On Tue, Aug 19, 2025 at 08:36:50PM +0300, Leon Romanovsky wrote:

From: Leon Romanovsky <leonro@nvidia.com>

Combine iommu_dma_*map_phys with iommu_dma_*map_resource interfaces in
order to allow single phys_addr_t flow.

In the following patches, the iommu_dma_map_resource() will be removed
in favour of iommu_dma_map_phys(..., attrs | DMA_ATTR_MMIO) flow.

I would reword this a little bit

iommu/dma: implement DMA_ATTR_MMIO for iommu_dma_(un)map_phys()

Make iommu_dma_map_phys() and iommu_dma_unmap_phys() respect
DMA_ATTR_MMIO.

DMA_ATTR_MMIO makes the functions behave the same as
iommu_dma_(un)map_resource():
 - No swiotlb is possible
 - No cache flushing is done (ATTR_MMIO should not be cached memory)
 - prot for iommu_map() has IOMMU_MMIO not IOMMU_CACHE 

This is preperation for replacing iommu_dma_map_resource() callers
with iommu_dma_map_phys(DMA_ATTR_MMIO) and removing
iommu_dma_(un)map_resource().

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>

Jason