[PATCH mm-new v7 2/5] mm: khugepaged: refine scan progress number

Vernon Yang posted 5 patches 1 day, 6 hours ago
[PATCH mm-new v7 2/5] mm: khugepaged: refine scan progress number
Posted by Vernon Yang 1 day, 6 hours ago
From: Vernon Yang <yanglincheng@kylinos.cn>

Currently, each scan always increases "progress" by HPAGE_PMD_NR,
even if only scanning a single PTE/PMD entry.

- When only scanning a sigle PTE entry, let me provide a detailed
  example:

static int hpage_collapse_scan_pmd()
{
	for (addr = start_addr, _pte = pte; _pte < pte + HPAGE_PMD_NR;
	     _pte++, addr += PAGE_SIZE) {
		pte_t pteval = ptep_get(_pte);
		...
		if (pte_uffd_wp(pteval)) { <-- first scan hit
			result = SCAN_PTE_UFFD_WP;
			goto out_unmap;
		}
	}
}

During the first scan, if pte_uffd_wp(pteval) is true, the loop exits
directly. In practice, only one PTE is scanned before termination.
Here, "progress += 1" reflects the actual number of PTEs scanned, but
previously "progress += HPAGE_PMD_NR" always.

- When the memory has been collapsed to PMD, let me provide a detailed
  example:

The following data is traced by bpftrace on a desktop system. After
the system has been left idle for 10 minutes upon booting, a lot of
SCAN_PMD_MAPPED or SCAN_NO_PTE_TABLE are observed during a full scan
by khugepaged.

From trace_mm_khugepaged_scan_pmd and trace_mm_khugepaged_scan_file, the
following statuses were observed, with frequency mentioned next to them:

SCAN_SUCCEED          : 1
SCAN_EXCEED_SHARED_PTE: 2
SCAN_PMD_MAPPED       : 142
SCAN_NO_PTE_TABLE     : 178
total progress size   : 674 MB
Total time            : 419 seconds, include khugepaged_scan_sleep_millisecs

The khugepaged_scan list save all task that support collapse into hugepage,
as long as the task is not destroyed, khugepaged will not remove it from
the khugepaged_scan list. This exist a phenomenon where task has already
collapsed all memory regions into hugepage, but khugepaged continues to
scan it, which wastes CPU time and invalid, and due to
khugepaged_scan_sleep_millisecs (default 10s) causes a long wait for
scanning a large number of invalid task, so scanning really valid task
is later.

After applying this patch, when the memory is either SCAN_PMD_MAPPED or
SCAN_NO_PTE_TABLE, just skip it, as follow:

SCAN_EXCEED_SHARED_PTE: 2
SCAN_PMD_MAPPED       : 147
SCAN_NO_PTE_TABLE     : 173
total progress size   : 45 MB
Total time            : 20 seconds

Signed-off-by: Vernon Yang <yanglincheng@kylinos.cn>
---
 mm/khugepaged.c | 38 ++++++++++++++++++++++++++++----------
 1 file changed, 28 insertions(+), 10 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 4049234e1c8b..8b68ae3bc2c5 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -68,7 +68,10 @@ enum scan_result {
 static struct task_struct *khugepaged_thread __read_mostly;
 static DEFINE_MUTEX(khugepaged_mutex);
 
-/* default scan 8*HPAGE_PMD_NR ptes (or vmas) every 10 second */
+/*
+ * default scan 8*HPAGE_PMD_NR ptes, pmd_mapped, no_pte_table or vmas
+ * every 10 second.
+ */
 static unsigned int khugepaged_pages_to_scan __read_mostly;
 static unsigned int khugepaged_pages_collapsed;
 static unsigned int khugepaged_full_scans;
@@ -1240,7 +1243,8 @@ static enum scan_result collapse_huge_page(struct mm_struct *mm, unsigned long a
 }
 
 static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
-		struct vm_area_struct *vma, unsigned long start_addr, bool *mmap_locked,
+		struct vm_area_struct *vma, unsigned long start_addr,
+		bool *mmap_locked, unsigned int *cur_progress,
 		struct collapse_control *cc)
 {
 	pmd_t *pmd;
@@ -1256,19 +1260,27 @@ static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
 	VM_BUG_ON(start_addr & ~HPAGE_PMD_MASK);
 
