QEMU源码全解析 —— virtio（13）

接前一篇文章：

通过前文书（从QEMU源码全解析 —— virtio（9）开始）对整个流程以及各个相关函数的解析，可以看到从virtio PCI代理设备的具现化到virtio设备的具现化过程。但前述分析还遗漏了一部分，就是virtio设备挂载到virtio总线上的行为。这个过程是在virtio_device_realize函数中通过调用virtio_bus_device_plugged函数完成的。在QEMU源码全解析 —— virtio（11）中提到过，有图为证：

virtio_bus_device_plugged函数的作用就是将virtio设备插入到virtio总线上去。其源码在hw/virtio/virtio-bus.c中，如下：

/* A VirtIODevice is being plugged */
void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp)
{
    DeviceState *qdev = DEVICE(vdev);
    BusState *qbus = BUS(qdev_get_parent_bus(qdev));
    VirtioBusState *bus = VIRTIO_BUS(qbus);
    VirtioBusClass *klass = VIRTIO_BUS_GET_CLASS(bus);
    VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
    bool has_iommu = virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
    bool vdev_has_iommu;
    Error *local_err = NULL;

    DPRINTF("%s: plug device.\n", qbus->name);

    if (klass->pre_plugged != NULL) {
        klass->pre_plugged(qbus->parent, &local_err);
        if (local_err) {
            error_propagate(errp, local_err);
            return;
        }
    }

    /* Get the features of the plugged device. */
    assert(vdc->get_features != NULL);
    vdev->host_features = vdc->get_features(vdev, vdev->host_features,
                                            &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }

    if (klass->device_plugged != NULL) {
        klass->device_plugged(qbus->parent, &local_err);
    }
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }

    vdev->dma_as = &address_space_memory;
    if (has_iommu) {
        vdev_has_iommu = virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
        /*
         * Present IOMMU_PLATFORM to the driver iff iommu_plattform=on and
         * device operational. If the driver does not accept IOMMU_PLATFORM
         * we fail the device.
         */
        virtio_add_feature(&vdev->host_features, VIRTIO_F_IOMMU_PLATFORM);
        if (klass->get_dma_as) {
            vdev->dma_as = klass->get_dma_as(qbus->parent);
            if (!vdev_has_iommu && vdev->dma_as != &address_space_memory) {
                error_setg(errp,
                       "iommu_platform=true is not supported by the device");
                return;
            }
        }
    }
}

virtio_bus_device_plugged函数主要是调用了VirtioBusClass类型的device_plugged回调函数。代码片段如下：

    VirtioBusClass *klass = VIRTIO_BUS_GET_CLASS(bus);
    ……
    if (klass->device_plugged != NULL) {
        klass->device_plugged(qbus->parent, &local_err);
    }
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }

device_pluggeg回调函数也即klass->device_plugged函数指针所指向的函数在virtio_pci_bus_class_init函数中被初始化成了virtio_pci_device_plugged函数。virtio_pci_bus_class_init函数在hw/virtio/virtio-pci.c中，代码如下：

static void virtio_pci_bus_class_init(ObjectClass *klass, void *data)
{
    BusClass *bus_class = BUS_CLASS(klass);
    VirtioBusClass *k = VIRTIO_BUS_CLASS(klass);
    bus_class->max_dev = 1;
    k->notify = virtio_pci_notify;
    k->save_config = virtio_pci_save_config;
    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_guest_notifiers = virtio_pci_set_guest_notifiers;
    k->set_host_notifier_mr = virtio_pci_set_host_notifier_mr;
    k->vmstate_change = virtio_pci_vmstate_change;
    k->pre_plugged = virtio_pci_pre_plugged;
    k->device_plugged = virtio_pci_device_plugged;
    k->device_unplugged = virtio_pci_device_unplugged;
    k->query_nvectors = virtio_pci_query_nvectors;
    k->ioeventfd_enabled = virtio_pci_ioeventfd_enabled;
    k->ioeventfd_assign = virtio_pci_ioeventfd_assign;
    k->get_dma_as = virtio_pci_get_dma_as;
    k->iommu_enabled = virtio_pci_iommu_enabled;
    k->queue_enabled = virtio_pci_queue_enabled;
}

virtio_pci_device_plugged函数在hw/virtio/virtio-pci.c中，代码如下：

/* This is called by virtio-bus just after the device is plugged. */
static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
{
    VirtIOPCIProxy *proxy = VIRTIO_PCI(d);
    VirtioBusState *bus = &proxy->bus;
    bool legacy = virtio_pci_legacy(proxy);
    bool 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);

