasowang/qemu into staging

# -----BEGIN PGP SIGNATURE-----
#
# iQEzBAABCAAdFiEEIV1G9IJGaJ7HfzVi7wSWWzmNYhEFAmasTgwACgkQ7wSWWzmN
# YhFUtAgAq45v7fQJ7cKKwRam/VrIkxT5cM59ODwzLSL9kPWfL6f/bJ7xM/zvLyvn
# LNBXFWWu+eNKA73f95cckZwaqZ4U6giGbiesCACn1IpgVtieLS+Lq78jsifKIAsR
# yxFvbT9oLhU0dZ1Up3+isc6V+jeAE4ZYu4KOiIt7PscTEzkJl+vSUjN4X9rRVtUD
# PzONUacL6MoTJtX8UZJZXNzLN9JTsN39Gx+LSDGQ27MDmDvE3R9BW+T0ZgF9JQZ7
# wnrL5sharqF3gxa7X55fPBI1qwY5gWcH0yyJpRdM8guA13vhtvlrhNSypip9eKWi
# HtPHUTKEB5YOvF236WRiuQPIm/GNpA==
# =7HGN
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 02 Aug 2024 01:10:04 PM AEST
# gpg:                using RSA key 215D46F48246689EC77F3562EF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>" [undefined]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 215D 46F4 8246 689E C77F  3562 EF04 965B 398D 6211

* tag 'net-pull-request' of https://github.com/jasowang/qemu:
  net: Reinstate '-net nic, model=help' output as documented in man page
  net: update netdev stream man page with the reconnect parameter
  net: update netdev dgram man page with unix socket
  net: update netdev stream man page with unix socket
  net: update netdev stream/dgram man page
  virtio-net: Fix network stall at the host side waiting for kick
  virtio-net: Ensure queue index fits with RSS
  rtl8139: Fix behaviour for old kernels.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

6 files changed, 310 insertions, 24 deletions

diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index 897c86e..03a204e 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -2738,7 +2738,11 @@ static void rtl8139_io_writeb(void *opaque, uint8_t addr, uint32_t val)
             }
 
             break;
-
+        case RxConfig:
+            DPRINTF("RxConfig write(b) val=0x%02x\n", val);
+            rtl8139_RxConfig_write(s,
+                (rtl8139_RxConfig_read(s) & 0xFFFFFF00) | val);
+            break;
         default:
             DPRINTF("not implemented write(b) addr=0x%x val=0x%02x\n", addr,
                 val);
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 8f30972..08aa0b6 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -1641,24 +1641,28 @@ static bool virtio_net_can_receive(NetClientState *nc)
 
 static int virtio_net_has_buffers(VirtIONetQueue *q, int bufsize)
 {
+    int opaque;
+    unsigned int in_bytes;
     VirtIONet *n = q->n;
-    if (virtio_queue_empty(q->rx_vq) ||
-        (n->mergeable_rx_bufs &&
-         !virtqueue_avail_bytes(q->rx_vq, bufsize, 0))) {
-        virtio_queue_set_notification(q->rx_vq, 1);
-
-        /* To avoid a race condition where the guest has made some buffers
-         * available after the above check but before notification was
-         * enabled, check for available buffers again.
-         */
-        if (virtio_queue_empty(q->rx_vq) ||
-            (n->mergeable_rx_bufs &&
-             !virtqueue_avail_bytes(q->rx_vq, bufsize, 0))) {
+
+    while (virtio_queue_empty(q->rx_vq) || n->mergeable_rx_bufs) {
+        opaque = virtqueue_get_avail_bytes(q->rx_vq, &in_bytes, NULL,
+                                           bufsize, 0);
+        /* Buffer is enough, disable notifiaction */
+        if (bufsize <= in_bytes) {
+            break;
+        }
+
+        if (virtio_queue_enable_notification_and_check(q->rx_vq, opaque)) {
+            /* Guest has added some buffers, try again */
+            continue;
+        } else {
             return 0;
         }
     }
 
