[PATCH v1 15/16] iommu/tegra241-cmdqv: Add user-space use support

[Tian, Kevin]

> From: Nicolin Chen <nicolinc at nvidia.com>
> Sent: Thursday, April 24, 2025 2:52 PM
> 
> On Wed, Apr 23, 2025 at 08:13:33PM -0300, Jason Gunthorpe wrote:
> > On Wed, Apr 23, 2025 at 11:31:29AM -0700, Nicolin Chen wrote:
> >
> > > > It also needs to act like a mdev and lock down the part of the IOAS
> > > > that provides that memory so the pin can't be released and UAF things.
> > >
> > > If I capture this correctly, the GPA->PA mapping is already done
> > > at the IOAS level for the S2 HWPT/domain, i.e. pages are already
> > > pinned. So we just need to a pair of for-driver APIs to validate
> > > the contiguity and refcount pages calling iopt_area_add_access().
> >
> > Yes, adding an access is the key thing, the access will give you a
> > page list which you can validate, but it also provides a way to
> > synchronize if a hostile userspace does an unmap.
> 
> The new APIs are very like iommufd_access_pin/unpin_pages(). But
> to reduce the amount of code that we have to share with driver.o,
> I added a smaller iopt_area_get/put_access() that gets an access
> and increases/decreases the refcounts only.
> 
> Yet, this still inevitably doubled (-ish) the size of driver.o:
>    text	   data	    bss	    dec	    hex	filename
>    4429	    296	      0	   4725	   1275	drivers/iommu/iommufd/driver.o
>    text	   data	    bss	    dec	    hex	filename
>    8430	    783	      0	   9213	   23fd	drivers/iommu/iommufd/driver.o
> 
> Meanwhile, I am thinking if we could use the known S2 domain to
> translate the GPAs to PAs for the contiguity test, which feels a
> little cleaner to do in an IOMMU driver v.s. with a page list?
> 

but w/o adding an access to increase the refcounts, it's unsafe
to walk the S2 domain...