Re: [PATCH mm-unstable v2 5/5] mm/khugepaged: unify khugepaged and madv_collapse with collapse_single_pmd()

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

On 2/26/26 02:29, Nico Pache wrote:
> The khugepaged daemon and madvise_collapse have two different
> implementations that do almost the same thing.
> 
> Create collapse_single_pmd to increase code reuse and create an entry
> point to these two users.
> 
> Refactor madvise_collapse and collapse_scan_mm_slot to use the new
> collapse_single_pmd function. This introduces a minor behavioral change
> that is most likely an undiscovered bug. The current implementation of
> khugepaged tests collapse_test_exit_or_disable before calling
> collapse_pte_mapped_thp, but we weren't doing it in the madvise_collapse
> case. By unifying these two callers madvise_collapse now also performs
> this check. We also modify the return value to be SCAN_ANY_PROCESS which
> properly indicates that this process is no longer valid to operate on.
> 
> We also guard the khugepaged_pages_collapsed variable to ensure its only
> incremented for khugepaged.
> 
> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>

Probably best to drop Lorenzo's RB after bigger changes.

> Signed-off-by: Nico Pache <npache@redhat.com>
> ---
>  mm/khugepaged.c | 128 ++++++++++++++++++++++++++----------------------
>  1 file changed, 69 insertions(+), 59 deletions(-)
> 
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 64086488ca01..0058970d4579 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -2417,6 +2417,70 @@ static enum scan_result collapse_scan_file(struct mm_struct *mm, unsigned long a
>  	return result;
>  }
>  
> +/*
> + * Try to collapse a single PMD starting at a PMD aligned addr, and return
> + * the results.
> + */
> +static enum scan_result collapse_single_pmd(unsigned long addr,
> +		struct vm_area_struct *vma, bool *mmap_locked,
> +		unsigned int *cur_progress, struct collapse_control *cc)
> +{
> +	struct mm_struct *mm = vma->vm_mm;
> +	bool triggered_wb = false;
> +	enum scan_result result;
> +	struct file *file;
> +	pgoff_t pgoff;
> +
> +	if (vma_is_anonymous(vma)) {
> +		result = collapse_scan_pmd(mm, vma, addr, mmap_locked, cur_progress, cc);
> +		goto end;
> +	}
> +
> +	file = get_file(vma->vm_file);
> +	pgoff = linear_page_index(vma, addr);
> +
> +	mmap_read_unlock(mm);
> +	*mmap_locked = false;
> +retry:
> +	result = collapse_scan_file(mm, addr, file, pgoff, cur_progress, cc);
> +
> +	/*
> +	 * For MADV_COLLAPSE, when encountering dirty pages, try to writeback,
> +	 * then retry the collapse one time.
> +	 */
> +	if (!cc->is_khugepaged && result == SCAN_PAGE_DIRTY_OR_WRITEBACK &&
> +	    triggered_wb && mapping_can_writeback(file->f_mapping)) {

!triggered_wb, right?


> +		const loff_t lstart = (loff_t)pgoff << PAGE_SHIFT;
> +		const loff_t lend = lstart + HPAGE_PMD_SIZE - 1;
> +
> +		filemap_write_and_wait_range(file->f_mapping, lstart, lend);
> +		triggered_wb = true;
> +		goto retry;
> +	}
> +	fput(file);
> +
> +	if (result != SCAN_PTE_MAPPED_HUGEPAGE)
> +		goto end;
> +
> +	mmap_read_lock(mm);
> +	*mmap_locked = true;

On all paths below, you set "*mmap_locked = false". Why even bother about setting the variable?

> +	if (collapse_test_exit_or_disable(mm)) {
> +		mmap_read_unlock(mm);
> +		*mmap_locked = false;
> +		return SCAN_ANY_PROCESS;
> +	}
> +	result = try_collapse_pte_mapped_thp(mm, addr, !cc->is_khugepaged);
> +	if (result == SCAN_PMD_MAPPED)
> +		result = SCAN_SUCCEED;
> +	mmap_read_unlock(mm);
> +	*mmap_locked = false;

This might all read nicer without the goto and without the early return.

/* If we have a THP in the pagecache, try to retract the pagetable. */
if (result == SCAN_PTE_MAPPED_HUGEPAGE) {
	mmap_read_lock(mm);
	if (collapse_test_exit_or_disable(mm))
		result = SCAN_ANY_PROCESS;
	else
		result = try_collapse_pte_mapped_thp(mm, addr, !cc->is_khugepaged);
	if (result == SCAN_PMD_MAPPED)
		result = SCAN_SUCCEED
	}
	mmap_read_unlock(mm);
}

> +
> +end:
> +	if (cc->is_khugepaged && result == SCAN_SUCCEED)
> +		++khugepaged_pages_collapsed;
> +	return result;
> +}
> +
>  static unsigned int collapse_scan_mm_slot(unsigned int pages, enum scan_result *result,
>  					    struct collapse_control *cc)
>  	__releases(&khugepaged_mm_lock)
> @@ -2489,36 +2553,9 @@ static unsigned int collapse_scan_mm_slot(unsigned int pages, enum scan_result *
>  			VM_BUG_ON(khugepaged_scan.address < hstart ||
>  				  khugepaged_scan.address + HPAGE_PMD_SIZE >
>  				  hend);
> -			if (!vma_is_anonymous(vma)) {
> -				struct file *file = get_file(vma->vm_file);
> -				pgoff_t pgoff = linear_page_index(vma,
> -						khugepaged_scan.address);
> -
> -				mmap_read_unlock(mm);
> -				mmap_locked = false;
> -				*result = collapse_scan_file(mm,
> -					khugepaged_scan.address, file, pgoff,
> -					&cur_progress, cc);
> -				fput(file);
> -				if (*result == SCAN_PTE_MAPPED_HUGEPAGE) {
> -					mmap_read_lock(mm);
> -					if (collapse_test_exit_or_disable(mm))
> -						goto breakouterloop;
> -					*result = try_collapse_pte_mapped_thp(mm,
> -						khugepaged_scan.address, false);
> -					if (*result == SCAN_PMD_MAPPED)
> -						*result = SCAN_SUCCEED;
> -					mmap_read_unlock(mm);
> -				}
> -			} else {
> -				*result = collapse_scan_pmd(mm, vma,
> -					khugepaged_scan.address, &mmap_locked,
> -					&cur_progress, cc);
> -			}
> -
> -			if (*result == SCAN_SUCCEED)
> -				++khugepaged_pages_collapsed;
>  
> +			*result = collapse_single_pmd(khugepaged_scan.address,
> +						      vma, &mmap_locked, &cur_progress, cc);
>  			/* move to next address */
>  			khugepaged_scan.address += HPAGE_PMD_SIZE;
>  			progress += cur_progress;
> @@ -2819,13 +2856,12 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
>  
>  	for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) {
>  		enum scan_result result = SCAN_FAIL;
> -		bool triggered_wb = false;
>  
> -retry:
>  		if (!mmap_locked) {
>  			cond_resched();
>  			mmap_read_lock(mm);
>  			mmap_locked = true;
> +			*lock_dropped = true;

Hm, is this change here required at all? Shouldn't we instead need to know from
collapse_single_pmd() whether it dropped the lock?


-- 
Cheers,

David