From mboxrd@z Thu Jan 1 00:00:00 1970 From: Linus Torvalds Subject: Re: [git patches] libata fixes Date: Wed, 27 Jun 2007 08:48:48 -0700 (PDT) Message-ID: References: <20070627073526.GA18787@havoc.gtf.org> <20070627003841.68fd0ea9.akpm@linux-foundation.org> <46821613.9010305@garzik.org> Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=us-ascii Return-path: Received: from smtp2.linux-foundation.org ([207.189.120.14]:52567 "EHLO smtp2.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752894AbXF0Ps7 (ORCPT ); Wed, 27 Jun 2007 11:48:59 -0400 In-Reply-To: <46821613.9010305@garzik.org> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Jeff Garzik Cc: Andrew Morton , linux-ide@vger.kernel.org, LKML On Wed, 27 Jun 2007, Jeff Garzik wrote: > > Such would be a diagnostic that would trigger on valid SCSI commands, when the > user is doing nothing wrong and the system can indeed complete the command > just fine. Additionally, this is moving us in the direction of what the IDE > driver has apparently been doing. Indeed. At least the IDE CD-ROM driver does if ((rq->data_len & 15) || (addr & mask)) info->dma = 0; where the "mask" is the dma_alignment mask. So it requires the length to be a multiple of 16, and also requires a certain alignment of the data (which defaults to 32 bytes for some reason I cannot for the life of me remember). The generic BIO layer does that DMA alignment check too when mapping user pages. Linus