Return-path: Received: from mail.candelatech.com ([208.74.158.172]:57787 "EHLO ns3.lanforge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754893AbaCCWIq (ORCPT ); Mon, 3 Mar 2014 17:08:46 -0500 Message-ID: <5314FD54.7070202@candelatech.com> (sfid-20140303_230850_200030_C388C3E8) Date: Mon, 03 Mar 2014 14:08:20 -0800 From: Ben Greear MIME-Version: 1.0 To: Michal Kazior CC: "ath10k@lists.infradead.org" , linux-wireless Subject: Re: [PATCH v2] ath10k: support msdu chaining. References: <1393550452-1302-1-git-send-email-greearb@candelatech.com> In-Reply-To: Content-Type: text/plain; charset=UTF-8 Sender: linux-wireless-owner@vger.kernel.org List-ID: On 02/27/2014 11:51 PM, Michal Kazior wrote: > On 28 February 2014 02:20, wrote: >> From: Ben Greear >> >> Consolidate the list of msdu skbs into the msdu-head skb, delete the >> rest of the skbs, pass the msdu-head skb on up the stack as normal. >> >> Tested with high-speed TCP and UDP traffic on modified firmware that >> supports raw-rx. > > As for an umodified firmware I expect ath10k will just re-assemble > corrupted frames just to have them dropped by mac80211. It might be > worth checking: > > if (chaining && fcs_error) > drop(); As far as I can tell, packets with bad FCS are dropped earlier in that rx method? Thanks, Ben -- Ben Greear Candela Technologies Inc http://www.candelatech.com