X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=net%2Fipv4%2Ftcp_timer.c;h=7c1bde3cd6cb725b06fbea58a35743a62faa0552;hb=cc169158e75d370ff961e5653a326a7ee1688b6b;hp=799ebe061e2ca51c1fdd0831e4f227211c2b71e3;hpb=207e0a826fdee4bfe853681aef2175a739c11286;p=linux-2.6.git

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 799ebe061..7c1bde3cd 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -36,49 +36,13 @@ static void tcp_write_timer(unsigned long);
 static void tcp_delack_timer(unsigned long);
 static void tcp_keepalive_timer (unsigned long data);
 
-#ifdef TCP_DEBUG
-const char tcp_timer_bug_msg[] = KERN_DEBUG "tcpbug: unknown timer value\n";
-EXPORT_SYMBOL(tcp_timer_bug_msg);
-#endif
-
-/*
- * Using different timers for retransmit, delayed acks and probes
- * We may wish use just one timer maintaining a list of expire jiffies 
- * to optimize.
- */
-
 void tcp_init_xmit_timers(struct sock *sk)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	init_timer(&tp->retransmit_timer);
-	tp->retransmit_timer.function=&tcp_write_timer;
-	tp->retransmit_timer.data = (unsigned long) sk;
-	tp->pending = 0;
-
-	init_timer(&tp->delack_timer);
-	tp->delack_timer.function=&tcp_delack_timer;
-	tp->delack_timer.data = (unsigned long) sk;
-	tp->ack.pending = 0;
-
-	init_timer(&sk->sk_timer);
-	sk->sk_timer.function	= &tcp_keepalive_timer;
-	sk->sk_timer.data	= (unsigned long)sk;
+	inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
+				  &tcp_keepalive_timer);
 }
 
-void tcp_clear_xmit_timers(struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	tp->pending = 0;
-	sk_stop_timer(sk, &tp->retransmit_timer);
-
-	tp->ack.pending = 0;
-	tp->ack.blocked = 0;
-	sk_stop_timer(sk, &tp->delack_timer);
-
-	sk_stop_timer(sk, &sk->sk_timer);
-}
+EXPORT_SYMBOL(tcp_init_xmit_timers);
 
 static void tcp_write_err(struct sock *sk)
 {
@@ -94,7 +58,7 @@ static void tcp_write_err(struct sock *sk)
  * to prevent DoS attacks. It is called when a retransmission timeout
  * or zero probe timeout occurs on orphaned socket.
  *
- * Criterium is still not confirmed experimentally and may change.
+ * Criteria is still not confirmed experimentally and may change.
  * We kill the socket, if:
  * 1. If number of orphaned sockets exceeds an administratively configured
  *    limit.
@@ -155,50 +119,46 @@ static int tcp_orphan_retries(struct sock *sk, int alive)
 /* A write timeout has occurred. Process the after effects. */
 static int tcp_write_timeout(struct sock *sk)
 {
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int retry_until;
+	int mss;
 
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
-		if (tp->retransmits)
+		if (icsk->icsk_retransmits)
 			dst_negative_advice(&sk->sk_dst_cache);
-		retry_until = tp->syn_retries ? : sysctl_tcp_syn_retries;
+		retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
 	} else {
-		if (tp->retransmits >= sysctl_tcp_retries1) {
-			/* NOTE. draft-ietf-tcpimpl-pmtud-01.txt requires pmtu black
-			   hole detection. :-(
-
-			   It is place to make it. It is not made. I do not want
-			   to make it. It is disguisting. It does not work in any
-			   case. Let me to cite the same draft, which requires for
-			   us to implement this:
-
-   "The one security concern raised by this memo is that ICMP black holes
-   are often caused by over-zealous security administrators who block
-   all ICMP messages.  It is vitally important that those who design and
-   deploy security systems understand the impact of strict filtering on
-   upper-layer protocols.  The safest web site in the world is worthless
-   if most TCP implementations cannot transfer data from it.  It would
-   be far nicer to have all of the black holes fixed rather than fixing
-   all of the TCP implementations."
-
-                           Golden words :-).
-		   */
+		if (icsk->icsk_retransmits >= sysctl_tcp_retries1) {
+			/* Black hole detection */
+			if (sysctl_tcp_mtu_probing) {
+				if (!icsk->icsk_mtup.enabled) {
+					icsk->icsk_mtup.enabled = 1;
+					tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
+				} else {
+					mss = min(sysctl_tcp_base_mss,
+					          tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low)/2);
+					mss = max(mss, 68 - tp->tcp_header_len);
+					icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
+					tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
+				}
+			}
 
