Something went wrong. Try again.
(I'm so sorry!) Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux
Something went wrong. Try again.
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685/* SPDX-License-Identifier: GPL-2.0 */#ifndef _LINUX_PAGEMAP_H#define _LINUX_PAGEMAP_H
/* * Copyright 1995 Linus Torvalds */#include <linux/mm.h>#include <linux/fs.h>#include <linux/list.h>#include <linux/highmem.h>#include <linux/compiler.h>#include <linux/uaccess.h>#include <linux/gfp.h>#include <linux/bitops.h>#include <linux/hardirq.h> /* for in_interrupt() */
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 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){ 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 filemap_check_errors(struct address_space *mapping);void __filemap_set_wb_err(struct address_space *mapping, int err);int kiocb_write_and_wait(struct kiocb *iocb, size_t count);
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(const struct address_space *mapping){ return xa_empty(&mapping->i_pages);}
/* * mapping_shrinkable - test if page cache state allows inode reclaim * @mapping: the page cache mapping * * This checks the mapping's cache state for the pupose of inode * reclaim and LRU management. * * The caller is expected to hold the i_lock, but is not required to * hold the i_pages lock, which usually protects cache state. That's * because the i_lock and the list_lru lock that protect the inode and * its LRU state don't nest inside the irq-safe i_pages lock. * * Cache deletions are performed under the i_lock, which ensures that * when an inode goes empty, it will reliably get queued on the LRU. * * Cache additions do not acquire the i_lock and may race with this * check, in which case we'll report the inode as shrinkable when it * has cache pages. This is okay: the shrinker also checks the * 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(const struct address_space *mapping){ void *head;
/* * On highmem systems, there could be lowmem pressure from the * inodes before there is highmem pressure from the page * cache. Make inodes shrinkable regardless of cache state. */ if (IS_ENABLED(CONFIG_HIGHMEM)) return true;
/* Cache completely empty? Shrink away. */ head = rcu_access_pointer(mapping->i_pages.xa_head); if (!head) return true;
/* * The xarray stores single offset-0 entries directly in the * head pointer, which allows non-resident page cache entries * to escape the shadow shrinker's list of xarray nodes. The * inode shrinker needs to pick them up under memory pressure. */ if (!xa_is_node(head) && xa_is_value(head)) return true;
return false;}
/* * Bits in mapping->flags. */enum mapping_flags { AS_EIO = 0, /* IO error on async write */ AS_ENOSPC = 1, /* ENOSPC on async write */ AS_MM_ALL_LOCKS = 2, /* under mm_take_all_locks() */ AS_UNEVICTABLE = 3, /* e.g., ramdisk, SHM_LOCK */ AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, 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 * @error: the error to set in the 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 * mapping_set_error to record the error in the mapping so that it can be * reported when the application calls fsync(2). */static inline void mapping_set_error(struct address_space *mapping, int error){ if (likely(!error)) return;
/* Record in wb_err for checkers using errseq_t based tracking */ __filemap_set_wb_err(mapping, error);
/* Record it in superblock */ if (mapping->host) errseq_set(&mapping->host->i_sb->s_wb_err, error);
/* Record it in flags for now, for legacy callers */ if (error == -ENOSPC) set_bit(AS_ENOSPC, &mapping->flags); else set_bit(AS_EIO, &mapping->flags);}
static inline void mapping_set_unevictable(struct address_space *mapping){ set_bit(AS_UNEVICTABLE, &mapping->flags);}
static inline void mapping_clear_unevictable(struct address_space *mapping){ clear_bit(AS_UNEVICTABLE, &mapping->flags);}
static inline bool mapping_unevictable(const struct address_space *mapping){ return mapping && test_bit(AS_UNEVICTABLE, &mapping->flags);}
static inline void mapping_set_exiting(struct address_space *mapping){ set_bit(AS_EXITING, &mapping->flags);}
static inline int mapping_exiting(const struct address_space *mapping){ return test_bit(AS_EXITING, &mapping->flags);}
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(const struct address_space *mapping){ return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);}
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(const struct address_space *mapping, gfp_t gfp_mask){ return mapping_gfp_mask(mapping) & gfp_mask;}
/* * This is non-atomic. Only to be used before the mapping is activated. * Probably needs a barrier... */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 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 * the file. * * Context: This should not be called while the inode is active as it * is non-atomic. */static inline void mapping_set_large_folios(struct address_space *mapping){ mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER);}
static inline unsigned intmapping_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 intmapping_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 longmapping_min_folio_nrpages(const struct address_space *mapping){ return 1UL << mapping_min_folio_order(mapping);}
static inline unsigned longmapping_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(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;}
