[置顶] linux内核学习之网络篇——网络物理层的设备初步
网卡是是网络中最基本的硬件之一。
在内核中，每个网络设备都一个一个net_device 结构体实例，在进行初始化完成之后，会将该结构注册到内核中。然能内核知道该结构的存在。
这会创建一个sysfs项，这，关联到该设备的对应目录中。该目录为
[root@localhost ~]# ls -l /sys/class/net 总计 0 drwxr-xr-x 3 root root 0 10-08 00:17 eth0 drwxr-xr-x 3 root root 0 10-08 00:17 lo drwxr-xr-x 4 root root 0 10-08 00:17 peth0 drwxr-xr-x 3 root root 0 10-08 00:17 sit0 drwxr-xr-x 3 root root 0 10-08 00:17 veth1 drwxr-xr-x 3 root root 0 10-08 00:17 veth2 drwxr-xr-x 3 root root 0 10-08 00:17 veth3 drwxr-xr-x 4 root root 0 10-08 00:17 vif0.0 drwxr-xr-x 3 root root 0 10-08 00:17 vif0.1 drwxr-xr-x 3 root root 0 10-08 00:17 vif0.2 drwxr-xr-x 3 root root 0 10-08 00:17 vif0.3 drwxr-xr-x 5 root root 0 10-08 00:17 xenbr0
可以看到 我虚拟机上的网络设备有以上的设备。eth0 是第一个网卡。其他的我也不知道干嘛的。
该设备不是全局的。因此也是在一个命名空间的。
所有网络设备都保存在一个单链表中。表头为dev_base.
按设备名散列。
按接口索引散列
下面我就不得不晓得linux中 最大的一个结构体数据结构。几百行代码
如下代码
/*
* The DEVICE structure.
* Actually, this whole structure is a big mistake. It mixes I/O
* data with strictly "high-level" data, and it has to know about
* almost every data structure used in the INET module.
*
* FIXME: cleanup struct net_device such that network protocol info
* moves out.
*/
struct net_device
{
/*
* This is the first field of the "visible" part of this structure
* (i.e. as seen by users in the "Space.c" file). It is the name
* the interface.
*/
char name[IFNAMSIZ];
/*
* I/O specific fields
* FIXME: Merge these and struct ifmap into one
*/
unsigned long mem_end; /* shared mem end */
unsigned long mem_start; /* shared mem start */
unsigned long base_addr; /* device I/O address */
unsigned int irq; /* device IRQ number */
/*
* Some hardware also needs these fields, but they are not
* part of the usual set specified in Space.c.
*/
unsigned char if_port; /* Selectable AUI, TP,..*/
unsigned char dma; /* DMA channel */
unsigned long state;
struct net_device *next;
/* The device initialization function. Called only once. */
int (*init)(struct net_device *dev);
/* ------- Fields preinitialized in Space.c finish here ------- */
struct net_device *next_sched;
/* Interface index. Unique device identifier */
int ifindex;
int iflink;
struct net_device_stats* (*get_stats)(struct net_device *dev);
struct iw_statistics* (*get_wireless_stats)(struct net_device *dev);
/* List of functions to handle Wireless Extensions (instead of ioctl).
* See <net/iw_handler.h> for details. Jean II */
struct iw_handler_def * wireless_handlers;
struct ethtool_ops *ethtool_ops;
/*
* This marks the end of the "visible" part of the structure. All
* fields hereafter are internal to the system, and may change at
* will (read: may be cleaned up at will).
*/
/* These may be needed for future network-power-down code. */
unsigned long trans_start; /* Time (in jiffies) of last Tx */
unsigned long last_rx; /* Time of last Rx */
unsigned short flags; /* interface flags (a la BSD) */
unsigned short gflags;
unsigned short priv_flags; /* Like 'flags' but invisible to userspace. */
unsigned short unused_alignment_fixer; /* Because we need priv_flags,
* and we want to be 32-bit aligned.
*/
unsigned mtu; /* interface MTU value */
unsigned short type; /* interface hardware type */
unsigned short hard_header_len; /* hardware hdr length */
void *priv; /* pointer to private data */
struct net_device *master; /* Pointer to master device of a group,
* which this device is member of.
