Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

virtio,vhost,pc: fixes and updates

balloon fixes wrt migration
virtio-vsock device support

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Fri 09 Sep 2016 22:36:13 BST
# gpg:                using RSA key 0x281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream:
  vhost-vsock: add virtio sockets device
  tests/acpi: speedup acpi tests
  virtio-pci: minor refactoring
  vhost: don't set vring call if no vector
  virtio-pci: error out when both legacy and modern modes are disabled
  virtio-balloon: fix stats vq migration
  virtio: add virtqueue_rewind()
  virtio-balloon: discard virtqueue element on reset
  virtio: zero vq->inuse in virtio_reset()
  virtio-pci: reduce modern_mem_bar size
  target-i386: present virtual L3 cache info for vcpus
  pc: Add 2.8 machine
  virtio-pci: use size from correct structure
  virtio: Tell the user what went wrong when event_notifier_init failed

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

23 files changed, 825 insertions, 39 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/i386/pc_piix.c b/hw/i386/pc_piix.c
index 2af8888f0a..a54a468c0a 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -437,13 +437,25 @@ static void pc_i440fx_machine_options(MachineClass *m)
     m->default_display = "std";
 }
 
-static void pc_i440fx_2_7_machine_options(MachineClass *m)
+static void pc_i440fx_2_8_machine_options(MachineClass *m)
 {
     pc_i440fx_machine_options(m);
     m->alias = "pc";
     m->is_default = 1;
 }
 
+DEFINE_I440FX_MACHINE(v2_8, "pc-i440fx-2.8", NULL,
+                      pc_i440fx_2_8_machine_options);
+
+
+static void pc_i440fx_2_7_machine_options(MachineClass *m)
+{
+    pc_i440fx_2_8_machine_options(m);
+    m->is_default = 0;
+    m->alias = NULL;
+    SET_MACHINE_COMPAT(m, PC_COMPAT_2_7);
+}
+
 DEFINE_I440FX_MACHINE(v2_7, "pc-i440fx-2.7", NULL,
                       pc_i440fx_2_7_machine_options);
 
@@ -452,8 +464,6 @@ static void pc_i440fx_2_6_machine_options(MachineClass *m)
 {
     PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_i440fx_2_7_machine_options(m);
-    m->is_default = 0;
-    m->alias = NULL;
     pcmc->legacy_cpu_hotplug = true;
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_6);
 }
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 3cbcbb0c7e..0b214f24c9 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -293,12 +293,22 @@ static void pc_q35_machine_options(MachineClass *m)
     m->has_dynamic_sysbus = true;
 }
 
-static void pc_q35_2_7_machine_options(MachineClass *m)
+static void pc_q35_2_8_machine_options(MachineClass *m)
 {
     pc_q35_machine_options(m);
     m->alias = "q35";
 }
 
+DEFINE_Q35_MACHINE(v2_8, "pc-q35-2.8", NULL,
+                   pc_q35_2_8_machine_options);
+
+static void pc_q35_2_7_machine_options(MachineClass *m)
+{
+    pc_q35_2_8_machine_options(m);
+    m->alias = NULL;
+    SET_MACHINE_COMPAT(m, PC_COMPAT_2_7);
+}
+
 DEFINE_Q35_MACHINE(v2_7, "pc-q35-2.7", NULL,
                    pc_q35_2_7_machine_options);
 
@@ -306,7 +316,6 @@ static void pc_q35_2_6_machine_options(MachineClass *m)
 {
     PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_q35_2_7_machine_options(m);
-    m->alias = NULL;
     pcmc->legacy_cpu_hotplug = true;
     SET_MACHINE_COMPAT(m, PC_COMPAT_2_6);
 }
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/vhost.c b/hw/virtio/vhost.c
index 3d0c807d0e..bd051ab2e1 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -822,6 +822,9 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
                                 struct vhost_virtqueue *vq,
                                 unsigned idx)
 {
+    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
+    VirtioBusState *vbus = VIRTIO_BUS(qbus);
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus);
     hwaddr s, l, a;
     int r;
     int vhost_vq_index = dev->vhost_ops->vhost_get_vq_index(dev, idx);
@@ -912,8 +915,19 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
         vhost_virtqueue_mask(dev, vdev, idx, false);
     }
 
