diff options
Diffstat (limited to 'include/linux/pagemap.h')
| -rw-r--r-- | include/linux/pagemap.h | 784 |
1 files changed, 453 insertions, 331 deletions
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 29e1f9e76eb6..31a848485ad9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -30,13 +30,21 @@ static inline void invalidate_remote_inode(struct inode *inode) int invalidate_inode_pages2(struct address_space *mapping); int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end); +int kiocb_invalidate_pages(struct kiocb *iocb, size_t count); +void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count); +int filemap_invalidate_pages(struct address_space *mapping, + loff_t pos, loff_t end, bool nowait); + int write_inode_now(struct inode *, int sync); int filemap_fdatawrite(struct address_space *); int filemap_flush(struct address_space *); +int filemap_flush_nr(struct address_space *mapping, long *nr_to_write); 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); +int filemap_invalidate_inode(struct inode *inode, bool flush, + loff_t start, loff_t end); static inline int filemap_fdatawait(struct address_space *mapping) { @@ -46,14 +54,11 @@ static inline int filemap_fdatawait(struct address_space *mapping) 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); +int kiocb_write_and_wait(struct kiocb *iocb, size_t count); static inline int filemap_write_and_wait(struct address_space *mapping) { @@ -132,7 +137,7 @@ static inline int inode_drain_writes(struct inode *inode) return filemap_write_and_wait(inode->i_mapping); } -static inline bool mapping_empty(struct address_space *mapping) +static inline bool mapping_empty(const struct address_space *mapping) { return xa_empty(&mapping->i_pages); } @@ -158,7 +163,7 @@ static inline bool mapping_empty(struct address_space *mapping) * refcount and the referenced bit, which will be elevated or set in * the process of adding new cache pages to an inode. */ -static inline bool mapping_shrinkable(struct address_space *mapping) +static inline bool mapping_shrinkable(const struct address_space *mapping) { void *head; @@ -198,9 +203,24 @@ enum mapping_flags { AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, - AS_LARGE_FOLIO_SUPPORT = 6, + AS_RELEASE_ALWAYS = 6, /* Call ->release_folio(), even if no private data */ + AS_STABLE_WRITES = 7, /* must wait for writeback before modifying + folio contents */ + AS_INACCESSIBLE = 8, /* Do not attempt direct R/W access to the mapping */ + AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, + AS_KERNEL_FILE = 10, /* mapping for a fake kernel file that shouldn't + account usage to user cgroups */ + /* Bits 16-25 are used for FOLIO_ORDER */ + AS_FOLIO_ORDER_BITS = 5, + AS_FOLIO_ORDER_MIN = 16, + AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS, }; +#define AS_FOLIO_ORDER_BITS_MASK ((1u << AS_FOLIO_ORDER_BITS) - 1) +#define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MIN) +#define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MAX) +#define AS_FOLIO_ORDER_MASK (AS_FOLIO_ORDER_MIN_MASK | AS_FOLIO_ORDER_MAX_MASK) + /** * mapping_set_error - record a writeback error in the address_space * @mapping: the mapping in which an error should be set @@ -244,7 +264,7 @@ static inline void mapping_clear_unevictable(struct address_space *mapping) clear_bit(AS_UNEVICTABLE, &mapping->flags); } -static inline bool mapping_unevictable(struct address_space *mapping) +static inline bool mapping_unevictable(const struct address_space *mapping) { return mapping && test_bit(AS_UNEVICTABLE, &mapping->flags); } @@ -254,7 +274,7 @@ static inline void mapping_set_exiting(struct address_space *mapping) set_bit(AS_EXITING, &mapping->flags); } -static inline int mapping_exiting(struct address_space *mapping) +static inline int mapping_exiting(const struct address_space *mapping) { return test_bit(AS_EXITING, &mapping->flags); } @@ -264,18 +284,74 @@ static inline void mapping_set_no_writeback_tags(struct address_space *mapping) set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } -static inline int mapping_use_writeback_tags(struct address_space *mapping) +static inline int mapping_use_writeback_tags(const struct address_space *mapping) { return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } -static inline gfp_t mapping_gfp_mask(struct address_space * mapping) +static inline bool mapping_release_always(const struct address_space *mapping) +{ + return test_bit(AS_RELEASE_ALWAYS, &mapping->flags); +} + +static inline void mapping_set_release_always(struct address_space *mapping) +{ + set_bit(AS_RELEASE_ALWAYS, &mapping->flags); +} + +static inline void mapping_clear_release_always(struct address_space *mapping) +{ + clear_bit(AS_RELEASE_ALWAYS, &mapping->flags); +} + +static inline bool mapping_stable_writes(const struct address_space *mapping) +{ + return test_bit(AS_STABLE_WRITES, &mapping->flags); +} + +static inline void mapping_set_stable_writes(struct address_space *mapping) +{ + set_bit(AS_STABLE_WRITES, &mapping->flags); +} + +static inline void mapping_clear_stable_writes(struct address_space *mapping) +{ + clear_bit(AS_STABLE_WRITES, &mapping->flags); +} + +static inline void mapping_set_inaccessible(struct address_space *mapping) +{ + /* + * It's expected inaccessible mappings are also unevictable. Compaction + * migrate scanner (isolate_migratepages_block()) relies on this to + * reduce page locking. + */ + set_bit(AS_UNEVICTABLE, &mapping->flags); + set_bit(AS_INACCESSIBLE, &mapping->flags); +} + +static inline bool mapping_inaccessible(const struct address_space *mapping) +{ + return test_bit(AS_INACCESSIBLE, &mapping->flags); +} + +static inline void mapping_set_writeback_may_deadlock_on_reclaim(struct address_space *mapping) +{ + set_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); +} + +static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct address_space *mapping) +{ + return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); +} + +static inline gfp_t mapping_gfp_mask(const struct address_space *mapping) { return mapping->gfp_mask; } /* Restricts the given gfp_mask to what the mapping allows. */ -static inline gfp_t mapping_gfp_constraint(struct address_space *mapping, +static inline gfp_t mapping_gfp_constraint(const struct address_space *mapping, gfp_t gfp_mask) { return mapping_gfp_mask(mapping) & gfp_mask; @@ -290,9 +366,84 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) m->gfp_mask = mask; } +/* + * There are some parts of the kernel which assume that PMD entries + * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, + * limit the maximum allocation order to PMD size. I'm not aware of any + * assumptions about maximum order if THP are disabled, but 8 seems like + * a good order (that's 1MB if you're using 4kB pages) + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define PREFERRED_MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER +#else +#define PREFERRED_MAX_PAGECACHE_ORDER 8 +#endif + +/* + * xas_split_alloc() does not support arbitrary orders. This implies no + * 512MB THP on ARM64 with 64KB base page size. + */ +#define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1) +#define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER) + +/* + * mapping_max_folio_size_supported() - Check the max folio size supported + * + * The filesystem should call this function at mount time if there is a + * requirement on the folio mapping size in the page cache. + */ +static inline size_t mapping_max_folio_size_supported(void) +{ + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER); + return PAGE_SIZE; +} + +/* + * mapping_set_folio_order_range() - Set the orders supported by a file. + * @mapping: The address space of the file. + * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive). + * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive). + * + * The filesystem should call this function in its inode constructor to + * indicate which base size (min) and maximum size (max) of folio the VFS + * can use to cache the contents of the file. This should only be used + * if the filesystem needs special handling of folio sizes (ie there is + * something the core cannot know). + * Do not tune it based on, eg, i_size. + * + * Context: This should not be called while the inode is active as it + * is non-atomic. + */ +static inline void mapping_set_folio_order_range(struct address_space *mapping, + unsigned int min, + unsigned int max) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return; + + if (min > MAX_PAGECACHE_ORDER) + min = MAX_PAGECACHE_ORDER; + + if (max > MAX_PAGECACHE_ORDER) + max = MAX_PAGECACHE_ORDER; + + if (max < min) + max = min; + + mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) | + (min << AS_FOLIO_ORDER_MIN) | (max << AS_FOLIO_ORDER_MAX); +} + +static inline void mapping_set_folio_min_order(struct address_space *mapping, + unsigned int min) +{ + mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER); +} + /** * mapping_set_large_folios() - Indicate the file supports large folios. - * @mapping: The file. + * @mapping: The address space of the file. * * The filesystem should call this function in its inode constructor to * indicate that the VFS can use large folios to cache the contents of @@ -303,20 +454,72 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) */ static inline void mapping_set_large_folios(struct address_space *mapping) { - __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); + mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER); +} + +static inline unsigned int +mapping_max_folio_order(const struct address_space *mapping) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return 0; + return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX; +} + +static inline unsigned int +mapping_min_folio_order(const struct address_space *mapping) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return 0; + return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN; +} + +static