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

virtio, vhost: fixes for 2.5

This fixes a performance regression with virtio 1,
and makes device stop/start more robust for vhost-user.
virtio devices on pcie bus now have pcie and pm
capability, as required by the PCI Express spec.
migration now works better with virtio 9p.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Thu 12 Nov 2015 14:40:42 GMT 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:
  virtio-9p: add savem handlers
  hw/virtio: Add PCIe capability to virtio devices
  vhost: send SET_VRING_ENABLE at start/stop
  vhost: rename RESET_DEVICE backto RESET_OWNER
  vhost-user: modify SET_LOG_BASE to pass mmap size and offset
  virtio-pci: unbreak queue_enable read
  virtio-pci: introduce pio notification capability for modern device
  virtio-pci: use zero length mmio eventfd for 1.0 notification cap when possible
  KVM: add support for any length io eventfd
  memory: don't try to adjust endianness for zero length eventfd
  virtio-pci: fix 1.0 virtqueue migration

Conflicts:
	include/hw/compat.h
[Fixed a trivial merge conflict in compat.h]
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

docs/specs/vhost-user.txt

@@ -98,6 +98,7 @@ typedef struct VhostUserMsg {
         struct vhost_vring_state state;
         struct vhost_vring_addr addr;
         VhostUserMemory memory;
+        VhostUserLog log;
     };
 } QEMU_PACKED VhostUserMsg;
 
@@ -255,10 +256,10 @@ Message types
       as an owner of the session. This can be used on the Slave as a
       "session start" flag.
 
- * VHOST_USER_RESET_DEVICE
+ * VHOST_USER_RESET_OWNER
 
       Id: 4
-      Equivalent ioctl: VHOST_RESET_DEVICE
+      Equivalent ioctl: VHOST_RESET_OWNER
       Master payload: N/A
 
       Issued when a new connection is about to be closed. The Master will no
@@ -282,7 +283,12 @@ Message types
       Master payload: u64
       Slave payload: N/A
 
-      Sets the logging base address.
+      Sets logging shared memory space.
+      When slave has VHOST_USER_PROTOCOL_F_LOG_SHMFD protocol
+      feature, the log memory fd is provided in the ancillary data of
+      VHOST_USER_SET_LOG_BASE message, the size and offset of shared
+      memory area provided in the message.
+
 
  * VHOST_USER_SET_LOG_FD
 

hw/9pfs/virtio-9p-device.c

@@ -43,6 +43,16 @@ static void virtio_9p_get_config(VirtIODevice *vdev, uint8_t *config)
     g_free(cfg);
 }
 
+static void virtio_9p_save(QEMUFile *f, void *opaque)
+{
+    virtio_save(VIRTIO_DEVICE(opaque), f);
+}
+
+static int virtio_9p_load(QEMUFile *f, void *opaque, int version_id)
+{
+    return virtio_load(VIRTIO_DEVICE(opaque), f, version_id);
+}
+
 static void virtio_9p_device_realize(DeviceState *dev, Error **errp)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
@@ -130,6 +140,7 @@ static void virtio_9p_device_realize(DeviceState *dev, Error **errp)
     }
     v9fs_path_free(&path);
 
+    register_savevm(dev, "virtio-9p", -1, 1, virtio_9p_save, virtio_9p_load, s);
     return;
 out:
     g_free(s->ctx.fs_root);

hw/virtio/vhost-backend.c

@@ -156,7 +156,7 @@ static int vhost_kernel_set_owner(struct vhost_dev *dev)
 
 static int vhost_kernel_reset_device(struct vhost_dev *dev)
 {
-    return vhost_kernel_call(dev, VHOST_RESET_DEVICE, NULL);
+    return vhost_kernel_call(dev, VHOST_RESET_OWNER, NULL);
 }
 
 static int vhost_kernel_get_vq_index(struct vhost_dev *dev, int idx)

hw/virtio/vhost-user.c

@@ -43,7 +43,7 @@ typedef enum VhostUserRequest {
     VHOST_USER_GET_FEATURES = 1,
     VHOST_USER_SET_FEATURES = 2,
     VHOST_USER_SET_OWNER = 3,
-    VHOST_USER_RESET_DEVICE = 4,
+    VHOST_USER_RESET_OWNER = 4,
     VHOST_USER_SET_MEM_TABLE = 5,
     VHOST_USER_SET_LOG_BASE = 6,
     VHOST_USER_SET_LOG_FD = 7,
@@ -75,6 +75,11 @@ typedef struct VhostUserMemory {
     VhostUserMemoryRegion regions[VHOST_MEMORY_MAX_NREGIONS];
 } VhostUserMemory;
 
+typedef struct VhostUserLog {
+    uint64_t mmap_size;
+    uint64_t mmap_offset;
+} VhostUserLog;
+
 typedef struct VhostUserMsg {
     VhostUserRequest request;
 
@@ -89,6 +94,7 @@ typedef struct VhostUserMsg {
         struct vhost_vring_state state;
         struct vhost_vring_addr addr;
         VhostUserMemory memory;
+        VhostUserLog log;
     } payload;
 } QEMU_PACKED VhostUserMsg;
 
