Re: [PATCH v2 1/2] iommu/amd: Add PerfOpt IOMMU performance optimization support

[Jason Gunthorpe <jgg@ziepe.ca>]

On Fri, Sep 25, 2026 at 08:11:41AM -0500, Mario Limonciello wrote:
> 
> 
> On 9/25/26 07:28, Jason Gunthorpe wrote:
> > On Fri, Sep 25, 2026 at 09:20:02AM +0200, Joerg Roedel wrote:
> > > On Thu, Sep 24, 2026 at 07:50:18PM -0300, Jason Gunthorpe wrote:
> > > > Why does the GPU driver have to request this? Why can't the iommu
> > > > driver know that this is a special device that can use this magic fast
> > > > path and then auto set it when identity is asked for?
> > > 
> > > This is a layering violation either way. Either the IOMMU driver needs to poke
> > > into device details and their relations or the device driver needs to poke into
> > > IOMMU details.
> > 
> > There are no device details, this is just a module option in the gpu
> > driver.
> 
> Well the GPU driver has knowledge whether it's a GPU inside of an APU to
> decide if it's valid.  That information is part of the discovery table
> setup.

Where was that in patch 2?

The right way for this to work is to quirk it through the iommu driver
so it can choose the fast mode, and not involve the GPU driver at
all. Like we've done for every other GPU weirdness. And AMD should be
making this work better by providing ACPI support so the iommu driver
can understand how it should work without inspecting PCI IDs.

> > > This is not perfect but to some degree unavoidable with these highly integrated
> > > SOCs.
> > 
> > This is exactly the sort of hacky thing ACPI should describe so the
> > drivers can just turn things on automatically.
> > 
> > Who is ever going to track down and figure out it is OK to set these
> > kinds of module options in the first place? There is general negative
> > sentiment in the kernel to doing things like this with modue options.
> > 
> > How does Windows do it? There certainly isn't a "module option" there?
> 
> This specific one I don't know; but these kinds of things usually end up in
> knobs in a UI that plumb some IPC deep into the driver stack.

Given the huge delta I somehow doubt that AMD would ship a windows
driver that defaults to "slow" ? Nor should linux...

Jason