inline unsigned long +mapping_min_folio_nrpages(const struct address_space *mapping) +{ + return 1UL << mapping_min_folio_order(mapping); +} + +static inline unsigned long +mapping_min_folio_nrbytes(const struct address_space *mapping) +{ + return mapping_min_folio_nrpages(mapping) << PAGE_SHIFT; +} + +/** + * mapping_align_index() - Align index for this mapping. + * @mapping: The address_space. + * @index: The page index. + * + * The index of a folio must be naturally aligned. If you are adding a + * new folio to the page cache and need to know what index to give it, + * call this function. + */ +static inline pgoff_t mapping_align_index(const struct address_space *mapping, + pgoff_t index) +{ + return round_down(index, mapping_min_folio_nrpages(mapping)); } /* * 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) +static inline bool mapping_large_folio_support(const struct address_space *mapping) +{ + /* AS_FOLIO_ORDER is only reasonable for pagecache folios */ + VM_WARN_ONCE((unsigned long)mapping & FOLIO_MAPPING_ANON, + "Anonymous mapping always supports large folio"); + + return mapping_max_folio_order(mapping) > 0; +} + +/* Return the maximum folio size for this pagecache mapping, in bytes. */ +static inline size_t mapping_max_folio_size(const struct address_space *mapping) { - return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && - test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); + return PAGE_SIZE << mapping_max_folio_order(mapping); } -static inline int filemap_nr_thps(struct address_space *mapping) +static inline int filemap_nr_thps(const struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS return atomic_read(&mapping->nr_thps); @@ -345,44 +548,25 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) #endif } -struct address_space *page_mapping(struct page *); -struct address_space *folio_mapping(struct folio *); -struct address_space *swapcache_mapping(struct folio *); +struct address_space *folio_mapping(const struct folio *folio); /** - * folio_file_mapping - Find the mapping this folio belongs to. + * folio_flush_mapping - Find the file mapping this folio belongs to. * @folio: The folio. * * For folios which are in the page cache, return the mapping that this - * page belongs to. Folios in the swap cache return the mapping of the - * swap file or swap device where the data is stored. This is different - * from the mapping returned by folio_mapping(). The only reason to - * use it is if, like NFS, you return 0 from ->activate_swapfile. + * page belongs to. Anonymous folios return NULL, even if they're in + * the swap cache. Other kinds of folio also return NULL. * - * Do not call this for folios which aren't in the page cache or swap cache. + * This is ONLY used by architecture cache flushing code. If you aren't + * writing cache flushing code, you want either folio_mapping() or + * folio_file_mapping(). */ -static inline struct address_space *folio_file_mapping(struct folio *folio) +static inline struct address_space *folio_flush_mapping(struct folio *folio) { if (unlikely(folio_test_swapcache(folio))) - return swapcache_mapping(folio); - - return folio->mapping; -} - -static inline struct address_space *page_file_mapping(struct page *page) -{ - return folio_file_mapping(page_folio(page)); -} - -/* - * For file cache pages, return the address_space, otherwise return NULL - */ -static inline struct address_space *page_mapping_file(struct page *page) -{ - struct folio *folio = page_folio(page); - - if (unlikely(folio_test_swapcache(folio))) return NULL; + return folio_mapping(folio); } @@ -467,22 +651,22 @@ static inline void *detach_page_private(struct page *page) } #ifdef CONFIG_NUMA -struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order); +struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *policy); #else -static inline struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) +static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *policy) { - return folio_alloc(gfp, order); + return folio_alloc_noprof(gfp, order); } #endif -static inline struct page *__page_cache_alloc(gfp_t gfp) -{ - return &filemap_alloc_folio(gfp, 0)->page; -} +#define filemap_alloc_folio(...) \ + alloc_hooks(filemap_alloc_folio_noprof(__VA_ARGS__)) -static inline struct page *page_cache_alloc(struct address_space *x) +static inline struct page *__page_cache_alloc(gfp_t gfp) { - return __page_cache_alloc(mapping_gfp_mask(x)); + return &filemap_alloc_folio(gfp, 0, NULL)->page; } static inline gfp_t readahead_gfp_mask(struct address_space *x) @@ -497,20 +681,114 @@ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); -#define FGP_ACCESSED 0x00000001 -#define FGP_LOCK 0x00000002 -#define FGP_CREAT 0x00000004 -#define FGP_WRITE 0x00000008 -#define FGP_NOFS 0x00000010 -#define FGP_NOWAIT 0x00000020 -#define FGP_FOR_MMAP 0x00000040 -#define FGP_ENTRY 0x00000080 -#define FGP_STABLE 0x00000100 - -struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, - int