diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-12 12:37:02 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-12 12:37:02 -0800 |
commit | 6020c204be997e3f5129839ff9c801800fb4336e (patch) | |
tree | 2125670ece9bed7951946b8badd6f40cf5963570 | |
parent | 81ff0be4b9e3bcfee022d71cf89d72f7e2ed41ba (diff) | |
parent | 6b24ca4a1a8d4ee3221d6d44ddbb99f542e4bda3 (diff) | |
download | linux-6020c204be997e3f5129839ff9c801800fb4336e.tar.bz2 |
Merge tag 'folio-5.17' of git://git.infradead.org/users/willy/pagecache
Pull folio conversion updates from Matthew Wilcox:
"Convert much of the page cache to use folios
This stops just short of actually enabling large folios. It converts
everything that I noticed needs to be converted, but there may still
be places I've overlooked which still have page size assumptions.
The big change here is using large entries in the page cache XArray
instead of many small entries. That only affects shmem for now, but
it's a pretty big change for shmem since it changes where memory needs
to be allocated (at split time instead of insertion)"
* tag 'folio-5.17' of git://git.infradead.org/users/willy/pagecache: (49 commits)
mm: Use multi-index entries in the page cache
XArray: Add xas_advance()
truncate,shmem: Handle truncates that split large folios
truncate: Convert invalidate_inode_pages2_range to folios
fs: Convert vfs_dedupe_file_range_compare to folios
mm: Remove pagevec_remove_exceptionals()
mm: Convert find_lock_entries() to use a folio_batch
filemap: Return only folios from find_get_entries()
filemap: Convert filemap_get_read_batch() to use a folio_batch
filemap: Convert filemap_read() to use a folio
truncate: Add invalidate_complete_folio2()
truncate: Convert invalidate_inode_pages2_range() to use a folio
truncate: Skip known-truncated indices
truncate,shmem: Add truncate_inode_folio()
shmem: Convert part of shmem_undo_range() to use a folio
mm: Add unmap_mapping_folio()
truncate: Add truncate_cleanup_folio()
filemap: Add filemap_release_folio()
filemap: Use a folio in filemap_page_mkwrite
filemap: Use a folio in filemap_map_pages
...
-rw-r--r-- | fs/f2fs/f2fs.h | 2 | ||||
-rw-r--r-- | fs/fs-writeback.c | 24 | ||||
-rw-r--r-- | fs/remap_range.c | 116 | ||||
-rw-r--r-- | include/linux/huge_mm.h | 14 | ||||
-rw-r--r-- | include/linux/mm.h | 68 | ||||
-rw-r--r-- | include/linux/page-flags.h | 13 | ||||
-rw-r--r-- | include/linux/pagemap.h | 59 | ||||
-rw-r--r-- | include/linux/pagevec.h | 67 | ||||
-rw-r--r-- | include/linux/uio.h | 7 | ||||
-rw-r--r-- | include/linux/xarray.h | 18 | ||||
-rw-r--r-- | include/trace/events/filemap.h | 32 | ||||
-rw-r--r-- | lib/iov_iter.c | 30 | ||||
-rw-r--r-- | lib/xarray.c | 6 | ||||
-rw-r--r-- | mm/filemap.c | 1004 | ||||
-rw-r--r-- | mm/folio-compat.c | 11 | ||||
-rw-r--r-- | mm/huge_memory.c | 18 | ||||
-rw-r--r-- | mm/internal.h | 14 | ||||
-rw-r--r-- | mm/khugepaged.c | 12 | ||||
-rw-r--r-- | mm/memory.c | 49 | ||||
-rw-r--r-- | mm/migrate.c | 29 | ||||
-rw-r--r-- | mm/page-writeback.c | 6 | ||||
-rw-r--r-- | mm/readahead.c | 24 | ||||
-rw-r--r-- | mm/shmem.c | 174 | ||||
-rw-r--r-- | mm/swap.c | 26 | ||||
-rw-r--r-- | mm/truncate.c | 304 |
25 files changed, 1114 insertions, 1013 deletions
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index ce9fc9f13000..d0d603187171 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -28,6 +28,8 @@ #include <linux/fscrypt.h> #include <linux/fsverity.h> +struct pagevec; + #ifdef CONFIG_F2FS_CHECK_FS #define f2fs_bug_on(sbi, condition) BUG_ON(condition) #else diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 67f0e88eed01..4f680f848c8b 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -372,7 +372,7 @@ static bool inode_do_switch_wbs(struct inode *inode, { struct address_space *mapping = inode->i_mapping; XA_STATE(xas, &mapping->i_pages, 0); - struct page *page; + struct folio *folio; bool switched = false; spin_lock(&inode->i_lock); @@ -389,21 +389,23 @@ static bool inode_do_switch_wbs(struct inode *inode, /* * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points - * to possibly dirty pages while PAGECACHE_TAG_WRITEBACK points to - * pages actually under writeback. + * to possibly dirty folios while PAGECACHE_TAG_WRITEBACK points to + * folios actually under writeback. */ - xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_DIRTY) { - if (PageDirty(page)) { - dec_wb_stat(old_wb, WB_RECLAIMABLE); - inc_wb_stat(new_wb, WB_RECLAIMABLE); + xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_DIRTY) { + if (folio_test_dirty(folio)) { + long nr = folio_nr_pages(folio); + wb_stat_mod(old_wb, WB_RECLAIMABLE, -nr); + wb_stat_mod(new_wb, WB_RECLAIMABLE, nr); } } xas_set(&xas, 0); - xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { - WARN_ON_ONCE(!PageWriteback(page)); - dec_wb_stat(old_wb, WB_WRITEBACK); - inc_wb_stat(new_wb, WB_WRITEBACK); + xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { + long nr = folio_nr_pages(folio); + WARN_ON_ONCE(!folio_test_writeback(folio)); + wb_stat_mod(old_wb, WB_WRITEBACK, -nr); + wb_stat_mod(new_wb, WB_WRITEBACK, nr); } if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) { diff --git a/fs/remap_range.c b/fs/remap_range.c index 6d4a9beaa097..231159682907 100644 --- a/fs/remap_range.c +++ b/fs/remap_range.c @@ -146,41 +146,41 @@ static int generic_remap_check_len(struct inode *inode_in, } /* Read a page's worth of file data into the page cache. */ -static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset) +static struct folio *vfs_dedupe_get_folio(struct inode *inode, loff_t pos) { - struct page *page; + struct folio *folio; - page = read_mapping_page(inode->i_mapping, offset >> PAGE_SHIFT, NULL); - if (IS_ERR(page)) - return page; - if (!PageUptodate(page)) { - put_page(page); + folio = read_mapping_folio(inode->i_mapping, pos >> PAGE_SHIFT, NULL); + if (IS_ERR(folio)) + return folio; + if (!folio_test_uptodate(folio)) { + folio_put(folio); return ERR_PTR(-EIO); } - return page; + return folio; } /* - * Lock two pages, ensuring that we lock in offset order if the pages are from - * the same file. + * Lock two folios, ensuring that we lock in offset order if the folios + * are from the same file. */ -static void vfs_lock_two_pages(struct page *page1, struct page *page2) +static void vfs_lock_two_folios(struct folio *folio1, struct folio *folio2) { /* Always lock in order of increasing index. */ - if (page1->index > page2->index) - swap(page1, page2); + if (folio1->index > folio2->index) + swap(folio1, folio2); - lock_page(page1); - if (page1 != page2) - lock_page(page2); + folio_lock(folio1); + if (folio1 != folio2) + folio_lock(folio2); } -/* Unlock two pages, being careful not to unlock the same page twice. */ -static void vfs_unlock_two_pages(struct page *page1, struct page *page2) +/* Unlock two folios, being careful not to unlock the same folio twice. */ +static void vfs_unlock_two_folios(struct folio *folio1, struct folio *folio2) { - unlock_page(page1); - if (page1 != page2) - unlock_page(page2); + folio_unlock(folio1); + if (folio1 != folio2) + folio_unlock(folio2); } /* @@ -188,77 +188,71 @@ static void vfs_unlock_two_pages(struct page *page1, struct page *page2) * Caller must have locked both inodes to prevent write races. */ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, - struct inode *dest, loff_t destoff, + struct inode *dest, loff_t dstoff, loff_t len, bool *is_same) { - loff_t src_poff; - loff_t dest_poff; - void *src_addr; - void *dest_addr; - struct page *src_page; - struct page *dest_page; - loff_t cmp_len; - bool same; - int error; - - error = -EINVAL; - same = true; + bool same = true; + int error = -EINVAL; + while (len) { - src_poff = srcoff & (PAGE_SIZE - 1); - dest_poff = destoff & (PAGE_SIZE - 1); - cmp_len = min(PAGE_SIZE - src_poff, - PAGE_SIZE - dest_poff); + struct folio *src_folio, *dst_folio; + void *src_addr, *dst_addr; + loff_t cmp_len = min(PAGE_SIZE - offset_in_page(srcoff), + PAGE_SIZE - offset_in_page(dstoff)); + cmp_len = min(cmp_len, len); if (cmp_len <= 0) goto out_error; - src_page = vfs_dedupe_get_page(src, srcoff); - if (IS_ERR(src_page)) { - error = PTR_ERR(src_page); + src_folio = vfs_dedupe_get_folio(src, srcoff); + if (IS_ERR(src_folio)) { + error = PTR_ERR(src_folio); goto out_error; } - dest_page = vfs_dedupe_get_page(dest, destoff); - if (IS_ERR(dest_page)) { - error = PTR_ERR(dest_page); - put_page(src_page); + dst_folio = vfs_dedupe_get_folio(dest, dstoff); + if (IS_ERR(dst_folio)) { + error = PTR_ERR(dst_folio); + folio_put(src_folio); goto out_error; } - vfs_lock_two_pages(src_page, dest_page); + vfs_lock_two_folios(src_folio, dst_folio); /* - * Now that we've locked both pages, make sure they're still + * Now that we've locked both folios, make sure they're still * mapped to the file data we're interested in. If not, * someone is invalidating pages on us and we lose. */ - if (!PageUptodate(src_page) || !PageUptodate(dest_page) || - src_page->mapping != src->i_mapping || - dest_page->mapping != dest->i_mapping) { + if (!folio_test_uptodate(src_folio) || !folio_test_uptodate(dst_folio) || + src_folio->mapping != src->i_mapping || + dst_folio->mapping != dest->i_mapping) { same = false; goto unlock; } - src_addr = kmap_atomic(src_page); - dest_addr = kmap_atomic(dest_page); + src_addr = kmap_local_folio(src_folio, + offset_in_folio(src_folio, srcoff)); + dst_addr = kmap_local_folio(dst_folio, + offset_in_folio(dst_folio, dstoff)); - flush_dcache_page(src_page); - flush_dcache_page(dest_page); + flush_dcache_folio(src_folio); + flush_dcache_folio(dst_folio); - if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len)) + if (memcmp(src_addr, dst_addr, cmp_len)) same = false; - kunmap_atomic(dest_addr); - kunmap_atomic(src_addr); + kunmap_local(dst_addr); + kunmap_local(src_addr); unlock: - vfs_unlock_two_pages(src_page, dest_page); - put_page(dest_page); - put_page(src_page); + vfs_unlock_two_folios(src_folio, dst_folio); + folio_put(dst_folio); + folio_put(src_folio); if (!same) break; srcoff += cmp_len; - destoff += cmp_len; + dstoff += cmp_len; len -= cmp_len; } diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f280f33ff223..e4c18ba8d3bf 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -274,6 +274,15 @@ static inline int thp_nr_pages(struct page *page) return 1; } +/** + * folio_test_pmd_mappable - Can we map this folio with a PMD? + * @folio: The folio to test + */ +static inline bool folio_test_pmd_mappable(struct folio *folio) +{ + return folio_order(folio) >= HPAGE_PMD_ORDER; +} + struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, @@ -339,6 +348,11 @@ static inline int thp_nr_pages(struct page *page) return 1; } +static inline bool folio_test_pmd_mappable(struct folio *folio) +{ + return false; +} + static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { return false; diff --git a/include/linux/mm.h b/include/linux/mm.h index de103949860f..c768a7c81b0b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -714,6 +714,27 @@ int vma_is_stack_for_current(struct vm_area_struct *vma); struct mmu_gather; struct inode; +static inline unsigned int compound_order(struct page *page) +{ + if (!PageHead(page)) + return 0; + return page[1].compound_order; +} + +/** + * folio_order - The allocation order of a folio. + * @folio: The folio. + * + * A folio is composed of 2^order pages. See get_order() for the definition + * of order. + * + * Return: The order of the folio. + */ +static inline unsigned int folio_order(struct folio *folio) +{ + return compound_order(&folio->page); +} + #include <linux/huge_mm.h> /* @@ -913,27 +934,6 @@ static inline void destroy_compound_page(struct page *page) compound_page_dtors[page[1].compound_dtor](page); } -static inline unsigned int compound_order(struct page *page) -{ - if (!PageHead(page)) - return 0; - return page[1].compound_order; -} - -/** - * folio_order - The allocation order of a folio. - * @folio: The folio. - * - * A folio is composed of 2^order pages. See get_order() for the definition - * of order. - * - * Return: The order of the folio. - */ -static inline unsigned int folio_order(struct folio *folio) -{ - return compound_order(&folio->page); -} - static inline bool hpage_pincount_available(struct page *page) { /* @@ -1837,28 +1837,6 @@ static inline bool can_do_mlock(void) { return false; } extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); -/* - * Parameter block passed down to zap_pte_range in exceptional cases. - */ -struct zap_details { - struct address_space *zap_mapping; /* Check page->mapping if set */ - struct page *single_page; /* Locked page to be unmapped */ -}; - -/* - * We set details->zap_mappings when we want to unmap shared but keep private - * pages. Return true if skip zapping this page, false otherwise. - */ -static inline bool -zap_skip_check_mapping(struct zap_details *details, struct page *page) -{ - if (!details || !page) - return false; - - return details->zap_mapping && - (details->zap_mapping != page_rmapping(page)); -} - struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -1893,7 +1871,6 @@ extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); -int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); int invalidate_inode_page(struct page *page); @@ -1904,7 +1881,6 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); -void unmap_mapping_page(struct page *page); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, @@ -1925,7 +1901,6 @@ static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, BUG(); return -EFAULT; } -static inline void unmap_mapping_page(struct page *page) { } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, @@ -1982,7 +1957,6 @@ int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); -extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b5f14d581113..b3d353d537e2 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -68,9 +68,6 @@ * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as * a result of MADV_FREE). * - * PG_uptodate tells whether the page's contents is valid. When a read - * completes, the page becomes uptodate, unless a disk I/O error happened. - * * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * @@ -615,6 +612,16 @@ TESTPAGEFLAG_FALSE(Ksm, ksm) u64 stable_page_flags(struct page *page); +/** + * folio_test_uptodate - Is this folio up to date? + * @folio: The folio. + * + * The uptodate flag is set on a folio when every byte in the folio is + * at least as new as the corresponding bytes on storage. Anonymous + * and CoW folios are always uptodate. If the folio is not uptodate, + * some of the bytes in it may be; see the is_partially_uptodate() + * address_space operation. + */ static inline bool folio_test_uptodate(struct folio *folio) { bool ret = test_bit(PG_uptodate, folio_flags(folio, 0)); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 422bdf9f4e76..270bf5136c34 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -16,7 +16,7 @@ #include <linux/hardirq.h> /* for in_interrupt() */ #include <linux/hugetlb_inline.h> -struct pagevec; +struct folio_batch; static inline bool mapping_empty(struct address_space *mapping) { @@ -511,15 +511,6 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, mapping_gfp_mask(mapping)); } -/* Does this page contain this index? */ -static inline bool thp_contains(struct page *head, pgoff_t index) -{ - /* HugeTLBfs indexes the page cache in units of hpage_size */ - if (PageHuge(head)) - return head->index == index; - return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL)); -} - #define swapcache_index(folio) __page_file_index(&(folio)->page) /** @@ -600,8 +591,6 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) return head + (index & (thp_nr_pages(head) - 1)); } -unsigned find_get_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, struct pagevec *pvec, pgoff_t *indices); unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages); @@ -637,8 +626,10 @@ static inline struct page *grab_cache_page(struct address_space *mapping, return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } -extern struct page * read_cache_page(struct address_space *mapping, - pgoff_t index, filler_t *filler, void *data); +struct folio *read_cache_folio(struct address_space *, pgoff_t index, + filler_t *filler, void *data); +struct page *read_cache_page(struct address_space *, pgoff_t index, + filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern int read_cache_pages(struct address_space *mapping, @@ -650,6 +641,12 @@ static inline struct page *read_mapping_page(struct address_space *mapping, return read_cache_page(mapping, index, NULL, data); } +static inline struct folio *read_mapping_folio(struct address_space *mapping, + pgoff_t index, void *data) +{ + return read_cache_folio(mapping, index, NULL, data); +} + /* * Get index of the page within radix-tree (but not for hugetlb pages). * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) @@ -867,7 +864,7 @@ static inline int wait_on_page_locked_killable(struct page *page) return folio_wait_locked_killable(page_folio(page)); } -int put_and_wait_on_page_locked(struct page *page, int state); +int folio_put_wait_locked(struct folio *folio, int state); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); @@ -883,11 +880,6 @@ static inline void __set_page_dirty(struct page *page, } void folio_account_cleaned(struct folio *folio, struct address_space *mapping, struct bdi_writeback *wb); -static inline void account_page_cleaned(struct page *page, - struct address_space *mapping, struct bdi_writeback *wb) -{ - return folio_account_cleaned(page_folio(page), mapping, wb); -} void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) { @@ -934,11 +926,18 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp); -extern void delete_from_page_cache(struct page *page); -extern void __delete_from_page_cache(struct page *page, void *shadow); +void filemap_remove_folio(struct folio *folio); +void delete_from_page_cache(struct page *page); +void __filemap_remove_folio(struct folio *folio, void *shadow); +static inline void __delete_from_page_cache(struct page *page, void *shadow) +{ + __filemap_remove_folio(page_folio(page), shadow); +} void replace_page_cache_page(struct page *old, struct page *new); void delete_from_page_cache_batch(struct address_space *mapping, - struct pagevec *pvec); + struct folio_batch *fbatch); +int try_to_release_page(struct page *page, gfp_t gfp); +bool filemap_release_folio(struct folio *folio, gfp_t gfp); loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end, int whence); @@ -1030,7 +1029,7 @@ struct readahead_control { void page_cache_ra_unbounded(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_count); void page_cache_sync_ra(struct readahead_control *, unsigned long req_count); -void page_cache_async_ra(struct readahead_control *, struct page *, +void page_cache_async_ra(struct readahead_control *, struct folio *, unsigned long req_count); void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len); @@ -1077,7 +1076,7 @@ void page_cache_async_readahead(struct address_space *mapping, struct page *page, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, index); - page_cache_async_ra(&ractl, page, req_count); + page_cache_async_ra(&ractl, page_folio(page), req_count); } static inline struct folio *__readahead_folio(struct readahead_control *ractl) @@ -1154,16 +1153,6 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; rac->_batch_count += thp_nr_pages(page); - - /* - * The page cache isn't using multi-index entries yet, - * so the xas cursor needs to be manually moved to the - * next index. This can be removed once the page cache - * is converted. - */ - if (PageHead(page)) - xas_set(&xas, rac->_index + rac->_batch_count); - if (i == array_sz) break; } diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 7f3f19065a9f..dda8d5868c81 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -15,8 +15,10 @@ #define PAGEVEC_SIZE 15 struct page; +struct folio; struct address_space; +/* Layout must match folio_batch */ struct pagevec { unsigned char nr; bool percpu_pvec_drained; @@ -25,7 +27,6 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); -void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start, pgoff_t end); @@ -81,4 +82,68 @@ static inline void pagevec_release(struct pagevec *pvec) __pagevec_release(pvec); } +/** + * struct folio_batch - A collection of folios. + * + * The folio_batch is used to amortise the cost of retrieving and + * operating on a set of folios. The order of folios in the batch may be + * significant (eg delete_from_page_cache_batch()). Some users of the + * folio_batch store "exceptional" entries in it which can be removed + * by calling folio_batch_remove_exceptionals(). + */ +struct folio_batch { + unsigned char nr; + bool percpu_pvec_drained; + struct folio *folios[PAGEVEC_SIZE]; +}; + +/* Layout must match pagevec */ +static_assert(sizeof(struct pagevec) == sizeof(struct folio_batch)); +static_assert(offsetof(struct pagevec, pages) == + offsetof(struct folio_batch, folios)); + +/** + * folio_batch_init() - Initialise a batch of folios + * @fbatch: The folio batch. + * + * A freshly initialised folio_batch contains zero folios. + */ +static inline void folio_batch_init(struct folio_batch *fbatch) +{ + fbatch->nr = 0; +} + +static inline unsigned int folio_batch_count(struct folio_batch *fbatch) +{ + return fbatch->nr; +} + +static inline unsigned int fbatch_space(struct folio_batch *fbatch) +{ + return PAGEVEC_SIZE - fbatch->nr; +} + +/** + * folio_batch_add() - Add a folio to a batch. + * @fbatch: The folio batch. + * @folio: The folio to add. + * + * The folio is added to the end of the batch. + * The batch must have previously been initialised using folio_batch_init(). + * + * Return: The number of slots still available. + */ +static inline unsigned folio_batch_add(struct folio_batch *fbatch, + struct folio *folio) +{ + fbatch->folios[fbatch->nr++] = folio; + return fbatch_space(fbatch); +} + +static inline void folio_batch_release(struct folio_batch *fbatch) +{ + pagevec_release((struct pagevec *)fbatch); +} + +void folio_batch_remove_exceptionals(struct folio_batch *fbatch); #endif /* _LINUX_PAGEVEC_H */ diff --git a/include/linux/uio.h b/include/linux/uio.h index 6350354f97e9..43321dbebba8 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -7,6 +7,7 @@ #include <linux/kernel.h> #include <linux/thread_info.h> +#include <linux/mm_types.h> #include <uapi/linux/uio.h> struct page; @@ -146,6 +147,12 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); +static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, + size_t bytes, struct iov_iter *i) +{ + return copy_page_to_iter(&folio->page, offset, bytes, i); +} + static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { diff --git a/include/linux/xarray.h b/include/linux/xarray.h index a91e3d90df8a..d6d5da6ed735 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1581,6 +1581,24 @@ static inline void xas_set(struct xa_state *xas, unsigned long index) } /** + * xas_advance() - Skip over sibling entries. + * @xas: XArray operation state. + * @index: Index of last sibling entry. + * + * Move the operation state to refer to the last sibling entry. + * This is useful for loops that normally want to see sibling + * entries but sometimes want to skip them. Use xas_set() if you + * want to move to an index which is not part of this entry. + */ +static inline void xas_advance(struct xa_state *xas, unsigned long index) +{ + unsigned char shift = xas_is_node(xas) ? xas->xa_node->shift : 0; + + xas->xa_index = index; + xas->xa_offset = (index >> shift) & XA_CHUNK_MASK; +} + +/** * xas_set_order() - Set up XArray operation state for a multislot entry. * @xas: XArray operation state. * @index: Target of the operation. diff --git a/include/trace/events/filemap.h b/include/trace/events/filemap.h index c47b63db124e..46c89c1e460c 100644 --- a/include/trace/events/filemap.h +++ b/include/trace/events/filemap.h @@ -15,43 +15,45 @@ DECLARE_EVENT_CLASS(mm_filemap_op_page_cache, - TP_PROTO(struct page *page), + TP_PROTO(struct folio *folio), - TP_ARGS(page), + TP_ARGS(folio), TP_STRUCT__entry( __field(unsigned long, pfn) __field(unsigned long, i_ino) __field(unsigned long, index) __field(dev_t, s_dev) + __field(unsigned char, order) ), TP_fast_assign( - __entry->pfn = page_to_pfn(page); - __entry->i_ino = page->mapping->host->i_ino; - __entry->index = page->index; - if (page->mapping->host->i_sb) - __entry->s_dev = page->mapping->host->i_sb->s_dev; + __entry->pfn = folio_pfn(folio); + __entry->i_ino = folio->mapping->host->i_ino; + __entry->index = folio->index; + if (folio->mapping->host->i_sb) + __entry->s_dev = folio->mapping->host->i_sb->s_dev; else - __entry->s_dev = page->mapping->host->i_rdev; + __entry->s_dev = folio->mapping->host->i_rdev; + __entry->order = folio_order(folio); ), - TP_printk("dev %d:%d ino %lx page=%p pfn=0x%lx ofs=%lu", + TP_printk("dev %d:%d ino %lx pfn=0x%lx ofs=%lu order=%u", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, - pfn_to_page(__entry->pfn), __entry->pfn, - __entry->index << PAGE_SHIFT) + __entry->index << PAGE_SHIFT, + __entry->order) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_delete_from_page_cache, - TP_PROTO(struct page *page), - TP_ARGS(page) + TP_PROTO(struct folio *folio), + TP_ARGS(folio) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_add_to_page_cache, - TP_PROTO(struct page *page), - TP_ARGS(page) + TP_PROTO(struct folio *folio), + TP_ARGS(folio) ); TRACE_EVENT(filemap_set_wb_err, diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 66a740e6e153..b0e0acdf96c1 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -69,42 +69,40 @@ #define iterate_xarray(i, n, base, len, __off, STEP) { \ __label__ __out; \ size_t __off = 0; \ - struct page *head = NULL; \ + struct folio *folio; \ loff_t start = i->xarray_start + i->iov_offset; \ - unsigned offset = start % PAGE_SIZE; \ pgoff_t index = start / PAGE_SIZE; \ - int j; \ - \ XA_STATE(xas, i->xarray, index); \ \ + len = PAGE_SIZE - offset_in_page(start); \ rcu_read_lock(); \ - xas_for_each(&xas, head, ULONG_MAX) { \ + xas_for_each(&xas, folio, ULONG_MAX) { \ unsigned left; \ - if (xas_retry(&xas, head)) \ + size_t offset; \ + if (xas_retry(&xas, folio)) \ continue; \ - if (WARN_ON(xa_is_value(head))) \ + if (WARN_ON(xa_is_value(folio))) \ break; \ - if (WARN_ON(PageHuge(head))) \ + if (WARN_ON(folio_test_hugetlb(folio))) \ break; \ - for (j = (head->index < index) ? index - head->index : 0; \ - j < thp_nr_pages(head); j++) { \ - void *kaddr = kmap_local_page(head + j); \ - base = kaddr + offset; \ - len = PAGE_SIZE - offset; \ + offset = offset_in_folio(folio, start + __off); \ + while (offset < folio_size(folio)) { \ + base = kmap_local_folio(folio, offset); \ len = min(n, len); \ left = (STEP); \ - kunmap_local(kaddr); \ + kunmap_local(base); \ len -= left; \ __off += len; \ n -= len; \ if (left || n == 0) \ goto __out; \ - offset = 0; \ + offset += len; \ + len = PAGE_SIZE; \ } \ } \ __out: \ rcu_read_unlock(); \ - i->iov_offset += __off; \ + i->iov_offset += __off; \ n = __off; \ } diff --git a/lib/xarray.c b/lib/xarray.c index f5d8f54907b4..6f47f6375808 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -157,7 +157,7 @@ static void xas_move_index(struct xa_state *xas, unsigned long offset) xas->xa_index += offset << shift; } -static void xas_advance(struct xa_state *xas) +static void xas_next_offset(struct xa_state *xas) { xas->xa_offset++; xas_move_index(xas, xas->xa_offset); @@ -1250,7 +1250,7 @@ void *xas_find(struct xa_state *xas, unsigned long max) xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1; } - xas_advance(xas); + xas_next_offset(xas); while (xas->xa_node && (xas->xa_index <= max)) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { @@ -1268,7 +1268,7 @@ void *xas_find(struct xa_state *xas, unsigned long max) if (entry && !xa_is_sibling(entry)) return entry; - xas_advance(xas); + xas_next_offset(xas); } if (!xas->xa_node) diff --git a/mm/filemap.c b/mm/filemap.c index 3baf03c0f608..2fd9b2f24025 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -121,99 +121,97 @@ */ static void page_cache_delete(struct address_space *mapping, - struct page *page, void *shadow) + struct folio *folio, void *shadow) { - XA_STATE(xas, &mapping->i_pages, page->index); - unsigned int nr = 1; + XA_STATE(xas, &mapping->i_pages, folio->index); + long nr = 1; mapping_set_update(&xas, mapping); /* hugetlb pages are represented by a single entry in the xarray */ - if (!PageHuge(page)) { - xas_set_order(&xas, page->index, compound_order(page)); - nr = compound_nr(page); + if (!folio_test_hugetlb(folio)) { + xas_set_order(&xas, folio->index, folio_order(folio)); + nr = folio_nr_pages(folio); } - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(PageTail(page), page); - VM_BUG_ON_PAGE(nr != 1 && shadow, page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); xas_store(&xas, shadow); xas_init_marks(&xas); - page->mapping = NULL; + folio->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ mapping->nrpages -= nr; } -static void unaccount_page_cache_page(struct address_space *mapping, - struct page *page) +static void filemap_unaccount_folio(struct address_space *mapping, + struct folio *folio) { - int nr; + long nr; /* * if we're uptodate, flush out into the cleancache, otherwise * invalidate any existing cleancache entries. We can't leave * stale data around in the cleancache once our page is gone */ - if (PageUptodate(page) && PageMappedToDisk(page)) - cleancache_put_page(page); + if (folio_test_uptodate(folio) && folio_test_mappedtodisk(folio)) + cleancache_put_page(&folio->page); else - cleancache_invalidate_page(mapping, page); + cleancache_invalidate_page(mapping, &folio->page); - VM_BUG_ON_PAGE(PageTail(page), page); - VM_BUG_ON_PAGE(page_mapped(page), page); - if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) { + VM_BUG_ON_FOLIO(folio_mapped(folio), folio); + if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) { int mapcount; pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", - current->comm, page_to_pfn(page)); - dump_page(page, "still mapped when deleted"); + current->comm, folio_pfn(folio)); + dump_page(&folio->page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); - mapcount = page_mapcount(page); + mapcount = page_mapcount(&folio->page); if (mapping_exiting(mapping) && - page_count(page) >= mapcount + 2) { + folio_ref_count(folio) >= mapcount + 2) { /* * All vmas have already been torn down, so it's - * a good bet that actually the page is unmapped, + * a good bet that actually the folio is unmapped, * and we'd prefer not to leak it: if we're wrong, * some other bad page check should catch it later. */ - page_mapcount_reset(page); - page_ref_sub(page, mapcount); + page_mapcount_reset(&folio->page); + folio_ref_sub(folio, mapcount); } } - /* hugetlb pages do not participate in page cache accounting. */ - if (PageHuge(page)) + /* hugetlb folios do not participate in page cache accounting. */ + if (folio_test_hugetlb(folio)) return; - nr = thp_nr_pages(page); + nr = folio_nr_pages(folio); - __mod_lruvec_page_state(page, NR_FILE_PAGES, -nr); - if (PageSwapBacked(page)) { - __mod_lruvec_page_state(page, NR_SHMEM, -nr); - if (PageTransHuge(page)) - __mod_lruvec_page_state(page, NR_SHMEM_THPS, -nr); - } else if (PageTransHuge(page)) { - __mod_lruvec_page_state(page, NR_FILE_THPS, -nr); + __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); + if (folio_test_swapbacked(folio)) { + __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); + if (folio_test_pmd_mappable(folio)) + __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); + } else if (folio_test_pmd_mappable(folio)) { + __lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } /* - * At this point page must be either written or cleaned by - * truncate. Dirty page here signals a bug and loss of + * At this point folio must be either written or cleaned by + * truncate. Dirty folio here signals a bug and loss of * unwritten data. * - * This fixes dirty accounting after removing the page entirely - * but leaves PageDirty set: it has no effect for truncated - * page and anyway will be cleared before returning page into + * This fixes dirty accounting after removing the folio entirely + * but leaves the dirty flag set: it has no effect for truncated + * folio and anyway will be cleared before returning folio to * buddy allocator. */ - if (WARN_ON_ONCE(PageDirty(page))) - account_page_cleaned(page, mapping, inode_to_wb(mapping->host)); + if (WARN_ON_ONCE(folio_test_dirty(folio))) + folio_account_cleaned(folio, mapping, + inode_to_wb(mapping->host)); } /* @@ -221,87 +219,83 @@ static void unaccount_page_cache_page(struct address_space *mapping, * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ -void __delete_from_page_cache(struct page *page, void *shadow) +void __filemap_remove_folio(struct folio *folio, void *shadow) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; - trace_mm_filemap_delete_from_page_cache(page); - - unaccount_page_cache_page(mapping, page); - page_cache_delete(mapping, page, shadow); + trace_mm_filemap_delete_from_page_cache(folio); + filemap_unaccount_folio(mapping, folio); + page_cache_delete(mapping, folio, shadow); } -static void page_cache_free_page(struct address_space *mapping, - struct page *page) +void filemap_free_folio(struct address_space *mapping, struct folio *folio) { void (*freepage)(struct page *); freepage = mapping->a_ops->freepage; if (freepage) - freepage(page); + freepage(&folio->page); - if (PageTransHuge(page) && !PageHuge(page)) { - page_ref_sub(page, thp_nr_pages(page)); - VM_BUG_ON_PAGE(page_count(page) <= 0, page); + if (folio_test_large(folio) && !folio_test_hugetlb(folio)) { + folio_ref_sub(folio, folio_nr_pages(folio)); + VM_BUG_ON_FOLIO(folio_ref_count(folio) <= 0, folio); } else { - put_page(page); + folio_put(folio); } } /** - * delete_from_page_cache - delete page from page cache - * @page: the page which the kernel is trying to remove from page cache + * filemap_remove_folio - Remove folio from page cache. + * @folio: The folio. * - * This must be called only on pages that have been verified to be in the page - * cache and locked. It will never put the page into the free list, the caller - * has a reference on the page. + * This must be called only on folios that are locked and have been + * verified to be in the page cache. It will never put the folio into + * the free list because the caller has a reference on the page. */ -void delete_from_page_cache(struct page *page) +void filemap_remove_folio(struct folio *folio) { - struct address_space *mapping = page_mapping(page); + struct address_space *mapping = folio->mapping; - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); - __delete_from_page_cache(page, NULL); + __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); - page_cache_free_page(mapping, page); + filemap_free_folio(mapping, folio); } -EXPORT_SYMBOL(delete_from_page_cache); /* - * page_cache_delete_batch - delete several pages from page cache - * @mapping: the mapping to which pages belong - * @pvec: pagevec with pages to delete + * page_cache_delete_batch - delete several folios from page cache + * @mapping: the mapping to which folios belong + * @fbatch: batch of folios to delete * - * The function walks over mapping->i_pages and removes pages passed in @pvec - * from the mapping. The function expects @pvec to be sorted by page index - * and is optimised for it to be dense. - * It tolerates holes in @pvec (mapping entries at those indices are not - * modified). The function expects only THP head pages to be present in the - * @pvec. + * The function walks over mapping->i_pages and removes folios passed in + * @fbatch from the mapping. The function expects @fbatch to be sorted + * by page index and is optimised for it to be dense. + * It tolerates holes in @fbatch (mapping entries at those indices are not + * modified). * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, - struct pagevec *pvec) + struct folio_batch *fbatch) { - XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index); - int total_pages = 0; + XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index); + long total_pages = 0; int i = 0; - struct page *page; + struct folio *folio; mapping_set_update(&xas, mapping); - xas_for_each(&xas, page, ULONG_MAX) { - if (i >= pagevec_count(pvec)) + xas_for_each(&xas, folio, ULONG_MAX) { + if (i >= folio_batch_count(fbatch)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ - if (xa_is_value(page)) + if (xa_is_value(folio)) continue; /* * A page got inserted in our range? Skip it. We have our @@ -310,54 +304,48 @@ static void page_cache_delete_batch(struct address_space *mapping, * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ - if (page != pvec->pages[i]) { - VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index, - page); + if (folio != fbatch->folios[i]) { + VM_BUG_ON_FOLIO(folio->index > + fbatch->folios[i]->index, folio); continue; } - WARN_ON_ONCE(!PageLocked(page)); + WARN_ON_ONCE(!folio_test_locked(folio)); - if (page->index == xas.xa_index) - page->mapping = NULL; - /* Leave page->index set: truncation lookup relies on it */ + folio->mapping = NULL; + /* Leave folio->index set: truncation lookup relies on it */ - /* - * Move to the next page in the vector if this is a regular - * page or the index is of the last sub-page of this compound - * page. - */ - if (page->index + compound_nr(page) - 1 == xas.xa_index) - i++; + i++; xas_store(&xas, NULL); - total_pages++; + total_pages += folio_nr_pages(folio); } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, - struct pagevec *pvec) + struct folio_batch *fbatch) { int i; - if (!pagevec_count(pvec)) + if (!folio_batch_count(fbatch)) return; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); - for (i = 0; i < pagevec_count(pvec); i++) { - trace_mm_filemap_delete_from_page_cache(pvec->pages[i]); + for (i = 0; i < folio_batch_count(fbatch); i++) { + struct folio *folio = fbatch->folios[i]; - unaccount_page_cache_page(mapping, pvec->pages[i]); + trace_mm_filemap_delete_from_page_cache(folio); + filemap_unaccount_folio(mapping, folio); } - page_cache_delete_batch(mapping, pvec); + page_cache_delete_batch(mapping, fbatch); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); - for (i = 0; i < pagevec_count(pvec); i++) - page_cache_free_page(mapping, pvec->pages[i]); + for (i = 0; i < folio_batch_count(fbatch); i++) + filemap_free_folio(mapping, fbatch->folios[i]); } int filemap_check_errors(struct address_space *mapping) @@ -933,7 +921,7 @@ unlock: goto error; } - trace_mm_filemap_add_to_page_cache(&folio->page); + trace_mm_filemap_add_to_page_cache(folio); return 0; error: folio->mapping = NULL; @@ -1233,10 +1221,10 @@ enum behavior { * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like - * wait_on_page_writeback() waiting on PG_writeback. + * folio_wait_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, - * like put_and_wait_on_page_locked() on PG_locked. + * like folio_put_wait_locked() on PG_locked. */ }; @@ -1413,22 +1401,21 @@ int folio_wait_bit_killable(struct folio *folio, int bit_nr) EXPORT_SYMBOL(folio_wait_bit_killable); /** - * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked - * @page: The page to wait for. + * folio_put_wait_locked - Drop a reference and wait for it to be unlocked + * @folio: The folio to wait for. * @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc). * - * The caller should hold a reference on @page. They expect the page to + * The caller should hold a reference on @folio. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration - * (for example) by holding the reference while waiting for the page to + * (for example) by holding the reference while waiting for the folio to * come unlocked. After this function returns, the caller should not - * dereference @page. + * dereference @folio. * - * Return: 0 if the page was unlocked or -EINTR if interrupted by a signal. + * Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal. */ -int put_and_wait_on_page_locked(struct page *page, int state) +int folio_put_wait_locked(struct folio *folio, int state) { - return folio_wait_bit_common(page_folio(page), PG_locked, state, - DROP); + return folio_wait_bit_common(folio, PG_locked, state, DROP); } /** @@ -1953,37 +1940,36 @@ no_page: } EXPORT_SYMBOL(__filemap_get_folio); -static inline struct page *find_get_entry(struct xa_state *xas, pgoff_t max, +static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max, xa_mark_t mark) { - struct page *page; + struct folio *folio; retry: if (mark == XA_PRESENT) - page = xas_find(xas, max); + folio = xas_find(xas, max); else - page = xas_find_marked(xas, max, mark); + folio = xas_find_marked(xas, max, mark); - if (xas_retry(xas, page)) + if (xas_retry(xas, folio)) goto retry; /* * A shadow entry of a recently evicted page, a swap * entry from shmem/tmpfs or a DAX entry. Return it * without attempting to raise page count. */ - if (!page || xa_is_value(page)) - return page; + if (!folio || xa_is_value(folio)) + return folio; - if (!page_cache_get_speculative(page)) + if (!folio_try_get_rcu(folio)) goto reset; - /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(xas))) { - put_page(page); + if (unlikely(folio != xas_reload(xas))) { + folio_put(folio); goto reset; } - return page; + return folio; reset: xas_reset(xas); goto retry; @@ -1994,56 +1980,36 @@ reset: * @mapping: The address_space to search * @start: The starting page cache index * @end: The final page index (inclusive). - * @pvec: Where the resulting entries are placed. + * @fbatch: Where the resulting entries are placed. * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a batch of entries in - * the mapping. The entries are placed in @pvec. find_get_entries() - * takes a reference on any actual pages it returns. + * the mapping. The entries are placed in @fbatch. find_get_entries() + * takes a reference on any actual folios it returns. * - * The search returns a group of mapping-contiguous page cache entries - * with ascending indexes. There may be holes in the indices due to - * not-present pages. + * The entries have ascending indexes. The indices may not be consecutive + * due to not-present entries or large folios. * - * Any shadow entries of evicted pages, or swap entries from + * Any shadow entries of evicted folios, or swap entries from * shmem/tmpfs, are included in the returned array. * - * If it finds a Transparent Huge Page, head or tail, find_get_entries() - * stops at that page: the caller is likely to have a better way to handle - * the compound page as a whole, and then skip its extent, than repeatedly - * calling find_get_entries() to return all its tails. - * - * Return: the number of pages and shadow entries which were found. + * Return: The number of entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, struct pagevec *pvec, pgoff_t *indices) + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, start); - struct page *page; - unsigned int ret = 0; - unsigned nr_entries = PAGEVEC_SIZE; + struct folio *folio; rcu_read_lock(); - while ((page = find_get_entry(&xas, end, XA_PRESENT))) { - /* - * Terminate early on finding a THP, to allow the caller to - * handle it all at once; but continue if this is hugetlbfs. - */ - if (!xa_is_value(page) && PageTransHuge(page) && - !PageHuge(page)) { - page = find_subpage(page, xas.xa_index); - nr_entries = ret + 1; - } - - indices[ret] = xas.xa_index; - pvec->pages[ret] = page; - if (++ret == nr_entries) + while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { + indices[fbatch->nr] = xas.xa_index; + if (!folio_batch_add(fbatch, folio)) break; } rcu_read_unlock(); - pvec->nr = ret; - return ret; + return folio_batch_count(fbatch); } /** @@ -2051,63 +2017,64 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t start, * @mapping: The address_space to search. * @start: The starting page cache index. * @end: The final page index (inclusive). - * @pvec: Where the resulting entries are placed. - * @indices: The cache indices of the entries in @pvec. + * @fbatch: Where the resulting entries are placed. + * @indices: The cache indices of the entries in @fbatch. * * find_lock_entries() will return a batch of entries from @mapping. - * Swap, shadow and DAX entries are included. Pages are returned - * locked and with an incremented refcount. Pages which are locked by - * somebody else or under writeback are skipped. Only the head page of - * a THP is returned. Pages which are partially outside the range are - * not returned. + * Swap, shadow and DAX entries are included. Folios are returned + * locked and with an incremented refcount. Folios which are locked + * by somebody else or under writeback are skipped. Folios which are + * partially outside the range are not returned. * * The entries have ascending indexes. The indices may not be consecutive - * due to not-present entries, THP pages, pages which could not be locked - * or pages under writeback. + * due to not-present entries, large folios, folios which could not be + * locked or folios under writeback. * * Return: The number of entries which were found. */ unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, struct pagevec *pvec, pgoff_t *indices) + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, start); - struct page *page; + struct folio *folio; rcu_read_lock(); - while ((page = find_get_entry(&xas, end, XA_PRESENT))) { - if (!xa_is_value(page)) { - if (page->index < start) + while ((folio = find_get_entry(&xas, end, XA_PRESENT))) { + if (!xa_is_value(folio)) { + if (folio->index < start) goto put; - if (page->index + thp_nr_pages(page) - 1 > end) + if (folio->index + folio_nr_pages(folio) - 1 > end) goto put; - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto put; - if (page->mapping != mapping || PageWriteback(page)) + if (folio->mapping != mapping || + folio_test_writeback(folio)) goto unlock; - VM_BUG_ON_PAGE(!thp_contains(page, xas.xa_index), - page); + VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index), + folio); } - indices[pvec->nr] = xas.xa_index; - if (!pagevec_add(pvec, page)) + indices[fbatch->nr] = xas.xa_index; + if (!folio_batch_add(fbatch, folio)) break; - goto next; + continue; unlock: - unlock_page(page); + folio_unlock(folio); put: - put_page(page); -next: - if (!xa_is_value(page) && PageTransHuge(page)) { - unsigned int nr_pages = thp_nr_pages(page); - - /* Final THP may cross MAX_LFS_FILESIZE on 32-bit */ - xas_set(&xas, page->index + nr_pages); - if (xas.xa_index < nr_pages) - break; - } + folio_put(folio); } rcu_read_unlock(); - return pagevec_count(pvec); + return folio_batch_count(fbatch); +} + +static inline +bool folio_more_pages(struct folio *folio, pgoff_t index, pgoff_t max) +{ + if (!folio_test_large(folio) || folio_test_hugetlb(folio)) + return false; + if (index >= max) + return false; + return index < folio->index + folio_nr_pages(folio) - 1; } /** @@ -2136,23 +2103,29 @@ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, struct page **pages) { XA_STATE(xas, &mapping->i_pages, *start); - struct page *page; + struct folio *folio; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); - while ((page = find_get_entry(&xas, end, XA_PRESENT))) { + while ((folio = find_get_entry(&xas, end, XA_PRESENT))) { /* Skip over shadow, swap and DAX entries */ - if (xa_is_value(page)) + if (xa_is_value(folio)) continue; - pages[ret] = find_subpage(page, xas.xa_index); +again: + pages[ret] = folio_file_page(folio, xas.xa_index); if (++ret == nr_pages) { *start = xas.xa_index + 1; goto out; } + if (folio_more_pages(folio, xas.xa_index, end)) { + xas.xa_index++; + folio_ref_inc(folio); + goto again; + } } /* @@ -2187,36 +2160,41 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, index); - struct page *page; + struct folio *folio; unsigned int ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); - for (page = xas_load(&xas); page; page = xas_next(&xas)) { - if (xas_retry(&xas, page)) + for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { + if (xas_retry(&xas, folio)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ - if (xa_is_value(page)) + if (xa_is_value(folio)) break; - if (!page_cache_get_speculative(page)) + if (!folio_try_get_rcu(folio)) goto retry; - /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) + if (unlikely(folio != xas_reload(&xas))) goto put_page; - pages[ret] = find_subpage(page, xas.xa_index); +again: + pages[ret] = folio_file_page(folio, xas.xa_index); if (++ret == nr_pages) break; + if (folio_more_pages(folio, xas.xa_index, ULONG_MAX)) { + xas.xa_index++; + folio_ref_inc(folio); + goto again; + } continue; put_page: - put_page(page); + folio_put(folio); retry: xas_reset(&xas); } @@ -2245,25 +2223,25 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, struct page **pages) { XA_STATE(xas, &mapping->i_pages, *index); - struct page *page; + struct folio *folio; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); - while ((page = find_get_entry(&xas, end, tag))) { + while ((folio = find_get_entry(&xas, end, tag))) { /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ - if (xa_is_value(page)) + if (xa_is_value(folio)) continue; - pages[ret] = page; + pages[ret] = &folio->page; if (++ret == nr_pages) { - *index = page->index + thp_nr_pages(page); + *index = folio->index + folio_nr_pages(folio); goto out; } } @@ -2306,52 +2284,50 @@ static void shrink_readahead_size_eio(struct file_ra_state *ra) } /* - * filemap_get_read_batch - Get a batch of pages for read + * filemap_get_read_batch - Get a batch of folios for read * - * Get a batch of pages which represent a contiguous range of bytes - * in the file. No tail pages will be returned. If @index is in the - * middle of a THP, the entire THP will be returned. The last page in - * the batch may have Readahead set or be not Uptodate so that the - * caller can take the appropriate action. + * Get a batch of folios which represent a contiguous range of bytes in + * the file. No exceptional entries will be returned. If @index is in + * the middle of a folio, the entire folio will be returned. The last + * folio in the batch may have the readahead flag set or the uptodate flag + * clear so that the caller can take the appropriate action. */ static void filemap_get_read_batch(struct address_space *mapping, - pgoff_t index, pgoff_t max, struct pagevec *pvec) + pgoff_t index, pgoff_t max, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, index); - struct page *head; + struct folio *folio; rcu_read_lock(); - for (head = xas_load(&xas); head; head = xas_next(&xas)) { - if (xas_retry(&xas, head)) + for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { + if (xas_retry(&xas, folio)) continue; - if (xas.xa_index > max || xa_is_value(head)) + if (xas.xa_index > max || xa_is_value(folio)) break; - if (!page_cache_get_speculative(head)) + if (!folio_try_get_rcu(folio)) goto retry; - /* Has the page moved or been split? */ - if (unlikely(head != xas_reload(&xas))) - goto put_page; + if (unlikely(folio != xas_reload(&xas))) + goto put_folio; - if (!pagevec_add(pvec, head)) + if (!folio_batch_add(fbatch, folio)) break; - if (!PageUptodate(head)) + if (!folio_test_uptodate(folio)) break; - if (PageReadahead(head)) + if (folio_test_readahead(folio)) break; - xas.xa_index = head->index + thp_nr_pages(head) - 1; - xas.xa_offset = (xas.xa_index >> xas.xa_shift) & XA_CHUNK_MASK; + xas_advance(&xas, folio->index + folio_nr_pages(folio) - 1); continue; -put_page: - put_page(head); +put_folio: + folio_put(folio); retry: xas_reset(&xas); } rcu_read_unlock(); } -static int filemap_read_page(struct file *file, struct address_space *mapping, - struct page *page) +static int filemap_read_folio(struct file *file, struct address_space *mapping, + struct folio *folio) { int error; @@ -2360,52 +2336,51 @@ static int filemap_read_page(struct file *file, struct address_space *mapping, * eg. multipath errors. PG_error will be set again if readpage * fails. */ - ClearPageError(page); + folio_clear_error(folio); /* Start the actual read. The read will unlock the page. */ - error = mapping->a_ops->readpage(file, page); + error = mapping->a_ops->readpage(file, &folio->page); if (error) return error; - error = wait_on_page_locked_killable(page); + error = folio_wait_locked_killable(folio); if (error) return error; - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) return 0; shrink_readahead_size_eio(&file->f_ra); return -EIO; } static bool filemap_range_uptodate(struct address_space *mapping, - loff_t pos, struct iov_iter *iter, struct page *page) + loff_t pos, struct iov_iter *iter, struct folio *folio) { int count; - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) return true; /* pipes can't handle partially uptodate pages */ if (iov_iter_is_pipe(iter)) return false; if (!mapping->a_ops->is_partially_uptodate) return false; - if (mapping->host->i_blkbits >= (PAGE_SHIFT + thp_order(page))) + if (mapping->host->i_blkbits >= folio_shift(folio)) return false; count = iter->count; - if (page_offset(page) > pos) { - count -= page_offset(page) - pos; + if (folio_pos(folio) > pos) { + count -= folio_pos(folio) - pos; pos = 0; } else { - pos -= page_offset(page); + pos -= folio_pos(folio); } - return mapping->a_ops->is_partially_uptodate(page, pos, count); + return mapping->a_ops->is_partially_uptodate(&folio->page, pos, count); } static int filemap_update_page(struct kiocb *iocb, struct address_space *mapping, struct iov_iter *iter, - struct page *page) + struct folio *folio) { - struct folio *folio = page_folio(page); int error; if (iocb->ki_flags & IOCB_NOWAIT) { @@ -2421,7 +2396,11 @@ static int filemap_update_page(struct kiocb *iocb, goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { filemap_invalidate_unlock_shared(mapping); - put_and_wait_on_page_locked(&folio->page, TASK_KILLABLE); + /* + * This is where we usually end up waiting for a + * previously submitted readahead to finish. + */ + folio_put_wait_locked(folio, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } error = __folio_lock_async(folio, iocb->ki_waitq); @@ -2434,14 +2413,14 @@ static int filemap_update_page(struct kiocb *iocb, goto unlock; error = 0; - if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, &folio->page)) + if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, folio)) goto unlock; error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ)) goto unlock; - error = filemap_read_page(iocb->ki_filp, mapping, &folio->page); + error = filemap_read_folio(iocb->ki_filp, mapping, folio); goto unlock_mapping; unlock: folio_unlock(folio); @@ -2452,70 +2431,72 @@ unlock_mapping: return error; } -static int filemap_create_page(struct file *file, +static int filemap_create_folio(struct file *file, struct address_space *mapping, pgoff_t index, - struct pagevec *pvec) + struct folio_batch *fbatch) { - struct page *page; + struct folio *folio; int error; - page = page_cache_alloc(mapping); - if (!page) + folio = filemap_alloc_folio(mapping_gfp_mask(mapping), 0); + if (!folio) return -ENOMEM; /* - * Protect against truncate / hole punch. Grabbing invalidate_lock here - * assures we cannot instantiate and bring uptodate new pagecache pages - * after evicting page cache during truncate and before actually - * freeing blocks. Note that we could release invalidate_lock after - * inserting the page into page cache as the locked page would then be - * enough to synchronize with hole punching. But there are code paths - * such as filemap_update_page() filling in partially uptodate pages or - * ->readpages() that need to hold invalidate_lock while mapping blocks - * for IO so let's hold the lock here as well to keep locking rules - * simple. + * Protect against truncate / hole punch. Grabbing invalidate_lock + * here assures we cannot instantiate and bring uptodate new + * pagecache folios after evicting page cache during truncate + * and before actually freeing blocks. Note that we could + * release invalidate_lock after inserting the folio into + * the page cache as the locked folio would then be enough to + * synchronize with hole punching. But there are code paths + * such as filemap_update_page() filling in partially uptodate + * pages or ->readpages() that need to hold invalidate_lock + * while mapping blocks for IO so let's hold the lock here as + * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); - error = add_to_page_cache_lru(page, mapping, index, + error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) error = AOP_TRUNCATED_PAGE; if (error) goto error; - error = filemap_read_page(file, mapping, page); + error = filemap_read_folio(file, mapping, folio); if (error) goto error; filemap_invalidate_unlock_shared(mapping); - pagevec_add(pvec, page); + folio_batch_add(fbatch, folio); return 0; error: filemap_invalidate_unlock_shared(mapping); - put_page(page); + folio_put(folio); return error; } static int filemap_readahead(struct kiocb *iocb, struct file *file, - struct address_space *mapping, struct page *page, + struct address_space *mapping, struct folio *folio, pgoff_t last_index) { + DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, folio->index); + if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; - page_cache_async_readahead(mapping, &file->f_ra, file, page, - page->index, last_index - page->index); + page_cache_async_ra(&ractl, folio, last_index - folio->index); return 0; } static int filemap_get_pages(struct kiocb *iocb, struct iov_iter *iter, - struct pagevec *pvec) + struct folio_batch *fbatch) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; struct file_ra_state *ra = &filp->f_ra; pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; - struct page *page; + struct folio *folio; int err = 0; last_index = DIV_ROUND_UP(iocb->ki_pos + iter->count, PAGE_SIZE); @@ -2523,34 +2504,35 @@ retry: if (fatal_signal_pending(current)) return -EINTR; - filemap_get_read_batch(mapping, index, last_index, pvec); - if (!pagevec_count(pvec)) { + filemap_get_read_batch(mapping, index, last_index, fbatch); + if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); - filemap_get_read_batch(mapping, index, last_index, pvec); + filemap_get_read_batch(mapping, index, last_index, fbatch); } - if (!pagevec_count(pvec)) { + if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) return -EAGAIN; - err = filemap_create_page(filp, mapping, - iocb->ki_pos >> PAGE_SHIFT, pvec); + err = filemap_create_folio(filp, mapping, + iocb->ki_pos >> PAGE_SHIFT, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } - page = pvec->pages[pagevec_count(pvec) - 1]; - if (PageReadahead(page)) { - err = filemap_readahead(iocb, filp, mapping, page, last_index); + folio = fbatch->folios[folio_batch_count(fbatch) - 1]; + if (folio_test_readahead(folio)) { + err = filemap_readahead(iocb, filp, mapping, folio, last_index); if (err) goto err; } - if (!PageUptodate(page)) { - if ((iocb->ki_flags & IOCB_WAITQ) && pagevec_count(pvec) > 1) + if (!folio_test_uptodate(folio)) { + if ((iocb->ki_flags & IOCB_WAITQ) && + folio_batch_count(fbatch) > 1) iocb->ki_flags |= IOCB_NOWAIT; - err = filemap_update_page(iocb, mapping, iter, page); + err = filemap_update_page(iocb, mapping, iter, folio); if (err) goto err; } @@ -2558,8 +2540,8 @@ retry: return 0; err: if (err < 0) - put_page(page); - if (likely(--pvec->nr)) + folio_put(folio); + if (likely(--fbatch->nr)) return 0; if (err == AOP_TRUNCATED_PAGE) goto retry; @@ -2586,7 +2568,7 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, struct file_ra_state *ra = &filp->f_ra; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; - struct pagevec pvec; + struct folio_batch fbatch; int i, error = 0; bool writably_mapped; loff_t isize, end_offset; @@ -2597,7 +2579,7 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes); - pagevec_init(&pvec); + folio_batch_init(&fbatch); do { cond_resched(); @@ -2613,7 +2595,7 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(iocb->ki_pos >= i_size_read(inode))) break; - error = filemap_get_pages(iocb, iter, &pvec); + error = filemap_get_pages(iocb, iter, &fbatch); if (error < 0) break; @@ -2627,7 +2609,7 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, */ isize = i_size_read(inode); if (unlikely(iocb->ki_pos >= isize)) - goto put_pages; + goto put_folios; end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); /* @@ -2642,33 +2624,29 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, */ if (iocb->ki_pos >> PAGE_SHIFT != ra->prev_pos >> PAGE_SHIFT) - mark_page_accessed(pvec.pages[0]); + folio_mark_accessed(fbatch.folios[0]); - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; - size_t page_size = thp_size(page); - size_t offset = iocb->ki_pos & (page_size - 1); + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; + size_t fsize = folio_size(folio); + size_t offset = iocb->ki_pos & (fsize - 1); size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos, - page_size - offset); + fsize - offset); size_t copied; - if (end_offset < page_offset(page)) + if (end_offset < folio_pos(folio)) break; if (i > 0) - mark_page_accessed(page); + folio_mark_accessed(folio); /* - * If users can be writing to this page using arbitrary - * virtual addresses, take care about potential aliasing - * before reading the page on the kernel side. + * If users can be writing to this folio using arbitrary + * virtual addresses, take care of potential aliasing + * before reading the folio on the kernel side. */ - if (writably_mapped) { - int j; - - for (j = 0; j < thp_nr_pages(page); j++) - flush_dcache_page(page + j); - } + if (writably_mapped) + flush_dcache_folio(folio); - copied = copy_page_to_iter(page, offset, bytes, iter); + copied = copy_folio_to_iter(folio, offset, bytes, iter); already_read += copied; iocb->ki_pos += copied; @@ -2679,10 +2657,10 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, break; } } -put_pages: - for (i = 0; i < pagevec_count(&pvec); i++) - put_page(pvec.pages[i]); - pagevec_reinit(&pvec); +put_folios: + for (i = 0; i < folio_batch_count(&fbatch); i++) + folio_put(fbatch.folios[i]); + folio_batch_init(&fbatch); } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); file_accessed(filp); @@ -2767,44 +2745,44 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) } EXPORT_SYMBOL(generic_file_read_iter); -static inline loff_t page_seek_hole_data(struct xa_state *xas, - struct address_space *mapping, struct page *page, +static inline loff_t folio_seek_hole_data(struct xa_state *xas, + struct address_space *mapping, struct folio *folio, loff_t start, loff_t end, bool seek_data) { const struct address_space_operations *ops = mapping->a_ops; size_t offset, bsz = i_blocksize(mapping->host); - if (xa_is_value(page) || PageUptodate(page)) + if (xa_is_value(folio) || folio_test_uptodate(folio)) return seek_data ? start : end; if (!ops->is_partially_uptodate) return seek_data ? end : start; xas_pause(xas); rcu_read_unlock(); - lock_page(page); - if (unlikely(page->mapping != mapping)) + folio_lock(folio); + if (unlikely(folio->mapping != mapping)) goto unlock; - offset = offset_in_thp(page, start) & ~(bsz - 1); + offset = offset_in_folio(folio, start) & ~(bsz - 1); do { - if (ops->is_partially_uptodate(page, offset, bsz) == seek_data) + if (ops->is_partially_uptodate(&folio->page, offset, bsz) == + seek_data) break; start = (start + bsz) & ~(bsz - 1); offset += bsz; - } while (offset < thp_size(page)); + } while (offset < folio_size(folio)); unlock: - unlock_page(page); + folio_unlock(folio); rcu_read_lock(); return start; } -static inline -unsigned int seek_page_size(struct xa_state *xas, struct page *page) +static inline size_t seek_folio_size(struct xa_state *xas, struct folio *folio) { - if (xa_is_value(page)) + if (xa_is_value(folio)) return PAGE_SIZE << xa_get_order(xas->xa, xas->xa_index); - return thp_size(page); + return folio_size(folio); } /** @@ -2831,15 +2809,15 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT); pgoff_t max = (end - 1) >> PAGE_SHIFT; bool seek_data = (whence == SEEK_DATA); - struct page *page; + struct folio *folio; if (end <= start) return -ENXIO; rcu_read_lock(); - while ((page = find_get_entry(&xas, max, XA_PRESENT))) { + while ((folio = find_get_entry(&xas, max, XA_PRESENT))) { loff_t pos = (u64)xas.xa_index << PAGE_SHIFT; - unsigned int seek_size; + size_t seek_size; if (start < pos) { if (!seek_data) @@ -2847,9 +2825,9 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, start = pos; } - seek_size = seek_page_size(&xas, page); - pos = round_up(pos + 1, seek_size); - start = page_seek_hole_data(&xas, mapping, page, start, pos, + seek_size = seek_folio_size(&xas, folio); + pos = round_up((u64)pos + 1, seek_size); + start = folio_seek_hole_data(&xas, mapping, folio, start, pos, seek_data); if (start < pos) goto unlock; @@ -2857,15 +2835,15 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, break; if (seek_size > PAGE_SIZE) xas_set(&xas, pos >> PAGE_SHIFT); - if (!xa_is_value(page)) - put_page(page); + if (!xa_is_value(folio)) + folio_put(folio); } if (seek_data) start = -ENXIO; unlock: rcu_read_unlock(); - if (page && !xa_is_value(page)) - put_page(page); + if (folio && !xa_is_value(folio)) + folio_put(folio); if (start > end) return end; return start; @@ -2874,21 +2852,20 @@ unlock: #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* - * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock + * lock_folio_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. - * @page - the page to lock. + * @folio - the folio to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * - * This works similar to lock_page_or_retry in that it can drop the mmap_lock. - * It differs in that it actually returns the page locked if it returns 1 and 0 - * if it couldn't lock the page. If we did have to drop the mmap_lock then fpin - * will point to the pinned file and needs to be fput()'ed at a later point. + * This works similar to lock_folio_or_retry in that it can drop the + * mmap_lock. It differs in that it actually returns the folio locked + * if it returns 1 and 0 if it couldn't lock the folio. If we did have + * to drop the mmap_lock then fpin will point to the pinned file and + * needs to be fput()'ed at a later point. */ -static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, +static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio, struct file **fpin) { - struct folio *folio = page_folio(page); - if (folio_trylock(folio)) return 1; @@ -2977,25 +2954,25 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, - struct page *page) + struct folio *folio) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; - struct address_space *mapping = file->f_mapping; + DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff); struct file *fpin = NULL; unsigned int mmap_miss; - pgoff_t offset = vmf->pgoff; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; + mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); - if (PageReadahead(page)) { + + if (folio_test_readahead(folio)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); - page_cache_async_readahead(mapping, ra, file, - page, offset, ra->ra_pages); + page_cache_async_ra(&ractl, folio, ra->ra_pages); } return fpin; } @@ -3014,7 +2991,7 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, * vma->vm_mm->mmap_lock must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock - * may be dropped before doing I/O or by lock_page_maybe_drop_mmap(). + * may be dropped before doing I/O or by lock_folio_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. @@ -3030,28 +3007,27 @@ vm_fault_t filemap_fault(struct vm_fault *vmf) struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - pgoff_t offset = vmf->pgoff; - pgoff_t max_off; - struct page *page; + pgoff_t max_idx, index = vmf->pgoff; + struct folio *folio; vm_fault_t ret = 0; bool mapping_locked = false; - max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); - if (unlikely(offset >= max_off)) + max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + if (unlikely(index >= max_idx)) return VM_FAULT_SIGBUS; /* * Do we have something in the page cache already? */ - page = find_get_page(mapping, offset); - if (likely(page)) { + folio = filemap_get_folio(mapping, index); + if (likely(folio)) { /* * We found the page, so try async readahead before waiting for * the lock. */ if (!(vmf->flags & FAULT_FLAG_TRIED)) - fpin = do_async_mmap_readahead(vmf, page); - if (unlikely(!PageUptodate(page))) { + fpin = do_async_mmap_readahead(vmf, folio); + if (unlikely(!folio_test_uptodate(folio))) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } @@ -3063,17 +3039,17 @@ vm_fault_t filemap_fault(struct vm_fault *vmf) fpin = do_sync_mmap_readahead(vmf); retry_find: /* - * See comment in filemap_create_page() why we need + * See comment in filemap_create_folio() why we need * invalidate_lock */ if (!mapping_locked) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } - page = pagecache_get_page(mapping, offset, + folio = __filemap_get_folio(mapping, index, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); - if (!page) { + if (!folio) { if (fpin) goto out_retry; filemap_invalidate_unlock_shared(mapping); @@ -3081,22 +3057,22 @@ retry_find: } } - if (!lock_page_maybe_drop_mmap(vmf, page, &fpin)) + if (!lock_folio_maybe_drop_mmap(vmf, folio, &fpin)) goto out_retry; /* Did it get truncated? */ - if (unlikely(compound_head(page)->mapping != mapping)) { - unlock_page(page); - put_page(page); + if (unlikely(folio->mapping != mapping)) { + folio_unlock(folio); + folio_put(folio); goto retry_find; } - VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page); + VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); /* * We have a locked page in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error. */ - if (unlikely(!PageUptodate(page))) { + if (unlikely(!folio_test_uptodate(folio))) { /* * The page was in cache and uptodate and now it is not. * Strange but possible since we didn't hold the page lock all @@ -3104,8 +3080,8 @@ retry_find: * try again. */ if (!mapping_locked) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); goto retry_find; } goto page_not_uptodate; @@ -3117,7 +3093,7 @@ retry_find: * redo the fault. */ if (fpin) { - unlock_page(page); + folio_unlock(folio); goto out_retry; } if (mapping_locked) @@ -3127,14 +3103,14 @@ retry_find: * Found the page and have a reference on it. * We must recheck i_size under page lock. */ - max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); - if (unlikely(offset >= max_off)) { - unlock_page(page); - put_page(page); + max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + if (unlikely(index >= max_idx)) { + folio_unlock(folio); + folio_put(folio); return VM_FAULT_SIGBUS; } - vmf->page = page; + vmf->page = folio_file_page(folio, index); return ret | VM_FAULT_LOCKED; page_not_uptodate: @@ -3145,10 +3121,10 @@ page_not_uptodate: * and we need to check for errors. */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); - error = filemap_read_page(file, mapping, page); + error = filemap_read_folio(file, mapping, folio); if (fpin) goto out_retry; - put_page(page); + folio_put(folio); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; @@ -3162,8 +3138,8 @@ out_retry: * re-find the vma and come back and find our hopefully still populated * page. */ - if (page) - put_page(page); + if (folio) + folio_put(folio); if (mapping_locked) filemap_invalidate_unlock_shared(mapping); if (fpin) @@ -3205,48 +3181,48 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page) return false; } -static struct page *next_uptodate_page(struct page *page, +static struct folio *next_uptodate_page(struct folio *folio, struct address_space *mapping, struct xa_state *xas, pgoff_t end_pgoff) { unsigned long max_idx; do { - if (!page) + if (!folio) return NULL; - if (xas_retry(xas, page)) + if (xas_retry(xas, folio)) continue; - if (xa_is_value(page)) + if (xa_is_value(folio)) continue; - if (PageLocked(page)) + if (folio_test_locked(folio)) continue; - if (!page_cache_get_speculative(page)) + if (!folio_try_get_rcu(folio)) continue; /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(xas))) + if (unlikely(folio != xas_reload(xas))) goto skip; - if (!PageUptodate(page) || PageReadahead(page)) + if (!folio_test_uptodate(folio) || folio_test_readahead(folio)) goto skip; - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto skip; - if (page->mapping != mapping) + if (folio->mapping != mapping) goto unlock; - if (!PageUptodate(page)) + if (!folio_test_uptodate(folio)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (xas->xa_index >= max_idx) goto unlock; - return page; + return folio; unlock: - unlock_page(page); + folio_unlock(folio); skip: - put_page(page); - } while ((page = xas_next_entry(xas, end_pgoff)) != NULL); + folio_put(folio); + } while ((folio = xas_next_entry(xas, end_pgoff)) != NULL); return NULL; } -static inline struct page *first_map_page(struct address_space *mapping, +static inline struct folio *first_map_page(struct address_space *mapping, struct xa_state *xas, pgoff_t end_pgoff) { @@ -3254,7 +3230,7 @@ static inline struct page *first_map_page(struct address_space *mapping, mapping, xas, end_pgoff); } -static inline struct page *next_map_page(struct address_space *mapping, +static inline struct folio *next_map_page(struct address_space *mapping, struct xa_state *xas, pgoff_t end_pgoff) { @@ -3271,16 +3247,17 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t last_pgoff = start_pgoff; unsigned long addr; XA_STATE(xas, &mapping->i_pages, start_pgoff); - struct page *head, *page; + struct folio *folio; + struct page *page; unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss); vm_fault_t ret = 0; rcu_read_lock(); - head = first_map_page(mapping, &xas, end_pgoff); - if (!head) + folio = first_map_page(mapping, &xas, end_pgoff); + if (!folio) goto out; - if (filemap_map_pmd(vmf, head)) { + if (filemap_map_pmd(vmf, &folio->page)) { ret = VM_FAULT_NOPAGE; goto out; } @@ -3288,7 +3265,8 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); do { - page = find_subpage(head, xas.xa_index); +again: + page = folio_file_page(folio, xas.xa_index); if (PageHWPoison(page)) goto unlock; @@ -3309,12 +3287,21 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, do_set_pte(vmf, page, addr); /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache(vma, addr, vmf->pte); - unlock_page(head); + if (folio_more_pages(folio, xas.xa_index, end_pgoff)) { + xas.xa_index++; + folio_ref_inc(folio); + goto