Re: [PATCH kernel 4/9] dma/swiotlb: Stop forcing SWIOTLB for TDISP devices

[Alexey Kardashevskiy]

On 21/4/26 09:50, Jason Gunthorpe wrote:
> On Wed, Apr 15, 2026 at 04:32:14PM +1000, Alexey Kardashevskiy wrote:
> > > > So the DMA API should see the DMA_ATTR_CC_DECRYPTED and setup the
> > > > correct dma_dddr_t either by choosing the shared alias for the TDISP
> > > > device's vTOM, or setting the C bit in a vIOMMU S1.
> > >
> > > Something like that?
> > >
> > > https://github.com/AMDESE/linux-kvm/commit/266a41a1ea746557eb63debce886ce2c98820667
> > >
> > > With some little hacks I can make this tree do TDISP DMA to private or shared (swiotlb) memory by steering via this vTOM thing. Thanks,
> >
> > Ping? Thanks,
>
> That seems approx right, it is broadl similar to what ARM is
> doing.. But the address map changes when switching to T=1 for AMD?

Well, at the moment, in my WIP tree, I map the guest memory in the host IOMMU twice -

1) from 0 offset (and this is shared when T=0 and private when T=1) and
2) from vTOM offset (say, 1TB) - and this half of the mapping is always shared.

Thanks,


--
Alexey