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: Baolin Wang Acked-by: David Hildenbrand Co-developed-by: Dev Jain Signed-off-by: Dev Jain Signed-off-by: Nico Pache --- mm/khugepaged.c | 78 ++++++++++++++++++++++++++++++------------------- 1 file changed, 48 insertions(+), 30 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 2dea49522755..b0ae0b63fc9b 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -547,17 +547,17 @@ static void release_pte_pages(pte_t *pte, pte_t *_pte, } 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) + unsigned long address, pte_t *pte, struct collapse_control *cc, + unsigned int order, struct list_head *compound_pagelist) { struct page *page = NULL; struct folio *folio = NULL; pte_t *_pte; int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0; + int scaled_max_ptes_none = khugepaged_max_ptes_none >> (HPAGE_PMD_ORDER - order); + const unsigned long nr_pages = 1UL << order; - for (_pte = pte; _pte < pte + HPAGE_PMD_NR; + for (_pte = pte; _pte < pte + nr_pages; _pte++, address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (pte_none(pteval) || (pte_present(pteval) && @@ -565,7 +565,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || - none_or_zero <= khugepaged_max_ptes_none)) { + none_or_zero <= scaled_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; @@ -593,8 +593,14 @@ static int __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 (order != HPAGE_PMD_ORDER || (cc->is_khugepaged && + shared > khugepaged_max_ptes_shared)) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out; @@ -687,18 +693,18 @@ static int __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); @@ -751,13 +757,11 @@ 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 @@ -771,7 +775,7 @@ 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); } /* @@ -791,16 +795,16 @@ static void __collapse_huge_page_copy_failed(pte_t *pte, */ static int __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; int 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; @@ -819,10 +823,10 @@ static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio, 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; } @@ -995,13 +999,12 @@ static int check_pmd_still_valid(struct mm_struct *mm, * Returns result: if not SCAN_SUCCEED, mmap_lock has been released. */ static int __collapse_huge_page_swapin(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long haddr, pmd_t *pmd, - int referenced) + struct vm_area_struct *vma, unsigned long haddr, + pmd_t *pmd, int referenced, unsigned int order) { int swapped_in = 0; vm_fault_t ret = 0; - unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE); + unsigned long address, end = haddr + (PAGE_SIZE << order); int result; pte_t *pte = NULL; spinlock_t *ptl; @@ -1032,6 +1035,19 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm, if (!is_swap_pte(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 (order != HPAGE_PMD_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); @@ -1152,7 +1168,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, * 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; } @@ -1200,6 +1216,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, 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 { @@ -1230,6 +1247,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, 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)) -- 2.51.0