static void
bgp_sock_err(sock *sk, int err)
{
struct bgp_conn *conn = sk->data;
struct bgp_proto *p = conn->bgp;
/*
* This error hook may be called either asynchronously from main
* loop, or synchronously from sk_send(). But sk_send() is called
* only from bgp_tx() and bgp_kick_tx(), which are both called
* asynchronously from main loop. Moreover, they end if err hook is
* called. Therefore, we could suppose that it is always called
* asynchronously.
*/
bgp_store_error(p, conn, BE_SOCKET, err);
if (err)
BGP_TRACE(D_EVENTS, "Connection lost (%M)", err);
else
BGP_TRACE(D_EVENTS, "Connection closed");
if ((conn->state == BS_ESTABLISHED) && p->gr_ready)
bgp_handle_graceful_restart(p);
bgp_conn_enter_idle_state(conn);
}
void
bgp_conn_enter_established_state(struct bgp_conn *conn)
{
struct bgp_proto *p = conn->bgp;
BGP_TRACE(D_EVENTS, "BGP session established");
DBG("BGP: UP!!!\n");
/* For multi-hop BGP sessions */
if (ipa_zero(p->source_addr))
p->source_addr = conn->sk->saddr;
p->conn = conn;
p->last_error_class = 0;
p->last_error_code = 0;
bgp_init_bucket_table(p);
bgp_init_prefix_table(p, 8);
int peer_gr_ready = conn->peer_gr_aware && !(conn->peer_gr_flags & BGP_GRF_RESTART);
if (p->p.gr_recovery && !peer_gr_ready)
proto_graceful_restart_unlock(&p->p);
if (p->p.gr_recovery && (p->cf->gr_mode == BGP_GR_ABLE) && peer_gr_ready)
p->p.gr_wait = 1;
if (p->gr_active)
tm_stop(p->gr_timer);
if (p->gr_active && (!conn->peer_gr_able || !(conn->peer_gr_aflags & BGP_GRF_FORWARDING)))
bgp_graceful_restart_done(p);
bgp_conn_set_state(conn, BS_ESTABLISHED);
proto_notify_state(&p->p, PS_UP);
}
static void
bgp_graceful_restart_timeout(timer *t)
{
struct bgp_proto *p = t->data;
BGP_TRACE(D_EVENTS, "Neighbor graceful restart timeout");
bgp_stop(p, 0);
}
/**
* bgp_graceful_restart_done - finish active BGP graceful restart
* @p: BGP instance
*
* This function is called when the active BGP graceful restart of the neighbor
* should be finished - either successfully (the neighbor sends all paths and
* reports end-of-RIB on the new session) or unsuccessfully (the neighbor does
* not support BGP graceful restart on the new session). The function ends
* routing table refresh cycle and stops BGP restart timer.
*/
void
bgp_graceful_restart_done(struct bgp_proto *p)
{
BGP_TRACE(D_EVENTS, "Neighbor graceful restart done");
p->gr_active = 0;
tm_stop(p->gr_timer);
rt_refresh_end(p->p.main_ahook->table, p->p.main_ahook);
}
static void
bgp_down(struct bgp_proto *p)
{
if (p->start_state > BSS_PREPARE)
bgp_close(p, 1);
BGP_TRACE(D_EVENTS, "Down");
proto_notify_state(&p->p, PS_DOWN);
}
static void
bgp_connected(sock *sk)
{
struct bgp_conn *conn = sk->data;
struct bgp_proto *p = conn->bgp;
BGP_TRACE(D_EVENTS, "Connected");
bgp_send_open(conn);
}
static void
bgp_conn_leave_established_state(struct bgp_proto *p)
{
BGP_TRACE(D_EVENTS, "BGP session closed");
p->conn = NULL;
if (p->p.proto_state == PS_UP)
bgp_stop(p, 0);
}
static void
bgp_startup(struct bgp_proto *p)
{
BGP_TRACE(D_EVENTS, "Started");
p->start_state = p->cf->capabilities ? BSS_CONNECT : BSS_CONNECT_NOCAP;
if (!p->cf->passive)
bgp_active(p);
}
static void
bgp_active(struct bgp_proto *p)
{
int delay = MAX(1, p->cf->start_delay_time);
struct bgp_conn *conn = &p->outgoing_conn;
BGP_TRACE(D_EVENTS, "Connect delayed by %d seconds", delay);
bgp_setup_conn(p, conn);
bgp_conn_set_state(conn, BS_ACTIVE);
bgp_start_timer(conn->connect_retry_timer, delay);
}
/**
* bgp_incoming_connection - handle an incoming connection
* @sk: TCP socket
* @dummy: unused
*
* This function serves as a socket hook for accepting of new BGP
* connections. It searches a BGP instance corresponding to the peer
* which has connected and if such an instance exists, it creates a
* &bgp_conn structure, attaches it to the instance and either sends
* an Open message or (if there already is an active connection) it
* closes the new connection by sending a Notification message.
*/
static int
bgp_incoming_connection(sock *sk, int dummy UNUSED)
{
struct proto_config *pc;
DBG("BGP: Incoming connection from %I port %d\n", sk->daddr, sk->dport);
WALK_LIST(pc, config->protos)
if (pc->protocol == &proto_bgp && pc->proto)
{
struct bgp_proto *p = (struct bgp_proto *) pc->proto;
if (ipa_equal(p->cf->remote_ip, sk->daddr) &&
(!ipa_has_link_scope(sk->daddr) || (p->cf->iface == sk->iface)))
{
/* We are in proper state and there is no other incoming connection */
int acc = (p->p.proto_state == PS_START || p->p.proto_state == PS_UP) &&
(p->start_state >= BSS_CONNECT) && (!p->incoming_conn.sk);
if (p->conn && (p->conn->state == BS_ESTABLISHED) && p->gr_ready)
{
bgp_store_error(p, NULL, BE_MISC, BEM_GRACEFUL_RESTART);
bgp_handle_graceful_restart(p);
bgp_conn_enter_idle_state(p->conn);
acc = 1;
}
BGP_TRACE(D_EVENTS, "Incoming connection from %I%J (port %d) %s",
sk->daddr, ipa_has_link_scope(sk->daddr) ? sk->iface : NULL,
sk->dport, acc ? "accepted" : "rejected");
if (!acc)
goto reject;
int hops = p->cf->multihop ? : 1;
if (sk_set_ttl(sk, p->cf->ttl_security ? 255 : hops) < 0)
goto err;
if (p->cf->ttl_security)
if (sk_set_min_ttl(sk, 256 - hops) < 0)
goto err;
bgp_setup_conn(p, &p->incoming_conn);
bgp_setup_sk(&p->incoming_conn, sk);
bgp_send_open(&p->incoming_conn);
return 0;
err:
sk_log_error(sk, p->p.name);
log(L_ERR "%s: Incoming connection aborted", p->p.name);
rfree(sk);
return 0;
}
}
static void
bgp_initiate(struct bgp_proto *p)
{
int rv = bgp_open(p);
if (rv < 0)
return;
if (p->startup_delay)
{
BGP_TRACE(D_EVENTS, "Startup delayed by %d seconds", p->startup_delay);
bgp_start_timer(p->startup_timer, p->startup_delay);
}
else
bgp_startup(p);
}
/**
* bgp_handle_graceful_restart - handle detected BGP graceful restart
* @p: BGP instance
*
* This function is called when a BGP graceful restart of the neighbor is
* detected (when the TCP connection fails or when a new TCP connection
* appears). The function activates processing of the restart - starts routing
* table refresh cycle and activates BGP restart timer. The protocol state goes
* back to %PS_START, but changing BGP state back to %BS_IDLE is left for the
* caller.
*/
void
bgp_handle_graceful_restart(struct bgp_proto *p)
{
ASSERT(p->conn && (p->conn->state == BS_ESTABLISHED) && p->gr_ready);
BGP_TRACE(D_EVENTS, "Neighbor graceful restart detected%s",
p->gr_active ? " - already pending" : "");
proto_notify_state(&p->p, PS_START);
if (p->gr_active)
rt_refresh_end(p->p.main_ahook->table, p->p.main_ahook);
p->gr_active = 1;
bgp_start_timer(p->gr_timer, p->conn->peer_gr_time);
rt_refresh_begin(p->p.main_ahook->table, p->p.main_ahook);
}
/**
* bgp_connect - initiate an outgoing connection
* @p: BGP instance
*
* The bgp_connect() function creates a new &bgp_conn and initiates
* a TCP connection to the peer. The rest of connection setup is governed
* by the BGP state machine as described in the standard.
