vhost-vsock: add virtio sockets device

Implement the new virtio sockets device for host<->guest communication
using the Sockets API.  Most of the work is done in a vhost kernel
driver so that virtio-vsock can hook into the AF_VSOCK address family.
The QEMU vhost-vsock device handles configuration and live migration
while the rx/tx happens in the vhost_vsock.ko Linux kernel driver.

The vsock device must be given a CID (host-wide unique address):

  # qemu -device vhost-vsock-pci,id=vhost-vsock-pci0,guest-cid=3 ...

For more information see:
http://qemu-project.org/Features/VirtioVsock

[Endianness fixes and virtio-ccw support by Claudio Imbrenda
<imbrenda@linux.vnet.ibm.com>]

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
[mst: rebase to master]
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

11 files changed, 631 insertions, 0 deletions

diff --git a/configure b/configure
index 5a9bda18b5..331c36fb84 100755
--- a/configure
+++ b/configure
@@ -229,6 +229,7 @@ xfs=""
 
 vhost_net="no"
 vhost_scsi="no"
+vhost_vsock="no"
 kvm="no"
 rdma=""
 gprof="no"
@@ -674,6 +675,7 @@ Haiku)
   kvm="yes"
   vhost_net="yes"
   vhost_scsi="yes"
+  vhost_vsock="yes"
   QEMU_INCLUDES="-I\$(SRC_PATH)/linux-headers -I$(pwd)/linux-headers $QEMU_INCLUDES"
 ;;
 esac
@@ -1017,6 +1019,10 @@ for opt do
   ;;
   --enable-vhost-scsi) vhost_scsi="yes"
   ;;
+  --disable-vhost-vsock) vhost_vsock="no"
+  ;;
+  --enable-vhost-vsock) vhost_vsock="yes"
+  ;;
   --disable-opengl) opengl="no"
   ;;
   --enable-opengl) opengl="yes"
@@ -4883,6 +4889,7 @@ echo "uuid support      $uuid"
 echo "libcap-ng support $cap_ng"
 echo "vhost-net support $vhost_net"
 echo "vhost-scsi support $vhost_scsi"
+echo "vhost-vsock support $vhost_vsock"
 echo "Trace backends    $trace_backends"
 if have_backend "simple"; then
 echo "Trace output file $trace_file-<pid>"
@@ -5264,6 +5271,9 @@ fi
 if test "$vhost_net" = "yes" ; then
   echo "CONFIG_VHOST_NET_USED=y" >> $config_host_mak
 fi
+if test "$vhost_vsock" = "yes" ; then
+  echo "CONFIG_VHOST_VSOCK=y" >> $config_host_mak
+fi
 if test "$blobs" = "yes" ; then
   echo "INSTALL_BLOBS=yes" >> $config_host_mak
 fi
diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c
index a554a24d06..96789569a7 100644
--- a/hw/s390x/virtio-ccw.c
+++ b/hw/s390x/virtio-ccw.c
@@ -1658,6 +1658,57 @@ static const TypeInfo virtio_ccw_9p_info = {
 };
 #endif
 
