diff options
Diffstat (limited to 'include/linux/pagemap.h')
| -rw-r--r-- | include/linux/pagemap.h | 386 |
1 files changed, 280 insertions, 106 deletions
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 605246452305..bbccb4044222 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -16,7 +16,121 @@ #include <linux/hardirq.h> /* for in_interrupt() */ #include <linux/hugetlb_inline.h> -struct pagevec; +struct folio_batch; + +unsigned long invalidate_mapping_pages(struct address_space *mapping, + pgoff_t start, pgoff_t end); + +static inline void invalidate_remote_inode(struct inode *inode) +{ + if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode)) + invalidate_mapping_pages(inode->i_mapping, 0, -1); +} +int invalidate_inode_pages2(struct address_space *mapping); +int invalidate_inode_pages2_range(struct address_space *mapping, + pgoff_t start, pgoff_t end); +int write_inode_now(struct inode *, int sync); +int filemap_fdatawrite(struct address_space *); +int filemap_flush(struct address_space *); +int filemap_fdatawait_keep_errors(struct address_space *mapping); +int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); +int filemap_fdatawait_range_keep_errors(struct address_space *mapping, + loff_t start_byte, loff_t end_byte); + +static inline int filemap_fdatawait(struct address_space *mapping) +{ + return filemap_fdatawait_range(mapping, 0, LLONG_MAX); +} + +bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); +int filemap_write_and_wait_range(struct address_space *mapping, + loff_t lstart, loff_t lend); +int __filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end, int sync_mode); +int filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end); +int filemap_check_errors(struct address_space *mapping); +void __filemap_set_wb_err(struct address_space *mapping, int err); +int filemap_fdatawrite_wbc(struct address_space *mapping, + struct writeback_control *wbc); + +static inline int filemap_write_and_wait(struct address_space *mapping) +{ + return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); +} + +/** + * filemap_set_wb_err - set a writeback error on an address_space + * @mapping: mapping in which to set writeback error + * @err: error to be set in mapping + * + * When writeback fails in some way, we must record that error so that + * userspace can be informed when fsync and the like are called. We endeavor + * to report errors on any file that was open at the time of the error. Some + * internal callers also need to know when writeback errors have occurred. + * + * When a writeback error occurs, most filesystems will want to call + * filemap_set_wb_err to record the error in the mapping so that it will be + * automatically reported whenever fsync is called on the file. + */ +static inline void filemap_set_wb_err(struct address_space *mapping, int err) +{ + /* Fastpath for common case of no error */ + if (unlikely(err)) + __filemap_set_wb_err(mapping, err); +} + +/** + * filemap_check_wb_err - has an error occurred since the mark was sampled? + * @mapping: mapping to check for writeback errors + * @since: previously-sampled errseq_t + * + * Grab the errseq_t value from the mapping, and see if it has changed "since" + * the given value was sampled. + * + * If it has then report the latest error set, otherwise return 0. + */ +static inline int filemap_check_wb_err(struct address_space *mapping, + errseq_t since) +{ + return errseq_check(&mapping->wb_err, since); +} + +/** + * filemap_sample_wb_err - sample the current errseq_t to test for later errors + * @mapping: mapping to be sampled + * + * Writeback errors are always reported relative to a particular sample point + * in the past. This function provides those sample points. + */ +static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) +{ + return errseq_sample(&mapping->wb_err); +} + +/** + * file_sample_sb_err - sample the current errseq_t to test for later errors + * @file: file pointer to be sampled + * + * Grab the most current superblock-level errseq_t value for the given + * struct file. + */ +static inline errseq_t file_sample_sb_err(struct file *file) +{ + return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); +} + +/* + * Flush file data before changing attributes. Caller must hold any locks + * required to prevent further writes to this file until we're done setting + * flags. + */ +static inline int inode_drain_writes(struct inode *inode) +{ + inode_dio_wait(inode); + return filemap_write_and_wait(inode->i_mapping); +} static inline bool mapping_empty(struct address_space *mapping) { @@ -192,9 +306,14 @@ static inline void mapping_set_large_folios(struct address_space *mapping) __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } +/* + * Large