On Wed, Jan 21, 2026 at 11:19:45PM -0800, Matthew Brost wrote: > - Why is Intel the only one proving this stuff works? We can debate all > day about what should or should not work — but someone else needs to > actually prove it.i, rather than type hypotheticals.
Oh come on, NVIDIA has done an *enormous* amount of work to get these things to this point where they are actually getting close to functional and usable. Don't "Oh poor intel" me :P > - Intel has demonstrated that this works and is still getting blocked. We generally don't merge patches because they "works for me". The issue is the thing you presented is very ugly and inefficient, and when we start talking about the right way to do it you get all defensive and disappear. > - Given the current state of the discussion, I don’t think large device > pages should be in 6.19. And if so, why didn’t the entire device pages > series receive this level of scrutiny earlier? It’s my mistake for not > saying “no” until the reallocation at different sizes issue was resolved. It did, nobody noticed this bug or post something so obviously ugly :P > @Andrew. - I'd revert large device pages in 6.19 as it doesn't work and > we seemly cannot close on this. What's the issue here? You said you were going to go ahead with the ugly thing, go do it and come back with something better. That's what you wanted, right? Jason
