/*
 * net/tipc/link.c: TIPC link code
 *
 * Copyright (c) 1996-2007, 2012-2016, Ericsson AB
 * Copyright (c) 2004-2007, 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 "subscr.h"
#include "link.h"
#include "bcast.h"
#include "socket.h"
#include "name_distr.h"
#include "discover.h"
#include "netlink.h"
#include "monitor.h"
#include "trace.h"
#include "crypto.h"

#include <linux/pkt_sched.h>

struct tipc_stats {
	u32 sent_pkts;
	u32 recv_pkts;
	u32 sent_states;
	u32 recv_states;
	u32 sent_probes;
	u32 recv_probes;
	u32 sent_nacks;
	u32 recv_nacks;
	u32 sent_acks;
	u32 sent_bundled;
	u32 sent_bundles;
	u32 recv_bundled;
	u32 recv_bundles;
	u32 retransmitted;
	u32 sent_fragmented;
	u32 sent_fragments;
	u32 recv_fragmented;
	u32 recv_fragments;
	u32 link_congs;		/* # port sends blocked by congestion */
	u32 deferred_recv;
	u32 duplicates;
	u32 max_queue_sz;	/* send queue size high water mark */
	u32 accu_queue_sz;	/* used for send queue size profiling */
	u32 queue_sz_counts;	/* used for send queue size profiling */
	u32 msg_length_counts;	/* used for message length profiling */
	u32 msg_lengths_total;	/* used for message length profiling */
	u32 msg_length_profile[7]; /* used for msg. length profiling */
};

/**
 * struct tipc_link - TIPC link data structure
 * @addr: network address of link's peer node
 * @name: link name character string
 * @media_addr: media address to use when sending messages over link
 * @timer: link timer
 * @net: pointer to namespace struct
 * @refcnt: reference counter for permanent references (owner node & timer)
 * @peer_session: link session # being used by peer end of link
 * @peer_bearer_id: bearer id used by link's peer endpoint
 * @bearer_id: local bearer id used by link
 * @tolerance: minimum link continuity loss needed to reset link [in ms]
 * @abort_limit: # of unacknowledged continuity probes needed to reset link
 * @state: current state of link FSM
 * @peer_caps: bitmap describing capabilities of peer node
 * @silent_intv_cnt: # of timer intervals without any reception from peer
 * @proto_msg: template for control messages generated by link
 * @pmsg: convenience pointer to "proto_msg" field
 * @priority: current link priority
 * @net_plane: current link network plane ('A' through 'H')
 * @mon_state: cookie with information needed by link monitor
 * @backlog_limit: backlog queue congestion thresholds (indexed by importance)
 * @exp_msg_count: # of tunnelled messages expected during link changeover
 * @reset_rcv_checkpt: seq # of last acknowledged message at time of link reset
 * @mtu: current maximum packet size for this link
 * @advertised_mtu: advertised own mtu when link is being established
 * @transmitq: queue for sent, non-acked messages
 * @backlogq: queue for messages waiting to be sent
 * @snt_nxt: next sequence number to use for outbound messages
 * @ackers: # of peers that needs to ack each packet before it can be released
 * @acked: # last packet acked by a certain peer. Used for broadcast.
 * @rcv_nxt: next sequence number to expect for inbound messages
 * @deferred_queue: deferred queue saved OOS b'cast message received from node
 * @unacked_window: # of inbound messages rx'd without ack'ing back to peer
 * @inputq: buffer queue for messages to be delivered upwards
 * @namedq: buffer queue for name table messages to be delivered upwards
 * @next_out: ptr to first unsent outbound message in queue
 * @wakeupq: linked list of wakeup msgs waiting for link congestion to abate
 * @long_msg_seq_no: next identifier to use for outbound fragmented messages
 * @reasm_buf: head of partially reassembled inbound message fragments
 * @bc_rcvr: marks that this is a broadcast receiver link
 * @stats: collects statistics regarding link activity
 */
struct tipc_link {
	u32 addr;
	char name[TIPC_MAX_LINK_NAME];
	struct net *net;

	/* Management and link supervision data */
	u16 peer_session;
	u16 session;
	u16 snd_nxt_state;
	u16 rcv_nxt_state;
	u32 peer_bearer_id;
	u32 bearer_id;
	u32 tolerance;
	u32 abort_limit;
	u32 state;
	u16 peer_caps;
	bool in_session;
	bool active;
	u32 silent_intv_cnt;
	char if_name[TIPC_MAX_IF_NAME];
	u32 priority;
	char net_plane;
	struct tipc_mon_state mon_state;
	u16 rst_cnt;

	/* Failover/synch */
	u16 drop_point;
	struct sk_buff *failover_reasm_skb;
	struct sk_buff_head failover_deferdq;

	/* Max packet negotiation */
	u16 mtu;
	u16 advertised_mtu;

	/* Sending */
	struct sk_buff_head transmq;
	struct sk_buff_head backlogq;
	struct {
		u16 len;
		u16 limit;
		struct sk_buff *target_bskb;
	} backlog[5];
	u16 snd_nxt;

	/* Reception */
	u16 rcv_nxt;
	u32 rcv_unacked;
	struct sk_buff_head deferdq;
	struct sk_buff_head *inputq;
	struct sk_buff_head *namedq;

	/* Congestion handling */
	struct sk_buff_head wakeupq;
	u16 window;
	u16 min_win;
	u16 ssthresh;
	u16 max_win;
	u16 cong_acks;
	u16 checkpoint;

	/* Fragmentation/reassembly */
	struct sk_buff *reasm_buf;
	struct sk_buff *reasm_tnlmsg;

	/* Broadcast */
	u16 ackers;
	u16 acked;
	struct tipc_link *bc_rcvlink;
	struct tipc_link *bc_sndlink;
	u8 nack_state;
	bool bc_peer_is_up;

	/* Statistics */
	struct tipc_stats stats;
};

/*
 * Error message prefixes
 */
static const char *link_co_err = "Link tunneling error, ";
static const char *link_rst_msg = "Resetting link ";

/* Send states for broadcast NACKs
 */
enum {
	BC_NACK_SND_CONDITIONAL,
	BC_NACK_SND_UNCONDITIONAL,
	BC_NACK_SND_SUPPRESS,
};

#define TIPC_BC_RETR_LIM  (jiffies + msecs_to_jiffies(10))
#define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1))

/*
 * Interval between NACKs when packets arrive out of order
 */
#define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2)

/* Link FSM states:
 */
enum {
	LINK_ESTABLISHED     = 0xe,
	LINK_ESTABLISHING    = 0xe  << 4,
	LINK_RESET           = 0x1  << 8,
	LINK_RESETTING       = 0x2  << 12,
	LINK_PEER_RESET      = 0xd  << 16,
	LINK_FAILINGOVER     = 0xf  << 20,
	LINK_SYNCHING        = 0xc  << 24
};