+    if (k->query_guest_notifiers &&
+        k->query_guest_notifiers(qbus->parent) &&
+        virtio_queue_vector(vdev, idx) == VIRTIO_NO_VECTOR) {
+        file.fd = -1;
+        r = dev->vhost_ops->vhost_set_vring_call(dev, &file);
+        if (r) {
+            goto fail_vector;
+        }
+    }
+
     return 0;
 
+fail_vector:
 fail_kick:
 fail_alloc:
     cpu_physical_memory_unmap(vq->ring, virtio_queue_get_ring_size(vdev, idx),
diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
index 5af429a58a..49a2f4aade 100644
--- a/hw/virtio/virtio-balloon.c
+++ b/hw/virtio/virtio-balloon.c
@@ -463,11 +463,24 @@ static void virtio_balloon_device_reset(VirtIODevice *vdev)
     VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
 
     if (s->stats_vq_elem != NULL) {
+        virtqueue_discard(s->svq, s->stats_vq_elem, 0);
         g_free(s->stats_vq_elem);
         s->stats_vq_elem = NULL;
     }
 }
 
+static void virtio_balloon_set_status(VirtIODevice *vdev, uint8_t status)
+{
+    VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
+
+    if (!s->stats_vq_elem && vdev->vm_running &&
+        (status & VIRTIO_CONFIG_S_DRIVER_OK) && virtqueue_rewind(s->svq, 1)) {
+        /* poll stats queue for the element we have discarded when the VM
+         * was stopped */
+        virtio_balloon_receive_stats(vdev, s->svq);
+    }
+}
+
 static void virtio_balloon_instance_init(Object *obj)
 {
     VirtIOBalloon *s = VIRTIO_BALLOON(obj);
@@ -505,6 +518,7 @@ static void virtio_balloon_class_init(ObjectClass *klass, void *data)
     vdc->get_features = virtio_balloon_get_features;
     vdc->save = virtio_balloon_save_device;
     vdc->load = virtio_balloon_load_device;
+    vdc->set_status = virtio_balloon_set_status;
 }
 
 static const TypeInfo virtio_balloon_info = {
diff --git a/hw/virtio/virtio-bus.c b/hw/virtio/virtio-bus.c
index a85b7c8abe..14927935ae 100644
--- a/hw/virtio/virtio-bus.c
+++ b/hw/virtio/virtio-bus.c
@@ -164,7 +164,8 @@ static int set_host_notifier_internal(DeviceState *proxy, VirtioBusState *bus,
     if (assign) {
         r = event_notifier_init(notifier, 1);
         if (r < 0) {
-            error_report("%s: unable to init event notifier: %d", __func__, r);
+            error_report("%s: unable to init event notifier: %s (%d)",
+                         __func__, strerror(-r), r);
             return r;
         }
         virtio_queue_set_host_notifier_fd_handler(vq, true, set_handler);
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 755f9218b7..dde71a5965 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -294,6 +294,12 @@ static void virtio_pci_ioeventfd_set_disabled(DeviceState *d, bool disabled)
 
 #define QEMU_VIRTIO_PCI_QUEUE_MEM_MULT 0x1000
 
+static inline int virtio_pci_queue_mem_mult(struct VirtIOPCIProxy *proxy)
+{
+    return (proxy->flags & VIRTIO_PCI_FLAG_PAGE_PER_VQ) ?
+        QEMU_VIRTIO_PCI_QUEUE_MEM_MULT : 4;
+}
+
 static int virtio_pci_ioeventfd_assign(DeviceState *d, EventNotifier *notifier,
                                        int n, bool assign)
 {
@@ -307,7 +313,7 @@ static int virtio_pci_ioeventfd_assign(DeviceState *d, EventNotifier *notifier,
     MemoryRegion *modern_mr = &proxy->notify.mr;
     MemoryRegion *modern_notify_mr = &proxy->notify_pio.mr;
     MemoryRegion *legacy_mr = &proxy->bar;
-    hwaddr modern_addr = QEMU_VIRTIO_PCI_QUEUE_MEM_MULT *
+    hwaddr modern_addr = virtio_pci_queue_mem_mult(proxy) *
                          virtio_get_queue_index(vq);
     hwaddr legacy_addr = VIRTIO_PCI_QUEUE_NOTIFY;
 
