Re: [PATCH] iommu/amd: Add parameter to limit V1 page-sizes to 4 KiB

[Joerg Roedel]

On Wed, Sep 04, 2024 at 10:03:29AM -0300, Jason Gunthorpe wrote:
> Why is this a kernel command line? Surely it should be negotiated
> automaticaly with capability registers or ACPI like everone else does
> if there is something functionally wrong with the vIOMMU??

In the affected setups there is no vIOMMU. This is not about secure-IO,
the assigned devices will not be part of the trusted base.

> If we are doing this we also have a problem on mlx5 devices where
> there are too many page sizes in the v1 table and it blows up the ATS
> caching. It would be nice to widen this option to limit the page sizes
> to other combinations (4k/2M/1G or something).

Okay, I will update the patch to allow more settings.

Regards,

	Joerg