 	result = find_pmd_or_thp_or_none(mm, start_addr, &pmd);
-	if (result != SCAN_SUCCEED)
+	if (result != SCAN_SUCCEED) {
+		if (cur_progress)
+			*cur_progress = 1;
 		goto out;
+	}
 
 	memset(cc->node_load, 0, sizeof(cc->node_load));
 	nodes_clear(cc->alloc_nmask);
 	pte = pte_offset_map_lock(mm, pmd, start_addr, &ptl);
 	if (!pte) {
+		if (cur_progress)
+			*cur_progress = 1;
 		result = SCAN_NO_PTE_TABLE;
 		goto out;
 	}
 
 	for (addr = start_addr, _pte = pte; _pte < pte + HPAGE_PMD_NR;
 	     _pte++, addr += PAGE_SIZE) {
+		if (cur_progress)
+			*cur_progress += 1;
+
 		pte_t pteval = ptep_get(_pte);
 		if (pte_none_or_zero(pteval)) {
 			++none_or_zero;
@@ -2288,8 +2300,9 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,
 	return result;
 }
 
-static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
-		struct file *file, pgoff_t start, struct collapse_control *cc)
+static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm,
+		unsigned long addr, struct file *file, pgoff_t start,
+		unsigned int *cur_progress, struct collapse_control *cc)
 {
 	struct folio *folio = NULL;
 	struct address_space *mapping = file->f_mapping;
@@ -2378,6 +2391,8 @@ static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, unsigned
 			cond_resched_rcu();
 		}
 	}
+	if (cur_progress)
+		*cur_progress = HPAGE_PMD_NR;
 	rcu_read_unlock();
 
 	if (result == SCAN_SUCCEED) {
@@ -2457,6 +2472,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result
 
 		while (khugepaged_scan.address < hend) {
 			bool mmap_locked = true;
+			unsigned int cur_progress = 0;
 
 			cond_resched();
 			if (unlikely(hpage_collapse_test_exit_or_disable(mm)))
@@ -2473,7 +2489,8 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result
 				mmap_read_unlock(mm);
 				mmap_locked = false;
 				*result = hpage_collapse_scan_file(mm,
-					khugepaged_scan.address, file, pgoff, cc);
+					khugepaged_scan.address, file, pgoff,
+					&cur_progress, cc);
 				fput(file);
 				if (*result == SCAN_PTE_MAPPED_HUGEPAGE) {
 					mmap_read_lock(mm);
@@ -2487,7 +2504,8 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result
 				}
 			} else {
 				*result = hpage_collapse_scan_pmd(mm, vma,
-					khugepaged_scan.address, &mmap_locked, cc);
+					khugepaged_scan.address, &mmap_locked,
+					&cur_progress, cc);
 			}
 
 			if (*result == SCAN_SUCCEED)
@@ -2495,7 +2513,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result
 
 			/* move to next address */
 			khugepaged_scan.address += HPAGE_PMD_SIZE;
-			progress += HPAGE_PMD_NR;
+			progress += cur_progress;
 			if (!mmap_locked)
 				/*
 				 * We released mmap_lock so break loop.  Note
@@ -2818,7 +2836,7 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
 			mmap_locked = false;
 			*lock_dropped = true;
 			result = hpage_collapse_scan_file(mm, addr, file, pgoff,
-							  cc);
+							  NULL, cc);
 