fgp_flags, gfp_t gfp); +/** + * typedef fgf_t - Flags for getting folios from the page cache. + * + * Most users of the page cache will not need to use these flags; + * there are convenience functions such as filemap_get_folio() and + * filemap_lock_folio(). For users which need more control over exactly + * what is done with the folios, these flags to __filemap_get_folio() + * are available. + * + * * %FGP_ACCESSED - The folio will be marked accessed. + * * %FGP_LOCK - The folio is returned locked. + * * %FGP_CREAT - If no folio is present then a new folio is allocated, + * added to the page cache and the VM's LRU list. The folio is + * returned locked. + * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the + * folio is already in cache. If the folio was allocated, unlock it + * before returning so the caller can do the same dance. + * * %FGP_WRITE - The folio will be written to by the caller. + * * %FGP_NOFS - __GFP_FS will get cleared in gfp. + * * %FGP_NOWAIT - Don't block on the folio lock. + * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) + * * %FGP_DONTCACHE - Uncached buffered IO + * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin() + * implementation. + */ +typedef unsigned int __bitwise fgf_t; + +#define FGP_ACCESSED ((__force fgf_t)0x00000001) +#define FGP_LOCK ((__force fgf_t)0x00000002) +#define FGP_CREAT ((__force fgf_t)0x00000004) +#define FGP_WRITE ((__force fgf_t)0x00000008) +#define FGP_NOFS ((__force fgf_t)0x00000010) +#define FGP_NOWAIT ((__force fgf_t)0x00000020) +#define FGP_FOR_MMAP ((__force fgf_t)0x00000040) +#define FGP_STABLE ((__force fgf_t)0x00000080) +#define FGP_DONTCACHE ((__force fgf_t)0x00000100) +#define FGF_GET_ORDER(fgf) (((__force unsigned)fgf) >> 26) /* top 6 bits */ + +#define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) + +static inline unsigned int filemap_get_order(size_t size) +{ + unsigned int shift = ilog2(size); + + if (shift <= PAGE_SHIFT) + return 0; + + return shift - PAGE_SHIFT; +} + +/** + * fgf_set_order - Encode a length in the fgf_t flags. + * @size: The suggested size of the folio to create. + * + * The caller of __filemap_get_folio() can use this to suggest a preferred + * size for the folio that is created. If there is already a folio at + * the index, it will be returned, no matter what its size. If a folio + * is freshly created, it may be of a different size than requested + * due to alignment constraints, memory pressure, or the presence of + * other folios at nearby indices. + */ +static inline fgf_t fgf_set_order(size_t size) +{ + unsigned int order = filemap_get_order(size); + + if (!order) + return 0; + return (__force fgf_t)(order << 26); +} + +void *filemap_get_entry(struct address_space *mapping, pgoff_t index); +struct folio *__filemap_get_folio_mpol(struct address_space *mapping, + pgoff_t index, fgf_t fgf_flags, gfp_t gfp, struct mempolicy *policy); struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, - int fgp_flags, gfp_t gfp); + fgf_t fgp_flags, gfp_t gfp); + +static inline struct folio *__filemap_get_folio(struct address_space *mapping, + pgoff_t index, fgf_t fgf_flags, gfp_t gfp) +{ + return __filemap_get_folio_mpol(mapping, index, fgf_flags, gfp, NULL); +} + +/** + * write_begin_get_folio - Get folio for write_begin with flags. + * @iocb: The kiocb passed from write_begin (may be NULL). + * @mapping: The address space to search. + * @index: The page cache index. + * @len: Length of data being written. + * + * This is a helper for filesystem write_begin() implementations. + * It wraps __filemap_get_folio(), setting appropriate flags in + * the write begin context. + * + * Return: A folio or an ERR_PTR. + */ +static inline struct folio *write_begin_get_folio(const struct kiocb *iocb, + struct address_space *mapping, pgoff_t index, size_t len) +{ + fgf_t fgp_flags = FGP_WRITEBEGIN; + + fgp_flags |= fgf_set_order(len); + + if (iocb && iocb->ki_flags & IOCB_DONTCACHE) + fgp_flags |= FGP_DONTCACHE; + + return __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); +} /** * filemap_get_folio - Find and get a folio. @@ -520,7 +798,8 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned with an increased refcount. * - * Otherwise, %NULL is returned. + * Return: A folio or ERR_PTR(-ENOENT) 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_get_folio(struct address_space *mapping, pgoff_t index) @@ -537,8 +816,8 @@ static inline struct folio *filemap_get_folio(struct address_space *mapping, * 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. + * Return: A folio or ERR_PTR(-ENOENT) 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) @@ -547,6 +826,26 @@ static inline struct folio *filemap_lock_folio(struct address_space *mapping, } /** + * filemap_grab_folio - grab a folio from the page cache + * @mapping: The address space to search + * @index: The page index + * + * Looks up the page cache entry at @mapping & @index. If no folio is found, + * a new folio is