@@ -157,7 +163,7 @@ static bool vhost_user_one_time_request(VhostUserRequest request)
 {
     switch (request) {
     case VHOST_USER_SET_OWNER:
-    case VHOST_USER_RESET_DEVICE:
+    case VHOST_USER_RESET_OWNER:
     case VHOST_USER_SET_MEM_TABLE:
     case VHOST_USER_GET_QUEUE_NUM:
         return true;
@@ -200,8 +206,9 @@ static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base,
     VhostUserMsg msg = {
         .request = VHOST_USER_SET_LOG_BASE,
         .flags = VHOST_USER_VERSION,
-        .payload.u64 = base,
-        .size = sizeof(msg.payload.u64),
+        .payload.log.mmap_size = log->size,
+        .payload.log.mmap_offset = 0,
+        .size = sizeof(msg.payload.log),
     };
 
     if (shmfd && log->fd != -1) {
@@ -486,7 +493,7 @@ static int vhost_user_set_owner(struct vhost_dev *dev)
 static int vhost_user_reset_device(struct vhost_dev *dev)
 {
     VhostUserMsg msg = {
-        .request = VHOST_USER_RESET_DEVICE,
+        .request = VHOST_USER_RESET_OWNER,
         .flags = VHOST_USER_VERSION,
     };
 

hw/virtio/vhost.c

@@ -1226,6 +1226,11 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
         }
     }
 
+    if (hdev->vhost_ops->vhost_set_vring_enable) {
+        /* only enable first vq pair by default */
+        hdev->vhost_ops->vhost_set_vring_enable(hdev, hdev->vq_index == 0);
+    }
+
     return 0;
 fail_log:
     vhost_log_put(hdev, false);
@@ -1256,6 +1261,10 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)
                              hdev->vq_index + i);
     }
 
+    if (hdev->vhost_ops->vhost_set_vring_enable) {
+        hdev->vhost_ops->vhost_set_vring_enable(hdev, 0);
+    }
+
     vhost_log_put(hdev, true);
     hdev->started = false;
     hdev->log = NULL;

hw/virtio/virtio-pci.c

@@ -86,6 +86,129 @@ static void virtio_pci_save_config(DeviceState *d, QEMUFile *f)
         qemu_put_be16(f, vdev->config_vector);
 }
 
+static void virtio_pci_load_modern_queue_state(VirtIOPCIQueue *vq,
+                                               QEMUFile *f)
+{
+    vq->num = qemu_get_be16(f);
+    vq->enabled = qemu_get_be16(f);
+    vq->desc[0] = qemu_get_be32(f);
+    vq->desc[1] = qemu_get_be32(f);
+    vq->avail[0] = qemu_get_be32(f);
+    vq->avail[1] = qemu_get_be32(f);
+    vq->used[0] = qemu_get_be32(f);
+    vq->used[1] = qemu_get_be32(f);
+}
+
+static bool virtio_pci_has_extra_state(DeviceState *d)
+{
+    VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
+
+    return proxy->flags & VIRTIO_PCI_FLAG_MIGRATE_EXTRA;
+}
+
+static int get_virtio_pci_modern_state(QEMUFile *f, void *pv, size_t size)
+{
+    VirtIOPCIProxy *proxy = pv;
+    int i;
+
+    proxy->dfselect = qemu_get_be32(f);
+    proxy->gfselect = qemu_get_be32(f);
+    proxy->guest_features[0] = qemu_get_be32(f);
+    proxy->guest_features[1] = qemu_get_be32(f);
+    for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
+        virtio_pci_load_modern_queue_state(&proxy->vqs[i], f);
+    }
+
+    return 0;
+}
+
+static void virtio_pci_save_modern_queue_state(VirtIOPCIQueue *vq,
+                                               QEMUFile *f)
+{
+    qemu_put_be16(f, vq->num);
+    qemu_put_be16(f, vq->enabled);
+    qemu_put_be32(f, vq->desc[0]);
+    qemu_put_be32(f, vq->desc[1]);
+    qemu_put_be32(f, vq->avail[0]);
+    qemu_put_be32(f, vq->avail[1]);
+    qemu_put_be32(f, vq->used[0]);
+    qemu_put_be32(f, vq->used[1]);
+}
+
+static void put_virtio_pci_modern_state(QEMUFile *f, void *pv, size_t size)
+{
+    VirtIOPCIProxy *proxy = pv;
+    int i;
+
+    qemu_put_be32(f, proxy->dfselect);
+    qemu_put_be32(f, proxy->gfselect);
+    qemu_put_be32(f, proxy->guest_features[0]);
+    qemu_put_be32(f, proxy->guest_features[1]);
+    for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
+        virtio_pci_save_modern_queue_state(&proxy->vqs[i], f);
+    }
+}
+
+static const VMStateInfo vmstate_info_virtio_pci_modern_state = {
+    .name = "virtqueue_state",
+    .get = get_virtio_pci_modern_state,
+    .put = put_virtio_pci_modern_state,
+};
+
+static bool virtio_pci_modern_state_needed(void *opaque)
+{
+    VirtIOPCIProxy *proxy = opaque;
+
+    return !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN);
+}
+
+static const VMStateDescription vmstate_virtio_pci_modern_state = {
+    .name = "virtio_pci/modern_state",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = &virtio_pci_modern_state_needed,
+    .fields = (VMStateField[]) {
+        {
+            .name         = "modern_state",
+            .version_id   = 0,
+            .field_exists = NULL,
+            .size         = 0,
+            .info         = &vmstate_info_virtio_pci_modern_state,
+            .flags        = VMS_SINGLE,
+            .offset       = 0,
+        },
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static const VMStateDescription vmstate_virtio_pci = {
+    .name = "virtio_pci",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .minimum_version_id_old = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_END_OF_LIST()
+    },
+    .subsections = (const VMStateDescription*[]) {
+        &vmstate_virtio_pci_modern_state,
+        NULL
+    }
+};
+
+static void virtio_pci_save_extra_state(DeviceState *d, QEMUFile *f)
+{
+    VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
+
+    vmstate_save_state(f, &vmstate_virtio_pci, proxy, NULL);
+}
+
+static int virtio_pci_load_extra_state(DeviceState *d, QEMUFile *f)
+{
+    VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
+
+    return vmstate_load_state(f, &vmstate_virtio_pci, proxy, 1);
+}
+
 static void virtio_pci_save_queue(DeviceState *d, int n, QEMUFile *f)
 {
     VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
@@ -133,6 +256,7 @@ static int virtio_pci_load_queue(DeviceState *d, int n, QEMUFile *f)
     if (vector != VIRTIO_NO_VECTOR) {
         return msix_vector_use(&proxy->pci_dev, vector);
     }
+
     return 0;
 }
 
