mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-15 08:14:15 +08:00
8d6e79d3ce
Currently, the TIPC RPS dissector is based only on the incoming packets' source node address, hence steering all traffic from a node to the same core. We have seen that this makes the links vulnerable to starvation and unnecessary resets when we turn down the link tolerance to very low values. To reduce the risk of this happening, we exempt probe and probe replies packets from the convergence to one core per source node. Instead, we do the opposite, - we try to diverge those packets across as many cores as possible, by randomizing the flow selector key. To make such packets identifiable to the dissector, we add a new 'is_keepalive' bit to word 0 of the LINK_PROTOCOL header. This bit is set both for PROBE and PROBE_REPLY messages, and only for those. It should be noted that these packets are not part of any flow anyway, and only constitute a minuscule fraction of all packets sent across a link. Hence, there is no risk that this will affect overall performance. Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2143 lines
57 KiB
C
2143 lines
57 KiB
C
/*
|
|
* 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 <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
|
|
* @last_retransmitted: sequence number of most recently retransmitted message
|
|
* @stale_count: # of identical retransmit requests made by peer
|
|
* @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 */
|
|
u32 peer_session;
|
|
u32 session;
|
|
u32 peer_bearer_id;
|
|
u32 bearer_id;
|
|
u32 tolerance;
|
|
u32 abort_limit;
|
|
u32 state;
|
|
u16 peer_caps;
|
|
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;
|
|
|
|
/* Max packet negotiation */
|
|
u16 mtu;
|
|
u16 advertised_mtu;
|
|
|
|
/* Sending */
|
|
struct sk_buff_head transmq;
|
|
struct sk_buff_head backlogq;
|
|
struct {
|
|
u16 len;
|
|
u16 limit;
|
|
} backlog[5];
|
|
u16 snd_nxt;
|
|
u16 last_retransm;
|
|
u16 window;
|
|
u32 stale_count;
|
|
|
|
/* 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;
|
|
|
|
/* Fragmentation/reassembly */
|
|
struct sk_buff *reasm_buf;
|
|
|
|
/* Broadcast */
|
|
u16 ackers;
|
|
u16 acked;
|
|
struct tipc_link *bc_rcvlink;
|
|
struct tipc_link *bc_sndlink;
|
|
unsigned long prev_retr;
|
|
u16 prev_from;
|
|
u16 prev_to;
|
|
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_LIMIT 10 /* [ms] */
|
|
|
|
/*
|
|
* Interval between NACKs when packets arrive out of order
|
|
*/
|
|
#define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2)
|
|
|
|
/* Wildcard value for link session numbers. When it is known that
|
|
* peer endpoint is down, any session number must be accepted.
|
|
*/
|
|
#define ANY_SESSION 0x10000
|
|
|
|
/* 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 bool tipc_link_release_pkts(struct tipc_link *l, u16 to);
|
|
|
|
/*
|
|
* 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));
|
|
}
|
|
|
|
int tipc_link_is_active(struct tipc_link *l)
|
|
{
|
|
return l->active;
|
|
}
|
|
|
|
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_window(struct tipc_link *l)
|
|
{
|
|
return l->window;
|
|
}
|
|
|
|
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_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);
|
|
tipc_link_reset(rcv_l);
|
|
rcv_l->state = LINK_RESET;
|
|
if (!snd_l->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;
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
/**
|
|
* 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
|
|
* @window: 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,
|
|
int window, u32 session, u32 ownnode, u32 peer,
|
|
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)
|
|
{
|
|
struct tipc_link *l;
|
|
|
|
l = kzalloc(sizeof(*l), GFP_ATOMIC);
|
|
if (!l)
|
|
return false;
|
|
*link = l;
|
|
l->session = session;
|
|
|
|
/* Note: peer i/f name is completed by reset/activate message */
|
|
sprintf(l->name, "%u.%u.%u:%s-%u.%u.%u:unknown",
|
|
tipc_zone(ownnode), tipc_cluster(ownnode), tipc_node(ownnode),
|
|
if_name, tipc_zone(peer), tipc_cluster(peer), tipc_node(peer));
|
|
strcpy(l->if_name, if_name);
|
|
l->addr = peer;
|
|
l->peer_caps = peer_caps;
|
|
l->net = net;
|
|
l->peer_session = ANY_SESSION;
|
|
l->bearer_id = bearer_id;
|
|
l->tolerance = tolerance;
|
|
l->net_plane = net_plane;
|
|
l->advertised_mtu = mtu;
|
|
l->mtu = mtu;
|
|
l->priority = priority;
|
|
tipc_link_set_queue_limits(l, window);
|
|
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->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
|
|
* @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, int window, 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, window,
|
|
0, ownnode, peer, peer_caps, bc_sndlink,
|
|
NULL, inputq, namedq, link))
|
|
return false;
|
|
|
|
l = *link;
|
|
strcpy(l->name, tipc_bclink_name);
|
|
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_disable_rcast(net);
|
|
|
|
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;
|
|
|
|
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);
|
|
}
|
|
return rc;
|
|
illegal_evt:
|
|
