[PATCH] nvme-pci: fix dma unmapping when using PRPs and not using the IOVA mapping

[Keith Busch]

On Mon, Jul 07, 2025 at 02:52:23PM +0200, Christoph Hellwig wrote:
> The current version of the blk_rq_dma_map support in nvme-pci tries to
> reconstruct the DMA mappings from the on the wire descriptors if they
> are needed for unmapping.  While this is not the case for the direct
> mapping fast path and the IOVA path, it is needed for the non-IOVA slow
> path, e.g. when using the interconnect is not dma coherent, when using
> swiotlb bounce buffering, or a IOMMU mapping that can't coalesce.
> 
> While the reconstruction is easy and works fine for the SGL path, where
> the on the wire representation maps 1:1 to DMA mappings, the code to
> reconstruct the DMA mapping ranges from PRPs can't always work, as a
> given PRP layout can come from different DMA mappings, and the current
> code doesn't even always get that right.
> 
> Give up on this approach and track the actual DMA mapping when actually
> needed again.

Looks good.

Reviewed-by: Keith Busch <kbusch at kernel.org>