In current mremap_folio_pte_batch(), 1) pte_batch_hint() always
return one pte in non-ARM64 machine, it is not efficient. 2) Next,
it need to acquire a folio to call the folio_pte_batch().

Due to new added can_pte_batch_count(), we just call it instead of
folio_pte_batch(). And then rename mremap_folio_pte_batch() to
mremap_pte_batch().

Signed-off-by: Zhang Qilong <zhangqilong3@huawei.com>
---
 mm/mremap.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/mm/mremap.c b/mm/mremap.c
index bd7314898ec5..d11f93f1622f 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -169,27 +169,17 @@ static pte_t move_soft_dirty_pte(pte_t pte)
 		pte = pte_swp_mksoft_dirty(pte);
 #endif
 	return pte;
 }
 
-static int mremap_folio_pte_batch(struct vm_area_struct *vma, unsigned long addr,
+static int mremap_pte_batch(struct vm_area_struct *vma, unsigned long addr,
 		pte_t *ptep, pte_t pte, int max_nr)
 {
-	struct folio *folio;
-
 	if (max_nr == 1)
 		return 1;
 
-	/* Avoid expensive folio lookup if we stand no chance of benefit. */
-	if (pte_batch_hint(ptep, pte) == 1)
-		return 1;
-
-	folio = vm_normal_folio(vma, addr, pte);
-	if (!folio || !folio_test_large(folio))
-		return 1;
-
-	return folio_pte_batch(folio, ptep, pte, max_nr);
+	return can_pte_batch_count(vma, ptep, &pte, max_nr, 0);
 }
 
 static int move_ptes(struct pagetable_move_control *pmc,
 		unsigned long extent, pmd_t *old_pmd, pmd_t *new_pmd)
 {
@@ -278,11 +268,11 @@ static int move_ptes(struct pagetable_move_control *pmc,
 		 * make sure the physical page stays valid until
 		 * the TLB entry for the old mapping has been
 		 * flushed.
 		 */
 		if (pte_present(old_pte)) {
-			nr_ptes = mremap_folio_pte_batch(vma, old_addr, old_ptep,
+			nr_ptes = mremap_pte_batch(vma, old_addr, old_ptep,
 							 old_pte, max_nr_ptes);
 			force_flush = true;
 		}
 		pte = get_and_clear_ptes(mm, old_addr, old_ptep, nr_ptes);
 		pte = move_pte(pte, old_addr, new_addr);
-- 
2.43.0

On Mon, Oct 27, 2025 at 10:03:15PM +0800, Zhang Qilong wrote:
> In current mremap_folio_pte_batch(), 1) pte_batch_hint() always
> return one pte in non-ARM64 machine, it is not efficient. 2) Next,

Err... but there's basically no benefit for non-arm64 machines?

The key benefit is the mTHP side of things and making the underlying
arch-specific code more efficient right?

And again you need to get numbers to demonstrate you don't regress non-arm64.

> it need to acquire a folio to call the folio_pte_batch().
>
> Due to new added can_pte_batch_count(), we just call it instead of
> folio_pte_batch(). And then rename mremap_folio_pte_batch() to
> mremap_pte_batch().
>
> Signed-off-by: Zhang Qilong <zhangqilong3@huawei.com>
> ---
>  mm/mremap.c | 16 +++-------------
>  1 file changed, 3 insertions(+), 13 deletions(-)
>
> diff --git a/mm/mremap.c b/mm/mremap.c
> index bd7314898ec5..d11f93f1622f 100644
> --- a/mm/mremap.c
> +++ b/mm/mremap.c
> @@ -169,27 +169,17 @@ static pte_t move_soft_dirty_pte(pte_t pte)
>  		pte = pte_swp_mksoft_dirty(pte);
>  #endif
>  	return pte;
>  }
>
> -static int mremap_folio_pte_batch(struct vm_area_struct *vma, unsigned long addr,
> +static int mremap_pte_batch(struct vm_area_struct *vma, unsigned long addr,
>  		pte_t *ptep, pte_t pte, int max_nr)
>  {
> -	struct folio *folio;
> -
>  	if (max_nr == 1)
>  		return 1;
>
> -	/* Avoid expensive folio lookup if we stand no chance of benefit. */
> -	if (pte_batch_hint(ptep, pte) == 1)
> -		return 1;

Why are we eliminating an easy exit here and instead always invoking the
more involved function?

Again this has to be tested against non-arm architectures.

