Actually, seems like I do have a question. I see that you mention that we could stop passing use_dma_alloc=true to ttm_device_init() or use dma_alloc_noncoherent(). I'm not an expert on this nouveau's mm, but after skimming it seems like if we can simply check whether or not we need all noncoherent allocations without getting is_swiotlb_active() involved - which should be easy. Does this seem like a workable solution, or is there something I'm missing here? On Thu, 2022-07-28 at 17:17 -0400, Lyude Paul wrote: > Hi! Sorry about the slow reply to this, been busy with a bunch of other > pressing nouveau work lately. > > Anyway, the steps look pretty simple here so I can see if I can write up a > patch shortly :) > > On Mon, 2022-07-11 at 10:26 +0200, Christoph Hellwig wrote: > > Hi i915 and nouveau maintainers, > > > > any chance I could get some help to remove the remaining direct > > driver calls into swiotlb, namely swiotlb_max_segment and > > is_swiotlb_active. Either should not matter to a driver as they > > should be written to the DMA API. > > > > In the i915 case it seems like the driver should use > > dma_alloc_noncontiguous and/or dma_alloc_noncoherent to allocate > > DMAable memory instead of using alloc_page and the streaming > > dma mapping helpers. > > > > For the latter it seems like it should just stop passing > > use_dma_alloc == true to ttm_device_init and/or that function > > should switch to use dma_alloc_noncoherent. > > > -- Cheers, Lyude Paul (she/her) Software Engineer at Red Hat