 			dst_negative_advice(&sk->sk_dst_cache);
 		}
 
 		retry_until = sysctl_tcp_retries2;
 		if (sock_flag(sk, SOCK_DEAD)) {
-			int alive = (tp->rto < TCP_RTO_MAX);
+			const int alive = (icsk->icsk_rto < TCP_RTO_MAX);
  
 			retry_until = tcp_orphan_retries(sk, alive);
 
-			if (tcp_out_of_resources(sk, alive || tp->retransmits < retry_until))
+			if (tcp_out_of_resources(sk, alive || icsk->icsk_retransmits < retry_until))
 				return 1;
 		}
 	}
 
-	if (tp->retransmits >= retry_until) {
+	if (icsk->icsk_retransmits >= retry_until) {
 		/* Has it gone just too far? */
 		tcp_write_err(sk);
 		return 1;
@@ -210,32 +170,32 @@ static void tcp_delack_timer(unsigned long data)
 {
 	struct sock *sk = (struct sock*)data;
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
 		/* Try again later. */
-		tp->ack.blocked = 1;
+		icsk->icsk_ack.blocked = 1;
 		NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKLOCKED);
-		sk_reset_timer(sk, &tp->delack_timer, jiffies + TCP_DELACK_MIN);
+		sk_reset_timer(sk, &icsk->icsk_delack_timer, jiffies + TCP_DELACK_MIN);
 		goto out_unlock;
 	}
 
 	sk_stream_mem_reclaim(sk);
 
-	if (sk->sk_state == TCP_CLOSE || !(tp->ack.pending & TCP_ACK_TIMER))
+	if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		goto out;
 
-	if (time_after(tp->ack.timeout, jiffies)) {
-		sk_reset_timer(sk, &tp->delack_timer, tp->ack.timeout);
+	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
+		sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
 		goto out;
 	}
-	tp->ack.pending &= ~TCP_ACK_TIMER;
+	icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER;
 
-	if (skb_queue_len(&tp->ucopy.prequeue)) {
+	if (!skb_queue_empty(&tp->ucopy.prequeue)) {
 		struct sk_buff *skb;
 
-		NET_ADD_STATS_BH(LINUX_MIB_TCPSCHEDULERFAILED, 
-				 skb_queue_len(&tp->ucopy.prequeue));
+		NET_INC_STATS_BH(LINUX_MIB_TCPSCHEDULERFAILED);
 
 		while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
 			sk->sk_backlog_rcv(sk, skb);
@@ -243,16 +203,16 @@ static void tcp_delack_timer(unsigned long data)
 		tp->ucopy.memory = 0;
 	}
 
-	if (tcp_ack_scheduled(tp)) {
-		if (!tp->ack.pingpong) {
+	if (inet_csk_ack_scheduled(sk)) {
+		if (!icsk->icsk_ack.pingpong) {
 			/* Delayed ACK missed: inflate ATO. */
-			tp->ack.ato = min(tp->ack.ato << 1, tp->rto);
+			icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto);
 		} else {
 			/* Delayed ACK missed: leave pingpong mode and
 			 * deflate ATO.
 			 */
-			tp->ack.pingpong = 0;
-			tp->ack.ato = TCP_ATO_MIN;
+			icsk->icsk_ack.pingpong = 0;
+			icsk->icsk_ack.ato      = TCP_ATO_MIN;
 		}
 		tcp_send_ack(sk);
 		NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKS);
@@ -269,11 +229,12 @@ out_unlock:
 
 static void tcp_probe_timer(struct sock *sk)
 {
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int max_probes;
 
 	if (tp->packets_out || !sk->sk_send_head) {
-		tp->probes_out = 0;
+		icsk->icsk_probes_out = 0;
 		return;
 	}
 