/* Link FSM state checking routines
 */
static int link_is_up(struct tipc_link *l)
{
	return l->state & (LINK_ESTABLISHED | LINK_SYNCHING);
}

static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
			       struct sk_buff_head *xmitq);
static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
				      bool probe_reply, u16 rcvgap,
				      int tolerance, int priority,
				      struct sk_buff_head *xmitq);
static void link_print(struct tipc_link *l, const char *str);
static int tipc_link_build_nack_msg(struct tipc_link *l,
				    struct sk_buff_head *xmitq);
static void tipc_link_build_bc_init_msg(struct tipc_link *l,
					struct sk_buff_head *xmitq);
static int tipc_link_release_pkts(struct tipc_link *l, u16 to);
static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data, u16 gap);
static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
				     struct tipc_gap_ack_blks *ga,
				     struct sk_buff_head *xmitq);
static void tipc_link_update_cwin(struct tipc_link *l, int released,
				  bool retransmitted);
/*
 *  Simple non-static link routines (i.e. referenced outside this file)
 */
bool tipc_link_is_up(struct tipc_link *l)
{
	return link_is_up(l);
}

bool tipc_link_peer_is_down(struct tipc_link *l)
{
	return l->state == LINK_PEER_RESET;
}

bool tipc_link_is_reset(struct tipc_link *l)
{
	return l->state & (LINK_RESET | LINK_FAILINGOVER | LINK_ESTABLISHING);
}

bool tipc_link_is_establishing(struct tipc_link *l)
{
	return l->state == LINK_ESTABLISHING;
}

bool tipc_link_is_synching(struct tipc_link *l)
{
	return l->state == LINK_SYNCHING;
}

bool tipc_link_is_failingover(struct tipc_link *l)
{
	return l->state == LINK_FAILINGOVER;
}

bool tipc_link_is_blocked(struct tipc_link *l)
{
	return l->state & (LINK_RESETTING | LINK_PEER_RESET | LINK_FAILINGOVER);
}

static bool link_is_bc_sndlink(struct tipc_link *l)
{
	return !l->bc_sndlink;
}

static bool link_is_bc_rcvlink(struct tipc_link *l)
{
	return ((l->bc_rcvlink == l) && !link_is_bc_sndlink(l));
}

void tipc_link_set_active(struct tipc_link *l, bool active)
{
	l->active = active;
}

u32 tipc_link_id(struct tipc_link *l)
{
	return l->peer_bearer_id << 16 | l->bearer_id;
}

int tipc_link_min_win(struct tipc_link *l)
{
	return l->min_win;
}

int tipc_link_max_win(struct tipc_link *l)
{
	return l->max_win;
}

int tipc_link_prio(struct tipc_link *l)
{
	return l->priority;
}

unsigned long tipc_link_tolerance(struct tipc_link *l)
{
	return l->tolerance;
}

struct sk_buff_head *tipc_link_inputq(struct tipc_link *l)
{
	return l->inputq;
}

char tipc_link_plane(struct tipc_link *l)
{
	return l->net_plane;
}

void tipc_link_update_caps(struct tipc_link *l, u16 capabilities)
{
	l->peer_caps = capabilities;
}

void tipc_link_add_bc_peer(struct tipc_link *snd_l,
			   struct tipc_link *uc_l,
			   struct sk_buff_head *xmitq)
{
	struct tipc_link *rcv_l = uc_l->bc_rcvlink;

	snd_l->ackers++;
	rcv_l->acked = snd_l->snd_nxt - 1;
	snd_l->state = LINK_ESTABLISHED;
	tipc_link_build_bc_init_msg(uc_l, xmitq);
}

void tipc_link_remove_bc_peer(struct tipc_link *snd_l,
			      struct tipc_link *rcv_l,
			      struct sk_buff_head *xmitq)
{
	u16 ack = snd_l->snd_nxt - 1;

	snd_l->ackers--;
	rcv_l->bc_peer_is_up = true;
	rcv_l->state = LINK_ESTABLISHED;
	tipc_link_bc_ack_rcv(rcv_l, ack, xmitq);
	trace_tipc_link_reset(rcv_l, TIPC_DUMP_ALL, "bclink removed!");
	tipc_link_reset(rcv_l);
	rcv_l->state = LINK_RESET;
	if (!snd_l->ackers) {
		trace_tipc_link_reset(snd_l, TIPC_DUMP_ALL, "zero ackers!");
		tipc_link_reset(snd_l);
		snd_l->state = LINK_RESET;
		__skb_queue_purge(xmitq);
	}
}

int tipc_link_bc_peers(struct tipc_link *l)
{
	return l->ackers;
}

static u16 link_bc_rcv_gap(struct tipc_link *l)
{
	struct sk_buff *skb = skb_peek(&l->deferdq);
	u16 gap = 0;

	if (more(l->snd_nxt, l->rcv_nxt))
		gap = l->snd_nxt - l->rcv_nxt;
	if (skb)
		gap = buf_seqno(skb) - l->rcv_nxt;
	return gap;
}

void tipc_link_set_mtu(struct tipc_link *l, int mtu)
{
	l->mtu = mtu;
}

int tipc_link_mtu(struct tipc_link *l)
{
	return l->mtu;
}

int tipc_link_mss(struct tipc_link *l)
{
#ifdef CONFIG_TIPC_CRYPTO
	return l->mtu - INT_H_SIZE - EMSG_OVERHEAD;
#else
	return l->mtu - INT_H_SIZE;
#endif
}

u16 tipc_link_rcv_nxt(struct tipc_link *l)
{
	return l->rcv_nxt;
}

u16 tipc_link_acked(struct tipc_link *l)
{
	return l->acked;
}

char *tipc_link_name(struct tipc_link *l)
{
	return l->name;
}

u32 tipc_link_state(struct tipc_link *l)
{
	return l->state;
}

/**
 * tipc_link_create - create a new link
 * @n: pointer to associated node
 * @if_name: associated interface name
 * @bearer_id: id (index) of associated bearer
 * @tolerance: link tolerance to be used by link
 * @net_plane: network plane (A,B,c..) this link belongs to
 * @mtu: mtu to be advertised by link
 * @priority: priority to be used by link
 * @min_win: minimal send window to be used by link
 * @max_win: maximal send window to be used by link
 * @session: session to be used by link
 * @ownnode: identity of own node
 * @peer: node id of peer node
 * @peer_caps: bitmap describing peer node capabilities
 * @bc_sndlink: the namespace global link used for broadcast sending
 * @bc_rcvlink: the peer specific link used for broadcast reception
 * @inputq: queue to put messages ready for delivery
 * @namedq: queue to put binding table update messages ready for delivery
 * @link: return value, pointer to put the created link
 *
 * Returns true if link was created, otherwise false
 */
bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
		      int tolerance, char net_plane, u32 mtu, int priority,
		      u32 min_win, u32 max_win, u32 session, u32 self,
		      u32 peer, u8 *peer_id, u16 peer_caps,
		      struct tipc_link *bc_sndlink,
		      struct tipc_link *bc_rcvlink,
		      struct sk_buff_head *inputq,
		      struct sk_buff_head *namedq,
		      struct tipc_link **link)
{
	char peer_str[NODE_ID_STR_LEN] = {0,};
	char self_str[NODE_ID_STR_LEN] = {0,};
	struct tipc_link *l;

	l = kzalloc(sizeof(*l), GFP_ATOMIC);
	if (!l)
		return false;
	*link = l;
	l->session = session;

	/* Set link name for unicast links only */
	if (peer_id) {
		tipc_nodeid2string(self_str, tipc_own_id(net));
		if (strlen(self_str) > 16)
			sprintf(self_str, "%x", self);
		tipc_nodeid2string(peer_str, peer_id);
		if (strlen(peer_str) > 16)
			sprintf(peer_str, "%x", peer);
	}
	/* Peer i/f name will be completed by reset/activate message */
	snprintf(l->name, sizeof(l->name), "%s:%s-%s:unknown",
		 self_str, if_name, peer_str);

	strcpy(l->if_name, if_name);
	l->addr = peer;
	l->peer_caps = peer_caps;
	l->net = net;
	l->in_session = false;
	l->bearer_id = bearer_id;
	l->tolerance = tolerance;
	if (bc_rcvlink)
		bc_rcvlink->tolerance = tolerance;
	l->net_plane = net_plane;
	l->advertised_mtu = mtu;
	l->mtu = mtu;
	l->priority = priority;
	tipc_link_set_queue_limits(l, min_win, max_win);
	l->ackers = 1;
	l->bc_sndlink = bc_sndlink;
	l->bc_rcvlink = bc_rcvlink;
	l->inputq = inputq;
	l->namedq = namedq;
	l->state = LINK_RESETTING;
	__skb_queue_head_init(&l->transmq);
	__skb_queue_head_init(&l->backlogq);
	__skb_queue_head_init(&l->deferdq);
	__skb_queue_head_init(&l->failover_deferdq);
	skb_queue_head_init(&l->wakeupq);
	skb_queue_head_init(l->inputq);
	return true;
}

