套接字是一种使用系统的文件描述符和系统进程进行通信的一种方法。
1、下面是描述套接字地址的结构体：
struct sockaddr {
sa_family_t sa_family; /* address family, AF_xxx */
如果使用了tcp/ip协议，AF_INET
char sa_data[14]; /* 14 bytes of protocol address */
};
2、socket的系统调用：
我们创建套接字都是用socket来创建。
socket的系统调用：
//每一个网络操作函数都有一个对应 的宏定义代码
#define SYS_SOCKET 1 /* sys_socket(2) */
#define SYS_BIND 2 /* sys_bind(2) */
#define SYS_CONNECT 3 /* sys_connect(2) */
#define SYS_LISTEN 4 /* sys_listen(2) */
#define SYS_ACCEPT 5 /* sys_accept(2) */
#define SYS_GETSOCKNAME 6 /* sys_getsockname(2) */
#define SYS_GETPEERNAME 7 /* sys_getpeername(2) */
#define SYS_SOCKETPAIR 8 /* sys_socketpair(2) */
#define SYS_SEND 9 /* sys_send(2) */
#define SYS_RECV 10 /* sys_recv(2) */
#define SYS_SENDTO 11 /* sys_sendto(2) */
#define SYS_RECVFROM 12 /* sys_recvfrom(2) */
#define SYS_SHUTDOWN 13 /* sys_shutdown(2) */
#define SYS_SETSOCKOPT 14 /* sys_setsockopt(2) */
#define SYS_GETSOCKOPT 15 /* sys_getsockopt(2) */
#define SYS_SENDMSG 16 /* sys_sendmsg(2) */
#define SYS_RECVMSG 17 /* sys_recvmsg(2) */
在linux中，所有网络函数都通过sys_socketcall来实现：
asmlinkage long sys_socketcall(int call, unsigned long __user *args)
{
unsigned long a[6];
unsigned long a0, a1;
int err;
//入参的范围判断
if (call < 1 || call > SYS_RECVMSG)
return -EINVAL;
/* copy_from_user should be SMP safe. */
if (copy_from_user(a, args, nargs[call]))//将用户态的数组拷贝给A
return -EFAULT;
err = audit_socketcall(nargs[call] / sizeof(unsigned long), a);//record audit data for sys_socketcall
if (err)
return err;
a0 = a[0];
a1 = a[1];
switch (call) {
case SYS_SOCKET:
err = sys_socket(a0, a1, a[2]);
break;
case SYS_BIND:
err = sys_bind(a0, (struct sockaddr __user *)a1, a[2]);
break;
case SYS_CONNECT:
err = sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
break;
case SYS_LISTEN:
err = sys_listen(a0, a1);
break;
case SYS_ACCEPT:
err =
sys_accept(a0, (struct sockaddr __user *)a1,
(int __user *)a[2]);
break;
case SYS_GETSOCKNAME:
err =
sys_getsockname(a0, (struct sockaddr __user *)a1,
(int __user *)a[2]);
break;
case SYS_GETPEERNAME:
err =
sys_getpeername(a0, (struct sockaddr __user *)a1,
(int __user *)a[2]);
break;
case SYS_SOCKETPAIR:
err = sys_socketpair(a0, a1, a[2], (int __user *)a[3]);
break;
case SYS_SEND:
err = sys_send(a0, (void __user *)a1, a[2], a[3]);
break;
case SYS_SENDTO:
err = sys_sendto(a0, (void __user *)a1, a[2], a[3],
(struct sockaddr __user *)a[4], a[5]);
break;
case SYS_RECV:
err = sys_recv(a0, (void __user *)a1, a[2], a[3]);
break;
case SYS_RECVFROM:
err = sys_recvfrom(a0, (void __user *)a1, a[2], a[3],
(struct sockaddr __user *)a[4],
(int __user *)a[5]);
break;
case SYS_SHUTDOWN:
err = sys_shutdown(a0, a1);
break;
case SYS_SETSOCKOPT:
err = sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]);
break;
case SYS_GETSOCKOPT:
err =
sys_getsockopt(a0, a1, a[2], (char __user *)a[3],
(int __user *)a[4]);
break;
case SYS_SENDMSG:
err = sys_sendmsg(a0, (struct msghdr __user *)a1, a[2]);
break;
case SYS_RECVMSG:
err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]);
break;
default:
err = -EINVAL;
break;
}
return err;
}
linux应用层的程序通过标准的BSDsocket接口实现网络通信。在BSD中，用socket描述一个套接字，主要使用在BSD套接口层。
/**
* struct socket - general BSD socket
* @state: socket state (%SS_CONNECTED, etc)
* @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc)
* @ops: protocol specific socket operations
* @fasync_list: Asynchronous wake up list
* @file: File back pointer for gc
* @sk: internal networking protocol agnostic socket representation
* @wait: wait queue for several uses
* @type: socket type (%SOCK_STREAM, etc)
*/
struct socket {
socket_state state;
unsigned long flags;
const struct proto_ops *ops;//socket函数操作表
struct fasync_struct *fasync_list;
struct file *file;
struct sock *sk;
wait_queue_head_t wait;
short type;//数据报的类型
};
struct sock *sk;指向套接口对应INET套接字结构体struct sock,
根据协议去创建相关的套接字
struct net_proto_family {
int family;
int (*create)(struct net *net, struct socket *sock, int protocol);//协议族的创建函数
struct module *owner;
};
如：IPV4
static struct net_proto_family inet_family_ops = {
.family = PF_INET,
.create = inet_create,
.owner = THIS_MODULE,
};
3.套接字的创建：
asmlinkage long sys_socket(int family, int type, int protocol)
{
int retval;
struct socket *sock;
//创建套接字
retval = sock_create(family, type, protocol, &sock);
if (retval < 0)
goto out;
retval = sock_map_fd(sock);//关联文件系统
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;
}
int sock_create(int family, int type, int protocol, struct socket **res)
{
return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0);
}
//socket的创建函数
static 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;//AF_INET
}
//追踪这个函数将会发现
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();//分配socket结构体空间
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;
#if defined(CONFIG_KMOD)
/* 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 (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);
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;
}