*/
/* Interface address info. */
unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */
unsigned char dev_addr[MAX_ADDR_LEN]; /* hw address */
unsigned char addr_len; /* hardware address length */
struct dev_mc_list *mc_list; /* Multicast mac addresses */
int mc_count; /* Number of installed mcasts */
int promiscuity;
int allmulti;
int watchdog_timeo;
struct timer_list watchdog_timer;
/* Protocol specific pointers */
void *atalk_ptr; /* AppleTalk link */
void *ip_ptr; /* IPv4 specific data */
void *dn_ptr; /* DECnet specific data */
void *ip6_ptr; /* IPv6 specific data */
void *ec_ptr; /* Econet specific data */
void *ax25_ptr; /* AX.25 specific data */
struct list_head poll_list; /* Link to poll list */
int quota;
int weight;
struct Qdisc *qdisc;
struct Qdisc *qdisc_sleeping;
struct Qdisc *qdisc_list;
struct Qdisc *qdisc_ingress;
unsigned long tx_queue_len; /* Max frames per queue allowed */
/* hard_start_xmit synchronizer */
spinlock_t xmit_lock;
/* cpu id of processor entered to hard_start_xmit or -1,
if nobody entered there.
*/
int xmit_lock_owner;
/* device queue lock */
spinlock_t queue_lock;
/* Number of references to this device */
atomic_t refcnt;
/* delayed register/unregister */
struct list_head todo_list;
/* register/unregister state machine */
enum { NETREG_UNINITIALIZED=0,
NETREG_REGISTERING, /* called register_netdevice */
NETREG_REGISTERED, /* completed register todo */
NETREG_UNREGISTERING, /* called unregister_netdevice */
NETREG_UNREGISTERED, /* completed unregister todo */
NETREG_RELEASED, /* called free_netdev */
} reg_state;
/* Net device features */
int features;
#define NETIF_F_SG 1 /* Scatter/gather IO. */
#define NETIF_F_IP_CSUM 2 /* Can checksum only TCP/UDP over IPv4. */
#define NETIF_F_NO_CSUM 4 /* Does not require checksum. F.e. loopack. */
#define NETIF_F_HW_CSUM 8 /* Can checksum all the packets. */
#define NETIF_F_HIGHDMA 32 /* Can DMA to high memory. */
#define NETIF_F_FRAGLIST 64 /* Scatter/gather IO. */
#define NETIF_F_HW_VLAN_TX 128 /* Transmit VLAN hw acceleration */
#define NETIF_F_HW_VLAN_RX 256 /* Receive VLAN hw acceleration */
#define NETIF_F_HW_VLAN_FILTER 512 /* Receive filtering on VLAN */
#define NETIF_F_VLAN_CHALLENGED 1024 /* Device cannot handle VLAN packets */
#define NETIF_F_TSO 2048 /* Can offload TCP/IP segmentation */
/* Called after device is detached from network. */
void (*uninit)(struct net_device *dev);
/* Called after last user reference disappears. */
void (*destructor)(struct net_device *dev);
/* Pointers to interface service routines. */
int (*open)(struct net_device *dev);
int (*stop)(struct net_device *dev);
int (*hard_start_xmit) (struct sk_buff *skb,
struct net_device *dev);
#define HAVE_NETDEV_POLL
int (*poll) (struct net_device *dev, int *quota);
int (*hard_header) (struct sk_buff *skb,
struct net_device *dev,
unsigned short type,
void *daddr,
void *saddr,
unsigned len);
int (*rebuild_header)(struct sk_buff *skb);
#define HAVE_MULTICAST
void (*set_multicast_list)(struct net_device *dev);
#define HAVE_SET_MAC_ADDR
int (*set_mac_address)(struct net_device *dev,
void *addr);
#define HAVE_PRIVATE_IOCTL
int (*do_ioctl)(struct net_device *dev,
struct ifreq *ifr, int cmd);
#define HAVE_SET_CONFIG
int (*set_config)(struct net_device *dev,
struct ifmap *map);
#define HAVE_HEADER_CACHE
int (*hard_header_cache)(struct neighbour *neigh,
struct hh_cache *hh);
void (*header_cache_update)(struct hh_cache *hh,
struct net_device *dev,
unsigned char * haddr);