+#ifdef CONFIG_VHOST_VSOCK
+
+static Property vhost_vsock_ccw_properties[] = {
+    DEFINE_PROP_CSS_DEV_ID("devno", VirtioCcwDevice, parent_obj.bus_id),
+    DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev,
+                       VIRTIO_CCW_MAX_REV),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void vhost_vsock_ccw_realize(VirtioCcwDevice *ccw_dev, Error **errp)
+{
+    VHostVSockCCWState *dev = VHOST_VSOCK_CCW(ccw_dev);
+    DeviceState *vdev = DEVICE(&dev->vdev);
+    Error *err = NULL;
+
+    qdev_set_parent_bus(vdev, BUS(&ccw_dev->bus));
+    object_property_set_bool(OBJECT(vdev), true, "realized", &err);
+    if (err) {
+        error_propagate(errp, err);
+    }
+}
+
+static void vhost_vsock_ccw_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    VirtIOCCWDeviceClass *k = VIRTIO_CCW_DEVICE_CLASS(klass);
+
+    k->realize = vhost_vsock_ccw_realize;
+    k->exit = virtio_ccw_exit;
+    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+    dc->props = vhost_vsock_ccw_properties;
+    dc->reset = virtio_ccw_reset;
+}
+
+static void vhost_vsock_ccw_instance_init(Object *obj)
+{
+    VHostVSockCCWState *dev = VHOST_VSOCK_CCW(obj);
+
+    virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev),
+                                TYPE_VHOST_VSOCK);
+}
+
+static const TypeInfo vhost_vsock_ccw_info = {
+    .name          = TYPE_VHOST_VSOCK_CCW,
+    .parent        = TYPE_VIRTIO_CCW_DEVICE,
+    .instance_size = sizeof(VHostVSockCCWState),
+    .instance_init = vhost_vsock_ccw_instance_init,
+    .class_init    = vhost_vsock_ccw_class_init,
+};
+#endif
+
 static void virtio_ccw_register(void)
 {
     type_register_static(&virtio_ccw_bus_info);
@@ -1674,6 +1725,9 @@ static void virtio_ccw_register(void)
 #ifdef CONFIG_VIRTFS
     type_register_static(&virtio_ccw_9p_info);
 #endif
+#ifdef CONFIG_VHOST_VSOCK
+    type_register_static(&vhost_vsock_ccw_info);
+#endif
 }
 
 type_init(virtio_ccw_register)
diff --git a/hw/s390x/virtio-ccw.h b/hw/s390x/virtio-ccw.h
index 1c6bc86316..904e357581 100644
--- a/hw/s390x/virtio-ccw.h
+++ b/hw/s390x/virtio-ccw.h
@@ -23,6 +23,9 @@
 #include "hw/virtio/virtio-balloon.h"
 #include "hw/virtio/virtio-rng.h"
 #include "hw/virtio/virtio-bus.h"
+#ifdef CONFIG_VHOST_VSOCK
+#include "hw/virtio/vhost-vsock.h"
+#endif /* CONFIG_VHOST_VSOCK */
 
 #include "hw/s390x/s390_flic.h"
 #include "hw/s390x/css.h"
@@ -197,4 +200,16 @@ typedef struct V9fsCCWState {
 
 #endif /* CONFIG_VIRTFS */
 
+#ifdef CONFIG_VHOST_VSOCK
+#define TYPE_VHOST_VSOCK_CCW "vhost-vsock-ccw"
+#define VHOST_VSOCK_CCW(obj) \
+    OBJECT_CHECK(VHostVSockCCWState, (obj), TYPE_VHOST_VSOCK_CCW)
+
+typedef struct VHostVSockCCWState {
+    VirtioCcwDevice parent_obj;
+    VHostVSock vdev;
+} VHostVSockCCWState;
+
+#endif /* CONFIG_VHOST_VSOCK */
+
 #endif
diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs
index 3e2b175da8..e71630812e 100644
--- a/hw/virtio/Makefile.objs
+++ b/hw/virtio/Makefile.objs
@@ -5,3 +5,5 @@ common-obj-y += virtio-mmio.o
 
 obj-y += virtio.o virtio-balloon.o 
 obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o
+
+obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock.o
diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c
index 7681f152f3..272a5ec584 100644
--- a/hw/virtio/vhost-backend.c
+++ b/hw/virtio/vhost-backend.c
@@ -172,6 +172,19 @@ static int vhost_kernel_get_vq_index(struct vhost_dev *dev, int idx)
     return idx - dev->vq_index;
 }
 