@@ -146,7 +270,10 @@ static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy,
     EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
     bool legacy = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_LEGACY);
     bool modern = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN);
+    bool fast_mmio = kvm_ioeventfd_any_length_enabled();
+    bool modern_pio = proxy->flags & VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY;
     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 *
                          virtio_get_queue_index(vq);
@@ -162,8 +289,17 @@ static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy,
         }
         virtio_queue_set_host_notifier_fd_handler(vq, true, set_handler);
         if (modern) {
-            memory_region_add_eventfd(modern_mr, modern_addr, 2,
-                                      true, n, notifier);
+            if (fast_mmio) {
+                memory_region_add_eventfd(modern_mr, modern_addr, 0,
+                                          false, n, notifier);
+            } else {
+                memory_region_add_eventfd(modern_mr, modern_addr, 2,
+                                          false, n, notifier);
+            }
+            if (modern_pio) {
+                memory_region_add_eventfd(modern_notify_mr, 0, 2,
+                                              true, n, notifier);
+            }
         }
         if (legacy) {
             memory_region_add_eventfd(legacy_mr, legacy_addr, 2,
@@ -171,8 +307,17 @@ static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy,
         }
     } else {
         if (modern) {
-            memory_region_del_eventfd(modern_mr, modern_addr, 2,
-                                      true, n, notifier);
+            if (fast_mmio) {
+                memory_region_del_eventfd(modern_mr, modern_addr, 0,
+                                          false, n, notifier);
+            } else {
+                memory_region_del_eventfd(modern_mr, modern_addr, 2,
+                                          false, n, notifier);
+            }
+            if (modern_pio) {
+                memory_region_del_eventfd(modern_notify_mr, 0, 2,
+                                          true, n, notifier);
+            }
         }
         if (legacy) {
             memory_region_del_eventfd(legacy_mr, legacy_addr, 2,
@@ -1239,6 +1384,7 @@ static void virtio_pci_common_write(void *opaque, hwaddr addr,
                        proxy->vqs[vdev->queue_sel].avail[0],
                        ((uint64_t)proxy->vqs[vdev->queue_sel].used[1]) << 32 |
                        proxy->vqs[vdev->queue_sel].used[0]);
+        proxy->vqs[vdev->queue_sel].enabled = 1;
         break;
     case VIRTIO_PCI_COMMON_Q_DESCLO:
         proxy->vqs[vdev->queue_sel].desc[0] = val;
@@ -1281,6 +1427,17 @@ static void virtio_pci_notify_write(void *opaque, hwaddr addr,
     }
 }
 