 			if (result == SCAN_PAGE_DIRTY_OR_WRITEBACK && !triggered_wb &&
 			    mapping_can_writeback(file->f_mapping)) {
@@ -2833,7 +2851,7 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
 			fput(file);
 		} else {
 			result = hpage_collapse_scan_pmd(mm, vma, addr,
-							 &mmap_locked, cc);
+							 &mmap_locked, NULL, cc);
 		}
 		if (!mmap_locked)
 			*lock_dropped = true;
-- 
2.51.0
Re: [PATCH mm-new v7 2/5] mm: khugepaged: refine scan progress number
Posted by Dev Jain 5 hours ago
On 07/02/26 1:46 pm, Vernon Yang wrote:
> From: Vernon Yang <yanglincheng@kylinos.cn>
>
> Currently, each scan always increases "progress" by HPAGE_PMD_NR,
> even if only scanning a single PTE/PMD entry.
>
> - When only scanning a sigle PTE entry, let me provide a detailed
>   example:
>
> static int hpage_collapse_scan_pmd()
> {
> 	for (addr = start_addr, _pte = pte; _pte < pte + HPAGE_PMD_NR;
> 	     _pte++, addr += PAGE_SIZE) {
> 		pte_t pteval = ptep_get(_pte);
> 		...
> 		if (pte_uffd_wp(pteval)) { <-- first scan hit
> 			result = SCAN_PTE_UFFD_WP;
> 			goto out_unmap;
> 		}
> 	}
> }
>
> During the first scan, if pte_uffd_wp(pteval) is true, the loop exits
> directly. In practice, only one PTE is scanned before termination.
> Here, "progress += 1" reflects the actual number of PTEs scanned, but
> previously "progress += HPAGE_PMD_NR" always.
>
> - When the memory has been collapsed to PMD, let me provide a detailed
>   example:
>
> The following data is traced by bpftrace on a desktop system. After
> the system has been left idle for 10 minutes upon booting, a lot of
> SCAN_PMD_MAPPED or SCAN_NO_PTE_TABLE are observed during a full scan
> by khugepaged.
>
> From trace_mm_khugepaged_scan_pmd and trace_mm_khugepaged_scan_file, the
> following statuses were observed, with frequency mentioned next to them:
>
> SCAN_SUCCEED          : 1
> SCAN_EXCEED_SHARED_PTE: 2
> SCAN_PMD_MAPPED       : 142
> SCAN_NO_PTE_TABLE     : 178
> total progress size   : 674 MB
> Total time            : 419 seconds, include khugepaged_scan_sleep_millisecs
>
> The khugepaged_scan list save all task that support collapse into hugepage,
> as long as the task is not destroyed, khugepaged will not remove it from
> the khugepaged_scan list. This exist a phenomenon where task has already
> collapsed all memory regions into hugepage, but khugepaged continues to
> scan it, which wastes CPU time and invalid, and due to
> khugepaged_scan_sleep_millisecs (default 10s) causes a long wait for
> scanning a large number of invalid task, so scanning really valid task
> is later.
>
> After applying this patch, when the memory is either SCAN_PMD_MAPPED or
> SCAN_NO_PTE_TABLE, just skip it, as follow:
>
> SCAN_EXCEED_SHARED_PTE: 2
> SCAN_PMD_MAPPED       : 147
> SCAN_NO_PTE_TABLE     : 173
> total progress size   : 45 MB
> Total time            : 20 seconds
>
> Signed-off-by: Vernon Yang <yanglincheng@kylinos.cn>
> ---
>  mm/khugepaged.c | 38 ++++++++++++++++++++++++++++----------
>  1 file changed, 28 insertions(+), 10 deletions(-)
>
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 4049234e1c8b..8b68ae3bc2c5 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -68,7 +68,10 @@ enum scan_result {
>  static struct task_struct *khugepaged_thread __read_mostly;
>  static DEFINE_MUTEX(khugepaged_mutex);
>  
> -/* default scan 8*HPAGE_PMD_NR ptes (or vmas) every 10 second */
> +/*
> + * default scan 8*HPAGE_PMD_NR ptes, pmd_mapped, no_pte_table or vmas
> + * every 10 second.
> + */
>  static unsigned int khugepaged_pages_to_scan __read_mostly;
>  static unsigned int khugepaged_pages_collapsed;
>  static unsigned int khugepaged_full_scans;
> @@ -1240,7 +1243,8 @@ static enum scan_result collapse_huge_page(struct mm_struct *mm, unsigned long a
>  }
>  
>  static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
> -		struct vm_area_struct *vma, unsigned long start_addr, bool *mmap_locked,
> +		struct vm_area_struct *vma, unsigned long start_addr,
> +		bool *mmap_locked, unsigned int *cur_progress,
>  		struct collapse_control *cc)
>  {
>  	pmd_t *pmd;
> @@ -1256,19 +1260,27 @@ static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
>  	VM_BUG_ON(start_addr & ~HPAGE_PMD_MASK);
>  
>  	result = find_pmd_or_thp_or_none(mm, start_addr, &pmd);
> -	if (result != SCAN_SUCCEED)
> +	if (result != SCAN_SUCCEED) {
> +		if (cur_progress)
> +			*cur_progress = 1;
>  		goto out;
> +	}
>  
>  	memset(cc->node_load, 0, sizeof(cc->node_load));
>  	nodes_clear(cc->alloc_nmask);
>  	pte = pte_offset_map_lock(mm, pmd, start_addr, &ptl);
>  	if (!pte) {
> +		if (cur_progress)
> +			*cur_progress = 1;
>  		result = SCAN_NO_PTE_TABLE;
>  		goto out;
>  	}
>  
>  	for (addr = start_addr, _pte = pte; _pte < pte + HPAGE_PMD_NR;
>  	     _pte++, addr += PAGE_SIZE) {
> +		if (cur_progress)
> +			*cur_progress += 1;
> +
>  		pte_t pteval = ptep_get(_pte);
>  		if (pte_none_or_zero(pteval)) {
>  			++none_or_zero;
> @@ -2288,8 +2300,9 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,
>  	return result;
>  }
>  
> -static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
> -		struct file *file, pgoff_t start, struct collapse_control *cc)
> +static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm,
> +		unsigned long addr, struct file *file, pgoff_t start,
> +		unsigned int *cur_progress, struct collapse_control *cc)
>  {
>  	struct folio *folio = NULL;
>  	struct address_space *mapping = file->f_mapping;
> @@ -2378,6 +2391,8 @@ static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, unsigned
>  			cond_resched_rcu();
>  		}
>  	}
> +	if (cur_progress)
> +		*cur_progress = HPAGE_PMD_NR;
>  	rcu_read_unlock();
>  
>  

