> From: Nicolin Chen <nicol...@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...
