/*

   * net/tipc/socket.c: TIPC socket API

   *

   * Copyright (c) 2001-2007, 2012-2014, Ericsson AB

   * Copyright (c) 2004-2008, 2010-2013, Wind River Systems

   * All rights reserved.
   *

   * Redistribution and use in source and binary forms, with or without

   * modification, are permitted provided that the following conditions are met:
   *

   * 1. Redistributions of source code must retain the above copyright
   *    notice, this list of conditions and the following disclaimer.
   * 2. Redistributions in binary form must reproduce the above copyright
   *    notice, this list of conditions and the following disclaimer in the
   *    documentation and/or other materials provided with the distribution.
   * 3. Neither the names of the copyright holders nor the names of its
   *    contributors may be used to endorse or promote products derived from
   *    this software without specific prior written permission.

   *

   * Alternatively, this software may be distributed under the terms of the
   * GNU General Public License ("GPL") version 2 as published by the Free
   * Software Foundation.
   *
   * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
   * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
   * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
   * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
   * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
   * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
   * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
   * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
   * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
   * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE

   * POSSIBILITY OF SUCH DAMAGE.
   */

  #include "core.h"

  #include "port.h"

  #include "node.h"

  #include <linux/export.h>

  #include "link.h"

  #define SS_LISTENING	-1	/* socket is listening */
  #define SS_READY	-2	/* socket is connectionless */

  #define CONN_TIMEOUT_DEFAULT	8000	/* default connect timeout = 8s */

  static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb);

  static void tipc_data_ready(struct sock *sk);

  static void tipc_write_space(struct sock *sk);

  static int tipc_release(struct socket *sock);
  static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);

  static const struct proto_ops packet_ops;
  static const struct proto_ops stream_ops;
  static const struct proto_ops msg_ops;

  
  static struct proto tipc_proto;

  static struct proto tipc_proto_kern;

  /*

   * Revised TIPC socket locking policy:
   *
   * Most socket operations take the standard socket lock when they start
   * and hold it until they finish (or until they need to sleep).  Acquiring
   * this lock grants the owner exclusive access to the fields of the socket
   * data structures, with the exception of the backlog queue.  A few socket
   * operations can be done without taking the socket lock because they only
   * read socket information that never changes during the life of the socket.
   *
   * Socket operations may acquire the lock for the associated TIPC port if they
   * need to perform an operation on the port.  If any routine needs to acquire
   * both the socket lock and the port lock it must take the socket lock first
   * to avoid the risk of deadlock.
   *
   * The dispatcher handling incoming messages cannot grab the socket lock in
   * the standard fashion, since invoked it runs at the BH level and cannot block.
   * Instead, it checks to see if the socket lock is currently owned by someone,
   * and either handles the message itself or adds it to the socket's backlog
   * queue; in the latter case the queued message is processed once the process
   * owning the socket lock releases it.
   *
   * NOTE: Releasing the socket lock while an operation is sleeping overcomes
   * the problem of a blocked socket operation preventing any other operations
   * from occurring.  However, applications must be careful if they have
   * multiple threads trying to send (or receive) on the same socket, as these
   * operations might interfere with each other.  For example, doing a connect
   * and a receive at the same time might allow the receive to consume the
   * ACK message meant for the connect.  While additional work could be done
   * to try and overcome this, it doesn't seem to be worthwhile at the present.
   *
   * NOTE: Releasing the socket lock while an operation is sleeping also ensures
   * that another operation that must be performed in a non-blocking manner is
   * not delayed for very long because the lock has already been taken.
   *
   * NOTE: This code assumes that certain fields of a port/socket pair are
   * constant over its lifetime; such fields can be examined without taking
   * the socket lock and/or port lock, and do not need to be re-read even
   * after resuming processing after waiting.  These fields include:
   *   - socket type
   *   - pointer to socket sk structure (aka tipc_sock structure)
   *   - pointer to port structure
   *   - port reference
   */

  #include "socket.h"

  /**
   * advance_rx_queue - discard first buffer in socket receive queue
   *
   * Caller must hold socket lock

   */

  static void advance_rx_queue(struct sock *sk)

  {

  	kfree_skb(__skb_dequeue(&sk->sk_receive_queue));

  }

  /**

   * reject_rx_queue - reject all buffers in socket receive queue
   *
   * Caller must hold socket lock

   */

  static void reject_rx_queue(struct sock *sk)

  {

  	struct sk_buff *buf;

  	u32 dnode;

  	while ((buf = __skb_dequeue(&sk->sk_receive_queue))) {
  		if (tipc_msg_reverse(buf, &dnode, TIPC_ERR_NO_PORT))
  			tipc_link_xmit2(buf, dnode, 0);
  	}

  }
  
  /**

   * tipc_sk_create - create a TIPC socket

   * @net: network namespace (must be default network)

   * @sock: pre-allocated socket structure
   * @protocol: protocol indicator (must be 0)

   * @kern: caused by kernel or by userspace?

   *

   * This routine creates additional data structures used by the TIPC socket,
   * initializes them, and links them together.

