socket.c

/*
 * net/tipc/socket.c: TIPC socket API
 *
 * Copyright (c) 2001-2007, 2012-2016, 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 <linux/rhashtable.h>
#include "core.h"
#include "name_table.h"
#include "node.h"
#include "link.h"
#include "name_distr.h"
#include "socket.h"
#include "bcast.h"
#include "netlink.h"

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

#define CONN_TIMEOUT_DEFAULT	8000	/* default connect timeout = 8s */
#define CONN_PROBING_INTERVAL	msecs_to_jiffies(3600000)  /* [ms] => 1 h */
#define TIPC_FWD_MSG		1
#define TIPC_CONN_OK		0
#define TIPC_CONN_PROBING	1
#define TIPC_MAX_PORT		0xffffffff
#define TIPC_MIN_PORT		1

/**
 * struct tipc_sock - TIPC socket structure
 * @sk: socket - interacts with 'port' and with user via the socket API
 * @connected: non-zero if port is currently connected to a peer port
 * @conn_type: TIPC type used when connection was established
 * @conn_instance: TIPC instance used when connection was established
 * @published: non-zero if port has one or more associated names
 * @max_pkt: maximum packet size "hint" used when building messages sent by port
 * @portid: unique port identity in TIPC socket hash table
 * @phdr: preformatted message header used when sending messages
 * @port_list: adjacent ports in TIPC's global list of ports
 * @publications: list of publications for port
 * @pub_count: total # of publications port has made during its lifetime
 * @probing_state:
 * @probing_intv:
 * @conn_timeout: the time we can wait for an unresponded setup request
 * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
 * @link_cong: non-zero if owner must sleep because of link congestion
 * @sent_unacked: # messages sent by socket, and not yet acked by peer
 * @rcv_unacked: # messages read by user, but not yet acked back to peer
 * @remote: 'connected' peer for dgram/rdm
 * @node: hash table node
 * @rcu: rcu struct for tipc_sock
 */
struct tipc_sock {
	struct sock sk;
	int connected;
	u32 conn_type;
	u32 conn_instance;
	int published;
	u32 max_pkt;
	u32 portid;
	struct tipc_msg phdr;
	struct list_head sock_list;
	struct list_head publications;
	u32 pub_count;
	u32 probing_state;
	unsigned long probing_intv;
	uint conn_timeout;
	atomic_t dupl_rcvcnt;
	bool link_cong;
	u16 snt_unacked;
	u16 snd_win;
	u16 peer_caps;
	u16 rcv_unacked;
	u16 rcv_win;
	struct sockaddr_tipc remote;
	struct rhash_head node;
	struct rcu_head rcu;
};

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 void tipc_sock_destruct(struct sock *sk);
static int tipc_release(struct socket *sock);
static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p);
static void tipc_sk_timeout(unsigned long data);
static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
			   struct tipc_name_seq const *seq);
static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
			    struct tipc_name_seq const *seq);
static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid);
static int tipc_sk_insert(struct tipc_sock *tsk);
static void tipc_sk_remove(struct tipc_sock *tsk);
static int __tipc_send_stream(struct socket *sock, struct msghdr *m,
			      size_t dsz);
static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz);

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 const struct rhashtable_params tsk_rht_params;

static u32 tsk_own_node(struct tipc_sock *tsk)
{
	return msg_prevnode(&tsk->phdr);
}

static u32 tsk_peer_node(struct tipc_sock *tsk)
{
	return msg_destnode(&tsk->phdr);
}

static u32 tsk_peer_port(struct tipc_sock *tsk)
{
	return msg_destport(&tsk->phdr);
}

static  bool tsk_unreliable(struct tipc_sock *tsk)
{
	return msg_src_droppable(&tsk->phdr) != 0;
}

static void tsk_set_unreliable(struct tipc_sock *tsk, bool unreliable)
{
	msg_set_src_droppable(&tsk->phdr, unreliable ? 1 : 0);
}

static bool tsk_unreturnable(struct tipc_sock *tsk)
{
	return msg_dest_droppable(&tsk->phdr) != 0;
}

static void tsk_set_unreturnable(struct tipc_sock *tsk, bool unreturnable)
{
	msg_set_dest_droppable(&tsk->phdr, unreturnable ? 1 : 0);
}

static int tsk_importance(struct tipc_sock *tsk)
{
	return msg_importance(&tsk->phdr);
}

static int tsk_set_importance(struct tipc_sock *tsk, int imp)
{
	if (imp > TIPC_CRITICAL_IMPORTANCE)
		return -EINVAL;
	msg_set_importance(&tsk->phdr, (u32)imp);
	return 0;
}

static struct tipc_sock *tipc_sk(const struct sock *sk)
{
	return container_of(sk, struct tipc_sock, sk);
}

static bool tsk_conn_cong(struct tipc_sock *tsk)
{
	return tsk->snt_unacked >= tsk->snd_win;
}

/* tsk_blocks(): translate a buffer size in bytes to number of
 * advertisable blocks, taking into account the ratio truesize(len)/len
 * We can trust that this ratio is always < 4 for len >= FLOWCTL_BLK_SZ
 */
static u16 tsk_adv_blocks(int len)
{
	return len / FLOWCTL_BLK_SZ / 4;
}

/* tsk_inc(): increment counter for sent or received data
 * - If block based flow control is not supported by peer we
 *   fall back to message based ditto, incrementing the counter
 */
static u16 tsk_inc(struct tipc_sock *tsk, int msglen)
{
	if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL))
		return ((msglen / FLOWCTL_BLK_SZ) + 1);
	return 1;
}

/**
 * tsk_advance_rx_queue - discard first buffer in socket receive queue
 *
 * Caller must hold socket lock
 */
static void tsk_advance_rx_queue(struct sock *sk)
{
	kfree_skb(__skb_dequeue(&sk->sk_receive_queue));
}

/* tipc_sk_respond() : send response message back to sender
 */
static void tipc_sk_respond(struct sock *sk, struct sk_buff *skb, int err)
{
	u32 selector;
	u32 dnode;
	u32 onode = tipc_own_addr(sock_net(sk));

	if (!tipc_msg_reverse(onode, &skb, err))
		return;

	dnode = msg_destnode(buf_msg(skb));
	selector = msg_origport(buf_msg(skb));
	tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
}

/**
 * tsk_rej_rx_queue - reject all buffers in socket receive queue
 *
 * Caller must hold socket lock
 */
static void tsk_rej_rx_queue(struct sock *sk)
{
	struct sk_buff *skb;

	while ((skb = __skb_dequeue(&sk->sk_receive_queue)))
		tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT);
}

/* tsk_peer_msg - verify if message was sent by connected port's peer
 *
 * Handles cases where the node's network address has changed from
 * the default of <0.0.0> to its configured setting.
 */
static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
{
	struct tipc_net *tn = net_generic(sock_net(&tsk->sk), tipc_net_id);
	u32 peer_port = tsk_peer_port(tsk);
	u32 orig_node;
	u32 peer_node;

	if (unlikely(!tsk->connected))
		return false;

	if (unlikely(msg_origport(msg) != peer_port))
		return false;

	orig_node = msg_orignode(msg);
	peer_node = tsk_peer_node(tsk);

	if (likely(orig_node == peer_node))
		return true;

	if (!orig_node && (peer_node == tn->own_addr))
		return true;

	if (!peer_node && (orig_node == tn->own_addr))
		return true;

	return false;
}

/**
 * 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)
{
	struct tipc_net *tn;
	const struct proto_ops *ops;
	socket_state state;
	struct sock *sk;
	struct tipc_sock *tsk;
	struct tipc_msg *msg;

	/* 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 */
	sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto, kern);
	if (sk == NULL)
		return -ENOMEM;

	tsk = tipc_sk(sk);
	tsk->max_pkt = MAX_PKT_DEFAULT;
	INIT_LIST_HEAD(&tsk->publications);
	msg = &tsk->phdr;
	tn = net_generic(sock_net(sk), tipc_net_id);
	tipc_msg_init(tn->own_addr, msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG,
		      NAMED_H_SIZE, 0);

	/* Finish initializing socket data structures */
	sock->ops = ops;
	sock->state = state;
	sock_init_data(sock, sk);
	if (tipc_sk_insert(tsk)) {
		pr_warn("Socket create failed; port number exhausted\n");
		return -EINVAL;
	}
	msg_set_origport(msg, tsk->portid);
	setup_timer(&sk->sk_timer, tipc_sk_timeout, (unsigned long)tsk);
	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;
	sk->sk_destruct = tipc_sock_destruct;
	tsk->conn_timeout = CONN_TIMEOUT_DEFAULT;
	atomic_set(&tsk->dupl_rcvcnt, 0);

	/* Start out with safe limits until we receive an advertised window */
	tsk->snd_win = tsk_adv_blocks(RCVBUF_MIN);
	tsk->rcv_win = tsk->snd_win;

	if (sock->state == SS_READY) {
		tsk_set_unreturnable(tsk, true);
		if (sock->type == SOCK_DGRAM)
			tsk_set_unreliable(tsk, true);
	}
	return 0;
}

static void tipc_sk_callback(struct rcu_head *head)
{
	struct tipc_sock *tsk = container_of(head, struct tipc_sock, rcu);

	sock_put(&tsk->sk);
}

/**
 * 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 net *net;
	struct tipc_sock *tsk;
	struct sk_buff *skb;
	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;

	net = sock_net(sk);
	tsk = tipc_sk(sk);
	lock_sock(sk);

	/*
	 * Reject all unreceived messages, except on an active connection
	 * (which disconnects locally & sends a 'FIN+' to peer)
	 */
	dnode = tsk_peer_node(tsk);
	while (sock->state != SS_DISCONNECTING) {
		skb = __skb_dequeue(&sk->sk_receive_queue);
		if (skb == NULL)
			break;
		if (TIPC_SKB_CB(skb)->handle != NULL)
			kfree_skb(skb);
		else {
			if ((sock->state == SS_CONNECTING) ||
			    (sock->state == SS_CONNECTED)) {
				sock->state = SS_DISCONNECTING;
				tsk->connected = 0;
				tipc_node_remove_conn(net, dnode, tsk->portid);
			}
			tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT);
		}
	}

	tipc_sk_withdraw(tsk, 0, NULL);
	sk_stop_timer(sk, &sk->sk_timer);
	tipc_sk_remove(tsk);
	if (tsk->connected) {
		skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
				      TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
				      tsk_own_node(tsk), tsk_peer_port(tsk),
				      tsk->portid, TIPC_ERR_NO_PORT);
		if (skb)
			tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
		tipc_node_remove_conn(net, dnode, tsk->portid);
	}

	/* Reject any messages that accumulated in backlog queue */
	sock->state = SS_DISCONNECTING;
	release_sock(sk);

	call_rcu(&tsk->rcu, tipc_sk_callback);
	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_sk_withdraw(tsk, 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_sk_publish(tsk, addr->scope, &addr->addr.nameseq) :
		tipc_sk_withdraw(tsk, -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);
	struct tipc_net *tn = net_generic(sock_net(sock->sk), tipc_net_id);

	memset(addr, 0, sizeof(*addr));
	if (peer) {
		if ((sock->state != SS_CONNECTED) &&
			((peer != 2) || (sock->state != SS_DISCONNECTING)))
			return -ENOTCONN;
		addr->addr.id.ref = tsk_peer_port(tsk);
		addr->addr.id.node = tsk_peer_node(tsk);
	} else {
		addr->addr.id.ref = tsk->portid;
		addr->addr.id.node = tn->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->link_cong)
			mask |= POLLOUT;
		break;
	case SS_READY:
	case SS_CONNECTED:
		if (!tsk->link_cong && !tsk_conn_cong(tsk))
			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;
}

/**
 * tipc_sendmcast - send multicast message
 * @sock: socket structure
 * @seq: destination address
 * @msg: message to send
 * @dsz: total length of message data
 * @timeo: timeout to wait for wakeup
 *
 * Called from function tipc_sendmsg(), which has done all sanity checks
 * Returns the number of bytes sent on success, or errno
 */
static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
			  struct msghdr *msg, size_t dsz, long timeo)
{
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct net *net = sock_net(sk);
	struct tipc_msg *mhdr = &tsk->phdr;
	struct sk_buff_head pktchain;
	struct iov_iter save = msg->msg_iter;
	uint mtu;
	int rc;

	msg_set_type(mhdr, TIPC_MCAST_MSG);
	msg_set_lookup_scope(mhdr, TIPC_CLUSTER_SCOPE);
	msg_set_destport(mhdr, 0);
	msg_set_destnode(mhdr, 0);
	msg_set_nametype(mhdr, seq->type);
	msg_set_namelower(mhdr, seq->lower);
	msg_set_nameupper(mhdr, seq->upper);
	msg_set_hdr_sz(mhdr, MCAST_H_SIZE);

	skb_queue_head_init(&pktchain);

new_mtu:
	mtu = tipc_bcast_get_mtu(net);
	rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, &pktchain);
	if (unlikely(rc < 0))
		return rc;

	do {
		rc = tipc_bcast_xmit(net, &pktchain);
		if (likely(!rc))
			return dsz;

		if (rc == -ELINKCONG) {
			tsk->link_cong = 1;
			rc = tipc_wait_for_sndmsg(sock, &timeo);
			if (!rc)
				continue;
		}
		__skb_queue_purge(&pktchain);
		if (rc == -EMSGSIZE) {
			msg->msg_iter = save;
			goto new_mtu;
		}
		break;
	} while (1);
	return rc;
}

/**
 * tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets
 * @arrvq: queue with arriving messages, to be cloned after destination lookup
 * @inputq: queue with cloned messages, delivered to socket after dest lookup
 *
 * Multi-threaded: parallel calls with reference to same queues may occur
 */
void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
		       struct sk_buff_head *inputq)
{
	struct tipc_msg *msg;
	struct tipc_plist dports;
	u32 portid;
	u32 scope = TIPC_CLUSTER_SCOPE;
	struct sk_buff_head tmpq;
	uint hsz;
	struct sk_buff *skb, *_skb;

	__skb_queue_head_init(&tmpq);
	tipc_plist_init(&dports);

	skb = tipc_skb_peek(arrvq, &inputq->lock);
	for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) {
		msg = buf_msg(skb);
		hsz = skb_headroom(skb) + msg_hdr_sz(msg);

		if (in_own_node(net, msg_orignode(msg)))
			scope = TIPC_NODE_SCOPE;

		/* Create destination port list and message clones: */
		tipc_nametbl_mc_translate(net,
					  msg_nametype(msg), msg_namelower(msg),
					  msg_nameupper(msg), scope, &dports);
		portid = tipc_plist_pop(&dports);
		for (; portid; portid = tipc_plist_pop(&dports)) {
			_skb = __pskb_copy(skb, hsz, GFP_ATOMIC);
			if (_skb) {
				msg_set_destport(buf_msg(_skb), portid);
				__skb_queue_tail(&tmpq, _skb);
				continue;
			}
			pr_warn("Failed to clone mcast rcv buffer\n");
		}
		/* Append to inputq if not already done by other thread */
		spin_lock_bh(&inputq->lock);
		if (skb_peek(arrvq) == skb) {
			skb_queue_splice_tail_init(&tmpq, inputq);
			kfree_skb(__skb_dequeue(arrvq));
		}
		spin_unlock_bh(&inputq->lock);
		__skb_queue_purge(&tmpq);
		kfree_skb(skb);
	}
	tipc_sk_rcv(net, inputq);
}

/**
 * tipc_sk_proto_rcv - receive a connection mng protocol message
 * @tsk: receiving socket
 * @skb: pointer to message buffer.
 */
static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
			      struct sk_buff_head *xmitq)
{
	struct sock *sk = &tsk->sk;
	u32 onode = tsk_own_node(tsk);
	struct tipc_msg *hdr = buf_msg(skb);
	int mtyp = msg_type(hdr);
	bool conn_cong;

	/* Ignore if connection cannot be validated: */
	if (!tsk_peer_msg(tsk, hdr))
		goto exit;

	tsk->probing_state = TIPC_CONN_OK;

	if (mtyp == CONN_PROBE) {
		msg_set_type(hdr, CONN_PROBE_REPLY);
		if (tipc_msg_reverse(onode, &skb, TIPC_OK))
			__skb_queue_tail(xmitq, skb);
		return;
	} else if (mtyp == CONN_ACK) {
		conn_cong = tsk_conn_cong(tsk);
		tsk->snt_unacked -= msg_conn_ack(hdr);
		if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL)
			tsk->snd_win = msg_adv_win(hdr);
		if (conn_cong)
			sk->sk_write_space(sk);
	} else if (mtyp != CONN_PROBE_REPLY) {
		pr_warn("Received unknown CONN_PROTO msg\n");
	}
exit:
	kfree_skb(skb);
}

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

/**
 * tipc_sendmsg - send message in connectionless manner
 * @sock: socket structure
 * @m: message to send
 * @dsz: amount of user data to be sent
 *
 * 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 socket *sock,
			struct msghdr *m, size_t dsz)
{
	struct sock *sk = sock->sk;
	int ret;

	lock_sock(sk);
	ret = __tipc_sendmsg(sock, m, dsz);
	release_sock(sk);

	return ret;
}

static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
{
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct net *net = sock_net(sk);
	struct tipc_msg *mhdr = &tsk->phdr;
	u32 dnode, dport;
	struct sk_buff_head pktchain;
	struct sk_buff *skb;
	struct tipc_name_seq *seq;
	struct iov_iter save;
	u32 mtu;
	long timeo;
	int rc;

	if (dsz > TIPC_MAX_USER_MSG_SIZE)
		return -EMSGSIZE;
	if (unlikely(!dest)) {
		if (tsk->connected && sock->state == SS_READY)
			dest = &tsk->remote;
		else
			return -EDESTADDRREQ;
	} else if (unlikely(m->msg_namelen < sizeof(*dest)) ||
		   dest->family != AF_TIPC) {
		return -EINVAL;
	}
	if (unlikely(sock->state != SS_READY)) {
		if (sock->state == SS_LISTENING)
			return -EPIPE;
		if (sock->state != SS_UNCONNECTED)
			return -EISCONN;
		if (tsk->published)
			return -EOPNOTSUPP;
		if (dest->addrtype == TIPC_ADDR_NAME) {
			tsk->conn_type = dest->addr.name.name.type;
			tsk->conn_instance = dest->addr.name.name.instance;
		}
	}
	seq = &dest->addr.nameseq;
	timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);

	if (dest->addrtype == TIPC_ADDR_MCAST) {
		return tipc_sendmcast(sock, seq, m, dsz, timeo);
	} else if (dest->addrtype == TIPC_ADDR_NAME) {
		u32 type = dest->addr.name.name.type;
		u32 inst = dest->addr.name.name.instance;
		u32 domain = dest->addr.name.domain;

		dnode = domain;
		msg_set_type(mhdr, TIPC_NAMED_MSG);
		msg_set_hdr_sz(mhdr, NAMED_H_SIZE);
		msg_set_nametype(mhdr, type);
		msg_set_nameinst(mhdr, inst);
		msg_set_lookup_scope(mhdr, tipc_addr_scope(domain));
		dport = tipc_nametbl_translate(net, type, inst, &dnode);
		msg_set_destnode(mhdr, dnode);
		msg_set_destport(mhdr, dport);
		if (unlikely(!dport && !dnode))
			return -EHOSTUNREACH;
	} else if (dest->addrtype == TIPC_ADDR_ID) {
		dnode = dest->addr.id.node;
		msg_set_type(mhdr, TIPC_DIRECT_MSG);
		msg_set_lookup_scope(mhdr, 0);
		msg_set_destnode(mhdr, dnode);
		msg_set_destport(mhdr, dest->addr.id.ref);
		msg_set_hdr_sz(mhdr, BASIC_H_SIZE);
	}

	skb_queue_head_init(&pktchain);
	save = m->msg_iter;
new_mtu:
	mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
	rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, &pktchain);
	if (rc < 0)
		return rc;

	do {
		skb = skb_peek(&pktchain);
		TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong;
		rc = tipc_node_xmit(net, &pktchain, dnode, tsk->portid);
		if (likely(!rc)) {
			if (sock->state != SS_READY)
				sock->state = SS_CONNECTING;
			return dsz;
		}
		if (rc == -ELINKCONG) {
			tsk->link_cong = 1;
			rc = tipc_wait_for_sndmsg(sock, &timeo);
			if (!rc)
				continue;
		}
		__skb_queue_purge(&pktchain);
		if (rc == -EMSGSIZE) {
			m->msg_iter = save;
			goto new_mtu;
		}
		break;
	} while (1);

	return rc;
}

static int tipc_wait_for_sndpkt(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;
		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,
				     (!tsk->link_cong &&
				      !tsk_conn_cong(tsk)) ||
				     !tsk->connected);
		finish_wait(sk_sleep(sk), &wait);
	} while (!done);
	return 0;
}

/**
 * tipc_send_stream - send stream-oriented data
 * @sock: socket structure
 * @m: data to send
 * @dsz: total length of data to be transmitted
 *
 * 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 socket *sock, struct msghdr *m, size_t dsz)
{
	struct sock *sk = sock->sk;
	int ret;

	lock_sock(sk);
	ret = __tipc_send_stream(sock, m, dsz);
	release_sock(sk);

	return ret;
}

static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
{
	struct sock *sk = sock->sk;
	struct net *net = sock_net(sk);
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_msg *mhdr = &tsk->phdr;
	struct sk_buff_head pktchain;