@@ -1370,7 +1376,8 @@ static void virtio_pci_notify_write(void *opaque, hwaddr addr,
                                     uint64_t val, unsigned size)
 {
     VirtIODevice *vdev = opaque;
-    unsigned queue = addr / QEMU_VIRTIO_PCI_QUEUE_MEM_MULT;
+    VirtIOPCIProxy *proxy = VIRTIO_PCI(DEVICE(vdev)->parent_bus->parent);
+    unsigned queue = addr / virtio_pci_queue_mem_mult(proxy);
 
     if (queue < VIRTIO_QUEUE_MAX) {
         virtio_queue_notify(vdev, queue);
@@ -1520,7 +1527,7 @@ static void virtio_pci_modern_regions_init(VirtIOPCIProxy *proxy)
                           &notify_pio_ops,
                           virtio_bus_get_device(&proxy->bus),
                           "virtio-pci-notify-pio",
-                          proxy->notify.size);
+                          proxy->notify_pio.size);
 }
 
 static void virtio_pci_modern_region_map(VirtIOPCIProxy *proxy,
@@ -1609,7 +1616,7 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
         struct virtio_pci_notify_cap notify = {
             .cap.cap_len = sizeof notify,
             .notify_off_multiplier =
-                cpu_to_le32(QEMU_VIRTIO_PCI_QUEUE_MEM_MULT),
+                cpu_to_le32(virtio_pci_queue_mem_mult(proxy)),
         };
         struct virtio_pci_cfg_cap cfg = {
             .cap.cap_len = sizeof cfg,
@@ -1744,8 +1751,7 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
     proxy->device.type = VIRTIO_PCI_CAP_DEVICE_CFG;
 
     proxy->notify.offset = 0x3000;
-    proxy->notify.size =
-        QEMU_VIRTIO_PCI_QUEUE_MEM_MULT * VIRTIO_QUEUE_MAX;
+    proxy->notify.size = virtio_pci_queue_mem_mult(proxy) * VIRTIO_QUEUE_MAX;
     proxy->notify.type = VIRTIO_PCI_CAP_NOTIFY_CFG;
 
     proxy->notify_pio.offset = 0x0;
@@ -1754,8 +1760,8 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
 
     /* subclasses can enforce modern, so do this unconditionally */
     memory_region_init(&proxy->modern_bar, OBJECT(proxy), "virtio-pci",
-                       2 * QEMU_VIRTIO_PCI_QUEUE_MEM_MULT *
-                       VIRTIO_QUEUE_MAX);
+                       /* PCI BAR regions must be powers of 2 */
+                       pow2ceil(proxy->notify.offset + proxy->notify.size));
 
     memory_region_init_alias(&proxy->modern_cfg,
                              OBJECT(proxy),
@@ -1770,6 +1776,14 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
         proxy->disable_legacy = pcie_port ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
     }
 
+    if (!virtio_pci_modern(proxy) && !virtio_pci_legacy(proxy)) {
+        error_setg(errp, "device cannot work as neither modern nor legacy mode"
+                   " is enabled");
+        error_append_hint(errp, "Set either disable-modern or disable-legacy"
+                          " to off\n");
+        return;
+    }
+
     if (pcie_port && pci_is_express(pci_dev)) {
         int pos;
 
@@ -1833,6 +1847,8 @@ static Property virtio_pci_properties[] = {
                     VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT, false),
     DEFINE_PROP_BIT("x-disable-pcie", VirtIOPCIProxy, flags,
                     VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT, false),
+    DEFINE_PROP_BIT("page-per-vq", VirtIOPCIProxy, flags,
+                    VIRTIO_PCI_FLAG_PAGE_PER_VQ_BIT, false),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -2055,6 +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[] = {
@@ -2485,6 +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 25fbf8a375..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 */
 
