socket.c

EXPORT_SYMBOL(vlan_ioctl_set);

static DEFINE_MUTEX(dlci_ioctl_mutex);
static int (*dlci_ioctl_hook) (unsigned int, void __user *);

void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
{
	mutex_lock(&dlci_ioctl_mutex);
	dlci_ioctl_hook = hook;
	mutex_unlock(&dlci_ioctl_mutex);
}
EXPORT_SYMBOL(dlci_ioctl_set);

static long sock_do_ioctl(struct net *net, struct socket *sock,
				 unsigned int cmd, unsigned long arg)
{
	int err;
	void __user *argp = (void __user *)arg;

	err = sock->ops->ioctl(sock, cmd, arg);

	/*
	 * If this ioctl is unknown try to hand it down
	 * to the NIC driver.
	 */
	if (err == -ENOIOCTLCMD)
		err = dev_ioctl(net, cmd, argp);

	return err;
}

/*
 *	With an ioctl, arg may well be a user mode pointer, but we don't know
 *	what to do with it - that's up to the protocol still.
 */

static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
	struct socket *sock;
	struct sock *sk;
	void __user *argp = (void __user *)arg;
	int pid, err;
	struct net *net;

	sock = file->private_data;
	sk = sock->sk;
	net = sock_net(sk);
	if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) {
		err = dev_ioctl(net, cmd, argp);
	} else
#ifdef CONFIG_WEXT_CORE
	if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
		err = dev_ioctl(net, cmd, argp);
	} else
#endif
		switch (cmd) {
		case FIOSETOWN:
		case SIOCSPGRP:
			err = -EFAULT;
			if (get_user(pid, (int __user *)argp))
				break;
			err = f_setown(sock->file, pid, 1);
			break;
		case FIOGETOWN:
		case SIOCGPGRP:
			err = put_user(f_getown(sock->file),
				       (int __user *)argp);
			break;
		case SIOCGIFBR:
		case SIOCSIFBR:
		case SIOCBRADDBR:
		case SIOCBRDELBR:
			err = -ENOPKG;
			if (!br_ioctl_hook)
				request_module("bridge");

			mutex_lock(&br_ioctl_mutex);
			if (br_ioctl_hook)
				err = br_ioctl_hook(net, cmd, argp);
			mutex_unlock(&br_ioctl_mutex);
			break;
		case SIOCGIFVLAN:
		case SIOCSIFVLAN:
			err = -ENOPKG;
			if (!vlan_ioctl_hook)
				request_module("8021q");

			mutex_lock(&vlan_ioctl_mutex);
			if (vlan_ioctl_hook)
				err = vlan_ioctl_hook(net, argp);
			mutex_unlock(&vlan_ioctl_mutex);
			break;
		case SIOCADDDLCI:
		case SIOCDELDLCI:
			err = -ENOPKG;
			if (!dlci_ioctl_hook)
				request_module("dlci");

			mutex_lock(&dlci_ioctl_mutex);
			if (dlci_ioctl_hook)
				err = dlci_ioctl_hook(cmd, argp);
			mutex_unlock(&dlci_ioctl_mutex);
			break;
		default:
			err = sock_do_ioctl(net, sock, cmd, arg);
			break;
		}
	return err;
}

int sock_create_lite(int family, int type, int protocol, struct socket **res)
{
	int err;
	struct socket *sock = NULL;

	err = security_socket_create(family, type, protocol, 1);
	if (err)
		goto out;

	sock = sock_alloc();
	if (!sock) {
		err = -ENOMEM;
		goto out;
	}

	sock->type = type;
	err = security_socket_post_create(sock, family, type, protocol, 1);
	if (err)
		goto out_release;

out:
	*res = sock;
	return err;
out_release:
	sock_release(sock);
	sock = NULL;
	goto out;
}
EXPORT_SYMBOL(sock_create_lite);

/* No kernel lock held - perfect */
static unsigned int sock_poll(struct file *file, poll_table *wait)
{
	unsigned int busy_flag = 0;
	struct socket *sock;

