Re: [PATCH 0/2] Introduce iommu_commit() function

["Roedel, Joerg" <Joerg.Roedel@amd.com>]

On Thu, Jun 23, 2011 at 11:38:54AM -0400, David Woodhouse wrote:
> On Thu, 2011-06-23 at 17:31 +0200, Joerg Roedel wrote:
> > David, I think especially VT-d can benefit from such a callback. I will
> > implement support for it in the AMD IOMMU driver and post a patch-set
> > soon.
> > 
> > Any comments, thoughts?
> 
> Ick. We *already* do the flushes as appropriate while we're filling the
> page tables. So every time we move on from one page table page to the
> next, we'll flush the old one. And when we've *done* filling the page
> tables for the range we've been asked to map, we flush the last writes
> too.

It doesn't sound too complicated to make this work with iommu_commit.
All the VT-d driver needs to do is to keep track of the last page-table
page a map/unmap request was targeted to (per domain). Subsequent
map/unmap calls check if the same page is targeted and flushes the old
one if not.  The last writes are flushed in the iommu_commit() call
(together with the IOMMU cache flushes).

It is basically the same algorithm you use now except that it works
accross iommu_map/iommu_unmap calls.

	Joerg

-- 
AMD Operating System Research Center

Advanced Micro Devices GmbH Einsteinring 24 85609 Dornach
General Managers: Alberto Bozzo, Andrew Bowd
Registration: Dornach, Landkr. Muenchen; Registerger. Muenchen, HRB Nr. 43632