From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1763224AbYD2NP5 (ORCPT ); Tue, 29 Apr 2008 09:15:57 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1757540AbYD2NPh (ORCPT ); Tue, 29 Apr 2008 09:15:37 -0400 Received: from smtp-out03.alice-dsl.net ([88.44.63.5]:30149 "EHLO smtp-out03.alice-dsl.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756261AbYD2NPg (ORCPT ); Tue, 29 Apr 2008 09:15:36 -0400 To: Amit Shah Cc: kvm-devel@lists.sourceforge.net, chrisw@redhat.com, allen.m.kay@intel.com, linux-kernel@vger.kernel.org, gcosta@redhat.com, avi@qumranet.com, virtualization@lists.linux-foundation.org, BENAMI@il.ibm.com Subject: Re: [PATCH] x86 DMA: Handle devices assigned to the guest by the host From: Andi Kleen References: <1209465451-3758-1-git-send-email-amit.shah@qumranet.com> <1209465451-3758-2-git-send-email-amit.shah@qumranet.com> Date: Tue, 29 Apr 2008 15:14:23 +0200 In-Reply-To: <1209465451-3758-2-git-send-email-amit.shah@qumranet.com> (Amit Shah's message of "Tue, 29 Apr 2008 13:37:29 +0300") Message-ID: <87wsmghkgg.fsf@basil.nowhere.org> User-Agent: Gnus/5.1008 (Gnus v5.10.8) Emacs/21.3 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-OriginalArrivalTime: 29 Apr 2008 13:07:30.0678 (UTC) FILETIME=[FB384960:01C8A9F9] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Amit Shah writes: > diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c > index 388b113..678cafb 100644 > --- a/arch/x86/kernel/pci-dma.c > +++ b/arch/x86/kernel/pci-dma.c > @@ -443,6 +443,17 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, > memset(memory, 0, size); > if (!mmu) { > *dma_handle = bus; > + if (unlikely(dma_ops->is_pv_device) && > + unlikely(dma_ops->is_pv_device(dev, dev->bus_id))) { First double unlikely in a condition is useless. Just drop them. And then ->is_xyz() in a generic vops interface is about as ugly and non generic as you can get. dma_alloc_coherent is not performance critical, so you should rather change the interface that ->alloc_coherent is always called and the other handlers handle the !mmu case correctly. In fact they need that already I guess (e.g. on DMAR there is not really a nommu case) -Andi