	/*
	 *      We can't return errors to poll, so it's either yes or no.
	 */
	sock = file->private_data;

	if (sk_can_busy_loop(sock->sk)) {
		/* this socket can poll_ll so tell the system call */
		busy_flag = POLL_BUSY_LOOP;

		/* once, only if requested by syscall */
		if (wait && (wait->_key & POLL_BUSY_LOOP))
			sk_busy_loop(sock->sk, 1);
	}

	return busy_flag | sock->ops->poll(file, sock, wait);
}

static int sock_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct socket *sock = file->private_data;

	return sock->ops->mmap(file, sock, vma);
}

static int sock_close(struct inode *inode, struct file *filp)
{
	sock_release(SOCKET_I(inode));
	return 0;
}

/*
 *	Update the socket async list
 *
 *	Fasync_list locking strategy.
 *
 *	1. fasync_list is modified only under process context socket lock
 *	   i.e. under semaphore.
 *	2. fasync_list is used under read_lock(&sk->sk_callback_lock)
 *	   or under socket lock
 */

static int sock_fasync(int fd, struct file *filp, int on)
{
	struct socket *sock = filp->private_data;
	struct sock *sk = sock->sk;
	struct socket_wq *wq;

	if (sk == NULL)
		return -EINVAL;

	lock_sock(sk);
	wq = rcu_dereference_protected(sock->wq, sock_owned_by_user(sk));
	fasync_helper(fd, filp, on, &wq->fasync_list);

	if (!wq->fasync_list)
		sock_reset_flag(sk, SOCK_FASYNC);
	else
		sock_set_flag(sk, SOCK_FASYNC);

	release_sock(sk);
	return 0;
}

/* This function may be called only under socket lock or callback_lock or rcu_lock */

int sock_wake_async(struct socket *sock, int how, int band)
{
	struct socket_wq *wq;

	if (!sock)
		return -1;
	rcu_read_lock();
	wq = rcu_dereference(sock->wq);
	if (!wq || !wq->fasync_list) {
		rcu_read_unlock();
		return -1;
	}
	switch (how) {
	case SOCK_WAKE_WAITD:
		if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags))
			break;
		goto call_kill;
	case SOCK_WAKE_SPACE:
		if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags))
			break;
		/* fall through */
	case SOCK_WAKE_IO:
call_kill:
		kill_fasync(&wq->fasync_list, SIGIO, band);
		break;
	case SOCK_WAKE_URG:
		kill_fasync(&wq->fasync_list, SIGURG, band);
	}
	rcu_read_unlock();
	return 0;
}
EXPORT_SYMBOL(sock_wake_async);

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();
	if (!sock) {
		net_warn_ratelimited("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);
	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;
}
EXPORT_SYMBOL(__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);
}
EXPORT_SYMBOL(sock_create);

int sock_create_kern(int family, int type, int protocol, struct socket **res)
{
	return __sock_create(&init_net, family, type, protocol, res, 1);
}
EXPORT_SYMBOL(sock_create_kern);

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);
	if (retval < 0)
		goto out;

	retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
	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;
}

/*
 *	Create a pair of connected sockets.
 */

SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
		int __user *, usockvec)
{
	struct socket *sock1, *sock2;
	int fd1, fd2, err;
	struct file *newfile1, *newfile2;
	int flags;

	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;

	/*
	 * Obtain the first socket and check if the underlying protocol
	 * supports the socketpair call.
	 */

	err = sock_create(family, type, protocol, &sock1);
	if (err < 0)
		goto out;

	err = sock_create(family, type, protocol, &sock2);
	if (err < 0)
		goto out_release_1;

	err = sock1->ops->socketpair(sock1, sock2);
	if (err < 0)
		goto out_release_both;

	fd1 = get_unused_fd_flags(flags);
	if (unlikely(fd1 < 0)) {
		err = fd1;
		goto out_release_both;
	}

	fd2 = get_unused_fd_flags(flags);
	if (unlikely(fd2 < 0)) {
		err = fd2;
		goto out_put_unused_1;
	}

