From owner-freebsd-hackers@FreeBSD.ORG Tue Feb 15 22:07:13 2005 Return-Path: Delivered-To: freebsd-hackers@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7EFBE16A4CE for ; Tue, 15 Feb 2005 22:07:13 +0000 (GMT) Received: from harmony.village.org (rover.village.org [168.103.84.182]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0A9AD43D45 for ; Tue, 15 Feb 2005 22:07:13 +0000 (GMT) (envelope-from imp@bsdimp.com) Received: from localhost (localhost [IPv6:::1]) by harmony.village.org (8.13.1/8.13.1) with ESMTP id j1FM5YSe055747; Tue, 15 Feb 2005 15:05:39 -0700 (MST) (envelope-from imp@bsdimp.com) Date: Tue, 15 Feb 2005 15:05:34 -0700 (MST) Message-Id: <20050215.150534.48477202.imp@bsdimp.com> To: scottl@samsco.org From: Warner Losh In-Reply-To: <42126390.5020804@samsco.org> References: <16914.22016.593790.719399@grasshopper.cs.duke.edu> <42126390.5020804@samsco.org> X-Mailer: Mew version 3.3 on Emacs 21.3 / Mule 5.0 (SAKAKI) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit cc: freebsd-hackers@freebsd.org cc: gallatin@cs.duke.edu Subject: Re: mapping small parts of a pci card to conserve KVA X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 15 Feb 2005 22:07:13 -0000 From: Scott Long Subject: Re: mapping small parts of a pci card to conserve KVA Date: Tue, 15 Feb 2005 14:03:12 -0700 > Andrew Gallatin wrote: > > > I maintain drivers for a PCI card which presents itself as having > > 16MB of address space. Eg: > > > > mx0: mem 0xf9000000-0xf9ffffff irq 20 at device 3.0 on pci1 > > > > However, most of that address space does not need to be mapped into > > the host. Really, only a little over 2MB needs to be mapped (3 regions > > with length 1024 bytes, 256 bytes, and 2MB). > > > > I've tried to re-write things so that I make multiple calls > > to bus_alloc_resource() with the (hopefully) appropriate offset and > > lengths. Eg: > > > > rid = PCIR_MAPS; > > *res = bus_alloc_resource(is->arch.dev, SYS_RES_MEMORY, &rid, > > (u_long)offset, > > (u_long)(offset + len - 1), len, > > RF_ACTIVE|PCI_RF_DENSE); > > > > At least on 5.3R, I seem to get back the same struct resource * from > > each call. rman_get_virtual() returns a different kva for each > > mapping, yet they all seem to map to the same physical address. > > Eg, I call vtophys() on the results of rman_get_virtual(), > > for each segment, and they all map to 0xf9000000. > > > > Is there a way to just map what I need? > > > > Thanks, > > > > Drew > > > > You can use pmap_mapdev() to create a KVA mapping of an arbitrary > physaddr+len. In fact, this is exactly what newbus uses to create the > PCI MEMIO resources when bus_alloc_resource() is called. I'm not sure > if the range is mapped and activated before the driver makes that call, > Warner or John might know for sure. If you go that route, you need to allocate the resource (all of it). RF_ACTIVE in the flags, or bus_activate_resource is what maps it in, so if you don't do that, you can call pmap_mamdev. Warner