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

virtio,pc features, fixes

New features:
    vhost-user multiqueue support
    virtio-ccw virtio 1 support

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

# gpg: Signature made Fri 25 Sep 2015 07:40:35 BST using RSA key ID D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"

* remotes/mst/tags/for_upstream:
  MAINTAINERS: add more devices to the PCI section
  MAINTAINERS: add more devices to the PC section
  vhost-user: add a new message to disable/enable a specific virt queue.
  vhost-user: add multiple queue support
  vhost: introduce vhost_backend_get_vq_index method
  vhost-user: add VHOST_USER_GET_QUEUE_NUM message
  vhost: rename VHOST_RESET_OWNER to VHOST_RESET_DEVICE
  vhost-user: add protocol feature negotiation
  vhost-user: use VHOST_USER_XXX macro for switch statement
  virtio-ccw: enable virtio-1
  virtio-ccw: feature bits > 31 handling
  virtio-ccw: support ring size changes
  virtio: ring sizes vs. reset
  pc: Introduce pc-*-2.5 machine classes
  q35: Move options common to all classes to pc_i440fx_machine_options()
  q35: Move options common to all classes to pc_q35_machine_options()
  virtio-net: unbreak self announcement and guest offloads after migration
  virtio: right size for virtio_queue_get_avail_size

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

11 files changed, 375 insertions, 86 deletions

diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 3f925b26db..3ffb05f93e 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -460,19 +460,31 @@ static void pc_i440fx_machine_options(MachineClass *m)
     m->family = "pc_piix";
     m->desc = "Standard PC (i440FX + PIIX, 1996)";
     m->hot_add_cpu = pc_hot_add_cpu;
+    m->default_machine_opts = "firmware=bios-256k.bin";
+    m->default_display = "std";
 }
 
-static void pc_i440fx_2_4_machine_options(MachineClass *m)
+static void pc_i440fx_2_5_machine_options(MachineClass *m)
 {
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_i440fx_machine_options(m);
-    pcmc->broken_reserved_end = true;
-    m->default_machine_opts = "firmware=bios-256k.bin";
-    m->default_display = "std";
     m->alias = "pc";
     m->is_default = 1;
 }
 
+DEFINE_I440FX_MACHINE(v2_5, "pc-i440fx-2.5", NULL,
+                      pc_i440fx_2_5_machine_options);
+
+
+static void pc_i440fx_2_4_machine_options(MachineClass *m)
+{
+    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+    pc_i440fx_2_5_machine_options(m);
+    m->alias = NULL;
+    m->is_default = 0;
+    pcmc->broken_reserved_end = true;
+    SET_MACHINE_COMPAT(m, PC_COMPAT_2_4);
+}
+
 DEFINE_I440FX_MACHINE(v2_4, "pc-i440fx-2.4", NULL,
                       pc_i440fx_2_4_machine_options)
 
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 11601ab005..1b7d3b644e 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -364,18 +364,28 @@ static void pc_q35_machine_options(MachineClass *m)
     m->desc = "Standard PC (Q35 + ICH9, 2009)";
     m->hot_add_cpu = pc_hot_add_cpu;
     m->units_per_default_bus = 1;
+    m->default_machine_opts = "firmware=bios-256k.bin";
+    m->default_display = "std";
+    m->no_floppy = 1;
+    m->no_tco = 0;
+}
+
+static void pc_q35_2_5_machine_options(MachineClass *m)
+{
+    pc_q35_machine_options(m);
+    m->alias = "q35";
 }
 
+DEFINE_Q35_MACHINE(v2_5, "pc-q35-2.5", NULL,
+                   pc_q35_2_5_machine_options);
+
 static void pc_q35_2_4_machine_options(MachineClass *m)
 {
     PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
-    pc_q35_machine_options(m);
+    pc_q35_2_5_machine_options(m);
+    m->alias = NULL;
     pcmc->broken_reserved_end = true;
-    m->default_machine_opts = "firmware=bios-256k.bin";
-    m->default_display = "std";
-    m->no_floppy = 1;
-    m->no_tco = 0;
-    m->alias = "q35";
+    SET_MACHINE_COMPAT(m, PC_COMPAT_2_4);
 }
 
 DEFINE_Q35_MACHINE(v2_4, "pc-q35-2.4", NULL,
diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index 1d76b94c84..2bce89129d 100644
--- a/hw/net/vhost_net.c
+++ b/hw/net/vhost_net.c
@@ -122,6 +122,11 @@ void vhost_net_ack_features(struct vhost_net *net, uint64_t features)
     vhost_ack_features(&net->dev, vhost_net_get_feature_bits(net), features);
 }
 