/**
 * tipc_link_bc_create - create new link to be used for broadcast
 * @n: pointer to associated node
 * @mtu: mtu to be used initially if no peers
 * @window: send window to be used
 * @inputq: queue to put messages ready for delivery
 * @namedq: queue to put binding table update messages ready for delivery
 * @link: return value, pointer to put the created link
 *
 * Returns true if link was created, otherwise false
 */
bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer,
			 int mtu, u32 min_win, u32 max_win, u16 peer_caps,
			 struct sk_buff_head *inputq,
			 struct sk_buff_head *namedq,
			 struct tipc_link *bc_sndlink,
			 struct tipc_link **link)
{
	struct tipc_link *l;

	if (!tipc_link_create(net, "", MAX_BEARERS, 0, 'Z', mtu, 0, min_win,
			      max_win, 0, ownnode, peer, NULL, peer_caps,
			      bc_sndlink, NULL, inputq, namedq, link))
		return false;

	l = *link;
	strcpy(l->name, tipc_bclink_name);
	trace_tipc_link_reset(l, TIPC_DUMP_ALL, "bclink created!");
	tipc_link_reset(l);
	l->state = LINK_RESET;
	l->ackers = 0;
	l->bc_rcvlink = l;

	/* Broadcast send link is always up */
	if (link_is_bc_sndlink(l))
		l->state = LINK_ESTABLISHED;

	/* Disable replicast if even a single peer doesn't support it */
	if (link_is_bc_rcvlink(l) && !(peer_caps & TIPC_BCAST_RCAST))
		tipc_bcast_toggle_rcast(net, false);

	return true;
}

/**
 * tipc_link_fsm_evt - link finite state machine
 * @l: pointer to link
 * @evt: state machine event to be processed
 */
int tipc_link_fsm_evt(struct tipc_link *l, int evt)
{
	int rc = 0;
	int old_state = l->state;

	switch (l->state) {
	case LINK_RESETTING:
		switch (evt) {
		case LINK_PEER_RESET_EVT:
			l->state = LINK_PEER_RESET;
			break;
		case LINK_RESET_EVT:
			l->state = LINK_RESET;
			break;
		case LINK_FAILURE_EVT:
		case LINK_FAILOVER_BEGIN_EVT:
		case LINK_ESTABLISH_EVT:
		case LINK_FAILOVER_END_EVT:
		case LINK_SYNCH_BEGIN_EVT:
		case LINK_SYNCH_END_EVT:
		default:
			goto illegal_evt;
		}
		break;
	case LINK_RESET:
		switch (evt) {
		case LINK_PEER_RESET_EVT:
			l->state = LINK_ESTABLISHING;
			break;
		case LINK_FAILOVER_BEGIN_EVT:
			l->state = LINK_FAILINGOVER;
		case LINK_FAILURE_EVT:
		case LINK_RESET_EVT:
		case LINK_ESTABLISH_EVT:
		case LINK_FAILOVER_END_EVT:
			break;
		case LINK_SYNCH_BEGIN_EVT:
		case LINK_SYNCH_END_EVT:
		default:
			goto illegal_evt;
		}
		break;
	case LINK_PEER_RESET:
		switch (evt) {
		case LINK_RESET_EVT:
			l->state = LINK_ESTABLISHING;
			break;
		case LINK_PEER_RESET_EVT:
		case LINK_ESTABLISH_EVT:
		case LINK_FAILURE_EVT:
			break;
		case LINK_SYNCH_BEGIN_EVT:
		case LINK_SYNCH_END_EVT:
		case LINK_FAILOVER_BEGIN_EVT:
		case LINK_FAILOVER_END_EVT:
		default:
			goto illegal_evt;
		}
		break;
	case LINK_FAILINGOVER:
		switch (evt) {
		case LINK_FAILOVER_END_EVT:
			l->state = LINK_RESET;
			break;
		case LINK_PEER_RESET_EVT:
		case LINK_RESET_EVT:
		case LINK_ESTABLISH_EVT:
		case LINK_FAILURE_EVT:
			break;
		case LINK_FAILOVER_BEGIN_EVT:
		case LINK_SYNCH_BEGIN_EVT:
		case LINK_SYNCH_END_EVT:
		default:
			goto illegal_evt;
		}
		break;
	case LINK_ESTABLISHING:
		switch (evt) {
		case LINK_ESTABLISH_EVT:
			l->state = LINK_ESTABLISHED;
			break;
		case LINK_FAILOVER_BEGIN_EVT:
			l->state = LINK_FAILINGOVER;
			break;
		case LINK_RESET_EVT:
			l->state = LINK_RESET;
			break;
		case LINK_FAILURE_EVT:
		case LINK_PEER_RESET_EVT:
		case LINK_SYNCH_BEGIN_EVT:
		case LINK_FAILOVER_END_EVT:
			break;
		case LINK_SYNCH_END_EVT:
		default:
			goto illegal_evt;
		}
		break;
	case LINK_ESTABLISHED:
		switch (evt) {
		case LINK_PEER_RESET_EVT:
			l->state = LINK_PEER_RESET;
			rc |= TIPC_LINK_DOWN_EVT;
			break;
		case LINK_FAILURE_EVT:
			l->state = LINK_RESETTING;
			rc |= TIPC_LINK_DOWN_EVT;
			break;
		case LINK_RESET_EVT:
			l->state = LINK_RESET;
			break;
		case LINK_ESTABLISH_EVT:
		case LINK_SYNCH_END_EVT:
			break;
		case LINK_SYNCH_BEGIN_EVT:
			l->state = LINK_SYNCHING;
			break;
		case LINK_FAILOVER_BEGIN_EVT:
		case LINK_FAILOVER_END_EVT:
		default:
			goto illegal_evt;
		}
		break;
	case LINK_SYNCHING:
		switch (evt) {
		case LINK_PEER_RESET_EVT:
			l->state = LINK_PEER_RESET;
			rc |= TIPC_LINK_DOWN_EVT;
			break;
		case LINK_FAILURE_EVT:
			l->state = LINK_RESETTING;
			rc |= TIPC_LINK_DOWN_EVT;
			break;
		case LINK_RESET_EVT:
			l->state = LINK_RESET;
			break;
		case LINK_ESTABLISH_EVT:
		case LINK_SYNCH_BEGIN_EVT:
			break;
		case LINK_SYNCH_END_EVT:
			l->state = LINK_ESTABLISHED;
			break;
		case LINK_FAILOVER_BEGIN_EVT:
		case LINK_FAILOVER_END_EVT:
		default:
			goto illegal_evt;
		}
		break;
	default:
		pr_err("Unknown FSM state %x in %s\n", l->state, l->name);
	}
	trace_tipc_link_fsm(l->name, old_state, l->state, evt);
	return rc;
illegal_evt:
	pr_err("Illegal FSM event %x in state %x on link %s\n",
	       evt, l->state, l->name);
	trace_tipc_link_fsm(l->name, old_state, l->state, evt);
	return rc;
}

/* link_profile_stats - update statistical profiling of traffic
 */
static void link_profile_stats(struct tipc_link *l)
{
	struct sk_buff *skb;
	struct tipc_msg *msg;
	int length;

