From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jens Axboe Subject: Re: [PATCH] [14/20] Don't disable direct_io for unchecked_isa_dma in st.c Date: Mon, 17 Mar 2008 09:27:30 +0100 Message-ID: <20080317082730.GC17940@kernel.dk> References: <20080307653.720459648@firstfloor.org> <20080307175414.08C981B41AE@basil.firstfloor.org> <20080314135135.GT17940@kernel.dk> <20080314142412.GA30325@infradead.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from brick.kernel.dk ([87.55.233.238]:15712 "EHLO kernel.dk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752276AbYCQI1d (ORCPT ); Mon, 17 Mar 2008 04:27:33 -0400 Content-Disposition: inline In-Reply-To: <20080314142412.GA30325@infradead.org> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: Christoph Hellwig Cc: Andi Kleen , James.Bottomley@HansenPartnership.com, linux-scsi@vger.kernel.org On Fri, Mar 14 2008, Christoph Hellwig wrote: > On Fri, Mar 14, 2008 at 02:51:35PM +0100, Jens Axboe wrote: > > Are you sure? Seems to me that st builds its own list with > > get_user_pages() for direct io, where will that get bounced? The block > > layer will only bounce things that are mapped directly, so if st used > > blk_rq_map_kern() and inserted that request in the queue, we could > > proceed with killing that check in st. > > Which shouldn't be all too difficult and would be the right thing to > do. We really need someone to sit down and convert st/osst/sg to use > the proper block layer helpers. Right, I'm just saying that it currently will not work! -- Jens Axboe