@@ -64,6 +68,7 @@ enum {
     VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT,
     VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT,
     VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT,
+    VIRTIO_PCI_FLAG_PAGE_PER_VQ_BIT,
 };
 
 /* Need to activate work-arounds for buggy guests at vmstate load. */
@@ -84,6 +89,10 @@ enum {
 #define VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY \
     (1 << VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT)
 
+/* page per vq flag to be used by split drivers within guests */
+#define VIRTIO_PCI_FLAG_PAGE_PER_VQ \
+    (1 << VIRTIO_PCI_FLAG_PAGE_PER_VQ_BIT)
+
 typedef struct {
     MSIMessage msg;
     int virq;
@@ -324,6 +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/hw/virtio/virtio.c b/hw/virtio/virtio.c
index 74c085c74d..fcf3358d6c 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -272,6 +272,28 @@ void virtqueue_discard(VirtQueue *vq, const VirtQueueElement *elem,
     virtqueue_unmap_sg(vq, elem, len);
 }
 
+/* virtqueue_rewind:
+ * @vq: The #VirtQueue
+ * @num: Number of elements to push back
+ *
+ * Pretend that elements weren't popped from the virtqueue.  The next
+ * virtqueue_pop() will refetch the oldest element.
+ *
+ * Use virtqueue_discard() instead if you have a VirtQueueElement.
+ *
+ * Returns: true on success, false if @num is greater than the number of in use
+ * elements.
+ */
+bool virtqueue_rewind(VirtQueue *vq, unsigned int num)
+{
+    if (num > vq->inuse) {
+        return false;
+    }
+    vq->last_avail_idx -= num;
+    vq->inuse -= num;
+    return true;
+}
+
 void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem,
                     unsigned int len, unsigned int idx)
 {
@@ -822,6 +844,7 @@ void virtio_reset(void *opaque)
         vdev->vq[i].signalled_used_valid = false;
         vdev->vq[i].notification = true;
         vdev->vq[i].vring.num = vdev->vq[i].vring.num_default;
+        vdev->vq[i].inuse = 0;
     }
 }
 
diff --git a/include/hw/compat.h b/include/hw/compat.h
index 08dd4fbec2..a1d6694492 100644
--- a/include/hw/compat.h
+++ b/include/hw/compat.h
@@ -2,7 +2,11 @@
 #define HW_COMPAT_H
 
 #define HW_COMPAT_2_7 \
-        /* empty */
+    {\
+        .driver   = "virtio-pci",\
+        .property = "page-per-vq",\
+        .value    = "on",\
+    },
 
 #define HW_COMPAT_2_6 \
     {\
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index c4316c30a8..ebba151097 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -368,6 +368,18 @@ int e820_add_entry(uint64_t, uint64_t, uint32_t);
 int e820_get_num_entries(void);
 bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *);
 
+#define PC_COMPAT_2_8 \
+    {\
+        .driver   = TYPE_X86_CPU,\
+        .property = "l3-cache",\
+        .value    = "off",\
+    },
+
+
+#define PC_COMPAT_2_7 \
+    PC_COMPAT_2_8 \
+    HW_COMPAT_2_7
+
 #define PC_COMPAT_2_6 \
     HW_COMPAT_2_6 \
     {\
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 */
diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h
index d2490c1975..f05559d569 100644
--- a/include/hw/virtio/virtio.h
+++ b/include/hw/virtio/virtio.h
@@ -154,6 +154,7 @@ void virtqueue_push(VirtQueue *vq, const VirtQueueElement *elem,
 void virtqueue_flush(VirtQueue *vq, unsigned int count);
 void virtqueue_discard(VirtQueue *vq, const VirtQueueElement *elem,
                        unsigned int len);
+bool virtqueue_rewind(VirtQueue *vq, unsigned int num);
 void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem,
                     unsigned int len, unsigned int idx);
 
diff --git a/target-i386/cpu.c b/target-i386/cpu.c
index ec674dcb73..5a5299ad3c 100644
--- a/target-i386/cpu.c
+++ b/target-i386/cpu.c
@@ -57,6 +57,7 @@
 #define CPUID_2_L1D_32KB_8WAY_64B 0x2c
 #define CPUID_2_L1I_32KB_8WAY_64B 0x30
 #define CPUID_2_L2_2MB_8WAY_64B   0x7d
+#define CPUID_2_L3_16MB_16WAY_64B 0x4d
 