	/* Update counters used in statistical profiling of send traffic */
	l->stats.accu_queue_sz += skb_queue_len(&l->transmq);
	l->stats.queue_sz_counts++;

	skb = skb_peek(&l->transmq);
	if (!skb)
		return;
	msg = buf_msg(skb);
	length = msg_size(msg);

	if (msg_user(msg) == MSG_FRAGMENTER) {
		if (msg_type(msg) != FIRST_FRAGMENT)
			return;
		length = msg_size(msg_inner_hdr(msg));
	}
	l->stats.msg_lengths_total += length;
	l->stats.msg_length_counts++;
	if (length <= 64)
		l->stats.msg_length_profile[0]++;
	else if (length <= 256)
		l->stats.msg_length_profile[1]++;
	else if (length <= 1024)
		l->stats.msg_length_profile[2]++;
	else if (length <= 4096)
		l->stats.msg_length_profile[3]++;
	else if (length <= 16384)
		l->stats.msg_length_profile[4]++;
	else if (length <= 32768)
		l->stats.msg_length_profile[5]++;
	else
		l->stats.msg_length_profile[6]++;
}

/**
 * tipc_link_too_silent - check if link is "too silent"
 * @l: tipc link to be checked
 *
 * Returns true if the link 'silent_intv_cnt' is about to reach the
 * 'abort_limit' value, otherwise false
 */
bool tipc_link_too_silent(struct tipc_link *l)
{
	return (l->silent_intv_cnt + 2 > l->abort_limit);
}

static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r,
				u16 from, u16 to, struct sk_buff_head *xmitq);
/* tipc_link_timeout - perform periodic task as instructed from node timeout
 */
int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
{
	int mtyp = 0;
	int rc = 0;
	bool state = false;
	bool probe = false;
	bool setup = false;
	u16 bc_snt = l->bc_sndlink->snd_nxt - 1;
	u16 bc_acked = l->bc_rcvlink->acked;
	struct tipc_mon_state *mstate = &l->mon_state;

	trace_tipc_link_timeout(l, TIPC_DUMP_NONE, " ");
	trace_tipc_link_too_silent(l, TIPC_DUMP_ALL, " ");
	switch (l->state) {
	case LINK_ESTABLISHED:
	case LINK_SYNCHING:
		mtyp = STATE_MSG;
		link_profile_stats(l);
		tipc_mon_get_state(l->net, l->addr, mstate, l->bearer_id);
		if (mstate->reset || (l->silent_intv_cnt > l->abort_limit))
			return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
		state = bc_acked != bc_snt;
		state |= l->bc_rcvlink->rcv_unacked;
		state |= l->rcv_unacked;
		state |= !skb_queue_empty(&l->transmq);
		state |= !skb_queue_empty(&l->deferdq);
		probe = mstate->probing;
		probe |= l->silent_intv_cnt;
		if (probe || mstate->monitoring)
			l->silent_intv_cnt++;
		if (l->snd_nxt == l->checkpoint) {
			tipc_link_update_cwin(l, 0, 0);
			probe = true;
		}
		l->checkpoint = l->snd_nxt;
		break;
	case LINK_RESET:
		setup = l->rst_cnt++ <= 4;
		setup |= !(l->rst_cnt % 16);
		mtyp = RESET_MSG;
		break;
	case LINK_ESTABLISHING:
		setup = true;
		mtyp = ACTIVATE_MSG;
		break;
	case LINK_PEER_RESET:
	case LINK_RESETTING:
	case LINK_FAILINGOVER:
		break;
	default:
		break;
	}

	if (state || probe || setup)
		tipc_link_build_proto_msg(l, mtyp, probe, 0, 0, 0, 0, xmitq);

	return rc;
}

/**
 * link_schedule_user - schedule a message sender for wakeup after congestion
 * @l: congested link
 * @hdr: header of message that is being sent
 * Create pseudo msg to send back to user when congestion abates
 */
static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr)
{
	u32 dnode = tipc_own_addr(l->net);
	u32 dport = msg_origport(hdr);
	struct sk_buff *skb;

	/* Create and schedule wakeup pseudo message */
	skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0,
			      dnode, l->addr, dport, 0, 0);
	if (!skb)
		return -ENOBUFS;
	msg_set_dest_droppable(buf_msg(skb), true);
	TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr);
	skb_queue_tail(&l->wakeupq, skb);
	l->stats.link_congs++;
	trace_tipc_link_conges(l, TIPC_DUMP_ALL, "wakeup scheduled!");
	return -ELINKCONG;
}

/**
 * link_prepare_wakeup - prepare users for wakeup after congestion
 * @l: congested link
 * Wake up a number of waiting users, as permitted by available space
 * in the send queue
 */
static void link_prepare_wakeup(struct tipc_link *l)
{
	struct sk_buff_head *wakeupq = &l->wakeupq;
	struct sk_buff_head *inputq = l->inputq;
	struct sk_buff *skb, *tmp;
	struct sk_buff_head tmpq;
	int avail[5] = {0,};
	int imp = 0;

	__skb_queue_head_init(&tmpq);

	for (; imp <= TIPC_SYSTEM_IMPORTANCE; imp++)
		avail[imp] = l->backlog[imp].limit - l->backlog[imp].len;

	skb_queue_walk_safe(wakeupq, skb, tmp) {
		imp = TIPC_SKB_CB(skb)->chain_imp;
		if (avail[imp] <= 0)
			continue;
		avail[imp]--;
		__skb_unlink(skb, wakeupq);
		__skb_queue_tail(&tmpq, skb);
	}

	spin_lock_bh(&inputq->lock);
	skb_queue_splice_tail(&tmpq, inputq);
	spin_unlock_bh(&inputq->lock);

}

void tipc_link_reset(struct tipc_link *l)
{
	struct sk_buff_head list;
	u32 imp;

	__skb_queue_head_init(&list);

	l->in_session = false;
	/* Force re-synch of peer session number before establishing */
	l->peer_session--;
	l->session++;
	l->mtu = l->advertised_mtu;

	spin_lock_bh(&l->wakeupq.lock);
	skb_queue_splice_init(&l->wakeupq, &list);
	spin_unlock_bh(&l->wakeupq.lock);

	spin_lock_bh(&l->inputq->lock);
	skb_queue_splice_init(&list, l->inputq);
	spin_unlock_bh(&l->inputq->lock);

	__skb_queue_purge(&l->transmq);
	__skb_queue_purge(&l->deferdq);
	__skb_queue_purge(&l->backlogq);
	__skb_queue_purge(&l->failover_deferdq);
	for (imp = 0; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) {
		l->backlog[imp].len = 0;
		l->backlog[imp].target_bskb = NULL;
	}
	kfree_skb(l->reasm_buf);
	kfree_skb(l->reasm_tnlmsg);
	kfree_skb(l->failover_reasm_skb);
	l->reasm_buf = NULL;
	l->reasm_tnlmsg = NULL;
	l->failover_reasm_skb = NULL;
	l->rcv_unacked = 0;
	l->snd_nxt = 1;
	l->rcv_nxt = 1;
	l->snd_nxt_state = 1;
	l->rcv_nxt_state = 1;
	l->acked = 0;
	l->silent_intv_cnt = 0;
	l->rst_cnt = 0;
	l->bc_peer_is_up = false;
	memset(&l->mon_state, 0, sizeof(l->mon_state));
	tipc_link_reset_stats(l);
}

