目录
@(linux socket编程实现原理)
一、网络协议参考模型简介
国际标准组织(ISO)制定了OSI模型。这个模型把网络通信的工作分为7层，从上至下为应用层、表示层、会话层、
传输层、网络层、数据链路层、物理层。
而TCP/IP协议将OSI的7层模型简化为4层，从上至下分别为应用层、传输层、网络互连层(网际层)、网络接口层。
TCP/IP协议实际是一个协议族，为网际数据通信提供不同层次的通路。
TCP协议处于传输层，实现了从一个应用程序到另一个应用程序的数据传递。应用程序通过目的IP地址和端口号
来区分接收数据的不同应用程序。二、SOCKET概述
socket接口是TCP/IP网络的API，它定义了许多函数或例程，程序员可以使用它来开发TCP/IP网络上的应用程序，
要学习Internet上的TCP/IP网络编程，必须理解socket接口。socket接口设计者最先将接口放在UNIX操作系统中。
如果了解UNIX系统的输入输出的话，就很容易理解socket了。网络的socket数据传输是一种特殊的I/O，socket
也是一种文件描述符。三、SOCKET基本数据结构
struct sockaddr {
/* address family, AF_xxx;一般为AF_INET,代表Internet(TCP/IP)地址族的IPv4协议 */
sa_family_t sa_family;
/* 14 bytes of protocol address；包含了远程计算机的IP地址、端口号和套接字的数目，这些数据是混杂在一起的*/
char sa_data[14];
};
/* Structure describing an Internet (IP) socket address. */
#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */
struct sockaddr_in {
sa_family_t sin_family; /* Address family */
__be16 sin_port; /* Port number */
struct in_addr sin_addr; /* Internet address */
/* Pad to size of `struct sockaddr'. */
unsigned char __pad[__SOCK_SIZE__ - sizeof(short int) -
sizeof(unsigned short int) - sizeof(struct in_addr)];
};1、TCP通信编程
前面简单介绍了TCP/IP协议，事实上该协议是十分复杂的(要是一个人从头开始研究网络协议的话，这辈子可能
啥也没干就过去了)。要编写一个优秀的网络程序也是十分困难的。服务端与客户端TCP通信的过程大致如下：
服务器端：
1. 首先服务器启动，通过调用socket()建立一个套接字
2. 调用bind()将该套接字和本地网络地址联系在一起
3. 调用listen()使套接字做好侦听的准备，并规定它的请求队列的长度
4. 调用accept()来接收连接
客户端：
1. 通过调用socket()建立一个套接字
2. 调用connect()和服务器建立连接。
3. 连接一旦建立，客户机和服务器之间就可以通过调用read和write函数来发送和接收数据了
4. 最后，待数据传送结束之后，双方调用close()关闭套接字，通信关闭。2、服务器端实例代码
#include <stdio.h> /* perror */
#include <stdlib.h> /* exit */
#include <sys/types.h> /* WNOHANG */
#include <sys/wait.h> /* waitpid */
#include <string.h> /* memset */
#include "socketwrapper.h" /* socket layer wrapper */
#define true 1
#define false 0
#define MYPORT 12334 /* 监听的端口 */
#define BACKLOG 10 /* listen的请求接收队列长度 */
#define MAXSIZE 100
int main()
{
int numbytes=0;
int sockfd, new_fd; /* 监听端口，数据端口 */
struct sockaddr_in sa; /* 自身的地址信息 */
struct sockaddr_in client_addr; /* 连接对方的地址信息 */
int sin_size;
char buf[MAXSIZE];
if ((sockfd = socket(PF_INET, SOCK_STREAM, 0)) == -1)
{
perror("socket");
exit(1);
}
sa.sin_family = AF_INET;
sa.sin_port = Htons(MYPORT); /* 网络字节顺序 */
sa.sin_addr.s_addr = INADDR_ANY; /* 自动填本机IP */
memset(&(sa.sin_zero),0, 8); /* 其余部分置0 */
if ( Bind(sockfd, (struct sockaddr *)&sa, sizeof(sa)) == -1)
{
perror("bind");
exit(1);
}
if (Listen(sockfd, BACKLOG) == -1)
{
perror("listen");
exit(1);
}
sin_size = sizeof(struct sockaddr_in);
new_fd = Accept(sockfd, (struct sockaddr *)&client_addr, &sin_size);
if (new_fd == -1)
{
perror("accept");
exit(1);
}
printf("Got connection from %s\n", Inet_ntoa(client_addr.sin_addr));
/* 主循环 */
while(1)
{
if ((numbytes=recv(new_fd,buf,MAXSIZE,0))>0)
{
buf[numbytes]=0;
printf("received:%s & length=%d\n",buf,numbytes);
if(send(new_fd,buf,strlen(buf), 0) == -1)
perror("send");
}
}
return true;
}3、客户端实例代码
#include <stdio.h> /* perror */
#include <stdlib.h> /* exit */
#include <sys/types.h> /* WNOHANG */
#include <sys/wait.h> /* waitpid */
#include <string.h> /* memset */
#include "socketwrapper.h" /* socket layer wrapper */
#define true 1
#define false 0
#define PORT 12334 /* Server的端口 */
#define MAXDATASIZE 100 /*一次可以读的最大字节数 */
int main(int argc, char *argv[])
{
int sockfd, numbytes;
char buf[MAXDATASIZE];
struct hostent *he; /* 主机信息 */
struct sockaddr_in server_addr; /* 对方地址信息 */
if (argc != 2)
