X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv4%2Ftcp_timer.c;h=8816a20c25970ad4fe9ae172a4890af74ee928ce;hb=a83d8e8d099fc373a5ca7112ad08c553bb2c180f;hp=ea111e91f0e53f650bb0b6fe7d35656c64b156d9;hpb=829942c18704250fce4d5eca787065a3ee7c685d;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index ea111e9..8816a20 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -5,8 +5,6 @@
  *
  *		Implementation of the Transmission Control Protocol(TCP).
  *
- * Version:	$Id: tcp_timer.c,v 1.88 2002/02/01 22:01:04 davem Exp $
- *
  * Authors:	Ross Biro
  *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
  *		Mark Evans, <evansmp@uhura.aston.ac.uk>
@@ -50,7 +48,7 @@ static void tcp_write_err(struct sock *sk)
 	sk->sk_error_report(sk);
 
 	tcp_done(sk);
-	NET_INC_STATS_BH(LINUX_MIB_TCPABORTONTIMEOUT);
+	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
 }
 
 /* Do not allow orphaned sockets to eat all our resources.
@@ -67,7 +65,7 @@ static void tcp_write_err(struct sock *sk)
 static int tcp_out_of_resources(struct sock *sk, int do_reset)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	int orphans = atomic_read(&tcp_orphan_count);
+	int orphans = percpu_counter_read_positive(&tcp_orphan_count);
 
 	/* If peer does not open window for long time, or did not transmit
 	 * anything for long time, penalize it. */
@@ -91,7 +89,7 @@ static int tcp_out_of_resources(struct sock *sk, int do_reset)
 		if (do_reset)
 			tcp_send_active_reset(sk, GFP_ATOMIC);
 		tcp_done(sk);
-		NET_INC_STATS_BH(LINUX_MIB_TCPABORTONMEMORY);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
 		return 1;
 	}
 	return 0;
@@ -125,7 +123,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 			struct tcp_sock *tp = tcp_sk(sk);
 			int mss;
 
-			mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low)/2;
+			mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
 			mss = min(sysctl_tcp_base_mss, mss);
 			mss = max(mss, 68 - tp->tcp_header_len);
 			icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
@@ -134,22 +132,52 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 	}
 }
 
+/* This function calculates a "timeout" which is equivalent to the timeout of a
+ * TCP connection after "boundary" unsucessful, exponentially backed-off
+ * retransmissions with an initial RTO of TCP_RTO_MIN.
+ */
+static bool retransmits_timed_out(struct sock *sk,
+				  unsigned int boundary)
+{
+	unsigned int timeout, linear_backoff_thresh;
+	unsigned int start_ts;
+
+	if (!inet_csk(sk)->icsk_retransmits)
+		return false;
+
+	if (unlikely(!tcp_sk(sk)->retrans_stamp))
+		start_ts = TCP_SKB_CB(tcp_write_queue_head(sk))->when;
+	else
+		start_ts = tcp_sk(sk)->retrans_stamp;
+
+	linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN);
+
+	if (boundary <= linear_backoff_thresh)
+		timeout = ((2 << boundary) - 1) * TCP_RTO_MIN;
+	else
+		timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN +
+			  (boundary - linear_backoff_thresh) * TCP_RTO_MAX;
+
+	return (tcp_time_stamp - start_ts) >= timeout;
+}
+
 /* 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);
 	int retry_until;
+	bool do_reset;
 
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		if (icsk->icsk_retransmits)
-			dst_negative_advice(&sk->sk_dst_cache);
+			dst_negative_advice(&sk->sk_dst_cache, sk);
 		retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
 	} else {
-		if (icsk->icsk_retransmits >= sysctl_tcp_retries1) {
+		if (retransmits_timed_out(sk, sysctl_tcp_retries1)) {
 			/* Black hole detection */
 			tcp_mtu_probing(icsk, sk);
 