/** * mapping_pmd_folio_support() - Check if a mapping supports PMD-sized folio * @mapping: The address_space * * While some mappings support large folios, they might not support PMD-sized * folios. This function checks whether a mapping supports PMD-sized folios. * For example, khugepaged needs this information before attempting to * collapsing THPs. * * Return: True if PMD-sized folios are supported, otherwise false. */#ifdef CONFIG_TRANSPARENT_HUGEPAGEstatic inline bool mapping_pmd_folio_support(const struct address_space *mapping){ /* AS_FOLIO_ORDER is only reasonable for pagecache folios */ VM_WARN_ON_ONCE((unsigned long)mapping & FOLIO_MAPPING_ANON);
return mapping_min_folio_order(mapping) <= PMD_ORDER && mapping_max_folio_order(mapping) >= PMD_ORDER;}#elsestatic inline bool mapping_pmd_folio_support(const struct address_space *mapping){ return false;}#endif
/* 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 PAGE_SIZE << mapping_max_folio_order(mapping);}
struct address_space *folio_mapping(const struct folio *folio);
/** * 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. Anonymous folios return NULL, even if they're in * the swap cache. Other kinds of folio also return NULL. * * 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_flush_mapping(struct folio *folio){ if (unlikely(folio_test_swapcache(folio))) return NULL;
return folio_mapping(folio);}
/** * folio_inode - Get the host inode for this folio. * @folio: The folio. * * For folios which are in the page cache, return the inode that this folio * belongs to. * * Do not call this for folios which aren't in the page cache. */static inline struct inode *folio_inode(struct folio *folio){ return folio->mapping->host;}
/** * folio_attach_private - Attach private data to a folio. * @folio: Folio to attach data to. * @data: Data to attach to folio. * * Attaching private data to a folio increments the page's reference count. * The data must be detached before the folio will be freed. */static inline void folio_attach_private(struct folio *folio, void *data){ folio_get(folio); folio->private = data;}
/** * folio_change_private - Change private data on a folio. * @folio: Folio to change the data on. * @data: Data to set on the folio. * * Change the private data attached to a folio and return the old * data. The page must previously have had data attached and the data * must be detached before the folio will be freed. * * Return: Data that was previously attached to the folio. */static inline void *folio_change_private(struct folio *folio, void *data){ void *old = folio_get_private(folio);
folio->private = data; return old;}
/** * folio_detach_private - Detach private data from a folio. * @folio: Folio to detach data from. * * Removes the data that was previously attached to the folio and decrements * the refcount on the page. * * Return: Data that was attached to the folio. */static inline void *folio_detach_private(struct folio *folio){ void *data = folio_get_private(folio);
if (!data) return NULL; folio->private = NULL; folio_put(folio);
return data;}
static inline void attach_page_private(struct page *page, void *data){ folio_attach_private(page_folio(page), data);}
static inline void *detach_page_private(struct page *page){ return folio_detach_private(page_folio(page));}
#ifdef CONFIG_NUMAstruct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order, struct mempolicy *policy);#elsestatic inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order, struct mempolicy *policy){ return folio_alloc_noprof(gfp, order);}#endif
#define filemap_alloc_folio(...) \ alloc_hooks(filemap_alloc_folio_noprof(__VA_ARGS__))
static inline struct page *__page_cache_alloc(gfp_t gfp){ return &filemap_alloc_folio(gfp, 0, NULL)->page;}
static inline gfp_t readahead_gfp_mask(struct address_space *x){ return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN;}
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);pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan);
/** * 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, 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. * @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 with an increased refcount. * * 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){ return __filemap_get_folio(mapping, index, 0, 0);}
/** * 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 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){ return __filemap_get_folio(mapping, index, FGP_LOCK, 0);}
/** * 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 * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned with an increased refcount. * * Otherwise, %NULL is returned. */static inline struct page *find_get_page(struct address_space *mapping, pgoff_t offset){ return pagecache_get_page(mapping, offset, 0, 0);}
static inline struct page *find_get_page_flags(struct address_space *mapping, pgoff_t offset, fgf_t fgp_flags){ return pagecache_get_page(mapping, offset, fgp_flags, 0);}
/** * find_lock_page - locate, pin and lock a pagecache page * @mapping: the address_space to search * @index: the page index * * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, it is returned locked and with an increased * refcount. * * Context: May sleep. * Return: A struct page or %NULL if there is no page in the cache for this * index. */static inline struct page *find_lock_page(struct address_space *mapping, pgoff_t index){ return pagecache_get_page(mapping, index, FGP_LOCK, 0);}
