X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv4%2Ftcp_timer.c;h=8a0ab2977f1fd8be8c4bf9f27d21efa9c214418e;hb=c10f5e12bafde7f7a2f9b75d76f7a68d62154e91;hp=e77e7ae0bf2c9c6be0651f1f0ac8fc95307bb567;hpb=0b040829952d84bf2a62526f0e24b624e0699447;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index e77e7ae..8a0ab29 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/gfp.h>
 #include <net/tcp.h>
 
 int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES;
@@ -29,6 +30,7 @@ int sysctl_tcp_keepalive_intvl __read_mostly = TCP_KEEPALIVE_INTVL;
 int sysctl_tcp_retries1 __read_mostly = TCP_RETR1;
 int sysctl_tcp_retries2 __read_mostly = TCP_RETR2;
 int sysctl_tcp_orphan_retries __read_mostly;
+int sysctl_tcp_thin_linear_timeouts __read_mostly;
 
 static void tcp_write_timer(unsigned long);
 static void tcp_delack_timer(unsigned long);
@@ -48,7 +50,7 @@ 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.
@@ -65,7 +67,7 @@ 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. */
@@ -89,7 +91,7 @@ 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;
@@ -132,22 +134,52 @@ 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" unsuccessful, 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;
@@ -155,13 +187,15 @@ 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;
@@ -171,7 +205,7 @@ 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);
 
@@ -179,7 +213,7 @@ 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;
 	}
@@ -198,10 +232,10 @@ 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;
 	}
@@ -218,7 +252,7 @@ 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);
 
@@ -279,7 +313,7 @@ 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);
@@ -287,7 +321,7 @@ 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))) {
@@ -299,16 +333,16 @@ static void tcp_retransmit_timer(struct sock *sk)
 #ifdef TCP_DEBUG
 		struct inet_sock *inet = inet_sk(sk);
 		if (sk->sk_family == AF_INET) {
-			LIMIT_NETDEBUG(KERN_DEBUG "TCP: Treason uncloaked! Peer " NIPQUAD_FMT ":%u/%u shrinks window %u:%u. Repaired.\n",
-			       NIPQUAD(inet->daddr), ntohs(inet->dport),
-			       inet->num, tp->snd_una, tp->snd_nxt);
+			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: Treason uncloaked! Peer " NIP6_FMT ":%u/%u shrinks window %u:%u. Repaired.\n",
-			       NIP6(np->daddr), ntohs(inet->dport),
-			       inet->num, tp->snd_una, tp->snd_nxt);
+			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
@@ -326,24 +360,24 @@ 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)) {
@@ -383,9 +417,27 @@ static void tcp_retransmit_timer(struct sock *sk)
 	icsk->icsk_retransmits++;
 
 out_reset_timer:
-	icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
+	/* If stream is thin, use linear timeouts. Since 'icsk_backoff' is
+	 * used to reset timer, set to 0. Recalculate 'icsk_rto' as this
+	 * might be increased if the stream oscillates between thin and thick,
+	 * thus the old value might already be too high compared to the value
+	 * set by 'tcp_set_rto' in tcp_input.c which resets the rto without
+	 * backoff. Limit to TCP_THIN_LINEAR_RETRIES before initiating
+	 * exponential backoff behaviour to avoid continue hammering
+	 * linear-timeout retransmissions into a black hole
+	 */
+	if (sk->sk_state == TCP_ESTABLISHED &&
+	    (tp->thin_lto || sysctl_tcp_thin_linear_timeouts) &&
+	    tcp_stream_is_thin(tp) &&
+	    icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
+		icsk->icsk_backoff = 0;
+		icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX);
+	} else {
+		/* Use normal (exponential) backoff */
+		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:;
@@ -393,7 +445,7 @@ 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;
 
@@ -442,6 +494,12 @@ static void tcp_synack_timer(struct sock *sk)
 				   TCP_TIMEOUT_INIT, TCP_RTO_MAX);
 }
 
+void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req)
+{
+	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEOUTS);
+}
+EXPORT_SYMBOL(tcp_syn_ack_timeout);
+
 void tcp_set_keepalive(struct sock *sk, int val)
 {
 	if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
@@ -487,11 +545,6 @@ static void tcp_keepalive_timer (unsigned long data)
 		goto death;
 	}
 
-	if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) {
-		tcp_send_active_reset(sk, GFP_ATOMIC);
-		goto death;
-	}
-
 	if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE)
 		goto out;
 
@@ -504,8 +557,7 @@ 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;