From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH 3/9] netdev: bfin_mac: invalid data cache only once for each new rx skb buffer Date: Mon, 17 May 2010 17:21:38 -0700 (PDT) Message-ID: <20100517.172138.48493572.davem@davemloft.net> References: <1273505954-32588-1-git-send-email-vapier@gentoo.org> <1273505954-32588-3-git-send-email-vapier@gentoo.org> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, uclinux-dist-devel@blackfin.uclinux.org, sonic.zhang@analog.com To: vapier@gentoo.org Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:43031 "EHLO sunset.davemloft.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755514Ab0ERAVa (ORCPT ); Mon, 17 May 2010 20:21:30 -0400 In-Reply-To: <1273505954-32588-3-git-send-email-vapier@gentoo.org> Sender: netdev-owner@vger.kernel.org List-ID: From: Mike Frysinger Date: Mon, 10 May 2010 11:39:08 -0400 > From: Sonic Zhang > > The skb buffer isn't actually used until we finish transferring and pass > it up to higher layers, so only invalidate the range once before we start > receiving actual data. This also avoids the problem with data invalidating > on Blackfin systems -- there is no invalidate-only, just invalidate+flush. > So when running in writeback mode, there is the small (but not uncommon) > possibility of the flush overwriting valid DMA-ed data from the cache. > > Signed-off-by: Sonic Zhang > Signed-off-by: Mike Frysinger Applied.