From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tejun Heo Subject: Re: Random libata notes Date: Fri, 10 Mar 2006 23:33:47 +0900 Message-ID: <44118E4B.9050401@gmail.com> References: <4409CF74.7030808@garzik.org> <44118B3D.9040103@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from zproxy.gmail.com ([64.233.162.199]:57071 "EHLO zproxy.gmail.com") by vger.kernel.org with ESMTP id S1751317AbWCJO4G (ORCPT ); Fri, 10 Mar 2006 09:56:06 -0500 Received: by zproxy.gmail.com with SMTP id 14so771088nzn for ; Fri, 10 Mar 2006 06:56:06 -0800 (PST) In-Reply-To: <44118B3D.9040103@gmail.com> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Jeff Garzik Cc: "linux-ide@vger.kernel.org" , Jens Axboe , Mark Lord Tejun Heo wrote: > Jeff Garzik wrote: > >> These are small TODO bits that I didn't want to forget... Patches >> welcome. >> >> 1) ATAPI edge case. Due to adding the padding s/g entry, we must >> adjust sg_tablesize to include ' - 1' for each driver > > > Isn't this handled by ata_scsi_slave_config()? If the attached device is > ATAPI, ata_scsi_slave_config() reduces max_hw_segments by 1. We'll need > to increment it back when detaching the device though. > >> >> 2) ata_scsi_slave_config() hardcodes a call to >> blk_queue_max_phys_segments(, LIBATA_MAX_PRD), when the value passed >> should not be so limited on nice hardware like AHCI. And, AFAICS, we can increase max_phys_segments all we want. This limits the number of segments before IOMMU mapping. The only part that's affected is the driver (software) and I don't see any limitation in libata PIO implementation that puts limitation on the number of sg entries. Simply changing LIBATA_MAX_PRD to 65535 should do it. >> >> 3) sata_mv: add back SCR_ERR clear? >> mv_scr_write(ap, SCR_ERROR, mv_scr_read(ap, SCR_ERROR)); >> >> 4) sata_mv: set DMA mask >> -- tejun