pr_err("Illegal FSM event %x in state %x on link %s\n",
|
|
evt, l->state, l->name);
|
|
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_get_wrapped(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_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;
|
|
|
|
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++;
|
|
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++;
|
|
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
|
|
*/
|
|
void link_prepare_wakeup(struct tipc_link *l)
|
|
{
|
|
struct sk_buff *skb, *tmp;
|
|
int imp, i = 0;
|
|
|
|
skb_queue_walk_safe(&l->wakeupq, skb, tmp) {
|
|
imp = TIPC_SKB_CB(skb)->chain_imp;
|
|
if (l->backlog[imp].len < l->backlog[imp].limit) {
|
|
skb_unlink(skb, &l->wakeupq);
|
|
skb_queue_tail(l->inputq, skb);
|
|
} else if (i++ > 10) {
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
void tipc_link_reset(struct tipc_link *l)
|
|
{
|
|
l->peer_session = ANY_SESSION;
|
|
l->session++;
|
|
l->mtu = l->advertised_mtu;
|
|
__skb_queue_purge(&l->transmq);
|
|
__skb_queue_purge(&l->deferdq);
|
|
skb_queue_splice_init(&l->wakeupq, l->inputq);
|
|
__skb_queue_purge(&l->backlogq);
|
|
l->backlog[TIPC_LOW_IMPORTANCE].len = 0;
|
|
l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0;
|
|
l->backlog[TIPC_HIGH_IMPORTANCE].len = 0;
|
|
l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0;
|
|
l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0;
|
|
kfree_skb(l->reasm_buf);
|
|
kfree_skb(l->failover_reasm_skb);
|
|
l->reasm_buf = NULL;
|
|
l->failover_reasm_skb = NULL;
|
|
l->rcv_unacked = 0;
|
|
l->snd_nxt = 1;
|
|
l->rcv_nxt = 1;
|
|
l->acked = 0;
|
|
l->silent_intv_cnt = 0;
|
|
l->rst_cnt = 0;
|
|
l->stale_count = 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));
|
|
unsigned int maxwin = l->window;
|
|
int imp = msg_importance(hdr);
|
|
unsigned int mtu = l->mtu;
|
|
u16 ack = l->rcv_nxt - 1;
|
|
u16 seqno = l->snd_nxt;
|
|
u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
|
|
struct sk_buff_head *transmq = &l->transmq;
|
|
struct sk_buff_head *backlogq = &l->backlogq;
|
|
struct sk_buff *skb, *_skb, *bskb;
|
|
int pkt_cnt = skb_queue_len(list);
|
|
int rc = 0;
|
|
|
|
if (unlikely(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_queue_len(list)) {
|
|
skb = skb_peek(list);
|
|
hdr = buf_msg(skb);
|
|
msg_set_seqno(hdr, seqno);
|
|
msg_set_ack(hdr, ack);
|
|
msg_set_bcast_ack(hdr, bc_ack);
|
|
|
|
if (likely(skb_queue_len(transmq) < maxwin)) {
|
|
_skb = skb_clone(skb, GFP_ATOMIC);
|
|
if (!_skb) {
|
|
skb_queue_purge(list);
|
|
return -ENOBUFS;
|
|
}
|
|
__skb_dequeue(list);
|
|
__skb_queue_tail(transmq, skb);
|
|
__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_bundle(skb_peek_tail(backlogq), hdr, mtu)) {
|
|
kfree_skb(__skb_dequeue(list));
|
|
l->stats.sent_bundled++;
|
|
continue;
|
|
}
|
|
if (tipc_msg_make_bundle(&bskb, hdr, mtu, l->addr)) {
|
|
kfree_skb(__skb_dequeue(list));
|
|
__skb_queue_tail(backlogq, bskb);
|
|
l->backlog[msg_importance(buf_msg(bskb))].len++;
|
|
l->stats.sent_bundled++;
|
|
l->stats.sent_bundles++;
|
|
continue;
|
|
}
|
|
l->backlog[imp].len += skb_queue_len(list);
|
|
skb_queue_splice_tail_init(list, backlogq);
|
|
}
|
|
l->snd_nxt = seqno;
|
|
return rc;
|
|
}
|
|
|
|
void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq)
|
|
{
|
|
struct sk_buff *skb, *_skb;
|
|
struct tipc_msg *hdr;
|
|
u16 seqno = l->snd_nxt;
|
|
u16 ack = l->rcv_nxt - 1;
|
|
u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
|
|
|
|
while (skb_queue_len(&l->transmq) < l->window) {
|
|
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);
|
|
l->backlog[msg_importance(hdr)].len--;
|
|
__skb_queue_tail(&l->transmq, skb);
|
|
__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;
|
|
}
|
|
|
|
static void link_retransmit_failure(struct tipc_link *l, struct sk_buff *skb)
|
|
{
|
|
struct tipc_msg *hdr = buf_msg(skb);
|
|
|
|
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, src: %x\n",
|
|
msg_seqno(hdr), msg_prevnode(hdr), msg_orignode(hdr));
|
|
}
|
|
|
|
int tipc_link_retrans(struct tipc_link *l, struct tipc_link *nacker,
|
|
u16 from, u16 to, struct sk_buff_head *xmitq)
|
|
{
|
|
struct sk_buff *_skb, *skb = skb_peek(&l->transmq);
|
|
struct tipc_msg *hdr;
|
|
u16 ack = l->rcv_nxt - 1;
|
|
u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
|
|
|
|
if (!skb)
|
|
return 0;
|
|
|
|
/* Detect repeated retransmit failures on same packet */
|
|
if (nacker->last_retransm != buf_seqno(skb)) {
|
|
nacker->last_retransm = buf_seqno(skb);
|
|
nacker->stale_count = 1;
|
|
} else if (++nacker->stale_count > 100) {
|
|
link_retransmit_failure(l, skb);
|
|
nacker->stale_count = 0;
|
|
if (link_is_bc_sndlink(l))
|
|
return TIPC_LINK_DOWN_EVT;
|
|
return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
|
|
}
|
|
|
|
/* Move forward to where retransmission should start */
|
|
skb_queue_walk(&l->transmq, skb) {
|
|
if (!less(buf_seqno(skb), from))
|
|
break;
|
|
}
|
|
|
|
skb_queue_walk_from(&l->transmq, skb) {
|
|
if (more(buf_seqno(skb), to))
|
|
break;
|
|
hdr = buf_msg(skb);
|
|
