On 08/01/18 11:09 AM, Jason Gunthorpe wrote:
It could, if we had a DMA op for p2p then the drivers that provide
their own ops can implement it appropriately or not at all.
I was thinking of doing something like this. I'll probably rough out a
patch and send it along today or tomorrow.
> If at all it should be in the dma_map* wrappers, but for that
> a good identifier. And it still would not solve the whole fake dma
> ops issue.
Very long term the IOMMUs under the ops will need to care about this,
so the wrapper is not an optimal place to put it - but I wouldn't
object if it gets it out of RDMA :)
Well, creating the extra op doesn't really change anything to the RDMA
patch in this series. The point is, for the time being, we need to track
whether we are doing a P2P or normal mapping using a side channel as we
don't have a good way of tracking it in the SGL at this time.
Adding an extra DMA op is just one way to allow the existing DMA
providers to opt-in/out.