created. The folio is locked, marked as accessed, and + * returned. + * + * Return: A found or created folio. ERR_PTR(-ENOMEM) if no folio is found + * and failed to create a folio. + */ +static inline struct folio *filemap_grab_folio(struct address_space *mapping, + pgoff_t index) +{ + return __filemap_get_folio(mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + mapping_gfp_mask(mapping)); +} + +/** * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index @@ -563,7 +862,7 @@ static inline struct page *find_get_page(struct address_space *mapping, } static inline struct page *find_get_page_flags(struct address_space *mapping, - pgoff_t offset, int fgp_flags) + pgoff_t offset, fgf_t fgp_flags) { return pagecache_get_page(mapping, offset, fgp_flags, 0); } @@ -619,7 +918,8 @@ static inline struct page *find_or_create_page(struct address_space *mapping, * @mapping: target address_space * @index: the page index * - * Same as grab_cache_page(), but do not wait if the page is unavailable. + * Returns locked page at given index in given cache, creating it if + * needed, but do not wait if the page is locked or to reclaim memory. * This is intended for speculative data generators, where the data can * be regenerated if the page couldn't be grabbed. This routine should * be safe to call while holding the lock for another page. @@ -635,35 +935,26 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, mapping_gfp_mask(mapping)); } -#define swapcache_index(folio) __page_file_index(&(folio)->page) - /** - * folio_index - File index of a folio. - * @folio: The folio. - * - * For a folio which is either in the page cache or the swap cache, - * return its index within the address_space it belongs to. If you know - * the page is definitely in the page cache, you can look at the folio's - * index directly. + * folio_next_index - Get the index of the next folio. + * @folio: The current folio. * - * Return: The index (offset in units of pages) of a folio in its file. + * Return: The index of the folio which follows this folio in the file. */ -static inline pgoff_t folio_index(struct folio *folio) +static inline pgoff_t folio_next_index(const struct folio *folio) { - if (unlikely(folio_test_swapcache(folio))) - return swapcache_index(folio); - return folio->index; + return folio->index + folio_nr_pages(folio); } /** - * folio_next_index - Get the index of the next folio. + * folio_next_pos - Get the file position of the next folio. * @folio: The current folio. * - * Return: The index of the folio which follows this folio in the file. + * Return: The position of the folio which follows this folio in the file. */ -static inline pgoff_t folio_next_index(struct folio *folio) +static inline loff_t folio_next_pos(const struct folio *folio) { - return folio->index + folio_nr_pages(folio); + return (loff_t)folio_next_index(folio) << PAGE_SHIFT; } /** @@ -678,9 +969,6 @@ static inline pgoff_t folio_next_index(struct folio *folio) */ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) { - /* HugeTLBfs indexes the page cache in units of hpage_size */ - if (folio_test_hugetlb(folio)) - return &folio->page; return folio_page(folio, index & (folio_nr_pages(folio) - 1)); } @@ -689,61 +977,29 @@ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) * @folio: The folio. * @index: The page index within the file. * - * Context: The caller should have the page locked in order to prevent - * (eg) shmem from moving the page between the page cache and swap cache - * and changing its index in the middle of the operation. + * Context: The caller should have the folio locked and ensure + * e.g., shmem did not move this folio to the swap cache. * Return: true or false. */ -static inline bool folio_contains(struct folio *folio, pgoff_t index) +static inline bool folio_contains(const struct folio *folio, pgoff_t index) { - /* HugeTLBfs indexes the page cache in units of hpage_size */ - if (folio_test_hugetlb(folio)) - return folio->index == index; - return index - folio_index(folio) < folio_nr_pages(folio); -} - -/* - * Given the page we found in the page cache, return the page corresponding - * to this index in the file - */ -static inline struct page *find_subpage(struct page *head, pgoff_t index) -{ - /* HugeTLBfs wants the head page regardless */ - if (PageHuge(head)) - return head; - - return head + (index & (thp_nr_pages(head) - 1)); + VM_WARN_ON_ONCE_FOLIO(folio_test_swapcache(folio), folio); + return index - folio->index < folio_nr_pages(folio); } 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); -static inline unsigned find_get_pages_tag(struct address_space *mapping, - pgoff_t *index, xa_mark_t tag, unsigned int nr_pages, - struct page **pages) -{ - return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag, - nr_pages, pages); -} - -struct page *grab_cache_page_write_begin(struct address_space *mapping, - pgoff_t index); - -/* - * Returns locked page at given index in given cache, creating it if needed. - */ -static