+uint64_t vhost_net_get_max_queues(VHostNetState *net)
+{
+    return net->dev.max_queues;
+}
+
 static int vhost_net_get_fd(NetClientState *backend)
 {
     switch (backend->info->type) {
@@ -143,6 +148,11 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options)
         fprintf(stderr, "vhost-net requires net backend to be setup\n");
         goto fail;
     }
+    net->nc = options->net_backend;
+
+    net->dev.max_queues = 1;
+    net->dev.nvqs = 2;
+    net->dev.vqs = net->vqs;
 
     if (backend_kernel) {
         r = vhost_net_get_fd(options->net_backend);
@@ -152,14 +162,15 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options)
         net->dev.backend_features = qemu_has_vnet_hdr(options->net_backend)
             ? 0 : (1ULL << VHOST_NET_F_VIRTIO_NET_HDR);
         net->backend = r;
+        net->dev.protocol_features = 0;
     } else {
         net->dev.backend_features = 0;
+        net->dev.protocol_features = 0;
         net->backend = -1;
-    }
-    net->nc = options->net_backend;
 
-    net->dev.nvqs = 2;
-    net->dev.vqs = net->vqs;
+        /* vhost-user needs vq_index to initiate a specific queue pair */
+        net->dev.vq_index = net->nc->queue_index * net->dev.nvqs;
+    }
 
     r = vhost_dev_init(&net->dev, options->opaque,
                        options->backend_type);
@@ -285,7 +296,7 @@ static void vhost_net_stop_one(struct vhost_net *net,
     } else if (net->nc->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER) {
         for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
             const VhostOps *vhost_ops = net->dev.vhost_ops;
-            int r = vhost_ops->vhost_call(&net->dev, VHOST_RESET_OWNER,
+            int r = vhost_ops->vhost_call(&net->dev, VHOST_RESET_DEVICE,
                                           NULL);
             assert(r >= 0);
         }
@@ -411,7 +422,25 @@ VHostNetState *get_vhost_net(NetClientState *nc)
 
     return vhost_net;
 }
+
+int vhost_set_vring_enable(NetClientState *nc, int enable)
+{
+    VHostNetState *net = get_vhost_net(nc);
+    const VhostOps *vhost_ops = net->dev.vhost_ops;
+
+    if (vhost_ops->vhost_backend_set_vring_enable) {
+        return vhost_ops->vhost_backend_set_vring_enable(&net->dev, enable);
+    }
+
+    return 0;
+}
+
 #else
+uint64_t vhost_net_get_max_queues(VHostNetState *net)
+{
+    return 1;
+}
+
 struct vhost_net *vhost_net_init(VhostNetOptions *options)
 {
     error_report("vhost-net support is not compiled in");
@@ -456,4 +485,9 @@ VHostNetState *get_vhost_net(NetClientState *nc)
 {
     return 0;
 }
+
+int vhost_set_vring_enable(NetClientState *nc, int enable)
+{
+    return 0;
+}
 #endif
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index f72eebff2b..d388c5571d 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -406,6 +406,10 @@ static int peer_attach(VirtIONet *n, int index)
         return 0;
     }
 
+    if (nc->peer->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER) {
+        vhost_set_vring_enable(nc->peer, 1);
+    }
+
     if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) {
         return 0;
     }
@@ -421,6 +425,10 @@ static int peer_detach(VirtIONet *n, int index)
         return 0;
     }
 
+    if (nc->peer->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER) {
+        vhost_set_vring_enable(nc->peer, 0);
+    }
+
     if (nc->peer->info->type !=  NET_CLIENT_OPTIONS_KIND_TAP) {
         return 0;
     }
@@ -1458,11 +1466,33 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int version_id)
 {
     VirtIONet *n = opaque;
     VirtIODevice *vdev = VIRTIO_DEVICE(n);
+    int ret;
 
     if (version_id < 2 || version_id > VIRTIO_NET_VM_VERSION)
         return -EINVAL;
 
