On Tue, Aug 09, 2022 at 12:36:50PM +0100, Tvrtko Ursulin wrote:
>
> Digging through git history at least running as Xen dom0 looks to have been
> impacted, but commits such as abb0deacb5a6 ("drm/i915: Fallback to single
> PAGE_SIZE segments for DMA remapping") are older and suggest problem was
> generic. 1625e7e549c5 ("drm/i915: make compact dma scatter lists creation
> work with SWIOTLB backend.") as well. So it looks it did work behind
> swiotlb despite those missing calls you highlighted.
Hmm. xen-swiotlb bounce buffers as soon as any single mapping that
straddles a Xen page size boundary. Could the magic value there
somehow made all mappings small enough to just avoid bounce buffering
for Xen by more or less accident?
