博所搬至http://xiaogr.com
全部博文(79)
分类: LINUX
2007-10-22 17:24:34
------------------------------------------
本文系本站原创,欢迎转载!
转载请注明出处:http://ericxiao.cublog.cn/
-------------------------------------------
注意到这么庞大的结构中,有个成员叫: struct net_device *next,呵呵,很熟悉吧,就是用它来建立网络设备的链表。
每一个网络设备启动的时候,都会调用register_netdev() (drivers/net/net_init.c)
跟踪这个函数:
int register_netdev(struct net_device *dev)
{
int err;
rtnl_lock();
/*
* If the name is a format string the caller wants us to
* do a name allocation
*/
if (strchr(dev->name, '%'))
{
err = dev_alloc_name(dev, dev->name);
if (err < 0)
goto out;
}
/*
* Back compatibility hook. Kill this one in 2.5
*/
if (dev->name[0]==0 || dev->name[0]==' ')
{
err = dev_alloc_name(dev, "eth%d");
if (err < 0)
goto out;
}
err = register_netdevice(dev);
out:
rtnl_unlock();
return err;
}
跟踪至: register_netdevice(struct net_device *dev) (net/core/dev.c)
int register_netdevice(struct net_device *dev)
{
struct hlist_head *head;
struct hlist_node *p;
int ret;
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
/* When net_device's are persistent, this will be fatal. */
BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
spin_lock_init(&dev->queue_lock);
spin_lock_init(&dev->xmit_lock);
dev->xmit_lock_owner = -1;
#ifdef CONFIG_NET_CLS_ACT
spin_lock_init(&dev->ingress_lock);
#endif
ret = alloc_divert_blk(dev);
if (ret)
goto out;
dev->iflink = -1;
/* Init, if this function is available */
//如果dev -> init 被赋值,那么调用此函数
if (dev->init) {
ret = dev->init(dev);
if (ret) {
if (ret > 0)
ret = -EIO;
goto out_err;
}
}
//判断name 是否合法
if (!dev_valid_name(dev->name)) {
ret = -EINVAL;
goto out_err;
}
//为此设备分配一个index
dev->ifindex = dev_new_index();
if (dev->iflink == -1)
dev->iflink = dev->ifindex;
/* Check for existence of name */
//所有网络设备,以名字作为哈希主键存在dev_name_head中,该变量是一个哈希数组
//找到该名字对应的链表
//如果内核中已经含有此名字的网络设备,出错退出
head = dev_name_hash(dev->name);
hlist_for_each(p, head) {
struct net_device *d
= hlist_entry(p, struct net_device, name_hlist);
if (!strncmp(d->name, dev->name, IFNAMSIZ)) {
ret = -EEXIST;
goto out_err;
}
}
/* Fix illegal SG+CSUM combinations. */
if ((dev->features & NETIF_F_SG) &&
!(dev->features & (NETIF_F_IP_CSUM |
NETIF_F_NO_CSUM |
NETIF_F_HW_CSUM))) {
printk("%s: Dropping NETIF_F_SG since no checksum feature.\n",
dev->name);
dev->features &= ~NETIF_F_SG;
}
/*
* nil rebuild_header routine,
* that should be never called and used as just bug trap.
*/
//为rebuild_header赋默认值
if (!dev->rebuild_header)
dev->rebuild_header = default_rebuild_header;
/*
* Default initial state at registry is that the
* device is present.