-    return virtio_load(vdev, f, version_id);
+    ret = virtio_load(vdev, f, version_id);
+    if (ret) {
+        return ret;
+    }
+
+    if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) {
+        n->curr_guest_offloads = qemu_get_be64(f);
+    } else {
+        n->curr_guest_offloads = virtio_net_supported_guest_offloads(n);
+    }
+
+    if (peer_has_vnet_hdr(n)) {
+        virtio_net_apply_guest_offloads(n);
+    }
+
+    if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_GUEST_ANNOUNCE) &&
+        virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) {
+        n->announce_counter = SELF_ANNOUNCE_ROUNDS;
+        timer_mod(n->announce_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL));
+    }
+
+    return 0;
 }
 
 static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f,
@@ -1559,16 +1589,6 @@ static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f,
         }
     }
 
-    if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) {
-        n->curr_guest_offloads = qemu_get_be64(f);
-    } else {
-        n->curr_guest_offloads = virtio_net_supported_guest_offloads(n);
-    }
-
-    if (peer_has_vnet_hdr(n)) {
-        virtio_net_apply_guest_offloads(n);
-    }
-
     virtio_net_set_queues(n);
 
     /* Find the first multicast entry in the saved MAC filter */
@@ -1586,12 +1606,6 @@ static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f,
         qemu_get_subqueue(n->nic, i)->link_down = link_down;
     }
 
-    if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_GUEST_ANNOUNCE) &&
-        virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) {
-        n->announce_counter = SELF_ANNOUNCE_ROUNDS;
-        timer_mod(n->announce_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL));
-    }
-
     return 0;
 }
 
diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 36f78b417c..c53ebc1ae1 100644
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -242,6 +242,26 @@ static const TypeInfo ccw_machine_info = {
             .driver   = TYPE_S390_SKEYS,\
             .property = "migration-enabled",\
             .value    = "off",\
+        },{\
+            .driver   = "virtio-blk-ccw",\
+            .property = "max_revision",\
+            .value    = "0",\
+        },{\
+            .driver   = "virtio-balloon-ccw",\
+            .property = "max_revision",\
+            .value    = "0",\
+        },{\
+            .driver   = "virtio-serial-ccw",\
+            .property = "max_revision",\
+            .value    = "0",\
+        },{\
+            .driver   = "virtio-9p-ccw",\
+            .property = "max_revision",\
+            .value    = "0",\
+        },{\
+            .driver   = "virtio-rng-ccw",\
+            .property = "max_revision",\
+            .value    = "0",\
         },
 
 static void ccw_machine_2_4_class_init(ObjectClass *oc, void *data)
diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c
index d36373e88a..fb103b78ac 100644
--- a/hw/s390x/virtio-ccw.c
+++ b/hw/s390x/virtio-ccw.c
@@ -307,11 +307,18 @@ static int virtio_ccw_set_vqs(SubchDev *sch, VqInfoBlock *info,
     if (!desc) {
         virtio_queue_set_vector(vdev, index, VIRTIO_NO_VECTOR);
     } else {
-        /* Fail if we don't have a big enough queue. */
-        /* TODO: Add interface to handle vring.num changing */
-        if (virtio_queue_get_num(vdev, index) > num) {
+        if (info) {
+            /* virtio-1 allows changing the ring size. */
+            if (virtio_queue_get_num(vdev, index) < num) {
+                /* Fail if we exceed the maximum number. */
+                return -EINVAL;
+            }
+            virtio_queue_set_num(vdev, index, num);
+        } else if (virtio_queue_get_num(vdev, index) > num) {
+            /* Fail if we don't have a big enough queue. */
             return -EINVAL;
         }
+        /* We ignore possible increased num for legacy for compatibility. */
         virtio_queue_set_vector(vdev, index, index);
     }
     /* tell notify handler in case of config change */
@@ -460,16 +467,19 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
                                                 MEMTXATTRS_UNSPECIFIED,
                                                 NULL);
             if (features.index == 0) {
-                features.features = (uint32_t)vdev->host_features;
-            } else if (features.index == 1) {
-                features.features = (uint32_t)(vdev->host_features >> 32);
+                if (dev->revision >= 1) {
+                    /* Don't offer legacy features for modern devices. */
+                    features.features = (uint32_t)
+                        (vdev->host_features & ~VIRTIO_LEGACY_FEATURES);
+                } else {
+                    features.features = (uint32_t)vdev->host_features;
+                }
+            } else if ((features.index == 1) && (dev->revision >= 1)) {
                 /*
-                 * Don't offer version 1 to the guest if it did not
-                 * negotiate at least revision 1.
+                 * Only offer feature bits beyond 31 if the guest has
+                 * negotiated at least revision 1.
                  */
-                if (dev->revision <= 0) {
-                    features.features &= ~(1 << (VIRTIO_F_VERSION_1 - 32));
-                }
+                features.features = (uint32_t)(vdev->host_features >> 32);
             } else {
                 /* Return zeroes if the guest supports more feature bits. */
                 features.features = 0;
@@ -508,14 +518,12 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
                 virtio_set_features(vdev,
                                     (vdev->guest_features & 0xffffffff00000000ULL) |
                                     features.features);
-            } else if (features.index == 1) {
+            } else if ((features.index == 1) && (dev->revision >= 1)) {
                 /*
-                 * The guest should not set version 1 if it didn't
-                 * negotiate a revision >= 1.
+                 * If the guest did not negotiate at least revision 1,
+                 * we did not offer it any feature bits beyond 31. Such a
+                 * guest passing us any bit here is therefore buggy.
                  */
-                if (dev->revision <= 0) {
-                    features.features &= ~(1 << (VIRTIO_F_VERSION_1 - 32));
-                }
                 virtio_set_features(vdev,
                                     (vdev->guest_features & 0x00000000ffffffffULL) |
                                     ((uint64_t)features.features << 32));
@@ -766,7 +774,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
          * need to fetch it here. Nothing to do for now, though.
          */
         if (dev->revision >= 0 ||
-            revinfo.revision > virtio_ccw_rev_max(vdev)) {
+            revinfo.revision > virtio_ccw_rev_max(dev)) {
             ret = -ENOSYS;
             break;
         }
@@ -1539,6 +1547,10 @@ static void virtio_ccw_device_plugged(DeviceState *d, Error **errp)
 
