Add enforce_young flag to struct collapse_control that allows context to ignore requirement that some pages in region being collapsed be young or referenced. 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 | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index ca730aec0e3e..b14807b7002e 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -90,6 +90,9 @@ struct collapse_control { /* Respect khugepaged_max_ptes_[none|swap|shared] */ bool enforce_pte_scan_limits; + /* Require memory to be young */ + bool enforce_young; + /* Num pages scanned per node */ int node_load[MAX_NUMNODES]; @@ -720,9 +723,10 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, list_add_tail(&page->lru, compound_pagelist); next: /* There should be enough young pte to collapse the page */ - if (pte_young(pteval) || - page_is_young(page) || PageReferenced(page) || - mmu_notifier_test_young(vma->vm_mm, address)) + if (cc->enforce_young && + (pte_young(pteval) || page_is_young(page) || + PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, + address))) referenced++; if (pte_write(pteval)) @@ -731,7 +735,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, if (unlikely(!writable)) { result = SCAN_PAGE_RO; - } else if (unlikely(!referenced)) { + } else if (unlikely(cc->enforce_young && !referenced)) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; @@ -1387,14 +1391,16 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, result = SCAN_PAGE_COUNT; goto out_unmap; } - if (pte_young(pteval) || - page_is_young(page) || PageReferenced(page) || - mmu_notifier_test_young(vma->vm_mm, address)) + if (cc->enforce_young && + (pte_young(pteval) || page_is_young(page) || + PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, + address))) referenced++; } if (!writable) { result = SCAN_PAGE_RO; - } else if (!referenced || (unmapped && referenced < HPAGE_PMD_NR/2)) { + } else if (cc->enforce_young && (!referenced || (unmapped && referenced + < HPAGE_PMD_NR / 2))) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; @@ -2343,6 +2349,7 @@ static int khugepaged(void *none) struct mm_slot *mm_slot; struct collapse_control cc = { .enforce_pte_scan_limits = true, + .enforce_young = true, .last_target_node = NUMA_NO_NODE, .alloc_charge_hpage = &alloc_charge_hpage, }; -- 2.36.0.464.gb9c8b46e94-goog