tcp: Stalling connections: Fix timeout calculation routine

This patch fixes a problem in the TCP connection timeout calculation.
Currently, timeout decisions are made on the basis of the current
tcp_time_stamp and retrans_stamp, which is usually set at the first
retransmission.
However, if the retransmission fails in tcp_retransmit_skb(),
retrans_stamp is not updated and remains zero. This leads to wrong
decisions in retransmits_timed_out() if tcp_time_stamp is larger than
the specified timeout, which is very likely.
In this case, the TCP connection dies after the first attempted
(and unsuccessful) retransmission.

With this patch, tcp_skb_cb->when is used instead, when retrans_stamp
is not available.

This bug has been introduced together with retransmits_timed_out() in
2.6.32, as the number of retransmissions has been used for timeout
decisions before. The corresponding commit was
6fa12c85031485dff38ce550c24f10da23b0adaa (Revert Backoff [v3]:
Calculate TCP's connection close threshold as a time value.).

Thanks to Ilpo Järvinen for code suggestions and Frederic Leroy for
testing.

Reported-by: Frederic Leroy <fredo@starox.org>
Signed-off-by: Damian Lukowski <damian@tvk.rwth-aachen.de>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 8 insertions, 2 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e2d2ca2..e54bd85 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1265,14 +1265,20 @@ static inline struct sk_buff *tcp_write_queue_prev(struct sock *sk, struct sk_bu
  * TCP connection after "boundary" unsucessful, exponentially backed-off
  * retransmissions with an initial RTO of TCP_RTO_MIN.
  */
-static inline bool retransmits_timed_out(const struct sock *sk,
+static inline 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)
@@ -1281,7 +1287,7 @@ static inline bool retransmits_timed_out(const struct sock *sk,
 		timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN +
 			  (boundary - linear_backoff_thresh) * TCP_RTO_MAX;
 
-	return (tcp_time_stamp - tcp_sk(sk)->retrans_stamp) >= timeout;
+	return (tcp_time_stamp - start_ts) >= timeout;
 }
 
 static inline struct sk_buff *tcp_send_head(struct sock *sk)