To enable batched unmapping of anonymous folios, we need to handle the sharing of exclusive pages. Hence, a batched version of folio_try_share_anon_rmap_pte is required. Currently, the sole purpose of nr_pages in __folio_try_share_anon_rmap is to do some rmap sanity checks. Add helpers to clear the PageAnonExclusive bit on a batch of nr_pages. Note that __folio_try_share_anon_rmap can receive nr_pages == HPAGE_PMD_NR from the PMD path, but currently we only clear the bit on the head page. Retain this behaviour by setting nr_pages = 1 in case the caller is folio_try_share_anon_rmap_pmd. While at it, convert nr_pages to unsigned long to future-proof from overflow in case P4D-huge mappings etc get supported down the road. I haven't made such a change in each function receiving nr_pages in try_to_unmap_one - perhaps this can be done incrementally. Signed-off-by: Dev Jain --- include/linux/mm.h | 11 +++++++++++ include/linux/rmap.h | 27 ++++++++++++++++++++------- 2 files changed, 31 insertions(+), 7 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 31e27ff6a35fa..0b77329cf57a4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -243,6 +243,17 @@ static inline unsigned long folio_page_idx(const struct folio *folio, return page - &folio->page; } +static __always_inline void folio_clear_pages_anon_exclusive(struct page *page, + unsigned long nr_pages) +{ + for (;;) { + ClearPageAnonExclusive(page); + if (--nr_pages == 0) + break; + ++page; + } +} + static inline struct folio *lru_to_folio(struct list_head *head) { return list_entry((head)->prev, struct folio, lru); diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 8dc0871e5f001..f3b3ee3955afc 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -706,15 +706,19 @@ static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio, } static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, - struct page *page, int nr_pages, enum pgtable_level level) + struct page *page, unsigned long nr_pages, enum pgtable_level level) { VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); VM_WARN_ON_FOLIO(!PageAnonExclusive(page), folio); __folio_rmap_sanity_checks(folio, page, nr_pages, level); + /* We only clear anon-exclusive from head page of PMD folio */ + if (level == PGTABLE_LEVEL_PMD) + nr_pages = 1; + /* device private folios cannot get pinned via GUP. */ if (unlikely(folio_is_device_private(folio))) { - ClearPageAnonExclusive(page); + folio_clear_pages_anon_exclusive(page, nr_pages); return 0; } @@ -766,7 +770,7 @@ static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, if (unlikely(folio_maybe_dma_pinned(folio))) return -EBUSY; - ClearPageAnonExclusive(page); + folio_clear_pages_anon_exclusive(page, nr_pages); /* * This is conceptually a smp_wmb() paired with the smp_rmb() in @@ -778,11 +782,12 @@ static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, } /** - * folio_try_share_anon_rmap_pte - try marking an exclusive anonymous page - * mapped by a PTE possibly shared to prepare + * folio_try_share_anon_rmap_ptes - try marking exclusive anonymous pages + * mapped by PTEs possibly shared to prepare * for KSM or temporary unmapping * @folio: The folio to share a mapping of - * @page: The mapped exclusive page + * @page: The first mapped exclusive page of the batch in the folio + * @nr_pages: The number of pages to share in the folio (batch size) * * The caller needs to hold the page table lock and has to have the page table * entries cleared/invalidated. @@ -797,11 +802,19 @@ static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, * * Returns 0 if marking the mapped page possibly shared succeeded. Returns * -EBUSY otherwise. + * + * The caller needs to hold the page table lock. */ +static inline int folio_try_share_anon_rmap_ptes(struct folio *folio, + struct page *page, unsigned long nr_pages) +{ + return __folio_try_share_anon_rmap(folio, page, nr_pages, PGTABLE_LEVEL_PTE); +} + static inline int folio_try_share_anon_rmap_pte(struct folio *folio, struct page *page) { - return __folio_try_share_anon_rmap(folio, page, 1, PGTABLE_LEVEL_PTE); + return folio_try_share_anon_rmap_ptes(folio, page, 1); } /** -- 2.34.1