-			dst_negative_advice(&sk->sk_dst_cache);
+			dst_negative_advice(&sk->sk_dst_cache, sk);
 		}
 
 		retry_until = sysctl_tcp_retries2;
@@ -157,13 +185,15 @@ static int tcp_write_timeout(struct sock *sk)
 			const int alive = (icsk->icsk_rto < TCP_RTO_MAX);
 
 			retry_until = tcp_orphan_retries(sk, alive);
+			do_reset = alive ||
+				   !retransmits_timed_out(sk, retry_until);
 
-			if (tcp_out_of_resources(sk, alive || icsk->icsk_retransmits < retry_until))
+			if (tcp_out_of_resources(sk, do_reset))
 				return 1;
 		}
 	}
 
-	if (icsk->icsk_retransmits >= retry_until) {
+	if (retransmits_timed_out(sk, retry_until)) {
 		/* Has it gone just too far? */
 		tcp_write_err(sk);
 		return 1;
@@ -173,7 +203,7 @@ static int tcp_write_timeout(struct sock *sk)
 
 static void tcp_delack_timer(unsigned long data)
 {
-	struct sock *sk = (struct sock*)data;
+	struct sock *sk = (struct sock *)data;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -181,12 +211,12 @@ static void tcp_delack_timer(unsigned long data)
 	if (sock_owned_by_user(sk)) {
 		/* Try again later. */
 		icsk->icsk_ack.blocked = 1;
-		NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKLOCKED);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
 		sk_reset_timer(sk, &icsk->icsk_delack_timer, jiffies + TCP_DELACK_MIN);
 		goto out_unlock;
 	}
 
-	sk_stream_mem_reclaim(sk);
+	sk_mem_reclaim_partial(sk);
 
 	if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		goto out;
@@ -200,10 +230,10 @@ static void tcp_delack_timer(unsigned long data)
 	if (!skb_queue_empty(&tp->ucopy.prequeue)) {
 		struct sk_buff *skb;
 
-		NET_INC_STATS_BH(LINUX_MIB_TCPSCHEDULERFAILED);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSCHEDULERFAILED);
 
 		while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
-			sk->sk_backlog_rcv(sk, skb);
+			sk_backlog_rcv(sk, skb);
 
 		tp->ucopy.memory = 0;
 	}
@@ -220,13 +250,13 @@ static void tcp_delack_timer(unsigned long data)
 			icsk->icsk_ack.ato      = TCP_ATO_MIN;
 		}
 		tcp_send_ack(sk);
-		NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKS);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKS);
 	}
 	TCP_CHECK_TIMER(sk);
 
 out:
 	if (tcp_memory_pressure)
-		sk_stream_mem_reclaim(sk);
+		sk_mem_reclaim(sk);
 out_unlock:
 	bh_unlock_sock(sk);
 	sock_put(sk);
@@ -281,7 +311,7 @@ static void tcp_probe_timer(struct sock *sk)
  *	The TCP retransmit timer.
  */
 
-static void tcp_retransmit_timer(struct sock *sk)
+void tcp_retransmit_timer(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
@@ -289,7 +319,7 @@ static void tcp_retransmit_timer(struct sock *sk)
 	if (!tp->packets_out)
 		goto out;
 
-	BUG_TRAP(!tcp_write_queue_empty(sk));
+	WARN_ON(tcp_write_queue_empty(sk));
 