   *
   * Returns 0 on success, errno otherwise
   */

  static int tipc_sk_create(struct net *net, struct socket *sock,
  			  int protocol, int kern)

  {

  	const struct proto_ops *ops;
  	socket_state state;

  	struct sock *sk;

  	struct tipc_sock *tsk;
  	struct tipc_port *port;
  	u32 ref;

  
  	/* Validate arguments */

  	if (unlikely(protocol != 0))
  		return -EPROTONOSUPPORT;

  	switch (sock->type) {
  	case SOCK_STREAM:

  		ops = &stream_ops;
  		state = SS_UNCONNECTED;

  		break;
  	case SOCK_SEQPACKET:

  		ops = &packet_ops;
  		state = SS_UNCONNECTED;

  		break;
  	case SOCK_DGRAM:

  	case SOCK_RDM:

  		ops = &msg_ops;
  		state = SS_READY;

  		break;

  	default:

  		return -EPROTOTYPE;

  	}

  	/* Allocate socket's protocol area */

  	if (!kern)
  		sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto);
  	else
  		sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto_kern);

  	if (sk == NULL)

  		return -ENOMEM;

  	tsk = tipc_sk(sk);
  	port = &tsk->port;
  
  	ref = tipc_port_init(port, TIPC_LOW_IMPORTANCE);
  	if (!ref) {
  		pr_warn("Socket registration failed, ref. table exhausted
  ");

  		sk_free(sk);
  		return -ENOMEM;
  	}

  	/* Finish initializing socket data structures */

  	sock->ops = ops;
  	sock->state = state;

  	sock_init_data(sock, sk);

  	sk->sk_backlog_rcv = tipc_backlog_rcv;

  	sk->sk_rcvbuf = sysctl_tipc_rmem[1];

  	sk->sk_data_ready = tipc_data_ready;
  	sk->sk_write_space = tipc_write_space;

  	tsk->conn_timeout = CONN_TIMEOUT_DEFAULT;
  	atomic_set(&tsk->dupl_rcvcnt, 0);

  	tipc_port_unlock(port);

  	if (sock->state == SS_READY) {

  		tipc_port_set_unreturnable(port, true);

  		if (sock->type == SOCK_DGRAM)

  			tipc_port_set_unreliable(port, true);

  	}

  	return 0;
  }
  
  /**

   * tipc_sock_create_local - create TIPC socket from inside TIPC module
   * @type: socket type - SOCK_RDM or SOCK_SEQPACKET
   *
   * We cannot use sock_creat_kern here because it bumps module user count.
   * Since socket owner and creator is the same module we must make sure
   * that module count remains zero for module local sockets, otherwise
   * we cannot do rmmod.
   *
   * Returns 0 on success, errno otherwise
   */
  int tipc_sock_create_local(int type, struct socket **res)
  {
  	int rc;

  
  	rc = sock_create_lite(AF_TIPC, type, 0, res);
  	if (rc < 0) {
  		pr_err("Failed to create kernel socket
  ");
  		return rc;
  	}
  	tipc_sk_create(&init_net, *res, 0, 1);

  	return 0;
  }
  
  /**
   * tipc_sock_release_local - release socket created by tipc_sock_create_local
   * @sock: the socket to be released.
   *
   * Module reference count is not incremented when such sockets are created,
   * so we must keep it from being decremented when they are released.
   */
  void tipc_sock_release_local(struct socket *sock)
  {

  	tipc_release(sock);

  	sock->ops = NULL;
  	sock_release(sock);
  }
  
  /**
   * tipc_sock_accept_local - accept a connection on a socket created
   * with tipc_sock_create_local. Use this function to avoid that
   * module reference count is inadvertently incremented.
   *
   * @sock:    the accepting socket
   * @newsock: reference to the new socket to be created
   * @flags:   socket flags
   */
  
  int tipc_sock_accept_local(struct socket *sock, struct socket **newsock,

  			   int flags)

  {
  	struct sock *sk = sock->sk;
  	int ret;
  
  	ret = sock_create_lite(sk->sk_family, sk->sk_type,
  			       sk->sk_protocol, newsock);
  	if (ret < 0)
  		return ret;

  	ret = tipc_accept(sock, *newsock, flags);

  	if (ret < 0) {
  		sock_release(*newsock);
  		return ret;
  	}
  	(*newsock)->ops = sock->ops;
  	return ret;
  }
  
  /**

   * tipc_release - destroy a TIPC socket

   * @sock: socket to destroy
   *
   * This routine cleans up any messages that are still queued on the socket.
   * For DGRAM and RDM socket types, all queued messages are rejected.
   * For SEQPACKET and STREAM socket types, the first message is rejected
   * and any others are discarded.  (If the first message on a STREAM socket
   * is partially-read, it is discarded and the next one is rejected instead.)

   *

   * NOTE: Rejected messages are not necessarily returned to the sender!  They
   * are returned or discarded according to the "destination droppable" setting
   * specified for the message by the sender.
   *
   * Returns 0 on success, errno otherwise
   */

  static int tipc_release(struct socket *sock)

  {

  	struct sock *sk = sock->sk;

  	struct tipc_sock *tsk;
  	struct tipc_port *port;

  	struct sk_buff *buf;

  	u32 dnode;

  	/*
  	 * Exit if socket isn't fully initialized (occurs when a failed accept()
  	 * releases a pre-allocated child socket that was never used)
  	 */

  	if (sk == NULL)

  		return 0;

  	tsk = tipc_sk(sk);
  	port = &tsk->port;

  	lock_sock(sk);
  
  	/*
  	 * Reject all unreceived messages, except on an active connection
  	 * (which disconnects locally & sends a 'FIN+' to peer)
  	 */

  	while (sock->state != SS_DISCONNECTING) {

  		buf = __skb_dequeue(&sk->sk_receive_queue);
  		if (buf == NULL)

  			break;

  		if (TIPC_SKB_CB(buf)->handle != NULL)

  			kfree_skb(buf);

  		else {
  			if ((sock->state == SS_CONNECTING) ||
  			    (sock->state == SS_CONNECTED)) {
  				sock->state = SS_DISCONNECTING;

  				tipc_port_disconnect(port->ref);

  			}

  			if (tipc_msg_reverse(buf, &dnode, TIPC_ERR_NO_PORT))
  				tipc_link_xmit2(buf, dnode, 0);

  		}

  	}

  	/* Destroy TIPC port; also disconnects an active connection and
  	 * sends a 'FIN-' to peer.

