On Tue, Nov 02, 2021 at 11:21:16AM +0800, Walter Wu wrote: > Our platform is arch64. We need a dynamic allocated buffer from CMA is > not to read by CPU peculative execution, so we need to remove its > kernel mapping.
If your CPU speculates into unused kernel direct mappings your have a worse problem than this, because all the dma coherent allocations for non-coherent devices still have a cachable direct mapping. Will mentioned he wanted to look into getting rid of that mapping now that the core dma code has the infrastucture for that, so adding him here. _______________________________________________ iommu mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/iommu
