/* * 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.
*/
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 * @net: pointer to namespace struct * @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 * @priority: current link priority * @net_plane: current link network plane ('A' through 'H') * @mon_state: cookie with information needed by link monitor * @mtu: current maximum packet size for this link * @advertised_mtu: advertised own mtu when link is being established * @backlogq: queue for messages waiting to be sent * @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 * @inputq: buffer queue for messages to be delivered upwards * @namedq: buffer queue for name table messages to be delivered upwards * @wakeupq: linked list of wakeup msgs waiting for link congestion to abate * @reasm_buf: head of partially reassembled inbound message fragments * @stats: collects statistics regarding link activity * @session: session to be used by link * @snd_nxt_state: next send seq number * @rcv_nxt_state: next rcv seq number * @in_session: have received ACTIVATE_MSG from peer * @active: link is active * @if_name: associated interface name * @rst_cnt: link reset counter * @drop_point: seq number for failover handling (FIXME) * @failover_reasm_skb: saved failover msg ptr (FIXME) * @failover_deferdq: deferred message queue for failover processing (FIXME) * @transmq: the link's transmit queue * @backlog: link's backlog by priority (importance) * @snd_nxt: next sequence number to be used * @rcv_unacked: # messages read by user, but not yet acked back to peer * @deferdq: deferred receive queue * @window: sliding window size for congestion handling * @min_win: minimal send window to be used by link * @ssthresh: slow start threshold for congestion handling * @max_win: maximal send window to be used by link * @cong_acks: congestion acks for congestion avoidance (FIXME) * @checkpoint: seq number for congestion window size handling * @reasm_tnlmsg: fragmentation/reassembly area for tunnel protocol message * @last_gap: last gap ack blocks for bcast (FIXME) * @last_ga: ptr to gap ack blocks * @bc_rcvlink: the peer specific link used for broadcast reception * @bc_sndlink: the namespace global link used for broadcast sending * @nack_state: bcast nack state * @bc_peer_is_up: peer has acked the bcast init msg
*/ struct tipc_link {
u32 addr; char name[TIPC_MAX_LINK_NAME]; struct net *net;
/** * tipc_link_create - create a new link * @net: pointer to associated network namespace * @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 * @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 * @self: local unicast link id * @peer_id: 128-bit ID of peer * * Return: 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) returnfalse;
*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);
/** * tipc_link_bc_create - create new link to be used for broadcast * @net: pointer to associated network namespace * @mtu: mtu to be used initially if no peers * @min_win: minimal send window to be used by link * @max_win: maximal send window to be used by link * @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 * @ownnode: identity of own node * @peer: node id of peer node * @peer_id: 128-bit ID of peer * @peer_caps: bitmap describing peer node capabilities * @bc_sndlink: the namespace global link used for broadcast sending * * Return: true if link was created, otherwise false
*/ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, u8 *peer_id, 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;
/* 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);
returntrue;
}
/** * 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; break; 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;
}
/** * tipc_link_too_silent - check if link is "too silent" * @l: tipc link to be checked * * Return: 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);
}
/* 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);
probe = mstate->probing;
probe |= l->silent_intv_cnt; if (probe || mstate->monitoring)
l->silent_intv_cnt++;
probe |= !skb_queue_empty(&l->deferdq); 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;
}
/** * 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
*/ staticint 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;
/** * 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
*/ staticvoid 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;
/** * tipc_link_set_skb_retransmit_time - set the time at which retransmission of * the given skb should be next attempted * @skb: skb to set a future retransmission time for * @l: link the skb will be transmitted on
*/ staticvoid tipc_link_set_skb_retransmit_time(struct sk_buff *skb, struct tipc_link *l)
{ if (link_is_bc_sndlink(l))
TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; else
TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME;
}
/** * tipc_link_xmit(): enqueue buffer list according to queue situation * @l: link to use * @list: chain of buffers containing message * @xmitq: returned list of packets to be sent by caller * * Consumes the buffer chain. * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS
*/ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *xmitq)
{ 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); unsignedint mss = tipc_link_mss(l); unsignedint cwin = l->window; unsignedint mtu = l->mtu; struct tipc_msg *hdr; bool new_bundle; int rc = 0; int imp;
if (pkt_cnt <= 0) return 0;
hdr = buf_msg(skb_peek(list)); 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;
}
imp = msg_importance(hdr); /* 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);
__skb_queue_purge(list); 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);
tipc_link_set_skb_retransmit_time(skb, l);
__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;
}
staticvoid 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;
/* 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
*/ staticbool 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); returntrue;
}
fallthrough; case CONN_MANAGER:
skb_queue_tail(inputq, skb); returntrue; case GROUP_PROTOCOL:
skb_queue_tail(mc_inputq, skb); returntrue; case NAME_DISTRIBUTOR:
l->bc_rcvlink->state = LINK_ESTABLISHED;
skb_queue_tail(l->namedq, skb); returntrue; case MSG_BUNDLER: case TUNNEL_PROTOCOL: case MSG_FRAGMENTER: case BCAST_PROTOCOL: returnfalse; #ifdef CONFIG_TIPC_CRYPTO case MSG_CRYPTO: if (sysctl_tipc_key_exchange_enabled &&
TIPC_SKB_CB(skb)->decrypted) {
tipc_crypto_msg_rcv(l->net, skb); returntrue;
}
fallthrough; #endif default:
pr_warn("Dropping received illegal msg type\n");
kfree_skb(skb); returntrue;
}
}
/* tipc_link_input - process packet that has passed link protocol check * * Consumes buffer
*/ staticint 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;
/* 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
*/ staticint 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); elseif (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;
}
/** * tipc_get_gap_ack_blks - get Gap ACK blocks from PROTOCOL/STATE_MSG * @ga: returned pointer to the Gap ACK blocks if any * @l: the tipc link * @hdr: the PROTOCOL/STATE_MSG header * @uc: desired Gap ACK blocks type, i.e. unicast (= 1) or broadcast (= 0) * * Return: the total Gap ACK blocks size
*/
u16 tipc_get_gap_ack_blks(struct tipc_gap_ack_blks **ga, struct tipc_link *l, struct tipc_msg *hdr, bool uc)
{ struct tipc_gap_ack_blks *p;
u16 sz = 0;
/* Does peer support the Gap ACK blocks feature? */ if (l->peer_caps & TIPC_GAP_ACK_BLOCK) {
p = (struct tipc_gap_ack_blks *)msg_data(hdr);
sz = ntohs(p->len); /* Sanity check */ if (sz == struct_size(p, gacks, size_add(p->ugack_cnt, p->bgack_cnt))) { /* Good, check if the desired type exists */ if ((uc && p->ugack_cnt) || (!uc && p->bgack_cnt)) goto ok; /* Backward compatible: peer might not support bc, but uc? */
} elseif (uc && sz == struct_size(p, gacks, p->ugack_cnt)) { if (p->ugack_cnt) {
p->bgack_cnt = 0; goto ok;
}
}
} /* Other cases: ignore! */
p = NULL;
/* tipc_build_gap_ack_blks - build Gap ACK blocks * @l: tipc unicast link * @hdr: the tipc message buffer to store the Gap ACK blocks after built * * The function builds Gap ACK blocks for both the unicast & broadcast receiver * links of a certain peer, the buffer after built has the network data format * as found at the struct tipc_gap_ack_blks definition. * * returns the actual allocated memory size
*/ static u16 tipc_build_gap_ack_blks(struct tipc_link *l, struct tipc_msg *hdr)
{ struct tipc_link *bcl = l->bc_rcvlink; struct tipc_gap_ack_blks *ga;
u16 len;
ga = (struct tipc_gap_ack_blks *)msg_data(hdr);
/* Start with broadcast link first */
tipc_bcast_lock(bcl->net);
msg_set_bcast_ack(hdr, bcl->rcv_nxt - 1);
msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl));
ga->bgack_cnt = __tipc_build_gap_ack_blks(ga, bcl, 0);
tipc_bcast_unlock(bcl->net);
/* Now for unicast link, but an explicit NACK only (???) */
ga->ugack_cnt = (msg_seq_gap(hdr)) ?
