Re: [RFC PATCH 1/3] hugetlb: skip to end of PT page mapping when pte not present

[Baolin Wang]

On 6/16/2022 5:22 AM, Mike Kravetz wrote:
> On 05/30/22 18:10, Baolin Wang wrote:
> > On 5/28/2022 6:58 AM, Mike Kravetz wrote:
> > > HugeTLB address ranges are linearly scanned during fork, unmap and
> > > remap operations.  If a non-present entry is encountered, the code
> > > currently continues to the next huge page aligned address.  However,
> > > a non-present entry implies that the page table page for that entry
> > > is not present.  Therefore, the linear scan can skip to the end of
> > > range mapped by the page table page.  This can speed operations on
> > > large sparsely populated hugetlb mappings.
> > >
> > > Create a new routine hugetlb_mask_last_hp() that will return an
> > > address mask.  When the mask is ORed with an address, the result
> > > will be the address of the last huge page mapped by the associated
> > > page table page.  Use this mask to update addresses in routines which
> > > linearly scan hugetlb address ranges when a non-present pte is
> > > encountered.
> > >
> > > hugetlb_mask_last_hp is related to the implementation of huge_pte_offset
> > > as hugetlb_mask_last_hp is called when huge_pte_offset returns NULL.
> > > This patch only provides a complete hugetlb_mask_last_hp implementation
> > > when CONFIG_ARCH_WANT_GENERAL_HUGETLB is defined.  Architectures which
> > > provide their own versions of huge_pte_offset can also provide their own
> > > version of hugetlb_mask_last_hp.
> >
> > I tested on my ARM64 machine with implementing arm64 specific
> > hugetlb_mask_last_hp() as below, and it works well.
> >
> > Just a few nits inline, otherwise looks good to me.
> > Tested-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
> > Reviewed-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
> >
> > diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
> > index d93ba128a2b0..e04a097ffcc4 100644
> > --- a/arch/arm64/mm/hugetlbpage.c
> > +++ b/arch/arm64/mm/hugetlbpage.c
> > @@ -376,6 +376,28 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
> >          return NULL;
> >   }
> >
> > +unsigned long hugetlb_mask_last_hp(struct hstate *h)
> > +{
> > +       unsigned long hp_size = huge_page_size(h);
> > +
> > +       switch (hp_size) {
> > +       case P4D_SIZE:
> > +               return PGDIR_SIZE - P4D_SIZE;
> > +       case PUD_SIZE:
> > +               return P4D_SIZE - PUD_SIZE;
> > +       case CONT_PMD_SIZE:
> > +               return PUD_SIZE - CONT_PMD_SIZE;
> > +       case PMD_SIZE:
> > +               return PUD_SIZE - PMD_SIZE;
> > +       case CONT_PTE_SIZE:
> > +               return PMD_SIZE - CONT_PTE_SIZE;
> > +       default:
> > +               break;
> > +       }
> > +
> > +       return ~(0UL);
> > +}
>
> Hello Baolin,
>
> Would you mind sending this as a proper patch with commit message and
> 'Signed-off-by:'?  I would like to include it in the upcoming patch series.

Sure. I've sent it out [1], and please fold it into your series. Thanks.

[1] 
https://lore.kernel.org/all/7256dbe078d7231f45b0f47c2c52a3bd3aa10da7.1655350193.git.baolin.wang@xxxxxxxxxxxxxxxxx/