1 files changed, 41 insertions, 27 deletions

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 808bb920c9f..74a6aa00365 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -66,18 +66,18 @@ 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 = percpu_counter_read_positive(&tcp_orphan_count);
+	int shift = 0;
 
 	/* If peer does not open window for long time, or did not transmit
 	 * anything for long time, penalize it. */
 	if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset)
-		orphans <<= 1;
+		shift++;
 
 	/* If some dubious ICMP arrived, penalize even more. */
 	if (sk->sk_err_soft)
-		orphans <<= 1;
+		shift++;
 
-	if (tcp_too_many_orphans(sk, orphans)) {
+	if (tcp_too_many_orphans(sk, shift)) {
 		if (net_ratelimit())
 			printk(KERN_INFO "Out of socket memory\n");
 
@@ -135,13 +135,16 @@ 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.
+ * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if
+ * syn_set flag is set.
  */
 static bool retransmits_timed_out(struct sock *sk,
-				  unsigned int boundary)
+				  unsigned int boundary,
+				  unsigned int timeout,
+				  bool syn_set)
 {
-	unsigned int timeout, linear_backoff_thresh;
-	unsigned int start_ts;
+	unsigned int linear_backoff_thresh, start_ts;
+	unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN;
 
 	if (!inet_csk(sk)->icsk_retransmits)
 		return false;
@@ -151,14 +154,15 @@ static bool retransmits_timed_out(struct sock *sk,
 	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;
+	if (likely(timeout == 0)) {
+		linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);
 
+		if (boundary <= linear_backoff_thresh)
+			timeout = ((2 << boundary) - 1) * rto_base;
+		else
+			timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
+				(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
+	}
 	return (tcp_time_stamp - start_ts) >= timeout;
 }
 
@@ -167,14 +171,15 @@ static int tcp_write_timeout(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int retry_until;
-	bool do_reset;
+	bool do_reset, syn_set = 0;
 
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		if (icsk->icsk_retransmits)
 			dst_negative_advice(sk);
 		retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
+		syn_set = 1;
 	} else {
-		if (retransmits_timed_out(sk, sysctl_tcp_retries1)) {
+		if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
 			/* Black hole detection */
 			tcp_mtu_probing(icsk, sk);
 
@@ -187,14 +192,15 @@ static int tcp_write_timeout(struct sock *sk)
 
 			retry_until = tcp_orphan_retries(sk, alive);
 			do_reset = alive ||
-				   !retransmits_timed_out(sk, retry_until);
+				!retransmits_timed_out(sk, retry_until, 0, 0);
 
 			if (tcp_out_of_resources(sk, do_reset))
 				return 1;
 		}
 	}
 
-	if (retransmits_timed_out(sk, retry_until)) {
+	if (retransmits_timed_out(sk, retry_until,
+				  syn_set ? 0 : icsk->icsk_user_timeout, syn_set)) {
 		/* Has it gone just too far? */
 		tcp_write_err(sk);
 		return 1;
@@ -361,18 +367,19 @@ void tcp_retransmit_timer(struct sock *sk)
 	if (icsk->icsk_retransmits == 0) {
 		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 (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) {
 			mib_idx = LINUX_MIB_TCPLOSSFAILURES;
+		} else if ((icsk->icsk_ca_state == TCP_CA_Disorder) ||
+			   tp->sacked_out) {
+			if (tcp_is_sack(tp))
+				mib_idx = LINUX_MIB_TCPSACKFAILURES;
+			else
+				mib_idx = LINUX_MIB_TCPRENOFAILURES;
 		} else {
 			mib_idx = LINUX_MIB_TCPTIMEOUTS;
 		}
@@ -436,7 +443,7 @@ 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 (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1))
+	if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0, 0))
 		__sk_dst_reset(sk);
 
 out:;
@@ -556,7 +563,14 @@ static void tcp_keepalive_timer (unsigned long data)
 	elapsed = keepalive_time_elapsed(tp);
 
 	if (elapsed >= keepalive_time_when(tp)) {
-		if (icsk->icsk_probes_out >= keepalive_probes(tp)) {
+		/* If the TCP_USER_TIMEOUT option is enabled, use that
+		 * to determine when to timeout instead.
+		 */
+		if ((icsk->icsk_user_timeout != 0 &&
+		    elapsed >= icsk->icsk_user_timeout &&
+		    icsk->icsk_probes_out > 0) ||
+		    (icsk->icsk_user_timeout == 0 &&
+		    icsk->icsk_probes_out >= keepalive_probes(tp))) {
 			tcp_send_active_reset(sk, GFP_ATOMIC);
 			tcp_write_err(sk);
 			goto out;