	newfile1 = sock_alloc_file(sock1, flags, NULL);
	if (unlikely(IS_ERR(newfile1))) {
		err = PTR_ERR(newfile1);
		goto out_put_unused_both;
	}

	newfile2 = sock_alloc_file(sock2, flags, NULL);
	if (IS_ERR(newfile2)) {
		err = PTR_ERR(newfile2);
		goto out_fput_1;
	}

	err = put_user(fd1, &usockvec[0]);
	if (err)
		goto out_fput_both;

	err = put_user(fd2, &usockvec[1]);
	if (err)
		goto out_fput_both;

	audit_fd_pair(fd1, fd2);

	fd_install(fd1, newfile1);
	fd_install(fd2, newfile2);
	/* fd1 and fd2 may be already another descriptors.
	 * Not kernel problem.
	 */

	return 0;

out_fput_both:
	fput(newfile2);
	fput(newfile1);
	put_unused_fd(fd2);
	put_unused_fd(fd1);
	goto out;

out_fput_1:
	fput(newfile1);
	put_unused_fd(fd2);
	put_unused_fd(fd1);
	sock_release(sock2);
	goto out;

out_put_unused_both:
	put_unused_fd(fd2);
out_put_unused_1:
	put_unused_fd(fd1);
out_release_both:
	sock_release(sock2);
out_release_1:
	sock_release(sock1);
out:
	return err;
}

/*
 *	Bind a name to a socket. Nothing much to do here since it's
 *	the protocol's responsibility to handle the local address.
 *
 *	We move the socket address to kernel space before we call
 *	the protocol layer (having also checked the address is ok).
 */

SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock) {
		err = move_addr_to_kernel(umyaddr, addrlen, &address);
		if (err >= 0) {
			err = security_socket_bind(sock,
						   (struct sockaddr *)&address,
						   addrlen);
			if (!err)
				err = sock->ops->bind(sock,
						      (struct sockaddr *)
						      &address, addrlen);
		}
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	Perform a listen. Basically, we allow the protocol to do anything
 *	necessary for a listen, and if that works, we mark the socket as
 *	ready for listening.
 */

SYSCALL_DEFINE2(listen, int, fd, int, backlog)
{
	struct socket *sock;
	int err, fput_needed;
	int somaxconn;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock) {
		somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn;
		if ((unsigned int)backlog > somaxconn)
			backlog = somaxconn;

		err = security_socket_listen(sock, backlog);
		if (!err)
			err = sock->ops->listen(sock, backlog);

		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	For accept, we attempt to create a new socket, set up the link
 *	with the client, wake up the client, then return the new
 *	connected fd. We collect the address of the connector in kernel
 *	space and move it to user at the very end. This is unclean because
 *	we open the socket then return an error.
 *
 *	1003.1g adds the ability to recvmsg() to query connection pending
 *	status to recvmsg. We need to add that support in a way thats
 *	clean when we restucture accept also.
 */

SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
		int __user *, upeer_addrlen, int, flags)
{
	struct socket *sock, *newsock;
	struct file *newfile;
	int err, len, newfd, fput_needed;
	struct sockaddr_storage address;

	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
		return -EINVAL;

	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	err = -ENFILE;
	newsock = sock_alloc();
	if (!newsock)
		goto out_put;

	newsock->type = sock->type;
	newsock->ops = sock->ops;

	/*
	 * We don't need try_module_get here, as the listening socket (sock)
	 * has the protocol module (sock->ops->owner) held.
	 */
	__module_get(newsock->ops->owner);

	newfd = get_unused_fd_flags(flags);
	if (unlikely(newfd < 0)) {
		err = newfd;
		sock_release(newsock);
		goto out_put;
	}
	newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name);
	if (unlikely(IS_ERR(newfile))) {
		err = PTR_ERR(newfile);
		put_unused_fd(newfd);
		sock_release(newsock);
		goto out_put;
	}

	err = security_socket_accept(sock, newsock);
	if (err)
		goto out_fd;

	err = sock->ops->accept(sock, newsock, sock->file->f_flags);
	if (err < 0)
		goto out_fd;

	if (upeer_sockaddr) {
		if (newsock->ops->getname(newsock, (struct sockaddr *)&address,
					  &len, 2) < 0) {
			err = -ECONNABORTED;
			goto out_fd;
		}
		err = move_addr_to_user(&address,
					len, upeer_sockaddr, upeer_addrlen);
		if (err < 0)
			goto out_fd;
	}