/**
 * tipc_link_xmit(): enqueue buffer list according to queue situation
 * @link: link to use
 * @list: chain of buffers containing message
 * @xmitq: returned list of packets to be sent by caller
 *
 * Consumes the buffer chain.
 * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS
 * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted
 */
int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
		   struct sk_buff_head *xmitq)
{
	struct tipc_msg *hdr = buf_msg(skb_peek(list));
	struct sk_buff_head *backlogq = &l->backlogq;
	struct sk_buff_head *transmq = &l->transmq;
	struct sk_buff *skb, *_skb;
	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
	u16 ack = l->rcv_nxt - 1;
	u16 seqno = l->snd_nxt;
	int pkt_cnt = skb_queue_len(list);
	int imp = msg_importance(hdr);
	unsigned int mss = tipc_link_mss(l);
	unsigned int cwin = l->window;
	unsigned int mtu = l->mtu;
	bool new_bundle;
	int rc = 0;

	if (unlikely(msg_size(hdr) > mtu)) {
		pr_warn("Too large msg, purging xmit list %d %d %d %d %d!\n",
			skb_queue_len(list), msg_user(hdr),
			msg_type(hdr), msg_size(hdr), mtu);
		__skb_queue_purge(list);
		return -EMSGSIZE;
	}

	/* Allow oversubscription of one data msg per source at congestion */
	if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) {
		if (imp == TIPC_SYSTEM_IMPORTANCE) {
			pr_warn("%s<%s>, link overflow", link_rst_msg, l->name);
			return -ENOBUFS;
		}
		rc = link_schedule_user(l, hdr);
	}

	if (pkt_cnt > 1) {
		l->stats.sent_fragmented++;
		l->stats.sent_fragments += pkt_cnt;
	}

	/* Prepare each packet for sending, and add to relevant queue: */
	while ((skb = __skb_dequeue(list))) {
		if (likely(skb_queue_len(transmq) < cwin)) {
			hdr = buf_msg(skb);
			msg_set_seqno(hdr, seqno);
			msg_set_ack(hdr, ack);
			msg_set_bcast_ack(hdr, bc_ack);
			_skb = skb_clone(skb, GFP_ATOMIC);
			if (!_skb) {
				kfree_skb(skb);
				__skb_queue_purge(list);
				return -ENOBUFS;
			}
			__skb_queue_tail(transmq, skb);
			/* next retransmit attempt */
			if (link_is_bc_sndlink(l))
				TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
			__skb_queue_tail(xmitq, _skb);
			TIPC_SKB_CB(skb)->ackers = l->ackers;
			l->rcv_unacked = 0;
			l->stats.sent_pkts++;
			seqno++;
			continue;
		}
		if (tipc_msg_try_bundle(l->backlog[imp].target_bskb, &skb,
					mss, l->addr, &new_bundle)) {
			if (skb) {
				/* Keep a ref. to the skb for next try */
				l->backlog[imp].target_bskb = skb;
				l->backlog[imp].len++;
				__skb_queue_tail(backlogq, skb);
			} else {
				if (new_bundle) {
					l->stats.sent_bundles++;
					l->stats.sent_bundled++;
				}
				l->stats.sent_bundled++;
			}
			continue;
		}
		l->backlog[imp].target_bskb = NULL;
		l->backlog[imp].len += (1 + skb_queue_len(list));
		__skb_queue_tail(backlogq, skb);
		skb_queue_splice_tail_init(list, backlogq);
	}
	l->snd_nxt = seqno;
	return rc;
}

static void tipc_link_update_cwin(struct tipc_link *l, int released,
				  bool retransmitted)
{
	int bklog_len = skb_queue_len(&l->backlogq);
	struct sk_buff_head *txq = &l->transmq;
	int txq_len = skb_queue_len(txq);
	u16 cwin = l->window;

	/* Enter fast recovery */
	if (unlikely(retransmitted)) {
		l->ssthresh = max_t(u16, l->window / 2, 300);
		l->window = min_t(u16, l->ssthresh, l->window);
		return;
	}
	/* Enter slow start */
	if (unlikely(!released)) {
		l->ssthresh = max_t(u16, l->window / 2, 300);
		l->window = l->min_win;
		return;
	}
	/* Don't increase window if no pressure on the transmit queue */
	if (txq_len + bklog_len < cwin)
		return;

	/* Don't increase window if there are holes the transmit queue */
	if (txq_len && l->snd_nxt - buf_seqno(skb_peek(txq)) != txq_len)
		return;

	l->cong_acks += released;

	/* Slow start  */
	if (cwin <= l->ssthresh) {
		l->window = min_t(u16, cwin + released, l->max_win);
		return;
	}
	/* Congestion avoidance */
	if (l->cong_acks < cwin)
		return;
	l->window = min_t(u16, ++cwin, l->max_win);
	l->cong_acks = 0;
}

static void tipc_link_advance_backlog(struct tipc_link *l,
				      struct sk_buff_head *xmitq)
{
	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
	struct sk_buff_head *txq = &l->transmq;
	struct sk_buff *skb, *_skb;
	u16 ack = l->rcv_nxt - 1;
	u16 seqno = l->snd_nxt;
	struct tipc_msg *hdr;
	u16 cwin = l->window;
	u32 imp;

	while (skb_queue_len(txq) < cwin) {
		skb = skb_peek(&l->backlogq);
		if (!skb)
			break;
		_skb = skb_clone(skb, GFP_ATOMIC);
		if (!_skb)
			break;
		__skb_dequeue(&l->backlogq);
		hdr = buf_msg(skb);
		imp = msg_importance(hdr);
		l->backlog[imp].len--;
		if (unlikely(skb == l->backlog[imp].target_bskb))
			l->backlog[imp].target_bskb = NULL;
		__skb_queue_tail(&l->transmq, skb);
		/* next retransmit attempt */
		if (link_is_bc_sndlink(l))
			TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;

		__skb_queue_tail(xmitq, _skb);
		TIPC_SKB_CB(skb)->ackers = l->ackers;
		msg_set_seqno(hdr, seqno);
		msg_set_ack(hdr, ack);
		msg_set_bcast_ack(hdr, bc_ack);
		l->rcv_unacked = 0;
		l->stats.sent_pkts++;
		seqno++;
	}
	l->snd_nxt = seqno;
}

/**
 * link_retransmit_failure() - Detect repeated retransmit failures
 * @l: tipc link sender
 * @r: tipc link receiver (= l in case of unicast)
 * @rc: returned code
 *
 * Return: true if the repeated retransmit failures happens, otherwise
 * false
 */
static bool link_retransmit_failure(struct tipc_link *l, struct tipc_link *r,
				    int *rc)
{
	struct sk_buff *skb = skb_peek(&l->transmq);
	struct tipc_msg *hdr;

	if (!skb)
		return false;

	if (!TIPC_SKB_CB(skb)->retr_cnt)
		return false;

	if (!time_after(jiffies, TIPC_SKB_CB(skb)->retr_stamp +
			msecs_to_jiffies(r->tolerance * 10)))
		return false;

	hdr = buf_msg(skb);
	if (link_is_bc_sndlink(l) && !less(r->acked, msg_seqno(hdr)))
		return false;

	pr_warn("Retransmission failure on link <%s>\n", l->name);
	link_print(l, "State of link ");
	pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n",
		msg_user(hdr), msg_type(hdr), msg_size(hdr), msg_errcode(hdr));
	pr_info("sqno %u, prev: %x, dest: %x\n",
		msg_seqno(hdr), msg_prevnode(hdr), msg_destnode(hdr));
	pr_info("retr_stamp %d, retr_cnt %d\n",
		jiffies_to_msecs(TIPC_SKB_CB(skb)->retr_stamp),
		TIPC_SKB_CB(skb)->retr_cnt);

	trace_tipc_list_dump(&l->transmq, true, "retrans failure!");
	trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!");
	trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!");

