netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Patrick McHardy <kaber@trash.net>
To: "David S. Miller" <davem@davemloft.net>,
	"Ilpo Järvinen" <ilpo.jarvinen@helsinki.fi>
Cc: Linux Netdev List <netdev@vger.kernel.org>
Subject: [TCP]: Fix shrinking windows with window scaling
Date: Fri, 14 Mar 2008 18:42:38 +0100	[thread overview]
Message-ID: <47DAB90E.40806@trash.net> (raw)

[-- Attachment #1: Type: text/plain, Size: 71 bytes --]

Please review carefully since I'm not too familiar with the
TCP code.


[-- Attachment #2: x --]
[-- Type: text/plain, Size: 2308 bytes --]

commit adced31497ffbb3fe6ffef2d05f2b8fc74f1f138
Author: Patrick McHardy <kaber@trash.net>
Date:   Fri Mar 14 17:15:20 2008 +0100

    [TCP]: Fix shrinking windows with window scaling

    When selecting a new window, tcp_select_window() tries not to shrink
    the offered window by using the maximum of the remaining offered window
    size and the newly calculated window size. The newly calculated window
    size is always a multiple of the window scaling factor, the remaining
    window size however might not be since it depends on rcv_wup/rcv_nxt.
    This means we're effectively shrinking the window when scaling it down.


    The dump below shows the problem (scaling factor 2^7):

    - Window size of 557 (71296) is advertised, up to 3111907257:

    IP 172.2.2.3.33000 > 172.2.2.2.33000: . ack 3111835961 win 557 <...>

    - New window size of 514 (65792) is advertised, up to 3111907217, 40 bytes
      below the last end:

    IP 172.2.2.3.33000 > 172.2.2.2.33000: . 3113575668:3113577116(1448) ack 3111841425 win 514 <...>

    The number 40 results from downscaling the remaining window:

    3111907257 - 3111841425 = 65832
    65832 / 2^7 = 514
    65832 % 2^7 = 40

    If the sender uses up the entire window before it is shrunk, this can have
    chaotic effects on the connection. When sending ACKs, tcp_acceptable_seq()
    will notice that the window has been shrunk since tcp_wnd_end() is before
    tp->snd_nxt, which makes it choose tcp_wnd_end() as sequence number.
    This will fail the receivers checks in tcp_sequence() however since it
    is before it's tp->rcv_wup, making it respond with a dupack.

    If both sides are in this condition, this leads to a constant flood of
    ACKs until the connection times out.


    Make sure the window is never shrunk by aligning the remaining window to
    the window scaling factor.

    Signed-off-by: Patrick McHardy <kaber@trash.net>

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 01578f5..72b9350 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -255,7 +255,7 @@ static u16 tcp_select_window(struct sock *sk)
 		 *
 		 * Relax Will Robinson.
 		 */
-		new_win = cur_win;
+		new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale);
 	}
 	tp->rcv_wnd = new_win;
 	tp->rcv_wup = tp->rcv_nxt;

             reply	other threads:[~2008-03-14 17:51 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-03-14 17:42 Patrick McHardy [this message]
2008-03-20 23:12 ` [TCP]: Fix shrinking windows with window scaling 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=47DAB90E.40806@trash.net \
    --to=kaber@trash.net \
    --cc=davem@davemloft.net \
    --cc=ilpo.jarvinen@helsinki.fi \
    --cc=netdev@vger.kernel.org \
    /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;
as well as URLs for NNTP newsgroup(s).