云计算国产化之路 vnc登录 文件系统直通(virtio-9p) 扩展qemu接口 gpg WARNING 珍藏博客 虚拟内存情况dommemstat分析 免密码自动登录脚本 Linux网桥 测试网段IP占用情况 Linux 进程状态 systemc强制依赖 调试openstack ut uefi p2v 重做ubuntu内核 virsh创建虚拟机简介 virtio IO路径 虚拟化层升级后磁盘无法卸载卷 vmtouch使用 Taint flags 主机和虚拟机文件共享处理的几种方法 kvm分析工具 kvm中对磁盘的io cache 虚拟化不同导致的guestos中软件安装差异(未解决) 设备直通(PCI Assignment)到底是咋整的 virtio到底是咋整的 内核启动参数 虚拟化实时性提升(零)之配置步骤 中断虚拟化(pic)到底是咋整的 中断虚拟化(apic)到底是咋整的 Raid卡配置丢失导致服务器无法启动 tainted kernels cpu stuck for 23s问题分析 虚拟化实时性提升(一)之hostOS切换为强实时系统 内存虚拟化到底是咋整的 qemu-kvm中vcpu虚拟化到底是咋整的 风河虚拟化技术点分析 使用qga的好处 qemu迁移代码分析 虚拟机串口配置及其导出到主机pts和console.log System-based I/O vs. Raw I/O 虚拟机使用Hugepage(大页) 硬件辅助分页(hardware assisted paging) 修改centos7默认启动项目 virtio的工作流程——kernel中virtio-pci初始化(2) virtio的工作流程——qemu中virtio-backend初始化(1) qmp ceilometer取不到memory.usage指标 Virtio-Balloon超详细分析 slabtop输出 虚拟机磁盘cache导致的host os kernel崩溃 虚拟机cpu和memory性能优化测评 PCI配置空间(PCI Configuration Space) centos下网卡设备直通(VT-dpci passthrough)遇到的问题及其解决思路 libguestfs详解 yum卸载软件包及其依赖 通过原始Centos ISO来定制自己的ISO centos下网卡设备直通(VT-d,pci passthrough) (占位符)window虚拟机中拔盘如何通知到libvirt和qemu后端的 cirrus漏洞分析CVE-2017-2615 XSA-208 qcow2随笔 控制寄存器概览 ceilometer对接postgresql 解压initrd和vmlinuz qemu guest agent验证 QEMU升级指南(待续) ubuntu中kdump的配置 qemu(2.3)接口梳理 热迁移导致的FC存储场景下的multipath卷残留问题分析 virsh命令(4)secret,snapshot,pool,volume部分 virsh命令(3)之interface,filter,network virsh命令(2)monitor,host,nodedev部分 virsh命令(1)之domain部分 QEMU内存管理之FlatView模型(QEMU2.0.0) ovirt基于sanock的高可用(主机粒度HA) Sanlock防脑裂场景功能测试用例 gnocchi配置及与ceilometer对接指南 make patch for libvirt in centos centos使用sanlock指导 高可用nfs资料 ubuntu14中使用sanlock指导 LVM操作指南 sanlock相关功能验证流程汇总 make patch for libvirt in ubuntu libvirt.so.0-version `LIBVIRT_PRIVATE_1.2.7' not found gdb debug libvirt 基于ubuntu社区源码包编译libvirt compile libvirt(centos) No PCI buses available nfs lead to Linux halt nfs install and config anti-virus for cloud platform nova fetch image from glance(something about _base) token auth process ovs入门指南 virt software anti-virus something about ceilometer disk sample context interview questions openstack vm injection openstack Restful and RPC murano 概览 创建虚拟机流程(compute节点)之网络创建 创建虚拟机流程之compute_api之虚拟机实例填充之配额检测 创建虚拟机流程之compute_api之基本参数生成 创建虚拟机流程之compute_api 创建虚拟机流程(主) 创建虚拟机之image 创建虚拟机流程之准备网桥 创建虚拟机流程之virt 创建虚拟机流程之compute节点 CI/CD研发流程之工程创建 CI/CD研发流程之代码合入 CI/CD研发流程之UT(单元测试) 向openstack社区合入代码记 openstack/ceilometer/gnocchi杂谈 影子页表原理 mem_add(exec.c) qemu编译安装调试 openstack/ceilometer/gnocchi之Grafana简介 openstack wiki etcd openstack计量ceilometer openstack计费cloudKitty enventlet backdoor USB 安装VMWARE ESX pycharm设置指南 无法执行modprobe -a kvm-intel解决办法 QEMU配置项 网络不通小记 libvirt之XML(虚拟机定义文件) openstack-horizon 证书认证 ceilometer与ceph对接 openstack定时任务剖析(TODO) 服务器重启后mongodb进程无法启动 ubuntu14下新增openstack服务到service的导引 ERROR 1045(28000)-数据库连不上 Python两个内置函数—locals和globals unknown exit, hardware reason 31