*/
set_bit(__LINK_STATE_PRESENT, &dev->state);
dev->next = NULL;
dev_init_scheduler(dev);
write_lock_bh(&dev_base_lock);
//初始化的时候,有struct net_device **dev_tail = &dev_base;
//这段代码的意思实际就是:把dev加入dev_base为首结点队链表的尾部
*dev_tail = dev;
dev_tail = &dev->next;
//把此结点加入到以名字为哈希主键的链表数组dev_name_head中
hlist_add_head(&dev->name_hlist, head);
//把此结点加到以序号为主键的链表数组dev_index_head中
hlist_add_head(&dev->index_hlist, dev_index_hash(dev->ifindex));
dev_hold(dev);
dev->reg_state = NETREG_REGISTERING;
write_unlock_bh(&dev_base_lock);
/* Notify protocols, that a new device appeared. */
//在通知链表上发送事件
notifier_call_chain(&netdev_chain, NETDEV_REGISTER, dev);
/* Finish registration after unlock */
net_set_todo(dev);
ret = 0;
out:
return ret;
out_err:
free_divert_blk(dev);
goto out;
}
从此可以看出。新加入一个设备时,会插入三个位置:以名字为哈希值组织的dev_name_head ,以序号为主链的哈希数组dev_index_head.还有dev_base.它为快速查找网络设备提供了基础。事实上。在内核中,经常要根据index找到dev. 或者根据name找到dev.我们遇到的时候再分析
到现在,我们可以在内核中顺藤摸瓜的找到每一个网络设备了。
还有很重要的。设备更改了配置,要怎么通知跟他相关的子系统呢?例如,网卡更新了IP,如何使路由得到更新?
接着往下看:
注意到上面注册代码中所调用的一个函数notifier_call_chain(&netdev_chain, NETDEV_REGISTER, dev).
该函数的作用是,在通知链表上netdev_chain上发送NETDEV_REGISTER消息,所有在与该通知链表关联的子系统都可以收到此消息。以此,可以快速的更新整个系统的配置消息。
以路由子系统为例,来讲述该过程:
在IPV4子系统加载的时候,加调用ip_init(),接着调用fib_init(),然后再调用ip_fib_init()
跟踪一下此函数:
void __init ip_fib_init(void)
{
#ifndef CONFIG_IP_MULTIPLE_TABLES
ip_fib_local_table = fib_hash_init(RT_TABLE_LOCAL);
ip_fib_main_table = fib_hash_init(RT_TABLE_MAIN);
#else
fib_rules_init();
#endif
register_netdevice_notifier(&fib_netdev_notifier);
register_inetaddr_notifier(&fib_inetaddr_notifier);
}
register_netdevice_notifier是做什么的呢?往下跟踪:
int register_netdevice_notifier(struct notifier_block *nb)
{
struct net_device *dev;
int err;
rtnl_lock();
//注册通知链
err = notifier_chain_register(&netdev_chain, nb);
if (!err) {
for (dev = dev_base; dev; dev = dev->next) {
nb->notifier_call(nb, NETDEV_REGISTER, dev);
if (dev->flags & IFF_UP)
nb->notifier_call(nb, NETDEV_UP, dev);
}
}
rtnl_unlock();
return err;
}
呵呵,它在netdev_chain上注册了通知链,当此链上有事件发生时,会调用fib_netdev_notifiers中的相关信息处理,看一下fib_netdev_notifier的信息:
struct notifier_block fib_netdev_notifier = {
.notifier_call =fib_netdev_event,
};
OK,现在越来越具体了,如果netdev_chain有事件,会调用fib_netdev_event处理。继续跟踪:
static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct net_device *dev = ptr;
struct in_device *in_dev = __in_dev_get(dev);
//设备注销
if (event == NETDEV_UNREGISTER) {
fib_disable_ip(dev, 2);
return NOTIFY_DONE;
}
if (!in_dev)
return NOTIFY_DONE;
switch (event) {
//设备UP
case NETDEV_UP:
for_ifa(in_dev) {
fib_add_ifaddr(ifa);
} endfor_ifa(in_dev);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
fib_sync_up(dev);
#endif
rt_cache_flush(-1);
break;
//设备DOWN
case NETDEV_DOWN:
fib_disable_ip(dev, 0);
break;
//设备参数改变
case NETDEV_CHANGEMTU:
case NETDEV_CHANGE:
rt_cache_flush(0);
break;
}
return NOTIFY_DONE;
}
路由部份的代码将在后续的笔记中给出。至此,整个网络设备的架构非常的清晰了!