Re: [PATCH 4/5] mm: support batched checking of the young flag for MGLRU

["David Hildenbrand (Arm)" <david@kernel.org>]

On 2/24/26 02:56, Baolin Wang wrote:
> Use the batched helper clear_young_ptes_notify() to check and clear the
> young flag to improve the performance during large folio reclamation when
> MGLRU is enabled.
> 
> Meanwhile, we can also support batched checking the young and dirty flag
> when MGLRU walks the mm's pagetable to update the folios' generation
> counter. Since MGLRU also checks the PTE dirty bit, use folio_pte_batch_flags()
> with FPB_MERGE_YOUNG_DIRTY set to detect batches of PTEs for a large folio.
> 
> Then we can remove the ptep_clear_young_notify() since it has no users now.
> 
> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> ---

[...]

>  
> -static inline int ptep_clear_young_notify(struct vm_area_struct *vma,
> -					  unsigned long addr, pte_t *ptep)
> -{
> -	return clear_young_ptes_notify(vma, addr, ptep, 1);
> -}
> -
>  static inline int pmdp_clear_young_notify(struct vm_area_struct *vma,
>  					  unsigned long addr, pmd_t *pmdp)
>  {
> @@ -1847,12 +1841,6 @@ static inline int pmdp_clear_young_notify(struct vm_area_struct *vma,
>  #define clear_young_ptes_notify	test_and_clear_young_ptes
>  #define pmdp_clear_young_notify	pmdp_test_and_clear_young
>  
> -static inline int ptep_clear_young_notify(struct vm_area_struct *vma,
> -					  unsigned long addr, pte_t *ptep)
> -{
> -	return test_and_clear_young_ptes(vma, addr, ptep, 1);
> -}
> -

Oh, we remove the last user, nice.


>  #endif /* CONFIG_MMU_NOTIFIER */
>  
>  #endif	/* __MM_INTERNAL_H */
> diff --git a/mm/rmap.c b/mm/rmap.c
> index be785dfc9336..1c147251ae28 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -958,25 +958,21 @@ static bool folio_referenced_one(struct folio *folio,
>  			return false;
>  		}
>  
> +		if (pvmw.pte && folio_test_large(folio)) {
> +			unsigned long end_addr = pmd_addr_end(address, vma->vm_end);
> +			unsigned int max_nr = (end_addr - address) >> PAGE_SHIFT;

Both could be const.

> +			pte_t pteval = ptep_get(pvmw.pte);

I wonder if there could be a way to avoid this ptep_get() by letting
page_vma_mapped_walk() just provide the last value it used (in
check_pte() I guess). Something for another patch.

> +
> +			nr = folio_pte_batch(folio, pvmw.pte, pteval, max_nr);
> +			ptes += nr;
> +		}
> +
>  		if (lru_gen_enabled() && pvmw.pte) {
> -			if (lru_gen_look_around(&pvmw))
> +			if (lru_gen_look_around(&pvmw, nr))
>  				referenced++;
>  		} else if (pvmw.pte) {
> -			if (folio_test_large(folio)) {
> -				unsigned long end_addr = pmd_addr_end(address, vma->vm_end);
> -				unsigned int max_nr = (end_addr - address) >> PAGE_SHIFT;
> -				pte_t pteval = ptep_get(pvmw.pte);
> -
> -				nr = folio_pte_batch(folio, pvmw.pte,
> -						     pteval, max_nr);
> -			}
> -
> -			ptes += nr;
>  			if (clear_flush_young_ptes_notify(vma, address, pvmw.pte, nr))
>  				referenced++;
> -			/* Skip the batched PTEs */
> -			pvmw.pte += nr - 1;
> -			pvmw.address += (nr - 1) * PAGE_SIZE;
>  		} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
>  			if (pmdp_clear_flush_young_notify(vma, address,
>  						pvmw.pmd))
> @@ -995,6 +991,12 @@ static bool folio_referenced_one(struct folio *folio,
>  			page_vma_mapped_walk_done(&pvmw);
>  			break;
>  		}
> +
> +		/* Skip the batched PTEs */
> +		if (nr > 1) {
> +			pvmw.pte += nr - 1;
> +			pvmw.address += (nr - 1) * PAGE_SIZE;
> +		}

As nr >= 1, you can just unconditionaly do

pvmw.pte += nr - 1;
pvmw.address += (nr - 1) * PAGE_SIZE;

>  	}
>  
>  	if (referenced)
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 728868c61750..d83962468b2e 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -3494,6 +3494,7 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
>  	struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
>  	DEFINE_MAX_SEQ(walk->lruvec);
>  	int gen = lru_gen_from_seq(max_seq);
> +	unsigned int nr;
>  	pmd_t pmdval;
>  
>  	pte = pte_offset_map_rw_nolock(args->mm, pmd, start & PMD_MASK, &pmdval, &ptl);
> @@ -3512,11 +3513,13 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
>  
>  	lazy_mmu_mode_enable();
>  restart:
> -	for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) {
> +	for (i = pte_index(start), addr = start; addr != end; i += nr, addr += nr * PAGE_SIZE) {
>  		unsigned long pfn;
>  		struct folio *folio;
> -		pte_t ptent = ptep_get(pte + i);
> +		pte_t *ptep = pte + i;
> +		pte_t ptent = ptep_get(ptep);


Existing "pte vs ptent" vs. "ptep vs. pte" is already confusing.
Combining them into "pte vs. ptep vs. ptent" is no good.

If you need another variable, call it "cur_pte". Or rename "pte" to
"start_pte".

>  
> +		nr = 1;
>  		total++;
>  		walk->mm_stats[MM_LEAF_TOTAL]++;
>  
> @@ -3528,7 +3531,14 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
>  		if (!folio)
>  			continue;
>  
> -		if (!ptep_clear_young_notify(args->vma, addr, pte + i))
> +		if (folio_test_large(folio)) {
> +			unsigned int max_nr = (end - addr) >> PAGE_SHIFT;
> +
> +			nr = folio_pte_batch_flags(folio, NULL, ptep, &ptent,
> +						   max_nr, FPB_MERGE_YOUNG_DIRTY);
> +		}
> +
> +		if (!clear_young_ptes_notify(args->vma, addr, ptep, nr))
>  			continue;
>  
>  		if (last != folio) {
> @@ -4186,7 +4196,7 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
>   * the PTE table to the Bloom filter. This forms a feedback loop between the
>   * eviction and the aging.
>   */
> -bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
> +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw, unsigned int batched)

What is "batched"? Did you mean "nr_ptes" ? Or just the initial value
for "nr" ?

[...]

>  
> -		if (!ptep_clear_young_notify(vma, addr, pte + i))
> +		if (folio_test_large(folio)) {
> +			unsigned int max_nr = (end - addr) >> PAGE_SHIFT;

Can be const.

> +
> +			nr = folio_pte_batch_flags(folio, NULL, ptep, &ptent,
> +						   max_nr, FPB_MERGE_YOUNG_DIRTY);
> +		}

I guess we might benefit from a FPB_MERGE_YOUNG only here. But this
should work.

-- 
Cheers,

David