From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: NETIF_F_HIGHDMA? Date: Wed, 12 Feb 2014 17:51:54 -0500 (EST) Message-ID: <20140212.175154.969884304002436752.davem@davemloft.net> References: <52FBFD03.6000703@cogentembedded.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org To: sergei.shtylyov@cogentembedded.com Return-path: Received: from shards.monkeyblade.net ([149.20.54.216]:32965 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753284AbaBLWv4 (ORCPT ); Wed, 12 Feb 2014 17:51:56 -0500 In-Reply-To: <52FBFD03.6000703@cogentembedded.com> Sender: netdev-owner@vger.kernel.org List-ID: From: Sergei Shtylyov Date: Thu, 13 Feb 2014 02:00:19 +0300 > Hello. > > I fail to understand why this flag is needed at > all. netdev-features.txt says: > > * Transmit DMA from high memory > > On platforms where this is relevant, NETIF_F_HIGHDMA signals that > ndo_start_xmit can handle skbs with frags in high memory. Back when this flag was created we had pretty much no infrastructure to deal with DMA masks, and furthermore it was not universal that code accessed high memory pages correctly. So this was the hack we used, the flag meant that your driver was able to access high memory pages correctly (ie. didn't assume that all pages were identity mapped) and that you could handle pages that potentially had physical addresses above 4GB. It was a big hammer handling a lack of proper APIs, that's all.