	if (link_is_bc_sndlink(l)) {
		r->state = LINK_RESET;
		*rc = TIPC_LINK_DOWN_EVT;
	} else {
		*rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
	}

	return true;
}

/* tipc_link_bc_retrans() - retransmit zero or more packets
 * @l: the link to transmit on
 * @r: the receiving link ordering the retransmit. Same as l if unicast
 * @from: retransmit from (inclusive) this sequence number
 * @to: retransmit to (inclusive) this sequence number
 * xmitq: queue for accumulating the retransmitted packets
 */
static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r,
				u16 from, u16 to, struct sk_buff_head *xmitq)
{
	struct sk_buff *_skb, *skb = skb_peek(&l->transmq);
	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
	u16 ack = l->rcv_nxt - 1;
	int retransmitted = 0;
	struct tipc_msg *hdr;
	int rc = 0;

	if (!skb)
		return 0;
	if (less(to, from))
		return 0;

	trace_tipc_link_retrans(r, from, to, &l->transmq);

	if (link_retransmit_failure(l, r, &rc))
		return rc;

	skb_queue_walk(&l->transmq, skb) {
		hdr = buf_msg(skb);
		if (less(msg_seqno(hdr), from))
			continue;
		if (more(msg_seqno(hdr), to))
			break;
		if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
			continue;
		TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
		_skb = pskb_copy(skb, GFP_ATOMIC);
		if (!_skb)
			return 0;
		hdr = buf_msg(_skb);
		msg_set_ack(hdr, ack);
		msg_set_bcast_ack(hdr, bc_ack);
		_skb->priority = TC_PRIO_CONTROL;
		__skb_queue_tail(xmitq, _skb);
		l->stats.retransmitted++;
		retransmitted++;
		/* Increase actual retrans counter & mark first time */
		if (!TIPC_SKB_CB(skb)->retr_cnt++)
			TIPC_SKB_CB(skb)->retr_stamp = jiffies;
	}
	tipc_link_update_cwin(l, 0, retransmitted);
	return 0;
}

/* tipc_data_input - deliver data and name distr msgs to upper layer
 *
 * Consumes buffer if message is of right type
 * Node lock must be held
 */
static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
			    struct sk_buff_head *inputq)
{
	struct sk_buff_head *mc_inputq = l->bc_rcvlink->inputq;
	struct tipc_msg *hdr = buf_msg(skb);

	switch (msg_user(hdr)) {
	case TIPC_LOW_IMPORTANCE:
	case TIPC_MEDIUM_IMPORTANCE:
	case TIPC_HIGH_IMPORTANCE:
	case TIPC_CRITICAL_IMPORTANCE:
		if (unlikely(msg_in_group(hdr) || msg_mcast(hdr))) {
			skb_queue_tail(mc_inputq, skb);
			return true;
		}
		/* fall through */
	case CONN_MANAGER:
		skb_queue_tail(inputq, skb);
		return true;
	case GROUP_PROTOCOL:
		skb_queue_tail(mc_inputq, skb);
		return true;
	case NAME_DISTRIBUTOR:
		l->bc_rcvlink->state = LINK_ESTABLISHED;
		skb_queue_tail(l->namedq, skb);
		return true;
	case MSG_BUNDLER:
	case TUNNEL_PROTOCOL:
	case MSG_FRAGMENTER:
	case BCAST_PROTOCOL:
		return false;
	default:
		pr_warn("Dropping received illegal msg type\n");
		kfree_skb(skb);
		return true;
	};
}

/* tipc_link_input - process packet that has passed link protocol check
 *
 * Consumes buffer
 */
static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb,
			   struct sk_buff_head *inputq,
			   struct sk_buff **reasm_skb)
{
	struct tipc_msg *hdr = buf_msg(skb);
	struct sk_buff *iskb;
	struct sk_buff_head tmpq;
	int usr = msg_user(hdr);
	int pos = 0;

	if (usr == MSG_BUNDLER) {
		skb_queue_head_init(&tmpq);
		l->stats.recv_bundles++;
		l->stats.recv_bundled += msg_msgcnt(hdr);
		while (tipc_msg_extract(skb, &iskb, &pos))
			tipc_data_input(l, iskb, &tmpq);
		tipc_skb_queue_splice_tail(&tmpq, inputq);
		return 0;
	} else if (usr == MSG_FRAGMENTER) {
		l->stats.recv_fragments++;
		if (tipc_buf_append(reasm_skb, &skb)) {
			l->stats.recv_fragmented++;
			tipc_data_input(l, skb, inputq);
		} else if (!*reasm_skb && !link_is_bc_rcvlink(l)) {
			pr_warn_ratelimited("Unable to build fragment list\n");
			return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
		}
		return 0;
	} else if (usr == BCAST_PROTOCOL) {
		tipc_bcast_lock(l->net);
		tipc_link_bc_init_rcv(l->bc_rcvlink, hdr);
		tipc_bcast_unlock(l->net);
	}

	kfree_skb(skb);
	return 0;
}

/* tipc_link_tnl_rcv() - receive TUNNEL_PROTOCOL message, drop or process the
 *			 inner message along with the ones in the old link's
 *			 deferdq
 * @l: tunnel link
 * @skb: TUNNEL_PROTOCOL message
 * @inputq: queue to put messages ready for delivery
 */
static int tipc_link_tnl_rcv(struct tipc_link *l, struct sk_buff *skb,
			     struct sk_buff_head *inputq)
{
	struct sk_buff **reasm_skb = &l->failover_reasm_skb;
	struct sk_buff **reasm_tnlmsg = &l->reasm_tnlmsg;
	struct sk_buff_head *fdefq = &l->failover_deferdq;
	struct tipc_msg *hdr = buf_msg(skb);
	struct sk_buff *iskb;
	int ipos = 0;
	int rc = 0;
	u16 seqno;

	if (msg_type(hdr) == SYNCH_MSG) {
		kfree_skb(skb);
		return 0;
	}

	/* Not a fragment? */
	if (likely(!msg_nof_fragms(hdr))) {
		if (unlikely(!tipc_msg_extract(skb, &iskb, &ipos))) {
			pr_warn_ratelimited("Unable to extract msg, defq: %d\n",
					    skb_queue_len(fdefq));
			return 0;
		}
		kfree_skb(skb);
	} else {
		/* Set fragment type for buf_append */
		if (msg_fragm_no(hdr) == 1)
			msg_set_type(hdr, FIRST_FRAGMENT);
		else if (msg_fragm_no(hdr) < msg_nof_fragms(hdr))
			msg_set_type(hdr, FRAGMENT);
		else
			msg_set_type(hdr, LAST_FRAGMENT);

		if (!tipc_buf_append(reasm_tnlmsg, &skb)) {
			/* Successful but non-complete reassembly? */
			if (*reasm_tnlmsg || link_is_bc_rcvlink(l))
				return 0;
			pr_warn_ratelimited("Unable to reassemble tunnel msg\n");
			return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
		}
		iskb = skb;
	}

	do {
		seqno = buf_seqno(iskb);
		if (unlikely(less(seqno, l->drop_point))) {
			kfree_skb(iskb);
			continue;
		}
		if (unlikely(seqno != l->drop_point)) {
			__tipc_skb_queue_sorted(fdefq, seqno, iskb);
			continue;
		}

		l->drop_point++;
		if (!tipc_data_input(l, iskb, inputq))
			rc |= tipc_link_input(l, iskb, inputq, reasm_skb);
		if (unlikely(rc))
			break;
	} while ((iskb = __tipc_skb_dequeue(fdefq, l->drop_point)));

	return rc;
}

static int tipc_link_release_pkts(struct tipc_link *l, u16 acked)
{
	int released = 0;
	struct sk_buff *skb, *tmp;

	skb_queue_walk_safe(&l->transmq, skb, tmp) {
		if (more(buf_seqno(skb), acked))
			break;
		__skb_unlink(skb, &l->transmq);
		kfree_skb(skb);
		released++;
	}
	return released;
}