+#ifdef CONFIG_VHOST_VSOCK
+static int vhost_kernel_vsock_set_guest_cid(struct vhost_dev *dev,
+                                            uint64_t guest_cid)
+{
+    return vhost_kernel_call(dev, VHOST_VSOCK_SET_GUEST_CID, &guest_cid);
+}
+
+static int vhost_kernel_vsock_set_running(struct vhost_dev *dev, int start)
+{
+    return vhost_kernel_call(dev, VHOST_VSOCK_SET_RUNNING, &start);
+}
+#endif /* CONFIG_VHOST_VSOCK */
+
 static const VhostOps kernel_ops = {
         .backend_type = VHOST_BACKEND_TYPE_KERNEL,
         .vhost_backend_init = vhost_kernel_init,
@@ -197,6 +210,10 @@ static const VhostOps kernel_ops = {
         .vhost_set_owner = vhost_kernel_set_owner,
         .vhost_reset_device = vhost_kernel_reset_device,
         .vhost_get_vq_index = vhost_kernel_get_vq_index,
+#ifdef CONFIG_VHOST_VSOCK
+        .vhost_vsock_set_guest_cid = vhost_kernel_vsock_set_guest_cid,
+        .vhost_vsock_set_running = vhost_kernel_vsock_set_running,
+#endif /* CONFIG_VHOST_VSOCK */
 };
 