_skb = __pskb_copy(skb, MIN_H_SIZE, 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++;
|
|
}
|
|
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;
|
|
}
|
|
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 false;
|
|
};
|
|
}
|
|
|
|
/* 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 tipc_msg *hdr = buf_msg(skb);
|
|
struct sk_buff **reasm_skb = &l->reasm_buf;
|
|
struct sk_buff *iskb;
|
|
struct sk_buff_head tmpq;
|
|
int usr = msg_user(hdr);
|
|
int rc = 0;
|
|
int pos = 0;
|
|
int ipos = 0;
|
|
|
|
if (unlikely(usr == TUNNEL_PROTOCOL)) {
|
|
if (msg_type(hdr) == SYNCH_MSG) {
|
|
__skb_queue_purge(&l->deferdq);
|
|
goto drop;
|
|
}
|
|
if (!tipc_msg_extract(skb, &iskb, &ipos))
|
|
return rc;
|
|
kfree_skb(skb);
|
|
skb = iskb;
|
|
hdr = buf_msg(skb);
|
|
if (less(msg_seqno(hdr), l->drop_point))
|
|
goto drop;
|
|
if (tipc_data_input(l, skb, inputq))
|
|
return rc;
|
|
usr = msg_user(hdr);
|
|
reasm_skb = &l->failover_reasm_skb;
|
|
}
|
|
|
|
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);
|
|
}
|
|
drop:
|
|
kfree_skb(skb);
|
|
return 0;
|
|
}
|
|
|
|
static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked)
|
|
{
|
|
bool released = false;
|
|
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 = true;
|
|
}
|
|
return released;
|
|
}
|
|
|
|
/* 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;
|
|
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 ((skb_queue_len(&l->deferdq) == 1) || !(def_cnt % TIPC_NACK_INTV))
|
|
tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 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;
|
|
u16 seqno, rcv_nxt, win_lim;
|
|
int rc = 0;
|
|
|
|
do {
|
|
hdr = buf_msg(skb);
|
|
seqno = msg_seqno(hdr);
|
|
rcv_nxt = l->rcv_nxt;
|
|
win_lim = rcv_nxt + TIPC_MAX_LINK_WIN;
|
|
|
|
/* Verify and update link state */
|
|
if (unlikely(msg_user(hdr) == LINK_PROTOCOL))
|
|
return tipc_link_proto_rcv(l, skb, xmitq);
|
|
|
|
if (unlikely(!link_is_up(l))) {
|
|
if (l->state == LINK_ESTABLISHING)
|
|
rc = TIPC_LINK_UP_EVT;
|
|
goto drop;
|
|
}
|
|
|
|
/* Don't send probe at next timeout expiration */
|
|
l->silent_intv_cnt = 0;
|
|
|
|
/* Drop if outside receive window */
|
|
if (unlikely(less(seqno, rcv_nxt) || more(seqno, win_lim))) {
|
|
l->stats.duplicates++;
|
|
goto drop;
|
|
}
|
|
|
|
/* Forward queues and wake up waiting users */
|
|
if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) {
|
|
tipc_link_advance_backlog(l, xmitq);
|
|
if (unlikely(!skb_queue_empty(&l->wakeupq)))
|
|
link_prepare_wakeup(l);
|
|
}
|
|
|
|
/* 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 (!tipc_data_input(l, skb, l->inputq))
|
|
rc |= tipc_link_input(l, skb, l->inputq);
|
|
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 = __skb_dequeue(defq)));
|
|
|
|
return rc;
|
|
drop:
|
|
kfree_skb(skb);
|
|
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;
|
|
|
|
/* 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 (!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, 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) {
|
|
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);
|
|
tipc_mon_prep(l->net, data, &dlen, mstate, l->bearer_id);
|
|
msg_set_size(hdr, INT_H_SIZE + dlen);
|
|
skb_trim(skb, INT_H_SIZE + dlen);
|
|
l->stats.sent_states++;
|
|
l->rcv_unacked = 0;
|
|
} else {
|
|
/* RESET_MSG or ACTIVATE_MSG */
|
|
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);
|
|
}
|
|
|
|
/* 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 *skb, *tnlskb;
|
|
struct tipc_msg *hdr, tnlhdr;
|
|
struct sk_buff_head *queue = &l->transmq;
|
|
struct sk_buff_head tmpxq, tnlq;
|
|
u16 pktlen, pktcnt, seqno = l->snd_nxt;
|
|
|
|
if (!tnl)
|
|
return;
|
|
|
|
skb_queue_head_init(&tnlq);
|
|
skb_queue_head_init(&tmpxq);
|
|
|
|
/* At least one packet required for safe algorithm => add dummy */
|
|
skb = tipc_msg_create(TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG,
|
|
BASIC_H_SIZE, 0, l->addr, tipc_own_addr(l->net),
|
|
0, 0, TIPC_ERR_NO_PORT);
|
|
if (!skb) {
|
|
pr_warn("%sunable to create tunnel packet\n", link_co_err);
|
|
return;
|
|
}
|
|
skb_queue_tail(&tnlq, skb);
|
|
tipc_link_xmit(l, &tnlq, &tmpxq);
|
|
__skb_queue_purge(&tmpxq);
|
|
|
|
/* Initialize reusable tunnel packet header */
|
|
tipc_msg_init(tipc_own_addr(l->net), &tnlhdr, TUNNEL_PROTOCOL,
|
|
mtyp, INT_H_SIZE, l->addr);
|
|
pktcnt = skb_queue_len(&l->transmq) + skb_queue_len(&l->backlogq);
|
|
msg_set_msgcnt(&tnlhdr, pktcnt);
|
|
msg_set_bearer_id(&tnlhdr, l->peer_bearer_id);
|
|
tnl:
|
|
/* Wrap each packet into a tunnel packet */
|
|
skb_queue_walk(queue, skb) {
|
|
hdr = buf_msg(skb);
|
|
if (queue == &l->backlogq)
|
|
msg_set_seqno(hdr, seqno++);
|
|
pktlen = msg_size(hdr);
|
|
msg_set_size(&tnlhdr, pktlen + INT_H_SIZE);
|
|
tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE, GFP_ATOMIC);
|
|
if (!tnlskb) {
|
|
pr_warn("%sunable to send packet\n", link_co_err);
|
|
return;
|
|
}
|
|
skb_copy_to_linear_data(tnlskb, &tnlhdr, INT_H_SIZE);
|
|
skb_copy_to_linear_data_offset(tnlskb, INT_H_SIZE, hdr, pktlen);
|
|
__skb_queue_tail(&tnlq, tnlskb);
|
|
}
|
|
if (queue != &l->backlogq) {