/* tipc_build_gap_ack_blks - build Gap ACK blocks
 * @l: tipc link that data have come with gaps in sequence if any
 * @data: data buffer to store the Gap ACK blocks after built
 *
 * returns the actual allocated memory size
 */
static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data, u16 gap)
{
	struct sk_buff *skb = skb_peek(&l->deferdq);
	struct tipc_gap_ack_blks *ga = data;
	u16 len, expect, seqno = 0;
	u8 n = 0;

	if (!skb || !gap)
		goto exit;

	expect = buf_seqno(skb);
	skb_queue_walk(&l->deferdq, skb) {
		seqno = buf_seqno(skb);
		if (unlikely(more(seqno, expect))) {
			ga->gacks[n].ack = htons(expect - 1);
			ga->gacks[n].gap = htons(seqno - expect);
			if (++n >= MAX_GAP_ACK_BLKS) {
				pr_info_ratelimited("Too few Gap ACK blocks!\n");
				goto exit;
			}
		} else if (unlikely(less(seqno, expect))) {
			pr_warn("Unexpected skb in deferdq!\n");
			continue;
		}
		expect = seqno + 1;
	}

	/* last block */
	ga->gacks[n].ack = htons(seqno);
	ga->gacks[n].gap = 0;
	n++;

exit:
	len = tipc_gap_ack_blks_sz(n);
	ga->len = htons(len);
	ga->gack_cnt = n;
	return len;
}

/* tipc_link_advance_transmq - advance TIPC link transmq queue by releasing
 *			       acked packets, also doing retransmissions if
 *			       gaps found
 * @l: tipc link with transmq queue to be advanced
 * @acked: seqno of last packet acked by peer without any gaps before
 * @gap: # of gap packets
 * @ga: buffer pointer to Gap ACK blocks from peer
 * @xmitq: queue for accumulating the retransmitted packets if any
 *
 * In case of a repeated retransmit failures, the call will return shortly
 * with a returned code (e.g. TIPC_LINK_DOWN_EVT)
 */
static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
				     struct tipc_gap_ack_blks *ga,
				     struct sk_buff_head *xmitq)
{
	struct sk_buff *skb, *_skb, *tmp;
	struct tipc_msg *hdr;
	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
	bool retransmitted = false;
	u16 ack = l->rcv_nxt - 1;
	bool passed = false;
	u16 released = 0;
	u16 seqno, n = 0;
	int rc = 0;

	skb_queue_walk_safe(&l->transmq, skb, tmp) {
		seqno = buf_seqno(skb);

next_gap_ack:
		if (less_eq(seqno, acked)) {
			/* release skb */
			__skb_unlink(skb, &l->transmq);
			kfree_skb(skb);
			released++;
		} else if (less_eq(seqno, acked + gap)) {
			/* First, check if repeated retrans failures occurs? */
			if (!passed && link_retransmit_failure(l, l, &rc))
				return rc;
			passed = true;

			/* retransmit skb if unrestricted*/
			if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
				continue;
			TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME;
			_skb = pskb_copy(skb, GFP_ATOMIC);
			if (!_skb)
				continue;
			hdr = buf_msg(_skb);
			msg_set_ack(hdr, ack);
			msg_set_bcast_ack(hdr, bc_ack);
			_skb->priority = TC_PRIO_CONTROL;
			__skb_queue_tail(xmitq, _skb);
			l->stats.retransmitted++;
			retransmitted = true;
			/* Increase actual retrans counter & mark first time */
			if (!TIPC_SKB_CB(skb)->retr_cnt++)
				TIPC_SKB_CB(skb)->retr_stamp = jiffies;
		} else {
			/* retry with Gap ACK blocks if any */
			if (!ga || n >= ga->gack_cnt)
				break;
			acked = ntohs(ga->gacks[n].ack);
			gap = ntohs(ga->gacks[n].gap);
			n++;
			goto next_gap_ack;
		}
	}
	if (released || retransmitted)
		tipc_link_update_cwin(l, released, retransmitted);
	if (released)
		tipc_link_advance_backlog(l, xmitq);
	return 0;
}

/* tipc_link_build_state_msg: prepare link state message for transmission
 *
 * Note that sending of broadcast ack is coordinated among nodes, to reduce
 * risk of ack storms towards the sender
 */
int tipc_link_build_state_msg(struct tipc_link *l, struct sk_buff_head *xmitq)
{
	if (!l)
		return 0;

	/* Broadcast ACK must be sent via a unicast link => defer to caller */
	if (link_is_bc_rcvlink(l)) {
		if (((l->rcv_nxt ^ tipc_own_addr(l->net)) & 0xf) != 0xf)
			return 0;
		l->rcv_unacked = 0;

		/* Use snd_nxt to store peer's snd_nxt in broadcast rcv link */
		l->snd_nxt = l->rcv_nxt;
		return TIPC_LINK_SND_STATE;
	}
	/* Unicast ACK */
	l->rcv_unacked = 0;
	l->stats.sent_acks++;
	tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq);
	return 0;
}

/* tipc_link_build_reset_msg: prepare link RESET or ACTIVATE message
 */
void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq)
{
	int mtyp = RESET_MSG;
	struct sk_buff *skb;

	if (l->state == LINK_ESTABLISHING)
		mtyp = ACTIVATE_MSG;

	tipc_link_build_proto_msg(l, mtyp, 0, 0, 0, 0, 0, xmitq);

	/* Inform peer that this endpoint is going down if applicable */
	skb = skb_peek_tail(xmitq);
	if (skb && (l->state == LINK_RESET))
		msg_set_peer_stopping(buf_msg(skb), 1);
}

/* tipc_link_build_nack_msg: prepare link nack message for transmission
 * Note that sending of broadcast NACK is coordinated among nodes, to
 * reduce the risk of NACK storms towards the sender
 */
static int tipc_link_build_nack_msg(struct tipc_link *l,
				    struct sk_buff_head *xmitq)
{
	u32 def_cnt = ++l->stats.deferred_recv;
	struct sk_buff_head *dfq = &l->deferdq;
	u32 defq_len = skb_queue_len(dfq);
	int match1, match2;

	if (link_is_bc_rcvlink(l)) {
		match1 = def_cnt & 0xf;
		match2 = tipc_own_addr(l->net) & 0xf;
		if (match1 == match2)
			return TIPC_LINK_SND_STATE;
		return 0;
	}

	if (defq_len >= 3 && !((defq_len - 3) % 16)) {
		u16 rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt;

		tipc_link_build_proto_msg(l, STATE_MSG, 0, 0,
					  rcvgap, 0, 0, xmitq);
	}
	return 0;
}

/* tipc_link_rcv - process TIPC packets/messages arriving from off-node
 * @l: the link that should handle the message
 * @skb: TIPC packet
 * @xmitq: queue to place packets to be sent after this call
 */
int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
		  struct sk_buff_head *xmitq)
{
	struct sk_buff_head *defq = &l->deferdq;
	struct tipc_msg *hdr = buf_msg(skb);
	u16 seqno, rcv_nxt, win_lim;
	int released = 0;
	int rc = 0;

	/* Verify and update link state */
	if (unlikely(msg_user(hdr) == LINK_PROTOCOL))
		return tipc_link_proto_rcv(l, skb, xmitq);