folio support currently depends on THP. These dependencies are + * being worked on but are not yet fixed. + */ static inline bool mapping_large_folio_support(struct address_space *mapping) { - return test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); + return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } static inline int filemap_nr_thps(struct address_space *mapping) @@ -212,7 +331,7 @@ static inline void filemap_nr_thps_inc(struct address_space *mapping) if (!mapping_large_folio_support(mapping)) atomic_inc(&mapping->nr_thps); #else - WARN_ON_ONCE(1); + WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } @@ -222,12 +341,10 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) if (!mapping_large_folio_support(mapping)) atomic_dec(&mapping->nr_thps); #else - WARN_ON_ONCE(1); + WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } -void release_pages(struct page **pages, int nr); - struct address_space *page_mapping(struct page *); struct address_space *folio_mapping(struct folio *); struct address_space *swapcache_mapping(struct folio *); @@ -283,17 +400,6 @@ static inline struct inode *folio_inode(struct folio *folio) return folio->mapping->host; } -static inline bool page_cache_add_speculative(struct page *page, int count) -{ - VM_BUG_ON_PAGE(PageTail(page), page); - return folio_ref_try_add_rcu((struct folio *)page, count); -} - -static inline bool page_cache_get_speculative(struct page *page) -{ - return page_cache_add_speculative(page, 1); -} - /** * folio_attach_private - Attach private data to a folio. * @folio: Folio to attach data to. @@ -384,7 +490,7 @@ static inline gfp_t readahead_gfp_mask(struct address_space *x) return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; } -typedef int filler_t(void *, struct page *); +typedef int filler_t(struct file *, struct folio *); pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); @@ -424,6 +530,24 @@ static inline struct folio *filemap_get_folio(struct address_space *mapping, } /** + * filemap_lock_folio - Find and lock a folio. + * @mapping: The address_space to search. + * @index: The page index. + * + * Looks up the page cache entry at @mapping & @index. If a folio is + * present, it is returned locked with an increased refcount. + * + * Context: May sleep. + * Return: A folio or %NULL if there is no folio in the cache for this + * index. Will not return a shadow, swap or DAX entry. + */ +static inline struct folio *filemap_lock_folio(struct address_space *mapping, + pgoff_t index) +{ + return __filemap_get_folio(mapping, index, FGP_LOCK, 0); +} + +/** * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index @@ -512,15 +636,6 @@ 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) /** @@ -601,20 +716,10 @@ 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); -static inline unsigned find_get_pages(struct address_space *mapping, - pgoff_t *start, unsigned int nr_pages, - struct page **pages) -{ - return find_get_pages_range(mapping, start, (pgoff_t)-1, nr_pages, - pages); -} -unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, - unsigned int nr_pages, struct page **pages); +unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, + pgoff_t end, struct folio_batch *fbatch); +unsigned filemap_get_folios_contig(struct address_space *mapping, + pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages); @@ -627,7 +732,7 @@ static inline unsigned find_get_pages_tag(struct address_space *mapping, } struct page *grab_cache_page_write_begin(struct address_space *mapping, - pgoff_t index, unsigned flags); + pgoff_t index); /* * Returns locked page at given index in given cache, creating it if needed. @@ -638,17 +743,23 @@ 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, struct file *file); +struct page *read_cache_page(struct address_space *, pgoff_t index, + filler_t *filler, struct file *file); 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, - struct list_head *pages, filler_t *filler, void *data); static inline struct page *read_mapping_page(struct address_space *mapping, - pgoff_t index, void *data) + pgoff_t index, struct file *file) +{ + return read_cache_page(mapping, index, NULL, file); +} + +static inline struct folio *read_mapping_folio(struct address_space *mapping, + pgoff_t index, struct file *file) { - return read_cache_page(mapping, index, NULL, data); + return read_cache_folio(mapping, index, NULL, file); } /* @@ -717,6 +828,17 @@ static inline loff_t folio_file_pos(struct folio *folio) return page_file_offset(&folio->page); } +/* + * Get the offset in PAGE_SIZE (even for hugetlb folios). + * (TODO: hugetlb folios should have ->index in PAGE_SIZE) + */ +static inline pgoff_t folio_pgoff(struct