  	 */

  	tipc_port_destroy(port);

  	/* Discard any remaining (connection-based) messages in receive queue */

  	__skb_queue_purge(&sk->sk_receive_queue);

  	/* Reject any messages that accumulated in backlog queue */

  	sock->state = SS_DISCONNECTING;
  	release_sock(sk);

  
  	sock_put(sk);

  	sock->sk = NULL;

  	return 0;

  }
  
  /**

   * tipc_bind - associate or disassocate TIPC name(s) with a socket

   * @sock: socket structure
   * @uaddr: socket address describing name(s) and desired operation
   * @uaddr_len: size of socket address data structure

   *

   * Name and name sequence binding is indicated using a positive scope value;
   * a negative scope value unbinds the specified name.  Specifying no name
   * (i.e. a socket address length of 0) unbinds all names from the socket.

   *

   * Returns 0 on success, errno otherwise

   *
   * NOTE: This routine doesn't need to take the socket lock since it doesn't
   *       access any non-constant socket information.

   */

  static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
  		     int uaddr_len)

  {

  	struct sock *sk = sock->sk;

  	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;

  	struct tipc_sock *tsk = tipc_sk(sk);

  	int res = -EINVAL;

  	lock_sock(sk);
  	if (unlikely(!uaddr_len)) {

  		res = tipc_withdraw(&tsk->port, 0, NULL);

  		goto exit;
  	}

  	if (uaddr_len < sizeof(struct sockaddr_tipc)) {
  		res = -EINVAL;
  		goto exit;
  	}
  	if (addr->family != AF_TIPC) {
  		res = -EAFNOSUPPORT;
  		goto exit;
  	}

  	if (addr->addrtype == TIPC_ADDR_NAME)
  		addr->addr.nameseq.upper = addr->addr.nameseq.lower;

  	else if (addr->addrtype != TIPC_ADDR_NAMESEQ) {
  		res = -EAFNOSUPPORT;
  		goto exit;
  	}

  	if ((addr->addr.nameseq.type < TIPC_RESERVED_TYPES) &&

  	    (addr->addr.nameseq.type != TIPC_TOP_SRV) &&

  	    (addr->addr.nameseq.type != TIPC_CFG_SRV)) {
  		res = -EACCES;
  		goto exit;
  	}

  	res = (addr->scope > 0) ?

  		tipc_publish(&tsk->port, addr->scope, &addr->addr.nameseq) :
  		tipc_withdraw(&tsk->port, -addr->scope, &addr->addr.nameseq);

  exit:
  	release_sock(sk);
  	return res;

  }

  /**

   * tipc_getname - get port ID of socket or peer socket

   * @sock: socket structure
   * @uaddr: area for returned socket address
   * @uaddr_len: area for returned length of socket address

   * @peer: 0 = own ID, 1 = current peer ID, 2 = current/former peer ID

   *

   * Returns 0 on success, errno otherwise

   *

   * NOTE: This routine doesn't need to take the socket lock since it only
   *       accesses socket information that is unchanging (or which changes in

   *       a completely predictable manner).

   */

  static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
  			int *uaddr_len, int peer)

  {

  	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;

  	struct tipc_sock *tsk = tipc_sk(sock->sk);

  	memset(addr, 0, sizeof(*addr));

  	if (peer) {

  		if ((sock->state != SS_CONNECTED) &&
  			((peer != 2) || (sock->state != SS_DISCONNECTING)))
  			return -ENOTCONN;

  		addr->addr.id.ref = tipc_port_peerport(&tsk->port);
  		addr->addr.id.node = tipc_port_peernode(&tsk->port);

  	} else {

  		addr->addr.id.ref = tsk->port.ref;

  		addr->addr.id.node = tipc_own_addr;

  	}

  
  	*uaddr_len = sizeof(*addr);
  	addr->addrtype = TIPC_ADDR_ID;
  	addr->family = AF_TIPC;
  	addr->scope = 0;

  	addr->addr.name.domain = 0;

  	return 0;

  }
  
  /**

   * tipc_poll - read and possibly block on pollmask

   * @file: file structure associated with the socket
   * @sock: socket for which to calculate the poll bits
   * @wait: ???
   *

   * Returns pollmask value
   *
   * COMMENTARY:
   * It appears that the usual socket locking mechanisms are not useful here
   * since the pollmask info is potentially out-of-date the moment this routine
   * exits.  TCP and other protocols seem to rely on higher level poll routines
   * to handle any preventable race conditions, so TIPC will do the same ...
   *
   * TIPC sets the returned events as follows:

   *
   * socket state		flags set
   * ------------		---------
   * unconnected		no read flags

   *			POLLOUT if port is not congested

   *
   * connecting		POLLIN/POLLRDNORM if ACK/NACK in rx queue
   *			no write flags
   *
   * connected		POLLIN/POLLRDNORM if data in rx queue
   *			POLLOUT if port is not congested
   *
   * disconnecting	POLLIN/POLLRDNORM/POLLHUP
   *			no write flags
   *
   * listening		POLLIN if SYN in rx queue
   *			no write flags
   *
   * ready		POLLIN/POLLRDNORM if data in rx queue
   * [connectionless]	POLLOUT (since port cannot be congested)
   *
   * IMPORTANT: The fact that a read or write operation is indicated does NOT
   * imply that the operation will succeed, merely that it should be performed
   * and will not block.