virtio的工作流程——kernel中virtio-pci初始化(2)

2017年03月28日

接上节,这次主要讲virtio-pci设备初始化,以及建立相应的通信通道。
一个virtio-pci设备有2个区域
一个是data区域,一个是config区域
使用 info mtree 可以看到这个结果。
data区域是pci-conf-data,config区域是virtio-pci

其中data区域主要记录了pci设备的 设备号,厂商等等信息。
而config区域就是用来前后协商,以及irq中断通知。

首先,检测到pci设备,会加载virtio-pci驱动,主要就是初始化相关寄存器,这是一个pci设备。 然后向virtio-bus注册设备,开始实体化我们的virtio设备。

virtio-pci的驱动加载是在寄存器初始化好以后,开始进行的。


static int virtio_pci_probe(struct pci_dev *pci_dev,
const struct pci_device_id *id)
{
struct virtio_pci_device *vp_dev;
int err;

/* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
return -ENODEV;

if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION) {
printk(KERN_ERR "virtio_pci: expected ABI version %d, got %d\n",
VIRTIO_PCI_ABI_VERSION, pci_dev->revision);
return -ENODEV;
}

/* allocate our structure and fill it out */
vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
if (vp_dev == NULL)
return -ENOMEM;

vp_dev->vdev.dev.parent = &pci_dev->dev;
vp_dev->vdev.dev.release = virtio_pci_release_dev;
vp_dev->vdev.config = &virtio_pci_config_ops;
vp_dev->pci_dev = pci_dev;
INIT_LIST_HEAD(&vp_dev->virtqueues);
spin_lock_init(&vp_dev->lock);

/* Disable MSI/MSIX to bring device to a known good state. */
//操作pci msi相关寄存器
pci_msi_off(pci_dev);

/* enable the device */
err = pci_enable_device(pci_dev);
if (err)
goto out;
//标记virtio-pci使用的区域
err = pci_request_regions(pci_dev, "virtio-pci");
if (err)
goto out_enable_device;

vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
if (vp_dev->ioaddr == NULL) {
err = -ENOMEM;
goto out_req_regions;
}

pci_set_drvdata(pci_dev, vp_dev);
//设置总线DMA模式
pci_set_master(pci_dev);

/* we use the subsystem vendor/device id as the virtio vendor/device
* id. this allows us to use the same PCI vendor/device id for all
* virtio devices and to identify the particular virtio driver by
* the subsystem ids */

vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
vp_dev->vdev.id.device = pci_dev->subsystem_device;

/* finally register the virtio device */
err = register_virtio_device(&vp_dev->vdev);
if (err)
goto out_set_drvdata;

return 0;

out_set_drvdata:
pci_set_drvdata(pci_dev, NULL);
pci_iounmap(pci_dev, vp_dev->ioaddr);
out_req_regions:
pci_release_regions(pci_dev);
out_enable_device:
pci_disable_device(pci_dev);
out:
kfree(vp_dev);
return err;
}

register_virtio_device主要是注册设备,并且对设备进行状态设置, VIRTIO_CONFIG_S_ACKNOWLEDGE 表示是发现了设备,这里注册设备到virtio_bus,这里会触发vritio_bus的probe函数。

  int register_virtio_device(struct virtio_device *dev)
{
int err;

dev->dev.bus = &virtio_bus;

/* Assign a unique device index and hence name. */
err = ida_simple_get(&virtio_index_ida, 0, 0, GFP_KERNEL);
if (err < 0)
goto out;