    /*
     * Virtio capabilities present without
     * VIRTIO_F_VERSION_1 confuses guests
     */
    if (!proxy->ignore_backend_features &&
            !virtio_has_feature(vdev->host_features, VIRTIO_F_VERSION_1)) {
        virtio_pci_disable_modern(proxy);

        if (!legacy) {
            error_setg(errp, "Device doesn't support modern mode, and legacy"
                             " mode is disabled");
            error_append_hint(errp, "Set disable-legacy to off\n");

            return;
        }
    }

    modern = virtio_pci_modern(proxy);

    config = proxy->pci_dev.config;
    if (proxy->class_code) {
        pci_config_set_class(config, proxy->class_code);
    }

    if (legacy) {
        if (!virtio_legacy_allowed(vdev)) {
            /*
             * To avoid migration issues, we allow legacy mode when legacy
             * check is disabled in the old machine types (< 5.1).
             */
            if (virtio_legacy_check_disabled(vdev)) {
                warn_report("device is modern-only, but for backward "
                            "compatibility legacy is allowed");
            } else {
                error_setg(errp,
                           "device is modern-only, use disable-legacy=on");
                return;
            }
        }
        if (virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM)) {
            error_setg(errp, "VIRTIO_F_IOMMU_PLATFORM was supported by"
                       " neither legacy nor transitional device");
            return;
        }
        /*
         * Legacy and transitional devices use specific subsystem IDs.
         * Note that the subsystem vendor ID (config + PCI_SUBSYSTEM_VENDOR_ID)
         * is set to PCI_SUBVENDOR_ID_REDHAT_QUMRANET by default.
         */
        pci_set_word(config + PCI_SUBSYSTEM_ID, virtio_bus_get_vdev_id(bus));
        if (proxy->trans_devid) {
            pci_config_set_device_id(config, proxy->trans_devid);
        }
    } else {
        /* pure virtio-1.0 */
        pci_set_word(config + PCI_VENDOR_ID,
                     PCI_VENDOR_ID_REDHAT_QUMRANET);
        pci_set_word(config + PCI_DEVICE_ID,
                     PCI_DEVICE_ID_VIRTIO_10_BASE + virtio_bus_get_vdev_id(bus));
        pci_config_set_revision(config, 1);
    }
    config[PCI_INTERRUPT_PIN] = 1;


    if (modern) {
        struct virtio_pci_cap cap = {
            .cap_len = sizeof cap,
        };
        struct virtio_pci_notify_cap notify = {
            .cap.cap_len = sizeof notify,
            .notify_off_multiplier =
                cpu_to_le32(virtio_pci_queue_mem_mult(proxy)),
        };
        struct virtio_pci_cfg_cap cfg = {
            .cap.cap_len = sizeof cfg,
            .cap.cfg_type = VIRTIO_PCI_CAP_PCI_CFG,
        };
        struct virtio_pci_notify_cap notify_pio = {
            .cap.cap_len = sizeof notify,
            .notify_off_multiplier = cpu_to_le32(0x0),
        };

        struct virtio_pci_cfg_cap *cfg_mask;

        virtio_pci_modern_regions_init(proxy, vdev->name);

        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_idx,
                             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_idx,
                         PCI_BASE_ADDRESS_SPACE_MEMORY |
                         PCI_BASE_ADDRESS_MEM_PREFETCH |
                         PCI_BASE_ADDRESS_MEM_TYPE_64,
                         &proxy->modern_bar);

        proxy->config_cap = virtio_pci_add_mem_cap(proxy, &cfg.cap);
        cfg_mask = (void *)(proxy->pci_dev.wmask + proxy->config_cap);
        pci_set_byte(&cfg_mask->cap.bar, ~0x0);
        pci_set_long((uint8_t *)&cfg_mask->cap.offset, ~0x0);
        pci_set_long((uint8_t *)&cfg_mask->cap.length, ~0x0);
        pci_set_long(cfg_mask->pci_cfg_data, ~0x0);
    }

    if (proxy->nvectors) {
        int err = msix_init_exclusive_bar(&proxy->pci_dev, proxy->nvectors,
                                          proxy->msix_bar_idx, NULL);
        if (err) {
            /* Notice when a system that supports MSIx can't initialize it */
            if (err != -ENOTSUP) {
                warn_report("unable to init msix vectors to %" PRIu32,
                            proxy->nvectors);
            }
            proxy->nvectors = 0;
        }
    }

    proxy->pci_dev.config_write = virtio_write_config;
    proxy->pci_dev.config_read = virtio_read_config;

    if (legacy) {
        size = VIRTIO_PCI_REGION_SIZE(&proxy->pci_dev)
            + virtio_bus_get_vdev_config_len(bus);
        size = pow2ceil(size);

        memory_region_init_io(&proxy->bar, OBJECT(proxy),
                              &virtio_pci_config_ops,
                              proxy, "virtio-pci", size);

        pci_register_bar(&proxy->pci_dev, proxy->legacy_io_bar_idx,
                         PCI_BASE_ADDRESS_SPACE_IO, &proxy->bar);
    }
}

可以看到，virtio_pci_device_plugged函数比较长，在笔者选用的qemu-8.1.3版本的源码中有160行左右。

对于virtio_pci_device_plugged函数的详细解析，请看下回。