Re: [RFC v2 7/9] khugepaged: add mTHP support

[Usama Arif <usamaarif642@gmail.com>]

On 11/02/2025 00:30, Nico Pache wrote:
> Introduce the ability for khugepaged to collapse to different mTHP sizes.
> While scanning a PMD range for potential collapse candidates, keep track
> of pages in MIN_MTHP_ORDER chunks via a bitmap. Each bit represents a
> utilized region of order MIN_MTHP_ORDER ptes. We remove the restriction
> of max_ptes_none during the scan phase so we dont bailout early and miss
> potential mTHP candidates.
> 
> After the scan is complete we will perform binary recursion on the
> bitmap to determine which mTHP size would be most efficient to collapse
> to. max_ptes_none will be scaled by the attempted collapse order to
> determine how full a THP must be to be eligible.
> 
> If a mTHP collapse is attempted, but contains swapped out, or shared
> pages, we dont perform the collapse.
> 
> Signed-off-by: Nico Pache <npache@redhat.com>
> ---
>  mm/khugepaged.c | 122 ++++++++++++++++++++++++++++++++----------------
>  1 file changed, 83 insertions(+), 39 deletions(-)
> 
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index c8048d9ec7fb..cd310989725b 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -1127,13 +1127,14 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
>  {
>  	LIST_HEAD(compound_pagelist);
>  	pmd_t *pmd, _pmd;
> -	pte_t *pte;
> +	pte_t *pte, mthp_pte;
>  	pgtable_t pgtable;
>  	struct folio *folio;
>  	spinlock_t *pmd_ptl, *pte_ptl;
>  	int result = SCAN_FAIL;
>  	struct vm_area_struct *vma;
>  	struct mmu_notifier_range range;
> +	unsigned long _address = address + offset * PAGE_SIZE;
>  	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
>  
>  	/*
> @@ -1148,12 +1149,13 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
>  		*mmap_locked = false;
>  	}
>  
> -	result = alloc_charge_folio(&folio, mm, cc, HPAGE_PMD_ORDER);
> +	result = alloc_charge_folio(&folio, mm, cc, order);
>  	if (result != SCAN_SUCCEED)
>  		goto out_nolock;
>  
>  	mmap_read_lock(mm);
> -	result = hugepage_vma_revalidate(mm, address, true, &vma, cc, HPAGE_PMD_ORDER);
> +	*mmap_locked = true;
> +	result = hugepage_vma_revalidate(mm, address, true, &vma, cc, order);
>  	if (result != SCAN_SUCCEED) {
>  		mmap_read_unlock(mm);
>  		goto out_nolock;
> @@ -1171,13 +1173,14 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
>  		 * released when it fails. So we jump out_nolock directly in
>  		 * that case.  Continuing to collapse causes inconsistency.
>  		 */
> -		result = __collapse_huge_page_swapin(mm, vma, address, pmd,
> -				referenced, HPAGE_PMD_ORDER);
> +		result = __collapse_huge_page_swapin(mm, vma, _address, pmd,
> +				referenced, order);
>  		if (result != SCAN_SUCCEED)
>  			goto out_nolock;
>  	}
>  
>  	mmap_read_unlock(mm);
> +	*mmap_locked = false;
>  	/*
>  	 * Prevent all access to pagetables with the exception of
>  	 * gup_fast later handled by the ptep_clear_flush and the VM
> @@ -1187,7 +1190,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
>  	 * mmap_lock.
>  	 */
>  	mmap_write_lock(mm);
> -	result = hugepage_vma_revalidate(mm, address, true, &vma, cc, HPAGE_PMD_ORDER);
> +	result = hugepage_vma_revalidate(mm, address, true, &vma, cc, order);
>  	if (result != SCAN_SUCCEED)
>  		goto out_up_write;
>  	/* check if the pmd is still valid */
> @@ -1198,11 +1201,12 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
>  	vma_start_write(vma);
>  	anon_vma_lock_write(vma->anon_vma);