|
|
queue = &l->backlogq;
|
|
goto tnl;
|
|
}
|
|
|
|
tipc_link_xmit(tnl, &tnlq, xmitq);
|
|
|
|
if (mtyp == FAILOVER_MSG) {
|
|
tnl->drop_point = l->rcv_nxt;
|
|
tnl->failover_reasm_skb = l->reasm_buf;
|
|
l->reasm_buf = NULL;
|
|
}
|
|
}
|
|
|
|
/* tipc_link_proto_rcv(): receive link level protocol message :
|
|
* Note that network plane id propagates through the network, and may
|
|
* change at any time. The node with lowest numerical id determines
|
|
* network plane
|
|
*/
|
|
static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
|
|
struct sk_buff_head *xmitq)
|
|
{
|
|
struct tipc_msg *hdr = buf_msg(skb);
|
|
u16 rcvgap = 0;
|
|
u16 ack = msg_ack(hdr);
|
|
u16 gap = msg_seq_gap(hdr);
|
|
u16 peers_snd_nxt = msg_next_sent(hdr);
|
|
u16 peers_tol = msg_link_tolerance(hdr);
|
|
u16 peers_prio = msg_linkprio(hdr);
|
|
u16 rcv_nxt = l->rcv_nxt;
|
|
u16 dlen = msg_data_sz(hdr);
|
|
int mtyp = msg_type(hdr);
|
|
bool reply = msg_probe(hdr);
|
|
void *data;
|
|
char *if_name;
|
|
int rc = 0;
|
|
|
|
if (tipc_link_is_blocked(l) || !xmitq)
|
|
goto exit;
|
|
|
|
if (tipc_own_addr(l->net) > msg_prevnode(hdr))
|
|
l->net_plane = msg_net_plane(hdr);
|
|
|
|
skb_linearize(skb);
|
|
hdr = buf_msg(skb);
|
|
data = msg_data(hdr);
|
|
|
|
switch (mtyp) {
|
|
case RESET_MSG:
|
|
|
|
/* Ignore duplicate RESET with old session number */
|
|
if ((less_eq(msg_session(hdr), l->peer_session)) &&
|
|
(l->peer_session != ANY_SESSION))
|
|
break;
|
|
/* fall thru' */
|
|
|
|
case ACTIVATE_MSG:
|
|
|
|
/* Complete own link name with peer's interface name */
|
|
if_name = strrchr(l->name, ':') + 1;
|
|
if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME)
|
|
break;
|
|
if (msg_data_sz(hdr) < TIPC_MAX_IF_NAME)
|
|
break;
|
|
strncpy(if_name, data, TIPC_MAX_IF_NAME);
|
|
|
|
/* Update own tolerance if peer indicates a non-zero value */
|
|
if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL))
|
|
l->tolerance = peers_tol;
|
|
|
|
/* Update own priority if peer's priority is higher */
|
|
if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI))
|
|
l->priority = peers_prio;
|
|
|
|
/* ACTIVATE_MSG serves as PEER_RESET if link is already down */
|
|
if (msg_peer_stopping(hdr))
|
|
rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
|
|
else if ((mtyp == RESET_MSG) || !link_is_up(l))
|
|
rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
|
|
|
|
/* ACTIVATE_MSG takes up link if it was already locally reset */
|
|
if ((mtyp == ACTIVATE_MSG) && (l->state == LINK_ESTABLISHING))
|
|
rc = TIPC_LINK_UP_EVT;
|
|
|
|
l->peer_session = msg_session(hdr);
|
|
l->peer_bearer_id = msg_bearer_id(hdr);
|
|
if (l->mtu > msg_max_pkt(hdr))
|
|
l->mtu = msg_max_pkt(hdr);
|
|
break;
|
|
|
|
case STATE_MSG:
|
|
|
|
/* Update own tolerance if peer indicates a non-zero value */
|
|
if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL))
|
|
l->tolerance = peers_tol;
|
|
|
|
/* Update own prio if peer indicates a different value */
|
|
if ((peers_prio != l->priority) &&
|
|
in_range(peers_prio, 1, TIPC_MAX_LINK_PRI)) {
|
|
l->priority = peers_prio;
|
|
rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
|
|
}
|
|
|
|
l->silent_intv_cnt = 0;
|
|
l->stats.recv_states++;
|
|
if (msg_probe(hdr))
|
|
l->stats.recv_probes++;
|
|
|
|
if (!link_is_up(l)) {
|
|
if (l->state == LINK_ESTABLISHING)
|
|
rc = TIPC_LINK_UP_EVT;
|
|
break;
|
|
}
|
|
tipc_mon_rcv(l->net, data, dlen, l->addr,
|
|
&l->mon_state, l->bearer_id);
|
|
|
|
/* Send NACK if peer has sent pkts we haven't received yet */
|
|
if (more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l))
|
|
rcvgap = peers_snd_nxt - l->rcv_nxt;
|
|
if (rcvgap || reply)
|
|
tipc_link_build_proto_msg(l, STATE_MSG, 0, reply,
|
|
rcvgap, 0, 0, xmitq);
|
|
tipc_link_release_pkts(l, ack);
|
|
|
|
/* If NACK, retransmit will now start at right position */
|
|
if (gap) {
|
|
rc = tipc_link_retrans(l, l, ack + 1, ack + gap, xmitq);
|
|
l->stats.recv_nacks++;
|
|
}
|
|
|
|
tipc_link_advance_backlog(l, xmitq);
|
|
if (unlikely(!skb_queue_empty(&l->wakeupq)))
|
|
link_prepare_wakeup(l);
|
|
}
|
|
exit:
|
|
kfree_skb(skb);
|
|
return rc;
|
|
}
|
|
|
|
/* tipc_link_build_bc_proto_msg() - create broadcast protocol message
|
|
*/
|
|
static bool tipc_link_build_bc_proto_msg(struct tipc_link *l, bool bcast,
|
|
u16 peers_snd_nxt,
|
|
struct sk_buff_head *xmitq)
|
|
{
|
|
struct sk_buff *skb;
|
|
struct tipc_msg *hdr;
|
|
struct sk_buff *dfrd_skb = skb_peek(&l->deferdq);
|
|
u16 ack = l->rcv_nxt - 1;
|
|
u16 gap_to = peers_snd_nxt - 1;
|
|
|
|
skb = tipc_msg_create(BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE,
|
|
0, l->addr, tipc_own_addr(l->net), 0, 0, 0);
|
|
if (!skb)
|
|
return false;
|
|
hdr = buf_msg(skb);
|
|
msg_set_last_bcast(hdr, l->bc_sndlink->snd_nxt - 1);
|
|
msg_set_bcast_ack(hdr, ack);
|
|
msg_set_bcgap_after(hdr, ack);
|
|
if (dfrd_skb)
|
|
gap_to = buf_seqno(dfrd_skb) - 1;
|
|
msg_set_bcgap_to(hdr, gap_to);
|
|
msg_set_non_seq(hdr, bcast);
|
|
__skb_queue_tail(xmitq, skb);
|
|
return true;
|
|
}
|
|
|
|
/* tipc_link_build_bc_init_msg() - synchronize broadcast link endpoints.