__tipc_build_gap_ack_blks(ga, l, ga->bgack_cnt) : 0;
/* Total len */
len = struct_size(ga, gacks, size_add(ga->bgack_cnt, ga->ugack_cnt));
ga->len = htons(len); 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 * @r: tipc link "receiver" i.e. in case of broadcast (= "l" if unicast) * @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 * @retransmitted: returned boolean value if a retransmission is really issued * @rc: returned code e.g. TIPC_LINK_DOWN_EVT if a repeated retransmit failures * happens (- unlikely case) * * Return: the number of packets released from the link transmq
*/ staticint tipc_link_advance_transmq(struct tipc_link *l, struct tipc_link *r,
u16 acked, u16 gap, struct tipc_gap_ack_blks *ga, struct sk_buff_head *xmitq, bool *retransmitted, int *rc)
{ struct tipc_gap_ack_blks *last_ga = r->last_ga, *this_ga = NULL; struct tipc_gap_ack *gacks = NULL; struct sk_buff *skb, *_skb, *tmp; struct tipc_msg *hdr;
u32 qlen = skb_queue_len(&l->transmq);
u16 nacked = acked, ngap = gap, gack_cnt = 0;
u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
u16 ack = l->rcv_nxt - 1;
u16 seqno, n = 0;
u16 end = r->acked, start = end, offset = r->last_gap;
u16 si = (last_ga) ? last_ga->start_index : 0; bool is_uc = !link_is_bc_sndlink(l); bool bc_has_acked = false;
/* Determine Gap ACK blocks if any for the particular link */ if (ga && is_uc) { /* Get the Gap ACKs, uc part */
gack_cnt = ga->ugack_cnt;
gacks = &ga->gacks[ga->bgack_cnt];
} elseif (ga) { /* Copy the Gap ACKs, bc part, for later renewal if needed */
this_ga = kmemdup(ga, struct_size(ga, gacks, ga->bgack_cnt),
GFP_ATOMIC); if (likely(this_ga)) {
this_ga->start_index = 0; /* Start with the bc Gap ACKs */
gack_cnt = this_ga->bgack_cnt;
gacks = &this_ga->gacks[0];
} else { /* Hmm, we can get in trouble..., simply ignore it */
pr_warn_ratelimited("Ignoring bc Gap ACKs, no memory\n");
}
}
/* Advance the link transmq */
skb_queue_walk_safe(&l->transmq, skb, tmp) {
seqno = buf_seqno(skb);
next_gap_ack: if (less_eq(seqno, nacked)) { if (is_uc) goto release; /* Skip packets peer has already acked */ if (!more(seqno, r->acked)) continue; /* Get the next of last Gap ACK blocks */ while (more(seqno, end)) { if (!last_ga || si >= last_ga->bgack_cnt) break;
start = end + offset + 1;
end = ntohs(last_ga->gacks[si].ack);
offset = ntohs(last_ga->gacks[si].gap);
si++;
WARN_ONCE(more(start, end) ||
(!offset &&
si < last_ga->bgack_cnt) ||
si > MAX_GAP_ACK_BLKS, "Corrupted Gap ACK: %d %d %d %d %d\n",
start, end, offset, si,
last_ga->bgack_cnt);
} /* Check against the last Gap ACK block */ if (tipc_in_range(seqno, start, end)) continue; /* Update/release the packet peer is acking */
bc_has_acked = true; if (--TIPC_SKB_CB(skb)->ackers) continue;
release: /* release skb */
__skb_unlink(skb, &l->transmq);
kfree_skb(skb);
} elseif (less_eq(seqno, nacked + ngap)) { /* First gap: check if repeated retrans failures? */ if (unlikely(seqno == acked + 1 &&
link_retransmit_failure(l, r, rc))) { /* Ignore this bc Gap ACKs if any */
kfree(this_ga);
this_ga = NULL; break;
} /* retransmit skb if unrestricted*/ if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) continue;
tipc_link_set_skb_retransmit_time(skb, l);