>  
> -	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address,
> -				address + HPAGE_PMD_SIZE);
> +	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, _address,
> +				_address + (PAGE_SIZE << order));
>  	mmu_notifier_invalidate_range_start(&range);
>  
>  	pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
> +
>  	/*
>  	 * This removes any huge TLB entry from the CPU so we won't allow
>  	 * huge and small TLB entries for the same virtual address to
> @@ -1216,10 +1220,10 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
>  	mmu_notifier_invalidate_range_end(&range);
>  	tlb_remove_table_sync_one();
>  
> -	pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl);
> +	pte = pte_offset_map_lock(mm, &_pmd, _address, &pte_ptl);
>  	if (pte) {
> -		result = __collapse_huge_page_isolate(vma, address, pte, cc,
> -					&compound_pagelist, HPAGE_PMD_ORDER);
> +		result = __collapse_huge_page_isolate(vma, _address, pte, cc,
> +					&compound_pagelist, order);
>  		spin_unlock(pte_ptl);
>  	} else {
>  		result = SCAN_PMD_NULL;
> @@ -1248,8 +1252,8 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
>  	anon_vma_unlock_write(vma->anon_vma);
>  
>  	result = __collapse_huge_page_copy(pte, folio, pmd, _pmd,
> -					   vma, address, pte_ptl,
> -					   &compound_pagelist, HPAGE_PMD_ORDER);
> +					   vma, _address, pte_ptl,
> +					   &compound_pagelist, order);
>  	pte_unmap(pte);
>  	if (unlikely(result != SCAN_SUCCEED))
>  		goto out_up_write;
> @@ -1260,20 +1264,37 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
>  	 * write.
>  	 */
>  	__folio_mark_uptodate(folio);
> -	pgtable = pmd_pgtable(_pmd);
> -
> -	_pmd = mk_huge_pmd(&folio->page, vma->vm_page_prot);
> -	_pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
> -
> -	spin_lock(pmd_ptl);
> -	BUG_ON(!pmd_none(*pmd));
> -	folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE);
> -	folio_add_lru_vma(folio, vma);
> -	pgtable_trans_huge_deposit(mm, pmd, pgtable);
> -	set_pmd_at(mm, address, pmd, _pmd);
> -	update_mmu_cache_pmd(vma, address, pmd);
> -	deferred_split_folio(folio, false);
> -	spin_unlock(pmd_ptl);
> +	if (order == HPAGE_PMD_ORDER) {
> +		pgtable = pmd_pgtable(_pmd);
> +		_pmd = mk_huge_pmd(&folio->page, vma->vm_page_prot);
> +		_pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
> +
> +		spin_lock(pmd_ptl);
> +		BUG_ON(!pmd_none(*pmd));
> +		folio_add_new_anon_rmap(folio, vma, _address, RMAP_EXCLUSIVE);
> +		folio_add_lru_vma(folio, vma);
> +		pgtable_trans_huge_deposit(mm, pmd, pgtable);
> +		set_pmd_at(mm, address, pmd, _pmd);
> +		update_mmu_cache_pmd(vma, address, pmd);
> +		deferred_split_folio(folio, false);
> +		spin_unlock(pmd_ptl);
> +	} else { //mTHP
> +		mthp_pte = mk_pte(&folio->page, vma->vm_page_prot);
> +		mthp_pte = maybe_mkwrite(pte_mkdirty(mthp_pte), vma);
> +
> +		spin_lock(pmd_ptl);
> +		folio_ref_add(folio, (1 << order) - 1);
> +		folio_add_new_anon_rmap(folio, vma, _address, RMAP_EXCLUSIVE);
> +		folio_add_lru_vma(folio, vma);
> +		spin_lock(pte_ptl);
> +		set_ptes(vma->vm_mm, _address, pte, mthp_pte, (1 << order));
> +		update_mmu_cache_range(NULL, vma, _address, pte, (1 << order));
> +		spin_unlock(pte_ptl);
> +		smp_wmb(); /* make pte visible before pmd */
> +		pmd_populate(mm, pmd, pmd_pgtable(_pmd));
> +		deferred_split_folio(folio, false);


Hi Nico,

This patch will have the same issue as the one I pointed out in
https://lore.kernel.org/all/82b9efd1-f2a6-4452-b2ea-6c163e17cdf7@gmail.com/ ?