|
|
*
|
|
* Give a newly added peer node the sequence number where it should
|
|
* start receiving and acking broadcast packets.
|
|
*/
|
|
static void tipc_link_build_bc_init_msg(struct tipc_link *l,
|
|
struct sk_buff_head *xmitq)
|
|
{
|
|
struct sk_buff_head list;
|
|
|
|
__skb_queue_head_init(&list);
|
|
if (!tipc_link_build_bc_proto_msg(l->bc_rcvlink, false, 0, &list))
|
|
return;
|
|
msg_set_bc_ack_invalid(buf_msg(skb_peek(&list)), true);
|
|
tipc_link_xmit(l, &list, xmitq);
|
|
}
|
|
|
|
/* tipc_link_bc_init_rcv - receive initial broadcast synch data from peer
|
|
*/
|
|
void tipc_link_bc_init_rcv(struct tipc_link *l, struct tipc_msg *hdr)
|
|
{
|
|
int mtyp = msg_type(hdr);
|
|
u16 peers_snd_nxt = msg_bc_snd_nxt(hdr);
|
|
|
|
if (link_is_up(l))
|
|
return;
|
|
|
|
if (msg_user(hdr) == BCAST_PROTOCOL) {
|
|
l->rcv_nxt = peers_snd_nxt;
|
|
l->state = LINK_ESTABLISHED;
|
|
return;
|
|
}
|
|
|
|
if (l->peer_caps & TIPC_BCAST_SYNCH)
|
|
return;
|
|
|
|
if (msg_peer_node_is_up(hdr))
|
|
return;
|
|
|
|
/* Compatibility: accept older, less safe initial synch data */
|
|
if ((mtyp == RESET_MSG) || (mtyp == ACTIVATE_MSG))
|
|
l->rcv_nxt = peers_snd_nxt;
|
|
}
|
|
|
|
/* link_bc_retr eval()- check if the indicated range can be retransmitted now
|
|
* - Adjust permitted range if there is overlap with previous retransmission
|
|
*/
|
|
static bool link_bc_retr_eval(struct tipc_link *l, u16 *from, u16 *to)
|
|
{
|
|
unsigned long elapsed = jiffies_to_msecs(jiffies - l->prev_retr);
|
|
|
|
if (less(*to, *from))
|
|
return false;
|
|
|
|
/* New retransmission request */
|
|
if ((elapsed > TIPC_BC_RETR_LIMIT) ||
|
|
less(*to, l->prev_from) || more(*from, l->prev_to)) {
|
|
l->prev_from = *from;
|
|
l->prev_to = *to;
|
|
l->prev_retr = jiffies;
|
|
return true;
|
|
}
|
|
|
|
/* Inside range of previous retransmit */
|
|
if (!less(*from, l->prev_from) && !more(*to, l->prev_to))
|
|
return false;
|
|
|
|
/* Fully or partially outside previous range => exclude overlap */
|
|
if (less(*from, l->prev_from)) {
|
|
*to = l->prev_from - 1;
|
|
l->prev_from = *from;
|
|
}
|
|
if (more(*to, l->prev_to)) {
|
|
*from = l->prev_to + 1;
|
|
l->prev_to = *to;
|
|
}
|
|
l->prev_retr = jiffies;
|
|
return true;
|
|
}
|
|
|
|
/* tipc_link_bc_sync_rcv - update rcv link according to peer's send state
|
|
*/
|
|
int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr,
|
|
struct sk_buff_head *xmitq)
|
|
{
|
|
struct tipc_link *snd_l = l->bc_sndlink;
|
|
u16 peers_snd_nxt = msg_bc_snd_nxt(hdr);
|
|
u16 from = msg_bcast_ack(hdr) + 1;
|
|
u16 to = from + msg_bc_gap(hdr) - 1;
|
|
int rc = 0;
|
|
|
|
if (!link_is_up(l))
|
|
return rc;
|
|
|
|
if (!msg_peer_node_is_up(hdr))
|
|
return rc;
|
|
|
|
/* Open when peer ackowledges our bcast init msg (pkt #1) */
|
|
if (msg_ack(hdr))
|
|
l->bc_peer_is_up = true;
|
|
|
|
if (!l->bc_peer_is_up)
|
|
return rc;
|
|
|
|
l->stats.recv_nacks++;
|
|
|
|
/* Ignore if peers_snd_nxt goes beyond receive window */
|
|
if (more(peers_snd_nxt, l->rcv_nxt + l->window))
|
|
return rc;
|
|
|
|
if (link_bc_retr_eval(snd_l, &from, &to))
|
|
rc = tipc_link_retrans(snd_l, l, from, to, xmitq);
|
|
|
|
l->snd_nxt = peers_snd_nxt;
|
|
if (link_bc_rcv_gap(l))
|
|
rc |= TIPC_LINK_SND_STATE;
|
|
|
|
/* Return now if sender supports nack via STATE messages */
|
|
if (l->peer_caps & TIPC_BCAST_STATE_NACK)
|
|
return rc;
|
|
|
|
/* Otherwise, be backwards compatible */
|
|
|
|
if (!more(peers_snd_nxt, l->rcv_nxt)) {
|
|
l->nack_state = BC_NACK_SND_CONDITIONAL;
|
|
return 0;
|
|
}
|
|
|
|
/* Don't NACK if one was recently sent or peeked */
|
|
if (l->nack_state == BC_NACK_SND_SUPPRESS) {
|
|
l->nack_state = BC_NACK_SND_UNCONDITIONAL;
|
|
return 0;
|
|
}
|
|
|
|
/* Conditionally delay NACK sending until next synch rcv */
|
|
if (l->nack_state == BC_NACK_SND_CONDITIONAL) {
|
|
l->nack_state = BC_NACK_SND_UNCONDITIONAL;
|
|
if ((peers_snd_nxt - l->rcv_nxt) < TIPC_MIN_LINK_WIN)
|
|
return 0;
|
|
}
|
|
|
|
/* Send NACK now but suppress next one */
|
|
tipc_link_build_bc_proto_msg(l, true, peers_snd_nxt, xmitq);
|
|
l->nack_state = BC_NACK_SND_SUPPRESS;
|
|
return 0;
|
|
}
|
|
|
|
void tipc_link_bc_ack_rcv(struct tipc_link *l, u16 acked,
|
|
struct sk_buff_head *xmitq)
|
|
{
|
|
struct sk_buff *skb, *tmp;
|
|
struct tipc_link *snd_l = l->bc_sndlink;
|
|
|
|
if (!link_is_up(l) || !l->bc_peer_is_up)
|
|
return;
|
|
|
|
if (!more(acked, l->acked))
|
|
return;
|
|
|
|
/* Skip over packets peer has already acked */
|
|
