From: Chris Wright <chrisw@osdl.org>
Date: Fri, 30 Sep 2005 02:05:28 +0000 (-0700)
Subject: Add tcp_clam_window() fix fwd from DaveM
X-Git-Tag: v2.6.13.3~4
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=1222d9e254549e14af1e8dbffc3d3ba12d9cf863;p=thirdparty%2Fkernel%2Fstable-queue.git

Add tcp_clam_window() fix fwd from DaveM
---

diff --git a/queue/series b/queue/series
index b45bf51377e..8077aaf676b 100644
--- a/queue/series
+++ b/queue/series
@@ -7,3 +7,4 @@ uml-fix-x86_64-page-leak.patch
 check-connect-status-for-IPv6-UDP-socket.patch
 skge-set-mac-address-oops-with-bonding.patch
 tcp-set-default-congestion-control-correctly.patch
+tcp-dont-over-clamp-window-in-tcp_clamp_window.patch
diff --git a/queue/tcp-dont-over-clamp-window-in-tcp_clamp_window.patch b/queue/tcp-dont-over-clamp-window-in-tcp_clamp_window.patch
new file mode 100644
index 00000000000..d6fe80591f6
--- /dev/null
+++ b/queue/tcp-dont-over-clamp-window-in-tcp_clamp_window.patch
@@ -0,0 +1,51 @@
+From stable-bounces@linux.kernel.org  Thu Sep 29 17:19:58 2005
+Date: Thu, 29 Sep 2005 17:19:42 -0700 (PDT)
+To: stable@kernel.org
+From: "David S. Miller" <davem@davemloft.net>
+Subject: [TCP]: Don't over-clamp window in tcp_clamp_window()
+
+From: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
+
+Handle better the case where the sender sends full sized
+frames initially, then moves to a mode where it trickles
+out small amounts of data at a time.
+
+This known problem is even mentioned in the comments
+above tcp_grow_window() in tcp_input.c, specifically:
+
+...
+ * The scheme does not work when sender sends good segments opening
+ * window and then starts to feed us spagetti. But it should work
+ * in common situations. Otherwise, we have to rely on queue collapsing.
+...
+
+When the sender gives full sized frames, the "struct sk_buff" overhead
+from each packet is small.  So we'll advertize a larger window.
+If the sender moves to a mode where small segments are sent, this
+ratio becomes tilted to the other extreme and we start overrunning
+the socket buffer space.
+
+tcp_clamp_window() tries to address this, but it's clamping of
+tp->window_clamp is a wee bit too aggressive for this particular case.
+
+Fix confirmed by Ion Badulescu.
+
+Signed-off-by: "David S. Miller" <davem@davemloft.net>
+Signed-off-by: Chris Wright <chrisw@osdl.org>
+---
+ net/ipv4/tcp_input.c |    2 --
+ 1 files changed, 2 deletions(-)
+
+Index: linux-2.6.13.y/net/ipv4/tcp_input.c
+===================================================================
+--- linux-2.6.13.y.orig/net/ipv4/tcp_input.c
++++ linux-2.6.13.y/net/ipv4/tcp_input.c
+@@ -350,8 +350,6 @@ static void tcp_clamp_window(struct sock
+ 			app_win -= tp->ack.rcv_mss;
+ 		app_win = max(app_win, 2U*tp->advmss);
+ 
+-		if (!ofo_win)
+-			tp->window_clamp = min(tp->window_clamp, app_win);
+ 		tp->rcv_ssthresh = min(tp->window_clamp, 2U*tp->advmss);
+ 	}
+ }