_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++; if (!is_uc)
r->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 (n >= gack_cnt) break;
nacked = ntohs(gacks[n].ack);
ngap = ntohs(gacks[n].gap);
n++; goto next_gap_ack;
}
}
/* Renew last Gap ACK blocks for bc if needed */ if (bc_has_acked) { if (this_ga) {
kfree(last_ga);
r->last_ga = this_ga;
r->last_gap = gap;
} elseif (last_ga) { if (less(acked, start)) {
si--;
offset = start - acked - 1;
} elseif (less(acked, end)) {
acked = end;
} if (si < last_ga->bgack_cnt) {
last_ga->start_index = si;
r->last_gap = offset;
} else {
kfree(last_ga);
r->last_ga = NULL;
r->last_gap = 0;
}
} else {
r->last_gap = 0;
}
r->acked = acked;
} else {
kfree(this_ga);
}
return qlen - skb_queue_len(&l->transmq);
}
/* 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;
/* 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
*/ staticint 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;
/* 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;
if (unlikely(msg_user(hdr) == TUNNEL_PROTOCOL))
rc |= tipc_link_tnl_rcv(l, skb, l->inputq); elseif (!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;
}
/* 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, 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_create(TUNNEL_PROTOCOL, SYNCH_MSG,
INT_H_SIZE, 0, l->addr,
tipc_own_addr(l->net),
0, 0, 0); if (!tnlskb) {
pr_warn("%sunable to create dummy SYNCH_MSG\n",
link_co_err); return;
}
/* Tunnel link MTU is not large enough? This could be * due to: * 1) Link MTU has just changed or set differently; * 2) Or FAILOVER on the top of a SYNCH message * * The 2nd case should not happen if peer supports * TIPC_TUNNEL_ENHANCED
*/ if (pktlen > tnl->mtu - INT_H_SIZE) { if (mtyp == FAILOVER_MSG &&
(tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) {
rc = tipc_msg_fragment(skb, &tnlhdr, tnl->mtu,
&frags); if (rc) {
pr_warn("%sunable to frag msg: rc %d\n",
link_co_err, rc); return;
}
pktcnt += skb_queue_len(&frags) - 1;
pktcnt_need_update = true;
skb_queue_splice_tail_init(&frags, &tnlq); continue;
} /* Unluckily, peer doesn't have TIPC_TUNNEL_ENHANCED * => Just warn it and return!
*/
pr_warn_ratelimited("%stoo large msg <%d, %d>: %d!\n",
link_co_err, msg_user(hdr),
msg_type(hdr), msg_size(hdr)); return;
}
/* Failover the link's deferdq */ if (unlikely(!skb_queue_empty(fdefq))) {
pr_warn("Link failover deferdq not empty: %d!\n",
skb_queue_len(fdefq));
__skb_queue_purge(fdefq);
}
skb_queue_splice_init(&l->deferdq, fdefq);
}
}
/** * tipc_link_failover_prepare() - prepare tnl for link failover * * This is a special version of the precursor - tipc_link_tnl_prepare(), * see the tipc_node_link_failover() for details * * @l: failover link * @tnl: tunnel link * @xmitq: queue for messages to be xmited
*/ void tipc_link_failover_prepare(struct tipc_link *l, struct tipc_link *tnl, struct sk_buff_head *xmitq)
{ struct sk_buff_head *fdefq = &tnl->failover_deferdq;
tipc_link_create_dummy_tnl_msg(tnl, xmitq);
/* This failover link endpoint was never established before, * so it has not received anything from peer. * Otherwise, it must be a normal failover situation or the * node has entered SELF_DOWN_PEER_LEAVING and both peer nodes * would have to start over from scratch instead.
