af_inet.c

Linux内核源代码 为压缩文件 是<<Linux内核>>一书中的源代码

	struct sock *sk=sock->sk;

	if (uaddr->sa_family == AF_UNSPEC)
		return sk->prot->disconnect(sk, flags);

	if (sk->num==0 && inet_autobind(sk) != 0)
		return -EAGAIN;
	return sk->prot->connect(sk, (struct sockaddr *)uaddr, addr_len);
}

static long inet_wait_for_connect(struct sock *sk, long timeo)
{
	DECLARE_WAITQUEUE(wait, current);

	__set_current_state(TASK_INTERRUPTIBLE);
	add_wait_queue(sk->sleep, &wait);

	/* Basic assumption: if someone sets sk->err, he _must_
	 * change state of the socket from TCP_SYN_*.
	 * Connect() does not allow to get error notifications
	 * without closing the socket.
	 */
	while ((1<<sk->state)&(TCPF_SYN_SENT|TCPF_SYN_RECV)) {
		release_sock(sk);
		timeo = schedule_timeout(timeo);
		lock_sock(sk);
		if (signal_pending(current) || !timeo)
			break;
		set_current_state(TASK_INTERRUPTIBLE);
	}
	__set_current_state(TASK_RUNNING);
	remove_wait_queue(sk->sleep, &wait);
	return timeo;
}

/*
 *	Connect to a remote host. There is regrettably still a little
 *	TCP 'magic' in here.
 */
 
int inet_stream_connect(struct socket *sock, struct sockaddr * uaddr,
			int addr_len, int flags)
{
	struct sock *sk=sock->sk;
	int err;
	long timeo;

	lock_sock(sk);

	if (uaddr->sa_family == AF_UNSPEC) {
		err = sk->prot->disconnect(sk, flags);
		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
		goto out;
	}

	switch (sock->state) {
	default:
		err = -EINVAL;
		goto out;
	case SS_CONNECTED:
		err = -EISCONN;
		goto out;
	case SS_CONNECTING:
		err = -EALREADY;
		/* Fall out of switch with err, set for this state */
		break;
	case SS_UNCONNECTED:
		err = -EISCONN;
		if (sk->state != TCP_CLOSE) 
			goto out;

		err = -EAGAIN;
		if (sk->num == 0) {
			if (sk->prot->get_port(sk, 0) != 0)
				goto out;
			sk->sport = htons(sk->num);
		}

		err = sk->prot->connect(sk, uaddr, addr_len);
		if (err < 0)
			goto out;

  		sock->state = SS_CONNECTING;

		/* Just entered SS_CONNECTING state; the only
		 * difference is that return value in non-blocking
		 * case is EINPROGRESS, rather than EALREADY.
		 */
		err = -EINPROGRESS;
		break;
	}

	timeo = sock_sndtimeo(sk, flags&O_NONBLOCK);

	if ((1<<sk->state)&(TCPF_SYN_SENT|TCPF_SYN_RECV)) {
		/* Error code is set above */
		if (!timeo || !inet_wait_for_connect(sk, timeo))
			goto out;

		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			goto out;
	}

	/* Connection was closed by RST, timeout, ICMP error
	 * or another process disconnected us.
	 */
	if (sk->state == TCP_CLOSE)
		goto sock_error;

	/* sk->err may be not zero now, if RECVERR was ordered by user
	 * and error was received after socket entered established state.
	 * Hence, it is handled normally after connect() return successfully.
	 */

	sock->state = SS_CONNECTED;
	err = 0;
out:
	release_sock(sk);
	return err;

sock_error:
	err = sock_error(sk) ? : -ECONNABORTED;
	sock->state = SS_UNCONNECTED;
	if (sk->prot->disconnect(sk, flags))
		sock->state = SS_DISCONNECTING;
	goto out;
}

/*
 *	Accept a pending connection. The TCP layer now gives BSD semantics.
 */

int inet_accept(struct socket *sock, struct socket *newsock, int flags)
{
	struct sock *sk1 = sock->sk;
	struct sock *sk2;
	int err = -EINVAL;

	if((sk2 = sk1->prot->accept(sk1,flags,&err)) == NULL)
		goto do_err;

	lock_sock(sk2);

	BUG_TRAP((1<<sk2->state)&(TCPF_ESTABLISHED|TCPF_CLOSE_WAIT|TCPF_CLOSE));

	sock_graft(sk2, newsock);

	newsock->state = SS_CONNECTED;
	release_sock(sk2);
	return 0;

do_err:
	return err;
}


/*
 *	This does both peername and sockname.
 */
 
static int inet_getname(struct socket *sock, struct sockaddr *uaddr,
		 int *uaddr_len, int peer)
{
	struct sock *sk		= sock->sk;
	struct sockaddr_in *sin	= (struct sockaddr_in *)uaddr;
  
