Re: [PATCH 05/16] iommu/amd: Split device table initialization into irq and dma part

[Joerg Roedel <joerg.roedel-5C7GfCeVMHo@public.gmane.org>]

On Fri, Sep 28, 2012 at 11:00:10AM -0400, Konrad Rzeszutek Wilk wrote:
> On Fri, Sep 28, 2012 at 04:25:55PM +0200, Joerg Roedel wrote:
> > On Fri, Sep 28, 2012 at 10:17:53AM -0400, Konrad Rzeszutek Wilk wrote:
> > > On Fri, Sep 28, 2012 at 02:23:55PM +0200, Joerg Roedel wrote:
> > > > When the IOMMU is enabled very early (as with irq-remapping)
> > > > some devices are still in BIOS hand. When dma is blocked
> > > > early this can cause lots of IO_PAGE_FAULTs. So delay the
> > > > DMA initialization and do it right before the dma_ops are
> > > > initialized.
> > > > To be secure, block all interrupts by default when irq-remapping is
> > > 
> > > What are you trying to be secure against?
> > 
> > Against attacks of faked MSI msgs that could DoS the system. MSI
> > messages are only specific DMA transactions in the end and a guest with
> > a device assigned has control over its DMA engine and can thus send
> > arbitrary interrupt requests to the host. There is a whole paper about
> > such attacks. I can't find right now, but I send you  a link when I find
> > it.
> 
> I think I know which one you are talking about - that is the Joanna's
> Rutkowski/Rafal Wojtczuk paper. Could you include a bit about it
> in the description or at least the title in the git commit pls?

Okay, I will do.

-- 
AMD Operating System Research Center

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