Re: [PATCH net-next v3 1/2] dma-mapping: introduce DMA_ATTR_CC_DECRYPTED for pre-decrypted memory

[Jason Gunthorpe <jgg@ziepe.ca>]

On Thu, Mar 12, 2026 at 10:03:37AM +0100, Jiri Pirko wrote:
> >Alot of device MMIO is decrypted by nature and can't be encrypted, so
> >you'd have to use both flags. eg in VFIO we'd want to do this.
> 
> Why both flags? Why MMIO flag is not enough? You still want to hit
> "if (attrs & DMA_ATTR_MMIO) {" path, don't you?

Because we will eventually have both decrypted and encrypted MMIO.

> I mean, CC_DECRYPTED says the memory to be mapped was explicitly
> decrypted before the call. MMIO was not explicitly decrypted, it is
> decrypted by definition. For me that does not fit the CC_DECRYPTED
> semantics.

I would say CC_DECRYPTED means that pgprot_decrypted must be used to
form a PTE, and !CC_DECRYPTED means that pgprot_encrypted() was used

This flag should someday flow down into the vIOMMU driver and set the
corresponding C bit the IOPTE (for AMD) exactly as the pgprot does.

Less about set_memory_encrypted as that is only for DRAM.

Jason