> -
> -	folio = vm_normal_folio(vma, addr, pte);
> -	if (!folio || !folio_test_large(folio))
> -		return 1;
> -
> -	return folio_pte_batch(folio, ptep, pte, max_nr);
> +	return can_pte_batch_count(vma, ptep, &pte, max_nr, 0);

This is very silly to have this function now ust return another function + a
trivial check that your function should be doing...

>  }
>
>  static int move_ptes(struct pagetable_move_control *pmc,
>  		unsigned long extent, pmd_t *old_pmd, pmd_t *new_pmd)
>  {
> @@ -278,11 +268,11 @@ static int move_ptes(struct pagetable_move_control *pmc,
>  		 * make sure the physical page stays valid until
>  		 * the TLB entry for the old mapping has been
>  		 * flushed.
>  		 */
>  		if (pte_present(old_pte)) {
> -			nr_ptes = mremap_folio_pte_batch(vma, old_addr, old_ptep,
> +			nr_ptes = mremap_pte_batch(vma, old_addr, old_ptep,
>  							 old_pte, max_nr_ptes);
>  			force_flush = true;
>  		}
>  		pte = get_and_clear_ptes(mm, old_addr, old_ptep, nr_ptes);
>  		pte = move_pte(pte, old_addr, new_addr);
> --
> 2.43.0
>

On 27.10.25 15:03, Zhang Qilong wrote:
> In current mremap_folio_pte_batch(), 1) pte_batch_hint() always
> return one pte in non-ARM64 machine, it is not efficient. 2) Next,
> it need to acquire a folio to call the folio_pte_batch().
> 
> Due to new added can_pte_batch_count(), we just call it instead of
> folio_pte_batch(). And then rename mremap_folio_pte_batch() to
> mremap_pte_batch().
> 
> Signed-off-by: Zhang Qilong <zhangqilong3@huawei.com>
> ---
>   mm/mremap.c | 16 +++-------------
>   1 file changed, 3 insertions(+), 13 deletions(-)
> 
> diff --git a/mm/mremap.c b/mm/mremap.c
> index bd7314898ec5..d11f93f1622f 100644
> --- a/mm/mremap.c
> +++ b/mm/mremap.c
> @@ -169,27 +169,17 @@ static pte_t move_soft_dirty_pte(pte_t pte)
>   		pte = pte_swp_mksoft_dirty(pte);
>   #endif
>   	return pte;
>   }
>   
> -static int mremap_folio_pte_batch(struct vm_area_struct *vma, unsigned long addr,
> +static int mremap_pte_batch(struct vm_area_struct *vma, unsigned long addr,
>   		pte_t *ptep, pte_t pte, int max_nr)
>   {
> -	struct folio *folio;
> -
>   	if (max_nr == 1)
>   		return 1;
>   
> -	/* Avoid expensive folio lookup if we stand no chance of benefit. */
> -	if (pte_batch_hint(ptep, pte) == 1)
> -		return 1;
> -
> -	folio = vm_normal_folio(vma, addr, pte);
> -	if (!folio || !folio_test_large(folio))
> -		return 1;
> -
> -	return folio_pte_batch(folio, ptep, pte, max_nr);
> +	return can_pte_batch_count(vma, ptep, &pte, max_nr, 0);
>   }
>   
>   static int move_ptes(struct pagetable_move_control *pmc,
>   		unsigned long extent, pmd_t *old_pmd, pmd_t *new_pmd)
>   {
> @@ -278,11 +268,11 @@ static int move_ptes(struct pagetable_move_control *pmc,
>   		 * make sure the physical page stays valid until
>   		 * the TLB entry for the old mapping has been
>   		 * flushed.
>   		 */
>   		if (pte_present(old_pte)) {
> -			nr_ptes = mremap_folio_pte_batch(vma, old_addr, old_ptep,
> +			nr_ptes = mremap_pte_batch(vma, old_addr, old_ptep,
>   							 old_pte, max_nr_ptes);
>   			force_flush = true;
>   		}
>   		pte = get_and_clear_ptes(mm, old_addr, old_ptep, nr_ptes);

get_and_clear_ptes() documents: "Clear present PTEs that map consecutive 
pages of the same folio, collecting dirty/accessed bits."

And as can_pte_batch_count() will merge access/dirty bits, you would 
silently set ptes dirty/accessed that belong to other folios, which 
sounds very wrong.

Staring at the code, I wonder if there is also a problem with the write 
bit, have to dig into that.

-- 
Cheers

David / dhildenb