diff --git a/Documentation/mm/transhuge.rst b/Documentation/mm/transhuge.rst index 9a607059ea11cfc3765a11c98d46f11021690215..93c9239b9ebe23146c417aae0a725856c7fca230 100644 --- a/Documentation/mm/transhuge.rst +++ b/Documentation/mm/transhuge.rst @@ -117,7 +117,7 @@ pages: - map/unmap of a PMD entry for the whole THP increment/decrement folio->_entire_mapcount and also increment/decrement - folio->_nr_pages_mapped by COMPOUND_MAPPED when _entire_mapcount + folio->_nr_pages_mapped by ENTIRELY_MAPPED when _entire_mapcount goes from -1 to 0 or 0 to -1. - map/unmap of individual pages with PTE entry increment/decrement @@ -156,7 +156,7 @@ Partial unmap and deferred_split_folio() Unmapping part of THP (with munmap() or other way) is not going to free memory immediately. Instead, we detect that a subpage of THP is not in use -in page_remove_rmap() and queue the THP for splitting if memory pressure +in folio_remove_rmap_*() and queue the THP for splitting if memory pressure comes. Splitting will free up unused subpages. Splitting the page right away is not an option due to locking context in diff --git a/Documentation/mm/unevictable-lru.rst b/Documentation/mm/unevictable-lru.rst index 67f1338440a50ab942160f6489964c41bc7c3b9e..b6a07a26b10d58ca2e0b24bcaa0739159033dbb0 100644 --- a/Documentation/mm/unevictable-lru.rst +++ b/Documentation/mm/unevictable-lru.rst @@ -486,7 +486,7 @@ munlock the pages if we're removing the last VM_LOCKED VMA that maps the pages. Before the unevictable/mlock changes, mlocking did not mark the pages in any way, so unmapping them required no processing. -For each PTE (or PMD) being unmapped from a VMA, page_remove_rmap() calls +For each PTE (or PMD) being unmapped from a VMA, folio_remove_rmap_*() calls munlock_vma_folio(), which calls munlock_folio() when the VMA is VM_LOCKED (unless it was a PTE mapping of a part of a transparent huge page). @@ -511,7 +511,7 @@ userspace; truncation even unmaps and deletes any private anonymous pages which had been Copied-On-Write from the file pages now being truncated. Mlocked pages can be munlocked and deleted in this way: like with munmap(), -for each PTE (or PMD) being unmapped from a VMA, page_remove_rmap() calls +for each PTE (or PMD) being unmapped from a VMA, folio_remove_rmap_*() calls munlock_vma_folio(), which calls munlock_folio() when the VMA is VM_LOCKED (unless it was a PTE mapping of a part of a transparent huge page). diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e86ba420159d03b78201f0485eb4e0ef2ad140f7..53adaf4e39be9c2e066c8b6868404d645e3fcf96 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1213,15 +1213,6 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, local_irq_restore(flags); } -static inline void count_memcg_page_event(struct page *page, - enum vm_event_item idx) -{ - struct mem_cgroup *memcg = page_memcg(page); - - if (memcg) - count_memcg_events(memcg, idx, 1); -} - static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { @@ -1741,11 +1732,6 @@ static inline void __count_memcg_events(struct mem_cgroup *memcg, { } -static inline void count_memcg_page_event(struct page *page, - int idx) -{ -} - static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { diff --git a/include/linux/mm.h b/include/linux/mm.h index ffa00d1cd17d37c33c23699a561aad7a3220e792..3452aa356a71b210b65ff1f5d18b5310249da0be 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1980,15 +1980,15 @@ static inline bool page_maybe_dma_pinned(struct page *page) * * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ -static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, - struct page *page) +static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma, + struct folio *folio) { VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) return false; - return page_maybe_dma_pinned(page); + return folio_maybe_dma_pinned(folio); } /** diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 3c2fc291b071d16ceee17a42bc86935508f46e11..5f750cdc458bc9bf0ce4cb2fe6ac120a816eaeab 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -172,133 +172,325 @@ struct anon_vma *folio_get_anon_vma(struct folio *folio); typedef int __bitwise rmap_t; /* - * No special request: if the page is a subpage of a compound page, it is - * mapped via a PTE. The mapped (sub)page is possibly shared between processes. + * No special request: A mapped anonymous (sub)page is possibly shared between + * processes. */ #define RMAP_NONE ((__force rmap_t)0) -/* The (sub)page is exclusive to a single process. */ +/* The anonymous (sub)page is exclusive to a single process. */ #define RMAP_EXCLUSIVE ((__force rmap_t)BIT(0)) /* - * The compound page is not mapped via PTEs, but instead via a single PMD and - * should be accounted accordingly. + * Internally, we're using an enum to specify the granularity. We make the + * compiler emit specialized code for each granularity. */ -#define RMAP_COMPOUND ((__force rmap_t)BIT(1)) +enum rmap_level { + RMAP_LEVEL_PTE = 0, + RMAP_LEVEL_PMD, +}; + +static inline void __folio_rmap_sanity_checks(struct folio *folio, + struct page *page, int nr_pages, enum rmap_level level) +{ + /* hugetlb folios are handled separately. */ + VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); + + /* + * TODO: we get driver-allocated folios that have nothing to do with + * the rmap using vm_insert_page(); therefore, we cannot assume that + * folio_test_large_rmappable() holds for large folios. We should + * handle any desired mapcount+stats accounting for these folios in + * VM_MIXEDMAP VMAs separately, and then sanity-check here that + * we really only get rmappable folios. + */ + + VM_WARN_ON_ONCE(nr_pages <= 0); + VM_WARN_ON_FOLIO(page_folio(page) != folio, folio); + VM_WARN_ON_FOLIO(page_folio(page + nr_pages - 1) != folio, folio); + + switch (level) { + case RMAP_LEVEL_PTE: + break; + case RMAP_LEVEL_PMD: + /* + * We don't support folios larger than a single PMD yet. So + * when RMAP_LEVEL_PMD is set, we assume that we are creating + * a single "entire" mapping of the folio. + */ + VM_WARN_ON_FOLIO(folio_nr_pages(folio) != HPAGE_PMD_NR, folio); + VM_WARN_ON_FOLIO(nr_pages != HPAGE_PMD_NR, folio); + break; + default: + VM_WARN_ON_ONCE(true); + } +} /* * rmap interfaces called when adding or removing pte of page */ void folio_move_anon_rmap(struct folio *, struct vm_area_struct *); -void page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, rmap_t flags); +void folio_add_anon_rmap_ptes(struct folio *, struct page *, int nr_pages, + struct vm_area_struct *, unsigned long address, rmap_t flags); +#define folio_add_anon_rmap_pte(folio, page, vma, address, flags) \ + folio_add_anon_rmap_ptes(folio, page, 1, vma, address, flags) +void folio_add_anon_rmap_pmd(struct folio *, struct page *, + struct vm_area_struct *, unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address); void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address); -void page_add_file_rmap(struct page *, struct vm_area_struct *, - bool compound); -void folio_add_file_rmap_range(struct folio *, struct page *, unsigned int nr, - struct vm_area_struct *, bool compound); -void page_remove_rmap(struct page *, struct vm_area_struct *, - bool compound); - -void hugepage_add_anon_rmap(struct folio *, struct vm_area_struct *, +void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages, + struct vm_area_struct *); +#define folio_add_file_rmap_pte(folio, page, vma) \ + folio_add_file_rmap_ptes(folio, page, 1, vma) +void folio_add_file_rmap_pmd(struct folio *, struct page *, + struct vm_area_struct *); +void folio_remove_rmap_ptes(struct folio *, struct page *, int nr_pages, + struct vm_area_struct *); +#define folio_remove_rmap_pte(folio, page, vma) \ + folio_remove_rmap_ptes(folio, page, 1, vma) +void folio_remove_rmap_pmd(struct folio *, struct page *, + struct vm_area_struct *); + +void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address, rmap_t flags); -void hugepage_add_new_anon_rmap(struct folio *, struct vm_area_struct *, +void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address); -static inline void __page_dup_rmap(struct page *page, bool compound) +/* See folio_try_dup_anon_rmap_*() */ +static inline int hugetlb_try_dup_anon_rmap(struct folio *folio, + struct vm_area_struct *vma) { - if (compound) { - struct folio *folio = (struct folio *)page; + VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); - VM_BUG_ON_PAGE(compound && !PageHead(page), page); - atomic_inc(&folio->_entire_mapcount); - } else { - atomic_inc(&page->_mapcount); + if (PageAnonExclusive(&folio->page)) { + if (unlikely(folio_needs_cow_for_dma(vma, folio))) + return -EBUSY; + ClearPageAnonExclusive(&folio->page); } + atomic_inc(&folio->_entire_mapcount); + return 0; +} + +/* See folio_try_share_anon_rmap_*() */ +static inline int hugetlb_try_share_anon_rmap(struct folio *folio) +{ + VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); + VM_WARN_ON_FOLIO(!PageAnonExclusive(&folio->page), folio); + + /* Paired with the memory barrier in try_grab_folio(). */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_mb(); + + if (unlikely(folio_maybe_dma_pinned(folio))) + return -EBUSY; + ClearPageAnonExclusive(&folio->page); + + /* + * This is conceptually a smp_wmb() paired with the smp_rmb() in + * gup_must_unshare(). + */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_mb__after_atomic(); + return 0; } -static inline void page_dup_file_rmap(struct page *page, bool compound) +static inline void hugetlb_add_file_rmap(struct folio *folio) { - __page_dup_rmap(page, compound); + VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); + VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); + + atomic_inc(&folio->_entire_mapcount); +} + +static inline void hugetlb_remove_rmap(struct folio *folio) +{ + VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); + + atomic_dec(&folio->_entire_mapcount); +} + +static __always_inline void __folio_dup_file_rmap(struct folio *folio, + struct page *page, int nr_pages, enum rmap_level level) +{ + __folio_rmap_sanity_checks(folio, page, nr_pages, level); + + switch (level) { + case RMAP_LEVEL_PTE: + do { + atomic_inc(&page->_mapcount); + } while (page++, --nr_pages > 0); + break; + case RMAP_LEVEL_PMD: + atomic_inc(&folio->_entire_mapcount); + break; + } } /** - * page_try_dup_anon_rmap - try duplicating a mapping of an already mapped - * anonymous page - * @page: the page to duplicate the mapping for - * @compound: the page is mapped as compound