Re: [PATCH v3 01/11] PCI/P2PDMA: Support peer-to-peer memory

[Logan Gunthorpe]

On 14/03/18 06:16 AM, David Laight wrote:
> That surprises me (unless I missed something last time I read the spec).
> While P2P writes are relatively easy to handle, reads and any other TLP that
> require acks are a completely different proposition.
> There are no additional fields that can be set in the read TLP and will be
> reflected back in the ack(s) than can be used to route the acks back to the
> correct initiator.
>
> I'm pretty sure that to support P2P reads a switch would have to save
> the received read TLP and (possibly later on) issue read TLP of its own
> for the required data.
> I'm not even sure it is easy to interleave the P2P reads with those
> coming from the root.
> That requires a potentially infinite queue of pending requests.

This is wrong. A completion is a TLP just like any other and makes use
of the Destination ID field in the header to route it back to the
original requester.

> Some x86 root ports support P2P writes (maybe with a bios option).
> It would be a shame not to be able to do P2P writes on such systems
> even though P2P reads won't work.

Yes, and this has been discussed many times. It won't be changing in the
near term.

Logan