*/
static void
bgp_connect(struct bgp_proto *p) /* Enter Connect state and start establishing connection */
{
sock *s;
struct bgp_conn *conn = &p->outgoing_conn;
int hops = p->cf->multihop ? : 1;
DBG("BGP: Connecting\n");
s = sk_new(p->p.pool);
s->type = SK_TCP_ACTIVE;
s->saddr = p->source_addr;
s->daddr = p->cf->remote_ip;
s->iface = p->neigh ? p->neigh->iface : NULL;
s->dport = BGP_PORT;
s->ttl = p->cf->ttl_security ? 255 : hops;
s->rbsize = BGP_RX_BUFFER_SIZE;
s->tbsize = BGP_TX_BUFFER_SIZE;
s->tos = IP_PREC_INTERNET_CONTROL;
s->password = p->cf->password;
s->tx_hook = bgp_connected;
BGP_TRACE(D_EVENTS, "Connecting to %I%J from local address %I%J", s->daddr, p->cf->iface,
s->saddr, ipa_has_link_scope(s->saddr) ? s->iface : NULL);
bgp_setup_conn(p, conn);
bgp_setup_sk(conn, s);
bgp_conn_set_state(conn, BS_CONNECT);
if (sk_open(s) < 0)
{
bgp_sock_err(s, 0);
return;
}
/* Set minimal receive TTL if needed */
if (p->cf->ttl_security)
{
DBG("Setting minimum received TTL to %d", 256 - hops);
if (sk_set_min_ttl(s, 256 - hops) < 0)
{
log(L_ERR "TTL security configuration failed, closing session");
bgp_sock_err(s, 0);
return;
}
}
DBG("BGP: Waiting for connect success\n");
bgp_start_timer(conn->connect_retry_timer, p->cf->connect_retry_time);
}
/**
* bgp_incoming_connection - handle an incoming connection
* @sk: TCP socket
* @dummy: unused
*
* This function serves as a socket hook for accepting of new BGP
* connections. It searches a BGP instance corresponding to the peer
* which has connected and if such an instance exists, it creates a
* &bgp_conn structure, attaches it to the instance and either sends
* an Open message or (if there already is an active connection) it
* closes the new connection by sending a Notification message.
*/
static int
bgp_incoming_connection(sock *sk, int dummy UNUSED)
{
struct proto_config *pc;
DBG("BGP: Incoming connection from %I port %d\n", sk->daddr, sk->dport);
WALK_LIST(pc, config->protos)
if (pc->protocol == &proto_bgp && pc->proto)
{
struct bgp_proto *p = (struct bgp_proto *) pc->proto;
if (ipa_equal(p->cf->remote_ip, sk->daddr) &&
(!ipa_has_link_scope(sk->daddr) || (p->cf->iface == sk->iface)))
{
/* We are in proper state and there is no other incoming connection */
int acc = (p->p.proto_state == PS_START || p->p.proto_state == PS_UP) &&
(p->start_state >= BSS_CONNECT) && (!p->incoming_conn.sk);
BGP_TRACE(D_EVENTS, "Incoming connection from %I%J (port %d) %s",
sk->daddr, ipa_has_link_scope(sk->daddr) ? sk->iface : NULL,
sk->dport, acc ? "accepted" : "rejected");
if (!acc)
goto err;
int hops = p->cf->multihop ? : 1;
if (p->cf->ttl_security)
{
/* TTL security support */
if ((sk_set_ttl(sk, 255) < 0) ||
(sk_set_min_ttl(sk, 256 - hops) < 0))
{
log(L_ERR "TTL security configuration failed, closing session");
goto err;
}
}
else
sk_set_ttl(sk, hops);
bgp_setup_conn(p, &p->incoming_conn);
bgp_setup_sk(&p->incoming_conn, sk);
bgp_send_open(&p->incoming_conn);
return 0;
}
}
void
bgp_conn_enter_established_state(struct bgp_conn *conn)