+static void virtio_pci_notify_write_pio(void *opaque, hwaddr addr,
+                                        uint64_t val, unsigned size)
+{
+    VirtIODevice *vdev = opaque;
+    unsigned queue = val;
+
+    if (queue < VIRTIO_QUEUE_MAX) {
+        virtio_queue_notify(vdev, queue);
+    }
+}
+
 static uint64_t virtio_pci_isr_read(void *opaque, hwaddr addr,
                                     unsigned size)
 {
@@ -1374,6 +1531,16 @@ static void virtio_pci_modern_regions_init(VirtIOPCIProxy *proxy)
         },
         .endianness = DEVICE_LITTLE_ENDIAN,
     };
+    static const MemoryRegionOps notify_pio_ops = {
+        .read = virtio_pci_notify_read,
+        .write = virtio_pci_notify_write_pio,
+        .impl = {
+            .min_access_size = 1,
+            .max_access_size = 4,
+        },
+        .endianness = DEVICE_LITTLE_ENDIAN,
+    };
+
 
     memory_region_init_io(&proxy->common.mr, OBJECT(proxy),
                           &common_ops,
@@ -1398,30 +1565,60 @@ static void virtio_pci_modern_regions_init(VirtIOPCIProxy *proxy)
                           virtio_bus_get_device(&proxy->bus),
                           "virtio-pci-notify",
                           proxy->notify.size);
+
+    memory_region_init_io(&proxy->notify_pio.mr, OBJECT(proxy),
+                          &notify_pio_ops,
+                          virtio_bus_get_device(&proxy->bus),
+                          "virtio-pci-notify-pio",
+                          proxy->notify.size);
 }
 
 static void virtio_pci_modern_region_map(VirtIOPCIProxy *proxy,
                                          VirtIOPCIRegion *region,
-                                         struct virtio_pci_cap *cap)
+                                         struct virtio_pci_cap *cap,
+                                         MemoryRegion *mr,
+                                         uint8_t bar)
 {
-    memory_region_add_subregion(&proxy->modern_bar,
-                                region->offset,
-                                &region->mr);
+    memory_region_add_subregion(mr, region->offset, &region->mr);
 
     cap->cfg_type = region->type;
-    cap->bar = proxy->modern_mem_bar;
+    cap->bar = bar;
     cap->offset = cpu_to_le32(region->offset);
     cap->length = cpu_to_le32(region->size);
     virtio_pci_add_mem_cap(proxy, cap);
+
+}
+
+static void virtio_pci_modern_mem_region_map(VirtIOPCIProxy *proxy,
+                                             VirtIOPCIRegion *region,
+                                             struct virtio_pci_cap *cap)
+{
+    virtio_pci_modern_region_map(proxy, region, cap,
+                                 &proxy->modern_bar, proxy->modern_mem_bar);
 }
 
-static void virtio_pci_modern_region_unmap(VirtIOPCIProxy *proxy,
-                                           VirtIOPCIRegion *region)
+static void virtio_pci_modern_io_region_map(VirtIOPCIProxy *proxy,
+                                            VirtIOPCIRegion *region,
+                                            struct virtio_pci_cap *cap)
+{
+    virtio_pci_modern_region_map(proxy, region, cap,
+                                 &proxy->io_bar, proxy->modern_io_bar);
+}
+
+static void virtio_pci_modern_mem_region_unmap(VirtIOPCIProxy *proxy,
+                                               VirtIOPCIRegion *region)
 {
     memory_region_del_subregion(&proxy->modern_bar,
                                 &region->mr);
 }
 
+static void virtio_pci_modern_io_region_unmap(VirtIOPCIProxy *proxy,
+                                              VirtIOPCIRegion *region)
+{
+    memory_region_del_subregion(&proxy->io_bar,
+                                &region->mr);
+}
+
 /* This is called by virtio-bus just after the device is plugged. */
 static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
 {
@@ -1429,6 +1626,7 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
     VirtioBusState *bus = &proxy->bus;
     bool legacy = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_LEGACY);
     bool modern = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN);
+    bool modern_pio = proxy->flags & VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY;
     uint8_t *config;
     uint32_t size;
     VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
@@ -1467,16 +1665,31 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
             .cap.cap_len = sizeof cfg,
             .cap.cfg_type = VIRTIO_PCI_CAP_PCI_CFG,
         };
-        struct virtio_pci_cfg_cap *cfg_mask;
+        struct virtio_pci_notify_cap notify_pio = {
+            .cap.cap_len = sizeof notify,
+            .notify_off_multiplier = cpu_to_le32(0x0),
+        };
 
-        /* TODO: add io access for speed */
+        struct virtio_pci_cfg_cap *cfg_mask;
 
         virtio_add_feature(&vdev->host_features, VIRTIO_F_VERSION_1);
         virtio_pci_modern_regions_init(proxy);
-        virtio_pci_modern_region_map(proxy, &proxy->common, &cap);
-        virtio_pci_modern_region_map(proxy, &proxy->isr, &cap);
-        virtio_pci_modern_region_map(proxy, &proxy->device, &cap);
-        virtio_pci_modern_region_map(proxy, &proxy->notify, &notify.cap);
+
+        virtio_pci_modern_mem_region_map(proxy, &proxy->common, &cap);
+        virtio_pci_modern_mem_region_map(proxy, &proxy->isr, &cap);
+        virtio_pci_modern_mem_region_map(proxy, &proxy->device, &cap);
+        virtio_pci_modern_mem_region_map(proxy, &proxy->notify, &notify.cap);
+
+        if (modern_pio) {
+            memory_region_init(&proxy->io_bar, OBJECT(proxy),
+                               "virtio-pci-io", 0x4);
+
+            pci_register_bar(&proxy->pci_dev, proxy->modern_io_bar,
+                             PCI_BASE_ADDRESS_SPACE_IO, &proxy->io_bar);
+
+            virtio_pci_modern_io_region_map(proxy, &proxy->notify_pio,
+                                            &notify_pio.cap);
+        }
 