@@ -284,7 +245,7 @@ static void tcp_probe_timer(struct sock *sk)
 	 * FIXME: We ought not to do it, Solaris 2.5 actually has fixing
 	 * this behaviour in Solaris down as a bug fix. [AC]
 	 *
-	 * Let me to explain. probes_out is zeroed by incoming ACKs
+	 * Let me to explain. icsk_probes_out is zeroed by incoming ACKs
 	 * even if they advertise zero window. Hence, connection is killed only
 	 * if we received no ACKs for normal connection timeout. It is not killed
 	 * only because window stays zero for some time, window may be zero
@@ -295,15 +256,15 @@ static void tcp_probe_timer(struct sock *sk)
 	max_probes = sysctl_tcp_retries2;
 
 	if (sock_flag(sk, SOCK_DEAD)) {
-		int alive = ((tp->rto<<tp->backoff) < TCP_RTO_MAX);
+		const int alive = ((icsk->icsk_rto << icsk->icsk_backoff) < TCP_RTO_MAX);
  
 		max_probes = tcp_orphan_retries(sk, alive);
 
-		if (tcp_out_of_resources(sk, alive || tp->probes_out <= max_probes))
+		if (tcp_out_of_resources(sk, alive || icsk->icsk_probes_out <= max_probes))
 			return;
 	}
 
-	if (tp->probes_out > max_probes) {
+	if (icsk->icsk_probes_out > max_probes) {
 		tcp_write_err(sk);
 	} else {
 		/* Only send another probe if we didn't close things up. */
@@ -318,6 +279,7 @@ static void tcp_probe_timer(struct sock *sk)
 static void tcp_retransmit_timer(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	if (!tp->packets_out)
 		goto out;
@@ -352,20 +314,21 @@ static void tcp_retransmit_timer(struct sock *sk)
 	if (tcp_write_timeout(sk))
 		goto out;
 
-	if (tp->retransmits == 0) {
-		if (tp->ca_state == TCP_CA_Disorder || tp->ca_state == TCP_CA_Recovery) {
+	if (icsk->icsk_retransmits == 0) {
+		if (icsk->icsk_ca_state == TCP_CA_Disorder ||
+		    icsk->icsk_ca_state == TCP_CA_Recovery) {
 			if (tp->rx_opt.sack_ok) {
-				if (tp->ca_state == TCP_CA_Recovery)
+				if (icsk->icsk_ca_state == TCP_CA_Recovery)
 					NET_INC_STATS_BH(LINUX_MIB_TCPSACKRECOVERYFAIL);
 				else
 					NET_INC_STATS_BH(LINUX_MIB_TCPSACKFAILURES);
 			} else {
-				if (tp->ca_state == TCP_CA_Recovery)
+				if (icsk->icsk_ca_state == TCP_CA_Recovery)
 					NET_INC_STATS_BH(LINUX_MIB_TCPRENORECOVERYFAIL);
 				else
 					NET_INC_STATS_BH(LINUX_MIB_TCPRENOFAILURES);
 			}
-		} else if (tp->ca_state == TCP_CA_Loss) {
+		} else if (icsk->icsk_ca_state == TCP_CA_Loss) {
 			NET_INC_STATS_BH(LINUX_MIB_TCPLOSSFAILURES);
 		} else {
 			NET_INC_STATS_BH(LINUX_MIB_TCPTIMEOUTS);
@@ -382,10 +345,11 @@ static void tcp_retransmit_timer(struct sock *sk)
 		/* Retransmission failed because of local congestion,
 		 * do not backoff.
 		 */
-		if (!tp->retransmits)
-			tp->retransmits=1;
-		tcp_reset_xmit_timer(sk, TCP_TIME_RETRANS,
-				     min(tp->rto, TCP_RESOURCE_PROBE_INTERVAL));
+		if (!icsk->icsk_retransmits)
+			icsk->icsk_retransmits = 1;
+		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+					  min(icsk->icsk_rto, TCP_RESOURCE_PROBE_INTERVAL),
+					  TCP_RTO_MAX);
 		goto out;
 	}
 
