Re: [RFC PATCH v4 07/28] x86: Provide general kernel support for memory encryption

[Tom Lendacky]

On 2/22/2017 12:13 PM, Dave Hansen wrote:
> On 02/16/2017 07:43 AM, Tom Lendacky wrote:
> >  static inline unsigned long pte_pfn(pte_t pte)
> >  {
> > -	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
> > +	return (pte_val(pte) & ~sme_me_mask & PTE_PFN_MASK) >> PAGE_SHIFT;
> >  }
> >
> >  static inline unsigned long pmd_pfn(pmd_t pmd)
> >  {
> > -	return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
> > +	return (pmd_val(pmd) & ~sme_me_mask & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
> >  }
>
> Could you talk a bit about why you chose to do the "~sme_me_mask" bit in
> here instead of making it a part of PTE_PFN_MASK / pmd_pfn_mask(pmd)?

I think that's a good catch.  Let me look at it, but I believe that it
should be possible to do and avoid what you're worried about below.

Thanks,
Tom

> It might not matter, but I'd be worried that this ends up breaking
> direct users of PTE_PFN_MASK / pmd_pfn_mask(pmd) since they now no
> longer mask the PFN out of a PTE.