[PATCH mm-unstable v14 06/16] khugepaged: generalize __collapse_huge_page_* for mTHP support

[Nico Pache <npache@redhat.com>]

generalize the order of the __collapse_huge_page_* functions
to support future mTHP collapse.

mTHP collapse will not honor the khugepaged_max_ptes_shared or
khugepaged_max_ptes_swap parameters, and will fail if it encounters a
shared or swapped entry.

No functional changes in this patch.

Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Reviewed-by: Lance Yang <lance.yang@linux.dev>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Acked-by: David Hildenbrand <david@redhat.com>
Co-developed-by: Dev Jain <dev.jain@arm.com>
Signed-off-by: Dev Jain <dev.jain@arm.com>
Signed-off-by: Nico Pache <npache@redhat.com>
---
 mm/khugepaged.c | 73 +++++++++++++++++++++++++++++++------------------
 1 file changed, 47 insertions(+), 26 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 384d30b6bdd3..0f68902edd9a 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -539,7 +539,7 @@ static void release_pte_pages(pte_t *pte, pte_t *_pte,
 
 static enum scan_result __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		unsigned long start_addr, pte_t *pte, struct collapse_control *cc,
-		struct list_head *compound_pagelist)
+		unsigned int order, struct list_head *compound_pagelist)
 {
 	struct page *page = NULL;
 	struct folio *folio = NULL;
@@ -547,15 +547,17 @@ static enum scan_result __collapse_huge_page_isolate(struct vm_area_struct *vma,
 	pte_t *_pte;
 	int none_or_zero = 0, shared = 0, referenced = 0;
 	enum scan_result result = SCAN_FAIL;
+	const unsigned long nr_pages = 1UL << order;
+	int max_ptes_none = khugepaged_max_ptes_none >> (HPAGE_PMD_ORDER - order);
 
-	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
+	for (_pte = pte; _pte < pte + nr_pages;
 	     _pte++, addr += PAGE_SIZE) {
 		pte_t pteval = ptep_get(_pte);
 		if (pte_none_or_zero(pteval)) {
 			++none_or_zero;
 			if (!userfaultfd_armed(vma) &&
 			    (!cc->is_khugepaged ||
-			     none_or_zero <= khugepaged_max_ptes_none)) {
+			     none_or_zero <= max_ptes_none)) {
 				continue;
 			} else {
 				result = SCAN_EXCEED_NONE_PTE;
@@ -583,8 +585,14 @@ static enum scan_result __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		/* See collapse_scan_pmd(). */
 		if (folio_maybe_mapped_shared(folio)) {
 			++shared;
-			if (cc->is_khugepaged &&
-			    shared > khugepaged_max_ptes_shared) {
+			/*
+			 * TODO: Support shared pages without leading to further
+			 * mTHP collapses. Currently bringing in new pages via
+			 * shared may cause a future higher order collapse on a
+			 * rescan of the same range.
+			 */
+			if (!is_pmd_order(order) || (cc->is_khugepaged &&
+			    shared > khugepaged_max_ptes_shared)) {
 				result = SCAN_EXCEED_SHARED_PTE;
 				count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
 				goto out;
@@ -677,18 +685,18 @@ static enum scan_result __collapse_huge_page_isolate(struct vm_area_struct *vma,
 }
 
 static void __collapse_huge_page_copy_succeeded(pte_t *pte,
-						struct vm_area_struct *vma,
-						unsigned long address,
-						spinlock_t *ptl,
-						struct list_head *compound_pagelist)
+		struct vm_area_struct *vma, unsigned long address,
+		spinlock_t *ptl, unsigned int order,
+		struct list_head *compound_pagelist)
 {
-	unsigned long end = address + HPAGE_PMD_SIZE;
+	unsigned long end = address + (PAGE_SIZE << order);
 	struct folio *src, *tmp;
 	pte_t pteval;
 	pte_t *_pte;
 	unsigned int nr_ptes;
+	const unsigned long nr_pages = 1UL << order;
 
-	for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte += nr_ptes,
+	for (_pte = pte; _pte < pte + nr_pages; _pte += nr_ptes,
 	     address += nr_ptes * PAGE_SIZE) {
 		nr_ptes = 1;
 		pteval = ptep_get(_pte);
@@ -741,13 +749,11 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte,
 }
 
 static void __collapse_huge_page_copy_failed(pte_t *pte,
-					     pmd_t *pmd,
-					     pmd_t orig_pmd,
-					     struct vm_area_struct *vma,
-					     struct list_head *compound_pagelist)
+		pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma,
+		unsigned int order, struct list_head *compound_pagelist)
 {
 	spinlock_t *pmd_ptl;
-
+	const unsigned long nr_pages = 1UL << order;
 	/*
 	 * Re-establish the PMD to point to the original page table
 	 * entry. Restoring PMD needs to be done prior to releasing
@@ -761,7 +767,7 @@ static void __collapse_huge_page_copy_failed(pte_t *pte,
 	 * Release both raw and compound pages isolated
 	 * in __collapse_huge_page_isolate.
 	 */
-	release_pte_pages(pte, pte + HPAGE_PMD_NR, compound_pagelist);
+	release_pte_pages(pte, pte + nr_pages, compound_pagelist);
 }
 