{
fprintf(stderr,"usage: client hostname\n");
exit(1);
}
/* get the host info */
if ((he=Gethostbyname(argv[1])) == NULL)
{
/* 注意：获取DNS信息时，显示出错需要用herror而不是perror */
/* herror 在新的版本中会出现警告，已经建议不要使用了 */
perror("gethostbyname");
exit(1);
}
if ((sockfd=socket(PF_INET,SOCK_STREAM,0))==-1)
{
perror("socket");
exit(1);
}
server_addr.sin_family = AF_INET;
server_addr.sin_port = Htons(PORT); /* short, NBO */
server_addr.sin_addr = *((struct in_addr *)he->h_addr_list[0]);
memset(&(server_addr.sin_zero),0, 8); /* 其余部分设成0 */
if (Connect(sockfd, (struct sockaddr *)&server_addr, sizeof(struct sockaddr)) == -1)
{
perror("connect");
exit(1);
}
while(1)
{
printf("Enter Something:");
scanf("%s",buf);
numbytes=send(sockfd,buf,strlen(buf),0);
numbytes=recv(sockfd,buf,MAXDATASIZE,0);
buf[numbytes]='\0';
printf("received:%s\n",buf);
}
Close(sockfd);
return true;
}4、头文件socketwrapper.h
/********************************************************************/
/* Copyright (C) SSE-USTC, 2010 */
/* */
/* FILE NAME : socketwraper.h */
/* PRINCIPAL AUTHOR : Mengning */
/* SUBSYSTEM NAME : ChatSys */
/* MODULE NAME : ChatSys */
/* LANGUAGE : C */
/* TARGET ENVIRONMENT : ANY */
/* DATE OF FIRST RELEASE : 2010/10/18 */
/* DESCRIPTION : the interface to socket layer. */
/********************************************************************/
/*
* Revision log:
*
* Created by Mengning,2010/10/18
*
*/
#ifndef _SOCKET_WRAPER_H_
#define _SOCKET_WRAPER_H_
#include <sys/time.h>
#include <sys/types.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/socket.h>
#include <errno.h>
#include <arpa/inet.h>
#include <netdb.h> /* gethostbyname */
/* ChatSys Socket - Standard Socket Call Mapping Definition */
#define Socket(x,y,z) socket(x,y,z)
#define Bind(x,y,z) bind(x,y,z)
#define Connect(x,y,z) connect(x,y,z)
#define Listen(x,y) listen(x,y)
#define Read(x,y,z ) read(x,y,z)
#define Accept(x,y,z ) accept(x,y,(socklen_t *)z)
#define Recv(w,x,y,z) recv(w,x,y,z)
#define Recvfrom(a,b,c,d,e,f) recvfrom(a,b,c,d,e,f )
#define Recvmsg(a,b,c) recvmsg(a,b,c)
#define Write(a,b,c) write(a,b,c)
#define Send(a,b,c,d) send(a,b,c,d)
#define Sendto(a,b,c,d,e,f) sendto(a,b,c,d,e,f)
#define Sendmsg(a,b,c) sendmsg(a,b,c)
#define Close(a) close(a)
#define Htons(a) htons(a)
#define Inet_ntoa(a) inet_ntoa(a)
/* Name */
#define Gethostbyname(a) gethostbyname(a)
#endif /* _SOCKET_WRAPER_H_ */5、程序实现功能
首先运行server，然后运行client。连接建立之后，client通过键盘输入字符，发送到server。
server接收到数据之后，直接返回给client。验证通信是否成功。实现效果
client第一次发送hello，第二次发送nice
server接收到数据
6、探究socket系统调用
-
SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol) { int retval; struct socket *sock; int flags; /* Check the SOCK_* constants for consistency. */ BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); flags = type & ~SOCK_TYPE_MASK; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; type &= SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; retval = sock_create(family, type, protocol, &sock);/*重要函数*/ if (retval < 0) goto out; retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));/*重要函数*/ if (retval < 0) goto out_release; out: /* It may be already another descriptor 8) Not kernel problem. */ return retval; out_release: sock_release(sock); return retval; }可以看出 SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)代码中主要是使用了
sock_create()和sock_map_fd()这两个函数。那么接下来先分析sock_create() -
