From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Garzik Subject: Re: [PATCH 1/6] via-velocity: remove the bounce buffers Date: Fri, 11 Jul 2008 01:14:04 -0400 Message-ID: <4876EC1C.4080705@garzik.org> References: <20080710220344.GB29764@electric-eye.fr.zoreil.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: netdev@vger.kernel.org, =?ISO-8859-1?Q?S=E9guier_R=E9gis?= , akpm@linux-foundation.org To: Francois Romieu Return-path: Received: from srv5.dvmed.net ([207.36.208.214]:46466 "EHLO mail.dvmed.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750886AbYGKFOM (ORCPT ); Fri, 11 Jul 2008 01:14:12 -0400 In-Reply-To: <20080710220344.GB29764@electric-eye.fr.zoreil.com> Sender: netdev-owner@vger.kernel.org List-ID: =46rancois Romieu wrote: > Executive summary: the bounce buffers are in my way >=20 > - they use something like a 64 * 1500 bytes area of PCI > consistent area > - they are not resized when the MTU changes > - they are used > - to hand-pad undersized packets. skb_pad anyone ? > - to linearize fragmented skbs whose fragment count > goes beyond the 7 fragments hardware limit in order > to claim scatter-gather support >=20 > Actually the SG code is commented out and I wonder if it > could not be implemented (ab-)using the large send feature > of the chipset since the latter should support some > multi-descriptor packet transmitting. >=20 > Signed-off-by: Francois Romieu > Fixed-by: S=E9guier R=E9gis > --- > drivers/net/via-velocity.c | 72 +++++++++++-----------------------= ---------- > drivers/net/via-velocity.h | 5 --- > 2 files changed, 18 insertions(+), 59 deletions(-) >=20 ACK patches 1-6 applied 1-4, patch #5 failed to apply