>That said, I've now gone and looked and AFAICS both the Intel...
Ah, I missed that, you're right.
>...and AMD
It doesn't look like it. On AMD the cache is flushed during
iommu_ops::map only if the there are page table pages to free (if
we're allocating a large page and freeing the sub pages), rig
On 11/04/2019 19:47, Tom Murphy wrote:
Both the AMD and Intel drivers can cache not present IOTLB entries. To
convert these drivers to the dma-iommu api we need a generic way to
flush the NP cache. IOMMU drivers which have a NP cache can implement
the .flush_np_cache function in the iommu ops str
Both the AMD and Intel drivers can cache not present IOTLB entries. To
convert these drivers to the dma-iommu api we need a generic way to
flush the NP cache. IOMMU drivers which have a NP cache can implement
the .flush_np_cache function in the iommu ops struct. I will implement
.flush_np_cache for