skb_queue_walk(&snd_l->transmq, skb) {
|
|
if (more(buf_seqno(skb), l->acked))
|
|
break;
|
|
}
|
|
|
|
/* Update/release the packets peer is acking now */
|
|
skb_queue_walk_from_safe(&snd_l->transmq, skb, tmp) {
|
|
if (more(buf_seqno(skb), acked))
|
|
break;
|
|
if (!--TIPC_SKB_CB(skb)->ackers) {
|
|
__skb_unlink(skb, &snd_l->transmq);
|
|
kfree_skb(skb);
|
|
}
|
|
}
|
|
l->acked = acked;
|
|
tipc_link_advance_backlog(snd_l, xmitq);
|
|
if (unlikely(!skb_queue_empty(&snd_l->wakeupq)))
|
|
link_prepare_wakeup(snd_l);
|
|
}
|
|
|
|
/* tipc_link_bc_nack_rcv(): receive broadcast nack message
|
|
* This function is here for backwards compatibility, since
|
|
* no BCAST_PROTOCOL/STATE messages occur from TIPC v2.5.
|
|
*/
|
|
int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb,
|
|
struct sk_buff_head *xmitq)
|
|
{
|
|
struct tipc_msg *hdr = buf_msg(skb);
|
|
u32 dnode = msg_destnode(hdr);
|
|
int mtyp = msg_type(hdr);
|
|
u16 acked = msg_bcast_ack(hdr);
|
|
u16 from = acked + 1;
|
|
u16 to = msg_bcgap_to(hdr);
|
|
u16 peers_snd_nxt = to + 1;
|
|
int rc = 0;
|
|
|
|
kfree_skb(skb);
|
|
|
|
if (!tipc_link_is_up(l) || !l->bc_peer_is_up)
|
|
return 0;
|
|
|
|
if (mtyp != STATE_MSG)
|
|
return 0;
|
|
|
|
if (dnode == tipc_own_addr(l->net)) {
|
|
tipc_link_bc_ack_rcv(l, acked, xmitq);
|
|
rc = tipc_link_retrans(l->bc_sndlink, l, from, to, xmitq);
|
|
l->stats.recv_nacks++;
|
|
return rc;
|
|
}
|
|
|
|
/* Msg for other node => suppress own NACK at next sync if applicable */
|
|
if (more(peers_snd_nxt, l->rcv_nxt) && !less(l->rcv_nxt, from))
|
|
l->nack_state = BC_NACK_SND_SUPPRESS;
|
|
|
|
return 0;
|
|
}
|
|
|
|
void tipc_link_set_queue_limits(struct tipc_link *l, u32 win)
|
|
{
|
|
int max_bulk = TIPC_MAX_PUBLICATIONS / (l->mtu / ITEM_SIZE);
|
|
|
|
l->window = win;
|
|
l->backlog[TIPC_LOW_IMPORTANCE].limit = max_t(u16, 50, win);
|
|
l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = max_t(u16, 100, win * 2);
|
|
l->backlog[TIPC_HIGH_IMPORTANCE].limit = max_t(u16, 150, win * 3);
|
|
l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = max_t(u16, 200, win * 4);
|
|
l->backlog[TIPC_SYSTEM_IMPORTANCE].limit = max_bulk;
|
|
}
|
|
|
|
/**
|
|
* link_reset_stats - reset link statistics
|
|
* @l: pointer to link
|
|
*/
|
|
void tipc_link_reset_stats(struct tipc_link *l)
|
|
{
|
|
memset(&l->stats, 0, sizeof(l->stats));
|
|
}
|
|
|
|
static void link_print(struct tipc_link *l, const char *str)
|
|
{
|
|
struct sk_buff *hskb = skb_peek(&l->transmq);
|
|
u16 head = hskb ? msg_seqno(buf_msg(hskb)) : l->snd_nxt - 1;
|
|
u16 tail = l->snd_nxt - 1;
|
|
|
|
pr_info("%s Link <%s> state %x\n", str, l->name, l->state);
|
|
pr_info("XMTQ: %u [%u-%u], BKLGQ: %u, SNDNX: %u, RCVNX: %u\n",
|
|
skb_queue_len(&l->transmq), head, tail,
|
|
skb_queue_len(&l->backlogq), l->snd_nxt, l->rcv_nxt);
|
|
}
|
|
|
|
/* Parse and validate nested (link) properties valid for media, bearer and link
|
|
*/
|
|
int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[])
|
|
{
|
|
int err;
|
|
|
|
err = nla_parse_nested(props, TIPC_NLA_PROP_MAX, prop,
|
|
tipc_nl_prop_policy, NULL);
|
|
if (err)
|
|
return err;
|
|
|
|
if (props[TIPC_NLA_PROP_PRIO]) {
|
|
u32 prio;
|
|
|
|
prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
|
|
if (prio > TIPC_MAX_LINK_PRI)
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (props[TIPC_NLA_PROP_TOL]) {
|
|
u32 tol;
|
|
|
|
tol = nla_get_u32(props[TIPC_NLA_PROP_TOL]);
|
|
if ((tol < TIPC_MIN_LINK_TOL) || (tol > TIPC_MAX_LINK_TOL))
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (props[TIPC_NLA_PROP_WIN]) {
|
|
u32 win;
|
|
|
|
win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
|
|
if ((win < TIPC_MIN_LINK_WIN) || (win > TIPC_MAX_LINK_WIN))
|
|
return -EINVAL;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s)
|
|
{
|
|
int i;
|
|
struct nlattr *stats;
|
|
|
|
struct nla_map {
|
|
u32 key;
|
|
u32 val;
|
|
};
|
|
|
|
struct nla_map map[] = {
|
|
{TIPC_NLA_STATS_RX_INFO, 0},
|
|
{TIPC_NLA_STATS_RX_FRAGMENTS, s->recv_fragments},
|
|
{TIPC_NLA_STATS_RX_FRAGMENTED, s->recv_fragmented},
|
|
{TIPC_NLA_STATS_RX_BUNDLES, s->recv_bundles},
|
|
{TIPC_NLA_STATS_RX_BUNDLED, s->recv_bundled},
|
|
{TIPC_NLA_STATS_TX_INFO, 0},
|
|
{TIPC_NLA_STATS_TX_FRAGMENTS, s->sent_fragments},
|
|
{TIPC_NLA_STATS_TX_FRAGMENTED, s->sent_fragmented},
|
|
{TIPC_NLA_STATS_TX_BUNDLES, s->sent_bundles},
|
|
{TIPC_NLA_STATS_TX_BUNDLED, s->sent_bundled},
|
|
{TIPC_NLA_STATS_MSG_PROF_TOT, (s->msg_length_counts) ?
