From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755464AbYIIOrV (ORCPT ); Tue, 9 Sep 2008 10:47:21 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752963AbYIIOrK (ORCPT ); Tue, 9 Sep 2008 10:47:10 -0400 Received: from gw.goop.org ([64.81.55.164]:50548 "EHLO mail.goop.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750871AbYIIOrJ (ORCPT ); Tue, 9 Sep 2008 10:47:09 -0400 Message-ID: <48C68C6B.7030803@goop.org> Date: Tue, 09 Sep 2008 07:47:07 -0700 From: Jeremy Fitzhardinge User-Agent: Thunderbird 2.0.0.16 (X11/20080723) MIME-Version: 1.0 To: Avi Kivity CC: Ingo Molnar , linux-kernel@vger.kernel.org, "H. Peter Anvin" , Xen Devel , Andi Kleen Subject: Re: [PATCH 1 of 7] x86: add _PAGE_IOMAP pte flag for IO mappings References: <4d93ba619c716c45cca0.1220826073@localhost> <48C67AE0.5060503@qumranet.com> In-Reply-To: <48C67AE0.5060503@qumranet.com> X-Enigmail-Version: 0.95.7 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Avi Kivity wrote: > Jeremy Fitzhardinge wrote: >> Use one of the software-defined PTE bits to indicate that a mapping is >> intended for an IO address. On native hardware this is irrelevent, >> since a physical address is a physical address. But in a virtual >> environment, physical addresses are also virtualized, so there needs >> to be some way to distinguish between pseudo-physical addresses and >> actual hardware addresses; _PAGE_IOMAP indicates this intent. >> >> By default, __supported_pte_mask masks out _PAGE_IOMAP, so it doesn't >> even appear in the final pagetable. >> > > Could PTE_SPECIAL, added for get_user_pages_really_fast(), be reused > for this? > I'm not sure; I still don't really understand how _PAGE_SPECIAL gets used, other than being user-mode mapping only. But in principle, _PAGE_IOMAP could be set on both kernel and user mappings (if you direct map a device into a process address space), so I think they would conflict then? Also, _PAGE_SPECIAL is also shared with _PAGE_CPA_TEST, which is only used on kernel mappings, so they can co-exist happily. Is _PAGE_IOMAP at all useful for device passthrough in kvm? J