 	if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) &&
 	    !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) {
@@ -299,12 +329,20 @@ static void tcp_retransmit_timer(struct sock *sk)
 		 * we cannot allow such beasts to hang infinitely.
 		 */
 #ifdef TCP_DEBUG
-		if (1) {
-			struct inet_sock *inet = inet_sk(sk);
-			LIMIT_NETDEBUG(KERN_DEBUG "TCP: Treason uncloaked! Peer %u.%u.%u.%u:%u/%u shrinks window %u:%u. Repaired.\n",
-			       NIPQUAD(inet->daddr), ntohs(inet->dport),
-			       inet->num, tp->snd_una, tp->snd_nxt);
+		struct inet_sock *inet = inet_sk(sk);
+		if (sk->sk_family == AF_INET) {
+			LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
+			       &inet->inet_daddr, ntohs(inet->inet_dport),
+			       inet->inet_num, tp->snd_una, tp->snd_nxt);
 		}
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+		else if (sk->sk_family == AF_INET6) {
+			struct ipv6_pinfo *np = inet6_sk(sk);
+			LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
+			       &np->daddr, ntohs(inet->inet_dport),
+			       inet->inet_num, tp->snd_una, tp->snd_nxt);
+		}
+#endif
 #endif
 		if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) {
 			tcp_write_err(sk);
@@ -320,24 +358,24 @@ static void tcp_retransmit_timer(struct sock *sk)
 		goto out;
 
 	if (icsk->icsk_retransmits == 0) {
-		if (icsk->icsk_ca_state == TCP_CA_Disorder ||
-		    icsk->icsk_ca_state == TCP_CA_Recovery) {
-			if (tcp_is_sack(tp)) {
-				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 (icsk->icsk_ca_state == TCP_CA_Recovery)
-					NET_INC_STATS_BH(LINUX_MIB_TCPRENORECOVERYFAIL);
-				else
-					NET_INC_STATS_BH(LINUX_MIB_TCPRENOFAILURES);
-			}
+		int mib_idx;
+
+		if (icsk->icsk_ca_state == TCP_CA_Disorder) {
+			if (tcp_is_sack(tp))
+				mib_idx = LINUX_MIB_TCPSACKFAILURES;
+			else
+				mib_idx = LINUX_MIB_TCPRENOFAILURES;
+		} else if (icsk->icsk_ca_state == TCP_CA_Recovery) {
+			if (tcp_is_sack(tp))
+				mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL;
+			else
+				mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL;
 		} else if (icsk->icsk_ca_state == TCP_CA_Loss) {
-			NET_INC_STATS_BH(LINUX_MIB_TCPLOSSFAILURES);
+			mib_idx = LINUX_MIB_TCPLOSSFAILURES;
 		} else {
-			NET_INC_STATS_BH(LINUX_MIB_TCPTIMEOUTS);
+			mib_idx = LINUX_MIB_TCPTIMEOUTS;
 		}
+		NET_INC_STATS_BH(sock_net(sk), mib_idx);
 	}
 
 	if (tcp_use_frto(sk)) {
@@ -379,7 +417,7 @@ static void tcp_retransmit_timer(struct sock *sk)
 out_reset_timer:
 	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)
+	if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1))
 		__sk_dst_reset(sk);
 
 out:;
@@ -387,7 +425,7 @@ out:;
 
 static void tcp_write_timer(unsigned long data)
 {
-	struct sock *sk = (struct sock*)data;
+	struct sock *sk = (struct sock *)data;
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int event;
 
@@ -420,7 +458,7 @@ static void tcp_write_timer(unsigned long data)
 	TCP_CHECK_TIMER(sk);
 
 out:
-	sk_stream_mem_reclaim(sk);
+	sk_mem_reclaim(sk);
 out_unlock:
 	bh_unlock_sock(sk);
 	sock_put(sk);
@@ -493,8 +531,7 @@ 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 && icsk->icsk_probes_out >= sysctl_tcp_keepalive_probes) ||
-		     (tp->keepalive_probes && icsk->icsk_probes_out >= tp->keepalive_probes)) {
+		if (icsk->icsk_probes_out >= keepalive_probes(tp)) {
 			tcp_send_active_reset(sk, GFP_ATOMIC);
 			tcp_write_err(sk);
 			goto out;
@@ -514,7 +551,7 @@ static void tcp_keepalive_timer (unsigned long data)
 	}
 
 	TCP_CHECK_TIMER(sk);
-	sk_stream_mem_reclaim(sk);
+	sk_mem_reclaim(sk);
 
 resched:
 	inet_csk_reset_keepalive_timer (sk, elapsed);