|
|
s->msg_length_counts : 1},
|
|
{TIPC_NLA_STATS_MSG_LEN_CNT, s->msg_length_counts},
|
|
{TIPC_NLA_STATS_MSG_LEN_TOT, s->msg_lengths_total},
|
|
{TIPC_NLA_STATS_MSG_LEN_P0, s->msg_length_profile[0]},
|
|
{TIPC_NLA_STATS_MSG_LEN_P1, s->msg_length_profile[1]},
|
|
{TIPC_NLA_STATS_MSG_LEN_P2, s->msg_length_profile[2]},
|
|
{TIPC_NLA_STATS_MSG_LEN_P3, s->msg_length_profile[3]},
|
|
{TIPC_NLA_STATS_MSG_LEN_P4, s->msg_length_profile[4]},
|
|
{TIPC_NLA_STATS_MSG_LEN_P5, s->msg_length_profile[5]},
|
|
{TIPC_NLA_STATS_MSG_LEN_P6, s->msg_length_profile[6]},
|
|
{TIPC_NLA_STATS_RX_STATES, s->recv_states},
|
|
{TIPC_NLA_STATS_RX_PROBES, s->recv_probes},
|
|
{TIPC_NLA_STATS_RX_NACKS, s->recv_nacks},
|
|
{TIPC_NLA_STATS_RX_DEFERRED, s->deferred_recv},
|
|
{TIPC_NLA_STATS_TX_STATES, s->sent_states},
|
|
{TIPC_NLA_STATS_TX_PROBES, s->sent_probes},
|
|
{TIPC_NLA_STATS_TX_NACKS, s->sent_nacks},
|
|
{TIPC_NLA_STATS_TX_ACKS, s->sent_acks},
|
|
{TIPC_NLA_STATS_RETRANSMITTED, s->retransmitted},
|
|
{TIPC_NLA_STATS_DUPLICATES, s->duplicates},
|
|
{TIPC_NLA_STATS_LINK_CONGS, s->link_congs},
|
|
{TIPC_NLA_STATS_MAX_QUEUE, s->max_queue_sz},
|
|
{TIPC_NLA_STATS_AVG_QUEUE, s->queue_sz_counts ?
|
|
(s->accu_queue_sz / s->queue_sz_counts) : 0}
|
|
};
|
|
|
|
stats = nla_nest_start(skb, TIPC_NLA_LINK_STATS);
|
|
if (!stats)
|
|
return -EMSGSIZE;
|
|
|
|
for (i = 0; i < ARRAY_SIZE(map); i++)
|
|
if (nla_put_u32(skb, map[i].key, map[i].val))
|
|
goto msg_full;
|
|
|
|
nla_nest_end(skb, stats);
|
|
|
|
return 0;
|
|
msg_full:
|
|
nla_nest_cancel(skb, stats);
|
|
|
|
return -EMSGSIZE;
|
|
}
|
|
|
|
/* Caller should hold appropriate locks to protect the link */
|
|
int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg,
|
|
struct tipc_link *link, int nlflags)
|
|
{
|
|
int err;
|
|
void *hdr;
|
|
struct nlattr *attrs;
|
|
struct nlattr *prop;
|
|
struct tipc_net *tn = net_generic(net, tipc_net_id);
|
|
|
|
hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
|
|
nlflags, TIPC_NL_LINK_GET);
|
|
if (!hdr)
|
|
return -EMSGSIZE;
|
|
|
|
attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
|
|
if (!attrs)
|
|
goto msg_full;
|
|
|
|
if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, link->name))
|
|
goto attr_msg_full;
|
|
if (nla_put_u32(msg->skb, TIPC_NLA_LINK_DEST,
|
|
tipc_cluster_mask(tn->own_addr)))
|
|
goto attr_msg_full;
|
|
if (nla_put_u32(msg->skb, TIPC_NLA_LINK_MTU, link->mtu))
|
|
goto attr_msg_full;
|
|
if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->stats.recv_pkts))
|
|
goto attr_msg_full;
|
|
if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->stats.sent_pkts))
|
|
goto attr_msg_full;
|
|
|
|
if (tipc_link_is_up(link))
|
|
if (nla_put_flag(msg->skb, TIPC_NLA_LINK_UP))
|
|
goto attr_msg_full;
|
|
if (link->active)
|
|
if (nla_put_flag(msg->skb, TIPC_NLA_LINK_ACTIVE))
|
|
goto attr_msg_full;
|
|
|
|
prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP);
|
|
if (!prop)
|
|
goto attr_msg_full;
|
|
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority))
|
|
goto prop_msg_full;
|
|
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, link->tolerance))
|
|
goto prop_msg_full;
|
|
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN,
|
|
link->window))
|
|
goto prop_msg_full;
|
|
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority))
|
|
goto prop_msg_full;
|
|
nla_nest_end(msg->skb, prop);
|
|
|
|
err = __tipc_nl_add_stats(msg->skb, &link->stats);
|
|
if (err)
|
|
goto attr_msg_full;
|
|
|
|
nla_nest_end(msg->skb, attrs);
|
|
genlmsg_end(msg->skb, hdr);
|
|
|
|
return 0;
|
|
|
|
prop_msg_full:
|
|
nla_nest_cancel(msg->skb, prop);
|
|
attr_msg_full:
|
|
nla_nest_cancel(msg->skb, attrs);
|
|
msg_full:
|
|
genlmsg_cancel(msg->skb, hdr);
|
|
|
|
return -EMSGSIZE;
|
|
}
|
|
|
|
static int __tipc_nl_add_bc_link_stat(struct sk_buff *skb,
|
|
struct tipc_stats *stats)
|
|
{
|
|
int i;
|
|
struct nlattr *nest;
|
|
|
|
struct nla_map {
|
|
__u32 key;
|
|
__u32 val;
|
|
};
|
|
|
|
struct nla_map map[] = {
|
|
{TIPC_NLA_STATS_RX_INFO, stats->recv_pkts},
|
|
{TIPC_NLA_STATS_RX_FRAGMENTS, stats->recv_fragments},
|
|
{TIPC_NLA_STATS_RX_FRAGMENTED, stats->recv_fragmented},
|
|
{TIPC_NLA_STATS_RX_BUNDLES, stats->recv_bundles},
|
|
{TIPC_NLA_STATS_RX_BUNDLED, stats->recv_bundled},
|
|
{TIPC_NLA_STATS_TX_INFO, stats->sent_pkts},
|
|
{TIPC_NLA_STATS_TX_FRAGMENTS, stats->sent_fragments},
|
|
{TIPC_NLA_STATS_TX_FRAGMENTED, stats->sent_fragmented},
|
|
{TIPC_NLA_STATS_TX_BUNDLES, stats->sent_bundles},
|
|
{TIPC_NLA_STATS_TX_BUNDLED, stats->sent_bundled},
|
|
{TIPC_NLA_STATS_RX_NACKS, stats->recv_nacks},
|
|
{TIPC_NLA_STATS_RX_DEFERRED, stats->deferred_recv},
|
|
{TIPC_NLA_STATS_TX_NACKS, stats->sent_nacks},
|
|
{TIPC_NLA_STATS_TX_ACKS, stats->sent_acks},
|
|
{TIPC_NLA_STATS_RETRANSMITTED, stats->retransmitted},
|
|
{TIPC_NLA_STATS_DUPLICATES, stats->duplicates},
|
|
{TIPC_NLA_STATS_LINK_CONGS, stats->link_congs},
|
|
{TIPC_NLA_STATS_MAX_QUEUE, stats->max_queue_sz},
|
|
{TIPC_NLA_STATS_AVG_QUEUE, stats->queue_sz_counts ?
|
|
(stats->accu_queue_sz / stats->queue_sz_counts) : 0}
|
|
};
|
|
|
|
nest = nla_nest_start(skb, TIPC_NLA_LINK_STATS);
|
|
if (!nest)
|
|
return -EMSGSIZE;
|
|
|
|
for (i = 0; i < ARRAY_SIZE(map); i++)
|
|
if (nla_put_u32(skb, map[i].key, map[i].val))
|
|
goto msg_full;
|
|
|
|
nla_nest_end(skb, nest);
|
|
|
|
return 0;
|
|
msg_full:
|
|
nla_nest_cancel(skb, nest);
|
|
|
|
return -EMSGSIZE;
|
|
}
|
|
|
|
int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg)
|
|
{
|
|
int err;
|
|
void *hdr;
|
|
struct nlattr *attrs;
|
|
struct nlattr *prop;
|
|
struct tipc_net *tn = net_generic(net, tipc_net_id);
|
|
struct tipc_link *bcl = tn->bcl;
|
|
|
|
if (!bcl)
|
|
return 0;
|
|
|
|
tipc_bcast_lock(net);
|
|
|
|
hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
|
|
NLM_F_MULTI, TIPC_NL_LINK_GET);
|
|
if (!hdr) {
|
|
tipc_bcast_unlock(net);
|
|
return -EMSGSIZE;
|
|
}
|
|
|
|
attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
|
|
if (!attrs)
|
|
goto msg_full;
|
|
|
|
/* The broadcast link is always up */
|
|
if (nla_put_flag(msg->skb, TIPC_NLA_LINK_UP))
|
|
goto attr_msg_full;
|
|
|
|
if (nla_put_flag(msg->skb, TIPC_NLA_LINK_BROADCAST))
|
|
goto attr_msg_full;
|
|
if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, bcl->name))
|
|
goto attr_msg_full;
|
|
if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, 0))
|
|
goto attr_msg_full;
|
|
if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, 0))
|
|
goto attr_msg_full;
|
|
|
|
prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP);
|
|
if (!prop)
|
|
goto attr_msg_full;
|
|
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->window))
|
|
goto prop_msg_full;
|
|
nla_nest_end(msg->skb, prop);
|
|
|
|
err = __tipc_nl_add_bc_link_stat(msg->skb, &bcl->stats);
|
|
if (err)
|
|
goto attr_msg_full;
|
|
|
|
tipc_bcast_unlock(net);
|
|
nla_nest_end(msg->skb, attrs);
|
|
genlmsg_end(msg->skb, hdr);
|
|
|
|
return 0;
|
|
|
|
prop_msg_full:
|
|
nla_nest_cancel(msg->skb, prop);
|
|
attr_msg_full:
|
|
nla_nest_cancel(msg->skb, attrs);
|
|
msg_full:
|
|
tipc_bcast_unlock(net);
|
|
genlmsg_cancel(msg->skb, hdr);
|
|
|
|
return -EMSGSIZE;
|
|
}
|
|
|
|
void tipc_link_set_tolerance(struct tipc_link *l, u32 tol,
|
|
struct sk_buff_head *xmitq)
|
|
{
|
|
l->tolerance = tol;
|
|
tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq);
|
|
}
|
|
|
|
void tipc_link_set_prio(struct tipc_link *l, u32 prio,
|
|
struct sk_buff_head *xmitq)
|
|
{
|
|
l->priority = prio;
|
|
tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, prio, xmitq);
|
|
}
|
|
|
|
void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit)
|
|
{
|
|
l->abort_limit = limit;
|
|
}
|