     virtio_queue_set_notification(q->rx_vq, 0);
+
     return 1;
 }
 
@@ -1905,7 +1909,8 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
     if (!no_rss && n->rss_data.enabled && n->rss_data.enabled_software_rss) {
         int index = virtio_net_process_rss(nc, buf, size, &extra_hdr);
         if (index >= 0) {
-            NetClientState *nc2 = qemu_get_subqueue(n->nic, index);
+            NetClientState *nc2 =
+                qemu_get_subqueue(n->nic, index % n->curr_queue_pairs);
             return virtio_net_receive_rcu(nc2, buf, size, true);
         }
     }
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index 397c261..9e10cbc 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -744,6 +744,60 @@ int virtio_queue_empty(VirtQueue *vq)
     }
 }
 
+static bool virtio_queue_split_poll(VirtQueue *vq, unsigned shadow_idx)
+{
+    if (unlikely(!vq->vring.avail)) {
+        return false;
+    }
+
+    return (uint16_t)shadow_idx != vring_avail_idx(vq);
+}
+
+static bool virtio_queue_packed_poll(VirtQueue *vq, unsigned shadow_idx)
+{
+    VRingPackedDesc desc;
+    VRingMemoryRegionCaches *caches;
+
+    if (unlikely(!vq->vring.desc)) {
+        return false;
+    }
+
+    caches = vring_get_region_caches(vq);
+    if (!caches) {
+        return false;
+    }
+
+    vring_packed_desc_read(vq->vdev, &desc, &caches->desc,
+                           shadow_idx, true);
+
+    return is_desc_avail(desc.flags, vq->shadow_avail_wrap_counter);
+}
+
+static bool virtio_queue_poll(VirtQueue *vq, unsigned shadow_idx)
+{
+    if (virtio_device_disabled(vq->vdev)) {
+        return false;
+    }
+
+    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) {
+        return virtio_queue_packed_poll(vq, shadow_idx);
+    } else {
+        return virtio_queue_split_poll(vq, shadow_idx);
+    }
+}
+
+bool virtio_queue_enable_notification_and_check(VirtQueue *vq,
+                                                int opaque)
+{
+    virtio_queue_set_notification(vq, 1);
+
+    if (opaque >= 0) {
+        return virtio_queue_poll(vq, (unsigned)opaque);
+    } else {
+        return false;
+    }
+}
+
 static void virtqueue_unmap_sg(VirtQueue *vq, const VirtQueueElement *elem,
                                unsigned int len)
 {
@@ -1442,9 +1496,9 @@ err:
     goto done;
 }
 
-void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes,
-                               unsigned int *out_bytes,
-                               unsigned max_in_bytes, unsigned max_out_bytes)
+int virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes,
+                              unsigned int *out_bytes, unsigned max_in_bytes,
+                              unsigned max_out_bytes)
 {
     uint16_t desc_size;
     VRingMemoryRegionCaches *caches;
@@ -1477,7 +1531,7 @@ void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes,
                                         caches);
     }
 
-    return;
+    return (int)vq->shadow_avail_idx;
 err:
     if (in_bytes) {
         *in_bytes = 0;
@@ -1485,6 +1539,8 @@ err:
     if (out_bytes) {
         *out_bytes = 0;
     }
+
+    return -1;
 }
 
 int virtqueue_avail_bytes(VirtQueue *vq, unsigned int in_bytes,
diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h
index d2a1938..0fcbc5c 100644
--- a/include/hw/virtio/virtio.h
+++ b/include/hw/virtio/virtio.h
@@ -273,9 +273,13 @@ void qemu_put_virtqueue_element(VirtIODevice *vdev, QEMUFile *f,
                                 VirtQueueElement *elem);
 int virtqueue_avail_bytes(VirtQueue *vq, unsigned int in_bytes,
                           unsigned int out_bytes);
-void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes,
-                               unsigned int *out_bytes,
-                               unsigned max_in_bytes, unsigned max_out_bytes);
+/**
+ * Return <0 on error or an opaque >=0 to pass to
+ * virtio_queue_enable_notification_and_check on success.
+ */
+int virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes,
+                              unsigned int *out_bytes, unsigned max_in_bytes,
+                              unsigned max_out_bytes);
 
 void virtio_notify_irqfd(VirtIODevice *vdev, VirtQueue *vq);
 void virtio_notify(VirtIODevice *vdev, VirtQueue *vq);
@@ -309,6 +313,15 @@ int virtio_queue_ready(VirtQueue *vq);
 
 int virtio_queue_empty(VirtQueue *vq);
 