Nit: Could move this at the end of the function. Looks weird before the
rcu_read_unlock.

Reviewed-by: Dev Jain <dev.jain@arm.com>
Re: [PATCH mm-new v7 2/5] mm: khugepaged: refine scan progress number
Posted by Vernon Yang an hour ago
On Sun, Feb 8, 2026 at 5:17 PM Dev Jain <dev.jain@arm.com> wrote:
>
> On 07/02/26 1:46 pm, Vernon Yang wrote:
> > From: Vernon Yang <yanglincheng@kylinos.cn>
> >
> > Currently, each scan always increases "progress" by HPAGE_PMD_NR,
> > even if only scanning a single PTE/PMD entry.
> >
> > - When only scanning a sigle PTE entry, let me provide a detailed
> >   example:
> >
> > static int hpage_collapse_scan_pmd()
> > {
> >       for (addr = start_addr, _pte = pte; _pte < pte + HPAGE_PMD_NR;
> >            _pte++, addr += PAGE_SIZE) {
> >               pte_t pteval = ptep_get(_pte);
> >               ...
> >               if (pte_uffd_wp(pteval)) { <-- first scan hit
> >                       result = SCAN_PTE_UFFD_WP;
> >                       goto out_unmap;
> >               }
> >       }
> > }
> >
> > During the first scan, if pte_uffd_wp(pteval) is true, the loop exits
> > directly. In practice, only one PTE is scanned before termination.
> > Here, "progress += 1" reflects the actual number of PTEs scanned, but
> > previously "progress += HPAGE_PMD_NR" always.
> >
> > - When the memory has been collapsed to PMD, let me provide a detailed
> >   example:
> >
> > The following data is traced by bpftrace on a desktop system. After
> > the system has been left idle for 10 minutes upon booting, a lot of
> > SCAN_PMD_MAPPED or SCAN_NO_PTE_TABLE are observed during a full scan
> > by khugepaged.
> >
> > From trace_mm_khugepaged_scan_pmd and trace_mm_khugepaged_scan_file, the
> > following statuses were observed, with frequency mentioned next to them:
> >
> > SCAN_SUCCEED          : 1
> > SCAN_EXCEED_SHARED_PTE: 2
> > SCAN_PMD_MAPPED       : 142
> > SCAN_NO_PTE_TABLE     : 178
> > total progress size   : 674 MB
> > Total time            : 419 seconds, include khugepaged_scan_sleep_millisecs
> >
> > The khugepaged_scan list save all task that support collapse into hugepage,
> > as long as the task is not destroyed, khugepaged will not remove it from
> > the khugepaged_scan list. This exist a phenomenon where task has already
> > collapsed all memory regions into hugepage, but khugepaged continues to
> > scan it, which wastes CPU time and invalid, and due to
> > khugepaged_scan_sleep_millisecs (default 10s) causes a long wait for
> > scanning a large number of invalid task, so scanning really valid task
> > is later.
> >
> > After applying this patch, when the memory is either SCAN_PMD_MAPPED or
> > SCAN_NO_PTE_TABLE, just skip it, as follow:
> >
> > SCAN_EXCEED_SHARED_PTE: 2
> > SCAN_PMD_MAPPED       : 147
> > SCAN_NO_PTE_TABLE     : 173
> > total progress size   : 45 MB
> > Total time            : 20 seconds
> >
> > Signed-off-by: Vernon Yang <yanglincheng@kylinos.cn>
> > ---
> >  mm/khugepaged.c | 38 ++++++++++++++++++++++++++++----------
> >  1 file changed, 28 insertions(+), 10 deletions(-)
> >
> > diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> > index 4049234e1c8b..8b68ae3bc2c5 100644
> > --- a/mm/khugepaged.c
> > +++ b/mm/khugepaged.c