again; + } + folio_unlock(folio); continue; unlock: - unlock_page(head); - put_page(head); - } while ((head = next_map_page(mapping, &xas, end_pgoff)) != NULL); + if (folio_more_pages(folio, xas.xa_index, end_pgoff)) { + xas.xa_index++; + goto again; + } + folio_unlock(folio); + folio_put(folio); + } while ((folio = next_map_page(mapping, &xas, end_pgoff)) != NULL); pte_unmap_unlock(vmf->pte, vmf->ptl); out: rcu_read_unlock(); @@ -3326,24 +3313,24 @@ EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; - struct page *page = vmf->page; + struct folio *folio = page_folio(vmf->page); vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(mapping->host->i_sb); file_update_time(vmf->vma->vm_file); - lock_page(page); - if (page->mapping != mapping) { - unlock_page(page); + folio_lock(folio); + if (folio->mapping != mapping) { + folio_unlock(folio); ret = VM_FAULT_NOPAGE; goto out; } /* - * We mark the page dirty already here so that when freeze is in + * We mark the folio dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will - * see the dirty page and writeprotect it again. + * see the dirty folio and writeprotect it again. */ - set_page_dirty(page); - wait_for_stable_page(page); + folio_mark_dirty(folio); + folio_wait_stable(folio); out: sb_end_pagefault(mapping->host->i_sb); return ret; @@ -3396,35 +3383,20 @@ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); -static struct page *wait_on_page_read(struct page *page) +static struct folio *do_read_cache_folio(struct address_space *mapping, + pgoff_t index, filler_t filler, void *data, gfp_t gfp) { - if (!IS_ERR(page)) { - wait_on_page_locked(page); - if (!PageUptodate(page)) { - put_page(page); - page = ERR_PTR(-EIO); - } - } - return page; -} - -static struct page *do_read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data, - gfp_t gfp) -{ - struct page *page; + struct folio *folio; int err; repeat: - page = find_get_page(mapping, index); - if (!page) { - page = __page_cache_alloc(gfp); - if (!page) + folio = filemap_get_folio(mapping, index); + if (!folio) { + folio = filemap_alloc_folio(gfp, 0); + if (!folio) return ERR_PTR(-ENOMEM); - err = add_to_page_cache_lru(page, mapping, index, gfp); + err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { - put_page(page); + folio_put(folio); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ @@ -3433,71 +3405,41 @@ repeat: filler: if (filler) - err = filler(data, page); + err = filler(data, &folio->page); else - err = mapping->a_ops->readpage(data, page); + err = mapping->a_ops->readpage(data, &folio->page); if (err < 0) { - put_page(page); + folio_put(folio); return ERR_PTR(err); } - page = wait_on_page_read(page); - if (IS_ERR(page)) - return page; + folio_wait_locked(folio); + if (!folio_test_uptodate(folio)) { + folio_put(folio); + return ERR_PTR(-EIO); + } + goto out; } - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) goto out; - /* - * Page is not up to date and may be locked due to one of the following - * case a: Page is being filled and the page lock is held - * case b: Read/write error clearing the page uptodate status - * case c: Truncation in progress (page locked) - * case d: Reclaim in progress - * - * Case a, the page will be up to date when the page is unlocked. - * There is no need to serialise on the page lock here as the page - * is pinned so the lock gives no additional protection. Even if the - * page is truncated, the data is still valid if PageUptodate as - * it's a race vs truncate race. - * Case b, the page will not be up to date - * Case c, the page may be truncated but in itself, the data may still - * be valid after IO completes as it's a read vs truncate race. The - * operation must restart if the page is not uptodate on unlock but - * otherwise serialising on page lock to stabilise the mapping gives - * no additional guarantees to the caller as the page lock is - * released before return. - * Case d, similar to truncation. If reclaim holds the page lock, it - * will be a race with remove_mapping that determines if the mapping - * is valid on unlock but otherwise the data is valid and there is - * no need to serialise with page lock. - * - * As the page lock gives no additional guarantee, we optimistically - * wait on the page to be unlocked and check if it's up to date and - * use the page if it is. Otherwise, the page lock is required to - * distinguish between the different cases. The motivation is that we - * avoid spurious serialisations and wakeups when multiple processes - * wait on the same page for IO to complete. - */ - wait_on_page_locked(page); - if (PageUptodate(page)) - goto out; - - /* Distinguish between all the cases under the safety of the lock */ - lock_page(page); + if (!folio_trylock(folio)) { + folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); + goto repeat; + } - /* Case c or d, restart the operation */ - if (!page->mapping) { - unlock_page(page); - put_page(page); + /* Folio was truncated from mapping */ + if (!folio->mapping) { + folio_unlock(folio); + folio_put(folio); goto repeat; } /* Someone else locked and filled the page in a very small window */ - if (PageUptodate(page)) { - unlock_page(page); + if (folio_test_uptodate(folio)) { + folio_unlock(folio); goto out; } @@ -3507,16 +3449,16 @@ filler: * Clear page error before actual read, PG_error will be * set again if read page fails. */ - ClearPageError(page); + folio_clear_error(folio); goto filler; out: - mark_page_accessed(page); - return page; + folio_mark_accessed(folio); + return folio; } /** - * read_cache_page - read into page cache, fill it if needed + * read_cache_folio - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read @@ -3531,10 +3473,27 @@ out: * * Return: up to date page on success, ERR_PTR() on failure. */ +struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index, + filler_t filler, void *data) +{ + return do_read_cache_folio(mapping, index, filler, data, + mapping_gfp_mask(mapping)); +} +EXPORT_SYMBOL(read_cache_folio); + +static struct page *do_read_cache_page(struct address_space *mapping, + pgoff_t index, filler_t *filler, void *data, gfp_t gfp) +{ + struct folio *folio; + + folio = do_read_cache_folio(mapping, index, filler, data, gfp); + if (IS_ERR(folio)) + return &folio->page; + return folio_file_page(folio, index); +} + struct page *read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data) + pgoff_t index, filler_t *filler, void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); @@ -3894,33 +3853,32 @@ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) EXPORT_SYMBOL(generic_file_write_iter); /** - * try_to_release_page() - release old fs-specific metadata on a page - * - * @page: the page which the kernel is trying to free - * @gfp_mask: memory allocation flags (and I/O mode) + * filemap_release_folio() - Release fs-specific metadata on a folio. + * @folio: The folio which the kernel is trying to free. + * @gfp: Memory allocation flags (and I/O mode). * - * The address_space is to try to release any data against the page - * (presumably at page->private). + * The address_space is trying to release any data attached to a folio + * (presumably at folio->private). * - * This may also be called if PG_fscache is set on a page, indicating that the - * page is known to the local caching routines. + * This will also be called if the private_2 flag is set on a page, + * indicating that the folio has other metadata associated with it. * - * The @gfp_mask argument specifies whether I/O may be performed to release - * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS). + * The @gfp argument specifies whether I/O may be performed to release + * this page (__GFP_IO), and whether the call may block + * (__GFP_RECLAIM & __GFP_FS). * - * Return: %1 if the release was successful, otherwise return zero. + * Return: %true if the release was successful, otherwise %false. */ -int try_to_release_page(struct page *page, gfp_t gfp_mask) +bool filemap_release_folio(struct folio *folio, gfp_t gfp) { - struct address_space * const mapping = page->mapping; + struct address_space * const mapping = folio->mapping; - BUG_ON(!PageLocked(page)); - if (PageWriteback(page)) - return 0; + BUG_ON(!folio_test_locked(folio)); + if (folio_test_writeback(folio)) + return false; if (mapping && mapping->a_ops->releasepage) - return mapping->a_ops->releasepage(page, gfp_mask); - return try_to_free_buffers(page); + return mapping->a_ops->releasepage(&folio->page, gfp); + return try_to_free_buffers(&folio->page); } - -EXPORT_SYMBOL(try_to_release_page); +EXPORT_SYMBOL(filemap_release_folio); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 5b6ae1da314e..749555a232a8 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -140,3 +140,14 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(grab_cache_page_write_begin); + +void delete_from_page_cache(struct page *page) +{ + return filemap_remove_folio(page_folio(page)); +} + +int try_to_release_page(struct page *page, gfp_t gfp) +{ + return filemap_release_folio(page_folio(page), gfp); +} +EXPORT_SYMBOL(try_to_release_page); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e5483347291c..f58524394dc1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2614,6 +2614,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) { struct page *head = compound_head(page); struct deferred_split *ds_queue = get_deferred_split_queue(head); + XA_STATE(xas, &head->mapping->i_pages, head->index); struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; int extra_pins, ret; @@ -2652,6 +2653,13 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) goto out; } + xas_split_alloc(&xas, head, compound_order(head), + mapping_gfp_mask(mapping) & GFP_RECLAIM_MASK); + if (xas_error(&xas)) { + ret = xas_error(&xas); + goto out; + } + anon_vma = NULL; i_mmap_lock_read(mapping); @@ -2681,13 +2689,12 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) /* block interrupt reentry in xa_lock and spinlock */ local_irq_disable(); if (mapping) { - XA_STATE(xas, &mapping->i_pages, page_index(head)); - /* * Check if the head page is present in page cache. * We assume all tail are present too, if head is there. */ - xa_lock(&mapping->i_pages); + xas_lock(&xas); + xas_reset(&xas); if (xas_load(&xas) != head) goto fail; } @@ -2703,6 +2710,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) if (mapping) { int nr = thp_nr_pages(head); + xas_split(&xas, head, thp_order(head)); if (PageSwapBacked(head)) { __mod_lruvec_page_state(head, NR_SHMEM_THPS, -nr); @@ -2719,7 +2727,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) spin_unlock(&ds_queue->split_queue_lock); fail: if (mapping) - xa_unlock(&mapping->i_pages); + xas_unlock(&xas); local_irq_enable(); remap_page(head, thp_nr_pages(head)); ret = -EBUSY; @@ -2733,6 +2741,8 @@ out_unlock: if (mapping) i_mmap_unlock_read(mapping); out: + /* Free any memory we didn't use */ + xas_nomem(&xas, 0); count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); return ret; } diff --git a/mm/internal.h b/mm/internal.h index 3b79a5c9427a..26af8a5a5be3 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -12,6 +12,8 @@ #include <linux/pagemap.h> #include <linux/tracepoint-defs.h> +struct folio_batch; + /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints @@ -74,6 +76,7 @@ static inline bool can_madv_lru_vma(struct vm_area_struct *vma) return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)); } +struct zap_details; void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, @@ -90,7 +93,13 @@ static inline void force_page_cache_readahead(struct address_space *mapping, } unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, struct pagevec *pvec, pgoff_t *indices); + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); +unsigned find_get_entries(struct address_space *mapping, pgoff_t start, + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); +void filemap_free_folio(struct address_space *mapping, struct folio *folio); +int truncate_inode_folio(struct address_space *mapping, struct folio *folio); +bool truncate_inode_partial_folio(struct folio *folio, loff_t start, + loff_t end); /** * folio_evictable - Test whether a folio is evictable. @@ -388,6 +397,7 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma); #ifdef CONFIG_MMU +void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); extern long faultin_vma_page_range(struct vm_area_struct *vma, @@ -491,8 +501,8 @@ static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, } return fpin; } - #else /* !CONFIG_MMU */ +static inline void unmap_mapping_folio(struct folio *folio) { } static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index e99101162f1a..2e1911cc3466 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1667,7 +1667,10 @@ static void collapse_file(struct mm_struct *mm, } count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC); - /* This will be less messy when we use multi-index entries */ + /* + * Ensure we have slots for all the pages in the range. This is + * almost certainly a no-op because most of the pages must be present + */ do { xas_lock_irq(&xas); xas_create_range(&xas); @@ -1892,6 +1895,9 @@ out_unlock: __mod_lruvec_page_state(new_page, NR_SHMEM, nr_none); } + /* Join all the small entries into a single multi-index entry */ + xas_set_order(&xas, start, HPAGE_PMD_ORDER); + xas_store(&xas, new_page); xa_locked: xas_unlock_irq(&xas); xa_unlocked: @@ -2013,6 +2019,10 @@ static void khugepaged_scan_file(struct mm_struct *mm, continue; } + /* + * XXX: khugepaged should compact smaller compound pages + * into a PMD sized page + */ if (PageTransCompound(page)) { result = SCAN_PAGE_COMPOUND; break; diff --git a/mm/memory.c b/mm/memory.c index 8f1de811a1dc..23f2f1300d42 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1304,6 +1304,28 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) return ret; } +/* + * Parameter block passed down to zap_pte_range in exceptional cases. + */ +struct zap_details { + struct address_space *zap_mapping; /* Check page->mapping if set */ + struct folio *single_folio; /* Locked folio to be unmapped */ +}; + +/* + * We set details->zap_mapping when we want to unmap shared but keep private + * pages. Return true if skip zapping this page, false otherwise. + */ +static inline bool +zap_skip_check_mapping(struct zap_details *details, struct page *page) +{ + if (!details || !page) + return false; + + return details->zap_mapping && + (details->zap_mapping != page_rmapping(page)); +} + static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, @@ -1443,8 +1465,8 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ - } else if (details && details->single_page && - PageTransCompound(details->single_page) && + } else if (details && details->single_folio && + folio_test_pmd_mappable(details->single_folio) && next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { spinlock_t *ptl = pmd_lock(tlb->mm, pmd); /* @@ -3332,31 +3354,30 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root, } /** - * unmap_mapping_page() - Unmap single page from processes. - * @page: The locked page to be unmapped. + * unmap_mapping_folio() - Unmap single folio from processes. + * @folio: The locked folio to be unmapped. * - * Unmap this page from any userspace process which still has it mmaped. + * Unmap this folio from any userspace process which still has it mmaped. * Typically, for efficiency, the range of nearby pages has already been * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once - * truncation or invalidation holds the lock on a page, it may find that - * the page has been remapped again: and then uses unmap_mapping_page() + * truncation or invalidation holds the lock on a folio, it may find that + * the page has been remapped again: and then uses unmap_mapping_folio() * to unmap it finally. */ -void unmap_mapping_page(struct page *page) +void unmap_mapping_folio(struct folio *folio) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; struct zap_details details = { }; pgoff_t first_index; pgoff_t last_index; - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(PageTail(page)); + VM_BUG_ON(!folio_test_locked(folio)); - first_index = page->index; - last_index = page->index + thp_nr_pages(page) - 1; + first_index = folio->index; + last_index = folio->index + folio_nr_pages(folio) - 1; details.zap_mapping = mapping; - details.single_page = page; + details.single_folio = folio; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) diff --git a/mm/migrate.c b/mm/migrate.c index cf25b00f03c8..7079e6b7dbe7 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -291,7 +291,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, { pte_t pte; swp_entry_t entry; - struct page *page; + struct folio *folio; spin_lock(ptl); pte = *ptep; @@ -302,18 +302,17 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, if (!is_migration_entry(entry)) goto out; - page = pfn_swap_entry_to_page(entry); - page = compound_head(page); + folio = page_folio(pfn_swap_entry_to_page(entry)); /* * Once page cache replacement of page migration started, page_count - * is zero; but we must not call put_and_wait_on_page_locked() without - * a ref. Use get_page_unless_zero(), and just fault again if it fails. + * is zero; but we must not call folio_put_wait_locked() without + * a ref. Use folio_try_get(), and just fault again if it fails. */ - if (!get_page_unless_zero(page)) + if (!folio_try_get(folio)) goto out; pte_unmap_unlock(ptep, ptl); - put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); + folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); return; out: pte_unmap_unlock(ptep, ptl); @@ -338,16 +337,16 @@ void migration_entry_wait_huge(struct vm_area_struct *vma, void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl; - struct page *page; + struct folio *folio; ptl = pmd_lock(mm, pmd); if (!is_pmd_migration_entry(*pmd)) goto unlock; - page = pfn_swap_entry_to_page(pmd_to_swp_entry(*pmd)); - if (!get_page_unless_zero(page)) + folio = page_folio(pfn_swap_entry_to_page(pmd_to_swp_entry(*pmd))); + if (!folio_try_get(folio)) goto unlock; spin_unlock(ptl); - put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); + folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); return; unlock: spin_unlock(ptl); @@ -434,14 +433,6 @@ int folio_migrate_mapping(struct address_space *mapping, } xas_store(&xas, newfolio); - if (nr > 1) { - int i; - - for (i = 1; i < nr; i++) { - xas_next(&xas); - xas_store(&xas, newfolio); - } - } /* * Drop cache reference from old page by unfreezing diff --git a/mm/page-writeback.c b/mm/page-writeback.c index a613f8ef6a02..91d163f8d36b 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2496,7 +2496,11 @@ void folio_account_cleaned(struct folio *folio, struct address_space *mapping, * If warn is true, then emit a warning if the folio is not uptodate and has * not been truncated. * - * The caller must hold lock_page_memcg(). + * The caller must hold lock_page_memcg(). Most callers have the folio + * locked. A few have the folio blocked from truncation through other + * means (eg zap_page_range() has it mapped and is holding the page table + * lock). This can also be called from mark_buffer_dirty(), which I + * cannot prove is always protected against truncate. */ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, int warn) diff --git a/mm/readahead.c b/mm/readahead.c index 6ae5693de28c..cf0dcf89eb69 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -196,9 +196,9 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, * Preallocate as many pages as we will need. */ for (i = 0; i < nr_to_read; i++) { - struct page *page = xa_load(&mapping->i_pages, index + i); + struct folio *folio = xa_load(&mapping->i_pages, index + i); - if (page && !xa_is_value(page)) { + if (folio && !xa_is_value(folio)) { /* * Page already present? Kick off the current batch * of contiguous pages before continuing with the @@ -212,21 +212,21 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, continue; } - page = __page_cache_alloc(gfp_mask); - if (!page) + folio = filemap_alloc_folio(gfp_mask, 0); + if (!folio) break; if (mapping->a_ops->readpages) { - page->index = index + i; - list_add(&page->lru, &page_pool); - } else if (add_to_page_cache_lru(page, mapping, index + i, + folio->index = index + i; + list_add(&folio->lru, &page_pool); + } else if (filemap_add_folio(mapping, folio, index + i, gfp_mask) < 0) { - put_page(page); + folio_put(folio); read_pages(ractl, &page_pool, true); i = ractl->_index + ractl->_nr_pages - index - 1; continue; } if (i == nr_to_read - lookahead_size) - SetPageReadahead(page); + folio_set_readahead(folio); ractl->_nr_pages++; } @@ -581,7 +581,7 @@ void page_cache_sync_ra(struct readahead_control *ractl, EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, - struct page *page, unsigned long req_count) + struct folio *folio, unsigned long req_count) { /* no read-ahead */ if (!ractl->ra->ra_pages) @@ -590,10 +590,10 @@ void page_cache_async_ra(struct readahead_control *ractl, /* * Same bit is used for PG_readahead and PG_reclaim. */ - if (PageWriteback(page)) + if (folio_test_writeback(folio)) return; - ClearPageReadahead(page); + folio_clear_readahead(folio); /* * Defer asynchronous read-ahead on IO congestion. diff --git a/mm/shmem.c b/mm/shmem.c index 18f93c2d68f1..28d627444a24 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -694,7 +694,6 @@ static int shmem_add_to_page_cache(struct page *page, struct mm_struct *charge_mm) { XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page)); - unsigned long i = 0; unsigned long nr = compound_nr(page); int error; @@ -721,20 +720,18 @@ static int shmem_add_to_page_cache(struct page *page, cgroup_throttle_swaprate(page, gfp); do { - void *entry; xas_lock_irq(&xas); - entry = xas_find_conflict(&xas); - if (entry != expected) + if (expected != xas_find_conflict(&xas)) { + xas_set_err(&xas, -EEXIST); + goto unlock; + } + if (expected && xas_find_conflict(&xas)) { xas_set_err(&xas, -EEXIST); - xas_create_range(&xas); - if (xas_error(&xas)) goto unlock; -next: - xas_store(&xas, page); - if (++i < nr) { - xas_next(&xas); - goto next; } + xas_store(&xas, page); + if (xas_error(&xas)) + goto unlock; if (PageTransHuge(page)) { count_vm_event(THP_FILE_ALLOC); __mod_lruvec_page_state(page, NR_SHMEM_THPS, nr); @@ -880,30 +877,26 @@ void shmem_unlock_mapping(struct address_space *mapping) } } -/* - * Check whether a hole-punch or truncation needs to split a huge page, - * returning true if no split was required, or the split has been successful. - * - * Eviction (or truncation to 0 size) should never need to split a huge page; - * but in rare cases might do so, if shmem_undo_range() failed to trylock on - * head, and then succeeded to trylock on tail. - * - * A split can only succeed when there are no additional references on the - * huge page: so the split below relies upon find_get_entries() having stopped - * when it found a subpage of the huge page, without getting further references. - */ -static bool shmem_punch_compound(struct page *page, pgoff_t start, pgoff_t end) +static struct folio *shmem_get_partial_folio(struct inode *inode, pgoff_t index) { - if (!PageTransCompound(page)) - return true; - - /* Just proceed to delete a huge page wholly within the range punched */ - if (PageHead(page) && - page->index >= start && page->index + HPAGE_PMD_NR <= end) - return true; + struct folio *folio; + struct page *page; - /* Try to split huge page, so we can truly punch the hole or truncate */ - return split_huge_page(page) >= 0; + /* + * At first avoid shmem_getpage(,,,SGP_READ): that fails + * beyond i_size, and reports fallocated pages as holes. + */ + folio = __filemap_get_folio(inode->i_mapping, index, + FGP_ENTRY | FGP_LOCK, 0); + if (!xa_is_value(folio)) + return folio; + /* + * But read a page back from swap if any of it is within i_size + * (although in some cases this is just a waste of time). + */ + page = NULL; + shmem_getpage(inode, index, &page, SGP_READ); + return page ? page_folio(page) : NULL; } /* @@ -917,10 +910,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; pgoff_t end = (lend + 1) >> PAGE_SHIFT; - unsigned int partial_start = lstart & (PAGE_SIZE - 1); - unsigned int partial_end = (lend + 1) & (PAGE_SIZE - 1); - struct pagevec pvec; + struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; + struct folio *folio; + bool same_folio; long nr_swaps_freed = 0; pgoff_t index; int i; @@ -931,67 +924,64 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (info->fallocend > start && info->fallocend <= end && !unfalloc) info->fallocend = start; - pagevec_init(&pvec); + folio_batch_init(&fbatch); index = start; while (index < end && find_lock_entries(mapping, index, end - 1, - &pvec, indices)) { - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; + &fbatch, indices)) { + for (i = 0; i < folio_batch_count(&fbatch); i++) { + folio = fbatch.folios[i]; index = indices[i]; - if (xa_is_value(page)) { + if (xa_is_value(folio)) { if (unfalloc) continue; nr_swaps_freed += !shmem_free_swap(mapping, - index, page); + index, folio); continue; } - index += thp_nr_pages(page) - 1; + index += folio_nr_pages(folio) - 1; - if (!unfalloc || !PageUptodate(page)) - truncate_inode_page(mapping, page); - unlock_page(page); + if (!unfalloc || !folio_test_uptodate(folio)) + truncate_inode_folio(mapping, folio); + folio_unlock(folio); } - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); + folio_batch_remove_exceptionals(&fbatch); + folio_batch_release(&fbatch); cond_resched(); index++; } - if (partial_start) { - struct page *page = NULL; - shmem_getpage(inode, start - 1, &page, SGP_READ); - if (page) { - unsigned int top = PAGE_SIZE; - if (start > end) { - top = partial_end; - partial_end = 0; - } - zero_user_segment(page, partial_start, top); - set_page_dirty(page); - unlock_page(page); - put_page(page); + same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT); + folio = shmem_get_partial_folio(inode, lstart >> PAGE_SHIFT); + if (folio) { + same_folio = lend < folio_pos(folio) + folio_size(folio); + folio_mark_dirty(folio); + if (!truncate_inode_partial_folio(folio, lstart, lend)) { + start = folio->index + folio_nr_pages(folio); + if (same_folio) + end = folio->index; } + folio_unlock(folio); + folio_put(folio); + folio = NULL; } - if (partial_end) { - struct page *page = NULL; - shmem_getpage(inode, end, &page, SGP_READ); - if (page) { - zero_user_segment(page, 0, partial_end); - set_page_dirty(page); - unlock_page(page); - put_page(page); - } + + if (!same_folio) + folio = shmem_get_partial_folio(inode, lend >> PAGE_SHIFT); + if (folio) { + folio_mark_dirty(folio); + if (!truncate_inode_partial_folio(folio, lstart, lend)) + end = folio->index; + folio_unlock(folio); + folio_put(folio); } - if (start >= end) - return; index = start; while (index < end) { cond_resched(); - if (!find_get_entries(mapping, index, end - 1, &pvec, + if (!find_get_entries(mapping, index, end - 1, &fbatch, indices)) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) @@ -1000,14 +990,14 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index = start; continue; } - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; + for (i = 0; i < folio_batch_count(&fbatch); i++) { + folio = fbatch.folios[i]; index = indices[i]; - if (xa_is_value(page)) { + if (xa_is_value(folio)) { if (unfalloc) continue; - if (shmem_free_swap(mapping, index, page)) { + if (shmem_free_swap(mapping, index, folio)) { /* Swap was replaced by page: retry */ index--; break; @@ -1016,32 +1006,24 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, continue; } - lock_page(page); + folio_lock(folio); - if (!unfalloc || !PageUptodate(page)) { - if (page_mapping(page) != mapping) { + if (!unfalloc || !folio_test_uptodate(folio)) { + if (folio_mapping(folio) != mapping) { /* Page was replaced by swap: retry */ - unlock_page(page); + folio_unlock(folio); index--; break; } - VM_BUG_ON_PAGE(PageWriteback(page), page); - if (shmem_punch_compound(page, start, end)) - truncate_inode_page(mapping, page); - else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { - /* Wipe the page and don't get stuck */ - clear_highpage(page); - flush_dcache_page(page); - set_page_dirty(page); - if (index < - round_up(start, HPAGE_PMD_NR)) - start = index + 1; - } + VM_BUG_ON_FOLIO(folio_test_writeback(folio), + folio); + truncate_inode_folio(mapping, folio); } - unlock_page(page); + index = folio->index + folio_nr_pages(folio) - 1; + folio_unlock(folio); } - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); + folio_batch_remove_exceptionals(&fbatch); + folio_batch_release(&fbatch); index++; } diff --git a/mm/swap.c b/mm/swap.c index e8c9dc6d0377..74f6b311d7ee 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1077,24 +1077,24 @@ void __pagevec_lru_add(struct pagevec *pvec) } /** - * pagevec_remove_exceptionals - pagevec exceptionals pruning - * @pvec: The pagevec to prune + * folio_batch_remove_exceptionals() - Prune non-folios from a batch. + * @fbatch: The batch to prune * - * find_get_entries() fills both pages and XArray value entries (aka - * exceptional entries) into the pagevec. This function prunes all - * exceptionals from @pvec without leaving holes, so that it can be - * passed on to page-only pagevec operations. + * find_get_entries() fills a batch with both folios and shadow/swap/DAX + * entries. This function prunes all the non-folio entries from @fbatch + * without leaving holes, so that it can be passed on to folio-only batch + * operations. */ -void pagevec_remove_exceptionals(struct pagevec *pvec) +void folio_batch_remove_exceptionals(struct folio_batch *fbatch) { - int i, j; + unsigned int i, j; - for (i = 0, j = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; - if (!xa_is_value(page)) - pvec->pages[j++] = page; + for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) { + struct folio *folio = fbatch->folios[i]; + if (!xa_is_value(folio)) + fbatch->folios[j++] = folio; } - pvec->nr = j; + fbatch->nr = j; } /** diff --git a/mm/truncate.c b/mm/truncate.c index cc83a3f7c1ad..5c87cdc70e7b 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -56,11 +56,11 @@ static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, /* * Unconditionally remove exceptional entries. Usually called from truncate - * path. Note that the pagevec may be altered by this function by removing - * exceptional entries similar to what pagevec_remove_exceptionals does. + * path. Note that the folio_batch may be altered by this function by removing + * exceptional entries similar to what folio_batch_remove_exceptionals() does. */ -static void truncate_exceptional_pvec_entries(struct address_space *mapping, - struct pagevec *pvec, pgoff_t *indices) +static void truncate_folio_batch_exceptionals(struct address_space *mapping, + struct folio_batch *fbatch, pgoff_t *indices) { int i, j; bool dax; @@ -69,11 +69,11 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, if (shmem_mapping(mapping)) return; - for (j = 0; j < pagevec_count(pvec); j++) - if (xa_is_value(pvec->pages[j])) + for (j = 0; j < folio_batch_count(fbatch); j++) + if (xa_is_value(fbatch->folios[j])) break; - if (j == pagevec_count(pvec)) + if (j == folio_batch_count(fbatch)) return; dax = dax_mapping(mapping); @@ -82,12 +82,12 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, xa_lock_irq(&mapping->i_pages); } - for (i = j; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; + for (i = j; i < folio_batch_count(fbatch); i++) { + struct folio *folio = fbatch->folios[i]; pgoff_t index = indices[i]; - if (!xa_is_value(page)) { - pvec->pages[j++] = page; + if (!xa_is_value(folio)) { + fbatch->folios[j++] = folio; continue; } @@ -96,7 +96,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, continue; } - __clear_shadow_entry(mapping, index, page); + __clear_shadow_entry(mapping, index, folio); } if (!dax) { @@ -105,7 +105,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); } - pvec->nr = j; + fbatch->nr = j; } /* @@ -177,21 +177,21 @@ void do_invalidatepage(struct page *page, unsigned int offset, * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ -static void truncate_cleanup_page(struct page *page) +static void truncate_cleanup_folio(struct folio *folio) { - if (page_mapped(page)) - unmap_mapping_page(page); + if (folio_mapped(folio)) + unmap_mapping_folio(folio); - if (page_has_private(page)) - do_invalidatepage(page, 0, thp_size(page)); + if (folio_has_private(folio)) + do_invalidatepage(&folio->page, 0, folio_size(folio)); /* * Some filesystems seem to re-dirty the page even after * the VM has canceled the dirty bit (eg ext3 journaling). * Hence dirty accounting check is placed after invalidation. */ - cancel_dirty_page(page); - ClearPageMappedToDisk(page); + folio_cancel_dirty(folio); + folio_clear_mappedtodisk(folio); } /* @@ -218,23 +218,75 @@ invalidate_complete_page(struct address_space *mapping, struct page *page) return ret; } -int truncate_inode_page(struct address_space *mapping, struct page *page) +int truncate_inode_folio(struct address_space *mapping, struct folio *folio) { - VM_BUG_ON_PAGE(PageTail(page), page); - - if (page->mapping != mapping) + if (folio->mapping != mapping) return -EIO; - truncate_cleanup_page(page); - delete_from_page_cache(page); + truncate_cleanup_folio(folio); + filemap_remove_folio(folio); return 0; } /* + * Handle partial folios. The folio may be entirely within the + * range if a split has raced with us. If not, we zero the part of the + * folio that's within the [start, end] range, and then split the folio if + * it's large. split_page_range() will discard pages which now lie beyond + * i_size, and we rely on the caller to discard pages which lie within a + * newly created hole. + * + * Returns false if splitting failed so the caller can avoid + * discarding the entire folio which is stubbornly unsplit. + */ +bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) +{ + loff_t pos = folio_pos(folio); + unsigned int offset, length; + + if (pos < start) + offset = start - pos; + else + offset = 0; + length = folio_size(folio); + if (pos + length <= (u64)end) + length = length - offset; + else + length = end + 1 - pos - offset; + + folio_wait_writeback(folio); + if (length == folio_size(folio)) { + truncate_inode_folio(folio->mapping, folio); + return true; + } + + /* + * We may be zeroing pages we're about to discard, but it avoids + * doing a complex calculation here, and then doing the zeroing + * anyway if the page split fails. + */ + folio_zero_range(folio, offset, length); + + cleancache_invalidate_page(folio->mapping, &folio->page); + if (folio_has_private(folio)) + do_invalidatepage(&folio->page, offset, length); + if (!folio_test_large(folio)) + return true; + if (split_huge_page(&folio->page) == 0) + return true; + if (folio_test_dirty(folio)) + return false; + truncate_inode_folio(folio->mapping, folio); + return true; +} + +/* * Used to get rid of pages on hardware memory corruption. */ int generic_error_remove_page(struct address_space *mapping, struct page *page) { + VM_BUG_ON_PAGE(PageTail(page), page); + if (!mapping) return -EINVAL; /* @@ -243,7 +295,7 @@ int generic_error_remove_page(struct address_space *mapping, struct page *page) */ if (!S_ISREG(mapping->host->i_mode)) return -EIO; - return truncate_inode_page(mapping, page); + return truncate_inode_folio(mapping, page_folio(page)); } EXPORT_SYMBOL(generic_error_remove_page); @@ -294,20 +346,16 @@ void truncate_inode_pages_range(struct address_space *mapping, { pgoff_t start; /* inclusive */ pgoff_t end; /* exclusive */ - unsigned int partial_start; /* inclusive */ - unsigned int partial_end; /* exclusive */ - struct pagevec pvec; + struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; + struct folio *folio; + bool same_folio; if (mapping_empty(mapping)) goto out; - /* Offsets within partial pages */ - partial_start = lstart & (PAGE_SIZE - 1); - partial_end = (lend + 1) & (PAGE_SIZE - 1); - /* * 'start' and 'end' always covers the range of pages to be fully * truncated. Partial pages are covered with 'partial_start' at the @@ -325,64 +373,49 @@ void truncate_inode_pages_range(struct address_space *mapping, else end = (lend + 1) >> PAGE_SHIFT; - pagevec_init(&pvec); + folio_batch_init(&fbatch); index = start; while (index < end && find_lock_entries(mapping, index, end - 1, - &pvec, indices)) { - index = indices[pagevec_count(&pvec) - 1] + 1; - truncate_exceptional_pvec_entries(mapping, &pvec, indices); - for (i = 0; i < pagevec_count(&pvec); i++) - truncate_cleanup_page(pvec.pages[i]); - delete_from_page_cache_batch(mapping, &pvec); - for (i = 0; i < pagevec_count(&pvec); i++) - unlock_page(pvec.pages[i]); - pagevec_release(&pvec); + &fbatch, indices)) { + index = indices[folio_batch_count(&fbatch) - 1] + 1; + truncate_folio_batch_exceptionals(mapping, &fbatch, indices); + for (i = 0; i < folio_batch_count(&fbatch); i++) + truncate_cleanup_folio(fbatch.folios[i]); + delete_from_page_cache_batch(mapping, &fbatch); + for (i = 0; i < folio_batch_count(&fbatch); i++) + folio_unlock(fbatch.folios[i]); + folio_batch_release(&fbatch); cond_resched(); } - if (partial_start) { - struct page *page = find_lock_page(mapping, start - 1); - if (page) { - unsigned int top = PAGE_SIZE; - if (start > end) { - /* Truncation within a single page */ - top = partial_end; - partial_end = 0; - } - wait_on_page_writeback(page); - zero_user_segment(page, partial_start, top); - cleancache_invalidate_page(mapping, page); - if (page_has_private(page)) - do_invalidatepage(page, partial_start, - top - partial_start); - unlock_page(page); - put_page(page); + same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT); + folio = __filemap_get_folio(mapping, lstart >> PAGE_SHIFT, FGP_LOCK, 0); + if (folio) { + same_folio = lend < folio_pos(folio) + folio_size(folio); + if (!truncate_inode_partial_folio(folio, lstart, lend)) { + start = folio->index + folio_nr_pages(folio); + if (same_folio) + end = folio->index; } + folio_unlock(folio); + folio_put(folio); + folio = NULL; } - if (partial_end) { - struct page *page = find_lock_page(mapping, end); - if (page) { - wait_on_page_writeback(page); - zero_user_segment(page, 0, partial_end); - cleancache_invalidate_page(mapping, page); - if (page_has_private(page)) - do_invalidatepage(page, 0, - partial_end); - unlock_page(page); - put_page(page); - } + + if (!same_folio) + folio = __filemap_get_folio(mapping, lend >> PAGE_SHIFT, + FGP_LOCK, 0); + if (folio) { + if (!truncate_inode_partial_folio(folio, lstart, lend)) + end = folio->index; + folio_unlock(folio); + folio_put(folio); } - /* - * If the truncation happened within a single page no pages - * will be released, just zeroed, so we can bail out now. - */ - if (start >= end) - goto out; index = start; - for ( ; ; ) { + while (index < end) { cond_resched(); - if (!find_get_entries(mapping, index, end - 1, &pvec, + if (!find_get_entries(mapping, index, end - 1, &fbatch, indices)) { /* If all gone from start onwards, we're done */ if (index == start) @@ -392,23 +425,24 @@ void truncate_inode_pages_range(struct address_space *mapping, continue; } - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; - if (xa_is_value(page)) + if (xa_is_value(folio)) continue; - lock_page(page); - WARN_ON(page_to_index(page) != index); - wait_on_page_writeback(page); - truncate_inode_page(mapping, page); - unlock_page(page); + folio_lock(folio); + VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); + folio_wait_writeback(folio); + truncate_inode_folio(mapping, folio); + folio_unlock(folio); + index = folio_index(folio) + folio_nr_pages(folio) - 1; } - truncate_exceptional_pvec_entries(mapping, &pvec, indices); - pagevec_release(&pvec); + truncate_folio_batch_exceptionals(mapping, &fbatch, indices); + folio_batch_release(&fbatch); index++; } @@ -479,16 +513,16 @@ static unsigned long __invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_pagevec) { pgoff_t indices[PAGEVEC_SIZE]; - struct pagevec pvec; + struct folio_batch fbatch; pgoff_t index = start; unsigned long ret; unsigned long count = 0; int i; - pagevec_init(&pvec); - while (find_lock_entries(mapping, index, end, &pvec, indices)) { - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; + folio_batch_init(&fbatch); + while (find_lock_entries(mapping, index, end, &fbatch, indices)) { + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct page *page = &fbatch.folios[i]->page; /* We rely upon deletion not changing page->index */ index = indices[i]; @@ -515,8 +549,8 @@ static unsigned long __invalidate_mapping_pages(struct address_space *mapping, } count += ret; } - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); + folio_batch_remove_exceptionals(&fbatch); + folio_batch_release(&fbatch); cond_resched(); index++; } @@ -568,31 +602,29 @@ void invalidate_mapping_pagevec(struct address_space *mapping, * shrink_page_list() has a temp ref on them, or because they're transiently * sitting in the lru_cache_add() pagevecs. */ -static int -invalidate_complete_page2(struct address_space *mapping, struct page *page) +static int invalidate_complete_folio2(struct address_space *mapping, + struct folio *folio) { - if (page->mapping != mapping) + if (folio->mapping != mapping) return 0; - if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) + if (folio_has_private(folio) && + !filemap_release_folio(folio, GFP_KERNEL)) return 0; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); - if (PageDirty(page)) + if (folio_test_dirty(folio)) goto failed; - BUG_ON(page_has_private(page)); - __delete_from_page_cache(page, NULL); + BUG_ON(folio_has_private(folio)); + __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); - if (mapping->a_ops->freepage) - mapping->a_ops->freepage(page); - - put_page(page); /* pagecache ref */ + filemap_free_folio(mapping, folio); return 1; failed: xa_unlock_irq(&mapping->i_pages); @@ -600,13 +632,13 @@ failed: return 0; } -static int do_launder_page(struct address_space *mapping, struct page *page) +static int do_launder_folio(struct address_space *mapping, struct folio *folio) { - if (!PageDirty(page)) + if (!folio_test_dirty(folio)) return 0; - if (page->mapping != mapping || mapping->a_ops->launder_page == NULL) + if (folio->mapping != mapping || mapping->a_ops->launder_page == NULL) return 0; - return mapping->a_ops->launder_page(page); + return mapping->a_ops->launder_page(&folio->page); } /** @@ -624,7 +656,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { pgoff_t indices[PAGEVEC_SIZE]; - struct pagevec pvec; + struct folio_batch fbatch; pgoff_t index; int i; int ret = 0; @@ -634,25 +666,25 @@ int invalidate_inode_pages2_range(struct address_space *mapping, if (mapping_empty(mapping)) goto out; - pagevec_init(&pvec); + folio_batch_init(&fbatch); index = start; - while (find_get_entries(mapping, index, end, &pvec, indices)) { - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; + while (find_get_entries(mapping, index, end, &fbatch, indices)) { + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; - /* We rely upon deletion not changing page->index */ + /* We rely upon deletion not changing folio->index */ index = indices[i]; - if (xa_is_value(page)) { + if (xa_is_value(folio)) { if (!invalidate_exceptional_entry2(mapping, - index, page)) + index, folio)) ret = -EBUSY; continue; } - if (!did_range_unmap && page_mapped(page)) { + if (!did_range_unmap && folio_mapped(folio)) { /* - * If page is mapped, before taking its lock, + * If folio is mapped, before taking its lock, * zap the rest of the file in one hit. */ unmap_mapping_pages(mapping, index, @@ -660,29 +692,29 @@ int invalidate_inode_pages2_range(struct address_space *mapping, did_range_unmap = 1; } - lock_page(page); - WARN_ON(page_to_index(page) != index); - if (page->mapping != mapping) { - unlock_page(page); + folio_lock(folio); + VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); + if (folio->mapping != mapping) { + folio_unlock(folio); continue; } - wait_on_page_writeback(page); + folio_wait_writeback(folio); - if (page_mapped(page)) - unmap_mapping_page(page); - BUG_ON(page_mapped(page)); + if (folio_mapped(folio)) + unmap_mapping_folio(folio); + BUG_ON(folio_mapped(folio)); - ret2 = do_launder_page(mapping, page); + ret2 = do_launder_folio(mapping, folio); if (ret2 == 0) { - if (!invalidate_complete_page2(mapping, page)) + if (!invalidate_complete_folio2(mapping, folio)) ret2 = -EBUSY; } if (ret2 < 0) ret = ret2; - unlock_page(page); + folio_unlock(folio); } - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); + folio_batch_remove_exceptionals(&fbatch); + folio_batch_release(&fbatch); cond_resched(); index++; } |