From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tejun Heo Subject: Re: [PATCH 13/13] libata: use PIO for misc ATAPI commands Date: Wed, 28 Nov 2007 08:37:07 +0900 Message-ID: <474CAA23.1070400@gmail.com> References: <11961764391983-git-send-email-htejun@gmail.com> <11961764413291-git-send-email-htejun@gmail.com> <20071127165600.39b8c383@the-village.bc.nu> <474CA1E2.1060008@gmail.com> <474CA8DD.3040004@rtr.ca> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: Received: from ro-out-1112.google.com ([72.14.202.177]:33510 "EHLO ro-out-1112.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757819AbXK0XhP (ORCPT ); Tue, 27 Nov 2007 18:37:15 -0500 Received: by ro-out-1112.google.com with SMTP id p4so2074212roc for ; Tue, 27 Nov 2007 15:37:14 -0800 (PST) In-Reply-To: <474CA8DD.3040004@rtr.ca> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Mark Lord Cc: Alan Cox , jeff@garzik.org, linux-ide@vger.kernel.org, albertl@mail.com, jens.axboe@oracle.com Mark Lord wrote: > Tejun Heo wrote: >> Alan Cox wrote: > .. >> Because we can't use DMA uniformly, I went the other way and tried to >> use PIO uniformly. Another important point is that the other OS which >> is probably the only platform most ATAPI device vendors test against use >> PIO for these commands. >> >>> - Control over the DMA/PIO strategy belongs with the driver. If we mess >>> that up it will cost us dearly later. >> >> And I don't get what we'll lose. Care to deliberate? > .. > > Mmmm.. so what happens with the various controllers that can do PIO > using host-DMA and host-queuing ? Dropping to *real* PIO mode can > be quite expensive on those, especially when the channel is shared > with a hard disk. They continue to do PIO the way they used to do. No reason to drop to *real* PIO mode. Also, as now DMA / DMA-PIO buffers have trailing drain buffer for misc ATAPI commands, it should behave the same way as real PIO mode to the attached drive. -- tejun