 
 /* CPUID Leaf 4 constants: */
@@ -131,11 +132,18 @@
 #define L2_LINES_PER_TAG       1
 #define L2_SIZE_KB_AMD       512
 
-/* No L3 cache: */
+/* Level 3 unified cache: */
 #define L3_SIZE_KB             0 /* disabled */
 #define L3_ASSOCIATIVITY       0 /* disabled */
 #define L3_LINES_PER_TAG       0 /* disabled */
 #define L3_LINE_SIZE           0 /* disabled */
+#define L3_N_LINE_SIZE         64
+#define L3_N_ASSOCIATIVITY     16
+#define L3_N_SETS           16384
+#define L3_N_PARTITIONS         1
+#define L3_N_DESCRIPTOR CPUID_2_L3_16MB_16WAY_64B
+#define L3_N_LINES_PER_TAG      1
+#define L3_N_SIZE_KB_AMD    16384
 
 /* TLB definitions: */
 
@@ -2279,6 +2287,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
 {
     X86CPU *cpu = x86_env_get_cpu(env);
     CPUState *cs = CPU(cpu);
+    uint32_t pkg_offset;
 
     /* test if maximum index reached */
     if (index & 0x80000000) {
@@ -2332,7 +2341,11 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
         }
         *eax = 1; /* Number of CPUID[EAX=2] calls required */
         *ebx = 0;
-        *ecx = 0;
+        if (!cpu->enable_l3_cache) {
+            *ecx = 0;
+        } else {
+            *ecx = L3_N_DESCRIPTOR;
+        }
         *edx = (L1D_DESCRIPTOR << 16) | \
                (L1I_DESCRIPTOR <<  8) | \
                (L2_DESCRIPTOR);
@@ -2378,6 +2391,25 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
                 *ecx = L2_SETS - 1;
                 *edx = CPUID_4_NO_INVD_SHARING;
                 break;
+            case 3: /* L3 cache info */
+                if (!cpu->enable_l3_cache) {
+                    *eax = 0;
+                    *ebx = 0;
+                    *ecx = 0;
+                    *edx = 0;
+                    break;
+                }
+                *eax |= CPUID_4_TYPE_UNIFIED | \
+                        CPUID_4_LEVEL(3) | \
+                        CPUID_4_SELF_INIT_LEVEL;
+                pkg_offset = apicid_pkg_offset(cs->nr_cores, cs->nr_threads);
+                *eax |= ((1 << pkg_offset) - 1) << 14;
+                *ebx = (L3_N_LINE_SIZE - 1) | \
+                       ((L3_N_PARTITIONS - 1) << 12) | \
+                       ((L3_N_ASSOCIATIVITY - 1) << 22);
+                *ecx = L3_N_SETS - 1;
+                *edx = CPUID_4_INCLUSIVE | CPUID_4_COMPLEX_IDX;
+                break;
             default: /* end of info */
                 *eax = 0;
                 *ebx = 0;
@@ -2589,9 +2621,15 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
         *ecx = (L2_SIZE_KB_AMD << 16) | \
                (AMD_ENC_ASSOC(L2_ASSOCIATIVITY) << 12) | \
                (L2_LINES_PER_TAG << 8) | (L2_LINE_SIZE);
-        *edx = ((L3_SIZE_KB/512) << 18) | \
-               (AMD_ENC_ASSOC(L3_ASSOCIATIVITY) << 12) | \
-               (L3_LINES_PER_TAG << 8) | (L3_LINE_SIZE);
+        if (!cpu->enable_l3_cache) {
+            *edx = ((L3_SIZE_KB / 512) << 18) | \
+                   (AMD_ENC_ASSOC(L3_ASSOCIATIVITY) << 12) | \
+                   (L3_LINES_PER_TAG << 8) | (L3_LINE_SIZE);
+        } else {
+            *edx = ((L3_N_SIZE_KB_AMD / 512) << 18) | \
+                   (AMD_ENC_ASSOC(L3_N_ASSOCIATIVITY) << 12) | \
+                   (L3_N_LINES_PER_TAG << 8) | (L3_N_LINE_SIZE);
+        }
         break;
     case 0x80000007:
         *eax = 0;
@@ -3368,6 +3406,7 @@ static Property x86_cpu_properties[] = {
     DEFINE_PROP_STRING("hv-vendor-id", X86CPU, hyperv_vendor_id),
     DEFINE_PROP_BOOL("cpuid-0xb", X86CPU, enable_cpuid_0xb, true),
     DEFINE_PROP_BOOL("lmce", X86CPU, enable_lmce, false),
+    DEFINE_PROP_BOOL("l3-cache", X86CPU, enable_l3_cache, true),
     DEFINE_PROP_END_OF_LIST()
 };
 