 int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)
diff --git a/hw/virtio/vhost-vsock.c b/hw/virtio/vhost-vsock.c
new file mode 100644
index 0000000000..bde2456621
--- /dev/null
+++ b/hw/virtio/vhost-vsock.c
@@ -0,0 +1,417 @@
+/*
+ * Virtio vsock device
+ *
+ * Copyright 2015 Red Hat, Inc.
+ *
+ * Authors:
+ *  Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * (at your option) any later version.  See the COPYING file in the
+ * top-level directory.
+ */
+
+#include <sys/ioctl.h>
+#include "qemu/osdep.h"
+#include "standard-headers/linux/virtio_vsock.h"
+#include "qapi/error.h"
+#include "hw/virtio/virtio-bus.h"
+#include "hw/virtio/virtio-access.h"
+#include "migration/migration.h"
+#include "qemu/error-report.h"
+#include "hw/virtio/vhost-vsock.h"
+#include "qemu/iov.h"
+#include "monitor/monitor.h"
+
+enum {
+    VHOST_VSOCK_SAVEVM_VERSION = 0,
+
+    VHOST_VSOCK_QUEUE_SIZE = 128,
+};
+
+static void vhost_vsock_get_config(VirtIODevice *vdev, uint8_t *config)
+{
+    VHostVSock *vsock = VHOST_VSOCK(vdev);
+    struct virtio_vsock_config vsockcfg = {};
+
+    virtio_stq_p(vdev, &vsockcfg.guest_cid, vsock->conf.guest_cid);
+    memcpy(config, &vsockcfg, sizeof(vsockcfg));
+}
+
+static int vhost_vsock_set_guest_cid(VHostVSock *vsock)
+{
+    const VhostOps *vhost_ops = vsock->vhost_dev.vhost_ops;
+    int ret;
+
+    if (!vhost_ops->vhost_vsock_set_guest_cid) {
+        return -ENOSYS;
+    }
+
+    ret = vhost_ops->vhost_vsock_set_guest_cid(&vsock->vhost_dev,
+                                               vsock->conf.guest_cid);
+    if (ret < 0) {
+        return -errno;
+    }
+    return 0;
+}
+
+static int vhost_vsock_set_running(VHostVSock *vsock, int start)
+{
+    const VhostOps *vhost_ops = vsock->vhost_dev.vhost_ops;
+    int ret;
+
+    if (!vhost_ops->vhost_vsock_set_running) {
+        return -ENOSYS;
+    }
+
+    ret = vhost_ops->vhost_vsock_set_running(&vsock->vhost_dev, start);
+    if (ret < 0) {
+        return -errno;
+    }
+    return 0;
+}
+
+static void vhost_vsock_start(VirtIODevice *vdev)
+{
+    VHostVSock *vsock = VHOST_VSOCK(vdev);
+    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+    int ret;
+    int i;
+
+    if (!k->set_guest_notifiers) {
+        error_report("binding does not support guest notifiers");
+        return;
+    }
+
+    ret = vhost_dev_enable_notifiers(&vsock->vhost_dev, vdev);
+    if (ret < 0) {
+        error_report("Error enabling host notifiers: %d", -ret);
+        return;
+    }
+
+    ret = k->set_guest_notifiers(qbus->parent, vsock->vhost_dev.nvqs, true);
+    if (ret < 0) {
+        error_report("Error binding guest notifier: %d", -ret);
+        goto err_host_notifiers;
+    }
+
+    vsock->vhost_dev.acked_features = vdev->guest_features;
+    ret = vhost_dev_start(&vsock->vhost_dev, vdev);
+    if (ret < 0) {
+        error_report("Error starting vhost: %d", -ret);
+        goto err_guest_notifiers;
+    }
+
+    ret = vhost_vsock_set_running(vsock, 1);
+    if (ret < 0) {
+        error_report("Error starting vhost vsock: %d", -ret);
+        goto err_dev_start;
+    }
+
+    /* guest_notifier_mask/pending not used yet, so just unmask
+     * everything here.  virtio-pci will do the right thing by
+     * enabling/disabling irqfd.
+     */
+    for (i = 0; i < vsock->vhost_dev.nvqs; i++) {
+        vhost_virtqueue_mask(&vsock->vhost_dev, vdev, i, false);
+    }
+
+    return;
+
+err_dev_start:
+    vhost_dev_stop(&vsock->vhost_dev, vdev);
+err_guest_notifiers:
+    k->set_guest_notifiers(qbus->parent, vsock->vhost_dev.nvqs, false);
+err_host_notifiers:
+    vhost_dev_disable_notifiers(&vsock->vhost_dev, vdev);
+}
+
+static void vhost_vsock_stop(VirtIODevice *vdev)
+{
+    VHostVSock *vsock = VHOST_VSOCK(vdev);
+    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+    int ret;
+
+    if (!k->set_guest_notifiers) {
+        return;
+    }
+
+    ret = vhost_vsock_set_running(vsock, 0);
+    if (ret < 0) {
+        error_report("vhost vsock set running failed: %d", ret);
+        return;
+    }
+
+    vhost_dev_stop(&vsock->vhost_dev, vdev);
+
+    ret = k->set_guest_notifiers(qbus->parent, vsock->vhost_dev.nvqs, false);
+    if (ret < 0) {
+        error_report("vhost guest notifier cleanup failed: %d", ret);
+        return;
+    }
+
+    vhost_dev_disable_notifiers(&vsock->vhost_dev, vdev);
+}
+
+static void vhost_vsock_set_status(VirtIODevice *vdev, uint8_t status)
+{
+    VHostVSock *vsock = VHOST_VSOCK(vdev);
+    bool should_start = status & VIRTIO_CONFIG_S_DRIVER_OK;
+
+    if (!vdev->vm_running) {
+        should_start = false;
+    }
+
+    if (vsock->vhost_dev.started == should_start) {
+        return;
+    }
+
+    if (should_start) {
+        vhost_vsock_start(vdev);
+    } else {
+        vhost_vsock_stop(vdev);
+    }
+}
+
+static uint64_t vhost_vsock_get_features(VirtIODevice *vdev,
+                                         uint64_t requested_features,
+                                         Error **errp)
+{
+    /* No feature bits used yet */
+    return requested_features;
+}
+
+static void vhost_vsock_handle_output(VirtIODevice *vdev, VirtQueue *vq)
+{
+    /* Do nothing */
+}
+
+static void vhost_vsock_guest_notifier_mask(VirtIODevice *vdev, int idx,
+                                            bool mask)
+{
+    VHostVSock *vsock = VHOST_VSOCK(vdev);
+
+    vhost_virtqueue_mask(&vsock->vhost_dev, vdev, idx, mask);
+}
+
+static bool vhost_vsock_guest_notifier_pending(VirtIODevice *vdev, int idx)
+{
+    VHostVSock *vsock = VHOST_VSOCK(vdev);
+
+    return vhost_virtqueue_pending(&vsock->vhost_dev, idx);
+}
+
+static void vhost_vsock_send_transport_reset(VHostVSock *vsock)
+{
+    VirtQueueElement *elem;
+    VirtQueue *vq = vsock->event_vq;
+    struct virtio_vsock_event event = {
+        .id = cpu_to_le32(VIRTIO_VSOCK_EVENT_TRANSPORT_RESET),
+    };
+
+    elem = virtqueue_pop(vq, sizeof(VirtQueueElement));
+    if (!elem) {
+        error_report("vhost-vsock missed transport reset event");
+        return;
+    }
+
+    if (elem->out_num) {
+        error_report("invalid vhost-vsock event virtqueue element with "