int sock_create(int family, int type, int protocol, struct socket **res) { return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0); }可以看出sock_create()实际调用__sock_create()，继续递归
-
int __sock_create(struct net *net, int family, int type, int protocol, struct socket **res, int kern) { int err; struct socket *sock; const struct net_proto_family *pf; /* * Check protocol is in range */ if (family < 0 || family >= NPROTO) return -EAFNOSUPPORT; if (type < 0 || type >= SOCK_MAX) return -EINVAL; /* Compatibility. This uglymoron is moved from INET layer to here to avoid deadlock in module load. */ if (family == PF_INET && type == SOCK_PACKET) { static int warned; if (!warned) { warned = 1; printk(KERN_INFO "%s uses obsolete (PF_INET,SOCK_PACKET)\n", current->comm); } family = PF_PACKET; } err = security_socket_create(family, type, protocol, kern); if (err) return err; /* * Allocate the socket and allow the family to set things up. if * the protocol is 0, the family is instructed to select an appropriate * default. */ sock = sock_alloc();/*重要*/ if (!sock) { if (net_ratelimit()) printk(KERN_WARNING "socket: no more sockets\n"); return -ENFILE; /* Not exactly a match, but its the closest posix thing */ } sock->type = type; #ifdef CONFIG_MODULES /* Attempt to load a protocol module if the find failed. * * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user * requested real, full-featured networking support upon configuration. * Otherwise module support will break! */ if (rcu_access_pointer(net_families[family]) == NULL) request_module("net-pf-%d", family); #endif rcu_read_lock(); pf = rcu_dereference(net_families[family]); err = -EAFNOSUPPORT; if (!pf) goto out_release; /* * We will call the ->create function, that possibly is in a loadable * module, so we have to bump that loadable module refcnt first. */ if (!try_module_get(pf->owner)) goto out_release; /* Now protected by module ref count */ rcu_read_unlock(); err = pf->create(net, sock, protocol, kern);/*重要*/ if (err < 0) goto out_module_put; /* * Now to bump the refcnt of the [loadable] module that owns this * socket at sock_release time we decrement its refcnt. */ if (!try_module_get(sock->ops->owner)) goto out_module_busy; /* * Now that we're done with the ->create function, the [loadable] * module can have its refcnt decremented */ module_put(pf->owner); err = security_socket_post_create(sock, family, type, protocol, kern); if (err) goto out_sock_release; *res = sock; return 0; out_module_busy: err = -EAFNOSUPPORT; out_module_put: sock->ops = NULL; module_put(pf->owner); out_sock_release: sock_release(sock); return err; out_release: rcu_read_unlock(); goto out_sock_release; }其中重要的函数有sock_alloc()和pf->create(net, sock, protocol, kern)函数，递归查看sock_alloc()
static struct socket *sock_alloc(void) { struct inode *inode; struct socket *sock; inode = new_inode(sock_mnt->mnt_sb); if (!inode) return NULL; sock = SOCKET_I(inode); kmemcheck_annotate_bitfield(sock, type); inode->i_ino = get_next_ino(); inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); percpu_add(sockets_in_use, 1); return sock; }-
struct inode *new_inode(struct super_block *sb) { struct inode *inode; spin_lock_prefetch(&inode_sb_list_lock); inode = alloc_inode(sb); if (inode) { spin_lock(&inode->i_lock); inode->i_state = 0; spin_unlock(&inode->i_lock); inode_sb_list_add(inode); } return inode; }到这里已经快结束了。大致的系统调用栈也已经清晰，最终调用 inode = alloc_inode(sb);