"Aneesh Kumar K.V" <aneesh.ku...@linux.vnet.ibm.com> writes:
> Paul Mackerras <pau...@ozlabs.org> writes:
>
>>
>> #define _PAGE_PTE (1ul << 62) /* distinguishes PTEs from
>> pointers */
>> #define _PAGE_PRESENT (1ul << 63) /* pte contains a
>> translation */
>> diff --git a/arch/powerpc/mm/pgtable-book3s64.c
>> b/arch/powerpc/mm/pgtable-book3s64.c
>> index f4f437c..7ff0289 100644
>> --- a/arch/powerpc/mm/pgtable-book3s64.c
>> +++ b/arch/powerpc/mm/pgtable-book3s64.c
>> @@ -86,7 +86,7 @@ pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot)
>> {
>> unsigned long pmdv;
>>
>> - pmdv = (pfn << PAGE_SHIFT) & PTE_RPN_MASK;
>> + pmdv = ((pfn << PAGE_SHIFT) & PTE_RPN_MASK) | _PAGE_LARGE;
>> return pmd_set_protbits(__pmd(pmdv), pgprot);
>> }
>>
>
> I will look at this and see if can make the patch simpler. But do we
> really want to use the pte bit for this ? Aren't we low on free pte bits
Ok this will work, provided we are ok to take up two pte bits for this
So we can use make_huge_pte() to fixup the pte entry for hugetlb and
pmd_mkhuge() to fixup the THP.
Now the question will be how will we support _PAGE_DEVMAP (for nvidmm).
We don't have free software pte bits after we make the above change.
NOTE: We do have 3 reserved bits(ppc bit 4-6 ) can we use that ?
-aneesh