     sch->id.cu_model = virtio_bus_get_vdev_id(&dev->bus);
 
+    if (dev->max_rev >= 1) {
+        virtio_add_feature(&vdev->host_features, VIRTIO_F_VERSION_1);
+    }
+
     css_generate_sch_crws(sch->cssid, sch->ssid, sch->schid,
                           d->hotplugged, 1);
 }
@@ -1555,6 +1567,8 @@ static Property virtio_ccw_net_properties[] = {
     DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id),
     DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags,
                     VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true),
+    DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev,
+                       VIRTIO_CCW_MAX_REV),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -1582,6 +1596,8 @@ static Property virtio_ccw_blk_properties[] = {
     DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id),
     DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags,
                     VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true),
+    DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev,
+                       VIRTIO_CCW_MAX_REV),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -1609,6 +1625,8 @@ static Property virtio_ccw_serial_properties[] = {
     DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id),
     DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags,
                     VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true),
+    DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev,
+                       VIRTIO_CCW_MAX_REV),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -1636,6 +1654,8 @@ static Property virtio_ccw_balloon_properties[] = {
     DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id),
     DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags,
                     VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true),
+    DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev,
+                       VIRTIO_CCW_MAX_REV),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -1663,6 +1683,8 @@ static Property virtio_ccw_scsi_properties[] = {
     DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id),
     DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags,
                     VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true),
+    DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev,
+                       VIRTIO_CCW_MAX_REV),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -1689,6 +1711,8 @@ static const TypeInfo virtio_ccw_scsi = {
 #ifdef CONFIG_VHOST_SCSI
 static Property vhost_ccw_scsi_properties[] = {
     DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id),
+    DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev,
+                       VIRTIO_CCW_MAX_REV),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -1727,6 +1751,8 @@ static Property virtio_ccw_rng_properties[] = {
     DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id),
     DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags,
                     VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true),
+    DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev,
+                       VIRTIO_CCW_MAX_REV),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -1880,6 +1906,8 @@ static Property virtio_ccw_9p_properties[] = {
     DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id),
     DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags,
             VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true),
+    DEFINE_PROP_UINT32("max_revision", VirtioCcwDevice, max_rev,
+                       VIRTIO_CCW_MAX_REV),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/s390x/virtio-ccw.h b/hw/s390x/virtio-ccw.h
index 692ddd7318..7ab8367baa 100644
--- a/hw/s390x/virtio-ccw.h
+++ b/hw/s390x/virtio-ccw.h
@@ -88,6 +88,7 @@ struct VirtioCcwDevice {
     SubchDev *sch;
     char *bus_id;
     int revision;
+    uint32_t max_rev;
     VirtioBusState bus;
     bool ioeventfd_started;
     bool ioeventfd_disabled;
@@ -102,9 +103,10 @@ struct VirtioCcwDevice {
 };
 