	sin->sin_family = AF_INET;
	if (peer) {
		if (!sk->dport)
			return -ENOTCONN;
		if (((1<<sk->state)&(TCPF_CLOSE|TCPF_SYN_SENT)) && peer == 1)
			return -ENOTCONN;
		sin->sin_port = sk->dport;
		sin->sin_addr.s_addr = sk->daddr;
	} else {
		__u32 addr = sk->rcv_saddr;
		if (!addr)
			addr = sk->saddr;
		sin->sin_port = sk->sport;
		sin->sin_addr.s_addr = addr;
	}
	*uaddr_len = sizeof(*sin);
	return(0);
}



int inet_recvmsg(struct socket *sock, struct msghdr *msg, int size,
		 int flags, struct scm_cookie *scm)
{
	struct sock *sk = sock->sk;
	int addr_len = 0;
	int err;

	err = sk->prot->recvmsg(sk, msg, size, flags&MSG_DONTWAIT,
				flags&~MSG_DONTWAIT, &addr_len);
	if (err >= 0)
		msg->msg_namelen = addr_len;
	return err;
}


int inet_sendmsg(struct socket *sock, struct msghdr *msg, int size,
		 struct scm_cookie *scm)
{
	struct sock *sk = sock->sk;

	/* We may need to bind the socket. */
	if (sk->num==0 && inet_autobind(sk) != 0)
		return -EAGAIN;

	return sk->prot->sendmsg(sk, msg, size);
}

int inet_shutdown(struct socket *sock, int how)
{
	struct sock *sk = sock->sk;
	int err = 0;

	/* This should really check to make sure
	 * the socket is a TCP socket. (WHY AC...)
	 */
	how++; /* maps 0->1 has the advantage of making bit 1 rcvs and
		       1->2 bit 2 snds.
		       2->3 */
	if ((how & ~SHUTDOWN_MASK) || how==0)	/* MAXINT->0 */
		return -EINVAL;

	lock_sock(sk);
	if (sock->state == SS_CONNECTING) {
		if ((1<<sk->state)&(TCPF_SYN_SENT|TCPF_SYN_RECV|TCPF_CLOSE))
			sock->state = SS_DISCONNECTING;
		else
			sock->state = SS_CONNECTED;
	}

	switch (sk->state) {
	case TCP_CLOSE:
		err = -ENOTCONN;
		/* Hack to wake up other listeners, who can poll for
		   POLLHUP, even on eg. unconnected UDP sockets -- RR */
	default:
		sk->shutdown |= how;
		if (sk->prot->shutdown)
			sk->prot->shutdown(sk, how);
		break;

	/* Remaining two branches are temporary solution for missing
	 * close() in multithreaded environment. It is _not_ a good idea,
	 * but we have no choice until close() is repaired at VFS level.
	 */
	case TCP_LISTEN:
		if (!(how & RCV_SHUTDOWN))
			break;
		/* Fall through */
	case TCP_SYN_SENT:
		err = sk->prot->disconnect(sk, O_NONBLOCK);
		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
		break;
	}

	/* Wake up anyone sleeping in poll. */
	sk->state_change(sk);
	release_sock(sk);
	return err;
}

/*
 *	ioctl() calls you can issue on an INET socket. Most of these are
 *	device configuration and stuff and very rarely used. Some ioctls
 *	pass on to the socket itself.
 *
 *	NOTE: I like the idea of a module for the config stuff. ie ifconfig
 *	loads the devconfigure module does its configuring and unloads it.
 *	There's a good 20K of config code hanging around the kernel.
 */

static int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	struct sock *sk = sock->sk;
	int err;
	int pid;

	switch(cmd) 
	{
		case FIOSETOWN:
		case SIOCSPGRP:
			err = get_user(pid, (int *) arg);
			if (err)
				return err; 
			if (current->pid != pid && current->pgrp != -pid && 
			    !capable(CAP_NET_ADMIN))
				return -EPERM;
			sk->proc = pid;
			return(0);
		case FIOGETOWN:
		case SIOCGPGRP:
			return put_user(sk->proc, (int *)arg);
		case SIOCGSTAMP:
			if(sk->stamp.tv_sec==0)
				return -ENOENT;
			err = copy_to_user((void *)arg,&sk->stamp,sizeof(struct timeval));
			if (err)
				err = -EFAULT;
			return err;
		case SIOCADDRT:
		case SIOCDELRT:
		case SIOCRTMSG:
			return(ip_rt_ioctl(cmd,(void *) arg));
		case SIOCDARP:
		case SIOCGARP:
		case SIOCSARP:
			return(arp_ioctl(cmd,(void *) arg));
		case SIOCGIFADDR:
		case SIOCSIFADDR:
		case SIOCGIFBRDADDR:
		case SIOCSIFBRDADDR:
		case SIOCGIFNETMASK:
		case SIOCSIFNETMASK:
		case SIOCGIFDSTADDR:
		case SIOCSIFDSTADDR:
		case SIOCSIFPFLAGS:	
		case SIOCGIFPFLAGS:	
		case SIOCSIFFLAGS:
			return(devinet_ioctl(cmd,(void *) arg));
		case SIOCGIFBR:
		case SIOCSIFBR:
#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)
#ifdef CONFIG_KMOD
			if (br_ioctl_hook == NULL)
				request_module("bridge");
#endif
			if (br_ioctl_hook != NULL)
				return br_ioctl_hook(arg);
#endif
		case SIOCGIFDIVERT:
		case SIOCSIFDIVERT:
#ifdef CONFIG_NET_DIVERT
			return(divert_ioctl(cmd, (struct divert_cf *) arg));
#else
			return -ENOPKG;
#endif	/* CONFIG_NET_DIVERT */
			return -ENOPKG;
			
		case SIOCADDDLCI:
		case SIOCDELDLCI:
#ifdef CONFIG_DLCI
			lock_kernel();
			err = dlci_ioctl(cmd, (void *) arg);
			unlock_kernel();
			return err;
#endif

