From 52e054f7184097bea009963e033cdd54af7bf8a2 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 9 Feb 2026 22:07:24 +0800 Subject: mm: rmap: support batched checks of the references for large folios Patch series "support batch checking of references and unmapping for large folios", v6. Currently, folio_referenced_one() always checks the young flag for each PTE sequentially, which is inefficient for large folios. This inefficiency is especially noticeable when reclaiming clean file-backed large folios, where folio_referenced() is observed as a significant performance hotspot. Moreover, on Arm architecture, which supports contiguous PTEs, there is already an optimization to clear the young flags for PTEs within a contiguous range. However, this is not sufficient. We can extend this to perform batched operations for the entire large folio (which might exceed the contiguous range: CONT_PTE_SIZE). Similar to folio_referenced_one(), we can also apply batched unmapping for large file folios to optimize the performance of file folio reclamation. By supporting batched checking of the young flags, flushing TLB entries, and unmapping, I can observed a significant performance improvements in my performance tests for file folios reclamation. Please check the performance data in the commit message of each patch. This patch (of 5): Currently, folio_referenced_one() always checks the young flag for each PTE sequentially, which is inefficient for large folios. This inefficiency is especially noticeable when reclaiming clean file-backed large folios, where folio_referenced() is observed as a significant performance hotspot. Moreover, on Arm64 architecture, which supports contiguous PTEs, there is already an optimization to clear the young flags for PTEs within a contiguous range. However, this is not sufficient. We can extend this to perform batched operations for the entire large folio (which might exceed the contiguous range: CONT_PTE_SIZE). Introduce a new API: clear_flush_young_ptes() to facilitate batched checking of the young flags and flushing TLB entries, thereby improving performance during large folio reclamation. And it will be overridden by the architecture that implements a more efficient batch operation in the following patches. While we are at it, rename ptep_clear_flush_young_notify() to clear_flush_young_ptes_notify() to indicate that this is a batch operation. Link: https://lkml.kernel.org/r/cover.1770645603.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/12132694536834262062d1fb304f8f8a064b6750.1770645603.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Harry Yoo Reviewed-by: Ryan Roberts Acked-by: David Hildenbrand (Arm) Cc: Catalin Marinas Cc: Jann Horn Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Rik van Riel Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Will Deacon Cc: Barry Song Signed-off-by: Andrew Morton --- mm/rmap.c | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/rmap.c b/mm/rmap.c index ab099405151f..3dbc2c4e02dc 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -913,9 +913,11 @@ static bool folio_referenced_one(struct folio *folio, struct folio_referenced_arg *pra = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int ptes = 0, referenced = 0; + unsigned int nr; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; + nr = 1; if (vma->vm_flags & VM_LOCKED) { ptes++; @@ -960,9 +962,21 @@ static bool folio_referenced_one(struct folio *folio, if (lru_gen_look_around(&pvmw)) referenced++; } else if (pvmw.pte) { - if (ptep_clear_flush_young_notify(vma, address, - pvmw.pte)) + if (folio_test_large(folio)) { + unsigned long end_addr = pmd_addr_end(address, vma->vm_end); + unsigned int max_nr = (end_addr - address) >> PAGE_SHIFT; + pte_t pteval = ptep_get(pvmw.pte); + + nr = folio_pte_batch(folio, pvmw.pte, + pteval, max_nr); + } + + ptes += nr; + if (clear_flush_young_ptes_notify(vma, address, pvmw.pte, nr)) referenced++; + /* Skip the batched PTEs */ + pvmw.pte += nr - 1; + pvmw.address += (nr - 1) * PAGE_SIZE; } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) @@ -972,7 +986,15 @@ static bool folio_referenced_one(struct folio *folio, WARN_ON_ONCE(1); } - pra->mapcount--; + pra->mapcount -= nr; + /* + * If we are sure that we batched the entire folio, + * we can just optimize and stop right here. + */ + if (ptes == pvmw.nr_pages) { + page_vma_mapped_walk_done(&pvmw); + break; + } } if (referenced) -- cgit v1.2.3