{
struct bgp_proto *p = conn->bgp;
BGP_TRACE(D_EVENTS, "BGP session established");
DBG("BGP: UP!!!\n");
/* For multi-hop BGP sessions */
if (ipa_zero(p->source_addr))
p->source_addr = conn->sk->saddr;
p->conn = conn;
p->last_error_class = 0;
p->last_error_code = 0;
p->feed_state = BFS_NONE;
p->load_state = BFS_NONE;
bgp_init_bucket_table(p);
bgp_init_prefix_table(p, 8);
int peer_gr_ready = conn->peer_gr_aware && !(conn->peer_gr_flags & BGP_GRF_RESTART);
if (p->p.gr_recovery && !peer_gr_ready)
proto_graceful_restart_unlock(&p->p);
if (p->p.gr_recovery && (p->cf->gr_mode == BGP_GR_ABLE) && peer_gr_ready)
p->p.gr_wait = 1;
if (p->gr_active)
tm_stop(p->gr_timer);
if (p->gr_active && (!conn->peer_gr_able || !(conn->peer_gr_aflags & BGP_GRF_FORWARDING)))
bgp_graceful_restart_done(p);
/* GR capability implies that neighbor will send End-of-RIB */
if (conn->peer_gr_aware)
p->load_state = BFS_LOADING;
/* proto_notify_state() will likely call bgp_feed_begin(), setting p->feed_state */
bgp_conn_set_state(conn, BS_ESTABLISHED);
proto_notify_state(&p->p, PS_UP);
}
static void
bgp_initiate(struct bgp_proto *p)
{
int rv = bgp_open(p);
if (rv < 0)
return;
if (p->cf->bfd)
bgp_update_bfd(p, p->cf->bfd);
if (p->startup_delay)
{
p->start_state = BSS_DELAY;
BGP_TRACE(D_EVENTS, "Startup delayed by %d seconds", p->startup_delay);
bgp_start_timer(p->startup_timer, p->startup_delay);
}
else
bgp_startup(p);
}
/**
* bgp_connect - initiate an outgoing connection
* @p: BGP instance
*
* The bgp_connect() function creates a new &bgp_conn and initiates
* a TCP connection to the peer. The rest of connection setup is governed
* by the BGP state machine as described in the standard.
*/
static void
bgp_connect(struct bgp_proto *p) /* Enter Connect state and start establishing connection */
{
sock *s;
struct bgp_conn *conn = &p->outgoing_conn;
int hops = p->cf->multihop ? : 1;
DBG("BGP: Connecting\n");
s = sk_new(p->p.pool);
s->type = SK_TCP_ACTIVE;
s->saddr = p->source_addr;
s->daddr = p->cf->remote_ip;
s->dport = p->cf->remote_port;
s->iface = p->neigh ? p->neigh->iface : NULL;
s->ttl = p->cf->ttl_security ? 255 : hops;
s->rbsize = p->cf->enable_extended_messages ? BGP_RX_BUFFER_EXT_SIZE : BGP_RX_BUFFER_SIZE;
s->tbsize = p->cf->enable_extended_messages ? BGP_TX_BUFFER_EXT_SIZE : BGP_TX_BUFFER_SIZE;
s->tos = IP_PREC_INTERNET_CONTROL;
s->password = p->cf->password;
s->tx_hook = bgp_connected;
BGP_TRACE(D_EVENTS, "Connecting to %I%J from local address %I%J", s->daddr, p->cf->iface,
s->saddr, ipa_is_link_local(s->saddr) ? s->iface : NULL);
bgp_setup_conn(p, conn);
bgp_setup_sk(conn, s);
bgp_conn_set_state(conn, BS_CONNECT);
if (sk_open(s) < 0)
goto err;
/* Set minimal receive TTL if needed */
if (p->cf->ttl_security)
if (sk_set_min_ttl(s, 256 - hops) < 0)
goto err;
DBG("BGP: Waiting for connect success\n");
bgp_start_timer(conn->connect_retry_timer, p->cf->connect_retry_time);
return;
err:
sk_log_error(s, p->p.name);
bgp_sock_err(s, 0);
return;
}
void