#ifdef CONFIG_DLCI_MODULE

#ifdef CONFIG_KMOD
			if (dlci_ioctl_hook == NULL)
				request_module("dlci");
#endif

			if (dlci_ioctl_hook) {
				lock_kernel();
				err = (*dlci_ioctl_hook)(cmd, (void *) arg);
				unlock_kernel();
				return err;
			}
#endif
			return -ENOPKG;

		default:
			if ((cmd >= SIOCDEVPRIVATE) &&
			    (cmd <= (SIOCDEVPRIVATE + 15)))
				return(dev_ioctl(cmd,(void *) arg));

#ifdef WIRELESS_EXT
			if((cmd >= SIOCIWFIRST) && (cmd <= SIOCIWLAST))
				return(dev_ioctl(cmd,(void *) arg));
#endif	/* WIRELESS_EXT */

			if (sk->prot->ioctl==NULL || (err=sk->prot->ioctl(sk, cmd, arg))==-ENOIOCTLCMD)
				return(dev_ioctl(cmd,(void *) arg));		
			return err;
	}
	/*NOTREACHED*/
	return(0);
}

struct proto_ops inet_stream_ops = {
	family:		PF_INET,

	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:	inet_setsockopt,
	getsockopt:	inet_getsockopt,
	sendmsg:	inet_sendmsg,
	recvmsg:	inet_recvmsg,
	mmap:		sock_no_mmap
};

struct proto_ops inet_dgram_ops = {
	family:		PF_INET,

	release:	inet_release,
	bind:		inet_bind,
	connect:	inet_dgram_connect,
	socketpair:	sock_no_socketpair,
	accept:		sock_no_accept,
	getname:	inet_getname, 
	poll:		datagram_poll,
	ioctl:		inet_ioctl,
	listen:		sock_no_listen,
	shutdown:	inet_shutdown,
	setsockopt:	inet_setsockopt,
	getsockopt:	inet_getsockopt,
	sendmsg:	inet_sendmsg,
	recvmsg:	inet_recvmsg,
	mmap:		sock_no_mmap,
};

struct net_proto_family inet_family_ops = {
	PF_INET,
	inet_create
};


extern void tcp_init(void);
extern void tcp_v4_init(struct net_proto_family *);


/*
 *	Called by socket.c on kernel startup.  
 */
 
static int __init inet_init(void)
{
	struct sk_buff *dummy_skb;
	struct inet_protocol *p;

	printk(KERN_INFO "NET4: Linux TCP/IP 1.0 for NET4.0\n");

	if (sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb))
	{
		printk(KERN_CRIT "inet_proto_init: panic\n");
		return -EINVAL;
	}

	/*
	 *	Tell SOCKET that we are alive... 
	 */
   
  	(void) sock_register(&inet_family_ops);

	/*
	 *	Add all the protocols. 
	 */

	printk(KERN_INFO "IP Protocols: ");
	for(p = inet_protocol_base; p != NULL;) 
	{
		struct inet_protocol *tmp = (struct inet_protocol *) p->next;
		inet_add_protocol(p);
		printk("%s%s",p->name,tmp?", ":"\n");
		p = tmp;
	}

	/*
	 *	Set the ARP module up
	 */

	arp_init();

  	/*
  	 *	Set the IP module up
  	 */

	ip_init();

	tcp_v4_init(&inet_family_ops);

	/* Setup TCP slab cache for open requests. */
	tcp_init();


	/*
	 *	Set the ICMP layer up
	 */

	icmp_init(&inet_family_ops);

	/* I wish inet_add_protocol had no constructor hook...
	   I had to move IPIP from net/ipv4/protocol.c :-( --ANK
	 */
#ifdef CONFIG_NET_IPIP
	ipip_init();
#endif
#ifdef CONFIG_NET_IPGRE
	ipgre_init();
#endif

	/*
	 *	Initialise the multicast router
	 */
#if defined(CONFIG_IP_MROUTE)
	ip_mr_init();
#endif

	/*
	 *	Create all the /proc entries.
	 */
#ifdef CONFIG_PROC_FS
	proc_net_create ("raw", 0, raw_get_info);
	proc_net_create ("netstat", 0, netstat_get_info);
	proc_net_create ("snmp", 0, snmp_get_info);
	proc_net_create ("sockstat", 0, afinet_get_info);
	proc_net_create ("tcp", 0, tcp_get_info);
	proc_net_create ("udp", 0, udp_get_info);
#endif		/* CONFIG_PROC_FS */
	return 0;
}
module_init(inet_init);