/net/tipc/socket.c

Large files files are truncated, but you can click here to view the full file

/*
 * net/tipc/socket.c: TIPC socket API
 *
 * Copyright (c) 2001-2007, 2012-2017, 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 <linux/sched/signal.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"
#include "group.h"

#define CONN_TIMEOUT_DEFAULT	8000	/* default connect timeout = 8s */
#define CONN_PROBING_INTV	msecs_to_jiffies(3600000)  /* [ms] => 1 h */
#define TIPC_FWD_MSG		1
#define TIPC_MAX_PORT		0xffffffff
#define TIPC_MIN_PORT		1
#define TIPC_ACK_RATE		4       /* ACK at 1/4 of of rcv window size */

enum {
	TIPC_LISTEN = TCP_LISTEN,
	TIPC_ESTABLISHED = TCP_ESTABLISHED,
	TIPC_OPEN = TCP_CLOSE,
	TIPC_DISCONNECTING = TCP_CLOSE_WAIT,
	TIPC_CONNECTING = TCP_SYN_SENT,
};

struct sockaddr_pair {
	struct sockaddr_tipc sock;
	struct sockaddr_tipc member;
};

/**
 * struct tipc_sock - TIPC socket structure
 * @sk: socket - interacts with 'port' and with user via the socket API
 * @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
 * #cong_links: list of congested links
 * @publications: list of publications for port
 * @blocking_link: address of the congested link we are currently sleeping on
 * @pub_count: total # of publications port has made during its lifetime
 * @probing_state:
 * @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
 * @cong_link_cnt: number of congested links
 * @snt_unacked: # messages sent by socket, and not yet acked by peer
 * @rcv_unacked: # messages read by user, but not yet acked back to peer
 * @peer: 'connected' peer for dgram/rdm
 * @node: hash table node
 * @mc_method: cookie for use between socket and broadcast layer
 * @rcu: rcu struct for tipc_sock
 */
struct tipc_sock {
	struct sock sk;
	u32 conn_type;
	u32 conn_instance;
	int published;
	u32 max_pkt;
	u32 portid;
	struct tipc_msg phdr;
	struct list_head cong_links;
	struct list_head publications;
	u32 pub_count;
	uint conn_timeout;
	atomic_t dupl_rcvcnt;
	bool probe_unacked;
	u16 cong_link_cnt;
	u16 snt_unacked;
	u16 snd_win;
	u16 peer_caps;
	u16 rcv_unacked;
	u16 rcv_win;
	struct sockaddr_tipc peer;
	struct rhash_head node;
	struct tipc_mc_method mc_method;
	struct rcu_head rcu;
	struct tipc_group *group;
};

static int tipc_sk_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,
		       bool kern);
static void tipc_sk_timeout(struct timer_list *t);
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 int tipc_sk_leave(struct tipc_sock *tsk);
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_sendstream(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;
}

static u16 tsk_blocks(int len)
{
	return ((len / FLOWCTL_BLK_SZ) + 1);
}

/* 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);
}

static bool tipc_sk_connected(struct sock *sk)
{
	return sk->sk_state == TIPC_ESTABLISHED;
}

/* tipc_sk_type_connectionless - check if the socket is datagram socket
 * @sk: socket
 *
 * Returns true if connection less, false otherwise
 */
static bool tipc_sk_type_connectionless(struct sock *sk)
{
	return sk->sk_type == SOCK_RDM || sk->sk_type == SOCK_DGRAM;
}

/* 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 sock *sk = &tsk->sk;
	struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id);
	u32 peer_port = tsk_peer_port(tsk);
	u32 orig_node;
	u32 peer_node;

	if (unlikely(!tipc_sk_connected(sk)))
		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_set_sk_state - set the sk_state of the socket
 * @sk: socket
 *
 * Caller must hold socket lock
 *
 * Returns 0 on success, errno otherwise
 */
static int tipc_set_sk_state(struct sock *sk, int state)
{
	int oldsk_state = sk->sk_state;
	int res = -EINVAL;

	switch (state) {
	case TIPC_OPEN:
		res = 0;
		break;
	case TIPC_LISTEN:
	case TIPC_CONNECTING:
		if (oldsk_state == TIPC_OPEN)
			res = 0;
		break;
	case TIPC_ESTABLISHED:
		if (oldsk_state == TIPC_CONNECTING ||
		    oldsk_state == TIPC_OPEN)
			res = 0;
		break;
	case TIPC_DISCONNECTING:
		if (oldsk_state == TIPC_CONNECTING ||
		    oldsk_state == TIPC_ESTABLISHED)
			res = 0;
		break;
	}

