From owner-freebsd-current@FreeBSD.ORG Fri Mar 2 16:04:04 2007 Return-Path: X-Original-To: current@freebsd.org Delivered-To: freebsd-current@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 0046316A403 for ; Fri, 2 Mar 2007 16:04:03 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.freebsd.org (Postfix) with ESMTP id A8D8713C494 for ; Fri, 2 Mar 2007 16:04:03 +0000 (UTC) (envelope-from scottl@samsco.org) Received: from phobos.samsco.home (phobos.samsco.home [192.168.254.11]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id l22G3jfd063203; Fri, 2 Mar 2007 09:03:50 -0700 (MST) (envelope-from scottl@samsco.org) Message-ID: <45E84AD3.7010908@samsco.org> Date: Fri, 02 Mar 2007 09:03:31 -0700 From: Scott Long User-Agent: Mozilla/5.0 (Macintosh; U; Intel Mac OS X; en-US; rv:1.8.1.2pre) Gecko/20070111 SeaMonkey/1.1 MIME-Version: 1.0 To: Mark Tinguely References: <200703021442.l22Eg6QT058195@casselton.net> In-Reply-To: <200703021442.l22Eg6QT058195@casselton.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Greylist: Sender succeeded SMTP AUTH authentication, not delayed by milter-greylist-2.0.2 (pooker.samsco.org [168.103.85.57]); Fri, 02 Mar 2007 09:03:50 -0700 (MST) X-Spam-Status: No, score=-1.4 required=3.8 tests=ALL_TRUSTED autolearn=failed version=3.1.1 X-Spam-Checker-Version: SpamAssassin 3.1.1 (2006-03-10) on pooker.samsco.org Cc: current@freebsd.org Subject: Re: multisegment bus_dmamem_alloc() X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 02 Mar 2007 16:04:04 -0000 Mark Tinguely wrote: > Are there any other devices other than bktr(4) that could benefit > from a multisegment bus_dmamem_alloc(9) routine? The old USB system > comes to mind, but I have not studied the new USB. There may be others. > > NetBSD only partially implements this (if the number page allocated > number > of segments, they punt and do a totally contiguous allocation - IMO, they > could fix this pretty easy though). > > I know chages to contigmalloc() is a tricky subject. I was hoping > there are enough drivers that would provide enough merits to change > such an important part of the system. If not, please forgive this noise. > Looking at bktr, it's not at all clear to me why the author felt that FreeBSD didn't support bus_dmamem_alloc. It's even stranger since the author explicitly tells the NetBSD/OpenBSD code to only allocate 1 segment. Meh. I'm getting tired of fighting the busdma API fight with developers who deliberately ignore standard API's that have been around for almost 10 years. Multi-segment bus_dmamem_alloc support would be nice, but bringing the drivers up to API standards would be an even nicer first step. Scott