From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paul Mackerras Subject: Re: [PATCH 3/4] powerpc: preparing to support real mode optimization Date: Fri, 15 Feb 2013 14:37:40 +1100 Message-ID: <20130215033740.GC25015@drongo> References: <1360584763-21988-1-git-send-email-a> <5118e069.22ca320a.1f08.ffffe2f0@mx.google.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Alexander Graf , Michael Ellerman , linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org, kvm-ppc@vger.kernel.org, kvm@vger.kernel.org, David Gibson To: aik@ozlabs.ru Return-path: Content-Disposition: inline In-Reply-To: <5118e069.22ca320a.1f08.ffffe2f0@mx.google.com> Sender: kvm-ppc-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On Mon, Feb 11, 2013 at 11:12:42PM +1100, aik@ozlabs.ru wrote: > From: Alexey Kardashevskiy > > he current VFIO-on-POWER implementation supports only user mode > driven mapping, i.e. QEMU is sending requests to map/unmap pages. > However this approach is really slow in really fast hardware so > it is better to be moved to the real mode. > > The patch adds an API to increment/decrement page counter as > get_user_pages API used for user mode mapping does not work > in the real mode. > > CONFIG_SPARSEMEM_VMEMMAP and CONFIG_FLATMEN are supported. > > Signed-off-by: Alexey Kardashevskiy > Cc: David Gibson > --- The names are slightly odd, in that they include "vmemmap_" but exist and work in the flatmem case as well. Apart from that... Reviewed-by: Paul Mackerras Paul.