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index cf14bcb6d0..bb3ffda244 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -1207,6 +1207,12 @@ struct X86CPU {
      */
     bool enable_lmce;
 
+    /* Compatibility bits for old machine types.
+     * If true present virtual l3 cache for VM, the vcpus in the same virtual
+     * socket share an virtual l3 cache.
+     */
+    bool enable_l3_cache;
+
     /* Compatibility bits for old machine types: */
     bool enable_cpuid_0xb;
 
diff --git a/tests/bios-tables-test.c b/tests/bios-tables-test.c
index de4019e57d..7e27ea95ad 100644
--- a/tests/bios-tables-test.c
+++ b/tests/bios-tables-test.c
@@ -711,9 +711,12 @@ static void test_acpi_one(const char *params, test_data *data)
 {
     char *args;
 
-    args = g_strdup_printf("-net none -display none %s "
+    /* Disable kernel irqchip to be able to override apic irq0. */
+    args = g_strdup_printf("-machine %s,accel=%s,kernel-irqchip=off "
+                           "-net none -display none %s "
                            "-drive id=hd0,if=none,file=%s,format=raw "
                            "-device ide-hd,drive=hd0 ",
+                           data->machine, "kvm:tcg",
                            params ? params : "", disk);
 
     qtest_start(args);
@@ -758,7 +761,7 @@ static void test_acpi_piix4_tcg(void)
     data.machine = MACHINE_PC;
     data.required_struct_types = base_required_struct_types;
     data.required_struct_types_len = ARRAY_SIZE(base_required_struct_types);
-    test_acpi_one("-machine accel=tcg", &data);
+    test_acpi_one(NULL, &data);
     free_test_data(&data);
 }
 
@@ -771,7 +774,7 @@ static void test_acpi_piix4_tcg_bridge(void)
     data.variant = ".bridge";
     data.required_struct_types = base_required_struct_types;
     data.required_struct_types_len = ARRAY_SIZE(base_required_struct_types);
-    test_acpi_one("-machine accel=tcg -device pci-bridge,chassis_nr=1", &data);
+    test_acpi_one("-device pci-bridge,chassis_nr=1", &data);
     free_test_data(&data);
 }
 
@@ -783,7 +786,7 @@ static void test_acpi_q35_tcg(void)
     data.machine = MACHINE_Q35;
     data.required_struct_types = base_required_struct_types;
     data.required_struct_types_len = ARRAY_SIZE(base_required_struct_types);
-    test_acpi_one("-machine q35,accel=tcg", &data);
+    test_acpi_one(NULL, &data);
     free_test_data(&data);
 }
 