   */

  static unsigned int tipc_poll(struct file *file, struct socket *sock,
  			      poll_table *wait)

  {

  	struct sock *sk = sock->sk;

  	struct tipc_sock *tsk = tipc_sk(sk);

  	u32 mask = 0;

  	sock_poll_wait(file, sk_sleep(sk), wait);

  	switch ((int)sock->state) {

  	case SS_UNCONNECTED:

  		if (!tsk->port.congested)

  			mask |= POLLOUT;
  		break;

  	case SS_READY:
  	case SS_CONNECTED:

  		if (!tsk->port.congested)

  			mask |= POLLOUT;
  		/* fall thru' */
  	case SS_CONNECTING:
  	case SS_LISTENING:
  		if (!skb_queue_empty(&sk->sk_receive_queue))
  			mask |= (POLLIN | POLLRDNORM);
  		break;
  	case SS_DISCONNECTING:
  		mask = (POLLIN | POLLRDNORM | POLLHUP);
  		break;
  	}

  
  	return mask;

  }

  /**

   * dest_name_check - verify user is permitted to send to specified port name
   * @dest: destination address
   * @m: descriptor for message to be sent

   *

   * Prevents restricted configuration commands from being issued by
   * unauthorized users.

   *

   * Returns 0 if permission is granted, otherwise errno
   */

  static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m)

  {
  	struct tipc_cfg_msg_hdr hdr;

  	if (likely(dest->addr.name.name.type >= TIPC_RESERVED_TYPES))
  		return 0;
  	if (likely(dest->addr.name.name.type == TIPC_TOP_SRV))
  		return 0;

  	if (likely(dest->addr.name.name.type != TIPC_CFG_SRV))
  		return -EACCES;

  	if (!m->msg_iovlen || (m->msg_iov[0].iov_len < sizeof(hdr)))
  		return -EMSGSIZE;

  	if (copy_from_user(&hdr, m->msg_iov[0].iov_base, sizeof(hdr)))

  		return -EFAULT;

  	if ((ntohs(hdr.tcm_type) & 0xC000) && (!capable(CAP_NET_ADMIN)))

  		return -EACCES;

  	return 0;
  }

  static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p)
  {
  	struct sock *sk = sock->sk;

  	struct tipc_sock *tsk = tipc_sk(sk);

  	DEFINE_WAIT(wait);
  	int done;
  
  	do {
  		int err = sock_error(sk);
  		if (err)
  			return err;
  		if (sock->state == SS_DISCONNECTING)
  			return -EPIPE;
  		if (!*timeo_p)
  			return -EAGAIN;
  		if (signal_pending(current))
  			return sock_intr_errno(*timeo_p);
  
  		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);

  		done = sk_wait_event(sk, timeo_p, !tsk->port.congested);

  		finish_wait(sk_sleep(sk), &wait);
  	} while (!done);
  	return 0;
  }

  /**

   * tipc_sendmsg - send message in connectionless manner

   * @iocb: if NULL, indicates that socket lock is already held

   * @sock: socket structure
   * @m: message to send

   * @total_len: length of message

   *

   * Message must have an destination specified explicitly.

   * Used for SOCK_RDM and SOCK_DGRAM messages,

   * and for 'SYN' messages on SOCK_SEQPACKET and SOCK_STREAM connections.
   * (Note: 'SYN+' is prohibited on SOCK_STREAM.)

   *

   * Returns the number of bytes sent on success, or errno otherwise
   */

  static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock,
  			struct msghdr *m, size_t total_len)

  {

  	struct sock *sk = sock->sk;

  	struct tipc_sock *tsk = tipc_sk(sk);

  	struct tipc_port *port = &tsk->port;

  	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);

  	int needs_conn;

  	long timeo;

  	int res = -EINVAL;
  
  	if (unlikely(!dest))
  		return -EDESTADDRREQ;

  	if (unlikely((m->msg_namelen < sizeof(*dest)) ||
  		     (dest->family != AF_TIPC)))

  		return -EINVAL;

  	if (total_len > TIPC_MAX_USER_MSG_SIZE)

  		return -EMSGSIZE;

  	if (iocb)
  		lock_sock(sk);

  	needs_conn = (sock->state != SS_READY);
  	if (unlikely(needs_conn)) {

  		if (sock->state == SS_LISTENING) {
  			res = -EPIPE;
  			goto exit;
  		}
  		if (sock->state != SS_UNCONNECTED) {
  			res = -EISCONN;
  			goto exit;
  		}

  		if (tsk->port.published) {

  			res = -EOPNOTSUPP;
  			goto exit;
  		}

  		if (dest->addrtype == TIPC_ADDR_NAME) {

  			tsk->port.conn_type = dest->addr.name.name.type;
  			tsk->port.conn_instance = dest->addr.name.name.instance;

  		}

  
  		/* Abort any pending connection attempts (very unlikely) */

  		reject_rx_queue(sk);

  	}

  	timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);

  	do {
  		if (dest->addrtype == TIPC_ADDR_NAME) {

  			res = dest_name_check(dest, m);
  			if (res)

  				break;

  			res = tipc_send2name(port,

  					     &dest->addr.name.name,
  					     dest->addr.name.domain,

  					     m->msg_iov,
  					     total_len);

  		} else if (dest->addrtype == TIPC_ADDR_ID) {

  			res = tipc_send2port(port,

  					     &dest->addr.id,

  					     m->msg_iov,
  					     total_len);

  		} else if (dest->addrtype == TIPC_ADDR_MCAST) {

  			if (needs_conn) {
  				res = -EOPNOTSUPP;

  				break;

  			}

  			res = dest_name_check(dest, m);
  			if (res)

  				break;

  			res = tipc_port_mcast_xmit(port,

  						   &dest->addr.nameseq,
  						   m->msg_iov,
  						   total_len);

  		}
  		if (likely(res != -ELINKCONG)) {

  			if (needs_conn && (res >= 0))

  				sock->state = SS_CONNECTING;

  			break;

  		}

  		res = tipc_wait_for_sndmsg(sock, &timeo);
  		if (res)

  			break;

  	} while (1);

  
  exit:
  	if (iocb)
  		release_sock(sk);
  	return res;

  }

  static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p)
  {
  	struct sock *sk = sock->sk;

  	struct tipc_sock *tsk = tipc_sk(sk);
  	struct tipc_port *port = &tsk->port;

