Linux内核--网络协议栈深入分析（三）--INET协议族socket和传输层sock

本文分析基于Linux Kernel 3.2.1Linux内核中协议族有INET协议族,UNIX协议族等，我们还是以INET协议族为例。更多请查看 Linux内核--网络内核实现分析下面是内核中的协议族声明：

/* Supported address families. */
#define AF_UNSPEC 0
#define AF_UNIX 1 /* Unix domain sockets */
#define AF_LOCAL 1 /* POSIX name for AF_UNIX */
#define AF_INET 2 /* Internet IP Protocol */
#define AF_AX25 3 /* Amateur Radio AX.25 */
#define AF_IPX 4 /* Novell IPX */
#define AF_APPLETALK 5 /* AppleTalk DDP */
#define AF_NETROM 6 /* Amateur Radio NET/ROM */
#define AF_BRIDGE 7 /* Multiprotocol bridge */
#define AF_ATMPVC 8 /* ATM PVCs */
#define AF_X25 9 /* Reserved for X.25 project */
#define AF_INET6 10 /* IP version 6 */
#define AF_ROSE 11 /* Amateur Radio X.25 PLP */
#define AF_DECnet 12 /* Reserved for DECnet project */
#define AF_NETBEUI 13 /* Reserved for 802.2LLC project*/
#define AF_SECURITY 14 /* Security callback pseudo AF */
#define AF_KEY 15 /* PF_KEY key management API */
#define AF_NETLINK 16
#define AF_ROUTE AF_NETLINK /* Alias to emulate 4.4BSD */
#define AF_PACKET 17 /* Packet family */
#define AF_ASH 18 /* Ash */
#define AF_ECONET 19 /* Acorn Econet */
#define AF_ATMSVC 20 /* ATM SVCs */
#define AF_RDS 21 /* RDS sockets */
#define AF_SNA 22 /* Linux SNA Project （nutters！） */
#define AF_IRDA 23 /* IRDA sockets */
#define AF_PPPOX 24 /* PPPoX sockets */
#define AF_WANPIPE 25 /* Wanpipe API Sockets */
#define AF_LLC 26 /* Linux LLC */
#define AF_CAN 29 /* Controller Area Network */
#define AF_TIPC 30 /* TIPC sockets */
#define AF_BLUETOOTH 31 /* Bluetooth sockets */
#define AF_IUCV 32 /* IUCV sockets */
#define AF_RXRPC 33 /* RxRPC sockets */
#define AF_ISDN 34 /* mISDN sockets */
#define AF_PHONET 35 /* Phonet sockets */
#define AF_IEEE802154 36 /* IEEE802154 sockets */
#define AF_CAIF 37 /* CAIF sockets */
#define AF_ALG 38 /* Algorithm sockets */
#define AF_NFC 39 /* NFC sockets */
#define AF_MAX 40 /* For now.. */

内核中的PF_***和AF_***其实可以混用，它的宏定义如下：

/* Protocol families, same as address families. */
#define PF_UNSPEC AF_UNSPEC
#define PF_UNIX AF_UNIX
#define PF_LOCAL AF_LOCAL
#define PF_INET AF_INET
#define PF_AX25 AF_AX25
#define PF_IPX AF_IPX
#define PF_APPLETALK AF_APPLETALK
#define PF_NETROM AF_NETROM
#define PF_BRIDGE AF_BRIDGE
#define PF_ATMPVC AF_ATMPVC
#define PF_X25 AF_X25
#define PF_INET6 AF_INET6
#define PF_ROSE AF_ROSE
#define PF_DECnet AF_DECnet
#define PF_NETBEUI AF_NETBEUI
#define PF_SECURITY AF_SECURITY
#define PF_KEY AF_KEY
#define PF_NETLINK AF_NETLINK
#define PF_ROUTE AF_ROUTE
#define PF_PACKET AF_PACKET
#define PF_ASH AF_ASH
#define PF_ECONET AF_ECONET
#define PF_ATMSVC AF_ATMSVC
#define PF_RDS AF_RDS
#define PF_SNA AF_SNA
#define PF_IRDA AF_IRDA
#define PF_PPPOX AF_PPPOX
#define PF_WANPIPE AF_WANPIPE
#define PF_LLC AF_LLC
#define PF_CAN AF_CAN
#define PF_TIPC AF_TIPC
#define PF_BLUETOOTH AF_BLUETOOTH
#define PF_IUCV AF_IUCV
#define PF_RXRPC AF_RXRPC
#define PF_ISDN AF_ISDN
#define PF_PHONET AF_PHONET
#define PF_IEEE802154 AF_IEEE802154
#define PF_CAIF AF_CAIF
#define PF_ALG AF_ALG
#define PF_NFC AF_NFC
#define PF_MAX AF_MAX

