Re: [RFC PATCH 0/5] iommu/arm-smmu-v3: Implement Runtime/System Sleep ops

[Jason Gunthorpe <jgg@ziepe.ca>]

On Thu, Mar 27, 2025 at 05:39:26PM +0000, Mostafa Saleh wrote:

> I agree, I don’t like the approach of adding a (yet another) flag for
> firmware to populate, I guess we can either:
> - Prevent SMMUv3 suspend, and that’s already the status quo as it
>   doesn’t support RPM, instead of doing that from the driver by
>   detecting non-secure attaches, we can just make VFIO takes a PM
>   reference on the IOMMU.

That would break runtime PM support through VFIO on other platforms..
 
> - Disable the PCI device, or unmap it from userspace from VFIO suspend
>   handler, and retrieve it’s state on the VFIO resume handler which would
>   be ordered after the SMMUv3.

I don't think that works, the PCI device could have already been
programmed to do a hostile DMA prior to any unmap.

I think the only thing that makes sense is for the SMMU to not do
power management if it can't obey the API requirement around domains.

iommus are expected to always translate according to their attached
domain, never something else. The only possible exception would be
abort-all.

Jason