  	DEFINE_WAIT(wait);
  	int done;
  
  	do {
  		int err = sock_error(sk);
  		if (err)
  			return err;
  		if (sock->state == SS_DISCONNECTING)
  			return -EPIPE;
  		else if (sock->state != SS_CONNECTED)
  			return -ENOTCONN;
  		if (!*timeo_p)
  			return -EAGAIN;
  		if (signal_pending(current))
  			return sock_intr_errno(*timeo_p);
  
  		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
  		done = sk_wait_event(sk, timeo_p,

  				     (!port->congested || !port->connected));

  		finish_wait(sk_sleep(sk), &wait);
  	} while (!done);
  	return 0;
  }

  /**

   * tipc_send_packet - send a connection-oriented message

   * @iocb: if NULL, indicates that socket lock is already held

   * @sock: socket structure
   * @m: message to send

   * @total_len: length of message

   *

   * Used for SOCK_SEQPACKET messages and SOCK_STREAM data.

   *

   * Returns the number of bytes sent on success, or errno otherwise
   */

  static int tipc_send_packet(struct kiocb *iocb, struct socket *sock,
  			    struct msghdr *m, size_t total_len)

  {

  	struct sock *sk = sock->sk;

  	struct tipc_sock *tsk = tipc_sk(sk);

  	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);

  	int res = -EINVAL;
  	long timeo;

  
  	/* Handle implied connection establishment */

  	if (unlikely(dest))

  		return tipc_sendmsg(iocb, sock, m, total_len);

  	if (total_len > TIPC_MAX_USER_MSG_SIZE)

  		return -EMSGSIZE;

  	if (iocb)
  		lock_sock(sk);

  	if (unlikely(sock->state != SS_CONNECTED)) {
  		if (sock->state == SS_DISCONNECTING)
  			res = -EPIPE;
  		else
  			res = -ENOTCONN;
  		goto exit;
  	}

  	timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);

  	do {

  		res = tipc_send(&tsk->port, m->msg_iov, total_len);

  		if (likely(res != -ELINKCONG))

  			break;

  		res = tipc_wait_for_sndpkt(sock, &timeo);
  		if (res)

  			break;

  	} while (1);

  exit:

  	if (iocb)
  		release_sock(sk);
  	return res;

  }

  /**

   * tipc_send_stream - send stream-oriented data

   * @iocb: (unused)
   * @sock: socket structure
   * @m: data to send
   * @total_len: total length of data to be sent

   *

   * Used for SOCK_STREAM data.

   *
   * Returns the number of bytes sent on success (or partial success),

   * or errno if no data sent

   */

  static int tipc_send_stream(struct kiocb *iocb, struct socket *sock,
  			    struct msghdr *m, size_t total_len)

  {

  	struct sock *sk = sock->sk;

  	struct tipc_sock *tsk = tipc_sk(sk);

  	struct msghdr my_msg;
  	struct iovec my_iov;
  	struct iovec *curr_iov;
  	int curr_iovlen;
  	char __user *curr_start;

  	u32 hdr_size;

  	int curr_left;
  	int bytes_to_send;

  	int bytes_sent;

  	int res;

  	lock_sock(sk);

  	/* Handle special cases where there is no connection */

  	if (unlikely(sock->state != SS_CONNECTED)) {

  		if (sock->state == SS_UNCONNECTED)

  			res = tipc_send_packet(NULL, sock, m, total_len);

  		else
  			res = sock->state == SS_DISCONNECTING ? -EPIPE : -ENOTCONN;

  		goto exit;

  	}

  	if (unlikely(m->msg_name)) {
  		res = -EISCONN;
  		goto exit;
  	}

  	if (total_len > (unsigned int)INT_MAX) {

  		res = -EMSGSIZE;
  		goto exit;
  	}

  	/*

  	 * Send each iovec entry using one or more messages
  	 *

  	 * Note: This algorithm is good for the most likely case

  	 * (i.e. one large iovec entry), but could be improved to pass sets
  	 * of small iovec entries into send_packet().
  	 */

  	curr_iov = m->msg_iov;
  	curr_iovlen = m->msg_iovlen;

  	my_msg.msg_iov = &my_iov;
  	my_msg.msg_iovlen = 1;

  	my_msg.msg_flags = m->msg_flags;
  	my_msg.msg_name = NULL;

  	bytes_sent = 0;

  	hdr_size = msg_hdr_sz(&tsk->port.phdr);

  	while (curr_iovlen--) {
  		curr_start = curr_iov->iov_base;
  		curr_left = curr_iov->iov_len;
  
  		while (curr_left) {

  			bytes_to_send = tsk->port.max_pkt - hdr_size;

  			if (bytes_to_send > TIPC_MAX_USER_MSG_SIZE)
  				bytes_to_send = TIPC_MAX_USER_MSG_SIZE;
  			if (curr_left < bytes_to_send)
  				bytes_to_send = curr_left;

  			my_iov.iov_base = curr_start;
  			my_iov.iov_len = bytes_to_send;

  			res = tipc_send_packet(NULL, sock, &my_msg,
  					       bytes_to_send);

  			if (res < 0) {

  				if (bytes_sent)

  					res = bytes_sent;

  				goto exit;

  			}

  			curr_left -= bytes_to_send;
  			curr_start += bytes_to_send;

  			bytes_sent += bytes_to_send;

  		}
  
  		curr_iov++;
  	}

  	res = bytes_sent;
  exit:
  	release_sock(sk);
  	return res;

  }
  
  /**
   * auto_connect - complete connection setup to a remote port

   * @tsk: tipc socket structure

   * @msg: peer's response message

   *

   * Returns 0 on success, errno otherwise
   */

  static int auto_connect(struct tipc_sock *tsk, struct tipc_msg *msg)