@@ -404,13 +368,13 @@ static void tcp_retransmit_timer(struct sock *sk)
 	 * implemented ftp to mars will work nicely. We will have to fix
 	 * the 120 second clamps though!
 	 */
-	tp->backoff++;
-	tp->retransmits++;
+	icsk->icsk_backoff++;
+	icsk->icsk_retransmits++;
 
 out_reset_timer:
-	tp->rto = min(tp->rto << 1, TCP_RTO_MAX);
-	tcp_reset_xmit_timer(sk, TCP_TIME_RETRANS, tp->rto);
-	if (tp->retransmits > sysctl_tcp_retries1)
+	icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
+	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
+	if (icsk->icsk_retransmits > sysctl_tcp_retries1)
 		__sk_dst_reset(sk);
 
 out:;
@@ -419,32 +383,32 @@ out:;
 static void tcp_write_timer(unsigned long data)
 {
 	struct sock *sk = (struct sock*)data;
-	struct tcp_sock *tp = tcp_sk(sk);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	int event;
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
 		/* Try again later */
-		sk_reset_timer(sk, &tp->retransmit_timer, jiffies + (HZ / 20));
+		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + (HZ / 20));
 		goto out_unlock;
 	}
 
-	if (sk->sk_state == TCP_CLOSE || !tp->pending)
+	if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending)
 		goto out;
 
-	if (time_after(tp->timeout, jiffies)) {
-		sk_reset_timer(sk, &tp->retransmit_timer, tp->timeout);
+	if (time_after(icsk->icsk_timeout, jiffies)) {
+		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
 		goto out;
 	}
 
-	event = tp->pending;
-	tp->pending = 0;
+	event = icsk->icsk_pending;
+	icsk->icsk_pending = 0;
 
 	switch (event) {
-	case TCP_TIME_RETRANS:
+	case ICSK_TIME_RETRANS:
 		tcp_retransmit_timer(sk);
 		break;
-	case TCP_TIME_PROBE0:
+	case ICSK_TIME_PROBE0:
 		tcp_probe_timer(sk);
 		break;
 	}
@@ -463,100 +427,8 @@ out_unlock:
 
 static void tcp_synack_timer(struct sock *sk)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcp_listen_opt *lopt = tp->listen_opt;
-	int max_retries = tp->syn_retries ? : sysctl_tcp_synack_retries;
-	int thresh = max_retries;
-	unsigned long now = jiffies;
-	struct open_request **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 (tp->defer_accept)
-		max_retries = tp->defer_accept;
-
-	budget = 2*(TCP_SYNQ_HSIZE/(TCP_TIMEOUT_INIT/TCP_SYNQ_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 ||
-				     (req->acked && req->retrans < max_retries))
-				    && !req->class->rtx_syn_ack(sk, req, NULL)) {
-					unsigned long timeo;
-
-					if (req->retrans++ == 0)
-						lopt->qlen_young--;
-					timeo = min((TCP_TIMEOUT_INIT << req->retrans),
-						    TCP_RTO_MAX);
-					req->expires = now + timeo;
-					reqp = &req->dl_next;
-					continue;
-				}
-
-				/* Drop this request */
-				write_lock(&tp->syn_wait_lock);
-				*reqp = req->dl_next;
-				write_unlock(&tp->syn_wait_lock);
-				lopt->qlen--;
-				if (req->retrans == 0)
-					lopt->qlen_young--;
-				tcp_openreq_free(req);
-				continue;
-			}
-			reqp = &req->dl_next;
-		}
-
-		i = (i+1)&(TCP_SYNQ_HSIZE-1);
-
-	} while (--budget > 0);
-
-	lopt->clock_hand = i;
-
-	if (lopt->qlen)
-		tcp_reset_keepalive_timer(sk, TCP_SYNQ_INTERVAL);
-}
-
-void tcp_delete_keepalive_timer (struct sock *sk)
-{
-	sk_stop_timer(sk, &sk->sk_timer);
-}
-
-void tcp_reset_keepalive_timer (struct sock *sk, unsigned long len)
-{
-	sk_reset_timer(sk, &sk->sk_timer, jiffies + len);
+	inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL,
+				   TCP_TIMEOUT_INIT, TCP_RTO_MAX);
 }
 