 /* The maximum virtio revision we support. */
-static inline int virtio_ccw_rev_max(VirtIODevice *vdev)
+#define VIRTIO_CCW_MAX_REV 1
+static inline int virtio_ccw_rev_max(VirtioCcwDevice *dev)
 {
-    return 0;
+    return dev->max_rev;
 }
 
 /* virtual css bus type */
diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c
index 4d68a27658..72d1392b35 100644
--- a/hw/virtio/vhost-backend.c
+++ b/hw/virtio/vhost-backend.c
@@ -42,11 +42,19 @@ static int vhost_kernel_cleanup(struct vhost_dev *dev)
     return close(fd);
 }
 
+static int vhost_kernel_get_vq_index(struct vhost_dev *dev, int idx)
+{
+    assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs);
+
+    return idx - dev->vq_index;
+}
+
 static const VhostOps kernel_ops = {
         .backend_type = VHOST_BACKEND_TYPE_KERNEL,
         .vhost_call = vhost_kernel_call,
         .vhost_backend_init = vhost_kernel_init,
-        .vhost_backend_cleanup = vhost_kernel_cleanup
+        .vhost_backend_cleanup = vhost_kernel_cleanup,
+        .vhost_backend_get_vq_index = vhost_kernel_get_vq_index,
 };
 
 int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index e7ab8293d1..b11c0d21a0 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -24,13 +24,17 @@
 #include <linux/vhost.h>
 
 #define VHOST_MEMORY_MAX_NREGIONS    8
+#define VHOST_USER_F_PROTOCOL_FEATURES 30
+#define VHOST_USER_PROTOCOL_FEATURE_MASK 0x1ULL
+
+#define VHOST_USER_PROTOCOL_F_MQ    0
 
 typedef enum VhostUserRequest {
     VHOST_USER_NONE = 0,
     VHOST_USER_GET_FEATURES = 1,
     VHOST_USER_SET_FEATURES = 2,
     VHOST_USER_SET_OWNER = 3,
-    VHOST_USER_RESET_OWNER = 4,
+    VHOST_USER_RESET_DEVICE = 4,
     VHOST_USER_SET_MEM_TABLE = 5,
     VHOST_USER_SET_LOG_BASE = 6,
     VHOST_USER_SET_LOG_FD = 7,
@@ -41,6 +45,10 @@ typedef enum VhostUserRequest {
     VHOST_USER_SET_VRING_KICK = 12,
     VHOST_USER_SET_VRING_CALL = 13,
     VHOST_USER_SET_VRING_ERR = 14,
+    VHOST_USER_GET_PROTOCOL_FEATURES = 15,
+    VHOST_USER_SET_PROTOCOL_FEATURES = 16,
+    VHOST_USER_GET_QUEUE_NUM = 17,
+    VHOST_USER_SET_VRING_ENABLE = 18,
     VHOST_USER_MAX
 } VhostUserRequest;
 
@@ -94,7 +102,7 @@ static unsigned long int ioctl_to_vhost_user_request[VHOST_USER_MAX] = {
     VHOST_GET_FEATURES,     /* VHOST_USER_GET_FEATURES */
     VHOST_SET_FEATURES,     /* VHOST_USER_SET_FEATURES */
     VHOST_SET_OWNER,        /* VHOST_USER_SET_OWNER */
-    VHOST_RESET_OWNER,      /* VHOST_USER_RESET_OWNER */
+    VHOST_RESET_DEVICE,      /* VHOST_USER_RESET_DEVICE */
     VHOST_SET_MEM_TABLE,    /* VHOST_USER_SET_MEM_TABLE */
     VHOST_SET_LOG_BASE,     /* VHOST_USER_SET_LOG_BASE */
     VHOST_SET_LOG_FD,       /* VHOST_USER_SET_LOG_FD */
@@ -180,6 +188,19 @@ static int vhost_user_write(struct vhost_dev *dev, VhostUserMsg *msg,
             0 : -1;
 }
 
+static bool vhost_user_one_time_request(VhostUserRequest request)
+{
+    switch (request) {
+    case VHOST_USER_SET_OWNER:
+    case VHOST_USER_RESET_DEVICE:
+    case VHOST_USER_SET_MEM_TABLE:
+    case VHOST_USER_GET_QUEUE_NUM:
+        return true;
+    default:
+        return false;
+    }
+}
+
 static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
         void *arg)
 {
@@ -193,27 +214,45 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
 
     assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
 
-    msg_request = vhost_user_request_translate(request);
+    /* only translate vhost ioctl requests */
+    if (request > VHOST_USER_MAX) {
+        msg_request = vhost_user_request_translate(request);
+    } else {
+        msg_request = request;
+    }
+
+    /*
+     * For non-vring specific requests, like VHOST_USER_SET_MEM_TABLE,
+     * we just need send it once in the first time. For later such
+     * request, we just ignore it.
+     */
+    if (vhost_user_one_time_request(msg_request) && dev->vq_index != 0) {
+        return 0;
+    }
+
     msg.request = msg_request;
     msg.flags = VHOST_USER_VERSION;
     msg.size = 0;
 