+                     "out buffers");
+        goto out;
+    }
+
+    if (iov_from_buf(elem->in_sg, elem->in_num, 0,
+                     &event, sizeof(event)) != sizeof(event)) {
+        error_report("vhost-vsock event virtqueue element is too short");
+        goto out;
+    }
+
+    virtqueue_push(vq, elem, sizeof(event));
+    virtio_notify(VIRTIO_DEVICE(vsock), vq);
+
+out:
+    g_free(elem);
+}
+
+static void vhost_vsock_save(QEMUFile *f, void *opaque, size_t size)
+{
+    VHostVSock *vsock = opaque;
+    VirtIODevice *vdev = VIRTIO_DEVICE(vsock);
+
+    /* At this point, backend must be stopped, otherwise
+     * it might keep writing to memory. */
+    assert(!vsock->vhost_dev.started);
+    virtio_save(vdev, f);
+}
+
+static void vhost_vsock_post_load_timer_cleanup(VHostVSock *vsock)
+{
+    if (!vsock->post_load_timer) {
+        return;
+    }
+
+    timer_del(vsock->post_load_timer);
+    timer_free(vsock->post_load_timer);
+    vsock->post_load_timer = NULL;
+}
+
+static void vhost_vsock_post_load_timer_cb(void *opaque)
+{
+    VHostVSock *vsock = opaque;
+
+    vhost_vsock_post_load_timer_cleanup(vsock);
+    vhost_vsock_send_transport_reset(vsock);
+}
+
+static int vhost_vsock_load(QEMUFile *f, void *opaque, size_t size)
+{
+    VHostVSock *vsock = opaque;
+    VirtIODevice *vdev = VIRTIO_DEVICE(vsock);
+    int ret;
+
+    ret = virtio_load(vdev, f, VHOST_VSOCK_SAVEVM_VERSION);
+    if (ret) {
+        return ret;
+    }
+
+    if (virtio_queue_get_addr(vdev, 2)) {
+        /* Defer transport reset event to a vm clock timer so that virtqueue
+         * changes happen after migration has completed.
+         */
+        assert(!vsock->post_load_timer);
+        vsock->post_load_timer =
+            timer_new_ns(QEMU_CLOCK_VIRTUAL,
+                         vhost_vsock_post_load_timer_cb,
+                         vsock);
+        timer_mod(vsock->post_load_timer, 1);
+    }
+
+    return 0;
+}
+
+VMSTATE_VIRTIO_DEVICE(vhost_vsock, VHOST_VSOCK_SAVEVM_VERSION,
+                      vhost_vsock_load, vhost_vsock_save);
+
+static void vhost_vsock_device_realize(DeviceState *dev, Error **errp)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VHostVSock *vsock = VHOST_VSOCK(dev);
+    int vhostfd;
+    int ret;
+
+    /* Refuse to use reserved CID numbers */
+    if (vsock->conf.guest_cid <= 2) {
+        error_setg(errp, "guest-cid property must be greater than 2");
+        return;
+    }
+
+    if (vsock->conf.guest_cid > UINT32_MAX) {
+        error_setg(errp, "guest-cid property must be a 32-bit number");
+        return;
+    }
+
+    if (vsock->conf.vhostfd) {
+        vhostfd = monitor_fd_param(cur_mon, vsock->conf.vhostfd, errp);
+        if (vhostfd == -1) {
+            error_prepend(errp, "vhost-vsock: unable to parse vhostfd: ");
+            return;
+        }
+    } else {
+        vhostfd = open("/dev/vhost-vsock", O_RDWR);
+        if (vhostfd < 0) {
+            error_setg_errno(errp, -errno,
+                             "vhost-vsock: failed to open vhost device");
+            return;
+        }
+    }
+
+    virtio_init(vdev, "vhost-vsock", VIRTIO_ID_VSOCK,
+                sizeof(struct virtio_vsock_config));
+
+    /* Receive and transmit queues belong to vhost */
+    virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE, vhost_vsock_handle_output);
+    virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE, vhost_vsock_handle_output);
+
+    /* The event queue belongs to QEMU */
+    vsock->event_vq = virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE,
+                                       vhost_vsock_handle_output);
+
+    vsock->vhost_dev.nvqs = ARRAY_SIZE(vsock->vhost_vqs);
+    vsock->vhost_dev.vqs = vsock->vhost_vqs;
+    ret = vhost_dev_init(&vsock->vhost_dev, (void *)(uintptr_t)vhostfd,
+                         VHOST_BACKEND_TYPE_KERNEL, 0);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "vhost-vsock: vhost_dev_init failed");
+        goto err_virtio;
+    }
+
+    ret = vhost_vsock_set_guest_cid(vsock);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "vhost-vsock: unable to set guest cid");
+        goto err_vhost_dev;
+    }
+
+    vsock->post_load_timer = NULL;
+    return;
+
+err_vhost_dev:
+    vhost_dev_cleanup(&vsock->vhost_dev);
+err_virtio:
+    virtio_cleanup(vdev);
+    close(vhostfd);
+    return;
+}
+
+static void vhost_vsock_device_unrealize(DeviceState *dev, Error **errp)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VHostVSock *vsock = VHOST_VSOCK(dev);
+
+    vhost_vsock_post_load_timer_cleanup(vsock);
+
+    /* This will stop vhost backend if appropriate. */
+    vhost_vsock_set_status(vdev, 0);
+
+    vhost_dev_cleanup(&vsock->vhost_dev);
+    virtio_cleanup(vdev);
+}
+
+static Property vhost_vsock_properties[] = {
+    DEFINE_PROP_UINT64("guest-cid", VHostVSock, conf.guest_cid, 0),
+    DEFINE_PROP_STRING("vhostfd", VHostVSock, conf.vhostfd),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void vhost_vsock_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
+
+    dc->props = vhost_vsock_properties;
+    dc->vmsd = &vmstate_virtio_vhost_vsock;
+    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+    vdc->realize = vhost_vsock_device_realize;
+    vdc->unrealize = vhost_vsock_device_unrealize;
+    vdc->get_features = vhost_vsock_get_features;
+    vdc->get_config = vhost_vsock_get_config;
+    vdc->set_status = vhost_vsock_set_status;
+    vdc->guest_notifier_mask = vhost_vsock_guest_notifier_mask;
+    vdc->guest_notifier_pending = vhost_vsock_guest_notifier_pending;
+}
+
+static const TypeInfo vhost_vsock_info = {
+    .name = TYPE_VHOST_VSOCK,
+    .parent = TYPE_VIRTIO_DEVICE,
+    .instance_size = sizeof(VHostVSock),
+    .class_init = vhost_vsock_class_init,
+};
+
+static void vhost_vsock_register_types(void)
+{
+    type_register_static(&vhost_vsock_info);
+}
+
+type_init(vhost_vsock_register_types)
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index bf19808e87..dde71a5965 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -2071,6 +2071,54 @@ static const TypeInfo vhost_scsi_pci_info = {
 };
 #endif
 
