Re: [RFC 09/11] khugepaged: add mTHP support

[Dev Jain <dev.jain@arm.com>]

On 09/01/25 5:01 am, Nico Pache wrote:
> Introduce the ability for khugepaged to collapse to different mTHP sizes.
> While scanning a PMD range for potential hugepage collapse, track pages
> in MIN_MTHP_ORDER chunks. Each bit represents a fully utilized region of
> order MIN_MTHP_ORDER ptes.
> 
> With this bitmap we can determine which mTHP sizes would be the most
> efficient to collapse to if the PMD collapse is not suitible.
> 
> Signed-off-by: Nico Pache <npache@redhat.com>
> ---
>   mm/khugepaged.c | 111 +++++++++++++++++++++++++++++++++---------------
>   1 file changed, 77 insertions(+), 34 deletions(-)
> 
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index de1dc6ea3c71..4d3c560f20b4 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -1139,13 +1139,14 @@ 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);
>   
>   	/* if collapsing mTHPs we may have already released the read_lock, and
> @@ -1162,12 +1163,13 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
>   	mmap_read_unlock(mm);
>   	*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;
> @@ -1185,13 +1187,14 @@ 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
> @@ -1201,7 +1204,7 @@ 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 */
> @@ -1212,11 +1215,12 @@ 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));

Since we are nuking the PMD for both cases, we do not need to change it 
for order, this should remain address + HPAGE_PMD_SIZE.

>   	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
> @@ -1230,10 +1234,10 @@ 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;
> @@ -1262,8 +1266,8 @@ 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;
> @@ -1274,20 +1278,37 @@ 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);
> +		spin_unlock(pmd_ptl);
> +	}

You have done lock nesting here: lock(pmd_ptl) -> lock(pte_ptl) -> 
unlock(pte_ptl) -> unlock(pmd_ptl). Anyways, you do not need to take 
pmd_ptl when you are setting the ptes. I am almost done with my v2, and 
according to me this function should look like this:

/* Similar to the PMD case except we have to batch set the PTEs */
static int vma_collapse_anon_folio(struct mm_struct *mm, unsigned long 
address,
		struct vm_area_struct *vma, struct collapse_control *cc, pmd_t *pmd,
		struct folio *folio, int order)
{
	LIST_HEAD(compound_pagelist);
	spinlock_t *pmd_ptl, *pte_ptl;
	int result = SCAN_FAIL;
	struct mmu_notifier_range range;
	pmd_t _pmd;
	pte_t *pte;
	pte_t entry;
	int nr_pages = folio_nr_pages(folio);
	unsigned long haddress = address & HPAGE_PMD_MASK;

	VM_BUG_ON(address & ((1UL << order) - 1));;

	mmap_read_unlock(mm);

	mmap_write_lock(mm);
	result = hugepage_vma_revalidate(mm, address, true, &vma, order, cc);
	if (result != SCAN_SUCCEED)
		goto out_up_write;
	result = check_pmd_still_valid(mm, address, pmd);
	if (result != SCAN_SUCCEED)
		goto out_up_write;

	vma_start_write(vma);
	anon_vma_lock_write(vma->anon_vma);

	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddress,
				haddress + HPAGE_PMD_SIZE);
	mmu_notifier_invalidate_range_start(&range);

	pmd_ptl = pmd_lock(mm, pmd);
	_pmd = pmdp_collapse_flush(vma, haddress, pmd);
	spin_unlock(pmd_ptl);
	mmu_notifier_invalidate_range_end(&range);
	tlb_remove_table_sync_one();

	pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl);
	if (pte) {
		result = __collapse_huge_page_isolate(vma, address, pte, cc,
						      &compound_pagelist, order);
		spin_unlock(pte_ptl);
	} else {
		result = SCAN_PMD_NULL;
	}

	if (unlikely(result != SCAN_SUCCEED)) {
		if (pte)
			pte_unmap(pte);
		spin_lock(pmd_ptl);
		BUG_ON(!pmd_none(*pmd));
		pmd_populate(mm, pmd, pmd_pgtable(_pmd));
		spin_unlock(pmd_ptl);
		anon_vma_unlock_write(vma->anon_vma);
		goto out_up_write;
	}

	anon_vma_unlock_write(vma->anon_vma);

	__folio_mark_uptodate(folio);
	entry = mk_pte(&folio->page, vma->vm_page_prot);
	entry = maybe_mkwrite(pte_mkdirty(entry), vma);

	result = __collapse_huge_page_copy(pte, folio, pmd, *pmd,
					   vma, address, pte_ptl,
					   &compound_pagelist, order);
	pte_unmap(pte);
	if (unlikely(result != SCAN_SUCCEED))
		goto out_up_write;

	folio_ref_add(folio, nr_pages - 1);
	folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE);
	folio_add_lru_vma(folio, vma);
	spin_lock(pte_ptl);
	set_ptes(mm, address, pte, entry, nr_pages);
	spin_unlock(pte_ptl);
	spin_lock(pmd_ptl);