+/**
+ * Enable notification and check whether guest has added some
+ * buffers since last call to virtqueue_get_avail_bytes.
+ *
+ * @opaque: value returned from virtqueue_get_avail_bytes
+ */
+bool virtio_queue_enable_notification_and_check(VirtQueue *vq,
+                                                int opaque);
+
 void virtio_queue_set_shadow_avail_idx(VirtQueue *vq, uint16_t idx);
 
 /* Host binding interface.  */
diff --git a/net/net.c b/net/net.c
index 6938da0..2eb8bc9 100644
--- a/net/net.c
+++ b/net/net.c
@@ -1139,6 +1139,21 @@ NICInfo *qemu_find_nic_info(const char *typename, bool match_default,
     return NULL;
 }
 
+static bool is_nic_model_help_option(const char *model)
+{
+    if (model && is_help_option(model)) {
+        /*
+         * Trigger the help output by instantiating the hash table which
+         * will gather tha available models as they get registered.
+         */
+        if (!nic_model_help) {
+            nic_model_help = g_hash_table_new_full(g_str_hash, g_str_equal,
+                                                   g_free, NULL);
+        }
+        return true;
+    }
+    return false;
+}
 
 /* "I have created a device. Please configure it if you can" */
 bool qemu_configure_nic_device(DeviceState *dev, bool match_default,
@@ -1722,6 +1737,12 @@ void net_check_clients(void)
 
 static int net_init_client(void *dummy, QemuOpts *opts, Error **errp)
 {
+    const char *model = qemu_opt_get_del(opts, "model");
+
+    if (is_nic_model_help_option(model)) {
+        return 0;
+    }
+
     return net_client_init(opts, false, errp);
 }
 
@@ -1778,9 +1799,7 @@ static int net_param_nic(void *dummy, QemuOpts *opts, Error **errp)
     memset(ni, 0, sizeof(*ni));
     ni->model = qemu_opt_get_del(opts, "model");
 
-    if (!nic_model_help && !g_strcmp0(ni->model, "help")) {
-        nic_model_help = g_hash_table_new_full(g_str_hash, g_str_equal,
-                                               g_free, NULL);
+    if (is_nic_model_help_option(ni->model)) {
         return 0;
     }
 
diff --git a/qemu-options.hx b/qemu-options.hx
index 369ae81..cee0da2 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -3353,6 +3353,195 @@ SRST
                          -device e1000,netdev=n1,mac=52:54:00:12:34:56 \\
                          -netdev socket,id=n1,mcast=239.192.168.1:1102,localaddr=1.2.3.4
 