@@ -796,7 +799,7 @@ static void test_acpi_q35_tcg_bridge(void)
     data.variant = ".bridge";
     data.required_struct_types = base_required_struct_types;
     data.required_struct_types_len = ARRAY_SIZE(base_required_struct_types);
-    test_acpi_one("-machine q35,accel=tcg -device pci-bridge,chassis_nr=1",
+    test_acpi_one("-device pci-bridge,chassis_nr=1",
                   &data);
     free_test_data(&data);
 }
@@ -808,8 +811,7 @@ static void test_acpi_piix4_tcg_cphp(void)
     memset(&data, 0, sizeof(data));
     data.machine = MACHINE_PC;
     data.variant = ".cphp";
-    test_acpi_one("-machine accel=tcg"
-                  " -smp 2,cores=3,sockets=2,maxcpus=6",
+    test_acpi_one("-smp 2,cores=3,sockets=2,maxcpus=6",
                   &data);
     free_test_data(&data);
 }
@@ -821,8 +823,7 @@ static void test_acpi_q35_tcg_cphp(void)
     memset(&data, 0, sizeof(data));
     data.machine = MACHINE_Q35;
     data.variant = ".cphp";
-    test_acpi_one("-machine q35,accel=tcg"
-                  " -smp 2,cores=3,sockets=2,maxcpus=6",
+    test_acpi_one(" -smp 2,cores=3,sockets=2,maxcpus=6",
                   &data);
     free_test_data(&data);
 }
@@ -840,7 +841,7 @@ static void test_acpi_q35_tcg_ipmi(void)
     data.variant = ".ipmibt";
     data.required_struct_types = ipmi_required_struct_types;
     data.required_struct_types_len = ARRAY_SIZE(ipmi_required_struct_types);
-    test_acpi_one("-machine q35,accel=tcg -device ipmi-bmc-sim,id=bmc0"
+    test_acpi_one("-device ipmi-bmc-sim,id=bmc0"
                   " -device isa-ipmi-bt,bmc=bmc0",
                   &data);
     free_test_data(&data);
@@ -858,7 +859,7 @@ static void test_acpi_piix4_tcg_ipmi(void)
     data.variant = ".ipmikcs";
     data.required_struct_types = ipmi_required_struct_types;
     data.required_struct_types_len = ARRAY_SIZE(ipmi_required_struct_types);
-    test_acpi_one("-machine accel=tcg -device ipmi-bmc-sim,id=bmc0"
+    test_acpi_one("-device ipmi-bmc-sim,id=bmc0"
                   " -device isa-ipmi-kcs,irq=0,bmc=bmc0",
                   &data);
     free_test_data(&data);
@@ -876,14 +877,14 @@ int main(int argc, char *argv[])
     g_test_init(&argc, &argv, NULL);
 
     if (strcmp(arch, "i386") == 0 || strcmp(arch, "x86_64") == 0) {
-        qtest_add_func("acpi/piix4/tcg", test_acpi_piix4_tcg);
-        qtest_add_func("acpi/piix4/tcg/bridge", test_acpi_piix4_tcg_bridge);
-        qtest_add_func("acpi/q35/tcg", test_acpi_q35_tcg);
-        qtest_add_func("acpi/q35/tcg/bridge", test_acpi_q35_tcg_bridge);
-        qtest_add_func("acpi/piix4/tcg/ipmi", test_acpi_piix4_tcg_ipmi);
-        qtest_add_func("acpi/q35/tcg/ipmi", test_acpi_q35_tcg_ipmi);
-        qtest_add_func("acpi/piix4/tcg/cpuhp", test_acpi_piix4_tcg_cphp);
-        qtest_add_func("acpi/q35/tcg/cpuhp", test_acpi_q35_tcg_cphp);
+        qtest_add_func("acpi/piix4", test_acpi_piix4_tcg);
+        qtest_add_func("acpi/piix4/bridge", test_acpi_piix4_tcg_bridge);
+        qtest_add_func("acpi/q35", test_acpi_q35_tcg);
+        qtest_add_func("acpi/q35/bridge", test_acpi_q35_tcg_bridge);
+        qtest_add_func("acpi/piix4/ipmi", test_acpi_piix4_tcg_ipmi);
+        qtest_add_func("acpi/q35/ipmi", test_acpi_q35_tcg_ipmi);
+        qtest_add_func("acpi/piix4/cpuhp", test_acpi_piix4_tcg_cphp);
+        qtest_add_func("acpi/q35/cpuhp", test_acpi_q35_tcg_cphp);
     }
     ret = g_test_run();
     boot_sector_cleanup(disk);