  {

  	struct tipc_port *port = &tsk->port;
  	struct socket *sock = tsk->sk.sk_socket;

  	struct tipc_portid peer;
  
  	peer.ref = msg_origport(msg);
  	peer.node = msg_orignode(msg);

  	__tipc_port_connect(port->ref, port, &peer);

  
  	if (msg_importance(msg) > TIPC_CRITICAL_IMPORTANCE)
  		return -EINVAL;

  	msg_set_importance(&port->phdr, (u32)msg_importance(msg));

  	sock->state = SS_CONNECTED;
  	return 0;
  }
  
  /**
   * set_orig_addr - capture sender's address for received message
   * @m: descriptor for message info
   * @msg: received message header

   *

   * Note: Address is not captured if not requested by receiver.
   */

  static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg)

  {

  	DECLARE_SOCKADDR(struct sockaddr_tipc *, addr, m->msg_name);

  	if (addr) {

  		addr->family = AF_TIPC;
  		addr->addrtype = TIPC_ADDR_ID;

  		memset(&addr->addr, 0, sizeof(addr->addr));

  		addr->addr.id.ref = msg_origport(msg);
  		addr->addr.id.node = msg_orignode(msg);

  		addr->addr.name.domain = 0;	/* could leave uninitialized */
  		addr->scope = 0;		/* could leave uninitialized */

  		m->msg_namelen = sizeof(struct sockaddr_tipc);
  	}
  }
  
  /**

   * anc_data_recv - optionally capture ancillary data for received message

   * @m: descriptor for message info
   * @msg: received message header
   * @tport: TIPC port associated with message

   *

   * Note: Ancillary data is not captured if not requested by receiver.

   *

   * Returns 0 if successful, otherwise errno
   */

  static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg,

  			 struct tipc_port *tport)

  {
  	u32 anc_data[3];
  	u32 err;
  	u32 dest_type;

  	int has_name;

  	int res;
  
  	if (likely(m->msg_controllen == 0))
  		return 0;
  
  	/* Optionally capture errored message object(s) */

  	err = msg ? msg_errcode(msg) : 0;
  	if (unlikely(err)) {
  		anc_data[0] = err;
  		anc_data[1] = msg_data_sz(msg);

  		res = put_cmsg(m, SOL_TIPC, TIPC_ERRINFO, 8, anc_data);
  		if (res)

  			return res;

  		if (anc_data[1]) {
  			res = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, anc_data[1],
  				       msg_data(msg));
  			if (res)
  				return res;
  		}

  	}
  
  	/* Optionally capture message destination object */

  	dest_type = msg ? msg_type(msg) : TIPC_DIRECT_MSG;
  	switch (dest_type) {
  	case TIPC_NAMED_MSG:

  		has_name = 1;

  		anc_data[0] = msg_nametype(msg);
  		anc_data[1] = msg_namelower(msg);
  		anc_data[2] = msg_namelower(msg);
  		break;
  	case TIPC_MCAST_MSG:

  		has_name = 1;

  		anc_data[0] = msg_nametype(msg);
  		anc_data[1] = msg_namelower(msg);
  		anc_data[2] = msg_nameupper(msg);
  		break;
  	case TIPC_CONN_MSG:

  		has_name = (tport->conn_type != 0);

  		anc_data[0] = tport->conn_type;
  		anc_data[1] = tport->conn_instance;
  		anc_data[2] = tport->conn_instance;
  		break;
  	default:

  		has_name = 0;

  	}

  	if (has_name) {
  		res = put_cmsg(m, SOL_TIPC, TIPC_DESTNAME, 12, anc_data);
  		if (res)
  			return res;
  	}

  
  	return 0;
  }

  static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)

  {
  	struct sock *sk = sock->sk;
  	DEFINE_WAIT(wait);

  	long timeo = *timeop;

  	int err;
  
  	for (;;) {
  		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);

  		if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {

  			if (sock->state == SS_DISCONNECTING) {
  				err = -ENOTCONN;
  				break;
  			}
  			release_sock(sk);
  			timeo = schedule_timeout(timeo);
  			lock_sock(sk);
  		}
  		err = 0;
  		if (!skb_queue_empty(&sk->sk_receive_queue))
  			break;
  		err = sock_intr_errno(timeo);
  		if (signal_pending(current))
  			break;
  		err = -EAGAIN;
  		if (!timeo)
  			break;
  	}
  	finish_wait(sk_sleep(sk), &wait);

  	*timeop = timeo;

  	return err;
  }

  /**

   * tipc_recvmsg - receive packet-oriented message

   * @iocb: (unused)
   * @m: descriptor for message info
   * @buf_len: total size of user buffer area
   * @flags: receive flags

   *

   * Used for SOCK_DGRAM, SOCK_RDM, and SOCK_SEQPACKET messages.
   * If the complete message doesn't fit in user area, truncate it.
   *
   * Returns size of returned message data, errno otherwise
   */

  static int tipc_recvmsg(struct kiocb *iocb, struct socket *sock,
  			struct msghdr *m, size_t buf_len, int flags)

  {

  	struct sock *sk = sock->sk;

  	struct tipc_sock *tsk = tipc_sk(sk);
  	struct tipc_port *port = &tsk->port;

  	struct sk_buff *buf;
  	struct tipc_msg *msg;

  	long timeo;

  	unsigned int sz;
  	u32 err;
  	int res;

  	/* Catch invalid receive requests */

  	if (unlikely(!buf_len))
  		return -EINVAL;

  	lock_sock(sk);

  	if (unlikely(sock->state == SS_UNCONNECTED)) {
  		res = -ENOTCONN;

  		goto exit;
  	}

  	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);

  restart:

  	/* Look for a message in receive queue; wait if necessary */

  	res = tipc_wait_for_rcvmsg(sock, &timeo);

  	if (res)
  		goto exit;