+/* vhost-vsock-pci */
+
+#ifdef CONFIG_VHOST_VSOCK
+static Property vhost_vsock_pci_properties[] = {
+    DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 3),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void vhost_vsock_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
+{
+    VHostVSockPCI *dev = VHOST_VSOCK_PCI(vpci_dev);
+    DeviceState *vdev = DEVICE(&dev->vdev);
+
+    qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus));
+    object_property_set_bool(OBJECT(vdev), true, "realized", errp);
+}
+
+static void vhost_vsock_pci_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass);
+    PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass);
+    k->realize = vhost_vsock_pci_realize;
+    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+    dc->props = vhost_vsock_pci_properties;
+    pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET;
+    pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_VSOCK;
+    pcidev_k->revision = 0x00;
+    pcidev_k->class_id = PCI_CLASS_COMMUNICATION_OTHER;
+}
+
+static void vhost_vsock_pci_instance_init(Object *obj)
+{
+    VHostVSockPCI *dev = VHOST_VSOCK_PCI(obj);
+
+    virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev),
+                                TYPE_VHOST_VSOCK);
+}
+
+static const TypeInfo vhost_vsock_pci_info = {
+    .name          = TYPE_VHOST_VSOCK_PCI,
+    .parent        = TYPE_VIRTIO_PCI,
+    .instance_size = sizeof(VHostVSockPCI),
+    .instance_init = vhost_vsock_pci_instance_init,
+    .class_init    = vhost_vsock_pci_class_init,
+};
+#endif
+
 /* virtio-balloon-pci */
 
