Return-path: Received: from smtp2.linux-foundation.org ([207.189.120.14]:37519 "EHLO smtp2.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753783AbXIRWhk (ORCPT ); Tue, 18 Sep 2007 18:37:40 -0400 Date: Tue, 18 Sep 2007 15:36:23 -0700 (PDT) From: Linus Torvalds To: Benjamin Herrenschmidt cc: "Luis R. Rodriguez" , Alan Cox , linux-kernel , Jeff Garzik , "John W. Linville" , linux-wireless Subject: Re: [PATCH] Clarify pci_iomap() usage for MMIO-only devices In-Reply-To: <1190154117.6403.127.camel@localhost.localdomain> Message-ID: References: <43e72e890709171322x76ab6b70xd29bf97e3643c553@mail.gmail.com> <20070918113401.6a8a737f@the-village.bc.nu> <43e72e890709181146s604e0f9fl8b0c16627469c77f@mail.gmail.com> <43e72e890709181207j7c85dc29sb355a9f5a4207411@mail.gmail.com> <43e72e890709181312sf2b421cn49be3389b3786a2a@mail.gmail.com> <1190154117.6403.127.camel@localhost.localdomain> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=us-ascii Sender: linux-wireless-owner@vger.kernel.org List-ID: On Wed, 19 Sep 2007, Benjamin Herrenschmidt wrote: > > Also, I've been told that modern x86 chipsets have the ability to remap > IO space in the CPU physical address space. Is that true ? That would > allow even x86 to get rid of the condition and just use some magic > offset at map time. I've not seen that, but I wouldn't be entirely surprised if IO virtualization eventually causes something like this to happen: virtualizing PIO is just damn painful right now, due to the lack of any way to remap it. I *think* you may be confused with the PCI config cycles, where the new MMIO configuration was introduced (for similar virtualization reasons). But it's also possible that this is one of those undocumented areas and CPU's actually do have some IO remapping facility. Linus