qemu虚拟化-pci设备模拟

pci设备算是学习qemu必须要掌握的一类设备的模拟，单独提出来说一下。这里以qemu的pci教学程序为基础讲解，源码路径：hw/misc/edu.c

1.设备的定义

typedef struct {
    PCIDevice pdev;
    MemoryRegion mmio;

    QemuThread thread;
    QemuMutex thr_mutex;
    QemuCond thr_cond;
    bool stopping;

    uint32_t addr4;
    uint32_t fact;
#define EDU_STATUS_COMPUTING    0x01
#define EDU_STATUS_IRQFACT      0x80
    uint32_t status;

    uint32_t irq_status;

#define EDU_DMA_RUN             0x1
#define EDU_DMA_DIR(cmd)        (((cmd) & 0x2) >> 1)
# define EDU_DMA_FROM_PCI       0
# define EDU_DMA_TO_PCI         1
#define EDU_DMA_IRQ             0x4
    struct dma_state {
        dma_addr_t src;
        dma_addr_t dst;
        dma_addr_t cnt;
        dma_addr_t cmd;
    } dma;
    QEMUTimer dma_timer;
    char dma_buf[DMA_SIZE];
    uint64_t dma_mask;
} EduState;

这个设备有一个dma，继承自PCIDevice，初始化过后是PCIDeviceClass类型，来看一下PCIDeviceClass

typedef struct PCIDeviceClass {
    DeviceClass parent_class;

    void (*realize)(PCIDevice *dev, Error **errp);
    PCIUnregisterFunc *exit;
    PCIConfigReadFunc *config_read;
    PCIConfigWriteFunc *config_write;

    uint16_t vendor_id;
    uint16_t device_id;
    uint8_t revision;
    uint16_t class_id;
    uint16_t subsystem_vendor_id;       /* only for header type = 0 */
    uint16_t subsystem_id;              /* only for header type = 0 */

    /*
     * pci-to-pci bridge or normal device.
     * This doesn't mean pci host switch.
     * When card bus bridge is supported, this would be enhanced.
     */
    int is_bridge;

    /* rom bar */
    const char *romfile;
} PCIDeviceClass;

主要关注config_read、config_write、vendor_id、device_id、revision、class_id
config_read、config_write两个函数不需要我们自己去实现，pci框架里面已经实现好了。框架会模拟好config的读写。

2.类的初始化

static void edu_class_init(ObjectClass *class, void *data)
{
    PCIDeviceClass *k = PCI_DEVICE_CLASS(class);

    k->realize = pci_edu_realize;
    k->exit = pci_edu_uninit;
    k->vendor_id = PCI_VENDOR_ID_QEMU;
    k->device_id = 0x11e8;
    k->revision = 0x10;
    k->class_id = PCI_CLASS_OTHERS;
}

static void pci_edu_register_types(void)
{
    static InterfaceInfo interfaces[] = {
        { INTERFACE_CONVENTIONAL_PCI_DEVICE },
        { },
    };
    static const TypeInfo edu_info = {
        .name          = TYPE_PCI_EDU_DEVICE,
        .parent        = TYPE_PCI_DEVICE,
        .instance_size = sizeof(EduState),
        .instance_init = edu_instance_init,
        .class_init    = edu_class_init,
        .interfaces = interfaces,
    };

    type_register_static(&edu_info);
}对吗

对象的初始化不需要定义太多，参考PCIDeviceClass结构体中定义的那些函数实现了就行。config_read、config_write一般不需要自己写，框架有默认的实现。

3.设备的初始化

static void pci_edu_realize(PCIDevice *pdev, Error **errp)
{
    EduState *edu = EDU(pdev);
    uint8_t *pci_conf = pdev->config;

    pci_config_set_interrupt_pin(pci_conf, 1);

    if (msi_init(pdev, 0, 1, true, false, errp)) {
        return;
    }

    timer_init_ms(&edu->dma_timer, QEMU_CLOCK_VIRTUAL, edu_dma_timer, edu);

    qemu_mutex_init(&edu->thr_mutex);
    qemu_cond_init(&edu->thr_cond);
    qemu_thread_create(&edu->thread, "edu", edu_fact_thread,
                       edu, QEMU_THREAD_JOINABLE);

    memory_region_init_io(&edu->mmio, OBJECT(edu), &edu_mmio_ops, edu,
                    "edu-mmio", 1 * MiB);
    pci_register_bar(pdev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY, &edu->mmio);
}

static void pci_edu_uninit(PCIDevice *pdev)
{
    EduState *edu = EDU(pdev);

    qemu_mutex_lock(&edu->thr_mutex);
    edu->stopping = true;
    qemu_mutex_unlock(&edu->thr_mutex);
    qemu_cond_signal(&edu->thr_cond);
    qemu_thread_join(&edu->thread);

    qemu_cond_destroy(&edu->thr_cond);
    qemu_mutex_destroy(&edu->thr_mutex);

    timer_del(&edu->dma_timer);
}

static void edu_obj_uint64(Object *obj, Visitor *v, const char *name,
                           void *opaque, Error **errp)
{
    uint64_t *val = opaque;

    visit_type_uint64(v, name, val, errp);
}

static void edu_instance_init(Object *obj)
{
    EduState *edu = EDU(obj);
    edu->dma_mask = (1UL << 28) - 1;
    object_property_add(obj, "dma_mask", "uint64", edu_obj_uint64,
                    edu_obj_uint64, NULL, &edu->dma_mask, NULL);
}

timer_init_ms注册定时器，不间断的查看是否有dma传送需求
qemu_thread_create创建一个线程
memory_region_init_io设置好mmio参数，mmio大小为1M
pci_register_bar吧上一步设置好的mmio参数注册到pci桥上，参数照着写就行。