inline struct page *grab_cache_page(struct address_space *mapping, - pgoff_t index) -{ - return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); -} +unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, + pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch); +unsigned filemap_get_folios_dirty(struct address_space *mapping, + pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); struct folio *read_cache_folio(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); +struct folio *mapping_read_folio_gfp(struct address_space *, pgoff_t index, + gfp_t flags); 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, @@ -761,36 +1017,34 @@ static inline struct folio *read_mapping_folio(struct address_space *mapping, return read_cache_folio(mapping, index, NULL, file); } -/* - * Get index of the page within radix-tree (but not for hugetlb pages). - * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) +/** + * page_pgoff - Calculate the logical page offset of this page. + * @folio: The folio containing this page. + * @page: The page which we need the offset of. + * + * For file pages, this is the offset from the beginning of the file + * in units of PAGE_SIZE. For anonymous pages, this is the offset from + * the beginning of the anon_vma in units of PAGE_SIZE. This will + * return nonsense for KSM pages. + * + * Context: Caller must have a reference on the folio or otherwise + * prevent it from being split or freed. + * + * Return: The offset in units of PAGE_SIZE. */ -static inline pgoff_t page_to_index(struct page *page) +static inline pgoff_t page_pgoff(const struct folio *folio, + const struct page *page) { - struct page *head; - - if (likely(!PageTransTail(page))) - return page->index; - - head = compound_head(page); - /* - * We don't initialize ->index for tail pages: calculate based on - * head page - */ - return head->index + page - head; + return folio->index + folio_page_idx(folio, page); } -extern pgoff_t hugetlb_basepage_index(struct page *page); - -/* - * Get the offset in PAGE_SIZE (even for hugetlb pages). - * (TODO: hugetlb pages should have ->index in PAGE_SIZE) +/** + * folio_pos - Returns the byte position of this folio in its file. + * @folio: The folio. */ -static inline pgoff_t page_to_pgoff(struct page *page) +static inline loff_t folio_pos(const struct folio *folio) { - if (unlikely(PageHuge(page))) - return hugetlb_basepage_index(page); - return page_to_index(page); + return ((loff_t)folio->index) * PAGE_SIZE; } /* @@ -798,55 +1052,23 @@ static inline pgoff_t page_to_pgoff(struct page *page) */ static inline loff_t page_offset(struct page *page) { - return ((loff_t)page->index) << PAGE_SHIFT; -} - -static inline loff_t page_file_offset(struct page *page) -{ - return ((loff_t)page_index(page)) << PAGE_SHIFT; -} - -/** - * folio_pos - Returns the byte position of this folio in its file. - * @folio: The folio. - */ -static inline loff_t folio_pos(struct folio *folio) -{ - return page_offset(&folio->page); -} + struct folio *folio = page_folio(page); -/** - * folio_file_pos - Returns the byte position of this folio in its file. - * @folio: The folio. - * - * This differs from folio_pos() for folios which belong to a swap file. - * NFS is the only filesystem today which needs to use folio_file_pos(). - */ -static inline loff_t folio_file_pos(struct folio *folio) -{ - return page_file_offset(&folio->page); + return folio_pos(folio) + folio_page_idx(folio, page) * PAGE_SIZE; } /* * 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) +static inline pgoff_t folio_pgoff(const 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); - -static inline pgoff_t linear_page_index(struct vm_area_struct *vma, - unsigned long address) +static inline pgoff_t linear_page_index(const struct vm_area_struct *vma, + const unsigned long address) { pgoff_t pgoff; - if (unlikely(is_vm_hugetlb_page(vma))) - return linear_hugepage_index(vma, address); pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; return pgoff; @@ -879,8 +1101,7 @@ static inline bool wake_page_match(struct wait_page_queue *wait_page, void __folio_lock(struct folio *folio); int __folio_lock_killable(struct folio *folio); -bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, - unsigned int flags); +vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf); void unlock_page(struct page *page); void folio_unlock(struct folio *folio); @@ -904,7 +1125,7 @@ static inline bool folio_trylock(struct folio *folio) /* * Return true if the page was successfully locked */ -static inline int trylock_page(struct page *page) +static inline bool trylock_page(struct page *page) { return folio_trylock(page_folio(page)); } @@ -978,27 +1199,19 @@ static inline int folio_lock_killable(struct folio *folio) } /* - * lock_page_killable is like lock_page but can be interrupted by fatal - * signals. It returns 0 if it locked the page and -EINTR if it was - * killed while waiting. - */ -static inline int lock_page_killable(struct page *page) -{ - return folio_lock_killable(page_folio(page)); -} - -/* * 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 folio_lock_or_retry(struct folio *folio, - struct mm_struct *mm, unsigned int flags) +static inline vm_fault_t folio_lock_or_retry(struct folio *folio, + struct vm_fault *vmf) { might_sleep(); - return folio_trylock(folio) || __folio_lock_or_retry(folio, mm, flags); + if (!folio_trylock(folio)) + return __folio_lock_or_retry(folio, vmf); + return 0; } /* @@ -1028,29 +1241,16 @@ static inline int folio_wait_locked_killable(struct folio *folio) return folio_wait_bit_killable(folio, PG_locked); } -static inline void wait_on_page_locked(struct page *page) -{ - folio_wait_locked(page_folio(page)); -} - -static inline int wait_on_page_locked_killable(struct page *page) -{ - return folio_wait_locked_killable(page_folio(page)); -} - +void folio_end_read(struct folio *folio, bool success); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); void end_page_writeback(struct page *page); void folio_end_writeback(struct folio *folio); -void wait_for_stable_page(struct page *page); +void folio_end_writeback_no_dropbehind(struct folio *folio); +void folio_end_dropbehind(struct folio *folio); void folio_wait_stable(struct folio *folio); void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn); -static inline void __set_page_dirty(struct page *page, - struct address_space *mapping, int warn) -{ - __folio_mark_dirty(page_folio(page), mapping, warn); -} 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) @@ -1062,13 +1262,6 @@ static inline void folio_cancel_dirty(struct folio *folio) 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) -{ - return folio_write_one(page_folio(page)); -} - -int __set_page_dirty_nobuffers(struct page *page); bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_MIGRATION @@ -1077,18 +1270,11 @@ int filemap_migrate_folio(struct address_space *mapping, struct folio *dst, #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); void folio_wait_private_2(struct folio *folio); int folio_wait_private_2_killable(struct folio *folio); /* - * Add an arbitrary waiter to a page's wait queue - */ -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); @@ -1146,9 +1332,9 @@ static inline bool filemap_range_needs_writeback(struct address_space *mapping, * struct readahead_control - Describes a readahead request. * * A readahead request is for consecutive pages. Filesystems which - * implement the ->readahead method should call readahead_page() or - * readahead_page_batch() in a loop and attempt to start I/O against - * each page in the request. + * implement the ->readahead method should call readahead_folio() or + * __readahead_batch() in a loop and attempt to start reads into each + * folio in the request. * * Most of the fields in this struct are private and should be accessed * by the functions below. @@ -1166,6 +1352,7 @@ struct readahead_control { pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; + bool dropbehind; bool _workingset; unsigned long _pflags; }; @@ -1215,8 +1402,7 @@ 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. - * @folio: The folio at @index which triggered the readahead call. - * @index: Index of first page to be read. + * @folio: The folio which triggered the readahead call. * @req_count: Total number of pages being read by the caller. * * page_cache_async_readahead() should be called when a page is used which @@ -1227,9 +1413,9 @@ 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 folio *folio, pgoff_t index, unsigned long req_count) + struct folio *folio, unsigned long req_count) { - DEFINE_READAHEAD(ractl, file, ra, mapping, index); + DEFINE_READAHEAD(ractl, file, ra, mapping, folio->index); page_cache_async_ra(&ractl, folio, req_count); } @@ -1254,22 +1440,6 @@ static inline struct folio *__readahead_folio(struct readahead_control *ractl) } /** - * readahead_page - Get the next page to read. - * @ractl: The current readahead request. - * - * Context: The page is locked and has an elevated refcount. The caller - * should decreases the refcount once the page has been submitted for I/O - * and unlock the page once all I/O to that page has completed. - * Return: A pointer to the next page, or %NULL if we are done. - */ -static inline struct page *readahead_page(struct readahead_control *ractl) -{ - struct folio *folio = __readahead_folio(ractl); - - return &folio->page; -} - -/** * readahead_folio - Get the next folio to read. * @ractl: The current readahead request. * @@ -1291,7 +1461,7 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, { unsigned int i = 0; XA_STATE(xas, &rac->mapping->i_pages, 0); - struct page *page; + struct folio *folio; BUG_ON(rac->_batch_count > rac->_nr_pages); rac->_nr_pages -= rac->_batch_count; @@ -1300,13 +1470,12 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, xas_set(&xas, rac->_index); rcu_read_lock(); - xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { - if (xas_retry(&xas, page)) + xas_for_each(&xas, folio, rac->_index + rac->_nr_pages - 1) { + if (xas_retry(&xas, folio)) continue; - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(PageTail(page), page); - array[i++] = page; - rac->_batch_count += thp_nr_pages(page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + array[i++] = folio_page(folio, 0); + rac->_batch_count += folio_nr_pages(folio); if (i == array_sz) break; } @@ -1316,24 +1485,10 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, } /** - * readahead_page_batch - Get a batch of pages to read. - * @rac: The current readahead request. - * @array: An array of pointers to struct page. - * - * Context: The pages are locked and have an elevated refcount. The caller - * should decreases the refcount once the page has been submitted for I/O - * and unlock the page once all I/O to that page has completed. - * Return: The number of pages placed in the array. 0 indicates the request - * is complete. - */ -#define readahead_page_batch(rac, array) \ - __readahead_batch(rac, array, ARRAY_SIZE(array)) - -/** * readahead_pos - The byte offset into the file of this readahead request. * @rac: The readahead request. */ -static inline loff_t readahead_pos(struct readahead_control *rac) +static inline loff_t readahead_pos(const struct readahead_control *rac) { return (loff_t)rac->_index * PAGE_SIZE; } @@ -1342,7 +1497,7 @@ static inline loff_t readahead_pos(struct readahead_control *rac) * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */ -static inline size_t readahead_length(struct readahead_control *rac) +static inline size_t readahead_length(const struct readahead_control *rac) { return rac->_nr_pages * PAGE_SIZE; } @@ -1351,7 +1506,7 @@ static inline size_t readahead_length(struct readahead_control *rac) * readahead_index - The index of the first page in this readahead request. * @rac: The readahead request. */ -static inline pgoff_t readahead_index(struct readahead_control *rac) +static inline pgoff_t readahead_index(const struct readahead_control *rac) { return rac->_index; } @@ -1360,7 +1515,7 @@ static inline pgoff_t readahead_index(struct readahead_control *rac) * readahead_count - The number of pages in this readahead request. * @rac: The readahead request. */ -static inline unsigned int readahead_count(struct readahead_control *rac) +static inline unsigned int readahead_count(const struct readahead_control *rac) { return rac->_nr_pages; } @@ -1369,12 +1524,12 @@ static inline unsigned int readahead_count(struct readahead_control *rac) * readahead_batch_length - The number of bytes in the current batch. * @rac: The readahead request. */ -static inline size_t readahead_batch_length(struct readahead_control *rac) +static inline size_t readahead_batch_length(const struct readahead_control *rac) { return rac->_batch_count * PAGE_SIZE; } -static inline unsigned long dir_pages(struct inode *inode) +static inline unsigned long dir_pages(const struct inode *inode) { return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; @@ -1388,8 +1543,8 @@ static inline unsigned long dir_pages(struct inode *inode) * Return: the number of bytes in the folio up to EOF, * or -EFAULT if the folio was truncated. */ -static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio, - struct inode *inode) +static inline ssize_t folio_mkwrite_check_truncate(const struct folio *folio, + const struct inode *inode) { loff_t size = i_size_read(inode); pgoff_t index = size >> PAGE_SHIFT; @@ -1409,34 +1564,6 @@ static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio, } /** - * page_mkwrite_check_truncate - check if page was truncated - * @page: the page to check - * @inode: the inode to check the page against - * - * Returns the number of bytes in the page up to EOF, - * or -EFAULT if the page was truncated. - */ -static inline int page_mkwrite_check_truncate(struct page *page, - struct inode *inode) -{ - loff_t size = i_size_read(inode); - pgoff_t index = size >> PAGE_SHIFT; - int offset = offset_in_page(size); - - if (page->mapping != inode->i_mapping) - return -EFAULT; - - /* page is wholly inside EOF */ - if (page->index < index) - return PAGE_SIZE; - /* page is wholly past EOF */ - if (page->index > index || !offset) - return -EFAULT; - /* page is partially inside EOF */ - return offset; -} - -/** * i_blocks_per_folio - How many blocks fit in this folio. * @inode: The inode which contains the blocks. * @folio: The folio. @@ -1448,14 +1575,9 @@ static inline int page_mkwrite_check_truncate(struct page *page, * Return: The number of filesystem blocks covered by this folio. */ static inline -unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio) +unsigned int i_blocks_per_folio(const struct inode *inode, + const struct folio *folio) { return folio_size(folio) >> inode->i_blkbits; } - -static inline -unsigned int i_blocks_per_page(struct inode *inode, struct page *page) -{ - return i_blocks_per_folio(inode, page_folio(page)); -} #endif /* _LINUX_PAGEMAP_H */ |