On 2019-01-29 9:18 p.m., Jason Gunthorpe wrote: > Every attempt to give BAR memory to struct page has run into major > trouble, IMHO, so I like that this approach avoids that. > > And if you don't have struct page then the only kernel object left to > hang meta data off is the VMA itself. > > It seems very similar to the existing P2P work between in-kernel > consumers, just that VMA is now mediating a general user space driven > discovery process instead of being hard wired into a driver. But the kernel now has P2P bars backed by struct pages and it works well. And that's what we are doing in-kernel. We even have a hacky out-of-tree module which exposes these pages and it also works (but would need Jerome's solution for denying those pages in GUP, etc). So why do something completely different in userspace so they can't share any of the DMA map infrastructure? Logan