4.设备的读写模拟

static uint64_t edu_mmio_read(void *opaque, hwaddr addr, unsigned size)
{
    EduState *edu = opaque;
    uint64_t val = ~0ULL;

    if (size != 4) {
        return val;
    }

    switch (addr) {
    case 0x00:
        val = 0x010000edu;
        break;
    case 0x04:
        val = edu->addr4;
        break;
    case 0x08:
        qemu_mutex_lock(&edu->thr_mutex);
        val = edu->fact;
        qemu_mutex_unlock(&edu->thr_mutex);
        break;
    case 0x20:
        val = atomic_read(&edu->status);
        break;
    case 0x24:
        val = edu->irq_status;
        break;
    case 0x80:
        dma_rw(edu, false, &val, &edu->dma.src, false);
        break;
    case 0x88:
        dma_rw(edu, false, &val, &edu->dma.dst, false);
        break;
    case 0x90:
        dma_rw(edu, false, &val, &edu->dma.cnt, false);
        break;
    case 0x98:
        dma_rw(edu, false, &val, &edu->dma.cmd, false);
        break;
    }

    return val;
}

static void edu_mmio_write(void *opaque, hwaddr addr, uint64_t val,
                unsigned size)
{
    EduState *edu = opaque;

    if (addr < 0x80 && size != 4) {
        return;
    }

    if (addr >= 0x80 && size != 4 && size != 8) {
        return;
    }

    switch (addr) {
    case 0x04:
        edu->addr4 = ~val;
        break;
    case 0x08:
        if (atomic_read(&edu->status) & EDU_STATUS_COMPUTING) {
            break;
        }
        /* EDU_STATUS_COMPUTING cannot go 0->1 concurrently, because it is only
         * set in this function and it is under the iothread mutex.
         */
        qemu_mutex_lock(&edu->thr_mutex);
        edu->fact = val;
        atomic_or(&edu->status, EDU_STATUS_COMPUTING);
        qemu_cond_signal(&edu->thr_cond);
        qemu_mutex_unlock(&edu->thr_mutex);
        break;
    case 0x20:
        if (val & EDU_STATUS_IRQFACT) {
            atomic_or(&edu->status, EDU_STATUS_IRQFACT);
        } else {
            atomic_and(&edu->status, ~EDU_STATUS_IRQFACT);
        }
        break;
    case 0x60:
        edu_raise_irq(edu, val);
        break;
    case 0x64:
        edu_lower_irq(edu, val);
        break;
    case 0x80:
        dma_rw(edu, true, &val, &edu->dma.src, false);
        break;
    case 0x88:
        dma_rw(edu, true, &val, &edu->dma.dst, false);
        break;
    case 0x90:
        dma_rw(edu, true, &val, &edu->dma.cnt, false);
        break;
    case 0x98:
        if (!(val & EDU_DMA_RUN)) {
            break;
        }
        dma_rw(edu, true, &val, &edu->dma.cmd, true);
        break;
    }
}

MMIO的读写模拟本质上跟普通设备没有任何区别，这里就不多说了。

5.设备dma的模拟

static void edu_dma_timer(void *opaque)
{
    EduState *edu = opaque;
    bool raise_irq = false;

    if (!(edu->dma.cmd & EDU_DMA_RUN)) {
        return;
    }

    if (EDU_DMA_DIR(edu->dma.cmd) == EDU_DMA_FROM_PCI) {
        uint32_t dst = edu->dma.dst;
        edu_check_range(dst, edu->dma.cnt, DMA_START, DMA_SIZE);
        dst -= DMA_START;
        pci_dma_read(&edu->pdev, edu_clamp_addr(edu, edu->dma.src),
                edu->dma_buf + dst, edu->dma.cnt);
    } else {
        uint32_t src = edu->dma.src;
        edu_check_range(src, edu->dma.cnt, DMA_START, DMA_SIZE);
        src -= DMA_START;
        pci_dma_write(&edu->pdev, edu_clamp_addr(edu, edu->dma.dst),
                edu->dma_buf + src, edu->dma.cnt);
    }

    edu->dma.cmd &= ~EDU_DMA_RUN;
    if (edu->dma.cmd & EDU_DMA_IRQ) {
        raise_irq = true;
    }

    if (raise_irq) {
        edu_raise_irq(edu, DMA_IRQ);
    }
}

static void dma_rw(EduState *edu, bool write, dma_addr_t *val, dma_addr_t *dma,
                bool timer)
{
    if (write && (edu->dma.cmd & EDU_DMA_RUN)) {
        return;
    }

    if (write) {
        *dma = *val;
    } else {
        *val = *dma;
    }

    if (timer) {
        timer_mod(&edu->dma_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + 100);
    }
}

这里的dma完全用的软件模拟，命令下发后延时100ms进行数据拷贝，完全软件拷贝。完成后设置好irq通知guest。