On Mon, Jan 11, 2021 at 9:36 AM . Christoph Hellwig <hch@xxxxxx> wrote: > > On Thu, Jan 07, 2021 at 03:14:08PM +0100, Ricardo Ribalda wrote: > > > 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? > > > > > Best regards! > > > > > > > > -- > > Ricardo Ribalda > ---end quoted text--- -- Ricardo Ribalda