	/* File flags are not inherited via accept() unlike another OSes. */

	fd_install(newfd, newfile);
	err = newfd;

out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
out_fd:
	fput(newfile);
	put_unused_fd(newfd);
	goto out_put;
}

SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr,
		int __user *, upeer_addrlen)
{
	return sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0);
}

/*
 *	Attempt to connect to a socket with the server address.  The address
 *	is in user space so we verify it is OK and move it to kernel space.
 *
 *	For 1003.1g we need to add clean support for a bind to AF_UNSPEC to
 *	break bindings
 *
 *	NOTE: 1003.1g draft 6.3 is broken with respect to AX.25/NetROM and
 *	other SEQPACKET protocols that take time to connect() as it doesn't
 *	include the -EINPROGRESS status for such sockets.
 */

SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
		int, addrlen)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;
	err = move_addr_to_kernel(uservaddr, addrlen, &address);
	if (err < 0)
		goto out_put;

	err =
	    security_socket_connect(sock, (struct sockaddr *)&address, addrlen);
	if (err)
		goto out_put;

	err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen,
				 sock->file->f_flags);
out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *	Get the local address ('name') of a socket object. Move the obtained
 *	name to user space.
 */

SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
		int __user *, usockaddr_len)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int len, err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	err = security_socket_getsockname(sock);
	if (err)
		goto out_put;

	err = sock->ops->getname(sock, (struct sockaddr *)&address, &len, 0);
	if (err)
		goto out_put;
	err = move_addr_to_user(&address, len, usockaddr, usockaddr_len);

out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *	Get the remote address ('name') of a socket object. Move the obtained
 *	name to user space.
 */

SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
		int __user *, usockaddr_len)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int len, err, fput_needed;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock != NULL) {
		err = security_socket_getpeername(sock);
		if (err) {
			fput_light(sock->file, fput_needed);
			return err;
		}

		err =
		    sock->ops->getname(sock, (struct sockaddr *)&address, &len,
				       1);
		if (!err)
			err = move_addr_to_user(&address, len, usockaddr,
						usockaddr_len);
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	Send a datagram to a given address. We move the address into kernel
 *	space and check the user space data area is readable before invoking
 *	the protocol.
 */

SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
		unsigned int, flags, struct sockaddr __user *, addr,
		int, addr_len)
{
	struct socket *sock;
	struct sockaddr_storage address;
	int err;
	struct msghdr msg;
	struct iovec iov;
	int fput_needed;

	if (len > INT_MAX)
		len = INT_MAX;
	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	iov.iov_base = buff;
	iov.iov_len = len;
	msg.msg_name = NULL;
	msg.msg_iov = &iov;
	msg.msg_iovlen = 1;
	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	msg.msg_namelen = 0;
	if (addr) {
		err = move_addr_to_kernel(addr, addr_len, &address);
		if (err < 0)
			goto out_put;
		msg.msg_name = (struct sockaddr *)&address;
		msg.msg_namelen = addr_len;
	}
	if (sock->file->f_flags & O_NONBLOCK)
		flags |= MSG_DONTWAIT;
	msg.msg_flags = flags;
	err = sock_sendmsg(sock, &msg, len);

out_put:
	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *	Send a datagram down a socket.
 */

SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len,
		unsigned int, flags)
{
	return sys_sendto(fd, buff, len, flags, NULL, 0);
}

/*
 *	Receive a frame from the socket and optionally record the address of the
 *	sender. We verify the buffers are writable and if needed move the
 *	sender address from kernel to user space.
 */

SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
		unsigned int, flags, struct sockaddr __user *, addr,
		int __user *, addr_len)
{
	struct socket *sock;
	struct iovec iov;
	struct msghdr msg;
	struct sockaddr_storage address;
	int err, err2;
	int fput_needed;

	if (size > INT_MAX)
		size = INT_MAX;
	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (!sock)
		goto out;

	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	msg.msg_iovlen = 1;
	msg.msg_iov = &iov;
	iov.iov_len = size;
	iov.iov_base = ubuf;
	/* Save some cycles and don't copy the address if not needed */
	msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
	/* We assume all kernel code knows the size of sockaddr_storage */
	msg.msg_namelen = 0;
	if (sock->file->f_flags & O_NONBLOCK)
		flags |= MSG_DONTWAIT;
	err = sock_recvmsg(sock, &msg, size, flags);

	if (err >= 0 && addr != NULL) {
		err2 = move_addr_to_user(&address,
					 msg.msg_namelen, addr, addr_len);
		if (err2 < 0)
			err = err2;
	}

	fput_light(sock->file, fput_needed);
out:
	return err;
}

/*
 *	Receive a datagram from a socket.
 */

asmlinkage long sys_recv(int fd, void __user *ubuf, size_t size,
			 unsigned int flags)
{
	return sys_recvfrom(fd, ubuf, size, flags, NULL, NULL);
}

/*
 *	Set a socket option. Because we don't know the option lengths we have
 *	to pass the user mode parameter for the protocols to sort out.
 */

SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
		char __user *, optval, int, optlen)
{
	int err, fput_needed;
	struct socket *sock;

	if (optlen < 0)
		return -EINVAL;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock != NULL) {
		err = security_socket_setsockopt(sock, level, optname);
		if (err)
			goto out_put;

		if (level == SOL_SOCKET)
			err =
			    sock_setsockopt(sock, level, optname, optval,
					    optlen);
		else
			err =
			    sock->ops->setsockopt(sock, level, optname, optval,
						  optlen);
out_put:
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	Get a socket option. Because we don't know the option lengths we have
 *	to pass a user mode parameter for the protocols to sort out.
 */

SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
		char __user *, optval, int __user *, optlen)
{
	int err, fput_needed;
	struct socket *sock;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock != NULL) {
		err = security_socket_getsockopt(sock, level, optname);
		if (err)
			goto out_put;

		if (level == SOL_SOCKET)
			err =
			    sock_getsockopt(sock, level, optname, optval,
					    optlen);
		else
			err =
			    sock->ops->getsockopt(sock, level, optname, optval,
						  optlen);
out_put:
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/*
 *	Shutdown a socket.
 */

SYSCALL_DEFINE2(shutdown, int, fd, int, how)
{
	int err, fput_needed;
	struct socket *sock;

	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock != NULL) {
		err = security_socket_shutdown(sock, how);
		if (!err)
			err = sock->ops->shutdown(sock, how);
		fput_light(sock->file, fput_needed);
	}
	return err;
}

/* A couple of helpful macros for getting the address of the 32/64 bit
 * fields which are the same type (int / unsigned) on our platforms.
 */
#define COMPAT_MSG(msg, member)	((MSG_CMSG_COMPAT & flags) ? &msg##_compat->member : &msg->member)
#define COMPAT_NAMELEN(msg)	COMPAT_MSG(msg, msg_namelen)
#define COMPAT_FLAGS(msg)	COMPAT_MSG(msg, msg_flags)

struct used_address {
	struct sockaddr_storage name;
	unsigned int name_len;
};

static int copy_msghdr_from_user(struct msghdr *kmsg,
				 struct msghdr __user *umsg)
{
	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
		return -EFAULT;
	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
	return 0;
}

static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
			 struct msghdr *msg_sys, unsigned int flags,
			 struct used_address *used_address)
{
	struct compat_msghdr __user *msg_compat =
	    (struct compat_msghdr __user *)msg;
	struct sockaddr_storage address;