 static Property virtio_balloon_pci_properties[] = {
@@ -2501,6 +2549,9 @@ static void virtio_pci_register_types(void)
 #ifdef CONFIG_VHOST_SCSI
     type_register_static(&vhost_scsi_pci_info);
 #endif
+#ifdef CONFIG_VHOST_VSOCK
+    type_register_static(&vhost_vsock_pci_info);
+#endif
 }
 
 type_init(virtio_pci_register_types)
diff --git a/hw/virtio/virtio-pci.h b/hw/virtio/virtio-pci.h
index a7455126f5..0698157b32 100644
--- a/hw/virtio/virtio-pci.h
+++ b/hw/virtio/virtio-pci.h
@@ -31,6 +31,9 @@
 #ifdef CONFIG_VHOST_SCSI
 #include "hw/virtio/vhost-scsi.h"
 #endif
+#ifdef CONFIG_VHOST_VSOCK
+#include "hw/virtio/vhost-vsock.h"
+#endif
 
 typedef struct VirtIOPCIProxy VirtIOPCIProxy;
 typedef struct VirtIOBlkPCI VirtIOBlkPCI;
@@ -44,6 +47,7 @@ typedef struct VirtIOInputPCI VirtIOInputPCI;
 typedef struct VirtIOInputHIDPCI VirtIOInputHIDPCI;
 typedef struct VirtIOInputHostPCI VirtIOInputHostPCI;
 typedef struct VirtIOGPUPCI VirtIOGPUPCI;
+typedef struct VHostVSockPCI VHostVSockPCI;
 
 /* virtio-pci-bus */
 
@@ -329,6 +333,20 @@ struct VirtIOGPUPCI {
     VirtIOGPU vdev;
 };
 
