All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Jorge Boncompte [DTI2]" <jorge@dti2.net>
To: Linux Network Development list <netdev@vger.kernel.org>
Subject: [PATCH] udp: fix for unicast RX path optimization
Date: Thu, 08 Apr 2010 16:56:48 +0200	[thread overview]
Message-ID: <4BBDEEB0.7060003@dti2.net> (raw)

	Commits 5051ebd275de672b807c28d93002c2fb0514a3c9 and
5051ebd275de672b807c28d93002c2fb0514a3c9 ("ipv[46]: udp: optimize unicast RX
path") broke some programs.

	After upgrading a L2TP server to 2.6.33 it started to fail, tunnels going up an
down, after the 10th tunnel came up. My modified rp-l2tp uses a global
unconnected socket bound to (INADDR_ANY, 1701) and one connected socket per
tunnel after parameter negotiation.

	After ten sockets were open and due to mixed parameters to
udp[46]_lib_lookup2() kernel started to drop packets.

Signed-off-by: Jorge Boncompte [DTI2] <jorge@dti2.net>
---
diff -uNrp linux-2.6.33/net/ipv4/udp.c kernel-netns/net/ipv4/udp.c
--- linux-2.6.33/net/ipv4/udp.c	2010-02-24 19:52:17.000000000 +0100
+++ kernel-netns/net/ipv4/udp.c	2010-04-08 15:07:21.888717449 +0200
@@ -471,8 +471,8 @@ static struct sock *__udp4_lib_lookup(st
 			if (hslot->count < hslot2->count)
 				goto begin;

-			result = udp4_lib_lookup2(net, INADDR_ANY, sport,
-						  daddr, hnum, dif,
+			result = udp4_lib_lookup2(net, saddr, sport,
+						  INADDR_ANY, hnum, dif,
 						  hslot2, slot2);
 		}
 		rcu_read_unlock();
diff -uNrp linux-2.6.33/net/ipv6/udp.c kernel-netns/net/ipv6/udp.c
--- linux-2.6.33/net/ipv6/udp.c	2010-02-24 19:52:17.000000000 +0100
+++ kernel-netns/net/ipv6/udp.c	2010-04-08 15:07:57.081396901 +0200
@@ -258,8 +258,8 @@ static struct sock *__udp6_lib_lookup(st
 			if (hslot->count < hslot2->count)
 				goto begin;

-			result = udp6_lib_lookup2(net, &in6addr_any, sport,
-						  daddr, hnum, dif,
+			result = udp6_lib_lookup2(net, saddr, sport,
+						  &in6addr_any, hnum, dif,
 						  hslot2, slot2);
 		}
 		rcu_read_unlock();


             reply	other threads:[~2010-04-08 15:02 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-04-08 14:56 Jorge Boncompte [DTI2] [this message]
2010-04-08 15:12 ` [PATCH] udp: fix for unicast RX path optimization Eric Dumazet
2010-04-08 18:16   ` David Miller
2010-04-08 18:30   ` 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=4BBDEEB0.7060003@dti2.net \
    --to=jorge@dti2.net \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.