	if (!res)
		sk->sk_state = state;

	return res;
}

static int tipc_sk_sock_err(struct socket *sock, long *timeout)
{
	struct sock *sk = sock->sk;
	int err = sock_error(sk);
	int typ = sock->type;

	if (err)
		return err;
	if (typ == SOCK_STREAM || typ == SOCK_SEQPACKET) {
		if (sk->sk_state == TIPC_DISCONNECTING)
			return -EPIPE;
		else if (!tipc_sk_connected(sk))
			return -ENOTCONN;
	}
	if (!*timeout)
		return -EAGAIN;
	if (signal_pending(current))
		return sock_intr_errno(*timeout);

	return 0;
}

#define tipc_wait_for_cond(sock_, timeo_, condition_)			       \
({                                                                             \
	struct sock *sk_;						       \
	int rc_;							       \
									       \
	while ((rc_ = !(condition_))) {					       \
		DEFINE_WAIT_FUNC(wait_, woken_wake_function);	               \
		sk_ = (sock_)->sk;					       \
		rc_ = tipc_sk_sock_err((sock_), timeo_);		       \
		if (rc_)						       \
			break;						       \
		prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE);    \
		release_sock(sk_);					       \
		*(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \
		sched_annotate_sleep();				               \
		lock_sock(sk_);						       \
		remove_wait_queue(sk_sleep(sk_), &wait_);		       \
	}								       \
	rc_;								       \
})

/**
 * 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;
	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;
		break;
	case SOCK_SEQPACKET:
		ops = &packet_ops;
		break;
	case SOCK_DGRAM:
	case SOCK_RDM:
		ops = &msg_ops;
		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);
	INIT_LIST_HEAD(&tsk->cong_links);
	msg = &tsk->phdr;
	tn = net_generic(sock_net(sk), tipc_net_id);

	/* Finish initializing socket data structures */
	sock->ops = ops;
	sock_init_data(sock, sk);
	tipc_set_sk_state(sk, TIPC_OPEN);
	if (tipc_sk_insert(tsk)) {
		pr_warn("Socket create failed; port number exhausted\n");
		return -EINVAL;
	}

	/* Ensure tsk is visible before we read own_addr. */
	smp_mb();

	tipc_msg_init(tn->own_addr, msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG,
		      NAMED_H_SIZE, 0);

	msg_set_origport(msg, tsk->portid);
	timer_setup(&sk->sk_timer, tipc_sk_timeout, 0);
	sk->sk_shutdown = 0;
	sk->sk_backlog_rcv = tipc_sk_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 (tipc_sk_type_connectionless(sk)) {
		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);
}

/* Caller should hold socket lock for the socket. */
static void __tipc_shutdown(struct socket *sock, int error)
{
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct net *net = sock_net(sk);
	long timeout = CONN_TIMEOUT_DEFAULT;
	u32 dnode = tsk_peer_node(tsk);
	struct sk_buff *skb;

	/* Avoid that hi-prio shutdown msgs bypass msgs in link wakeup queue */
	tipc_wait_for_cond(sock, &timeout, (!tsk->cong_link_cnt &&
					    !tsk_conn_cong(tsk)));

	/* Reject all unreceived messages, except on an active connection
	 * (which disconnects locally & sends a 'FIN+' to peer).
	 */
	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		if (TIPC_SKB_CB(skb)->bytes_read) {
			kfree_skb(skb);
			continue;
		}
		if (!tipc_sk_type_connectionless(sk) &&
		    sk->sk_state != TIPC_DISCONNECTING) {
			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
			tipc_node_remove_conn(net, dnode, tsk->portid);
		}
		tipc_sk_respond(sk, skb, error);
	}

	if (tipc_sk_type_connectionless(sk))
		return;

	if (sk->sk_state != TIPC_DISCONNECTING) {
		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, error);
		if (skb)
			tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
		tipc_node_remove_conn(net, dnode, tsk->portid);
		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
	}
}

/**
 * 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;

	/*
	 * 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);
	lock_sock(sk);

	__tipc_shutdown(sock, TIPC_ERR_NO_PORT);
	sk->sk_shutdown = SHUTDOWN_MASK;
	tipc_sk_leave(tsk);
	tipc_sk_withdraw(tsk, 0, NULL);
	sk_stop_timer(sk, &sk->sk_timer);
	tipc_sk_remove(tsk);