#define HAVE_CHANGE_MTU
int (*change_mtu)(struct net_device *dev, int new_mtu);
#define HAVE_TX_TIMEOUT
void (*tx_timeout) (struct net_device *dev);
void (*vlan_rx_register)(struct net_device *dev,
struct vlan_group *grp);
void (*vlan_rx_add_vid)(struct net_device *dev,
unsigned short vid);
void (*vlan_rx_kill_vid)(struct net_device *dev,
unsigned short vid);
int (*hard_header_parse)(struct sk_buff *skb,
unsigned char *haddr);
int (*neigh_setup)(struct net_device *dev, struct neigh_parms *);
int (*accept_fastpath)(struct net_device *, struct dst_entry*);
/* bridge stuff */
struct net_bridge_port *br_port;
#ifdef CONFIG_NET_FASTROUTE
#define NETDEV_FASTROUTE_HMASK 0xF
/* Semi-private data. Keep it at the end of device struct. */
rwlock_t fastpath_lock;
struct dst_entry *fastpath[NETDEV_FASTROUTE_HMASK+1];
#endif
#ifdef CONFIG_NET_DIVERT
/* this will get initialized at each interface type init routine */
struct divert_blk *divert;
#endif /* CONFIG_NET_DIVERT */
/* class/net/name entry */
struct class_device class_dev;
struct net_device_stats* (*last_stats)(struct net_device *);
};
每个网络设备都有个结构体，然后按照链表的形式。每个字段都有相应的注释，就不详细介绍。
注意一点就是这里定义了mtu，也就是一个传输帧的最大长度。因此，网络层必须遵守改最大值。进行拆分数据包。type定义了设备的常数。dev_addr,表示硬件地址。
下面在展示一个结构体
struct packet_type {
unsigned short type; /* This is really htons(ether_type). */
struct net_device *dev; /* NULL is wildcarded here */
int (*func) (struct sk_buff *, struct net_device *,
struct packet_type *);
void *af_packet_priv;
struct list_head list;
};
此结构将之前介绍的struct sk_buff 和struct net_device关联起来。进行处理。
有大量的函数
extern void dev_add_pack(struct packet_type *pt); extern void dev_remove_pack(struct packet_type *pt); extern void __dev_remove_pack(struct packet_type *pt);
具体的函数作用要细细的分析，在这里，就不做详细分析，需要看代码一点点分析。
只给大家展示一下将网络设备注册到内核的一个核心方法
/**
* register_netdevice - register a network device
* @dev: device to register
*
* Take a completed network device structure and add it to the kernel
* interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier
* chain. 0 is returned on success. A negative errno code is returned
* on a failure to set up the device, or if the name is a duplicate.
*
* Callers must hold the rtnl semaphore. See the comment at the
* end of Space.c for details about the locking. You may want
* register_netdev() instead of this.
*
* BUGS:
* The locking appears insufficient to guarantee two parallel registers
* will not get the same name.
*/
int register_netdevice(struct net_device *dev)
{
struct net_device *d, **dp;
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);
///队列锁 spin_lock_init(&dev->xmit_lock);
dev->xmit_lock_owner = -1;
#ifdef CONFIG_NET_FASTROUTE
dev->fastpath_lock = RW_LOCK_UNLOCKED;
#endif
ret = alloc_divert_blk(dev);
if (ret)
goto out;
dev->iflink = -1;
/* Init, if this function is available */
if (dev->init) {
ret = dev->init(dev);
if (ret) {
if (ret > 0)
ret = -EIO;
goto out_err;
}
}
dev->ifindex = dev_new_index();
if (dev->iflink == -1)
dev->iflink = dev->ifindex;
/* Check for existence, and append to tail of chain */
ret = -EEXIST;
for (dp = &dev_base; (d = *dp) != NULL; dp = &d->next) {
if (d == dev || !strcmp(d->name, dev->name))
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.
*/
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);
*dp = dev;
dev_hold(dev);
dev->reg_state = NETREG_REGISTERING;
write_unlock_bh(&dev_base_lock);
/* Notify protocols, that a new device appeared. */
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;
}
今天休写到这里。更多文章，欢迎访问 http://blog.csdn.net/wallwind