 /*
@@ -781,16 +787,16 @@ static void __collapse_huge_page_copy_failed(pte_t *pte,
  */
 static enum scan_result __collapse_huge_page_copy(pte_t *pte, struct folio *folio,
 		pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma,
-		unsigned long address, spinlock_t *ptl,
+		unsigned long address, spinlock_t *ptl, unsigned int order,
 		struct list_head *compound_pagelist)
 {
 	unsigned int i;
 	enum scan_result result = SCAN_SUCCEED;
-
+	const unsigned long nr_pages = 1UL << order;
 	/*
 	 * Copying pages' contents is subject to memory poison at any iteration.
 	 */
-	for (i = 0; i < HPAGE_PMD_NR; i++) {
+	for (i = 0; i < nr_pages; i++) {
 		pte_t pteval = ptep_get(pte + i);
 		struct page *page = folio_page(folio, i);
 		unsigned long src_addr = address + i * PAGE_SIZE;
@@ -809,10 +815,10 @@ static enum scan_result __collapse_huge_page_copy(pte_t *pte, struct folio *foli
 
 	if (likely(result == SCAN_SUCCEED))
 		__collapse_huge_page_copy_succeeded(pte, vma, address, ptl,
-						    compound_pagelist);
+						    order, compound_pagelist);
 	else
 		__collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma,
-						 compound_pagelist);
+						 order, compound_pagelist);
 
 	return result;
 }
@@ -983,12 +989,12 @@ static enum scan_result check_pmd_still_valid(struct mm_struct *mm,
  * Returns result: if not SCAN_SUCCEED, mmap_lock has been released.
  */
 static enum scan_result __collapse_huge_page_swapin(struct mm_struct *mm,
-		struct vm_area_struct *vma, unsigned long start_addr, pmd_t *pmd,
-		int referenced)
+		struct vm_area_struct *vma, unsigned long start_addr,
+		pmd_t *pmd, int referenced, unsigned int order)
 {
 	int swapped_in = 0;
 	vm_fault_t ret = 0;
-	unsigned long addr, end = start_addr + (HPAGE_PMD_NR * PAGE_SIZE);
+	unsigned long addr, end = start_addr + (PAGE_SIZE << order);
 	enum scan_result result;
 	pte_t *pte = NULL;
 	spinlock_t *ptl;
@@ -1020,6 +1026,19 @@ static enum scan_result __collapse_huge_page_swapin(struct mm_struct *mm,
 		    pte_present(vmf.orig_pte))
 			continue;
 
+		/*
+		 * TODO: Support swapin without leading to further mTHP
+		 * collapses. Currently bringing in new pages via swapin may
+		 * cause a future higher order collapse on a rescan of the same
+		 * range.
+		 */
+		if (!is_pmd_order(order)) {
+			pte_unmap(pte);
+			mmap_read_unlock(mm);
+			result = SCAN_EXCEED_SWAP_PTE;
+			goto out;
+		}
+
 		vmf.pte = pte;
 		vmf.ptl = ptl;
 		ret = do_swap_page(&vmf);
@@ -1139,7 +1158,7 @@ static enum scan_result collapse_huge_page(struct mm_struct *mm, unsigned long a
 		 * that case.  Continuing to collapse causes inconsistency.
 		 */
 		result = __collapse_huge_page_swapin(mm, vma, address, pmd,
-						     referenced);
+						     referenced, HPAGE_PMD_ORDER);
 		if (result != SCAN_SUCCEED)
 			goto out_nolock;
 	}
@@ -1187,6 +1206,7 @@ static enum scan_result collapse_huge_page(struct mm_struct *mm, unsigned long a
 	pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl);
 	if (pte) {
 		result = __collapse_huge_page_isolate(vma, address, pte, cc,
+						      HPAGE_PMD_ORDER,
 						      &compound_pagelist);
 		spin_unlock(pte_ptl);
 	} else {
@@ -1217,6 +1237,7 @@ static enum scan_result collapse_huge_page(struct mm_struct *mm, unsigned long a
 
 	result = __collapse_huge_page_copy(pte, folio, pmd, _pmd,
 					   vma, address, pte_ptl,
+					   HPAGE_PMD_ORDER,
 					   &compound_pagelist);
 	pte_unmap(pte);
 	if (unlikely(result != SCAN_SUCCEED))
-- 
2.52.0