QEMU源码全解析 —— virtio（14）

接前一篇文章：

本回对于virtio_pci_device_plugged函数进行详细解析。为了便于理解，再次贴出virtio_pci_device_plugged函数源码，在hw/virtio/virtio-pci.c中，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);
    }
}

这里只讲解virtio是modern模式的情况，也就是代码中非legacy的情况。

（1）virtio_pci_device_plugged函数设置virtio PCI代理设备的配置空间的vendor id和device id。代码片段如下：

    if (legacy) {
    {
        ……
    } 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);
    }

• vendor id

将vendor id设置为PCI_VENDOR_ID_REDHAT_QUMRANE。相关宏定义在include/hw/pci/pci.h中，如下：

/* Red Hat / Qumranet (for QEMU) -- see pci-ids.txt */
#define PCI_VENDOR_ID_REDHAT_QUMRANET    0x1af4
#define PCI_SUBVENDOR_ID_REDHAT_QUMRANET 0x1af4
#define PCI_SUBDEVICE_ID_QEMU            0x1100

• device id

将device id设置为PCI_DEVICE_ID_VIRTIO_10_BASE加上virtio设备类型的id。相关宏定义在include/hw/pci/pci.h中，如下：

/*
 * modern virtio-pci devices get their id assigned automatically,
 * there is no need to add #defines here.  It gets calculated as
 *
 * PCI_DEVICE_ID = PCI_DEVICE_ID_VIRTIO_10_BASE +
 *                 virtio_bus_get_vdev_id(bus)
 */
#define PCI_DEVICE_ID_VIRTIO_10_BASE     0x1040

对于virtual balloon来说是VIRTIO_ID_BALLOON。相关宏定义在include/standard-headers/linux/virtio_ids.h中，如下：

#define VIRTIO_ID_BALLOON		5 /* virtio balloon */

（2）接下来将virtio设备的寄存器配置信息作为PCIcapability写入到配置空间中。代码片段如下：

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);
    }

要看懂这段代码，需要先了解pci capability。pci capability用来表明设备的功能。virtio会把多个MemoryRegion作为VirtIOPCIProxy设备MMIO对用MemoryRegion的子MemoryRegion（比较拗口），这几个MemoryRegion的信息会作为capability写入到virtioPCI代理这个PCI设备的配置空间。这些capability的头结构用struct virtio_pci_cap表示。virtio_pci_cap结构的定义在include/standard-headers/linux/virtio_pci.h中，如下：

/* This is the PCI capability header: */
struct virtio_pci_cap {
	uint8_t cap_vndr;		/* Generic PCI field: PCI_CAP_ID_VNDR */
	uint8_t cap_next;		/* Generic PCI field: next ptr. */
	uint8_t cap_len;		/* Generic PCI field: capability length */
	uint8_t cfg_type;		/* Identifies the structure. */
	uint8_t bar;		/* Where to find it. */
	uint8_t id;		/* Multiple capabilities of the same type */
	uint8_t padding[2];	/* Pad to full dword. */
	uint32_t offset;		/* Offset within bar. */
	uint32_t length;		/* Length of the structure, in bytes. */
};

其中：

• cap_vndr用来表示capability的id。除了一些标准的capability外，如果是设备自定义的（如这里的virtio设备），会设置为PCI_CAP_ID_VNDR。
• cap_next指向下一个capability在PCI配置空间的偏移。
• bar表示这个capability使用哪个bar。
• offset表示这个capability代表的MemoryRegion在virtioPCI代理设备的bar中从哪里开始。
• length则表示此capability的长度。

整体上，virtio_pci_cap结构用来描述virtioPCI代理设备modern MMIO中的一段地址空间。virtio驱动可以通过这些capability信息将对应的地址映射到内核虚拟地址空间中，从而便于之后访问。PCI配置空间与cap以及MMIO的关系如下图所示：

virtio_pci_device_plugged函数的其余部分，将在下一回继续解析。