From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:35582) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1eRf7h-0001nN-Cr for qemu-devel@nongnu.org; Wed, 20 Dec 2017 09:13:30 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1eRf7e-0007D5-Dx for qemu-devel@nongnu.org; Wed, 20 Dec 2017 09:13:29 -0500 Received: from mail-pl0-x232.google.com ([2607:f8b0:400e:c01::232]:34705) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1eRf7e-0007Av-8t for qemu-devel@nongnu.org; Wed, 20 Dec 2017 09:13:26 -0500 Received: by mail-pl0-x232.google.com with SMTP id d21so9066929pll.1 for ; Wed, 20 Dec 2017 06:13:25 -0800 (PST) References: <20171212051853.24583-1-aik@ozlabs.ru> <20171211224650.71237179@w520.home> <20171219070919.42d90b94@w520.home> <87e241ad-4d65-1b51-aa22-a84f18de1cb6@redhat.com> <344fb27b-1765-92e0-312f-6d5610925c5a@ozlabs.ru> From: Alexey Kardashevskiy Message-ID: Date: Thu, 21 Dec 2017 01:13:18 +1100 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8 Content-Language: en-AU Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH qemu] RFC: spapr/iommu: Enable in-kernel TCE acceleration via VFIO KVM device List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Paolo Bonzini , Alex Williamson Cc: qemu-devel@nongnu.org, qemu-ppc@nongnu.org, David Gibson On 20/12/17 20:04, Paolo Bonzini wrote: > On 20/12/2017 02:47, Alexey Kardashevskiy wrote: >>> - if we foresee having more IOMMU devices in KVM, let's rename >>> KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE to KVM_DEV_VFIO_GROUP_ATTACH_IOMMU and >>> add a new function >>> >>> int iommu_memory_region_get_kvm_fd(IOMMUMemoryRegion *iommu); >>> >>> that requires no object-type check in VFIO. >> >> This is how it started and the comment was that this KVM fd needs to have a >> well defined semantic which I struggle to provide. > > I don't think the definition should be anything more than "it can be > passed to KVM_DEV_VFIO_GROUP_ATTACH_IOMMU". I'll discuss it with Alex > later today. That was more David's concern :) -- Alexey