bgp_conn_enter_established_state(struct bgp_conn *conn)
{
struct bgp_proto *p = conn->bgp;
BGP_TRACE(D_EVENTS, "BGP session established");
DBG("BGP: UP!!!\n");
/* For multi-hop BGP sessions */
if (ipa_zero(p->source_addr))
p->source_addr = conn->sk->saddr;
p->conn = conn;
p->last_error_class = 0;
p->last_error_code = 0;
bgp_attr_init(conn->bgp);
bgp_conn_set_state(conn, BS_ESTABLISHED);
proto_notify_state(&p->p, PS_UP);
}
static void
bgp_hold_timeout(timer *t)
{
struct bgp_conn *conn = t->data;
struct bgp_proto *p = conn->bgp;
DBG("BGP: Hold timeout\n");
/* We are already closing the connection - just do hangup */
if (conn->state == BS_CLOSE)
{
BGP_TRACE(D_EVENTS, "Connection stalled");
bgp_conn_enter_idle_state(conn);
return;
}
/* If there is something in input queue, we are probably congested
and perhaps just not processed BGP packets in time. */
if (sk_rx_ready(conn->sk) > 0)
bgp_start_timer(conn->hold_timer, 10);
else
bgp_error(conn, 4, 0, NULL, 0);
}
/**
* bgp_incoming_connection - handle an incoming connection
* @sk: TCP socket
* @dummy: unused
*
* This function serves as a socket hook for accepting of new BGP
* connections. It searches a BGP instance corresponding to the peer
* which has connected and if such an instance exists, it creates a
* &bgp_conn structure, attaches it to the instance and either sends
* an Open message or (if there already is an active connection) it
* closes the new connection by sending a Notification message.
*/
static int
bgp_incoming_connection(sock *sk, int dummy UNUSED)
{
struct bgp_proto *p;
int acc, hops;
DBG("BGP: Incoming connection from %I port %d\n", sk->daddr, sk->dport);
p = bgp_find_proto(sk);
if (!p)
{
log(L_WARN "BGP: Unexpected connect from unknown address %I%J (port %d)",
sk->daddr, ipa_is_link_local(sk->daddr) ? sk->iface : NULL, sk->dport);
rfree(sk);
return 0;
}
/* We are in proper state and there is no other incoming connection */
acc = (p->p.proto_state == PS_START || p->p.proto_state == PS_UP) &&
(p->start_state >= BSS_CONNECT) && (!p->incoming_conn.sk);
if (p->conn && (p->conn->state == BS_ESTABLISHED) && p->gr_ready)
{
bgp_store_error(p, NULL, BE_MISC, BEM_GRACEFUL_RESTART);
bgp_handle_graceful_restart(p);
bgp_conn_enter_idle_state(p->conn);
acc = 1;
}
BGP_TRACE(D_EVENTS, "Incoming connection from %I%J (port %d) %s",
sk->daddr, ipa_is_link_local(sk->daddr) ? sk->iface : NULL,
sk->dport, acc ? "accepted" : "rejected");
if (!acc)
{
rfree(sk);
return 0;
}
hops = p->cf->multihop ? : 1;
if (sk_set_ttl(sk, p->cf->ttl_security ? 255 : hops) < 0)
goto err;
if (p->cf->ttl_security)
if (sk_set_min_ttl(sk, 256 - hops) < 0)
goto err;
if (p->cf->enable_extended_messages)
{
sk->rbsize = BGP_RX_BUFFER_EXT_SIZE;
sk->tbsize = BGP_TX_BUFFER_EXT_SIZE;
sk_reallocate(sk);
}
bgp_setup_conn(p, &p->incoming_conn);
bgp_setup_sk(&p->incoming_conn, sk);
bgp_send_open(&p->incoming_conn);
return 0;
err:
sk_log_error(sk, p->p.name);
log(L_ERR "%s: Incoming connection aborted", p->p.name);
rfree(sk);
return 0;
}