From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH] gso: Validate assumption of frag_list segementation Date: Mon, 17 Apr 2017 15:32:59 -0400 (EDT) Message-ID: <20170417.153259.1519976990479511796.davem@davemloft.net> References: <20170416080007.15990-1-ilant@mellanox.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, alexander.h.duyck@intel.com, eric.dumazet@gmail.com, steffen.klassert@secunet.com, borisp@mellanox.com, ilyal@mellanox.com To: ilant@mellanox.com Return-path: Received: from shards.monkeyblade.net ([184.105.139.130]:57384 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753906AbdDQTdB (ORCPT ); Mon, 17 Apr 2017 15:33:01 -0400 In-Reply-To: <20170416080007.15990-1-ilant@mellanox.com> Sender: netdev-owner@vger.kernel.org List-ID: From: Date: Sun, 16 Apr 2017 11:00:07 +0300 > From: Ilan Tayari > > Commit 07b26c9454a2 ("gso: Support partial splitting at the frag_list > pointer") assumes that all SKBs in a frag_list (except maybe the last > one) contain the same amount of GSO payload. > > This assumption is not always correct, resulting in the following > warning message in the log: > skb_segment: too many frags > > For example, mlx5 driver in Striding RQ mode creates some RX SKBs with > one frag, and some with 2 frags. > After GRO, the frag_list SKBs end up having different amounts of payload. > If this frag_list SKB is then forwarded, the aforementioned assumption > is violated. > > Validate the assumption, and fall back to software GSO if it not true. > > Fixes: 07b26c9454a2 ("gso: Support partial splitting at the frag_list pointer") > Signed-off-by: Ilan Tayari > Signed-off-by: Ilya Lesokhin > --- Your commit message mentions a fixes tag which make this change seem relevant for 'net', but your patch depends upon things in 'net-next' and therefore only applies there. I've added this change to net-next, but I want an explanation of why this change is not targettting 'net' if it seems to fix a problem there. Thanks.