-    switch (request) {
-    case VHOST_GET_FEATURES:
+    switch (msg_request) {
+    case VHOST_USER_GET_FEATURES:
+    case VHOST_USER_GET_PROTOCOL_FEATURES:
+    case VHOST_USER_GET_QUEUE_NUM:
         need_reply = 1;
         break;
 
-    case VHOST_SET_FEATURES:
-    case VHOST_SET_LOG_BASE:
+    case VHOST_USER_SET_FEATURES:
+    case VHOST_USER_SET_LOG_BASE:
+    case VHOST_USER_SET_PROTOCOL_FEATURES:
         msg.u64 = *((__u64 *) arg);
         msg.size = sizeof(m.u64);
         break;
 
-    case VHOST_SET_OWNER:
-    case VHOST_RESET_OWNER:
+    case VHOST_USER_SET_OWNER:
+    case VHOST_USER_RESET_DEVICE:
         break;
 
-    case VHOST_SET_MEM_TABLE:
+    case VHOST_USER_SET_MEM_TABLE:
         for (i = 0; i < dev->mem->nregions; ++i) {
             struct vhost_memory_region *reg = dev->mem->regions + i;
             ram_addr_t ram_addr;
@@ -246,30 +285,31 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
 
         break;
 
-    case VHOST_SET_LOG_FD:
+    case VHOST_USER_SET_LOG_FD:
         fds[fd_num++] = *((int *) arg);
         break;
 
-    case VHOST_SET_VRING_NUM:
-    case VHOST_SET_VRING_BASE:
+    case VHOST_USER_SET_VRING_NUM:
+    case VHOST_USER_SET_VRING_BASE:
+    case VHOST_USER_SET_VRING_ENABLE:
         memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
         msg.size = sizeof(m.state);
         break;
 
-    case VHOST_GET_VRING_BASE:
+    case VHOST_USER_GET_VRING_BASE:
         memcpy(&msg.state, arg, sizeof(struct vhost_vring_state));
         msg.size = sizeof(m.state);
         need_reply = 1;
         break;
 
-    case VHOST_SET_VRING_ADDR:
+    case VHOST_USER_SET_VRING_ADDR:
         memcpy(&msg.addr, arg, sizeof(struct vhost_vring_addr));
         msg.size = sizeof(m.addr);
         break;
 
-    case VHOST_SET_VRING_KICK:
-    case VHOST_SET_VRING_CALL:
-    case VHOST_SET_VRING_ERR:
+    case VHOST_USER_SET_VRING_KICK:
+    case VHOST_USER_SET_VRING_CALL:
+    case VHOST_USER_SET_VRING_ERR:
         file = arg;
         msg.u64 = file->index & VHOST_USER_VRING_IDX_MASK;
         msg.size = sizeof(m.u64);
@@ -302,6 +342,8 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
 
         switch (msg_request) {
         case VHOST_USER_GET_FEATURES:
+        case VHOST_USER_GET_PROTOCOL_FEATURES:
+        case VHOST_USER_GET_QUEUE_NUM:
             if (msg.size != sizeof(m.u64)) {
                 error_report("Received bad msg size.");
                 return -1;
@@ -327,13 +369,61 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request,
 
 static int vhost_user_init(struct vhost_dev *dev, void *opaque)
 {
+    unsigned long long features;
+    int err;
+
     assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
 
     dev->opaque = opaque;
 
+    err = vhost_user_call(dev, VHOST_USER_GET_FEATURES, &features);
+    if (err < 0) {
+        return err;
+    }
+
+    if (virtio_has_feature(features, VHOST_USER_F_PROTOCOL_FEATURES)) {
+        dev->backend_features |= 1ULL << VHOST_USER_F_PROTOCOL_FEATURES;
+
+        err = vhost_user_call(dev, VHOST_USER_GET_PROTOCOL_FEATURES, &features);
+        if (err < 0) {
+            return err;
+        }
+
+        dev->protocol_features = features & VHOST_USER_PROTOCOL_FEATURE_MASK;
+        err = vhost_user_call(dev, VHOST_USER_SET_PROTOCOL_FEATURES,
+                              &dev->protocol_features);
+        if (err < 0) {
+            return err;
+        }
+
+        /* query the max queues we support if backend supports Multiple Queue */
+        if (dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ)) {
+            err = vhost_user_call(dev, VHOST_USER_GET_QUEUE_NUM, &dev->max_queues);
+            if (err < 0) {
+                return err;
+            }
+        }
+    }
+
     return 0;
 }
 