         pci_register_bar(&proxy->pci_dev, proxy->modern_mem_bar,
                          PCI_BASE_ADDRESS_SPACE_MEMORY |
@@ -1532,14 +1745,18 @@ static void virtio_pci_device_unplugged(DeviceState *d)
 {
     VirtIOPCIProxy *proxy = VIRTIO_PCI(d);
     bool modern = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN);
+    bool modern_pio = proxy->flags & VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY;
 
     virtio_pci_stop_ioeventfd(proxy);
 
     if (modern) {
-        virtio_pci_modern_region_unmap(proxy, &proxy->common);
-        virtio_pci_modern_region_unmap(proxy, &proxy->isr);
-        virtio_pci_modern_region_unmap(proxy, &proxy->device);
-        virtio_pci_modern_region_unmap(proxy, &proxy->notify);
+        virtio_pci_modern_mem_region_unmap(proxy, &proxy->common);
+        virtio_pci_modern_mem_region_unmap(proxy, &proxy->isr);
+        virtio_pci_modern_mem_region_unmap(proxy, &proxy->device);
+        virtio_pci_modern_mem_region_unmap(proxy, &proxy->notify);
+        if (modern_pio) {
+            virtio_pci_modern_io_region_unmap(proxy, &proxy->notify_pio);
+        }
     }
 }
 
@@ -1559,6 +1776,7 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
      */
     proxy->legacy_io_bar  = 0;
     proxy->msix_bar       = 1;
+    proxy->modern_io_bar  = 2;
     proxy->modern_mem_bar = 4;
 
     proxy->common.offset = 0x0;
@@ -1578,6 +1796,10 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
         QEMU_VIRTIO_PCI_QUEUE_MEM_MULT * VIRTIO_QUEUE_MAX;
     proxy->notify.type = VIRTIO_PCI_CAP_NOTIFY_CFG;
 
+    proxy->notify_pio.offset = 0x0;
+    proxy->notify_pio.size = 0x4;
+    proxy->notify_pio.type = VIRTIO_PCI_CAP_NOTIFY_CFG;
+
     /* 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 *
@@ -1592,6 +1814,26 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
 
     address_space_init(&proxy->modern_as, &proxy->modern_cfg, "virtio-pci-cfg-as");
 
+    if (!(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_PCIE)
+        && !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN)
+        && pci_bus_is_express(pci_dev->bus)
+        && !pci_bus_is_root(pci_dev->bus)) {
+        int pos;
+
+        pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS;
+        pos = pcie_endpoint_cap_init(pci_dev, 0);
+        assert(pos > 0);
+
+        pos = pci_add_capability(pci_dev, PCI_CAP_ID_PM, 0, PCI_PM_SIZEOF);
+        assert(pos > 0);
+
+        /*
+         * Indicates that this function complies with revision 1.2 of the
+         * PCI Power Management Interface Specification.
+         */
+        pci_set_word(pci_dev->config + pos + PCI_PM_PMC, 0x3);
+    }
+
     virtio_pci_bus_new(&proxy->bus, sizeof(proxy->bus), proxy);
     if (k->realize) {
         k->realize(proxy, errp);
@@ -1610,9 +1852,15 @@ static void virtio_pci_reset(DeviceState *qdev)
 {
     VirtIOPCIProxy *proxy = VIRTIO_PCI(qdev);
     VirtioBusState *bus = VIRTIO_BUS(&proxy->bus);
+    int i;
+
     virtio_pci_stop_ioeventfd(proxy);
     virtio_bus_reset(bus);
     msix_unuse_all_vectors(&proxy->pci_dev);
+
+    for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
+        proxy->vqs[i].enabled = 0;
+    }
 }
 
 static Property virtio_pci_properties[] = {
@@ -1622,6 +1870,12 @@ static Property virtio_pci_properties[] = {
                     VIRTIO_PCI_FLAG_DISABLE_LEGACY_BIT, false),
     DEFINE_PROP_BIT("disable-modern", VirtIOPCIProxy, flags,
                     VIRTIO_PCI_FLAG_DISABLE_MODERN_BIT, true),
+    DEFINE_PROP_BIT("migrate-extra", VirtIOPCIProxy, flags,
+                    VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT, true),
+    DEFINE_PROP_BIT("modern-pio-notify", VirtIOPCIProxy, flags,
+                    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_END_OF_LIST(),
 };
 