/** * find_or_create_page - locate or add a pagecache page * @mapping: the page's address_space * @index: the page's index into the mapping * @gfp_mask: page allocation mode * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned locked and with an increased * refcount. * * If the page is not present, a new page is allocated using @gfp_mask * and added to the page cache and the VM's LRU list. The page is * returned locked and with an increased refcount. * * On memory exhaustion, %NULL is returned. * * find_or_create_page() may sleep, even if @gfp_flags specifies an * atomic allocation! */static inline struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask){ return pagecache_get_page(mapping, index, FGP_LOCK|FGP_ACCESSED|FGP_CREAT, gfp_mask);}
/** * grab_cache_page_nowait - returns locked page at given index in given cache * @mapping: target address_space * @index: the page index * * 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. * * Clear __GFP_FS when allocating the page to avoid recursion into the fs * and deadlock against the caller's locked page. */static inline struct page *grab_cache_page_nowait(struct address_space *mapping, pgoff_t index){ return pagecache_get_page(mapping, index, FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, mapping_gfp_mask(mapping));}
/** * folio_next_index - Get the index of the next folio. * @folio: The current folio. * * Return: The index of the folio which follows this folio in the file. */static inline pgoff_t folio_next_index(const struct folio *folio){ return folio->index + folio_nr_pages(folio);}
/** * folio_next_pos - Get the file position of the next folio. * @folio: The current folio. * * Return: The position of the folio which follows this folio in the file. */static inline loff_t folio_next_pos(const struct folio *folio){ return (loff_t)folio_next_index(folio) << PAGE_SHIFT;}
/** * folio_file_page - The page for a particular index. * @folio: The folio which contains this index. * @index: The index we want to look up. * * Sometimes after looking up a folio in the page cache, we need to * obtain the specific page for an index (eg a page fault). * * Return: The page containing the file data for this index. */static inline struct page *folio_file_page(struct folio *folio, pgoff_t index){ return folio_page(folio, index & (folio_nr_pages(folio) - 1));}
/** * folio_contains - Does this folio contain this index? * @folio: The folio. * @index: The page index within the file. * * 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(const struct folio *folio, pgoff_t index){ 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 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, pgoff_t index, gfp_t gfp_mask);
static inline struct page *read_mapping_page(struct address_space *mapping, 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_folio(mapping, index, NULL, file);}
/** * 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_pgoff(const struct folio *folio, const struct page *page){ return folio->index + folio_page_idx(folio, page);}
/** * folio_pos - Returns the byte position of this folio in its file. * @folio: The folio. */static inline loff_t folio_pos(const struct folio *folio){ return ((loff_t)folio->index) * PAGE_SIZE;}
/* * Return byte-offset into filesystem object for page. */static inline loff_t page_offset(struct page *page){ struct folio *folio = page_folio(page);
return folio_pos(folio) + folio_page_idx(folio, page) * PAGE_SIZE;}
/* * Get the offset in PAGE_SIZE (even for hugetlb folios). */static inline pgoff_t folio_pgoff(const struct folio *folio){ return folio->index;}
/** * linear_page_delta() - Determine the relative page offset of @address within * @vma. * @vma: The VMA in which @address resides. * @address: The address whose relative page offset is required. * * The result is identical for both file-backed and anonymous mappings and * simply determines how many pages @address lies from @vma->vm_start. * * Returns: The number of pages @address is offset by within @vma. */static inline pgoff_t linear_page_delta(const struct vm_area_struct *vma, const unsigned long address){ return (address - vma->vm_start) >> PAGE_SHIFT;}
/** * linear_page_index() - Determine the absolute page offset of @address within * @vma. * @vma: The VMA in which @address resides. * @address: The address whose absolute page offset is required. * * See the comment for vma_start_pgoff() for a description of what the page * offset signifies. * * Returns: The absolute page offset of @address within @vma. */static inline pgoff_t linear_page_index(const struct vm_area_struct *vma, const unsigned long address){ return linear_page_delta(vma, address) + vma_start_pgoff(vma);}
static inline pgoff_t __linear_anon_page_index(const struct vm_area_struct *vma, const unsigned long address){ return linear_page_delta(vma, address) + vma_start_anon_pgoff(vma);}
