QEMU源码全解析 —— virtio（15）
接前一篇文章：
上一回讲解了virtio_pci_device_plugged函数的前两部分，本回继续讲解virtio_pci_device_plugged函数的其余部分。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, ¬ify.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,
¬ify_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);
}
}（3）virtio_pci_modern_regions_init函数初始化5个MemoryRegion，分别是virtio-pci-common、virtio-pci-isr、virtio-pci-device、virtio-pci-notify和virtio-pci-notify-pio。代码片段如下：
virtio_pci_modern_regions_init(proxy, vdev->name);virtio_pci_modern_regions_init函数在hw/virtio/virtio-pci.c中，代码如下：
static void virtio_pci_modern_regions_init(VirtIOPCIProxy *proxy,
const char *vdev_name)
{
static const MemoryRegionOps common_ops = {
.read = virtio_pci_common_read,
.write = virtio_pci_common_write,
.impl = {
.min_access_size = 1,
.max_access_size = 4,
},
.endianness = DEVICE_LITTLE_ENDIAN,
};
static const MemoryRegionOps isr_ops = {
.read = virtio_pci_isr_read,
.write = virtio_pci_isr_write,
.impl = {
.min_access_size = 1,
.max_access_size = 4,
},
.endianness = DEVICE_LITTLE_ENDIAN,
};
static const MemoryRegionOps device_ops = {
.read = virtio_pci_device_read,
.write = virtio_pci_device_write,
.impl = {
.min_access_size = 1,
.max_access_size = 4,
},
.endianness = DEVICE_LITTLE_ENDIAN,
};
static const MemoryRegionOps notify_ops = {
.read = virtio_pci_notify_read,
.write = virtio_pci_notify_write,
.impl = {
.min_access_size = 1,
.max_access_size = 4,
},
.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,
};
g_autoptr(GString) name = g_string_new(NULL);
g_string_printf(name, "virtio-pci-common-%s", vdev_name);
memory_region_init_io(&proxy->common.mr, OBJECT(proxy),
&common_ops,
proxy,
name->str,
proxy->common.size);
g_string_printf(name, "virtio-pci-isr-%s", vdev_name);
memory_region_init_io(&proxy->isr.mr, OBJECT(proxy),
&isr_ops,
proxy,
name->str,
proxy->isr.size);
g_string_printf(name, "virtio-pci-device-%s", vdev_name);
memory_region_init_io(&proxy->device.mr, OBJECT(proxy),
&device_ops,
proxy,
name->str,
proxy->device.size);
g_string_printf(name, "virtio-pci-notify-%s", vdev_name);
memory_region_init_io(&proxy->notify.mr, OBJECT(proxy),
¬ify_ops,
proxy,
name->str,
proxy->notify.size);
g_string_printf(name, "virtio-pci-notify-pio-%s", vdev_name);
memory_region_init_io(&proxy->notify_pio.mr, OBJECT(proxy),
¬ify_pio_ops,
proxy,
name->str,
proxy->notify_pio.size);
}VirtIOPCIProxy结构的定义在include/hw/virtio/virtio-pci.h中，如下：
struct VirtIOPCIProxy {
PCIDevice pci_dev;
MemoryRegion bar;
union {
struct {
VirtIOPCIRegion common;
VirtIOPCIRegion isr;
VirtIOPCIRegion device;
VirtIOPCIRegion notify;
VirtIOPCIRegion notify_pio;
};
VirtIOPCIRegion regs[5];
};
MemoryRegion modern_bar;
MemoryRegion io_bar;
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;
/* Transitional device id */
uint16_t trans_devid;
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;
};virtio-pci-common、virtio-pci-isr、virtio-pci-device、virtio-pci-notify和virtio-pci-notify-pio这5个MemoryRegion的相关信息存放在VirtIOPCIProxy结构中的几个VirtIOPCIRegion成员中。
（4）virtio_pci_device_plugged接下来调用virtio_pci_modern_mem_region_map函。代码片段如下：
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, ¬ify.cap);virtio_pci_modern_mem_region_map函数在hw/virtio/virtio-pci.c中，代码如下：
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_idx);
}virtio_pci_modern_mem_region_map函数仅仅调用了virtio_pci_modern_region_map函数。该函数也在hw/virtio/virtio-pci.c中（就在上边），代码如下：
static void virtio_pci_modern_region_map(VirtIOPCIProxy *proxy,
VirtIOPCIRegion *region,
struct virtio_pci_cap *cap,
MemoryRegion *mr,
uint8_t bar)
{
memory_region_add_subregion(mr, region->offset, ®ion->mr);
cap->cfg_type = region->type;
cap->bar = bar;
cap->offset = cpu_to_le32(region->offset);
cap->length = cpu_to_le32(region->size);
virtio_pci_add_mem_cap(proxy, cap);
}
virtio_pci_modern_region_map函数完成了两个功能：
1）将VirtIOPCIRegion的mr成员virtio-pci-***作为子MemoryRegion加入到VirtIOProxy的modern_bar成员中去。所以当在虚拟机内部写virtio PCI proxy的MMIO时会落入这几个virtio设备的MemoryRegion的回调函数。
2）调用virtio_pci_add_mem_cap函数将这些寄存器信息加入到virtio PCI代理设备的pci capability上去。virtio_pci_add_mem_cap函数同样在hw/virtio/virtio-pci.c中，代码如下：
static int virtio_pci_add_mem_cap(VirtIOPCIProxy *proxy,
struct virtio_pci_cap *cap)
{
PCIDevice *dev = &proxy->pci_dev;
int offset;
offset = pci_add_capability(dev, PCI_CAP_ID_VNDR, 0,
cap->cap_len, &error_abort);
assert(cap->cap_len >= sizeof *cap);
memcpy(dev->config + offset + PCI_CAP_FLAGS, &cap->cap_len,
cap->cap_len - PCI_CAP_FLAGS);
return offset;
}virtio_pci_device_plugged函数的其余部分，将在下一回继续解析。