Any examples of this in the Linux kernel? Not doubting you, I'm just curious. I would think this would be device driver specific rather than architecture specific.

Most drivers I've seen just use the kernel's DMA API (dma_alloc_coherent), which is guaranteed to provide a buffer that doesn't require any explicit cache management. If the architecture is coherent, then it leaves caching turned on for those pages. If it's non-coherent, then it turns it off.