+``-netdev stream,id=str[,server=on|off],addr.type=inet,addr.host=host,addr.port=port[,to=maxport][,numeric=on|off][,keep-alive=on|off][,mptcp=on|off][,addr.ipv4=on|off][,addr.ipv6=on|off][,reconnect=seconds]``
+    Configure a network backend to connect to another QEMU virtual machine or a proxy using a TCP/IP socket.
+
+    ``server=on|off``
+        if ``on`` create a server socket
+
+    ``addr.host=host,addr.port=port``
+        socket address to listen on (server=on) or connect to (server=off)
+
+    ``to=maxport``
+        if present, this is range of possible addresses, with port between ``port`` and ``maxport``.
+
+    ``numeric=on|off``
+        if ``on`` ``host`` and ``port`` are guaranteed to be numeric, otherwise a name resolution should be attempted (default: ``off``)
+
+    ``keep-alive=on|off``
+        enable keep-alive when connecting to this socket.  Not supported for passive sockets.
+
+    ``mptcp=on|off``
+        enable multipath TCP
+
+    ``ipv4=on|off``
+        whether to accept IPv4 addresses, default to try both IPv4 and IPv6
+
+    ``ipv6=on|off``
+        whether to accept IPv6 addresses, default to try both IPv4 and IPv6
+
+    ``reconnect=seconds``
+        for a client socket, if a socket is disconnected, then attempt a reconnect after the given number of seconds.
+        Setting this to zero disables this function.  (default: 0)
+
+    Example (two guests connected using a TCP/IP socket):
+
+    .. parsed-literal::
+
+        # first VM
+        |qemu_system| linux.img \\
+                      -device virtio-net,netdev=net0,mac=52:54:00:12:34:56 \\
+                      -netdev stream,id=net0,server=on,addr.type=inet,addr.host=localhost,addr.port=1234
+        # second VM
+        |qemu_system| linux.img \\
+                      -device virtio-net,netdev=net0,mac=52:54:00:12:34:57 \\
+                      -netdev stream,id=net0,server=off,addr.type=inet,addr.host=localhost,addr.port=1234,reconnect=5
+
+``-netdev stream,id=str[,server=on|off],addr.type=unix,addr.path=path[,abstract=on|off][,tight=on|off][,reconnect=seconds]``
+    Configure a network backend to connect to another QEMU virtual machine or a proxy using a stream oriented unix domain socket.
+
+    ``server=on|off``
+        if ``on`` create a server socket
+
+    ``addr.path=path``
+        filesystem path to use
+
+    ``abstract=on|off``
+        if ``on``, this is a Linux abstract socket address.
+
+    ``tight=on|off``
+        if false, pad an abstract socket address with enough null bytes to make it fill struct sockaddr_un member sun_path.
+
+    ``reconnect=seconds``
+        for a client socket, if a socket is disconnected, then attempt a reconnect after the given number of seconds.
+        Setting this to zero disables this function.  (default: 0)
+
+    Example (using passt as a replacement of -netdev user):
+
+    .. parsed-literal::
+
+        # start passt server as a non privileged user
+        passt
+        UNIX domain socket bound at /tmp/passt_1.socket
+        # start QEMU to connect to passt
+        |qemu_system| linux.img \\
+                      -device virtio-net,netdev=net0 \\
+                      -netdev stream,id=net0,server=off,addr.type=unix,addr.path=/tmp/passt_1.socket
+
+    Example (two guests connected using a stream oriented unix domain socket):
+
+    .. parsed-literal::
+
+        # first VM
+        |qemu_system| linux.img \\
+                      -device virtio-net,netdev=net0,mac=52:54:00:12:34:56 \\
+                      netdev stream,id=net0,server=on,addr.type=unix,addr.path=/tmp/qemu0
+        # second VM
+        |qemu_system| linux.img \\
+                      -device virtio-net,netdev=net0,mac=52:54:00:12:34:57 \\
+                      -netdev stream,id=net0,server=off,addr.type=unix,addr.path=/tmp/qemu0,reconnect=5
+
+``-netdev stream,id=str[,server=on|off],addr.type=fd,addr.str=file-descriptor[,reconnect=seconds]``
+    Configure a network backend to connect to another QEMU virtual machine or a proxy using a stream oriented socket file descriptor.
+
+    ``server=on|off``
+        if ``on`` create a server socket
+
+    ``addr.str=file-descriptor``
+        file descriptor number to use as a socket
+
+    ``reconnect=seconds``
+        for a client socket, if a socket is disconnected, then attempt a reconnect after the given number of seconds.
+        Setting this to zero disables this function.  (default: 0)
