On Mon, Jan 11, 2021 at 9:36 AM . Christoph Hellwig [off-list ref] wrote:

On Thu, Jan 07, 2021 at 03:14:08PM +0100, Ricardo Ribalda wrote:

quoted

quoted

So I think we do want these branches for coherent vs non-coherent as they
have very different semantics and I do not think that hiding them under
the same API helps people to understand those vastly different semantics.

OTOH we should look into a fallback for DMA API instances that do not
support the discontigous allocations.

I think between your comments and those from Ricardo I have a good idea
for a somewhat updated API.  I'll try to post something in the next days.

Did you have time to look into this?

No hurry, I just want to make sure that I didn't miss anything ;)

Haven't managed to get to it, sorry.

No worries!, is there something we can do to help you with this?

quoted

Best regards!



--
Ricardo Ribalda

---end quoted text---

-- 
Ricardo Ribalda