@@ -2212,6 +2466,9 @@ static void virtio_pci_bus_class_init(ObjectClass *klass, void *data)
     k->load_config = virtio_pci_load_config;
     k->save_queue = virtio_pci_save_queue;
     k->load_queue = virtio_pci_load_queue;
+    k->save_extra_state = virtio_pci_save_extra_state;
+    k->load_extra_state = virtio_pci_load_extra_state;
+    k->has_extra_state = virtio_pci_has_extra_state;
     k->query_guest_notifiers = virtio_pci_query_guest_notifiers;
     k->set_host_notifier = virtio_pci_set_host_notifier;
     k->set_guest_notifiers = virtio_pci_set_guest_notifiers;

hw/virtio/virtio-pci.h

@@ -72,8 +72,19 @@ typedef struct VirtioBusClass VirtioPCIBusClass;
 /* virtio version flags */
 #define VIRTIO_PCI_FLAG_DISABLE_LEGACY_BIT 2
 #define VIRTIO_PCI_FLAG_DISABLE_MODERN_BIT 3
+#define VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT 4
 #define VIRTIO_PCI_FLAG_DISABLE_LEGACY (1 << VIRTIO_PCI_FLAG_DISABLE_LEGACY_BIT)
 #define VIRTIO_PCI_FLAG_DISABLE_MODERN (1 << VIRTIO_PCI_FLAG_DISABLE_MODERN_BIT)
+#define VIRTIO_PCI_FLAG_DISABLE_PCIE (1 << VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT)
+
+/* migrate extra state */
+#define VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT 4
+#define VIRTIO_PCI_FLAG_MIGRATE_EXTRA (1 << VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT)
+
+/* have pio notification for modern device ? */
+#define VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT 5
+#define VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY \
+    (1 << VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT)
 
 typedef struct {
     MSIMessage msg;
@@ -104,6 +115,14 @@ typedef struct VirtIOPCIRegion {
     uint32_t type;
 } VirtIOPCIRegion;
 
+typedef struct VirtIOPCIQueue {
+  uint16_t num;
+  bool enabled;
+  uint32_t desc[2];
+  uint32_t avail[2];
+  uint32_t used[2];
+} VirtIOPCIQueue;
+
 struct VirtIOPCIProxy {
     PCIDevice pci_dev;
     MemoryRegion bar;
@@ -111,11 +130,14 @@ struct VirtIOPCIProxy {
     VirtIOPCIRegion isr;
     VirtIOPCIRegion device;
     VirtIOPCIRegion notify;
+    VirtIOPCIRegion notify_pio;
     MemoryRegion modern_bar;
+    MemoryRegion io_bar;
     MemoryRegion modern_cfg;
     AddressSpace modern_as;
     uint32_t legacy_io_bar;
     uint32_t msix_bar;
+    uint32_t modern_io_bar;
     uint32_t modern_mem_bar;
     int config_cap;
     uint32_t flags;
@@ -124,13 +146,7 @@ struct VirtIOPCIProxy {
     uint32_t dfselect;
     uint32_t gfselect;
     uint32_t guest_features[2];
-    struct {
-        uint16_t num;
-        bool enabled;
-        uint32_t desc[2];
-        uint32_t avail[2];
-        uint32_t used[2];
-    } vqs[VIRTIO_QUEUE_MAX];
+    VirtIOPCIQueue vqs[VIRTIO_QUEUE_MAX];
 
     bool ioeventfd_disabled;
     bool ioeventfd_started;

hw/virtio/virtio.c

@@ -1116,6 +1116,16 @@ static bool virtio_ringsize_needed(void *opaque)
     return false;
 }
 
+static bool virtio_extra_state_needed(void *opaque)
+{
+    VirtIODevice *vdev = opaque;
+    BusState *qbus = qdev_get_parent_bus(DEVICE(vdev));
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+
+    return k->has_extra_state &&
+        k->has_extra_state(qbus->parent);
+}
+
 static void put_virtqueue_state(QEMUFile *f, void *pv, size_t size)
 {
     VirtIODevice *vdev = pv;
@@ -1210,6 +1220,53 @@ static const VMStateDescription vmstate_virtio_ringsize = {
     }
 };
 
+static int get_extra_state(QEMUFile *f, void *pv, size_t size)
+{
+    VirtIODevice *vdev = pv;
+    BusState *qbus = qdev_get_parent_bus(DEVICE(vdev));
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+
+    if (!k->load_extra_state) {
+        return -1;
+    } else {
+        return k->load_extra_state(qbus->parent, f);
+    }
+}
+
+static void put_extra_state(QEMUFile *f, void *pv, size_t size)
+{
+    VirtIODevice *vdev = pv;
+    BusState *qbus = qdev_get_parent_bus(DEVICE(vdev));
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+
+    k->save_extra_state(qbus->parent, f);
+}
+
+static const VMStateInfo vmstate_info_extra_state = {
+    .name = "virtqueue_extra_state",
+    .get = get_extra_state,
+    .put = put_extra_state,
+};
+
+static const VMStateDescription vmstate_virtio_extra_state = {
+    .name = "virtio/extra_state",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = &virtio_extra_state_needed,
+    .fields = (VMStateField[]) {
+        {
+            .name         = "extra_state",
+            .version_id   = 0,
+            .field_exists = NULL,
+            .size         = 0,
+            .info         = &vmstate_info_extra_state,
+            .flags        = VMS_SINGLE,
+            .offset       = 0,
+        },
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_virtio_device_endian = {
     .name = "virtio/device_endian",
     .version_id = 1,
@@ -1245,6 +1302,7 @@ static const VMStateDescription vmstate_virtio = {
         &vmstate_virtio_64bit_features,
         &vmstate_virtio_virtqueues,
         &vmstate_virtio_ringsize,
+        &vmstate_virtio_extra_state,
         NULL
     }
 };