	/* Reject any messages that accumulated in backlog queue */
	release_sock(sk);
	tipc_dest_list_purge(&tsk->cong_links);
	tsk->cong_link_cnt = 0;
	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 (tsk->group) {
		res = -EACCES;
		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 sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_net *tn = net_generic(sock_net(sock->sk), tipc_net_id);

	memset(addr, 0, sizeof(*addr));
	if (peer) {
		if ((!tipc_sk_connected(sk)) &&
		    ((peer != 2) || (sk->sk_state != TIPC_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 ...
 *
 * 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);
	struct tipc_group *grp = tsk->group;
	u32 revents = 0;

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

	if (sk->sk_shutdown & RCV_SHUTDOWN)
		revents |= POLLRDHUP | POLLIN | POLLRDNORM;
	if (sk->sk_shutdown == SHUTDOWN_MASK)
		revents |= POLLHUP;

	switch (sk->sk_state) {
	case TIPC_ESTABLISHED:
		if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
			revents |= POLLOUT;
		/* fall thru' */
	case TIPC_LISTEN:
	case TIPC_CONNECTING:
		if (!skb_queue_empty(&sk->sk_receive_queue))
			revents |= POLLIN | POLLRDNORM;
		break;
	case TIPC_OPEN:
		if (!grp || tipc_group_size(grp))
			if (!tsk->cong_link_cnt)
				revents |= POLLOUT;
		if (!tipc_sk_type_connectionless(sk))
			break;
		if (skb_queue_empty(&sk->sk_receive_queue))
			break;
		revents |= POLLIN | POLLRDNORM;
		break;
	case TIPC_DISCONNECTING:
		revents = POLLIN | POLLRDNORM | POLLHUP;
		break;
	}
	return revents;
}

/**
 * tipc_sendmcast - send multicast message
 * @sock: socket structure
 * @seq: destination address
 * @msg: message to send
 * @dlen: length of data to send
 * @timeout: 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 dlen, long timeout)
{
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_msg *hdr = &tsk->phdr;
	struct net *net = sock_net(sk);
	int mtu = tipc_bcast_get_mtu(net);
	struct tipc_mc_method *method = &tsk->mc_method;
	u32 domain = addr_domain(net, TIPC_CLUSTER_SCOPE);
	struct sk_buff_head pkts;
	struct tipc_nlist dsts;
	int rc;

	if (tsk->group)
		return -EACCES;

	/* Block or return if any destination link is congested */
	rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt);
	if (unlikely(rc))
		return rc;

	/* Lookup destination nodes */
	tipc_nlist_init(&dsts, tipc_own_addr(net));
	tipc_nametbl_lookup_dst_nodes(net, seq->type, seq->lower,
				      seq->upper, domain, &dsts);
	if (!dsts.local && !dsts.remote)
		return -EHOSTUNREACH;

	/* Build message header */
	msg_set_type(hdr, TIPC_MCAST_MSG);
	msg_set_hdr_sz(hdr, MCAST_H_SIZE);
	msg_set_lookup_scope(hdr, TIPC_CLUSTER_SCOPE);
	msg_set_destport(hdr, 0);
	msg_set_destnode(hdr, 0);
	msg_set_nametype(hdr, seq->type);
	msg_set_namelower(hdr, seq->lower);
	msg_set_nameupper(hdr, seq->upper);

	/* Build message as chain of buffers */
	skb_queue_head_init(&pkts);
	rc = tipc_msg_build(hdr, msg, 0, dlen, mtu, &pkts);

	/* Send message if build was successful */
	if (unlikely(rc == dlen))
		rc = tipc_mcast_xmit(net, &pkts, method, &dsts,
				     &tsk->cong_link_cnt);

	tipc_nlist_purge(&dsts);

	return rc ? rc : dlen;
}

/**
 * tipc_send_group_msg - send a message to a member in the group
 * @net: network namespace
 * @m: message to send
 * @mb: group member
 * @dnode: destination node
 * @dport: destination port
 * @dlen: total length of message data
 */
static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk,
			       struct msghdr *m, struct tipc_member *mb,
			       u32 dnode, u32 dport, int dlen)
{
	u16 bc_snd_nxt = tipc_group_bc_snd_nxt(tsk->group);
	struct tipc_mc_method *method = &tsk->mc_method;
	int blks = tsk_blocks(GROUP_H_SIZE + dlen);
	struct tipc_msg *hdr = &tsk->phdr;
	struct sk_buff_head pkts;
	int mtu, rc;

	/* Complete message header */
	msg_set_type(hdr, TIPC_GRP_UCAST_MSG);
	msg_set_hdr_sz(hdr, GROUP_H_SIZE);
	msg_set_destport(hdr, dport);
	msg_set_destnode(hdr, dnode);
	msg_set_grp_bc_seqno(hdr, bc_snd_nxt);