+static int vhost_user_set_vring_enable(struct vhost_dev *dev, int enable)
+{
+    struct vhost_vring_state state = {
+        .index = dev->vq_index,
+        .num   = enable,
+    };
+
+    assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
+
+    if (!(dev->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ))) {
+        return -1;
+    }
+
+    return vhost_user_call(dev, VHOST_USER_SET_VRING_ENABLE, &state);
+}
+
 static int vhost_user_cleanup(struct vhost_dev *dev)
 {
     assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
@@ -343,9 +433,18 @@ static int vhost_user_cleanup(struct vhost_dev *dev)
     return 0;
 }
 
+static int vhost_user_get_vq_index(struct vhost_dev *dev, int idx)
+{
+    assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs);
+
+    return idx;
+}
+
 const VhostOps user_ops = {
         .backend_type = VHOST_BACKEND_TYPE_USER,
         .vhost_call = vhost_user_call,
         .vhost_backend_init = vhost_user_init,
-        .vhost_backend_cleanup = vhost_user_cleanup
-        };
+        .vhost_backend_cleanup = vhost_user_cleanup,
+        .vhost_backend_get_vq_index = vhost_user_get_vq_index,
+        .vhost_backend_set_vring_enable = vhost_user_set_vring_enable,
+};
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index a08c36bb45..c0ed5b263f 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -719,7 +719,7 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
 {
     hwaddr s, l, a;
     int r;
-    int vhost_vq_index = idx - dev->vq_index;
+    int vhost_vq_index = dev->vhost_ops->vhost_backend_get_vq_index(dev, idx);
     struct vhost_vring_file file = {
         .index = vhost_vq_index
     };
@@ -728,7 +728,6 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
     };
     struct VirtQueue *vvq = virtio_get_queue(vdev, idx);
 
-    assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs);
 
     vq->num = state.num = virtio_queue_get_num(vdev, idx);
     r = dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_NUM, &state);
@@ -822,12 +821,12 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev,
                                     struct vhost_virtqueue *vq,
                                     unsigned idx)
 {
-    int vhost_vq_index = idx - dev->vq_index;
+    int vhost_vq_index = dev->vhost_ops->vhost_backend_get_vq_index(dev, idx);
     struct vhost_vring_state state = {
         .index = vhost_vq_index,
     };
     int r;
-    assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs);
+
     r = dev->vhost_ops->vhost_call(dev, VHOST_GET_VRING_BASE, &state);
     if (r < 0) {
         fprintf(stderr, "vhost VQ %d ring restore failed: %d\n", idx, r);
@@ -875,8 +874,9 @@ static void vhost_eventfd_del(MemoryListener *listener,
 static int vhost_virtqueue_init(struct vhost_dev *dev,
                                 struct vhost_virtqueue *vq, int n)
 {
+    int vhost_vq_index = dev->vhost_ops->vhost_backend_get_vq_index(dev, n);
     struct vhost_vring_file file = {
-        .index = n,
+        .index = vhost_vq_index,
     };
     int r = event_notifier_init(&vq->masked_notifier, 0);
     if (r < 0) {
@@ -927,7 +927,7 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
     }
 
     for (i = 0; i < hdev->nvqs; ++i) {
-        r = vhost_virtqueue_init(hdev, hdev->vqs + i, i);
+        r = vhost_virtqueue_init(hdev, hdev->vqs + i, hdev->vq_index + i);
         if (r < 0) {
             goto fail_vq;
         }
@@ -1066,17 +1066,15 @@ void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n,
 {
     struct VirtQueue *vvq = virtio_get_queue(vdev, n);
     int r, index = n - hdev->vq_index;
+    struct vhost_vring_file file;
 