//注册了一个virtio设备。
dev->index = err;
dev_set_name(&dev->dev, "virtio%u", dev->index);

/* We always start by resetting the device, in case a previous
* driver messed it up. This also tests that code path a little. */

dev->config->reset(dev);

/* Acknowledge that we've seen the device. */
add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);

INIT_LIST_HEAD(&dev->vqs);

/* device_register() causes the bus infrastructure to look for a
* matching driver. */

err = device_register(&dev->dev);
out:
if (err)
add_status(dev, VIRTIO_CONFIG_S_FAILED);
return err;
}

会调用的virtio设备的virtio_dev_probe初始化设备。然后调用具体的vritio设备驱动来初始化。 可以看到virtio_bus主要控制了设备的连接状态,对于真正需要virito前后端建立连接的工作还是 调用了具体的virtio_blk的probe函数继续进行。 VIRTIO_CONFIG_S_DRIVER 发现了设备 VIRTIO_CONFIG_S_DRIVER_OK 驱动初始化完成。

  static int virtio_dev_probe(struct device *_d)
{
int err, i;
struct virtio_device *dev = dev_to_virtio(_d);
struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
u32 device_features;

/* We have a driver! */
add_status(dev, VIRTIO_CONFIG_S_DRIVER);

/* Figure out what features the device supports. */
device_features = dev->config->get_features(dev);

/* Features supported by both device and driver into dev->features. */
memset(dev->features, 0, sizeof(dev->features));
for (i = 0; i < drv->feature_table_size; i++) {
unsigned int f = drv->feature_table[i];
BUG_ON(f >= 32);
if (device_features & (1 << f))
set_bit(f, dev->features);
}

/* Transport features always preserved to pass to finalize_features. */
for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++)
if (device_features & (1 << i))
set_bit(i, dev->features);

dev->config->finalize_features(dev);

err = drv->probe(dev);
if (err)
add_status(dev, VIRTIO_CONFIG_S_FAILED);
else {
add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
if (drv->scan)
drv->scan(dev);
}

return err;
}

virtblk_probe 函数主要做了这些,读取配置,初始化ring环。

  static int virtblk_probe(struct virtio_device *vdev)
{
struct virtio_blk *vblk;
struct request_queue *q;
int err, index;
int pool_size;

u64 cap;
u32 v, blk_size, sg_elems, opt_io_size;
u16 min_io_size;
u8 physical_block_exp, alignment_offset;

err = ida_simple_get(&vd_index_ida, 0, minor_to_index(1 << MINORBITS),
GFP_KERNEL);
if (err < 0)
goto out;
index = err;

//这里读取后端配置。
/* We need to know how many segments before we allocate. */
err = virtio_config_val(vdev, VIRTIO_BLK_F_SEG_MAX,
offsetof(struct virtio_blk_config, seg_max),
&sg_elems);

/* We need at least one SG element, whatever they say. */
if (err || !sg_elems)
sg_elems = 1;

/* We need an extra sg elements at head and tail. */
sg_elems += 2;
vdev->priv = vblk = kmalloc(sizeof(*vblk) +
sizeof(vblk->sg[0]) * sg_elems, GFP_KERNEL);
if (!vblk) {
err = -ENOMEM;
goto out_free_index;
}

init_waitqueue_head(&vblk->queue_wait);
vblk->vdev = vdev;
vblk->sg_elems = sg_elems;
sg_init_table(vblk->sg, vblk->sg_elems);
mutex_init(&vblk->config_lock);

INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
vblk->config_enable = true;

//这里开启了msix中断,并建立了vring
err = init_vq(vblk);
if (err)
goto out_free_vblk;

pool_size = sizeof(struct virtblk_req);
if (use_bio)
pool_size += sizeof(struct scatterlist) * sg_elems;
vblk->pool = mempool_create_kmalloc_pool(1, pool_size);
if (!vblk->pool) {
err = -ENOMEM;
goto out_free_vq;
}

