Re: [PATCH v5 10/19] mm: pagewalk: Add p4d_entry() and pgd_entry()

[Mike Rapoport]

On Thu, Mar 21, 2019 at 02:19:44PM +0000, Steven Price wrote:
> pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410
> ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were
> no users. We're about to add users so reintroduce them, along with
> p4d_entry() as we now have 5 levels of tables.
> 
> Note that commit a00cc7d9dd93d66a ("mm, x86: add support for
> PUD-sized transparent hugepages") already re-added pud_entry() but with
> different semantics to the other callbacks. Since there have never
> been upstream users of this, revert the semantics back to match the
> other callbacks. This means pud_entry() is called for all entries, not
> just transparent huge pages.
> 
> Signed-off-by: Steven Price <steven.price@xxxxxxx>
> ---
>  include/linux/mm.h |  9 ++++++---
>  mm/pagewalk.c      | 27 ++++++++++++++++-----------
>  2 files changed, 22 insertions(+), 14 deletions(-)
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 76769749b5a5..2983f2396a72 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1367,10 +1367,9 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
> 
>  /**
>   * mm_walk - callbacks for walk_page_range
> + * @pgd_entry: if set, called for each non-empty PGD (top-level) entry
> + * @p4d_entry: if set, called for each non-empty P4D (1st-level) entry

IMHO, p4d implies the 4th level :)

I think it would make more sense to start counting from PTE rather than
from PGD. Then it would be consistent across architectures with fewer
levels.

>   * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
> - *	       this handler should only handle pud_trans_huge() puds.
> - *	       the pmd_entry or pte_entry callbacks will be used for
> - *	       regular PUDs.
>   * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
>   *	       this handler is required to be able to handle
>   *	       pmd_trans_huge() pmds.  They may simply choose to
> @@ -1390,6 +1389,10 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
>   * (see the comment on walk_page_range() for more details)
>   */
>  struct mm_walk {
> +	int (*pgd_entry)(pgd_t *pgd, unsigned long addr,
> +			 unsigned long next, struct mm_walk *walk);
> +	int (*p4d_entry)(p4d_t *p4d, unsigned long addr,
> +			 unsigned long next, struct mm_walk *walk);
>  	int (*pud_entry)(pud_t *pud, unsigned long addr,
>  			 unsigned long next, struct mm_walk *walk);
>  	int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
> diff --git a/mm/pagewalk.c b/mm/pagewalk.c
> index c3084ff2569d..98373a9f88b8 100644
> --- a/mm/pagewalk.c
> +++ b/mm/pagewalk.c
> @@ -90,15 +90,9 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
>  		}
> 
>  		if (walk->pud_entry) {
> -			spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma);
> -
> -			if (ptl) {
> -				err = walk->pud_entry(pud, addr, next, walk);
> -				spin_unlock(ptl);
> -				if (err)
> -					break;
> -				continue;
> -			}
> +			err = walk->pud_entry(pud, addr, next, walk);
> +			if (err)
> +				break;
>  		}
> 
>  		split_huge_pud(walk->vma, pud, addr);
> @@ -131,7 +125,12 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
>  				break;
>  			continue;
>  		}
> -		if (walk->pmd_entry || walk->pte_entry)
> +		if (walk->p4d_entry) {
> +			err = walk->p4d_entry(p4d, addr, next, walk);
> +			if (err)
> +				break;
> +		}
> +		if (walk->pud_entry || walk->pmd_entry || walk->pte_entry)
>  			err = walk_pud_range(p4d, addr, next, walk);
>  		if (err)
>  			break;
> @@ -157,7 +156,13 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
>  				break;
>  			continue;
>  		}
> -		if (walk->pmd_entry || walk->pte_entry)
> +		if (walk->pgd_entry) {
> +			err = walk->pgd_entry(pgd, addr, next, walk);
> +			if (err)
> +				break;
> +		}
> +		if (walk->p4d_entry || walk->pud_entry || walk->pmd_entry ||
> +				walk->pte_entry)
>  			err = walk_p4d_range(pgd, addr, next, walk);
>  		if (err)
>  			break;
> -- 
> 2.20.1
> 

-- 
Sincerely yours,
Mike.