folio *folio) +{ + if (unlikely(folio_test_hugetlb(folio))) + return hugetlb_basepage_index(&folio->page); + return folio->index; +} + extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, unsigned long address); @@ -763,6 +885,18 @@ bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, void unlock_page(struct page *page); void folio_unlock(struct folio *folio); +/** + * folio_trylock() - Attempt to lock a folio. + * @folio: The folio to attempt to lock. + * + * Sometimes it is undesirable to wait for a folio to be unlocked (eg + * when the locks are being taken in the wrong order, or if making + * progress through a batch of folios is more important than processing + * them in order). Usually folio_lock() is the correct function to call. + * + * Context: Any context. + * Return: Whether the lock was successfully acquired. + */ static inline bool folio_trylock(struct folio *folio) { return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0))); @@ -776,6 +910,28 @@ static inline int trylock_page(struct page *page) return folio_trylock(page_folio(page)); } +/** + * folio_lock() - Lock this folio. + * @folio: The folio to lock. + * + * The folio lock protects against many things, probably more than it + * should. It is primarily held while a folio is being brought uptodate, + * either from its backing file or from swap. It is also held while a + * folio is being truncated from its address_space, so holding the lock + * is sufficient to keep folio->mapping stable. + * + * The folio lock is also held while write() is modifying the page to + * provide POSIX atomicity guarantees (as long as the write does not + * cross a page boundary). Other modifications to the data in the folio + * do not hold the folio lock and can race with writes, eg DMA and stores + * to mapped pages. + * + * Context: May sleep. If you need to acquire the locks of two or + * more folios, they must be in order of ascending index, if they are + * in the same address_space. If they are in different address_spaces, + * acquire the lock of the folio which belongs to the address_space which + * has the lowest address in memory first. + */ static inline void folio_lock(struct folio *folio) { might_sleep(); @@ -783,8 +939,16 @@ static inline void folio_lock(struct folio *folio) __folio_lock(folio); } -/* - * lock_page may only be called if we have the page's inode pinned. +/** + * lock_page() - Lock the folio containing this page. + * @page: The page to lock. + * + * See folio_lock() for a description of what the lock protects. + * This is a legacy function and new code should probably use folio_lock() + * instead. + * + * Context: May sleep. Pages in the same folio share a lock, so do not + * attempt to lock two pages which share a folio. */ static inline void lock_page(struct page *page) { @@ -796,6 +960,16 @@ static inline void lock_page(struct page *page) __folio_lock(folio); } +/** + * folio_lock_killable() - Lock this folio, interruptible by a fatal signal. + * @folio: The folio to lock. + * + * Attempts to lock the folio, like folio_lock(), except that the sleep + * to acquire the lock is interruptible by a fatal signal. + * + * Context: May sleep; see folio_lock(). + * Return: 0 if the lock was acquired; -EINTR if a fatal signal was received. + */ static inline int folio_lock_killable(struct folio *folio) { might_sleep(); @@ -815,19 +989,16 @@ static inline int lock_page_killable(struct page *page) } /* - * lock_page_or_retry - Lock the page, unless this would block and the + * folio_lock_or_retry - Lock the folio, unless this would block and the * caller indicated that it can handle a retry. * * Return value and mmap_lock implications depend on flags; see * __folio_lock_or_retry(). */ -static inline bool lock_page_or_retry(struct page *page, struct mm_struct *mm, - unsigned int flags) +static inline bool folio_lock_or_retry(struct folio *folio, + struct mm_struct *mm, unsigned int flags) { - struct folio *folio; might_sleep(); - - folio = page_folio(page); return folio_trylock(folio) || __folio_lock_or_retry(folio, mm, flags); } @@ -842,8 +1013,8 @@ int folio_wait_bit_killable(struct folio *folio, int bit_nr); * Wait for a folio to be unlocked. * * This must be called with the caller "holding" the folio, - * ie with increased "page->count" so that the folio won't - * go away during the wait.. + * ie with increased folio reference count so that the folio won't + * go away during the wait. */ static inline void folio_wait_locked(struct folio *folio) { @@ -868,7 +1039,6 @@ 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); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); @@ -882,13 +1052,7 @@ static inline void __set_page_dirty(struct page *page, { __folio_mark_dirty(page_folio(page), mapping, warn); } -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_account_cleaned(struct folio *folio, struct bdi_writeback *wb); void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) { @@ -896,12 +1060,9 @@ static inline void folio_cancel_dirty(struct folio *folio) if (folio_test_dirty(folio)) __folio_cancel_dirty(folio); } -static inline void cancel_dirty_page(struct page *page) -{ - folio_cancel_dirty(page_folio(page)); -} bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); +void folio_invalidate(struct folio *folio, size_t offset, size_t length); int __must_check folio_write_one(struct folio *folio); static inline int __must_check write_one_page(struct page *page) { @@ -909,8 +1070,14 @@ static inline int __must_check write_one_page(struct page *page) } int __set_page_dirty_nobuffers(struct page *page); -int __set_page_dirty_no_writeback(struct page *page); +bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); +#ifdef CONFIG_MIGRATION +int filemap_migrate_folio(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode); +#else +#define filemap_migrate_folio NULL +#endif void page_endio(struct page *page, bool is_write, int err); void folio_end_private_2(struct folio *folio); @@ -926,43 +1093,58 @@ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter); * Fault in userspace address range. */ size_t fault_in_writeable(char __user *uaddr, size_t size); +size_t fault_in_subpage_writeable(char __user *uaddr, size_t size); size_t fault_in_safe_writeable(const char __user *uaddr, size_t size); size_t fault_in_readable(const char __user *uaddr, size_t size); -int add_to_page_cache_locked(struct page *page, struct address_space *mapping, - pgoff_t index, gfp_t gfp); 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); 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); -/* - * Like add_to_page_cache_locked, but used to add newly allocated pages: - * the page is new, so we can just run __SetPageLocked() against it. - */ -static inline int add_to_page_cache(struct page *page, - struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) -{ - int error; - - __SetPageLocked(page); - error = add_to_page_cache_locked(page, mapping, offset, gfp_mask); - if (unlikely(error)) - __ClearPageLocked(page); - return error; -} - /* Must be non-static for BPF error injection */ int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp); +bool filemap_range_has_writeback(struct address_space *mapping, + loff_t start_byte, loff_t end_byte); + +/** + * filemap_range_needs_writeback - check if range potentially needs writeback + * @mapping: address space within which to check + * @start_byte: offset in bytes where the range starts + * @end_byte: offset in bytes where the range ends (inclusive) + * + * Find at least one page in the range supplied, usually used to check if + * direct writing in this range will trigger a writeback. Used by O_DIRECT + * read/write with IOCB_NOWAIT, to see if the caller needs to do + * filemap_write_and_wait_range() before proceeding. + * + * Return: %true if the caller should do filemap_write_and_wait_range() before + * doing O_DIRECT to a page in this range, %false otherwise. + */ +static inline bool filemap_range_needs_writeback(struct address_space *mapping, + loff_t start_byte, + loff_t end_byte) +{ + if (!mapping->nrpages) + return false; + if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && + !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) + return false; + return filemap_range_has_writeback(mapping, start_byte, end_byte); +} + /** * struct readahead_control - Describes a readahead request. * @@ -987,6 +1169,8 @@ struct readahead_control { pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; + bool _workingset; + unsigned long _pflags; }; #define DEFINE_READAHEAD(ractl, f, r, m, i) \ @@ -1002,7 +1186,7 @@ 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); @@ -1034,7 +1218,7 @@ void page_cache_sync_readahead(struct address_space *mapping, * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. - * @page: The page at @index which triggered the readahead call. + * @folio: The folio at @index which triggered the readahead call. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * @@ -1046,10 +1230,10 @@ void page_cache_sync_readahead(struct address_space *mapping, static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, - struct page *page, pgoff_t index, unsigned long req_count) + struct folio *folio, 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, folio, req_count); } static inline struct folio *__readahead_folio(struct readahead_control *ractl) @@ -1126,16 +1310,6 @@ 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; } |