Patchwork tcp: fix an infinite loop in tcp_slow_start()

login
register
mail settings
Submitter Eric Dumazet
Date Feb. 2, 2013, 3:23 p.m.
Message ID <1359818596.30177.84.camel@edumazet-glaptop>
Download mbox | patch
Permalink /patch/217675/
State Accepted
Delegated to: David Miller
Headers show

Comments

Eric Dumazet - Feb. 2, 2013, 3:23 p.m.
From: Eric Dumazet <edumazet@google.com>

Since commit 9dc274151a548 (tcp: fix ABC in tcp_slow_start()),
a nul snd_cwnd triggers an infinite loop in tcp_slow_start()

Avoid this infinite loop and log a one time error for further
analysis. FRTO code is suspected to cause this bug.

Reported-by: Pasi Kärkkäinen <pasik@iki.fi>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
---
 net/ipv4/tcp_cong.c |   14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)



--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
David Miller - Feb. 3, 2013, 9:01 p.m.
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Sat, 02 Feb 2013 07:23:16 -0800

> From: Eric Dumazet <edumazet@google.com>
> 
> Since commit 9dc274151a548 (tcp: fix ABC in tcp_slow_start()),
> a nul snd_cwnd triggers an infinite loop in tcp_slow_start()
> 
> Avoid this infinite loop and log a one time error for further
> analysis. FRTO code is suspected to cause this bug.
> 
> Reported-by: Pasi Kärkkäinen <pasik@iki.fi>
> Signed-off-by: Eric Dumazet <edumazet@google.com>

Applied.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 291f2ed..cdf2e70 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -310,6 +310,12 @@  void tcp_slow_start(struct tcp_sock *tp)
 {
 	int cnt; /* increase in packets */
 	unsigned int delta = 0;
+	u32 snd_cwnd = tp->snd_cwnd;
+
+	if (unlikely(!snd_cwnd)) {
+		pr_err_once("snd_cwnd is nul, please report this bug.\n");
+		snd_cwnd = 1U;
+	}
 
 	/* RFC3465: ABC Slow start
 	 * Increase only after a full MSS of bytes is acked
@@ -324,7 +330,7 @@  void tcp_slow_start(struct tcp_sock *tp)
 	if (sysctl_tcp_max_ssthresh > 0 && tp->snd_cwnd > sysctl_tcp_max_ssthresh)
 		cnt = sysctl_tcp_max_ssthresh >> 1;	/* limited slow start */
 	else
-		cnt = tp->snd_cwnd;			/* exponential increase */
+		cnt = snd_cwnd;				/* exponential increase */
 
 	/* RFC3465: ABC
 	 * We MAY increase by 2 if discovered delayed ack
@@ -334,11 +340,11 @@  void tcp_slow_start(struct tcp_sock *tp)
 	tp->bytes_acked = 0;
 
 	tp->snd_cwnd_cnt += cnt;
-	while (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
-		tp->snd_cwnd_cnt -= tp->snd_cwnd;
+	while (tp->snd_cwnd_cnt >= snd_cwnd) {
+		tp->snd_cwnd_cnt -= snd_cwnd;
 		delta++;
 	}
-	tp->snd_cwnd = min(tp->snd_cwnd + delta, tp->snd_cwnd_clamp);
+	tp->snd_cwnd = min(snd_cwnd + delta, tp->snd_cwnd_clamp);
 }
 EXPORT_SYMBOL_GPL(tcp_slow_start);