af_inet.c

linux 内核源代码

{
	struct sock *sk = sock->sk;

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

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

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

	prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);

	/* Basic assumption: if someone sets sk->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->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		release_sock(sk);
		timeo = schedule_timeout(timeo);
		lock_sock(sk);
		if (signal_pending(current) || !timeo)
			break;
		prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
	}
	finish_wait(sk->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->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->sk_state != TCP_CLOSE)
			goto out;

		err = sk->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->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->sk_state == TCP_CLOSE)
		goto sock_error;

	/* sk->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->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;
	int err = -EINVAL;
	struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err);

	if (!sk2)
		goto do_err;

	lock_sock(sk2);

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

	sock_graft(sk2, newsock);

	newsock->state = SS_CONNECTED;
	err = 0;
	release_sock(sk2);
do_err:
	return err;
}


/*
 *	This does both peername and sockname.
 */
int inet_getname(struct socket *sock, struct sockaddr *uaddr,
			int *uaddr_len, int peer)
{
	struct sock *sk		= sock->sk;
	struct inet_sock *inet	= inet_sk(sk);
	struct sockaddr_in *sin	= (struct sockaddr_in *)uaddr;

	sin->sin_family = AF_INET;
	if (peer) {
		if (!inet->dport ||
		    (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) &&
		     peer == 1))
			return -ENOTCONN;
		sin->sin_port = inet->dport;
		sin->sin_addr.s_addr = inet->daddr;
	} else {
		__be32 addr = inet->rcv_saddr;
		if (!addr)
			addr = inet->saddr;
		sin->sin_port = inet->sport;
		sin->sin_addr.s_addr = addr;
	}
	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
	*uaddr_len = sizeof(*sin);
	return 0;
}

int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
		 size_t size)
{
	struct sock *sk = sock->sk;

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

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


static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags)
{
	struct sock *sk = sock->sk;

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

	if (sk->sk_prot->sendpage)
		return sk->sk_prot->sendpage(sk, page, offset, size, flags);
	return sock_no_sendpage(sock, page, offset, size, flags);
}


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)	/* MAXINT->0 */
		return -EINVAL;

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

	switch (sk->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->sk_shutdown |= how;
		if (sk->sk_prot->shutdown)
			sk->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->sk_prot->disconnect(sk, O_NONBLOCK);
		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
		break;
	}

	/* Wake up anyone sleeping in poll. */
	sk->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.
 */

int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	struct sock *sk = sock->sk;
	int err = 0;

	switch (cmd) {
		case SIOCGSTAMP:
			err = sock_get_timestamp(sk, (struct timeval __user *)arg);
			break;
		case SIOCGSTAMPNS:
			err = sock_get_timestampns(sk, (struct timespec __user *)arg);
			break;
		case SIOCADDRT:
		case SIOCDELRT:
		case SIOCRTMSG:
			err = ip_rt_ioctl(cmd, (void __user *)arg);
			break;
		case SIOCDARP:
		case SIOCGARP:
		case SIOCSARP:
			err = arp_ioctl(cmd, (void __user *)arg);
			break;
		case SIOCGIFADDR:
		case SIOCSIFADDR:
		case SIOCGIFBRDADDR:
		case SIOCSIFBRDADDR:
		case SIOCGIFNETMASK:
		case SIOCSIFNETMASK:
		case SIOCGIFDSTADDR:
		case SIOCSIFDSTADDR:
		case SIOCSIFPFLAGS:
		case SIOCGIFPFLAGS:
		case SIOCSIFFLAGS:
			err = devinet_ioctl(cmd, (void __user *)arg);
			break;
		default:
			if (sk->sk_prot->ioctl)
				err = sk->sk_prot->ioctl(sk, cmd, arg);
			else
				err = -ENOIOCTLCMD;
			break;
	}
	return err;
}

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	   = tcp_sendmsg,
	.recvmsg	   = sock_common_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = tcp_sendpage,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};

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	   = sock_common_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = inet_sendpage,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};

/*
 * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
 * udp_poll
 */
static const struct proto_ops inet_sockraw_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		   = datagram_poll,
	.ioctl		   = inet_ioctl,
	.listen		   = sock_no_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet_sendmsg,
	.recvmsg	   = sock_common_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = inet_sendpage,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};

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

/* Upon startup we insert all the elements in inetsw_array[] into
 * the linked list inetsw.
 */
static struct inet_protosw inetsw_array[] =
{
	{
		.type =       SOCK_STREAM,
		.protocol =   IPPROTO_TCP,
		.prot =       &tcp_prot,
		.ops =        &inet_stream_ops,
		.capability = -1,
		.no_check =   0,
		.flags =      INET_PROTOSW_PERMANENT |
			      INET_PROTOSW_ICSK,
	},

	{
		.type =       SOCK_DGRAM,
		.protocol =   IPPROTO_UDP,
		.prot =       &udp_prot,
		.ops =        &inet_dgram_ops,
		.capability = -1,
		.no_check =   UDP_CSUM_DEFAULT,
		.flags =      INET_PROTOSW_PERMANENT,
       },


       {
	       .type =       SOCK_RAW,
	       .protocol =   IPPROTO_IP,	/* wild card */
	       .prot =       &raw_prot,
	       .ops =        &inet_sockraw_ops,
	       .capability = CAP_NET_RAW,
	       .no_check =   UDP_CSUM_DEFAULT,
	       .flags =      INET_PROTOSW_REUSE,
       }
};

#define INETSW_ARRAY_LEN ARRAY_SIZE(inetsw_array)

void inet_register_protosw(struct inet_protosw *p)
{
	struct list_head *lh;
	struct inet_protosw *answer;
	int protocol = p->protocol;
	struct list_head *last_perm;

	spin_lock_bh(&inetsw_lock);

	if (p->type >= SOCK_MAX)
		goto out_illegal;

	/* If we are trying to override a permanent protocol, bail. */
	answer = NULL;
	last_perm = &inetsw[p->type];
	list_for_each(lh, &inetsw[p->type]) {
		answer = list_entry(lh, struct inet_protosw, list);

		/* Check only the non-wild match. */
		if (INET_PROTOSW_PERMANENT & answer->flags) {
			if (protocol == answer->protocol)
				break;
			last_perm = lh;
		}

		answer = NULL;
	}
	if (answer)
		goto out_permanent;

	/* Add the new entry after the last permanent entry if any, so that
	 * the new entry does not override a permanent entry when matched with
	 * a wild-card protocol. But it is allowed to override any existing
	 * non-permanent entry.  This means that when we remove this entry, the
	 * system automatically returns to the old behavior.
	 */
	list_add_rcu(&p->list, last_perm);
out:
	spin_unlock_bh(&inetsw_lock);

	synchronize_net();

	return;

out_permanent:
	printk(KERN_ERR "Attempt to override permanent protocol %d.\n",
	       protocol);
	goto out;

out_illegal:
	printk(KERN_ERR
	       "Ignoring attempt to register invalid socket type %d.\n",
	       p->type);
	goto out;
}

void inet_unregister_protosw(struct inet_protosw *p)
{
	if (INET_PROTOSW_PERMANENT & p->flags) {
		printk(KERN_ERR
		       "Attempt to unregister permanent protocol %d.\n",
		       p->protocol);
	} else {
		spin_lock_bh(&inetsw_lock);
		list_del_rcu(&p->list);
		spin_unlock_bh(&inetsw_lock);

		synchronize_net();