Re: [PATCH 4/4] iommu/vt-d: Do access checks before calling handle_mm_fault()

[Joerg Roedel <joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>]

On Tue, Nov 10, 2015 at 09:43:03AM -0800, Linus Torvalds wrote:
> On Tue, Nov 10, 2015 at 5:26 AM, Joerg Roedel <joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org> wrote:
> > +
> > +static bool access_error(struct vm_area_struct *vma, struct page_req_dsc *req)
> > +{
> > +       return !((req->rd_req  && (vma->vm_flags & VM_READ))  ||
> > +                (req->wr_req  && (vma->vm_flags & VM_WRITE)) ||
> > +                (req->exe_req && (vma->vm_flags & VM_EXEC)));
> > +}
> 
> This seems odd.
> 
> Shouldn't it be
> 
>     return ((req->rd_req  && !(vma->vm_flags & VM_READ))  ||
>             (req->wr_req  && !(vma->vm_flags & VM_WRITE)) ||
>             (req->exe_req && !(vma->vm_flags & VM_EXEC)));
> 
> instead?

Yes,  thats better, it solves the multiple-bits-set problem too, which
David mentioned.

> Of course, if you just used the VM_xyz flags internally itself, this
> would all be easier, and you'd end up with something like
> 
>     /* Do we have requested bits that aren't in the allowed set? */
>     return (requested & ~vma->vm_flags) != 0;
> 
> instead..

But this is probably the best solution, some architecture page-fault
handlers do something similar. I'll update the patch and use this for
the AMD part too.


Thanks,

	Joerg