-    assert(n >= hdev->vq_index && n < hdev->vq_index + hdev->nvqs);
-
-    struct vhost_vring_file file = {
-        .index = index
-    };
     if (mask) {
         file.fd = event_notifier_get_fd(&hdev->vqs[index].masked_notifier);
     } else {
         file.fd = event_notifier_get_fd(virtio_queue_get_guest_notifier(vvq));
     }
+
+    file.index = hdev->vhost_ops->vhost_backend_get_vq_index(hdev, n);
     r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_VRING_CALL, &file);
     assert(r >= 0);
 }
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index 0832db9935..7504f8b33a 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -60,6 +60,7 @@ typedef struct VRingUsed
 typedef struct VRing
 {
     unsigned int num;
+    unsigned int num_default;
     unsigned int align;
     hwaddr desc;
     hwaddr avail;
@@ -633,6 +634,7 @@ void virtio_reset(void *opaque)
         vdev->vq[i].signalled_used = 0;
         vdev->vq[i].signalled_used_valid = false;
         vdev->vq[i].notification = true;
+        vdev->vq[i].vring.num = vdev->vq[i].vring.num_default;
     }
 }
 
@@ -964,6 +966,7 @@ VirtQueue *virtio_add_queue(VirtIODevice *vdev, int queue_size,
         abort();
 
     vdev->vq[i].vring.num = queue_size;
+    vdev->vq[i].vring.num_default = queue_size;
     vdev->vq[i].vring.align = VIRTIO_PCI_VRING_ALIGN;
     vdev->vq[i].handle_output = handle_output;
 
@@ -977,6 +980,7 @@ void virtio_del_queue(VirtIODevice *vdev, int n)
     }
 
     vdev->vq[n].vring.num = 0;
+    vdev->vq[n].vring.num_default = 0;
 }
 
 void virtio_irq(VirtQueue *vq)
@@ -1056,6 +1060,19 @@ static bool virtio_virtqueue_needed(void *opaque)
     return virtio_host_has_feature(vdev, VIRTIO_F_VERSION_1);
 }
 
+static bool virtio_ringsize_needed(void *opaque)
+{
+    VirtIODevice *vdev = opaque;
+    int i;
+
+    for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
+        if (vdev->vq[i].vring.num != vdev->vq[i].vring.num_default) {
+            return true;
+        }
+    }
+    return false;
+}
+
 static void put_virtqueue_state(QEMUFile *f, void *pv, size_t size)
 {
     VirtIODevice *vdev = pv;
@@ -1104,6 +1121,52 @@ static const VMStateDescription vmstate_virtio_virtqueues = {
     }
 };
 
+static void put_ringsize_state(QEMUFile *f, void *pv, size_t size)
+{
+    VirtIODevice *vdev = pv;
+    int i;
+
+    for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
+        qemu_put_be32(f, vdev->vq[i].vring.num_default);
+    }
+}
+
+static int get_ringsize_state(QEMUFile *f, void *pv, size_t size)
+{
+    VirtIODevice *vdev = pv;
+    int i;
+
+    for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
+        vdev->vq[i].vring.num_default = qemu_get_be32(f);
+    }
+    return 0;
+}
+
+static VMStateInfo vmstate_info_ringsize = {
+    .name = "ringsize_state",
+    .get = get_ringsize_state,
+    .put = put_ringsize_state,
+};
+
+static const VMStateDescription vmstate_virtio_ringsize = {
+    .name = "virtio/ringsize",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = &virtio_ringsize_needed,
+    .fields = (VMStateField[]) {
+        {
+            .name         = "ringsize",
+            .version_id   = 0,
+            .field_exists = NULL,
+            .size         = 0,
+            .info         = &vmstate_info_ringsize,
+            .flags        = VMS_SINGLE,
+            .offset       = 0,
+        },
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_virtio_device_endian = {
     .name = "virtio/device_endian",
     .version_id = 1,
@@ -1138,6 +1201,7 @@ static const VMStateDescription vmstate_virtio = {
         &vmstate_virtio_device_endian,
         &vmstate_virtio_64bit_features,
         &vmstate_virtio_virtqueues,
+        &vmstate_virtio_ringsize,
         NULL
     }
 };
@@ -1460,7 +1524,7 @@ hwaddr virtio_queue_get_desc_size(VirtIODevice *vdev, int n)
 hwaddr virtio_queue_get_avail_size(VirtIODevice *vdev, int n)
 {
     return offsetof(VRingAvail, ring) +
-        sizeof(uint64_t) * vdev->vq[n].vring.num;
+        sizeof(uint16_t) * vdev->vq[n].vring.num;
 }
 
 hwaddr virtio_queue_get_used_size(VirtIODevice *vdev, int n)