From mboxrd@z Thu Jan 1 00:00:00 1970 From: Vlad Yasevich Subject: Re: [PATCH net] ipv6: don't use CHECKSUM_PARTIAL on MSG_MORE/UDP_CORK sockets Date: Tue, 20 Oct 2015 17:39:47 -0400 Message-ID: <5626B4A3.6080900@gmail.com> References: <1445351922-8463-1-git-send-email-hannes@stressinduktion.org> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Cc: sd@quesysnail.net, bcodding@redhat.com To: Hannes Frederic Sowa , netdev@vger.kernel.org Return-path: Received: from mail-qk0-f172.google.com ([209.85.220.172]:33234 "EHLO mail-qk0-f172.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753944AbbJTVkJ (ORCPT ); Tue, 20 Oct 2015 17:40:09 -0400 Received: by qkcy65 with SMTP id y65so14101253qkc.0 for ; Tue, 20 Oct 2015 14:40:08 -0700 (PDT) In-Reply-To: <1445351922-8463-1-git-send-email-hannes@stressinduktion.org> Sender: netdev-owner@vger.kernel.org List-ID: On 10/20/2015 10:38 AM, Hannes Frederic Sowa wrote: > MSG_MORE might cause the packet to get fragmented in the end when > passed down to the flush function and the transhdrlen check alone is > not sufficient to protect against fragmentation. Instead check if the > socket user intends to add more data to the socket on the first packet. > > This broke checksum calculation for UDPv6 for NFS protocols. > > Fixes: 32dce968dd987 ("ipv6: Allow for partial checksums on non-ufo packets") > Cc: Vlad Yasevich > Tested-by: Sabrina Dubroca > Tested-by: Benjamin Coddington > Signed-off-by: Hannes Frederic Sowa > --- > net/ipv6/ip6_output.c | 1 + > 1 file changed, 1 insertion(+) > > diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c > index 61d403e..95c5780 100644 > --- a/net/ipv6/ip6_output.c > +++ b/net/ipv6/ip6_output.c > @@ -1317,6 +1317,7 @@ emsgsize: > * sums only work when transhdrlen is set. > */ > if (transhdrlen && sk->sk_protocol == IPPROTO_UDP && > + !(flags & MSG_MORE) && > length + fragheaderlen < mtu && > rt->dst.dev->features & NETIF_F_V6_CSUM && > !exthdrlen) > Hmm... so while this solves this problem by simply avoiding the combination of skb #1 having CHECKSUM_PARTIAL and others having CHECKSUM_NONE, I think the actual problem is a bit deeper. The above combination seems to work for me since udp6_hwcsum_outgoing() corrects the checksum. However, my testing so far has been on nics that have NETIF_F_V6_CSUM, but without UFO support. On such systems a simple test of using MSG_MORE an IPv6 udp socket sending 200 bytes followed by 2000 bytes works correctly. I am now wondering if this might be UFO related instead and looking for a nic that has UFO support. -vlad