or as a small page - * @vma: the source vma + * folio_dup_file_rmap_ptes - duplicate PTE mappings of a page range of a folio + * @folio: The folio to duplicate the mappings of + * @page: The first page to duplicate the mappings of + * @nr_pages: The number of pages of which the mapping will be duplicated * - * The caller needs to hold the PT lock and the vma->vma_mm->write_protect_seq. + * The page range of the folio is defined by [page, page + nr_pages) * - * Duplicating the mapping can only fail if the page may be pinned; device - * private pages cannot get pinned and consequently this function cannot fail. + * The caller needs to hold the page table lock. + */ +static inline void folio_dup_file_rmap_ptes(struct folio *folio, + struct page *page, int nr_pages) +{ + __folio_dup_file_rmap(folio, page, nr_pages, RMAP_LEVEL_PTE); +} +#define folio_dup_file_rmap_pte(folio, page) \ + folio_dup_file_rmap_ptes(folio, page, 1) + +/** + * folio_dup_file_rmap_pmd - duplicate a PMD mapping of a page range of a folio + * @folio: The folio to duplicate the mapping of + * @page: The first page to duplicate the mapping of * - * If duplicating the mapping succeeds, the page has to be mapped R/O into - * the parent and the child. It must *not* get mapped writable after this call. + * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * - * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise. + * The caller needs to hold the page table lock. */ -static inline int page_try_dup_anon_rmap(struct page *page, bool compound, - struct vm_area_struct *vma) +static inline void folio_dup_file_rmap_pmd(struct folio *folio, + struct page *page) { - VM_BUG_ON_PAGE(!PageAnon(page), page); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + __folio_dup_file_rmap(folio, page, HPAGE_PMD_NR, RMAP_LEVEL_PTE); +#else + WARN_ON_ONCE(true); +#endif +} - /* - * No need to check+clear for already shared pages, including KSM - * pages. - */ - if (!PageAnonExclusive(page)) - goto dup; +static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, + struct page *page, int nr_pages, struct vm_area_struct *src_vma, + enum rmap_level level) +{ + bool maybe_pinned; + int i; + + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); + __folio_rmap_sanity_checks(folio, page, nr_pages, level); /* - * If this page may have been pinned by the parent process, - * don't allow to duplicate the mapping but instead require to e.g., - * copy the page immediately for the child so that we'll always - * guarantee the pinned page won't be randomly replaced in the + * If this folio may have been pinned by the parent process, + * don't allow to duplicate the mappings but instead require to e.g., + * copy the subpage immediately for the child so that we'll always + * guarantee the pinned folio won't be randomly replaced in the * future on write faults. */ - if (likely(!is_device_private_page(page)) && - unlikely(page_needs_cow_for_dma(vma, page))) - return -EBUSY; + maybe_pinned = likely(!folio_is_device_private(folio)) && + unlikely(folio_needs_cow_for_dma(src_vma, folio)); - ClearPageAnonExclusive(page); /* - * It's okay to share the anon page between both processes, mapping - * the page R/O into both processes. + * No need to check+clear for already shared PTEs/PMDs of the + * folio. But if any page is PageAnonExclusive, we must fallback to + * copying if the folio maybe pinned. */ -dup: - __page_dup_rmap(page, compound); + switch (level) { + case RMAP_LEVEL_PTE: + if (unlikely(maybe_pinned)) { + for (i = 0; i < nr_pages; i++) + if (PageAnonExclusive(page + i)) + return -EBUSY; + } + do { + if (PageAnonExclusive(page)) + ClearPageAnonExclusive(page); + atomic_inc(&page->_mapcount); + } while (page++, --nr_pages > 0); + break; + case RMAP_LEVEL_PMD: + if (PageAnonExclusive(page)) { + if (unlikely(maybe_pinned)) + return -EBUSY; + ClearPageAnonExclusive(page); + } + atomic_inc(&folio->_entire_mapcount); + break; + } return 0; } /** - * page_try_share_anon_rmap - try marking an exclusive anonymous page possibly - * shared to prepare for KSM or temporary unmapping - * @page: the exclusive anonymous page to try marking possibly shared + * folio_try_dup_anon_rmap_ptes - try duplicating PTE mappings of a page range + * of a folio + * @folio: The folio to duplicate the mappings of + * @page: The first page to duplicate the mappings of + * @nr_pages: The number of pages of which the mapping will be duplicated + * @src_vma: The vm area from which the mappings are duplicated * - * The caller needs to hold the PT lock and has to have the page table entry - * cleared/invalidated. + * The page range of the folio is defined by [page, page + nr_pages) * - * This is similar to page_try_dup_anon_rmap(), however, not used during fork() - * to duplicate a mapping, but instead to prepare for KSM or temporarily - * unmapping a page (swap, migration) via page_remove_rmap(). + * The caller needs to hold the page table lock and the + * vma->vma_mm->write_protect_seq. * - * Marking the page shared can only fail if the page may be pinned; device - * private pages cannot get pinned and consequently this function cannot fail. + * Duplicating the mappings can only fail if the folio may be pinned; device + * private folios cannot get pinned and consequently this function cannot fail + * for them. * - * Returns 0 if marking the page possibly shared succeeded. Returns -EBUSY - * otherwise. + * If duplicating the mappings succeeded, the duplicated PTEs have to be R/O in + * the parent and the child. They must *not* be writable after this call + * succeeded. + * + * Returns 0 if duplicating the mappings succeeded. Returns -EBUSY otherwise. */ -static inline int page_try_share_anon_rmap(struct page *page) +static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio, + struct page *page, int nr_pages, struct vm_area_struct *src_vma) { - VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page); + return __folio_try_dup_anon_rmap(folio, page, nr_pages, src_vma, + RMAP_LEVEL_PTE); +} +#define folio_try_dup_anon_rmap_pte(folio, page, vma) \ + folio_try_dup_anon_rmap_ptes(folio, page, 1, vma) + +/** + * folio_try_dup_anon_rmap_pmd - try duplicating a PMD mapping of a page range + * of a folio + * @folio: The folio to duplicate the mapping of + * @page: The first page to duplicate the mapping of + * @src_vma: The vm area from which the mapping is duplicated + * + * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) + * + * The caller needs to hold the page table lock and the + * vma->vma_mm->write_protect_seq. + * + * Duplicating the mapping can only fail if the folio may be pinned; device + * private folios cannot get pinned and consequently this function cannot fail + * for them. + * + * If duplicating the mapping succeeds, the duplicated PMD has to be R/O in + * the parent and the child. They must *not* be writable after this call + * succeeded. + * + * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise. + */ +static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio, + struct page *page, struct vm_area_struct *src_vma) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + return __folio_try_dup_anon_rmap(folio, page, HPAGE_PMD_NR, src_vma, + RMAP_LEVEL_PMD); +#else + WARN_ON_ONCE(true); + return -EBUSY; +#endif +} - /* device private pages cannot get pinned via GUP. */ - if (unlikely(is_device_private_page(page))) { +static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, + struct page *page, int nr_pages, enum rmap_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); + + /* device private folios cannot get pinned via GUP. */ + if (unlikely(folio_is_device_private(folio))) { ClearPageAnonExclusive(page); return 0; } @@ -349,7 +541,7 @@ static inline int page_try_share_anon_rmap(struct page *page) if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) smp_mb(); - if (unlikely(page_maybe_dma_pinned(page))) + if (unlikely(folio_maybe_dma_pinned(folio))) return -EBUSY; ClearPageAnonExclusive(page); @@ -362,6 +554,68 @@ static inline int page_try_share_anon_rmap(struct page *page) return 0; } +/** + * folio_try_share_anon_rmap_pte - try marking an exclusive anonymous page + * mapped by a PTE possibly shared to prepare + * for KSM or temporary unmapping + * @folio: The folio to share a mapping of + * @page: The mapped exclusive page + * + * The caller needs to hold the page table lock and has to have the page table + * entries cleared/invalidated. + * + * This is similar to folio_try_dup_anon_rmap_pte(), however, not used during + * fork() to duplicate mappings, but instead to prepare for KSM or temporarily + * unmapping parts of a folio (swap, migration) via folio_remove_rmap_pte(). + * + * Marking the mapped page shared can only fail if the folio maybe pinned; + * device private folios cannot get pinned and consequently this function cannot + * fail. + * + * Returns 0 if marking the mapped page possibly shared succeeded. Returns + * -EBUSY otherwise. + */ +static inline int folio_try_share_anon_rmap_pte(struct folio *folio, + struct page *page) +{ + return __folio_try_share_anon_rmap(folio, page, 1, RMAP_LEVEL_PTE); +} + +/** + * folio_try_share_anon_rmap_pmd - try marking an exclusive anonymous page + * range mapped by a PMD possibly shared to + * prepare for temporary unmapping + * @folio: The folio to share the mapping of + * @page: The first page to share the mapping of + * + * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) + * + * The caller needs to hold the page table lock and has to have the page table + * entries cleared/invalidated. + * + * This is similar to folio_try_dup_anon_rmap_pmd(), however, not used during + * fork() to duplicate a mapping, but instead to prepare for temporarily + * unmapping parts of a folio (swap, migration) via folio_remove_rmap_pmd(). + * + * Marking the mapped pages shared can only fail if the folio maybe pinned; + * device private folios cannot get pinned and consequently this function cannot + * fail. + * + * Returns 0 if marking the mapped pages possibly shared succeeded. Returns + * -EBUSY otherwise. + */ +static inline int folio_try_share_anon_rmap_pmd(struct folio *folio, + struct page *page) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + return __folio_try_share_anon_rmap(folio, page, HPAGE_PMD_NR, + RMAP_LEVEL_PMD); +#else + WARN_ON_ONCE(true); + return -EBUSY; +#endif +} + /* * Called from mm/vmscan.c to handle paging out */ diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index