	/* Build message as chain of buffers */
	skb_queue_head_init(&pkts);
	mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
	rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
	if (unlikely(rc != dlen))
		return rc;

	/* Send message */
	rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
	if (unlikely(rc == -ELINKCONG)) {
		tipc_dest_push(&tsk->cong_links, dnode, 0);
		tsk->cong_link_cnt++;
	}

	/* Update send window */
	tipc_group_update_member(mb, blks);

	/* A broadcast sent within next EXPIRE period must follow same path */
	method->rcast = true;
	method->mandatory = true;
	return dlen;
}

/**
 * tipc_send_group_unicast - send message to a member in the group
 * @sock: socket structure
 * @m: message to send
 * @dlen: total length of message data
 * @timeout: 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_send_group_unicast(struct socket *sock, struct msghdr *m,
				   int dlen, long timeout)
{
	struct sock *sk = sock->sk;
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	int blks = tsk_blocks(GROUP_H_SIZE + dlen);
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_group *grp = tsk->group;
	struct net *net = sock_net(sk);
	struct tipc_member *mb = NULL;
	u32 node, port;
	int rc;

	node = dest->addr.id.node;
	port = dest->addr.id.ref;
	if (!port && !node)
		return -EHOSTUNREACH;

	/* Block or return if destination link or member is congested */
	rc = tipc_wait_for_cond(sock, &timeout,
				!tipc_dest_find(&tsk->cong_links, node, 0) &&
				!tipc_group_cong(grp, node, port, blks, &mb));
	if (unlikely(rc))
		return rc;

	if (unlikely(!mb))
		return -EHOSTUNREACH;

	rc = tipc_send_group_msg(net, tsk, m, mb, node, port, dlen);

	return rc ? rc : dlen;
}

/**
 * tipc_send_group_anycast - send message to any member with given identity
 * @sock: socket structure
 * @m: message to send
 * @dlen: total length of message data
 * @timeout: 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_send_group_anycast(struct socket *sock, struct msghdr *m,
				   int dlen, long timeout)
{
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	struct sock *sk = sock->sk;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct list_head *cong_links = &tsk->cong_links;
	int blks = tsk_blocks(GROUP_H_SIZE + dlen);
	struct tipc_group *grp = tsk->group;
	struct tipc_member *first = NULL;
	struct tipc_member *mbr = NULL;
	struct net *net = sock_net(sk);
	u32 node, port, exclude;
	u32 type, inst, domain;
	struct list_head dsts;
	int lookups = 0;
	int dstcnt, rc;
	bool cong;

	INIT_LIST_HEAD(&dsts);

	type = dest->addr.name.name.type;
	inst = dest->addr.name.name.instance;
	domain = addr_domain(net, dest->scope);
	exclude = tipc_group_exclude(grp);

	while (++lookups < 4) {
		first = NULL;

		/* Look for a non-congested destination member, if any */
		while (1) {
			if (!tipc_nametbl_lookup(net, type, inst, domain, &dsts,
						 &dstcnt, exclude, false))
				return -EHOSTUNREACH;
			tipc_dest_pop(&dsts, &node, &port);
			cong = tipc_group_cong(grp, node, port, blks, &mbr);
			if (!cong)
				break;
			if (mbr == first)
				break;
			if (!first)
				first = mbr;
		}

		/* Start over if destination was not in member list */
		if (unlikely(!mbr))
			continue;

		if (likely(!cong && !tipc_dest_find(cong_links, node, 0)))
			break;

		/* Block or return if destination link or member is congested */
		rc = tipc_wait_for_cond(sock, &timeout,
					!tipc_dest_find(cong_links, node, 0) &&
					!tipc_group_cong(grp, node, port,
							 blks, &mbr));
		if (unlikely(rc))
			return rc;

		/* Send, unless destination disappeared while waiting */
		if (likely(mbr))
			break;
	}

	if (unlikely(lookups >= 4))
		return -EHOSTUNREACH;

	rc = tipc_send_group_msg(net, tsk, m, mbr, node, port, dlen);

	return rc ? rc : dlen;
}

/**
 * tipc_send_group_bcast - send message to all members in communication group
 * @sk: socket structure
 * @m: message to send
 * @dlen: total length of message data
 * @timeout: 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_send_group_bcast(struct socket *sock, struct msghdr *m,
				 int dlen, long timeout)
{
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	struct sock *sk = sock->sk;
	struct net *net = sock_net(sk);
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_group *grp = tsk->group;
	struct tipc_nlist *dsts = tipc_group_dests(grp);
	struct tipc_mc_method *method = &tsk->mc_method;
	bool ack = method->mandatory && method->rcast;
	int blks = tsk_blocks(MCAST_H_SIZE + dlen);
	struct tipc_msg *hdr = &tsk->phdr;
	int mtu = tipc_bcast_get_mtu(net);
	struct sk_buff_head pkts;
	int rc = -EHOSTUNREACH;

	if (!dsts->local && !dsts->remote)
		return -EHOSTUNREACH;

	/* Block or return if any destination link or member is congested */
	rc = tipc_wait_for_cond(sock, &timeout,	!tsk->cong_link_cnt &&
				!tipc_group_bc_cong(grp, blks));
	if (unlikely(rc))
		return rc;

	/* Complete message header */
	if (dest) {
		msg_set_type(hdr, TIPC_GRP_MCAST_MSG);
		msg_set_nameinst(hdr, dest->addr.name.name.instance);
	} else {
		msg_set_type(hdr, TIPC_GRP_BCAST_MSG);
		msg_set_nameinst(hdr, 0);
	}
	msg_set_hdr_sz(hdr, GROUP_H_SIZE);
	msg_set_destport(hdr, 0);
	msg_set_destnode(hdr, 0);
	msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp));

	/* Avoid getting stuck with repeated forced replicasts */
	msg_set_grp_bc_ack_req(hdr, ack);

	/* Build message as chain of buffers */
	skb_queue_head_init(&pkts);
	rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
	if (unlikely(rc != dlen))
		return rc;

	/* Send message */
	rc = tipc_mcast_xmit(net, &pkts, method, dsts, &tsk->cong_link_cnt);
	if (unlikely(rc))
		return rc;

	/* Update broadcast sequence number and send windows */
	tipc_group_update_bc_members(tsk->group, blks, ack);

	/* Broadcast link is now free to choose method for next broadcast */
	method->mandatory = false;
	method->expires = jiffies;

	return dlen;
}

/**
 * tipc_send_group_mcast - send message to all members with given identity
 * @sock: socket structure
 * @m: message to send
 * @dlen: total length of message data
 * @timeout: 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_send_group_mcast(struct socket *sock, struct msghdr *m,
				 int dlen, long timeout)
{
	struct sock *sk = sock->sk;
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	struct tipc_name_seq *seq = &dest->addr.nameseq;
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_group *grp = tsk->group;
	struct net *net = sock_net(sk);
	u32 domain, exclude, dstcnt;
	struct list_head dsts;

	INIT_LIST_HEAD(&dsts);

	if (seq->lower != seq->upper)
		return -ENOTSUPP;

	domain = addr_domain(net, dest->scope);
	exclude = tipc_group_exclude(grp);
	if (!tipc_nametbl_lookup(net, seq->type, seq->lower, domain,
				 &dsts, &dstcnt, exclude, true))
		return -EHOSTUNREACH;

	if (dstcnt == 1) {
		tipc_dest_pop(&dsts, &dest->addr.id.node, &dest->addr.id.ref);
		return tipc_send_group_unicast(sock, m, dlen, timeout);
	}

	tipc_dest_list_purge(&dsts);
	return tipc_send_group_bcast(sock, m, dlen, timeout);
}

/**
 * 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)
{
	u32 scope = TIPC_CLUSTER_SCOPE;
	u32 self = tipc_own_addr(net);
	struct sk_buff *skb, *_skb;
	u32 lower = 0, upper = ~0;
	struct sk_buff_head tmpq;
	u32 portid, oport, onode;
	struct list_head dports;
	struct tipc_msg *msg;
	int user, mtyp, hsz;

	__skb_queue_head_init(&tmpq);
	INIT_LIST_HEAD(&dports);

	skb = tipc_skb_peek(arrvq, &inputq->lock);
	for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) {
		msg = buf_msg(skb);
		user = msg_user(msg);
		mtyp = msg_type(msg);
		if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) {
			spin_lock_bh(&inputq->lock);
			if (skb_peek(arrvq) == skb) {
				__skb_dequeue(arrvq);
				__skb_queue_tail(inputq, skb);
			}
			refcount_dec(&skb->users);
			spin_unlock_bh(&inputq->lock);
			continue;
		}
		hsz = skb_headroom(skb) + msg_hdr_sz(msg);
		oport = msg_origport(msg);
		onode = msg_orignode(msg);
		if (onode == self)
			scope = TIPC_NODE_SCOPE;

		/* Create destination port list and message clones: */
		if (!msg_in_group(msg)) {
			lower = msg_namelower(msg);
			upper = msg_nameupper(msg);
		}
		tipc_nametbl_mc_translate(net, msg_nametype(msg), lower, upper,
					  scope, &dports);
		while (tipc_dest_pop(&dports, NULL, &portid)) {
			_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_conn_proto_rcv - receive a connection mng protocol message
 * @tsk: receiving socket
 * @skb: pointer to message buffer.
 */
static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
				   struct sk_buff_head *xmitq)
{
	struct tipc_msg *hdr = buf_msg(skb);
	u32 onode = tsk_own_node(tsk);
	struct sock *sk = &tsk->sk;
	int mtyp = msg_type(hdr);
	bool conn_cong;

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

	if (unlikely(msg_errcode(hdr))) {
		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
		tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk),
				      tsk_peer_port(tsk));
		sk->sk_state_change(sk);
		goto exit;
	}

	tsk->probe_unacked = false;

	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);
}

/**
 * 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 dlen)
{
	struct sock *sk = sock->sk;
	struct net *net = sock_net(sk);
	struct tipc_sock *tsk = tipc_sk(sk);
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	long timeout = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
	struct list_head *clinks = &tsk->cong_links;
	bool syn = !tipc_sk_type_connectionless(sk);
	struct tipc_group *grp = tsk->group;
	struct tipc_msg *hdr = &tsk->phdr;
	struct tipc_name_seq *seq;
	struct sk_buff_head pkts;
	u32 type, inst, domain;
	u32 dnode, dport;
	int mtu, rc;

	if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE))
		return -EMSGSIZE;

	if (likely(dest)) {
		if (unlikely(m->msg_namelen < sizeof(*dest)))
			return -EINVAL;
		if (unlikely(dest->family != AF_TIPC))
			return -EINVAL;
	}

	if (grp) {
		if (!dest)
			return tipc_send_group_bcast(sock, m, dlen, timeout);
		if (dest->addrtype == TIPC_ADDR_NAME)
			return tipc_send_group_anycast(sock, m, dlen, timeout);
		if (dest->addrtype == TIPC_ADDR_ID)
			return tipc_send_group_unicast(sock, m, dlen, timeout);
		if (dest->addrtype == TIPC_ADDR_MCAST)
			return tipc_send_group_mcast(sock, m, dlen, timeout);
		return -EINVAL;
	}

	if (unlikely(!dest)) {
		dest = &tsk->peer;
		if (!syn || dest->family != AF_TIPC)
			return -EDESTADDRREQ;
	}

	if (unlikely(syn)) {
		if (sk->sk_state == TIPC_LISTEN)
			return -EPIPE;
		if (sk->sk_state != TIPC_OPEN)
			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;
	if (dest->addrtype == TIPC_ADDR_MCAST)
		return tipc_sendmcast(sock, seq, m, dlen, timeout);

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

	/* Block or return if destination link is congested */
	rc = tipc_wait_for_cond(sock, &timeout,
				!tipc_dest_find(clinks, dnode, 0));
	if (unlikely(rc))
		return rc;

	skb_queue_head_init(&pkts);
	mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
	rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
	if (unlikely(rc != dlen))
		return rc;

	rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
	if (unlikely(rc == -ELINKCONG)) {
		tipc_dest_push(clinks, dnode, 0);
		tsk->cong_link_cnt++;
		rc = 0;
	}

	if (unlikely(syn && !rc))
		tipc_set_sk_state(sk, TIPC_CONNECTING);

	return rc ? rc : dlen;
}

/**
 * tipc_sendstream - 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_sendstream(struct socket *sock, struct msghdr *m, size_t dsz)
{
	struct sock *sk = sock->sk;
	int ret;

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

	return ret;
}

static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
{
	struct sock *sk = sock->sk;
	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
	long timeout = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
	struct tipc_sock *tsk = tipc_sk(sk);
	struct tipc_msg *hdr = &tsk->phdr;
	struct net *net = sock_net(sk);
	struct sk_buff_head pkts;
	u32 dnode = tsk_peer_node(tsk);
	int send, sent = 0;
	int rc = 0;

	skb_queue_head_init(&pkts);

	if (unlikely(dlen > INT_MAX))
		return -EMSGSIZE;

	/* Handle implicit connection setup */
	if (unlikely(dest)) {
		rc = __tipc_sendmsg(sock, m, dlen);
		if (dlen && (dlen == rc))
			tsk->snt_unacked = tsk_inc(tsk, dlen + msg_hdr_sz(hdr));
		return rc;
	}

	do {
		rc = tipc_wait_for_cond(sock, &timeout,
					(!tsk->cong_link_cnt &&
					 !tsk_conn_cong(tsk) &&
					 tipc_sk_connected(sk)));
		if (unlikely(rc))
			break;

		send = min_t(size_t, dlen - sent, TIPC_MAX_USER_MSG_SIZE);
		rc = tipc_msg_build(hdr, m, sent, send, tsk->max_pkt, &pkts);
		if (unlikely(rc != send))
			break;

		rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
		if (unlikely(rc == -ELINKCONG)) {
			tsk->cong_link_cnt = 1;
			rc = 0;
		}
		if (likely(!rc)) {
			tsk->snt_unacked += tsk_inc(tsk, send + MIN_H_SIZE);
			sent += send;
		}
	} while (sent < dlen && !rc);

	return sent ? sent : rc;
}

/**
 * tipc_send_packet - send a connection-oriented message
 * @sock: socket structure
 * @m: message to send
 * @dsz: length of data to be transmitted
 *
 * Used for SOCK_SEQPACKET messages.
 *
 * Returns the number of bytes sent on success, or errno otherwise
 */
static int tipc_send_packet(struct socket *sock, struct msghdr *m, size_t dsz)
{
	if (dsz > TIPC_MAX_USER_MSG_SIZE)
		return -EMSGSIZE;

	return tipc_sendstream(sock, m, dsz);
}

/* tipc_sk_finish_conn - complete the setup of a connection
 */
static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
				u32 peer_node)
{
	struct sock *sk = &tsk->sk;
	struct net *net = sock_net(sk);
	struct tipc_msg *msg = &tsk->phdr;

	msg_set_destnode(msg, peer_node);
	msg_set_destport(msg, peer_port);
	msg_set_type(msg, TIPC_CONN_MSG);
	msg_set_lookup_scope(msg, 0);
	msg_set_hdr_sz(msg, SHORT_H_SIZE);

	sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTV);
	tipc_set_sk_state(sk, TIPC_ESTABLISHED);
	tipc_node_add_conn(net, peer_node, tsk->portid, peer_port);
	tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid);
	tsk->peer_caps = tipc_node_get_capabilities(net, peer_node);
	if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL)
		return;

	/* Fall back to message based flow control */
	tsk->rcv_win = FLOWCTL_MSG_WIN;
	tsk->snd_win = FLOWCTL_MSG_WIN;
}

/**
 * tipc_sk_set_orig_addr - capture sender's address for received message
 * @m: descriptor for message info
 * @hdr: received message header
 *
 * Note: Address is not captured if not requested by receiver.
 */
static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
{
	DECLARE_SOCKADDR(struct sockaddr_pair *, srcaddr, m->msg_name);
	struct tipc_msg *hdr = buf_msg(skb);

	if (!srcaddr)
		return;

	srcaddr->sock.family = AF_TIPC;
	srcaddr->sock.addrtype = TIPC_ADDR_ID;
	srcaddr->sock.addr.id.ref = msg_origport(hdr);
	srcaddr->sock.addr.id.node = msg_orignode(hdr);
	srcaddr->sock.addr.name.domain = 0;
	srcaddr->sock.scope = 0;
	m->msg_namelen = sizeof(struct sockaddr_tipc);

	if (!msg_in_group(hdr))
		return;

	/* Group message users may also want to know sending member's id */
	srcaddr->member.family = AF_TIPC;
	srcaddr->member.addrtype = TIPC_ADDR_NAME;
	srcaddr->member.addr.name.name.type = msg_nametype(hdr);
	srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member;
	srcaddr->member.addr.name.domain = 0;
	m->msg_namelen = sizeof(*srcaddr);
}

/**
 * tipc_sk_anc_data_recv - optionally capture ancillary data for received message
 * @m: descriptor for message info
 * @msg: received message header
 * @tsk: TIPC port associated with message
 *
 * Note: Ancillary data is not captured if not requested by receiver.
 *
 * Returns 0 if successful, otherwise errno
 */
static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
				 struct tipc_sock *tsk)
{
	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 = (tsk->conn_type != 0);
		anc_data[0] = tsk->conn_type;
		anc_data[1] = tsk->conn_instance;
		anc_data[2] = tsk->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 void tipc_sk_send_ack(struct tipc_sock *tsk)
{
	struct sock *sk = &tsk->sk;
	struct net *net = sock_net(sk);
	struct sk_buff *skb = NULL;
	struct tipc_msg *msg;
	u32 peer_port = tsk_peer_port(tsk);
	u32 dnode = tsk_peer_node(tsk);

	if (!tipc_sk_connected(sk))
		return;
	skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0,
			      dnode, tsk_own_node(tsk), peer_port,
			      tsk->portid, TIPC_OK);
	if (!skb)
		return;
	msg = buf_msg(skb);
	msg_set_conn_ack(msg, tsk->rcv_unacked);
	tsk->rcv_unacked = 0;

	/* Adjust to and advertize the correct window limit */
	if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL) {
		tsk->rcv_win = tsk_adv_blocks(tsk->sk.sk_rcvbuf);
		msg_set_adv_win(msg, tsk->rcv_win);
	}
	tipc_node_xmit_skb(net, skb, dnode, msg_link_selector(msg));
}

static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
{
	struct sock *sk = sock->sk;
	DEFINE_WAIT(wait);
	long timeo = *timeop;
	int err = sock_error(sk);

	if (err)
		return err;

	for (;;) {
		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
		if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
			if (sk->sk_shutdown & RCV_SHUTDOWN) {
				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 = -EAGAIN;
		if (!timeo)
			break;
		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			break;

		err = sock_error(sk);
		if (err)
			break;
	}
	finish_wait(sk_sleep(sk), &wait);
	*timeop = timeo;
	return err;
}

/**
 * tipc_recvmsg - receive packet-oriented message
 * @m: descriptor for message info
 * @buflen: length 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 socket *sock, struct msghdr *m,
			size_t buflen,	int flags)
{
	struct sock *sk = sock->sk;
	bool connected = !tipc_sk_type_connectionless(sk);
	struct tipc_sock *tsk = tipc_sk(sk);
	int rc, err, hlen, dlen, copy;
	struct sk_buff_head xmitq;
	struct tipc_msg *hdr;
	struct sk_buff *skb;
	bool grp_evt;
	long timeout;

	/* Catch invalid receive requests */
	if (unlikely(!buflen))
		return -EINVAL;

	lock_sock(sk);
	if (unlikely(connected && sk->sk_state == TIPC_OPEN)) {
		rc = -ENOTCONN;
		goto exit;
	}
	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);

	/* Step rcv queue to first msg with data or error; wait if necessary */
	do {
		rc = tipc_wait_for_rcvmsg(sock, &timeout);
		if (unlikely(rc))
			goto exit;
		skb = skb_peek(&sk->sk_receive_queue);
		hdr = buf_msg(skb);
		dlen = msg_data_sz(hdr);
		hlen = msg_hdr_sz(hdr);
		err = msg_errcode(hdr);
		grp_evt = msg_is_grp_evt(hdr);
		if (likely(dlen || err))
			break;
		tsk_advance_rx_queue(sk);
	} while (1);

	/* Collect msg meta data, including error code and rejected data */
	tipc_sk_set_orig_addr(m, skb);
	rc = tipc_sk_anc_data_recv(m, hdr, tsk);
	if (unlikely(rc))
		goto exit;

	/* Capture data if non-error msg, otherwise just set return value */
	if (likely(!err)) {
		copy = min_t(int, dlen, buflen);
		if (unlikely(copy != dlen))
			m->msg_flags |= MSG_TRUNC;
		rc = skb_copy_datagram_msg(skb, hlen, m, copy);
	} else {
		copy = 0;
		rc = 0;
		if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control)
			rc = -ECONNRESET;
	}
	if (unlikely(rc))
		goto exit;

	/* Mark message as group event if applicable */
	if (unlikely(grp_evt)) {
		if (msg_grp_evt(hdr) == TIPC_WITHDRAWN)
			m->msg_flags |= MSG_EOR;
		m->msg_flags |= MSG_OOB;
		copy = 0;
	}

	/* Caption of data or error code/rejected data was successful */
	if (unlikely(flags & MSG_PEEK))
		goto exit;

	/* Send group flow control advertisement when applicable */
	if (tsk->group && msg_in_group(hdr) && !grp_evt) {
		skb_queue_head_init(&xmitq);
		tipc_group_update_rcv_win(tsk->group, tsk_blocks(hlen + dlen),
					  msg_orignode(hdr), msg_origport(hdr),
					  &xmitq);
		tipc_node_distr_xmit(sock_net(sk), &xmitq);
	}

	tsk_advance_rx_queue(sk);

	if (likely(!connected))
		goto exit;

	/* Send connection flow control advertisement when applicable */
	tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen);
	if (tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE)
		tipc_sk_send_ack(tsk);
exit:
	release_sock(sk);
	return rc ? rc : copy;
}

/**
 * tipc_recvstream - receive stream-oriented data
 * @m: descriptor for message info
 * @buflen: 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_recvstream(struct socket *sock, struct msghdr *m,
			   siz…