	/* Don't send probe at next timeout expiration */
	l->silent_intv_cnt = 0;

	do {
		hdr = buf_msg(skb);
		seqno = msg_seqno(hdr);
		rcv_nxt = l->rcv_nxt;
		win_lim = rcv_nxt + TIPC_MAX_LINK_WIN;

		if (unlikely(!link_is_up(l))) {
			if (l->state == LINK_ESTABLISHING)
				rc = TIPC_LINK_UP_EVT;
			kfree_skb(skb);
			break;
		}

		/* Drop if outside receive window */
		if (unlikely(less(seqno, rcv_nxt) || more(seqno, win_lim))) {
			l->stats.duplicates++;
			kfree_skb(skb);
			break;
		}
		released += tipc_link_release_pkts(l, msg_ack(hdr));

		/* Defer delivery if sequence gap */
		if (unlikely(seqno != rcv_nxt)) {
			__tipc_skb_queue_sorted(defq, seqno, skb);
			rc |= tipc_link_build_nack_msg(l, xmitq);
			break;
		}

		/* Deliver packet */
		l->rcv_nxt++;
		l->stats.recv_pkts++;

		if (unlikely(msg_user(hdr) == TUNNEL_PROTOCOL))
			rc |= tipc_link_tnl_rcv(l, skb, l->inputq);
		else if (!tipc_data_input(l, skb, l->inputq))
			rc |= tipc_link_input(l, skb, l->inputq, &l->reasm_buf);
		if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN))
			rc |= tipc_link_build_state_msg(l, xmitq);
		if (unlikely(rc & ~TIPC_LINK_SND_STATE))
			break;
	} while ((skb = __tipc_skb_dequeue(defq, l->rcv_nxt)));

	/* Forward queues and wake up waiting users */
	if (released) {
		tipc_link_update_cwin(l, released, 0);
		tipc_link_advance_backlog(l, xmitq);
		if (unlikely(!skb_queue_empty(&l->wakeupq)))
			link_prepare_wakeup(l);
	}
	return rc;
}

static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
				      bool probe_reply, u16 rcvgap,
				      int tolerance, int priority,
				      struct sk_buff_head *xmitq)
{
	struct tipc_link *bcl = l->bc_rcvlink;
	struct sk_buff *skb;
	struct tipc_msg *hdr;
	struct sk_buff_head *dfq = &l->deferdq;
	bool node_up = link_is_up(bcl);
	struct tipc_mon_state *mstate = &l->mon_state;
	int dlen = 0;
	void *data;
	u16 glen = 0;

	/* Don't send protocol message during reset or link failover */
	if (tipc_link_is_blocked(l))
		return;

	if (!tipc_link_is_up(l) && (mtyp == STATE_MSG))
		return;

	if ((probe || probe_reply) && !skb_queue_empty(dfq))
		rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt;

	skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE,
			      tipc_max_domain_size + MAX_GAP_ACK_BLKS_SZ,
			      l->addr, tipc_own_addr(l->net), 0, 0, 0);
	if (!skb)
		return;

	hdr = buf_msg(skb);
	data = msg_data(hdr);
	msg_set_session(hdr, l->session);
	msg_set_bearer_id(hdr, l->bearer_id);
	msg_set_net_plane(hdr, l->net_plane);
	msg_set_next_sent(hdr, l->snd_nxt);
	msg_set_ack(hdr, l->rcv_nxt - 1);
	msg_set_bcast_ack(hdr, bcl->rcv_nxt - 1);
	msg_set_bc_ack_invalid(hdr, !node_up);
	msg_set_last_bcast(hdr, l->bc_sndlink->snd_nxt - 1);
	msg_set_link_tolerance(hdr, tolerance);
	msg_set_linkprio(hdr, priority);
	msg_set_redundant_link(hdr, node_up);
	msg_set_seq_gap(hdr, 0);
	msg_set_seqno(hdr, l->snd_nxt + U16_MAX / 2);

	if (mtyp == STATE_MSG) {
		if (l->peer_caps & TIPC_LINK_PROTO_SEQNO)
			msg_set_seqno(hdr, l->snd_nxt_state++);
		msg_set_seq_gap(hdr, rcvgap);
		msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl));
		msg_set_probe(hdr, probe);
		msg_set_is_keepalive(hdr, probe || probe_reply);
		if (l->peer_caps & TIPC_GAP_ACK_BLOCK)
			glen = tipc_build_gap_ack_blks(l, data, rcvgap);
		tipc_mon_prep(l->net, data + glen, &dlen, mstate, l->bearer_id);
		msg_set_size(hdr, INT_H_SIZE + glen + dlen);
		skb_trim(skb, INT_H_SIZE + glen + dlen);
		l->stats.sent_states++;
		l->rcv_unacked = 0;
	} else {
		/* RESET_MSG or ACTIVATE_MSG */
		if (mtyp == ACTIVATE_MSG) {
			msg_set_dest_session_valid(hdr, 1);
			msg_set_dest_session(hdr, l->peer_session);
		}
		msg_set_max_pkt(hdr, l->advertised_mtu);
		strcpy(data, l->if_name);
		msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME);
		skb_trim(skb, INT_H_SIZE + TIPC_MAX_IF_NAME);
	}
	if (probe)
		l->stats.sent_probes++;
	if (rcvgap)
		l->stats.sent_nacks++;
	skb->priority = TC_PRIO_CONTROL;
	__skb_queue_tail(xmitq, skb);
	trace_tipc_proto_build(skb, false, l->name);
}

void tipc_link_create_dummy_tnl_msg(struct tipc_link *l,
				    struct sk_buff_head *xmitq)
{
	u32 onode = tipc_own_addr(l->net);
	struct tipc_msg *hdr, *ihdr;
	struct sk_buff_head tnlq;
	struct sk_buff *skb;
	u32 dnode = l->addr;

	__skb_queue_head_init(&tnlq);
	skb = tipc_msg_create(TUNNEL_PROTOCOL, FAILOVER_MSG,
			      INT_H_SIZE, BASIC_H_SIZE,
			      dnode, onode, 0, 0, 0);
	if (!skb) {
		pr_warn("%sunable to create tunnel packet\n", link_co_err);
		return;
	}

	hdr = buf_msg(skb);
	msg_set_msgcnt(hdr, 1);
	msg_set_bearer_id(hdr, l->peer_bearer_id);

	ihdr = (struct tipc_msg *)msg_data(hdr);
	tipc_msg_init(onode, ihdr, TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG,
		      BASIC_H_SIZE, dnode);
	msg_set_errcode(ihdr, TIPC_ERR_NO_PORT);
	__skb_queue_tail(&tnlq, skb);
	tipc_link_xmit(l, &tnlq, xmitq);
}

/* tipc_link_tnl_prepare(): prepare and return a list of tunnel packets
 * with contents of the link's transmit and backlog queues.
 */
void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl,
			   int mtyp, struct sk_buff_head *xmitq)
{
	struct sk_buff_head *fdefq = &tnl->failover_deferdq;
	struct sk_buff *skb, *tnlskb;
	struct tipc_msg *hdr, tnlhdr;
	struct sk_buff_head *queue = &l->transmq;
	struct sk_buff_head tmpxq, tnlq, frags;
	u16 pktlen, pktcnt, seqno = l->snd_nxt;
	bool pktcnt_need_update = false;
	u16 syncpt;
	int rc;

	if (!tnl)
		return;

	__skb_queue_head_init(&tnlq);
	/* Link Synching:
	 * From now on, send only one single ("dummy") SYNCH message
	 * to peer. The SYNCH message does not contain any data, just
	 * a header conveying the synch point to the peer.
	 */
	if (mtyp == SYNCH_MSG && (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) {
		tnlskb = tipc_msg_c…