/** * linear_anon_page_index() - Determine the absolute anonymous page offset of * @address within @vma. * @vma: An anonymous or MAP_PRIVATE file-backed VMA in which @address resides. * @address: The address whose absolute page offset is required. * * This returns the anonymous page offset of @address, which is the page offset * the address possessed at the time the VMA was first faulted. * * For anonymous mappings, this returns the same value as linear_page_index(). * * For MAP_PRIVATE file-backed mappings, this returns the anonymous page offset * of @address, which is the page offset the address possessed at the time the * VMA was first faulted. * * It is not valid to call this function for shared file-backed mappings. * * Returns: The absolute anonymous page offset of @address within @vma. */static inline pgoff_t linear_anon_page_index(const struct vm_area_struct *vma, const unsigned long address){ const pgoff_t pgoff = __linear_anon_page_index(vma, address);
VM_WARN_ON_ONCE(!vma_is_cow_mapping(vma)); if (vma_is_anonymous(vma)) VM_WARN_ON_ONCE(pgoff != linear_page_index(vma, address));
return pgoff;}
struct wait_page_key { struct folio *folio; int bit_nr; int page_match;};
struct wait_page_queue { struct folio *folio; int bit_nr; wait_queue_entry_t wait;};
static inline bool wake_page_match(struct wait_page_queue *wait_page, struct wait_page_key *key){ if (wait_page->folio != key->folio) return false; key->page_match = 1;
if (wait_page->bit_nr != key->bit_nr) return false;
return true;}
void __folio_lock(struct folio *folio);int __folio_lock_killable(struct folio *folio);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);
/** * 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)));}
/* * Return true if the page was successfully locked */static inline bool 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(); if (!folio_trylock(folio)) __folio_lock(folio);}
/** * 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){ struct folio *folio; might_sleep();
folio = page_folio(page); if (!folio_trylock(folio)) __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(); if (!folio_trylock(folio)) return __folio_lock_killable(folio); return 0;}
/* * 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 vm_fault_t folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf){ might_sleep(); if (!folio_trylock(folio)) return __folio_lock_or_retry(folio, vmf); return 0;}
/* * This is exported only for folio_wait_locked/folio_wait_writeback, etc., * and should not be used directly. */void folio_wait_bit(struct folio *folio, int bit_nr);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 folio reference count so that the folio won't * go away during the wait. */static inline void folio_wait_locked(struct folio *folio){ if (folio_test_locked(folio)) folio_wait_bit(folio, PG_locked);}
static inline int folio_wait_locked_killable(struct folio *folio){ if (!folio_test_locked(folio)) return 0; return folio_wait_bit_killable(folio, PG_locked);}
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 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);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){ /* Avoid atomic ops, locking, etc. when not actually needed. */ if (folio_test_dirty(folio)) __folio_cancel_dirty(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);bool noop_dirty_folio(struct address_space *mapping, struct folio *folio);
#ifdef CONFIG_MIGRATIONint filemap_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode);#else#define filemap_migrate_folio NULL#endifvoid folio_end_private_2(struct folio *folio);void folio_wait_private_2(struct folio *folio);int folio_wait_private_2_killable(struct folio *folio);
/* * 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_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);void filemap_remove_folio(struct folio *folio);void __filemap_remove_folio(struct folio *folio, void *shadow);void replace_page_cache_folio(struct folio *old, struct folio *new);void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch);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);
/* 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. * * A readahead request is for consecutive pages. Filesystems which * 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. * * @file: The file, used primarily by network filesystems for authentication. * May be NULL if invoked internally by the filesystem. * @mapping: Readahead this filesystem object. * @ra: File readahead state. May be NULL. */struct readahead_control { struct file *file; struct address_space *mapping; struct file_ra_state *ra;/* private: use the readahead_* accessors instead */ pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; bool dropbehind; bool _workingset; unsigned long _pflags; bool _forward;};
#define DEFINE_READAHEAD(ractl, f, r, m, i) \ struct readahead_control ractl = { \ .file = f, \ .mapping = m, \ .ra = r, \ ._index = i, \ }
#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE)
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 folio *, unsigned long req_count);void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len);
/** * page_cache_sync_readahead - generic file readahead * @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. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * * page_cache_sync_readahead() should be called when a cache miss happened: * it will submit the read. The readahead logic may decide to piggyback more * pages onto the read request if access patterns suggest it will improve * performance. */static inlinevoid page_cache_sync_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, pgoff_t index, unsigned long req_count){ DEFINE_READAHEAD(ractl, file, ra, mapping, index); page_cache_sync_ra(&ractl, req_count);}