 void tcp_set_keepalive(struct sock *sk, int val)
@@ -565,15 +437,16 @@ void tcp_set_keepalive(struct sock *sk, int val)
 		return;
 
 	if (val && !sock_flag(sk, SOCK_KEEPOPEN))
-		tcp_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk)));
+		inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk)));
 	else if (!val)
-		tcp_delete_keepalive_timer(sk);
+		inet_csk_delete_keepalive_timer(sk);
 }
 
 
 static void tcp_keepalive_timer (unsigned long data)
 {
 	struct sock *sk = (struct sock *) data;
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	__u32 elapsed;
 
@@ -581,7 +454,7 @@ static void tcp_keepalive_timer (unsigned long data)
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
 		/* Try again later. */ 
-		tcp_reset_keepalive_timer (sk, HZ/20);
+		inet_csk_reset_keepalive_timer (sk, HZ/20);
 		goto out;
 	}
 
@@ -592,7 +465,7 @@ static void tcp_keepalive_timer (unsigned long data)
 
 	if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) {
 		if (tp->linger2 >= 0) {
-			int tmo = tcp_fin_time(tp) - TCP_TIMEWAIT_LEN;
+			const int tmo = tcp_fin_time(sk) - TCP_TIMEWAIT_LEN;
 
 			if (tmo > 0) {
 				tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
@@ -615,14 +488,14 @@ static void tcp_keepalive_timer (unsigned long data)
 	elapsed = tcp_time_stamp - tp->rcv_tstamp;
 
 	if (elapsed >= keepalive_time_when(tp)) {
-		if ((!tp->keepalive_probes && tp->probes_out >= sysctl_tcp_keepalive_probes) ||
-		     (tp->keepalive_probes && tp->probes_out >= tp->keepalive_probes)) {
+		if ((!tp->keepalive_probes && icsk->icsk_probes_out >= sysctl_tcp_keepalive_probes) ||
+		     (tp->keepalive_probes && icsk->icsk_probes_out >= tp->keepalive_probes)) {
 			tcp_send_active_reset(sk, GFP_ATOMIC);
 			tcp_write_err(sk);
 			goto out;
 		}
 		if (tcp_write_wakeup(sk) <= 0) {
-			tp->probes_out++;
+			icsk->icsk_probes_out++;
 			elapsed = keepalive_intvl_when(tp);
 		} else {
 			/* If keepalive was lost due to local congestion,
@@ -639,7 +512,7 @@ static void tcp_keepalive_timer (unsigned long data)
 	sk_stream_mem_reclaim(sk);
 
 resched:
-	tcp_reset_keepalive_timer (sk, elapsed);
+	inet_csk_reset_keepalive_timer (sk, elapsed);
 	goto out;
 
 death:	
@@ -649,8 +522,3 @@ out:
 	bh_unlock_sock(sk);
 	sock_put(sk);
 }
-
-EXPORT_SYMBOL(tcp_clear_xmit_timers);
-EXPORT_SYMBOL(tcp_delete_keepalive_timer);
-EXPORT_SYMBOL(tcp_init_xmit_timers);
-EXPORT_SYMBOL(tcp_reset_keepalive_timer);