*/
tnl->drop_point = 1;
tnl->failover_reasm_skb = NULL;
/* Initiate the link's failover deferdq */ if (unlikely(!skb_queue_empty(fdefq))) {
pr_warn("Link failover deferdq not empty: %d!\n",
skb_queue_len(fdefq));
__skb_queue_purge(fdefq);
}
}
/* tipc_link_validate_msg(): validate message against current link state * Returns true if message should be accepted, otherwise false
*/ bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr)
{
u16 curr_session = l->peer_session;
u16 session = msg_session(hdr); int mtyp = msg_type(hdr);
if (msg_user(hdr) != LINK_PROTOCOL) returntrue;
switch (mtyp) { case RESET_MSG: if (!l->in_session) returntrue; /* Accept only RESET with new session number */ return more(session, curr_session); case ACTIVATE_MSG: if (!l->in_session) returntrue; /* Accept only ACTIVATE with new or current session number */ return !less(session, curr_session); case STATE_MSG: /* Accept only STATE with current session number */ if (!l->in_session) returnfalse; if (session != curr_session) returnfalse; /* Extra sanity check */ if (!tipc_link_is_up(l) && msg_ack(hdr)) returnfalse; if (!(l->peer_caps & TIPC_LINK_PROTO_SEQNO)) returntrue; /* Accept only STATE with new sequence number */ return !less(msg_seqno(hdr), l->rcv_nxt_state); default: returnfalse;
}
}
/* 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
*/ staticint tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq)
{ struct tipc_msg *hdr = buf_msg(skb); struct tipc_gap_ack_blks *ga = NULL; bool reply = msg_probe(hdr), retransmitted = false;
u32 dlen = msg_data_sz(hdr), glen = 0, msg_max;
u16 peers_snd_nxt = msg_next_sent(hdr);
u16 peers_tol = msg_link_tolerance(hdr);
u16 peers_prio = msg_linkprio(hdr);
u16 gap = msg_seq_gap(hdr);
u16 ack = msg_ack(hdr);
u16 rcv_nxt = l->rcv_nxt;
u16 rcvgap = 0; int mtyp = msg_type(hdr); int rc = 0, released; char *if_name; void *data;
trace_tipc_proto_rcv(skb, false, l->name);
if (dlen > U16_MAX) gotoexit;
if (tipc_link_is_blocked(l) || !xmitq) gotoexit;
if (tipc_own_addr(l->net) > msg_prevnode(hdr))
l->net_plane = msg_net_plane(hdr);
switch (mtyp) { case RESET_MSG: case ACTIVATE_MSG:
msg_max = msg_max_pkt(hdr); if (msg_max < tipc_bearer_min_mtu(l->net, l->bearer_id)) break; /* 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;
strscpy(if_name, data, TIPC_MAX_IF_NAME);
/* Update own tolerance if peer indicates a non-zero value */ if (tipc_in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) {
l->tolerance = peers_tol;
l->bc_rcvlink->tolerance = peers_tol;
} /* Update own priority if peer's priority is higher */ if (tipc_in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI))
l->priority = peers_prio;
/* If peer is going down we want full re-establish cycle */ if (msg_peer_stopping(hdr)) {
rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); break;
}
/* If this endpoint was re-created while peer was ESTABLISHING * it doesn't know current session number. Force re-synch.
*/ if (mtyp == ACTIVATE_MSG && msg_dest_session_valid(hdr) &&
l->session != msg_dest_session(hdr)) { if (less(l->session, msg_dest_session(hdr)))
l->session = msg_dest_session(hdr) + 1; break;
}
/* ACTIVATE_MSG serves as PEER_RESET if link is already down */ if (mtyp == RESET_MSG || !tipc_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;
case STATE_MSG: /* Validate Gap ACK blocks, drop if invalid */
glen = tipc_get_gap_ack_blks(&ga, l, hdr, true); if (glen > dlen) break;
l->rcv_nxt_state = msg_seqno(hdr) + 1;
/* Update own tolerance if peer indicates a non-zero value */ if (tipc_in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) {
l->tolerance = peers_tol;
l->bc_rcvlink->tolerance = peers_tol;
} /* Update own prio if peer indicates a different value */ if ((peers_prio != l->priority) &&
tipc_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 (!tipc_link_is_up(l)) { if (l->state == LINK_ESTABLISHING)
rc = TIPC_LINK_UP_EVT; break;
}
tipc_mon_rcv(l->net, data + glen, dlen - glen, l->addr,
&l->mon_state, l->bearer_id);
/* Send NACK if peer has sent pkts we haven't received yet */ if ((reply || msg_is_keepalive(hdr)) &&
more(peers_snd_nxt, rcv_nxt) &&
!tipc_link_is_synching(l) &&
skb_queue_empty(&l->deferdq))
rcvgap = peers_snd_nxt - l->rcv_nxt; if (rcvgap || reply)
tipc_link_build_proto_msg(l, STATE_MSG, 0, reply,
rcvgap, 0, 0, xmitq);
released = tipc_link_advance_transmq(l, l, ack, gap, ga, xmitq,
&retransmitted, &rc); if (gap)
l->stats.recv_nacks++; if (released || retransmitted)
tipc_link_update_cwin(l, released, retransmitted); if (released)
tipc_link_advance_backlog(l, xmitq); if (unlikely(!skb_queue_empty(&l->wakeupq)))
link_prepare_wakeup(l);
} exit:
kfree_skb(skb); return rc;
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.