[PATCH v5 06/13] mm/khugepaged: add flag to ignore khugepaged_max_ptes_*

["Zach O'Keefe" <zokeefe@xxxxxxxxxx>]

Add enforce_pte_scan_limits flag to struct collapse_control that allows
context to ignore the sysfs-controlled knobs
khugepaged_max_ptes_[none|swap|shared] and set this flag in khugepaged
collapse context to preserve existing khugepaged behavior.

This flag will be used (unset) when introducing madvise collapse
context since here, the user presumably has reason to believe the
collapse will be beneficial and khugepaged heuristics shouldn't tell
the user they are wrong.

Signed-off-by: Zach O'Keefe <zokeefe@xxxxxxxxxx>
---
 mm/khugepaged.c | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 1314caed65b0..ca730aec0e3e 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -87,6 +87,9 @@ static struct kmem_cache *mm_slot_cache __read_mostly;
 #define MAX_PTE_MAPPED_THP 8
 
 struct collapse_control {
+	/* Respect khugepaged_max_ptes_[none|swap|shared] */
+	bool enforce_pte_scan_limits;
+
 	/* Num pages scanned per node */
 	int node_load[MAX_NUMNODES];
 
@@ -614,6 +617,7 @@ static bool is_refcount_suitable(struct page *page)
 static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 					unsigned long address,
 					pte_t *pte,
+					struct collapse_control *cc,
 					struct list_head *compound_pagelist)
 {
 	struct page *page = NULL;
@@ -627,7 +631,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		if (pte_none(pteval) || (pte_present(pteval) &&
 				is_zero_pfn(pte_pfn(pteval)))) {
 			if (!userfaultfd_armed(vma) &&
-			    ++none_or_zero <= khugepaged_max_ptes_none) {
+			    (++none_or_zero <= khugepaged_max_ptes_none ||
+			     !cc->enforce_pte_scan_limits)) {
 				continue;
 			} else {
 				result = SCAN_EXCEED_NONE_PTE;
@@ -647,8 +652,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 
 		VM_BUG_ON_PAGE(!PageAnon(page), page);
 
-		if (page_mapcount(page) > 1 &&
-				++shared > khugepaged_max_ptes_shared) {
+		if (cc->enforce_pte_scan_limits && page_mapcount(page) > 1 &&
+		    ++shared > khugepaged_max_ptes_shared) {
 			result = SCAN_EXCEED_SHARED_PTE;
 			count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
 			goto out;
@@ -1187,7 +1192,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	mmu_notifier_invalidate_range_end(&range);
 
 	spin_lock(pte_ptl);
-	result =  __collapse_huge_page_isolate(vma, address, pte,
+	result =  __collapse_huge_page_isolate(vma, address, pte, cc,
 					       &compound_pagelist);
 	spin_unlock(pte_ptl);
 
@@ -1275,7 +1280,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
 	     _pte++, _address += PAGE_SIZE) {
 		pte_t pteval = *_pte;
 		if (is_swap_pte(pteval)) {
-			if (++unmapped <= khugepaged_max_ptes_swap) {
+			if (++unmapped <= khugepaged_max_ptes_swap ||
+			    !cc->enforce_pte_scan_limits) {
 				/*
 				 * Always be strict with uffd-wp
 				 * enabled swap entries.  Please see
@@ -1294,7 +1300,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
 		}
 		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
 			if (!userfaultfd_armed(vma) &&
-			    ++none_or_zero <= khugepaged_max_ptes_none) {
+			    (++none_or_zero <= khugepaged_max_ptes_none ||
+			     !cc->enforce_pte_scan_limits)) {
 				continue;
 			} else {
 				result = SCAN_EXCEED_NONE_PTE;
@@ -1324,8 +1331,9 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
 			goto out_unmap;
 		}
 
-		if (page_mapcount(page) > 1 &&
-				++shared > khugepaged_max_ptes_shared) {
+		if (cc->enforce_pte_scan_limits &&
+		    page_mapcount(page) > 1 &&
+		    ++shared > khugepaged_max_ptes_shared) {
 			result = SCAN_EXCEED_SHARED_PTE;
 			count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
 			goto out_unmap;
@@ -2051,7 +2059,8 @@ static int khugepaged_scan_file(struct mm_struct *mm, struct file *file,
 			continue;
 
 		if (xa_is_value(page)) {
-			if (++swap > khugepaged_max_ptes_swap) {
+			if (cc->enforce_pte_scan_limits &&
+			    ++swap > khugepaged_max_ptes_swap) {
 				result = SCAN_EXCEED_SWAP_PTE;
 				count_vm_event(THP_SCAN_EXCEED_SWAP_PTE);
 				break;
@@ -2102,7 +2111,8 @@ static int khugepaged_scan_file(struct mm_struct *mm, struct file *file,
 	rcu_read_unlock();
 
 	if (result == SCAN_SUCCEED) {
-		if (present < HPAGE_PMD_NR - khugepaged_max_ptes_none) {
+		if (present < HPAGE_PMD_NR - khugepaged_max_ptes_none &&
+		    cc->enforce_pte_scan_limits) {
 			result = SCAN_EXCEED_NONE_PTE;
 			count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
 		} else {
@@ -2332,6 +2342,7 @@ static int khugepaged(void *none)
 {
 	struct mm_slot *mm_slot;
 	struct collapse_control cc = {
+		.enforce_pte_scan_limits = true,
 		.last_target_node = NUMA_NO_NODE,
 		.alloc_charge_hpage = &alloc_charge_hpage,
 	};
-- 
2.36.0.464.gb9c8b46e94-goog