+#ifdef CONFIG_VHOST_VSOCK
+/*
+ * vhost-vsock-pci: This extends VirtioPCIProxy.
+ */
+#define TYPE_VHOST_VSOCK_PCI "vhost-vsock-pci"
+#define VHOST_VSOCK_PCI(obj) \
+        OBJECT_CHECK(VHostVSockPCI, (obj), TYPE_VHOST_VSOCK_PCI)
+
+struct VHostVSockPCI {
+    VirtIOPCIProxy parent_obj;
+    VHostVSock vdev;
+};
+#endif
+
 /* Virtio ABI version, if we increment this, we break the guest driver. */
 #define VIRTIO_PCI_ABI_VERSION          0
 
diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index 929ec2fb07..e8b83bbb1e 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -79,6 +79,7 @@
 #define PCI_DEVICE_ID_VIRTIO_SCSI        0x1004
 #define PCI_DEVICE_ID_VIRTIO_RNG         0x1005
 #define PCI_DEVICE_ID_VIRTIO_9P          0x1009
+#define PCI_DEVICE_ID_VIRTIO_VSOCK       0x1012
 
 #define PCI_VENDOR_ID_REDHAT             0x1b36
 #define PCI_DEVICE_ID_REDHAT_BRIDGE      0x0001
diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h
index cf7f0b5a69..6e90703cad 100644
--- a/include/hw/virtio/vhost-backend.h
+++ b/include/hw/virtio/vhost-backend.h
@@ -73,6 +73,9 @@ typedef int (*vhost_migration_done_op)(struct vhost_dev *dev,
 typedef bool (*vhost_backend_can_merge_op)(struct vhost_dev *dev,
                                            uint64_t start1, uint64_t size1,
                                            uint64_t start2, uint64_t size2);
+typedef int (*vhost_vsock_set_guest_cid_op)(struct vhost_dev *dev,
+                                            uint64_t guest_cid);
+typedef int (*vhost_vsock_set_running_op)(struct vhost_dev *dev, int start);
 
 typedef struct VhostOps {
     VhostBackendType backend_type;
@@ -102,6 +105,8 @@ typedef struct VhostOps {
     vhost_requires_shm_log_op vhost_requires_shm_log;
     vhost_migration_done_op vhost_migration_done;
     vhost_backend_can_merge_op vhost_backend_can_merge;
+    vhost_vsock_set_guest_cid_op vhost_vsock_set_guest_cid;
+    vhost_vsock_set_running_op vhost_vsock_set_running;
 } VhostOps;
 
 extern const VhostOps user_ops;
diff --git a/include/hw/virtio/vhost-vsock.h b/include/hw/virtio/vhost-vsock.h
new file mode 100644
index 0000000000..7b9205fe3f
--- /dev/null
+++ b/include/hw/virtio/vhost-vsock.h
@@ -0,0 +1,41 @@
+/*
+ * Vhost vsock virtio device
+ *
+ * Copyright 2015 Red Hat, Inc.
+ *
+ * Authors:
+ *  Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * (at your option) any later version.  See the COPYING file in the
+ * top-level directory.
+ */
+
+#ifndef _QEMU_VHOST_VSOCK_H
+#define _QEMU_VHOST_VSOCK_H
+
+#include "hw/virtio/virtio.h"
+#include "hw/virtio/vhost.h"
+
+#define TYPE_VHOST_VSOCK "vhost-vsock-device"
+#define VHOST_VSOCK(obj) \
+        OBJECT_CHECK(VHostVSock, (obj), TYPE_VHOST_VSOCK)
+
+typedef struct {
+    uint64_t guest_cid;
+    char *vhostfd;
+} VHostVSockConf;
+
+typedef struct {
+    /*< private >*/
+    VirtIODevice parent;
+    VHostVSockConf conf;
+    struct vhost_virtqueue vhost_vqs[2];
+    struct vhost_dev vhost_dev;
+    VirtQueue *event_vq;
+    QEMUTimer *post_load_timer;
+
+    /*< public >*/
+} VHostVSock;
+
+#endif /* _QEMU_VHOST_VSOCK_H */