+
+``-netdev dgram,id=str,remote.type=inet,remote.host=maddr,remote.port=port[,local.type=inet,local.host=addr]``
+    Configure a network backend to connect to a multicast address.
+
+    ``remote.host=maddr,remote.port=port``
+        multicast address
+
+    ``local.host=addr``
+        specify the host address to send packets from
+
+    Example:
+
+    .. parsed-literal::
+
+        # launch one QEMU instance
+        |qemu_system| linux.img \\
+                      -device virtio-net,netdev=net0,mac=52:54:00:12:34:56 \\
+                      -netdev dgram,id=net0,remote.type=inet,remote.host=224.0.0.1,remote.port=1234
+        # launch another QEMU instance on same "bus"
+        |qemu_system| linux.img \\
+                      -device virtio-net,netdev=net0,mac=52:54:00:12:34:57 \\
+                      -netdev dgram,id=net0,remote.type=inet,remote.host=224.0.0.1,remote.port=1234
+        # launch yet another QEMU instance on same "bus"
+        |qemu_system| linux.img \\
+                      -device virtio-net,netdev=net0,mac=52:54:00:12:34:58 \\
+                      -netdev dgram,id=net0,remote.type=inet,remote.host=224.0.0.1,remote.port=1234
+
+``-netdev dgram,id=str,remote.type=inet,remote.host=maddr,remote.port=port[,local.type=fd,local.str=file-descriptor]``
+    Configure a network backend to connect to a multicast address using a UDP socket file descriptor.
+
+    ``remote.host=maddr,remote.port=port``
+        multicast address
+
+    ``local.str=file-descriptor``
+        File descriptor to use to send packets
+
+``-netdev dgram,id=str,local.type=inet,local.host=addr,local.port=port[,remote.type=inet,remote.host=addr,remote.port=port]``
+    Configure a network backend to connect to another QEMU virtual
+    machine or a proxy using a datagram oriented unix domain socket.
+
+    ``local.host=addr,local.port=port``
+        IP address to use to send the packets from
+
+    ``remote.host=addr,remote.port=port``
+        Destination IP address
+
+    Example (two guests connected using an UDP/IP socket):
+
+    .. parsed-literal::
+
+        # first VM
+        |qemu_system| linux.img \\
+                      -device virtio-net,netdev=net0,mac=52:54:00:12:34:56 \\
+                      -netdev dgram,id=net0,local.type=inet,local.host=localhost,local.port=1234,remote.type=inet,remote.host=localhost,remote.port=1235
+        # second VM
+        |qemu_system| linux.img \\
+                      -device virtio-net,netdev=net0,mac=52:54:00:12:34:56 \\
+                      -netdev dgram,id=net0,local.type=inet,local.host=localhost,local.port=1235,remote.type=inet,remote.host=localhost,remote.port=1234
+
+``-netdev dgram,id=str,local.type=unix,local.path=path[,remote.type=unix,remote.path=path]``
+    Configure a network backend to connect to another QEMU virtual
+    machine or a proxy using a datagram oriented unix socket.
+
+    ``local.path=path``
+        filesystem path to use to bind the socket
+
+    ``remote.path=path``
+        filesystem path to use as a destination (see sendto(2))
+
+    Example (two guests connected using an UDP/UNIX socket):
+
+    .. parsed-literal::
+
+        # first VM
+        |qemu_system| linux.img \\
+                      -device virtio-net,netdev=net0,mac=52:54:00:12:34:56 \\
+                      -netdev dgram,id=net0,local.type=unix,local.path=/tmp/qemu0,remote.type=unix,remote.path=/tmp/qemu1
+        # second VM
+        |qemu_system| linux.img \\
+                      -device virtio-net,netdev=net0,mac=52:54:00:12:34:57 \\
+                      -netdev dgram,id=net0,local.type=unix,local.path=/tmp/qemu1,remote.type=unix,remote.path=/tmp/qemu0
+
+``-netdev dgram,id=str,local.type=fd,local.str=file-descriptor``
+    Configure a network backend to connect to another QEMU virtual
+    machine or a proxy using a datagram oriented socket file descriptor.
+
+    ``local.str=file-descriptor``
+        File descriptor to use to send packets
+
 ``-netdev l2tpv3,id=id,src=srcaddr,dst=dstaddr[,srcport=srcport][,dstport=dstport],txsession=txsession[,rxsession=rxsession][,ipv6=on|off][,udp=on|off][,cookie64=on|off][,counter=on|off][,pincounter=on|off][,txcookie=txcookie][,rxcookie=rxcookie][,offset=offset]``
     Configure a L2TPv3 pseudowire host network backend. L2TPv3 (RFC3931)
     is a popular protocol to transport Ethernet (and other Layer 2) data