> > @@ -68,7 +68,10 @@ enum scan_result {
> >  static struct task_struct *khugepaged_thread __read_mostly;
> >  static DEFINE_MUTEX(khugepaged_mutex);
> >
> > -/* default scan 8*HPAGE_PMD_NR ptes (or vmas) every 10 second */
> > +/*
> > + * default scan 8*HPAGE_PMD_NR ptes, pmd_mapped, no_pte_table or vmas
> > + * every 10 second.
> > + */
> >  static unsigned int khugepaged_pages_to_scan __read_mostly;
> >  static unsigned int khugepaged_pages_collapsed;
> >  static unsigned int khugepaged_full_scans;
> > @@ -1240,7 +1243,8 @@ static enum scan_result collapse_huge_page(struct mm_struct *mm, unsigned long a
> >  }
> >
> >  static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
> > -             struct vm_area_struct *vma, unsigned long start_addr, bool *mmap_locked,
> > +             struct vm_area_struct *vma, unsigned long start_addr,
> > +             bool *mmap_locked, unsigned int *cur_progress,
> >               struct collapse_control *cc)
> >  {
> >       pmd_t *pmd;
> > @@ -1256,19 +1260,27 @@ static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
> >       VM_BUG_ON(start_addr & ~HPAGE_PMD_MASK);
> >
> >       result = find_pmd_or_thp_or_none(mm, start_addr, &pmd);
> > -     if (result != SCAN_SUCCEED)
> > +     if (result != SCAN_SUCCEED) {
> > +             if (cur_progress)
> > +                     *cur_progress = 1;
> >               goto out;
> > +     }
> >
> >       memset(cc->node_load, 0, sizeof(cc->node_load));
> >       nodes_clear(cc->alloc_nmask);
> >       pte = pte_offset_map_lock(mm, pmd, start_addr, &ptl);
> >       if (!pte) {
> > +             if (cur_progress)
> > +                     *cur_progress = 1;
> >               result = SCAN_NO_PTE_TABLE;
> >               goto out;
> >       }
> >
> >       for (addr = start_addr, _pte = pte; _pte < pte + HPAGE_PMD_NR;
> >            _pte++, addr += PAGE_SIZE) {
> > +             if (cur_progress)
> > +                     *cur_progress += 1;
> > +
> >               pte_t pteval = ptep_get(_pte);
> >               if (pte_none_or_zero(pteval)) {
> >                       ++none_or_zero;
> > @@ -2288,8 +2300,9 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,
> >       return result;
> >  }
> >
> > -static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
> > -             struct file *file, pgoff_t start, struct collapse_control *cc)
> > +static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm,
> > +             unsigned long addr, struct file *file, pgoff_t start,
> > +             unsigned int *cur_progress, struct collapse_control *cc)
> >  {
> >       struct folio *folio = NULL;
> >       struct address_space *mapping = file->f_mapping;
> > @@ -2378,6 +2391,8 @@ static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, unsigned
> >                       cond_resched_rcu();
> >               }
> >       }
> > +     if (cur_progress)
> > +             *cur_progress = HPAGE_PMD_NR;
> >       rcu_read_unlock();
> >
> >
>
> Nit: Could move this at the end of the function. Looks weird before the
> rcu_read_unlock.

I placed it on the next line of rcu_read_unlock() because it follows
the loop more clearly for readability.

> Reviewed-by: Dev Jain <dev.jain@arm.com>

Thank you for review.