	/* See pmd_install() */
	smp_wmb();
	pmd_populate(mm, pmd, pmd_pgtable(_pmd));
	update_mmu_cache_pmd(vma, haddress, pmd);
	spin_unlock(pmd_ptl);

	result = SCAN_SUCCEED;
out_up_write:
	mmap_write_unlock(mm);
	return result;
}


The difference being, I take the pte_ptl, set the ptes, drop the 
pte_ptl, then take pmd_ptl, do pmd_populate(). Now, instead of 
update_mmu_cache_range() in the mTHP case, we still need to do 
update_mmu_cache_pmd() since we are repopulating the PMD. And, IIUC 
update_mmu_cache_pmd() is a superset of update_mmu_cache_range(), so we 
can drop the latter altogether.

>   
>   	folio = NULL;
>   
> @@ -1367,21 +1388,26 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
>   {
>   	pmd_t *pmd;
>   	pte_t *pte, *_pte;
> +	int i;
>   	int result = SCAN_FAIL, referenced = 0;
>   	int none_or_zero = 0, shared = 0;
>   	struct page *page = NULL;
>   	struct folio *folio = NULL;
>   	unsigned long _address;
> +	unsigned long enabled_orders;
>   	spinlock_t *ptl;
>   	int node = NUMA_NO_NODE, unmapped = 0;
>   	bool writable = false;
> -
> +	bool all_valid = true;
> +	unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0;
>   	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
>   
>   	result = find_pmd_or_thp_or_none(mm, address, &pmd);
>   	if (result != SCAN_SUCCEED)
>   		goto out;
>   
> +	bitmap_zero(cc->mthp_bitmap, 1 << (HPAGE_PMD_ORDER - MIN_MTHP_ORDER));
> +	bitmap_zero(cc->mthp_bitmap_temp, 1 << (HPAGE_PMD_ORDER - MIN_MTHP_ORDER));
>   	memset(cc->node_load, 0, sizeof(cc->node_load));
>   	nodes_clear(cc->alloc_nmask);
>   	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
> @@ -1390,8 +1416,12 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
>   		goto out;
>   	}
>   
> -	for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR;
> -	     _pte++, _address += PAGE_SIZE) {
> +	for (i = 0; i < HPAGE_PMD_NR; i++) {
> +		if (i % MIN_MTHP_NR == 0)
> +			all_valid = true;
> +
> +		_pte = pte + i;
> +		_address = address + i * PAGE_SIZE;
>   		pte_t pteval = ptep_get(_pte);
>   		if (is_swap_pte(pteval)) {
>   			++unmapped;
> @@ -1414,6 +1444,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
>   			}
>   		}
>   		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
> +			all_valid = false;
>   			++none_or_zero;
>   			if (!userfaultfd_armed(vma) &&
>   			    (!cc->is_khugepaged ||
> @@ -1514,7 +1545,15 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
>   		     folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm,
>   								     address)))
>   			referenced++;
> +
> +		/*
> +		 * we are reading in MIN_MTHP_NR page chunks. if there are no empty
> +		 * pages keep track of it in the bitmap for mTHP collapsing.
> +		 */
> +		if (all_valid && (i + 1) % MIN_MTHP_NR == 0)
> +			bitmap_set(cc->mthp_bitmap, i / MIN_MTHP_NR, 1);
>   	}
> +
>   	if (!writable) {
>   		result = SCAN_PAGE_RO;
>   	} else if (cc->is_khugepaged &&
> @@ -1527,10 +1566,12 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
>   out_unmap:
>   	pte_unmap_unlock(pte, ptl);
>   	if (result == SCAN_SUCCEED) {
> -		result = collapse_huge_page(mm, address, referenced,
> -					    unmapped, cc, mmap_locked, HPAGE_PMD_ORDER, 0);
> -		/* collapse_huge_page will return with the mmap_lock released */
> -		*mmap_locked = false;
> +		enabled_orders = thp_vma_allowable_orders(vma, vma->vm_flags,
> +			tva_flags, THP_ORDERS_ALL_ANON);
> +		result = khugepaged_scan_bitmap(mm, address, referenced, unmapped, cc,
> +			       mmap_locked, enabled_orders);
> +		if (result > 0)
> +			result = SCAN_SUCCEED;
>   	}
>   out:
>   	trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced,
> @@ -2477,11 +2518,13 @@ static int khugepaged_collapse_single_pmd(unsigned long addr, struct mm_struct *
>   			fput(file);
>   			if (result == SCAN_PTE_MAPPED_HUGEPAGE) {
>   				mmap_read_lock(mm);
> +				*mmap_locked = true;
>   				if (khugepaged_test_exit_or_disable(mm))
>   					goto end;
>   				result = collapse_pte_mapped_thp(mm, addr,
>   								 !cc->is_khugepaged);
>   				mmap_read_unlock(mm);
> +				*mmap_locked = false;
>   			}
>   		} else {
>   			result = khugepaged_scan_pmd(mm, vma, addr,