// 这里开始初始化bdi设备。
/* FIXME: How many partitions? How long is a piece of string? */
vblk->disk = alloc_disk(1 << PART_BITS);
if (!vblk->disk) {
err = -ENOMEM;
goto out_mempool;
}

q = vblk->disk->queue = blk_init_queue(virtblk_request, NULL);
if (!q) {
err = -ENOMEM;
goto out_put_disk;
}

if (use_bio)
blk_queue_make_request(q, virtblk_make_request);
q->queuedata = vblk;

virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN);

vblk->disk->major = major;
vblk->disk->first_minor = index_to_minor(index);
vblk->disk->private_data = vblk;
vblk->disk->fops = &virtblk_fops;
vblk->disk->driverfs_dev = &vdev->dev;
vblk->index = index;

/* configure queue flush support */
virtblk_update_cache_mode(vdev);

/* If disk is read-only in the host, the guest should obey */
if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
set_disk_ro(vblk->disk, 1);

/* Host must always specify the capacity. */
vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity),
&cap, sizeof(cap));

/* If capacity is too big, truncate with warning. */
if ((sector_t)cap != cap) {
dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
(unsigned long long)cap);
cap = (sector_t)-1;
}
set_capacity(vblk->disk, cap);

/* We can handle whatever the host told us to handle. */
blk_queue_max_segments(q, vblk->sg_elems-2);

/* No need to bounce any requests */
blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);

/* No real sector limit. */
blk_queue_max_hw_sectors(q, -1U);

/* Host can optionally specify maximum segment size and number of
* segments. */

err = virtio_config_val(vdev, VIRTIO_BLK_F_SIZE_MAX,
offsetof(struct virtio_blk_config, size_max),
&v);
if (!err)
blk_queue_max_segment_size(q, v);
else
blk_queue_max_segment_size(q, -1U);

/* Host can optionally specify the block size of the device */
err = virtio_config_val(vdev, VIRTIO_BLK_F_BLK_SIZE,
offsetof(struct virtio_blk_config, blk_size),
&blk_size);
if (!err)
blk_queue_logical_block_size(q, blk_size);
else
blk_size = queue_logical_block_size(q);

/* Use topology information if available */
err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY,
offsetof(struct virtio_blk_config, physical_block_exp),
&physical_block_exp);
if (!err && physical_block_exp)
blk_queue_physical_block_size(q,
blk_size * (1 << physical_block_exp));

err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY,
offsetof(struct virtio_blk_config, alignment_offset),
&alignment_offset);
if (!err && alignment_offset)
blk_queue_alignment_offset(q, blk_size * alignment_offset);

err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY,
offsetof(struct virtio_blk_config, min_io_size),
&min_io_size);
if (!err && min_io_size)
blk_queue_io_min(q, blk_size * min_io_size);

err = virtio_config_val(vdev, VIRTIO_BLK_F_TOPOLOGY,
offsetof(struct virtio_blk_config, opt_io_size),
&opt_io_size);
if (!err && opt_io_size)
blk_queue_io_opt(q, blk_size * opt_io_size);

add_disk(vblk->disk);
err = device_create_file(disk_to_dev(vblk->disk), &dev_attr_serial);
if (err)
goto out_del_disk;

if (virtio_has_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE))
err = device_create_file(disk_to_dev(vblk->disk),
&dev_attr_cache_type_rw);
else
err = device_create_file(disk_to_dev(vblk->disk),
&dev_attr_cache_type_ro);
if (err)
goto out_del_disk;
return 0;

out_del_disk:
del_gendisk(vblk->disk);
blk_cleanup_queue(vblk->disk->queue);
out_put_disk:
put_disk(vblk->disk);
out_mempool:
mempool_destroy(vblk->pool);
out_free_vq:
vdev->config->del_vqs(vdev);
out_free_vblk:
kfree(vblk);
out_free_index:
ida_simple_remove(&vd_index_ida, index);
out:
return err;
}

vq_init->virtio_find_single_vq,调用了virtio-pci驱动中的vp_find_vqs->vp_try_to_find_vqs。 这里,根据情况 初始化msix或者是irq中断。并注册了callback。

  static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs,
struct virtqueue *vqs[],
vq_callback_t *callbacks[],
const char *names[],
bool use_msix,
bool per_vq_vectors)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
u16 msix_vec;
int i, err, nvectors, allocated_vectors;