/** * page_cache_async_readahead - file readahead for marked pages * @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 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 * is marked as PageReadahead; this is a marker to suggest that the application * has used up enough of the readahead window that we should start pulling in * more pages. */static inlinevoid page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, struct folio *folio, unsigned long req_count){ DEFINE_READAHEAD(ractl, file, ra, mapping, folio->index); page_cache_async_ra(&ractl, folio, req_count);}
/* * Adjust readahead_control to ensure next folio comes from * [_index, _index + _nr_pages) afterwards and reset _batch_count. */static inline void __readahead_advance(struct readahead_control *rac){ if (rac->_forward) rac->_index += rac->_batch_count;
rac->_nr_pages -= rac->_batch_count; rac->_batch_count = 0;}
static inline struct folio *__readahead_folio(struct readahead_control *ractl){ struct folio *folio;
BUG_ON(ractl->_batch_count > ractl->_nr_pages); __readahead_advance(ractl); ractl->_forward = true;
if (!ractl->_nr_pages) return NULL;
folio = xa_load(&ractl->mapping->i_pages, ractl->_index); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); ractl->_batch_count = folio_nr_pages(folio);
return folio;}
/** * readahead_folio - Get the next folio to read. * @ractl: The current readahead request. * * Context: The folio is locked. The caller should unlock the folio once * all I/O to that folio has completed. * Return: A pointer to the next folio, or %NULL if we are done. */static inline struct folio *readahead_folio(struct readahead_control *ractl){ struct folio *folio = __readahead_folio(ractl);
if (folio) folio_put(folio); return folio;}
/** * readahead_folio_last - Get the next folio to read, from the tail. * @ractl: The current readahead request. * * Like readahead_folio(), but walks the range back-to-front. The folio is * returned locked with its refcount dropped; the caller unlocks it once I/O * completes. Compound folios are returned once, at their head index. * * Context: The folio is locked. * Return: A pointer to the next folio, or %NULL when done. */static inline struct folio *readahead_folio_last(struct readahead_control *ractl){ struct folio *folio;
/* Drop the previously returned batch from the remaining range. */ __readahead_advance(ractl); ractl->_forward = false;
if (!ractl->_nr_pages) return NULL;
/* xa_load() follows sibling entries, so a tail index returns the head */ folio = xa_load(&ractl->mapping->i_pages, ractl->_index + ractl->_nr_pages - 1); VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio);
ractl->_batch_count = folio_nr_pages(folio);
folio_put(folio); return folio;}
static inline unsigned int __readahead_batch(struct readahead_control *rac, struct page **array, unsigned int array_sz){ unsigned int i = 0; XA_STATE(xas, &rac->mapping->i_pages, 0); struct folio *folio;
BUG_ON(rac->_batch_count > rac->_nr_pages); __readahead_advance(rac); rac->_forward = true;
xas_set(&xas, rac->_index); rcu_read_lock(); xas_for_each(&xas, folio, rac->_index + rac->_nr_pages - 1) { if (xas_retry(&xas, folio)) continue; 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; } rcu_read_unlock();
return i;}
/** * readahead_pos - The byte offset into the file of this readahead request. * @rac: The readahead request. */static inline loff_t readahead_pos(const struct readahead_control *rac){ return (loff_t)rac->_index * PAGE_SIZE;}
/** * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */static inline size_t readahead_length(const struct readahead_control *rac){ return rac->_nr_pages * PAGE_SIZE;}
/** * readahead_index - The index of the first page in this readahead request. * @rac: The readahead request. */static inline pgoff_t readahead_index(const struct readahead_control *rac){ return rac->_index;}
/** * readahead_count - The number of pages in this readahead request. * @rac: The readahead request. */static inline unsigned int readahead_count(const struct readahead_control *rac){ return rac->_nr_pages;}
/** * readahead_batch_length - The number of bytes in the current batch. * @rac: The readahead request. */static inline size_t readahead_batch_length(const struct readahead_control *rac){ return rac->_batch_count * PAGE_SIZE;}
static inline unsigned long dir_pages(const struct inode *inode){ return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT;}
/** * folio_mkwrite_check_truncate - check if folio was truncated * @folio: the folio to check * @inode: the inode to check the folio against * * 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(const struct folio *folio, const struct inode *inode){ loff_t size = i_size_read(inode); pgoff_t index = size >> PAGE_SHIFT; size_t offset = offset_in_folio(folio, size);
if (!folio->mapping) return -EFAULT;
/* folio is wholly inside EOF */ if (folio_next_index(folio) - 1 < index) return folio_size(folio); /* folio is wholly past EOF */ if (folio->index > index || !offset) return -EFAULT; /* folio 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. * * If the block size is larger than the size of this folio, return zero. * * Context: The caller should hold a refcount on the folio to prevent it * from being split. * Return: The number of filesystem blocks covered by this folio. */static inlineunsigned int i_blocks_per_folio(const struct inode *inode, const struct folio *folio){ return folio_size(folio) >> inode->i_blkbits;}#endif /* _LINUX_PAGEMAP_H */