Re: [PATCH v2 06/19] mm/pagewalk: Check pfnmap for folio_walk_start()

[Jason Gunthorpe <jgg@nvidia.com>]

On Wed, Aug 28, 2024 at 03:45:49PM -0400, Peter Xu wrote:

> Meanwhile I'm actually not 100% sure pte_special is only needed in
> gup-fast.  See vm_normal_page() and for VM_PFNMAP when pte_special bit is
> not defined:
> 
> 		} else {
> 			unsigned long off;
> 			off = (addr - vma->vm_start) >> PAGE_SHIFT;
> 			if (pfn == vma->vm_pgoff + off) <------------------ [1]
> 				return NULL;
> 			if (!is_cow_mapping(vma->vm_flags))
> 				return NULL;
> 		}
> 
> I suspect things can go wrong when there's assumption on vm_pgoff [1].  At
> least vfio-pci isn't storing vm_pgoff for the base PFN, so this check will
> go wrong when pte_special is not supported on any arch but when vfio-pci is
> present.  I suspect more drivers can break it.

I think that is a very important point.

IIRC this was done magically in one of the ioremap pfns type calls,
and if VFIO is using fault instead it won't do it.

This probably needs more hand holding for the driver somehow..

> So I wonder if it's really the case in real life that only gup-fast would
> need the special bit.  It could be that we thought it like that, but nobody
> really seriously tried run it without special bit yet to see things broke.

Indeed.

What arches even use the whole 'special but not special' system?

Can we start banning some of this stuff on non-special arches?

Jason