  	/* Look at first message in receive queue */

  	buf = skb_peek(&sk->sk_receive_queue);

  	msg = buf_msg(buf);
  	sz = msg_data_sz(msg);
  	err = msg_errcode(msg);

  	/* Discard an empty non-errored message & try again */

  	if ((!sz) && (!err)) {

  		advance_rx_queue(sk);

  		goto restart;
  	}
  
  	/* Capture sender's address (optional) */

  	set_orig_addr(m, msg);
  
  	/* Capture ancillary data (optional) */

  	res = anc_data_recv(m, msg, port);

  	if (res)

  		goto exit;
  
  	/* Capture message data (if valid) & compute return value (always) */

  	if (!err) {
  		if (unlikely(buf_len < sz)) {
  			sz = buf_len;
  			m->msg_flags |= MSG_TRUNC;
  		}

  		res = skb_copy_datagram_iovec(buf, msg_hdr_sz(msg),
  					      m->msg_iov, sz);
  		if (res)

  			goto exit;

  		res = sz;
  	} else {
  		if ((sock->state == SS_READY) ||
  		    ((err == TIPC_CONN_SHUTDOWN) || m->msg_control))
  			res = 0;
  		else
  			res = -ECONNRESET;
  	}
  
  	/* Consume received message (optional) */

  	if (likely(!(flags & MSG_PEEK))) {

  		if ((sock->state != SS_READY) &&

  		    (++port->conn_unacked >= TIPC_CONNACK_INTV))

  			tipc_acknowledge(port->ref, port->conn_unacked);

  		advance_rx_queue(sk);

  	}

  exit:

  	release_sock(sk);

  	return res;
  }

  /**

   * tipc_recv_stream - receive stream-oriented data

   * @iocb: (unused)
   * @m: descriptor for message info
   * @buf_len: total size of user buffer area
   * @flags: receive flags

   *
   * Used for SOCK_STREAM messages only.  If not enough data is available

   * will optionally wait for more; never truncates data.
   *
   * Returns size of returned message data, errno otherwise
   */

  static int tipc_recv_stream(struct kiocb *iocb, struct socket *sock,
  			    struct msghdr *m, size_t buf_len, int flags)

  {

  	struct sock *sk = sock->sk;

  	struct tipc_sock *tsk = tipc_sk(sk);
  	struct tipc_port *port = &tsk->port;

  	struct sk_buff *buf;
  	struct tipc_msg *msg;

  	long timeo;

  	unsigned int sz;

  	int sz_to_copy, target, needed;

  	int sz_copied = 0;

  	u32 err;

  	int res = 0;

  	/* Catch invalid receive attempts */

  	if (unlikely(!buf_len))
  		return -EINVAL;

  	lock_sock(sk);

  	if (unlikely(sock->state == SS_UNCONNECTED)) {

  		res = -ENOTCONN;

  		goto exit;
  	}

  	target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len);

  	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);

  restart:

  	/* Look for a message in receive queue; wait if necessary */

  	res = tipc_wait_for_rcvmsg(sock, &timeo);

  	if (res)
  		goto exit;

  	/* Look at first message in receive queue */

  	buf = skb_peek(&sk->sk_receive_queue);

  	msg = buf_msg(buf);
  	sz = msg_data_sz(msg);
  	err = msg_errcode(msg);
  
  	/* Discard an empty non-errored message & try again */

  	if ((!sz) && (!err)) {

  		advance_rx_queue(sk);

  		goto restart;
  	}
  
  	/* Optionally capture sender's address & ancillary data of first msg */

  	if (sz_copied == 0) {
  		set_orig_addr(m, msg);

  		res = anc_data_recv(m, msg, port);

  		if (res)

  			goto exit;
  	}
  
  	/* Capture message data (if valid) & compute return value (always) */

  	if (!err) {

  		u32 offset = (u32)(unsigned long)(TIPC_SKB_CB(buf)->handle);

  		sz -= offset;

  		needed = (buf_len - sz_copied);
  		sz_to_copy = (sz <= needed) ? sz : needed;

  
  		res = skb_copy_datagram_iovec(buf, msg_hdr_sz(msg) + offset,
  					      m->msg_iov, sz_to_copy);
  		if (res)

  			goto exit;

  		sz_copied += sz_to_copy;
  
  		if (sz_to_copy < sz) {
  			if (!(flags & MSG_PEEK))

  				TIPC_SKB_CB(buf)->handle =
  				(void *)(unsigned long)(offset + sz_to_copy);

  			goto exit;
  		}

  	} else {
  		if (sz_copied != 0)
  			goto exit; /* can't add error msg to valid data */
  
  		if ((err == TIPC_CONN_SHUTDOWN) || m->msg_control)
  			res = 0;
  		else
  			res = -ECONNRESET;
  	}
  
  	/* Consume received message (optional) */

  	if (likely(!(flags & MSG_PEEK))) {

  		if (unlikely(++port->conn_unacked >= TIPC_CONNACK_INTV))

  			tipc_acknowledge(port->ref, port->conn_unacked);

  		advance_rx_queue(sk);

  	}

  
  	/* Loop around if more data is required */

  	if ((sz_copied < buf_len) &&	/* didn't get all requested data */
  	    (!skb_queue_empty(&sk->sk_receive_queue) ||

  	    (sz_copied < target)) &&	/* and more is ready or required */

  	    (!(flags & MSG_PEEK)) &&	/* and aren't just peeking at data */
  	    (!err))			/* and haven't reached a FIN */

  		goto restart;
  
  exit:

  	release_sock(sk);

  	return sz_copied ? sz_copied : res;