include/hw/compat.h

@@ -10,7 +10,15 @@
             .driver   = "e1000",\
             .property = "extra_mac_registers",\
             .value    = "off",\
-         },
+        },{\
+            .driver   = "virtio-pci",\
+            .property = "x-disable-pcie",\
+            .value    = "on",\
+        },{\
+            .driver   = "virtio-pci",\
+            .property = "migrate-extra",\
+            .value    = "off",\
+        },
 
 #define HW_COMPAT_2_3 \
         {\

include/hw/virtio/virtio-bus.h

@@ -44,9 +44,12 @@ typedef struct VirtioBusClass {
     void (*notify)(DeviceState *d, uint16_t vector);
     void (*save_config)(DeviceState *d, QEMUFile *f);
     void (*save_queue)(DeviceState *d, int n, QEMUFile *f);
+    void (*save_extra_state)(DeviceState *d, QEMUFile *f);
     int (*load_config)(DeviceState *d, QEMUFile *f);
     int (*load_queue)(DeviceState *d, int n, QEMUFile *f);
     int (*load_done)(DeviceState *d, QEMUFile *f);
+    int (*load_extra_state)(DeviceState *d, QEMUFile *f);
+    bool (*has_extra_state)(DeviceState *d);
     bool (*query_guest_notifiers)(DeviceState *d);
     int (*set_guest_notifiers)(DeviceState *d, int nvqs, bool assign);
     int (*set_host_notifier)(DeviceState *d, int n, bool assigned);

include/sysemu/kvm.h

@@ -53,6 +53,7 @@ extern bool kvm_gsi_routing_allowed;
 extern bool kvm_gsi_direct_mapping;
 extern bool kvm_readonly_mem_allowed;
 extern bool kvm_direct_msi_allowed;
+extern bool kvm_ioeventfd_any_length_allowed;
 
 #if defined CONFIG_KVM || !defined NEED_CPU_H
 #define kvm_enabled()           (kvm_allowed)
@@ -153,6 +154,12 @@ extern bool kvm_direct_msi_allowed;
  */
 #define kvm_direct_msi_enabled() (kvm_direct_msi_allowed)
 
+/**
+ * kvm_ioeventfd_any_length_enabled:
+ * Returns: true if KVM allows any length io eventfd.
+ */
+#define kvm_ioeventfd_any_length_enabled() (kvm_ioeventfd_any_length_allowed)
+
 #else
 #define kvm_enabled()           (0)
 #define kvm_irqchip_in_kernel() (false)
@@ -166,6 +173,7 @@ extern bool kvm_direct_msi_allowed;
 #define kvm_gsi_direct_mapping() (false)
 #define kvm_readonly_mem_enabled() (false)
 #define kvm_direct_msi_enabled() (false)
+#define kvm_ioeventfd_any_length_enabled() (false)
 #endif
 
 struct kvm_run;

kvm-all.c

@@ -109,6 +109,7 @@ bool kvm_allowed;
 bool kvm_readonly_mem_allowed;
 bool kvm_vm_attributes_allowed;
 bool kvm_direct_msi_allowed;
+bool kvm_ioeventfd_any_length_allowed;
 
 static const KVMCapabilityInfo kvm_required_capabilites[] = {
     KVM_CAP_INFO(USER_MEMORY),
@@ -1611,6 +1612,9 @@ static int kvm_init(MachineState *ms)
     kvm_vm_attributes_allowed =
         (kvm_check_extension(s, KVM_CAP_VM_ATTRIBUTES) > 0);
 
+    kvm_ioeventfd_any_length_allowed =
+        (kvm_check_extension(s, KVM_CAP_IOEVENTFD_ANY_LENGTH) > 0);
+
     ret = kvm_arch_init(ms, s);
     if (ret < 0) {
         goto err;

kvm-stub.c

@@ -30,6 +30,7 @@ bool kvm_gsi_routing_allowed;
 bool kvm_gsi_direct_mapping;
 bool kvm_allowed;
 bool kvm_readonly_mem_allowed;
+bool kvm_ioeventfd_any_length_allowed;
 
 int kvm_init_vcpu(CPUState *cpu)
 {

linux-headers/linux/vhost.h

@@ -78,7 +78,7 @@ struct vhost_memory {
 #define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
 /* Give up ownership, and reset the device to default values.
  * Allows subsequent call to VHOST_OWNER_SET to succeed. */
-#define VHOST_RESET_DEVICE _IO(VHOST_VIRTIO, 0x02)
+#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
 
 /* Set up/modify memory layout */
 #define VHOST_SET_MEM_TABLE	_IOW(VHOST_VIRTIO, 0x03, struct vhost_memory)

memory.c

@@ -1688,7 +1688,9 @@ void memory_region_add_eventfd(MemoryRegion *mr,
     };
     unsigned i;
 
-    adjust_endianness(mr, &mrfd.data, size);
+    if (size) {
+        adjust_endianness(mr, &mrfd.data, size);
+    }
     memory_region_transaction_begin();
     for (i = 0; i < mr->ioeventfd_nb; ++i) {
         if (memory_region_ioeventfd_before(mrfd, mr->ioeventfds[i])) {
@@ -1721,7 +1723,9 @@ void memory_region_del_eventfd(MemoryRegion *mr,
     };
     unsigned i;
 
-    adjust_endianness(mr, &mrfd.data, size);
+    if (size) {
+        adjust_endianness(mr, &mrfd.data, size);
+    }
     memory_region_transaction_begin();
     for (i = 0; i < mr->ioeventfd_nb; ++i) {
         if (memory_region_ioeventfd_equal(mrfd, mr->ioeventfds[i])) {

tests/vhost-user-bridge.c

@@ -188,7 +188,7 @@ typedef enum VhostUserRequest {
     VHOST_USER_GET_FEATURES = 1,
     VHOST_USER_SET_FEATURES = 2,
     VHOST_USER_SET_OWNER = 3,
-    VHOST_USER_RESET_DEVICE = 4,
+    VHOST_USER_RESET_OWNER = 4,
     VHOST_USER_SET_MEM_TABLE = 5,
     VHOST_USER_SET_LOG_BASE = 6,
     VHOST_USER_SET_LOG_FD = 7,
@@ -274,7 +274,7 @@ static const char *vubr_request_str[] = {
     [VHOST_USER_GET_FEATURES]           =  "VHOST_USER_GET_FEATURES",
     [VHOST_USER_SET_FEATURES]           =  "VHOST_USER_SET_FEATURES",
     [VHOST_USER_SET_OWNER]              =  "VHOST_USER_SET_OWNER",
-    [VHOST_USER_RESET_DEVICE]           =  "VHOST_USER_RESET_DEVICE",
+    [VHOST_USER_RESET_OWNER]           =  "VHOST_USER_RESET_OWNER",
     [VHOST_USER_SET_MEM_TABLE]          =  "VHOST_USER_SET_MEM_TABLE",
     [VHOST_USER_SET_LOG_BASE]           =  "VHOST_USER_SET_LOG_BASE",
     [VHOST_USER_SET_LOG_FD]             =  "VHOST_USER_SET_LOG_FD",
@@ -921,7 +921,7 @@ vubr_execute_request(VubrDev *dev, VhostUserMsg *vmsg)
         return vubr_set_features_exec(dev, vmsg);
     case VHOST_USER_SET_OWNER:
         return vubr_set_owner_exec(dev, vmsg);
-    case VHOST_USER_RESET_DEVICE:
+    case VHOST_USER_RESET_OWNER:
         return vubr_reset_device_exec(dev, vmsg);
     case VHOST_USER_SET_MEM_TABLE:
         return vubr_set_mem_table_exec(dev, vmsg);

tests/vhost-user-test.c

@@ -57,7 +57,7 @@ typedef enum VhostUserRequest {
     VHOST_USER_GET_FEATURES = 1,
     VHOST_USER_SET_FEATURES = 2,
     VHOST_USER_SET_OWNER = 3,
-    VHOST_USER_RESET_DEVICE = 4,
+    VHOST_USER_RESET_OWNER = 4,
     VHOST_USER_SET_MEM_TABLE = 5,
     VHOST_USER_SET_LOG_BASE = 6,
     VHOST_USER_SET_LOG_FD = 7,
@@ -86,6 +86,11 @@ typedef struct VhostUserMemory {
     VhostUserMemoryRegion regions[VHOST_MEMORY_MAX_NREGIONS];
 } VhostUserMemory;
 
+typedef struct VhostUserLog {
+    uint64_t mmap_size;
+    uint64_t mmap_offset;
+} VhostUserLog;
+
 typedef struct VhostUserMsg {
     VhostUserRequest request;
 
@@ -94,10 +99,13 @@ typedef struct VhostUserMsg {
     uint32_t flags;
     uint32_t size; /* the following payload size */
     union {
+#define VHOST_USER_VRING_IDX_MASK   (0xff)
+#define VHOST_USER_VRING_NOFD_MASK  (0x1<<8)
         uint64_t u64;
         struct vhost_vring_state state;
         struct vhost_vring_addr addr;
         VhostUserMemory memory;
+        VhostUserLog log;
     } payload;
 } QEMU_PACKED VhostUserMsg;
 
@@ -307,7 +315,7 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
         g_cond_signal(&s->data_cond);
         break;
 
-    case VHOST_USER_RESET_DEVICE:
+    case VHOST_USER_RESET_OWNER:
         s->fds_num = 0;
         break;