cf52555455a31e99db1542dfc41d0576ba41ff28..3103cd259383f42cb6b63712c37cac2e42d70f31 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -200,7 +200,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, mk_pte(new_page, vma->vm_page_prot)); add_reliable_page_counter(old_page, mm, -1); - page_remove_rmap(old_page, vma, false); + folio_remove_rmap_pte(old_folio, old_page, vma); if (!folio_mapped(old_folio)) folio_free_swap(old_folio); page_vma_mapped_walk_done(&pvmw); diff --git a/mm/filemap.c b/mm/filemap.c index db830ebe0f3f6d2e49d9b013a9a7eac57d21f8ec..12d73aa8487d1b192541fc7e6e6cf7e138cd5c5a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -113,11 +113,11 @@ * ->i_pages lock (try_to_unmap_one) * ->lruvec->lru_lock (follow_page->mark_page_accessed) * ->lruvec->lru_lock (check_pte_range->isolate_lru_page) - * ->private_lock (page_remove_rmap->set_page_dirty) - * ->i_pages lock (page_remove_rmap->set_page_dirty) - * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) - * ->inode->i_lock (page_remove_rmap->set_page_dirty) - * ->memcg->move_lock (page_remove_rmap->folio_memcg_lock) + * ->private_lock (folio_remove_rmap_pte->set_page_dirty) + * ->i_pages lock (folio_remove_rmap_pte->set_page_dirty) + * bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty) + * ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty) + * ->memcg->move_lock (folio_remove_rmap_pte->folio_memcg_lock) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->block_dirty_folio) diff --git a/mm/gup.c b/mm/gup.c index 813add0d3a74145d0a12b612789aa23cfa43a78a..5332f37a79eeba6d4bc6e1d45a436b133d276ba1 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -177,7 +177,7 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) /* * Adjust the pincount before re-checking the PTE for changes. * This is essentially a smp_mb() and is paired with a memory - * barrier in page_try_share_anon_rmap(). + * barrier in folio_try_share_anon_rmap_*(). */ smp_mb__after_atomic(); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5a2131be45401951e4911752e36daa79e4116953..2d325daab41169832796cbc6fe0968711455cb73 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1249,6 +1249,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, { spinlock_t *dst_ptl, *src_ptl; struct page *src_page; + struct folio *src_folio; pmd_t pmd; pgtable_t pgtable = NULL; int ret = -ENOMEM; @@ -1315,11 +1316,12 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); + src_folio = page_folio(src_page); - get_page(src_page); - if (unlikely(page_try_dup_anon_rmap(src_page, true, src_vma))) { + folio_get(src_folio); + if (unlikely(folio_try_dup_anon_rmap_pmd(src_folio, src_page, src_vma))) { /* Page maybe pinned: split and retry the fault on PTEs. */ - put_page(src_page); + folio_put(src_folio); pte_free(dst_mm, pgtable); spin_unlock(src_ptl); spin_unlock(dst_ptl); @@ -1429,8 +1431,8 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, } /* - * TODO: once we support anonymous pages, use page_try_dup_anon_rmap() - * and split if duplicating fails. + * TODO: once we support anonymous pages, use + * folio_try_dup_anon_rmap_*() and split if duplicating fails. */ pudp_set_wrprotect(src_mm, addr, src_pud); pud = pud_mkold(pud_wrprotect(pud)); @@ -1874,7 +1876,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (pmd_present(orig_pmd)) { page = pmd_page(orig_pmd); add_reliable_page_counter(page, tlb->mm, -HPAGE_PMD_NR); - page_remove_rmap(page, vma, true); + folio_remove_rmap_pmd(page_folio(page), page, vma); VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); VM_BUG_ON_PAGE(!PageHead(page), page); } else if (thp_migration_supported()) { @@ -2253,6 +2255,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, unsigned long haddr, bool freeze) { struct mm_struct *mm = vma->vm_mm; + struct folio *folio; struct page *page; pgtable_t pgtable; pmd_t old_pmd, _pmd; @@ -2287,13 +2290,14 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, page = pfn_swap_entry_to_page(entry); } else { page = pmd_page(old_pmd); - if (!PageDirty(page) && pmd_dirty(old_pmd)) - set_page_dirty(page); - if (!PageReferenced(page) && pmd_young(old_pmd)) - SetPageReferenced(page); + folio = page_folio(page); + if (!folio_test_dirty(folio) && pmd_dirty(old_pmd)) + folio_mark_dirty(folio); + if (!folio_test_referenced(folio) && pmd_young(old_pmd)) + folio_set_referenced(folio); add_reliable_page_counter(page, mm, -HPAGE_PMD_NR); - page_remove_rmap(page, vma, true); - put_page(page); + folio_remove_rmap_pmd(folio, page, vma); + folio_put(folio); } add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR); return; @@ -2349,16 +2353,18 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, uffd_wp = pmd_swp_uffd_wp(old_pmd); } else { page = pmd_page(old_pmd); + folio = page_folio(page); if (pmd_dirty(old_pmd)) { dirty = true; - SetPageDirty(page); + folio_set_dirty(folio); } write = pmd_write(old_pmd); young = pmd_young(old_pmd); soft_dirty = pmd_soft_dirty(old_pmd); uffd_wp = pmd_uffd_wp(old_pmd); - VM_BUG_ON_PAGE(!page_count(page), page); + VM_WARN_ON_FOLIO(!folio_ref_count(folio), folio); + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); /* * Without "freeze", we'll simply split the PMD, propagating the @@ -2373,13 +2379,21 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, * In case we cannot clear PageAnonExclusive(), split the PMD * only and let try_to_migrate_one() fail later. * - * See page_try_share_anon_rmap(): invalidate PMD first. + * See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */ - anon_exclusive = PageAnon(page) && PageAnonExclusive(page); - if (freeze && anon_exclusive && page_try_share_anon_rmap(page)) + anon_exclusive = PageAnonExclusive(page); + if (freeze && anon_exclusive && + folio_try_share_anon_rmap_pmd(folio, page)) freeze = false; - if (!freeze) - page_ref_add(page, HPAGE_PMD_NR - 1); + if (!freeze) { + rmap_t rmap_flags = RMAP_NONE; + + folio_ref_add(folio, HPAGE_PMD_NR - 1); + if (anon_exclusive) + rmap_flags |= RMAP_EXCLUSIVE; + folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR, + vma, haddr, rmap_flags); + } } /* @@ -2422,8 +2436,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot)); if (write) entry = pte_mkwrite(entry, vma); - if (anon_exclusive) - SetPageAnonExclusive(page + i); if (!young) entry = pte_mkold(entry); /* NOTE: this may set soft-dirty too on some archs */ @@ -2433,7 +2445,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = pte_mksoft_dirty(entry); if (uffd_wp) entry = pte_mkuffd_wp(entry); - page_add_anon_rmap(page + i, vma, addr, RMAP_NONE); } VM_BUG_ON(!pte_none(ptep_get(pte))); set_pte_at(mm, addr, pte, entry); @@ -2442,7 +2453,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pte_unmap(pte - 1); if (!pmd_migration) - page_remove_rmap(page, vma, true); + folio_remove_rmap_pmd(folio, page, vma); if (freeze) put_page(page); @@ -3391,6 +3402,7 @@ late_initcall(split_huge_pages_debugfs); int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { + struct folio *folio = page_folio(page); struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long address = pvmw->address; @@ -3405,15 +3417,15 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); pmdval = pmdp_invalidate(vma, address, pvmw->pmd); - /* See page_try_share_anon_rmap(): invalidate PMD first. */ - anon_exclusive = PageAnon(page) && PageAnonExclusive(page); - if (anon_exclusive && page_try_share_anon_rmap(page)) { + /* See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */ + anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(page); + if (anon_exclusive && folio_try_share_anon_rmap_pmd(folio, page)) { set_pmd_at(mm, address, pvmw->pmd, pmdval); return -EBUSY; } if (pmd_dirty(pmdval)) - set_page_dirty(page); + folio_mark_dirty(folio); if (pmd_write(pmdval)) entry = make_writable_migration_entry(page_to_pfn(page)); else if (anon_exclusive) @@ -3430,8 +3442,8 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, if (pmd_uffd_wp(pmdval)) pmdswp = pmd_swp_mkuffd_wp(pmdswp); set_pmd_at(mm, address, pvmw->pmd, pmdswp); - page_remove_rmap(page, vma, true); - put_page(page); + folio_remove_rmap_pmd(folio, page, vma); + folio_put(folio); trace_set_migration_pmd(address, pmd_val(pmdswp)); return 0; @@ -3439,6 +3451,7 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { + struct folio *folio = page_folio(new); struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long address = pvmw->address; @@ -3450,7 +3463,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) return; entry = pmd_to_swp_entry(*pvmw->pmd); - get_page(new); + folio_get(folio); pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot)); if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); @@ -3461,20 +3474,20 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) if (!is_migration_entry_young(entry)) pmde = pmd_mkold(pmde); /* NOTE: this may contain setting soft-dirty on some archs */ - if (PageDirty(new) && is_migration_entry_dirty(entry)) + if (folio_test_dirty(folio) && is_migration_entry_dirty(entry)) pmde = pmd_mkdirty(pmde); - if (PageAnon(new)) { - rmap_t rmap_flags = RMAP_COMPOUND; + if (folio_test_anon(folio)) { + rmap_t rmap_flags = RMAP_NONE; if (!is_readable_migration_entry(entry)) rmap_flags |= RMAP_EXCLUSIVE; - page_add_anon_rmap(new, vma, haddr, rmap_flags); + folio_add_anon_rmap_pmd(folio, new, vma, haddr, rmap_flags); } else { - page_add_file_rmap(new, vma, true); + folio_add_file_rmap_pmd(folio, new, vma); } - VM_BUG_ON(pmd_write(pmde) && PageAnon(new) && !PageAnonExclusive(new)); + VM_BUG_ON(pmd_write(pmde) && folio_test_anon(folio) && !PageAnonExclusive(new)); set_pmd_at(mm, haddr, pvmw->pmd, pmde); /* No need to invalidate - it was non-present before */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0d36485728989177c30aef98bb97ad1a66282822..3a4a06f5e83625bc81b653fa38de54e4f35b59cb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5230,7 +5230,7 @@ hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long add pte_t newpte = make_huge_pte(vma, &new_folio->page, 1); __folio_mark_uptodate(new_folio); - hugepage_add_new_anon_rmap(new_folio, vma, addr); + hugetlb_add_new_anon_rmap(new_folio, vma, addr); if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz); @@ -5353,9 +5353,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, * sleep during the process. */ if (!folio_test_anon(pte_folio)) { - page_dup_file_rmap(&pte_folio->page, true); - } else if (page_try_dup_anon_rmap(&pte_folio->page, - true, src_vma)) { + hugetlb_add_file_rmap(pte_folio); + } else if (hugetlb_try_dup_anon_rmap(pte_folio, src_vma)) { pte_t src_pte_old = entry; struct folio *new_folio; @@ -5628,7 +5627,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, make_pte_marker(PTE_MARKER_UFFD_WP), sz); hugetlb_count_sub(pages_per_huge_page(h), mm); - page_remove_rmap(page, vma, true); + hugetlb_remove_rmap(page_folio(page)); spin_unlock(ptl); tlb_remove_page_size(tlb, page, huge_page_size(h)); @@ -5939,8 +5938,8 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, /* Break COW or unshare */ huge_ptep_clear_flush(vma, haddr, ptep); - page_remove_rmap(&old_folio->page, vma, true); - hugepage_add_new_anon_rmap(new_folio, vma, haddr); + hugetlb_remove_rmap(old_folio); + hugetlb_add_new_anon_rmap(new_folio, vma, haddr); if (huge_pte_uffd_wp(pte)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(mm, haddr, ptep, newpte, huge_page_size(h)); @@ -6228,9 +6227,9 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, goto backout; if (anon_rmap) - hugepage_add_new_anon_rmap(folio, vma, haddr); + hugetlb_add_new_anon_rmap(folio, vma, haddr); else - page_dup_file_rmap(&folio->page, true); + hugetlb_add_file_rmap(folio); new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); /* @@ -6654,9 +6653,9 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, goto out_release_unlock; if (folio_in_pagecache) - page_dup_file_rmap(&folio->page, true); + hugetlb_add_file_rmap(folio); else - hugepage_add_new_anon_rmap(folio, dst_vma, dst_addr); + hugetlb_add_new_anon_rmap(folio, dst_vma, dst_addr); /* * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY diff --git a/mm/internal.h b/mm/internal.h index eab2199d16c8a84a66b531e9492ec9b3212ad867..ef68eddaa5d36e63f644580843f4cba97908f42d 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -54,12 +54,12 @@ void page_writeback_init(void); /* * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages, - * its nr_pages_mapped would be 0x400000: choose the COMPOUND_MAPPED bit + * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently * leaves nr_pages_mapped at 0, but avoid surprise if it participates later. */ -#define COMPOUND_MAPPED 0x800000 -#define FOLIO_PAGES_MAPPED (COMPOUND_MAPPED - 1) +#define ENTIRELY_MAPPED 0x800000 +#define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1) /* * Flags passed to __show_mem() and show_free_areas() to suppress output in @@ -647,8 +647,8 @@ folio_within_vma(struct folio *folio, struct vm_area_struct *vma) * should be called with vma's mmap_lock held for read or write, * under page table lock for the pte/pmd being added or removed. * - * mlock is usually called at the end of page_add_*_rmap(), munlock at - * the end of page_remove_rmap(); but new anon folios are managed by + * mlock is usually called at the end of folio_add_*_rmap_*(), munlock at + * the end of folio_remove_rmap_*(); but new anon folios are managed by * folio_add_lru_vma() calling mlock_new_folio(). */ void mlock_folio(struct folio *folio); @@ -1033,7 +1033,7 @@ enum { * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq * * GUP-fast and KSM or temporary unmapping (swap, migration): see - * page_try_share_anon_rmap() + * folio_try_share_anon_rmap_*() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a @@ -1076,7 +1076,7 @@ static inline bool gup_must_unshare(struct vm_area_struct *vma, return is_cow_mapping(vma->vm_flags); } - /* Paired with a memory barrier in page_try_share_anon_rmap(). */ + /* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */ if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) smp_rmb(); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index b0a7af8f81b3820fe13a89cef4e4880758df052d..89b47a6e24af3e1fb9383d84196f9c58b8c3ac4a 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -501,11 +501,6 @@ static void release_pte_folio(struct folio *folio) folio_putback_lru(folio); } -static void release_pte_page(struct page *page) -{ - release_pte_folio(page_folio(page)); -} - static void release_pte_pages(pte_t *pte, pte_t *_pte, struct list_head *compound_pagelist) { @@ -532,15 +527,15 @@ static void release_pte_pages(pte_t *pte, pte_t *_pte, } } -static bool is_refcount_suitable(struct page *page) +static bool is_refcount_suitable(struct folio *folio) { int expected_refcount; - expected_refcount = total_mapcount(page); - if (PageSwapCache(page)) - expected_refcount += compound_nr(page); + expected_refcount = folio_mapcount(folio); + if (folio_test_swapcache(folio)) + expected_refcount += folio_nr_pages(folio); - return page_count(page) == expected_refcount; + return folio_ref_count(folio) == expected_refcount; } static int __collapse_huge_page_isolate(struct vm_area_struct *vma, @@ -550,6 +545,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, 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; bool writable = false; @@ -584,7 +580,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, goto out; } - VM_BUG_ON_PAGE(!PageAnon(page), page); + folio = page_folio(page); + VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio); if (page_mapcount(page) > 1) { ++shared; @@ -596,16 +593,15 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, } } - if (PageCompound(page)) { - struct page *p; - page = compound_head(page); + if (folio_test_large(folio)) { + struct folio *f; /* * Check if we have dealt with the compound page * already */ - list_for_each_entry(p, compound_pagelist, lru) { - if (page == p) + list_for_each_entry(f, compound_pagelist, lru) { + if (folio == f) goto next; } } @@ -616,7 +612,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, * is needed to serialize against split_huge_page * when invoked from the VM. */ - if (!trylock_page(page)) { + if (!folio_trylock(folio)) { result = SCAN_PAGE_LOCK; goto out; } @@ -632,8 +628,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, * but not from this process. The other process cannot write to * the page, only trigger CoW. */ - if (!is_refcount_suitable(page)) { - unlock_page(page); + if (!is_refcount_suitable(folio)) { + folio_unlock(folio); result = SCAN_PAGE_COUNT; goto out; } @@ -642,27 +638,27 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, * Isolate the page to avoid collapsing an hugepage * currently in use by the VM. */ - if (!isolate_lru_page(page)) { - unlock_page(page); + if (!folio_isolate_lru(folio)) { + folio_unlock(folio); result = SCAN_DEL_PAGE_LRU; goto out; } - mod_node_page_state(page_pgdat(page), - NR_ISOLATED_ANON + page_is_file_lru(page), - compound_nr(page)); - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(PageLRU(page), page); + node_stat_mod_folio(folio, + NR_ISOLATED_ANON + folio_is_file_lru(folio), + folio_nr_pages(folio)); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - if (PageCompound(page)) - list_add_tail(&page->lru, compound_pagelist); + if (folio_test_large(folio)) + list_add_tail(&folio->lru, compound_pagelist); next: /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && - (pte_young(pteval) || page_is_young(page) || - PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, + (pte_young(pteval) || folio_test_young(folio) || + folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; @@ -676,13 +672,13 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; - trace_mm_collapse_huge_page_isolate(page, none_or_zero, + trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } out: release_pte_pages(pte, _pte, compound_pagelist); - trace_mm_collapse_huge_page_isolate(page, none_or_zero, + trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } @@ -693,6 +689,7 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte, spinlock_t *ptl, struct list_head *compound_pagelist) { + struct folio *src_folio; struct page *src_page; struct page *tmp; pte_t *_pte; @@ -714,17 +711,18 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte, } } else { src_page = pte_page(pteval); - if (!PageCompound(src_page)) - release_pte_page(src_page); + src_folio = page_folio(src_page); + if (!folio_test_large(src_folio)) + release_pte_folio(src_folio); /* * ptl mostly unnecessary, but preempt has to * be disabled to update the per-cpu stats - * inside page_remove_rmap(). + * inside folio_remove_rmap_pte(). */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); add_reliable_page_counter(src_page, vma->vm_mm, 1); - page_remove_rmap(src_page, vma, false); + folio_remove_rmap_pte(src_folio, src_page, vma); spin_unlock(ptl); free_page_and_swap_cache(src_page); } @@ -897,16 +895,16 @@ static int hpage_collapse_find_target_node(struct collapse_control *cc) } #endif -static bool hpage_collapse_alloc_page(struct page **hpage, gfp_t gfp, int node, +static bool hpage_collapse_alloc_folio(struct folio **folio, gfp_t gfp, int node, nodemask_t *nmask) { - *hpage = __alloc_pages(gfp, HPAGE_PMD_ORDER, node, nmask); - if (unlikely(!*hpage)) { + *folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, nmask); + + if (unlikely(!*folio)) { count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return false; } - folio_prep_large_rmappable((struct folio *)*hpage); count_vm_event(THP_COLLAPSE_ALLOC); return true; } @@ -1076,17 +1074,20 @@ static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm, if (cc->reliable) gfp |= GFP_RELIABLE; - if (!hpage_collapse_alloc_page(hpage, gfp, node, &cc->alloc_nmask)) + if (!hpage_collapse_alloc_folio(&folio, gfp, node, &cc->alloc_nmask)) { + *hpage = NULL; return SCAN_ALLOC_HUGE_PAGE_FAIL; + } - folio = page_folio(*hpage); if (unlikely(mem_cgroup_charge(folio, mm, gfp))) { folio_put(folio); *hpage = NULL; return SCAN_CGROUP_CHARGE_FAIL; } - count_memcg_page_event(*hpage, THP_COLLAPSE_ALLOC); + count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1); + + *hpage = folio_page(folio, 0); return SCAN_SUCCEED; } @@ -1261,6 +1262,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, int result = SCAN_FAIL, referenced = 0; int none_or_zero = 0, shared = 0; struct page *page = NULL; + struct folio *folio = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE, unmapped = 0; @@ -1348,29 +1350,28 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, } } - page = compound_head(page); - + folio = page_folio(page); /* * Record which node the original page is from and save this * information to cc->node_load[]. * Khugepaged will allocate hugepage from the node has the max * hit record. */ - node = page_to_nid(page); + node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; goto out_unmap; } cc->node_load[node]++; - if (!PageLRU(page)) { + if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; goto out_unmap; } - if (PageLocked(page)) { + if (folio_test_locked(folio)) { result = SCAN_PAGE_LOCK; goto out_unmap; } - if (!PageAnon(page)) { + if (!folio_test_anon(folio)) { result = SCAN_PAGE_ANON; goto out_unmap; } @@ -1390,7 +1391,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, * has excessive GUP pins (i.e. 512). Anyway the same check * will be done again later the risk seems low. */ - if (!is_refcount_suitable(page)) { + if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; goto out_unmap; } @@ -1400,8 +1401,8 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && - (pte_young(pteval) || page_is_young(page) || - PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, + (pte_young(pteval) || folio_test_young(folio) || + folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; @@ -1426,7 +1427,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, *mmap_locked = false; } out: - trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced, + trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced, none_or_zero, result, unmapped); return result; } @@ -1496,7 +1497,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool notified = false; unsigned long haddr = addr & HPAGE_PMD_MASK; struct vm_area_struct *vma = vma_lookup(mm, haddr); - struct page *hpage; + struct folio *folio; pte_t *start_pte, *pte; pmd_t *pmd, pgt_pmd; spinlock_t *pml = NULL, *ptl; @@ -1530,19 +1531,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP; - hpage = find_lock_page(vma->vm_file->f_mapping, + folio = filemap_lock_folio(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); - if (!hpage) + if (IS_ERR(folio)) return SCAN_PAGE_NULL; - if (!PageHead(hpage)) { - result = SCAN_FAIL; - goto drop_hpage; - } - - if (compound_order(hpage) != HPAGE_PMD_ORDER) { + if (folio_order(folio) != HPAGE_PMD_ORDER) { result = SCAN_PAGE_COMPOUND; - goto drop_hpage; + goto drop_folio; } result = find_pmd_or_thp_or_none(mm, haddr, &pmd); @@ -1556,13 +1552,13 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, */ goto maybe_install_pmd; default: - goto drop_hpage; + goto drop_folio; } result = SCAN_FAIL; start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ - goto drop_hpage; + goto drop_folio; /* step 1: check all mapped PTEs are to the right huge page */ for (i = 0, addr = haddr, pte = start_pte; @@ -1587,7 +1583,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. */ - if (hpage + i != page) + if (folio_page(folio, i) != page) goto abort; } @@ -1602,7 +1598,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, * page_table_lock) ptl nests inside pml. The less time we hold pml, * the better; but userfaultfd's mfill_atomic_pte() on a private VMA * inserts a valid as-if-COWed PTE without even looking up page cache. - * So page lock of hpage does not protect from it, so we must not drop + * So page lock of folio does not protect from it, so we must not drop * ptl before pgt_pmd is removed, so uffd private needs pml taken now. */ if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED)) @@ -1626,7 +1622,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, continue; /* * We dropped ptl after the first scan, to do the mmu_notifier: - * page lock stops more PTEs of the hpage being faulted in, but + * page lock stops more PTEs of the folio being faulted in, but * does not stop write faults COWing anon copies from existing * PTEs; and does not stop those being swapped out or migrated. */ @@ -1635,7 +1631,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, goto abort; } page = vm_normal_page(vma, addr, ptent); - if (hpage + i != page) + if (folio_page(folio, i) != page) goto abort; /* @@ -1644,7 +1640,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, * PTE dirty? Shmem page is already dirty; file is read-only. */ ptep_clear(mm, addr, pte); - page_remove_rmap(page, vma, false); + folio_remove_rmap_pte(folio, page, vma); add_reliable_page_counter(page, mm, -1); nr_ptes++; } @@ -1655,8 +1651,8 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, /* step 3: set proper refcount and mm_counters. */ if (nr_ptes) { - page_ref_sub(hpage, nr_ptes); - add_mm_counter(mm, mm_counter_file(hpage), -nr_ptes); + folio_ref_sub(folio, nr_ptes); + add_mm_counter(mm, mm_counter_file(&folio->page), -nr_ptes); } /* step 4: remove empty page table */ @@ -1680,14 +1676,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, maybe_install_pmd: /* step 5: install pmd entry */ result = install_pmd - ? set_huge_pmd(vma, haddr, pmd, hpage) + ? set_huge_pmd(vma, haddr, pmd, &folio->page) : SCAN_SUCCEED; - goto drop_hpage; + goto drop_folio; abort: if (nr_ptes) { flush_tlb_mm(mm); - page_ref_sub(hpage, nr_ptes); - add_mm_counter(mm, mm_counter_file(hpage), -nr_ptes); + folio_ref_sub(folio, nr_ptes); + add_mm_counter(mm, mm_counter_file(&folio->page), -nr_ptes); } if (start_pte) pte_unmap_unlock(start_pte, ptl); @@ -1695,9 +1691,9 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, spin_unlock(pml); if (notified) mmu_notifier_invalidate_range_end(&range); -drop_hpage: - unlock_page(hpage); - put_page(hpage); +drop_folio: + folio_unlock(folio); + folio_put(folio); return result; } diff --git a/mm/ksm.c b/mm/ksm.c index da8416e2debe8a76d52faf53600a49313d8ab9b9..94207293e6fc9949135b1770d68ebba3735de683 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1148,8 +1148,9 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, goto out_unlock; } - /* See page_try_share_anon_rmap(): clear PTE first. */ - if (anon_exclusive && page_try_share_anon_rmap(page)) { + /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ + if (anon_exclusive && + folio_try_share_anon_rmap_pte(page_folio(page), page)) { set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } @@ -1186,6 +1187,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, static int replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage, pte_t orig_pte) { + struct folio *kfolio = page_folio(kpage); struct mm_struct *mm = vma->vm_mm; struct folio *folio; pmd_t *pmd; @@ -1225,16 +1227,17 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, goto out_mn; } VM_BUG_ON_PAGE(PageAnonExclusive(page), page); - VM_BUG_ON_PAGE(PageAnon(kpage) && PageAnonExclusive(kpage), kpage); + VM_BUG_ON_FOLIO(folio_test_anon(kfolio) && PageAnonExclusive(kpage), + kfolio); /* * No need to check ksm_use_zero_pages here: we can only have a * zero_page here if ksm_use_zero_pages was enabled already. */ if (!is_zero_pfn(page_to_pfn(kpage))) { - get_page(kpage); + folio_get(kfolio); add_reliable_page_counter(kpage, mm, 1); - page_add_anon_rmap(kpage, vma, addr, RMAP_NONE); + folio_add_anon_rmap_pte(kfolio, kpage, vma, addr, RMAP_NONE); newpte = mk_pte(kpage, vma->vm_page_prot); } else { /* @@ -1266,7 +1269,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, add_reliable_page_counter(page, mm, -1); folio = page_folio(page); - page_remove_rmap(page, vma, false); + folio_remove_rmap_pte(folio, page, vma); if (!folio_mapped(folio)) folio_free_swap(folio); folio_put(folio); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f5ec4750feeffbc1758347c32740a8b83d77ec6d..c9372bae352473b75e6f71de3819f507feb26af4 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2328,8 +2328,8 @@ int memory_failure(unsigned long pfn, int flags) * We use page flags to determine what action should be taken, but * the flags can be modified by the error containment action. One * example is an mlocked page, where PG_mlocked is cleared by - * page_remove_rmap() in try_to_unmap_one(). So to determine page status - * correctly, we save a copy of the page flags at this time. + * folio_remove_rmap_*() in try_to_unmap_one(). So to determine page + * status correctly, we save a copy of the page flags at this time. */ page_flags = p->flags; diff --git a/mm/memory.c b/mm/memory.c index 13012c3294b43ff71eb0874c8d612b9ded20d9e2..031ff37a91fbad7516f91b4bd1a96e471ccc8b9d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -713,6 +713,7 @@ static void restore_exclusive_pte(struct vm_area_struct *vma, struct page *page, unsigned long address, pte_t *ptep) { + struct folio *folio = page_folio(page); pte_t orig_pte; pte_t pte; swp_entry_t entry; @@ -728,14 +729,15 @@ static void restore_exclusive_pte(struct vm_area_struct *vma, else if (is_writable_device_exclusive_entry(entry)) pte = maybe_mkwrite(pte_mkdirty(pte), vma); - VM_BUG_ON(pte_write(pte) && !(PageAnon(page) && PageAnonExclusive(page))); + VM_BUG_ON_FOLIO(pte_write(pte) && (!folio_test_anon(folio) && + PageAnonExclusive(page)), folio); /* * No need to take a page reference as one was already * created when the swap entry was made. */ - if (PageAnon(page)) - page_add_anon_rmap(page, vma, address, RMAP_NONE); + if (folio_test_anon(folio)) + folio_add_anon_rmap_pte(folio, page, vma, address, RMAP_NONE); else /* * Currently device exclusive access only supports anonymous @@ -786,6 +788,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, unsigned long vm_flags = dst_vma->vm_flags; pte_t orig_pte = ptep_get(src_pte); pte_t pte = orig_pte; + struct folio *folio; struct page *page; swp_entry_t entry = pte_to_swp_entry(orig_pte); @@ -830,6 +833,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, } } else if (is_device_private_entry(entry)) { page = pfn_swap_entry_to_page(entry); + folio = page_folio(page); /* * Update rss count even for unaddressable pages, as @@ -840,10 +844,10 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, * for unaddressable pages, at some point. But for now * keep things as they are. */ - get_page(page); + folio_get(folio); rss[mm_counter(page)]++; /* Cannot fail as these pages cannot get pinned. */ - BUG_ON(page_try_dup_anon_rmap(page, false, src_vma)); + folio_try_dup_anon_rmap_pte(folio, page, src_vma); /* * We do not preserve soft-dirty information, because so @@ -957,7 +961,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, * future. */ folio_get(folio); - if (unlikely(page_try_dup_anon_rmap(page, false, src_vma))) { + if (unlikely(folio_try_dup_anon_rmap_pte(folio, page, src_vma))) { /* Page may be pinned, we have to copy. */ folio_put(folio); return copy_present_page(dst_vma, src_vma, dst_pte, src_pte, @@ -966,7 +970,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, rss[MM_ANONPAGES]++; } else if (page) { folio_get(folio); - page_dup_file_rmap(page, false); + folio_dup_file_rmap_pte(folio, page); rss[mm_counter_file(page)]++; add_reliable_folio_counter(folio, dst_vma->vm_mm, 1); } @@ -1431,6 +1435,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, arch_enter_lazy_mmu_mode(); do { pte_t ptent = ptep_get(pte); + struct folio *folio; struct page *page; if (pte_none(ptent)) @@ -1456,22 +1461,23 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, continue; } + folio = page_folio(page); delay_rmap = 0; - if (!PageAnon(page)) { + if (!folio_test_anon(folio)) { if (pte_dirty(ptent)) { - set_page_dirty(page); + folio_mark_dirty(folio); if (tlb_delay_rmap(tlb)) { delay_rmap = 1; force_flush = 1; } } if (pte_young(ptent) && likely(vma_has_recency(vma))) - mark_page_accessed(page); + folio_mark_accessed(folio); } rss[mm_counter(page)]--; add_reliable_page_counter(page, mm, -1); if (!delay_rmap) { - page_remove_rmap(page, vma, false); + folio_remove_rmap_pte(folio, page, vma); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); } @@ -1487,6 +1493,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, if (is_device_private_entry(entry) || is_device_exclusive_entry(entry)) { page = pfn_swap_entry_to_page(entry); + folio = page_folio(page); if (unlikely(!should_zap_page(details, page))) continue; /* @@ -1499,8 +1506,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, rss[mm_counter(page)]--; add_reliable_page_counter(page, mm, -1); if (is_device_private_entry(entry)) - page_remove_rmap(page, vma, false); - put_page(page); + folio_remove_rmap_pte(folio, page, vma); + folio_put(folio); } else if (!non_swap_entry(entry)) { /* Genuine swap entry, hence a private anon page */ if (!should_zap_cows(details)) @@ -1859,12 +1866,14 @@ static int validate_page_before_insert(struct page *page) static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { + struct folio *folio = page_folio(page); + if (!pte_none(ptep_get(pte))) return -EBUSY; /* Ok, finally just insert the thing.. */ - get_page(page); + folio_get(folio); inc_mm_counter(vma->vm_mm, mm_counter_file(page)); - page_add_file_rmap(page, vma, false); + folio_add_file_rmap_pte(folio, page, vma); set_pte_at(vma->vm_mm, addr, pte, mk_pte(page, prot)); return 0; } @@ -3223,10 +3232,10 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * threads. * * The critical issue is to order this - * page_remove_rmap with the ptp_clear_flush above. - * Those stores are ordered by (if nothing else,) + * folio_remove_rmap_pte() with the ptp_clear_flush + * above. Those stores are ordered by (if nothing else,) * the barrier present in the atomic_add_negative - * in page_remove_rmap. + * in folio_remove_rmap_pte(); * * Then the TLB flush in ptep_clear_flush ensures that * no process can access the old page before the @@ -3235,7 +3244,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ - page_remove_rmap(vmf->page, vma, false); + folio_remove_rmap_pte(old_folio, vmf->page, vma); } /* Free the old page.. */ @@ -4083,7 +4092,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) page_add_new_anon_rmap(page, vma, vmf->address); folio_add_lru_vma(folio, vma); } else { - page_add_anon_rmap(page, vma, vmf->address, rmap_flags); + folio_add_anon_rmap_pte(folio, page, vma, vmf->address, + rmap_flags); } VM_BUG_ON(!folio_test_anon(folio) || @@ -4425,6 +4435,7 @@ static void deposit_prealloc_pte(struct vm_fault *vmf) vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { + struct folio *folio = page_folio(page); struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; @@ -4434,8 +4445,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return ret; - page = compound_head(page); - if (compound_order(page) != HPAGE_PMD_ORDER) + if (page != &folio->page || folio_order(folio) != HPAGE_PMD_ORDER) return ret; /* @@ -4444,7 +4454,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) * check. This kind of THP just can be PTE mapped. Access to * the corrupted subpage should trigger SIGBUS as expected. */ - if (unlikely(PageHasHWPoisoned(page))) + if (unlikely(folio_test_has_hwpoisoned(folio))) return ret; /* @@ -4469,7 +4479,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR); add_reliable_page_counter(page, vma->vm_mm, HPAGE_PMD_NR); - page_add_file_rmap(page, vma, true); + folio_add_file_rmap_pmd(folio, page, vma); /* * deposit and withdraw with pmd lock held @@ -4533,7 +4543,7 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio, folio_add_lru_vma(folio, vma); } else { add_mm_counter(vma->vm_mm, mm_counter_file(page), nr); - folio_add_file_rmap_range(folio, page, nr, vma, false); + folio_add_file_rmap_ptes(folio, page, nr, vma); } set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr); diff --git a/mm/migrate.c b/mm/migrate.c index 1e88f81d23694618899890ab68f911fad9616263..29cb7617037813b104f50b40d2507581529626b9 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -249,20 +249,20 @@ static bool remove_migration_pte(struct folio *folio, pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (folio_test_anon(folio)) - hugepage_add_anon_rmap(folio, vma, pvmw.address, - rmap_flags); + hugetlb_add_anon_rmap(folio, vma, pvmw.address, + rmap_flags); else - page_dup_file_rmap(new, true); + hugetlb_add_file_rmap(folio); set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte, psize); } else #endif { if (folio_test_anon(folio)) - page_add_anon_rmap(new, vma, pvmw.address, - rmap_flags); + folio_add_anon_rmap_pte(folio, new, vma, + pvmw.address, rmap_flags); else - page_add_file_rmap(new, vma, false); + folio_add_file_rmap_pte(folio, new, vma); set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); } if (vma->vm_flags & VM_LOCKED) diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 2e5bce2f1cb9eb249c174f02c974c6a53b5f0ddb..40032b85ab4be5bd8a7864f8d9eb849a337addc4 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -107,6 +107,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, for (; addr < end; addr += PAGE_SIZE, ptep++) { unsigned long mpfn = 0, pfn; + struct folio *folio; struct page *page; swp_entry_t entry; pte_t pte; @@ -168,41 +169,43 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, } /* - * By getting a reference on the page we pin it and that blocks + * By getting a reference on the folio we pin it and that blocks * any kind of migration. Side effect is that it "freezes" the * pte. * - * We drop this reference after isolating the page from the lru - * for non device page (device page are not on the lru and thus + * We drop this reference after isolating the folio from the lru + * for non device folio (device folio are not on the lru and thus * can't be dropped from it). */ - get_page(page); + folio = page_folio(page); + folio_get(folio); /* - * We rely on trylock_page() to avoid deadlock between + * We rely on folio_trylock() to avoid deadlock between * concurrent migrations where each is waiting on the others - * page lock. If we can't immediately lock the page we fail this + * folio lock. If we can't immediately lock the folio we fail this * migration as it is only best effort anyway. * - * If we can lock the page it's safe to set up a migration entry - * now. In the common case where the page is mapped once in a + * If we can lock the folio it's safe to set up a migration entry + * now. In the common case where the folio is mapped once in a * single process setting up the migration entry now is an * optimisation to avoid walking the rmap later with * try_to_migrate(). */ - if (trylock_page(page)) { + if (folio_trylock(folio)) { bool anon_exclusive; pte_t swp_pte; flush_cache_page(vma, addr, pte_pfn(pte)); - anon_exclusive = PageAnon(page) && PageAnonExclusive(page); + anon_exclusive = folio_test_anon(folio) && + PageAnonExclusive(page); if (anon_exclusive) { pte = ptep_clear_flush(vma, addr, ptep); - if (page_try_share_anon_rmap(page)) { + if (folio_try_share_anon_rmap_pte(folio, page)) { set_pte_at(mm, addr, ptep, pte); - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); mpfn = 0; goto next; } @@ -214,7 +217,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pte)) - folio_mark_dirty(page_folio(page)); + folio_mark_dirty(folio); /* Setup special migration page table entry */ if (mpfn & MIGRATE_PFN_WRITE) @@ -248,16 +251,16 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, /* * This is like regular unmap: we remove the rmap and - * drop page refcount. Page won't be freed, as we took - * a reference just above. + * drop the folio refcount. The folio won't be freed, as + * we took a reference just above. */ - page_remove_rmap(page, vma, false); - put_page(page); + folio_remove_rmap_pte(folio, page, vma); + folio_put(folio); if (pte_present(pte)) unmapped++; } else { - put_page(page); + folio_put(folio); mpfn = 0; } diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 4f559f4ddd217180362b9af41727998aad3c6d46..604ddf08affed2063923549bc503f0e18c6fd34e 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -55,7 +55,7 @@ static void tlb_flush_rmap_batch(struct mmu_gather_batch *batch, struct vm_area_ if (encoded_page_flags(enc)) { struct page *page = encoded_page_ptr(enc); - page_remove_rmap(page, vma, false); + folio_remove_rmap_pte(page_folio(page), page, vma); } } } diff --git a/mm/rmap.c b/mm/rmap.c index 5c3d20916949b6fd0cf272dd1d25721b1ee61a0f..73f2b3a33158bae01a8c07fbe1e050949d865dc0 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -470,7 +470,7 @@ void __init anon_vma_init(void) /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * - * Since there is no serialization what so ever against page_remove_rmap() + * Since there is no serialization what so ever against folio_remove_rmap_*() * the best this function can do is return a refcount increased anon_vma * that might have been relevant to this page. * @@ -487,7 +487,7 @@ void __init anon_vma_init(void) * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from - * page_remove_rmap() that the anon_vma pointer from page->mapping is valid + * folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. */ @@ -1127,6 +1127,48 @@ int folio_total_mapcount(struct folio *folio) return mapcount; } +static __always_inline unsigned int __folio_add_rmap(struct folio *folio, + struct page *page, int nr_pages, enum rmap_level level, + int *nr_pmdmapped) +{ + atomic_t *mapped = &folio->_nr_pages_mapped; + int first, nr = 0; + + __folio_rmap_sanity_checks(folio, page, nr_pages, level); + + switch (level) { + case RMAP_LEVEL_PTE: + do { + first = atomic_inc_and_test(&page->_mapcount); + if (first && folio_test_large(folio)) { + first = atomic_inc_return_relaxed(mapped); + first = (first < ENTIRELY_MAPPED); + } + + if (first) + nr++; + } while (page++, --nr_pages > 0); + break; + case RMAP_LEVEL_PMD: + first = atomic_inc_and_test(&folio->_entire_mapcount); + if (first) { + nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped); + if (likely(nr < ENTIRELY_MAPPED + ENTIRELY_MAPPED)) { + *nr_pmdmapped = folio_nr_pages(folio); + nr = *nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); + /* Raced ahead of a remove and another add? */ + if (unlikely(nr < 0)) + nr = 0; + } else { + /* Raced ahead of a remove of ENTIRELY_MAPPED */ + nr = 0; + } + } + break; + } + return nr; +} + /** * folio_move_anon_rmap - move a folio to our anon_vma * @folio: The folio to move to our anon_vma @@ -1198,7 +1240,7 @@ static void __page_check_anon_rmap(struct folio *folio, struct page *page, * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. * - * We have exclusion against page_add_anon_rmap because the caller + * We have exclusion against folio_add_anon_rmap_*() because the caller * always holds the page locked. * * We have exclusion against page_add_new_anon_rmap because those pages @@ -1211,54 +1253,13 @@ static void __page_check_anon_rmap(struct folio *folio, struct page *page, page); } -/** - * page_add_anon_rmap - add pte mapping to an anonymous page - * @page: the page to add the mapping to - * @vma: the vm area in which the mapping is added - * @address: the user virtual address mapped - * @flags: the rmap flags - * - * The caller needs to hold the pte lock, and the page must be locked in - * the anon_vma case: to serialize mapping,index checking after setting, - * and to ensure that PageAnon is not being upgraded racily to PageKsm - * (but PageKsm is never downgraded to PageAnon). - */ -void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, - unsigned long address, rmap_t flags) +static __always_inline void __folio_add_anon_rmap(struct folio *folio, + struct page *page, int nr_pages, struct vm_area_struct *vma, + unsigned long address, rmap_t flags, enum rmap_level level) { - struct folio *folio = page_folio(page); - atomic_t *mapped = &folio->_nr_pages_mapped; - int nr = 0, nr_pmdmapped = 0; - bool compound = flags & RMAP_COMPOUND; - bool first; - - /* Is page being mapped by PTE? Is this its first map to be added? */ - if (likely(!compound)) { - first = atomic_inc_and_test(&page->_mapcount); - nr = first; - if (first && folio_test_large(folio)) { - nr = atomic_inc_return_relaxed(mapped); - nr = (nr < COMPOUND_MAPPED); - } - } else if (folio_test_pmd_mappable(folio)) { - /* That test is redundant: it's for safety or to optimize out */ - - first = atomic_inc_and_test(&folio->_entire_mapcount); - if (first) { - nr = atomic_add_return_relaxed(COMPOUND_MAPPED, mapped); - if (likely(nr < COMPOUND_MAPPED + COMPOUND_MAPPED)) { - nr_pmdmapped = folio_nr_pages(folio); - nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); - /* Raced ahead of a remove and another add? */ - if (unlikely(nr < 0)) - nr = 0; - } else { - /* Raced ahead of a remove of COMPOUND_MAPPED */ - nr = 0; - } - } - } + int i, nr, nr_pmdmapped = 0; + nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped); if (nr_pmdmapped) __lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr_pmdmapped); if (nr) @@ -1272,18 +1273,34 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, * folio->index right when not given the address of the head * page. */ - VM_WARN_ON_FOLIO(folio_test_large(folio) && !compound, folio); + VM_WARN_ON_FOLIO(folio_test_large(folio) && + level != RMAP_LEVEL_PMD, folio); __folio_set_anon(folio, vma, address, !!(flags & RMAP_EXCLUSIVE)); } else if (likely(!folio_test_ksm(folio))) { __page_check_anon_rmap(folio, page, vma, address); } - if (flags & RMAP_EXCLUSIVE) - SetPageAnonExclusive(page); - /* While PTE-mapping a THP we have a PMD and a PTE mapping. */ - VM_WARN_ON_FOLIO((atomic_read(&page->_mapcount) > 0 || - (folio_test_large(folio) && folio_entire_mapcount(folio) > 1)) && - PageAnonExclusive(page), folio); + + if (flags & RMAP_EXCLUSIVE) { + switch (level) { + case RMAP_LEVEL_PTE: + for (i = 0; i < nr_pages; i++) + SetPageAnonExclusive(page + i); + break; + case RMAP_LEVEL_PMD: + SetPageAnonExclusive(page); + break; + } + } + for (i = 0; i < nr_pages; i++) { + struct page *cur_page = page + i; + + /* While PTE-mapping a THP we have a PMD and a PTE mapping. */ + VM_WARN_ON_FOLIO((atomic_read(&cur_page->_mapcount) > 0 || + (folio_test_large(folio) && + folio_entire_mapcount(folio) > 1)) && + PageAnonExclusive(cur_page), folio); + } /* * For large folio, only mlock it if it's fully mapped to VMA. It's @@ -1295,13 +1312,61 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, mlock_vma_folio(folio, vma); } +/** + * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio + * @folio: The folio to add the mappings to + * @page: The first page to add + * @nr_pages: The number of pages which will be mapped + * @vma: The vm area in which the mappings are added + * @address: The user virtual address of the first page to map + * @flags: The rmap flags + * + * The page range of folio is defined by [first_page, first_page + nr_pages) + * + * The caller needs to hold the page table lock, and the page must be locked in + * the anon_vma case: to serialize mapping,index checking after setting, + * and to ensure that an anon folio is not being upgraded racily to a KSM folio + * (but KSM folios are never downgraded). + */ +void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page, + int nr_pages, struct vm_area_struct *vma, unsigned long address, + rmap_t flags) +{ + __folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags, + RMAP_LEVEL_PTE); +} + +/** + * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio + * @folio: The folio to add the mapping to + * @page: The first page to add + * @vma: The vm area in which the mapping is added + * @address: The user virtual address of the first page to map + * @flags: The rmap flags + * + * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR) + * + * The caller needs to hold the page table lock, and the page must be locked in + * the anon_vma case: to serialize mapping,index checking after setting. + */ +void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page, + struct vm_area_struct *vma, unsigned long address, rmap_t flags) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + __folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags, + RMAP_LEVEL_PMD); +#else + WARN_ON_ONCE(true); +#endif +} + /** * folio_add_new_anon_rmap - Add mapping to a new anonymous folio. * @folio: The folio to add the mapping to. * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * - * Like page_add_anon_rmap() but must only be called on *new* folios. + * Like folio_add_anon_rmap_*() but must only be called on *new* folios. * This means the inc-and-test can be bypassed. * The folio does not have to be locked. * @@ -1313,6 +1378,7 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, { int nr = folio_nr_pages(folio); + VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); VM_BUG_ON_VMA(address < vma->vm_start || address + (nr << PAGE_SHIFT) > vma->vm_end, vma); __folio_set_swapbacked(folio); @@ -1337,7 +1403,7 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, } else { /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); - atomic_set(&folio->_nr_pages_mapped, COMPOUND_MAPPED); + atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED); SetPageAnonExclusive(&folio->page); __lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr); } @@ -1345,145 +1411,102 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr); } -/** - * folio_add_file_rmap_range - add pte mapping to page range of a folio - * @folio: The folio to add the mapping to - * @page: The first page to add - * @nr_pages: The number of pages which will be mapped - * @vma: the vm area in which the mapping is added - * @compound: charge the page as compound or small page - * - * The page range of folio is defined by [first_page, first_page + nr_pages) - * - * The caller needs to hold the pte lock. - */ -void folio_add_file_rmap_range(struct folio *folio, struct page *page, - unsigned int nr_pages, struct vm_area_struct *vma, - bool compound) +static __always_inline void __folio_add_file_rmap(struct folio *folio, + struct page *page, int nr_pages, struct vm_area_struct *vma, + enum rmap_level level) { - atomic_t *mapped = &folio->_nr_pages_mapped; - unsigned int nr_pmdmapped = 0, first; - int nr = 0; - - VM_WARN_ON_FOLIO(compound && !folio_test_pmd_mappable(folio), folio); - - /* Is page being mapped by PTE? Is this its first map to be added? */ - if (likely(!compound)) { - do { - first = atomic_inc_and_test(&page->_mapcount); - if (first && folio_test_large(folio)) { - first = atomic_inc_return_relaxed(mapped); - first = (first < COMPOUND_MAPPED); - } + int nr, nr_pmdmapped = 0; - if (first) - nr++; - } while (page++, --nr_pages > 0); - } else if (folio_test_pmd_mappable(folio)) { - /* That test is redundant: it's for safety or to optimize out */ - - first = atomic_inc_and_test(&folio->_entire_mapcount); - if (first) { - nr = atomic_add_return_relaxed(COMPOUND_MAPPED, mapped); - if (likely(nr < COMPOUND_MAPPED + COMPOUND_MAPPED)) { - nr_pmdmapped = folio_nr_pages(folio); - nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); - /* Raced ahead of a remove and another add? */ - if (unlikely(nr < 0)) - nr = 0; - } else { - /* Raced ahead of a remove of COMPOUND_MAPPED */ - nr = 0; - } - } - } + VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); + nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped); if (nr_pmdmapped) __lruvec_stat_mod_folio(folio, folio_test_swapbacked(folio) ? NR_SHMEM_PMDMAPPED : NR_FILE_PMDMAPPED, nr_pmdmapped); if (nr) __lruvec_stat_mod_folio(folio, NR_FILE_MAPPED, nr); - /* See comments in page_add_anon_rmap() */ + /* See comments in folio_add_anon_rmap_*() */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); } /** - * page_add_file_rmap - add pte mapping to a file page - * @page: the page to add the mapping to - * @vma: the vm area in which the mapping is added - * @compound: charge the page as compound or small page + * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio + * @folio: The folio to add the mappings to + * @page: The first page to add + * @nr_pages: The number of pages that will be mapped using PTEs + * @vma: The vm area in which the mappings are added + * + * The page range of the folio is defined by [page, page + nr_pages) * - * The caller needs to hold the pte lock. + * The caller needs to hold the page table lock. */ -void page_add_file_rmap(struct page *page, struct vm_area_struct *vma, - bool compound) +void folio_add_file_rmap_ptes(struct folio *folio, struct page *page, + int nr_pages, struct vm_area_struct *vma) { - struct folio *folio = page_folio(page); - unsigned int nr_pages; - - VM_WARN_ON_ONCE_PAGE(compound && !PageTransHuge(page), page); - - if (likely(!compound)) - nr_pages = 1; - else - nr_pages = folio_nr_pages(folio); - - folio_add_file_rmap_range(folio, page, nr_pages, vma, compound); + __folio_add_file_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE); } /** - * page_remove_rmap - take down pte mapping from a page - * @page: page to remove mapping from - * @vma: the vm area from which the mapping is removed - * @compound: uncharge the page as compound or small page + * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio + * @folio: The folio to add the mapping to + * @page: The first page to add + * @vma: The vm area in which the mapping is added + * + * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * - * The caller needs to hold the pte lock. + * The caller needs to hold the page table lock. */ -void page_remove_rmap(struct page *page, struct vm_area_struct *vma, - bool compound) +void folio_add_file_rmap_pmd(struct folio *folio, struct page *page, + struct vm_area_struct *vma) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + __folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD); +#else + WARN_ON_ONCE(true); +#endif +} + +static __always_inline void __folio_remove_rmap(struct folio *folio, + struct page *page, int nr_pages, struct vm_area_struct *vma, + enum rmap_level level) { - struct folio *folio = page_folio(page); atomic_t *mapped = &folio->_nr_pages_mapped; - int nr = 0, nr_pmdmapped = 0; - bool last; + int last, nr = 0, nr_pmdmapped = 0; enum node_stat_item idx; - VM_BUG_ON_PAGE(compound && !PageHead(page), page); - - /* Hugetlb pages are not counted in NR_*MAPPED */ - if (unlikely(folio_test_hugetlb(folio))) { - /* hugetlb pages are always mapped with pmds */ - atomic_dec(&folio->_entire_mapcount); - return; - } + __folio_rmap_sanity_checks(folio, page, nr_pages, level); - /* Is page being unmapped by PTE? Is this its last map to be removed? */ - if (likely(!compound)) { - last = atomic_add_negative(-1, &page->_mapcount); - nr = last; - if (last && folio_test_large(folio)) { - nr = atomic_dec_return_relaxed(mapped); - nr = (nr < COMPOUND_MAPPED); - } - } else if (folio_test_pmd_mappable(folio)) { - /* That test is redundant: it's for safety or to optimize out */ + switch (level) { + case RMAP_LEVEL_PTE: + do { + last = atomic_add_negative(-1, &page->_mapcount); + if (last && folio_test_large(folio)) { + last = atomic_dec_return_relaxed(mapped); + last = (last < ENTIRELY_MAPPED); + } + if (last) + nr++; + } while (page++, --nr_pages > 0); + break; + case RMAP_LEVEL_PMD: last = atomic_add_negative(-1, &folio->_entire_mapcount); if (last) { - nr = atomic_sub_return_relaxed(COMPOUND_MAPPED, mapped); - if (likely(nr < COMPOUND_MAPPED)) { + nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped); + if (likely(nr < ENTIRELY_MAPPED)) { nr_pmdmapped = folio_nr_pages(folio); nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of another remove and an add? */ if (unlikely(nr < 0)) nr = 0; } else { - /* An add of COMPOUND_MAPPED raced ahead */ + /* An add of ENTIRELY_MAPPED raced ahead */ nr = 0; } } + break; } if (nr_pmdmapped) { @@ -1505,13 +1528,13 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma, * is still mapped. */ if (folio_test_large(folio) && folio_test_anon(folio)) - if (!compound || nr < nr_pmdmapped) + if (level == RMAP_LEVEL_PTE || nr < nr_pmdmapped) deferred_split_folio(folio); } /* * It would be tidy to reset folio_test_anon mapping when fully - * unmapped, but that might overwrite a racing page_add_anon_rmap + * unmapped, but that might overwrite a racing folio_add_anon_rmap_*() * which increments mapcount after us but sets mapping before us: * so leave the reset to free_pages_prepare, and remember that * it's only reliable while mapped. @@ -1520,6 +1543,43 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma, munlock_vma_folio(folio, vma); } +/** + * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio + * @folio: The folio to remove the mappings from + * @page: The first page to remove + * @nr_pages: The number of pages that will be removed from the mapping + * @vma: The vm area from which the mappings are removed + * + * The page range of the folio is defined by [page, page + nr_pages) + * + * The caller needs to hold the page table lock. + */ +void folio_remove_rmap_ptes(struct folio *folio, struct page *page, + int nr_pages, struct vm_area_struct *vma) +{ + __folio_remove_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE); +} + +/** + * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio + * @folio: The folio to remove the mapping from + * @page: The first page to remove + * @vma: The vm area from which the mapping is removed + * + * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) + * + * The caller needs to hold the page table lock. + */ +void folio_remove_rmap_pmd(struct folio *folio, struct page *page, + struct vm_area_struct *vma) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + __folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD); +#else + WARN_ON_ONCE(true); +#endif +} + /* * @arg: enum ttu_flags will be passed to this argument */ @@ -1538,7 +1598,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, /* * When racing against e.g. zap_pte_range() on another cpu, - * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_unmap() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ @@ -1779,9 +1839,9 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, break; } - /* See page_try_share_anon_rmap(): clear PTE first. */ + /* See folio_try_share_anon_rmap(): clear PTE first. */ if (anon_exclusive && - page_try_share_anon_rmap(subpage)) { + folio_try_share_anon_rmap_pte(folio, subpage)) { swap_free(entry); set_pte_at(mm, address, pvmw.pte, pteval); ret = false; @@ -1821,7 +1881,10 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, add_reliable_folio_counter(folio, mm, -1); } discard: - page_remove_rmap(subpage, vma, folio_test_hugetlb(folio)); + if (unlikely(folio_test_hugetlb(folio))) + hugetlb_remove_rmap(folio); + else + folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); @@ -1889,7 +1952,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, /* * When racing against e.g. zap_pte_range() on another cpu, - * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_migrate() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ @@ -2054,7 +2117,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, pte_t swp_pte; if (anon_exclusive) - BUG_ON(page_try_share_anon_rmap(subpage)); + WARN_ON_ONCE(folio_try_share_anon_rmap_pte(folio, + subpage)); /* * Store the pfn of the page in a special migration @@ -2127,14 +2191,19 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) && !anon_exclusive, subpage); - /* See page_try_share_anon_rmap(): clear PTE first. */ - if (anon_exclusive && - page_try_share_anon_rmap(subpage)) { - if (folio_test_hugetlb(folio)) + /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ + if (folio_test_hugetlb(folio)) { + if (anon_exclusive && + hugetlb_try_share_anon_rmap(folio)) { set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); - else - set_pte_at(mm, address, pvmw.pte, pteval); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + } else if (anon_exclusive && + folio_try_share_anon_rmap_pte(folio, subpage)) { + set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; @@ -2176,7 +2245,10 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, */ } - page_remove_rmap(subpage, vma, folio_test_hugetlb(folio)); + if (unlikely(folio_test_hugetlb(folio))) + hugetlb_remove_rmap(folio); + else + folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); @@ -2315,7 +2387,7 @@ static bool page_make_device_exclusive_one(struct folio *folio, * There is a reference on the page for the swap entry which has * been removed, so shouldn't take another. */ - page_remove_rmap(subpage, vma, false); + folio_remove_rmap_pte(folio, subpage, vma); } mmu_notifier_invalidate_range_end(&range); @@ -2599,12 +2671,11 @@ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. - * - * RMAP_COMPOUND is ignored. */ -void hugepage_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, - unsigned long address, rmap_t flags) +void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, + unsigned long address, rmap_t flags) { + VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); @@ -2614,9 +2685,11 @@ void hugepage_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, PageAnonExclusive(&folio->page), folio); } -void hugepage_add_new_anon_rmap(struct folio *folio, - struct vm_area_struct *vma, unsigned long address) +void hugetlb_add_new_anon_rmap(struct folio *folio, + struct vm_area_struct *vma, unsigned long address) { + VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); + BUG_ON(address < vma->vm_start || address >= vma->vm_end); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); diff --git a/mm/swapfile.c b/mm/swapfile.c index b12b1dd7e151024179f0367103496cb6f8491b67..91f48df479525d990e1dc0bc3bb90c89a6c0f6c2 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1896,7 +1896,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, if (pte_swp_exclusive(old_pte)) rmap_flags |= RMAP_EXCLUSIVE; - page_add_anon_rmap(page, vma, addr, rmap_flags); + folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr); lru_cache_add_inactive_or_unevictable(page, vma); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 32903238db3afd39db2d13fd49109527880646ca..f8449f506af2b9290b8b9663712f9e0e71f4217b 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -115,7 +115,7 @@ int mfill_atomic_install_pte(pmd_t *dst_pmd, /* Usually, cache pages are already added to LRU */ if (newly_allocated) folio_add_lru(folio); - page_add_file_rmap(page, dst_vma, false); + folio_add_file_rmap_pte(folio, page, dst_vma); } else { page_add_new_anon_rmap(page, dst_vma, dst_addr); folio_add_lru_vma(folio, dst_vma); diff --git a/mm/userswap.c b/mm/userswap.c index e76e9d7a40de030ad07461835789dba3780a09b3..20ee53dc5eea5a418aa8b3d0714d804a0be35a2b 100644 --- a/mm/userswap.c +++ b/mm/userswap.c @@ -163,7 +163,7 @@ static int uswap_unmap_anon_page(struct mm_struct *mm, dec_mm_counter(mm, MM_ANONPAGES); add_reliable_page_counter(page, mm, -1); - page_remove_rmap(page, vma, false); + folio_remove_rmap_pte(page_folio(page), page, vma); page->mapping = NULL; out_release_unlock: