Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754248AbZFRTKG (ORCPT ); Thu, 18 Jun 2009 15:10:06 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753054AbZFRTJ4 (ORCPT ); Thu, 18 Jun 2009 15:09:56 -0400 Received: from mga14.intel.com ([143.182.124.37]:33401 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751895AbZFRTJ4 convert rfc822-to-8bit (ORCPT ); Thu, 18 Jun 2009 15:09:56 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.42,246,1243839600"; d="scan'208";a="156136862" From: "Yu, Fenghua" To: "'Chris Wright'" , "'Muli Ben-Yehuda'" CC: "'David Woodhouse'" , "'Linus Torvalds'" , "'Stephen Rothwell'" , "'Andrew Morton'" , "'Ingo Molnar'" , "Kay, Allen M" , "'lkml'" , "'iommu'" Date: Thu, 18 Jun 2009 12:09:56 -0700 Subject: RE: [PATCH 1/2] IOMMU Identity Mapping Support: iommu_identity_mapping definition Thread-Topic: [PATCH 1/2] IOMMU Identity Mapping Support: iommu_identity_mapping definition Thread-Index: AcnwRd+5WZBLTONITv2GHwCGn2svUQAAdHhw Message-ID: References: <20090513231351.GA22386@linux-os.sc.intel.com> <1242314271.3393.11.camel@macbook.infradead.org> <20090514175944.GA5168@linux-os.sc.intel.com> <20090618180514.GA24082@linux-os.sc.intel.com> <20090618180835.GB6838@il.ibm.com> <20090618182545.GC6838@il.ibm.com> <20090618183121.GB2500@x200.localdomain> <20090618184101.GE6838@il.ibm.com> <20090618185115.GC2500@x200.localdomain> In-Reply-To: <20090618185115.GC2500@x200.localdomain> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: acceptlanguage: en-US Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 8BIT MIME-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 977 Lines: 18 >> mapping. Instead of a global command line option, we need to provide a >> way to enable/disable pt or identity mapping (I agree that the user >> shouldn't know or care which is used, the kernel should pick the best >> one automatically) on a per BDF basis. > >Yeah, that's a possible enhancement. Although once you've disabled one >device's isolation you've created a hole... > The isolation hole is not much better than a global 1:1 mapping. If one device is 1:1 mapped to all memory. All of other devices can access part of this device's DMA range. And this device can access all of other devices' DMA range. Only better place than a global 1:1 mapping is all of other devices are isolated from each other. Thanks. -Fenghua -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/