From mboxrd@z Thu Jan 1 00:00:00 1970 From: Robert Hancock Subject: Re: [RFC PATCH] nForce4 ADMA with NCQ: It's aliiiive.. Date: Mon, 16 Oct 2006 17:40:12 -0600 Message-ID: <4534185C.9060401@shaw.ca> References: <452C7C1D.3040704@shaw.ca> <20061011103038.GK6515@kernel.dk> <452F053B.2000906@shaw.ca> <4533B0B3.8070205@rtr.ca> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from shawidc-mo1.cg.shawcable.net ([24.71.223.10]:24338 "EHLO pd2mo2so.prod.shaw.ca") by vger.kernel.org with ESMTP id S1422939AbWJPXlF (ORCPT ); Mon, 16 Oct 2006 19:41:05 -0400 In-reply-to: <4533B0B3.8070205@rtr.ca> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Mark Lord Cc: Jens Axboe , Allen Martin , Jeff Garzik , linux-kernel , linux-ide@vger.kernel.org, prakash@punnoor.de Mark Lord wrote: > Robert Hancock wrote: >> >> I also noticed that I'm still using the default 64KB libata >> dma_boundary value, this should be 4GB for ADMA mode (but fixed up >> back to the default if an ATAPI device is connected, same as with the >> DMA mask). > > Be careful of that. The original PDC hardware for ADMA still had > the "don't cross a 64KB boundary" requirement. > > Cheers That is part of the ADMA spec - but in that case, how come the pdc_adma.c driver sets the dma_boundary in the SCSI host template to 4GB? That seems wrong. In any case, however, I really doubt the NVIDIA ADMA controller shares this limitation - they provide 32 bits for the region length (standard ADMA only has 16 bits), which wouldn't be very useful if you couldn't cross a 64KB boundary.. -- Robert Hancock Saskatoon, SK, Canada To email, remove "nospam" from hancockr@nospamshaw.ca Home Page: http://www.roberthancock.com/