From mboxrd@z Thu Jan 1 00:00:00 1970 From: Mark Lord Subject: Re: LibPATA code issues / 2.6.15.4 Date: Fri, 17 Mar 2006 00:26:11 -0500 Message-ID: <441A4873.3030102@rtr.ca> References: <1142344212.4416ca14a26b4@webmail.aon.at> <44182CD7.9070401@rtr.ca> <20060316100838.GF3595@suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from rtr.ca ([64.26.128.89]:42190 "EHLO mail.rtr.ca") by vger.kernel.org with ESMTP id S1751272AbWCQF0O (ORCPT ); Fri, 17 Mar 2006 00:26:14 -0500 In-Reply-To: <20060316100838.GF3595@suse.de> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Jens Axboe Cc: me_trash1@aon.at, linux-ide@vger.kernel.org, Jeff Garzik Jens Axboe wrote: > On Wed, Mar 15 2006, Mark Lord wrote: .. >> ATA cmd=0x35 is ATA_CMD_WRITE_EXT, and 0x25 (lower down in the logs) >> is ATA_CMD_READ_EXT. >> >> Those are the bog-standard (and slow!) PIO R/W commands, >> which generate one interrupt per 512-bytes transferred. > > Eh no they are not, 0x35 is WRITEDMA_EXT and 0x25 is READMA_EXT. We're both correct, in that 0x35 is ATA_CMD_WRITE_EXT as I said. But the naming had me fooled -- they really are DMA commands, even if the linux/ata.h names are incomplete. Cheers