From a019d6fe2b9da68ea4ba6cf3c4e86fc1dbf554c3 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:15:09 -0700 Subject: [ICSK]: Move generalised functions from tcp to inet_connection_sock This also improves reqsk_queue_prune and renames it to inet_csk_reqsk_queue_prune, as it deals with both inet_connection_sock and inet_request_sock objects, not just with request_sock ones thus belonging to inet_request_sock. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- net/dccp/timer.c | 6 +- net/ipv4/inet_connection_sock.c | 214 ++++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp.c | 120 ---------------------- net/ipv4/tcp_timer.c | 93 +---------------- 4 files changed, 217 insertions(+), 216 deletions(-) (limited to 'net') diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 8c396ee01aac..9f1f1ab9e2b4 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -220,11 +220,7 @@ out: */ static void dccp_response_timer(struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); - const int max_retries = icsk->icsk_syn_retries ? : TCP_SYNACK_RETRIES /* FIXME sysctl_tcp_synack_retries */; - - reqsk_queue_prune(&icsk->icsk_accept_queue, sk, TCP_SYNQ_INTERVAL, - DCCP_TIMEOUT_INIT, DCCP_RTO_MAX, max_retries); + inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL, DCCP_TIMEOUT_INIT, DCCP_RTO_MAX); } static void dccp_keepalive_timer(unsigned long data) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 136ada050b63..026630a15ea0 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -23,6 +23,7 @@ #include #include #include +#include #ifdef INET_CSK_DEBUG const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n"; @@ -398,8 +399,100 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, inet_csk_reqsk_queue_added(sk, timeout); } +/* Only thing we need from tcp.h */ +extern int sysctl_tcp_synack_retries; + EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); +void inet_csk_reqsk_queue_prune(struct sock *parent, + const unsigned long interval, + const unsigned long timeout, + const unsigned long max_rto) +{ + struct inet_connection_sock *icsk = inet_csk(parent); + struct request_sock_queue *queue = &icsk->icsk_accept_queue; + struct listen_sock *lopt = queue->listen_opt; + int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; + int thresh = max_retries; + unsigned long now = jiffies; + struct request_sock **reqp, *req; + int i, budget; + + if (lopt == NULL || lopt->qlen == 0) + return; + + /* Normally all the openreqs are young and become mature + * (i.e. converted to established socket) for first timeout. + * If synack was not acknowledged for 3 seconds, it means + * one of the following things: synack was lost, ack was lost, + * rtt is high or nobody planned to ack (i.e. synflood). + * When server is a bit loaded, queue is populated with old + * open requests, reducing effective size of queue. + * When server is well loaded, queue size reduces to zero + * after several minutes of work. It is not synflood, + * it is normal operation. The solution is pruning + * too old entries overriding normal timeout, when + * situation becomes dangerous. + * + * Essentially, we reserve half of room for young + * embrions; and abort old ones without pity, if old + * ones are about to clog our table. + */ + if (lopt->qlen>>(lopt->max_qlen_log-1)) { + int young = (lopt->qlen_young<<1); + + while (thresh > 2) { + if (lopt->qlen < young) + break; + thresh--; + young <<= 1; + } + } + + if (queue->rskq_defer_accept) + max_retries = queue->rskq_defer_accept; + + budget = 2 * (lopt->nr_table_entries / (timeout / interval)); + i = lopt->clock_hand; + + do { + reqp=&lopt->syn_table[i]; + while ((req = *reqp) != NULL) { + if (time_after_eq(now, req->expires)) { + if ((req->retrans < thresh || + (inet_rsk(req)->acked && req->retrans < max_retries)) + && !req->rsk_ops->rtx_syn_ack(parent, req, NULL)) { + unsigned long timeo; + + if (req->retrans++ == 0) + lopt->qlen_young--; + timeo = min((timeout << req->retrans), max_rto); + req->expires = now + timeo; + reqp = &req->dl_next; + continue; + } + + /* Drop this request */ + inet_csk_reqsk_queue_unlink(parent, req, reqp); + reqsk_queue_removed(queue, req); + reqsk_free(req); + continue; + } + reqp = &req->dl_next; + } + + i = (i + 1) & (lopt->nr_table_entries - 1); + + } while (--budget > 0); + + lopt->clock_hand = i; + + if (lopt->qlen) + inet_csk_reset_keepalive_timer(parent, interval); +} + +EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_prune); + struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req, const unsigned int __nocast priority) { @@ -424,3 +517,124 @@ struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req, } EXPORT_SYMBOL_GPL(inet_csk_clone); + +/* + * At this point, there should be no process reference to this + * socket, and thus no user references at all. Therefore we + * can assume the socket waitqueue is inactive and nobody will + * try to jump onto it. + */ +void inet_csk_destroy_sock(struct sock *sk) +{ + BUG_TRAP(sk->sk_state == TCP_CLOSE); + BUG_TRAP(sock_flag(sk, SOCK_DEAD)); + + /* It cannot be in hash table! */ + BUG_TRAP(sk_unhashed(sk)); + + /* If it has not 0 inet_sk(sk)->num, it must be bound */ + BUG_TRAP(!inet_sk(sk)->num || inet_csk(sk)->icsk_bind_hash); + + sk->sk_prot->destroy(sk); + + sk_stream_kill_queues(sk); + + xfrm_sk_free_policy(sk); + + sk_refcnt_debug_release(sk); + + atomic_dec(sk->sk_prot->orphan_count); + sock_put(sk); +} + +EXPORT_SYMBOL(inet_csk_destroy_sock); + +int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) +{ + struct inet_sock *inet = inet_sk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + int rc = reqsk_queue_alloc(&icsk->icsk_accept_queue, nr_table_entries); + + if (rc != 0) + return rc; + + sk->sk_max_ack_backlog = 0; + sk->sk_ack_backlog = 0; + inet_csk_delack_init(sk); + + /* There is race window here: we announce ourselves listening, + * but this transition is still not validated by get_port(). + * It is OK, because this socket enters to hash table only + * after validation is complete. + */ + sk->sk_state = TCP_LISTEN; + if (!sk->sk_prot->get_port(sk, inet->num)) { + inet->sport = htons(inet->num); + + sk_dst_reset(sk); + sk->sk_prot->hash(sk); + + return 0; + } + + sk->sk_state = TCP_CLOSE; + __reqsk_queue_destroy(&icsk->icsk_accept_queue); + return -EADDRINUSE; +} + +EXPORT_SYMBOL_GPL(inet_csk_listen_start); + +/* + * This routine closes sockets which have been at least partially + * opened, but not yet accepted. + */ +void inet_csk_listen_stop(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock *acc_req; + struct request_sock *req; + + inet_csk_delete_keepalive_timer(sk); + + /* make all the listen_opt local to us */ + acc_req = reqsk_queue_yank_acceptq(&icsk->icsk_accept_queue); + + /* Following specs, it would be better either to send FIN + * (and enter FIN-WAIT-1, it is normal close) + * or to send active reset (abort). + * Certainly, it is pretty dangerous while synflood, but it is + * bad justification for our negligence 8) + * To be honest, we are not able to make either + * of the variants now. --ANK + */ + reqsk_queue_destroy(&icsk->icsk_accept_queue); + + while ((req = acc_req) != NULL) { + struct sock *child = req->sk; + + acc_req = req->dl_next; + + local_bh_disable(); + bh_lock_sock(child); + BUG_TRAP(!sock_owned_by_user(child)); + sock_hold(child); + + sk->sk_prot->disconnect(child, O_NONBLOCK); + + sock_orphan(child); + + atomic_inc(sk->sk_prot->orphan_count); + + inet_csk_destroy_sock(child); + + bh_unlock_sock(child); + local_bh_enable(); + sock_put(child); + + sk_acceptq_removed(sk); + __reqsk_free(req); + } + BUG_TRAP(!sk->sk_ack_backlog); +} + +EXPORT_SYMBOL_GPL(inet_csk_listen_stop); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a4e9eec44895..4bda522d25cf 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -456,96 +456,6 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) return put_user(answ, (int __user *)arg); } -int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) -{ - struct inet_sock *inet = inet_sk(sk); - struct inet_connection_sock *icsk = inet_csk(sk); - int rc = reqsk_queue_alloc(&icsk->icsk_accept_queue, nr_table_entries); - - if (rc != 0) - return rc; - - sk->sk_max_ack_backlog = 0; - sk->sk_ack_backlog = 0; - inet_csk_delack_init(sk); - - /* There is race window here: we announce ourselves listening, - * but this transition is still not validated by get_port(). - * It is OK, because this socket enters to hash table only - * after validation is complete. - */ - sk->sk_state = TCP_LISTEN; - if (!sk->sk_prot->get_port(sk, inet->num)) { - inet->sport = htons(inet->num); - - sk_dst_reset(sk); - sk->sk_prot->hash(sk); - - return 0; - } - - sk->sk_state = TCP_CLOSE; - __reqsk_queue_destroy(&icsk->icsk_accept_queue); - return -EADDRINUSE; -} - -EXPORT_SYMBOL_GPL(inet_csk_listen_start); - -/* - * This routine closes sockets which have been at least partially - * opened, but not yet accepted. - */ -void inet_csk_listen_stop(struct sock *sk) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct request_sock *acc_req; - struct request_sock *req; - - inet_csk_delete_keepalive_timer(sk); - - /* make all the listen_opt local to us */ - acc_req = reqsk_queue_yank_acceptq(&icsk->icsk_accept_queue); - - /* Following specs, it would be better either to send FIN - * (and enter FIN-WAIT-1, it is normal close) - * or to send active reset (abort). - * Certainly, it is pretty dangerous while synflood, but it is - * bad justification for our negligence 8) - * To be honest, we are not able to make either - * of the variants now. --ANK - */ - reqsk_queue_destroy(&icsk->icsk_accept_queue); - - while ((req = acc_req) != NULL) { - struct sock *child = req->sk; - - acc_req = req->dl_next; - - local_bh_disable(); - bh_lock_sock(child); - BUG_TRAP(!sock_owned_by_user(child)); - sock_hold(child); - - sk->sk_prot->disconnect(child, O_NONBLOCK); - - sock_orphan(child); - - atomic_inc(sk->sk_prot->orphan_count); - - inet_csk_destroy_sock(child); - - bh_unlock_sock(child); - local_bh_enable(); - sock_put(child); - - sk_acceptq_removed(sk); - __reqsk_free(req); - } - BUG_TRAP(!sk->sk_ack_backlog); -} - -EXPORT_SYMBOL_GPL(inet_csk_listen_stop); - static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) { TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH; @@ -1559,35 +1469,6 @@ void tcp_shutdown(struct sock *sk, int how) } } -/* - * At this point, there should be no process reference to this - * socket, and thus no user references at all. Therefore we - * can assume the socket waitqueue is inactive and nobody will - * try to jump onto it. - */ -void inet_csk_destroy_sock(struct sock *sk) -{ - BUG_TRAP(sk->sk_state == TCP_CLOSE); - BUG_TRAP(sock_flag(sk, SOCK_DEAD)); - - /* It cannot be in hash table! */ - BUG_TRAP(sk_unhashed(sk)); - - /* If it has not 0 inet_sk(sk)->num, it must be bound */ - BUG_TRAP(!inet_sk(sk)->num || inet_csk(sk)->icsk_bind_hash); - - sk->sk_prot->destroy(sk); - - sk_stream_kill_queues(sk); - - xfrm_sk_free_policy(sk); - - sk_refcnt_debug_release(sk); - - atomic_dec(sk->sk_prot->orphan_count); - sock_put(sk); -} - void tcp_close(struct sock *sk, long timeout) { struct sk_buff *skb; @@ -2258,7 +2139,6 @@ void __init tcp_init(void) } EXPORT_SYMBOL(tcp_close); -EXPORT_SYMBOL(inet_csk_destroy_sock); EXPORT_SYMBOL(tcp_disconnect); EXPORT_SYMBOL(tcp_getsockopt); EXPORT_SYMBOL(tcp_ioctl); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b614ad4d30c9..72cec6981830 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -424,103 +424,14 @@ out_unlock: sock_put(sk); } -void reqsk_queue_prune(struct request_sock_queue *queue, struct sock *parent, - const unsigned long interval, const unsigned long timeout, - const unsigned long max_rto, int max_retries) -{ - struct inet_connection_sock *icsk = inet_csk(parent); - struct listen_sock *lopt = queue->listen_opt; - int thresh = max_retries; - unsigned long now = jiffies; - struct request_sock **reqp, *req; - int i, budget; - - if (lopt == NULL || lopt->qlen == 0) - return; - - /* Normally all the openreqs are young and become mature - * (i.e. converted to established socket) for first timeout. - * If synack was not acknowledged for 3 seconds, it means - * one of the following things: synack was lost, ack was lost, - * rtt is high or nobody planned to ack (i.e. synflood). - * When server is a bit loaded, queue is populated with old - * open requests, reducing effective size of queue. - * When server is well loaded, queue size reduces to zero - * after several minutes of work. It is not synflood, - * it is normal operation. The solution is pruning - * too old entries overriding normal timeout, when - * situation becomes dangerous. - * - * Essentially, we reserve half of room for young - * embrions; and abort old ones without pity, if old - * ones are about to clog our table. - */ - if (lopt->qlen>>(lopt->max_qlen_log-1)) { - int young = (lopt->qlen_young<<1); - - while (thresh > 2) { - if (lopt->qlen < young) - break; - thresh--; - young <<= 1; - } - } - - if (queue->rskq_defer_accept) - max_retries = queue->rskq_defer_accept; - - budget = 2 * (lopt->nr_table_entries / (timeout / interval)); - i = lopt->clock_hand; - - do { - reqp=&lopt->syn_table[i]; - while ((req = *reqp) != NULL) { - if (time_after_eq(now, req->expires)) { - if ((req->retrans < thresh || - (inet_rsk(req)->acked && req->retrans < max_retries)) - && !req->rsk_ops->rtx_syn_ack(parent, req, NULL)) { - unsigned long timeo; - - if (req->retrans++ == 0) - lopt->qlen_young--; - timeo = min((timeout << req->retrans), max_rto); - req->expires = now + timeo; - reqp = &req->dl_next; - continue; - } - - /* Drop this request */ - inet_csk_reqsk_queue_unlink(parent, req, reqp); - reqsk_queue_removed(&icsk->icsk_accept_queue, req); - reqsk_free(req); - continue; - } - reqp = &req->dl_next; - } - - i = (i + 1) & (lopt->nr_table_entries - 1); - - } while (--budget > 0); - - lopt->clock_hand = i; - - if (lopt->qlen) - inet_csk_reset_keepalive_timer(parent, interval); -} - -EXPORT_SYMBOL_GPL(reqsk_queue_prune); - /* * Timer for listening sockets */ static void tcp_synack_timer(struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); - const int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; - - reqsk_queue_prune(&icsk->icsk_accept_queue, sk, TCP_SYNQ_INTERVAL, - TCP_TIMEOUT_INIT, TCP_RTO_MAX, max_retries); + inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL, + TCP_TIMEOUT_INIT, TCP_RTO_MAX); } void tcp_set_keepalive(struct sock *sk, int val) -- cgit v1.2.3-59-g8ed1b