以后的分析就是以INET协议族为例来分析的。下面的结构体就是在系统初始化时用来管理协议族初始化的结构体：

struct net_proto_family {
int family;
int （*create）（struct net *net, struct socket *sock,
int protocol, int kern）;
struct module *owner;
};

第一个属性就是协议族的宏定义，如PF_INET；第二个属性就是协议族对应的初始化函数指针；INET协议族对应该结构的定义如下：

static const struct net_proto_family inet_family_ops = {
.family = PF_INET,
.create = inet_create,
.owner = THIS_MODULE,
};

下面结构体是协议族操作集结构体定义：

struct proto_ops {
int family;
struct module *owner;
int （*release）（struct socket *sock）;
int （*bind）（struct socket *sock,
struct sockaddr *myaddr,
int sockaddr_len）;
int （*connect）（struct socket *sock,
struct sockaddr *vaddr,
int sockaddr_len, int flags）;
int （*socketpair）（struct socket *sock1,
struct socket *sock2）;
int （*accept）（struct socket *sock,
struct socket *newsock, int flags）;
int （*getname）（struct socket *sock,
struct sockaddr *addr,
int *sockaddr_len, int peer）;
unsigned int （*poll）（struct file *file, struct socket *sock,
struct poll_table_struct *wait）;
int （*ioctl）（struct socket *sock, unsigned int cmd,
unsigned long arg）;
#ifdef CONFIG_COMPAT
int （*compat_ioctl）（struct socket *sock, unsigned int cmd,
unsigned long arg）;
#endif
int （*listen）（struct socket *sock, int len）;
int （*shutdown）（struct socket *sock, int flags）;
int （*setsockopt）（struct socket *sock, int level,
int optname, char __user *optval, unsigned int optlen）;
int （*getsockopt）（struct socket *sock, int level,
int optname, char __user *optval, int __user *optlen）;
#ifdef CONFIG_COMPAT
int （*compat_setsockopt）（struct socket *sock, int level,
int optname, char __user *optval, unsigned int optlen）;
int （*compat_getsockopt）（struct socket *sock, int level,
int optname, char __user *optval, int __user *optlen）;
#endif
int （*sendmsg）（struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len）;
int （*recvmsg）（struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len,
int flags）;
int （*mmap）（struct file *file, struct socket *sock,
struct vm_area_struct * vma）;
ssize_t （*sendpage）（struct socket *sock, struct page *page,
int offset, size_t size, int flags）;
ssize_t （*splice_read）（struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len, unsigned int flags）;
};

INET协议族中TCP和UDP协议对应的上述操作集的定义不同： TCP协议z在INET层操作集inet_stream_ops

const struct proto_ops inet_stream_ops = {
.family = PF_INET,
.owner = THIS_MODULE,
.release = inet_release,
.bind = inet_bind,
.connect = inet_stream_connect,
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet_getname,
.poll = tcp_poll,
.ioctl = inet_ioctl,
.listen = inet_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
.recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
.sendpage = inet_sendpage,
.splice_read = tcp_splice_read,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
.compat_ioctl = inet_compat_ioctl,
#endif
};

UDP协议在INET层操作集inet_dgram_ops

const struct proto_ops inet_dgram_ops = {
.family = PF_INET,
.owner = THIS_MODULE,
.release = inet_release,
.bind = inet_bind,
.connect = inet_dgram_connect,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = inet_getname,
.poll = udp_poll,
.ioctl = inet_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
.recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
.sendpage = inet_sendpage,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
.compat_ioctl = inet_compat_ioctl,
#endif
};

上面两个操作集是属于INET协议族层次，可以由协议族层套接字socket来管理，下面是协议族层析的套接字结构体（BSD Socket）定义：

/**
* struct socket - general BSD socket
* @state: socket state （%SS_CONNECTED, etc）
* @type: socket type （%SOCK_STREAM, etc）
* @flags: socket flags （%SOCK_ASYNC_NOSPACE, etc）
* @ops: protocol specific socket operations
* @file: File back pointer for gc
* @sk: internal networking protocol agnostic socket representation
* @wq: wait queue for several uses
*/
struct socket {
socket_state state;
kmemcheck_bitfield_begin（type）;
short type;
kmemcheck_bitfield_end（type）;
unsigned long flags;
struct socket_wq __rcu *wq;
struct file *file;
struct sock *sk;
const struct proto_ops *ops;
};