public inbox for netdev@vger.kernel.org
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: David Miller <davem@davemloft.net>
Cc: netdev <netdev@vger.kernel.org>,
	Neal Cardwell <ncardwell@google.com>,
	Van Jacobson <vanj@google.com>,
	Stephen Hemminger <stephen@networkplumber.org>,
	Yuchung Cheng <ycheng@google.com>
Subject: [PATCH] tcp: cubic: fix overflow error in bictcp_update()
Date: Mon, 05 Aug 2013 17:10:15 -0700	[thread overview]
Message-ID: <1375747815.4457.59.camel@edumazet-glaptop> (raw)

From: Eric Dumazet <edumazet@google.com>

commit 17a6e9f1aa9 ("tcp_cubic: fix clock dependency") added an
overflow error in bictcp_update() in following code :

/* change the unit from HZ to bictcp_HZ */
t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3) -
      ca->epoch_start) << BICTCP_HZ) / HZ;

Because msecs_to_jiffies() being unsigned long, compiler does
implicit type promotion.

We really want to constrain (tcp_time_stamp - ca->epoch_start)
to a signed 32bit value, or else 't' has unexpected high values.

This bugs triggers an increase of retransmit rates ~24 days after
boot [1], as the high order bit of tcp_time_stamp flips.

[1] for hosts with HZ=1000

Big thanks to Van Jacobson for spotting this problem.

Diagnosed-by: Van Jacobson <vanj@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
---
 net/ipv4/tcp_cubic.c |   10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index a9077f4..b6b591f 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -206,8 +206,8 @@ static u32 cubic_root(u64 a)
  */
 static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
 {
-	u64 offs;
-	u32 delta, t, bic_target, max_cnt;
+	u32 delta, bic_target, max_cnt;
+	u64 offs, t;
 
 	ca->ack_cnt++;	/* count the number of ACKs */
 
@@ -250,9 +250,11 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
 	 * if the cwnd < 1 million packets !!!
 	 */
 
+	t = (s32)(tcp_time_stamp - ca->epoch_start);
+	t += msecs_to_jiffies(ca->delay_min >> 3);
 	/* change the unit from HZ to bictcp_HZ */
-	t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3)
-	      - ca->epoch_start) << BICTCP_HZ) / HZ;
+	t <<= BICTCP_HZ;
+	do_div(t, HZ);
 
 	if (t < ca->bic_K)		/* t - K */
 		offs = ca->bic_K - t;

             reply	other threads:[~2013-08-06  0:10 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-08-06  0:10 Eric Dumazet [this message]
2013-08-06 15:12 ` [PATCH] tcp: cubic: fix overflow error in bictcp_update() Neal Cardwell
2013-08-07 17:36 ` David Miller

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1375747815.4457.59.camel@edumazet-glaptop \
    --to=eric.dumazet@gmail.com \
    --cc=davem@davemloft.net \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=stephen@networkplumber.org \
    --cc=vanj@google.com \
    --cc=ycheng@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox