virtio blk原理

别人写的virtio blk原理

virtio的原理说起来挺简单的，两边是front-driver，backend-driver，中间是virtio和vring。关键是front-driver如何将io操作传到backend-driver，backend-driver又是如何将这些io操作解析出来，执行完，通知回front-driver的？这里面的细节，细思极恐！
问题一：Guest，Hypervisor，Host是如何建立联系的？本质就是初始化过程！

virtio初始化函数很有规律基本就是：virtio_*_init，这种形式，那就好搞了，用systemtap抓取初始化的调用：

各种class初始化：
call virtio_device_class_init
call virtio_blk_class_init
call virtio_rng_class_init
call virtio_serial_port_class_init
call virtio_pci_class_init
call virtio_serial_pci_class_init
call virtio_bus_class_init
call virtio_pci_bus_class_init
call virtio_scsi_pci_class_init
call virtio_balloon_pci_class_init
call virtio_serial_class_init
call virtio_balloon_class_init
call virtio_mmio_bus_class_init
call virtio_scsi_common_class_init
call virtio_net_class_init
call virtio_mmio_class_init
call virtio_9p_class_init
call virtio_blk_pci_class_init
call virtio_scsi_class_init
call virtio_9p_pci_class_init
call virtio_rng_pci_class_init
call virtio_net_pci_class_init

virtio-serial-pci初始化（这个是个什么设备）：
call virtio_serial_pci_instance_init
call virtio_pci_init
call virtio_serial_pci_init

我们的主角virtio blk初始化：
call virtio_blk_pci_instance_init
call virtio_pci_init
call virtio_blk_pci_init

我在虚拟机里面添加了virtio balloon设备：
call virtio_balloon_pci_instance_init
call virtio_pci_init
call virtio_balloon_pci_init

virtio blk的Qemu相关参数有两个：

-drive file=/home/mq/Documents/IDV/idv-update/login.img,if=none,id=drive-virtio-disk1,format=qcow2 
-device virtio-blk-pci,scsi=off,bus=pci.0,addr=0x8,drive=drive-virtio-disk1,id=virtio-disk1,bootindex=1

可以看到virtio blk的TypeInfo name是："virtio-blk-pci"。
Instance结构：

struct PCIDevice {
    DeviceState qdev;

    /* PCI config space */
    uint8_t *config;

    /* Used to enable config checks on load. Note that writable bits are
     * never checked even if set in cmask. */
    uint8_t *cmask;

    /* Used to implement R/W bytes */
    uint8_t *wmask;

    /* Used to implement RW1C(Write 1 to Clear) bytes */
    uint8_t *w1cmask;

    /* Used to allocate config space for capabilities. */
    uint8_t *used;

    /* the following fields are read only */
    PCIBus *bus;
    int32_t devfn;
    /* Cached device to fetch requester ID from, to avoid the PCI
     * tree walking every time we invoke PCI request (e.g.,
     * MSI). For conventional PCI root complex, this field is
     * meaningless. */
    PCIReqIDCache requester_id_cache;
    char name[64];
    PCIIORegion io_regions[PCI_NUM_REGIONS];
    AddressSpace bus_master_as;
    MemoryRegion bus_master_container_region;
    MemoryRegion bus_master_enable_region;

    /* do not access the following fields */
    PCIConfigReadFunc *config_read;
    PCIConfigWriteFunc *config_write;

    /* Legacy PCI VGA regions */
    MemoryRegion *vga_regions[QEMU_PCI_VGA_NUM_REGIONS];
    bool has_vga;

    /* Current IRQ levels.  Used internally by the generic PCI code.  */
    uint8_t irq_state;

    /* Capability bits */
    uint32_t cap_present;

    /* Offset of MSI-X capability in config space */
    uint8_t msix_cap;

    /* MSI-X entries */
    int msix_entries_nr;

    /* Space to store MSIX table & pending bit array */
    uint8_t *msix_table;
    uint8_t *msix_pba;
    /* MemoryRegion container for msix exclusive BAR setup */
    MemoryRegion msix_exclusive_bar;
    /* Memory Regions for MSIX table and pending bit entries. */
    MemoryRegion msix_table_mmio;
    MemoryRegion msix_pba_mmio;
    /* Reference-count for entries actually in use by driver. */
    unsigned *msix_entry_used;
    /* MSIX function mask set or MSIX disabled */
    bool msix_function_masked;
    /* Version id needed for VMState */
    int32_t version_id;

    /* Offset of MSI capability in config space */
    uint8_t msi_cap;

    /* PCI Express */
    PCIExpressDevice exp;

    /* SHPC */
    SHPCDevice *shpc;

    /* Location of option rom */
    char *romfile;
    bool has_rom;
    MemoryRegion rom;
    uint32_t rom_bar;

    /* INTx routing notifier */
    PCIINTxRoutingNotifier intx_routing_notifier;

    /* MSI-X notifiers */
    MSIVectorUseNotifier msix_vector_use_notifier;
    MSIVectorReleaseNotifier msix_vector_release_notifier;
    MSIVectorPollNotifier msix_vector_poll_notifier;
};
struct VirtIOPCIProxy {
    PCIDevice pci_dev;
    MemoryRegion bar;
    VirtIOPCIRegion common;
    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_idx;
    uint32_t msix_bar_idx;
    uint32_t modern_io_bar_idx;
    uint32_t modern_mem_bar_idx;
    int config_cap;
    uint32_t flags;
    bool disable_modern;
    bool ignore_backend_features;
    OnOffAuto disable_legacy;
    uint32_t class_code;
    uint32_t nvectors;
    uint32_t dfselect;
    uint32_t gfselect;
    uint32_t guest_features[2];
    VirtIOPCIQueue vqs[VIRTIO_QUEUE_MAX];

    VirtIOIRQFD *vector_irqfd;
    int nvqs_with_notifiers;
    VirtioBusState bus;
};
struct VirtIOBlkPCI {
    VirtIOPCIProxy parent_obj;
    VirtIOBlock vdev;
};

上面的结构体有个规律，逐渐由pci device往blk device转变，VirtIOPCIProxy，VirtIOBlock两个就是pci device和blk device的桥梁。