  }
  
  /**

   * tipc_write_space - wake up thread if port congestion is released
   * @sk: socket
   */
  static void tipc_write_space(struct sock *sk)
  {
  	struct socket_wq *wq;
  
  	rcu_read_lock();
  	wq = rcu_dereference(sk->sk_wq);
  	if (wq_has_sleeper(wq))
  		wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
  						POLLWRNORM | POLLWRBAND);
  	rcu_read_unlock();
  }
  
  /**
   * tipc_data_ready - wake up threads to indicate messages have been received
   * @sk: socket
   * @len: the length of messages
   */

  static void tipc_data_ready(struct sock *sk)

  {
  	struct socket_wq *wq;
  
  	rcu_read_lock();
  	wq = rcu_dereference(sk->sk_wq);
  	if (wq_has_sleeper(wq))
  		wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
  						POLLRDNORM | POLLRDBAND);
  	rcu_read_unlock();
  }
  
  /**

   * filter_connect - Handle all incoming messages for a connection-based socket

   * @tsk: TIPC socket

   * @msg: message
   *

   * Returns 0 (TIPC_OK) if everyting ok, -TIPC_ERR_NO_PORT otherwise

   */

  static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf)

  {

  	struct sock *sk = &tsk->sk;
  	struct tipc_port *port = &tsk->port;

  	struct socket *sock = sk->sk_socket;

  	struct tipc_msg *msg = buf_msg(*buf);

  	int retval = -TIPC_ERR_NO_PORT;

  	int res;

  
  	if (msg_mcast(msg))
  		return retval;
  
  	switch ((int)sock->state) {
  	case SS_CONNECTED:
  		/* Accept only connection-based messages sent by peer */

  		if (msg_connected(msg) && tipc_port_peer_msg(port, msg)) {

  			if (unlikely(msg_errcode(msg))) {
  				sock->state = SS_DISCONNECTING;

  				__tipc_port_disconnect(port);

  			}
  			retval = TIPC_OK;
  		}
  		break;
  	case SS_CONNECTING:
  		/* Accept only ACK or NACK message */

  		if (unlikely(msg_errcode(msg))) {
  			sock->state = SS_DISCONNECTING;

  			sk->sk_err = ECONNREFUSED;

  			retval = TIPC_OK;
  			break;
  		}
  
  		if (unlikely(!msg_connected(msg)))
  			break;

  		res = auto_connect(tsk, msg);

  		if (res) {
  			sock->state = SS_DISCONNECTING;

  			sk->sk_err = -res;

  			retval = TIPC_OK;

  			break;
  		}
  
  		/* If an incoming message is an 'ACK-', it should be
  		 * discarded here because it doesn't contain useful
  		 * data. In addition, we should try to wake up
  		 * connect() routine if sleeping.
  		 */
  		if (msg_data_sz(msg) == 0) {
  			kfree_skb(*buf);
  			*buf = NULL;
  			if (waitqueue_active(sk_sleep(sk)))
  				wake_up_interruptible(sk_sleep(sk));
  		}
  		retval = TIPC_OK;

  		break;
  	case SS_LISTENING:
  	case SS_UNCONNECTED:
  		/* Accept only SYN message */
  		if (!msg_connected(msg) && !(msg_errcode(msg)))
  			retval = TIPC_OK;
  		break;
  	case SS_DISCONNECTING:
  		break;
  	default:
  		pr_err("Unknown socket state %u
  ", sock->state);
  	}
  	return retval;
  }
  
  /**

   * rcvbuf_limit - get proper overload limit of socket receive queue
   * @sk: socket
   * @buf: message
   *
   * For all connection oriented messages, irrespective of importance,
   * the default overload value (i.e. 67MB) is set as limit.
   *
   * For all connectionless messages, by default new queue limits are
   * as belows:
   *

   * TIPC_LOW_IMPORTANCE       (4 MB)
   * TIPC_MEDIUM_IMPORTANCE    (8 MB)
   * TIPC_HIGH_IMPORTANCE      (16 MB)
   * TIPC_CRITICAL_IMPORTANCE  (32 MB)

   *
   * Returns overload limit according to corresponding message importance
   */
  static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf)
  {
  	struct tipc_msg *msg = buf_msg(buf);

  
  	if (msg_connected(msg))

  		return sysctl_tipc_rmem[2];
  
  	return sk->sk_rcvbuf >> TIPC_CRITICAL_IMPORTANCE <<
  		msg_importance(msg);

  }
  
  /**

   * filter_rcv - validate incoming message
   * @sk: socket

   * @buf: message

   *

   * Enqueues message on receive queue if acceptable; optionally handles
   * disconnect indication for a connected socket.
   *
   * Called with socket lock already taken; port lock may also be taken.

   *

   * Returns 0 (TIPC_OK) if message was consumed, -TIPC error code if message
   * to be rejected.

   */

  static int filter_rcv(struct sock *sk, struct sk_buff *buf)

  {

  	struct socket *sock = sk->sk_socket;

  	struct tipc_sock *tsk = tipc_sk(sk);

  	struct tipc_msg *msg = buf_msg(buf);

  	unsigned int limit = rcvbuf_limit(sk, buf);

  	int rc = TIPC_OK;

  	/* Reject message if it is wrong sort of message for socket */

  	if (msg_type(msg) > TIPC_DIRECT_MSG)

  		return -TIPC_ERR_NO_PORT;

  	if (sock->state == SS_READY) {

  		if (msg_connected(msg))

  			return -TIPC_ERR_NO_PORT;

  	} else {

  		rc = filter_connect(tsk, &buf);
  		if (rc != TIPC_OK || buf == NULL)
  			return rc;

  	}
  
  	/* Reject message if there isn't room to queue it */

  	if (sk_rmem_alloc_get(sk) + buf->truesize >= limit)

  		return -TIPC_ERR_OVERLOAD;

  	/* Enqueue message */

  	TIPC_SKB_CB(buf)->handle = NULL;

  	__skb_queue_tail(&sk->sk_receive_queue, buf);