if (!use_msix) {
//使用的是irq中断
/* Old style: one normal interrupt for change and all vqs. */
err = vp_request_intx(vdev);
if (err)
goto error_request;
} else {
if (per_vq_vectors) {
/* Best option: one for change interrupt, one per vq. */
nvectors = 1;
for (i = 0; i < nvqs; ++i)
if (callbacks[i])
++nvectors;
} else {
/* Second best: one for change, shared for all vqs. */
nvectors = 2;
}
//使用msix中断,这里申请了2个msix 中断,一个绑定回调config_change用来更新config
另外一个绑定了vring_interupt 用来调用callback,来处理io

err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors);
if (err)
goto error_request;
}

vp_dev->per_vq_vectors = per_vq_vectors;
allocated_vectors = vp_dev->msix_used_vectors;
for (i = 0; i < nvqs; ++i) {
if (!names[i]) {
vqs[i] = NULL;
continue;
} else if (!callbacks[i] || !vp_dev->msix_enabled)
msix_vec = VIRTIO_MSI_NO_VECTOR;
else if (vp_dev->per_vq_vectors)
msix_vec = allocated_vectors++;
else
msix_vec = VP_MSIX_VQ_VECTOR;
//通知后端msix中断,以及初始化vring
vqs[i] = setup_vq(vdev, i, callbacks[i], names[i], msix_vec);
if (IS_ERR(vqs[i])) {
err = PTR_ERR(vqs[i]);
goto error_find;
}

if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
continue;

/* allocate per-vq irq if available and necessary */
snprintf(vp_dev->msix_names[msix_vec],
sizeof *vp_dev->msix_names,
"%s-%s",
dev_name(&vp_dev->vdev.dev), names[i]);
err = request_irq(vp_dev->msix_entries[msix_vec].vector,
vring_interrupt, 0,
vp_dev->msix_names[msix_vec],
vqs[i]);
if (err) {
vp_del_vq(vqs[i]);
goto error_find;
}
}
return 0;

error_find:
vp_del_vqs(vdev);

error_request:
return err;
}
false, false);
}

setup_vq用来初始化vring,并且通知后端msix中断。

  static struct virtqueue *setup_vq(struct virtio_device *vdev, unsigned index,
void (*callback)(struct virtqueue *vq),
const char *name,
u16 msix_vec)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
struct virtio_pci_vq_info *info;
struct virtqueue *vq;
unsigned long flags, size;
u16 num;
int err;

/* Select the queue we're interested in */
iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);

/* Check if queue is either not available or already active. */
//读取后端设置的queue的长度,这里一般是128
num = ioread16(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
return ERR_PTR(-ENOENT);

/* allocate and fill out our structure the represents an active
* queue */

info = kmalloc(sizeof(struct virtio_pci_vq_info), GFP_KERNEL);
if (!info)
return ERR_PTR(-ENOMEM);

info->num = num;
info->msix_vector = msix_vec;

//计算vring的长度。 是 num * vring_desc +num *vring_used_elem 以及其他信息。
size = PAGE_ALIGN(vring_size(num, VIRTIO_PCI_VRING_ALIGN));
//分配一段连续的页
info->queue = alloc_pages_exact(size, GFP_KERNEL|__GFP_ZERO);
if (info->queue == NULL) {
err = -ENOMEM;
goto out_info;
}

/* activate the queue */
//通知后端pfn号,这样后端可以通过pfn来直接访问guest的内存。
iowrite32(virt_to_phys(info->queue) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);

/* create the vring */
vq = vring_new_virtqueue(index, info->num, VIRTIO_PCI_VRING_ALIGN, vdev,
true, info->queue, vp_notify, callback, name);
if (!vq) {
err = -ENOMEM;
goto out_activate_queue;
}

vq->priv = info;
info->vq = vq;

if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
iowrite16(msix_vec, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
msix_vec = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
err = -EBUSY;
goto out_assign;
}
}

if (callback) {
spin_lock_irqsave(&vp_dev->lock, flags);
list_add(&info->node, &vp_dev->virtqueues);
spin_unlock_irqrestore(&vp_dev->lock, flags);
} else {
INIT_LIST_HEAD(&info->node);
}

return vq;

out_assign:
vring_del_virtqueue(vq);
out_activate_queue:
iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
free_pages_exact(info->queue, size);
out_info:
kfree(info);
return ERR_PTR(err);
}

本文转自肖丁博客